diff options
| author | Maxime Ripard <maxime@cerno.tech> | 2022-10-18 15:00:03 +0200 |
|---|---|---|
| committer | Maxime Ripard <maxime@cerno.tech> | 2022-10-18 15:00:03 +0200 |
| commit | a140a6a2d5ec0329ad05cd3532a91ad0ce58dceb (patch) | |
| tree | b2d44a1da423c53bd6c3ab3facd45ff5f2087ffd /drivers/gpu/drm | |
| parent | 28743e25fa1c867675bd8ff976eb92d4251f13a1 (diff) | |
| parent | 9abf2313adc1ca1b6180c508c25f22f9395cc780 (diff) | |
| download | linux-stable-a140a6a2d5ec0329ad05cd3532a91ad0ce58dceb.tar.gz linux-stable-a140a6a2d5ec0329ad05cd3532a91ad0ce58dceb.tar.bz2 linux-stable-a140a6a2d5ec0329ad05cd3532a91ad0ce58dceb.zip | |
Merge drm/drm-next into drm-misc-next
Let's kick-off this release cycle.
Signed-off-by: Maxime Ripard <maxime@cerno.tech>
Diffstat (limited to 'drivers/gpu/drm')
593 files changed, 21856 insertions, 16314 deletions
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index 198ba846d34b..34f5a092c99e 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -51,6 +51,18 @@ config DRM_DEBUG_MM If in doubt, say "N". +config DRM_USE_DYNAMIC_DEBUG + bool "use dynamic debug to implement drm.debug" + default y + depends on DRM + depends on DYNAMIC_DEBUG || DYNAMIC_DEBUG_CORE + depends on JUMP_LABEL + help + Use dynamic-debug to avoid drm_debug_enabled() runtime overheads. + Due to callsite counts in DRM drivers (~4k in amdgpu) and 56 + bytes per callsite, the .data costs can be substantial, and + are therefore configurable. + config DRM_KUNIT_TEST tristate "KUnit tests for DRM" if !KUNIT_ALL_TESTS depends on DRM && KUNIT diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 6ad98d3ceff7..6e55c47288e4 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -3,6 +3,8 @@ # Makefile for the drm device driver. This driver provides support for the # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher. +CFLAGS-$(CONFIG_DRM_USE_DYNAMIC_DEBUG) += -DDYNAMIC_DEBUG_MODULE + drm-y := \ drm_aperture.o \ drm_atomic.o \ 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; } diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c index 0f0950c11196..78b72739e5c3 100644 --- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c +++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c @@ -1346,7 +1346,7 @@ uninit_regulators: return ret; } -static int adv7511_remove(struct i2c_client *i2c) +static void adv7511_remove(struct i2c_client *i2c) { struct adv7511 *adv7511 = i2c_get_clientdata(i2c); @@ -1362,8 +1362,6 @@ static int adv7511_remove(struct i2c_client *i2c) i2c_unregister_device(adv7511->i2c_packet); i2c_unregister_device(adv7511->i2c_edid); - - return 0; } static const struct i2c_device_id adv7511_i2c_ids[] = { diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c index ae3d6e9a606c..660a54857929 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx6345.c @@ -787,7 +787,7 @@ err_unregister_i2c: return err; } -static int anx6345_i2c_remove(struct i2c_client *client) +static void anx6345_i2c_remove(struct i2c_client *client) { struct anx6345 *anx6345 = i2c_get_clientdata(client); @@ -798,8 +798,6 @@ static int anx6345_i2c_remove(struct i2c_client *client) kfree(anx6345->edid); mutex_destroy(&anx6345->lock); - - return 0; } static const struct i2c_device_id anx6345_id[] = { diff --git a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c index d2fc8676fab6..5997049fde5b 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c +++ b/drivers/gpu/drm/bridge/analogix/analogix-anx78xx.c @@ -1357,7 +1357,7 @@ err_unregister_i2c: return err; } -static int anx78xx_i2c_remove(struct i2c_client *client) +static void anx78xx_i2c_remove(struct i2c_client *client) { struct anx78xx *anx78xx = i2c_get_clientdata(client); @@ -1366,8 +1366,6 @@ static int anx78xx_i2c_remove(struct i2c_client *client) unregister_i2c_dummy_clients(anx78xx); kfree(anx78xx->edid); - - return 0; } static const struct i2c_device_id anx78xx_id[] = { diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c index 8aadcc0aa90b..df9370e0ff23 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c @@ -1864,12 +1864,6 @@ EXPORT_SYMBOL_GPL(analogix_dp_remove); int analogix_dp_suspend(struct analogix_dp_device *dp) { clk_disable_unprepare(dp->clock); - - if (dp->plat_data->panel) { - if (drm_panel_unprepare(dp->plat_data->panel)) - DRM_ERROR("failed to turnoff the panel\n"); - } - return 0; } EXPORT_SYMBOL_GPL(analogix_dp_suspend); @@ -1884,13 +1878,6 @@ int analogix_dp_resume(struct analogix_dp_device *dp) return ret; } - if (dp->plat_data->panel) { - if (drm_panel_prepare(dp->plat_data->panel)) { - DRM_ERROR("failed to setup the panel\n"); - return -EBUSY; - } - } - return 0; } EXPORT_SYMBOL_GPL(analogix_dp_resume); diff --git a/drivers/gpu/drm/bridge/analogix/anx7625.c b/drivers/gpu/drm/bridge/analogix/anx7625.c index 0c323b5a1c99..b0ff1ecb80a5 100644 --- a/drivers/gpu/drm/bridge/analogix/anx7625.c +++ b/drivers/gpu/drm/bridge/analogix/anx7625.c @@ -2715,7 +2715,7 @@ free_hdcp_wq: return ret; } -static int anx7625_i2c_remove(struct i2c_client *client) +static void anx7625_i2c_remove(struct i2c_client *client) { struct anx7625_data *platform = i2c_get_clientdata(client); @@ -2735,8 +2735,6 @@ static int anx7625_i2c_remove(struct i2c_client *client) if (platform->pdata.audio_en) anx7625_unregister_audio(platform); - - return 0; } static const struct i2c_device_id anx7625_id[] = { diff --git a/drivers/gpu/drm/bridge/chrontel-ch7033.c b/drivers/gpu/drm/bridge/chrontel-ch7033.c index ba060277c3fd..b94f39a86846 100644 --- a/drivers/gpu/drm/bridge/chrontel-ch7033.c +++ b/drivers/gpu/drm/bridge/chrontel-ch7033.c @@ -583,14 +583,12 @@ static int ch7033_probe(struct i2c_client *client, return 0; } -static int ch7033_remove(struct i2c_client *client) +static void ch7033_remove(struct i2c_client *client) { struct device *dev = &client->dev; struct ch7033_priv *priv = dev_get_drvdata(dev); drm_bridge_remove(&priv->bridge); - - return 0; } static const struct of_device_id ch7033_dt_ids[] = { diff --git a/drivers/gpu/drm/bridge/cros-ec-anx7688.c b/drivers/gpu/drm/bridge/cros-ec-anx7688.c index 0f6d907432e3..fa91bdeddef0 100644 --- a/drivers/gpu/drm/bridge/cros-ec-anx7688.c +++ b/drivers/gpu/drm/bridge/cros-ec-anx7688.c @@ -159,13 +159,11 @@ static int cros_ec_anx7688_bridge_probe(struct i2c_client *client) return 0; } -static int cros_ec_anx7688_bridge_remove(struct i2c_client *client) +static void cros_ec_anx7688_bridge_remove(struct i2c_client *client) { struct cros_ec_anx7688 *anx7688 = i2c_get_clientdata(client); drm_bridge_remove(&anx7688->bridge); - - return 0; } static const struct of_device_id cros_ec_anx7688_bridge_match_table[] = { diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c index a4302492cf8d..1fd09911fe8c 100644 --- a/drivers/gpu/drm/bridge/ite-it6505.c +++ b/drivers/gpu/drm/bridge/ite-it6505.c @@ -3363,7 +3363,7 @@ static int it6505_i2c_probe(struct i2c_client *client, return 0; } -static int it6505_i2c_remove(struct i2c_client *client) +static void it6505_i2c_remove(struct i2c_client *client) { struct it6505 *it6505 = i2c_get_clientdata(client); @@ -3371,8 +3371,6 @@ static int it6505_i2c_remove(struct i2c_client *client) drm_dp_aux_unregister(&it6505->aux); it6505_debugfs_remove(it6505); it6505_poweroff(it6505); - - return 0; } static const struct i2c_device_id it6505_id[] = { diff --git a/drivers/gpu/drm/bridge/ite-it66121.c b/drivers/gpu/drm/bridge/ite-it66121.c index 44278d54d35d..4f6f1deba28c 100644 --- a/drivers/gpu/drm/bridge/ite-it66121.c +++ b/drivers/gpu/drm/bridge/ite-it66121.c @@ -1623,15 +1623,13 @@ static int it66121_probe(struct i2c_client *client, return 0; } -static int it66121_remove(struct i2c_client *client) +static void it66121_remove(struct i2c_client *client) { struct it66121_ctx *ctx = i2c_get_clientdata(client); ite66121_power_off(ctx); drm_bridge_remove(&ctx->bridge); mutex_destroy(&ctx->lock); - - return 0; } static const struct of_device_id it66121_dt_match[] = { diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 3e870d45f881..a98efef0ba0e 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -731,7 +731,7 @@ err_dt_parse: return ret; } -static int lt8912_remove(struct i2c_client *client) +static void lt8912_remove(struct i2c_client *client) { struct lt8912 *lt = i2c_get_clientdata(client); @@ -739,7 +739,6 @@ static int lt8912_remove(struct i2c_client *client) drm_bridge_remove(<->bridge); lt8912_free_i2c(lt); lt8912_put_dt(lt); - return 0; } static const struct of_device_id lt8912_dt_match[] = { diff --git a/drivers/gpu/drm/bridge/lontium-lt9211.c b/drivers/gpu/drm/bridge/lontium-lt9211.c index 9a3e90427d12..933ca028d612 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9211.c +++ b/drivers/gpu/drm/bridge/lontium-lt9211.c @@ -766,13 +766,11 @@ static int lt9211_probe(struct i2c_client *client, return ret; } -static int lt9211_remove(struct i2c_client *client) +static void lt9211_remove(struct i2c_client *client) { struct lt9211 *ctx = i2c_get_clientdata(client); drm_bridge_remove(&ctx->bridge); - - return 0; } static struct i2c_device_id lt9211_id[] = { diff --git a/drivers/gpu/drm/bridge/lontium-lt9611.c b/drivers/gpu/drm/bridge/lontium-lt9611.c index 5fccacc159f0..7c0a99173b39 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611.c @@ -1217,7 +1217,7 @@ err_of_put: return ret; } -static int lt9611_remove(struct i2c_client *client) +static void lt9611_remove(struct i2c_client *client) { struct lt9611 *lt9611 = i2c_get_clientdata(client); @@ -1229,8 +1229,6 @@ static int lt9611_remove(struct i2c_client *client) of_node_put(lt9611->dsi1_node); of_node_put(lt9611->dsi0_node); - - return 0; } static struct i2c_device_id lt9611_id[] = { diff --git a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c index fdf12d4c6416..fa1ee6264d92 100644 --- a/drivers/gpu/drm/bridge/lontium-lt9611uxc.c +++ b/drivers/gpu/drm/bridge/lontium-lt9611uxc.c @@ -978,7 +978,7 @@ err_of_put: return ret; } -static int lt9611uxc_remove(struct i2c_client *client) +static void lt9611uxc_remove(struct i2c_client *client) { struct lt9611uxc *lt9611uxc = i2c_get_clientdata(client); @@ -993,8 +993,6 @@ static int lt9611uxc_remove(struct i2c_client *client) of_node_put(lt9611uxc->dsi1_node); of_node_put(lt9611uxc->dsi0_node); - - return 0; } static struct i2c_device_id lt9611uxc_id[] = { diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c index 72248a565579..97359f807bfc 100644 --- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c +++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c @@ -357,11 +357,9 @@ static int stdp4028_ge_b850v3_fw_probe(struct i2c_client *stdp4028_i2c, return ge_b850v3_register(); } -static int stdp4028_ge_b850v3_fw_remove(struct i2c_client *stdp4028_i2c) +static void stdp4028_ge_b850v3_fw_remove(struct i2c_client *stdp4028_i2c) { ge_b850v3_lvds_remove(); - - return 0; } static const struct i2c_device_id stdp4028_ge_b850v3_fw_i2c_table[] = { @@ -407,11 +405,9 @@ static int stdp2690_ge_b850v3_fw_probe(struct i2c_client *stdp2690_i2c, return ge_b850v3_register(); } -static int stdp2690_ge_b850v3_fw_remove(struct i2c_client *stdp2690_i2c) +static void stdp2690_ge_b850v3_fw_remove(struct i2c_client *stdp2690_i2c) { ge_b850v3_lvds_remove(); - - return 0; } static const struct i2c_device_id stdp2690_ge_b850v3_fw_i2c_table[] = { diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c index 1ab91f4e057b..0851101a8c72 100644 --- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -315,13 +315,11 @@ static int ptn3460_probe(struct i2c_client *client, return 0; } -static int ptn3460_remove(struct i2c_client *client) +static void ptn3460_remove(struct i2c_client *client) { struct ptn3460_bridge *ptn_bridge = i2c_get_clientdata(client); drm_bridge_remove(&ptn_bridge->bridge); - - return 0; } static const struct i2c_device_id ptn3460_i2c_table[] = { diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c index b5750e5f71d7..309de802863d 100644 --- a/drivers/gpu/drm/bridge/parade-ps8622.c +++ b/drivers/gpu/drm/bridge/parade-ps8622.c @@ -520,14 +520,12 @@ static int ps8622_probe(struct i2c_client *client, return 0; } -static int ps8622_remove(struct i2c_client *client) +static void ps8622_remove(struct i2c_client *client) { struct ps8622_bridge *ps8622 = i2c_get_clientdata(client); backlight_device_unregister(ps8622->bl); drm_bridge_remove(&ps8622->bridge); - - return 0; } static const struct i2c_device_id ps8622_i2c_table[] = { diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c index 7ab38d734ad6..878fb7d3732b 100644 --- a/drivers/gpu/drm/bridge/sii902x.c +++ b/drivers/gpu/drm/bridge/sii902x.c @@ -1145,7 +1145,7 @@ static int sii902x_probe(struct i2c_client *client, return ret; } -static int sii902x_remove(struct i2c_client *client) +static void sii902x_remove(struct i2c_client *client) { struct sii902x *sii902x = i2c_get_clientdata(client); @@ -1154,8 +1154,6 @@ static int sii902x_remove(struct i2c_client *client) drm_bridge_remove(&sii902x->bridge); regulator_bulk_disable(ARRAY_SIZE(sii902x->supplies), sii902x->supplies); - - return 0; } static const struct of_device_id sii902x_dt_ids[] = { diff --git a/drivers/gpu/drm/bridge/sii9234.c b/drivers/gpu/drm/bridge/sii9234.c index 15c98a7bd81c..5b3061d4b5c3 100644 --- a/drivers/gpu/drm/bridge/sii9234.c +++ b/drivers/gpu/drm/bridge/sii9234.c @@ -936,14 +936,12 @@ static int sii9234_probe(struct i2c_client *client, return 0; } -static int sii9234_remove(struct i2c_client *client) +static void sii9234_remove(struct i2c_client *client) { struct sii9234 *ctx = i2c_get_clientdata(client); sii9234_cable_out(ctx); drm_bridge_remove(&ctx->bridge); - - return 0; } static const struct of_device_id sii9234_dt_match[] = { diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c index ab0bce4a988c..511982a1cedb 100644 --- a/drivers/gpu/drm/bridge/sil-sii8620.c +++ b/drivers/gpu/drm/bridge/sil-sii8620.c @@ -2346,7 +2346,7 @@ static int sii8620_probe(struct i2c_client *client, return 0; } -static int sii8620_remove(struct i2c_client *client) +static void sii8620_remove(struct i2c_client *client) { struct sii8620 *ctx = i2c_get_clientdata(client); @@ -2360,8 +2360,6 @@ static int sii8620_remove(struct i2c_client *client) sii8620_cable_out(ctx); } drm_bridge_remove(&ctx->bridge); - - return 0; } static const struct of_device_id sii8620_dt_match[] = { diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 89e060b273ef..2a58eb271f70 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -2184,13 +2184,11 @@ static int tc_probe(struct i2c_client *client, const struct i2c_device_id *id) return 0; } -static int tc_remove(struct i2c_client *client) +static void tc_remove(struct i2c_client *client) { struct tc_data *tc = i2c_get_clientdata(client); drm_bridge_remove(&tc->bridge); - - return 0; } static const struct i2c_device_id tc358767_i2c_ids[] = { diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index fd585bf925fe..4c4b77ce8aba 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -1072,13 +1072,11 @@ static int tc358768_i2c_probe(struct i2c_client *client, return mipi_dsi_host_register(&priv->dsi_host); } -static int tc358768_i2c_remove(struct i2c_client *client) +static void tc358768_i2c_remove(struct i2c_client *client) { struct tc358768_priv *priv = i2c_get_clientdata(client); mipi_dsi_host_unregister(&priv->dsi_host); - - return 0; } static struct i2c_driver tc358768_driver = { diff --git a/drivers/gpu/drm/bridge/tc358775.c b/drivers/gpu/drm/bridge/tc358775.c index a5f5eae1e80f..3ceb0e9f9bdc 100644 --- a/drivers/gpu/drm/bridge/tc358775.c +++ b/drivers/gpu/drm/bridge/tc358775.c @@ -704,13 +704,11 @@ err_bridge_remove: return ret; } -static int tc_remove(struct i2c_client *client) +static void tc_remove(struct i2c_client *client) { struct tc_data *tc = i2c_get_clientdata(client); drm_bridge_remove(&tc->bridge); - - return 0; } static const struct i2c_device_id tc358775_i2c_ids[] = { diff --git a/drivers/gpu/drm/bridge/ti-dlpc3433.c b/drivers/gpu/drm/bridge/ti-dlpc3433.c index cef454862b67..186a9e2ff24d 100644 --- a/drivers/gpu/drm/bridge/ti-dlpc3433.c +++ b/drivers/gpu/drm/bridge/ti-dlpc3433.c @@ -379,14 +379,12 @@ err_remove_bridge: return ret; } -static int dlpc3433_remove(struct i2c_client *client) +static void dlpc3433_remove(struct i2c_client *client) { struct dlpc *dlpc = i2c_get_clientdata(client); drm_bridge_remove(&dlpc->bridge); of_node_put(dlpc->host_node); - - return 0; } static const struct i2c_device_id dlpc3433_id[] = { diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c index 14e7aa77e758..7ba9467fff12 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c @@ -708,13 +708,11 @@ err_remove_bridge: return ret; } -static int sn65dsi83_remove(struct i2c_client *client) +static void sn65dsi83_remove(struct i2c_client *client) { struct sn65dsi83 *ctx = i2c_get_clientdata(client); drm_bridge_remove(&ctx->bridge); - - return 0; } static struct i2c_device_id sn65dsi83_id[] = { diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c index 401fe61217c7..b9635abbad16 100644 --- a/drivers/gpu/drm/bridge/ti-tfp410.c +++ b/drivers/gpu/drm/bridge/ti-tfp410.c @@ -394,11 +394,9 @@ static int tfp410_i2c_probe(struct i2c_client *client, return tfp410_init(&client->dev, true); } -static int tfp410_i2c_remove(struct i2c_client *client) +static void tfp410_i2c_remove(struct i2c_client *client) { tfp410_fini(&client->dev); - - return 0; } static const struct i2c_device_id tfp410_i2c_ids[] = { diff --git a/drivers/gpu/drm/display/drm_dp_helper.c b/drivers/gpu/drm/display/drm_dp_helper.c index 9f055d9710ea..16565a0a5da6 100644 --- a/drivers/gpu/drm/display/drm_dp_helper.c +++ b/drivers/gpu/drm/display/drm_dp_helper.c @@ -30,6 +30,7 @@ #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/string_helpers.h> +#include <linux/dynamic_debug.h> #include <drm/display/drm_dp_helper.h> #include <drm/display/drm_dp_mst_helper.h> @@ -40,6 +41,18 @@ #include "drm_dp_helper_internal.h" +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 dp_aux_backlight { struct backlight_device *base; struct drm_dp_aux *aux; diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c index 1f0a270ac984..f5fb22e0d033 100644 --- a/drivers/gpu/drm/drm_crtc_helper.c +++ b/drivers/gpu/drm/drm_crtc_helper.c @@ -32,6 +32,7 @@ #include <linux/export.h> #include <linux/kernel.h> #include <linux/moduleparam.h> +#include <linux/dynamic_debug.h> #include <drm/drm_atomic.h> #include <drm/drm_atomic_helper.h> @@ -50,6 +51,18 @@ #include "drm_crtc_helper_internal.h" +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"); + /** * DOC: overview * diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c index 493922069c90..01ee3febb813 100644 --- a/drivers/gpu/drm/drm_debugfs.c +++ b/drivers/gpu/drm/drm_debugfs.c @@ -377,8 +377,8 @@ static int vrr_range_show(struct seq_file *m, void *data) if (connector->status != connector_status_connected) return -ENODEV; - seq_printf(m, "Min: %u\n", (u8)connector->display_info.monitor_range.min_vfreq); - seq_printf(m, "Max: %u\n", (u8)connector->display_info.monitor_range.max_vfreq); + seq_printf(m, "Min: %u\n", connector->display_info.monitor_range.min_vfreq); + seq_printf(m, "Max: %u\n", connector->display_info.monitor_range.max_vfreq); return 0; } diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 73c614efc132..47465b9765f1 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -6112,12 +6112,14 @@ static void drm_parse_cea_ext(struct drm_connector *connector, } static -void get_monitor_range(const struct detailed_timing *timing, - void *info_monitor_range) +void get_monitor_range(const struct detailed_timing *timing, void *c) { - struct drm_monitor_range_info *monitor_range = info_monitor_range; + struct detailed_mode_closure *closure = c; + struct drm_display_info *info = &closure->connector->display_info; + struct drm_monitor_range_info *monitor_range = &info->monitor_range; const struct detailed_non_pixel *data = &timing->data.other_data; const struct detailed_data_monitor_range *range = &data->data.range; + const struct edid *edid = closure->drm_edid->edid; if (!is_display_descriptor(timing, EDID_DETAIL_MONITOR_RANGE)) return; @@ -6136,12 +6138,23 @@ void get_monitor_range(const struct detailed_timing *timing, monitor_range->min_vfreq = range->min_vfreq; monitor_range->max_vfreq = range->max_vfreq; + + if (edid->revision >= 4) { + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MIN_VFREQ) + monitor_range->min_vfreq += 255; + if (data->pad2 & DRM_EDID_RANGE_OFFSET_MAX_VFREQ) + monitor_range->max_vfreq += 255; + } } static void drm_get_monitor_range(struct drm_connector *connector, const struct drm_edid *drm_edid) { - struct drm_display_info *info = &connector->display_info; + const struct drm_display_info *info = &connector->display_info; + struct detailed_mode_closure closure = { + .connector = connector, + .drm_edid = drm_edid, + }; if (drm_edid->edid->revision < 4) return; @@ -6149,8 +6162,7 @@ static void drm_get_monitor_range(struct drm_connector *connector, if (!(drm_edid->edid->features & DRM_EDID_FEATURE_CONTINUOUS_FREQ)) return; - drm_for_each_detailed_block(drm_edid, get_monitor_range, - &info->monitor_range); + drm_for_each_detailed_block(drm_edid, get_monitor_range, &closure); DRM_DEBUG_KMS("Supported Monitor Refresh rate range is %d Hz - %d Hz\n", info->monitor_range.min_vfreq, diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index dbee4863e4f7..b8db675e7fb5 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -165,24 +165,10 @@ void drm_gem_private_object_init(struct drm_device *dev, obj->resv = &obj->_resv; drm_vma_node_reset(&obj->vma_node); + INIT_LIST_HEAD(&obj->lru_node); } EXPORT_SYMBOL(drm_gem_private_object_init); -static void -drm_gem_remove_prime_handles(struct drm_gem_object *obj, struct drm_file *filp) -{ - /* - * Note: obj->dma_buf can't disappear as long as we still hold a - * handle reference in obj->handle_count. - */ - mutex_lock(&filp->prime.lock); - if (obj->dma_buf) { - drm_prime_remove_buf_handle_locked(&filp->prime, - obj->dma_buf); - } - mutex_unlock(&filp->prime.lock); -} - /** * drm_gem_object_handle_free - release resources bound to userspace handles * @obj: GEM object to clean up. @@ -253,7 +239,7 @@ drm_gem_object_release_handle(int id, void *ptr, void *data) if (obj->funcs->close) obj->funcs->close(obj, file_priv); - drm_gem_remove_prime_handles(obj, file_priv); + drm_prime_remove_buf_handle(&file_priv->prime, id); drm_vma_node_revoke(&obj->vma_node, file_priv); drm_gem_object_handle_put_unlocked(obj); @@ -951,6 +937,7 @@ drm_gem_object_release(struct drm_gem_object *obj) dma_resv_fini(&obj->_resv); drm_gem_free_mmap_offset(obj); + drm_gem_lru_remove(obj); } EXPORT_SYMBOL(drm_gem_object_release); @@ -1298,3 +1285,171 @@ drm_gem_unlock_reservations(struct drm_gem_object **objs, int count, ww_acquire_fini(acquire_ctx); } EXPORT_SYMBOL(drm_gem_unlock_reservations); + +/** + * drm_gem_lru_init - initialize a LRU + * + * @lru: The LRU to initialize + * @lock: The lock protecting the LRU + */ +void +drm_gem_lru_init(struct drm_gem_lru *lru, struct mutex *lock) +{ + lru->lock = lock; + lru->count = 0; + INIT_LIST_HEAD(&lru->list); +} +EXPORT_SYMBOL(drm_gem_lru_init); + +static void +drm_gem_lru_remove_locked(struct drm_gem_object *obj) +{ + obj->lru->count -= obj->size >> PAGE_SHIFT; + WARN_ON(obj->lru->count < 0); + list_del(&obj->lru_node); + obj->lru = NULL; +} + +/** + * drm_gem_lru_remove - remove object from whatever LRU it is in + * + * If the object is currently in any LRU, remove it. + * + * @obj: The GEM object to remove from current LRU + */ +void +drm_gem_lru_remove(struct drm_gem_object *obj) +{ + struct drm_gem_lru *lru = obj->lru; + + if (!lru) + return; + + mutex_lock(lru->lock); + drm_gem_lru_remove_locked(obj); + mutex_unlock(lru->lock); +} +EXPORT_SYMBOL(drm_gem_lru_remove); + +static void +drm_gem_lru_move_tail_locked(struct drm_gem_lru *lru, struct drm_gem_object *obj) +{ + lockdep_assert_held_once(lru->lock); + + if (obj->lru) + drm_gem_lru_remove_locked(obj); + + lru->count += obj->size >> PAGE_SHIFT; + list_add_tail(&obj->lru_node, &lru->list); + obj->lru = lru; +} + +/** + * drm_gem_lru_move_tail - move the object to the tail of the LRU + * + * If the object is already in this LRU it will be moved to the + * tail. Otherwise it will be removed from whichever other LRU + * it is in (if any) and moved into this LRU. + * + * @lru: The LRU to move the object into. + * @obj: The GEM object to move into this LRU + */ +void +drm_gem_lru_move_tail(struct drm_gem_lru *lru, struct drm_gem_object *obj) +{ + mutex_lock(lru->lock); + drm_gem_lru_move_tail_locked(lru, obj); + mutex_unlock(lru->lock); +} +EXPORT_SYMBOL(drm_gem_lru_move_tail); + +/** + * drm_gem_lru_scan - helper to implement shrinker.scan_objects + * + * If the shrink callback succeeds, it is expected that the driver + * move the object out of this LRU. + * + * If the LRU possibly contain active buffers, it is the responsibility + * of the shrink callback to check for this (ie. dma_resv_test_signaled()) + * or if necessary block until the buffer becomes idle. + * + * @lru: The LRU to scan + * @nr_to_scan: The number of pages to try to reclaim + * @shrink: Callback to try to shrink/reclaim the object. + */ +unsigned long +drm_gem_lru_scan(struct drm_gem_lru *lru, unsigned nr_to_scan, + bool (*shrink)(struct drm_gem_object *obj)) +{ + struct drm_gem_lru still_in_lru; + struct drm_gem_object *obj; + unsigned freed = 0; + + drm_gem_lru_init(&still_in_lru, lru->lock); + + mutex_lock(lru->lock); + + while (freed < nr_to_scan) { + obj = list_first_entry_or_null(&lru->list, typeof(*obj), lru_node); + + if (!obj) + break; + + drm_gem_lru_move_tail_locked(&still_in_lru, obj); + + /* + * If it's in the process of being freed, gem_object->free() + * may be blocked on lock waiting to remove it. So just + * skip it. + */ + if (!kref_get_unless_zero(&obj->refcount)) + continue; + + /* + * Now that we own a reference, we can drop the lock for the + * rest of the loop body, to reduce contention with other + * code paths that need the LRU lock + */ + mutex_unlock(lru->lock); + + /* + * Note that this still needs to be trylock, since we can + * hit shrinker in response to trying to get backing pages + * for this obj (ie. while it's lock is already held) + */ + if (!dma_resv_trylock(obj->resv)) + goto tail; + + if (shrink(obj)) { + freed += obj->size >> PAGE_SHIFT; + + /* + * If we succeeded in releasing the object's backing + * pages, we expect the driver to have moved the object + * out of this LRU + */ + WARN_ON(obj->lru == &still_in_lru); + WARN_ON(obj->lru == lru); + } + + dma_resv_unlock(obj->resv); + +tail: + drm_gem_object_put(obj); + mutex_lock(lru->lock); + } + + /* + * Move objects we've skipped over out of the temporary still_in_lru + * back into this LRU + */ + list_for_each_entry (obj, &still_in_lru.list, lru_node) + obj->lru = lru; + list_splice_tail(&still_in_lru.list, &lru->list); + lru->count += still_in_lru.count; + + mutex_unlock(lru->lock); + + return freed; +} +EXPORT_SYMBOL(drm_gem_lru_scan); diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h index 1fbbc19f1ac0..7bb98e6a446d 100644 --- a/drivers/gpu/drm/drm_internal.h +++ b/drivers/gpu/drm/drm_internal.h @@ -74,8 +74,8 @@ int drm_prime_fd_to_handle_ioctl(struct drm_device *dev, void *data, void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv); void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv); -void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, - struct dma_buf *dma_buf); +void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, + uint32_t handle); /* drm_drv.c */ struct drm_minor *drm_minor_acquire(unsigned int minor_id); diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index ef50c4e2e509..20e109a802ae 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -190,29 +190,33 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri return -ENOENT; } -void drm_prime_remove_buf_handle_locked(struct drm_prime_file_private *prime_fpriv, - struct dma_buf *dma_buf) +void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv, + uint32_t handle) { struct rb_node *rb; - rb = prime_fpriv->dmabufs.rb_node; + mutex_lock(&prime_fpriv->lock); + + rb = prime_fpriv->handles.rb_node; while (rb) { struct drm_prime_member *member; - member = rb_entry(rb, struct drm_prime_member, dmabuf_rb); - if (member->dma_buf == dma_buf) { + member = rb_entry(rb, struct drm_prime_member, handle_rb); + if (member->handle == handle) { rb_erase(&member->handle_rb, &prime_fpriv->handles); rb_erase(&member->dmabuf_rb, &prime_fpriv->dmabufs); - dma_buf_put(dma_buf); + dma_buf_put(member->dma_buf); kfree(member); - return; - } else if (member->dma_buf < dma_buf) { + break; + } else if (member->handle < handle) { rb = rb->rb_right; } else { rb = rb->rb_left; } } + + mutex_unlock(&prime_fpriv->lock); } void drm_prime_init_file_private(struct drm_prime_file_private *prime_fpriv) diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index f783d4963d4b..5b93c11895bb 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -23,14 +23,13 @@ * Rob Clark <robdclark@gmail.com> */ -#define DEBUG /* for pr_debug() */ - #include <linux/stdarg.h> #include <linux/io.h> #include <linux/moduleparam.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/dynamic_debug.h> #include <drm/drm.h> #include <drm/drm_drv.h> @@ -40,7 +39,7 @@ * __drm_debug: Enable debug output. * Bitmask of DRM_UT_x. See include/drm/drm_print.h for details. */ -unsigned int __drm_debug; +unsigned long __drm_debug; EXPORT_SYMBOL(__drm_debug); MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug category.\n" @@ -52,7 +51,30 @@ MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug cat "\t\tBit 5 (0x20) will enable VBL messages (vblank code)\n" "\t\tBit 7 (0x80) will enable LEASE messages (leasing code)\n" "\t\tBit 8 (0x100) will enable DP messages (displayport code)"); -module_param_named(debug, __drm_debug, int, 0600); + +#if !defined(CONFIG_DRM_USE_DYNAMIC_DEBUG) +module_param_named(debug, __drm_debug, ulong, 0600); +#else +/* classnames must match vals of enum drm_debug_category */ +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"); + +static struct ddebug_class_param drm_debug_bitmap = { + .bits = &__drm_debug, + .flags = "p", + .map = &drm_debug_classes, +}; +module_param_cb(debug, ¶m_ops_dyndbg_classes, &drm_debug_bitmap, 0600); +#endif void __drm_puts_coredump(struct drm_printer *p, const char *str) { @@ -162,7 +184,8 @@ EXPORT_SYMBOL(__drm_printfn_info); void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf) { - pr_debug("%s %pV", p->prefix, vaf); + /* pr_debug callsite decorations are unhelpful here */ + printk(KERN_DEBUG "%s %pV", p->prefix, vaf); } EXPORT_SYMBOL(__drm_printfn_debug); @@ -256,15 +279,16 @@ void drm_dev_printk(const struct device *dev, const char *level, } EXPORT_SYMBOL(drm_dev_printk); -void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, - const char *format, ...) +void __drm_dev_dbg(struct _ddebug *desc, const struct device *dev, + enum drm_debug_category category, const char *format, ...) { struct va_format vaf; va_list args; - if (!drm_debug_enabled(category)) + if (!__drm_debug_enabled(category)) return; + /* we know we are printing for either syslog, tracefs, or both */ va_start(args, format); vaf.fmt = format; vaf.va = &args; @@ -278,14 +302,14 @@ void drm_dev_dbg(const struct device *dev, enum drm_debug_category category, va_end(args); } -EXPORT_SYMBOL(drm_dev_dbg); +EXPORT_SYMBOL(__drm_dev_dbg); -void __drm_dbg(enum drm_debug_category category, const char *format, ...) +void ___drm_dbg(struct _ddebug *desc, enum drm_debug_category category, const char *format, ...) { struct va_format vaf; va_list args; - if (!drm_debug_enabled(category)) + if (!__drm_debug_enabled(category)) return; va_start(args, format); @@ -297,7 +321,7 @@ void __drm_dbg(enum drm_debug_category category, const char *format, ...) va_end(args); } -EXPORT_SYMBOL(__drm_dbg); +EXPORT_SYMBOL(___drm_dbg); void __drm_err(const char *format, ...) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_dma.c b/drivers/gpu/drm/exynos/exynos_drm_dma.c index bf33c3084cb4..a971590b8132 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dma.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dma.c @@ -4,7 +4,6 @@ // Author: Inki Dae <inki.dae@samsung.com> // Author: Andrzej Hajda <a.hajda@samsung.com> -#include <linux/dma-iommu.h> #include <linux/dma-map-ops.h> #include <linux/iommu.h> #include <linux/platform_device.h> diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c index 10b0036f8a2e..b7c11bdce2c8 100644 --- a/drivers/gpu/drm/exynos/exynos_hdmi.c +++ b/drivers/gpu/drm/exynos/exynos_hdmi.c @@ -893,7 +893,7 @@ static int hdmi_get_modes(struct drm_connector *connector) if (!edid) return -ENODEV; - hdata->dvi_mode = !drm_detect_hdmi_monitor(edid); + hdata->dvi_mode = !connector->display_info.is_hdmi; DRM_DEV_DEBUG_KMS(hdata->dev, "%s : width[%d] x height[%d]\n", (hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"), edid->width_cm, edid->height_cm); @@ -922,8 +922,8 @@ static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock) return -EINVAL; } -static int hdmi_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status hdmi_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct hdmi_context *hdata = connector_to_hdmi(connector); int ret; diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c index 65260a658684..8d333db813b7 100644 --- a/drivers/gpu/drm/exynos/exynos_mixer.c +++ b/drivers/gpu/drm/exynos/exynos_mixer.c @@ -1045,7 +1045,7 @@ static void mixer_atomic_disable(struct exynos_drm_crtc *crtc) clear_bit(MXR_BIT_POWERED, &ctx->flags); } -static int mixer_mode_valid(struct exynos_drm_crtc *crtc, +static enum drm_mode_status mixer_mode_valid(struct exynos_drm_crtc *crtc, const struct drm_display_mode *mode) { struct mixer_context *ctx = crtc->ctx; diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c index dffe37490206..4b7627a72637 100644 --- a/drivers/gpu/drm/gma500/gem.c +++ b/drivers/gpu/drm/gma500/gem.c @@ -112,12 +112,12 @@ static void psb_gem_free_object(struct drm_gem_object *obj) { struct psb_gem_object *pobj = to_psb_gem_object(obj); - drm_gem_object_release(obj); - /* Undo the mmap pin if we are destroying the object */ if (pobj->mmapping) psb_gem_unpin(pobj); + drm_gem_object_release(obj); + WARN_ON(pobj->in_gart && !pobj->stolen); release_resource(&pobj->resource); diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c index b0ea911b27de..fe7b8436f87a 100644 --- a/drivers/gpu/drm/gma500/gma_display.c +++ b/drivers/gpu/drm/gma500/gma_display.c @@ -532,15 +532,18 @@ int gma_crtc_page_flip(struct drm_crtc *crtc, WARN_ON(drm_crtc_vblank_get(crtc) != 0); gma_crtc->page_flip_event = event; + spin_unlock_irqrestore(&dev->event_lock, flags); /* Call this locked if we want an event at vblank interrupt. */ ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb); if (ret) { - gma_crtc->page_flip_event = NULL; - drm_crtc_vblank_put(crtc); + spin_lock_irqsave(&dev->event_lock, flags); + if (gma_crtc->page_flip_event) { + gma_crtc->page_flip_event = NULL; + drm_crtc_vblank_put(crtc); + } + spin_unlock_irqrestore(&dev->event_lock, flags); } - - spin_unlock_irqrestore(&dev->event_lock, flags); } else { ret = crtc_funcs->mode_set_base(crtc, crtc->x, crtc->y, old_fb); } diff --git a/drivers/gpu/drm/hisilicon/hibmc/Kconfig b/drivers/gpu/drm/hisilicon/hibmc/Kconfig index 073adfe438dd..4e41c144a290 100644 --- a/drivers/gpu/drm/hisilicon/hibmc/Kconfig +++ b/drivers/gpu/drm/hisilicon/hibmc/Kconfig @@ -2,6 +2,7 @@ config DRM_HISI_HIBMC tristate "DRM Support for Hisilicon Hibmc" depends on DRM && PCI && (ARM64 || COMPILE_TEST) + depends on MMU select DRM_KMS_HELPER select DRM_VRAM_HELPER select DRM_TTM diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c index 6d11e7938c83..ca127ff797f7 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c @@ -23,9 +23,6 @@ #define DRIVER_MAJOR 1 #define DRIVER_MINOR 0 -#define PCI_VENDOR_ID_MICROSOFT 0x1414 -#define PCI_DEVICE_ID_HYPERV_VIDEO 0x5353 - DEFINE_DRM_GEM_FOPS(hv_fops); static struct drm_driver hyperv_driver = { @@ -133,7 +130,6 @@ static int hyperv_vmbus_probe(struct hv_device *hdev, } ret = hyperv_setup_vram(hv, hdev); - if (ret) goto err_vmbus_close; @@ -146,22 +142,22 @@ static int hyperv_vmbus_probe(struct hv_device *hdev, if (ret) drm_warn(dev, "Failed to update vram location.\n"); - hv->dirt_needed = true; - ret = hyperv_mode_config_init(hv); if (ret) - goto err_vmbus_close; + goto err_free_mmio; ret = drm_dev_register(dev, 0); if (ret) { drm_err(dev, "Failed to register drm driver.\n"); - goto err_vmbus_close; + goto err_free_mmio; } drm_fbdev_generic_setup(dev, 0); return 0; +err_free_mmio: + vmbus_free_mmio(hv->mem->start, hv->fb_size); err_vmbus_close: vmbus_close(hdev->channel); err_hv_set_drv_data: diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_proto.c b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c index 76a182a9a765..013a7829182d 100644 --- a/drivers/gpu/drm/hyperv/hyperv_drm_proto.c +++ b/drivers/gpu/drm/hyperv/hyperv_drm_proto.c @@ -208,7 +208,7 @@ static inline int hyperv_sendpacket(struct hv_device *hdev, struct synthvid_msg VM_PKT_DATA_INBAND, 0); if (ret) - drm_err(&hv->dev, "Unable to send packet via vmbus\n"); + drm_err_ratelimited(&hv->dev, "Unable to send packet via vmbus; error %d\n", ret); return ret; } diff --git a/drivers/gpu/drm/i2c/ch7006_drv.c b/drivers/gpu/drm/i2c/ch7006_drv.c index b91e48d2190d..578b738859b9 100644 --- a/drivers/gpu/drm/i2c/ch7006_drv.c +++ b/drivers/gpu/drm/i2c/ch7006_drv.c @@ -417,11 +417,9 @@ fail: return -ENODEV; } -static int ch7006_remove(struct i2c_client *client) +static void ch7006_remove(struct i2c_client *client) { ch7006_dbg(client, "\n"); - - return 0; } static int ch7006_resume(struct device *dev) diff --git a/drivers/gpu/drm/i2c/sil164_drv.c b/drivers/gpu/drm/i2c/sil164_drv.c index 741886b54419..1bc0b5de4499 100644 --- a/drivers/gpu/drm/i2c/sil164_drv.c +++ b/drivers/gpu/drm/i2c/sil164_drv.c @@ -370,12 +370,6 @@ sil164_probe(struct i2c_client *client, const struct i2c_device_id *id) return 0; } -static int -sil164_remove(struct i2c_client *client) -{ - return 0; -} - static struct i2c_client * sil164_detect_slave(struct i2c_client *client) { @@ -427,7 +421,6 @@ MODULE_DEVICE_TABLE(i2c, sil164_ids); static struct drm_i2c_encoder_driver sil164_driver = { .i2c_driver = { .probe = sil164_probe, - .remove = sil164_remove, .driver = { .name = "sil164", }, diff --git a/drivers/gpu/drm/i2c/tda9950.c b/drivers/gpu/drm/i2c/tda9950.c index 5b03fdd1eaa4..9ed54e7ccff2 100644 --- a/drivers/gpu/drm/i2c/tda9950.c +++ b/drivers/gpu/drm/i2c/tda9950.c @@ -478,14 +478,12 @@ static int tda9950_probe(struct i2c_client *client, return 0; } -static int tda9950_remove(struct i2c_client *client) +static void tda9950_remove(struct i2c_client *client) { struct tda9950_priv *priv = i2c_get_clientdata(client); cec_notifier_cec_adap_unregister(priv->notify, priv->adap); cec_unregister_adapter(priv->adap); - - return 0; } static struct i2c_device_id tda9950_ids[] = { diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c index f8eb6f69be05..d444e7fffb54 100644 --- a/drivers/gpu/drm/i2c/tda998x_drv.c +++ b/drivers/gpu/drm/i2c/tda998x_drv.c @@ -2076,11 +2076,10 @@ tda998x_probe(struct i2c_client *client, const struct i2c_device_id *id) return ret; } -static int tda998x_remove(struct i2c_client *client) +static void tda998x_remove(struct i2c_client *client) { component_del(&client->dev, &tda998x_ops); tda998x_destroy(&client->dev); - return 0; } #ifdef CONFIG_OF diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile index 522ef9b4aff3..a26edcdadc21 100644 --- a/drivers/gpu/drm/i915/Makefile +++ b/drivers/gpu/drm/i915/Makefile @@ -123,6 +123,7 @@ gt-y += \ gt/intel_ring.o \ gt/intel_ring_submission.o \ gt/intel_rps.o \ + gt/intel_sa_media.o \ gt/intel_sseu.o \ gt/intel_sseu_debugfs.o \ gt/intel_timeline.o \ @@ -257,7 +258,8 @@ i915-y += \ display/intel_vga.o \ display/i9xx_plane.o \ display/skl_scaler.o \ - display/skl_universal_plane.o + display/skl_universal_plane.o \ + display/skl_watermark.o i915-$(CONFIG_ACPI) += \ display/intel_acpi.o \ display/intel_opregion.o diff --git a/drivers/gpu/drm/i915/display/g4x_dp.c b/drivers/gpu/drm/i915/display/g4x_dp.c index 82ad8fe7440c..e3e3d27ffb53 100644 --- a/drivers/gpu/drm/i915/display/g4x_dp.c +++ b/drivers/gpu/drm/i915/display/g4x_dp.c @@ -1169,7 +1169,7 @@ intel_dp_hotplug(struct intel_encoder *encoder, static bool ibx_digital_port_connected(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - u32 bit = dev_priv->hotplug.pch_hpd[encoder->hpd_pin]; + u32 bit = dev_priv->display.hotplug.pch_hpd[encoder->hpd_pin]; return intel_de_read(dev_priv, SDEISR) & bit; } @@ -1223,7 +1223,7 @@ static bool gm45_digital_port_connected(struct intel_encoder *encoder) static bool ilk_digital_port_connected(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - u32 bit = dev_priv->hotplug.hpd[encoder->hpd_pin]; + u32 bit = dev_priv->display.hotplug.hpd[encoder->hpd_pin]; return intel_de_read(dev_priv, DEISR) & bit; } diff --git a/drivers/gpu/drm/i915/display/g4x_hdmi.c b/drivers/gpu/drm/i915/display/g4x_hdmi.c index 5fbd2ae95869..2b73f5ff0d02 100644 --- a/drivers/gpu/drm/i915/display/g4x_hdmi.c +++ b/drivers/gpu/drm/i915/display/g4x_hdmi.c @@ -120,7 +120,7 @@ static void intel_hdmi_get_config(struct intel_encoder *encoder, pipe_config->hw.adjusted_mode.flags |= flags; if ((tmp & SDVO_COLOR_FORMAT_MASK) == HDMI_COLOR_FORMAT_12bpc) - dotclock = pipe_config->port_clock * 2 / 3; + dotclock = DIV_ROUND_CLOSEST(pipe_config->port_clock * 2, 3); else dotclock = pipe_config->port_clock; diff --git a/drivers/gpu/drm/i915/display/hsw_ips.c b/drivers/gpu/drm/i915/display/hsw_ips.c index 861dcd2eb890..a5be4af792cb 100644 --- a/drivers/gpu/drm/i915/display/hsw_ips.c +++ b/drivers/gpu/drm/i915/display/hsw_ips.c @@ -202,7 +202,7 @@ bool hsw_crtc_state_ips_capable(const struct intel_crtc_state *crtc_state) * Should measure whether using a lower cdclk w/o IPS */ if (IS_BROADWELL(i915) && - crtc_state->pixel_rate > i915->max_cdclk_freq * 95 / 100) + crtc_state->pixel_rate > i915->display.cdclk.max_cdclk_freq * 95 / 100) return false; return true; diff --git a/drivers/gpu/drm/i915/display/i9xx_plane.c b/drivers/gpu/drm/i915/display/i9xx_plane.c index 0f35f2facdfc..5afbe3e98ee8 100644 --- a/drivers/gpu/drm/i915/display/i9xx_plane.c +++ b/drivers/gpu/drm/i915/display/i9xx_plane.c @@ -125,7 +125,7 @@ static struct intel_fbc *i9xx_plane_fbc(struct drm_i915_private *dev_priv, enum i9xx_plane_id i9xx_plane) { if (i9xx_plane_has_fbc(dev_priv, i9xx_plane)) - return dev_priv->fbc[INTEL_FBC_A]; + return dev_priv->display.fbc[INTEL_FBC_A]; else return NULL; } diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index 5dcfa7feffa9..ed4d93942dbd 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -33,6 +33,7 @@ #include "icl_dsi_regs.h" #include "intel_atomic.h" #include "intel_backlight.h" +#include "intel_backlight_regs.h" #include "intel_combo_phy.h" #include "intel_combo_phy_regs.h" #include "intel_connector.h" @@ -641,13 +642,13 @@ static void gen11_dsi_gate_clocks(struct intel_encoder *encoder) u32 tmp; enum phy phy; - mutex_lock(&dev_priv->dpll.lock); + mutex_lock(&dev_priv->display.dpll.lock); tmp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0); for_each_dsi_phy(phy, intel_dsi->phys) tmp |= ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy); intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, tmp); - mutex_unlock(&dev_priv->dpll.lock); + mutex_unlock(&dev_priv->display.dpll.lock); } static void gen11_dsi_ungate_clocks(struct intel_encoder *encoder) @@ -657,13 +658,13 @@ static void gen11_dsi_ungate_clocks(struct intel_encoder *encoder) u32 tmp; enum phy phy; - mutex_lock(&dev_priv->dpll.lock); + mutex_lock(&dev_priv->display.dpll.lock); tmp = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0); for_each_dsi_phy(phy, intel_dsi->phys) tmp &= ~ICL_DPCLKA_CFGCR0_DDI_CLK_OFF(phy); intel_de_write(dev_priv, ICL_DPCLKA_CFGCR0, tmp); - mutex_unlock(&dev_priv->dpll.lock); + mutex_unlock(&dev_priv->display.dpll.lock); } static bool gen11_dsi_is_clock_enabled(struct intel_encoder *encoder) @@ -693,7 +694,7 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder, enum phy phy; u32 val; - mutex_lock(&dev_priv->dpll.lock); + mutex_lock(&dev_priv->display.dpll.lock); val = intel_de_read(dev_priv, ICL_DPCLKA_CFGCR0); for_each_dsi_phy(phy, intel_dsi->phys) { @@ -709,7 +710,7 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder, intel_de_posting_read(dev_priv, ICL_DPCLKA_CFGCR0); - mutex_unlock(&dev_priv->dpll.lock); + mutex_unlock(&dev_priv->display.dpll.lock); } static void @@ -1629,6 +1630,8 @@ static int gen11_dsi_dsc_compute_config(struct intel_encoder *encoder, /* FIXME: initialize from VBT */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay; + ret = intel_dsc_compute_params(crtc_state); if (ret) return ret; @@ -2070,8 +2073,11 @@ void icl_dsi_init(struct drm_i915_private *dev_priv) else intel_dsi->ports = BIT(port); - intel_dsi->dcs_backlight_ports = intel_connector->panel.vbt.dsi.bl_ports; - intel_dsi->dcs_cabc_ports = intel_connector->panel.vbt.dsi.cabc_ports; + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports; + + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports; for_each_dsi_port(port, intel_dsi->ports) { struct intel_dsi_host *host; diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c index b94973b5633f..18f0a5ae3bac 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic.c +++ b/drivers/gpu/drm/i915/display/intel_atomic.c @@ -62,9 +62,9 @@ int intel_digital_connector_atomic_get_property(struct drm_connector *connector, struct intel_digital_connector_state *intel_conn_state = to_intel_digital_connector_state(state); - if (property == dev_priv->force_audio_property) + if (property == dev_priv->display.properties.force_audio) *val = intel_conn_state->force_audio; - else if (property == dev_priv->broadcast_rgb_property) + else if (property == dev_priv->display.properties.broadcast_rgb) *val = intel_conn_state->broadcast_rgb; else { drm_dbg_atomic(&dev_priv->drm, @@ -95,12 +95,12 @@ int intel_digital_connector_atomic_set_property(struct drm_connector *connector, struct intel_digital_connector_state *intel_conn_state = to_intel_digital_connector_state(state); - if (property == dev_priv->force_audio_property) { + if (property == dev_priv->display.properties.force_audio) { intel_conn_state->force_audio = val; return 0; } - if (property == dev_priv->broadcast_rgb_property) { + if (property == dev_priv->display.properties.broadcast_rgb) { intel_conn_state->broadcast_rgb = val; return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c index dd876dbbaa39..aaa6708256d5 100644 --- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c +++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c @@ -42,9 +42,9 @@ #include "intel_display_types.h" #include "intel_fb.h" #include "intel_fb_pin.h" -#include "intel_pm.h" #include "intel_sprite.h" #include "skl_scaler.h" +#include "skl_watermark.h" static void intel_plane_state_reset(struct intel_plane_state *plane_state, struct intel_plane *plane) diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c index 6c9ee905f132..aacbc6da84ef 100644 --- a/drivers/gpu/drm/i915/display/intel_audio.c +++ b/drivers/gpu/drm/i915/display/intel_audio.c @@ -393,7 +393,7 @@ hsw_dp_audio_config_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->audio.component; + struct i915_audio_component *acomp = dev_priv->display.audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum port port = encoder->port; const struct dp_aud_n_m *nm; @@ -441,7 +441,7 @@ hsw_hdmi_audio_config_update(struct intel_encoder *encoder, const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->audio.component; + struct i915_audio_component *acomp = dev_priv->display.audio.component; enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; enum port port = encoder->port; int n, rate; @@ -496,7 +496,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder, enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder; u32 tmp; - mutex_lock(&dev_priv->audio.mutex); + mutex_lock(&dev_priv->display.audio.mutex); /* Disable timestamps */ tmp = intel_de_read(dev_priv, HSW_AUD_CFG(cpu_transcoder)); @@ -514,7 +514,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder, tmp &= ~AUDIO_OUTPUT_ENABLE(cpu_transcoder); intel_de_write(dev_priv, HSW_AUD_PIN_ELD_CP_VLD, tmp); - mutex_unlock(&dev_priv->audio.mutex); + mutex_unlock(&dev_priv->display.audio.mutex); } static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder, @@ -532,7 +532,7 @@ static unsigned int calc_hblank_early_prog(struct intel_encoder *encoder, h_total = crtc_state->hw.adjusted_mode.crtc_htotal; pixel_clk = crtc_state->hw.adjusted_mode.crtc_clock; vdsc_bpp = crtc_state->dsc.compressed_bpp; - cdclk = i915->cdclk.hw.cdclk; + cdclk = i915->display.cdclk.hw.cdclk; /* fec= 0.972261, using rounding multiplier of 1000000 */ fec_coeff = 972261; link_clk = crtc_state->port_clock; @@ -639,7 +639,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder, u32 tmp; int len, i; - mutex_lock(&dev_priv->audio.mutex); + mutex_lock(&dev_priv->display.audio.mutex); /* Enable Audio WA for 4k DSC usecases */ if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP)) @@ -677,7 +677,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder, /* Enable timestamps */ hsw_audio_config_update(encoder, crtc_state); - mutex_unlock(&dev_priv->audio.mutex); + mutex_unlock(&dev_priv->display.audio.mutex); } static void ilk_audio_codec_disable(struct intel_encoder *encoder, @@ -814,7 +814,7 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, const struct drm_connector_state *conn_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->audio.component; + struct i915_audio_component *acomp = dev_priv->display.audio.component; struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_connector *connector = conn_state->connector; const struct drm_display_mode *adjusted_mode = @@ -838,17 +838,17 @@ void intel_audio_codec_enable(struct intel_encoder *encoder, connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2; - if (dev_priv->audio.funcs) - dev_priv->audio.funcs->audio_codec_enable(encoder, - crtc_state, - conn_state); + if (dev_priv->display.funcs.audio) + dev_priv->display.funcs.audio->audio_codec_enable(encoder, + crtc_state, + conn_state); - mutex_lock(&dev_priv->audio.mutex); + mutex_lock(&dev_priv->display.audio.mutex); encoder->audio_connector = connector; /* referred in audio callbacks */ - dev_priv->audio.encoder_map[pipe] = encoder; - mutex_unlock(&dev_priv->audio.mutex); + dev_priv->display.audio.encoder_map[pipe] = encoder; + mutex_unlock(&dev_priv->display.audio.mutex); if (acomp && acomp->base.audio_ops && acomp->base.audio_ops->pin_eld_notify) { @@ -878,7 +878,7 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, const struct drm_connector_state *old_conn_state) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_audio_component *acomp = dev_priv->audio.component; + struct i915_audio_component *acomp = dev_priv->display.audio.component; struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->uapi.crtc); struct drm_connector *connector = old_conn_state->connector; enum port port = encoder->port; @@ -891,15 +891,15 @@ void intel_audio_codec_disable(struct intel_encoder *encoder, connector->base.id, connector->name, encoder->base.base.id, encoder->base.name, pipe_name(pipe)); - if (dev_priv->audio.funcs) - dev_priv->audio.funcs->audio_codec_disable(encoder, - old_crtc_state, - old_conn_state); + if (dev_priv->display.funcs.audio) + dev_priv->display.funcs.audio->audio_codec_disable(encoder, + old_crtc_state, + old_conn_state); - mutex_lock(&dev_priv->audio.mutex); + mutex_lock(&dev_priv->display.audio.mutex); encoder->audio_connector = NULL; - dev_priv->audio.encoder_map[pipe] = NULL; - mutex_unlock(&dev_priv->audio.mutex); + dev_priv->display.audio.encoder_map[pipe] = NULL; + mutex_unlock(&dev_priv->display.audio.mutex); if (acomp && acomp->base.audio_ops && acomp->base.audio_ops->pin_eld_notify) { @@ -935,13 +935,13 @@ static const struct intel_audio_funcs hsw_audio_funcs = { void intel_audio_hooks_init(struct drm_i915_private *dev_priv) { if (IS_G4X(dev_priv)) { - dev_priv->audio.funcs = &g4x_audio_funcs; + dev_priv->display.funcs.audio = &g4x_audio_funcs; } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { - dev_priv->audio.funcs = &ilk_audio_funcs; + dev_priv->display.funcs.audio = &ilk_audio_funcs; } else if (IS_HASWELL(dev_priv) || DISPLAY_VER(dev_priv) >= 8) { - dev_priv->audio.funcs = &hsw_audio_funcs; + dev_priv->display.funcs.audio = &hsw_audio_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->audio.funcs = &ilk_audio_funcs; + dev_priv->display.funcs.audio = &ilk_audio_funcs; } } @@ -971,7 +971,7 @@ void intel_audio_cdclk_change_post(struct drm_i915_private *i915) struct aud_ts_cdclk_m_n aud_ts; if (DISPLAY_VER(i915) >= 13) { - get_aud_ts_cdclk_m_n(i915->cdclk.hw.ref, i915->cdclk.hw.cdclk, &aud_ts); + get_aud_ts_cdclk_m_n(i915->display.cdclk.hw.ref, i915->display.cdclk.hw.cdclk, &aud_ts); intel_de_write(i915, AUD_TS_CDCLK_N, aud_ts.n); intel_de_write(i915, AUD_TS_CDCLK_M, aud_ts.m | AUD_TS_CDCLK_M_EN); @@ -1046,13 +1046,13 @@ static unsigned long i915_audio_component_get_power(struct device *kdev) ret = intel_display_power_get(dev_priv, POWER_DOMAIN_AUDIO_PLAYBACK); - if (dev_priv->audio.power_refcount++ == 0) { + if (dev_priv->display.audio.power_refcount++ == 0) { if (DISPLAY_VER(dev_priv) >= 9) { intel_de_write(dev_priv, AUD_FREQ_CNTRL, - dev_priv->audio.freq_cntrl); + dev_priv->display.audio.freq_cntrl); drm_dbg_kms(&dev_priv->drm, "restored AUD_FREQ_CNTRL to 0x%x\n", - dev_priv->audio.freq_cntrl); + dev_priv->display.audio.freq_cntrl); } /* Force CDCLK to 2*BCLK as long as we need audio powered. */ @@ -1073,7 +1073,7 @@ static void i915_audio_component_put_power(struct device *kdev, struct drm_i915_private *dev_priv = kdev_to_i915(kdev); /* Stop forcing CDCLK to 2*BCLK if no need for audio to be powered. */ - if (--dev_priv->audio.power_refcount == 0) + if (--dev_priv->display.audio.power_refcount == 0) if (IS_GEMINILAKE(dev_priv)) glk_force_audio_cdclk(dev_priv, false); @@ -1119,7 +1119,7 @@ static int i915_audio_component_get_cdclk_freq(struct device *kdev) if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_DDI(dev_priv))) return -ENODEV; - return dev_priv->cdclk.hw.cdclk; + return dev_priv->display.cdclk.hw.cdclk; } /* @@ -1140,10 +1140,10 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, /* MST */ if (pipe >= 0) { if (drm_WARN_ON(&dev_priv->drm, - pipe >= ARRAY_SIZE(dev_priv->audio.encoder_map))) + pipe >= ARRAY_SIZE(dev_priv->display.audio.encoder_map))) return NULL; - encoder = dev_priv->audio.encoder_map[pipe]; + encoder = dev_priv->display.audio.encoder_map[pipe]; /* * when bootup, audio driver may not know it is * MST or not. So it will poll all the port & pipe @@ -1159,7 +1159,7 @@ static struct intel_encoder *get_saved_enc(struct drm_i915_private *dev_priv, return NULL; for_each_pipe(dev_priv, pipe) { - encoder = dev_priv->audio.encoder_map[pipe]; + encoder = dev_priv->display.audio.encoder_map[pipe]; if (encoder == NULL) continue; @@ -1177,7 +1177,7 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, int pipe, int rate) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); - struct i915_audio_component *acomp = dev_priv->audio.component; + struct i915_audio_component *acomp = dev_priv->display.audio.component; struct intel_encoder *encoder; struct intel_crtc *crtc; unsigned long cookie; @@ -1187,7 +1187,7 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, return 0; cookie = i915_audio_component_get_power(kdev); - mutex_lock(&dev_priv->audio.mutex); + mutex_lock(&dev_priv->display.audio.mutex); /* 1. get the pipe */ encoder = get_saved_enc(dev_priv, port, pipe); @@ -1206,7 +1206,7 @@ static int i915_audio_component_sync_audio_rate(struct device *kdev, int port, hsw_audio_config_update(encoder, crtc->config); unlock: - mutex_unlock(&dev_priv->audio.mutex); + mutex_unlock(&dev_priv->display.audio.mutex); i915_audio_component_put_power(kdev, cookie); return err; } @@ -1220,13 +1220,13 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, const u8 *eld; int ret = -EINVAL; - mutex_lock(&dev_priv->audio.mutex); + mutex_lock(&dev_priv->display.audio.mutex); intel_encoder = get_saved_enc(dev_priv, port, pipe); if (!intel_encoder) { drm_dbg_kms(&dev_priv->drm, "Not valid for port %c\n", port_name(port)); - mutex_unlock(&dev_priv->audio.mutex); + mutex_unlock(&dev_priv->display.audio.mutex); return ret; } @@ -1238,7 +1238,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port, memcpy(buf, eld, min(max_bytes, ret)); } - mutex_unlock(&dev_priv->audio.mutex); + mutex_unlock(&dev_priv->display.audio.mutex); return ret; } @@ -1273,7 +1273,7 @@ static int i915_audio_component_bind(struct device *i915_kdev, BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS); for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++) acomp->aud_sample_rate[i] = 0; - dev_priv->audio.component = acomp; + dev_priv->display.audio.component = acomp; drm_modeset_unlock_all(&dev_priv->drm); return 0; @@ -1288,14 +1288,14 @@ static void i915_audio_component_unbind(struct device *i915_kdev, drm_modeset_lock_all(&dev_priv->drm); acomp->base.ops = NULL; acomp->base.dev = NULL; - dev_priv->audio.component = NULL; + dev_priv->display.audio.component = NULL; drm_modeset_unlock_all(&dev_priv->drm); device_link_remove(hda_kdev, i915_kdev); - if (dev_priv->audio.power_refcount) + if (dev_priv->display.audio.power_refcount) drm_err(&dev_priv->drm, "audio power refcount %d after unbind\n", - dev_priv->audio.power_refcount); + dev_priv->display.audio.power_refcount); } static const struct component_ops i915_audio_component_bind_ops = { @@ -1359,13 +1359,13 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) drm_dbg_kms(&dev_priv->drm, "use AUD_FREQ_CNTRL of 0x%x (init value 0x%x)\n", aud_freq, aud_freq_init); - dev_priv->audio.freq_cntrl = aud_freq; + dev_priv->display.audio.freq_cntrl = aud_freq; } /* init with current cdclk */ intel_audio_cdclk_change_post(dev_priv); - dev_priv->audio.component_registered = true; + dev_priv->display.audio.component_registered = true; } /** @@ -1377,11 +1377,11 @@ static void i915_audio_component_init(struct drm_i915_private *dev_priv) */ static void i915_audio_component_cleanup(struct drm_i915_private *dev_priv) { - if (!dev_priv->audio.component_registered) + if (!dev_priv->display.audio.component_registered) return; component_del(dev_priv->drm.dev, &i915_audio_component_bind_ops); - dev_priv->audio.component_registered = false; + dev_priv->display.audio.component_registered = false; } /** @@ -1403,7 +1403,7 @@ void intel_audio_init(struct drm_i915_private *dev_priv) */ void intel_audio_deinit(struct drm_i915_private *dev_priv) { - if ((dev_priv)->audio.lpe.platdev != NULL) + if (dev_priv->display.audio.lpe.platdev != NULL) intel_lpe_audio_teardown(dev_priv); else i915_audio_component_cleanup(dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c index 84639e9df5c9..beba39a38c87 100644 --- a/drivers/gpu/drm/i915/display/intel_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_backlight.c @@ -11,6 +11,7 @@ #include <acpi/video.h> #include "intel_backlight.h" +#include "intel_backlight_regs.h" #include "intel_connector.h" #include "intel_de.h" #include "intel_display_types.h" @@ -18,6 +19,8 @@ #include "intel_dsi_dcs_backlight.h" #include "intel_panel.h" #include "intel_pci_config.h" +#include "intel_pps.h" +#include "intel_quirks.h" /** * scale - scale values from one range to another @@ -88,7 +91,7 @@ u32 intel_backlight_invert_pwm_level(struct intel_connector *connector, u32 val) return val; if (dev_priv->params.invert_brightness > 0 || - dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS) { + intel_has_quirk(dev_priv, QUIRK_INVERT_BRIGHTNESS)) { return panel->backlight.pwm_level_max - val + panel->backlight.pwm_level_min; } @@ -128,7 +131,7 @@ u32 intel_backlight_level_from_pwm(struct intel_connector *connector, u32 val) panel->backlight.max == 0 || panel->backlight.pwm_level_max == 0); if (dev_priv->params.invert_brightness > 0 || - (dev_priv->params.invert_brightness == 0 && dev_priv->quirks & QUIRK_INVERT_BRIGHTNESS)) + (dev_priv->params.invert_brightness == 0 && intel_has_quirk(dev_priv, QUIRK_INVERT_BRIGHTNESS))) val = panel->backlight.pwm_level_max - (val - panel->backlight.pwm_level_min); return scale(val, panel->backlight.pwm_level_min, panel->backlight.pwm_level_max, @@ -305,7 +308,7 @@ void intel_backlight_set_acpi(const struct drm_connector_state *conn_state, if (!panel->backlight.present || !conn_state->crtc) return; - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); drm_WARN_ON(&dev_priv->drm, panel->backlight.max == 0); @@ -321,7 +324,7 @@ void intel_backlight_set_acpi(const struct drm_connector_state *conn_state, if (panel->backlight.enabled) intel_panel_actually_set_backlight(conn_state, hw_level); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); } static void lpt_disable_backlight(const struct drm_connector_state *old_conn_state, u32 level) @@ -465,14 +468,14 @@ void intel_backlight_disable(const struct drm_connector_state *old_conn_state) return; } - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); if (panel->backlight.device) panel->backlight.device->props.power = FB_BLANK_POWERDOWN; panel->backlight.enabled = false; panel->backlight.funcs->disable(old_conn_state, 0); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); } static void lpt_enable_backlight(const struct intel_crtc_state *crtc_state, @@ -815,11 +818,11 @@ void intel_backlight_enable(const struct intel_crtc_state *crtc_state, drm_dbg_kms(&dev_priv->drm, "pipe %c\n", pipe_name(pipe)); - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); __intel_backlight_enable(crtc_state, conn_state); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); } #if IS_ENABLED(CONFIG_BACKLIGHT_CLASS_DEVICE) @@ -829,12 +832,12 @@ static u32 intel_panel_get_backlight(struct intel_connector *connector) struct intel_panel *panel = &connector->panel; u32 val = 0; - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); if (panel->backlight.enabled) val = panel->backlight.funcs->get(connector, intel_connector_get_pipe(connector)); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); drm_dbg_kms(&dev_priv->drm, "get backlight PWM = %d\n", val); return val; @@ -862,7 +865,7 @@ static void intel_panel_set_backlight(const struct drm_connector_state *conn_sta if (!panel->backlight.present) return; - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); drm_WARN_ON(&dev_priv->drm, panel->backlight.max == 0); @@ -872,7 +875,7 @@ static void intel_panel_set_backlight(const struct drm_connector_state *conn_sta if (panel->backlight.enabled) intel_panel_actually_set_backlight(conn_state, hw_level); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); } static int intel_backlight_device_update_status(struct backlight_device *bd) @@ -978,26 +981,24 @@ int intel_backlight_device_register(struct intel_connector *connector) if (!name) return -ENOMEM; - bd = backlight_device_register(name, connector->base.kdev, connector, - &intel_backlight_device_ops, &props); - - /* - * Using the same name independent of the drm device or connector - * prevents registration of multiple backlight devices in the - * driver. However, we need to use the default name for backward - * compatibility. Use unique names for subsequent backlight devices as a - * fallback when the default name already exists. - */ - if (IS_ERR(bd) && PTR_ERR(bd) == -EEXIST) { + bd = backlight_device_get_by_name(name); + if (bd) { + put_device(&bd->dev); + /* + * Using the same name independent of the drm device or connector + * prevents registration of multiple backlight devices in the + * driver. However, we need to use the default name for backward + * compatibility. Use unique names for subsequent backlight devices as a + * fallback when the default name already exists. + */ kfree(name); name = kasprintf(GFP_KERNEL, "card%d-%s-backlight", i915->drm.primary->index, connector->base.name); if (!name) return -ENOMEM; - - bd = backlight_device_register(name, connector->base.kdev, connector, - &intel_backlight_device_ops, &props); } + bd = backlight_device_register(name, connector->base.kdev, connector, + &intel_backlight_device_ops, &props); if (IS_ERR(bd)) { drm_err(&i915->drm, @@ -1120,7 +1121,7 @@ static u32 i9xx_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) if (IS_PINEVIEW(dev_priv)) clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq); else - clock = KHz(dev_priv->cdclk.hw.cdclk); + clock = KHz(dev_priv->display.cdclk.hw.cdclk); return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * 32); } @@ -1138,7 +1139,7 @@ static u32 i965_hz_to_pwm(struct intel_connector *connector, u32 pwm_freq_hz) if (IS_G4X(dev_priv)) clock = KHz(RUNTIME_INFO(dev_priv)->rawclk_freq); else - clock = KHz(dev_priv->cdclk.hw.cdclk); + clock = KHz(dev_priv->display.cdclk.hw.cdclk); return DIV_ROUND_CLOSEST(clock, pwm_freq_hz * 128); } @@ -1598,11 +1599,11 @@ void intel_backlight_update(struct intel_atomic_state *state, if (!panel->backlight.present) return; - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); if (!panel->backlight.enabled) __intel_backlight_enable(crtc_state, conn_state); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); } int intel_backlight_setup(struct intel_connector *connector, enum pipe pipe) @@ -1612,7 +1613,7 @@ int intel_backlight_setup(struct intel_connector *connector, enum pipe pipe) int ret; if (!connector->panel.vbt.backlight.present) { - if (dev_priv->quirks & QUIRK_BACKLIGHT_PRESENT) { + if (intel_has_quirk(dev_priv, QUIRK_BACKLIGHT_PRESENT)) { drm_dbg_kms(&dev_priv->drm, "no backlight present per VBT, but present per quirk\n"); } else { @@ -1627,9 +1628,9 @@ int intel_backlight_setup(struct intel_connector *connector, enum pipe pipe) return -ENODEV; /* set level and max in panel struct */ - mutex_lock(&dev_priv->backlight_lock); + mutex_lock(&dev_priv->display.backlight.lock); ret = panel->backlight.funcs->setup(connector, pipe); - mutex_unlock(&dev_priv->backlight_lock); + mutex_unlock(&dev_priv->display.backlight.lock); if (ret) { drm_dbg_kms(&dev_priv->drm, @@ -1780,9 +1781,13 @@ void intel_backlight_init_funcs(struct intel_panel *panel) panel->backlight.pwm_funcs = &i9xx_pwm_funcs; } - if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP && - intel_dp_aux_init_backlight_funcs(connector) == 0) - return; + if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP) { + if (intel_dp_aux_init_backlight_funcs(connector) == 0) + return; + + if (!intel_has_quirk(dev_priv, QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK)) + connector->panel.backlight.power = intel_pps_backlight_power; + } /* We're using a standard PWM backlight interface */ panel->backlight.funcs = &pwm_bl_funcs; diff --git a/drivers/gpu/drm/i915/display/intel_backlight_regs.h b/drivers/gpu/drm/i915/display/intel_backlight_regs.h new file mode 100644 index 000000000000..50c1210f6d5d --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_backlight_regs.h @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_BACKLIGHT_REGS_H__ +#define __INTEL_BACKLIGHT_REGS_H__ + +#include "i915_reg_defs.h" + +#define _VLV_BLC_PWM_CTL2_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61250) +#define _VLV_BLC_PWM_CTL2_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61350) +#define VLV_BLC_PWM_CTL2(pipe) _MMIO_PIPE(pipe, _VLV_BLC_PWM_CTL2_A, \ + _VLV_BLC_PWM_CTL2_B) + +#define _VLV_BLC_PWM_CTL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61254) +#define _VLV_BLC_PWM_CTL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61354) +#define VLV_BLC_PWM_CTL(pipe) _MMIO_PIPE(pipe, _VLV_BLC_PWM_CTL_A, \ + _VLV_BLC_PWM_CTL_B) + +#define _VLV_BLC_HIST_CTL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61260) +#define _VLV_BLC_HIST_CTL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61360) +#define VLV_BLC_HIST_CTL(pipe) _MMIO_PIPE(pipe, _VLV_BLC_HIST_CTL_A, \ + _VLV_BLC_HIST_CTL_B) + +/* Backlight control */ +#define BLC_PWM_CTL2 _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61250) /* 965+ only */ +#define BLM_PWM_ENABLE (1 << 31) +#define BLM_COMBINATION_MODE (1 << 30) /* gen4 only */ +#define BLM_PIPE_SELECT (1 << 29) +#define BLM_PIPE_SELECT_IVB (3 << 29) +#define BLM_PIPE_A (0 << 29) +#define BLM_PIPE_B (1 << 29) +#define BLM_PIPE_C (2 << 29) /* ivb + */ +#define BLM_TRANSCODER_A BLM_PIPE_A /* hsw */ +#define BLM_TRANSCODER_B BLM_PIPE_B +#define BLM_TRANSCODER_C BLM_PIPE_C +#define BLM_TRANSCODER_EDP (3 << 29) +#define BLM_PIPE(pipe) ((pipe) << 29) +#define BLM_POLARITY_I965 (1 << 28) /* gen4 only */ +#define BLM_PHASE_IN_INTERUPT_STATUS (1 << 26) +#define BLM_PHASE_IN_ENABLE (1 << 25) +#define BLM_PHASE_IN_INTERUPT_ENABL (1 << 24) +#define BLM_PHASE_IN_TIME_BASE_SHIFT (16) +#define BLM_PHASE_IN_TIME_BASE_MASK (0xff << 16) +#define BLM_PHASE_IN_COUNT_SHIFT (8) +#define BLM_PHASE_IN_COUNT_MASK (0xff << 8) +#define BLM_PHASE_IN_INCR_SHIFT (0) +#define BLM_PHASE_IN_INCR_MASK (0xff << 0) +#define BLC_PWM_CTL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61254) +/* + * This is the most significant 15 bits of the number of backlight cycles in a + * complete cycle of the modulated backlight control. + * + * The actual value is this field multiplied by two. + */ +#define BACKLIGHT_MODULATION_FREQ_SHIFT (17) +#define BACKLIGHT_MODULATION_FREQ_MASK (0x7fff << 17) +#define BLM_LEGACY_MODE (1 << 16) /* gen2 only */ +/* + * This is the number of cycles out of the backlight modulation cycle for which + * the backlight is on. + * + * This field must be no greater than the number of cycles in the complete + * backlight modulation cycle. + */ +#define BACKLIGHT_DUTY_CYCLE_SHIFT (0) +#define BACKLIGHT_DUTY_CYCLE_MASK (0xffff) +#define BACKLIGHT_DUTY_CYCLE_MASK_PNV (0xfffe) +#define BLM_POLARITY_PNV (1 << 0) /* pnv only */ + +#define BLC_HIST_CTL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61260) +#define BLM_HISTOGRAM_ENABLE (1 << 31) + +/* New registers for PCH-split platforms. Safe where new bits show up, the + * register layout machtes with gen4 BLC_PWM_CTL[12]. */ +#define BLC_PWM_CPU_CTL2 _MMIO(0x48250) +#define BLC_PWM_CPU_CTL _MMIO(0x48254) + +#define HSW_BLC_PWM2_CTL _MMIO(0x48350) + +/* PCH CTL1 is totally different, all but the below bits are reserved. CTL2 is + * like the normal CTL from gen4 and earlier. Hooray for confusing naming. */ +#define BLC_PWM_PCH_CTL1 _MMIO(0xc8250) +#define BLM_PCH_PWM_ENABLE (1 << 31) +#define BLM_PCH_OVERRIDE_ENABLE (1 << 30) +#define BLM_PCH_POLARITY (1 << 29) +#define BLC_PWM_PCH_CTL2 _MMIO(0xc8254) + +/* BXT backlight register definition. */ +#define _BXT_BLC_PWM_CTL1 0xC8250 +#define BXT_BLC_PWM_ENABLE (1 << 31) +#define BXT_BLC_PWM_POLARITY (1 << 29) +#define _BXT_BLC_PWM_FREQ1 0xC8254 +#define _BXT_BLC_PWM_DUTY1 0xC8258 + +#define _BXT_BLC_PWM_CTL2 0xC8350 +#define _BXT_BLC_PWM_FREQ2 0xC8354 +#define _BXT_BLC_PWM_DUTY2 0xC8358 + +#define BXT_BLC_PWM_CTL(controller) _MMIO_PIPE(controller, \ + _BXT_BLC_PWM_CTL1, _BXT_BLC_PWM_CTL2) +#define BXT_BLC_PWM_FREQ(controller) _MMIO_PIPE(controller, \ + _BXT_BLC_PWM_FREQ1, _BXT_BLC_PWM_FREQ2) +#define BXT_BLC_PWM_DUTY(controller) _MMIO_PIPE(controller, \ + _BXT_BLC_PWM_DUTY1, _BXT_BLC_PWM_DUTY2) + +/* Utility pin */ +#define UTIL_PIN_CTL _MMIO(0x48400) +#define UTIL_PIN_ENABLE (1 << 31) +#define UTIL_PIN_PIPE_MASK (3 << 29) +#define UTIL_PIN_PIPE(x) ((x) << 29) +#define UTIL_PIN_MODE_MASK (0xf << 24) +#define UTIL_PIN_MODE_DATA (0 << 24) +#define UTIL_PIN_MODE_PWM (1 << 24) +#define UTIL_PIN_MODE_VBLANK (4 << 24) +#define UTIL_PIN_MODE_VSYNC (5 << 24) +#define UTIL_PIN_MODE_EYE_LEVEL (8 << 24) +#define UTIL_PIN_OUTPUT_DATA (1 << 23) +#define UTIL_PIN_POLARITY (1 << 22) +#define UTIL_PIN_DIRECTION_INPUT (1 << 19) +#define UTIL_PIN_INPUT_DATA (1 << 16) + +#endif /* __INTEL_BACKLIGHT_REGS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c index 51dde5bfd956..28bdb936cd1f 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.c +++ b/drivers/gpu/drm/i915/display/intel_bios.c @@ -135,18 +135,6 @@ static u32 raw_block_offset(const void *bdb, enum bdb_block_id section_id) return block - bdb; } -/* size of the block excluding the header */ -static u32 raw_block_size(const void *bdb, enum bdb_block_id section_id) -{ - const void *block; - - block = find_raw_section(bdb, section_id); - if (!block) - return 0; - - return get_blocksize(block); -} - struct bdb_block_entry { struct list_head node; enum bdb_block_id section_id; @@ -159,7 +147,7 @@ find_section(struct drm_i915_private *i915, { struct bdb_block_entry *entry; - list_for_each_entry(entry, &i915->vbt.bdb_blocks, node) { + list_for_each_entry(entry, &i915->display.vbt.bdb_blocks, node) { if (entry->section_id == section_id) return entry->data + 3; } @@ -231,9 +219,14 @@ static bool validate_lfp_data_ptrs(const void *bdb, { int fp_timing_size, dvo_timing_size, panel_pnp_id_size, panel_name_size; int data_block_size, lfp_data_size; + const void *data_block; int i; - data_block_size = raw_block_size(bdb, BDB_LVDS_LFP_DATA); + data_block = find_raw_section(bdb, BDB_LVDS_LFP_DATA); + if (!data_block) + return false; + + data_block_size = get_blocksize(data_block); if (data_block_size == 0) return false; @@ -261,21 +254,6 @@ static bool validate_lfp_data_ptrs(const void *bdb, if (16 * lfp_data_size > data_block_size) return false; - /* - * Except for vlv/chv machines all real VBTs seem to have 6 - * unaccounted bytes in the fp_timing table. And it doesn't - * appear to be a really intentional hole as the fp_timing - * 0xffff terminator is always within those 6 missing bytes. - */ - if (fp_timing_size + dvo_timing_size + panel_pnp_id_size != lfp_data_size && - fp_timing_size + 6 + dvo_timing_size + panel_pnp_id_size != lfp_data_size) - return false; - - if (ptrs->ptr[0].fp_timing.offset + fp_timing_size > ptrs->ptr[0].dvo_timing.offset || - ptrs->ptr[0].dvo_timing.offset + dvo_timing_size != ptrs->ptr[0].panel_pnp_id.offset || - ptrs->ptr[0].panel_pnp_id.offset + panel_pnp_id_size != lfp_data_size) - return false; - /* make sure the table entries have uniform size */ for (i = 1; i < 16; i++) { if (ptrs->ptr[i].fp_timing.table_size != fp_timing_size || @@ -289,6 +267,23 @@ static bool validate_lfp_data_ptrs(const void *bdb, return false; } + /* + * Except for vlv/chv machines all real VBTs seem to have 6 + * unaccounted bytes in the fp_timing table. And it doesn't + * appear to be a really intentional hole as the fp_timing + * 0xffff terminator is always within those 6 missing bytes. + */ + if (fp_timing_size + 6 + dvo_timing_size + panel_pnp_id_size == lfp_data_size) + fp_timing_size += 6; + + if (fp_timing_size + dvo_timing_size + panel_pnp_id_size != lfp_data_size) + return false; + + if (ptrs->ptr[0].fp_timing.offset + fp_timing_size != ptrs->ptr[0].dvo_timing.offset || + ptrs->ptr[0].dvo_timing.offset + dvo_timing_size != ptrs->ptr[0].panel_pnp_id.offset || + ptrs->ptr[0].panel_pnp_id.offset + panel_pnp_id_size != lfp_data_size) + return false; + /* make sure the tables fit inside the data block */ for (i = 0; i < 16; i++) { if (ptrs->ptr[i].fp_timing.offset + fp_timing_size > data_block_size || @@ -300,6 +295,15 @@ static bool validate_lfp_data_ptrs(const void *bdb, if (ptrs->panel_name.offset + 16 * panel_name_size > data_block_size) return false; + /* make sure fp_timing terminators are present at expected locations */ + for (i = 0; i < 16; i++) { + const u16 *t = data_block + ptrs->ptr[i].fp_timing.offset + + fp_timing_size - 2; + + if (*t != 0xffff) + return false; + } + return true; } @@ -333,18 +337,6 @@ static bool fixup_lfp_data_ptrs(const void *bdb, void *ptrs_block) return validate_lfp_data_ptrs(bdb, ptrs); } -static const void *find_fp_timing_terminator(const u8 *data, int size) -{ - int i; - - for (i = 0; i < size - 1; i++) { - if (data[i] == 0xff && data[i+1] == 0xff) - return &data[i]; - } - - return NULL; -} - static int make_lfp_data_ptr(struct lvds_lfp_data_ptr_table *table, int table_size, int total_size) { @@ -368,11 +360,22 @@ static void next_lfp_data_ptr(struct lvds_lfp_data_ptr_table *next, static void *generate_lfp_data_ptrs(struct drm_i915_private *i915, const void *bdb) { - int i, size, table_size, block_size, offset; - const void *t0, *t1, *block; + int i, size, table_size, block_size, offset, fp_timing_size; struct bdb_lvds_lfp_data_ptrs *ptrs; + const void *block; void *ptrs_block; + /* + * The hardcoded fp_timing_size is only valid for + * modernish VBTs. All older VBTs definitely should + * include block 41 and thus we don't need to + * generate one. + */ + if (i915->display.vbt.version < 155) + return NULL; + + fp_timing_size = 38; + block = find_raw_section(bdb, BDB_LVDS_LFP_DATA); if (!block) return NULL; @@ -381,17 +384,8 @@ static void *generate_lfp_data_ptrs(struct drm_i915_private *i915, block_size = get_blocksize(block); - size = block_size; - t0 = find_fp_timing_terminator(block, size); - if (!t0) - return NULL; - - size -= t0 - block - 2; - t1 = find_fp_timing_terminator(t0 + 2, size); - if (!t1) - return NULL; - - size = t1 - t0; + size = fp_timing_size + sizeof(struct lvds_dvo_timing) + + sizeof(struct lvds_pnp_id); if (size * 16 > block_size) return NULL; @@ -409,7 +403,7 @@ static void *generate_lfp_data_ptrs(struct drm_i915_private *i915, table_size = sizeof(struct lvds_dvo_timing); size = make_lfp_data_ptr(&ptrs->ptr[0].dvo_timing, table_size, size); - table_size = t0 - block + 2; + table_size = fp_timing_size; size = make_lfp_data_ptr(&ptrs->ptr[0].fp_timing, table_size, size); if (ptrs->ptr[0].fp_timing.table_size) @@ -424,14 +418,14 @@ static void *generate_lfp_data_ptrs(struct drm_i915_private *i915, return NULL; } - size = t1 - t0; + size = fp_timing_size + sizeof(struct lvds_dvo_timing) + + sizeof(struct lvds_pnp_id); for (i = 1; i < 16; i++) { next_lfp_data_ptr(&ptrs->ptr[i].fp_timing, &ptrs->ptr[i-1].fp_timing, size); next_lfp_data_ptr(&ptrs->ptr[i].dvo_timing, &ptrs->ptr[i-1].dvo_timing, size); next_lfp_data_ptr(&ptrs->ptr[i].panel_pnp_id, &ptrs->ptr[i-1].panel_pnp_id, size); } - size = t1 - t0; table_size = sizeof(struct lvds_lfp_panel_name); if (16 * (size + table_size) <= block_size) { @@ -479,6 +473,13 @@ init_bdb_block(struct drm_i915_private *i915, block_size = get_blocksize(block); + /* + * Version number and new block size are considered + * part of the header for MIPI sequenece block v3+. + */ + if (section_id == BDB_MIPI_SEQUENCE && *(const u8 *)block >= 3) + block_size += 5; + entry = kzalloc(struct_size(entry, data, max(min_size, block_size) + 3), GFP_KERNEL); if (!entry) { @@ -501,7 +502,7 @@ init_bdb_block(struct drm_i915_private *i915, return; } - list_add_tail(&entry->node, &i915->vbt.bdb_blocks); + list_add_tail(&entry->node, &i915->display.vbt.bdb_blocks); } static void init_bdb_blocks(struct drm_i915_private *i915, @@ -604,6 +605,19 @@ get_lfp_data_tail(const struct bdb_lvds_lfp_data *data, return NULL; } +static void dump_pnp_id(struct drm_i915_private *i915, + const struct lvds_pnp_id *pnp_id, + const char *name) +{ + u16 mfg_name = be16_to_cpu((__force __be16)pnp_id->mfg_name); + char vend[4]; + + drm_dbg_kms(&i915->drm, "%s PNPID mfg: %s (0x%x), prod: %u, serial: %u, week: %d, year: %d\n", + name, drm_edid_decode_mfg_id(mfg_name, vend), + pnp_id->mfg_name, pnp_id->product_code, pnp_id->serial, + pnp_id->mfg_week, pnp_id->mfg_year + 1990); +} + static int opregion_get_panel_type(struct drm_i915_private *i915, const struct intel_bios_encoder_data *devdata, const struct edid *edid) @@ -655,6 +669,8 @@ static int pnpid_get_panel_type(struct drm_i915_private *i915, edid_id_nodate.mfg_week = 0; edid_id_nodate.mfg_year = 0; + dump_pnp_id(i915, edid_id, "EDID"); + ptrs = find_section(i915, BDB_LVDS_LFP_DATA_PTRS); if (!ptrs) return -1; @@ -861,6 +877,7 @@ parse_lfp_data(struct drm_i915_private *i915, const struct bdb_lvds_lfp_data *data; const struct bdb_lvds_lfp_data_tail *tail; const struct bdb_lvds_lfp_data_ptrs *ptrs; + const struct lvds_pnp_id *pnp_id; int panel_type = panel->vbt.panel_type; ptrs = find_section(i915, BDB_LVDS_LFP_DATA_PTRS); @@ -874,11 +891,18 @@ parse_lfp_data(struct drm_i915_private *i915, if (!panel->vbt.lfp_lvds_vbt_mode) parse_lfp_panel_dtd(i915, panel, data, ptrs); + pnp_id = get_lvds_pnp_id(data, ptrs, panel_type); + dump_pnp_id(i915, pnp_id, "Panel"); + tail = get_lfp_data_tail(data, ptrs); if (!tail) return; - if (i915->vbt.version >= 188) { + drm_dbg_kms(&i915->drm, "Panel name: %.*s\n", + (int)sizeof(tail->panel_name[0].name), + tail->panel_name[panel_type].name); + + if (i915->display.vbt.version >= 188) { panel->vbt.seamless_drrs_min_refresh_rate = tail->seamless_drrs_min_refresh_rate[panel_type]; drm_dbg_kms(&i915->drm, @@ -904,7 +928,7 @@ parse_generic_dtd(struct drm_i915_private *i915, * first on VBT >= 229, but still fall back to trying the old LFP * block if that fails. */ - if (i915->vbt.version < 229) + if (i915->display.vbt.version < 229) return; generic_dtd = find_section(i915, BDB_GENERIC_DTD); @@ -1008,12 +1032,12 @@ parse_lfp_backlight(struct drm_i915_private *i915, } panel->vbt.backlight.type = INTEL_BACKLIGHT_DISPLAY_DDI; - if (i915->vbt.version >= 191) { + if (i915->display.vbt.version >= 191) { size_t exp_size; - if (i915->vbt.version >= 236) + if (i915->display.vbt.version >= 236) exp_size = sizeof(struct bdb_lfp_backlight_data); - else if (i915->vbt.version >= 234) + else if (i915->display.vbt.version >= 234) exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_234; else exp_size = EXP_BDB_LFP_BL_DATA_SIZE_REV_191; @@ -1030,14 +1054,14 @@ parse_lfp_backlight(struct drm_i915_private *i915, panel->vbt.backlight.pwm_freq_hz = entry->pwm_freq_hz; panel->vbt.backlight.active_low_pwm = entry->active_low_pwm; - if (i915->vbt.version >= 234) { + if (i915->display.vbt.version >= 234) { u16 min_level; bool scale; level = backlight_data->brightness_level[panel_type].level; min_level = backlight_data->brightness_min_level[panel_type].level; - if (i915->vbt.version >= 236) + if (i915->display.vbt.version >= 236) scale = backlight_data->brightness_precision_bits[panel_type] == 16; else scale = level > 255; @@ -1134,37 +1158,37 @@ parse_general_features(struct drm_i915_private *i915) if (!general) return; - i915->vbt.int_tv_support = general->int_tv_support; + i915->display.vbt.int_tv_support = general->int_tv_support; /* int_crt_support can't be trusted on earlier platforms */ - if (i915->vbt.version >= 155 && + if (i915->display.vbt.version >= 155 && (HAS_DDI(i915) || IS_VALLEYVIEW(i915))) - i915->vbt.int_crt_support = general->int_crt_support; - i915->vbt.lvds_use_ssc = general->enable_ssc; - i915->vbt.lvds_ssc_freq = + i915->display.vbt.int_crt_support = general->int_crt_support; + i915->display.vbt.lvds_use_ssc = general->enable_ssc; + i915->display.vbt.lvds_ssc_freq = intel_bios_ssc_frequency(i915, general->ssc_freq); - i915->vbt.display_clock_mode = general->display_clock_mode; - i915->vbt.fdi_rx_polarity_inverted = general->fdi_rx_polarity_inverted; - if (i915->vbt.version >= 181) { - i915->vbt.orientation = general->rotate_180 ? + i915->display.vbt.display_clock_mode = general->display_clock_mode; + i915->display.vbt.fdi_rx_polarity_inverted = general->fdi_rx_polarity_inverted; + if (i915->display.vbt.version >= 181) { + i915->display.vbt.orientation = general->rotate_180 ? DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP : DRM_MODE_PANEL_ORIENTATION_NORMAL; } else { - i915->vbt.orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN; + i915->display.vbt.orientation = DRM_MODE_PANEL_ORIENTATION_UNKNOWN; } - if (i915->vbt.version >= 249 && general->afc_startup_config) { - i915->vbt.override_afc_startup = true; - i915->vbt.override_afc_startup_val = general->afc_startup_config == 0x1 ? 0x0 : 0x7; + if (i915->display.vbt.version >= 249 && general->afc_startup_config) { + i915->display.vbt.override_afc_startup = true; + i915->display.vbt.override_afc_startup_val = general->afc_startup_config == 0x1 ? 0x0 : 0x7; } drm_dbg_kms(&i915->drm, "BDB_GENERAL_FEATURES int_tv_support %d int_crt_support %d lvds_use_ssc %d lvds_ssc_freq %d display_clock_mode %d fdi_rx_polarity_inverted %d\n", - i915->vbt.int_tv_support, - i915->vbt.int_crt_support, - i915->vbt.lvds_use_ssc, - i915->vbt.lvds_ssc_freq, - i915->vbt.display_clock_mode, - i915->vbt.fdi_rx_polarity_inverted); + i915->display.vbt.int_tv_support, + i915->display.vbt.int_crt_support, + i915->display.vbt.lvds_use_ssc, + i915->display.vbt.lvds_ssc_freq, + i915->display.vbt.display_clock_mode, + i915->display.vbt.fdi_rx_polarity_inverted); } static const struct child_device_config * @@ -1190,7 +1214,7 @@ parse_sdvo_device_mapping(struct drm_i915_private *i915) return; } - list_for_each_entry(devdata, &i915->vbt.display_devices, node) { + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) { child = &devdata->child; if (child->slave_addr != SLAVE_ADDR1 && @@ -1214,7 +1238,7 @@ parse_sdvo_device_mapping(struct drm_i915_private *i915) child->slave_addr, (child->dvo_port == DEVICE_PORT_DVOB) ? "SDVOB" : "SDVOC"); - mapping = &i915->vbt.sdvo_mappings[child->dvo_port - 1]; + mapping = &i915->display.vbt.sdvo_mappings[child->dvo_port - 1]; if (!mapping->initialized) { mapping->dvo_port = child->dvo_port; mapping->slave_addr = child->slave_addr; @@ -1265,7 +1289,7 @@ parse_driver_features(struct drm_i915_private *i915) * interpretation, but real world VBTs seem to. */ if (driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS) - i915->vbt.int_lvds_support = 0; + i915->display.vbt.int_lvds_support = 0; } else { /* * FIXME it's not clear which BDB version has the LVDS config @@ -1278,10 +1302,10 @@ parse_driver_features(struct drm_i915_private *i915) * in the wild with the bits correctly populated. Version * 108 (on i85x) does not have the bits correctly populated. */ - if (i915->vbt.version >= 134 && + if (i915->display.vbt.version >= 134 && driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS && driver->lvds_config != BDB_DRIVER_FEATURE_INT_SDVO_LVDS) - i915->vbt.int_lvds_support = 0; + i915->display.vbt.int_lvds_support = 0; } } @@ -1295,7 +1319,7 @@ parse_panel_driver_features(struct drm_i915_private *i915, if (!driver) return; - if (i915->vbt.version < 228) { + if (i915->display.vbt.version < 228) { drm_dbg_kms(&i915->drm, "DRRS State Enabled:%d\n", driver->drrs_enabled); /* @@ -1328,7 +1352,7 @@ parse_power_conservation_features(struct drm_i915_private *i915, panel->vbt.vrr = true; /* matches Windows behaviour */ - if (i915->vbt.version < 228) + if (i915->display.vbt.version < 228) return; power = find_section(i915, BDB_LFP_POWER); @@ -1354,10 +1378,10 @@ parse_power_conservation_features(struct drm_i915_private *i915, panel->vbt.drrs_type = DRRS_TYPE_NONE; } - if (i915->vbt.version >= 232) + if (i915->display.vbt.version >= 232) panel->vbt.edp.hobl = panel_bool(power->hobl, panel_type); - if (i915->vbt.version >= 233) + if (i915->display.vbt.version >= 233) panel->vbt.vrr = panel_bool(power->vrr_feature_enabled, panel_type); } @@ -1393,7 +1417,7 @@ parse_edp(struct drm_i915_private *i915, panel->vbt.edp.pps = *edp_pps; - if (i915->vbt.version >= 224) { + if (i915->display.vbt.version >= 224) { panel->vbt.edp.rate = edp->edp_fast_link_training_rate[panel_type] * 20; } else { @@ -1472,7 +1496,7 @@ parse_edp(struct drm_i915_private *i915, break; } - if (i915->vbt.version >= 173) { + if (i915->display.vbt.version >= 173) { u8 vswing; /* Don't read from VBT if module parameter has valid value*/ @@ -1488,7 +1512,7 @@ parse_edp(struct drm_i915_private *i915, panel->vbt.edp.drrs_msa_timing_delay = panel_bits(edp->sdrrs_msa_timing_delay, panel_type, 2); - if (i915->vbt.version >= 244) + if (i915->display.vbt.version >= 244) panel->vbt.edp.max_link_rate = edp->edp_max_port_link_rate[panel_type] * 20; } @@ -1520,7 +1544,7 @@ parse_psr(struct drm_i915_private *i915, * New psr options 0=500us, 1=100us, 2=2500us, 3=0us * Old decimal value is wake up time in multiples of 100 us. */ - if (i915->vbt.version >= 205 && + if (i915->display.vbt.version >= 205 && (DISPLAY_VER(i915) >= 9 && !IS_BROXTON(i915))) { switch (psr_table->tp1_wakeup_time) { case 0: @@ -1566,7 +1590,7 @@ parse_psr(struct drm_i915_private *i915, panel->vbt.psr.tp2_tp3_wakeup_time_us = psr_table->tp2_tp3_wakeup_time * 100; } - if (i915->vbt.version >= 226) { + if (i915->display.vbt.version >= 226) { u32 wakeup_time = psr->psr2_tp2_tp3_wakeup_time; wakeup_time = panel_bits(wakeup_time, panel_type, 2); @@ -1596,7 +1620,9 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915, struct intel_panel *panel, enum port port) { - if (!panel->vbt.dsi.config->dual_link || i915->vbt.version < 197) { + enum port port_bc = DISPLAY_VER(i915) >= 11 ? PORT_B : PORT_C; + + if (!panel->vbt.dsi.config->dual_link || i915->display.vbt.version < 197) { panel->vbt.dsi.bl_ports = BIT(port); if (panel->vbt.dsi.config->cabc_supported) panel->vbt.dsi.cabc_ports = BIT(port); @@ -1609,11 +1635,11 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915, panel->vbt.dsi.bl_ports = BIT(PORT_A); break; case DL_DCS_PORT_C: - panel->vbt.dsi.bl_ports = BIT(PORT_C); + panel->vbt.dsi.bl_ports = BIT(port_bc); break; default: case DL_DCS_PORT_A_AND_C: - panel->vbt.dsi.bl_ports = BIT(PORT_A) | BIT(PORT_C); + panel->vbt.dsi.bl_ports = BIT(PORT_A) | BIT(port_bc); break; } @@ -1625,12 +1651,12 @@ static void parse_dsi_backlight_ports(struct drm_i915_private *i915, panel->vbt.dsi.cabc_ports = BIT(PORT_A); break; case DL_DCS_PORT_C: - panel->vbt.dsi.cabc_ports = BIT(PORT_C); + panel->vbt.dsi.cabc_ports = BIT(port_bc); break; default: case DL_DCS_PORT_A_AND_C: panel->vbt.dsi.cabc_ports = - BIT(PORT_A) | BIT(PORT_C); + BIT(PORT_A) | BIT(port_bc); break; } } @@ -2051,7 +2077,7 @@ parse_compression_parameters(struct drm_i915_private *i915) u16 block_size; int index; - if (i915->vbt.version < 198) + if (i915->display.vbt.version < 198) return; params = find_section(i915, BDB_COMPRESSION_PARAMETERS); @@ -2071,7 +2097,7 @@ parse_compression_parameters(struct drm_i915_private *i915) } } - list_for_each_entry(devdata, &i915->vbt.display_devices, node) { + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) { child = &devdata->child; if (!child->compression_enable) @@ -2205,7 +2231,7 @@ static enum port get_port_by_ddc_pin(struct drm_i915_private *i915, u8 ddc_pin) return PORT_NONE; for_each_port(port) { - devdata = i915->vbt.ports[port]; + devdata = i915->display.vbt.ports[port]; if (devdata && ddc_pin == devdata->child.ddc_pin) return port; @@ -2254,7 +2280,7 @@ static void sanitize_ddc_pin(struct intel_bios_encoder_data *devdata, * there are real machines (eg. Asrock B250M-HDV) where VBT has both * port A and port E with the same AUX ch and we must pick port E :( */ - child = &i915->vbt.ports[p]->child; + child = &i915->display.vbt.ports[p]->child; child->device_type &= ~DEVICE_TYPE_TMDS_DVI_SIGNALING; child->device_type |= DEVICE_TYPE_NOT_HDMI_OUTPUT; @@ -2271,7 +2297,7 @@ static enum port get_port_by_aux_ch(struct drm_i915_private *i915, u8 aux_ch) return PORT_NONE; for_each_port(port) { - devdata = i915->vbt.ports[port]; + devdata = i915->display.vbt.ports[port]; if (devdata && aux_ch == devdata->child.aux_channel) return port; @@ -2306,7 +2332,7 @@ static void sanitize_aux_ch(struct intel_bios_encoder_data *devdata, * there are real machines (eg. Asrock B250M-HDV) where VBT has both * port A and port E with the same AUX ch and we must pick port E :( */ - child = &i915->vbt.ports[p]->child; + child = &i915->display.vbt.ports[p]->child; child->device_type &= ~DEVICE_TYPE_DISPLAYPORT_OUTPUT; child->aux_channel = 0; @@ -2418,7 +2444,7 @@ static enum port dvo_port_to_port(struct drm_i915_private *i915, [PORT_TC4] = { DVO_PORT_HDMII, DVO_PORT_DPI, -1 }, }; - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) return __dvo_port_to_port(ARRAY_SIZE(xelpd_port_mapping), ARRAY_SIZE(xelpd_port_mapping[0]), xelpd_port_mapping, @@ -2480,15 +2506,23 @@ static int parse_bdb_216_dp_max_link_rate(const int vbt_max_link_rate) static int _intel_bios_dp_max_link_rate(const struct intel_bios_encoder_data *devdata) { - if (!devdata || devdata->i915->vbt.version < 216) + if (!devdata || devdata->i915->display.vbt.version < 216) return 0; - if (devdata->i915->vbt.version >= 230) + if (devdata->i915->display.vbt.version >= 230) return parse_bdb_230_dp_max_link_rate(devdata->child.dp_max_link_rate); else return parse_bdb_216_dp_max_link_rate(devdata->child.dp_max_link_rate); } +static int _intel_bios_dp_max_lane_count(const struct intel_bios_encoder_data *devdata) +{ + if (!devdata || devdata->i915->display.vbt.version < 244) + return 0; + + return devdata->child.dp_max_lane_count + 1; +} + static void sanitize_device_type(struct intel_bios_encoder_data *devdata, enum port port) { @@ -2544,7 +2578,7 @@ intel_bios_encoder_supports_edp(const struct intel_bios_encoder_data *devdata) static int _intel_bios_hdmi_level_shift(const struct intel_bios_encoder_data *devdata) { - if (!devdata || devdata->i915->vbt.version < 158) + if (!devdata || devdata->i915->display.vbt.version < 158) return -1; return devdata->child.hdmi_level_shifter_value; @@ -2552,7 +2586,7 @@ static int _intel_bios_hdmi_level_shift(const struct intel_bios_encoder_data *de static int _intel_bios_max_tmds_clock(const struct intel_bios_encoder_data *devdata) { - if (!devdata || devdata->i915->vbt.version < 204) + if (!devdata || devdata->i915->display.vbt.version < 204) return 0; switch (devdata->child.hdmi_max_data_rate) { @@ -2661,7 +2695,7 @@ static void parse_ddi_port(struct intel_bios_encoder_data *devdata) return; } - if (i915->vbt.ports[port]) { + if (i915->display.vbt.ports[port]) { drm_dbg_kms(&i915->drm, "More than one child device for port %c in VBT, using the first.\n", port_name(port)); @@ -2676,7 +2710,7 @@ static void parse_ddi_port(struct intel_bios_encoder_data *devdata) if (intel_bios_encoder_supports_dp(devdata)) sanitize_aux_ch(devdata, port); - i915->vbt.ports[port] = devdata; + i915->display.vbt.ports[port] = devdata; } static bool has_ddi_port_info(struct drm_i915_private *i915) @@ -2692,12 +2726,12 @@ static void parse_ddi_ports(struct drm_i915_private *i915) if (!has_ddi_port_info(i915)) return; - list_for_each_entry(devdata, &i915->vbt.display_devices, node) + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) parse_ddi_port(devdata); for_each_port(port) { - if (i915->vbt.ports[port]) - print_ddi_port(i915->vbt.ports[port], port); + if (i915->display.vbt.ports[port]) + print_ddi_port(i915->display.vbt.ports[port], port); } } @@ -2730,33 +2764,33 @@ parse_general_definitions(struct drm_i915_private *i915) bus_pin = defs->crt_ddc_gmbus_pin; drm_dbg_kms(&i915->drm, "crt_ddc_bus_pin: %d\n", bus_pin); if (intel_gmbus_is_valid_pin(i915, bus_pin)) - i915->vbt.crt_ddc_pin = bus_pin; + i915->display.vbt.crt_ddc_pin = bus_pin; - if (i915->vbt.version < 106) { + if (i915->display.vbt.version < 106) { expected_size = 22; - } else if (i915->vbt.version < 111) { + } else if (i915->display.vbt.version < 111) { expected_size = 27; - } else if (i915->vbt.version < 195) { + } else if (i915->display.vbt.version < 195) { expected_size = LEGACY_CHILD_DEVICE_CONFIG_SIZE; - } else if (i915->vbt.version == 195) { + } else if (i915->display.vbt.version == 195) { expected_size = 37; - } else if (i915->vbt.version <= 215) { + } else if (i915->display.vbt.version <= 215) { expected_size = 38; - } else if (i915->vbt.version <= 237) { + } else if (i915->display.vbt.version <= 237) { expected_size = 39; } else { expected_size = sizeof(*child); BUILD_BUG_ON(sizeof(*child) < 39); drm_dbg(&i915->drm, "Expected child device config size for VBT version %u not known; assuming %u\n", - i915->vbt.version, expected_size); + i915->display.vbt.version, expected_size); } /* Flag an error for unexpected size, but continue anyway. */ if (defs->child_dev_size != expected_size) drm_err(&i915->drm, "Unexpected child device config size %u (expected %u for VBT version %u)\n", - defs->child_dev_size, expected_size, i915->vbt.version); + defs->child_dev_size, expected_size, i915->display.vbt.version); /* The legacy sized child device config is the minimum we need. */ if (defs->child_dev_size < LEGACY_CHILD_DEVICE_CONFIG_SIZE) { @@ -2792,10 +2826,10 @@ parse_general_definitions(struct drm_i915_private *i915) memcpy(&devdata->child, child, min_t(size_t, defs->child_dev_size, sizeof(*child))); - list_add_tail(&devdata->node, &i915->vbt.display_devices); + list_add_tail(&devdata->node, &i915->display.vbt.display_devices); } - if (list_empty(&i915->vbt.display_devices)) + if (list_empty(&i915->display.vbt.display_devices)) drm_dbg_kms(&i915->drm, "no child dev is parsed from VBT\n"); } @@ -2804,25 +2838,25 @@ parse_general_definitions(struct drm_i915_private *i915) static void init_vbt_defaults(struct drm_i915_private *i915) { - i915->vbt.crt_ddc_pin = GMBUS_PIN_VGADDC; + i915->display.vbt.crt_ddc_pin = GMBUS_PIN_VGADDC; /* general features */ - i915->vbt.int_tv_support = 1; - i915->vbt.int_crt_support = 1; + i915->display.vbt.int_tv_support = 1; + i915->display.vbt.int_crt_support = 1; /* driver features */ - i915->vbt.int_lvds_support = 1; + i915->display.vbt.int_lvds_support = 1; /* Default to using SSC */ - i915->vbt.lvds_use_ssc = 1; + i915->display.vbt.lvds_use_ssc = 1; /* * Core/SandyBridge/IvyBridge use alternative (120MHz) reference * clock for LVDS. */ - i915->vbt.lvds_ssc_freq = intel_bios_ssc_frequency(i915, - !HAS_PCH_SPLIT(i915)); + i915->display.vbt.lvds_ssc_freq = intel_bios_ssc_frequency(i915, + !HAS_PCH_SPLIT(i915)); drm_dbg_kms(&i915->drm, "Set default to SSC at %d kHz\n", - i915->vbt.lvds_ssc_freq); + i915->display.vbt.lvds_ssc_freq); } /* Common defaults which may be overridden by VBT. */ @@ -2883,7 +2917,7 @@ init_vbt_missing_defaults(struct drm_i915_private *i915) if (port == PORT_A) child->device_type |= DEVICE_TYPE_INTERNAL_CONNECTOR; - list_add_tail(&devdata->node, &i915->vbt.display_devices); + list_add_tail(&devdata->node, &i915->display.vbt.display_devices); drm_dbg_kms(&i915->drm, "Generating default VBT child device with type 0x04%x on port %c\n", @@ -2891,7 +2925,7 @@ init_vbt_missing_defaults(struct drm_i915_private *i915) } /* Bypass some minimum baseline VBT version checks */ - i915->vbt.version = 155; + i915->display.vbt.version = 155; } static const struct bdb_header *get_bdb_header(const struct vbt_header *vbt) @@ -3078,12 +3112,12 @@ err_unmap_oprom: */ void intel_bios_init(struct drm_i915_private *i915) { - const struct vbt_header *vbt = i915->opregion.vbt; + const struct vbt_header *vbt = i915->display.opregion.vbt; struct vbt_header *oprom_vbt = NULL; const struct bdb_header *bdb; - INIT_LIST_HEAD(&i915->vbt.display_devices); - INIT_LIST_HEAD(&i915->vbt.bdb_blocks); + INIT_LIST_HEAD(&i915->display.vbt.display_devices); + INIT_LIST_HEAD(&i915->display.vbt.bdb_blocks); if (!HAS_DISPLAY(i915)) { drm_dbg_kms(&i915->drm, @@ -3111,11 +3145,11 @@ void intel_bios_init(struct drm_i915_private *i915) goto out; bdb = get_bdb_header(vbt); - i915->vbt.version = bdb->version; + i915->display.vbt.version = bdb->version; drm_dbg_kms(&i915->drm, "VBT signature \"%.*s\", BDB version %d\n", - (int)sizeof(vbt->signature), vbt->signature, i915->vbt.version); + (int)sizeof(vbt->signature), vbt->signature, i915->display.vbt.version); init_bdb_blocks(i915, bdb); @@ -3172,13 +3206,13 @@ void intel_bios_driver_remove(struct drm_i915_private *i915) struct intel_bios_encoder_data *devdata, *nd; struct bdb_block_entry *entry, *ne; - list_for_each_entry_safe(devdata, nd, &i915->vbt.display_devices, node) { + list_for_each_entry_safe(devdata, nd, &i915->display.vbt.display_devices, node) { list_del(&devdata->node); kfree(devdata->dsc); kfree(devdata); } - list_for_each_entry_safe(entry, ne, &i915->vbt.bdb_blocks, node) { + list_for_each_entry_safe(entry, ne, &i915->display.vbt.bdb_blocks, node) { list_del(&entry->node); kfree(entry); } @@ -3212,13 +3246,13 @@ bool intel_bios_is_tv_present(struct drm_i915_private *i915) const struct intel_bios_encoder_data *devdata; const struct child_device_config *child; - if (!i915->vbt.int_tv_support) + if (!i915->display.vbt.int_tv_support) return false; - if (list_empty(&i915->vbt.display_devices)) + if (list_empty(&i915->display.vbt.display_devices)) return true; - list_for_each_entry(devdata, &i915->vbt.display_devices, node) { + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) { child = &devdata->child; /* @@ -3255,10 +3289,10 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *i915, u8 *i2c_pin) const struct intel_bios_encoder_data *devdata; const struct child_device_config *child; - if (list_empty(&i915->vbt.display_devices)) + if (list_empty(&i915->display.vbt.display_devices)) return true; - list_for_each_entry(devdata, &i915->vbt.display_devices, node) { + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) { child = &devdata->child; /* If the device type is not LFP, continue. @@ -3285,7 +3319,7 @@ bool intel_bios_is_lvds_present(struct drm_i915_private *i915, u8 *i2c_pin) * additional data. Trust that if the VBT was written into * the OpRegion then they have validated the LVDS's existence. */ - if (i915->opregion.vbt) + if (i915->display.opregion.vbt) return true; } @@ -3304,7 +3338,7 @@ bool intel_bios_is_port_present(struct drm_i915_private *i915, enum port port) if (WARN_ON(!has_ddi_port_info(i915))) return true; - return i915->vbt.ports[port]; + return i915->display.vbt.ports[port]; } /** @@ -3364,7 +3398,7 @@ bool intel_bios_is_dsi_present(struct drm_i915_private *i915, const struct child_device_config *child; u8 dvo_port; - list_for_each_entry(devdata, &i915->vbt.display_devices, node) { + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) { child = &devdata->child; if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT)) @@ -3463,7 +3497,7 @@ bool intel_bios_get_dsc_params(struct intel_encoder *encoder, const struct intel_bios_encoder_data *devdata; const struct child_device_config *child; - list_for_each_entry(devdata, &i915->vbt.display_devices, node) { + list_for_each_entry(devdata, &i915->display.vbt.display_devices, node) { child = &devdata->child; if (!(child->device_type & DEVICE_TYPE_MIPI_OUTPUT)) @@ -3494,7 +3528,7 @@ bool intel_bios_is_port_hpd_inverted(const struct drm_i915_private *i915, enum port port) { - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[port]; if (drm_WARN_ON_ONCE(&i915->drm, !IS_GEMINILAKE(i915) && !IS_BROXTON(i915))) @@ -3514,7 +3548,7 @@ bool intel_bios_is_lspcon_present(const struct drm_i915_private *i915, enum port port) { - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[port]; return HAS_LSPCON(i915) && devdata && devdata->child.lspcon; } @@ -3530,7 +3564,7 @@ bool intel_bios_is_lane_reversal_needed(const struct drm_i915_private *i915, enum port port) { - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[port]; return devdata && devdata->child.lane_reversal; } @@ -3538,7 +3572,7 @@ intel_bios_is_lane_reversal_needed(const struct drm_i915_private *i915, enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *i915, enum port port) { - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[port]; enum aux_ch aux_ch; if (!devdata || !devdata->child.aux_channel) { @@ -3576,7 +3610,7 @@ enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *i915, aux_ch = AUX_CH_C; break; case DP_AUX_D: - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) aux_ch = AUX_CH_D_XELPD; else if (IS_ALDERLAKE_S(i915)) aux_ch = AUX_CH_USBC3; @@ -3586,7 +3620,7 @@ enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *i915, aux_ch = AUX_CH_D; break; case DP_AUX_E: - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) aux_ch = AUX_CH_E_XELPD; else if (IS_ALDERLAKE_S(i915)) aux_ch = AUX_CH_USBC4; @@ -3594,25 +3628,25 @@ enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *i915, aux_ch = AUX_CH_E; break; case DP_AUX_F: - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) aux_ch = AUX_CH_USBC1; else aux_ch = AUX_CH_F; break; case DP_AUX_G: - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) aux_ch = AUX_CH_USBC2; else aux_ch = AUX_CH_G; break; case DP_AUX_H: - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) aux_ch = AUX_CH_USBC3; else aux_ch = AUX_CH_H; break; case DP_AUX_I: - if (DISPLAY_VER(i915) == 13) + if (DISPLAY_VER(i915) >= 13) aux_ch = AUX_CH_USBC4; else aux_ch = AUX_CH_I; @@ -3632,7 +3666,7 @@ enum aux_ch intel_bios_port_aux_ch(struct drm_i915_private *i915, int intel_bios_max_tmds_clock(struct intel_encoder *encoder) { struct drm_i915_private *i915 = to_i915(encoder->base.dev); - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[encoder->port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[encoder->port]; return _intel_bios_max_tmds_clock(devdata); } @@ -3641,14 +3675,14 @@ int intel_bios_max_tmds_clock(struct intel_encoder *encoder) int intel_bios_hdmi_level_shift(struct intel_encoder *encoder) { struct drm_i915_private *i915 = to_i915(encoder->base.dev); - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[encoder->port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[encoder->port]; return _intel_bios_hdmi_level_shift(devdata); } int intel_bios_encoder_dp_boost_level(const struct intel_bios_encoder_data *devdata) { - if (!devdata || devdata->i915->vbt.version < 196 || !devdata->child.iboost) + if (!devdata || devdata->i915->display.vbt.version < 196 || !devdata->child.iboost) return 0; return translate_iboost(devdata->child.dp_iboost_level); @@ -3656,7 +3690,7 @@ int intel_bios_encoder_dp_boost_level(const struct intel_bios_encoder_data *devd int intel_bios_encoder_hdmi_boost_level(const struct intel_bios_encoder_data *devdata) { - if (!devdata || devdata->i915->vbt.version < 196 || !devdata->child.iboost) + if (!devdata || devdata->i915->display.vbt.version < 196 || !devdata->child.iboost) return 0; return translate_iboost(devdata->child.hdmi_iboost_level); @@ -3665,15 +3699,23 @@ int intel_bios_encoder_hdmi_boost_level(const struct intel_bios_encoder_data *de int intel_bios_dp_max_link_rate(struct intel_encoder *encoder) { struct drm_i915_private *i915 = to_i915(encoder->base.dev); - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[encoder->port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[encoder->port]; return _intel_bios_dp_max_link_rate(devdata); } +int intel_bios_dp_max_lane_count(struct intel_encoder *encoder) +{ + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[encoder->port]; + + return _intel_bios_dp_max_lane_count(devdata); +} + int intel_bios_alternate_ddc_pin(struct intel_encoder *encoder) { struct drm_i915_private *i915 = to_i915(encoder->base.dev); - const struct intel_bios_encoder_data *devdata = i915->vbt.ports[encoder->port]; + const struct intel_bios_encoder_data *devdata = i915->display.vbt.ports[encoder->port]; if (!devdata || !devdata->child.ddc_pin) return 0; @@ -3683,16 +3725,16 @@ int intel_bios_alternate_ddc_pin(struct intel_encoder *encoder) bool intel_bios_encoder_supports_typec_usb(const struct intel_bios_encoder_data *devdata) { - return devdata->i915->vbt.version >= 195 && devdata->child.dp_usb_type_c; + return devdata->i915->display.vbt.version >= 195 && devdata->child.dp_usb_type_c; } bool intel_bios_encoder_supports_tbt(const struct intel_bios_encoder_data *devdata) { - return devdata->i915->vbt.version >= 209 && devdata->child.tbt; + return devdata->i915->display.vbt.version >= 209 && devdata->child.tbt; } const struct intel_bios_encoder_data * intel_bios_encoder_data_lookup(struct drm_i915_private *i915, enum port port) { - return i915->vbt.ports[port]; + return i915->display.vbt.ports[port]; } diff --git a/drivers/gpu/drm/i915/display/intel_bios.h b/drivers/gpu/drm/i915/display/intel_bios.h index e47582b0de0a..e375405a7828 100644 --- a/drivers/gpu/drm/i915/display/intel_bios.h +++ b/drivers/gpu/drm/i915/display/intel_bios.h @@ -258,6 +258,7 @@ bool intel_bios_get_dsc_params(struct intel_encoder *encoder, int intel_bios_max_tmds_clock(struct intel_encoder *encoder); int intel_bios_hdmi_level_shift(struct intel_encoder *encoder); int intel_bios_dp_max_link_rate(struct intel_encoder *encoder); +int intel_bios_dp_max_lane_count(struct intel_encoder *encoder); int intel_bios_alternate_ddc_pin(struct intel_encoder *encoder); bool intel_bios_port_supports_typec_usb(struct drm_i915_private *i915, enum port port); bool intel_bios_port_supports_tbt(struct drm_i915_private *i915, enum port port); diff --git a/drivers/gpu/drm/i915/display/intel_bw.c b/drivers/gpu/drm/i915/display/intel_bw.c index 79269d2c476b..4ace026b29bd 100644 --- a/drivers/gpu/drm/i915/display/intel_bw.c +++ b/drivers/gpu/drm/i915/display/intel_bw.c @@ -5,15 +5,17 @@ #include <drm/drm_atomic_state_helper.h> +#include "i915_drv.h" #include "i915_reg.h" #include "i915_utils.h" #include "intel_atomic.h" #include "intel_bw.h" #include "intel_cdclk.h" +#include "intel_display_core.h" #include "intel_display_types.h" +#include "skl_watermark.h" #include "intel_mchbar_regs.h" #include "intel_pcode.h" -#include "intel_pm.h" /* Parameters for Qclk Geyserville (QGV) */ struct intel_qgv_point { @@ -137,6 +139,42 @@ int icl_pcode_restrict_qgv_points(struct drm_i915_private *dev_priv, return 0; } +static int mtl_read_qgv_point_info(struct drm_i915_private *dev_priv, + struct intel_qgv_point *sp, int point) +{ + u32 val, val2; + u16 dclk; + + val = intel_uncore_read(&dev_priv->uncore, + MTL_MEM_SS_INFO_QGV_POINT_LOW(point)); + val2 = intel_uncore_read(&dev_priv->uncore, + MTL_MEM_SS_INFO_QGV_POINT_HIGH(point)); + dclk = REG_FIELD_GET(MTL_DCLK_MASK, val); + sp->dclk = DIV_ROUND_UP((16667 * dclk), 1000); + sp->t_rp = REG_FIELD_GET(MTL_TRP_MASK, val); + sp->t_rcd = REG_FIELD_GET(MTL_TRCD_MASK, val); + + sp->t_rdpre = REG_FIELD_GET(MTL_TRDPRE_MASK, val2); + sp->t_ras = REG_FIELD_GET(MTL_TRAS_MASK, val2); + + sp->t_rc = sp->t_rp + sp->t_ras; + + return 0; +} + +static int +intel_read_qgv_point_info(struct drm_i915_private *dev_priv, + struct intel_qgv_point *sp, + int point) +{ + if (DISPLAY_VER(dev_priv) >= 14) + return mtl_read_qgv_point_info(dev_priv, sp, point); + else if (IS_DG1(dev_priv)) + return dg1_mchbar_read_qgv_point_info(dev_priv, sp, point); + else + return icl_pcode_read_qgv_point_info(dev_priv, sp, point); +} + static int icl_get_qgv_points(struct drm_i915_private *dev_priv, struct intel_qgv_info *qi, bool is_y_tile) @@ -147,7 +185,32 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv, qi->num_points = dram_info->num_qgv_points; qi->num_psf_points = dram_info->num_psf_gv_points; - if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(dev_priv) >= 14) { + switch (dram_info->type) { + case INTEL_DRAM_DDR4: + qi->t_bl = 4; + qi->max_numchannels = 2; + qi->channel_width = 64; + qi->deinterleave = 2; + break; + case INTEL_DRAM_DDR5: + qi->t_bl = 8; + qi->max_numchannels = 4; + qi->channel_width = 32; + qi->deinterleave = 2; + break; + case INTEL_DRAM_LPDDR4: + case INTEL_DRAM_LPDDR5: + qi->t_bl = 16; + qi->max_numchannels = 8; + qi->channel_width = 16; + qi->deinterleave = 4; + break; + default: + MISSING_CASE(dram_info->type); + return -EINVAL; + } + } else if (DISPLAY_VER(dev_priv) >= 12) { switch (dram_info->type) { case INTEL_DRAM_DDR4: qi->t_bl = is_y_tile ? 8 : 4; @@ -181,7 +244,7 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv, qi->max_numchannels = 1; break; } - else if (DISPLAY_VER(dev_priv) == 11) { + } else if (DISPLAY_VER(dev_priv) == 11) { qi->t_bl = dev_priv->dram_info.type == INTEL_DRAM_DDR4 ? 4 : 8; qi->max_numchannels = 1; } @@ -193,11 +256,7 @@ static int icl_get_qgv_points(struct drm_i915_private *dev_priv, for (i = 0; i < qi->num_points; i++) { struct intel_qgv_point *sp = &qi->points[i]; - if (IS_DG1(dev_priv)) - ret = dg1_mchbar_read_qgv_point_info(dev_priv, sp, i); - else - ret = icl_pcode_read_qgv_point_info(dev_priv, sp, i); - + ret = intel_read_qgv_point_info(dev_priv, sp, i); if (ret) return ret; @@ -284,6 +343,13 @@ static const struct intel_sa_info adlp_sa_info = { .derating = 20, }; +static const struct intel_sa_info mtl_sa_info = { + .deburst = 32, + .deprogbwlimit = 38, /* GB/s */ + .displayrtids = 256, + .derating = 20, +}; + static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel_sa_info *sa) { struct intel_qgv_info qi = {}; @@ -292,7 +358,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel int ipqdepth, ipqdepthpch = 16; int dclk_max; int maxdebw; - int num_groups = ARRAY_SIZE(dev_priv->max_bw); + int num_groups = ARRAY_SIZE(dev_priv->display.bw.max); int i, ret; ret = icl_get_qgv_points(dev_priv, &qi, is_y_tile); @@ -308,7 +374,7 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel qi.deinterleave = DIV_ROUND_UP(num_channels, is_y_tile ? 4 : 2); for (i = 0; i < num_groups; i++) { - struct intel_bw_info *bi = &dev_priv->max_bw[i]; + struct intel_bw_info *bi = &dev_priv->display.bw.max[i]; int clpchgroup; int j; @@ -346,9 +412,9 @@ static int icl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel * as it will fail and pointless anyway. */ if (qi.num_points == 1) - dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED; + dev_priv->display.sagv.status = I915_SAGV_NOT_CONTROLLED; else - dev_priv->sagv_status = I915_SAGV_ENABLED; + dev_priv->display.sagv.status = I915_SAGV_ENABLED; return 0; } @@ -363,7 +429,7 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel int dclk_max; int maxdebw, peakbw; int clperchgroup; - int num_groups = ARRAY_SIZE(dev_priv->max_bw); + int num_groups = ARRAY_SIZE(dev_priv->display.bw.max); int i, ret; ret = icl_get_qgv_points(dev_priv, &qi, is_y_tile); @@ -399,20 +465,22 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel clperchgroup = 4 * DIV_ROUND_UP(8, num_channels) * qi.deinterleave; for (i = 0; i < num_groups; i++) { - struct intel_bw_info *bi = &dev_priv->max_bw[i]; + struct intel_bw_info *bi = &dev_priv->display.bw.max[i]; struct intel_bw_info *bi_next; int clpchgroup; int j; - if (i < num_groups - 1) - bi_next = &dev_priv->max_bw[i + 1]; - clpchgroup = (sa->deburst * qi.deinterleave / num_channels) << i; - if (i < num_groups - 1 && clpchgroup < clperchgroup) - bi_next->num_planes = (ipqdepth - clpchgroup) / clpchgroup + 1; - else - bi_next->num_planes = 0; + if (i < num_groups - 1) { + bi_next = &dev_priv->display.bw.max[i + 1]; + + if (clpchgroup < clperchgroup) + bi_next->num_planes = (ipqdepth - clpchgroup) / + clpchgroup + 1; + else + bi_next->num_planes = 0; + } bi->num_qgv_points = qi.num_points; bi->num_psf_gv_points = qi.num_psf_points; @@ -456,9 +524,9 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel * as it will fail and pointless anyway. */ if (qi.num_points == 1) - dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED; + dev_priv->display.sagv.status = I915_SAGV_NOT_CONTROLLED; else - dev_priv->sagv_status = I915_SAGV_ENABLED; + dev_priv->display.sagv.status = I915_SAGV_ENABLED; return 0; } @@ -466,7 +534,7 @@ static int tgl_get_bw_info(struct drm_i915_private *dev_priv, const struct intel static void dg2_get_bw_info(struct drm_i915_private *i915) { unsigned int deratedbw = IS_DG2_G11(i915) ? 38000 : 50000; - int num_groups = ARRAY_SIZE(i915->max_bw); + int num_groups = ARRAY_SIZE(i915->display.bw.max); int i; /* @@ -477,7 +545,7 @@ static void dg2_get_bw_info(struct drm_i915_private *i915) * whereas DG2-G11 platforms have 38 GB/s. */ for (i = 0; i < num_groups; i++) { - struct intel_bw_info *bi = &i915->max_bw[i]; + struct intel_bw_info *bi = &i915->display.bw.max[i]; bi->num_planes = 1; /* Need only one dummy QGV point per group */ @@ -485,7 +553,7 @@ static void dg2_get_bw_info(struct drm_i915_private *i915) bi->deratedbw[0] = deratedbw; } - i915->sagv_status = I915_SAGV_NOT_CONTROLLED; + i915->display.sagv.status = I915_SAGV_NOT_CONTROLLED; } static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, @@ -498,9 +566,9 @@ static unsigned int icl_max_bw(struct drm_i915_private *dev_priv, */ num_planes = max(1, num_planes); - for (i = 0; i < ARRAY_SIZE(dev_priv->max_bw); i++) { + for (i = 0; i < ARRAY_SIZE(dev_priv->display.bw.max); i++) { const struct intel_bw_info *bi = - &dev_priv->max_bw[i]; + &dev_priv->display.bw.max[i]; /* * Pcode will not expose all QGV points when @@ -526,9 +594,9 @@ static unsigned int tgl_max_bw(struct drm_i915_private *dev_priv, */ num_planes = max(1, num_planes); - for (i = ARRAY_SIZE(dev_priv->max_bw) - 1; i >= 0; i--) { + for (i = ARRAY_SIZE(dev_priv->display.bw.max) - 1; i >= 0; i--) { const struct intel_bw_info *bi = - &dev_priv->max_bw[i]; + &dev_priv->display.bw.max[i]; /* * Pcode will not expose all QGV points when @@ -541,14 +609,14 @@ static unsigned int tgl_max_bw(struct drm_i915_private *dev_priv, return bi->deratedbw[qgv_point]; } - return dev_priv->max_bw[0].deratedbw[qgv_point]; + return dev_priv->display.bw.max[0].deratedbw[qgv_point]; } static unsigned int adl_psf_bw(struct drm_i915_private *dev_priv, int psf_gv_point) { const struct intel_bw_info *bi = - &dev_priv->max_bw[0]; + &dev_priv->display.bw.max[0]; return bi->psf_bw[psf_gv_point]; } @@ -558,7 +626,9 @@ void intel_bw_init_hw(struct drm_i915_private *dev_priv) if (!HAS_DISPLAY(dev_priv)) return; - if (IS_DG2(dev_priv)) + if (DISPLAY_VER(dev_priv) >= 14) + tgl_get_bw_info(dev_priv, &mtl_sa_info); + else if (IS_DG2(dev_priv)) dg2_get_bw_info(dev_priv); else if (IS_ALDERLAKE_P(dev_priv)) tgl_get_bw_info(dev_priv, &adlp_sa_info); @@ -667,7 +737,7 @@ intel_atomic_get_old_bw_state(struct intel_atomic_state *state) struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_global_state *bw_state; - bw_state = intel_atomic_get_old_global_obj_state(state, &dev_priv->bw_obj); + bw_state = intel_atomic_get_old_global_obj_state(state, &dev_priv->display.bw.obj); return to_intel_bw_state(bw_state); } @@ -678,7 +748,7 @@ intel_atomic_get_new_bw_state(struct intel_atomic_state *state) struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_global_state *bw_state; - bw_state = intel_atomic_get_new_global_obj_state(state, &dev_priv->bw_obj); + bw_state = intel_atomic_get_new_global_obj_state(state, &dev_priv->display.bw.obj); return to_intel_bw_state(bw_state); } @@ -689,7 +759,7 @@ intel_atomic_get_bw_state(struct intel_atomic_state *state) struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_global_state *bw_state; - bw_state = intel_atomic_get_global_obj_state(state, &dev_priv->bw_obj); + bw_state = intel_atomic_get_global_obj_state(state, &dev_priv->display.bw.obj); if (IS_ERR(bw_state)) return ERR_CAST(bw_state); @@ -896,8 +966,8 @@ int intel_bw_calc_min_cdclk(struct intel_atomic_state *state, static u16 icl_qgv_points_mask(struct drm_i915_private *i915) { - unsigned int num_psf_gv_points = i915->max_bw[0].num_psf_gv_points; - unsigned int num_qgv_points = i915->max_bw[0].num_qgv_points; + unsigned int num_psf_gv_points = i915->display.bw.max[0].num_psf_gv_points; + unsigned int num_qgv_points = i915->display.bw.max[0].num_qgv_points; u16 qgv_points = 0, psf_points = 0; /* @@ -970,8 +1040,8 @@ int intel_bw_atomic_check(struct intel_atomic_state *state) int i, ret; u16 qgv_points = 0, psf_points = 0; unsigned int max_bw_point = 0, max_bw = 0; - unsigned int num_qgv_points = dev_priv->max_bw[0].num_qgv_points; - unsigned int num_psf_gv_points = dev_priv->max_bw[0].num_psf_gv_points; + unsigned int num_qgv_points = dev_priv->display.bw.max[0].num_qgv_points; + unsigned int num_psf_gv_points = dev_priv->display.bw.max[0].num_psf_gv_points; bool changed = false; /* FIXME earlier gens need some checks too */ @@ -1126,7 +1196,7 @@ int intel_bw_init(struct drm_i915_private *dev_priv) if (!state) return -ENOMEM; - intel_atomic_global_obj_init(dev_priv, &dev_priv->bw_obj, + intel_atomic_global_obj_init(dev_priv, &dev_priv->display.bw.obj, &state->base, &intel_bw_funcs); return 0; diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c index 6e80162632dd..ed05070b7307 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.c +++ b/drivers/gpu/drm/i915/display/intel_cdclk.c @@ -79,26 +79,26 @@ struct intel_cdclk_funcs { void intel_cdclk_get_cdclk(struct drm_i915_private *dev_priv, struct intel_cdclk_config *cdclk_config) { - dev_priv->cdclk_funcs->get_cdclk(dev_priv, cdclk_config); + dev_priv->display.funcs.cdclk->get_cdclk(dev_priv, cdclk_config); } static void intel_cdclk_set_cdclk(struct drm_i915_private *dev_priv, const struct intel_cdclk_config *cdclk_config, enum pipe pipe) { - dev_priv->cdclk_funcs->set_cdclk(dev_priv, cdclk_config, pipe); + dev_priv->display.funcs.cdclk->set_cdclk(dev_priv, cdclk_config, pipe); } static int intel_cdclk_modeset_calc_cdclk(struct drm_i915_private *dev_priv, struct intel_cdclk_state *cdclk_config) { - return dev_priv->cdclk_funcs->modeset_calc_cdclk(cdclk_config); + return dev_priv->display.funcs.cdclk->modeset_calc_cdclk(cdclk_config); } static u8 intel_cdclk_calc_voltage_level(struct drm_i915_private *dev_priv, int cdclk) { - return dev_priv->cdclk_funcs->calc_voltage_level(cdclk); + return dev_priv->display.funcs.cdclk->calc_voltage_level(cdclk); } static void fixed_133mhz_get_cdclk(struct drm_i915_private *dev_priv, @@ -548,7 +548,7 @@ static void vlv_program_pfi_credits(struct drm_i915_private *dev_priv) else default_credits = PFI_CREDIT(8); - if (dev_priv->cdclk.hw.cdclk >= dev_priv->czclk_freq) { + if (dev_priv->display.cdclk.hw.cdclk >= dev_priv->czclk_freq) { /* CHV suggested value is 31 or 63 */ if (IS_CHERRYVIEW(dev_priv)) credits = PFI_CREDIT_63; @@ -1026,7 +1026,7 @@ static void skl_dpll0_enable(struct drm_i915_private *dev_priv, int vco) if (intel_de_wait_for_set(dev_priv, LCPLL1_CTL, LCPLL_PLL_LOCK, 5)) drm_err(&dev_priv->drm, "DPLL0 not locked\n"); - dev_priv->cdclk.hw.vco = vco; + dev_priv->display.cdclk.hw.vco = vco; /* We'll want to keep using the current vco from now on. */ skl_set_preferred_cdclk_vco(dev_priv, vco); @@ -1040,7 +1040,7 @@ static void skl_dpll0_disable(struct drm_i915_private *dev_priv) if (intel_de_wait_for_clear(dev_priv, LCPLL1_CTL, LCPLL_PLL_LOCK, 1)) drm_err(&dev_priv->drm, "Couldn't disable DPLL0\n"); - dev_priv->cdclk.hw.vco = 0; + dev_priv->display.cdclk.hw.vco = 0; } static u32 skl_cdclk_freq_sel(struct drm_i915_private *dev_priv, @@ -1049,7 +1049,7 @@ static u32 skl_cdclk_freq_sel(struct drm_i915_private *dev_priv, switch (cdclk) { default: drm_WARN_ON(&dev_priv->drm, - cdclk != dev_priv->cdclk.hw.bypass); + cdclk != dev_priv->display.cdclk.hw.bypass); drm_WARN_ON(&dev_priv->drm, vco != 0); fallthrough; case 308571: @@ -1098,13 +1098,13 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, freq_select = skl_cdclk_freq_sel(dev_priv, cdclk, vco); - if (dev_priv->cdclk.hw.vco != 0 && - dev_priv->cdclk.hw.vco != vco) + if (dev_priv->display.cdclk.hw.vco != 0 && + dev_priv->display.cdclk.hw.vco != vco) skl_dpll0_disable(dev_priv); cdclk_ctl = intel_de_read(dev_priv, CDCLK_CTL); - if (dev_priv->cdclk.hw.vco != vco) { + if (dev_priv->display.cdclk.hw.vco != vco) { /* Wa Display #1183: skl,kbl,cfl */ cdclk_ctl &= ~(CDCLK_FREQ_SEL_MASK | CDCLK_FREQ_DECIMAL_MASK); cdclk_ctl |= freq_select | skl_cdclk_decimal(cdclk); @@ -1116,7 +1116,7 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv, intel_de_write(dev_priv, CDCLK_CTL, cdclk_ctl); intel_de_posting_read(dev_priv, CDCLK_CTL); - if (dev_priv->cdclk.hw.vco != vco) + if (dev_priv->display.cdclk.hw.vco != vco) skl_dpll0_enable(dev_priv, vco); /* Wa Display #1183: skl,kbl,cfl */ @@ -1151,11 +1151,11 @@ static void skl_sanitize_cdclk(struct drm_i915_private *dev_priv) goto sanitize; intel_update_cdclk(dev_priv); - intel_cdclk_dump_config(dev_priv, &dev_priv->cdclk.hw, "Current CDCLK"); + intel_cdclk_dump_config(dev_priv, &dev_priv->display.cdclk.hw, "Current CDCLK"); /* Is PLL enabled and locked ? */ - if (dev_priv->cdclk.hw.vco == 0 || - dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass) + if (dev_priv->display.cdclk.hw.vco == 0 || + dev_priv->display.cdclk.hw.cdclk == dev_priv->display.cdclk.hw.bypass) goto sanitize; /* DPLL okay; verify the cdclock @@ -1166,7 +1166,7 @@ static void skl_sanitize_cdclk(struct drm_i915_private *dev_priv) */ cdctl = intel_de_read(dev_priv, CDCLK_CTL); expected = (cdctl & CDCLK_FREQ_SEL_MASK) | - skl_cdclk_decimal(dev_priv->cdclk.hw.cdclk); + skl_cdclk_decimal(dev_priv->display.cdclk.hw.cdclk); if (cdctl == expected) /* All well; nothing to sanitize */ return; @@ -1175,9 +1175,9 @@ sanitize: drm_dbg_kms(&dev_priv->drm, "Sanitizing cdclk programmed by pre-os\n"); /* force cdclk programming */ - dev_priv->cdclk.hw.cdclk = 0; + dev_priv->display.cdclk.hw.cdclk = 0; /* force full PLL disable + enable */ - dev_priv->cdclk.hw.vco = -1; + dev_priv->display.cdclk.hw.vco = -1; } static void skl_cdclk_init_hw(struct drm_i915_private *dev_priv) @@ -1186,19 +1186,19 @@ static void skl_cdclk_init_hw(struct drm_i915_private *dev_priv) skl_sanitize_cdclk(dev_priv); - if (dev_priv->cdclk.hw.cdclk != 0 && - dev_priv->cdclk.hw.vco != 0) { + if (dev_priv->display.cdclk.hw.cdclk != 0 && + dev_priv->display.cdclk.hw.vco != 0) { /* * Use the current vco as our initial * guess as to what the preferred vco is. */ if (dev_priv->skl_preferred_vco_freq == 0) skl_set_preferred_cdclk_vco(dev_priv, - dev_priv->cdclk.hw.vco); + dev_priv->display.cdclk.hw.vco); return; } - cdclk_config = dev_priv->cdclk.hw; + cdclk_config = dev_priv->display.cdclk.hw; cdclk_config.vco = dev_priv->skl_preferred_vco_freq; if (cdclk_config.vco == 0) @@ -1211,7 +1211,7 @@ static void skl_cdclk_init_hw(struct drm_i915_private *dev_priv) static void skl_cdclk_uninit_hw(struct drm_i915_private *dev_priv) { - struct intel_cdclk_config cdclk_config = dev_priv->cdclk.hw; + struct intel_cdclk_config cdclk_config = dev_priv->display.cdclk.hw; cdclk_config.cdclk = cdclk_config.bypass; cdclk_config.vco = 0; @@ -1352,35 +1352,35 @@ static const struct intel_cdclk_vals dg2_cdclk_table[] = { static int bxt_calc_cdclk(struct drm_i915_private *dev_priv, int min_cdclk) { - const struct intel_cdclk_vals *table = dev_priv->cdclk.table; + const struct intel_cdclk_vals *table = dev_priv->display.cdclk.table; int i; for (i = 0; table[i].refclk; i++) - if (table[i].refclk == dev_priv->cdclk.hw.ref && + if (table[i].refclk == dev_priv->display.cdclk.hw.ref && table[i].cdclk >= min_cdclk) return table[i].cdclk; drm_WARN(&dev_priv->drm, 1, "Cannot satisfy minimum cdclk %d with refclk %u\n", - min_cdclk, dev_priv->cdclk.hw.ref); + min_cdclk, dev_priv->display.cdclk.hw.ref); return 0; } static int bxt_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk) { - const struct intel_cdclk_vals *table = dev_priv->cdclk.table; + const struct intel_cdclk_vals *table = dev_priv->display.cdclk.table; int i; - if (cdclk == dev_priv->cdclk.hw.bypass) + if (cdclk == dev_priv->display.cdclk.hw.bypass) return 0; for (i = 0; table[i].refclk; i++) - if (table[i].refclk == dev_priv->cdclk.hw.ref && + if (table[i].refclk == dev_priv->display.cdclk.hw.ref && table[i].cdclk == cdclk) - return dev_priv->cdclk.hw.ref * table[i].ratio; + return dev_priv->display.cdclk.hw.ref * table[i].ratio; drm_WARN(&dev_priv->drm, 1, "cdclk %d not valid for refclk %u\n", - cdclk, dev_priv->cdclk.hw.ref); + cdclk, dev_priv->display.cdclk.hw.ref); return 0; } @@ -1554,12 +1554,12 @@ static void bxt_de_pll_disable(struct drm_i915_private *dev_priv) BXT_DE_PLL_ENABLE, BXT_DE_PLL_LOCK, 1)) drm_err(&dev_priv->drm, "timeout waiting for DE PLL unlock\n"); - dev_priv->cdclk.hw.vco = 0; + dev_priv->display.cdclk.hw.vco = 0; } static void bxt_de_pll_enable(struct drm_i915_private *dev_priv, int vco) { - int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref); + int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->display.cdclk.hw.ref); intel_de_rmw(dev_priv, BXT_DE_PLL_CTL, BXT_DE_PLL_RATIO_MASK, BXT_DE_PLL_RATIO(ratio)); @@ -1571,7 +1571,7 @@ static void bxt_de_pll_enable(struct drm_i915_private *dev_priv, int vco) BXT_DE_PLL_ENABLE, BXT_DE_PLL_LOCK, 1)) drm_err(&dev_priv->drm, "timeout waiting for DE PLL lock\n"); - dev_priv->cdclk.hw.vco = vco; + dev_priv->display.cdclk.hw.vco = vco; } static void icl_cdclk_pll_disable(struct drm_i915_private *dev_priv) @@ -1583,12 +1583,12 @@ static void icl_cdclk_pll_disable(struct drm_i915_private *dev_priv) if (intel_de_wait_for_clear(dev_priv, BXT_DE_PLL_ENABLE, BXT_DE_PLL_LOCK, 1)) drm_err(&dev_priv->drm, "timeout waiting for CDCLK PLL unlock\n"); - dev_priv->cdclk.hw.vco = 0; + dev_priv->display.cdclk.hw.vco = 0; } static void icl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco) { - int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref); + int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->display.cdclk.hw.ref); u32 val; val = ICL_CDCLK_PLL_RATIO(ratio); @@ -1601,12 +1601,12 @@ static void icl_cdclk_pll_enable(struct drm_i915_private *dev_priv, int vco) if (intel_de_wait_for_set(dev_priv, BXT_DE_PLL_ENABLE, BXT_DE_PLL_LOCK, 1)) drm_err(&dev_priv->drm, "timeout waiting for CDCLK PLL lock\n"); - dev_priv->cdclk.hw.vco = vco; + dev_priv->display.cdclk.hw.vco = vco; } static void adlp_cdclk_pll_crawl(struct drm_i915_private *dev_priv, int vco) { - int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->cdclk.hw.ref); + int ratio = DIV_ROUND_CLOSEST(vco, dev_priv->display.cdclk.hw.ref); u32 val; /* Write PLL ratio without disabling */ @@ -1625,7 +1625,7 @@ static void adlp_cdclk_pll_crawl(struct drm_i915_private *dev_priv, int vco) val &= ~BXT_DE_PLL_FREQ_REQ; intel_de_write(dev_priv, BXT_DE_PLL_ENABLE, val); - dev_priv->cdclk.hw.vco = vco; + dev_priv->display.cdclk.hw.vco = vco; } static u32 bxt_cdclk_cd2x_pipe(struct drm_i915_private *dev_priv, enum pipe pipe) @@ -1655,7 +1655,7 @@ static u32 bxt_cdclk_cd2x_div_sel(struct drm_i915_private *dev_priv, switch (DIV_ROUND_CLOSEST(vco, cdclk)) { default: drm_WARN_ON(&dev_priv->drm, - cdclk != dev_priv->cdclk.hw.bypass); + cdclk != dev_priv->display.cdclk.hw.bypass); drm_WARN_ON(&dev_priv->drm, vco != 0); fallthrough; case 2: @@ -1672,19 +1672,19 @@ static u32 bxt_cdclk_cd2x_div_sel(struct drm_i915_private *dev_priv, static u32 cdclk_squash_waveform(struct drm_i915_private *dev_priv, int cdclk) { - const struct intel_cdclk_vals *table = dev_priv->cdclk.table; + const struct intel_cdclk_vals *table = dev_priv->display.cdclk.table; int i; - if (cdclk == dev_priv->cdclk.hw.bypass) + if (cdclk == dev_priv->display.cdclk.hw.bypass) return 0; for (i = 0; table[i].refclk; i++) - if (table[i].refclk == dev_priv->cdclk.hw.ref && + if (table[i].refclk == dev_priv->display.cdclk.hw.ref && table[i].cdclk == cdclk) return table[i].waveform; drm_WARN(&dev_priv->drm, 1, "cdclk %d not valid for refclk %u\n", - cdclk, dev_priv->cdclk.hw.ref); + cdclk, dev_priv->display.cdclk.hw.ref); return 0xffff; } @@ -1721,22 +1721,22 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, return; } - if (HAS_CDCLK_CRAWL(dev_priv) && dev_priv->cdclk.hw.vco > 0 && vco > 0) { - if (dev_priv->cdclk.hw.vco != vco) + if (HAS_CDCLK_CRAWL(dev_priv) && dev_priv->display.cdclk.hw.vco > 0 && vco > 0) { + if (dev_priv->display.cdclk.hw.vco != vco) adlp_cdclk_pll_crawl(dev_priv, vco); } else if (DISPLAY_VER(dev_priv) >= 11) { - if (dev_priv->cdclk.hw.vco != 0 && - dev_priv->cdclk.hw.vco != vco) + if (dev_priv->display.cdclk.hw.vco != 0 && + dev_priv->display.cdclk.hw.vco != vco) icl_cdclk_pll_disable(dev_priv); - if (dev_priv->cdclk.hw.vco != vco) + if (dev_priv->display.cdclk.hw.vco != vco) icl_cdclk_pll_enable(dev_priv, vco); } else { - if (dev_priv->cdclk.hw.vco != 0 && - dev_priv->cdclk.hw.vco != vco) + if (dev_priv->display.cdclk.hw.vco != 0 && + dev_priv->display.cdclk.hw.vco != vco) bxt_de_pll_disable(dev_priv); - if (dev_priv->cdclk.hw.vco != vco) + if (dev_priv->display.cdclk.hw.vco != vco) bxt_de_pll_enable(dev_priv, vco); } @@ -1803,7 +1803,7 @@ static void bxt_set_cdclk(struct drm_i915_private *dev_priv, * Can't read out the voltage level :( * Let's just assume everything is as expected. */ - dev_priv->cdclk.hw.voltage_level = cdclk_config->voltage_level; + dev_priv->display.cdclk.hw.voltage_level = cdclk_config->voltage_level; } static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv) @@ -1812,10 +1812,10 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv) int cdclk, clock, vco; intel_update_cdclk(dev_priv); - intel_cdclk_dump_config(dev_priv, &dev_priv->cdclk.hw, "Current CDCLK"); + intel_cdclk_dump_config(dev_priv, &dev_priv->display.cdclk.hw, "Current CDCLK"); - if (dev_priv->cdclk.hw.vco == 0 || - dev_priv->cdclk.hw.cdclk == dev_priv->cdclk.hw.bypass) + if (dev_priv->display.cdclk.hw.vco == 0 || + dev_priv->display.cdclk.hw.cdclk == dev_priv->display.cdclk.hw.bypass) goto sanitize; /* DPLL okay; verify the cdclock @@ -1833,32 +1833,32 @@ static void bxt_sanitize_cdclk(struct drm_i915_private *dev_priv) cdctl &= ~bxt_cdclk_cd2x_pipe(dev_priv, INVALID_PIPE); /* Make sure this is a legal cdclk value for the platform */ - cdclk = bxt_calc_cdclk(dev_priv, dev_priv->cdclk.hw.cdclk); - if (cdclk != dev_priv->cdclk.hw.cdclk) + cdclk = bxt_calc_cdclk(dev_priv, dev_priv->display.cdclk.hw.cdclk); + if (cdclk != dev_priv->display.cdclk.hw.cdclk) goto sanitize; /* Make sure the VCO is correct for the cdclk */ vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk); - if (vco != dev_priv->cdclk.hw.vco) + if (vco != dev_priv->display.cdclk.hw.vco) goto sanitize; expected = skl_cdclk_decimal(cdclk); /* Figure out what CD2X divider we should be using for this cdclk */ if (has_cdclk_squasher(dev_priv)) - clock = dev_priv->cdclk.hw.vco / 2; + clock = dev_priv->display.cdclk.hw.vco / 2; else - clock = dev_priv->cdclk.hw.cdclk; + clock = dev_priv->display.cdclk.hw.cdclk; expected |= bxt_cdclk_cd2x_div_sel(dev_priv, clock, - dev_priv->cdclk.hw.vco); + dev_priv->display.cdclk.hw.vco); /* * Disable SSA Precharge when CD clock frequency < 500 MHz, * enable otherwise. */ if ((IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) && - dev_priv->cdclk.hw.cdclk >= 500000) + dev_priv->display.cdclk.hw.cdclk >= 500000) expected |= BXT_CDCLK_SSA_PRECHARGE_ENABLE; if (cdctl == expected) @@ -1869,10 +1869,10 @@ sanitize: drm_dbg_kms(&dev_priv->drm, "Sanitizing cdclk programmed by pre-os\n"); /* force cdclk programming */ - dev_priv->cdclk.hw.cdclk = 0; + dev_priv->display.cdclk.hw.cdclk = 0; /* force full PLL disable + enable */ - dev_priv->cdclk.hw.vco = -1; + dev_priv->display.cdclk.hw.vco = -1; } static void bxt_cdclk_init_hw(struct drm_i915_private *dev_priv) @@ -1881,11 +1881,11 @@ static void bxt_cdclk_init_hw(struct drm_i915_private *dev_priv) bxt_sanitize_cdclk(dev_priv); - if (dev_priv->cdclk.hw.cdclk != 0 && - dev_priv->cdclk.hw.vco != 0) + if (dev_priv->display.cdclk.hw.cdclk != 0 && + dev_priv->display.cdclk.hw.vco != 0) return; - cdclk_config = dev_priv->cdclk.hw; + cdclk_config = dev_priv->display.cdclk.hw; /* * FIXME: @@ -1902,7 +1902,7 @@ static void bxt_cdclk_init_hw(struct drm_i915_private *dev_priv) static void bxt_cdclk_uninit_hw(struct drm_i915_private *dev_priv) { - struct intel_cdclk_config cdclk_config = dev_priv->cdclk.hw; + struct intel_cdclk_config cdclk_config = dev_priv->display.cdclk.hw; cdclk_config.cdclk = cdclk_config.bypass; cdclk_config.vco = 0; @@ -1916,7 +1916,7 @@ static void bxt_cdclk_uninit_hw(struct drm_i915_private *dev_priv) * intel_cdclk_init_hw - Initialize CDCLK hardware * @i915: i915 device * - * Initialize CDCLK. This consists mainly of initializing dev_priv->cdclk.hw and + * Initialize CDCLK. This consists mainly of initializing dev_priv->display.cdclk.hw and * sanitizing the state of the hardware if needed. This is generally done only * during the display core initialization sequence, after which the DMC will * take care of turning CDCLK off/on as needed. @@ -2077,10 +2077,10 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, { struct intel_encoder *encoder; - if (!intel_cdclk_changed(&dev_priv->cdclk.hw, cdclk_config)) + if (!intel_cdclk_changed(&dev_priv->display.cdclk.hw, cdclk_config)) return; - if (drm_WARN_ON_ONCE(&dev_priv->drm, !dev_priv->cdclk_funcs->set_cdclk)) + if (drm_WARN_ON_ONCE(&dev_priv->drm, !dev_priv->display.funcs.cdclk->set_cdclk)) return; intel_cdclk_dump_config(dev_priv, cdclk_config, "Changing CDCLK to"); @@ -2098,12 +2098,12 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, * functions use cdclk. Not all platforms/ports do, * but we'll lock them all for simplicity. */ - mutex_lock(&dev_priv->gmbus_mutex); + mutex_lock(&dev_priv->display.gmbus.mutex); for_each_intel_dp(&dev_priv->drm, encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); mutex_lock_nest_lock(&intel_dp->aux.hw_mutex, - &dev_priv->gmbus_mutex); + &dev_priv->display.gmbus.mutex); } intel_cdclk_set_cdclk(dev_priv, cdclk_config, pipe); @@ -2113,7 +2113,7 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, mutex_unlock(&intel_dp->aux.hw_mutex); } - mutex_unlock(&dev_priv->gmbus_mutex); + mutex_unlock(&dev_priv->display.gmbus.mutex); for_each_intel_encoder_with_psr(&dev_priv->drm, encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -2124,9 +2124,9 @@ static void intel_set_cdclk(struct drm_i915_private *dev_priv, intel_audio_cdclk_change_post(dev_priv); if (drm_WARN(&dev_priv->drm, - intel_cdclk_changed(&dev_priv->cdclk.hw, cdclk_config), + intel_cdclk_changed(&dev_priv->display.cdclk.hw, cdclk_config), "cdclk state doesn't match!\n")) { - intel_cdclk_dump_config(dev_priv, &dev_priv->cdclk.hw, "[hw state]"); + intel_cdclk_dump_config(dev_priv, &dev_priv->display.cdclk.hw, "[hw state]"); intel_cdclk_dump_config(dev_priv, cdclk_config, "[sw state]"); } } @@ -2300,7 +2300,7 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) min_cdclk = max(min_cdclk, (int)crtc_state->pixel_rate); /* - * HACK. Currently for TGL platforms we calculate + * HACK. Currently for TGL/DG2 platforms we calculate * min_cdclk initially based on pixel_rate divided * by 2, accounting for also plane requirements, * however in some cases the lowest possible CDCLK @@ -2308,14 +2308,14 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state) * Explicitly stating here that this seems to be currently * rather a Hack, than final solution. */ - if (IS_TIGERLAKE(dev_priv)) { + if (IS_TIGERLAKE(dev_priv) || IS_DG2(dev_priv)) { /* * Clamp to max_cdclk_freq in case pixel rate is higher, * in order not to break an 8K, but still leave W/A at place. */ min_cdclk = max_t(int, min_cdclk, min_t(int, crtc_state->pixel_rate, - dev_priv->max_cdclk_freq)); + dev_priv->display.cdclk.max_cdclk_freq)); } return min_cdclk; @@ -2368,10 +2368,10 @@ static int intel_compute_min_cdclk(struct intel_cdclk_state *cdclk_state) for_each_pipe(dev_priv, pipe) min_cdclk = max(cdclk_state->min_cdclk[pipe], min_cdclk); - if (min_cdclk > dev_priv->max_cdclk_freq) { + if (min_cdclk > dev_priv->display.cdclk.max_cdclk_freq) { drm_dbg_kms(&dev_priv->drm, "required cdclk (%d kHz) exceeds max (%d kHz)\n", - min_cdclk, dev_priv->max_cdclk_freq); + min_cdclk, dev_priv->display.cdclk.max_cdclk_freq); return -EINVAL; } @@ -2643,7 +2643,7 @@ intel_atomic_get_cdclk_state(struct intel_atomic_state *state) struct drm_i915_private *dev_priv = to_i915(state->base.dev); struct intel_global_state *cdclk_state; - cdclk_state = intel_atomic_get_global_obj_state(state, &dev_priv->cdclk.obj); + cdclk_state = intel_atomic_get_global_obj_state(state, &dev_priv->display.cdclk.obj); if (IS_ERR(cdclk_state)) return ERR_CAST(cdclk_state); @@ -2693,7 +2693,7 @@ int intel_cdclk_init(struct drm_i915_private *dev_priv) if (!cdclk_state) return -ENOMEM; - intel_atomic_global_obj_init(dev_priv, &dev_priv->cdclk.obj, + intel_atomic_global_obj_init(dev_priv, &dev_priv->display.cdclk.obj, &cdclk_state->base, &intel_cdclk_funcs); return 0; @@ -2799,7 +2799,7 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state) static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) { - int max_cdclk_freq = dev_priv->max_cdclk_freq; + int max_cdclk_freq = dev_priv->display.cdclk.max_cdclk_freq; if (DISPLAY_VER(dev_priv) >= 10) return 2 * max_cdclk_freq; @@ -2825,19 +2825,19 @@ static int intel_compute_max_dotclk(struct drm_i915_private *dev_priv) void intel_update_max_cdclk(struct drm_i915_private *dev_priv) { if (IS_JSL_EHL(dev_priv)) { - if (dev_priv->cdclk.hw.ref == 24000) - dev_priv->max_cdclk_freq = 552000; + if (dev_priv->display.cdclk.hw.ref == 24000) + dev_priv->display.cdclk.max_cdclk_freq = 552000; else - dev_priv->max_cdclk_freq = 556800; + dev_priv->display.cdclk.max_cdclk_freq = 556800; } else if (DISPLAY_VER(dev_priv) >= 11) { - if (dev_priv->cdclk.hw.ref == 24000) - dev_priv->max_cdclk_freq = 648000; + if (dev_priv->display.cdclk.hw.ref == 24000) + dev_priv->display.cdclk.max_cdclk_freq = 648000; else - dev_priv->max_cdclk_freq = 652800; + dev_priv->display.cdclk.max_cdclk_freq = 652800; } else if (IS_GEMINILAKE(dev_priv)) { - dev_priv->max_cdclk_freq = 316800; + dev_priv->display.cdclk.max_cdclk_freq = 316800; } else if (IS_BROXTON(dev_priv)) { - dev_priv->max_cdclk_freq = 624000; + dev_priv->display.cdclk.max_cdclk_freq = 624000; } else if (DISPLAY_VER(dev_priv) == 9) { u32 limit = intel_de_read(dev_priv, SKL_DFSM) & SKL_DFSM_CDCLK_LIMIT_MASK; int max_cdclk, vco; @@ -2859,7 +2859,7 @@ void intel_update_max_cdclk(struct drm_i915_private *dev_priv) else max_cdclk = 308571; - dev_priv->max_cdclk_freq = skl_calc_cdclk(max_cdclk, vco); + dev_priv->display.cdclk.max_cdclk_freq = skl_calc_cdclk(max_cdclk, vco); } else if (IS_BROADWELL(dev_priv)) { /* * FIXME with extra cooling we can allow @@ -2868,26 +2868,26 @@ void intel_update_max_cdclk(struct drm_i915_private *dev_priv) * available? PCI ID, VTB, something else? */ if (intel_de_read(dev_priv, FUSE_STRAP) & HSW_CDCLK_LIMIT) - dev_priv->max_cdclk_freq = 450000; + dev_priv->display.cdclk.max_cdclk_freq = 450000; else if (IS_BDW_ULX(dev_priv)) - dev_priv->max_cdclk_freq = 450000; + dev_priv->display.cdclk.max_cdclk_freq = 450000; else if (IS_BDW_ULT(dev_priv)) - dev_priv->max_cdclk_freq = 540000; + dev_priv->display.cdclk.max_cdclk_freq = 540000; else - dev_priv->max_cdclk_freq = 675000; + dev_priv->display.cdclk.max_cdclk_freq = 675000; } else if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->max_cdclk_freq = 320000; + dev_priv->display.cdclk.max_cdclk_freq = 320000; } else if (IS_VALLEYVIEW(dev_priv)) { - dev_priv->max_cdclk_freq = 400000; + dev_priv->display.cdclk.max_cdclk_freq = 400000; } else { /* otherwise assume cdclk is fixed */ - dev_priv->max_cdclk_freq = dev_priv->cdclk.hw.cdclk; + dev_priv->display.cdclk.max_cdclk_freq = dev_priv->display.cdclk.hw.cdclk; } dev_priv->max_dotclk_freq = intel_compute_max_dotclk(dev_priv); drm_dbg(&dev_priv->drm, "Max CD clock rate: %d kHz\n", - dev_priv->max_cdclk_freq); + dev_priv->display.cdclk.max_cdclk_freq); drm_dbg(&dev_priv->drm, "Max dotclock rate: %d kHz\n", dev_priv->max_dotclk_freq); @@ -2901,7 +2901,7 @@ void intel_update_max_cdclk(struct drm_i915_private *dev_priv) */ void intel_update_cdclk(struct drm_i915_private *dev_priv) { - intel_cdclk_get_cdclk(dev_priv, &dev_priv->cdclk.hw); + intel_cdclk_get_cdclk(dev_priv, &dev_priv->display.cdclk.hw); /* * 9:0 CMBUS [sic] CDCLK frequency (cdfreq): @@ -2911,7 +2911,7 @@ void intel_update_cdclk(struct drm_i915_private *dev_priv) */ if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) intel_de_write(dev_priv, GMBUSFREQ_VLV, - DIV_ROUND_UP(dev_priv->cdclk.hw.cdclk, 1000)); + DIV_ROUND_UP(dev_priv->display.cdclk.hw.cdclk, 1000)); } static int dg1_rawclk(struct drm_i915_private *dev_priv) @@ -3036,6 +3036,13 @@ u32 intel_read_rawclk(struct drm_i915_private *dev_priv) if (INTEL_PCH_TYPE(dev_priv) >= PCH_DG1) freq = dg1_rawclk(dev_priv); + else if (INTEL_PCH_TYPE(dev_priv) >= PCH_MTP) + /* + * MTL always uses a 38.4 MHz rawclk. The bspec tells us + * "RAWCLK_FREQ defaults to the values for 38.4 and does + * not need to be programmed." + */ + freq = 38400; else if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP) freq = cnp_rawclk(dev_priv); else if (HAS_PCH_SPLIT(dev_priv)) @@ -3187,78 +3194,78 @@ static const struct intel_cdclk_funcs i830_cdclk_funcs = { void intel_init_cdclk_hooks(struct drm_i915_private *dev_priv) { if (IS_DG2(dev_priv)) { - dev_priv->cdclk_funcs = &tgl_cdclk_funcs; - dev_priv->cdclk.table = dg2_cdclk_table; + dev_priv->display.funcs.cdclk = &tgl_cdclk_funcs; + dev_priv->display.cdclk.table = dg2_cdclk_table; } else if (IS_ALDERLAKE_P(dev_priv)) { - dev_priv->cdclk_funcs = &tgl_cdclk_funcs; + dev_priv->display.funcs.cdclk = &tgl_cdclk_funcs; /* Wa_22011320316:adl-p[a0] */ if (IS_ADLP_DISPLAY_STEP(dev_priv, STEP_A0, STEP_B0)) - dev_priv->cdclk.table = adlp_a_step_cdclk_table; + dev_priv->display.cdclk.table = adlp_a_step_cdclk_table; else - dev_priv->cdclk.table = adlp_cdclk_table; + dev_priv->display.cdclk.table = adlp_cdclk_table; } else if (IS_ROCKETLAKE(dev_priv)) { - dev_priv->cdclk_funcs = &tgl_cdclk_funcs; - dev_priv->cdclk.table = rkl_cdclk_table; + dev_priv->display.funcs.cdclk = &tgl_cdclk_funcs; + dev_priv->display.cdclk.table = rkl_cdclk_table; } else if (DISPLAY_VER(dev_priv) >= 12) { - dev_priv->cdclk_funcs = &tgl_cdclk_funcs; - dev_priv->cdclk.table = icl_cdclk_table; + dev_priv->display.funcs.cdclk = &tgl_cdclk_funcs; + dev_priv->display.cdclk.table = icl_cdclk_table; } else if (IS_JSL_EHL(dev_priv)) { - dev_priv->cdclk_funcs = &ehl_cdclk_funcs; - dev_priv->cdclk.table = icl_cdclk_table; + dev_priv->display.funcs.cdclk = &ehl_cdclk_funcs; + dev_priv->display.cdclk.table = icl_cdclk_table; } else if (DISPLAY_VER(dev_priv) >= 11) { - dev_priv->cdclk_funcs = &icl_cdclk_funcs; - dev_priv->cdclk.table = icl_cdclk_table; + dev_priv->display.funcs.cdclk = &icl_cdclk_funcs; + dev_priv->display.cdclk.table = icl_cdclk_table; } else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) { - dev_priv->cdclk_funcs = &bxt_cdclk_funcs; + dev_priv->display.funcs.cdclk = &bxt_cdclk_funcs; if (IS_GEMINILAKE(dev_priv)) - dev_priv->cdclk.table = glk_cdclk_table; + dev_priv->display.cdclk.table = glk_cdclk_table; else - dev_priv->cdclk.table = bxt_cdclk_table; + dev_priv->display.cdclk.table = bxt_cdclk_table; } else if (DISPLAY_VER(dev_priv) == 9) { - dev_priv->cdclk_funcs = &skl_cdclk_funcs; + dev_priv->display.funcs.cdclk = &skl_cdclk_funcs; } else if (IS_BROADWELL(dev_priv)) { - dev_priv->cdclk_funcs = &bdw_cdclk_funcs; + dev_priv->display.funcs.cdclk = &bdw_cdclk_funcs; } else if (IS_HASWELL(dev_priv)) { - dev_priv->cdclk_funcs = &hsw_cdclk_funcs; + dev_priv->display.funcs.cdclk = &hsw_cdclk_funcs; } else if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->cdclk_funcs = &chv_cdclk_funcs; + dev_priv->display.funcs.cdclk = &chv_cdclk_funcs; } else if (IS_VALLEYVIEW(dev_priv)) { - dev_priv->cdclk_funcs = &vlv_cdclk_funcs; + dev_priv->display.funcs.cdclk = &vlv_cdclk_funcs; } else if (IS_SANDYBRIDGE(dev_priv) || IS_IVYBRIDGE(dev_priv)) { - dev_priv->cdclk_funcs = &fixed_400mhz_cdclk_funcs; + dev_priv->display.funcs.cdclk = &fixed_400mhz_cdclk_funcs; } else if (IS_IRONLAKE(dev_priv)) { - dev_priv->cdclk_funcs = &ilk_cdclk_funcs; + dev_priv->display.funcs.cdclk = &ilk_cdclk_funcs; } else if (IS_GM45(dev_priv)) { - dev_priv->cdclk_funcs = &gm45_cdclk_funcs; + dev_priv->display.funcs.cdclk = &gm45_cdclk_funcs; } else if (IS_G45(dev_priv)) { - dev_priv->cdclk_funcs = &g33_cdclk_funcs; + dev_priv->display.funcs.cdclk = &g33_cdclk_funcs; } else if (IS_I965GM(dev_priv)) { - dev_priv->cdclk_funcs = &i965gm_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i965gm_cdclk_funcs; } else if (IS_I965G(dev_priv)) { - dev_priv->cdclk_funcs = &fixed_400mhz_cdclk_funcs; + dev_priv->display.funcs.cdclk = &fixed_400mhz_cdclk_funcs; } else if (IS_PINEVIEW(dev_priv)) { - dev_priv->cdclk_funcs = &pnv_cdclk_funcs; + dev_priv->display.funcs.cdclk = &pnv_cdclk_funcs; } else if (IS_G33(dev_priv)) { - dev_priv->cdclk_funcs = &g33_cdclk_funcs; + dev_priv->display.funcs.cdclk = &g33_cdclk_funcs; } else if (IS_I945GM(dev_priv)) { - dev_priv->cdclk_funcs = &i945gm_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i945gm_cdclk_funcs; } else if (IS_I945G(dev_priv)) { - dev_priv->cdclk_funcs = &fixed_400mhz_cdclk_funcs; + dev_priv->display.funcs.cdclk = &fixed_400mhz_cdclk_funcs; } else if (IS_I915GM(dev_priv)) { - dev_priv->cdclk_funcs = &i915gm_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i915gm_cdclk_funcs; } else if (IS_I915G(dev_priv)) { - dev_priv->cdclk_funcs = &i915g_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i915g_cdclk_funcs; } else if (IS_I865G(dev_priv)) { - dev_priv->cdclk_funcs = &i865g_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i865g_cdclk_funcs; } else if (IS_I85X(dev_priv)) { - dev_priv->cdclk_funcs = &i85x_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i85x_cdclk_funcs; } else if (IS_I845G(dev_priv)) { - dev_priv->cdclk_funcs = &i845g_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i845g_cdclk_funcs; } else if (IS_I830(dev_priv)) { - dev_priv->cdclk_funcs = &i830_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i830_cdclk_funcs; } - if (drm_WARN(&dev_priv->drm, !dev_priv->cdclk_funcs, + if (drm_WARN(&dev_priv->drm, !dev_priv->display.funcs.cdclk, "Unknown platform. Assuming i830\n")) - dev_priv->cdclk_funcs = &i830_cdclk_funcs; + dev_priv->display.funcs.cdclk = &i830_cdclk_funcs; } diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.h b/drivers/gpu/drm/i915/display/intel_cdclk.h index b535cf6a7d9e..c674879a84a5 100644 --- a/drivers/gpu/drm/i915/display/intel_cdclk.h +++ b/drivers/gpu/drm/i915/display/intel_cdclk.h @@ -77,9 +77,9 @@ intel_atomic_get_cdclk_state(struct intel_atomic_state *state); #define to_intel_cdclk_state(x) container_of((x), struct intel_cdclk_state, base) #define intel_atomic_get_old_cdclk_state(state) \ - to_intel_cdclk_state(intel_atomic_get_old_global_obj_state(state, &to_i915(state->base.dev)->cdclk.obj)) + to_intel_cdclk_state(intel_atomic_get_old_global_obj_state(state, &to_i915(state->base.dev)->display.cdclk.obj)) #define intel_atomic_get_new_cdclk_state(state) \ - to_intel_cdclk_state(intel_atomic_get_new_global_obj_state(state, &to_i915(state->base.dev)->cdclk.obj)) + to_intel_cdclk_state(intel_atomic_get_new_global_obj_state(state, &to_i915(state->base.dev)->display.cdclk.obj)) int intel_cdclk_init(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c index 9583d17e858d..6bda4274eae9 100644 --- a/drivers/gpu/drm/i915/display/intel_color.c +++ b/drivers/gpu/drm/i915/display/intel_color.c @@ -26,6 +26,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_dpll.h" +#include "intel_dsb.h" #include "vlv_dsi_pll.h" struct intel_color_funcs { @@ -1167,22 +1168,22 @@ void intel_color_load_luts(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - dev_priv->color_funcs->load_luts(crtc_state); + dev_priv->display.funcs.color->load_luts(crtc_state); } void intel_color_commit_noarm(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - if (dev_priv->color_funcs->color_commit_noarm) - dev_priv->color_funcs->color_commit_noarm(crtc_state); + if (dev_priv->display.funcs.color->color_commit_noarm) + dev_priv->display.funcs.color->color_commit_noarm(crtc_state); } void intel_color_commit_arm(const struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - dev_priv->color_funcs->color_commit_arm(crtc_state); + dev_priv->display.funcs.color->color_commit_arm(crtc_state); } static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state) @@ -1238,15 +1239,15 @@ int intel_color_check(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - return dev_priv->color_funcs->color_check(crtc_state); + return dev_priv->display.funcs.color->color_check(crtc_state); } void intel_color_get_config(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - if (dev_priv->color_funcs->read_luts) - dev_priv->color_funcs->read_luts(crtc_state); + if (dev_priv->display.funcs.color->read_luts) + dev_priv->display.funcs.color->read_luts(crtc_state); } static bool need_plane_update(struct intel_plane *plane, @@ -2225,28 +2226,28 @@ void intel_color_init(struct intel_crtc *crtc) if (HAS_GMCH(dev_priv)) { if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->color_funcs = &chv_color_funcs; + dev_priv->display.funcs.color = &chv_color_funcs; } else if (DISPLAY_VER(dev_priv) >= 4) { - dev_priv->color_funcs = &i965_color_funcs; + dev_priv->display.funcs.color = &i965_color_funcs; } else { - dev_priv->color_funcs = &i9xx_color_funcs; + dev_priv->display.funcs.color = &i9xx_color_funcs; } } else { if (DISPLAY_VER(dev_priv) >= 11) - dev_priv->color_funcs = &icl_color_funcs; + dev_priv->display.funcs.color = &icl_color_funcs; else if (DISPLAY_VER(dev_priv) == 10) - dev_priv->color_funcs = &glk_color_funcs; + dev_priv->display.funcs.color = &glk_color_funcs; else if (DISPLAY_VER(dev_priv) == 9) - dev_priv->color_funcs = &skl_color_funcs; + dev_priv->display.funcs.color = &skl_color_funcs; else if (DISPLAY_VER(dev_priv) == 8) - dev_priv->color_funcs = &bdw_color_funcs; + dev_priv->display.funcs.color = &bdw_color_funcs; else if (DISPLAY_VER(dev_priv) == 7) { if (IS_HASWELL(dev_priv)) - dev_priv->color_funcs = &hsw_color_funcs; + dev_priv->display.funcs.color = &hsw_color_funcs; else - dev_priv->color_funcs = &ivb_color_funcs; + dev_priv->display.funcs.color = &ivb_color_funcs; } else - dev_priv->color_funcs = &ilk_color_funcs; + dev_priv->display.funcs.color = &ilk_color_funcs; } drm_crtc_enable_color_mgmt(&crtc->base, diff --git a/drivers/gpu/drm/i915/display/intel_connector.c b/drivers/gpu/drm/i915/display/intel_connector.c index 1dcc268927a2..6d5cbeb8df4d 100644 --- a/drivers/gpu/drm/i915/display/intel_connector.c +++ b/drivers/gpu/drm/i915/display/intel_connector.c @@ -229,7 +229,7 @@ intel_attach_force_audio_property(struct drm_connector *connector) struct drm_i915_private *dev_priv = to_i915(dev); struct drm_property *prop; - prop = dev_priv->force_audio_property; + prop = dev_priv->display.properties.force_audio; if (prop == NULL) { prop = drm_property_create_enum(dev, 0, "audio", @@ -238,7 +238,7 @@ intel_attach_force_audio_property(struct drm_connector *connector) if (prop == NULL) return; - dev_priv->force_audio_property = prop; + dev_priv->display.properties.force_audio = prop; } drm_object_attach_property(&connector->base, prop, 0); } @@ -256,7 +256,7 @@ intel_attach_broadcast_rgb_property(struct drm_connector *connector) struct drm_i915_private *dev_priv = to_i915(dev); struct drm_property *prop; - prop = dev_priv->broadcast_rgb_property; + prop = dev_priv->display.properties.broadcast_rgb; if (prop == NULL) { prop = drm_property_create_enum(dev, DRM_MODE_PROP_ENUM, "Broadcast RGB", @@ -265,7 +265,7 @@ intel_attach_broadcast_rgb_property(struct drm_connector *connector) if (prop == NULL) return; - dev_priv->broadcast_rgb_property = prop; + dev_priv->display.properties.broadcast_rgb = prop; } drm_object_attach_property(&connector->base, prop, 0); diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 6a3893c8ff22..4a8ff2f97608 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -46,6 +46,7 @@ #include "intel_gmbus.h" #include "intel_hotplug.h" #include "intel_pch_display.h" +#include "intel_pch_refclk.h" /* Here's the desired hotplug mode */ #define ADPA_HOTPLUG_BITS (ADPA_CRT_HOTPLUG_PERIOD_128 | \ @@ -444,6 +445,8 @@ static int hsw_crt_compute_config(struct intel_encoder *encoder, /* FDI must always be 2.7 GHz */ pipe_config->port_clock = 135000 * 2; + adjusted_mode->crtc_clock = lpt_iclkip(pipe_config); + return 0; } @@ -643,9 +646,7 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector) struct i2c_adapter *i2c; bool ret = false; - BUG_ON(crt->base.type != INTEL_OUTPUT_ANALOG); - - i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->vbt.crt_ddc_pin); + i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->display.vbt.crt_ddc_pin); edid = intel_crt_get_edid(connector, i2c); if (edid) { @@ -931,7 +932,7 @@ static int intel_crt_get_modes(struct drm_connector *connector) wakeref = intel_display_power_get(dev_priv, intel_encoder->power_domain); - i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->vbt.crt_ddc_pin); + i2c = intel_gmbus_get_adapter(dev_priv, dev_priv->display.vbt.crt_ddc_pin); ret = intel_crt_ddc_get_modes(connector, i2c); if (ret || !IS_G4X(dev_priv)) goto out; @@ -1110,8 +1111,8 @@ void intel_crt_init(struct drm_i915_private *dev_priv) u32 fdi_config = FDI_RX_POLARITY_REVERSED_LPT | FDI_RX_LINK_REVERSAL_OVERRIDE; - dev_priv->fdi_rx_config = intel_de_read(dev_priv, - FDI_RX_CTL(PIPE_A)) & fdi_config; + dev_priv->display.fdi.rx_config = intel_de_read(dev_priv, + FDI_RX_CTL(PIPE_A)) & fdi_config; } intel_crt_reset(&crt->base.base); diff --git a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c index 4ca6e9493ff2..e9212f69c360 100644 --- a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c +++ b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c @@ -134,8 +134,8 @@ static void intel_dump_plane_state(const struct intel_plane_state *plane_state) plane->base.base.id, plane->base.name, fb->base.id, fb->width, fb->height, &fb->format->format, fb->modifier, str_yes_no(plane_state->uapi.visible)); - drm_dbg_kms(&i915->drm, "\trotation: 0x%x, scaler: %d\n", - plane_state->hw.rotation, plane_state->scaler_id); + drm_dbg_kms(&i915->drm, "\trotation: 0x%x, scaler: %d, scaling_filter: %d\n", + plane_state->hw.rotation, plane_state->scaler_id, plane_state->hw.scaling_filter); if (plane_state->uapi.visible) drm_dbg_kms(&i915->drm, "\tsrc: " DRM_RECT_FP_FMT " dst: " DRM_RECT_FMT "\n", @@ -262,10 +262,11 @@ void intel_crtc_state_dump(const struct intel_crtc_state *pipe_config, if (DISPLAY_VER(i915) >= 9) drm_dbg_kms(&i915->drm, - "num_scalers: %d, scaler_users: 0x%x, scaler_id: %d\n", + "num_scalers: %d, scaler_users: 0x%x, scaler_id: %d, scaling_filter: %d\n", crtc->num_scalers, pipe_config->scaler_state.scaler_users, - pipe_config->scaler_state.scaler_id); + pipe_config->scaler_state.scaler_id, + pipe_config->hw.scaling_filter); if (HAS_GMCH(i915)) drm_dbg_kms(&i915->drm, diff --git a/drivers/gpu/drm/i915/display/intel_cursor.c b/drivers/gpu/drm/i915/display/intel_cursor.c index 16ac560eab49..87899e89b3a7 100644 --- a/drivers/gpu/drm/i915/display/intel_cursor.c +++ b/drivers/gpu/drm/i915/display/intel_cursor.c @@ -19,9 +19,9 @@ #include "intel_fb.h" #include "intel_fb_pin.h" #include "intel_frontbuffer.h" -#include "intel_pm.h" #include "intel_psr.h" #include "intel_sprite.h" +#include "skl_watermark.h" /* Cursor formats */ static const u32 intel_cursor_formats[] = { diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 2330604b0bcc..da8472cdc135 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -57,6 +57,7 @@ #include "intel_lspcon.h" #include "intel_pps.h" #include "intel_psr.h" +#include "intel_quirks.h" #include "intel_snps_phy.h" #include "intel_sprite.h" #include "intel_tc.h" @@ -323,28 +324,6 @@ static int icl_calc_tbt_pll_link(struct drm_i915_private *dev_priv, } } -int intel_crtc_dotclock(const struct intel_crtc_state *pipe_config) -{ - int dotclock; - - if (intel_crtc_has_dp_encoder(pipe_config)) - dotclock = intel_dotclock_calculate(pipe_config->port_clock, - &pipe_config->dp_m_n); - else if (pipe_config->has_hdmi_sink && pipe_config->pipe_bpp > 24) - dotclock = pipe_config->port_clock * 24 / pipe_config->pipe_bpp; - else - dotclock = pipe_config->port_clock; - - if (pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 && - !intel_crtc_has_dp_encoder(pipe_config)) - dotclock *= 2; - - if (pipe_config->pixel_multiplier) - dotclock /= pipe_config->pixel_multiplier; - - return dotclock; -} - static void ddi_dotclock_get(struct intel_crtc_state *pipe_config) { /* CRT dotclock is determined via other means */ @@ -631,7 +610,7 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state intel_de_write(dev_priv, TRANS_DDI_FUNC_CTL(cpu_transcoder), ctl); - if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME && + if (intel_has_quirk(dev_priv, QUIRK_INCREASE_DDI_DISABLED_TIME) && intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) { drm_dbg_kms(&dev_priv->drm, "Quirk Increase DDI disabled time\n"); @@ -1425,7 +1404,7 @@ hsw_set_signal_levels(struct intel_encoder *encoder, static void _icl_ddi_enable_clock(struct drm_i915_private *i915, i915_reg_t reg, u32 clk_sel_mask, u32 clk_sel, u32 clk_off) { - mutex_lock(&i915->dpll.lock); + mutex_lock(&i915->display.dpll.lock); intel_de_rmw(i915, reg, clk_sel_mask, clk_sel); @@ -1435,17 +1414,17 @@ static void _icl_ddi_enable_clock(struct drm_i915_private *i915, i915_reg_t reg, */ intel_de_rmw(i915, reg, clk_off, 0); - mutex_unlock(&i915->dpll.lock); + mutex_unlock(&i915->display.dpll.lock); } static void _icl_ddi_disable_clock(struct drm_i915_private *i915, i915_reg_t reg, u32 clk_off) { - mutex_lock(&i915->dpll.lock); + mutex_lock(&i915->display.dpll.lock); intel_de_rmw(i915, reg, 0, clk_off); - mutex_unlock(&i915->dpll.lock); + mutex_unlock(&i915->display.dpll.lock); } static bool _icl_ddi_is_clock_enabled(struct drm_i915_private *i915, i915_reg_t reg, @@ -1720,12 +1699,12 @@ static void icl_ddi_tc_enable_clock(struct intel_encoder *encoder, intel_de_write(i915, DDI_CLK_SEL(port), icl_pll_to_ddi_clk_sel(encoder, crtc_state)); - mutex_lock(&i915->dpll.lock); + mutex_lock(&i915->display.dpll.lock); intel_de_rmw(i915, ICL_DPCLKA_CFGCR0, ICL_DPCLKA_CFGCR0_TC_CLK_OFF(tc_port), 0); - mutex_unlock(&i915->dpll.lock); + mutex_unlock(&i915->display.dpll.lock); } static void icl_ddi_tc_disable_clock(struct intel_encoder *encoder) @@ -1734,12 +1713,12 @@ static void icl_ddi_tc_disable_clock(struct intel_encoder *encoder) enum tc_port tc_port = intel_port_to_tc(i915, encoder->port); enum port port = encoder->port; - mutex_lock(&i915->dpll.lock); + mutex_lock(&i915->display.dpll.lock); intel_de_rmw(i915, ICL_DPCLKA_CFGCR0, 0, ICL_DPCLKA_CFGCR0_TC_CLK_OFF(tc_port)); - mutex_unlock(&i915->dpll.lock); + mutex_unlock(&i915->display.dpll.lock); intel_de_write(i915, DDI_CLK_SEL(port), DDI_CLK_SEL_NONE); } @@ -1824,7 +1803,7 @@ static void skl_ddi_enable_clock(struct intel_encoder *encoder, if (drm_WARN_ON(&i915->drm, !pll)) return; - mutex_lock(&i915->dpll.lock); + mutex_lock(&i915->display.dpll.lock); intel_de_rmw(i915, DPLL_CTRL2, DPLL_CTRL2_DDI_CLK_OFF(port) | @@ -1832,7 +1811,7 @@ static void skl_ddi_enable_clock(struct intel_encoder *encoder, DPLL_CTRL2_DDI_CLK_SEL(pll->info->id, port) | DPLL_CTRL2_DDI_SEL_OVERRIDE(port)); - mutex_unlock(&i915->dpll.lock); + mutex_unlock(&i915->display.dpll.lock); } static void skl_ddi_disable_clock(struct intel_encoder *encoder) @@ -1840,12 +1819,12 @@ static void skl_ddi_disable_clock(struct intel_encoder *encoder) struct drm_i915_private *i915 = to_i915(encoder->base.dev); enum port port = encoder->port; - mutex_lock(&i915->dpll.lock); + mutex_lock(&i915->display.dpll.lock); intel_de_rmw(i915, DPLL_CTRL2, 0, DPLL_CTRL2_DDI_CLK_OFF(port)); - mutex_unlock(&i915->dpll.lock); + mutex_unlock(&i915->display.dpll.lock); } static bool skl_ddi_is_clock_enabled(struct intel_encoder *encoder) @@ -2691,10 +2670,14 @@ static void intel_ddi_post_disable_hdmi(struct intel_atomic_state *state, dig_port->set_infoframes(encoder, false, old_crtc_state, old_conn_state); - intel_ddi_disable_pipe_clock(old_crtc_state); + if (DISPLAY_VER(dev_priv) < 12) + intel_ddi_disable_pipe_clock(old_crtc_state); intel_disable_ddi_buf(encoder, old_crtc_state); + if (DISPLAY_VER(dev_priv) >= 12) + intel_ddi_disable_pipe_clock(old_crtc_state); + intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain, fetch_and_zero(&dig_port->ddi_io_wakeref)); @@ -2862,6 +2845,8 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, struct intel_digital_port *dig_port = enc_to_dig_port(encoder); struct drm_connector *connector = conn_state->connector; enum port port = encoder->port; + enum phy phy = intel_port_to_phy(dev_priv, port); + u32 buf_ctl; if (!intel_hdmi_handle_sink_scrambling(encoder, connector, crtc_state->hdmi_high_tmds_clock_ratio, @@ -2919,8 +2904,12 @@ static void intel_enable_ddi_hdmi(struct intel_atomic_state *state, * On ADL_P the PHY link rate and lane count must be programmed but * these are both 0 for HDMI. */ - intel_de_write(dev_priv, DDI_BUF_CTL(port), - dig_port->saved_port_bits | DDI_BUF_CTL_ENABLE); + buf_ctl = dig_port->saved_port_bits | DDI_BUF_CTL_ENABLE; + if (IS_ALDERLAKE_P(dev_priv) && intel_phy_is_tc(dev_priv, phy)) { + drm_WARN_ON(&dev_priv->drm, !intel_tc_port_in_legacy_mode(dig_port)); + buf_ctl |= DDI_BUF_CTL_TC_PHY_OWNERSHIP; + } + intel_de_write(dev_priv, DDI_BUF_CTL(port), buf_ctl); intel_audio_codec_enable(encoder, crtc_state, conn_state); } @@ -3611,10 +3600,22 @@ static void intel_ddi_sync_state(struct intel_encoder *encoder, static bool intel_ddi_initial_fastset_check(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state) { - if (intel_crtc_has_dp_encoder(crtc_state)) - return intel_dp_initial_fastset_check(encoder, crtc_state); + struct drm_i915_private *i915 = to_i915(encoder->base.dev); + enum phy phy = intel_port_to_phy(i915, encoder->port); + bool fastset = true; - return true; + if (intel_phy_is_tc(i915, phy)) { + drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Forcing full modeset to compute TC port DPLLs\n", + encoder->base.base.id, encoder->base.name); + crtc_state->uapi.mode_changed = true; + fastset = false; + } + + if (intel_crtc_has_dp_encoder(crtc_state) && + !intel_dp_initial_fastset_check(encoder, crtc_state)) + fastset = false; + + return fastset; } static enum intel_output_type @@ -4028,7 +4029,7 @@ intel_ddi_hotplug(struct intel_encoder *encoder, static bool lpt_digital_port_connected(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - u32 bit = dev_priv->hotplug.pch_hpd[encoder->hpd_pin]; + u32 bit = dev_priv->display.hotplug.pch_hpd[encoder->hpd_pin]; return intel_de_read(dev_priv, SDEISR) & bit; } @@ -4036,7 +4037,7 @@ static bool lpt_digital_port_connected(struct intel_encoder *encoder) static bool hsw_digital_port_connected(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - u32 bit = dev_priv->hotplug.hpd[encoder->hpd_pin]; + u32 bit = dev_priv->display.hotplug.hpd[encoder->hpd_pin]; return intel_de_read(dev_priv, DEISR) & bit; } @@ -4044,7 +4045,7 @@ static bool hsw_digital_port_connected(struct intel_encoder *encoder) static bool bdw_digital_port_connected(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - u32 bit = dev_priv->hotplug.hpd[encoder->hpd_pin]; + u32 bit = dev_priv->display.hotplug.hpd[encoder->hpd_pin]; return intel_de_read(dev_priv, GEN8_DE_PORT_ISR) & bit; } diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 40fbf8a296e2..461c62c88413 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -91,6 +91,7 @@ #include "intel_dmc.h" #include "intel_dp_link_training.h" #include "intel_dpt.h" +#include "intel_dsb.h" #include "intel_fbc.h" #include "intel_fbdev.h" #include "intel_fdi.h" @@ -117,6 +118,7 @@ #include "i9xx_plane.h" #include "skl_scaler.h" #include "skl_universal_plane.h" +#include "skl_watermark.h" #include "vlv_dsi.h" #include "vlv_dsi_pll.h" #include "vlv_dsi_regs.h" @@ -163,16 +165,16 @@ static void ilk_pfit_enable(const struct intel_crtc_state *crtc_state); */ void intel_update_watermarks(struct drm_i915_private *dev_priv) { - if (dev_priv->wm_disp->update_wm) - dev_priv->wm_disp->update_wm(dev_priv); + if (dev_priv->display.funcs.wm->update_wm) + dev_priv->display.funcs.wm->update_wm(dev_priv); } static int intel_compute_pipe_wm(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - if (dev_priv->wm_disp->compute_pipe_wm) - return dev_priv->wm_disp->compute_pipe_wm(state, crtc); + if (dev_priv->display.funcs.wm->compute_pipe_wm) + return dev_priv->display.funcs.wm->compute_pipe_wm(state, crtc); return 0; } @@ -180,20 +182,20 @@ static int intel_compute_intermediate_wm(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - if (!dev_priv->wm_disp->compute_intermediate_wm) + if (!dev_priv->display.funcs.wm->compute_intermediate_wm) return 0; if (drm_WARN_ON(&dev_priv->drm, - !dev_priv->wm_disp->compute_pipe_wm)) + !dev_priv->display.funcs.wm->compute_pipe_wm)) return 0; - return dev_priv->wm_disp->compute_intermediate_wm(state, crtc); + return dev_priv->display.funcs.wm->compute_intermediate_wm(state, crtc); } static bool intel_initial_watermarks(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - if (dev_priv->wm_disp->initial_watermarks) { - dev_priv->wm_disp->initial_watermarks(state, crtc); + if (dev_priv->display.funcs.wm->initial_watermarks) { + dev_priv->display.funcs.wm->initial_watermarks(state, crtc); return true; } return false; @@ -203,23 +205,23 @@ static void intel_atomic_update_watermarks(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - if (dev_priv->wm_disp->atomic_update_watermarks) - dev_priv->wm_disp->atomic_update_watermarks(state, crtc); + if (dev_priv->display.funcs.wm->atomic_update_watermarks) + dev_priv->display.funcs.wm->atomic_update_watermarks(state, crtc); } static void intel_optimize_watermarks(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - if (dev_priv->wm_disp->optimize_watermarks) - dev_priv->wm_disp->optimize_watermarks(state, crtc); + if (dev_priv->display.funcs.wm->optimize_watermarks) + dev_priv->display.funcs.wm->optimize_watermarks(state, crtc); } static int intel_compute_global_watermarks(struct intel_atomic_state *state) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - if (dev_priv->wm_disp->compute_global_watermarks) - return dev_priv->wm_disp->compute_global_watermarks(state); + if (dev_priv->display.funcs.wm->compute_global_watermarks) + return dev_priv->display.funcs.wm->compute_global_watermarks(state); return 0; } @@ -618,7 +620,10 @@ void intel_disable_transcoder(const struct intel_crtc_state *old_crtc_state) if (!IS_I830(dev_priv)) val &= ~PIPECONF_ENABLE; - if (DISPLAY_VER(dev_priv) >= 12) + if (DISPLAY_VER(dev_priv) >= 14) + intel_de_rmw(dev_priv, MTL_CHICKEN_TRANS(cpu_transcoder), + FECSTALL_DIS_DPTSTREAM_DPTTG, 0); + else if (DISPLAY_VER(dev_priv) >= 12) intel_de_rmw(dev_priv, CHICKEN_TRANS(cpu_transcoder), FECSTALL_DIS_DPTSTREAM_DPTTG, 0); @@ -1486,7 +1491,7 @@ static void intel_encoders_update_prepare(struct intel_atomic_state *state) * Make sure the DPLL state is up-to-date for fastset TypeC ports after non-blocking commits. * TODO: Update the DPLL state for all cases in the encoder->update_prepare() hook. */ - if (i915->dpll.mgr) { + if (i915->display.dpll.mgr) { for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { if (intel_crtc_needs_modeset(new_crtc_state)) continue; @@ -1838,7 +1843,9 @@ static void hsw_set_frame_start_delay(const struct intel_crtc_state *crtc_state) { struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - i915_reg_t reg = CHICKEN_TRANS(crtc_state->cpu_transcoder); + enum transcoder transcoder = crtc_state->cpu_transcoder; + i915_reg_t reg = DISPLAY_VER(dev_priv) >= 14 ? MTL_CHICKEN_TRANS(transcoder) : + CHICKEN_TRANS(transcoder); u32 val; val = intel_de_read(dev_priv, reg); @@ -2080,22 +2087,20 @@ bool intel_phy_is_combo(struct drm_i915_private *dev_priv, enum phy phy) { if (phy == PHY_NONE) return false; - else if (IS_DG2(dev_priv)) - /* - * DG2 outputs labelled as "combo PHY" in the bspec use - * SNPS PHYs with completely different programming, - * hence we always return false here. - */ - return false; else if (IS_ALDERLAKE_S(dev_priv)) return phy <= PHY_E; else if (IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv)) return phy <= PHY_D; else if (IS_JSL_EHL(dev_priv)) return phy <= PHY_C; - else if (DISPLAY_VER(dev_priv) >= 11) + else if (IS_ALDERLAKE_P(dev_priv) || IS_DISPLAY_VER(dev_priv, 11, 12)) return phy <= PHY_B; else + /* + * DG2 outputs labelled as "combo PHY" in the bspec use + * SNPS PHYs with completely different programming, + * hence we always return false here. + */ return false; } @@ -2401,7 +2406,7 @@ static void i9xx_crtc_disable(struct intel_atomic_state *state, if (DISPLAY_VER(dev_priv) != 2) intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false); - if (!dev_priv->wm_disp->initial_watermarks) + if (!dev_priv->display.funcs.wm->initial_watermarks) intel_update_watermarks(dev_priv); /* clock the pipe down to 640x480@60 to potentially save power */ @@ -2660,7 +2665,7 @@ static int intel_crtc_compute_pipe_mode(struct intel_crtc_state *crtc_state) intel_mode_from_crtc_timings(pipe_mode, pipe_mode); if (DISPLAY_VER(i915) < 4) { - clock_limit = i915->max_cdclk_freq * 9 / 10; + clock_limit = i915->display.cdclk.max_cdclk_freq * 9 / 10; /* * Enable double wide mode when the dot clock @@ -2692,6 +2697,10 @@ static int intel_crtc_compute_config(struct intel_atomic_state *state, intel_atomic_get_new_crtc_state(state, crtc); int ret; + ret = intel_dpll_crtc_compute_clock(state, crtc); + if (ret) + return ret; + ret = intel_crtc_compute_pipe_src(crtc_state); if (ret) return ret; @@ -2718,19 +2727,11 @@ intel_reduce_m_n_ratio(u32 *num, u32 *den) } } -static void compute_m_n(unsigned int m, unsigned int n, - u32 *ret_m, u32 *ret_n, - bool constant_n) +static void compute_m_n(u32 *ret_m, u32 *ret_n, + u32 m, u32 n, u32 constant_n) { - /* - * Several DP dongles in particular seem to be fussy about - * too large link M/N values. Give N value as 0x8000 that - * should be acceptable by specific devices. 0x8000 is the - * specified fixed N value for asynchronous clock mode, - * which the devices expect also in synchronous clock mode. - */ if (constant_n) - *ret_n = DP_LINK_CONSTANT_N_VALUE; + *ret_n = constant_n; else *ret_n = min_t(unsigned int, roundup_pow_of_two(n), DATA_LINK_N_MAX); @@ -2742,22 +2743,28 @@ void intel_link_compute_m_n(u16 bits_per_pixel, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, - bool constant_n, bool fec_enable) + bool fec_enable) { u32 data_clock = bits_per_pixel * pixel_clock; if (fec_enable) data_clock = intel_dp_mode_to_fec_clock(data_clock); + /* + * Windows/BIOS uses fixed M/N values always. Follow suit. + * + * Also several DP dongles in particular seem to be fussy + * about too large link M/N values. Presumably the 20bit + * value used by Windows/BIOS is acceptable to everyone. + */ m_n->tu = 64; - compute_m_n(data_clock, - link_clock * nlanes * 8, - &m_n->data_m, &m_n->data_n, - constant_n); + compute_m_n(&m_n->data_m, &m_n->data_n, + data_clock, link_clock * nlanes * 8, + 0x8000000); - compute_m_n(pixel_clock, link_clock, - &m_n->link_m, &m_n->link_n, - constant_n); + compute_m_n(&m_n->link_m, &m_n->link_n, + pixel_clock, link_clock, + 0x80000); } static void intel_panel_sanitize_ssc(struct drm_i915_private *dev_priv) @@ -2773,12 +2780,12 @@ static void intel_panel_sanitize_ssc(struct drm_i915_private *dev_priv) PCH_DREF_CONTROL) & DREF_SSC1_ENABLE; - if (dev_priv->vbt.lvds_use_ssc != bios_lvds_use_ssc) { + if (dev_priv->display.vbt.lvds_use_ssc != bios_lvds_use_ssc) { drm_dbg_kms(&dev_priv->drm, "SSC %s by BIOS, overriding VBT which says %s\n", str_enabled_disabled(bios_lvds_use_ssc), - str_enabled_disabled(dev_priv->vbt.lvds_use_ssc)); - dev_priv->vbt.lvds_use_ssc = bios_lvds_use_ssc; + str_enabled_disabled(dev_priv->display.vbt.lvds_use_ssc)); + dev_priv->display.vbt.lvds_use_ssc = bios_lvds_use_ssc; } } } @@ -4126,7 +4133,9 @@ static bool hsw_get_pipe_config(struct intel_crtc *crtc, } if (!transcoder_is_dsi(pipe_config->cpu_transcoder)) { - tmp = intel_de_read(dev_priv, CHICKEN_TRANS(pipe_config->cpu_transcoder)); + tmp = intel_de_read(dev_priv, DISPLAY_VER(dev_priv) >= 14 ? + MTL_CHICKEN_TRANS(pipe_config->cpu_transcoder) : + CHICKEN_TRANS(pipe_config->cpu_transcoder)); pipe_config->framestart_delay = REG_FIELD_GET(HSW_FRAME_START_DELAY_MASK, tmp) + 1; } else { @@ -4145,7 +4154,7 @@ bool intel_crtc_get_pipe_config(struct intel_crtc_state *crtc_state) struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); struct drm_i915_private *i915 = to_i915(crtc->base.dev); - if (!i915->display->get_pipe_config(crtc, crtc_state)) + if (!i915->display.funcs.display->get_pipe_config(crtc, crtc_state)) return false; crtc_state->hw.active = true; @@ -4374,7 +4383,7 @@ static int i9xx_pll_refclk(struct drm_device *dev, u32 dpll = pipe_config->dpll_hw_state.dpll; if ((dpll & PLL_REF_INPUT_MASK) == PLLB_REF_INPUT_SPREADSPECTRUMIN) - return dev_priv->vbt.lvds_ssc_freq; + return dev_priv->display.vbt.lvds_ssc_freq; else if (HAS_PCH_SPLIT(dev_priv)) return 120000; else if (DISPLAY_VER(dev_priv) != 2) @@ -4492,7 +4501,31 @@ int intel_dotclock_calculate(int link_freq, if (!m_n->link_n) return 0; - return div_u64(mul_u32_u32(m_n->link_m, link_freq), m_n->link_n); + return DIV_ROUND_UP_ULL(mul_u32_u32(m_n->link_m, link_freq), + m_n->link_n); +} + +int intel_crtc_dotclock(const struct intel_crtc_state *pipe_config) +{ + int dotclock; + + if (intel_crtc_has_dp_encoder(pipe_config)) + dotclock = intel_dotclock_calculate(pipe_config->port_clock, + &pipe_config->dp_m_n); + else if (pipe_config->has_hdmi_sink && pipe_config->pipe_bpp > 24) + dotclock = DIV_ROUND_CLOSEST(pipe_config->port_clock * 24, + pipe_config->pipe_bpp); + else + dotclock = pipe_config->port_clock; + + if (pipe_config->output_format == INTEL_OUTPUT_FORMAT_YCBCR420 && + !intel_crtc_has_dp_encoder(pipe_config)) + dotclock *= 2; + + if (pipe_config->pixel_multiplier) + dotclock /= pipe_config->pixel_multiplier; + + return dotclock; } /* Returns the currently programmed mode of the given encoder. */ @@ -4753,7 +4786,7 @@ static u16 skl_linetime_wm(const struct intel_crtc_state *crtc_state) /* Display WA #1135: BXT:ALL GLK:ALL */ if ((IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) && - dev_priv->ipc_enabled) + skl_watermark_ipc_enabled(dev_priv)) linetime_wm /= 2; return min(linetime_wm, 0x1ff); @@ -4799,10 +4832,6 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state, crtc_state->update_wm_post = true; if (mode_changed) { - ret = intel_dpll_crtc_compute_clock(state, crtc); - if (ret) - return ret; - ret = intel_dpll_crtc_get_shared_dpll(state, crtc); if (ret) return ret; @@ -5367,46 +5396,14 @@ bool intel_fuzzy_clock_check(int clock1, int clock2) } static bool -intel_compare_m_n(unsigned int m, unsigned int n, - unsigned int m2, unsigned int n2, - bool exact) -{ - if (m == m2 && n == n2) - return true; - - if (exact || !m || !n || !m2 || !n2) - return false; - - BUILD_BUG_ON(DATA_LINK_M_N_MASK > INT_MAX); - - if (n > n2) { - while (n > n2) { - m2 <<= 1; - n2 <<= 1; - } - } else if (n < n2) { - while (n < n2) { - m <<= 1; - n <<= 1; - } - } - - if (n != n2) - return false; - - return intel_fuzzy_clock_check(m, m2); -} - -static bool intel_compare_link_m_n(const struct intel_link_m_n *m_n, - const struct intel_link_m_n *m2_n2, - bool exact) + const struct intel_link_m_n *m2_n2) { return m_n->tu == m2_n2->tu && - intel_compare_m_n(m_n->data_m, m_n->data_n, - m2_n2->data_m, m2_n2->data_n, exact) && - intel_compare_m_n(m_n->link_m, m_n->link_n, - m2_n2->link_m, m2_n2->link_n, exact); + m_n->data_m == m2_n2->data_m && + m_n->data_n == m2_n2->data_n && + m_n->link_m == m2_n2->link_m && + m_n->link_n == m2_n2->link_n; } static bool @@ -5600,8 +5597,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, #define PIPE_CONF_CHECK_M_N(name) do { \ if (!intel_compare_link_m_n(¤t_config->name, \ - &pipe_config->name,\ - !fastset)) { \ + &pipe_config->name)) { \ pipe_config_mismatch(fastset, crtc, __stringify(name), \ "(expected tu %i data %i/%i link %i/%i, " \ "found tu %i, data %i/%i link %i/%i)", \ @@ -5648,9 +5644,9 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, */ #define PIPE_CONF_CHECK_M_N_ALT(name, alt_name) do { \ if (!intel_compare_link_m_n(¤t_config->name, \ - &pipe_config->name, !fastset) && \ + &pipe_config->name) && \ !intel_compare_link_m_n(¤t_config->alt_name, \ - &pipe_config->name, !fastset)) { \ + &pipe_config->name)) { \ pipe_config_mismatch(fastset, crtc, __stringify(name), \ "(expected tu %i data %i/%i link %i/%i, " \ "or tu %i data %i/%i link %i/%i, " \ @@ -5685,16 +5681,6 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, } \ } while (0) -#define PIPE_CONF_CHECK_CLOCK_FUZZY(name) do { \ - if (!intel_fuzzy_clock_check(current_config->name, pipe_config->name)) { \ - pipe_config_mismatch(fastset, crtc, __stringify(name), \ - "(expected %i, found %i)", \ - current_config->name, \ - pipe_config->name); \ - ret = false; \ - } \ -} while (0) - #define PIPE_CONF_CHECK_INFOFRAME(name) do { \ if (!intel_compare_infoframe(¤t_config->infoframes.name, \ &pipe_config->infoframes.name)) { \ @@ -5750,8 +5736,9 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_I(lane_count); PIPE_CONF_CHECK_X(lane_lat_optim_mask); - if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) { - PIPE_CONF_CHECK_M_N_ALT(dp_m_n, dp_m2_n2); + if (HAS_DOUBLE_BUFFERED_M_N(dev_priv)) { + if (!fastset || !pipe_config->seamless_m_n) + PIPE_CONF_CHECK_M_N_ALT(dp_m_n, dp_m2_n2); } else { PIPE_CONF_CHECK_M_N(dp_m_n); PIPE_CONF_CHECK_M_N(dp_m2_n2); @@ -5813,7 +5800,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_RECT(pch_pfit.dst); PIPE_CONF_CHECK_I(scaler_state.scaler_id); - PIPE_CONF_CHECK_CLOCK_FUZZY(pixel_rate); + PIPE_CONF_CHECK_I(pixel_rate); PIPE_CONF_CHECK_X(gamma_mode); if (IS_CHERRYVIEW(dev_priv)) @@ -5840,7 +5827,7 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, PIPE_CONF_CHECK_BOOL(double_wide); - if (dev_priv->dpll.mgr) { + if (dev_priv->display.dpll.mgr) { PIPE_CONF_CHECK_P(shared_dpll); PIPE_CONF_CHECK_X(dpll_hw_state.dpll); @@ -5883,9 +5870,11 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, if (IS_G4X(dev_priv) || DISPLAY_VER(dev_priv) >= 5) PIPE_CONF_CHECK_I(pipe_bpp); - PIPE_CONF_CHECK_CLOCK_FUZZY(hw.pipe_mode.crtc_clock); - PIPE_CONF_CHECK_CLOCK_FUZZY(hw.adjusted_mode.crtc_clock); - PIPE_CONF_CHECK_CLOCK_FUZZY(port_clock); + if (!fastset || !pipe_config->seamless_m_n) { + PIPE_CONF_CHECK_I(hw.pipe_mode.crtc_clock); + PIPE_CONF_CHECK_I(hw.adjusted_mode.crtc_clock); + } + PIPE_CONF_CHECK_I(port_clock); PIPE_CONF_CHECK_I(min_voltage_level); @@ -5927,7 +5916,6 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config, #undef PIPE_CONF_CHECK_BOOL_INCOMPLETE #undef PIPE_CONF_CHECK_P #undef PIPE_CONF_CHECK_FLAGS -#undef PIPE_CONF_CHECK_CLOCK_FUZZY #undef PIPE_CONF_CHECK_COLOR_LUT #undef PIPE_CONF_CHECK_TIMINGS #undef PIPE_CONF_CHECK_RECT @@ -6049,20 +6037,6 @@ void intel_crtc_update_active_timings(const struct intel_crtc_state *crtc_state) } } -static void intel_modeset_clear_plls(struct intel_atomic_state *state) -{ - struct intel_crtc_state *new_crtc_state; - struct intel_crtc *crtc; - int i; - - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { - if (!intel_crtc_needs_modeset(new_crtc_state)) - continue; - - intel_release_shared_dplls(state, crtc); - } -} - /* * This implements the workaround described in the "notes" section of the mode * set sequence documentation. When going from no pipes or single pipe to @@ -6163,23 +6137,6 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta new_crtc_state->update_pipe = true; } -static void intel_crtc_copy_fastset(const struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state) -{ - /* - * If we're not doing the full modeset we want to - * keep the current M/N values as they may be - * sufficiently different to the computed values - * to cause problems. - * - * FIXME: should really copy more fuzzy state here - */ - new_crtc_state->fdi_m_n = old_crtc_state->fdi_m_n; - new_crtc_state->dp_m_n = old_crtc_state->dp_m_n; - new_crtc_state->dp_m2_n2 = old_crtc_state->dp_m2_n2; - new_crtc_state->has_drrs = old_crtc_state->has_drrs; -} - static int intel_crtc_add_planes_to_state(struct intel_atomic_state *state, struct intel_crtc *crtc, u8 plane_ids_mask) @@ -6836,9 +6793,11 @@ static int intel_atomic_check(struct drm_device *dev, if (!intel_crtc_needs_modeset(new_crtc_state)) continue; - ret = intel_modeset_pipe_config_late(state, crtc); - if (ret) - goto fail; + if (new_crtc_state->hw.enable) { + ret = intel_modeset_pipe_config_late(state, crtc); + if (ret) + goto fail; + } intel_crtc_check_fastset(old_crtc_state, new_crtc_state); } @@ -6889,15 +6848,12 @@ static int intel_atomic_check(struct drm_device *dev, for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { - if (intel_crtc_needs_modeset(new_crtc_state)) { - any_ms = true; + if (!intel_crtc_needs_modeset(new_crtc_state)) continue; - } - if (!new_crtc_state->update_pipe) - continue; + any_ms = true; - intel_crtc_copy_fastset(old_crtc_state, new_crtc_state); + intel_release_shared_dplls(state, crtc); } if (any_ms && !check_digital_port_conflicts(state)) { @@ -6938,8 +6894,6 @@ static int intel_atomic_check(struct drm_device *dev, ret = intel_modeset_calc_cdclk(state); if (ret) return ret; - - intel_modeset_clear_plls(state); } ret = intel_atomic_check_crtcs(state); @@ -7058,6 +7012,10 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_crtc_state, if (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) hsw_set_linetime_wm(new_crtc_state); + + if (new_crtc_state->seamless_m_n) + intel_cpu_transcoder_set_m1_n1(crtc, new_crtc_state->cpu_transcoder, + &new_crtc_state->dp_m_n); } static void commit_pipe_pre_planes(struct intel_atomic_state *state, @@ -7120,7 +7078,7 @@ static void intel_enable_crtc(struct intel_atomic_state *state, intel_crtc_update_active_timings(new_crtc_state); - dev_priv->display->crtc_enable(state, crtc); + dev_priv->display.funcs.display->crtc_enable(state, crtc); if (intel_crtc_is_bigjoiner_slave(new_crtc_state)) return; @@ -7199,7 +7157,7 @@ static void intel_old_crtc_state_disables(struct intel_atomic_state *state, */ intel_crtc_disable_pipe_crc(crtc); - dev_priv->display->crtc_disable(state, crtc); + dev_priv->display.funcs.display->crtc_disable(state, crtc); crtc->active = false; intel_fbc_disable(crtc); intel_disable_shared_dpll(old_crtc_state); @@ -7410,7 +7368,7 @@ static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv) struct intel_atomic_state *state, *next; struct llist_node *freed; - freed = llist_del_all(&dev_priv->atomic_helper.free_list); + freed = llist_del_all(&dev_priv->display.atomic_helper.free_list); llist_for_each_entry_safe(state, next, freed, freed) drm_atomic_state_put(&state->base); } @@ -7418,7 +7376,7 @@ static void intel_atomic_helper_free_state(struct drm_i915_private *dev_priv) static void intel_atomic_helper_free_state_worker(struct work_struct *work) { struct drm_i915_private *dev_priv = - container_of(work, typeof(*dev_priv), atomic_helper.free_work); + container_of(work, typeof(*dev_priv), display.atomic_helper.free_work); intel_atomic_helper_free_state(dev_priv); } @@ -7588,7 +7546,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state) } /* Now enable the clocks, plane, pipe, and connectors that we set up. */ - dev_priv->display->commit_modeset_enables(state); + dev_priv->display.funcs.display->commit_modeset_enables(state); intel_encoders_update_complete(state); @@ -7711,7 +7669,7 @@ intel_atomic_commit_ready(struct i915_sw_fence *fence, case FENCE_FREE: { struct intel_atomic_helper *helper = - &to_i915(state->base.dev)->atomic_helper; + &to_i915(state->base.dev)->display.atomic_helper; if (llist_add(&state->freed, &helper->free_list)) schedule_work(&helper->free_work); @@ -7814,12 +7772,12 @@ static int intel_atomic_commit(struct drm_device *dev, i915_sw_fence_commit(&state->commit_ready); if (nonblock && state->modeset) { - queue_work(dev_priv->modeset_wq, &state->base.commit_work); + queue_work(dev_priv->display.wq.modeset, &state->base.commit_work); } else if (nonblock) { - queue_work(dev_priv->flip_wq, &state->base.commit_work); + queue_work(dev_priv->display.wq.flip, &state->base.commit_work); } else { if (state->modeset) - flush_workqueue(dev_priv->modeset_wq); + flush_workqueue(dev_priv->display.wq.modeset); intel_atomic_commit_tail(state); } @@ -7925,7 +7883,7 @@ static bool intel_ddi_crt_present(struct drm_i915_private *dev_priv) if (intel_de_read(dev_priv, DDI_BUF_CTL(PORT_A)) & DDI_A_4_LANES) return false; - if (!dev_priv->vbt.int_crt_support) + if (!dev_priv->display.vbt.int_crt_support) return false; return true; @@ -8060,7 +8018,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { bool has_edp, has_port; - if (IS_VALLEYVIEW(dev_priv) && dev_priv->vbt.int_crt_support) + if (IS_VALLEYVIEW(dev_priv) && dev_priv->display.vbt.int_crt_support) intel_crt_init(dev_priv); /* @@ -8172,6 +8130,17 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv) drm_helper_move_panel_connectors_to_head(&dev_priv->drm); } +static int max_dotclock(struct drm_i915_private *i915) +{ + int max_dotclock = i915->max_dotclk_freq; + + /* icl+ might use bigjoiner */ + if (DISPLAY_VER(i915) >= 11) + max_dotclock *= 2; + + return max_dotclock; +} + static enum drm_mode_status intel_mode_valid(struct drm_device *dev, const struct drm_display_mode *mode) @@ -8209,6 +8178,13 @@ intel_mode_valid(struct drm_device *dev, DRM_MODE_FLAG_CLKDIV2)) return MODE_BAD; + /* + * Reject clearly excessive dotclocks early to + * avoid having to worry about huge integers later. + */ + if (mode->clock > max_dotclock(dev_priv)) + return MODE_CLOCK_HIGH; + /* Transcoder timing limits */ if (DISPLAY_VER(dev_priv) >= 11) { hdisplay_max = 16384; @@ -8319,7 +8295,7 @@ static const struct drm_mode_config_funcs intel_mode_funcs = { .atomic_state_free = intel_atomic_state_free, }; -static const struct drm_i915_display_funcs skl_display_funcs = { +static const struct intel_display_funcs skl_display_funcs = { .get_pipe_config = hsw_get_pipe_config, .crtc_enable = hsw_crtc_enable, .crtc_disable = hsw_crtc_disable, @@ -8327,7 +8303,7 @@ static const struct drm_i915_display_funcs skl_display_funcs = { .get_initial_plane_config = skl_get_initial_plane_config, }; -static const struct drm_i915_display_funcs ddi_display_funcs = { +static const struct intel_display_funcs ddi_display_funcs = { .get_pipe_config = hsw_get_pipe_config, .crtc_enable = hsw_crtc_enable, .crtc_disable = hsw_crtc_disable, @@ -8335,7 +8311,7 @@ static const struct drm_i915_display_funcs ddi_display_funcs = { .get_initial_plane_config = i9xx_get_initial_plane_config, }; -static const struct drm_i915_display_funcs pch_split_display_funcs = { +static const struct intel_display_funcs pch_split_display_funcs = { .get_pipe_config = ilk_get_pipe_config, .crtc_enable = ilk_crtc_enable, .crtc_disable = ilk_crtc_disable, @@ -8343,7 +8319,7 @@ static const struct drm_i915_display_funcs pch_split_display_funcs = { .get_initial_plane_config = i9xx_get_initial_plane_config, }; -static const struct drm_i915_display_funcs vlv_display_funcs = { +static const struct intel_display_funcs vlv_display_funcs = { .get_pipe_config = i9xx_get_pipe_config, .crtc_enable = valleyview_crtc_enable, .crtc_disable = i9xx_crtc_disable, @@ -8351,7 +8327,7 @@ static const struct drm_i915_display_funcs vlv_display_funcs = { .get_initial_plane_config = i9xx_get_initial_plane_config, }; -static const struct drm_i915_display_funcs i9xx_display_funcs = { +static const struct intel_display_funcs i9xx_display_funcs = { .get_pipe_config = i9xx_get_pipe_config, .crtc_enable = i9xx_crtc_enable, .crtc_disable = i9xx_crtc_disable, @@ -8374,16 +8350,16 @@ void intel_init_display_hooks(struct drm_i915_private *dev_priv) intel_dpll_init_clock_hook(dev_priv); if (DISPLAY_VER(dev_priv) >= 9) { - dev_priv->display = &skl_display_funcs; + dev_priv->display.funcs.display = &skl_display_funcs; } else if (HAS_DDI(dev_priv)) { - dev_priv->display = &ddi_display_funcs; + dev_priv->display.funcs.display = &ddi_display_funcs; } else if (HAS_PCH_SPLIT(dev_priv)) { - dev_priv->display = &pch_split_display_funcs; + dev_priv->display.funcs.display = &pch_split_display_funcs; } else if (IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv)) { - dev_priv->display = &vlv_display_funcs; + dev_priv->display.funcs.display = &vlv_display_funcs; } else { - dev_priv->display = &i9xx_display_funcs; + dev_priv->display.funcs.display = &i9xx_display_funcs; } intel_fdi_init_hook(dev_priv); @@ -8396,11 +8372,11 @@ void intel_modeset_init_hw(struct drm_i915_private *i915) if (!HAS_DISPLAY(i915)) return; - cdclk_state = to_intel_cdclk_state(i915->cdclk.obj.state); + cdclk_state = to_intel_cdclk_state(i915->display.cdclk.obj.state); intel_update_cdclk(i915); - intel_cdclk_dump_config(i915, &i915->cdclk.hw, "Current CDCLK"); - cdclk_state->logical = cdclk_state->actual = i915->cdclk.hw; + intel_cdclk_dump_config(i915, &i915->display.cdclk.hw, "Current CDCLK"); + cdclk_state->logical = cdclk_state->actual = i915->display.cdclk.hw; } static int sanitize_watermarks_add_affected(struct drm_atomic_state *state) @@ -8456,7 +8432,7 @@ static void sanitize_watermarks(struct drm_i915_private *dev_priv) int i; /* Only supported on platforms that use atomic watermark design */ - if (!dev_priv->wm_disp->optimize_watermarks) + if (!dev_priv->display.funcs.wm->optimize_watermarks) return; state = drm_atomic_state_alloc(&dev_priv->drm); @@ -8688,11 +8664,9 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) intel_dmc_ucode_init(i915); - i915->modeset_wq = alloc_ordered_workqueue("i915_modeset", 0); - i915->flip_wq = alloc_workqueue("i915_flip", WQ_HIGHPRI | - WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); - - i915->window2_delay = 0; /* No DSB so no window2 delay */ + i915->display.wq.modeset = alloc_ordered_workqueue("i915_modeset", 0); + i915->display.wq.flip = alloc_workqueue("i915_flip", WQ_HIGHPRI | + WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); intel_mode_config_init(i915); @@ -8708,8 +8682,8 @@ int intel_modeset_init_noirq(struct drm_i915_private *i915) if (ret) goto cleanup_vga_client_pw_domain_dmc; - init_llist_head(&i915->atomic_helper.free_list); - INIT_WORK(&i915->atomic_helper.free_work, + init_llist_head(&i915->display.atomic_helper.free_list); + INIT_WORK(&i915->display.atomic_helper.free_work, intel_atomic_helper_free_state_worker); intel_init_quirks(i915); @@ -8769,7 +8743,7 @@ int intel_modeset_init_nogem(struct drm_i915_private *i915) intel_hdcp_component_init(i915); - if (i915->max_cdclk_freq == 0) + if (i915->display.cdclk.max_cdclk_freq == 0) intel_update_max_cdclk(i915); /* @@ -8833,7 +8807,7 @@ int intel_modeset_init(struct drm_i915_private *i915) intel_hpd_init(i915); intel_hpd_poll_disable(i915); - intel_init_ipc(i915); + skl_watermark_ipc_init(i915); return 0; } @@ -8964,7 +8938,7 @@ void intel_display_resume(struct drm_device *dev) if (!ret) ret = __intel_display_resume(i915, state, &ctx); - intel_enable_ipc(i915); + skl_watermark_ipc_update(i915); drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); @@ -8999,11 +8973,18 @@ void intel_modeset_driver_remove(struct drm_i915_private *i915) if (!HAS_DISPLAY(i915)) return; - flush_workqueue(i915->flip_wq); - flush_workqueue(i915->modeset_wq); + flush_workqueue(i915->display.wq.flip); + flush_workqueue(i915->display.wq.modeset); + + flush_work(&i915->display.atomic_helper.free_work); + drm_WARN_ON(&i915->drm, !llist_empty(&i915->display.atomic_helper.free_list)); - flush_work(&i915->atomic_helper.free_work); - drm_WARN_ON(&i915->drm, !llist_empty(&i915->atomic_helper.free_list)); + /* + * MST topology needs to be suspended so we don't have any calls to + * fbdev after it's finalized. MST will be destroyed later as part of + * drm_mode_config_cleanup() + */ + intel_dp_mst_suspend(i915); } /* part #2: call after irq uninstall */ @@ -9018,13 +8999,6 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915) */ intel_hpd_poll_fini(i915); - /* - * MST topology needs to be suspended so we don't have any calls to - * fbdev after it's finalized. MST will be destroyed later as part of - * drm_mode_config_cleanup() - */ - intel_dp_mst_suspend(i915); - /* poll work can call into fbdev, hence clean that up afterwards */ intel_fbdev_fini(i915); @@ -9041,8 +9015,8 @@ void intel_modeset_driver_remove_noirq(struct drm_i915_private *i915) intel_gmbus_teardown(i915); - destroy_workqueue(i915->flip_wq); - destroy_workqueue(i915->modeset_wq); + destroy_workqueue(i915->display.wq.flip); + destroy_workqueue(i915->display.wq.modeset); intel_fbc_cleanup(i915); } diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index cef251025d7a..884e8e67b17c 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -375,7 +375,7 @@ enum hpd_pin { #define for_each_pipe(__dev_priv, __p) \ for ((__p) = 0; (__p) < I915_MAX_PIPES; (__p)++) \ - for_each_if(INTEL_INFO(__dev_priv)->display.pipe_mask & BIT(__p)) + for_each_if(RUNTIME_INFO(__dev_priv)->pipe_mask & BIT(__p)) #define for_each_pipe_masked(__dev_priv, __p, __mask) \ for_each_pipe(__dev_priv, __p) \ @@ -383,7 +383,7 @@ enum hpd_pin { #define for_each_cpu_transcoder(__dev_priv, __t) \ for ((__t) = 0; (__t) < I915_MAX_TRANSCODERS; (__t)++) \ - for_each_if (INTEL_INFO(__dev_priv)->display.cpu_transcoder_mask & BIT(__t)) + for_each_if (RUNTIME_INFO(__dev_priv)->cpu_transcoder_mask & BIT(__t)) #define for_each_cpu_transcoder_masked(__dev_priv, __t, __mask) \ for_each_cpu_transcoder(__dev_priv, __t) \ @@ -547,7 +547,7 @@ u8 intel_calc_active_pipes(struct intel_atomic_state *state, void intel_link_compute_m_n(u16 bpp, int nlanes, int pixel_clock, int link_clock, struct intel_link_m_n *m_n, - bool constant_n, bool fec_enable); + bool fec_enable); u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv, u32 pixel_format, u64 modifier); enum drm_mode_status diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h new file mode 100644 index 000000000000..96cf994b0ad1 --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_display_core.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_DISPLAY_CORE_H__ +#define __INTEL_DISPLAY_CORE_H__ + +#include <linux/list.h> +#include <linux/llist.h> +#include <linux/mutex.h> +#include <linux/types.h> +#include <linux/wait.h> +#include <linux/workqueue.h> + +#include <drm/drm_connector.h> + +#include "intel_cdclk.h" +#include "intel_display.h" +#include "intel_display_power.h" +#include "intel_dmc.h" +#include "intel_dpll_mgr.h" +#include "intel_fbc.h" +#include "intel_global_state.h" +#include "intel_gmbus.h" +#include "intel_opregion.h" +#include "intel_pm_types.h" + +struct drm_i915_private; +struct drm_property; +struct i915_audio_component; +struct i915_hdcp_comp_master; +struct intel_atomic_state; +struct intel_audio_funcs; +struct intel_bios_encoder_data; +struct intel_cdclk_funcs; +struct intel_cdclk_vals; +struct intel_color_funcs; +struct intel_crtc; +struct intel_crtc_state; +struct intel_dpll_funcs; +struct intel_dpll_mgr; +struct intel_fbdev; +struct intel_fdi_funcs; +struct intel_hotplug_funcs; +struct intel_initial_plane_config; +struct intel_overlay; + +/* Amount of SAGV/QGV points, BSpec precisely defines this */ +#define I915_NUM_QGV_POINTS 8 + +/* Amount of PSF GV points, BSpec precisely defines this */ +#define I915_NUM_PSF_GV_POINTS 3 + +struct intel_display_funcs { + /* + * Returns the active state of the crtc, and if the crtc is active, + * fills out the pipe-config with the hw state. + */ + bool (*get_pipe_config)(struct intel_crtc *, + struct intel_crtc_state *); + void (*get_initial_plane_config)(struct intel_crtc *, + struct intel_initial_plane_config *); + void (*crtc_enable)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*crtc_disable)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*commit_modeset_enables)(struct intel_atomic_state *state); +}; + +/* functions used for watermark calcs for display. */ +struct intel_wm_funcs { + /* update_wm is for legacy wm management */ + void (*update_wm)(struct drm_i915_private *dev_priv); + int (*compute_pipe_wm)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + int (*compute_intermediate_wm)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*initial_watermarks)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*atomic_update_watermarks)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + void (*optimize_watermarks)(struct intel_atomic_state *state, + struct intel_crtc *crtc); + int (*compute_global_watermarks)(struct intel_atomic_state *state); +}; + +struct intel_audio { + /* hda/i915 audio component */ + struct i915_audio_component *component; + bool component_registered; + /* mutex for audio/video sync */ + struct mutex mutex; + int power_refcount; + u32 freq_cntrl; + + /* Used to save the pipe-to-encoder mapping for audio */ + struct intel_encoder *encoder_map[I915_MAX_PIPES]; + + /* necessary resource sharing with HDMI LPE audio driver. */ + struct { + struct platform_device *platdev; + int irq; + } lpe; +}; + +/* + * dpll and cdclk state is protected by connection_mutex dpll.lock serializes + * intel_{prepare,enable,disable}_shared_dpll. Must be global rather than per + * dpll, because on some platforms plls share registers. + */ +struct intel_dpll { + struct mutex lock; + + int num_shared_dpll; + struct intel_shared_dpll shared_dplls[I915_NUM_PLLS]; + const struct intel_dpll_mgr *mgr; + + struct { + int nssc; + int ssc; + } ref_clks; +}; + +struct intel_frontbuffer_tracking { + spinlock_t lock; + + /* + * Tracking bits for delayed frontbuffer flushing du to gpu activity or + * scheduled flips. + */ + unsigned busy_bits; + unsigned flip_bits; +}; + +struct intel_hotplug { + struct delayed_work hotplug_work; + + const u32 *hpd, *pch_hpd; + + struct { + unsigned long last_jiffies; + int count; + enum { + HPD_ENABLED = 0, + HPD_DISABLED = 1, + HPD_MARK_DISABLED = 2 + } state; + } stats[HPD_NUM_PINS]; + u32 event_bits; + u32 retry_bits; + struct delayed_work reenable_work; + + u32 long_port_mask; + u32 short_port_mask; + struct work_struct dig_port_work; + + struct work_struct poll_init_work; + bool poll_enabled; + + unsigned int hpd_storm_threshold; + /* Whether or not to count short HPD IRQs in HPD storms */ + u8 hpd_short_storm_enabled; + + /* + * if we get a HPD irq from DP and a HPD irq from non-DP + * the non-DP HPD could block the workqueue on a mode config + * mutex getting, that userspace may have taken. However + * userspace is waiting on the DP workqueue to run which is + * blocked behind the non-DP one. + */ + struct workqueue_struct *dp_wq; +}; + +struct intel_vbt_data { + /* bdb version */ + u16 version; + + /* Feature bits */ + unsigned int int_tv_support:1; + unsigned int int_crt_support:1; + unsigned int lvds_use_ssc:1; + unsigned int int_lvds_support:1; + unsigned int display_clock_mode:1; + unsigned int fdi_rx_polarity_inverted:1; + int lvds_ssc_freq; + enum drm_panel_orientation orientation; + + bool override_afc_startup; + u8 override_afc_startup_val; + + int crt_ddc_pin; + + struct list_head display_devices; + struct list_head bdb_blocks; + + struct intel_bios_encoder_data *ports[I915_MAX_PORTS]; /* Non-NULL if port present. */ + struct sdvo_device_mapping { + u8 initialized; + u8 dvo_port; + u8 slave_addr; + u8 dvo_wiring; + u8 i2c_pin; + u8 ddc_pin; + } sdvo_mappings[2]; +}; + +struct intel_wm { + /* + * Raw watermark latency values: + * in 0.1us units for WM0, + * in 0.5us units for WM1+. + */ + /* primary */ + u16 pri_latency[5]; + /* sprite */ + u16 spr_latency[5]; + /* cursor */ + u16 cur_latency[5]; + /* + * Raw watermark memory latency values + * for SKL for all 8 levels + * in 1us units. + */ + u16 skl_latency[8]; + + /* current hardware state */ + union { + struct ilk_wm_values hw; + struct vlv_wm_values vlv; + struct g4x_wm_values g4x; + }; + + u8 max_level; + + /* + * Should be held around atomic WM register writing; also + * protects * intel_crtc->wm.active and + * crtc_state->wm.need_postvbl_update. + */ + struct mutex wm_mutex; + + bool ipc_enabled; +}; + +struct intel_display { + /* Display functions */ + struct { + /* Top level crtc-ish functions */ + const struct intel_display_funcs *display; + + /* Display CDCLK functions */ + const struct intel_cdclk_funcs *cdclk; + + /* Display pll funcs */ + const struct intel_dpll_funcs *dpll; + + /* irq display functions */ + const struct intel_hotplug_funcs *hotplug; + + /* pm display functions */ + const struct intel_wm_funcs *wm; + + /* fdi display functions */ + const struct intel_fdi_funcs *fdi; + + /* Display internal color functions */ + const struct intel_color_funcs *color; + + /* Display internal audio functions */ + const struct intel_audio_funcs *audio; + } funcs; + + /* Grouping using anonymous structs. Keep sorted. */ + struct intel_atomic_helper { + struct llist_head free_list; + struct work_struct free_work; + } atomic_helper; + + struct { + /* backlight registers and fields in struct intel_panel */ + struct mutex lock; + } backlight; + + struct { + struct intel_global_obj obj; + + struct intel_bw_info { + /* for each QGV point */ + unsigned int deratedbw[I915_NUM_QGV_POINTS]; + /* for each PSF GV point */ + unsigned int psf_bw[I915_NUM_PSF_GV_POINTS]; + u8 num_qgv_points; + u8 num_psf_gv_points; + u8 num_planes; + } max[6]; + } bw; + + struct { + /* The current hardware cdclk configuration */ + struct intel_cdclk_config hw; + + /* cdclk, divider, and ratio table from bspec */ + const struct intel_cdclk_vals *table; + + struct intel_global_obj obj; + + unsigned int max_cdclk_freq; + } cdclk; + + struct { + /* The current hardware dbuf configuration */ + u8 enabled_slices; + + struct intel_global_obj obj; + } dbuf; + + struct { + /* VLV/CHV/BXT/GLK DSI MMIO register base address */ + u32 mmio_base; + } dsi; + + struct { + /* list of fbdev register on this device */ + struct intel_fbdev *fbdev; + struct work_struct suspend_work; + } fbdev; + + struct { + unsigned int pll_freq; + u32 rx_config; + } fdi; + + struct { + /* + * Base address of where the gmbus and gpio blocks are located + * (either on PCH or on SoC for platforms without PCH). + */ + u32 mmio_base; + + /* + * gmbus.mutex protects against concurrent usage of the single + * hw gmbus controller on different i2c buses. + */ + struct mutex mutex; + + struct intel_gmbus *bus[GMBUS_NUM_PINS]; + + wait_queue_head_t wait_queue; + } gmbus; + + struct { + struct i915_hdcp_comp_master *master; + bool comp_added; + + /* Mutex to protect the above hdcp component related values. */ + struct mutex comp_mutex; + } hdcp; + + struct { + struct i915_power_domains domains; + + /* Shadow for DISPLAY_PHY_CONTROL which can't be safely read */ + u32 chv_phy_control; + + /* perform PHY state sanity checks? */ + bool chv_phy_assert[2]; + } power; + + struct { + u32 mmio_base; + + /* protects panel power sequencer state */ + struct mutex mutex; + } pps; + + struct { + struct drm_property *broadcast_rgb; + struct drm_property *force_audio; + } properties; + + struct { + unsigned long mask; + } quirks; + + struct { + enum { + I915_SAGV_UNKNOWN = 0, + I915_SAGV_DISABLED, + I915_SAGV_ENABLED, + I915_SAGV_NOT_CONTROLLED + } status; + + u32 block_time_us; + } sagv; + + struct { + /* ordered wq for modesets */ + struct workqueue_struct *modeset; + + /* unbound hipri wq for page flips/plane updates */ + struct workqueue_struct *flip; + } wq; + + /* Grouping using named structs. Keep sorted. */ + struct intel_audio audio; + struct intel_dmc dmc; + struct intel_dpll dpll; + struct intel_fbc *fbc[I915_MAX_FBCS]; + struct intel_frontbuffer_tracking fb_tracking; + struct intel_hotplug hotplug; + struct intel_opregion opregion; + struct intel_overlay *overlay; + struct intel_vbt_data vbt; + struct intel_wm wm; +}; + +#endif /* __INTEL_DISPLAY_CORE_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_display_debugfs.c b/drivers/gpu/drm/i915/display/intel_display_debugfs.c index 6c3954479047..7c7253a2541c 100644 --- a/drivers/gpu/drm/i915/display/intel_display_debugfs.c +++ b/drivers/gpu/drm/i915/display/intel_display_debugfs.c @@ -26,6 +26,7 @@ #include "intel_pm.h" #include "intel_psr.h" #include "intel_sprite.h" +#include "skl_watermark.h" static inline struct drm_i915_private *node_to_i915(struct drm_info_node *node) { @@ -37,10 +38,10 @@ static int i915_frontbuffer_tracking(struct seq_file *m, void *unused) struct drm_i915_private *dev_priv = node_to_i915(m->private); seq_printf(m, "FB tracking busy bits: 0x%08x\n", - dev_priv->fb_tracking.busy_bits); + dev_priv->display.fb_tracking.busy_bits); seq_printf(m, "FB tracking flip bits: 0x%08x\n", - dev_priv->fb_tracking.flip_bits); + dev_priv->display.fb_tracking.flip_bits); return 0; } @@ -103,7 +104,8 @@ static int i915_sr_status(struct seq_file *m, void *unused) static int i915_opregion(struct seq_file *m, void *unused) { - struct intel_opregion *opregion = &node_to_i915(m->private)->opregion; + struct drm_i915_private *i915 = node_to_i915(m->private); + struct intel_opregion *opregion = &i915->display.opregion; if (opregion->header) seq_write(m, opregion->header, OPREGION_SIZE); @@ -113,7 +115,8 @@ static int i915_opregion(struct seq_file *m, void *unused) static int i915_vbt(struct seq_file *m, void *unused) { - struct intel_opregion *opregion = &node_to_i915(m->private)->opregion; + struct drm_i915_private *i915 = node_to_i915(m->private); + struct intel_opregion *opregion = &i915->display.opregion; if (opregion->vbt) seq_write(m, opregion->vbt, opregion->vbt_size); @@ -129,7 +132,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data) struct drm_framebuffer *drm_fb; #ifdef CONFIG_DRM_FBDEV_EMULATION - fbdev_fb = intel_fbdev_framebuffer(dev_priv->fbdev); + fbdev_fb = intel_fbdev_framebuffer(dev_priv->display.fbdev.fbdev); if (fbdev_fb) { seq_printf(m, "fbcon size: %d x %d, depth %d, %d bpp, modifier 0x%llx, refcount %d, obj ", fbdev_fb->base.width, @@ -722,10 +725,11 @@ static void intel_scaler_info(struct seq_file *m, struct intel_crtc *crtc) /* Not all platformas have a scaler */ if (num_scalers) { - seq_printf(m, "\tnum_scalers=%d, scaler_users=%x scaler_id=%d", + seq_printf(m, "\tnum_scalers=%d, scaler_users=%x scaler_id=%d scaling_filter=%d", num_scalers, crtc_state->scaler_state.scaler_users, - crtc_state->scaler_state.scaler_id); + crtc_state->scaler_state.scaler_id, + crtc_state->hw.scaling_filter); for (i = 0; i < num_scalers; i++) { const struct intel_scaler *sc = @@ -932,11 +936,11 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) drm_modeset_lock_all(dev); seq_printf(m, "PLL refclks: non-SSC: %d kHz, SSC: %d kHz\n", - dev_priv->dpll.ref_clks.nssc, - dev_priv->dpll.ref_clks.ssc); + dev_priv->display.dpll.ref_clks.nssc, + dev_priv->display.dpll.ref_clks.ssc); - for (i = 0; i < dev_priv->dpll.num_shared_dpll; i++) { - struct intel_shared_dpll *pll = &dev_priv->dpll.shared_dplls[i]; + for (i = 0; i < dev_priv->display.dpll.num_shared_dpll; i++) { + struct intel_shared_dpll *pll = &dev_priv->display.dpll.shared_dplls[i]; seq_printf(m, "DPLL%i: %s, id: %i\n", i, pll->info->name, pll->info->id); @@ -979,58 +983,6 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused) return 0; } -static int i915_ipc_status_show(struct seq_file *m, void *data) -{ - struct drm_i915_private *dev_priv = m->private; - - seq_printf(m, "Isochronous Priority Control: %s\n", - str_yes_no(dev_priv->ipc_enabled)); - return 0; -} - -static int i915_ipc_status_open(struct inode *inode, struct file *file) -{ - struct drm_i915_private *dev_priv = inode->i_private; - - if (!HAS_IPC(dev_priv)) - return -ENODEV; - - return single_open(file, i915_ipc_status_show, dev_priv); -} - -static ssize_t i915_ipc_status_write(struct file *file, const char __user *ubuf, - size_t len, loff_t *offp) -{ - struct seq_file *m = file->private_data; - struct drm_i915_private *dev_priv = m->private; - intel_wakeref_t wakeref; - bool enable; - int ret; - - ret = kstrtobool_from_user(ubuf, len, &enable); - if (ret < 0) - return ret; - - with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) { - if (!dev_priv->ipc_enabled && enable) - drm_info(&dev_priv->drm, - "Enabling IPC: WM will be proper only after next commit\n"); - dev_priv->ipc_enabled = enable; - intel_enable_ipc(dev_priv); - } - - return len; -} - -static const struct file_operations i915_ipc_status_fops = { - .owner = THIS_MODULE, - .open = i915_ipc_status_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .write = i915_ipc_status_write -}; - static int i915_ddb_info(struct seq_file *m, void *unused) { struct drm_i915_private *dev_priv = node_to_i915(m->private); @@ -1427,9 +1379,9 @@ static int pri_wm_latency_show(struct seq_file *m, void *data) const u16 *latencies; if (DISPLAY_VER(dev_priv) >= 9) - latencies = dev_priv->wm.skl_latency; + latencies = dev_priv->display.wm.skl_latency; else - latencies = dev_priv->wm.pri_latency; + latencies = dev_priv->display.wm.pri_latency; wm_latency_show(m, latencies); @@ -1442,9 +1394,9 @@ static int spr_wm_latency_show(struct seq_file *m, void *data) const u16 *latencies; if (DISPLAY_VER(dev_priv) >= 9) - latencies = dev_priv->wm.skl_latency; + latencies = dev_priv->display.wm.skl_latency; else - latencies = dev_priv->wm.spr_latency; + latencies = dev_priv->display.wm.spr_latency; wm_latency_show(m, latencies); @@ -1457,9 +1409,9 @@ static int cur_wm_latency_show(struct seq_file *m, void *data) const u16 *latencies; if (DISPLAY_VER(dev_priv) >= 9) - latencies = dev_priv->wm.skl_latency; + latencies = dev_priv->display.wm.skl_latency; else - latencies = dev_priv->wm.cur_latency; + latencies = dev_priv->display.wm.cur_latency; wm_latency_show(m, latencies); @@ -1550,9 +1502,9 @@ static ssize_t pri_wm_latency_write(struct file *file, const char __user *ubuf, u16 *latencies; if (DISPLAY_VER(dev_priv) >= 9) - latencies = dev_priv->wm.skl_latency; + latencies = dev_priv->display.wm.skl_latency; else - latencies = dev_priv->wm.pri_latency; + latencies = dev_priv->display.wm.pri_latency; return wm_latency_write(file, ubuf, len, offp, latencies); } @@ -1565,9 +1517,9 @@ static ssize_t spr_wm_latency_write(struct file *file, const char __user *ubuf, u16 *latencies; if (DISPLAY_VER(dev_priv) >= 9) - latencies = dev_priv->wm.skl_latency; + latencies = dev_priv->display.wm.skl_latency; else - latencies = dev_priv->wm.spr_latency; + latencies = dev_priv->display.wm.spr_latency; return wm_latency_write(file, ubuf, len, offp, latencies); } @@ -1580,9 +1532,9 @@ static ssize_t cur_wm_latency_write(struct file *file, const char __user *ubuf, u16 *latencies; if (DISPLAY_VER(dev_priv) >= 9) - latencies = dev_priv->wm.skl_latency; + latencies = dev_priv->display.wm.skl_latency; else - latencies = dev_priv->wm.cur_latency; + latencies = dev_priv->display.wm.cur_latency; return wm_latency_write(file, ubuf, len, offp, latencies); } @@ -1617,14 +1569,14 @@ static const struct file_operations i915_cur_wm_latency_fops = { static int i915_hpd_storm_ctl_show(struct seq_file *m, void *data) { struct drm_i915_private *dev_priv = m->private; - struct i915_hotplug *hotplug = &dev_priv->hotplug; + struct intel_hotplug *hotplug = &dev_priv->display.hotplug; /* Synchronize with everything first in case there's been an HPD * storm, but we haven't finished handling it in the kernel yet */ intel_synchronize_irq(dev_priv); - flush_work(&dev_priv->hotplug.dig_port_work); - flush_delayed_work(&dev_priv->hotplug.hotplug_work); + flush_work(&dev_priv->display.hotplug.dig_port_work); + flush_delayed_work(&dev_priv->display.hotplug.hotplug_work); seq_printf(m, "Threshold: %d\n", hotplug->hpd_storm_threshold); seq_printf(m, "Detected: %s\n", @@ -1639,7 +1591,7 @@ static ssize_t i915_hpd_storm_ctl_write(struct file *file, { struct seq_file *m = file->private_data; struct drm_i915_private *dev_priv = m->private; - struct i915_hotplug *hotplug = &dev_priv->hotplug; + struct intel_hotplug *hotplug = &dev_priv->display.hotplug; unsigned int new_threshold; int i; char *newline; @@ -1678,7 +1630,7 @@ static ssize_t i915_hpd_storm_ctl_write(struct file *file, spin_unlock_irq(&dev_priv->irq_lock); /* Re-enable hpd immediately if we were in an irq storm */ - flush_delayed_work(&dev_priv->hotplug.reenable_work); + flush_delayed_work(&dev_priv->display.hotplug.reenable_work); return len; } @@ -1702,7 +1654,7 @@ static int i915_hpd_short_storm_ctl_show(struct seq_file *m, void *data) struct drm_i915_private *dev_priv = m->private; seq_printf(m, "Enabled: %s\n", - str_yes_no(dev_priv->hotplug.hpd_short_storm_enabled)); + str_yes_no(dev_priv->display.hotplug.hpd_short_storm_enabled)); return 0; } @@ -1720,7 +1672,7 @@ static ssize_t i915_hpd_short_storm_ctl_write(struct file *file, { struct seq_file *m = file->private_data; struct drm_i915_private *dev_priv = m->private; - struct i915_hotplug *hotplug = &dev_priv->hotplug; + struct intel_hotplug *hotplug = &dev_priv->display.hotplug; char *newline; char tmp[16]; int i; @@ -1756,7 +1708,7 @@ static ssize_t i915_hpd_short_storm_ctl_write(struct file *file, spin_unlock_irq(&dev_priv->irq_lock); /* Re-enable hpd immediately if we were in an irq storm */ - flush_delayed_work(&dev_priv->hotplug.reenable_work); + flush_delayed_work(&dev_priv->display.hotplug.reenable_work); return len; } @@ -1907,7 +1859,6 @@ static const struct { {"i915_dp_test_active", &i915_displayport_test_active_fops}, {"i915_hpd_storm_ctl", &i915_hpd_storm_ctl_fops}, {"i915_hpd_short_storm_ctl", &i915_hpd_short_storm_ctl_fops}, - {"i915_ipc_status", &i915_ipc_status_fops}, {"i915_drrs_ctl", &i915_drrs_ctl_fops}, {"i915_edp_psr_debug", &i915_edp_psr_debug_fops}, }; @@ -1931,6 +1882,7 @@ void intel_display_debugfs_register(struct drm_i915_private *i915) intel_dmc_debugfs_register(i915); intel_fbc_debugfs_register(i915); + skl_watermark_ipc_debugfs_register(i915); } static int i915_panel_show(struct seq_file *m, void *data) @@ -2137,7 +2089,7 @@ static const struct file_operations i915_dsc_fec_support_fops = { .write = i915_dsc_fec_support_write }; -static int i915_dsc_bpp_show(struct seq_file *m, void *data) +static int i915_dsc_bpc_show(struct seq_file *m, void *data) { struct drm_connector *connector = m->private; struct drm_device *dev = connector->dev; @@ -2160,14 +2112,14 @@ static int i915_dsc_bpp_show(struct seq_file *m, void *data) } crtc_state = to_intel_crtc_state(crtc->state); - seq_printf(m, "Compressed_BPP: %d\n", crtc_state->dsc.compressed_bpp); + seq_printf(m, "Input_BPC: %d\n", crtc_state->dsc.config.bits_per_component); out: drm_modeset_unlock(&dev->mode_config.connection_mutex); return ret; } -static ssize_t i915_dsc_bpp_write(struct file *file, +static ssize_t i915_dsc_bpc_write(struct file *file, const char __user *ubuf, size_t len, loff_t *offp) { @@ -2175,33 +2127,32 @@ static ssize_t i915_dsc_bpp_write(struct file *file, ((struct seq_file *)file->private_data)->private; struct intel_encoder *encoder = intel_attached_encoder(to_intel_connector(connector)); struct intel_dp *intel_dp = enc_to_intel_dp(encoder); - int dsc_bpp = 0; + int dsc_bpc = 0; int ret; - ret = kstrtoint_from_user(ubuf, len, 0, &dsc_bpp); + ret = kstrtoint_from_user(ubuf, len, 0, &dsc_bpc); if (ret < 0) return ret; - intel_dp->force_dsc_bpp = dsc_bpp; + intel_dp->force_dsc_bpc = dsc_bpc; *offp += len; return len; } -static int i915_dsc_bpp_open(struct inode *inode, +static int i915_dsc_bpc_open(struct inode *inode, struct file *file) { - return single_open(file, i915_dsc_bpp_show, - inode->i_private); + return single_open(file, i915_dsc_bpc_show, inode->i_private); } -static const struct file_operations i915_dsc_bpp_fops = { +static const struct file_operations i915_dsc_bpc_fops = { .owner = THIS_MODULE, - .open = i915_dsc_bpp_open, + .open = i915_dsc_bpc_open, .read = seq_read, .llseek = seq_lseek, .release = single_release, - .write = i915_dsc_bpp_write + .write = i915_dsc_bpc_write }; /* @@ -2271,8 +2222,8 @@ void intel_connector_debugfs_add(struct intel_connector *intel_connector) debugfs_create_file("i915_dsc_fec_support", 0644, root, connector, &i915_dsc_fec_support_fops); - debugfs_create_file("i915_dsc_bpp", 0644, root, - connector, &i915_dsc_bpp_fops); + debugfs_create_file("i915_dsc_bpc", 0644, root, + connector, &i915_dsc_bpc_fops); } if (connector->connector_type == DRM_MODE_CONNECTOR_DSI || diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 589af257edeb..1e608b9e5055 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -7,6 +7,7 @@ #include "i915_drv.h" #include "i915_irq.h" +#include "intel_backlight_regs.h" #include "intel_cdclk.h" #include "intel_combo_phy.h" #include "intel_de.h" @@ -18,8 +19,8 @@ #include "intel_mchbar_regs.h" #include "intel_pch_refclk.h" #include "intel_pcode.h" -#include "intel_pm.h" #include "intel_snps_phy.h" +#include "skl_watermark.h" #include "vlv_sideband.h" #define for_each_power_domain_well(__dev_priv, __power_well, __domain) \ @@ -243,7 +244,7 @@ bool intel_display_power_is_enabled(struct drm_i915_private *dev_priv, struct i915_power_domains *power_domains; bool ret; - power_domains = &dev_priv->power_domains; + power_domains = &dev_priv->display.power.domains; mutex_lock(&power_domains->lock); ret = __intel_display_power_is_enabled(dev_priv, domain); @@ -268,7 +269,7 @@ sanitize_target_dc_state(struct drm_i915_private *dev_priv, if (target_dc_state != states[i]) continue; - if (dev_priv->dmc.allowed_dc_mask & target_dc_state) + if (dev_priv->display.dmc.allowed_dc_mask & target_dc_state) break; target_dc_state = states[i + 1]; @@ -291,7 +292,7 @@ void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv, { struct i915_power_well *power_well; bool dc_off_enabled; - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; mutex_lock(&power_domains->lock); power_well = lookup_power_well(dev_priv, SKL_DISP_DC_OFF); @@ -301,7 +302,7 @@ void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv, state = sanitize_target_dc_state(dev_priv, state); - if (state == dev_priv->dmc.target_dc_state) + if (state == dev_priv->display.dmc.target_dc_state) goto unlock; dc_off_enabled = intel_power_well_is_enabled(dev_priv, power_well); @@ -312,7 +313,7 @@ void intel_display_power_set_target_dc_state(struct drm_i915_private *dev_priv, if (!dc_off_enabled) intel_power_well_enable(dev_priv, power_well); - dev_priv->dmc.target_dc_state = state; + dev_priv->display.dmc.target_dc_state = state; if (!dc_off_enabled) intel_power_well_disable(dev_priv, power_well); @@ -339,7 +340,7 @@ assert_async_put_domain_masks_disjoint(struct i915_power_domains *power_domains) { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); return !drm_WARN_ON(&i915->drm, bitmap_intersects(power_domains->async_put_domains[0].bits, @@ -352,7 +353,7 @@ __async_put_domains_state_ok(struct i915_power_domains *power_domains) { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); struct intel_power_domain_mask async_put_mask; enum intel_display_power_domain domain; bool err = false; @@ -375,7 +376,7 @@ static void print_power_domains(struct i915_power_domains *power_domains, { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); enum intel_display_power_domain domain; drm_dbg(&i915->drm, "%s (%d):\n", prefix, bitmap_weight(mask->bits, POWER_DOMAIN_NUM)); @@ -390,7 +391,7 @@ print_async_put_domains_state(struct i915_power_domains *power_domains) { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); drm_dbg(&i915->drm, "async_put_wakeref %u\n", power_domains->async_put_wakeref); @@ -445,7 +446,7 @@ static bool intel_display_power_grab_async_put_ref(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct intel_power_domain_mask async_put_mask; bool ret = false; @@ -474,7 +475,7 @@ static void __intel_display_power_get_domain(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *power_well; if (intel_display_power_grab_async_put_ref(dev_priv, domain)) @@ -501,7 +502,7 @@ __intel_display_power_get_domain(struct drm_i915_private *dev_priv, intel_wakeref_t intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; intel_wakeref_t wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm); mutex_lock(&power_domains->lock); @@ -527,7 +528,7 @@ intel_wakeref_t intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; intel_wakeref_t wakeref; bool is_enabled; @@ -563,7 +564,7 @@ __intel_display_power_put_domain(struct drm_i915_private *dev_priv, const char *name = intel_display_power_domain_str(domain); struct intel_power_domain_mask async_put_mask; - power_domains = &dev_priv->power_domains; + power_domains = &dev_priv->display.power.domains; drm_WARN(&dev_priv->drm, !power_domains->domain_use_count[domain], "Use count on domain %s is already zero\n", @@ -583,7 +584,7 @@ __intel_display_power_put_domain(struct drm_i915_private *dev_priv, static void __intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; mutex_lock(&power_domains->lock); __intel_display_power_put_domain(dev_priv, domain); @@ -596,7 +597,7 @@ queue_async_put_domains_work(struct i915_power_domains *power_domains, { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); drm_WARN_ON(&i915->drm, power_domains->async_put_wakeref); power_domains->async_put_wakeref = wakeref; drm_WARN_ON(&i915->drm, !queue_delayed_work(system_unbound_wq, @@ -610,7 +611,7 @@ release_async_put_domains(struct i915_power_domains *power_domains, { struct drm_i915_private *dev_priv = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; enum intel_display_power_domain domain; intel_wakeref_t wakeref; @@ -637,8 +638,8 @@ intel_display_power_put_async_work(struct work_struct *work) { struct drm_i915_private *dev_priv = container_of(work, struct drm_i915_private, - power_domains.async_put_work.work); - struct i915_power_domains *power_domains = &dev_priv->power_domains; + display.power.domains.async_put_work.work); + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; intel_wakeref_t new_work_wakeref = intel_runtime_pm_get_raw(rpm); intel_wakeref_t old_work_wakeref = 0; @@ -698,7 +699,7 @@ void __intel_display_power_put_async(struct drm_i915_private *i915, enum intel_display_power_domain domain, intel_wakeref_t wakeref) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; struct intel_runtime_pm *rpm = &i915->runtime_pm; intel_wakeref_t work_wakeref = intel_runtime_pm_get_raw(rpm); @@ -746,7 +747,7 @@ out_verify: */ void intel_display_power_flush_work(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; struct intel_power_domain_mask async_put_mask; intel_wakeref_t work_wakeref; @@ -779,7 +780,7 @@ out_verify: static void intel_display_power_flush_work_sync(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; intel_display_power_flush_work(i915); cancel_delayed_work_sync(&power_domains->async_put_work); @@ -908,7 +909,7 @@ static u32 get_allowed_dc_mask(const struct drm_i915_private *dev_priv, return 0; if (IS_DG2(dev_priv)) - max_dc = 0; + max_dc = 1; else if (IS_DG1(dev_priv)) max_dc = 3; else if (DISPLAY_VER(dev_priv) >= 12) @@ -976,15 +977,15 @@ static u32 get_allowed_dc_mask(const struct drm_i915_private *dev_priv, */ int intel_power_domains_init(struct drm_i915_private *dev_priv) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; dev_priv->params.disable_power_well = sanitize_disable_power_well_option(dev_priv, dev_priv->params.disable_power_well); - dev_priv->dmc.allowed_dc_mask = + dev_priv->display.dmc.allowed_dc_mask = get_allowed_dc_mask(dev_priv, dev_priv->params.enable_dc); - dev_priv->dmc.target_dc_state = + dev_priv->display.dmc.target_dc_state = sanitize_target_dc_state(dev_priv, DC_STATE_EN_UPTO_DC6); mutex_init(&power_domains->lock); @@ -1003,12 +1004,12 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv) */ void intel_power_domains_cleanup(struct drm_i915_private *dev_priv) { - intel_display_power_map_cleanup(&dev_priv->power_domains); + intel_display_power_map_cleanup(&dev_priv->display.power.domains); } static void intel_power_domains_sync_hw(struct drm_i915_private *dev_priv) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *power_well; mutex_lock(&power_domains->lock); @@ -1037,7 +1038,7 @@ static void gen9_dbuf_slice_set(struct drm_i915_private *dev_priv, void gen9_dbuf_slices_update(struct drm_i915_private *dev_priv, u8 req_slices) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; u8 slice_mask = INTEL_INFO(dev_priv)->display.dbuf.slice_mask; enum dbuf_slice slice; @@ -1060,14 +1061,14 @@ void gen9_dbuf_slices_update(struct drm_i915_private *dev_priv, for_each_dbuf_slice(dev_priv, slice) gen9_dbuf_slice_set(dev_priv, slice, req_slices & BIT(slice)); - dev_priv->dbuf.enabled_slices = req_slices; + dev_priv->display.dbuf.enabled_slices = req_slices; mutex_unlock(&power_domains->lock); } static void gen9_dbuf_enable(struct drm_i915_private *dev_priv) { - dev_priv->dbuf.enabled_slices = + dev_priv->display.dbuf.enabled_slices = intel_enabled_dbuf_slices_mask(dev_priv); /* @@ -1075,7 +1076,7 @@ static void gen9_dbuf_enable(struct drm_i915_private *dev_priv) * figure out later which slices we have and what we need. */ gen9_dbuf_slices_update(dev_priv, BIT(DBUF_S1) | - dev_priv->dbuf.enabled_slices); + dev_priv->display.dbuf.enabled_slices); } static void gen9_dbuf_disable(struct drm_i915_private *dev_priv) @@ -1101,7 +1102,7 @@ static void icl_mbus_init(struct drm_i915_private *dev_priv) unsigned long abox_regs = INTEL_INFO(dev_priv)->display.abox_mask; u32 mask, val, i; - if (IS_ALDERLAKE_P(dev_priv)) + if (IS_ALDERLAKE_P(dev_priv) || DISPLAY_VER(dev_priv) >= 14) return; mask = MBUS_ABOX_BT_CREDIT_POOL1_MASK | @@ -1309,7 +1310,7 @@ static void hsw_restore_lcpll(struct drm_i915_private *dev_priv) intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL); intel_update_cdclk(dev_priv); - intel_cdclk_dump_config(dev_priv, &dev_priv->cdclk.hw, "Current CDCLK"); + intel_cdclk_dump_config(dev_priv, &dev_priv->display.cdclk.hw, "Current CDCLK"); } /* @@ -1381,6 +1382,9 @@ static void intel_pch_reset_handshake(struct drm_i915_private *dev_priv, reset_bits = RESET_PCH_HANDSHAKE_ENABLE; } + if (DISPLAY_VER(dev_priv) >= 14) + reset_bits |= MTL_RESET_PICA_HANDSHAKE_EN; + val = intel_de_read(dev_priv, reg); if (enable) @@ -1394,7 +1398,7 @@ static void intel_pch_reset_handshake(struct drm_i915_private *dev_priv, static void skl_display_core_init(struct drm_i915_private *dev_priv, bool resume) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *well; gen9_set_dc_state(dev_priv, DC_STATE_DISABLE); @@ -1426,13 +1430,14 @@ static void skl_display_core_init(struct drm_i915_private *dev_priv, static void skl_display_core_uninit(struct drm_i915_private *dev_priv) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *well; if (!HAS_DISPLAY(dev_priv)) return; gen9_disable_dc_states(dev_priv); + /* TODO: disable DMC program */ gen9_dbuf_disable(dev_priv); @@ -1459,7 +1464,7 @@ static void skl_display_core_uninit(struct drm_i915_private *dev_priv) static void bxt_display_core_init(struct drm_i915_private *dev_priv, bool resume) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *well; gen9_set_dc_state(dev_priv, DC_STATE_DISABLE); @@ -1493,13 +1498,14 @@ static void bxt_display_core_init(struct drm_i915_private *dev_priv, bool resume static void bxt_display_core_uninit(struct drm_i915_private *dev_priv) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *well; if (!HAS_DISPLAY(dev_priv)) return; gen9_disable_dc_states(dev_priv); + /* TODO: disable DMC program */ gen9_dbuf_disable(dev_priv); @@ -1601,7 +1607,7 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) static void icl_display_core_init(struct drm_i915_private *dev_priv, bool resume) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *well; u32 val; @@ -1668,13 +1674,14 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv, static void icl_display_core_uninit(struct drm_i915_private *dev_priv) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; struct i915_power_well *well; if (!HAS_DISPLAY(dev_priv)) return; gen9_disable_dc_states(dev_priv); + intel_dmc_disable_program(dev_priv); /* 1. Disable all display engine functions -> aready done */ @@ -1712,7 +1719,7 @@ static void chv_phy_control_init(struct drm_i915_private *dev_priv) * power well state and lane status to reconstruct the * expected initial value. */ - dev_priv->chv_phy_control = + dev_priv->display.power.chv_phy_control = PHY_LDO_SEQ_DELAY(PHY_LDO_DELAY_600NS, DPIO_PHY0) | PHY_LDO_SEQ_DELAY(PHY_LDO_DELAY_600NS, DPIO_PHY1) | PHY_CH_POWER_MODE(PHY_CH_DEEP_PSR, DPIO_PHY0, DPIO_CH0) | @@ -1734,27 +1741,27 @@ static void chv_phy_control_init(struct drm_i915_private *dev_priv) if (mask == 0xf) mask = 0x0; else - dev_priv->chv_phy_control |= + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH0); - dev_priv->chv_phy_control |= + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY0, DPIO_CH0); mask = (status & DPLL_PORTC_READY_MASK) >> 4; if (mask == 0xf) mask = 0x0; else - dev_priv->chv_phy_control |= + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY0, DPIO_CH1); - dev_priv->chv_phy_control |= + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY0, DPIO_CH1); - dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY0); + dev_priv->display.power.chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY0); - dev_priv->chv_phy_assert[DPIO_PHY0] = false; + dev_priv->display.power.chv_phy_assert[DPIO_PHY0] = false; } else { - dev_priv->chv_phy_assert[DPIO_PHY0] = true; + dev_priv->display.power.chv_phy_assert[DPIO_PHY0] = true; } if (intel_power_well_is_enabled(dev_priv, cmn_d)) { @@ -1766,21 +1773,21 @@ static void chv_phy_control_init(struct drm_i915_private *dev_priv) if (mask == 0xf) mask = 0x0; else - dev_priv->chv_phy_control |= + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(DPIO_PHY1, DPIO_CH0); - dev_priv->chv_phy_control |= + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, DPIO_PHY1, DPIO_CH0); - dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY1); + dev_priv->display.power.chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(DPIO_PHY1); - dev_priv->chv_phy_assert[DPIO_PHY1] = false; + dev_priv->display.power.chv_phy_assert[DPIO_PHY1] = false; } else { - dev_priv->chv_phy_assert[DPIO_PHY1] = true; + dev_priv->display.power.chv_phy_assert[DPIO_PHY1] = true; } drm_dbg_kms(&dev_priv->drm, "Initial PHY_CONTROL=0x%08x\n", - dev_priv->chv_phy_control); + dev_priv->display.power.chv_phy_control); /* Defer application of initial phy_control to enabling the powerwell */ } @@ -1864,7 +1871,7 @@ static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv); */ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; power_domains->initializing = true; @@ -1905,8 +1912,8 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume) /* Disable power support if the user asked so. */ if (!i915->params.disable_power_well) { drm_WARN_ON(&i915->drm, power_domains->disable_wakeref); - i915->power_domains.disable_wakeref = intel_display_power_get(i915, - POWER_DOMAIN_INIT); + i915->display.power.domains.disable_wakeref = intel_display_power_get(i915, + POWER_DOMAIN_INIT); } intel_power_domains_sync_hw(i915); @@ -1927,12 +1934,12 @@ void intel_power_domains_init_hw(struct drm_i915_private *i915, bool resume) void intel_power_domains_driver_remove(struct drm_i915_private *i915) { intel_wakeref_t wakeref __maybe_unused = - fetch_and_zero(&i915->power_domains.init_wakeref); + fetch_and_zero(&i915->display.power.domains.init_wakeref); /* Remove the refcount we took to keep power well support disabled. */ if (!i915->params.disable_power_well) intel_display_power_put(i915, POWER_DOMAIN_INIT, - fetch_and_zero(&i915->power_domains.disable_wakeref)); + fetch_and_zero(&i915->display.power.domains.disable_wakeref)); intel_display_power_flush_work_sync(i915); @@ -1954,7 +1961,7 @@ void intel_power_domains_driver_remove(struct drm_i915_private *i915) */ void intel_power_domains_sanitize_state(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; struct i915_power_well *power_well; mutex_lock(&power_domains->lock); @@ -1988,7 +1995,7 @@ void intel_power_domains_sanitize_state(struct drm_i915_private *i915) void intel_power_domains_enable(struct drm_i915_private *i915) { intel_wakeref_t wakeref __maybe_unused = - fetch_and_zero(&i915->power_domains.init_wakeref); + fetch_and_zero(&i915->display.power.domains.init_wakeref); intel_display_power_put(i915, POWER_DOMAIN_INIT, wakeref); intel_power_domains_verify_state(i915); @@ -2003,7 +2010,7 @@ void intel_power_domains_enable(struct drm_i915_private *i915) */ void intel_power_domains_disable(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; drm_WARN_ON(&i915->drm, power_domains->init_wakeref); power_domains->init_wakeref = @@ -2026,7 +2033,7 @@ void intel_power_domains_disable(struct drm_i915_private *i915) void intel_power_domains_suspend(struct drm_i915_private *i915, enum i915_drm_suspend_mode suspend_mode) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; intel_wakeref_t wakeref __maybe_unused = fetch_and_zero(&power_domains->init_wakeref); @@ -2039,7 +2046,7 @@ void intel_power_domains_suspend(struct drm_i915_private *i915, * resources as required and also enable deeper system power states * that would be blocked if the firmware was inactive. */ - if (!(i915->dmc.allowed_dc_mask & DC_STATE_EN_DC9) && + if (!(i915->display.dmc.allowed_dc_mask & DC_STATE_EN_DC9) && suspend_mode == I915_DRM_SUSPEND_IDLE && intel_dmc_has_payload(i915)) { intel_display_power_flush_work(i915); @@ -2053,7 +2060,7 @@ void intel_power_domains_suspend(struct drm_i915_private *i915, */ if (!i915->params.disable_power_well) intel_display_power_put(i915, POWER_DOMAIN_INIT, - fetch_and_zero(&i915->power_domains.disable_wakeref)); + fetch_and_zero(&i915->display.power.domains.disable_wakeref)); intel_display_power_flush_work(i915); intel_power_domains_verify_state(i915); @@ -2080,7 +2087,7 @@ void intel_power_domains_suspend(struct drm_i915_private *i915, */ void intel_power_domains_resume(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; if (power_domains->display_core_suspended) { intel_power_domains_init_hw(i915, true); @@ -2098,7 +2105,7 @@ void intel_power_domains_resume(struct drm_i915_private *i915) static void intel_power_domains_dump_info(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; struct i915_power_well *power_well; for_each_power_well(i915, power_well) { @@ -2126,7 +2133,7 @@ static void intel_power_domains_dump_info(struct drm_i915_private *i915) */ static void intel_power_domains_verify_state(struct drm_i915_private *i915) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; struct i915_power_well *power_well; bool dump_domain_info; @@ -2232,10 +2239,10 @@ void intel_display_power_resume(struct drm_i915_private *i915) bxt_disable_dc9(i915); icl_display_core_init(i915, true); if (intel_dmc_has_payload(i915)) { - if (i915->dmc.allowed_dc_mask & + if (i915->display.dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC6) skl_enable_dc6(i915); - else if (i915->dmc.allowed_dc_mask & + else if (i915->display.dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC5) gen9_enable_dc5(i915); } @@ -2243,7 +2250,7 @@ void intel_display_power_resume(struct drm_i915_private *i915) bxt_disable_dc9(i915); bxt_display_core_init(i915, true); if (intel_dmc_has_payload(i915) && - (i915->dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC5)) + (i915->display.dmc.allowed_dc_mask & DC_STATE_EN_UPTO_DC5)) gen9_enable_dc5(i915); } else if (IS_HASWELL(i915) || IS_BROADWELL(i915)) { hsw_disable_pc8(i915); @@ -2252,7 +2259,7 @@ void intel_display_power_resume(struct drm_i915_private *i915) void intel_display_power_debug(struct drm_i915_private *i915, struct seq_file *m) { - struct i915_power_domains *power_domains = &i915->power_domains; + struct i915_power_domains *power_domains = &i915->display.power.domains; int i; mutex_lock(&power_domains->lock); diff --git a/drivers/gpu/drm/i915/display/intel_display_power_map.c b/drivers/gpu/drm/i915/display/intel_display_power_map.c index 97b367f39f35..dc04afc6cc8f 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_map.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_map.c @@ -1350,6 +1350,117 @@ static const struct i915_power_well_desc_list xelpd_power_wells[] = { I915_PW_DESCRIPTORS(xelpd_power_wells_main), }; +/* + * MTL is based on XELPD power domains with the exception of power gating for: + * - DDI_IO (moved to PLL logic) + * - AUX and AUX_IO functionality and register access for USBC1-4 (PICA always-on) + */ +#define XELPDP_PW_2_POWER_DOMAINS \ + XELPD_PW_B_POWER_DOMAINS, \ + XELPD_PW_C_POWER_DOMAINS, \ + XELPD_PW_D_POWER_DOMAINS, \ + POWER_DOMAIN_AUDIO_PLAYBACK, \ + POWER_DOMAIN_VGA, \ + POWER_DOMAIN_PORT_DDI_LANES_TC1, \ + POWER_DOMAIN_PORT_DDI_LANES_TC2, \ + POWER_DOMAIN_PORT_DDI_LANES_TC3, \ + POWER_DOMAIN_PORT_DDI_LANES_TC4 + +I915_DECL_PW_DOMAINS(xelpdp_pwdoms_pw_2, + XELPDP_PW_2_POWER_DOMAINS, + POWER_DOMAIN_INIT); + +I915_DECL_PW_DOMAINS(xelpdp_pwdoms_dc_off, + XELPDP_PW_2_POWER_DOMAINS, + POWER_DOMAIN_AUDIO_MMIO, + POWER_DOMAIN_MODESET, + POWER_DOMAIN_AUX_A, + POWER_DOMAIN_AUX_B, + POWER_DOMAIN_INIT); + +I915_DECL_PW_DOMAINS(xelpdp_pwdoms_aux_tc1, + POWER_DOMAIN_AUX_USBC1, + POWER_DOMAIN_AUX_TBT1); + +I915_DECL_PW_DOMAINS(xelpdp_pwdoms_aux_tc2, + POWER_DOMAIN_AUX_USBC2, + POWER_DOMAIN_AUX_TBT2); + +I915_DECL_PW_DOMAINS(xelpdp_pwdoms_aux_tc3, + POWER_DOMAIN_AUX_USBC3, + POWER_DOMAIN_AUX_TBT3); + +I915_DECL_PW_DOMAINS(xelpdp_pwdoms_aux_tc4, + POWER_DOMAIN_AUX_USBC4, + POWER_DOMAIN_AUX_TBT4); + +static const struct i915_power_well_desc xelpdp_power_wells_main[] = { + { + .instances = &I915_PW_INSTANCES( + I915_PW("DC_off", &xelpdp_pwdoms_dc_off, + .id = SKL_DISP_DC_OFF), + ), + .ops = &gen9_dc_off_power_well_ops, + }, { + .instances = &I915_PW_INSTANCES( + I915_PW("PW_2", &xelpdp_pwdoms_pw_2, + .hsw.idx = ICL_PW_CTL_IDX_PW_2, + .id = SKL_DISP_PW_2), + ), + .ops = &hsw_power_well_ops, + .has_vga = true, + .has_fuses = true, + }, { + .instances = &I915_PW_INSTANCES( + I915_PW("PW_A", &xelpd_pwdoms_pw_a, + .hsw.idx = XELPD_PW_CTL_IDX_PW_A), + ), + .ops = &hsw_power_well_ops, + .irq_pipe_mask = BIT(PIPE_A), + .has_fuses = true, + }, { + .instances = &I915_PW_INSTANCES( + I915_PW("PW_B", &xelpd_pwdoms_pw_b, + .hsw.idx = XELPD_PW_CTL_IDX_PW_B), + ), + .ops = &hsw_power_well_ops, + .irq_pipe_mask = BIT(PIPE_B), + .has_fuses = true, + }, { + .instances = &I915_PW_INSTANCES( + I915_PW("PW_C", &xelpd_pwdoms_pw_c, + .hsw.idx = XELPD_PW_CTL_IDX_PW_C), + ), + .ops = &hsw_power_well_ops, + .irq_pipe_mask = BIT(PIPE_C), + .has_fuses = true, + }, { + .instances = &I915_PW_INSTANCES( + I915_PW("PW_D", &xelpd_pwdoms_pw_d, + .hsw.idx = XELPD_PW_CTL_IDX_PW_D), + ), + .ops = &hsw_power_well_ops, + .irq_pipe_mask = BIT(PIPE_D), + .has_fuses = true, + }, { + .instances = &I915_PW_INSTANCES( + I915_PW("AUX_A", &icl_pwdoms_aux_a, .xelpdp.aux_ch = AUX_CH_A), + I915_PW("AUX_B", &icl_pwdoms_aux_b, .xelpdp.aux_ch = AUX_CH_B), + I915_PW("AUX_TC1", &xelpdp_pwdoms_aux_tc1, .xelpdp.aux_ch = AUX_CH_USBC1), + I915_PW("AUX_TC2", &xelpdp_pwdoms_aux_tc2, .xelpdp.aux_ch = AUX_CH_USBC2), + I915_PW("AUX_TC3", &xelpdp_pwdoms_aux_tc3, .xelpdp.aux_ch = AUX_CH_USBC3), + I915_PW("AUX_TC4", &xelpdp_pwdoms_aux_tc4, .xelpdp.aux_ch = AUX_CH_USBC4), + ), + .ops = &xelpdp_aux_power_well_ops, + }, +}; + +static const struct i915_power_well_desc_list xelpdp_power_wells[] = { + I915_PW_DESCRIPTORS(i9xx_power_wells_always_on), + I915_PW_DESCRIPTORS(icl_power_wells_pw_1), + I915_PW_DESCRIPTORS(xelpdp_power_wells_main), +}; + static void init_power_well_domains(const struct i915_power_well_instance *inst, struct i915_power_well *power_well) { @@ -1388,7 +1499,7 @@ __set_power_wells(struct i915_power_domains *power_domains, { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); u64 power_well_ids = 0; const struct i915_power_well_desc_list *desc_list; const struct i915_power_well_desc *desc; @@ -1447,7 +1558,7 @@ int intel_display_power_map_init(struct i915_power_domains *power_domains) { struct drm_i915_private *i915 = container_of(power_domains, struct drm_i915_private, - power_domains); + display.power.domains); /* * The enabling order will be from lower to higher indexed wells, * the disabling order is reversed. @@ -1457,7 +1568,9 @@ int intel_display_power_map_init(struct i915_power_domains *power_domains) return 0; } - if (DISPLAY_VER(i915) >= 13) + if (DISPLAY_VER(i915) >= 14) + return set_power_wells(power_domains, xelpdp_power_wells); + else if (DISPLAY_VER(i915) >= 13) return set_power_wells(power_domains, xelpd_power_wells); else if (IS_DG1(i915)) return set_power_wells(power_domains, dg1_power_wells); diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c index 91cfd5890f46..df7ee4969ef1 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.c +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c @@ -5,6 +5,7 @@ #include "i915_drv.h" #include "i915_irq.h" +#include "intel_backlight_regs.h" #include "intel_combo_phy.h" #include "intel_combo_phy_regs.h" #include "intel_crt.h" @@ -16,10 +17,10 @@ #include "intel_dpll.h" #include "intel_hotplug.h" #include "intel_pcode.h" -#include "intel_pm.h" #include "intel_pps.h" #include "intel_tc.h" #include "intel_vga.h" +#include "skl_watermark.h" #include "vlv_sideband.h" #include "vlv_sideband_reg.h" @@ -84,7 +85,7 @@ lookup_power_well(struct drm_i915_private *i915, drm_WARN(&i915->drm, 1, "Power well %d not defined for this platform\n", power_well_id); - return &i915->power_domains.power_wells[0]; + return &i915->display.power.domains.power_wells[0]; } void intel_power_well_enable(struct drm_i915_private *i915, @@ -710,8 +711,8 @@ void gen9_sanitize_dc_state(struct drm_i915_private *dev_priv) drm_dbg_kms(&dev_priv->drm, "Resetting DC state tracking from %02x to %02x\n", - dev_priv->dmc.dc_state, val); - dev_priv->dmc.dc_state = val; + dev_priv->display.dmc.dc_state, val); + dev_priv->display.dmc.dc_state = val; } /** @@ -746,8 +747,8 @@ void gen9_set_dc_state(struct drm_i915_private *dev_priv, u32 state) return; if (drm_WARN_ON_ONCE(&dev_priv->drm, - state & ~dev_priv->dmc.allowed_dc_mask)) - state &= dev_priv->dmc.allowed_dc_mask; + state & ~dev_priv->display.dmc.allowed_dc_mask)) + state &= dev_priv->display.dmc.allowed_dc_mask; val = intel_de_read(dev_priv, DC_STATE_EN); mask = gen9_dc_mask(dev_priv); @@ -755,16 +756,16 @@ void gen9_set_dc_state(struct drm_i915_private *dev_priv, u32 state) val & mask, state); /* Check if DMC is ignoring our DC state requests */ - if ((val & mask) != dev_priv->dmc.dc_state) + if ((val & mask) != dev_priv->display.dmc.dc_state) drm_err(&dev_priv->drm, "DC state mismatch (0x%x -> 0x%x)\n", - dev_priv->dmc.dc_state, val & mask); + dev_priv->display.dmc.dc_state, val & mask); val &= ~mask; val |= state; gen9_write_dc_state(dev_priv, val); - dev_priv->dmc.dc_state = val & mask; + dev_priv->display.dmc.dc_state = val & mask; } static void tgl_enable_dc3co(struct drm_i915_private *dev_priv) @@ -945,7 +946,7 @@ static bool gen9_dc_off_power_well_enabled(struct drm_i915_private *dev_priv, static void gen9_assert_dbuf_enabled(struct drm_i915_private *dev_priv) { u8 hw_enabled_dbuf_slices = intel_enabled_dbuf_slices_mask(dev_priv); - u8 enabled_dbuf_slices = dev_priv->dbuf.enabled_slices; + u8 enabled_dbuf_slices = dev_priv->display.dbuf.enabled_slices; drm_WARN(&dev_priv->drm, hw_enabled_dbuf_slices != enabled_dbuf_slices, @@ -958,7 +959,7 @@ void gen9_disable_dc_states(struct drm_i915_private *dev_priv) { struct intel_cdclk_config cdclk_config = {}; - if (dev_priv->dmc.target_dc_state == DC_STATE_EN_DC3CO) { + if (dev_priv->display.dmc.target_dc_state == DC_STATE_EN_DC3CO) { tgl_disable_dc3co(dev_priv); return; } @@ -971,7 +972,7 @@ void gen9_disable_dc_states(struct drm_i915_private *dev_priv) intel_cdclk_get_cdclk(dev_priv, &cdclk_config); /* Can't read out voltage_level so can't use intel_cdclk_changed() */ drm_WARN_ON(&dev_priv->drm, - intel_cdclk_needs_modeset(&dev_priv->cdclk.hw, + intel_cdclk_needs_modeset(&dev_priv->display.cdclk.hw, &cdclk_config)); gen9_assert_dbuf_enabled(dev_priv); @@ -1000,7 +1001,7 @@ static void gen9_dc_off_power_well_disable(struct drm_i915_private *dev_priv, if (!intel_dmc_has_payload(dev_priv)) return; - switch (dev_priv->dmc.target_dc_state) { + switch (dev_priv->display.dmc.target_dc_state) { case DC_STATE_EN_DC3CO: tgl_enable_dc3co(dev_priv); break; @@ -1156,10 +1157,10 @@ static void vlv_init_display_clock_gating(struct drm_i915_private *dev_priv) * (and never recovering) in this case. intel_dsi_post_disable() will * clear it when we turn off the display. */ - val = intel_de_read(dev_priv, DSPCLK_GATE_D); + val = intel_de_read(dev_priv, DSPCLK_GATE_D(dev_priv)); val &= DPOUNIT_CLOCK_GATE_DISABLE; val |= VRHUNIT_CLOCK_GATE_DISABLE; - intel_de_write(dev_priv, DSPCLK_GATE_D, val); + intel_de_write(dev_priv, DSPCLK_GATE_D(dev_priv), val); /* * Disable trickle feed and enable pnd deadline calculation @@ -1207,7 +1208,7 @@ static void vlv_display_power_well_init(struct drm_i915_private *dev_priv) * During driver initialization/resume we can avoid restoring the * part of the HW/SW state that will be inited anyway explicitly. */ - if (dev_priv->power_domains.initializing) + if (dev_priv->display.power.domains.initializing) return; intel_hpd_init(dev_priv); @@ -1302,7 +1303,7 @@ static void assert_chv_phy_status(struct drm_i915_private *dev_priv) lookup_power_well(dev_priv, VLV_DISP_PW_DPIO_CMN_BC); struct i915_power_well *cmn_d = lookup_power_well(dev_priv, CHV_DISP_PW_DPIO_CMN_D); - u32 phy_control = dev_priv->chv_phy_control; + u32 phy_control = dev_priv->display.power.chv_phy_control; u32 phy_status = 0; u32 phy_status_mask = 0xffffffff; @@ -1313,7 +1314,7 @@ static void assert_chv_phy_status(struct drm_i915_private *dev_priv) * reset (ie. the power well has been disabled at * least once). */ - if (!dev_priv->chv_phy_assert[DPIO_PHY0]) + if (!dev_priv->display.power.chv_phy_assert[DPIO_PHY0]) phy_status_mask &= ~(PHY_STATUS_CMN_LDO(DPIO_PHY0, DPIO_CH0) | PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 0) | PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH0, 1) | @@ -1321,7 +1322,7 @@ static void assert_chv_phy_status(struct drm_i915_private *dev_priv) PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 0) | PHY_STATUS_SPLINE_LDO(DPIO_PHY0, DPIO_CH1, 1)); - if (!dev_priv->chv_phy_assert[DPIO_PHY1]) + if (!dev_priv->display.power.chv_phy_assert[DPIO_PHY1]) phy_status_mask &= ~(PHY_STATUS_CMN_LDO(DPIO_PHY1, DPIO_CH0) | PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 0) | PHY_STATUS_SPLINE_LDO(DPIO_PHY1, DPIO_CH0, 1)); @@ -1397,7 +1398,7 @@ static void assert_chv_phy_status(struct drm_i915_private *dev_priv) drm_err(&dev_priv->drm, "Unexpected PHY_STATUS 0x%08x, expected 0x%08x (PHY_CONTROL=0x%08x)\n", intel_de_read(dev_priv, DISPLAY_PHY_STATUS) & phy_status_mask, - phy_status, dev_priv->chv_phy_control); + phy_status, dev_priv->display.power.chv_phy_control); } #undef BITS_SET @@ -1457,13 +1458,13 @@ static void chv_dpio_cmn_power_well_enable(struct drm_i915_private *dev_priv, vlv_dpio_put(dev_priv); - dev_priv->chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(phy); + dev_priv->display.power.chv_phy_control |= PHY_COM_LANE_RESET_DEASSERT(phy); intel_de_write(dev_priv, DISPLAY_PHY_CONTROL, - dev_priv->chv_phy_control); + dev_priv->display.power.chv_phy_control); drm_dbg_kms(&dev_priv->drm, "Enabled DPIO PHY%d (PHY_CONTROL=0x%08x)\n", - phy, dev_priv->chv_phy_control); + phy, dev_priv->display.power.chv_phy_control); assert_chv_phy_status(dev_priv); } @@ -1487,18 +1488,18 @@ static void chv_dpio_cmn_power_well_disable(struct drm_i915_private *dev_priv, assert_pll_disabled(dev_priv, PIPE_C); } - dev_priv->chv_phy_control &= ~PHY_COM_LANE_RESET_DEASSERT(phy); + dev_priv->display.power.chv_phy_control &= ~PHY_COM_LANE_RESET_DEASSERT(phy); intel_de_write(dev_priv, DISPLAY_PHY_CONTROL, - dev_priv->chv_phy_control); + dev_priv->display.power.chv_phy_control); vlv_set_power_well(dev_priv, power_well, false); drm_dbg_kms(&dev_priv->drm, "Disabled DPIO PHY%d (PHY_CONTROL=0x%08x)\n", - phy, dev_priv->chv_phy_control); + phy, dev_priv->display.power.chv_phy_control); /* PHY is fully reset now, so we can enable the PHY state asserts */ - dev_priv->chv_phy_assert[phy] = true; + dev_priv->display.power.chv_phy_assert[phy] = true; assert_chv_phy_status(dev_priv); } @@ -1516,7 +1517,7 @@ static void assert_chv_phy_powergate(struct drm_i915_private *dev_priv, enum dpi * reset (ie. the power well has been disabled at * least once). */ - if (!dev_priv->chv_phy_assert[phy]) + if (!dev_priv->display.power.chv_phy_assert[phy]) return; if (ch == DPIO_CH0) @@ -1570,27 +1571,27 @@ static void assert_chv_phy_powergate(struct drm_i915_private *dev_priv, enum dpi bool chv_phy_powergate_ch(struct drm_i915_private *dev_priv, enum dpio_phy phy, enum dpio_channel ch, bool override) { - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; bool was_override; mutex_lock(&power_domains->lock); - was_override = dev_priv->chv_phy_control & PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + was_override = dev_priv->display.power.chv_phy_control & PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); if (override == was_override) goto out; if (override) - dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); else - dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + dev_priv->display.power.chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); intel_de_write(dev_priv, DISPLAY_PHY_CONTROL, - dev_priv->chv_phy_control); + dev_priv->display.power.chv_phy_control); drm_dbg_kms(&dev_priv->drm, "Power gating DPIO PHY%d CH%d (DPIO_PHY_CONTROL=0x%08x)\n", - phy, ch, dev_priv->chv_phy_control); + phy, ch, dev_priv->display.power.chv_phy_control); assert_chv_phy_status(dev_priv); @@ -1604,26 +1605,26 @@ void chv_phy_powergate_lanes(struct intel_encoder *encoder, bool override, unsigned int mask) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_domains *power_domains = &dev_priv->display.power.domains; enum dpio_phy phy = vlv_dig_port_to_phy(enc_to_dig_port(encoder)); enum dpio_channel ch = vlv_dig_port_to_channel(enc_to_dig_port(encoder)); mutex_lock(&power_domains->lock); - dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD(0xf, phy, ch); - dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, phy, ch); + dev_priv->display.power.chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD(0xf, phy, ch); + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD(mask, phy, ch); if (override) - dev_priv->chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + dev_priv->display.power.chv_phy_control |= PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); else - dev_priv->chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); + dev_priv->display.power.chv_phy_control &= ~PHY_CH_POWER_DOWN_OVRD_EN(phy, ch); intel_de_write(dev_priv, DISPLAY_PHY_CONTROL, - dev_priv->chv_phy_control); + dev_priv->display.power.chv_phy_control); drm_dbg_kms(&dev_priv->drm, "Power gating DPIO PHY%d CH%d lanes 0x%x (PHY_CONTROL=0x%08x)\n", - phy, ch, mask, dev_priv->chv_phy_control); + phy, ch, mask, dev_priv->display.power.chv_phy_control); assert_chv_phy_status(dev_priv); @@ -1701,7 +1702,7 @@ static void chv_pipe_power_well_sync_hw(struct drm_i915_private *dev_priv, struct i915_power_well *power_well) { intel_de_write(dev_priv, DISPLAY_PHY_CONTROL, - dev_priv->chv_phy_control); + dev_priv->display.power.chv_phy_control); } static void chv_pipe_power_well_enable(struct drm_i915_private *dev_priv, @@ -1797,6 +1798,43 @@ tgl_tc_cold_off_power_well_is_enabled(struct drm_i915_private *dev_priv, return intel_power_well_refcount(power_well); } +static void xelpdp_aux_power_well_enable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + enum aux_ch aux_ch = i915_power_well_instance(power_well)->xelpdp.aux_ch; + + intel_de_rmw(dev_priv, XELPDP_DP_AUX_CH_CTL(aux_ch), + XELPDP_DP_AUX_CH_CTL_POWER_REQUEST, + XELPDP_DP_AUX_CH_CTL_POWER_REQUEST); + + /* + * The power status flag cannot be used to determine whether aux + * power wells have finished powering up. Instead we're + * expected to just wait a fixed 600us after raising the request + * bit. + */ + usleep_range(600, 1200); +} + +static void xelpdp_aux_power_well_disable(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + enum aux_ch aux_ch = i915_power_well_instance(power_well)->xelpdp.aux_ch; + + intel_de_rmw(dev_priv, XELPDP_DP_AUX_CH_CTL(aux_ch), + XELPDP_DP_AUX_CH_CTL_POWER_REQUEST, + 0); + usleep_range(10, 30); +} + +static bool xelpdp_aux_power_well_enabled(struct drm_i915_private *dev_priv, + struct i915_power_well *power_well) +{ + enum aux_ch aux_ch = i915_power_well_instance(power_well)->xelpdp.aux_ch; + + return intel_de_read(dev_priv, XELPDP_DP_AUX_CH_CTL(aux_ch)) & + XELPDP_DP_AUX_CH_CTL_POWER_STATUS; +} const struct i915_power_well_ops i9xx_always_on_power_well_ops = { .sync_hw = i9xx_power_well_sync_hw_noop, @@ -1910,3 +1948,10 @@ const struct i915_power_well_ops tgl_tc_cold_off_ops = { .disable = tgl_tc_cold_off_power_well_disable, .is_enabled = tgl_tc_cold_off_power_well_is_enabled, }; + +const struct i915_power_well_ops xelpdp_aux_power_well_ops = { + .sync_hw = i9xx_power_well_sync_hw_noop, + .enable = xelpdp_aux_power_well_enable, + .disable = xelpdp_aux_power_well_disable, + .is_enabled = xelpdp_aux_power_well_enabled, +}; diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.h b/drivers/gpu/drm/i915/display/intel_display_power_well.h index d0624642dcb6..e13b521e322a 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power_well.h +++ b/drivers/gpu/drm/i915/display/intel_display_power_well.h @@ -14,15 +14,15 @@ struct drm_i915_private; struct i915_power_well; #define for_each_power_well(__dev_priv, __power_well) \ - for ((__power_well) = (__dev_priv)->power_domains.power_wells; \ - (__power_well) - (__dev_priv)->power_domains.power_wells < \ - (__dev_priv)->power_domains.power_well_count; \ + for ((__power_well) = (__dev_priv)->display.power.domains.power_wells; \ + (__power_well) - (__dev_priv)->display.power.domains.power_wells < \ + (__dev_priv)->display.power.domains.power_well_count; \ (__power_well)++) #define for_each_power_well_reverse(__dev_priv, __power_well) \ - for ((__power_well) = (__dev_priv)->power_domains.power_wells + \ - (__dev_priv)->power_domains.power_well_count - 1; \ - (__power_well) - (__dev_priv)->power_domains.power_wells >= 0; \ + for ((__power_well) = (__dev_priv)->display.power.domains.power_wells + \ + (__dev_priv)->display.power.domains.power_well_count - 1; \ + (__power_well) - (__dev_priv)->display.power.domains.power_wells >= 0; \ (__power_well)--) /* @@ -80,6 +80,9 @@ struct i915_power_well_instance { */ u8 idx; } hsw; + struct { + u8 aux_ch; + } xelpdp; }; }; @@ -169,5 +172,6 @@ extern const struct i915_power_well_ops vlv_dpio_power_well_ops; extern const struct i915_power_well_ops icl_aux_power_well_ops; extern const struct i915_power_well_ops icl_ddi_power_well_ops; extern const struct i915_power_well_ops tgl_tc_cold_off_ops; +extern const struct i915_power_well_ops xelpdp_aux_power_well_ops; #endif diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h index 01977cd237eb..298d00a11f47 100644 --- a/drivers/gpu/drm/i915/display/intel_display_types.h +++ b/drivers/gpu/drm/i915/display/intel_display_types.h @@ -1130,6 +1130,7 @@ struct intel_crtc_state { /* m2_n2 for eDP downclock */ struct intel_link_m_n dp_m2_n2; bool has_drrs; + bool seamless_m_n; /* PSR is supported but might not be enabled due the lack of enabled planes */ bool has_psr; @@ -1712,7 +1713,7 @@ struct intel_dp { /* Display stream compression testing */ bool force_dsc_en; - int force_dsc_bpp; + int force_dsc_bpc; bool hobl_failed; bool hobl_active; diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c index fa9ef591b885..e52ecc0738a6 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.c +++ b/drivers/gpu/drm/i915/display/intel_dmc.c @@ -52,8 +52,8 @@ #define DISPLAY_VER12_DMC_MAX_FW_SIZE ICL_DMC_MAX_FW_SIZE -#define DG2_DMC_PATH DMC_PATH(dg2, 2, 06) -#define DG2_DMC_VERSION_REQUIRED DMC_VERSION(2, 06) +#define DG2_DMC_PATH DMC_PATH(dg2, 2, 07) +#define DG2_DMC_VERSION_REQUIRED DMC_VERSION(2, 07) MODULE_FIRMWARE(DG2_DMC_PATH); #define ADLP_DMC_PATH DMC_PATH(adlp, 2, 16) @@ -250,7 +250,7 @@ struct stepping_info { static bool has_dmc_id_fw(struct drm_i915_private *i915, int dmc_id) { - return i915->dmc.dmc_info[dmc_id].payload; + return i915->display.dmc.dmc_info[dmc_id].payload; } bool intel_dmc_has_payload(struct drm_i915_private *i915) @@ -277,6 +277,17 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv) intel_de_posting_read(dev_priv, DC_STATE_DEBUG); } +static void disable_event_handler(struct drm_i915_private *i915, + i915_reg_t ctl_reg, i915_reg_t htp_reg) +{ + intel_de_write(i915, ctl_reg, + REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK, + DMC_EVT_CTL_TYPE_EDGE_0_1) | + REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK, + DMC_EVT_CTL_EVENT_ID_FALSE)); + intel_de_write(i915, htp_reg, 0); +} + static void disable_flip_queue_event(struct drm_i915_private *i915, i915_reg_t ctl_reg, i915_reg_t htp_reg) @@ -299,12 +310,7 @@ disable_flip_queue_event(struct drm_i915_private *i915, return; } - intel_de_write(i915, ctl_reg, - REG_FIELD_PREP(DMC_EVT_CTL_TYPE_MASK, - DMC_EVT_CTL_TYPE_EDGE_0_1) | - REG_FIELD_PREP(DMC_EVT_CTL_EVENT_ID_MASK, - DMC_EVT_CTL_EVENT_ID_FALSE)); - intel_de_write(i915, htp_reg, 0); + disable_event_handler(i915, ctl_reg, htp_reg); } static bool @@ -356,6 +362,51 @@ disable_all_flip_queue_events(struct drm_i915_private *i915) } } +static void disable_all_event_handlers(struct drm_i915_private *i915) +{ + int id; + + /* TODO: disable the event handlers on pre-GEN12 platforms as well */ + if (DISPLAY_VER(i915) < 12) + return; + + for (id = DMC_FW_MAIN; id < DMC_FW_MAX; id++) { + int handler; + + if (!has_dmc_id_fw(i915, id)) + continue; + + for (handler = 0; handler < DMC_EVENT_HANDLER_COUNT_GEN12; handler++) + disable_event_handler(i915, + DMC_EVT_CTL(i915, id, handler), + DMC_EVT_HTP(i915, id, handler)); + } +} + +static void pipedmc_clock_gating_wa(struct drm_i915_private *i915, bool enable) +{ + enum pipe pipe; + + if (DISPLAY_VER(i915) != 13) + return; + + /* + * Wa_16015201720:adl-p,dg2 + * The WA requires clock gating to be disabled all the time + * for pipe A and B. + * For pipe C and D clock gating needs to be disabled only + * during initializing the firmware. + */ + if (enable) + for (pipe = PIPE_A; pipe <= PIPE_D; pipe++) + intel_de_rmw(i915, CLKGATE_DIS_PSL_EXT(pipe), + 0, PIPEDMC_GATING_DIS); + else + for (pipe = PIPE_C; pipe <= PIPE_D; pipe++) + intel_de_rmw(i915, CLKGATE_DIS_PSL_EXT(pipe), + PIPEDMC_GATING_DIS, 0); +} + /** * intel_dmc_load_program() - write the firmware from memory to register. * @dev_priv: i915 drm device. @@ -366,12 +417,16 @@ disable_all_flip_queue_events(struct drm_i915_private *i915) */ void intel_dmc_load_program(struct drm_i915_private *dev_priv) { - struct intel_dmc *dmc = &dev_priv->dmc; + struct intel_dmc *dmc = &dev_priv->display.dmc; u32 id, i; if (!intel_dmc_has_payload(dev_priv)) return; + pipedmc_clock_gating_wa(dev_priv, true); + + disable_all_event_handlers(dev_priv); + assert_rpm_wakelock_held(&dev_priv->runtime_pm); preempt_disable(); @@ -393,7 +448,7 @@ void intel_dmc_load_program(struct drm_i915_private *dev_priv) } } - dev_priv->dmc.dc_state = 0; + dev_priv->display.dmc.dc_state = 0; gen9_set_dc_state_debugmask(dev_priv); @@ -403,12 +458,31 @@ void intel_dmc_load_program(struct drm_i915_private *dev_priv) * here. */ disable_all_flip_queue_events(dev_priv); + + pipedmc_clock_gating_wa(dev_priv, false); +} + +/** + * intel_dmc_disable_program() - disable the firmware + * @i915: i915 drm device + * + * Disable all event handlers in the firmware, making sure the firmware is + * inactive after the display is uninitialized. + */ +void intel_dmc_disable_program(struct drm_i915_private *i915) +{ + if (!intel_dmc_has_payload(i915)) + return; + + pipedmc_clock_gating_wa(i915, true); + disable_all_event_handlers(i915); + pipedmc_clock_gating_wa(i915, false); } void assert_dmc_loaded(struct drm_i915_private *i915) { drm_WARN_ONCE(&i915->drm, - !intel_de_read(i915, DMC_PROGRAM(i915->dmc.dmc_info[DMC_FW_MAIN].start_mmioaddr, 0)), + !intel_de_read(i915, DMC_PROGRAM(i915->display.dmc.dmc_info[DMC_FW_MAIN].start_mmioaddr, 0)), "DMC program storage start is NULL\n"); drm_WARN_ONCE(&i915->drm, !intel_de_read(i915, DMC_SSP_BASE), "DMC SSP Base Not fine\n"); @@ -445,7 +519,7 @@ static void dmc_set_fw_offset(struct intel_dmc *dmc, { unsigned int i, id; - struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), display.dmc); for (i = 0; i < num_entries; i++) { id = package_ver <= 1 ? DMC_FW_MAIN : fw_info[i].dmc_id; @@ -473,7 +547,7 @@ static bool dmc_mmio_addr_sanity_check(struct intel_dmc *dmc, const u32 *mmioaddr, u32 mmio_count, int header_ver, u8 dmc_id) { - struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), display.dmc); u32 start_range, end_range; int i; @@ -511,7 +585,7 @@ static u32 parse_dmc_fw_header(struct intel_dmc *dmc, const struct intel_dmc_header_base *dmc_header, size_t rem_size, u8 dmc_id) { - struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), display.dmc); struct dmc_fw_info *dmc_info = &dmc->dmc_info[dmc_id]; unsigned int header_len_bytes, dmc_header_size, payload_size, i; const u32 *mmioaddr, *mmiodata; @@ -622,7 +696,7 @@ parse_dmc_fw_package(struct intel_dmc *dmc, const struct stepping_info *si, size_t rem_size) { - struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), display.dmc); u32 package_size = sizeof(struct intel_package_header); u32 num_entries, max_entries; const struct intel_fw_info *fw_info; @@ -676,7 +750,7 @@ static u32 parse_dmc_fw_css(struct intel_dmc *dmc, struct intel_css_header *css_header, size_t rem_size) { - struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), dmc); + struct drm_i915_private *i915 = container_of(dmc, typeof(*i915), display.dmc); if (rem_size < sizeof(struct intel_css_header)) { drm_err(&i915->drm, "Truncated DMC firmware, refusing.\n"); @@ -713,7 +787,7 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv, struct intel_css_header *css_header; struct intel_package_header *package_header; struct intel_dmc_header_base *dmc_header; - struct intel_dmc *dmc = &dev_priv->dmc; + struct intel_dmc *dmc = &dev_priv->display.dmc; struct stepping_info display_info = { '*', '*'}; const struct stepping_info *si = intel_get_stepping_info(dev_priv, &display_info); u32 readcount = 0; @@ -740,7 +814,7 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv, readcount += r; for (id = 0; id < DMC_FW_MAX; id++) { - if (!dev_priv->dmc.dmc_info[id].present) + if (!dev_priv->display.dmc.dmc_info[id].present) continue; offset = readcount + dmc->dmc_info[id].dmc_offset * 4; @@ -756,15 +830,15 @@ static void parse_dmc_fw(struct drm_i915_private *dev_priv, static void intel_dmc_runtime_pm_get(struct drm_i915_private *dev_priv) { - drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref); - dev_priv->dmc.wakeref = + drm_WARN_ON(&dev_priv->drm, dev_priv->display.dmc.wakeref); + dev_priv->display.dmc.wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_INIT); } static void intel_dmc_runtime_pm_put(struct drm_i915_private *dev_priv) { intel_wakeref_t wakeref __maybe_unused = - fetch_and_zero(&dev_priv->dmc.wakeref); + fetch_and_zero(&dev_priv->display.dmc.wakeref); intel_display_power_put(dev_priv, POWER_DOMAIN_INIT, wakeref); } @@ -775,10 +849,10 @@ static void dmc_load_work_fn(struct work_struct *work) struct intel_dmc *dmc; const struct firmware *fw = NULL; - dev_priv = container_of(work, typeof(*dev_priv), dmc.work); - dmc = &dev_priv->dmc; + dev_priv = container_of(work, typeof(*dev_priv), display.dmc.work); + dmc = &dev_priv->display.dmc; - request_firmware(&fw, dev_priv->dmc.fw_path, dev_priv->drm.dev); + request_firmware(&fw, dev_priv->display.dmc.fw_path, dev_priv->drm.dev); parse_dmc_fw(dev_priv, fw); if (intel_dmc_has_payload(dev_priv)) { @@ -787,7 +861,7 @@ static void dmc_load_work_fn(struct work_struct *work) drm_info(&dev_priv->drm, "Finished loading DMC firmware %s (v%u.%u)\n", - dev_priv->dmc.fw_path, DMC_VERSION_MAJOR(dmc->version), + dev_priv->display.dmc.fw_path, DMC_VERSION_MAJOR(dmc->version), DMC_VERSION_MINOR(dmc->version)); } else { drm_notice(&dev_priv->drm, @@ -810,9 +884,9 @@ static void dmc_load_work_fn(struct work_struct *work) */ void intel_dmc_ucode_init(struct drm_i915_private *dev_priv) { - struct intel_dmc *dmc = &dev_priv->dmc; + struct intel_dmc *dmc = &dev_priv->display.dmc; - INIT_WORK(&dev_priv->dmc.work, dmc_load_work_fn); + INIT_WORK(&dev_priv->display.dmc.work, dmc_load_work_fn); if (!HAS_DMC(dev_priv)) return; @@ -895,7 +969,7 @@ void intel_dmc_ucode_init(struct drm_i915_private *dev_priv) } drm_dbg_kms(&dev_priv->drm, "Loading %s\n", dmc->fw_path); - schedule_work(&dev_priv->dmc.work); + schedule_work(&dev_priv->display.dmc.work); } /** @@ -911,7 +985,7 @@ void intel_dmc_ucode_suspend(struct drm_i915_private *dev_priv) if (!HAS_DMC(dev_priv)) return; - flush_work(&dev_priv->dmc.work); + flush_work(&dev_priv->display.dmc.work); /* Drop the reference held in case DMC isn't loaded. */ if (!intel_dmc_has_payload(dev_priv)) @@ -953,16 +1027,16 @@ void intel_dmc_ucode_fini(struct drm_i915_private *dev_priv) return; intel_dmc_ucode_suspend(dev_priv); - drm_WARN_ON(&dev_priv->drm, dev_priv->dmc.wakeref); + drm_WARN_ON(&dev_priv->drm, dev_priv->display.dmc.wakeref); for (id = 0; id < DMC_FW_MAX; id++) - kfree(dev_priv->dmc.dmc_info[id].payload); + kfree(dev_priv->display.dmc.dmc_info[id].payload); } void intel_dmc_print_error_state(struct drm_i915_error_state_buf *m, struct drm_i915_private *i915) { - struct intel_dmc *dmc = &i915->dmc; + struct intel_dmc *dmc = &i915->display.dmc; if (!HAS_DMC(i915)) return; @@ -984,7 +1058,7 @@ static int intel_dmc_debugfs_status_show(struct seq_file *m, void *unused) if (!HAS_DMC(i915)) return -ENODEV; - dmc = &i915->dmc; + dmc = &i915->display.dmc; wakeref = intel_runtime_pm_get(&i915->runtime_pm); diff --git a/drivers/gpu/drm/i915/display/intel_dmc.h b/drivers/gpu/drm/i915/display/intel_dmc.h index 41091aee3b47..67e03315ef99 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc.h +++ b/drivers/gpu/drm/i915/display/intel_dmc.h @@ -47,6 +47,7 @@ struct intel_dmc { void intel_dmc_ucode_init(struct drm_i915_private *i915); void intel_dmc_load_program(struct drm_i915_private *i915); +void intel_dmc_disable_program(struct drm_i915_private *i915); void intel_dmc_ucode_fini(struct drm_i915_private *i915); void intel_dmc_ucode_suspend(struct drm_i915_private *i915); void intel_dmc_ucode_resume(struct drm_i915_private *i915); diff --git a/drivers/gpu/drm/i915/display/intel_dmc_regs.h b/drivers/gpu/drm/i915/display/intel_dmc_regs.h index 238620b55966..5e5e41644ddf 100644 --- a/drivers/gpu/drm/i915/display/intel_dmc_regs.h +++ b/drivers/gpu/drm/i915/display/intel_dmc_regs.h @@ -28,6 +28,8 @@ #define _DMC_REG(i915, dmc_id, reg) \ ((reg) - __DMC_REG_MMIO_BASE + _DMC_REG_MMIO_BASE(i915, dmc_id)) +#define DMC_EVENT_HANDLER_COUNT_GEN12 8 + #define _DMC_EVT_HTP_0 0x8f004 #define DMC_EVT_HTP(i915, dmc_id, handler) \ diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index a4e113253df3..c9be61d2348e 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -286,11 +286,22 @@ static int intel_dp_max_common_rate(struct intel_dp *intel_dp) return intel_dp_common_rate(intel_dp, intel_dp->num_common_rates - 1); } +static int intel_dp_max_source_lane_count(struct intel_digital_port *dig_port) +{ + int vbt_max_lanes = intel_bios_dp_max_lane_count(&dig_port->base); + int max_lanes = dig_port->max_lanes; + + if (vbt_max_lanes) + max_lanes = min(max_lanes, vbt_max_lanes); + + return max_lanes; +} + /* Theoretical max between source and sink */ static int intel_dp_max_common_lane_count(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - int source_max = dig_port->max_lanes; + int source_max = intel_dp_max_source_lane_count(dig_port); int sink_max = intel_dp->max_sink_lane_count; int fia_max = intel_tc_port_fia_max_lane_count(dig_port); int lttpr_max = drm_dp_lttpr_max_lane_count(intel_dp->lttpr_common_caps); @@ -389,23 +400,13 @@ static int dg2_max_source_rate(struct intel_dp *intel_dp) return intel_dp_is_edp(intel_dp) ? 810000 : 1350000; } -static bool is_low_voltage_sku(struct drm_i915_private *i915, enum phy phy) -{ - u32 voltage; - - voltage = intel_de_read(i915, ICL_PORT_COMP_DW3(phy)) & VOLTAGE_INFO_MASK; - - return voltage == VOLTAGE_INFO_0_85V; -} - static int icl_max_source_rate(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - if (intel_phy_is_combo(dev_priv, phy) && - (is_low_voltage_sku(dev_priv, phy) || !intel_dp_is_edp(intel_dp))) + if (intel_phy_is_combo(dev_priv, phy) && !intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -413,23 +414,7 @@ static int icl_max_source_rate(struct intel_dp *intel_dp) static int ehl_max_source_rate(struct intel_dp *intel_dp) { - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(dev_priv, dig_port->base.port); - - if (intel_dp_is_edp(intel_dp) || is_low_voltage_sku(dev_priv, phy)) - return 540000; - - return 810000; -} - -static int dg1_max_source_rate(struct intel_dp *intel_dp) -{ - struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); - enum phy phy = intel_port_to_phy(i915, dig_port->base.port); - - if (intel_phy_is_combo(i915, phy) && is_low_voltage_sku(i915, phy)) + if (intel_dp_is_edp(intel_dp)) return 540000; return 810000; @@ -491,7 +476,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp) max_rate = dg2_max_source_rate(intel_dp); else if (IS_ALDERLAKE_P(dev_priv) || IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv) || IS_ROCKETLAKE(dev_priv)) - max_rate = dg1_max_source_rate(intel_dp); + max_rate = 810000; else if (IS_JSL_EHL(dev_priv)) max_rate = ehl_max_source_rate(intel_dp); else @@ -720,7 +705,7 @@ static u16 intel_dp_dsc_get_output_bpp(struct drm_i915_private *i915, if (bigjoiner) { u32 max_bpp_bigjoiner = - i915->max_cdclk_freq * 48 / + i915->display.cdclk.max_cdclk_freq * 48 / intel_dp_mode_to_fec_clock(mode_clock); bits_per_pixel = min(bits_per_pixel, max_bpp_bigjoiner); @@ -1312,21 +1297,45 @@ intel_dp_adjust_compliance_config(struct intel_dp *intel_dp, } } +static bool has_seamless_m_n(struct intel_connector *connector) +{ + struct drm_i915_private *i915 = to_i915(connector->base.dev); + + /* + * Seamless M/N reprogramming only implemented + * for BDW+ double buffered M/N registers so far. + */ + return HAS_DOUBLE_BUFFERED_M_N(i915) && + intel_panel_drrs_type(connector) == DRRS_TYPE_SEAMLESS; +} + +static int intel_dp_mode_clock(const struct intel_crtc_state *crtc_state, + const struct drm_connector_state *conn_state) +{ + struct intel_connector *connector = to_intel_connector(conn_state->connector); + const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; + + /* FIXME a bit of a mess wrt clock vs. crtc_clock */ + if (has_seamless_m_n(connector)) + return intel_panel_highest_mode(connector, adjusted_mode)->clock; + else + return adjusted_mode->crtc_clock; +} + /* Optimize link config in order: max bpp, min clock, min lanes */ static int intel_dp_compute_link_config_wide(struct intel_dp *intel_dp, struct intel_crtc_state *pipe_config, + const struct drm_connector_state *conn_state, const struct link_config_limits *limits) { - struct drm_display_mode *adjusted_mode = &pipe_config->hw.adjusted_mode; - int bpp, i, lane_count; + int bpp, i, lane_count, clock = intel_dp_mode_clock(pipe_config, conn_state); int mode_rate, link_rate, link_avail; for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) { int output_bpp = intel_dp_output_bpp(pipe_config->output_format, bpp); - mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock, - output_bpp); + mode_rate = intel_dp_link_required(clock, output_bpp); for (i = 0; i < intel_dp->num_common_rates; i++) { link_rate = intel_dp_common_rate(intel_dp, i); @@ -1377,7 +1386,18 @@ static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 max_req_bpc) return 0; } -#define DSC_SUPPORTED_VERSION_MIN 1 +static int intel_dp_source_dsc_version_minor(struct intel_dp *intel_dp) +{ + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + + return DISPLAY_VER(i915) >= 14 ? 2 : 1; +} + +static int intel_dp_sink_dsc_version_minor(struct intel_dp *intel_dp) +{ + return (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] & DP_DSC_MINOR_MASK) >> + DP_DSC_MINOR_SHIFT; +} static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, struct intel_crtc_state *crtc_state) @@ -1395,6 +1415,7 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, * DP_DSC_RC_BUF_SIZE for this. */ vdsc_cfg->rc_model_size = DSC_RC_MODEL_SIZE_CONST; + vdsc_cfg->pic_height = crtc_state->hw.adjusted_mode.crtc_vdisplay; /* * Slice Height of 8 works for all currently available panels. So start @@ -1416,9 +1437,8 @@ static int intel_dp_dsc_compute_params(struct intel_encoder *encoder, (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] & DP_DSC_MAJOR_MASK) >> DP_DSC_MAJOR_SHIFT; vdsc_cfg->dsc_version_minor = - min(DSC_SUPPORTED_VERSION_MIN, - (intel_dp->dsc_dpcd[DP_DSC_REV - DP_DSC_SUPPORT] & - DP_DSC_MINOR_MASK) >> DP_DSC_MINOR_SHIFT); + min(intel_dp_source_dsc_version_minor(intel_dp), + intel_dp_sink_dsc_version_minor(intel_dp)); vdsc_cfg->convert_rgb = intel_dp->dsc_dpcd[DP_DSC_DEC_COLOR_FORMAT_CAP - DP_DSC_SUPPORT] & DP_DSC_RGB; @@ -1464,6 +1484,11 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, pipe_bpp = intel_dp_dsc_compute_bpp(intel_dp, conn_state->max_requested_bpc); + if (intel_dp->force_dsc_bpc) { + pipe_bpp = intel_dp->force_dsc_bpc * 3; + drm_dbg_kms(&dev_priv->drm, "Input DSC BPP forced to %d", pipe_bpp); + } + /* Min Input BPC for ICL+ is 8 */ if (pipe_bpp < 8 * 3) { drm_dbg_kms(&dev_priv->drm, @@ -1515,28 +1540,12 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp, pipe_config->dsc.slice_count = dsc_dp_slice_count; } - /* As of today we support DSC for only RGB */ - if (intel_dp->force_dsc_bpp) { - if (intel_dp->force_dsc_bpp >= 8 && - intel_dp->force_dsc_bpp < pipe_bpp) { - drm_dbg_kms(&dev_priv->drm, - "DSC BPP forced to %d", - intel_dp->force_dsc_bpp); - pipe_config->dsc.compressed_bpp = - intel_dp->force_dsc_bpp; - } else { - drm_dbg_kms(&dev_priv->drm, - "Invalid DSC BPP %d", - intel_dp->force_dsc_bpp); - } - } - /* * VDSC engine operates at 1 Pixel per clock, so if peak pixel rate * is greater than the maximum Cdclock and if slice count is even * then we need to use 2 VDSC instances. */ - if (adjusted_mode->crtc_clock > dev_priv->max_cdclk_freq || + if (adjusted_mode->crtc_clock > dev_priv->display.cdclk.max_cdclk_freq || pipe_config->bigjoiner_pipes) { if (pipe_config->dsc.slice_count < 2) { drm_dbg_kms(&dev_priv->drm, @@ -1626,7 +1635,7 @@ intel_dp_compute_link_config(struct intel_encoder *encoder, * Optimize for slow and wide for everything, because there are some * eDP 1.3 and 1.4 panels don't work well with fast and narrow. */ - ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits); + ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, conn_state, &limits); if (ret || joiner_needs_dsc || intel_dp->force_dsc_en) { drm_dbg_kms(&i915->drm, "Try DSC (fallback=%s, joiner=%s, force=%s)\n", @@ -1869,8 +1878,7 @@ intel_dp_compute_hdr_metadata_infoframe_sdp(struct intel_dp *intel_dp, static bool cpu_transcoder_has_drrs(struct drm_i915_private *i915, enum transcoder cpu_transcoder) { - /* M1/N1 is double buffered */ - if (DISPLAY_VER(i915) >= 9 || IS_BROADWELL(i915)) + if (HAS_DOUBLE_BUFFERED_M_N(i915)) return true; return intel_cpu_transcoder_has_m2_n2(i915, cpu_transcoder); @@ -1908,13 +1916,16 @@ static bool can_enable_drrs(struct intel_connector *connector, static void intel_dp_drrs_compute_config(struct intel_connector *connector, struct intel_crtc_state *pipe_config, - int output_bpp, bool constant_n) + int output_bpp) { struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *downclock_mode = intel_panel_downclock_mode(connector, &pipe_config->hw.adjusted_mode); int pixel_clock; + if (has_seamless_m_n(connector)) + pipe_config->seamless_m_n = true; + if (!can_enable_drrs(connector, pipe_config, downclock_mode)) { if (intel_cpu_transcoder_has_m2_n2(i915, pipe_config->cpu_transcoder)) intel_zero_m_n(&pipe_config->dp_m2_n2); @@ -1932,7 +1943,7 @@ intel_dp_drrs_compute_config(struct intel_connector *connector, intel_link_compute_m_n(output_bpp, pipe_config->lane_count, pixel_clock, pipe_config->port_clock, &pipe_config->dp_m2_n2, - constant_n, pipe_config->fec_enable); + pipe_config->fec_enable); /* FIXME: abstract this better */ if (pipe_config->splitter.enable) @@ -2007,7 +2018,6 @@ intel_dp_compute_config(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); const struct drm_display_mode *fixed_mode; struct intel_connector *connector = intel_dp->attached_connector; - bool constant_n = drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_CONSTANT_N); int ret = 0, output_bpp; if (HAS_PCH_SPLIT(dev_priv) && !HAS_DDI(dev_priv) && encoder->port != PORT_A) @@ -2086,7 +2096,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, adjusted_mode->crtc_clock, pipe_config->port_clock, &pipe_config->dp_m_n, - constant_n, pipe_config->fec_enable); + pipe_config->fec_enable); /* FIXME: abstract this better */ if (pipe_config->splitter.enable) @@ -2097,8 +2107,7 @@ intel_dp_compute_config(struct intel_encoder *encoder, intel_vrr_compute_config(pipe_config, conn_state); intel_psr_compute_config(intel_dp, pipe_config, conn_state); - intel_dp_drrs_compute_config(connector, pipe_config, - output_bpp, constant_n); + intel_dp_drrs_compute_config(connector, pipe_config, output_bpp); intel_dp_compute_vsc_sdp(intel_dp, pipe_config, conn_state); intel_dp_compute_hdr_metadata_infoframe_sdp(intel_dp, pipe_config, conn_state); @@ -5032,9 +5041,9 @@ static void intel_dp_oob_hotplug_event(struct drm_connector *connector) struct drm_i915_private *i915 = to_i915(connector->dev); spin_lock_irq(&i915->irq_lock); - i915->hotplug.event_bits |= BIT(encoder->hpd_pin); + i915->display.hotplug.event_bits |= BIT(encoder->hpd_pin); spin_unlock_irq(&i915->irq_lock); - queue_delayed_work(system_wq, &i915->hotplug.hotplug_work, 0); + queue_delayed_work(system_wq, &i915->display.hotplug.hotplug_work, 0); } static const struct drm_connector_funcs intel_dp_connector_funcs = { @@ -5192,7 +5201,7 @@ intel_edp_add_properties(struct intel_dp *intel_dp) return; drm_connector_set_panel_orientation_with_quirk(&connector->base, - i915->vbt.orientation, + i915->display.vbt.orientation, fixed_mode->hdisplay, fixed_mode->vdisplay); } @@ -5302,8 +5311,6 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp, intel_panel_init(intel_connector); - if (!(dev_priv->quirks & QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK)) - intel_connector->panel.backlight.power = intel_pps_backlight_power; intel_backlight_setup(intel_connector, pipe); intel_edp_add_properties(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c index 2bc119374555..48c375c65a41 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c @@ -42,7 +42,7 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp) bool done; #define C (((status = intel_uncore_read_notrace(&i915->uncore, ch_ctl)) & DP_AUX_CH_CTL_SEND_BUSY) == 0) - done = wait_event_timeout(i915->gmbus_wait_queue, C, + done = wait_event_timeout(i915->display.gmbus.wait_queue, C, msecs_to_jiffies_timeout(timeout_ms)); /* just trace the final value */ @@ -86,7 +86,7 @@ static u32 ilk_get_aux_clock_divider(struct intel_dp *intel_dp, int index) * divide by 2000 and use that */ if (dig_port->aux_ch == AUX_CH_A) - freq = dev_priv->cdclk.hw.cdclk; + freq = dev_priv->display.cdclk.hw.cdclk; else freq = RUNTIME_INFO(dev_priv)->rawclk_freq; return DIV_ROUND_CLOSEST(freq, 2000); @@ -150,6 +150,7 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, u32 unused) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); u32 ret; /* @@ -170,6 +171,13 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp, if (intel_tc_port_in_tbt_alt_mode(dig_port)) ret |= DP_AUX_CH_CTL_TBT_IO; + /* + * Power request bit is already set during aux power well enable. + * Preserve the bit across aux transactions. + */ + if (DISPLAY_VER(i915) >= 14) + ret |= XELPDP_DP_AUX_CH_CTL_POWER_REQUEST; + return ret; } @@ -629,6 +637,46 @@ static i915_reg_t tgl_aux_data_reg(struct intel_dp *intel_dp, int index) } } +static i915_reg_t xelpdp_aux_ctl_reg(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + enum aux_ch aux_ch = dig_port->aux_ch; + + switch (aux_ch) { + case AUX_CH_A: + case AUX_CH_B: + case AUX_CH_USBC1: + case AUX_CH_USBC2: + case AUX_CH_USBC3: + case AUX_CH_USBC4: + return XELPDP_DP_AUX_CH_CTL(aux_ch); + default: + MISSING_CASE(aux_ch); + return XELPDP_DP_AUX_CH_CTL(AUX_CH_A); + } +} + +static i915_reg_t xelpdp_aux_data_reg(struct intel_dp *intel_dp, int index) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + enum aux_ch aux_ch = dig_port->aux_ch; + + switch (aux_ch) { + case AUX_CH_A: + case AUX_CH_B: + case AUX_CH_USBC1: + case AUX_CH_USBC2: + case AUX_CH_USBC3: + case AUX_CH_USBC4: + return XELPDP_DP_AUX_CH_DATA(aux_ch, index); + default: + MISSING_CASE(aux_ch); + return XELPDP_DP_AUX_CH_DATA(AUX_CH_A, index); + } +} + void intel_dp_aux_fini(struct intel_dp *intel_dp) { if (cpu_latency_qos_request_active(&intel_dp->pm_qos)) @@ -644,7 +692,10 @@ void intel_dp_aux_init(struct intel_dp *intel_dp) struct intel_encoder *encoder = &dig_port->base; enum aux_ch aux_ch = dig_port->aux_ch; - if (DISPLAY_VER(dev_priv) >= 12) { + if (DISPLAY_VER(dev_priv) >= 14) { + intel_dp->aux_ch_ctl_reg = xelpdp_aux_ctl_reg; + intel_dp->aux_ch_data_reg = xelpdp_aux_data_reg; + } else if (DISPLAY_VER(dev_priv) >= 12) { intel_dp->aux_ch_ctl_reg = tgl_aux_ctl_reg; intel_dp->aux_ch_data_reg = tgl_aux_data_reg; } else if (DISPLAY_VER(dev_priv) >= 9) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c index a7640dbcf00e..88689124c013 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c @@ -17,6 +17,7 @@ #include "intel_dp.h" #include "intel_dp_hdcp.h" #include "intel_hdcp.h" +#include "intel_hdcp_regs.h" static unsigned int transcoder_to_stream_enc_status(enum transcoder cpu_transcoder) { diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 9feaf1a589f3..3d3efcf02011 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -37,17 +37,6 @@ static void intel_dp_reset_lttpr_count(struct intel_dp *intel_dp) DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] = 0; } -static const char *intel_dp_phy_name(enum drm_dp_phy dp_phy, - char *buf, size_t buf_size) -{ - if (dp_phy == DP_PHY_DPRX) - snprintf(buf, buf_size, "DPRX"); - else - snprintf(buf, buf_size, "LTTPR %d", dp_phy - DP_PHY_LTTPR1 + 1); - - return buf; -} - static u8 *intel_dp_lttpr_phy_caps(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy) { @@ -60,20 +49,19 @@ static void intel_dp_read_lttpr_phy_caps(struct intel_dp *intel_dp, { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; u8 *phy_caps = intel_dp_lttpr_phy_caps(intel_dp, dp_phy); - char phy_name[10]; - - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); if (drm_dp_read_lttpr_phy_caps(&intel_dp->aux, dpcd, dp_phy, phy_caps) < 0) { drm_dbg_kms(&dp_to_i915(intel_dp)->drm, "[ENCODER:%d:%s][%s] failed to read the PHY caps\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return; } drm_dbg_kms(&dp_to_i915(intel_dp)->drm, "[ENCODER:%d:%s][%s] PHY capabilities: %*ph\n", - encoder->base.base.id, encoder->base.name, phy_name, + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy), (int)sizeof(intel_dp->lttpr_phy_caps[0]), phy_caps); } @@ -423,14 +411,13 @@ intel_dp_get_adjust_train(struct intel_dp *intel_dp, { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *i915 = to_i915(encoder->base.dev); - char phy_name[10]; int lane; if (intel_dp_is_uhbr(crtc_state)) { drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] 128b/132b, lanes: %d, " "TX FFE request: " TRAIN_REQ_FMT "\n", encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), crtc_state->lane_count, TRAIN_REQ_TX_FFE_ARGS(link_status)); } else { @@ -438,7 +425,7 @@ intel_dp_get_adjust_train(struct intel_dp *intel_dp, "vswing request: " TRAIN_REQ_FMT ", " "pre-emphasis request: " TRAIN_REQ_FMT "\n", encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), crtc_state->lane_count, TRAIN_REQ_VSWING_ARGS(link_status), TRAIN_REQ_PREEMPH_ARGS(link_status)); @@ -503,13 +490,12 @@ intel_dp_program_link_training_pattern(struct intel_dp *intel_dp, struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *i915 = to_i915(encoder->base.dev); u8 train_pat = intel_dp_training_pattern_symbol(dp_train_pat); - char phy_name[10]; if (train_pat != DP_TRAINING_PATTERN_DISABLE) drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Using DP training pattern TPS%c\n", encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), dp_training_pattern_name(train_pat)); intel_dp->set_link_train(intel_dp, crtc_state, dp_train_pat); @@ -546,13 +532,12 @@ void intel_dp_set_signal_levels(struct intel_dp *intel_dp, { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *i915 = to_i915(encoder->base.dev); - char phy_name[10]; if (intel_dp_is_uhbr(crtc_state)) { drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] 128b/132b, lanes: %d, " "TX FFE presets: " TRAIN_SET_FMT "\n", encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), crtc_state->lane_count, TRAIN_SET_TX_FFE_ARGS(intel_dp->train_set)); } else { @@ -560,7 +545,7 @@ void intel_dp_set_signal_levels(struct intel_dp *intel_dp, "vswing levels: " TRAIN_SET_FMT ", " "pre-emphasis levels: " TRAIN_SET_FMT "\n", encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), crtc_state->lane_count, TRAIN_SET_VSWING_ARGS(intel_dp->train_set), TRAIN_SET_PREEMPH_ARGS(intel_dp->train_set)); @@ -671,6 +656,28 @@ intel_dp_prepare_link_train(struct intel_dp *intel_dp, intel_dp_compute_rate(intel_dp, crtc_state->port_clock, &link_bw, &rate_select); + /* + * WaEdpLinkRateDataReload + * + * Parade PS8461E MUX (used on varius TGL+ laptops) needs + * to snoop the link rates reported by the sink when we + * use LINK_RATE_SET in order to operate in jitter cleaning + * mode (as opposed to redriver mode). Unfortunately it + * loses track of the snooped link rates when powered down, + * so we need to make it re-snoop often. Without this high + * link rates are not stable. + */ + if (!link_bw) { + struct intel_connector *connector = intel_dp->attached_connector; + __le16 sink_rates[DP_MAX_SUPPORTED_RATES]; + + drm_dbg_kms(&i915->drm, "[CONNECTOR:%d:%s] Reloading eDP link rates\n", + connector->base.base.id, connector->base.name); + + drm_dp_dpcd_read(&intel_dp->aux, DP_SUPPORTED_LINK_RATES, + sink_rates, sizeof(sink_rates)); + } + if (link_bw) drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s] Using LINK_BW_SET value %02x\n", @@ -732,12 +739,11 @@ intel_dp_dump_link_status(struct intel_dp *intel_dp, enum drm_dp_phy dp_phy, { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *i915 = to_i915(encoder->base.dev); - char phy_name[10]; drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] ln0_1:0x%x ln2_3:0x%x align:0x%x sink:0x%x adj_req0_1:0x%x adj_req2_3:0x%x\n", encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), link_status[0], link_status[1], link_status[2], link_status[3], link_status[4], link_status[5]); } @@ -757,21 +763,19 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, int voltage_tries, cr_tries, max_cr_tries; u8 link_status[DP_LINK_STATUS_SIZE]; bool max_vswing_reached = false; - char phy_name[10]; int delay_us; delay_us = drm_dp_read_clock_recovery_delay(&intel_dp->aux, intel_dp->dpcd, dp_phy, intel_dp_is_uhbr(crtc_state)); - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); - /* clock recovery */ if (!intel_dp_reset_link_train(intel_dp, crtc_state, dp_phy, DP_TRAINING_PATTERN_1 | DP_LINK_SCRAMBLING_DISABLE)) { drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to enable link training\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return false; } @@ -795,14 +799,16 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, if (drm_dp_dpcd_read_phy_link_status(&intel_dp->aux, dp_phy, link_status) < 0) { drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to get link status\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return false; } if (drm_dp_clock_recovery_ok(link_status, crtc_state->lane_count)) { drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Clock recovery OK\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return true; } @@ -810,7 +816,8 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Same voltage tried 5 times\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return false; } @@ -818,7 +825,8 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Max Voltage Swing reached\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return false; } @@ -828,7 +836,8 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, if (!intel_dp_update_link_train(intel_dp, crtc_state, dp_phy)) { drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to update link training\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); return false; } @@ -846,7 +855,8 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp, intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed clock recovery %d times, giving up!\n", - encoder->base.base.id, encoder->base.name, phy_name, max_cr_tries); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy), max_cr_tries); return false; } @@ -924,15 +934,12 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, u32 training_pattern; u8 link_status[DP_LINK_STATUS_SIZE]; bool channel_eq = false; - char phy_name[10]; int delay_us; delay_us = drm_dp_read_channel_eq_delay(&intel_dp->aux, intel_dp->dpcd, dp_phy, intel_dp_is_uhbr(crtc_state)); - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)); - training_pattern = intel_dp_training_pattern(intel_dp, crtc_state, dp_phy); /* Scrambling is disabled for TPS2/3 and enabled for TPS4 */ if (training_pattern != DP_TRAINING_PATTERN_4) @@ -944,7 +951,7 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to start channel equalization\n", encoder->base.base.id, encoder->base.name, - phy_name); + drm_dp_phy_name(dp_phy)); return false; } @@ -955,7 +962,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, link_status) < 0) { drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to get link status\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); break; } @@ -966,7 +974,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Clock recovery check failed, cannot " "continue channel equalization\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); break; } @@ -975,7 +984,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, channel_eq = true; drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Channel EQ done. DP Training successful\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); break; } @@ -985,7 +995,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, if (!intel_dp_update_link_train(intel_dp, crtc_state, dp_phy)) { drm_err(&i915->drm, "[ENCODER:%d:%s][%s] Failed to update link training\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); break; } } @@ -995,7 +1006,8 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp, intel_dp_dump_link_status(intel_dp, dp_phy, link_status); drm_dbg_kms(&i915->drm, "[ENCODER:%d:%s][%s] Channel equalization failed 5 times\n", - encoder->base.base.id, encoder->base.name, phy_name); + encoder->base.base.id, encoder->base.name, + drm_dp_phy_name(dp_phy)); } return channel_eq; @@ -1070,7 +1082,6 @@ intel_dp_link_train_phy(struct intel_dp *intel_dp, { struct intel_connector *connector = intel_dp->attached_connector; struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; - char phy_name[10]; bool ret = false; if (!intel_dp_link_training_clock_recovery(intel_dp, crtc_state, dp_phy)) @@ -1086,7 +1097,7 @@ out: "[CONNECTOR:%d:%s][ENCODER:%d:%s][%s] Link Training %s at link rate = %d, lane count = %d\n", connector->base.base.id, connector->base.name, encoder->base.base.id, encoder->base.name, - intel_dp_phy_name(dp_phy, phy_name, sizeof(phy_name)), + drm_dp_phy_name(dp_phy), ret ? "passed" : "failed", crtc_state->port_clock, crtc_state->lane_count); diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 7713c19042f3..03604a37931c 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -58,7 +58,6 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *adjusted_mode = &crtc_state->hw.adjusted_mode; - bool constant_n = drm_dp_has_quirk(&intel_dp->desc, DP_DPCD_QUIRK_CONSTANT_N); int bpp, slots = -EINVAL; mst_state = drm_atomic_get_mst_topology_state(state, &intel_dp->mst_mgr); @@ -100,7 +99,7 @@ static int intel_dp_mst_compute_link_config(struct intel_encoder *encoder, adjusted_mode->crtc_clock, crtc_state->port_clock, &crtc_state->dp_m_n, - constant_n, crtc_state->fec_enable); + crtc_state->fec_enable); crtc_state->dp_m_n.tu = slots; return 0; @@ -566,7 +565,10 @@ static void intel_mst_enable_dp(struct intel_atomic_state *state, drm_dp_add_payload_part2(&intel_dp->mst_mgr, &state->base, drm_atomic_get_mst_payload_state(mst_state, connector->port)); - if (DISPLAY_VER(dev_priv) >= 12 && pipe_config->fec_enable) + if (DISPLAY_VER(dev_priv) >= 14 && pipe_config->fec_enable) + intel_de_rmw(dev_priv, MTL_CHICKEN_TRANS(trans), 0, + FECSTALL_DIS_DPTSTREAM_DPTTG); + else if (DISPLAY_VER(dev_priv) >= 12 && pipe_config->fec_enable) intel_de_rmw(dev_priv, CHICKEN_TRANS(trans), 0, FECSTALL_DIS_DPTSTREAM_DPTTG); diff --git a/drivers/gpu/drm/i915/display/intel_dpio_phy.c b/drivers/gpu/drm/i915/display/intel_dpio_phy.c index cc6abe761f5e..8732b8722ed7 100644 --- a/drivers/gpu/drm/i915/display/intel_dpio_phy.c +++ b/drivers/gpu/drm/i915/display/intel_dpio_phy.c @@ -484,7 +484,7 @@ void bxt_ddi_phy_init(struct drm_i915_private *dev_priv, enum dpio_phy phy) enum dpio_phy rcomp_phy = phy_info->rcomp_phy; bool was_enabled; - lockdep_assert_held(&dev_priv->power_domains.lock); + lockdep_assert_held(&dev_priv->display.power.domains.lock); was_enabled = true; if (rcomp_phy != -1) diff --git a/drivers/gpu/drm/i915/display/intel_dpll.c b/drivers/gpu/drm/i915/display/intel_dpll.c index 5262f16b45ac..b15ba78d64d6 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll.c +++ b/drivers/gpu/drm/i915/display/intel_dpll.c @@ -938,12 +938,25 @@ static int hsw_crtc_compute_clock(struct intel_atomic_state *state, intel_atomic_get_new_crtc_state(state, crtc); struct intel_encoder *encoder = intel_get_crtc_new_encoder(state, crtc_state); + int ret; if (DISPLAY_VER(dev_priv) < 11 && intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) return 0; - return intel_compute_shared_dplls(state, crtc, encoder); + ret = intel_compute_shared_dplls(state, crtc, encoder); + if (ret) + return ret; + + /* FIXME this is a mess */ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) + return 0; + + /* CRT dotclock is determined via other means */ + if (!crtc_state->has_pch_encoder) + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + + return 0; } static int hsw_crtc_get_shared_dpll(struct intel_atomic_state *state, @@ -969,8 +982,15 @@ static int dg2_crtc_compute_clock(struct intel_atomic_state *state, intel_atomic_get_new_crtc_state(state, crtc); struct intel_encoder *encoder = intel_get_crtc_new_encoder(state, crtc_state); + int ret; + + ret = intel_mpllb_calc_state(crtc_state, encoder); + if (ret) + return ret; + + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); - return intel_mpllb_calc_state(crtc_state, encoder); + return 0; } static bool ilk_needs_fb_cb_tune(const struct dpll *dpll, int factor) @@ -991,7 +1011,7 @@ static void ilk_update_pll_dividers(struct intel_crtc_state *crtc_state, factor = 21; if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) { if ((intel_panel_use_ssc(dev_priv) && - dev_priv->vbt.lvds_ssc_freq == 100000) || + dev_priv->display.vbt.lvds_ssc_freq == 100000) || (HAS_PCH_IBX(dev_priv) && intel_is_dual_link_lvds(dev_priv))) factor = 25; @@ -1096,6 +1116,7 @@ static int ilk_crtc_compute_clock(struct intel_atomic_state *state, intel_atomic_get_new_crtc_state(state, crtc); const struct intel_limit *limit; int refclk = 120000; + int ret; /* CPU eDP is the only output that doesn't need a PCH PLL of its own. */ if (!crtc_state->has_pch_encoder) @@ -1105,8 +1126,8 @@ static int ilk_crtc_compute_clock(struct intel_atomic_state *state, if (intel_panel_use_ssc(dev_priv)) { drm_dbg_kms(&dev_priv->drm, "using SSC reference clock of %d kHz\n", - dev_priv->vbt.lvds_ssc_freq); - refclk = dev_priv->vbt.lvds_ssc_freq; + dev_priv->display.vbt.lvds_ssc_freq); + refclk = dev_priv->display.vbt.lvds_ssc_freq; } if (intel_is_dual_link_lvds(dev_priv)) { @@ -1132,7 +1153,14 @@ static int ilk_crtc_compute_clock(struct intel_atomic_state *state, ilk_compute_dpll(crtc_state, &crtc_state->dpll, &crtc_state->dpll); - return intel_compute_shared_dplls(state, crtc, NULL); + ret = intel_compute_shared_dplls(state, crtc, NULL); + if (ret) + return ret; + + crtc_state->port_clock = crtc_state->dpll.dot; + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + + return ret; } static int ilk_crtc_get_shared_dpll(struct intel_atomic_state *state, @@ -1198,6 +1226,13 @@ static int chv_crtc_compute_clock(struct intel_atomic_state *state, chv_compute_dpll(crtc_state); + /* FIXME this is a mess */ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) + return 0; + + crtc_state->port_clock = crtc_state->dpll.dot; + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + return 0; } @@ -1217,6 +1252,13 @@ static int vlv_crtc_compute_clock(struct intel_atomic_state *state, vlv_compute_dpll(crtc_state); + /* FIXME this is a mess */ + if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) + return 0; + + crtc_state->port_clock = crtc_state->dpll.dot; + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + return 0; } @@ -1231,7 +1273,7 @@ static int g4x_crtc_compute_clock(struct intel_atomic_state *state, if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) { if (intel_panel_use_ssc(dev_priv)) { - refclk = dev_priv->vbt.lvds_ssc_freq; + refclk = dev_priv->display.vbt.lvds_ssc_freq; drm_dbg_kms(&dev_priv->drm, "using SSC reference clock of %d kHz\n", refclk); @@ -1259,6 +1301,11 @@ static int g4x_crtc_compute_clock(struct intel_atomic_state *state, i9xx_compute_dpll(crtc_state, &crtc_state->dpll, &crtc_state->dpll); + crtc_state->port_clock = crtc_state->dpll.dot; + /* FIXME this is a mess */ + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_TVOUT)) + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + return 0; } @@ -1273,7 +1320,7 @@ static int pnv_crtc_compute_clock(struct intel_atomic_state *state, if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) { if (intel_panel_use_ssc(dev_priv)) { - refclk = dev_priv->vbt.lvds_ssc_freq; + refclk = dev_priv->display.vbt.lvds_ssc_freq; drm_dbg_kms(&dev_priv->drm, "using SSC reference clock of %d kHz\n", refclk); @@ -1292,6 +1339,9 @@ static int pnv_crtc_compute_clock(struct intel_atomic_state *state, i9xx_compute_dpll(crtc_state, &crtc_state->dpll, &crtc_state->dpll); + crtc_state->port_clock = crtc_state->dpll.dot; + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + return 0; } @@ -1306,7 +1356,7 @@ static int i9xx_crtc_compute_clock(struct intel_atomic_state *state, if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) { if (intel_panel_use_ssc(dev_priv)) { - refclk = dev_priv->vbt.lvds_ssc_freq; + refclk = dev_priv->display.vbt.lvds_ssc_freq; drm_dbg_kms(&dev_priv->drm, "using SSC reference clock of %d kHz\n", refclk); @@ -1325,6 +1375,11 @@ static int i9xx_crtc_compute_clock(struct intel_atomic_state *state, i9xx_compute_dpll(crtc_state, &crtc_state->dpll, &crtc_state->dpll); + crtc_state->port_clock = crtc_state->dpll.dot; + /* FIXME this is a mess */ + if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_TVOUT)) + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + return 0; } @@ -1339,7 +1394,7 @@ static int i8xx_crtc_compute_clock(struct intel_atomic_state *state, if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_LVDS)) { if (intel_panel_use_ssc(dev_priv)) { - refclk = dev_priv->vbt.lvds_ssc_freq; + refclk = dev_priv->display.vbt.lvds_ssc_freq; drm_dbg_kms(&dev_priv->drm, "using SSC reference clock of %d kHz\n", refclk); @@ -1360,6 +1415,9 @@ static int i8xx_crtc_compute_clock(struct intel_atomic_state *state, i8xx_compute_dpll(crtc_state, &crtc_state->dpll, &crtc_state->dpll); + crtc_state->port_clock = crtc_state->dpll.dot; + crtc_state->hw.adjusted_mode.crtc_clock = intel_crtc_dotclock(crtc_state); + return 0; } @@ -1411,16 +1469,13 @@ int intel_dpll_crtc_compute_clock(struct intel_atomic_state *state, drm_WARN_ON(&i915->drm, !intel_crtc_needs_modeset(crtc_state)); - if (drm_WARN_ON(&i915->drm, crtc_state->shared_dpll)) - return 0; - memset(&crtc_state->dpll_hw_state, 0, sizeof(crtc_state->dpll_hw_state)); if (!crtc_state->hw.enable) return 0; - ret = i915->dpll_funcs->crtc_compute_clock(state, crtc); + ret = i915->display.funcs.dpll->crtc_compute_clock(state, crtc); if (ret) { drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] Couldn't calculate DPLL settings\n", crtc->base.base.id, crtc->base.name); @@ -1439,17 +1494,15 @@ int intel_dpll_crtc_get_shared_dpll(struct intel_atomic_state *state, int ret; drm_WARN_ON(&i915->drm, !intel_crtc_needs_modeset(crtc_state)); + drm_WARN_ON(&i915->drm, !crtc_state->hw.enable && crtc_state->shared_dpll); - if (drm_WARN_ON(&i915->drm, crtc_state->shared_dpll)) - return 0; - - if (!crtc_state->hw.enable) + if (!crtc_state->hw.enable || crtc_state->shared_dpll) return 0; - if (!i915->dpll_funcs->crtc_get_shared_dpll) + if (!i915->display.funcs.dpll->crtc_get_shared_dpll) return 0; - ret = i915->dpll_funcs->crtc_get_shared_dpll(state, crtc); + ret = i915->display.funcs.dpll->crtc_get_shared_dpll(state, crtc); if (ret) { drm_dbg_kms(&i915->drm, "[CRTC:%d:%s] Couldn't get a shared DPLL\n", crtc->base.base.id, crtc->base.name); @@ -1463,23 +1516,23 @@ void intel_dpll_init_clock_hook(struct drm_i915_private *dev_priv) { if (IS_DG2(dev_priv)) - dev_priv->dpll_funcs = &dg2_dpll_funcs; + dev_priv->display.funcs.dpll = &dg2_dpll_funcs; else if (DISPLAY_VER(dev_priv) >= 9 || HAS_DDI(dev_priv)) - dev_priv->dpll_funcs = &hsw_dpll_funcs; + dev_priv->display.funcs.dpll = &hsw_dpll_funcs; else if (HAS_PCH_SPLIT(dev_priv)) - dev_priv->dpll_funcs = &ilk_dpll_funcs; + dev_priv->display.funcs.dpll = &ilk_dpll_funcs; else if (IS_CHERRYVIEW(dev_priv)) - dev_priv->dpll_funcs = &chv_dpll_funcs; + dev_priv->display.funcs.dpll = &chv_dpll_funcs; else if (IS_VALLEYVIEW(dev_priv)) - dev_priv->dpll_funcs = &vlv_dpll_funcs; + dev_priv->display.funcs.dpll = &vlv_dpll_funcs; else if (IS_G4X(dev_priv)) - dev_priv->dpll_funcs = &g4x_dpll_funcs; + dev_priv->display.funcs.dpll = &g4x_dpll_funcs; else if (IS_PINEVIEW(dev_priv)) - dev_priv->dpll_funcs = &pnv_dpll_funcs; + dev_priv->display.funcs.dpll = &pnv_dpll_funcs; else if (DISPLAY_VER(dev_priv) != 2) - dev_priv->dpll_funcs = &i9xx_dpll_funcs; + dev_priv->display.funcs.dpll = &i9xx_dpll_funcs; else - dev_priv->dpll_funcs = &i8xx_dpll_funcs; + dev_priv->display.funcs.dpll = &i8xx_dpll_funcs; } static bool i9xx_has_pps(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 118598c9a809..e5fb66a5dd02 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -113,8 +113,8 @@ intel_atomic_duplicate_dpll_state(struct drm_i915_private *dev_priv, enum intel_dpll_id i; /* Copy shared dpll state */ - for (i = 0; i < dev_priv->dpll.num_shared_dpll; i++) { - struct intel_shared_dpll *pll = &dev_priv->dpll.shared_dplls[i]; + for (i = 0; i < dev_priv->display.dpll.num_shared_dpll; i++) { + struct intel_shared_dpll *pll = &dev_priv->display.dpll.shared_dplls[i]; shared_dpll[i] = pll->state; } @@ -149,7 +149,7 @@ struct intel_shared_dpll * intel_get_shared_dpll_by_id(struct drm_i915_private *dev_priv, enum intel_dpll_id id) { - return &dev_priv->dpll.shared_dplls[id]; + return &dev_priv->display.dpll.shared_dplls[id]; } /** @@ -164,11 +164,11 @@ enum intel_dpll_id intel_get_shared_dpll_id(struct drm_i915_private *dev_priv, struct intel_shared_dpll *pll) { - long pll_idx = pll - dev_priv->dpll.shared_dplls; + long pll_idx = pll - dev_priv->display.dpll.shared_dplls; if (drm_WARN_ON(&dev_priv->drm, pll_idx < 0 || - pll_idx >= dev_priv->dpll.num_shared_dpll)) + pll_idx >= dev_priv->display.dpll.num_shared_dpll)) return -1; return pll_idx; @@ -245,7 +245,7 @@ void intel_enable_shared_dpll(const struct intel_crtc_state *crtc_state) if (drm_WARN_ON(&dev_priv->drm, pll == NULL)) return; - mutex_lock(&dev_priv->dpll.lock); + mutex_lock(&dev_priv->display.dpll.lock); old_mask = pll->active_mask; if (drm_WARN_ON(&dev_priv->drm, !(pll->state.pipe_mask & pipe_mask)) || @@ -271,7 +271,7 @@ void intel_enable_shared_dpll(const struct intel_crtc_state *crtc_state) pll->on = true; out: - mutex_unlock(&dev_priv->dpll.lock); + mutex_unlock(&dev_priv->display.dpll.lock); } /** @@ -294,7 +294,7 @@ void intel_disable_shared_dpll(const struct intel_crtc_state *crtc_state) if (pll == NULL) return; - mutex_lock(&dev_priv->dpll.lock); + mutex_lock(&dev_priv->display.dpll.lock); if (drm_WARN(&dev_priv->drm, !(pll->active_mask & pipe_mask), "%s not used by [CRTC:%d:%s]\n", pll->info->name, crtc->base.base.id, crtc->base.name)) @@ -317,7 +317,7 @@ void intel_disable_shared_dpll(const struct intel_crtc_state *crtc_state) pll->on = false; out: - mutex_unlock(&dev_priv->dpll.lock); + mutex_unlock(&dev_priv->display.dpll.lock); } static struct intel_shared_dpll * @@ -336,7 +336,7 @@ intel_find_shared_dpll(struct intel_atomic_state *state, drm_WARN_ON(&dev_priv->drm, dpll_mask & ~(BIT(I915_NUM_PLLS) - 1)); for_each_set_bit(i, &dpll_mask, I915_NUM_PLLS) { - pll = &dev_priv->dpll.shared_dplls[i]; + pll = &dev_priv->display.dpll.shared_dplls[i]; /* Only want to check enabled timings first */ if (shared_dpll[i].pipe_mask == 0) { @@ -436,9 +436,9 @@ void intel_shared_dpll_swap_state(struct intel_atomic_state *state) if (!state->dpll_set) return; - for (i = 0; i < dev_priv->dpll.num_shared_dpll; i++) { + for (i = 0; i < dev_priv->display.dpll.num_shared_dpll; i++) { struct intel_shared_dpll *pll = - &dev_priv->dpll.shared_dplls[i]; + &dev_priv->display.dpll.shared_dplls[i]; swap(pll->state, shared_dpll[i]); } @@ -537,7 +537,7 @@ static int ibx_get_dpll(struct intel_atomic_state *state, if (HAS_PCH_IBX(dev_priv)) { /* Ironlake PCH has a fixed PLL->PCH pipe mapping. */ i = (enum intel_dpll_id) crtc->pipe; - pll = &dev_priv->dpll.shared_dplls[i]; + pll = &dev_priv->display.dpll.shared_dplls[i]; drm_dbg_kms(&dev_priv->drm, "[CRTC:%d:%s] using pre-allocated %s\n", @@ -905,37 +905,6 @@ hsw_ddi_calculate_wrpll(int clock /* in Hz */, *r2_out = best.r2; } -static int -hsw_ddi_wrpll_compute_dpll(struct intel_atomic_state *state, - struct intel_crtc *crtc) -{ - struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - unsigned int p, n2, r2; - - hsw_ddi_calculate_wrpll(crtc_state->port_clock * 1000, &r2, &n2, &p); - - crtc_state->dpll_hw_state.wrpll = - WRPLL_PLL_ENABLE | WRPLL_REF_LCPLL | - WRPLL_DIVIDER_REFERENCE(r2) | WRPLL_DIVIDER_FEEDBACK(n2) | - WRPLL_DIVIDER_POST(p); - - return 0; -} - -static struct intel_shared_dpll * -hsw_ddi_wrpll_get_dpll(struct intel_atomic_state *state, - struct intel_crtc *crtc) -{ - struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - - return intel_find_shared_dpll(state, crtc, - &crtc_state->dpll_hw_state, - BIT(DPLL_ID_WRPLL2) | - BIT(DPLL_ID_WRPLL1)); -} - static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv, const struct intel_shared_dpll *pll, const struct intel_dpll_hw_state *pll_state) @@ -948,7 +917,7 @@ static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv, case WRPLL_REF_SPECIAL_HSW: /* Muxed-SSC for BDW, non-SSC for non-ULT HSW. */ if (IS_HASWELL(dev_priv) && !IS_HSW_ULT(dev_priv)) { - refclk = dev_priv->dpll.ref_clks.nssc; + refclk = dev_priv->display.dpll.ref_clks.nssc; break; } fallthrough; @@ -958,7 +927,7 @@ static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv, * code only cares about 5% accuracy, and spread is a max of * 0.5% downspread. */ - refclk = dev_priv->dpll.ref_clks.ssc; + refclk = dev_priv->display.dpll.ref_clks.ssc; break; case WRPLL_REF_LCPLL: refclk = 2700000; @@ -977,6 +946,41 @@ static int hsw_ddi_wrpll_get_freq(struct drm_i915_private *dev_priv, } static int +hsw_ddi_wrpll_compute_dpll(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + unsigned int p, n2, r2; + + hsw_ddi_calculate_wrpll(crtc_state->port_clock * 1000, &r2, &n2, &p); + + crtc_state->dpll_hw_state.wrpll = + WRPLL_PLL_ENABLE | WRPLL_REF_LCPLL | + WRPLL_DIVIDER_REFERENCE(r2) | WRPLL_DIVIDER_FEEDBACK(n2) | + WRPLL_DIVIDER_POST(p); + + crtc_state->port_clock = hsw_ddi_wrpll_get_freq(i915, NULL, + &crtc_state->dpll_hw_state); + + return 0; +} + +static struct intel_shared_dpll * +hsw_ddi_wrpll_get_dpll(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + + return intel_find_shared_dpll(state, crtc, + &crtc_state->dpll_hw_state, + BIT(DPLL_ID_WRPLL2) | + BIT(DPLL_ID_WRPLL1)); +} + +static int hsw_ddi_lcpll_compute_dpll(struct intel_crtc_state *crtc_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); @@ -1145,12 +1149,12 @@ static int hsw_get_dpll(struct intel_atomic_state *state, static void hsw_update_dpll_ref_clks(struct drm_i915_private *i915) { - i915->dpll.ref_clks.ssc = 135000; + i915->display.dpll.ref_clks.ssc = 135000; /* Non-SSC is only used on non-ULT HSW. */ if (intel_de_read(i915, FUSE_STRAP3) & HSW_REF_CLK_SELECT) - i915->dpll.ref_clks.nssc = 24000; + i915->display.dpll.ref_clks.nssc = 24000; else - i915->dpll.ref_clks.nssc = 135000; + i915->display.dpll.ref_clks.nssc = 135000; } static void hsw_dump_hw_state(struct drm_i915_private *dev_priv, @@ -1618,48 +1622,11 @@ skip_remaining_dividers: return 0; } -static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state) -{ - struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); - struct skl_wrpll_params wrpll_params = {}; - u32 ctrl1, cfgcr1, cfgcr2; - int ret; - - /* - * See comment in intel_dpll_hw_state to understand why we always use 0 - * as the DPLL id in this function. - */ - ctrl1 = DPLL_CTRL1_OVERRIDE(0); - - ctrl1 |= DPLL_CTRL1_HDMI_MODE(0); - - ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000, - i915->dpll.ref_clks.nssc, &wrpll_params); - if (ret) - return ret; - - cfgcr1 = DPLL_CFGCR1_FREQ_ENABLE | - DPLL_CFGCR1_DCO_FRACTION(wrpll_params.dco_fraction) | - wrpll_params.dco_integer; - - cfgcr2 = DPLL_CFGCR2_QDIV_RATIO(wrpll_params.qdiv_ratio) | - DPLL_CFGCR2_QDIV_MODE(wrpll_params.qdiv_mode) | - DPLL_CFGCR2_KDIV(wrpll_params.kdiv) | - DPLL_CFGCR2_PDIV(wrpll_params.pdiv) | - wrpll_params.central_freq; - - crtc_state->dpll_hw_state.ctrl1 = ctrl1; - crtc_state->dpll_hw_state.cfgcr1 = cfgcr1; - crtc_state->dpll_hw_state.cfgcr2 = cfgcr2; - - return 0; -} - static int skl_ddi_wrpll_get_freq(struct drm_i915_private *i915, const struct intel_shared_dpll *pll, const struct intel_dpll_hw_state *pll_state) { - int ref_clock = i915->dpll.ref_clks.nssc; + int ref_clock = i915->display.dpll.ref_clks.nssc; u32 p0, p1, p2, dco_freq; p0 = pll_state->cfgcr2 & DPLL_CFGCR2_PDIV_MASK; @@ -1726,6 +1693,46 @@ static int skl_ddi_wrpll_get_freq(struct drm_i915_private *i915, return dco_freq / (p0 * p1 * p2 * 5); } +static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + struct skl_wrpll_params wrpll_params = {}; + u32 ctrl1, cfgcr1, cfgcr2; + int ret; + + /* + * See comment in intel_dpll_hw_state to understand why we always use 0 + * as the DPLL id in this function. + */ + ctrl1 = DPLL_CTRL1_OVERRIDE(0); + + ctrl1 |= DPLL_CTRL1_HDMI_MODE(0); + + ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000, + i915->display.dpll.ref_clks.nssc, &wrpll_params); + if (ret) + return ret; + + cfgcr1 = DPLL_CFGCR1_FREQ_ENABLE | + DPLL_CFGCR1_DCO_FRACTION(wrpll_params.dco_fraction) | + wrpll_params.dco_integer; + + cfgcr2 = DPLL_CFGCR2_QDIV_RATIO(wrpll_params.qdiv_ratio) | + DPLL_CFGCR2_QDIV_MODE(wrpll_params.qdiv_mode) | + DPLL_CFGCR2_KDIV(wrpll_params.kdiv) | + DPLL_CFGCR2_PDIV(wrpll_params.pdiv) | + wrpll_params.central_freq; + + crtc_state->dpll_hw_state.ctrl1 = ctrl1; + crtc_state->dpll_hw_state.cfgcr1 = cfgcr1; + crtc_state->dpll_hw_state.cfgcr2 = cfgcr2; + + crtc_state->port_clock = skl_ddi_wrpll_get_freq(i915, NULL, + &crtc_state->dpll_hw_state); + + return 0; +} + static int skl_ddi_dp_set_dpll_hw_state(struct intel_crtc_state *crtc_state) { @@ -1858,7 +1865,7 @@ static int skl_ddi_pll_get_freq(struct drm_i915_private *i915, static void skl_update_dpll_ref_clks(struct drm_i915_private *i915) { /* No SSC ref */ - i915->dpll.ref_clks.nssc = i915->cdclk.hw.ref; + i915->display.dpll.ref_clks.nssc = i915->display.cdclk.hw.ref; } static void skl_dump_hw_state(struct drm_i915_private *dev_priv, @@ -2171,7 +2178,7 @@ static void bxt_ddi_dp_pll_dividers(struct intel_crtc_state *crtc_state, } } - chv_calc_dpll_params(i915->dpll.ref_clks.nssc, clk_div); + chv_calc_dpll_params(i915->display.dpll.ref_clks.nssc, clk_div); drm_WARN_ON(&i915->drm, clk_div->vco == 0 || clk_div->dot != crtc_state->port_clock); @@ -2245,6 +2252,23 @@ static int bxt_ddi_set_dpll_hw_state(struct intel_crtc_state *crtc_state, return 0; } +static int bxt_ddi_pll_get_freq(struct drm_i915_private *i915, + const struct intel_shared_dpll *pll, + const struct intel_dpll_hw_state *pll_state) +{ + struct dpll clock; + + clock.m1 = 2; + clock.m2 = REG_FIELD_GET(PORT_PLL_M2_INT_MASK, pll_state->pll0) << 22; + if (pll_state->pll3 & PORT_PLL_M2_FRAC_ENABLE) + clock.m2 |= REG_FIELD_GET(PORT_PLL_M2_FRAC_MASK, pll_state->pll2); + clock.n = REG_FIELD_GET(PORT_PLL_N_MASK, pll_state->pll1); + clock.p1 = REG_FIELD_GET(PORT_PLL_P1_MASK, pll_state->ebb0); + clock.p2 = REG_FIELD_GET(PORT_PLL_P2_MASK, pll_state->ebb0); + + return chv_calc_dpll_params(i915->display.dpll.ref_clks.nssc, &clock); +} + static int bxt_ddi_dp_set_dpll_hw_state(struct intel_crtc_state *crtc_state) { @@ -2258,28 +2282,20 @@ bxt_ddi_dp_set_dpll_hw_state(struct intel_crtc_state *crtc_state) static int bxt_ddi_hdmi_set_dpll_hw_state(struct intel_crtc_state *crtc_state) { + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); struct dpll clk_div = {}; + int ret; bxt_ddi_hdmi_pll_dividers(crtc_state, &clk_div); - return bxt_ddi_set_dpll_hw_state(crtc_state, &clk_div); -} - -static int bxt_ddi_pll_get_freq(struct drm_i915_private *i915, - const struct intel_shared_dpll *pll, - const struct intel_dpll_hw_state *pll_state) -{ - struct dpll clock; + ret = bxt_ddi_set_dpll_hw_state(crtc_state, &clk_div); + if (ret) + return ret; - clock.m1 = 2; - clock.m2 = REG_FIELD_GET(PORT_PLL_M2_INT_MASK, pll_state->pll0) << 22; - if (pll_state->pll3 & PORT_PLL_M2_FRAC_ENABLE) - clock.m2 |= REG_FIELD_GET(PORT_PLL_M2_FRAC_MASK, pll_state->pll2); - clock.n = REG_FIELD_GET(PORT_PLL_N_MASK, pll_state->pll1); - clock.p1 = REG_FIELD_GET(PORT_PLL_P1_MASK, pll_state->ebb0); - clock.p2 = REG_FIELD_GET(PORT_PLL_P2_MASK, pll_state->ebb0); + crtc_state->port_clock = bxt_ddi_pll_get_freq(i915, NULL, + &crtc_state->dpll_hw_state); - return chv_calc_dpll_params(i915->dpll.ref_clks.nssc, &clock); + return 0; } static int bxt_compute_dpll(struct intel_atomic_state *state, @@ -2324,8 +2340,8 @@ static int bxt_get_dpll(struct intel_atomic_state *state, static void bxt_update_dpll_ref_clks(struct drm_i915_private *i915) { - i915->dpll.ref_clks.ssc = 100000; - i915->dpll.ref_clks.nssc = 100000; + i915->display.dpll.ref_clks.ssc = 100000; + i915->display.dpll.ref_clks.nssc = 100000; /* DSI non-SSC ref 19.2MHz */ } @@ -2468,7 +2484,7 @@ ehl_combo_pll_div_frac_wa_needed(struct drm_i915_private *i915) return ((IS_PLATFORM(i915, INTEL_ELKHARTLAKE) && IS_JSL_EHL_DISPLAY_STEP(i915, STEP_B0, STEP_FOREVER)) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_S(i915) || IS_ALDERLAKE_P(i915)) && - i915->dpll.ref_clks.nssc == 38400; + i915->display.dpll.ref_clks.nssc == 38400; } struct icl_combo_pll_params { @@ -2562,7 +2578,7 @@ static int icl_calc_dp_combo_pll(struct intel_crtc_state *crtc_state, { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); const struct icl_combo_pll_params *params = - dev_priv->dpll.ref_clks.nssc == 24000 ? + dev_priv->display.dpll.ref_clks.nssc == 24000 ? icl_dp_combo_pll_24MHz_values : icl_dp_combo_pll_19_2MHz_values; int clock = crtc_state->port_clock; @@ -2585,9 +2601,9 @@ static int icl_calc_tbt_pll(struct intel_crtc_state *crtc_state, struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); if (DISPLAY_VER(dev_priv) >= 12) { - switch (dev_priv->dpll.ref_clks.nssc) { + switch (dev_priv->display.dpll.ref_clks.nssc) { default: - MISSING_CASE(dev_priv->dpll.ref_clks.nssc); + MISSING_CASE(dev_priv->display.dpll.ref_clks.nssc); fallthrough; case 19200: case 38400: @@ -2598,9 +2614,9 @@ static int icl_calc_tbt_pll(struct intel_crtc_state *crtc_state, break; } } else { - switch (dev_priv->dpll.ref_clks.nssc) { + switch (dev_priv->display.dpll.ref_clks.nssc) { default: - MISSING_CASE(dev_priv->dpll.ref_clks.nssc); + MISSING_CASE(dev_priv->display.dpll.ref_clks.nssc); fallthrough; case 19200: case 38400: @@ -2630,7 +2646,7 @@ static int icl_ddi_tbt_pll_get_freq(struct drm_i915_private *i915, static int icl_wrpll_ref_clock(struct drm_i915_private *i915) { - int ref_clock = i915->dpll.ref_clks.nssc; + int ref_clock = i915->display.dpll.ref_clks.nssc; /* * For ICL+, the spec states: if reference frequency is 38.4, @@ -2769,8 +2785,8 @@ static void icl_calc_dpll_state(struct drm_i915_private *i915, else pll_state->cfgcr1 |= DPLL_CFGCR1_CENTRAL_FREQ_8400; - if (i915->vbt.override_afc_startup) - pll_state->div0 = TGL_DPLL0_DIV0_AFC_STARTUP(i915->vbt.override_afc_startup_val); + if (i915->display.vbt.override_afc_startup) + pll_state->div0 = TGL_DPLL0_DIV0_AFC_STARTUP(i915->display.vbt.override_afc_startup_val); } static int icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc, @@ -2857,7 +2873,7 @@ static int icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state, struct intel_dpll_hw_state *pll_state) { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - int refclk_khz = dev_priv->dpll.ref_clks.nssc; + int refclk_khz = dev_priv->display.dpll.ref_clks.nssc; int clock = crtc_state->port_clock; u32 dco_khz, m1div, m2div_int, m2div_rem, m2div_frac; u32 iref_ndiv, iref_trim, iref_pulse_w; @@ -2965,8 +2981,8 @@ static int icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state, DKL_PLL_DIV0_PROP_COEFF(prop_coeff) | DKL_PLL_DIV0_FBPREDIV(m1div) | DKL_PLL_DIV0_FBDIV_INT(m2div_int); - if (dev_priv->vbt.override_afc_startup) { - u8 val = dev_priv->vbt.override_afc_startup_val; + if (dev_priv->display.vbt.override_afc_startup) { + u8 val = dev_priv->display.vbt.override_afc_startup_val; pll_state->mg_pll_div0 |= DKL_PLL_DIV0_AFC_STARTUP(val); } @@ -3063,7 +3079,7 @@ static int icl_ddi_mg_pll_get_freq(struct drm_i915_private *dev_priv, u32 m1, m2_int, m2_frac, div1, div2, ref_clock; u64 tmp; - ref_clock = dev_priv->dpll.ref_clks.nssc; + ref_clock = dev_priv->display.dpll.ref_clks.nssc; if (DISPLAY_VER(dev_priv) >= 12) { m1 = pll_state->mg_pll_div0 & DKL_PLL_DIV0_FBPREDIV_MASK; @@ -3197,6 +3213,12 @@ static int icl_compute_combo_phy_dpll(struct intel_atomic_state *state, icl_calc_dpll_state(dev_priv, &pll_params, &port_dpll->hw_state); + /* this is mainly for the fastset check */ + icl_set_active_port_dpll(crtc_state, ICL_PORT_DPLL_DEFAULT); + + crtc_state->port_clock = icl_ddi_combo_pll_get_freq(dev_priv, NULL, + &port_dpll->hw_state); + return 0; } @@ -3282,6 +3304,12 @@ static int icl_compute_tc_phy_dplls(struct intel_atomic_state *state, if (ret) return ret; + /* this is mainly for the fastset check */ + icl_set_active_port_dpll(crtc_state, ICL_PORT_DPLL_MG_PHY); + + crtc_state->port_clock = icl_ddi_mg_pll_get_freq(dev_priv, NULL, + &port_dpll->hw_state); + return 0; } @@ -3440,7 +3468,7 @@ static bool mg_pll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->mg_pll_tdc_coldst_bias = intel_de_read(dev_priv, MG_PLL_TDC_COLDST_BIAS(tc_port)); - if (dev_priv->dpll.ref_clks.nssc == 38400) { + if (dev_priv->display.dpll.ref_clks.nssc == 38400) { hw_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART; hw_state->mg_pll_bias_mask = 0; } else { @@ -3502,7 +3530,7 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->mg_pll_div0 = intel_de_read(dev_priv, DKL_PLL_DIV0(tc_port)); val = DKL_PLL_DIV0_MASK; - if (dev_priv->vbt.override_afc_startup) + if (dev_priv->display.vbt.override_afc_startup) val |= DKL_PLL_DIV0_AFC_STARTUP_MASK; hw_state->mg_pll_div0 &= val; @@ -3566,7 +3594,7 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv, TGL_DPLL_CFGCR0(id)); hw_state->cfgcr1 = intel_de_read(dev_priv, TGL_DPLL_CFGCR1(id)); - if (dev_priv->vbt.override_afc_startup) { + if (dev_priv->display.vbt.override_afc_startup) { hw_state->div0 = intel_de_read(dev_priv, TGL_DPLL0_DIV0(id)); hw_state->div0 &= TGL_DPLL0_DIV0_AFC_STARTUP_MASK; } @@ -3638,9 +3666,9 @@ static void icl_dpll_write(struct drm_i915_private *dev_priv, intel_de_write(dev_priv, cfgcr0_reg, hw_state->cfgcr0); intel_de_write(dev_priv, cfgcr1_reg, hw_state->cfgcr1); - drm_WARN_ON_ONCE(&dev_priv->drm, dev_priv->vbt.override_afc_startup && + drm_WARN_ON_ONCE(&dev_priv->drm, dev_priv->display.vbt.override_afc_startup && !i915_mmio_reg_valid(div0_reg)); - if (dev_priv->vbt.override_afc_startup && + if (dev_priv->display.vbt.override_afc_startup && i915_mmio_reg_valid(div0_reg)) intel_de_rmw(dev_priv, div0_reg, TGL_DPLL0_DIV0_AFC_STARTUP_MASK, hw_state->div0); @@ -3732,7 +3760,7 @@ static void dkl_pll_write(struct drm_i915_private *dev_priv, intel_de_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val); val = DKL_PLL_DIV0_MASK; - if (dev_priv->vbt.override_afc_startup) + if (dev_priv->display.vbt.override_afc_startup) val |= DKL_PLL_DIV0_AFC_STARTUP_MASK; intel_de_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val, hw_state->mg_pll_div0); @@ -3967,7 +3995,7 @@ static void mg_pll_disable(struct drm_i915_private *dev_priv, static void icl_update_dpll_ref_clks(struct drm_i915_private *i915) { /* No SSC ref */ - i915->dpll.ref_clks.nssc = i915->cdclk.hw.ref; + i915->display.dpll.ref_clks.nssc = i915->display.cdclk.hw.ref; } static void icl_dump_hw_state(struct drm_i915_private *dev_priv, @@ -4192,22 +4220,24 @@ void intel_shared_dpll_init(struct drm_i915_private *dev_priv) dpll_mgr = &pch_pll_mgr; if (!dpll_mgr) { - dev_priv->dpll.num_shared_dpll = 0; + dev_priv->display.dpll.num_shared_dpll = 0; return; } dpll_info = dpll_mgr->dpll_info; for (i = 0; dpll_info[i].name; i++) { + if (drm_WARN_ON(&dev_priv->drm, + i >= ARRAY_SIZE(dev_priv->display.dpll.shared_dplls))) + break; + drm_WARN_ON(&dev_priv->drm, i != dpll_info[i].id); - dev_priv->dpll.shared_dplls[i].info = &dpll_info[i]; + dev_priv->display.dpll.shared_dplls[i].info = &dpll_info[i]; } - dev_priv->dpll.mgr = dpll_mgr; - dev_priv->dpll.num_shared_dpll = i; - mutex_init(&dev_priv->dpll.lock); - - BUG_ON(dev_priv->dpll.num_shared_dpll > I915_NUM_PLLS); + dev_priv->display.dpll.mgr = dpll_mgr; + dev_priv->display.dpll.num_shared_dpll = i; + mutex_init(&dev_priv->display.dpll.lock); } /** @@ -4229,7 +4259,7 @@ int intel_compute_shared_dplls(struct intel_atomic_state *state, struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_dpll_mgr *dpll_mgr = dev_priv->dpll.mgr; + const struct intel_dpll_mgr *dpll_mgr = dev_priv->display.dpll.mgr; if (drm_WARN_ON(&dev_priv->drm, !dpll_mgr)) return -EINVAL; @@ -4262,7 +4292,7 @@ int intel_reserve_shared_dplls(struct intel_atomic_state *state, struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_dpll_mgr *dpll_mgr = dev_priv->dpll.mgr; + const struct intel_dpll_mgr *dpll_mgr = dev_priv->display.dpll.mgr; if (drm_WARN_ON(&dev_priv->drm, !dpll_mgr)) return -EINVAL; @@ -4285,7 +4315,7 @@ void intel_release_shared_dplls(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_dpll_mgr *dpll_mgr = dev_priv->dpll.mgr; + const struct intel_dpll_mgr *dpll_mgr = dev_priv->display.dpll.mgr; /* * FIXME: this function is called for every platform having a @@ -4314,7 +4344,7 @@ void intel_update_active_dpll(struct intel_atomic_state *state, struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - const struct intel_dpll_mgr *dpll_mgr = dev_priv->dpll.mgr; + const struct intel_dpll_mgr *dpll_mgr = dev_priv->display.dpll.mgr; if (drm_WARN_ON(&dev_priv->drm, !dpll_mgr)) return; @@ -4385,16 +4415,16 @@ static void readout_dpll_hw_state(struct drm_i915_private *i915, void intel_dpll_update_ref_clks(struct drm_i915_private *i915) { - if (i915->dpll.mgr && i915->dpll.mgr->update_ref_clks) - i915->dpll.mgr->update_ref_clks(i915); + if (i915->display.dpll.mgr && i915->display.dpll.mgr->update_ref_clks) + i915->display.dpll.mgr->update_ref_clks(i915); } void intel_dpll_readout_hw_state(struct drm_i915_private *i915) { int i; - for (i = 0; i < i915->dpll.num_shared_dpll; i++) - readout_dpll_hw_state(i915, &i915->dpll.shared_dplls[i]); + for (i = 0; i < i915->display.dpll.num_shared_dpll; i++) + readout_dpll_hw_state(i915, &i915->display.dpll.shared_dplls[i]); } static void sanitize_dpll_state(struct drm_i915_private *i915, @@ -4420,8 +4450,8 @@ void intel_dpll_sanitize_state(struct drm_i915_private *i915) { int i; - for (i = 0; i < i915->dpll.num_shared_dpll; i++) - sanitize_dpll_state(i915, &i915->dpll.shared_dplls[i]); + for (i = 0; i < i915->display.dpll.num_shared_dpll; i++) + sanitize_dpll_state(i915, &i915->display.dpll.shared_dplls[i]); } /** @@ -4434,8 +4464,8 @@ void intel_dpll_sanitize_state(struct drm_i915_private *i915) void intel_dpll_dump_hw_state(struct drm_i915_private *dev_priv, const struct intel_dpll_hw_state *hw_state) { - if (dev_priv->dpll.mgr) { - dev_priv->dpll.mgr->dump_hw_state(dev_priv, hw_state); + if (dev_priv->display.dpll.mgr) { + dev_priv->display.dpll.mgr->dump_hw_state(dev_priv, hw_state); } else { /* fallback for platforms that don't use the shared dpll * infrastructure @@ -4533,7 +4563,7 @@ void intel_shared_dpll_verify_disabled(struct drm_i915_private *i915) { int i; - for (i = 0; i < i915->dpll.num_shared_dpll; i++) - verify_single_dpll_state(i915, &i915->dpll.shared_dplls[i], + for (i = 0; i < i915->display.dpll.num_shared_dpll; i++) + verify_single_dpll_state(i915, &i915->display.dpll.shared_dplls[i], NULL, NULL); } diff --git a/drivers/gpu/drm/i915/display/intel_dsb.c b/drivers/gpu/drm/i915/display/intel_dsb.c index c4affcb216fd..fc9c3e41c333 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.c +++ b/drivers/gpu/drm/i915/display/intel_dsb.c @@ -9,6 +9,36 @@ #include "i915_drv.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dsb.h" + +struct i915_vma; + +enum dsb_id { + INVALID_DSB = -1, + DSB1, + DSB2, + DSB3, + MAX_DSB_PER_PIPE +}; + +struct intel_dsb { + enum dsb_id id; + u32 *cmd_buf; + struct i915_vma *vma; + + /* + * free_pos will point the first free entry position + * and help in calculating tail of command buffer. + */ + int free_pos; + + /* + * ins_start_offset will help to store start address of the dsb + * instuction and help in identifying the batch of auto-increment + * register. + */ + u32 ins_start_offset; +}; #define DSB_BUF_SIZE (2 * PAGE_SIZE) diff --git a/drivers/gpu/drm/i915/display/intel_dsb.h b/drivers/gpu/drm/i915/display/intel_dsb.h index 6cb9c580cdca..74dd2b3343bb 100644 --- a/drivers/gpu/drm/i915/display/intel_dsb.h +++ b/drivers/gpu/drm/i915/display/intel_dsb.h @@ -11,34 +11,6 @@ #include "i915_reg_defs.h" struct intel_crtc_state; -struct i915_vma; - -enum dsb_id { - INVALID_DSB = -1, - DSB1, - DSB2, - DSB3, - MAX_DSB_PER_PIPE -}; - -struct intel_dsb { - enum dsb_id id; - u32 *cmd_buf; - struct i915_vma *vma; - - /* - * free_pos will point the first free entry position - * and help in calculating tail of command buffer. - */ - int free_pos; - - /* - * ins_start_offset will help to store start address of the dsb - * instuction and help in identifying the batch of auto-increment - * register. - */ - u32 ins_start_offset; -}; void intel_dsb_prepare(struct intel_crtc_state *crtc_state); void intel_dsb_cleanup(struct intel_crtc_state *crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dsi.c b/drivers/gpu/drm/i915/display/intel_dsi.c index 35e121cd226c..5efdd471ac2b 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.c +++ b/drivers/gpu/drm/i915/display/intel_dsi.c @@ -106,7 +106,7 @@ intel_dsi_get_panel_orientation(struct intel_connector *connector) if (orientation != DRM_MODE_PANEL_ORIENTATION_UNKNOWN) return orientation; - orientation = dev_priv->vbt.orientation; + orientation = dev_priv->display.vbt.orientation; if (orientation != DRM_MODE_PANEL_ORIENTATION_UNKNOWN) return orientation; diff --git a/drivers/gpu/drm/i915/display/intel_dsi.h b/drivers/gpu/drm/i915/display/intel_dsi.h index eafef0a87fea..ce80bd8be519 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi.h +++ b/drivers/gpu/drm/i915/display/intel_dsi.h @@ -89,9 +89,6 @@ struct intel_dsi { u8 escape_clk_div; u8 dual_link; - u16 dcs_backlight_ports; - u16 dcs_cabc_ports; - /* RGB or BGR */ bool bgr_enabled; diff --git a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c index 1bc7118c56a2..20e466d843ce 100644 --- a/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dsi_dcs_backlight.c @@ -53,7 +53,7 @@ static u32 dcs_get_backlight(struct intel_connector *connector, enum pipe unused enum port port; size_t len = panel->backlight.max > U8_MAX ? 2 : 1; - for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) { + for_each_dsi_port(port, panel->vbt.dsi.bl_ports) { dsi_device = intel_dsi->dsi_hosts[port]->device; mipi_dsi_dcs_read(dsi_device, MIPI_DCS_GET_DISPLAY_BRIGHTNESS, &data, len); @@ -80,7 +80,7 @@ static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32 data[1] = level; } - for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) { + for_each_dsi_port(port, panel->vbt.dsi.bl_ports) { dsi_device = intel_dsi->dsi_hosts[port]->device; mode_flags = dsi_device->mode_flags; dsi_device->mode_flags &= ~MIPI_DSI_MODE_LPM; @@ -93,12 +93,13 @@ static void dcs_set_backlight(const struct drm_connector_state *conn_state, u32 static void dcs_disable_backlight(const struct drm_connector_state *conn_state, u32 level) { struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder)); + struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel; struct mipi_dsi_device *dsi_device; enum port port; dcs_set_backlight(conn_state, 0); - for_each_dsi_port(port, intel_dsi->dcs_cabc_ports) { + for_each_dsi_port(port, panel->vbt.dsi.cabc_ports) { u8 cabc = POWER_SAVE_OFF; dsi_device = intel_dsi->dsi_hosts[port]->device; @@ -106,7 +107,7 @@ static void dcs_disable_backlight(const struct drm_connector_state *conn_state, &cabc, sizeof(cabc)); } - for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) { + for_each_dsi_port(port, panel->vbt.dsi.bl_ports) { u8 ctrl = 0; dsi_device = intel_dsi->dsi_hosts[port]->device; @@ -127,10 +128,11 @@ static void dcs_enable_backlight(const struct intel_crtc_state *crtc_state, const struct drm_connector_state *conn_state, u32 level) { struct intel_dsi *intel_dsi = enc_to_intel_dsi(to_intel_encoder(conn_state->best_encoder)); + struct intel_panel *panel = &to_intel_connector(conn_state->connector)->panel; struct mipi_dsi_device *dsi_device; enum port port; - for_each_dsi_port(port, intel_dsi->dcs_backlight_ports) { + for_each_dsi_port(port, panel->vbt.dsi.bl_ports) { u8 ctrl = 0; dsi_device = intel_dsi->dsi_hosts[port]->device; @@ -146,7 +148,7 @@ static void dcs_enable_backlight(const struct intel_crtc_state *crtc_state, &ctrl, sizeof(ctrl)); } - for_each_dsi_port(port, intel_dsi->dcs_cabc_ports) { + for_each_dsi_port(port, panel->vbt.dsi.cabc_ports) { u8 cabc = POWER_SAVE_MEDIUM; dsi_device = intel_dsi->dsi_hosts[port]->device; diff --git a/drivers/gpu/drm/i915/display/intel_dvo_dev.h b/drivers/gpu/drm/i915/display/intel_dvo_dev.h index d96c3cc46e50..50205f064d93 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo_dev.h +++ b/drivers/gpu/drm/i915/display/intel_dvo_dev.h @@ -75,8 +75,8 @@ struct intel_dvo_dev_ops { * * \return MODE_OK if the mode is valid, or another MODE_* otherwise. */ - int (*mode_valid)(struct intel_dvo_device *dvo, - struct drm_display_mode *mode); + enum drm_mode_status (*mode_valid)(struct intel_dvo_device *dvo, + struct drm_display_mode *mode); /* * Callback for preparing mode changes on an output diff --git a/drivers/gpu/drm/i915/display/intel_fb_pin.c b/drivers/gpu/drm/i915/display/intel_fb_pin.c index c86e5d4ee016..1dddd6abd77b 100644 --- a/drivers/gpu/drm/i915/display/intel_fb_pin.c +++ b/drivers/gpu/drm/i915/display/intel_fb_pin.c @@ -26,10 +26,17 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, struct drm_device *dev = fb->dev; struct drm_i915_private *dev_priv = to_i915(dev); struct drm_i915_gem_object *obj = intel_fb_obj(fb); + struct i915_gem_ww_ctx ww; struct i915_vma *vma; u32 alignment; int ret; + /* + * We are not syncing against the binding (and potential migrations) + * below, so this vm must never be async. + */ + GEM_WARN_ON(vm->bind_async_flags); + if (WARN_ON(!i915_gem_object_is_framebuffer(obj))) return ERR_PTR(-EINVAL); @@ -37,29 +44,48 @@ intel_pin_fb_obj_dpt(struct drm_framebuffer *fb, atomic_inc(&dev_priv->gpu_error.pending_fb_pin); - ret = i915_gem_object_lock_interruptible(obj, NULL); - if (!ret) { + for_i915_gem_ww(&ww, ret, true) { + ret = i915_gem_object_lock(obj, &ww); + if (ret) + continue; + + if (HAS_LMEM(dev_priv)) { + unsigned int flags = obj->flags; + + /* + * For this type of buffer we need to able to read from the CPU + * the clear color value found in the buffer, hence we need to + * ensure it is always in the mappable part of lmem, if this is + * a small-bar device. + */ + if (intel_fb_rc_ccs_cc_plane(fb) >= 0) + flags &= ~I915_BO_ALLOC_GPU_ONLY; + ret = __i915_gem_object_migrate(obj, &ww, INTEL_REGION_LMEM_0, + flags); + if (ret) + continue; + } + ret = i915_gem_object_set_cache_level(obj, I915_CACHE_NONE); - i915_gem_object_unlock(obj); - } - if (ret) { - vma = ERR_PTR(ret); - goto err; - } + if (ret) + continue; - vma = i915_vma_instance(obj, vm, view); - if (IS_ERR(vma)) - goto err; + vma = i915_vma_instance(obj, vm, view); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + continue; + } - if (i915_vma_misplaced(vma, 0, alignment, 0)) { - ret = i915_vma_unbind_unlocked(vma); - if (ret) { - vma = ERR_PTR(ret); - goto err; + if (i915_vma_misplaced(vma, 0, alignment, 0)) { + ret = i915_vma_unbind(vma); + if (ret) + continue; } - } - ret = i915_vma_pin(vma, 0, alignment, PIN_GLOBAL); + ret = i915_vma_pin_ww(vma, &ww, 0, alignment, PIN_GLOBAL); + if (ret) + continue; + } if (ret) { vma = ERR_PTR(ret); goto err; diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c index 16537830ccf0..f38175304928 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.c +++ b/drivers/gpu/drm/i915/display/intel_fbc.c @@ -55,11 +55,11 @@ #define for_each_fbc_id(__dev_priv, __fbc_id) \ for ((__fbc_id) = INTEL_FBC_A; (__fbc_id) < I915_MAX_FBCS; (__fbc_id)++) \ - for_each_if(INTEL_INFO(__dev_priv)->display.fbc_mask & BIT(__fbc_id)) + for_each_if(RUNTIME_INFO(__dev_priv)->fbc_mask & BIT(__fbc_id)) #define for_each_intel_fbc(__dev_priv, __fbc, __fbc_id) \ for_each_fbc_id((__dev_priv), (__fbc_id)) \ - for_each_if((__fbc) = (__dev_priv)->fbc[(__fbc_id)]) + for_each_if((__fbc) = (__dev_priv)->display.fbc[(__fbc_id)]) struct intel_fbc_funcs { void (*activate)(struct intel_fbc *fbc); @@ -1098,6 +1098,12 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state, return 0; } + /* Wa_14016291713 */ + if (IS_DISPLAY_VER(i915, 12, 13) && crtc_state->has_psr) { + plane_state->no_fbc_reason = "PSR1 enabled (Wa_14016291713)"; + return 0; + } + if (!pixel_format_is_valid(plane_state)) { plane_state->no_fbc_reason = "pixel format not supported"; return 0; @@ -1704,17 +1710,17 @@ void intel_fbc_init(struct drm_i915_private *i915) enum intel_fbc_id fbc_id; if (!drm_mm_initialized(&i915->mm.stolen)) - mkwrite_device_info(i915)->display.fbc_mask = 0; + RUNTIME_INFO(i915)->fbc_mask = 0; if (need_fbc_vtd_wa(i915)) - mkwrite_device_info(i915)->display.fbc_mask = 0; + RUNTIME_INFO(i915)->fbc_mask = 0; i915->params.enable_fbc = intel_sanitize_fbc_option(i915); drm_dbg_kms(&i915->drm, "Sanitized enable_fbc value: %d\n", i915->params.enable_fbc); for_each_fbc_id(i915, fbc_id) - i915->fbc[fbc_id] = intel_fbc_create(i915, fbc_id); + i915->display.fbc[fbc_id] = intel_fbc_create(i915, fbc_id); } /** @@ -1834,7 +1840,7 @@ void intel_fbc_debugfs_register(struct drm_i915_private *i915) struct drm_minor *minor = i915->drm.primary; struct intel_fbc *fbc; - fbc = i915->fbc[INTEL_FBC_A]; + fbc = i915->display.fbc[INTEL_FBC_A]; if (fbc) intel_fbc_debugfs_add(fbc, minor->debugfs_root); } diff --git a/drivers/gpu/drm/i915/display/intel_fbc.h b/drivers/gpu/drm/i915/display/intel_fbc.h index db60143295ec..4adb98afe6ff 100644 --- a/drivers/gpu/drm/i915/display/intel_fbc.h +++ b/drivers/gpu/drm/i915/display/intel_fbc.h @@ -19,6 +19,7 @@ struct intel_plane_state; enum intel_fbc_id { INTEL_FBC_A, + INTEL_FBC_B, I915_MAX_FBCS, }; diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c index 1922f62d04c0..112aa0447a0d 100644 --- a/drivers/gpu/drm/i915/display/intel_fbdev.c +++ b/drivers/gpu/drm/i915/display/intel_fbdev.c @@ -210,6 +210,12 @@ static int intelfb_create(struct drm_fb_helper *helper, struct drm_i915_gem_object *obj; int ret; + mutex_lock(&ifbdev->hpd_lock); + ret = ifbdev->hpd_suspended ? -EAGAIN : 0; + mutex_unlock(&ifbdev->hpd_lock); + if (ret) + return ret; + if (intel_fb && (sizes->fb_width > intel_fb->base.width || sizes->fb_height > intel_fb->base.height)) { @@ -500,7 +506,7 @@ static void intel_fbdev_suspend_worker(struct work_struct *work) { intel_fbdev_set_suspend(&container_of(work, struct drm_i915_private, - fbdev_suspend_work)->drm, + display.fbdev.suspend_work)->drm, FBINFO_STATE_RUNNING, true); } @@ -530,8 +536,8 @@ int intel_fbdev_init(struct drm_device *dev) return ret; } - dev_priv->fbdev = ifbdev; - INIT_WORK(&dev_priv->fbdev_suspend_work, intel_fbdev_suspend_worker); + dev_priv->display.fbdev.fbdev = ifbdev; + INIT_WORK(&dev_priv->display.fbdev.suspend_work, intel_fbdev_suspend_worker); return 0; } @@ -548,7 +554,7 @@ static void intel_fbdev_initial_config(void *data, async_cookie_t cookie) void intel_fbdev_initial_config_async(struct drm_device *dev) { - struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + struct intel_fbdev *ifbdev = to_i915(dev)->display.fbdev.fbdev; if (!ifbdev) return; @@ -568,12 +574,13 @@ static void intel_fbdev_sync(struct intel_fbdev *ifbdev) void intel_fbdev_unregister(struct drm_i915_private *dev_priv) { - struct intel_fbdev *ifbdev = dev_priv->fbdev; + struct intel_fbdev *ifbdev = dev_priv->display.fbdev.fbdev; if (!ifbdev) return; - cancel_work_sync(&dev_priv->fbdev_suspend_work); + intel_fbdev_set_suspend(&dev_priv->drm, FBINFO_STATE_SUSPENDED, true); + if (!current_is_async()) intel_fbdev_sync(ifbdev); @@ -582,7 +589,7 @@ void intel_fbdev_unregister(struct drm_i915_private *dev_priv) void intel_fbdev_fini(struct drm_i915_private *dev_priv) { - struct intel_fbdev *ifbdev = fetch_and_zero(&dev_priv->fbdev); + struct intel_fbdev *ifbdev = fetch_and_zero(&dev_priv->display.fbdev.fbdev); if (!ifbdev) return; @@ -596,7 +603,7 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv) */ static void intel_fbdev_hpd_set_suspend(struct drm_i915_private *i915, int state) { - struct intel_fbdev *ifbdev = i915->fbdev; + struct intel_fbdev *ifbdev = i915->display.fbdev.fbdev; bool send_hpd = false; mutex_lock(&ifbdev->hpd_lock); @@ -614,11 +621,11 @@ static void intel_fbdev_hpd_set_suspend(struct drm_i915_private *i915, int state void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous) { struct drm_i915_private *dev_priv = to_i915(dev); - struct intel_fbdev *ifbdev = dev_priv->fbdev; + struct intel_fbdev *ifbdev = dev_priv->display.fbdev.fbdev; struct fb_info *info; if (!ifbdev || !ifbdev->vma) - return; + goto set_suspend; info = ifbdev->helper.fbdev; @@ -631,7 +638,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous * ourselves, so only flush outstanding work upon suspend! */ if (state != FBINFO_STATE_RUNNING) - flush_work(&dev_priv->fbdev_suspend_work); + flush_work(&dev_priv->display.fbdev.suspend_work); console_lock(); } else { @@ -645,7 +652,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous /* Don't block our own workqueue as this can * be run in parallel with other i915.ko tasks. */ - schedule_work(&dev_priv->fbdev_suspend_work); + schedule_work(&dev_priv->display.fbdev.suspend_work); return; } } @@ -661,12 +668,13 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous drm_fb_helper_set_suspend(&ifbdev->helper, state); console_unlock(); +set_suspend: intel_fbdev_hpd_set_suspend(dev_priv, state); } void intel_fbdev_output_poll_changed(struct drm_device *dev) { - struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + struct intel_fbdev *ifbdev = to_i915(dev)->display.fbdev.fbdev; bool send_hpd; if (!ifbdev) @@ -685,7 +693,7 @@ void intel_fbdev_output_poll_changed(struct drm_device *dev) void intel_fbdev_restore_mode(struct drm_device *dev) { - struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + struct intel_fbdev *ifbdev = to_i915(dev)->display.fbdev.fbdev; if (!ifbdev) return; diff --git a/drivers/gpu/drm/i915/display/intel_fdi.c b/drivers/gpu/drm/i915/display/intel_fdi.c index 67d2484afbaa..7f47e5c85c81 100644 --- a/drivers/gpu/drm/i915/display/intel_fdi.c +++ b/drivers/gpu/drm/i915/display/intel_fdi.c @@ -113,7 +113,7 @@ void intel_fdi_link_train(struct intel_crtc *crtc, { struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - dev_priv->fdi_funcs->fdi_link_train(crtc, crtc_state); + dev_priv->display.funcs.fdi->fdi_link_train(crtc, crtc_state); } /* units of 100MHz */ @@ -210,14 +210,14 @@ void intel_fdi_pll_freq_update(struct drm_i915_private *i915) u32 fdi_pll_clk = intel_de_read(i915, FDI_PLL_BIOS_0) & FDI_PLL_FB_CLOCK_MASK; - i915->fdi_pll_freq = (fdi_pll_clk + 2) * 10000; + i915->display.fdi.pll_freq = (fdi_pll_clk + 2) * 10000; } else if (IS_SANDYBRIDGE(i915) || IS_IVYBRIDGE(i915)) { - i915->fdi_pll_freq = 270000; + i915->display.fdi.pll_freq = 270000; } else { return; } - drm_dbg(&i915->drm, "FDI PLL freq=%d\n", i915->fdi_pll_freq); + drm_dbg(&i915->drm, "FDI PLL freq=%d\n", i915->display.fdi.pll_freq); } int intel_fdi_link_freq(struct drm_i915_private *i915, @@ -226,7 +226,7 @@ int intel_fdi_link_freq(struct drm_i915_private *i915, if (HAS_DDI(i915)) return pipe_config->port_clock; /* SPLL */ else - return i915->fdi_pll_freq; + return i915->display.fdi.pll_freq; } int ilk_fdi_compute_config(struct intel_crtc *crtc, @@ -256,7 +256,7 @@ retry: pipe_config->fdi_lanes = lane; intel_link_compute_m_n(pipe_config->pipe_bpp, lane, fdi_dotclock, - link_bw, &pipe_config->fdi_m_n, false, false); + link_bw, &pipe_config->fdi_m_n, false); ret = ilk_check_fdi_lanes(dev, crtc->pipe, pipe_config); if (ret == -EDEADLK) @@ -789,7 +789,7 @@ void hsw_fdi_link_train(struct intel_encoder *encoder, FDI_RX_PWRDN_LANE1_VAL(2) | FDI_RX_PWRDN_LANE0_VAL(2) | FDI_RX_TP1_TO_TP2_48 | FDI_RX_FDI_DELAY_90); /* Enable the PCH Receiver FDI PLL */ - rx_ctl_val = dev_priv->fdi_rx_config | FDI_RX_ENHANCE_FRAME_ENABLE | + rx_ctl_val = dev_priv->display.fdi.rx_config | FDI_RX_ENHANCE_FRAME_ENABLE | FDI_RX_PLL_ENABLE | FDI_DP_PORT_WIDTH(crtc_state->fdi_lanes); intel_de_write(dev_priv, FDI_RX_CTL(PIPE_A), rx_ctl_val); @@ -1066,11 +1066,11 @@ void intel_fdi_init_hook(struct drm_i915_private *dev_priv) { if (IS_IRONLAKE(dev_priv)) { - dev_priv->fdi_funcs = &ilk_funcs; + dev_priv->display.funcs.fdi = &ilk_funcs; } else if (IS_SANDYBRIDGE(dev_priv)) { - dev_priv->fdi_funcs = &gen6_funcs; + dev_priv->display.funcs.fdi = &gen6_funcs; } else if (IS_IVYBRIDGE(dev_priv)) { /* FIXME: detect B0+ stepping and use auto training */ - dev_priv->fdi_funcs = &ivb_funcs; + dev_priv->display.funcs.fdi = &ivb_funcs; } } diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.c b/drivers/gpu/drm/i915/display/intel_frontbuffer.c index 791248f812aa..d80e3e8a9b01 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.c +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.c @@ -81,9 +81,9 @@ static void frontbuffer_flush(struct drm_i915_private *i915, enum fb_op_origin origin) { /* Delay flushing when rings are still busy.*/ - spin_lock(&i915->fb_tracking.lock); - frontbuffer_bits &= ~i915->fb_tracking.busy_bits; - spin_unlock(&i915->fb_tracking.lock); + spin_lock(&i915->display.fb_tracking.lock); + frontbuffer_bits &= ~i915->display.fb_tracking.busy_bits; + spin_unlock(&i915->display.fb_tracking.lock); if (!frontbuffer_bits) return; @@ -111,11 +111,11 @@ static void frontbuffer_flush(struct drm_i915_private *i915, void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915, unsigned frontbuffer_bits) { - spin_lock(&i915->fb_tracking.lock); - i915->fb_tracking.flip_bits |= frontbuffer_bits; + spin_lock(&i915->display.fb_tracking.lock); + i915->display.fb_tracking.flip_bits |= frontbuffer_bits; /* Remove stale busy bits due to the old buffer. */ - i915->fb_tracking.busy_bits &= ~frontbuffer_bits; - spin_unlock(&i915->fb_tracking.lock); + i915->display.fb_tracking.busy_bits &= ~frontbuffer_bits; + spin_unlock(&i915->display.fb_tracking.lock); } /** @@ -131,11 +131,11 @@ void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915, void intel_frontbuffer_flip_complete(struct drm_i915_private *i915, unsigned frontbuffer_bits) { - spin_lock(&i915->fb_tracking.lock); + spin_lock(&i915->display.fb_tracking.lock); /* Mask any cancelled flips. */ - frontbuffer_bits &= i915->fb_tracking.flip_bits; - i915->fb_tracking.flip_bits &= ~frontbuffer_bits; - spin_unlock(&i915->fb_tracking.lock); + frontbuffer_bits &= i915->display.fb_tracking.flip_bits; + i915->display.fb_tracking.flip_bits &= ~frontbuffer_bits; + spin_unlock(&i915->display.fb_tracking.lock); if (frontbuffer_bits) frontbuffer_flush(i915, frontbuffer_bits, ORIGIN_FLIP); @@ -155,10 +155,10 @@ void intel_frontbuffer_flip_complete(struct drm_i915_private *i915, void intel_frontbuffer_flip(struct drm_i915_private *i915, unsigned frontbuffer_bits) { - spin_lock(&i915->fb_tracking.lock); + spin_lock(&i915->display.fb_tracking.lock); /* Remove stale busy bits due to the old buffer. */ - i915->fb_tracking.busy_bits &= ~frontbuffer_bits; - spin_unlock(&i915->fb_tracking.lock); + i915->display.fb_tracking.busy_bits &= ~frontbuffer_bits; + spin_unlock(&i915->display.fb_tracking.lock); frontbuffer_flush(i915, frontbuffer_bits, ORIGIN_FLIP); } @@ -170,10 +170,10 @@ void __intel_fb_invalidate(struct intel_frontbuffer *front, struct drm_i915_private *i915 = to_i915(front->obj->base.dev); if (origin == ORIGIN_CS) { - spin_lock(&i915->fb_tracking.lock); - i915->fb_tracking.busy_bits |= frontbuffer_bits; - i915->fb_tracking.flip_bits &= ~frontbuffer_bits; - spin_unlock(&i915->fb_tracking.lock); + spin_lock(&i915->display.fb_tracking.lock); + i915->display.fb_tracking.busy_bits |= frontbuffer_bits; + i915->display.fb_tracking.flip_bits &= ~frontbuffer_bits; + spin_unlock(&i915->display.fb_tracking.lock); } trace_intel_frontbuffer_invalidate(frontbuffer_bits, origin); @@ -191,11 +191,11 @@ void __intel_fb_flush(struct intel_frontbuffer *front, struct drm_i915_private *i915 = to_i915(front->obj->base.dev); if (origin == ORIGIN_CS) { - spin_lock(&i915->fb_tracking.lock); + spin_lock(&i915->display.fb_tracking.lock); /* Filter out new bits since rendering started. */ - frontbuffer_bits &= i915->fb_tracking.busy_bits; - i915->fb_tracking.busy_bits &= ~frontbuffer_bits; - spin_unlock(&i915->fb_tracking.lock); + frontbuffer_bits &= i915->display.fb_tracking.busy_bits; + i915->display.fb_tracking.busy_bits &= ~frontbuffer_bits; + spin_unlock(&i915->display.fb_tracking.lock); } if (frontbuffer_bits) @@ -221,7 +221,7 @@ static void frontbuffer_retire(struct i915_active *ref) } static void frontbuffer_release(struct kref *ref) - __releases(&to_i915(front->obj->base.dev)->fb_tracking.lock) + __releases(&to_i915(front->obj->base.dev)->display.fb_tracking.lock) { struct intel_frontbuffer *front = container_of(ref, typeof(*front), ref); @@ -238,7 +238,7 @@ static void frontbuffer_release(struct kref *ref) spin_unlock(&obj->vma.lock); RCU_INIT_POINTER(obj->frontbuffer, NULL); - spin_unlock(&to_i915(obj->base.dev)->fb_tracking.lock); + spin_unlock(&to_i915(obj->base.dev)->display.fb_tracking.lock); i915_active_fini(&front->write); @@ -268,7 +268,7 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj) frontbuffer_retire, I915_ACTIVE_RETIRE_SLEEPS); - spin_lock(&i915->fb_tracking.lock); + spin_lock(&i915->display.fb_tracking.lock); if (rcu_access_pointer(obj->frontbuffer)) { kfree(front); front = rcu_dereference_protected(obj->frontbuffer, true); @@ -277,7 +277,7 @@ intel_frontbuffer_get(struct drm_i915_gem_object *obj) i915_gem_object_get(obj); rcu_assign_pointer(obj->frontbuffer, front); } - spin_unlock(&i915->fb_tracking.lock); + spin_unlock(&i915->display.fb_tracking.lock); return front; } @@ -286,7 +286,7 @@ void intel_frontbuffer_put(struct intel_frontbuffer *front) { kref_put_lock(&front->ref, frontbuffer_release, - &to_i915(front->obj->base.dev)->fb_tracking.lock); + &to_i915(front->obj->base.dev)->display.fb_tracking.lock); } /** @@ -311,6 +311,8 @@ void intel_frontbuffer_track(struct intel_frontbuffer *old, */ BUILD_BUG_ON(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES > BITS_PER_TYPE(atomic_t)); + BUILD_BUG_ON(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES > 32); + BUILD_BUG_ON(I915_MAX_PLANES > INTEL_FRONTBUFFER_BITS_PER_PIPE); if (old) { drm_WARN_ON(old->obj->base.dev, diff --git a/drivers/gpu/drm/i915/display/intel_frontbuffer.h b/drivers/gpu/drm/i915/display/intel_frontbuffer.h index ff0c37b079aa..3c474ed937fb 100644 --- a/drivers/gpu/drm/i915/display/intel_frontbuffer.h +++ b/drivers/gpu/drm/i915/display/intel_frontbuffer.h @@ -25,6 +25,7 @@ #define __INTEL_FRONTBUFFER_H__ #include <linux/atomic.h> +#include <linux/bits.h> #include <linux/kref.h> #include "gem/i915_gem_object_types.h" @@ -48,6 +49,23 @@ struct intel_frontbuffer { struct rcu_head rcu; }; +/* + * Frontbuffer tracking bits. Set in obj->frontbuffer_bits while a gem bo is + * considered to be the frontbuffer for the given plane interface-wise. This + * doesn't mean that the hw necessarily already scans it out, but that any + * rendering (by the cpu or gpu) will land in the frontbuffer eventually. + * + * We have one bit per pipe and per scanout plane type. + */ +#define INTEL_FRONTBUFFER_BITS_PER_PIPE 8 +#define INTEL_FRONTBUFFER(pipe, plane_id) \ + BIT((plane_id) + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)); +#define INTEL_FRONTBUFFER_OVERLAY(pipe) \ + BIT(INTEL_FRONTBUFFER_BITS_PER_PIPE - 1 + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)) +#define INTEL_FRONTBUFFER_ALL_MASK(pipe) \ + GENMASK(INTEL_FRONTBUFFER_BITS_PER_PIPE * ((pipe) + 1) - 1, \ + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)) + void intel_frontbuffer_flip_prepare(struct drm_i915_private *i915, unsigned frontbuffer_bits); void intel_frontbuffer_flip_complete(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.c b/drivers/gpu/drm/i915/display/intel_gmbus.c index a6ba7fb72339..74443f57f62d 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.c +++ b/drivers/gpu/drm/i915/display/intel_gmbus.c @@ -37,6 +37,7 @@ #include "intel_de.h" #include "intel_display_types.h" #include "intel_gmbus.h" +#include "intel_gmbus_regs.h" struct intel_gmbus { struct i2c_adapter adapter; @@ -45,7 +46,7 @@ struct intel_gmbus { u32 reg0; i915_reg_t gpio_reg; struct i2c_algo_bit_data bit_algo; - struct drm_i915_private *dev_priv; + struct drm_i915_private *i915; }; struct gmbus_pin { @@ -116,6 +117,18 @@ static const struct gmbus_pin gmbus_pins_dg2[] = { [GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOJ }, }; +static const struct gmbus_pin gmbus_pins_mtp[] = { + [GMBUS_PIN_1_BXT] = { "dpa", GPIOB }, + [GMBUS_PIN_2_BXT] = { "dpb", GPIOC }, + [GMBUS_PIN_3_BXT] = { "dpc", GPIOD }, + [GMBUS_PIN_4_CNP] = { "dpd", GPIOE }, + [GMBUS_PIN_5_MTP] = { "dpe", GPIOF }, + [GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOJ }, + [GMBUS_PIN_10_TC2_ICP] = { "tc2", GPIOK }, + [GMBUS_PIN_11_TC3_ICP] = { "tc3", GPIOL }, + [GMBUS_PIN_12_TC4_ICP] = { "tc4", GPIOM }, +}; + static const struct gmbus_pin *get_gmbus_pin(struct drm_i915_private *i915, unsigned int pin) { @@ -128,6 +141,9 @@ static const struct gmbus_pin *get_gmbus_pin(struct drm_i915_private *i915, } else if (INTEL_PCH_TYPE(i915) >= PCH_DG1) { pins = gmbus_pins_dg1; size = ARRAY_SIZE(gmbus_pins_dg1); + } else if (INTEL_PCH_TYPE(i915) >= PCH_MTP) { + pins = gmbus_pins_mtp; + size = ARRAY_SIZE(gmbus_pins_mtp); } else if (INTEL_PCH_TYPE(i915) >= PCH_ICP) { pins = gmbus_pins_icp; size = ARRAY_SIZE(gmbus_pins_icp); @@ -170,55 +186,55 @@ to_intel_gmbus(struct i2c_adapter *i2c) } void -intel_gmbus_reset(struct drm_i915_private *dev_priv) +intel_gmbus_reset(struct drm_i915_private *i915) { - intel_de_write(dev_priv, GMBUS0, 0); - intel_de_write(dev_priv, GMBUS4, 0); + intel_de_write(i915, GMBUS0(i915), 0); + intel_de_write(i915, GMBUS4(i915), 0); } -static void pnv_gmbus_clock_gating(struct drm_i915_private *dev_priv, +static void pnv_gmbus_clock_gating(struct drm_i915_private *i915, bool enable) { u32 val; /* When using bit bashing for I2C, this bit needs to be set to 1 */ - val = intel_de_read(dev_priv, DSPCLK_GATE_D); + val = intel_de_read(i915, DSPCLK_GATE_D(i915)); if (!enable) val |= PNV_GMBUSUNIT_CLOCK_GATE_DISABLE; else val &= ~PNV_GMBUSUNIT_CLOCK_GATE_DISABLE; - intel_de_write(dev_priv, DSPCLK_GATE_D, val); + intel_de_write(i915, DSPCLK_GATE_D(i915), val); } -static void pch_gmbus_clock_gating(struct drm_i915_private *dev_priv, +static void pch_gmbus_clock_gating(struct drm_i915_private *i915, bool enable) { u32 val; - val = intel_de_read(dev_priv, SOUTH_DSPCLK_GATE_D); + val = intel_de_read(i915, SOUTH_DSPCLK_GATE_D); if (!enable) val |= PCH_GMBUSUNIT_CLOCK_GATE_DISABLE; else val &= ~PCH_GMBUSUNIT_CLOCK_GATE_DISABLE; - intel_de_write(dev_priv, SOUTH_DSPCLK_GATE_D, val); + intel_de_write(i915, SOUTH_DSPCLK_GATE_D, val); } -static void bxt_gmbus_clock_gating(struct drm_i915_private *dev_priv, +static void bxt_gmbus_clock_gating(struct drm_i915_private *i915, bool enable) { u32 val; - val = intel_de_read(dev_priv, GEN9_CLKGATE_DIS_4); + val = intel_de_read(i915, GEN9_CLKGATE_DIS_4); if (!enable) val |= BXT_GMBUS_GATING_DIS; else val &= ~BXT_GMBUS_GATING_DIS; - intel_de_write(dev_priv, GEN9_CLKGATE_DIS_4, val); + intel_de_write(i915, GEN9_CLKGATE_DIS_4, val); } static u32 get_reserved(struct intel_gmbus *bus) { - struct drm_i915_private *i915 = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; struct intel_uncore *uncore = &i915->uncore; u32 reserved = 0; @@ -234,7 +250,7 @@ static u32 get_reserved(struct intel_gmbus *bus) static int get_clock(void *data) { struct intel_gmbus *bus = data; - struct intel_uncore *uncore = &bus->dev_priv->uncore; + struct intel_uncore *uncore = &bus->i915->uncore; u32 reserved = get_reserved(bus); intel_uncore_write_notrace(uncore, @@ -249,7 +265,7 @@ static int get_clock(void *data) static int get_data(void *data) { struct intel_gmbus *bus = data; - struct intel_uncore *uncore = &bus->dev_priv->uncore; + struct intel_uncore *uncore = &bus->i915->uncore; u32 reserved = get_reserved(bus); intel_uncore_write_notrace(uncore, @@ -264,7 +280,7 @@ static int get_data(void *data) static void set_clock(void *data, int state_high) { struct intel_gmbus *bus = data; - struct intel_uncore *uncore = &bus->dev_priv->uncore; + struct intel_uncore *uncore = &bus->i915->uncore; u32 reserved = get_reserved(bus); u32 clock_bits; @@ -283,7 +299,7 @@ static void set_clock(void *data, int state_high) static void set_data(void *data, int state_high) { struct intel_gmbus *bus = data; - struct intel_uncore *uncore = &bus->dev_priv->uncore; + struct intel_uncore *uncore = &bus->i915->uncore; u32 reserved = get_reserved(bus); u32 data_bits; @@ -301,12 +317,12 @@ static int intel_gpio_pre_xfer(struct i2c_adapter *adapter) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; - intel_gmbus_reset(dev_priv); + intel_gmbus_reset(i915); - if (IS_PINEVIEW(dev_priv)) - pnv_gmbus_clock_gating(dev_priv, false); + if (IS_PINEVIEW(i915)) + pnv_gmbus_clock_gating(i915, false); set_data(bus, 1); set_clock(bus, 1); @@ -318,13 +334,13 @@ static void intel_gpio_post_xfer(struct i2c_adapter *adapter) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; set_data(bus, 1); set_clock(bus, 1); - if (IS_PINEVIEW(dev_priv)) - pnv_gmbus_clock_gating(dev_priv, true); + if (IS_PINEVIEW(i915)) + pnv_gmbus_clock_gating(i915, true); } static void @@ -356,7 +372,7 @@ static bool has_gmbus_irq(struct drm_i915_private *i915) return HAS_GMBUS_IRQ(i915) && intel_irqs_enabled(i915); } -static int gmbus_wait(struct drm_i915_private *dev_priv, u32 status, u32 irq_en) +static int gmbus_wait(struct drm_i915_private *i915, u32 status, u32 irq_en) { DEFINE_WAIT(wait); u32 gmbus2; @@ -366,21 +382,21 @@ static int gmbus_wait(struct drm_i915_private *dev_priv, u32 status, u32 irq_en) * we also need to check for NAKs besides the hw ready/idle signal, we * need to wake up periodically and check that ourselves. */ - if (!has_gmbus_irq(dev_priv)) + if (!has_gmbus_irq(i915)) irq_en = 0; - add_wait_queue(&dev_priv->gmbus_wait_queue, &wait); - intel_de_write_fw(dev_priv, GMBUS4, irq_en); + add_wait_queue(&i915->display.gmbus.wait_queue, &wait); + intel_de_write_fw(i915, GMBUS4(i915), irq_en); status |= GMBUS_SATOER; - ret = wait_for_us((gmbus2 = intel_de_read_fw(dev_priv, GMBUS2)) & status, + ret = wait_for_us((gmbus2 = intel_de_read_fw(i915, GMBUS2(i915))) & status, 2); if (ret) - ret = wait_for((gmbus2 = intel_de_read_fw(dev_priv, GMBUS2)) & status, + ret = wait_for((gmbus2 = intel_de_read_fw(i915, GMBUS2(i915))) & status, 50); - intel_de_write_fw(dev_priv, GMBUS4, 0); - remove_wait_queue(&dev_priv->gmbus_wait_queue, &wait); + intel_de_write_fw(i915, GMBUS4(i915), 0); + remove_wait_queue(&i915->display.gmbus.wait_queue, &wait); if (gmbus2 & GMBUS_SATOER) return -ENXIO; @@ -389,7 +405,7 @@ static int gmbus_wait(struct drm_i915_private *dev_priv, u32 status, u32 irq_en) } static int -gmbus_wait_idle(struct drm_i915_private *dev_priv) +gmbus_wait_idle(struct drm_i915_private *i915) { DEFINE_WAIT(wait); u32 irq_enable; @@ -397,35 +413,35 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv) /* Important: The hw handles only the first bit, so set only one! */ irq_enable = 0; - if (has_gmbus_irq(dev_priv)) + if (has_gmbus_irq(i915)) irq_enable = GMBUS_IDLE_EN; - add_wait_queue(&dev_priv->gmbus_wait_queue, &wait); - intel_de_write_fw(dev_priv, GMBUS4, irq_enable); + add_wait_queue(&i915->display.gmbus.wait_queue, &wait); + intel_de_write_fw(i915, GMBUS4(i915), irq_enable); - ret = intel_wait_for_register_fw(&dev_priv->uncore, - GMBUS2, GMBUS_ACTIVE, 0, + ret = intel_wait_for_register_fw(&i915->uncore, + GMBUS2(i915), GMBUS_ACTIVE, 0, 10); - intel_de_write_fw(dev_priv, GMBUS4, 0); - remove_wait_queue(&dev_priv->gmbus_wait_queue, &wait); + intel_de_write_fw(i915, GMBUS4(i915), 0); + remove_wait_queue(&i915->display.gmbus.wait_queue, &wait); return ret; } -static unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv) +static unsigned int gmbus_max_xfer_size(struct drm_i915_private *i915) { - return DISPLAY_VER(dev_priv) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX : + return DISPLAY_VER(i915) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX : GMBUS_BYTE_COUNT_MAX; } static int -gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, +gmbus_xfer_read_chunk(struct drm_i915_private *i915, unsigned short addr, u8 *buf, unsigned int len, u32 gmbus0_reg, u32 gmbus1_index) { unsigned int size = len; - bool burst_read = len > gmbus_max_xfer_size(dev_priv); + bool burst_read = len > gmbus_max_xfer_size(i915); bool extra_byte_added = false; if (burst_read) { @@ -438,21 +454,21 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, len++; } size = len % 256 + 256; - intel_de_write_fw(dev_priv, GMBUS0, + intel_de_write_fw(i915, GMBUS0(i915), gmbus0_reg | GMBUS_BYTE_CNT_OVERRIDE); } - intel_de_write_fw(dev_priv, GMBUS1, + intel_de_write_fw(i915, GMBUS1(i915), gmbus1_index | GMBUS_CYCLE_WAIT | (size << GMBUS_BYTE_COUNT_SHIFT) | (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_READ | GMBUS_SW_RDY); while (len) { int ret; u32 val, loop = 0; - ret = gmbus_wait(dev_priv, GMBUS_HW_RDY, GMBUS_HW_RDY_EN); + ret = gmbus_wait(i915, GMBUS_HW_RDY, GMBUS_HW_RDY_EN); if (ret) return ret; - val = intel_de_read_fw(dev_priv, GMBUS3); + val = intel_de_read_fw(i915, GMBUS3(i915)); do { if (extra_byte_added && len == 1) break; @@ -463,7 +479,7 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, if (burst_read && len == size - 4) /* Reset the override bit */ - intel_de_write_fw(dev_priv, GMBUS0, gmbus0_reg); + intel_de_write_fw(i915, GMBUS0(i915), gmbus0_reg); } return 0; @@ -480,7 +496,7 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv, #define INTEL_GMBUS_BURST_READ_MAX_LEN 767U static int -gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, +gmbus_xfer_read(struct drm_i915_private *i915, struct i2c_msg *msg, u32 gmbus0_reg, u32 gmbus1_index) { u8 *buf = msg->buf; @@ -489,12 +505,12 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, int ret; do { - if (HAS_GMBUS_BURST_READ(dev_priv)) + if (HAS_GMBUS_BURST_READ(i915)) len = min(rx_size, INTEL_GMBUS_BURST_READ_MAX_LEN); else - len = min(rx_size, gmbus_max_xfer_size(dev_priv)); + len = min(rx_size, gmbus_max_xfer_size(i915)); - ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, buf, len, + ret = gmbus_xfer_read_chunk(i915, msg->addr, buf, len, gmbus0_reg, gmbus1_index); if (ret) return ret; @@ -507,7 +523,7 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg, } static int -gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, +gmbus_xfer_write_chunk(struct drm_i915_private *i915, unsigned short addr, u8 *buf, unsigned int len, u32 gmbus1_index) { @@ -520,8 +536,8 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, len -= 1; } - intel_de_write_fw(dev_priv, GMBUS3, val); - intel_de_write_fw(dev_priv, GMBUS1, + intel_de_write_fw(i915, GMBUS3(i915), val); + intel_de_write_fw(i915, GMBUS1(i915), gmbus1_index | GMBUS_CYCLE_WAIT | (chunk_size << GMBUS_BYTE_COUNT_SHIFT) | (addr << GMBUS_SLAVE_ADDR_SHIFT) | GMBUS_SLAVE_WRITE | GMBUS_SW_RDY); while (len) { int ret; @@ -531,9 +547,9 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, val |= *buf++ << (8 * loop); } while (--len && ++loop < 4); - intel_de_write_fw(dev_priv, GMBUS3, val); + intel_de_write_fw(i915, GMBUS3(i915), val); - ret = gmbus_wait(dev_priv, GMBUS_HW_RDY, GMBUS_HW_RDY_EN); + ret = gmbus_wait(i915, GMBUS_HW_RDY, GMBUS_HW_RDY_EN); if (ret) return ret; } @@ -542,7 +558,7 @@ gmbus_xfer_write_chunk(struct drm_i915_private *dev_priv, } static int -gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg, +gmbus_xfer_write(struct drm_i915_private *i915, struct i2c_msg *msg, u32 gmbus1_index) { u8 *buf = msg->buf; @@ -551,9 +567,9 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg, int ret; do { - len = min(tx_size, gmbus_max_xfer_size(dev_priv)); + len = min(tx_size, gmbus_max_xfer_size(i915)); - ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len, + ret = gmbus_xfer_write_chunk(i915, msg->addr, buf, len, gmbus1_index); if (ret) return ret; @@ -580,7 +596,7 @@ gmbus_is_index_xfer(struct i2c_msg *msgs, int i, int num) } static int -gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs, +gmbus_index_xfer(struct drm_i915_private *i915, struct i2c_msg *msgs, u32 gmbus0_reg) { u32 gmbus1_index = 0; @@ -596,17 +612,17 @@ gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs, /* GMBUS5 holds 16-bit index */ if (gmbus5) - intel_de_write_fw(dev_priv, GMBUS5, gmbus5); + intel_de_write_fw(i915, GMBUS5(i915), gmbus5); if (msgs[1].flags & I2C_M_RD) - ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus0_reg, + ret = gmbus_xfer_read(i915, &msgs[1], gmbus0_reg, gmbus1_index); else - ret = gmbus_xfer_write(dev_priv, &msgs[1], gmbus1_index); + ret = gmbus_xfer_write(i915, &msgs[1], gmbus1_index); /* Clear GMBUS5 after each index transfer */ if (gmbus5) - intel_de_write_fw(dev_priv, GMBUS5, 0); + intel_de_write_fw(i915, GMBUS5(i915), 0); return ret; } @@ -616,34 +632,34 @@ do_gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num, u32 gmbus0_source) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; int i = 0, inc, try = 0; int ret = 0; /* Display WA #0868: skl,bxt,kbl,cfl,glk */ - if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - bxt_gmbus_clock_gating(dev_priv, false); - else if (HAS_PCH_SPT(dev_priv) || HAS_PCH_CNP(dev_priv)) - pch_gmbus_clock_gating(dev_priv, false); + if (IS_GEMINILAKE(i915) || IS_BROXTON(i915)) + bxt_gmbus_clock_gating(i915, false); + else if (HAS_PCH_SPT(i915) || HAS_PCH_CNP(i915)) + pch_gmbus_clock_gating(i915, false); retry: - intel_de_write_fw(dev_priv, GMBUS0, gmbus0_source | bus->reg0); + intel_de_write_fw(i915, GMBUS0(i915), gmbus0_source | bus->reg0); for (; i < num; i += inc) { inc = 1; if (gmbus_is_index_xfer(msgs, i, num)) { - ret = gmbus_index_xfer(dev_priv, &msgs[i], + ret = gmbus_index_xfer(i915, &msgs[i], gmbus0_source | bus->reg0); inc = 2; /* an index transmission is two msgs */ } else if (msgs[i].flags & I2C_M_RD) { - ret = gmbus_xfer_read(dev_priv, &msgs[i], + ret = gmbus_xfer_read(i915, &msgs[i], gmbus0_source | bus->reg0, 0); } else { - ret = gmbus_xfer_write(dev_priv, &msgs[i], 0); + ret = gmbus_xfer_write(i915, &msgs[i], 0); } if (!ret) - ret = gmbus_wait(dev_priv, + ret = gmbus_wait(i915, GMBUS_HW_WAIT_PHASE, GMBUS_HW_WAIT_EN); if (ret == -ETIMEDOUT) goto timeout; @@ -655,19 +671,19 @@ retry: * a STOP on the very first cycle. To simplify the code we * unconditionally generate the STOP condition with an additional gmbus * cycle. */ - intel_de_write_fw(dev_priv, GMBUS1, GMBUS_CYCLE_STOP | GMBUS_SW_RDY); + intel_de_write_fw(i915, GMBUS1(i915), GMBUS_CYCLE_STOP | GMBUS_SW_RDY); /* Mark the GMBUS interface as disabled after waiting for idle. * We will re-enable it at the start of the next xfer, * till then let it sleep. */ - if (gmbus_wait_idle(dev_priv)) { - drm_dbg_kms(&dev_priv->drm, + if (gmbus_wait_idle(i915)) { + drm_dbg_kms(&i915->drm, "GMBUS [%s] timed out waiting for idle\n", adapter->name); ret = -ETIMEDOUT; } - intel_de_write_fw(dev_priv, GMBUS0, 0); + intel_de_write_fw(i915, GMBUS0(i915), 0); ret = ret ?: i; goto out; @@ -686,8 +702,8 @@ clear_err: * it's slow responding and only answers on the 2nd retry. */ ret = -ENXIO; - if (gmbus_wait_idle(dev_priv)) { - drm_dbg_kms(&dev_priv->drm, + if (gmbus_wait_idle(i915)) { + drm_dbg_kms(&i915->drm, "GMBUS [%s] timed out after NAK\n", adapter->name); ret = -ETIMEDOUT; @@ -697,11 +713,11 @@ clear_err: * of resetting the GMBUS controller and so clearing the * BUS_ERROR raised by the slave's NAK. */ - intel_de_write_fw(dev_priv, GMBUS1, GMBUS_SW_CLR_INT); - intel_de_write_fw(dev_priv, GMBUS1, 0); - intel_de_write_fw(dev_priv, GMBUS0, 0); + intel_de_write_fw(i915, GMBUS1(i915), GMBUS_SW_CLR_INT); + intel_de_write_fw(i915, GMBUS1(i915), 0); + intel_de_write_fw(i915, GMBUS0(i915), 0); - drm_dbg_kms(&dev_priv->drm, "GMBUS [%s] NAK for addr: %04x %c(%d)\n", + drm_dbg_kms(&i915->drm, "GMBUS [%s] NAK for addr: %04x %c(%d)\n", adapter->name, msgs[i].addr, (msgs[i].flags & I2C_M_RD) ? 'r' : 'w', msgs[i].len); @@ -712,7 +728,7 @@ clear_err: * drm_do_probe_ddc_edid, which bails out on the first -ENXIO. */ if (ret == -ENXIO && i == 0 && try++ == 0) { - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "GMBUS [%s] NAK on first message, retry\n", adapter->name); goto retry; @@ -721,10 +737,10 @@ clear_err: goto out; timeout: - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "GMBUS [%s] timed out, falling back to bit banging on pin %d\n", bus->adapter.name, bus->reg0 & 0xff); - intel_de_write_fw(dev_priv, GMBUS0, 0); + intel_de_write_fw(i915, GMBUS0(i915), 0); /* * Hardware may not support GMBUS over these pins? Try GPIO bitbanging @@ -734,10 +750,10 @@ timeout: out: /* Display WA #0868: skl,bxt,kbl,cfl,glk */ - if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - bxt_gmbus_clock_gating(dev_priv, true); - else if (HAS_PCH_SPT(dev_priv) || HAS_PCH_CNP(dev_priv)) - pch_gmbus_clock_gating(dev_priv, true); + if (IS_GEMINILAKE(i915) || IS_BROXTON(i915)) + bxt_gmbus_clock_gating(i915, true); + else if (HAS_PCH_SPT(i915) || HAS_PCH_CNP(i915)) + pch_gmbus_clock_gating(i915, true); return ret; } @@ -746,11 +762,11 @@ static int gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; intel_wakeref_t wakeref; int ret; - wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); + wakeref = intel_display_power_get(i915, POWER_DOMAIN_GMBUS); if (bus->force_bit) { ret = i2c_bit_algo.master_xfer(adapter, msgs, num); @@ -762,7 +778,7 @@ gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num) bus->force_bit |= GMBUS_FORCE_BIT_RETRY; } - intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref); + intel_display_power_put(i915, POWER_DOMAIN_GMBUS, wakeref); return ret; } @@ -770,7 +786,7 @@ gmbus_xfer(struct i2c_adapter *adapter, struct i2c_msg *msgs, int num) int intel_gmbus_output_aksv(struct i2c_adapter *adapter) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; u8 cmd = DRM_HDCP_DDC_AKSV; u8 buf[DRM_HDCP_KSV_LEN] = { 0 }; struct i2c_msg msgs[] = { @@ -790,8 +806,8 @@ int intel_gmbus_output_aksv(struct i2c_adapter *adapter) intel_wakeref_t wakeref; int ret; - wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_GMBUS); - mutex_lock(&dev_priv->gmbus_mutex); + wakeref = intel_display_power_get(i915, POWER_DOMAIN_GMBUS); + mutex_lock(&i915->display.gmbus.mutex); /* * In order to output Aksv to the receiver, use an indexed write to @@ -800,8 +816,8 @@ int intel_gmbus_output_aksv(struct i2c_adapter *adapter) */ ret = do_gmbus_xfer(adapter, msgs, ARRAY_SIZE(msgs), GMBUS_AKSV_SELECT); - mutex_unlock(&dev_priv->gmbus_mutex); - intel_display_power_put(dev_priv, POWER_DOMAIN_GMBUS, wakeref); + mutex_unlock(&i915->display.gmbus.mutex); + intel_display_power_put(i915, POWER_DOMAIN_GMBUS, wakeref); return ret; } @@ -824,27 +840,27 @@ static void gmbus_lock_bus(struct i2c_adapter *adapter, unsigned int flags) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; - mutex_lock(&dev_priv->gmbus_mutex); + mutex_lock(&i915->display.gmbus.mutex); } static int gmbus_trylock_bus(struct i2c_adapter *adapter, unsigned int flags) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; - return mutex_trylock(&dev_priv->gmbus_mutex); + return mutex_trylock(&i915->display.gmbus.mutex); } static void gmbus_unlock_bus(struct i2c_adapter *adapter, unsigned int flags) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; - mutex_unlock(&dev_priv->gmbus_mutex); + mutex_unlock(&i915->display.gmbus.mutex); } static const struct i2c_lock_operations gmbus_lock_ops = { @@ -855,31 +871,31 @@ static const struct i2c_lock_operations gmbus_lock_ops = { /** * intel_gmbus_setup - instantiate all Intel i2c GMBuses - * @dev_priv: i915 device private + * @i915: i915 device private */ -int intel_gmbus_setup(struct drm_i915_private *dev_priv) +int intel_gmbus_setup(struct drm_i915_private *i915) { - struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); + struct pci_dev *pdev = to_pci_dev(i915->drm.dev); unsigned int pin; int ret; - if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - dev_priv->gpio_mmio_base = VLV_DISPLAY_BASE; - else if (!HAS_GMCH(dev_priv)) + if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) + i915->display.gmbus.mmio_base = VLV_DISPLAY_BASE; + else if (!HAS_GMCH(i915)) /* * Broxton uses the same PCH offsets for South Display Engine, * even though it doesn't have a PCH. */ - dev_priv->gpio_mmio_base = PCH_DISPLAY_BASE; + i915->display.gmbus.mmio_base = PCH_DISPLAY_BASE; - mutex_init(&dev_priv->gmbus_mutex); - init_waitqueue_head(&dev_priv->gmbus_wait_queue); + mutex_init(&i915->display.gmbus.mutex); + init_waitqueue_head(&i915->display.gmbus.wait_queue); - for (pin = 0; pin < ARRAY_SIZE(dev_priv->gmbus); pin++) { + for (pin = 0; pin < ARRAY_SIZE(i915->display.gmbus.bus); pin++) { const struct gmbus_pin *gmbus_pin; struct intel_gmbus *bus; - gmbus_pin = get_gmbus_pin(dev_priv, pin); + gmbus_pin = get_gmbus_pin(i915, pin); if (!gmbus_pin) continue; @@ -896,7 +912,7 @@ int intel_gmbus_setup(struct drm_i915_private *dev_priv) "i915 gmbus %s", gmbus_pin->name); bus->adapter.dev.parent = &pdev->dev; - bus->dev_priv = dev_priv; + bus->i915 = i915; bus->adapter.algo = &gmbus_algorithm; bus->adapter.lock_ops = &gmbus_lock_ops; @@ -911,10 +927,10 @@ int intel_gmbus_setup(struct drm_i915_private *dev_priv) bus->reg0 = pin | GMBUS_RATE_100KHZ; /* gmbus seems to be broken on i830 */ - if (IS_I830(dev_priv)) + if (IS_I830(i915)) bus->force_bit = 1; - intel_gpio_setup(bus, GPIO(gmbus_pin->gpio)); + intel_gpio_setup(bus, GPIO(i915, gmbus_pin->gpio)); ret = i2c_add_adapter(&bus->adapter); if (ret) { @@ -922,43 +938,43 @@ int intel_gmbus_setup(struct drm_i915_private *dev_priv) goto err; } - dev_priv->gmbus[pin] = bus; + i915->display.gmbus.bus[pin] = bus; } - intel_gmbus_reset(dev_priv); + intel_gmbus_reset(i915); return 0; err: - intel_gmbus_teardown(dev_priv); + intel_gmbus_teardown(i915); return ret; } -struct i2c_adapter *intel_gmbus_get_adapter(struct drm_i915_private *dev_priv, +struct i2c_adapter *intel_gmbus_get_adapter(struct drm_i915_private *i915, unsigned int pin) { - if (drm_WARN_ON(&dev_priv->drm, pin >= ARRAY_SIZE(dev_priv->gmbus) || - !dev_priv->gmbus[pin])) + if (drm_WARN_ON(&i915->drm, pin >= ARRAY_SIZE(i915->display.gmbus.bus) || + !i915->display.gmbus.bus[pin])) return NULL; - return &dev_priv->gmbus[pin]->adapter; + return &i915->display.gmbus.bus[pin]->adapter; } void intel_gmbus_force_bit(struct i2c_adapter *adapter, bool force_bit) { struct intel_gmbus *bus = to_intel_gmbus(adapter); - struct drm_i915_private *dev_priv = bus->dev_priv; + struct drm_i915_private *i915 = bus->i915; - mutex_lock(&dev_priv->gmbus_mutex); + mutex_lock(&i915->display.gmbus.mutex); bus->force_bit += force_bit ? 1 : -1; - drm_dbg_kms(&dev_priv->drm, + drm_dbg_kms(&i915->drm, "%sabling bit-banging on %s. force bit now %d\n", force_bit ? "en" : "dis", adapter->name, bus->force_bit); - mutex_unlock(&dev_priv->gmbus_mutex); + mutex_unlock(&i915->display.gmbus.mutex); } bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter) @@ -968,20 +984,20 @@ bool intel_gmbus_is_forced_bit(struct i2c_adapter *adapter) return bus->force_bit; } -void intel_gmbus_teardown(struct drm_i915_private *dev_priv) +void intel_gmbus_teardown(struct drm_i915_private *i915) { unsigned int pin; - for (pin = 0; pin < ARRAY_SIZE(dev_priv->gmbus); pin++) { + for (pin = 0; pin < ARRAY_SIZE(i915->display.gmbus.bus); pin++) { struct intel_gmbus *bus; - bus = dev_priv->gmbus[pin]; + bus = i915->display.gmbus.bus[pin]; if (!bus) continue; i2c_del_adapter(&bus->adapter); kfree(bus); - dev_priv->gmbus[pin] = NULL; + i915->display.gmbus.bus[pin] = NULL; } } diff --git a/drivers/gpu/drm/i915/display/intel_gmbus.h b/drivers/gpu/drm/i915/display/intel_gmbus.h index 8edc2e99cf53..20f704bd4e70 100644 --- a/drivers/gpu/drm/i915/display/intel_gmbus.h +++ b/drivers/gpu/drm/i915/display/intel_gmbus.h @@ -24,6 +24,7 @@ struct i2c_adapter; #define GMBUS_PIN_2_BXT 2 #define GMBUS_PIN_3_BXT 3 #define GMBUS_PIN_4_CNP 4 +#define GMBUS_PIN_5_MTP 5 #define GMBUS_PIN_9_TC1_ICP 9 #define GMBUS_PIN_10_TC2_ICP 10 #define GMBUS_PIN_11_TC3_ICP 11 diff --git a/drivers/gpu/drm/i915/display/intel_gmbus_regs.h b/drivers/gpu/drm/i915/display/intel_gmbus_regs.h new file mode 100644 index 000000000000..53aacbda983c --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_gmbus_regs.h @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_GMBUS_REGS_H__ +#define __INTEL_GMBUS_REGS_H__ + +#include "i915_reg_defs.h" + +#define GMBUS_MMIO_BASE(__i915) ((__i915)->display.gmbus.mmio_base) + +#define GPIO(__i915, gpio) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x5010 + 4 * (gpio)) +#define GPIO_CLOCK_DIR_MASK (1 << 0) +#define GPIO_CLOCK_DIR_IN (0 << 1) +#define GPIO_CLOCK_DIR_OUT (1 << 1) +#define GPIO_CLOCK_VAL_MASK (1 << 2) +#define GPIO_CLOCK_VAL_OUT (1 << 3) +#define GPIO_CLOCK_VAL_IN (1 << 4) +#define GPIO_CLOCK_PULLUP_DISABLE (1 << 5) +#define GPIO_DATA_DIR_MASK (1 << 8) +#define GPIO_DATA_DIR_IN (0 << 9) +#define GPIO_DATA_DIR_OUT (1 << 9) +#define GPIO_DATA_VAL_MASK (1 << 10) +#define GPIO_DATA_VAL_OUT (1 << 11) +#define GPIO_DATA_VAL_IN (1 << 12) +#define GPIO_DATA_PULLUP_DISABLE (1 << 13) + +/* clock/port select */ +#define GMBUS0(__i915) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x5100) +#define GMBUS_AKSV_SELECT (1 << 11) +#define GMBUS_RATE_100KHZ (0 << 8) +#define GMBUS_RATE_50KHZ (1 << 8) +#define GMBUS_RATE_400KHZ (2 << 8) /* reserved on Pineview */ +#define GMBUS_RATE_1MHZ (3 << 8) /* reserved on Pineview */ +#define GMBUS_HOLD_EXT (1 << 7) /* 300ns hold time, rsvd on Pineview */ +#define GMBUS_BYTE_CNT_OVERRIDE (1 << 6) + +/* command/status */ +#define GMBUS1(__i915) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x5104) +#define GMBUS_SW_CLR_INT (1 << 31) +#define GMBUS_SW_RDY (1 << 30) +#define GMBUS_ENT (1 << 29) /* enable timeout */ +#define GMBUS_CYCLE_NONE (0 << 25) +#define GMBUS_CYCLE_WAIT (1 << 25) +#define GMBUS_CYCLE_INDEX (2 << 25) +#define GMBUS_CYCLE_STOP (4 << 25) +#define GMBUS_BYTE_COUNT_SHIFT 16 +#define GMBUS_BYTE_COUNT_MAX 256U +#define GEN9_GMBUS_BYTE_COUNT_MAX 511U +#define GMBUS_SLAVE_INDEX_SHIFT 8 +#define GMBUS_SLAVE_ADDR_SHIFT 1 +#define GMBUS_SLAVE_READ (1 << 0) +#define GMBUS_SLAVE_WRITE (0 << 0) + +/* status */ +#define GMBUS2(__i915) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x5108) +#define GMBUS_INUSE (1 << 15) +#define GMBUS_HW_WAIT_PHASE (1 << 14) +#define GMBUS_STALL_TIMEOUT (1 << 13) +#define GMBUS_INT (1 << 12) +#define GMBUS_HW_RDY (1 << 11) +#define GMBUS_SATOER (1 << 10) +#define GMBUS_ACTIVE (1 << 9) + +/* data buffer bytes 3-0 */ +#define GMBUS3(__i915) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x510c) + +/* interrupt mask (Pineview+) */ +#define GMBUS4(__i915) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x5110) +#define GMBUS_SLAVE_TIMEOUT_EN (1 << 4) +#define GMBUS_NAK_EN (1 << 3) +#define GMBUS_IDLE_EN (1 << 2) +#define GMBUS_HW_WAIT_EN (1 << 1) +#define GMBUS_HW_RDY_EN (1 << 0) + +/* byte index */ +#define GMBUS5(__i915) _MMIO(GMBUS_MMIO_BASE(__i915) + 0x5120) +#define GMBUS_2BYTE_INDEX_EN (1 << 31) + +#endif /* __INTEL_GMBUS_REGS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 7dbc9f0bb24f..6406fd487ee5 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -23,6 +23,7 @@ #include "intel_display_power_well.h" #include "intel_display_types.h" #include "intel_hdcp.h" +#include "intel_hdcp_regs.h" #include "intel_pcode.h" #define KEY_LOAD_TRIES 5 @@ -209,12 +210,12 @@ bool intel_hdcp2_capable(struct intel_connector *connector) return false; /* MEI interface is solid */ - mutex_lock(&dev_priv->hdcp_comp_mutex); - if (!dev_priv->hdcp_comp_added || !dev_priv->hdcp_master) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + if (!dev_priv->display.hdcp.comp_added || !dev_priv->display.hdcp.master) { + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return false; } - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); /* Sink's capability for HDCP2.2 */ hdcp->shim->hdcp_2_2_capable(dig_port, &capable); @@ -1131,8 +1132,8 @@ static void intel_hdcp_prop_work(struct work_struct *work) bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port) { - return INTEL_INFO(dev_priv)->display.has_hdcp && - (DISPLAY_VER(dev_priv) >= 12 || port < PORT_E); + return RUNTIME_INFO(dev_priv)->has_hdcp && + (DISPLAY_VER(dev_priv) >= 12 || port < PORT_E); } static int @@ -1145,11 +1146,11 @@ hdcp2_prepare_ake_init(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1157,7 +1158,7 @@ hdcp2_prepare_ake_init(struct intel_connector *connector, if (ret) drm_dbg_kms(&dev_priv->drm, "Prepare_ake_init failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1175,11 +1176,11 @@ hdcp2_verify_rx_cert_prepare_km(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1189,7 +1190,7 @@ hdcp2_verify_rx_cert_prepare_km(struct intel_connector *connector, if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Verify rx_cert failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1203,18 +1204,18 @@ static int hdcp2_verify_hprime(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } ret = comp->ops->verify_hprime(comp->mei_dev, data, rx_hprime); if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Verify hprime failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1229,11 +1230,11 @@ hdcp2_store_pairing_info(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1241,7 +1242,7 @@ hdcp2_store_pairing_info(struct intel_connector *connector, if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Store pairing info failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1256,11 +1257,11 @@ hdcp2_prepare_lc_init(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1268,7 +1269,7 @@ hdcp2_prepare_lc_init(struct intel_connector *connector, if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Prepare lc_init failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1283,11 +1284,11 @@ hdcp2_verify_lprime(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1295,7 +1296,7 @@ hdcp2_verify_lprime(struct intel_connector *connector, if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Verify L_Prime failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1309,11 +1310,11 @@ static int hdcp2_prepare_skey(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1321,7 +1322,7 @@ static int hdcp2_prepare_skey(struct intel_connector *connector, if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Get session key failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1338,11 +1339,11 @@ hdcp2_verify_rep_topology_prepare_ack(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1352,7 +1353,7 @@ hdcp2_verify_rep_topology_prepare_ack(struct intel_connector *connector, if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Verify rep topology failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1367,18 +1368,18 @@ hdcp2_verify_mprime(struct intel_connector *connector, struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } ret = comp->ops->verify_mprime(comp->mei_dev, data, stream_ready); if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Verify mprime failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1391,11 +1392,11 @@ static int hdcp2_authenticate_port(struct intel_connector *connector) struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } @@ -1403,7 +1404,7 @@ static int hdcp2_authenticate_port(struct intel_connector *connector) if (ret < 0) drm_dbg_kms(&dev_priv->drm, "Enable hdcp auth failed. %d\n", ret); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -1415,17 +1416,17 @@ static int hdcp2_close_mei_session(struct intel_connector *connector) struct i915_hdcp_comp_master *comp; int ret; - mutex_lock(&dev_priv->hdcp_comp_mutex); - comp = dev_priv->hdcp_master; + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + comp = dev_priv->display.hdcp.master; if (!comp || !comp->ops) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return -EINVAL; } ret = comp->ops->close_hdcp_session(comp->mei_dev, &dig_port->hdcp_port_data); - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return ret; } @@ -2143,10 +2144,10 @@ static int i915_hdcp_component_bind(struct device *i915_kdev, struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev); drm_dbg(&dev_priv->drm, "I915 HDCP comp bind\n"); - mutex_lock(&dev_priv->hdcp_comp_mutex); - dev_priv->hdcp_master = (struct i915_hdcp_comp_master *)data; - dev_priv->hdcp_master->mei_dev = mei_kdev; - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + dev_priv->display.hdcp.master = (struct i915_hdcp_comp_master *)data; + dev_priv->display.hdcp.master->mei_dev = mei_kdev; + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return 0; } @@ -2157,9 +2158,9 @@ static void i915_hdcp_component_unbind(struct device *i915_kdev, struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev); drm_dbg(&dev_priv->drm, "I915 HDCP comp unbind\n"); - mutex_lock(&dev_priv->hdcp_comp_mutex); - dev_priv->hdcp_master = NULL; - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + dev_priv->display.hdcp.master = NULL; + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); } static const struct component_ops i915_hdcp_component_ops = { @@ -2250,19 +2251,19 @@ void intel_hdcp_component_init(struct drm_i915_private *dev_priv) if (!is_hdcp2_supported(dev_priv)) return; - mutex_lock(&dev_priv->hdcp_comp_mutex); - drm_WARN_ON(&dev_priv->drm, dev_priv->hdcp_comp_added); + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + drm_WARN_ON(&dev_priv->drm, dev_priv->display.hdcp.comp_added); - dev_priv->hdcp_comp_added = true; - mutex_unlock(&dev_priv->hdcp_comp_mutex); + dev_priv->display.hdcp.comp_added = true; + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); ret = component_add_typed(dev_priv->drm.dev, &i915_hdcp_component_ops, I915_COMPONENT_HDCP); if (ret < 0) { drm_dbg_kms(&dev_priv->drm, "Failed at component add(%d)\n", ret); - mutex_lock(&dev_priv->hdcp_comp_mutex); - dev_priv->hdcp_comp_added = false; - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + dev_priv->display.hdcp.comp_added = false; + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return; } } @@ -2475,14 +2476,14 @@ void intel_hdcp_update_pipe(struct intel_atomic_state *state, void intel_hdcp_component_fini(struct drm_i915_private *dev_priv) { - mutex_lock(&dev_priv->hdcp_comp_mutex); - if (!dev_priv->hdcp_comp_added) { - mutex_unlock(&dev_priv->hdcp_comp_mutex); + mutex_lock(&dev_priv->display.hdcp.comp_mutex); + if (!dev_priv->display.hdcp.comp_added) { + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); return; } - dev_priv->hdcp_comp_added = false; - mutex_unlock(&dev_priv->hdcp_comp_mutex); + dev_priv->display.hdcp.comp_added = false; + mutex_unlock(&dev_priv->display.hdcp.comp_mutex); component_del(dev_priv->drm.dev, &i915_hdcp_component_ops); } diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h new file mode 100644 index 000000000000..2a3733e8966c --- /dev/null +++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h @@ -0,0 +1,270 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __INTEL_HDCP_REGS_H__ +#define __INTEL_HDCP_REGS_H__ + +#include "i915_reg_defs.h" + +/* HDCP Key Registers */ +#define HDCP_KEY_CONF _MMIO(0x66c00) +#define HDCP_AKSV_SEND_TRIGGER REG_BIT(31) +#define HDCP_CLEAR_KEYS_TRIGGER REG_BIT(30) +#define HDCP_KEY_LOAD_TRIGGER REG_BIT(8) +#define HDCP_KEY_STATUS _MMIO(0x66c04) +#define HDCP_FUSE_IN_PROGRESS REG_BIT(7) +#define HDCP_FUSE_ERROR REG_BIT(6) +#define HDCP_FUSE_DONE REG_BIT(5) +#define HDCP_KEY_LOAD_STATUS REG_BIT(1) +#define HDCP_KEY_LOAD_DONE REG_BIT(0) +#define HDCP_AKSV_LO _MMIO(0x66c10) +#define HDCP_AKSV_HI _MMIO(0x66c14) + +/* HDCP Repeater Registers */ +#define HDCP_REP_CTL _MMIO(0x66d00) +#define HDCP_TRANSA_REP_PRESENT REG_BIT(31) +#define HDCP_TRANSB_REP_PRESENT REG_BIT(30) +#define HDCP_TRANSC_REP_PRESENT REG_BIT(29) +#define HDCP_TRANSD_REP_PRESENT REG_BIT(28) +#define HDCP_DDIB_REP_PRESENT REG_BIT(30) +#define HDCP_DDIA_REP_PRESENT REG_BIT(29) +#define HDCP_DDIC_REP_PRESENT REG_BIT(28) +#define HDCP_DDID_REP_PRESENT REG_BIT(27) +#define HDCP_DDIF_REP_PRESENT REG_BIT(26) +#define HDCP_DDIE_REP_PRESENT REG_BIT(25) +#define HDCP_TRANSA_SHA1_M0 (1 << 20) +#define HDCP_TRANSB_SHA1_M0 (2 << 20) +#define HDCP_TRANSC_SHA1_M0 (3 << 20) +#define HDCP_TRANSD_SHA1_M0 (4 << 20) +#define HDCP_DDIB_SHA1_M0 (1 << 20) +#define HDCP_DDIA_SHA1_M0 (2 << 20) +#define HDCP_DDIC_SHA1_M0 (3 << 20) +#define HDCP_DDID_SHA1_M0 (4 << 20) +#define HDCP_DDIF_SHA1_M0 (5 << 20) +#define HDCP_DDIE_SHA1_M0 (6 << 20) /* Bspec says 5? */ +#define HDCP_SHA1_BUSY REG_BIT(16) +#define HDCP_SHA1_READY REG_BIT(17) +#define HDCP_SHA1_COMPLETE REG_BIT(18) +#define HDCP_SHA1_V_MATCH REG_BIT(19) +#define HDCP_SHA1_TEXT_32 (1 << 1) +#define HDCP_SHA1_COMPLETE_HASH (2 << 1) +#define HDCP_SHA1_TEXT_24 (4 << 1) +#define HDCP_SHA1_TEXT_16 (5 << 1) +#define HDCP_SHA1_TEXT_8 (6 << 1) +#define HDCP_SHA1_TEXT_0 (7 << 1) +#define HDCP_SHA_V_PRIME_H0 _MMIO(0x66d04) +#define HDCP_SHA_V_PRIME_H1 _MMIO(0x66d08) +#define HDCP_SHA_V_PRIME_H2 _MMIO(0x66d0C) +#define HDCP_SHA_V_PRIME_H3 _MMIO(0x66d10) +#define HDCP_SHA_V_PRIME_H4 _MMIO(0x66d14) +#define HDCP_SHA_V_PRIME(h) _MMIO((0x66d04 + (h) * 4)) +#define HDCP_SHA_TEXT _MMIO(0x66d18) + +/* HDCP Auth Registers */ +#define _PORTA_HDCP_AUTHENC 0x66800 +#define _PORTB_HDCP_AUTHENC 0x66500 +#define _PORTC_HDCP_AUTHENC 0x66600 +#define _PORTD_HDCP_AUTHENC 0x66700 +#define _PORTE_HDCP_AUTHENC 0x66A00 +#define _PORTF_HDCP_AUTHENC 0x66900 +#define _PORT_HDCP_AUTHENC(port, x) _MMIO(_PICK(port, \ + _PORTA_HDCP_AUTHENC, \ + _PORTB_HDCP_AUTHENC, \ + _PORTC_HDCP_AUTHENC, \ + _PORTD_HDCP_AUTHENC, \ + _PORTE_HDCP_AUTHENC, \ + _PORTF_HDCP_AUTHENC) + (x)) +#define PORT_HDCP_CONF(port) _PORT_HDCP_AUTHENC(port, 0x0) +#define _TRANSA_HDCP_CONF 0x66400 +#define _TRANSB_HDCP_CONF 0x66500 +#define TRANS_HDCP_CONF(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_CONF, \ + _TRANSB_HDCP_CONF) +#define HDCP_CONF(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_CONF(trans) : \ + PORT_HDCP_CONF(port)) + +#define HDCP_CONF_CAPTURE_AN REG_BIT(0) +#define HDCP_CONF_AUTH_AND_ENC (REG_BIT(1) | REG_BIT(0)) +#define PORT_HDCP_ANINIT(port) _PORT_HDCP_AUTHENC(port, 0x4) +#define _TRANSA_HDCP_ANINIT 0x66404 +#define _TRANSB_HDCP_ANINIT 0x66504 +#define TRANS_HDCP_ANINIT(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP_ANINIT, \ + _TRANSB_HDCP_ANINIT) +#define HDCP_ANINIT(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_ANINIT(trans) : \ + PORT_HDCP_ANINIT(port)) + +#define PORT_HDCP_ANLO(port) _PORT_HDCP_AUTHENC(port, 0x8) +#define _TRANSA_HDCP_ANLO 0x66408 +#define _TRANSB_HDCP_ANLO 0x66508 +#define TRANS_HDCP_ANLO(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_ANLO, \ + _TRANSB_HDCP_ANLO) +#define HDCP_ANLO(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_ANLO(trans) : \ + PORT_HDCP_ANLO(port)) + +#define PORT_HDCP_ANHI(port) _PORT_HDCP_AUTHENC(port, 0xC) +#define _TRANSA_HDCP_ANHI 0x6640C +#define _TRANSB_HDCP_ANHI 0x6650C +#define TRANS_HDCP_ANHI(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_ANHI, \ + _TRANSB_HDCP_ANHI) +#define HDCP_ANHI(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_ANHI(trans) : \ + PORT_HDCP_ANHI(port)) + +#define PORT_HDCP_BKSVLO(port) _PORT_HDCP_AUTHENC(port, 0x10) +#define _TRANSA_HDCP_BKSVLO 0x66410 +#define _TRANSB_HDCP_BKSVLO 0x66510 +#define TRANS_HDCP_BKSVLO(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP_BKSVLO, \ + _TRANSB_HDCP_BKSVLO) +#define HDCP_BKSVLO(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_BKSVLO(trans) : \ + PORT_HDCP_BKSVLO(port)) + +#define PORT_HDCP_BKSVHI(port) _PORT_HDCP_AUTHENC(port, 0x14) +#define _TRANSA_HDCP_BKSVHI 0x66414 +#define _TRANSB_HDCP_BKSVHI 0x66514 +#define TRANS_HDCP_BKSVHI(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP_BKSVHI, \ + _TRANSB_HDCP_BKSVHI) +#define HDCP_BKSVHI(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_BKSVHI(trans) : \ + PORT_HDCP_BKSVHI(port)) + +#define PORT_HDCP_RPRIME(port) _PORT_HDCP_AUTHENC(port, 0x18) +#define _TRANSA_HDCP_RPRIME 0x66418 +#define _TRANSB_HDCP_RPRIME 0x66518 +#define TRANS_HDCP_RPRIME(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP_RPRIME, \ + _TRANSB_HDCP_RPRIME) +#define HDCP_RPRIME(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_RPRIME(trans) : \ + PORT_HDCP_RPRIME(port)) + +#define PORT_HDCP_STATUS(port) _PORT_HDCP_AUTHENC(port, 0x1C) +#define _TRANSA_HDCP_STATUS 0x6641C +#define _TRANSB_HDCP_STATUS 0x6651C +#define TRANS_HDCP_STATUS(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP_STATUS, \ + _TRANSB_HDCP_STATUS) +#define HDCP_STATUS(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP_STATUS(trans) : \ + PORT_HDCP_STATUS(port)) + +#define HDCP_STATUS_STREAM_A_ENC REG_BIT(31) +#define HDCP_STATUS_STREAM_B_ENC REG_BIT(30) +#define HDCP_STATUS_STREAM_C_ENC REG_BIT(29) +#define HDCP_STATUS_STREAM_D_ENC REG_BIT(28) +#define HDCP_STATUS_AUTH REG_BIT(21) +#define HDCP_STATUS_ENC REG_BIT(20) +#define HDCP_STATUS_RI_MATCH REG_BIT(19) +#define HDCP_STATUS_R0_READY REG_BIT(18) +#define HDCP_STATUS_AN_READY REG_BIT(17) +#define HDCP_STATUS_CIPHER REG_BIT(16) +#define HDCP_STATUS_FRAME_CNT(x) (((x) >> 8) & 0xff) + +/* HDCP2.2 Registers */ +#define _PORTA_HDCP2_BASE 0x66800 +#define _PORTB_HDCP2_BASE 0x66500 +#define _PORTC_HDCP2_BASE 0x66600 +#define _PORTD_HDCP2_BASE 0x66700 +#define _PORTE_HDCP2_BASE 0x66A00 +#define _PORTF_HDCP2_BASE 0x66900 +#define _PORT_HDCP2_BASE(port, x) _MMIO(_PICK((port), \ + _PORTA_HDCP2_BASE, \ + _PORTB_HDCP2_BASE, \ + _PORTC_HDCP2_BASE, \ + _PORTD_HDCP2_BASE, \ + _PORTE_HDCP2_BASE, \ + _PORTF_HDCP2_BASE) + (x)) + +#define PORT_HDCP2_AUTH(port) _PORT_HDCP2_BASE(port, 0x98) +#define _TRANSA_HDCP2_AUTH 0x66498 +#define _TRANSB_HDCP2_AUTH 0x66598 +#define TRANS_HDCP2_AUTH(trans) _MMIO_TRANS(trans, _TRANSA_HDCP2_AUTH, \ + _TRANSB_HDCP2_AUTH) +#define AUTH_LINK_AUTHENTICATED REG_BIT(31) +#define AUTH_LINK_TYPE REG_BIT(30) +#define AUTH_FORCE_CLR_INPUTCTR REG_BIT(19) +#define AUTH_CLR_KEYS REG_BIT(18) +#define HDCP2_AUTH(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP2_AUTH(trans) : \ + PORT_HDCP2_AUTH(port)) + +#define PORT_HDCP2_CTL(port) _PORT_HDCP2_BASE(port, 0xB0) +#define _TRANSA_HDCP2_CTL 0x664B0 +#define _TRANSB_HDCP2_CTL 0x665B0 +#define TRANS_HDCP2_CTL(trans) _MMIO_TRANS(trans, _TRANSA_HDCP2_CTL, \ + _TRANSB_HDCP2_CTL) +#define CTL_LINK_ENCRYPTION_REQ REG_BIT(31) +#define HDCP2_CTL(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP2_CTL(trans) : \ + PORT_HDCP2_CTL(port)) + +#define PORT_HDCP2_STATUS(port) _PORT_HDCP2_BASE(port, 0xB4) +#define _TRANSA_HDCP2_STATUS 0x664B4 +#define _TRANSB_HDCP2_STATUS 0x665B4 +#define TRANS_HDCP2_STATUS(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP2_STATUS, \ + _TRANSB_HDCP2_STATUS) +#define LINK_TYPE_STATUS REG_BIT(22) +#define LINK_AUTH_STATUS REG_BIT(21) +#define LINK_ENCRYPTION_STATUS REG_BIT(20) +#define HDCP2_STATUS(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP2_STATUS(trans) : \ + PORT_HDCP2_STATUS(port)) + +#define _PIPEA_HDCP2_STREAM_STATUS 0x668C0 +#define _PIPEB_HDCP2_STREAM_STATUS 0x665C0 +#define _PIPEC_HDCP2_STREAM_STATUS 0x666C0 +#define _PIPED_HDCP2_STREAM_STATUS 0x667C0 +#define PIPE_HDCP2_STREAM_STATUS(pipe) _MMIO(_PICK((pipe), \ + _PIPEA_HDCP2_STREAM_STATUS, \ + _PIPEB_HDCP2_STREAM_STATUS, \ + _PIPEC_HDCP2_STREAM_STATUS, \ + _PIPED_HDCP2_STREAM_STATUS)) + +#define _TRANSA_HDCP2_STREAM_STATUS 0x664C0 +#define _TRANSB_HDCP2_STREAM_STATUS 0x665C0 +#define TRANS_HDCP2_STREAM_STATUS(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP2_STREAM_STATUS, \ + _TRANSB_HDCP2_STREAM_STATUS) +#define STREAM_ENCRYPTION_STATUS REG_BIT(31) +#define STREAM_TYPE_STATUS REG_BIT(30) +#define HDCP2_STREAM_STATUS(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP2_STREAM_STATUS(trans) : \ + PIPE_HDCP2_STREAM_STATUS(pipe)) + +#define _PORTA_HDCP2_AUTH_STREAM 0x66F00 +#define _PORTB_HDCP2_AUTH_STREAM 0x66F04 +#define PORT_HDCP2_AUTH_STREAM(port) _MMIO_PORT(port, \ + _PORTA_HDCP2_AUTH_STREAM, \ + _PORTB_HDCP2_AUTH_STREAM) +#define _TRANSA_HDCP2_AUTH_STREAM 0x66F00 +#define _TRANSB_HDCP2_AUTH_STREAM 0x66F04 +#define TRANS_HDCP2_AUTH_STREAM(trans) _MMIO_TRANS(trans, \ + _TRANSA_HDCP2_AUTH_STREAM, \ + _TRANSB_HDCP2_AUTH_STREAM) +#define AUTH_STREAM_TYPE REG_BIT(31) +#define HDCP2_AUTH_STREAM(dev_priv, trans, port) \ + (GRAPHICS_VER(dev_priv) >= 12 ? \ + TRANS_HDCP2_AUTH_STREAM(trans) : \ + PORT_HDCP2_AUTH_STREAM(port)) + +#endif /* __INTEL_HDCP_REGS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index ebd91aa69dd2..7816b2a33fee 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -50,6 +50,7 @@ #include "intel_dp.h" #include "intel_gmbus.h" #include "intel_hdcp.h" +#include "intel_hdcp_regs.h" #include "intel_hdmi.h" #include "intel_lspcon.h" #include "intel_panel.h" @@ -1891,7 +1892,7 @@ int intel_hdmi_tmds_clock(int clock, int bpc, bool ycbcr420_output) * 1.5x for 12bpc * 1.25x for 10bpc */ - return clock * bpc / 8; + return DIV_ROUND_CLOSEST(clock * bpc, 8); } static bool intel_hdmi_source_bpc_possible(struct drm_i915_private *i915, int bpc) @@ -2001,6 +2002,15 @@ intel_hdmi_mode_valid(struct drm_connector *connector, clock *= 2; } + /* + * HDMI2.1 requires higher resolution modes like 8k60, 4K120 to be + * enumerated only if FRL is supported. Current platforms do not support + * FRL so prune the higher resolution modes that require doctclock more + * than 600MHz. + */ + if (clock > 600000) + return MODE_CLOCK_HIGH; + ycbcr_420_only = drm_mode_is_420_only(&connector->display_info, mode); status = intel_hdmi_mode_clock_valid(connector, clock, has_hdmi_sink, ycbcr_420_only); diff --git a/drivers/gpu/drm/i915/display/intel_hotplug.c b/drivers/gpu/drm/i915/display/intel_hotplug.c index 5f8b4f481cff..f7a2f485b177 100644 --- a/drivers/gpu/drm/i915/display/intel_hotplug.c +++ b/drivers/gpu/drm/i915/display/intel_hotplug.c @@ -119,13 +119,13 @@ intel_connector_hpd_pin(struct intel_connector *connector) * responsible for further action. * * The number of IRQs that are allowed within @HPD_STORM_DETECT_PERIOD is - * stored in @dev_priv->hotplug.hpd_storm_threshold which defaults to + * stored in @dev_priv->display.hotplug.hpd_storm_threshold which defaults to * @HPD_STORM_DEFAULT_THRESHOLD. Long IRQs count as +10 to this threshold, and * short IRQs count as +1. If this threshold is exceeded, it's considered an * IRQ storm and the IRQ state is set to @HPD_MARK_DISABLED. * * By default, most systems will only count long IRQs towards - * &dev_priv->hotplug.hpd_storm_threshold. However, some older systems also + * &dev_priv->display.hotplug.hpd_storm_threshold. However, some older systems also * suffer from short IRQ storms and must also track these. Because short IRQ * storms are naturally caused by sideband interactions with DP MST devices, * short IRQ detection is only enabled for systems without DP MST support. @@ -140,7 +140,7 @@ intel_connector_hpd_pin(struct intel_connector *connector) static bool intel_hpd_irq_storm_detect(struct drm_i915_private *dev_priv, enum hpd_pin pin, bool long_hpd) { - struct i915_hotplug *hpd = &dev_priv->hotplug; + struct intel_hotplug *hpd = &dev_priv->display.hotplug; unsigned long start = hpd->stats[pin].last_jiffies; unsigned long end = start + msecs_to_jiffies(HPD_STORM_DETECT_PERIOD); const int increment = long_hpd ? 10 : 1; @@ -148,7 +148,7 @@ static bool intel_hpd_irq_storm_detect(struct drm_i915_private *dev_priv, bool storm = false; if (!threshold || - (!long_hpd && !dev_priv->hotplug.hpd_short_storm_enabled)) + (!long_hpd && !dev_priv->display.hotplug.hpd_short_storm_enabled)) return false; if (!time_in_range(jiffies, start, end)) { @@ -191,7 +191,7 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv) pin = intel_connector_hpd_pin(connector); if (pin == HPD_NONE || - dev_priv->hotplug.stats[pin].state != HPD_MARK_DISABLED) + dev_priv->display.hotplug.stats[pin].state != HPD_MARK_DISABLED) continue; drm_info(&dev_priv->drm, @@ -199,7 +199,7 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv) "switching from hotplug detection to polling\n", connector->base.name); - dev_priv->hotplug.stats[pin].state = HPD_DISABLED; + dev_priv->display.hotplug.stats[pin].state = HPD_DISABLED; connector->base.polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT; hpd_disabled = true; @@ -209,7 +209,7 @@ intel_hpd_irq_storm_switch_to_polling(struct drm_i915_private *dev_priv) /* Enable polling and queue hotplug re-enabling. */ if (hpd_disabled) { drm_kms_helper_poll_enable(dev); - mod_delayed_work(system_wq, &dev_priv->hotplug.reenable_work, + mod_delayed_work(system_wq, &dev_priv->display.hotplug.reenable_work, msecs_to_jiffies(HPD_STORM_REENABLE_DELAY)); } } @@ -218,7 +218,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) { struct drm_i915_private *dev_priv = container_of(work, typeof(*dev_priv), - hotplug.reenable_work.work); + display.hotplug.reenable_work.work); struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; @@ -233,7 +233,7 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) for_each_intel_connector_iter(connector, &conn_iter) { pin = intel_connector_hpd_pin(connector); if (pin == HPD_NONE || - dev_priv->hotplug.stats[pin].state != HPD_DISABLED) + dev_priv->display.hotplug.stats[pin].state != HPD_DISABLED) continue; if (connector->base.polled != connector->polled) @@ -245,8 +245,8 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work) drm_connector_list_iter_end(&conn_iter); for_each_hpd_pin(pin) { - if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) - dev_priv->hotplug.stats[pin].state = HPD_ENABLED; + if (dev_priv->display.hotplug.stats[pin].state == HPD_DISABLED) + dev_priv->display.hotplug.stats[pin].state = HPD_ENABLED; } intel_hpd_irq_setup(dev_priv); @@ -297,16 +297,16 @@ static bool intel_encoder_has_hpd_pulse(struct intel_encoder *encoder) static void i915_digport_work_func(struct work_struct *work) { struct drm_i915_private *dev_priv = - container_of(work, struct drm_i915_private, hotplug.dig_port_work); + container_of(work, struct drm_i915_private, display.hotplug.dig_port_work); u32 long_port_mask, short_port_mask; struct intel_encoder *encoder; u32 old_bits = 0; spin_lock_irq(&dev_priv->irq_lock); - long_port_mask = dev_priv->hotplug.long_port_mask; - dev_priv->hotplug.long_port_mask = 0; - short_port_mask = dev_priv->hotplug.short_port_mask; - dev_priv->hotplug.short_port_mask = 0; + long_port_mask = dev_priv->display.hotplug.long_port_mask; + dev_priv->display.hotplug.long_port_mask = 0; + short_port_mask = dev_priv->display.hotplug.short_port_mask; + dev_priv->display.hotplug.short_port_mask = 0; spin_unlock_irq(&dev_priv->irq_lock); for_each_intel_encoder(&dev_priv->drm, encoder) { @@ -335,9 +335,9 @@ static void i915_digport_work_func(struct work_struct *work) if (old_bits) { spin_lock_irq(&dev_priv->irq_lock); - dev_priv->hotplug.event_bits |= old_bits; + dev_priv->display.hotplug.event_bits |= old_bits; spin_unlock_irq(&dev_priv->irq_lock); - queue_delayed_work(system_wq, &dev_priv->hotplug.hotplug_work, 0); + queue_delayed_work(system_wq, &dev_priv->display.hotplug.hotplug_work, 0); } } @@ -353,10 +353,10 @@ void intel_hpd_trigger_irq(struct intel_digital_port *dig_port) struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); spin_lock_irq(&i915->irq_lock); - i915->hotplug.short_port_mask |= BIT(dig_port->base.port); + i915->display.hotplug.short_port_mask |= BIT(dig_port->base.port); spin_unlock_irq(&i915->irq_lock); - queue_work(i915->hotplug.dp_wq, &i915->hotplug.dig_port_work); + queue_work(i915->display.hotplug.dp_wq, &i915->display.hotplug.dig_port_work); } /* @@ -366,7 +366,7 @@ static void i915_hotplug_work_func(struct work_struct *work) { struct drm_i915_private *dev_priv = container_of(work, struct drm_i915_private, - hotplug.hotplug_work.work); + display.hotplug.hotplug_work.work); struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; @@ -379,10 +379,10 @@ static void i915_hotplug_work_func(struct work_struct *work) spin_lock_irq(&dev_priv->irq_lock); - hpd_event_bits = dev_priv->hotplug.event_bits; - dev_priv->hotplug.event_bits = 0; - hpd_retry_bits = dev_priv->hotplug.retry_bits; - dev_priv->hotplug.retry_bits = 0; + hpd_event_bits = dev_priv->display.hotplug.event_bits; + dev_priv->display.hotplug.event_bits = 0; + hpd_retry_bits = dev_priv->display.hotplug.retry_bits; + dev_priv->display.hotplug.retry_bits = 0; /* Enable polling for connectors which had HPD IRQ storms */ intel_hpd_irq_storm_switch_to_polling(dev_priv); @@ -435,10 +435,10 @@ static void i915_hotplug_work_func(struct work_struct *work) retry &= ~changed; if (retry) { spin_lock_irq(&dev_priv->irq_lock); - dev_priv->hotplug.retry_bits |= retry; + dev_priv->display.hotplug.retry_bits |= retry; spin_unlock_irq(&dev_priv->irq_lock); - mod_delayed_work(system_wq, &dev_priv->hotplug.hotplug_work, + mod_delayed_work(system_wq, &dev_priv->display.hotplug.hotplug_work, msecs_to_jiffies(HPD_RETRY_DELAY)); } } @@ -502,10 +502,10 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, if (long_hpd) { long_hpd_pulse_mask |= BIT(pin); - dev_priv->hotplug.long_port_mask |= BIT(port); + dev_priv->display.hotplug.long_port_mask |= BIT(port); } else { short_hpd_pulse_mask |= BIT(pin); - dev_priv->hotplug.short_port_mask |= BIT(port); + dev_priv->display.hotplug.short_port_mask |= BIT(port); } } @@ -516,7 +516,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, if (!(BIT(pin) & pin_mask)) continue; - if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) { + if (dev_priv->display.hotplug.stats[pin].state == HPD_DISABLED) { /* * On GMCH platforms the interrupt mask bits only * prevent irq generation, not the setting of the @@ -529,7 +529,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, continue; } - if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED) + if (dev_priv->display.hotplug.stats[pin].state != HPD_ENABLED) continue; /* @@ -540,13 +540,13 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, if (((short_hpd_pulse_mask | long_hpd_pulse_mask) & BIT(pin))) { long_hpd = long_hpd_pulse_mask & BIT(pin); } else { - dev_priv->hotplug.event_bits |= BIT(pin); + dev_priv->display.hotplug.event_bits |= BIT(pin); long_hpd = true; queue_hp = true; } if (intel_hpd_irq_storm_detect(dev_priv, pin, long_hpd)) { - dev_priv->hotplug.event_bits &= ~BIT(pin); + dev_priv->display.hotplug.event_bits &= ~BIT(pin); storm_detected = true; queue_hp = true; } @@ -567,9 +567,9 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv, * deadlock. */ if (queue_dig) - queue_work(dev_priv->hotplug.dp_wq, &dev_priv->hotplug.dig_port_work); + queue_work(dev_priv->display.hotplug.dp_wq, &dev_priv->display.hotplug.dig_port_work); if (queue_hp) - queue_delayed_work(system_wq, &dev_priv->hotplug.hotplug_work, 0); + queue_delayed_work(system_wq, &dev_priv->display.hotplug.hotplug_work, 0); } /** @@ -594,8 +594,8 @@ void intel_hpd_init(struct drm_i915_private *dev_priv) return; for_each_hpd_pin(i) { - dev_priv->hotplug.stats[i].count = 0; - dev_priv->hotplug.stats[i].state = HPD_ENABLED; + dev_priv->display.hotplug.stats[i].count = 0; + dev_priv->display.hotplug.stats[i].state = HPD_ENABLED; } /* @@ -611,7 +611,7 @@ static void i915_hpd_poll_init_work(struct work_struct *work) { struct drm_i915_private *dev_priv = container_of(work, struct drm_i915_private, - hotplug.poll_init_work); + display.hotplug.poll_init_work); struct drm_device *dev = &dev_priv->drm; struct drm_connector_list_iter conn_iter; struct intel_connector *connector; @@ -619,7 +619,7 @@ static void i915_hpd_poll_init_work(struct work_struct *work) mutex_lock(&dev->mode_config.mutex); - enabled = READ_ONCE(dev_priv->hotplug.poll_enabled); + enabled = READ_ONCE(dev_priv->display.hotplug.poll_enabled); drm_connector_list_iter_begin(dev, &conn_iter); for_each_intel_connector_iter(connector, &conn_iter) { @@ -672,7 +672,7 @@ void intel_hpd_poll_enable(struct drm_i915_private *dev_priv) !INTEL_DISPLAY_ENABLED(dev_priv)) return; - WRITE_ONCE(dev_priv->hotplug.poll_enabled, true); + WRITE_ONCE(dev_priv->display.hotplug.poll_enabled, true); /* * We might already be holding dev->mode_config.mutex, so do this in a @@ -680,7 +680,7 @@ void intel_hpd_poll_enable(struct drm_i915_private *dev_priv) * As well, there's no issue if we race here since we always reschedule * this worker anyway */ - schedule_work(&dev_priv->hotplug.poll_init_work); + schedule_work(&dev_priv->display.hotplug.poll_init_work); } /** @@ -707,17 +707,17 @@ void intel_hpd_poll_disable(struct drm_i915_private *dev_priv) if (!HAS_DISPLAY(dev_priv)) return; - WRITE_ONCE(dev_priv->hotplug.poll_enabled, false); - schedule_work(&dev_priv->hotplug.poll_init_work); + WRITE_ONCE(dev_priv->display.hotplug.poll_enabled, false); + schedule_work(&dev_priv->display.hotplug.poll_init_work); } void intel_hpd_init_work(struct drm_i915_private *dev_priv) { - INIT_DELAYED_WORK(&dev_priv->hotplug.hotplug_work, + INIT_DELAYED_WORK(&dev_priv->display.hotplug.hotplug_work, i915_hotplug_work_func); - INIT_WORK(&dev_priv->hotplug.dig_port_work, i915_digport_work_func); - INIT_WORK(&dev_priv->hotplug.poll_init_work, i915_hpd_poll_init_work); - INIT_DELAYED_WORK(&dev_priv->hotplug.reenable_work, + INIT_WORK(&dev_priv->display.hotplug.dig_port_work, i915_digport_work_func); + INIT_WORK(&dev_priv->display.hotplug.poll_init_work, i915_hpd_poll_init_work); + INIT_DELAYED_WORK(&dev_priv->display.hotplug.reenable_work, intel_hpd_irq_storm_reenable_work); } @@ -728,17 +728,17 @@ void intel_hpd_cancel_work(struct drm_i915_private *dev_priv) spin_lock_irq(&dev_priv->irq_lock); - dev_priv->hotplug.long_port_mask = 0; - dev_priv->hotplug.short_port_mask = 0; - dev_priv->hotplug.event_bits = 0; - dev_priv->hotplug.retry_bits = 0; + dev_priv->display.hotplug.long_port_mask = 0; + dev_priv->display.hotplug.short_port_mask = 0; + dev_priv->display.hotplug.event_bits = 0; + dev_priv->display.hotplug.retry_bits = 0; spin_unlock_irq(&dev_priv->irq_lock); - cancel_work_sync(&dev_priv->hotplug.dig_port_work); - cancel_delayed_work_sync(&dev_priv->hotplug.hotplug_work); - cancel_work_sync(&dev_priv->hotplug.poll_init_work); - cancel_delayed_work_sync(&dev_priv->hotplug.reenable_work); + cancel_work_sync(&dev_priv->display.hotplug.dig_port_work); + cancel_delayed_work_sync(&dev_priv->display.hotplug.hotplug_work); + cancel_work_sync(&dev_priv->display.hotplug.poll_init_work); + cancel_delayed_work_sync(&dev_priv->display.hotplug.reenable_work); } bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin) @@ -749,8 +749,8 @@ bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin) return false; spin_lock_irq(&dev_priv->irq_lock); - if (dev_priv->hotplug.stats[pin].state == HPD_ENABLED) { - dev_priv->hotplug.stats[pin].state = HPD_DISABLED; + if (dev_priv->display.hotplug.stats[pin].state == HPD_ENABLED) { + dev_priv->display.hotplug.stats[pin].state = HPD_DISABLED; ret = true; } spin_unlock_irq(&dev_priv->irq_lock); @@ -764,6 +764,6 @@ void intel_hpd_enable(struct drm_i915_private *dev_priv, enum hpd_pin pin) return; spin_lock_irq(&dev_priv->irq_lock); - dev_priv->hotplug.stats[pin].state = HPD_ENABLED; + dev_priv->display.hotplug.stats[pin].state = HPD_ENABLED; spin_unlock_irq(&dev_priv->irq_lock); } diff --git a/drivers/gpu/drm/i915/display/intel_lpe_audio.c b/drivers/gpu/drm/i915/display/intel_lpe_audio.c index 4970bf146c4a..dca6003ccac8 100644 --- a/drivers/gpu/drm/i915/display/intel_lpe_audio.c +++ b/drivers/gpu/drm/i915/display/intel_lpe_audio.c @@ -73,8 +73,9 @@ #include "i915_drv.h" #include "intel_de.h" #include "intel_lpe_audio.h" +#include "intel_pci_config.h" -#define HAS_LPE_AUDIO(dev_priv) ((dev_priv)->audio.lpe.platdev != NULL) +#define HAS_LPE_AUDIO(dev_priv) ((dev_priv)->display.audio.lpe.platdev != NULL) static struct platform_device * lpe_audio_platdev_create(struct drm_i915_private *dev_priv) @@ -96,13 +97,13 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv) return ERR_PTR(-ENOMEM); } - rsc[0].start = rsc[0].end = dev_priv->audio.lpe.irq; + rsc[0].start = rsc[0].end = dev_priv->display.audio.lpe.irq; rsc[0].flags = IORESOURCE_IRQ; rsc[0].name = "hdmi-lpe-audio-irq"; - rsc[1].start = pci_resource_start(pdev, 0) + + rsc[1].start = pci_resource_start(pdev, GTTMMADR_BAR) + I915_HDMI_LPE_AUDIO_BASE; - rsc[1].end = pci_resource_start(pdev, 0) + + rsc[1].end = pci_resource_start(pdev, GTTMMADR_BAR) + I915_HDMI_LPE_AUDIO_BASE + I915_HDMI_LPE_AUDIO_SIZE - 1; rsc[1].flags = IORESOURCE_MEM; rsc[1].name = "hdmi-lpe-audio-mmio"; @@ -148,7 +149,7 @@ static void lpe_audio_platdev_destroy(struct drm_i915_private *dev_priv) * than us fiddle with its internals. */ - platform_device_unregister(dev_priv->audio.lpe.platdev); + platform_device_unregister(dev_priv->display.audio.lpe.platdev); } static void lpe_audio_irq_unmask(struct irq_data *d) @@ -167,7 +168,7 @@ static struct irq_chip lpe_audio_irqchip = { static int lpe_audio_irq_init(struct drm_i915_private *dev_priv) { - int irq = dev_priv->audio.lpe.irq; + int irq = dev_priv->display.audio.lpe.irq; drm_WARN_ON(&dev_priv->drm, !intel_irqs_enabled(dev_priv)); irq_set_chip_and_handler_name(irq, @@ -204,15 +205,15 @@ static int lpe_audio_setup(struct drm_i915_private *dev_priv) { int ret; - dev_priv->audio.lpe.irq = irq_alloc_desc(0); - if (dev_priv->audio.lpe.irq < 0) { + dev_priv->display.audio.lpe.irq = irq_alloc_desc(0); + if (dev_priv->display.audio.lpe.irq < 0) { drm_err(&dev_priv->drm, "Failed to allocate IRQ desc: %d\n", - dev_priv->audio.lpe.irq); - ret = dev_priv->audio.lpe.irq; + dev_priv->display.audio.lpe.irq); + ret = dev_priv->display.audio.lpe.irq; goto err; } - drm_dbg(&dev_priv->drm, "irq = %d\n", dev_priv->audio.lpe.irq); + drm_dbg(&dev_priv->drm, "irq = %d\n", dev_priv->display.audio.lpe.irq); ret = lpe_audio_irq_init(dev_priv); @@ -223,10 +224,10 @@ static int lpe_audio_setup(struct drm_i915_private *dev_priv) goto err_free_irq; } - dev_priv->audio.lpe.platdev = lpe_audio_platdev_create(dev_priv); + dev_priv->display.audio.lpe.platdev = lpe_audio_platdev_create(dev_priv); - if (IS_ERR(dev_priv->audio.lpe.platdev)) { - ret = PTR_ERR(dev_priv->audio.lpe.platdev); + if (IS_ERR(dev_priv->display.audio.lpe.platdev)) { + ret = PTR_ERR(dev_priv->display.audio.lpe.platdev); drm_err(&dev_priv->drm, "Failed to create lpe audio platform device: %d\n", ret); @@ -241,10 +242,10 @@ static int lpe_audio_setup(struct drm_i915_private *dev_priv) return 0; err_free_irq: - irq_free_desc(dev_priv->audio.lpe.irq); + irq_free_desc(dev_priv->display.audio.lpe.irq); err: - dev_priv->audio.lpe.irq = -1; - dev_priv->audio.lpe.platdev = NULL; + dev_priv->display.audio.lpe.irq = -1; + dev_priv->display.audio.lpe.platdev = NULL; return ret; } @@ -262,7 +263,7 @@ void intel_lpe_audio_irq_handler(struct drm_i915_private *dev_priv) if (!HAS_LPE_AUDIO(dev_priv)) return; - ret = generic_handle_irq(dev_priv->audio.lpe.irq); + ret = generic_handle_irq(dev_priv->display.audio.lpe.irq); if (ret) drm_err_ratelimited(&dev_priv->drm, "error handling LPE audio irq: %d\n", ret); @@ -303,10 +304,10 @@ void intel_lpe_audio_teardown(struct drm_i915_private *dev_priv) lpe_audio_platdev_destroy(dev_priv); - irq_free_desc(dev_priv->audio.lpe.irq); + irq_free_desc(dev_priv->display.audio.lpe.irq); - dev_priv->audio.lpe.irq = -1; - dev_priv->audio.lpe.platdev = NULL; + dev_priv->display.audio.lpe.irq = -1; + dev_priv->display.audio.lpe.platdev = NULL; } /** @@ -333,7 +334,7 @@ void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, if (!HAS_LPE_AUDIO(dev_priv)) return; - pdata = dev_get_platdata(&dev_priv->audio.lpe.platdev->dev); + pdata = dev_get_platdata(&dev_priv->display.audio.lpe.platdev->dev); ppdata = &pdata->port[port - PORT_B]; spin_lock_irqsave(&pdata->lpe_audio_slock, irqflags); @@ -361,7 +362,7 @@ void intel_lpe_audio_notify(struct drm_i915_private *dev_priv, } if (pdata->notify_audio_lpe) - pdata->notify_audio_lpe(dev_priv->audio.lpe.platdev, port - PORT_B); + pdata->notify_audio_lpe(dev_priv->display.audio.lpe.platdev, port - PORT_B); spin_unlock_irqrestore(&pdata->lpe_audio_slock, irqflags); } diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 730480ac3300..9aa38e8141b5 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -837,12 +837,12 @@ void intel_lvds_init(struct drm_i915_private *dev_priv) /* Skip init on machines we know falsely report LVDS */ if (dmi_check_system(intel_no_lvds)) { - drm_WARN(dev, !dev_priv->vbt.int_lvds_support, + drm_WARN(dev, !dev_priv->display.vbt.int_lvds_support, "Useless DMI match. Internal LVDS support disabled by VBT\n"); return; } - if (!dev_priv->vbt.int_lvds_support) { + if (!dev_priv->display.vbt.int_lvds_support) { drm_dbg_kms(&dev_priv->drm, "Internal LVDS support disabled by VBT\n"); return; diff --git a/drivers/gpu/drm/i915/display/intel_modeset_setup.c b/drivers/gpu/drm/i915/display/intel_modeset_setup.c index f0e04d3904c6..cbfabd58b75a 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_setup.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_setup.c @@ -23,6 +23,7 @@ #include "intel_modeset_setup.h" #include "intel_pch_display.h" #include "intel_pm.h" +#include "skl_watermark.h" static void intel_crtc_disable_noatomic(struct intel_crtc *crtc, struct drm_modeset_acquire_ctx *ctx) @@ -30,11 +31,11 @@ static void intel_crtc_disable_noatomic(struct intel_crtc *crtc, struct intel_encoder *encoder; struct drm_i915_private *i915 = to_i915(crtc->base.dev); struct intel_bw_state *bw_state = - to_intel_bw_state(i915->bw_obj.state); + to_intel_bw_state(i915->display.bw.obj.state); struct intel_cdclk_state *cdclk_state = - to_intel_cdclk_state(i915->cdclk.obj.state); + to_intel_cdclk_state(i915->display.cdclk.obj.state); struct intel_dbuf_state *dbuf_state = - to_intel_dbuf_state(i915->dbuf.obj.state); + to_intel_dbuf_state(i915->display.dbuf.obj.state); struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct intel_plane *plane; @@ -70,7 +71,7 @@ static void intel_crtc_disable_noatomic(struct intel_crtc *crtc, drm_WARN_ON(&i915->drm, IS_ERR(temp_crtc_state) || ret); - i915->display->crtc_disable(to_intel_atomic_state(state), crtc); + i915->display.funcs.display->crtc_disable(to_intel_atomic_state(state), crtc); drm_atomic_state_put(state); @@ -415,9 +416,9 @@ static void readout_plane_state(struct drm_i915_private *i915) static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) { struct intel_cdclk_state *cdclk_state = - to_intel_cdclk_state(i915->cdclk.obj.state); + to_intel_cdclk_state(i915->display.cdclk.obj.state); struct intel_dbuf_state *dbuf_state = - to_intel_dbuf_state(i915->dbuf.obj.state); + to_intel_dbuf_state(i915->display.dbuf.obj.state); enum pipe pipe; struct intel_crtc *crtc; struct intel_encoder *encoder; @@ -535,7 +536,7 @@ static void intel_modeset_readout_hw_state(struct drm_i915_private *i915) for_each_intel_crtc(&i915->drm, crtc) { struct intel_bw_state *bw_state = - to_intel_bw_state(i915->bw_obj.state); + to_intel_bw_state(i915->display.bw.obj.state); struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct intel_plane *plane; diff --git a/drivers/gpu/drm/i915/display/intel_modeset_verify.c b/drivers/gpu/drm/i915/display/intel_modeset_verify.c index a91586d77cb6..0fdcf2e6d57f 100644 --- a/drivers/gpu/drm/i915/display/intel_modeset_verify.c +++ b/drivers/gpu/drm/i915/display/intel_modeset_verify.c @@ -15,8 +15,8 @@ #include "intel_display_types.h" #include "intel_fdi.h" #include "intel_modeset_verify.h" -#include "intel_pm.h" #include "intel_snps_phy.h" +#include "skl_watermark.h" /* * Cross check the actual hw state with our own modeset state tracking (and its @@ -94,10 +94,10 @@ static void intel_pipe_config_sanity_check(struct drm_i915_private *dev_priv, /* * FDI already provided one idea for the dotclock. - * Yell if the encoder disagrees. + * Yell if the encoder disagrees. Allow for slight + * rounding differences. */ - drm_WARN(&dev_priv->drm, - !intel_fuzzy_clock_check(fdi_dotclock, dotclock), + drm_WARN(&dev_priv->drm, abs(fdi_dotclock - dotclock) > 1, "FDI dotclock and encoder dotclock mismatch, fdi: %i, encoder: %i\n", fdi_dotclock, dotclock); } diff --git a/drivers/gpu/drm/i915/display/intel_opregion.c b/drivers/gpu/drm/i915/display/intel_opregion.c index 1c0c745c142d..caa07ef34f21 100644 --- a/drivers/gpu/drm/i915/display/intel_opregion.c +++ b/drivers/gpu/drm/i915/display/intel_opregion.c @@ -252,7 +252,7 @@ struct opregion_asle_ext { static int check_swsci_function(struct drm_i915_private *i915, u32 function) { - struct opregion_swsci *swsci = i915->opregion.swsci; + struct opregion_swsci *swsci = i915->display.opregion.swsci; u32 main_function, sub_function; if (!swsci) @@ -265,11 +265,11 @@ static int check_swsci_function(struct drm_i915_private *i915, u32 function) /* Check if we can call the function. See swsci_setup for details. */ if (main_function == SWSCI_SBCB) { - if ((i915->opregion.swsci_sbcb_sub_functions & + if ((i915->display.opregion.swsci_sbcb_sub_functions & (1 << sub_function)) == 0) return -EINVAL; } else if (main_function == SWSCI_GBDA) { - if ((i915->opregion.swsci_gbda_sub_functions & + if ((i915->display.opregion.swsci_gbda_sub_functions & (1 << sub_function)) == 0) return -EINVAL; } @@ -280,7 +280,7 @@ static int check_swsci_function(struct drm_i915_private *i915, u32 function) static int swsci(struct drm_i915_private *dev_priv, u32 function, u32 parm, u32 *parm_out) { - struct opregion_swsci *swsci = dev_priv->opregion.swsci; + struct opregion_swsci *swsci = dev_priv->display.opregion.swsci; struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); u32 scic, dslp; u16 swsci_val; @@ -462,7 +462,7 @@ static u32 asle_set_backlight(struct drm_i915_private *dev_priv, u32 bclp) { struct intel_connector *connector; struct drm_connector_list_iter conn_iter; - struct opregion_asle *asle = dev_priv->opregion.asle; + struct opregion_asle *asle = dev_priv->display.opregion.asle; struct drm_device *dev = &dev_priv->drm; drm_dbg(&dev_priv->drm, "bclp = 0x%08x\n", bclp); @@ -586,8 +586,8 @@ static void asle_work(struct work_struct *work) struct intel_opregion *opregion = container_of(work, struct intel_opregion, asle_work); struct drm_i915_private *dev_priv = - container_of(opregion, struct drm_i915_private, opregion); - struct opregion_asle *asle = dev_priv->opregion.asle; + container_of(opregion, struct drm_i915_private, display.opregion); + struct opregion_asle *asle = dev_priv->display.opregion.asle; u32 aslc_stat = 0; u32 aslc_req; @@ -635,8 +635,8 @@ static void asle_work(struct work_struct *work) void intel_opregion_asle_intr(struct drm_i915_private *dev_priv) { - if (dev_priv->opregion.asle) - schedule_work(&dev_priv->opregion.asle_work); + if (dev_priv->display.opregion.asle) + schedule_work(&dev_priv->display.opregion.asle_work); } #define ACPI_EV_DISPLAY_SWITCH (1<<0) @@ -692,7 +692,7 @@ static void set_did(struct intel_opregion *opregion, int i, u32 val) static void intel_didl_outputs(struct drm_i915_private *dev_priv) { - struct intel_opregion *opregion = &dev_priv->opregion; + struct intel_opregion *opregion = &dev_priv->display.opregion; struct intel_connector *connector; struct drm_connector_list_iter conn_iter; int i = 0, max_outputs; @@ -731,7 +731,7 @@ static void intel_didl_outputs(struct drm_i915_private *dev_priv) static void intel_setup_cadls(struct drm_i915_private *dev_priv) { - struct intel_opregion *opregion = &dev_priv->opregion; + struct intel_opregion *opregion = &dev_priv->display.opregion; struct intel_connector *connector; struct drm_connector_list_iter conn_iter; int i = 0; @@ -761,7 +761,7 @@ static void intel_setup_cadls(struct drm_i915_private *dev_priv) static void swsci_setup(struct drm_i915_private *dev_priv) { - struct intel_opregion *opregion = &dev_priv->opregion; + struct intel_opregion *opregion = &dev_priv->display.opregion; bool requested_callbacks = false; u32 tmp; @@ -839,7 +839,7 @@ static const struct dmi_system_id intel_no_opregion_vbt[] = { static int intel_load_vbt_firmware(struct drm_i915_private *dev_priv) { - struct intel_opregion *opregion = &dev_priv->opregion; + struct intel_opregion *opregion = &dev_priv->display.opregion; const struct firmware *fw = NULL; const char *name = dev_priv->params.vbt_firmware; int ret; @@ -879,7 +879,7 @@ static int intel_load_vbt_firmware(struct drm_i915_private *dev_priv) int intel_opregion_setup(struct drm_i915_private *dev_priv) { - struct intel_opregion *opregion = &dev_priv->opregion; + struct intel_opregion *opregion = &dev_priv->display.opregion; struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); u32 asls, mboxes; char buf[sizeof(OPREGION_SIGNATURE)]; @@ -1106,7 +1106,7 @@ struct edid *intel_opregion_get_edid(struct intel_connector *intel_connector) { struct drm_connector *connector = &intel_connector->base; struct drm_i915_private *i915 = to_i915(connector->dev); - struct intel_opregion *opregion = &i915->opregion; + struct intel_opregion *opregion = &i915->display.opregion; const void *in_edid; const struct edid *edid; struct edid *new_edid; @@ -1141,7 +1141,7 @@ struct edid *intel_opregion_get_edid(struct intel_connector *intel_connector) bool intel_opregion_headless_sku(struct drm_i915_private *i915) { - struct intel_opregion *opregion = &i915->opregion; + struct intel_opregion *opregion = &i915->display.opregion; struct opregion_header *header = opregion->header; if (!header || header->over.major < 2 || @@ -1153,7 +1153,7 @@ bool intel_opregion_headless_sku(struct drm_i915_private *i915) void intel_opregion_register(struct drm_i915_private *i915) { - struct intel_opregion *opregion = &i915->opregion; + struct intel_opregion *opregion = &i915->display.opregion; if (!opregion->header) return; @@ -1169,7 +1169,7 @@ void intel_opregion_register(struct drm_i915_private *i915) void intel_opregion_resume(struct drm_i915_private *i915) { - struct intel_opregion *opregion = &i915->opregion; + struct intel_opregion *opregion = &i915->display.opregion; if (!opregion->header) return; @@ -1200,7 +1200,7 @@ void intel_opregion_resume(struct drm_i915_private *i915) void intel_opregion_suspend(struct drm_i915_private *i915, pci_power_t state) { - struct intel_opregion *opregion = &i915->opregion; + struct intel_opregion *opregion = &i915->display.opregion; if (!opregion->header) return; @@ -1210,7 +1210,7 @@ void intel_opregion_suspend(struct drm_i915_private *i915, pci_power_t state) if (opregion->asle) opregion->asle->ardy = ASLE_ARDY_NOT_READY; - cancel_work_sync(&i915->opregion.asle_work); + cancel_work_sync(&i915->display.opregion.asle_work); if (opregion->acpi) opregion->acpi->drdy = 0; @@ -1218,7 +1218,7 @@ void intel_opregion_suspend(struct drm_i915_private *i915, pci_power_t state) void intel_opregion_unregister(struct drm_i915_private *i915) { - struct intel_opregion *opregion = &i915->opregion; + struct intel_opregion *opregion = &i915->display.opregion; intel_opregion_suspend(i915, PCI_D1); diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c index 79ed8bd04a07..c12bdca8da9b 100644 --- a/drivers/gpu/drm/i915/display/intel_overlay.c +++ b/drivers/gpu/drm/i915/display/intel_overlay.c @@ -211,9 +211,9 @@ static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv, /* WA_OVERLAY_CLKGATE:alm */ if (enable) - intel_de_write(dev_priv, DSPCLK_GATE_D, 0); + intel_de_write(dev_priv, DSPCLK_GATE_D(dev_priv), 0); else - intel_de_write(dev_priv, DSPCLK_GATE_D, + intel_de_write(dev_priv, DSPCLK_GATE_D(dev_priv), OVRUNIT_CLOCK_GATE_DISABLE); /* WA_DISABLE_L2CACHE_CLOCK_GATING:alm */ @@ -487,7 +487,7 @@ static int intel_overlay_release_old_vid(struct intel_overlay *overlay) void intel_overlay_reset(struct drm_i915_private *dev_priv) { - struct intel_overlay *overlay = dev_priv->overlay; + struct intel_overlay *overlay = dev_priv->display.overlay; if (!overlay) return; @@ -1113,7 +1113,7 @@ int intel_overlay_put_image_ioctl(struct drm_device *dev, void *data, struct drm_i915_gem_object *new_bo; int ret; - overlay = dev_priv->overlay; + overlay = dev_priv->display.overlay; if (!overlay) { drm_dbg(&dev_priv->drm, "userspace bug: no overlay\n"); return -ENODEV; @@ -1273,7 +1273,7 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, struct intel_overlay *overlay; int ret; - overlay = dev_priv->overlay; + overlay = dev_priv->display.overlay; if (!overlay) { drm_dbg(&dev_priv->drm, "userspace bug: no overlay\n"); return -ENODEV; @@ -1416,7 +1416,7 @@ void intel_overlay_setup(struct drm_i915_private *dev_priv) update_polyphase_filter(overlay->regs); update_reg_attrs(overlay, overlay->regs); - dev_priv->overlay = overlay; + dev_priv->display.overlay = overlay; drm_info(&dev_priv->drm, "Initialized overlay support.\n"); return; @@ -1428,7 +1428,7 @@ void intel_overlay_cleanup(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay; - overlay = fetch_and_zero(&dev_priv->overlay); + overlay = fetch_and_zero(&dev_priv->display.overlay); if (!overlay) return; @@ -1457,7 +1457,7 @@ struct intel_overlay_error_state { struct intel_overlay_error_state * intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) { - struct intel_overlay *overlay = dev_priv->overlay; + struct intel_overlay *overlay = dev_priv->display.overlay; struct intel_overlay_error_state *error; if (!overlay || !overlay->active) diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c index 237a40623dd7..a3a3f9fe4342 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.c +++ b/drivers/gpu/drm/i915/display/intel_panel.c @@ -37,13 +37,14 @@ #include "intel_display_types.h" #include "intel_drrs.h" #include "intel_panel.h" +#include "intel_quirks.h" bool intel_panel_use_ssc(struct drm_i915_private *i915) { if (i915->params.panel_use_ssc >= 0) return i915->params.panel_use_ssc != 0; - return i915->vbt.lvds_use_ssc - && !(i915->quirks & QUIRK_LVDS_SSC_DISABLE); + return i915->display.vbt.lvds_use_ssc && + !intel_has_quirk(i915, QUIRK_LVDS_SSC_DISABLE); } const struct drm_display_mode * @@ -81,15 +82,14 @@ static bool is_alt_drrs_mode(const struct drm_display_mode *mode, mode->clock != preferred_mode->clock; } -static bool is_alt_vrr_mode(const struct drm_display_mode *mode, - const struct drm_display_mode *preferred_mode) +static bool is_alt_fixed_mode(const struct drm_display_mode *mode, + const struct drm_display_mode *preferred_mode) { return drm_mode_match(mode, preferred_mode, DRM_MODE_MATCH_FLAGS | DRM_MODE_MATCH_3D_FLAGS) && mode->hdisplay == preferred_mode->hdisplay && - mode->vdisplay == preferred_mode->vdisplay && - mode->clock != preferred_mode->clock; + mode->vdisplay == preferred_mode->vdisplay; } const struct drm_display_mode * @@ -114,6 +114,21 @@ intel_panel_downclock_mode(struct intel_connector *connector, return best_mode; } +const struct drm_display_mode * +intel_panel_highest_mode(struct intel_connector *connector, + const struct drm_display_mode *adjusted_mode) +{ + const struct drm_display_mode *fixed_mode, *best_mode = adjusted_mode; + + /* pick the fixed_mode that has the highest clock */ + list_for_each_entry(fixed_mode, &connector->panel.fixed_modes, head) { + if (fixed_mode->clock > best_mode->clock) + best_mode = fixed_mode; + } + + return best_mode; +} + int intel_panel_get_modes(struct intel_connector *connector) { const struct drm_display_mode *fixed_mode; @@ -172,19 +187,7 @@ int intel_panel_compute_config(struct intel_connector *connector, return 0; } -static bool is_alt_fixed_mode(const struct drm_display_mode *mode, - const struct drm_display_mode *preferred_mode, - bool has_vrr) -{ - /* is_alt_drrs_mode() is a subset of is_alt_vrr_mode() */ - if (has_vrr) - return is_alt_vrr_mode(mode, preferred_mode); - else - return is_alt_drrs_mode(mode, preferred_mode); -} - -static void intel_panel_add_edid_alt_fixed_modes(struct intel_connector *connector, - bool has_vrr) +static void intel_panel_add_edid_alt_fixed_modes(struct intel_connector *connector) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); const struct drm_display_mode *preferred_mode = @@ -192,7 +195,7 @@ static void intel_panel_add_edid_alt_fixed_modes(struct intel_connector *connect struct drm_display_mode *mode, *next; list_for_each_entry_safe(mode, next, &connector->base.probed_modes, head) { - if (!is_alt_fixed_mode(mode, preferred_mode, has_vrr)) + if (!is_alt_fixed_mode(mode, preferred_mode)) continue; drm_dbg_kms(&dev_priv->drm, @@ -255,7 +258,7 @@ void intel_panel_add_edid_fixed_modes(struct intel_connector *connector, { intel_panel_add_edid_preferred_mode(connector); if (intel_panel_preferred_fixed_mode(connector) && (has_drrs || has_vrr)) - intel_panel_add_edid_alt_fixed_modes(connector, has_vrr); + intel_panel_add_edid_alt_fixed_modes(connector); intel_panel_destroy_probed_modes(connector); } diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h index b087c0c3cc6d..eff3ffd3d082 100644 --- a/drivers/gpu/drm/i915/display/intel_panel.h +++ b/drivers/gpu/drm/i915/display/intel_panel.h @@ -31,6 +31,9 @@ intel_panel_fixed_mode(struct intel_connector *connector, const struct drm_display_mode * intel_panel_downclock_mode(struct intel_connector *connector, const struct drm_display_mode *adjusted_mode); +const struct drm_display_mode * +intel_panel_highest_mode(struct intel_connector *connector, + const struct drm_display_mode *adjusted_mode); int intel_panel_get_modes(struct intel_connector *connector); enum drrs_type intel_panel_drrs_type(struct intel_connector *connector); enum drm_mode_status diff --git a/drivers/gpu/drm/i915/display/intel_pch_refclk.c b/drivers/gpu/drm/i915/display/intel_pch_refclk.c index 9934c8a9e240..a66097cdc1e0 100644 --- a/drivers/gpu/drm/i915/display/intel_pch_refclk.c +++ b/drivers/gpu/drm/i915/display/intel_pch_refclk.c @@ -167,6 +167,15 @@ static void lpt_compute_iclkip(struct iclkip_params *p, int clock) } } +int lpt_iclkip(const struct intel_crtc_state *crtc_state) +{ + struct iclkip_params p; + + lpt_compute_iclkip(&p, crtc_state->hw.adjusted_mode.crtc_clock); + + return lpt_iclkip_freq(&p); +} + /* Program iCLKIP clock to the desired frequency */ void lpt_program_iclkip(const struct intel_crtc_state *crtc_state) { @@ -179,6 +188,7 @@ void lpt_program_iclkip(const struct intel_crtc_state *crtc_state) lpt_disable_iclkip(dev_priv); lpt_compute_iclkip(&p, clock); + drm_WARN_ON(&dev_priv->drm, lpt_iclkip_freq(&p) != clock); /* This should not happen with any sane values */ drm_WARN_ON(&dev_priv->drm, SBI_SSCDIVINTPHASE_DIVSEL(p.divsel) & @@ -514,7 +524,7 @@ static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv) } if (HAS_PCH_IBX(dev_priv)) { - has_ck505 = dev_priv->vbt.display_clock_mode; + has_ck505 = dev_priv->display.vbt.display_clock_mode; can_ssc = has_ck505; } else { has_ck505 = false; @@ -522,7 +532,7 @@ static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv) } /* Check if any DPLLs are using the SSC source */ - for (i = 0; i < dev_priv->dpll.num_shared_dpll; i++) { + for (i = 0; i < dev_priv->display.dpll.num_shared_dpll; i++) { u32 temp = intel_de_read(dev_priv, PCH_DPLL(i)); if (!(temp & DPLL_VCO_ENABLE)) @@ -654,7 +664,7 @@ static void ilk_init_pch_refclk(struct drm_i915_private *dev_priv) } } - BUG_ON(val != final); + drm_WARN_ON(&dev_priv->drm, val != final); } /* diff --git a/drivers/gpu/drm/i915/display/intel_pch_refclk.h b/drivers/gpu/drm/i915/display/intel_pch_refclk.h index 12ab2c75a800..9bcf56629f24 100644 --- a/drivers/gpu/drm/i915/display/intel_pch_refclk.h +++ b/drivers/gpu/drm/i915/display/intel_pch_refclk.h @@ -14,6 +14,7 @@ struct intel_crtc_state; void lpt_program_iclkip(const struct intel_crtc_state *crtc_state); void lpt_disable_iclkip(struct drm_i915_private *dev_priv); int lpt_get_iclkip(struct drm_i915_private *dev_priv); +int lpt_iclkip(const struct intel_crtc_state *crtc_state); void intel_init_pch_refclk(struct drm_i915_private *dev_priv); void lpt_disable_clkout_dp(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/display/intel_plane_initial.c b/drivers/gpu/drm/i915/display/intel_plane_initial.c index d10f27d0b7b0..76be796df255 100644 --- a/drivers/gpu/drm/i915/display/intel_plane_initial.c +++ b/drivers/gpu/drm/i915/display/intel_plane_initial.c @@ -311,7 +311,7 @@ void intel_crtc_initial_plane_config(struct intel_crtc *crtc) * can even allow for smooth boot transitions if the BIOS * fb is large enough for the active pipe configuration. */ - dev_priv->display->get_initial_plane_config(crtc, &plane_config); + dev_priv->display.funcs.display->get_initial_plane_config(crtc, &plane_config); /* * If the fb is shared between multiple heads, we'll diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c index 1b21a341962f..21944f5bf3a8 100644 --- a/drivers/gpu/drm/i915/display/intel_pps.c +++ b/drivers/gpu/drm/i915/display/intel_pps.c @@ -12,6 +12,7 @@ #include "intel_dpll.h" #include "intel_lvds.h" #include "intel_pps.h" +#include "intel_quirks.h" static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv, enum pipe pipe); @@ -28,7 +29,7 @@ intel_wakeref_t intel_pps_lock(struct intel_dp *intel_dp) * See intel_pps_reset_all() why we need a power domain reference here. */ wakeref = intel_display_power_get(dev_priv, POWER_DOMAIN_DISPLAY_CORE); - mutex_lock(&dev_priv->pps_mutex); + mutex_lock(&dev_priv->display.pps.mutex); return wakeref; } @@ -38,7 +39,7 @@ intel_wakeref_t intel_pps_unlock(struct intel_dp *intel_dp, { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - mutex_unlock(&dev_priv->pps_mutex); + mutex_unlock(&dev_priv->display.pps.mutex); intel_display_power_put(dev_priv, POWER_DOMAIN_DISPLAY_CORE, wakeref); return 0; @@ -163,7 +164,7 @@ vlv_power_sequencer_pipe(struct intel_dp *intel_dp) struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); enum pipe pipe; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); /* We should never land here with regular DP ports */ drm_WARN_ON(&dev_priv->drm, !intel_dp_is_edp(intel_dp)); @@ -212,7 +213,7 @@ bxt_power_sequencer_idx(struct intel_dp *intel_dp) struct intel_connector *connector = intel_dp->attached_connector; int backlight_controller = connector->panel.vbt.backlight.controller; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); /* We should never land here with regular DP ports */ drm_WARN_ON(&dev_priv->drm, !intel_dp_is_edp(intel_dp)); @@ -282,7 +283,7 @@ vlv_initial_power_sequencer_setup(struct intel_dp *intel_dp) struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); enum port port = dig_port->base.port; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); /* try to find a pipe with this port selected */ /* first pick one where the panel is on */ @@ -407,7 +408,7 @@ static bool edp_have_panel_power(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && intel_dp->pps.pps_pipe == INVALID_PIPE) @@ -420,7 +421,7 @@ static bool edp_have_panel_vdd(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) && intel_dp->pps.pps_pipe == INVALID_PIPE) @@ -463,7 +464,7 @@ static void wait_panel_status(struct intel_dp *intel_dp, struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); i915_reg_t pp_stat_reg, pp_ctrl_reg; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); intel_pps_verify_state(intel_dp); @@ -556,7 +557,7 @@ static u32 ilk_get_pp_control(struct intel_dp *intel_dp) struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); u32 control; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); control = intel_de_read(dev_priv, _pp_ctrl_reg(intel_dp)); if (drm_WARN_ON(&dev_priv->drm, !HAS_DDI(dev_priv) && @@ -580,7 +581,7 @@ bool intel_pps_vdd_on_unlocked(struct intel_dp *intel_dp) i915_reg_t pp_stat_reg, pp_ctrl_reg; bool need_to_disable = !intel_dp->pps.want_panel_vdd; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if (!intel_dp_is_edp(intel_dp)) return false; @@ -657,7 +658,7 @@ static void intel_pps_vdd_off_sync_unlocked(struct intel_dp *intel_dp) u32 pp; i915_reg_t pp_stat_reg, pp_ctrl_reg; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); drm_WARN_ON(&dev_priv->drm, intel_dp->pps.want_panel_vdd); @@ -748,7 +749,7 @@ void intel_pps_vdd_off_unlocked(struct intel_dp *intel_dp, bool sync) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if (!intel_dp_is_edp(intel_dp)) return; @@ -771,7 +772,7 @@ void intel_pps_on_unlocked(struct intel_dp *intel_dp) u32 pp; i915_reg_t pp_ctrl_reg; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if (!intel_dp_is_edp(intel_dp)) return; @@ -832,7 +833,7 @@ void intel_pps_off_unlocked(struct intel_dp *intel_dp) u32 pp; i915_reg_t pp_ctrl_reg; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if (!intel_dp_is_edp(intel_dp)) return; @@ -991,7 +992,7 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv, { struct intel_encoder *encoder; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); for_each_intel_dp(&dev_priv->drm, encoder) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); @@ -1021,7 +1022,7 @@ void vlv_pps_init(struct intel_encoder *encoder, struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); drm_WARN_ON(&dev_priv->drm, intel_dp->pps.active_pipe != INVALID_PIPE); @@ -1064,7 +1065,7 @@ static void pps_vdd_init(struct intel_dp *intel_dp) struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if (!edp_have_panel_vdd(intel_dp)) return; @@ -1176,7 +1177,7 @@ static void pps_init_delays_bios(struct intel_dp *intel_dp, { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); if (!pps_delays_valid(&intel_dp->pps.bios_pps_delays)) intel_pps_readout_hw_state(intel_dp, &intel_dp->pps.bios_pps_delays); @@ -1202,7 +1203,7 @@ static void pps_init_delays_vbt(struct intel_dp *intel_dp, * just fails to power back on. Increasing the delay to 800ms * seems sufficient to avoid this problem. */ - if (dev_priv->quirks & QUIRK_INCREASE_T12_DELAY) { + if (intel_has_quirk(dev_priv, QUIRK_INCREASE_T12_DELAY)) { vbt->t11_t12 = max_t(u16, vbt->t11_t12, 1300 * 10); drm_dbg_kms(&dev_priv->drm, "Increasing T12 panel delay as per the quirk to %d\n", @@ -1223,7 +1224,7 @@ static void pps_init_delays_spec(struct intel_dp *intel_dp, { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); /* Upper limits from eDP 1.3 spec. Note that we use the clunky units of * our hw here, which are all in 100usec. */ @@ -1246,7 +1247,7 @@ static void pps_init_delays(struct intel_dp *intel_dp) struct edp_power_seq cur, vbt, spec, *final = &intel_dp->pps.pps_delays; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); /* already initialized? */ if (pps_delays_valid(final)) @@ -1312,7 +1313,7 @@ static void pps_init_registers(struct intel_dp *intel_dp, bool force_disable_vdd enum port port = dp_to_dig_port(intel_dp)->base.port; const struct edp_power_seq *seq = &intel_dp->pps.pps_delays; - lockdep_assert_held(&dev_priv->pps_mutex); + lockdep_assert_held(&dev_priv->display.pps.mutex); intel_pps_get_registers(intel_dp, ®s); @@ -1487,11 +1488,11 @@ void intel_pps_unlock_regs_wa(struct drm_i915_private *dev_priv) void intel_pps_setup(struct drm_i915_private *i915) { if (HAS_PCH_SPLIT(i915) || IS_GEMINILAKE(i915) || IS_BROXTON(i915)) - i915->pps_mmio_base = PCH_PPS_BASE; + i915->display.pps.mmio_base = PCH_PPS_BASE; else if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) - i915->pps_mmio_base = VLV_PPS_BASE; + i915->display.pps.mmio_base = VLV_PPS_BASE; else - i915->pps_mmio_base = PPS_BASE; + i915->display.pps.mmio_base = PPS_BASE; } void assert_pps_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe) diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index e6a870641cd2..d4cce627d7a8 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -116,34 +116,56 @@ static bool psr2_global_enabled(struct intel_dp *intel_dp) } } +static u32 psr_irq_psr_error_bit_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_ERROR : + EDP_PSR_ERROR(intel_dp->psr.transcoder); +} + +static u32 psr_irq_post_exit_bit_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_POST_EXIT : + EDP_PSR_POST_EXIT(intel_dp->psr.transcoder); +} + +static u32 psr_irq_pre_entry_bit_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_PRE_ENTRY : + EDP_PSR_PRE_ENTRY(intel_dp->psr.transcoder); +} + +static u32 psr_irq_mask_get(struct intel_dp *intel_dp) +{ + struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); + + return DISPLAY_VER(dev_priv) >= 12 ? TGL_PSR_MASK : + EDP_PSR_MASK(intel_dp->psr.transcoder); +} + static void psr_irq_control(struct intel_dp *intel_dp) { struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); - enum transcoder trans_shift; i915_reg_t imr_reg; u32 mask, val; - /* - * gen12+ has registers relative to transcoder and one per transcoder - * using the same bit definition: handle it as TRANSCODER_EDP to force - * 0 shift in bit definition - */ - if (DISPLAY_VER(dev_priv) >= 12) { - trans_shift = 0; + if (DISPLAY_VER(dev_priv) >= 12) imr_reg = TRANS_PSR_IMR(intel_dp->psr.transcoder); - } else { - trans_shift = intel_dp->psr.transcoder; + else imr_reg = EDP_PSR_IMR; - } - mask = EDP_PSR_ERROR(trans_shift); + mask = psr_irq_psr_error_bit_get(intel_dp); if (intel_dp->psr.debug & I915_PSR_DEBUG_IRQ) - mask |= EDP_PSR_POST_EXIT(trans_shift) | - EDP_PSR_PRE_ENTRY(trans_shift); + mask |= psr_irq_post_exit_bit_get(intel_dp) | + psr_irq_pre_entry_bit_get(intel_dp); - /* Warning: it is masking/setting reserved bits too */ val = intel_de_read(dev_priv, imr_reg); - val &= ~EDP_PSR_TRANS_MASK(trans_shift); + val &= ~psr_irq_mask_get(intel_dp); val |= ~mask; intel_de_write(dev_priv, imr_reg, val); } @@ -191,25 +213,21 @@ void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir) enum transcoder cpu_transcoder = intel_dp->psr.transcoder; struct drm_i915_private *dev_priv = dp_to_i915(intel_dp); ktime_t time_ns = ktime_get(); - enum transcoder trans_shift; i915_reg_t imr_reg; - if (DISPLAY_VER(dev_priv) >= 12) { - trans_shift = 0; + if (DISPLAY_VER(dev_priv) >= 12) imr_reg = TRANS_PSR_IMR(intel_dp->psr.transcoder); - } else { - trans_shift = intel_dp->psr.transcoder; + else imr_reg = EDP_PSR_IMR; - } - if (psr_iir & EDP_PSR_PRE_ENTRY(trans_shift)) { + if (psr_iir & psr_irq_pre_entry_bit_get(intel_dp)) { intel_dp->psr.last_entry_attempt = time_ns; drm_dbg_kms(&dev_priv->drm, "[transcoder %s] PSR entry attempt in 2 vblanks\n", transcoder_name(cpu_transcoder)); } - if (psr_iir & EDP_PSR_POST_EXIT(trans_shift)) { + if (psr_iir & psr_irq_post_exit_bit_get(intel_dp)) { intel_dp->psr.last_exit = time_ns; drm_dbg_kms(&dev_priv->drm, "[transcoder %s] PSR exit completed\n", @@ -226,7 +244,7 @@ void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir) } } - if (psr_iir & EDP_PSR_ERROR(trans_shift)) { + if (psr_iir & psr_irq_psr_error_bit_get(intel_dp)) { u32 val; drm_warn(&dev_priv->drm, "[transcoder %s] PSR aux error\n", @@ -243,7 +261,7 @@ void intel_psr_irq_handler(struct intel_dp *intel_dp, u32 psr_iir) * or unset irq_aux_error. */ val = intel_de_read(dev_priv, imr_reg); - val |= EDP_PSR_ERROR(trans_shift); + val |= psr_irq_psr_error_bit_get(intel_dp); intel_de_write(dev_priv, imr_reg, val); schedule_work(&intel_dp->psr.work); @@ -706,7 +724,7 @@ tgl_dc3co_exitline_compute_config(struct intel_dp *intel_dp, if (crtc_state->enable_psr2_sel_fetch) return; - if (!(dev_priv->dmc.allowed_dc_mask & DC_STATE_EN_DC3CO)) + if (!(dev_priv->display.dmc.allowed_dc_mask & DC_STATE_EN_DC3CO)) return; if (!dc3co_is_pipe_port_compatible(intel_dp, crtc_state)) @@ -805,13 +823,14 @@ static bool _compute_psr2_sdp_prior_scanline_indication(struct intel_dp *intel_d hblank_total = adjusted_mode->crtc_hblank_end - adjusted_mode->crtc_hblank_start; hblank_ns = div_u64(1000000ULL * hblank_total, adjusted_mode->crtc_clock); - /* From spec: (72 / number of lanes) * 1000 / symbol clock frequency MHz */ - req_ns = (72 / crtc_state->lane_count) * 1000 / (crtc_state->port_clock / 1000); + /* From spec: ((60 / number of lanes) + 11) * 1000 / symbol clock frequency MHz */ + req_ns = ((60 / crtc_state->lane_count) + 11) * 1000 / (crtc_state->port_clock / 1000); if ((hblank_ns - req_ns) > 100) return true; - if (DISPLAY_VER(dev_priv) < 13 || intel_dp->edp_dpcd[0] < DP_EDP_14b) + /* Not supported <13 / Wa_22012279113:adl-p */ + if (DISPLAY_VER(dev_priv) <= 13 || intel_dp->edp_dpcd[0] < DP_EDP_14b) return false; crtc_state->req_psr2_sdp_prior_scanline = true; @@ -1193,14 +1212,12 @@ static bool psr_interrupt_error_check(struct intel_dp *intel_dp) * first time that PSR HW tries to activate so lets keep PSR disabled * to avoid any rendering problems. */ - if (DISPLAY_VER(dev_priv) >= 12) { + if (DISPLAY_VER(dev_priv) >= 12) val = intel_de_read(dev_priv, TRANS_PSR_IIR(intel_dp->psr.transcoder)); - val &= EDP_PSR_ERROR(0); - } else { + else val = intel_de_read(dev_priv, EDP_PSR_IIR); - val &= EDP_PSR_ERROR(intel_dp->psr.transcoder); - } + val &= psr_irq_psr_error_bit_get(intel_dp); if (val) { intel_dp->psr.sink_not_reliable = true; drm_dbg_kms(&dev_priv->drm, @@ -1721,8 +1738,6 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, new_plane_state, i) { struct drm_rect src, damaged_area = { .x1 = 0, .y1 = -1, .x2 = INT_MAX }; - struct drm_atomic_helper_damage_iter iter; - struct drm_rect clip; if (new_plane_state->uapi.crtc != crtc_state->uapi.crtc) continue; @@ -1767,22 +1782,18 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state, continue; } - drm_rect_fp_to_int(&src, &new_plane_state->uapi.src); + src = drm_plane_state_src(&new_plane_state->uapi); + drm_rect_fp_to_int(&src, &src); - drm_atomic_helper_damage_iter_init(&iter, - &old_plane_state->uapi, - &new_plane_state->uapi); - drm_atomic_for_each_plane_damage(&iter, &clip) { - if (drm_rect_intersect(&clip, &src)) - clip_area_update(&damaged_area, &clip, - &crtc_state->pipe_src); - } - - if (damaged_area.y1 == -1) + if (!drm_atomic_helper_damage_merged(&old_plane_state->uapi, + &new_plane_state->uapi, &damaged_area)) continue; damaged_area.y1 += new_plane_state->uapi.dst.y1 - src.y1; damaged_area.y2 += new_plane_state->uapi.dst.y1 - src.y1; + damaged_area.x1 += new_plane_state->uapi.dst.x1 - src.x1; + damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1; + clip_area_update(&pipe_clip, &damaged_area, &crtc_state->pipe_src); } @@ -1863,7 +1874,9 @@ void intel_psr_pre_plane_update(struct intel_atomic_state *state, struct intel_crtc *crtc) { struct drm_i915_private *i915 = to_i915(state->base.dev); - const struct intel_crtc_state *crtc_state = + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + const struct intel_crtc_state *new_crtc_state = intel_atomic_get_new_crtc_state(state, crtc); struct intel_encoder *encoder; @@ -1871,7 +1884,7 @@ void intel_psr_pre_plane_update(struct intel_atomic_state *state, return; for_each_intel_encoder_mask_with_psr(state->base.dev, encoder, - crtc_state->uapi.encoder_mask) { + old_crtc_state->uapi.encoder_mask) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); struct intel_psr *psr = &intel_dp->psr; bool needs_to_disable = false; @@ -1884,10 +1897,10 @@ void intel_psr_pre_plane_update(struct intel_atomic_state *state, * - All planes will go inactive * - Changing between PSR versions */ - needs_to_disable |= intel_crtc_needs_modeset(crtc_state); - needs_to_disable |= !crtc_state->has_psr; - needs_to_disable |= !crtc_state->active_planes; - needs_to_disable |= crtc_state->has_psr2 != psr->psr2_enabled; + needs_to_disable |= intel_crtc_needs_modeset(new_crtc_state); + needs_to_disable |= !new_crtc_state->has_psr; + needs_to_disable |= !new_crtc_state->active_planes; + needs_to_disable |= new_crtc_state->has_psr2 != psr->psr2_enabled; if (psr->enabled && needs_to_disable) intel_psr_disable_locked(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c index c8488f5ebd04..6e48d3bcdfec 100644 --- a/drivers/gpu/drm/i915/display/intel_quirks.c +++ b/drivers/gpu/drm/i915/display/intel_quirks.c @@ -9,12 +9,17 @@ #include "intel_display_types.h" #include "intel_quirks.h" +static void intel_set_quirk(struct drm_i915_private *i915, enum intel_quirk_id quirk) +{ + i915->display.quirks.mask |= BIT(quirk); +} + /* * Some machines (Lenovo U160) do not work with SSC on LVDS for some reason */ static void quirk_ssc_force_disable(struct drm_i915_private *i915) { - i915->quirks |= QUIRK_LVDS_SSC_DISABLE; + intel_set_quirk(i915, QUIRK_LVDS_SSC_DISABLE); drm_info(&i915->drm, "applying lvds SSC disable quirk\n"); } @@ -24,14 +29,14 @@ static void quirk_ssc_force_disable(struct drm_i915_private *i915) */ static void quirk_invert_brightness(struct drm_i915_private *i915) { - i915->quirks |= QUIRK_INVERT_BRIGHTNESS; + intel_set_quirk(i915, QUIRK_INVERT_BRIGHTNESS); drm_info(&i915->drm, "applying inverted panel brightness quirk\n"); } /* Some VBT's incorrectly indicate no backlight is present */ static void quirk_backlight_present(struct drm_i915_private *i915) { - i915->quirks |= QUIRK_BACKLIGHT_PRESENT; + intel_set_quirk(i915, QUIRK_BACKLIGHT_PRESENT); drm_info(&i915->drm, "applying backlight present quirk\n"); } @@ -40,7 +45,7 @@ static void quirk_backlight_present(struct drm_i915_private *i915) */ static void quirk_increase_t12_delay(struct drm_i915_private *i915) { - i915->quirks |= QUIRK_INCREASE_T12_DELAY; + intel_set_quirk(i915, QUIRK_INCREASE_T12_DELAY); drm_info(&i915->drm, "Applying T12 delay quirk\n"); } @@ -50,13 +55,13 @@ static void quirk_increase_t12_delay(struct drm_i915_private *i915) */ static void quirk_increase_ddi_disabled_time(struct drm_i915_private *i915) { - i915->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME; + intel_set_quirk(i915, QUIRK_INCREASE_DDI_DISABLED_TIME); drm_info(&i915->drm, "Applying Increase DDI Disabled quirk\n"); } static void quirk_no_pps_backlight_power_hook(struct drm_i915_private *i915) { - i915->quirks |= QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK; + intel_set_quirk(i915, QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK); drm_info(&i915->drm, "Applying no pps backlight power quirk\n"); } @@ -191,6 +196,9 @@ static struct intel_quirk intel_quirks[] = { /* ASRock ITX*/ { 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, { 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time }, + /* ECS Liva Q2 */ + { 0x3185, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time }, + { 0x3184, 0x1019, 0xa94d, quirk_increase_ddi_disabled_time }, }; void intel_init_quirks(struct drm_i915_private *i915) @@ -213,3 +221,8 @@ void intel_init_quirks(struct drm_i915_private *i915) intel_dmi_quirks[i].hook(i915); } } + +bool intel_has_quirk(struct drm_i915_private *i915, enum intel_quirk_id quirk) +{ + return i915->display.quirks.mask & BIT(quirk); +} diff --git a/drivers/gpu/drm/i915/display/intel_quirks.h b/drivers/gpu/drm/i915/display/intel_quirks.h index b0fcff142a56..10a4d163149f 100644 --- a/drivers/gpu/drm/i915/display/intel_quirks.h +++ b/drivers/gpu/drm/i915/display/intel_quirks.h @@ -6,8 +6,20 @@ #ifndef __INTEL_QUIRKS_H__ #define __INTEL_QUIRKS_H__ +#include <linux/types.h> + struct drm_i915_private; -void intel_init_quirks(struct drm_i915_private *dev_priv); +enum intel_quirk_id { + QUIRK_BACKLIGHT_PRESENT, + QUIRK_INCREASE_DDI_DISABLED_TIME, + QUIRK_INCREASE_T12_DELAY, + QUIRK_INVERT_BRIGHTNESS, + QUIRK_LVDS_SSC_DISABLE, + QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK, +}; + +void intel_init_quirks(struct drm_i915_private *i915); +bool intel_has_quirk(struct drm_i915_private *i915, enum intel_quirk_id quirk); #endif /* __INTEL_QUIRKS_H__ */ diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index 19122bc6d2ab..f5b744bef18f 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -2016,7 +2016,7 @@ intel_sdvo_get_analog_edid(struct drm_connector *connector) return drm_get_edid(connector, intel_gmbus_get_adapter(dev_priv, - dev_priv->vbt.crt_ddc_pin)); + dev_priv->display.vbt.crt_ddc_pin)); } static enum drm_connector_status @@ -2581,9 +2581,9 @@ intel_sdvo_select_ddc_bus(struct drm_i915_private *dev_priv, struct sdvo_device_mapping *mapping; if (sdvo->port == PORT_B) - mapping = &dev_priv->vbt.sdvo_mappings[0]; + mapping = &dev_priv->display.vbt.sdvo_mappings[0]; else - mapping = &dev_priv->vbt.sdvo_mappings[1]; + mapping = &dev_priv->display.vbt.sdvo_mappings[1]; if (mapping->initialized) sdvo->ddc_bus = 1 << ((mapping->ddc_pin & 0xf0) >> 4); @@ -2599,9 +2599,9 @@ intel_sdvo_select_i2c_bus(struct drm_i915_private *dev_priv, u8 pin; if (sdvo->port == PORT_B) - mapping = &dev_priv->vbt.sdvo_mappings[0]; + mapping = &dev_priv->display.vbt.sdvo_mappings[0]; else - mapping = &dev_priv->vbt.sdvo_mappings[1]; + mapping = &dev_priv->display.vbt.sdvo_mappings[1]; if (mapping->initialized && intel_gmbus_is_valid_pin(dev_priv, mapping->i2c_pin)) @@ -2639,11 +2639,11 @@ intel_sdvo_get_slave_addr(struct drm_i915_private *dev_priv, struct sdvo_device_mapping *my_mapping, *other_mapping; if (sdvo->port == PORT_B) { - my_mapping = &dev_priv->vbt.sdvo_mappings[0]; - other_mapping = &dev_priv->vbt.sdvo_mappings[1]; + my_mapping = &dev_priv->display.vbt.sdvo_mappings[0]; + other_mapping = &dev_priv->display.vbt.sdvo_mappings[1]; } else { - my_mapping = &dev_priv->vbt.sdvo_mappings[1]; - other_mapping = &dev_priv->vbt.sdvo_mappings[0]; + my_mapping = &dev_priv->display.vbt.sdvo_mappings[1]; + other_mapping = &dev_priv->display.vbt.sdvo_mappings[0]; } /* If the BIOS described our SDVO device, take advantage of it. */ diff --git a/drivers/gpu/drm/i915/display/intel_snps_phy.c b/drivers/gpu/drm/i915/display/intel_snps_phy.c index 0bdbedc67d7d..937cefd6f78f 100644 --- a/drivers/gpu/drm/i915/display/intel_snps_phy.c +++ b/drivers/gpu/drm/i915/display/intel_snps_phy.c @@ -518,6 +518,1086 @@ static const struct intel_mpllb_state dg2_hdmi_148_5 = { }; /* values in the below table are calculted using the algo */ +static const struct intel_mpllb_state dg2_hdmi_25200 = { + .clock = 25200, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 5) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 128) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 41943) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 2621), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_27027 = { + .clock = 27027, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 5) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 140) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 31876) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 46555), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_28320 = { + .clock = 28320, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 5) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 148) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 40894) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 30408), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_30240 = { + .clock = 30240, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 5) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 160) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 50331) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 42466), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_31500 = { + .clock = 31500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 68) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 26214), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_36000 = { + .clock = 36000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 82) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 39321) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 39320), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_40000 = { + .clock = 40000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 96) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_49500 = { + .clock = 49500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 1), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 126) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 13107) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 13107), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_50000 = { + .clock = 50000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 1), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 128) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_57284 = { + .clock = 57284, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 150) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 42886) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 49701), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_58000 = { + .clock = 58000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 4) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 152) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 52428) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 52427), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_65000 = { + .clock = 65000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 72) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_71000 = { + .clock = 71000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 80) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 52428) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 52427), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_74176 = { + .clock = 74176, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 22334) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 43829), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_75000 = { + .clock = 75000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 88) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_78750 = { + .clock = 78750, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 94) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_85500 = { + .clock = 85500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 104) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 26214), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_88750 = { + .clock = 88750, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 1), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 110) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_106500 = { + .clock = 106500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 138) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 13107) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 13107), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_108000 = { + .clock = 108000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 140) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 26214), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_115500 = { + .clock = 115500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 152) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 26214), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_119000 = { + .clock = 119000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 3) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 158) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 13107) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 13107), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_135000 = { + .clock = 135000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 76) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 0), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_138500 = { + .clock = 138500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 78) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 26214) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 26214), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_147160 = { + .clock = 147160, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 84) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 56623) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 6815), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_148352 = { + .clock = 148352, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 22334) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 43829), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_154000 = { + .clock = 154000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 13) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 90) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 39321) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 39320), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_162000 = { + .clock = 162000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 2), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 96) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 52428) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 52427), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_209800 = { + .clock = 209800, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 134) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 60293) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 7864), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_262750 = { + .clock = 262750, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 72) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 36044) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 52427), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_268500 = { + .clock = 268500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 7) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 74) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 45875) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 13107), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_296703 = { + .clock = 296703, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 22321) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 36804), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_241500 = { + .clock = 241500, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 160) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 39321) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 39320), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_497750 = { + .clock = 497750, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 15) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 0), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 166) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 36044) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 52427), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_592000 = { + .clock = 592000, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 13107) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 13107), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + +static const struct intel_mpllb_state dg2_hdmi_593407 = { + .clock = 593407, + .ref_control = + REG_FIELD_PREP(SNPS_PHY_REF_CONTROL_REF_RANGE, 3), + .mpllb_cp = + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT, 6) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP, 14) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_INT_GS, 64) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_CP_PROP_GS, 124), + .mpllb_div = + REG_FIELD_PREP(SNPS_PHY_MPLLB_DIV5_CLK_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_TX_CLK_DIV, 0) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_PMIX_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_V2I, 2) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FREQ_VCO, 3), + .mpllb_div2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_REF_CLK_DIV, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_MULTIPLIER, 86) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_HDMI_DIV, 1), + .mpllb_fracn1 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_CGG_UPDATE_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_EN, 1) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_DEN, 65535), + .mpllb_fracn2 = + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_QUOT, 22328) | + REG_FIELD_PREP(SNPS_PHY_MPLLB_FRACN_REM, 7549), + .mpllb_sscen = + REG_FIELD_PREP(SNPS_PHY_MPLLB_SSC_UP_SPREAD, 1), +}; + static const struct intel_mpllb_state dg2_hdmi_297 = { .clock = 297000, .ref_control = @@ -584,6 +1664,42 @@ static const struct intel_mpllb_state * const dg2_hdmi_tables[] = { &dg2_hdmi_148_5, &dg2_hdmi_297, &dg2_hdmi_594, + &dg2_hdmi_25200, + &dg2_hdmi_27027, + &dg2_hdmi_28320, + &dg2_hdmi_30240, + &dg2_hdmi_31500, + &dg2_hdmi_36000, + &dg2_hdmi_40000, + &dg2_hdmi_49500, + &dg2_hdmi_50000, + &dg2_hdmi_57284, + &dg2_hdmi_58000, + &dg2_hdmi_65000, + &dg2_hdmi_71000, + &dg2_hdmi_74176, + &dg2_hdmi_75000, + &dg2_hdmi_78750, + &dg2_hdmi_85500, + &dg2_hdmi_88750, + &dg2_hdmi_106500, + &dg2_hdmi_108000, + &dg2_hdmi_115500, + &dg2_hdmi_119000, + &dg2_hdmi_135000, + &dg2_hdmi_138500, + &dg2_hdmi_147160, + &dg2_hdmi_148352, + &dg2_hdmi_154000, + &dg2_hdmi_162000, + &dg2_hdmi_209800, + &dg2_hdmi_241500, + &dg2_hdmi_262750, + &dg2_hdmi_268500, + &dg2_hdmi_296703, + &dg2_hdmi_497750, + &dg2_hdmi_592000, + &dg2_hdmi_593407, NULL, }; diff --git a/drivers/gpu/drm/i915/display/intel_tc.c b/drivers/gpu/drm/i915/display/intel_tc.c index 6773840f6cc7..e5af955b5600 100644 --- a/drivers/gpu/drm/i915/display/intel_tc.c +++ b/drivers/gpu/drm/i915/display/intel_tc.c @@ -246,7 +246,7 @@ static u32 icl_tc_port_live_status_mask(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); struct intel_uncore *uncore = &i915->uncore; - u32 isr_bit = i915->hotplug.pch_hpd[dig_port->base.hpd_pin]; + u32 isr_bit = i915->display.hotplug.pch_hpd[dig_port->base.hpd_pin]; u32 mask = 0; u32 val; @@ -279,7 +279,7 @@ static u32 adl_tc_port_live_status_mask(struct intel_digital_port *dig_port) { struct drm_i915_private *i915 = to_i915(dig_port->base.base.dev); enum tc_port tc_port = intel_port_to_tc(i915, dig_port->base.port); - u32 isr_bit = i915->hotplug.pch_hpd[dig_port->base.hpd_pin]; + u32 isr_bit = i915->display.hotplug.pch_hpd[dig_port->base.hpd_pin]; struct intel_uncore *uncore = &i915->uncore; u32 val, mask = 0; diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 9379f3463344..dcf89d701f0f 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -39,6 +39,7 @@ #include "intel_crtc.h" #include "intel_de.h" #include "intel_display_types.h" +#include "intel_dpll.h" #include "intel_hotplug.h" #include "intel_tv.h" @@ -982,10 +983,10 @@ intel_tv_mode_vdisplay(const struct tv_mode *tv_mode) static void intel_tv_mode_to_mode(struct drm_display_mode *mode, - const struct tv_mode *tv_mode) + const struct tv_mode *tv_mode, + int clock) { - mode->clock = tv_mode->clock / - (tv_mode->oversample >> !tv_mode->progressive); + mode->clock = clock / (tv_mode->oversample >> !tv_mode->progressive); /* * tv_mode horizontal timings: @@ -1143,7 +1144,7 @@ intel_tv_get_config(struct intel_encoder *encoder, xsize = tmp >> 16; ysize = tmp & 0xffff; - intel_tv_mode_to_mode(&mode, &tv_mode); + intel_tv_mode_to_mode(&mode, &tv_mode, pipe_config->port_clock); drm_dbg_kms(&dev_priv->drm, "TV mode: " DRM_MODE_FMT "\n", DRM_MODE_ARG(&mode)); @@ -1184,6 +1185,9 @@ intel_tv_compute_config(struct intel_encoder *encoder, struct intel_crtc_state *pipe_config, struct drm_connector_state *conn_state) { + struct intel_atomic_state *state = + to_intel_atomic_state(pipe_config->uapi.state); + struct intel_crtc *crtc = to_intel_crtc(pipe_config->uapi.crtc); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_tv_connector_state *tv_conn_state = to_intel_tv_connector_state(conn_state); @@ -1192,6 +1196,7 @@ intel_tv_compute_config(struct intel_encoder *encoder, &pipe_config->hw.adjusted_mode; int hdisplay = adjusted_mode->crtc_hdisplay; int vdisplay = adjusted_mode->crtc_vdisplay; + int ret; if (!tv_mode) return -EINVAL; @@ -1206,7 +1211,13 @@ intel_tv_compute_config(struct intel_encoder *encoder, pipe_config->port_clock = tv_mode->clock; - intel_tv_mode_to_mode(adjusted_mode, tv_mode); + ret = intel_dpll_crtc_compute_clock(state, crtc); + if (ret) + return ret; + + pipe_config->clock_set = true; + + intel_tv_mode_to_mode(adjusted_mode, tv_mode, pipe_config->port_clock); drm_mode_set_crtcinfo(adjusted_mode, 0); if (intel_tv_source_too_wide(dev_priv, hdisplay) || @@ -1804,7 +1815,7 @@ intel_tv_get_modes(struct drm_connector *connector) * about the actual timings of the mode. We * do ignore the margins though. */ - intel_tv_mode_to_mode(mode, tv_mode); + intel_tv_mode_to_mode(mode, tv_mode, tv_mode->clock); if (count == 0) { drm_dbg_kms(&dev_priv->drm, "TV mode: " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode)); diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h index 509b0a419c20..a9f44abfc9fc 100644 --- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h +++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h @@ -76,6 +76,20 @@ struct bdb_header { } __packed; /* + * BDB version number dependencies are documented as: + * + * <start>+ + * indicates the field was introduced in version <start> + * and is still valid + * + * <start>-<end> + * indicates the field was introduced in version <start> + * and obsoleted in version <end>+1. + * + * ??? indicates the specific version number is unknown + */ + +/* * There are several types of BIOS data blocks (BDBs), each block has * an ID and size in the first 3 bytes (ID in first, size in next 2). * Known types are listed below. @@ -144,12 +158,12 @@ struct bdb_general_features { /* bits 3 */ u8 disable_smooth_vision:1; u8 single_dvi:1; - u8 rotate_180:1; /* 181 */ + u8 rotate_180:1; /* 181+ */ u8 fdi_rx_polarity_inverted:1; - u8 vbios_extended_mode:1; /* 160 */ - u8 copy_ilfp_dtd_to_sdvo_lvds_dtd:1; /* 160 */ - u8 panel_best_fit_timing:1; /* 160 */ - u8 ignore_strap_state:1; /* 160 */ + u8 vbios_extended_mode:1; /* 160+ */ + u8 copy_ilfp_dtd_to_sdvo_lvds_dtd:1; /* 160+ */ + u8 panel_best_fit_timing:1; /* 160+ */ + u8 ignore_strap_state:1; /* 160+ */ /* bits 4 */ u8 legacy_monitor_detect; @@ -164,11 +178,11 @@ struct bdb_general_features { u8 rsvd11:2; /* finish byte */ /* bits 6 */ - u8 tc_hpd_retry_timeout:7; /* 242 */ + u8 tc_hpd_retry_timeout:7; /* 242+ */ u8 rsvd12:1; /* bits 7 */ - u8 afc_startup_config:2;/* 249 */ + u8 afc_startup_config:2; /* 249+ */ u8 rsvd13:6; } __packed; @@ -183,6 +197,15 @@ struct bdb_general_features { #define GPIO_PIN_ADD_DDC_I2C 0x06 /* "ADDCARD DDC/I2C GPIO pins" */ /* Device handle */ +#define DEVICE_HANDLE_CRT 0x0001 +#define DEVICE_HANDLE_EFP1 0x0004 +#define DEVICE_HANDLE_EFP2 0x0040 +#define DEVICE_HANDLE_EFP3 0x0020 +#define DEVICE_HANDLE_EFP4 0x0010 /* 194+ */ +#define DEVICE_HANDLE_EFP5 0x0002 /* 215+ */ +#define DEVICE_HANDLE_EFP6 0x0001 /* 217+ */ +#define DEVICE_HANDLE_EFP7 0x0100 /* 217+ */ +#define DEVICE_HANDLE_EFP8 0x0200 /* 217+ */ #define DEVICE_HANDLE_LFP1 0x0008 #define DEVICE_HANDLE_LFP2 0x0080 @@ -275,27 +298,27 @@ struct bdb_general_features { #define DVO_PORT_DPC 8 #define DVO_PORT_DPD 9 #define DVO_PORT_DPA 10 -#define DVO_PORT_DPE 11 /* 193 */ -#define DVO_PORT_HDMIE 12 /* 193 */ +#define DVO_PORT_DPE 11 /* 193+ */ +#define DVO_PORT_HDMIE 12 /* 193+ */ #define DVO_PORT_DPF 13 /* N/A */ #define DVO_PORT_HDMIF 14 /* N/A */ -#define DVO_PORT_DPG 15 /* 217 */ -#define DVO_PORT_HDMIG 16 /* 217 */ -#define DVO_PORT_DPH 17 /* 217 */ -#define DVO_PORT_HDMIH 18 /* 217 */ -#define DVO_PORT_DPI 19 /* 217 */ -#define DVO_PORT_HDMII 20 /* 217 */ -#define DVO_PORT_MIPIA 21 /* 171 */ -#define DVO_PORT_MIPIB 22 /* 171 */ -#define DVO_PORT_MIPIC 23 /* 171 */ -#define DVO_PORT_MIPID 24 /* 171 */ - -#define HDMI_MAX_DATA_RATE_PLATFORM 0 /* 204 */ -#define HDMI_MAX_DATA_RATE_297 1 /* 204 */ -#define HDMI_MAX_DATA_RATE_165 2 /* 204 */ -#define HDMI_MAX_DATA_RATE_594 3 /* 249 */ -#define HDMI_MAX_DATA_RATE_340 4 /* 249 */ -#define HDMI_MAX_DATA_RATE_300 5 /* 249 */ +#define DVO_PORT_DPG 15 /* 217+ */ +#define DVO_PORT_HDMIG 16 /* 217+ */ +#define DVO_PORT_DPH 17 /* 217+ */ +#define DVO_PORT_HDMIH 18 /* 217+ */ +#define DVO_PORT_DPI 19 /* 217+ */ +#define DVO_PORT_HDMII 20 /* 217+ */ +#define DVO_PORT_MIPIA 21 /* 171+ */ +#define DVO_PORT_MIPIB 22 /* 171+ */ +#define DVO_PORT_MIPIC 23 /* 171+ */ +#define DVO_PORT_MIPID 24 /* 171+ */ + +#define HDMI_MAX_DATA_RATE_PLATFORM 0 /* 204+ */ +#define HDMI_MAX_DATA_RATE_297 1 /* 204+ */ +#define HDMI_MAX_DATA_RATE_165 2 /* 204+ */ +#define HDMI_MAX_DATA_RATE_594 3 /* 249+ */ +#define HDMI_MAX_DATA_RATE_340 4 /* 249+ */ +#define HDMI_MAX_DATA_RATE_300 5 /* 249+ */ #define LEGACY_CHILD_DEVICE_CONFIG_SIZE 33 @@ -362,10 +385,10 @@ enum vbt_gmbus_ddi { * basically any of the fields to ensure the correct interpretation for the BDB * version in question. * - * When we copy the child device configs to dev_priv->vbt.child_dev, we reserve - * space for the full structure below, and initialize the tail not actually - * present in VBT to zeros. Accessing those fields is fine, as long as the - * default zero is taken into account, again according to the BDB version. + * When we copy the child device configs to dev_priv->display.vbt.child_dev, we + * reserve space for the full structure below, and initialize the tail not + * actually present in VBT to zeros. Accessing those fields is fine, as long as + * the default zero is taken into account, again according to the BDB version. * * BDB versions 155 and below are considered legacy, and version 155 seems to be * a baseline for some of the VBT documentation. When adding new fields, please @@ -379,20 +402,30 @@ struct child_device_config { u8 device_id[10]; /* ascii string */ struct { u8 i2c_speed; - u8 dp_onboard_redriver; /* 158 */ - u8 dp_ondock_redriver; /* 158 */ - u8 hdmi_level_shifter_value:5; /* 169 */ - u8 hdmi_max_data_rate:3; /* 204 */ - u16 dtd_buf_ptr; /* 161 */ - u8 edidless_efp:1; /* 161 */ - u8 compression_enable:1; /* 198 */ - u8 compression_method_cps:1; /* 198 */ - u8 ganged_edp:1; /* 202 */ - u8 reserved0:4; - u8 compression_structure_index:4; /* 198 */ - u8 reserved1:4; - u8 slave_port; /* 202 */ - u8 reserved2; + u8 dp_onboard_redriver_preemph:3; /* 158+ */ + u8 dp_onboard_redriver_vswing:3; /* 158+ */ + u8 dp_onboard_redriver_present:1; /* 158+ */ + u8 reserved0:1; + u8 dp_ondock_redriver_preemph:3; /* 158+ */ + u8 dp_ondock_redriver_vswing:3; /* 158+ */ + u8 dp_ondock_redriver_present:1; /* 158+ */ + u8 reserved1:1; + u8 hdmi_level_shifter_value:5; /* 158+ */ + u8 hdmi_max_data_rate:3; /* 204+ */ + u16 dtd_buf_ptr; /* 161+ */ + u8 edidless_efp:1; /* 161+ */ + u8 compression_enable:1; /* 198+ */ + u8 compression_method_cps:1; /* 198+ */ + u8 ganged_edp:1; /* 202+ */ + u8 lttpr_non_transparent:1; /* 235+ */ + u8 disable_compression_for_ext_disp:1; /* 251+ */ + u8 reserved2:2; + u8 compression_structure_index:4; /* 198+ */ + u8 reserved3:4; + u8 hdmi_max_frl_rate:4; /* 237+ */ + u8 hdmi_max_frl_rate_valid:1; /* 237+ */ + u8 reserved4:3; /* 237+ */ + u8 reserved5; } __packed; } __packed; @@ -412,16 +445,16 @@ struct child_device_config { u8 ddc2_pin; } __packed; struct { - u8 efp_routed:1; /* 158 */ - u8 lane_reversal:1; /* 184 */ - u8 lspcon:1; /* 192 */ - u8 iboost:1; /* 196 */ - u8 hpd_invert:1; /* 196 */ - u8 use_vbt_vswing:1; /* 218 */ - u8 flag_reserved:2; - u8 hdmi_support:1; /* 158 */ - u8 dp_support:1; /* 158 */ - u8 tmds_support:1; /* 158 */ + u8 efp_routed:1; /* 158+ */ + u8 lane_reversal:1; /* 184+ */ + u8 lspcon:1; /* 192+ */ + u8 iboost:1; /* 196+ */ + u8 hpd_invert:1; /* 196+ */ + u8 use_vbt_vswing:1; /* 218+ */ + u8 dp_max_lane_count:2; /* 244+ */ + u8 hdmi_support:1; /* 158+ */ + u8 dp_support:1; /* 158+ */ + u8 tmds_support:1; /* 158+ */ u8 support_reserved:5; u8 aux_channel; u8 dongle_detect; @@ -429,7 +462,7 @@ struct child_device_config { } __packed; u8 pipe_cap:2; - u8 sdvo_stall:1; /* 158 */ + u8 sdvo_stall:1; /* 158+ */ u8 hpd_status:2; u8 integrated_encoder:1; u8 capabilities_reserved:2; @@ -437,21 +470,21 @@ struct child_device_config { union { u8 dvo2_wiring; - u8 mipi_bridge_type; /* 171 */ + u8 mipi_bridge_type; /* 171+ */ } __packed; u16 extended_type; u8 dvo_function; - u8 dp_usb_type_c:1; /* 195 */ - u8 tbt:1; /* 209 */ - u8 flags2_reserved:2; /* 195 */ - u8 dp_port_trace_length:4; /* 209 */ - u8 dp_gpio_index; /* 195 */ - u16 dp_gpio_pin_num; /* 195 */ - u8 dp_iboost_level:4; /* 196 */ - u8 hdmi_iboost_level:4; /* 196 */ - u8 dp_max_link_rate:3; /* 216/230 GLK+ */ - u8 dp_max_link_rate_reserved:5; /* 216/230 */ + u8 dp_usb_type_c:1; /* 195+ */ + u8 tbt:1; /* 209+ */ + u8 flags2_reserved:2; /* 195+ */ + u8 dp_port_trace_length:4; /* 209+ */ + u8 dp_gpio_index; /* 195+ */ + u16 dp_gpio_pin_num; /* 195+ */ + u8 dp_iboost_level:4; /* 196+ */ + u8 hdmi_iboost_level:4; /* 196+ */ + u8 dp_max_link_rate:3; /* 216+ */ + u8 dp_max_link_rate_reserved:5; /* 216+ */ } __packed; struct bdb_general_definitions { @@ -459,7 +492,7 @@ struct bdb_general_definitions { u8 crt_ddc_gmbus_pin; /* DPMS bits */ - u8 dpms_acpi:1; + u8 dpms_non_acpi:1; u8 skip_boot_crt_detect:1; u8 dpms_aim:1; u8 rsvd1:5; /* finish byte */ @@ -488,25 +521,25 @@ struct bdb_general_definitions { struct psr_table { /* Feature bits */ - u8 full_link:1; - u8 require_aux_to_wakeup:1; + u8 full_link:1; /* 165+ */ + u8 require_aux_to_wakeup:1; /* 165+ */ u8 feature_bits_rsvd:6; /* Wait times */ - u8 idle_frames:4; - u8 lines_to_wait:3; + u8 idle_frames:4; /* 165+ */ + u8 lines_to_wait:3; /* 165+ */ u8 wait_times_rsvd:1; /* TP wake up time in multiple of 100 */ - u16 tp1_wakeup_time; - u16 tp2_tp3_wakeup_time; + u16 tp1_wakeup_time; /* 165+ */ + u16 tp2_tp3_wakeup_time; /* 165+ */ } __packed; struct bdb_psr { struct psr_table psr_table[16]; /* PSR2 TP2/TP3 wakeup time for 16 panels */ - u32 psr2_tp2_tp3_wakeup_time; + u32 psr2_tp2_tp3_wakeup_time; /* 226+ */ } __packed; /* @@ -519,9 +552,10 @@ struct bdb_psr { #define BDB_DRIVER_FEATURE_INT_SDVO_LVDS 3 struct bdb_driver_features { + /* Driver bits */ u8 boot_dev_algorithm:1; - u8 block_display_switch:1; - u8 allow_display_switch:1; + u8 allow_display_switch_dvd:1; + u8 allow_display_switch_dos:1; u8 hotplug_dvo:1; u8 dual_view_zoom:1; u8 int15h_hook:1; @@ -533,6 +567,7 @@ struct bdb_driver_features { u8 boot_mode_bpp; u8 boot_mode_refresh; + /* Extended Driver Bits 1 */ u16 enable_lfp_primary:1; u16 selective_mode_pruning:1; u16 dual_frequency:1; @@ -548,29 +583,40 @@ struct bdb_driver_features { u16 tv_hotplug:1; u16 hdmi_config:2; - u8 static_display:1; - u8 reserved2:7; + /* Driver Flags 1 */ + u8 static_display:1; /* 163+ */ + u8 embedded_platform:1; /* 163+ */ + u8 display_subsystem_enable:1; /* 163+ */ + u8 reserved0:5; + u16 legacy_crt_max_x; u16 legacy_crt_max_y; u8 legacy_crt_max_refresh; - u8 hdmi_termination; - u8 custom_vbt_version; - /* Driver features data block */ - u16 rmpm_enabled:1; - u16 s2ddt_enabled:1; - u16 dpst_enabled:1; - u16 bltclt_enabled:1; - u16 adb_enabled:1; - u16 drrs_enabled:1; - u16 grs_enabled:1; - u16 gpmt_enabled:1; - u16 tbt_enabled:1; - u16 psr_enabled:1; - u16 ips_enabled:1; - u16 reserved3:1; - u16 dmrrs_enabled:1; - u16 reserved4:2; + /* Extended Driver Bits 2 */ + u8 hdmi_termination:1; + u8 cea861d_hdmi_support:1; + u8 self_refresh_enable:1; + u8 reserved1:5; + + u8 custom_vbt_version; /* 155+ */ + + /* Driver Feature Flags */ + u16 rmpm_enabled:1; /* 165+ */ + u16 s2ddt_enabled:1; /* 165+ */ + u16 dpst_enabled:1; /* 165-227 */ + u16 bltclt_enabled:1; /* 165+ */ + u16 adb_enabled:1; /* 165-227 */ + u16 drrs_enabled:1; /* 165-227 */ + u16 grs_enabled:1; /* 165+ */ + u16 gpmt_enabled:1; /* 165+ */ + u16 tbt_enabled:1; /* 165+ */ + u16 psr_enabled:1; /* 165-227 */ + u16 ips_enabled:1; /* 165+ */ + u16 dpfs_enabled:1; /* 165+ */ + u16 dmrrs_enabled:1; /* 174-227 */ + u16 adt_enabled:1; /* ???-228 */ + u16 hpd_wake:1; /* 201-240 */ u16 pc_feature_valid:1; } __packed; @@ -657,7 +703,7 @@ struct bdb_sdvo_panel_dtds { struct edp_fast_link_params { - u8 rate:4; + u8 rate:4; /* ???-223 */ u8 lanes:4; u8 preemphasis:4; u8 vswing:4; @@ -690,18 +736,18 @@ struct bdb_edp { u32 sdrrs_msa_timing_delay; /* ith bit indicates enabled/disabled for (i+1)th panel */ - u16 edp_s3d_feature; /* 162 */ - u16 edp_t3_optimization; /* 165 */ - u64 edp_vswing_preemph; /* 173 */ - u16 fast_link_training; /* 182 */ - u16 dpcd_600h_write_required; /* 185 */ - struct edp_pwm_delays pwm_delays[16]; /* 186 */ - u16 full_link_params_provided; /* 199 */ - struct edp_full_link_params full_link_params[16]; /* 199 */ - u16 apical_enable; /* 203 */ - struct edp_apical_params apical_params[16]; /* 203 */ - u16 edp_fast_link_training_rate[16]; /* 224 */ - u16 edp_max_port_link_rate[16]; /* 244 */ + u16 edp_s3d_feature; /* 162+ */ + u16 edp_t3_optimization; /* 165+ */ + u64 edp_vswing_preemph; /* 173+ */ + u16 fast_link_training; /* 182+ */ + u16 dpcd_600h_write_required; /* 185+ */ + struct edp_pwm_delays pwm_delays[16]; /* 186+ */ + u16 full_link_params_provided; /* 199+ */ + struct edp_full_link_params full_link_params[16]; /* 199+ */ + u16 apical_enable; /* 203+ */ + struct edp_apical_params apical_params[16]; /* 203+ */ + u16 edp_fast_link_training_rate[16]; /* 224+ */ + u16 edp_max_port_link_rate[16]; /* 244+ */ } __packed; /* @@ -710,14 +756,14 @@ struct bdb_edp { struct bdb_lvds_options { u8 panel_type; - u8 panel_type2; /* 212 */ + u8 panel_type2; /* 212+ */ /* LVDS capabilities, stored in a dword */ u8 pfit_mode:2; u8 pfit_text_mode_enhanced:1; u8 pfit_gfx_mode_enhanced:1; u8 pfit_ratio_auto:1; u8 pixel_dither:1; - u8 lvds_edid:1; + u8 lvds_edid:1; /* ???-240 */ u8 rsvd2:1; u8 rsvd4; /* LVDS Panel channel bits stored here */ @@ -731,11 +777,11 @@ struct bdb_lvds_options { /* LVDS panel type bits stored here */ u32 dps_panel_type_bits; /* LVDS backlight control type bits stored here */ - u32 blt_control_type_bits; + u32 blt_control_type_bits; /* ???-240 */ - u16 lcdvcc_s0_enable; /* 200 */ - u32 rotation; /* 228 */ - u32 position; /* 240 */ + u16 lcdvcc_s0_enable; /* 200+ */ + u32 rotation; /* 228+ */ + u32 position; /* 240+ */ } __packed; /* @@ -756,7 +802,7 @@ struct lvds_lfp_data_ptr { struct bdb_lvds_lfp_data_ptrs { u8 lvds_entries; struct lvds_lfp_data_ptr ptr[16]; - struct lvds_lfp_data_ptr_table panel_name; /* 156-163? */ + struct lvds_lfp_data_ptr_table panel_name; /* (156-163?)+ */ } __packed; /* @@ -808,20 +854,20 @@ struct lvds_lfp_panel_name { } __packed; struct lvds_lfp_black_border { - u8 top; /* 227 */ - u8 bottom; /* 227 */ - u8 left; /* 238 */ - u8 right; /* 238 */ + u8 top; /* 227+ */ + u8 bottom; /* 227+ */ + u8 left; /* 238+ */ + u8 right; /* 238+ */ } __packed; struct bdb_lvds_lfp_data_tail { - struct lvds_lfp_panel_name panel_name[16]; /* 156-163? */ - u16 scaling_enable; /* 187 */ - u8 seamless_drrs_min_refresh_rate[16]; /* 188 */ - u8 pixel_overlap_count[16]; /* 208 */ - struct lvds_lfp_black_border black_border[16]; /* 227 */ - u16 dual_lfp_port_sync_enable; /* 231 */ - u16 gpu_dithering_for_banding_artifacts; /* 245 */ + struct lvds_lfp_panel_name panel_name[16]; /* (156-163?)+ */ + u16 scaling_enable; /* 187+ */ + u8 seamless_drrs_min_refresh_rate[16]; /* 188+ */ + u8 pixel_overlap_count[16]; /* 208+ */ + struct lvds_lfp_black_border black_border[16]; /* 227+ */ + u16 dual_lfp_port_sync_enable; /* 231+ */ + u16 gpu_dithering_for_banding_artifacts; /* 245+ */ } __packed; /* @@ -836,7 +882,7 @@ struct lfp_backlight_data_entry { u8 active_low_pwm:1; u8 obsolete1:5; u16 pwm_freq_hz; - u8 min_brightness; /* Obsolete from 234+ */ + u8 min_brightness; /* ???-233 */ u8 obsolete2; u8 obsolete3; } __packed; @@ -859,7 +905,7 @@ struct lfp_brightness_level { struct bdb_lfp_backlight_data { u8 entry_size; struct lfp_backlight_data_entry data[16]; - u8 level[16]; /* Obsolete from 234+ */ + u8 level[16]; /* ???-233 */ struct lfp_backlight_control_method backlight_control[16]; struct lfp_brightness_level brightness_level[16]; /* 234+ */ struct lfp_brightness_level brightness_min_level[16]; /* 234+ */ @@ -874,8 +920,8 @@ struct lfp_power_features { u8 reserved1:1; u8 power_conservation_pref:3; u8 reserved2:1; - u8 lace_enabled_status:1; - u8 lace_support:1; + u8 lace_enabled_status:1; /* 210+ */ + u8 lace_support:1; /* 210+ */ u8 als_enable:1; } __packed; @@ -895,24 +941,24 @@ struct aggressiveness_profile2_entry { } __packed; struct bdb_lfp_power { - struct lfp_power_features features; + struct lfp_power_features features; /* ???-227 */ struct als_data_entry als[5]; - u8 lace_aggressiveness_profile:3; + u8 lace_aggressiveness_profile:3; /* 210-227 */ u8 reserved1:5; - u16 dpst; - u16 psr; - u16 drrs; - u16 lace_support; - u16 adt; - u16 dmrrs; - u16 adb; - u16 lace_enabled_status; - struct aggressiveness_profile_entry aggressiveness[16]; - u16 hobl; /* 232+ */ - u16 vrr_feature_enabled; /* 233+ */ - u16 elp; /* 247+ */ - u16 opst; /* 247+ */ - struct aggressiveness_profile2_entry aggressiveness2[16]; /* 247+ */ + u16 dpst; /* 228+ */ + u16 psr; /* 228+ */ + u16 drrs; /* 228+ */ + u16 lace_support; /* 228+ */ + u16 adt; /* 228+ */ + u16 dmrrs; /* 228+ */ + u16 adb; /* 228+ */ + u16 lace_enabled_status; /* 228+ */ + struct aggressiveness_profile_entry aggressiveness[16]; /* 228+ */ + u16 hobl; /* 232+ */ + u16 vrr_feature_enabled; /* 233+ */ + u16 elp; /* 247+ */ + u16 opst; /* 247+ */ + struct aggressiveness_profile2_entry aggressiveness2[16]; /* 247+ */ } __packed; /* @@ -922,10 +968,10 @@ struct bdb_lfp_power { #define MAX_MIPI_CONFIGURATIONS 6 struct bdb_mipi_config { - struct mipi_config config[MAX_MIPI_CONFIGURATIONS]; /* 175 */ - struct mipi_pps_data pps[MAX_MIPI_CONFIGURATIONS]; /* 177 */ - struct edp_pwm_delays pwm_delays[MAX_MIPI_CONFIGURATIONS]; /* 186 */ - u8 pmic_i2c_bus_number[MAX_MIPI_CONFIGURATIONS]; /* 190 */ + struct mipi_config config[MAX_MIPI_CONFIGURATIONS]; /* 175+ */ + struct mipi_pps_data pps[MAX_MIPI_CONFIGURATIONS]; /* 177+ */ + struct edp_pwm_delays pwm_delays[MAX_MIPI_CONFIGURATIONS]; /* 186+ */ + u8 pmic_i2c_bus_number[MAX_MIPI_CONFIGURATIONS]; /* 190+ */ } __packed; /* diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c index 43e1bbc1e303..269f9792390d 100644 --- a/drivers/gpu/drm/i915/display/intel_vdsc.c +++ b/drivers/gpu/drm/i915/display/intel_vdsc.c @@ -344,7 +344,7 @@ bool intel_dsc_source_support(const struct intel_crtc_state *crtc_state) struct drm_i915_private *i915 = to_i915(crtc->base.dev); enum transcoder cpu_transcoder = crtc_state->cpu_transcoder; - if (!INTEL_INFO(i915)->display.has_dsc) + if (!RUNTIME_INFO(i915)->has_dsc) return false; if (DISPLAY_VER(i915) >= 12) @@ -460,7 +460,6 @@ int intel_dsc_compute_params(struct intel_crtc_state *pipe_config) u8 i = 0; vdsc_cfg->pic_width = pipe_config->hw.adjusted_mode.crtc_hdisplay; - vdsc_cfg->pic_height = pipe_config->hw.adjusted_mode.crtc_vdisplay; vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width, pipe_config->dsc.slice_count); @@ -597,6 +596,8 @@ static void intel_dsc_pps_configure(const struct intel_crtc_state *crtc_state) DSC_VER_MIN_SHIFT | vdsc_cfg->bits_per_component << DSC_BPC_SHIFT | vdsc_cfg->line_buf_depth << DSC_LINE_BUF_DEPTH_SHIFT; + if (vdsc_cfg->dsc_version_minor == 2) + pps_val |= DSC_ALT_ICH_SEL; if (vdsc_cfg->block_pred_enable) pps_val |= DSC_BLOCK_PREDICTION; if (vdsc_cfg->convert_rgb) diff --git a/drivers/gpu/drm/i915/display/intel_vrr.c b/drivers/gpu/drm/i915/display/intel_vrr.c index 04250a0fec3c..5eac99021875 100644 --- a/drivers/gpu/drm/i915/display/intel_vrr.c +++ b/drivers/gpu/drm/i915/display/intel_vrr.c @@ -142,11 +142,16 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, * For XE_LPD+, we use guardband and pipeline override * is deprecated. */ - if (DISPLAY_VER(i915) >= 13) + if (DISPLAY_VER(i915) >= 13) { + /* + * FIXME: Subtract Window2 delay from below value. + * + * Window2 specifies time required to program DSB (Window2) in + * number of scan lines. Assuming 0 for no DSB. + */ crtc_state->vrr.guardband = - crtc_state->vrr.vmin - adjusted_mode->crtc_vdisplay - - i915->window2_delay; - else + crtc_state->vrr.vmin - adjusted_mode->crtc_vdisplay; + } else { /* * FIXME: s/4/framestart_delay/ to get consistent * earliest/latest points for register latching regardless @@ -159,6 +164,7 @@ intel_vrr_compute_config(struct intel_crtc_state *crtc_state, */ crtc_state->vrr.pipeline_full = min(255, crtc_state->vrr.vmin - adjusted_mode->crtc_vdisplay - 4 - 1); + } crtc_state->mode_flags |= I915_MODE_FLAG_VRR; } diff --git a/drivers/gpu/drm/i915/display/skl_universal_plane.c b/drivers/gpu/drm/i915/display/skl_universal_plane.c index 4d6a27757065..7cb713043408 100644 --- a/drivers/gpu/drm/i915/display/skl_universal_plane.c +++ b/drivers/gpu/drm/i915/display/skl_universal_plane.c @@ -14,11 +14,11 @@ #include "intel_display_types.h" #include "intel_fb.h" #include "intel_fbc.h" -#include "intel_pm.h" #include "intel_psr.h" #include "intel_sprite.h" #include "skl_scaler.h" #include "skl_universal_plane.h" +#include "skl_watermark.h" #include "pxp/intel_pxp.h" static const u32 skl_plane_formats[] = { @@ -1928,7 +1928,7 @@ static enum intel_fbc_id skl_fbc_id_for_pipe(enum pipe pipe) static bool skl_plane_has_fbc(struct drm_i915_private *dev_priv, enum intel_fbc_id fbc_id, enum plane_id plane_id) { - if ((INTEL_INFO(dev_priv)->display.fbc_mask & BIT(fbc_id)) == 0) + if ((RUNTIME_INFO(dev_priv)->fbc_mask & BIT(fbc_id)) == 0) return false; return plane_id == PLANE_PRIMARY; @@ -1940,7 +1940,7 @@ static struct intel_fbc *skl_plane_fbc(struct drm_i915_private *dev_priv, enum intel_fbc_id fbc_id = skl_fbc_id_for_pipe(pipe); if (skl_plane_has_fbc(dev_priv, fbc_id, plane_id)) - return dev_priv->fbc[fbc_id]; + return dev_priv->display.fbc[fbc_id]; else return NULL; } diff --git a/drivers/gpu/drm/i915/display/skl_watermark.c b/drivers/gpu/drm/i915/display/skl_watermark.c new file mode 100644 index 000000000000..18178b01375e --- /dev/null +++ b/drivers/gpu/drm/i915/display/skl_watermark.c @@ -0,0 +1,3574 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2022 Intel Corporation + */ + +#include <drm/drm_blend.h> + +#include "intel_atomic.h" +#include "intel_atomic_plane.h" +#include "intel_bw.h" +#include "intel_de.h" +#include "intel_display.h" +#include "intel_display_power.h" +#include "intel_display_types.h" +#include "intel_fb.h" +#include "skl_watermark.h" + +#include "i915_drv.h" +#include "i915_fixed.h" +#include "i915_reg.h" +#include "intel_pcode.h" +#include "intel_pm.h" + +static void skl_sagv_disable(struct drm_i915_private *i915); + +/* Stores plane specific WM parameters */ +struct skl_wm_params { + bool x_tiled, y_tiled; + bool rc_surface; + bool is_planar; + u32 width; + u8 cpp; + u32 plane_pixel_rate; + u32 y_min_scanlines; + u32 plane_bytes_per_line; + uint_fixed_16_16_t plane_blocks_per_line; + uint_fixed_16_16_t y_tile_minimum; + u32 linetime_us; + u32 dbuf_block_size; +}; + +u8 intel_enabled_dbuf_slices_mask(struct drm_i915_private *i915) +{ + u8 enabled_slices = 0; + enum dbuf_slice slice; + + for_each_dbuf_slice(i915, slice) { + if (intel_uncore_read(&i915->uncore, + DBUF_CTL_S(slice)) & DBUF_POWER_STATE) + enabled_slices |= BIT(slice); + } + + return enabled_slices; +} + +/* + * FIXME: We still don't have the proper code detect if we need to apply the WA, + * so assume we'll always need it in order to avoid underruns. + */ +static bool skl_needs_memory_bw_wa(struct drm_i915_private *i915) +{ + return DISPLAY_VER(i915) == 9; +} + +static bool +intel_has_sagv(struct drm_i915_private *i915) +{ + return DISPLAY_VER(i915) >= 9 && !IS_LP(i915) && + i915->display.sagv.status != I915_SAGV_NOT_CONTROLLED; +} + +static u32 +intel_sagv_block_time(struct drm_i915_private *i915) +{ + if (DISPLAY_VER(i915) >= 14) { + u32 val; + + val = intel_uncore_read(&i915->uncore, MTL_LATENCY_SAGV); + + return REG_FIELD_GET(MTL_LATENCY_QCLK_SAGV, val); + } else if (DISPLAY_VER(i915) >= 12) { + u32 val = 0; + int ret; + + ret = snb_pcode_read(&i915->uncore, + GEN12_PCODE_READ_SAGV_BLOCK_TIME_US, + &val, NULL); + if (ret) { + drm_dbg_kms(&i915->drm, "Couldn't read SAGV block time!\n"); + return 0; + } + + return val; + } else if (DISPLAY_VER(i915) == 11) { + return 10; + } else if (DISPLAY_VER(i915) == 9 && !IS_LP(i915)) { + return 30; + } else { + return 0; + } +} + +static void intel_sagv_init(struct drm_i915_private *i915) +{ + if (!intel_has_sagv(i915)) + i915->display.sagv.status = I915_SAGV_NOT_CONTROLLED; + + /* + * Probe to see if we have working SAGV control. + * For icl+ this was already determined by intel_bw_init_hw(). + */ + if (DISPLAY_VER(i915) < 11) + skl_sagv_disable(i915); + + drm_WARN_ON(&i915->drm, i915->display.sagv.status == I915_SAGV_UNKNOWN); + + i915->display.sagv.block_time_us = intel_sagv_block_time(i915); + + drm_dbg_kms(&i915->drm, "SAGV supported: %s, original SAGV block time: %u us\n", + str_yes_no(intel_has_sagv(i915)), i915->display.sagv.block_time_us); + + /* avoid overflow when adding with wm0 latency/etc. */ + if (drm_WARN(&i915->drm, i915->display.sagv.block_time_us > U16_MAX, + "Excessive SAGV block time %u, ignoring\n", + i915->display.sagv.block_time_us)) + i915->display.sagv.block_time_us = 0; + + if (!intel_has_sagv(i915)) + i915->display.sagv.block_time_us = 0; +} + +/* + * SAGV dynamically adjusts the system agent voltage and clock frequencies + * depending on power and performance requirements. The display engine access + * to system memory is blocked during the adjustment time. Because of the + * blocking time, having this enabled can cause full system hangs and/or pipe + * underruns if we don't meet all of the following requirements: + * + * - <= 1 pipe enabled + * - All planes can enable watermarks for latencies >= SAGV engine block time + * - We're not using an interlaced display configuration + */ +static void skl_sagv_enable(struct drm_i915_private *i915) +{ + int ret; + + if (!intel_has_sagv(i915)) + return; + + if (i915->display.sagv.status == I915_SAGV_ENABLED) + return; + + drm_dbg_kms(&i915->drm, "Enabling SAGV\n"); + ret = snb_pcode_write(&i915->uncore, GEN9_PCODE_SAGV_CONTROL, + GEN9_SAGV_ENABLE); + + /* We don't need to wait for SAGV when enabling */ + + /* + * Some skl systems, pre-release machines in particular, + * don't actually have SAGV. + */ + if (IS_SKYLAKE(i915) && ret == -ENXIO) { + drm_dbg(&i915->drm, "No SAGV found on system, ignoring\n"); + i915->display.sagv.status = I915_SAGV_NOT_CONTROLLED; + return; + } else if (ret < 0) { + drm_err(&i915->drm, "Failed to enable SAGV\n"); + return; + } + + i915->display.sagv.status = I915_SAGV_ENABLED; +} + +static void skl_sagv_disable(struct drm_i915_private *i915) +{ + int ret; + + if (!intel_has_sagv(i915)) + return; + + if (i915->display.sagv.status == I915_SAGV_DISABLED) + return; + + drm_dbg_kms(&i915->drm, "Disabling SAGV\n"); + /* bspec says to keep retrying for at least 1 ms */ + ret = skl_pcode_request(&i915->uncore, GEN9_PCODE_SAGV_CONTROL, + GEN9_SAGV_DISABLE, + GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED, + 1); + /* + * Some skl systems, pre-release machines in particular, + * don't actually have SAGV. + */ + if (IS_SKYLAKE(i915) && ret == -ENXIO) { + drm_dbg(&i915->drm, "No SAGV found on system, ignoring\n"); + i915->display.sagv.status = I915_SAGV_NOT_CONTROLLED; + return; + } else if (ret < 0) { + drm_err(&i915->drm, "Failed to disable SAGV (%d)\n", ret); + return; + } + + i915->display.sagv.status = I915_SAGV_DISABLED; +} + +static void skl_sagv_pre_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_bw_state *new_bw_state = + intel_atomic_get_new_bw_state(state); + + if (!new_bw_state) + return; + + if (!intel_can_enable_sagv(i915, new_bw_state)) + skl_sagv_disable(i915); +} + +static void skl_sagv_post_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_bw_state *new_bw_state = + intel_atomic_get_new_bw_state(state); + + if (!new_bw_state) + return; + + if (intel_can_enable_sagv(i915, new_bw_state)) + skl_sagv_enable(i915); +} + +static void icl_sagv_pre_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_bw_state *old_bw_state = + intel_atomic_get_old_bw_state(state); + const struct intel_bw_state *new_bw_state = + intel_atomic_get_new_bw_state(state); + u16 old_mask, new_mask; + + if (!new_bw_state) + return; + + old_mask = old_bw_state->qgv_points_mask; + new_mask = old_bw_state->qgv_points_mask | new_bw_state->qgv_points_mask; + + if (old_mask == new_mask) + return; + + WARN_ON(!new_bw_state->base.changed); + + drm_dbg_kms(&i915->drm, "Restricting QGV points: 0x%x -> 0x%x\n", + old_mask, new_mask); + + /* + * Restrict required qgv points before updating the configuration. + * According to BSpec we can't mask and unmask qgv points at the same + * time. Also masking should be done before updating the configuration + * and unmasking afterwards. + */ + icl_pcode_restrict_qgv_points(i915, new_mask); +} + +static void icl_sagv_post_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_bw_state *old_bw_state = + intel_atomic_get_old_bw_state(state); + const struct intel_bw_state *new_bw_state = + intel_atomic_get_new_bw_state(state); + u16 old_mask, new_mask; + + if (!new_bw_state) + return; + + old_mask = old_bw_state->qgv_points_mask | new_bw_state->qgv_points_mask; + new_mask = new_bw_state->qgv_points_mask; + + if (old_mask == new_mask) + return; + + WARN_ON(!new_bw_state->base.changed); + + drm_dbg_kms(&i915->drm, "Relaxing QGV points: 0x%x -> 0x%x\n", + old_mask, new_mask); + + /* + * Allow required qgv points after updating the configuration. + * According to BSpec we can't mask and unmask qgv points at the same + * time. Also masking should be done before updating the configuration + * and unmasking afterwards. + */ + icl_pcode_restrict_qgv_points(i915, new_mask); +} + +void intel_sagv_pre_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + + /* + * Just return if we can't control SAGV or don't have it. + * This is different from situation when we have SAGV but just can't + * afford it due to DBuf limitation - in case if SAGV is completely + * disabled in a BIOS, we are not even allowed to send a PCode request, + * as it will throw an error. So have to check it here. + */ + if (!intel_has_sagv(i915)) + return; + + if (DISPLAY_VER(i915) >= 11) + icl_sagv_pre_plane_update(state); + else + skl_sagv_pre_plane_update(state); +} + +void intel_sagv_post_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + + /* + * Just return if we can't control SAGV or don't have it. + * This is different from situation when we have SAGV but just can't + * afford it due to DBuf limitation - in case if SAGV is completely + * disabled in a BIOS, we are not even allowed to send a PCode request, + * as it will throw an error. So have to check it here. + */ + if (!intel_has_sagv(i915)) + return; + + if (DISPLAY_VER(i915) >= 11) + icl_sagv_post_plane_update(state); + else + skl_sagv_post_plane_update(state); +} + +static bool skl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + enum plane_id plane_id; + int max_level = INT_MAX; + + if (!intel_has_sagv(i915)) + return false; + + if (!crtc_state->hw.active) + return true; + + if (crtc_state->hw.pipe_mode.flags & DRM_MODE_FLAG_INTERLACE) + return false; + + for_each_plane_id_on_crtc(crtc, plane_id) { + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + int level; + + /* Skip this plane if it's not enabled */ + if (!wm->wm[0].enable) + continue; + + /* Find the highest enabled wm level for this plane */ + for (level = ilk_wm_max_level(i915); + !wm->wm[level].enable; --level) + { } + + /* Highest common enabled wm level for all planes */ + max_level = min(level, max_level); + } + + /* No enabled planes? */ + if (max_level == INT_MAX) + return true; + + for_each_plane_id_on_crtc(crtc, plane_id) { + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + + /* + * All enabled planes must have enabled a common wm level that + * can tolerate memory latencies higher than sagv_block_time_us + */ + if (wm->wm[0].enable && !wm->wm[max_level].can_sagv) + return false; + } + + return true; +} + +static bool tgl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + enum plane_id plane_id; + + if (!crtc_state->hw.active) + return true; + + for_each_plane_id_on_crtc(crtc, plane_id) { + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + + if (wm->wm[0].enable && !wm->sagv.wm0.enable) + return false; + } + + return true; +} + +static bool intel_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + + if (DISPLAY_VER(i915) >= 12) + return tgl_crtc_can_enable_sagv(crtc_state); + else + return skl_crtc_can_enable_sagv(crtc_state); +} + +bool intel_can_enable_sagv(struct drm_i915_private *i915, + const struct intel_bw_state *bw_state) +{ + if (DISPLAY_VER(i915) < 11 && + bw_state->active_pipes && !is_power_of_2(bw_state->active_pipes)) + return false; + + return bw_state->pipe_sagv_reject == 0; +} + +static int intel_compute_sagv_mask(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + int ret; + struct intel_crtc *crtc; + struct intel_crtc_state *new_crtc_state; + struct intel_bw_state *new_bw_state = NULL; + const struct intel_bw_state *old_bw_state = NULL; + int i; + + for_each_new_intel_crtc_in_state(state, crtc, + new_crtc_state, i) { + new_bw_state = intel_atomic_get_bw_state(state); + if (IS_ERR(new_bw_state)) + return PTR_ERR(new_bw_state); + + old_bw_state = intel_atomic_get_old_bw_state(state); + + if (intel_crtc_can_enable_sagv(new_crtc_state)) + new_bw_state->pipe_sagv_reject &= ~BIT(crtc->pipe); + else + new_bw_state->pipe_sagv_reject |= BIT(crtc->pipe); + } + + if (!new_bw_state) + return 0; + + new_bw_state->active_pipes = + intel_calc_active_pipes(state, old_bw_state->active_pipes); + + if (new_bw_state->active_pipes != old_bw_state->active_pipes) { + ret = intel_atomic_lock_global_state(&new_bw_state->base); + if (ret) + return ret; + } + + if (intel_can_enable_sagv(i915, new_bw_state) != + intel_can_enable_sagv(i915, old_bw_state)) { + ret = intel_atomic_serialize_global_state(&new_bw_state->base); + if (ret) + return ret; + } else if (new_bw_state->pipe_sagv_reject != old_bw_state->pipe_sagv_reject) { + ret = intel_atomic_lock_global_state(&new_bw_state->base); + if (ret) + return ret; + } + + for_each_new_intel_crtc_in_state(state, crtc, + new_crtc_state, i) { + struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal; + + /* + * We store use_sagv_wm in the crtc state rather than relying on + * that bw state since we have no convenient way to get at the + * latter from the plane commit hooks (especially in the legacy + * cursor case) + */ + pipe_wm->use_sagv_wm = !HAS_HW_SAGV_WM(i915) && + DISPLAY_VER(i915) >= 12 && + intel_can_enable_sagv(i915, new_bw_state); + } + + return 0; +} + +static u16 skl_ddb_entry_init(struct skl_ddb_entry *entry, + u16 start, u16 end) +{ + entry->start = start; + entry->end = end; + + return end; +} + +static int intel_dbuf_slice_size(struct drm_i915_private *i915) +{ + return INTEL_INFO(i915)->display.dbuf.size / + hweight8(INTEL_INFO(i915)->display.dbuf.slice_mask); +} + +static void +skl_ddb_entry_for_slices(struct drm_i915_private *i915, u8 slice_mask, + struct skl_ddb_entry *ddb) +{ + int slice_size = intel_dbuf_slice_size(i915); + + if (!slice_mask) { + ddb->start = 0; + ddb->end = 0; + return; + } + + ddb->start = (ffs(slice_mask) - 1) * slice_size; + ddb->end = fls(slice_mask) * slice_size; + + WARN_ON(ddb->start >= ddb->end); + WARN_ON(ddb->end > INTEL_INFO(i915)->display.dbuf.size); +} + +static unsigned int mbus_ddb_offset(struct drm_i915_private *i915, u8 slice_mask) +{ + struct skl_ddb_entry ddb; + + if (slice_mask & (BIT(DBUF_S1) | BIT(DBUF_S2))) + slice_mask = BIT(DBUF_S1); + else if (slice_mask & (BIT(DBUF_S3) | BIT(DBUF_S4))) + slice_mask = BIT(DBUF_S3); + + skl_ddb_entry_for_slices(i915, slice_mask, &ddb); + + return ddb.start; +} + +u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *i915, + const struct skl_ddb_entry *entry) +{ + int slice_size = intel_dbuf_slice_size(i915); + enum dbuf_slice start_slice, end_slice; + u8 slice_mask = 0; + + if (!skl_ddb_entry_size(entry)) + return 0; + + start_slice = entry->start / slice_size; + end_slice = (entry->end - 1) / slice_size; + + /* + * Per plane DDB entry can in a really worst case be on multiple slices + * but single entry is anyway contigious. + */ + while (start_slice <= end_slice) { + slice_mask |= BIT(start_slice); + start_slice++; + } + + return slice_mask; +} + +static unsigned int intel_crtc_ddb_weight(const struct intel_crtc_state *crtc_state) +{ + const struct drm_display_mode *pipe_mode = &crtc_state->hw.pipe_mode; + int hdisplay, vdisplay; + + if (!crtc_state->hw.active) + return 0; + + /* + * Watermark/ddb requirement highly depends upon width of the + * framebuffer, So instead of allocating DDB equally among pipes + * distribute DDB based on resolution/width of the display. + */ + drm_mode_get_hv_timing(pipe_mode, &hdisplay, &vdisplay); + + return hdisplay; +} + +static void intel_crtc_dbuf_weights(const struct intel_dbuf_state *dbuf_state, + enum pipe for_pipe, + unsigned int *weight_start, + unsigned int *weight_end, + unsigned int *weight_total) +{ + struct drm_i915_private *i915 = + to_i915(dbuf_state->base.state->base.dev); + enum pipe pipe; + + *weight_start = 0; + *weight_end = 0; + *weight_total = 0; + + for_each_pipe(i915, pipe) { + int weight = dbuf_state->weight[pipe]; + + /* + * Do not account pipes using other slice sets + * luckily as of current BSpec slice sets do not partially + * intersect(pipes share either same one slice or same slice set + * i.e no partial intersection), so it is enough to check for + * equality for now. + */ + if (dbuf_state->slices[pipe] != dbuf_state->slices[for_pipe]) + continue; + + *weight_total += weight; + if (pipe < for_pipe) { + *weight_start += weight; + *weight_end += weight; + } else if (pipe == for_pipe) { + *weight_end += weight; + } + } +} + +static int +skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + unsigned int weight_total, weight_start, weight_end; + const struct intel_dbuf_state *old_dbuf_state = + intel_atomic_get_old_dbuf_state(state); + struct intel_dbuf_state *new_dbuf_state = + intel_atomic_get_new_dbuf_state(state); + struct intel_crtc_state *crtc_state; + struct skl_ddb_entry ddb_slices; + enum pipe pipe = crtc->pipe; + unsigned int mbus_offset = 0; + u32 ddb_range_size; + u32 dbuf_slice_mask; + u32 start, end; + int ret; + + if (new_dbuf_state->weight[pipe] == 0) { + skl_ddb_entry_init(&new_dbuf_state->ddb[pipe], 0, 0); + goto out; + } + + dbuf_slice_mask = new_dbuf_state->slices[pipe]; + + skl_ddb_entry_for_slices(i915, dbuf_slice_mask, &ddb_slices); + mbus_offset = mbus_ddb_offset(i915, dbuf_slice_mask); + ddb_range_size = skl_ddb_entry_size(&ddb_slices); + + intel_crtc_dbuf_weights(new_dbuf_state, pipe, + &weight_start, &weight_end, &weight_total); + + start = ddb_range_size * weight_start / weight_total; + end = ddb_range_size * weight_end / weight_total; + + skl_ddb_entry_init(&new_dbuf_state->ddb[pipe], + ddb_slices.start - mbus_offset + start, + ddb_slices.start - mbus_offset + end); + +out: + if (old_dbuf_state->slices[pipe] == new_dbuf_state->slices[pipe] && + skl_ddb_entry_equal(&old_dbuf_state->ddb[pipe], + &new_dbuf_state->ddb[pipe])) + return 0; + + ret = intel_atomic_lock_global_state(&new_dbuf_state->base); + if (ret) + return ret; + + crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); + if (IS_ERR(crtc_state)) + return PTR_ERR(crtc_state); + + /* + * Used for checking overlaps, so we need absolute + * offsets instead of MBUS relative offsets. + */ + crtc_state->wm.skl.ddb.start = mbus_offset + new_dbuf_state->ddb[pipe].start; + crtc_state->wm.skl.ddb.end = mbus_offset + new_dbuf_state->ddb[pipe].end; + + drm_dbg_kms(&i915->drm, + "[CRTC:%d:%s] dbuf slices 0x%x -> 0x%x, ddb (%d - %d) -> (%d - %d), active pipes 0x%x -> 0x%x\n", + crtc->base.base.id, crtc->base.name, + old_dbuf_state->slices[pipe], new_dbuf_state->slices[pipe], + old_dbuf_state->ddb[pipe].start, old_dbuf_state->ddb[pipe].end, + new_dbuf_state->ddb[pipe].start, new_dbuf_state->ddb[pipe].end, + old_dbuf_state->active_pipes, new_dbuf_state->active_pipes); + + return 0; +} + +static int skl_compute_wm_params(const struct intel_crtc_state *crtc_state, + int width, const struct drm_format_info *format, + u64 modifier, unsigned int rotation, + u32 plane_pixel_rate, struct skl_wm_params *wp, + int color_plane); + +static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, + struct intel_plane *plane, + int level, + unsigned int latency, + const struct skl_wm_params *wp, + const struct skl_wm_level *result_prev, + struct skl_wm_level *result /* out */); + +static unsigned int +skl_cursor_allocation(const struct intel_crtc_state *crtc_state, + int num_active) +{ + struct intel_plane *plane = to_intel_plane(crtc_state->uapi.crtc->cursor); + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + int level, max_level = ilk_wm_max_level(i915); + struct skl_wm_level wm = {}; + int ret, min_ddb_alloc = 0; + struct skl_wm_params wp; + + ret = skl_compute_wm_params(crtc_state, 256, + drm_format_info(DRM_FORMAT_ARGB8888), + DRM_FORMAT_MOD_LINEAR, + DRM_MODE_ROTATE_0, + crtc_state->pixel_rate, &wp, 0); + drm_WARN_ON(&i915->drm, ret); + + for (level = 0; level <= max_level; level++) { + unsigned int latency = i915->display.wm.skl_latency[level]; + + skl_compute_plane_wm(crtc_state, plane, level, latency, &wp, &wm, &wm); + if (wm.min_ddb_alloc == U16_MAX) + break; + + min_ddb_alloc = wm.min_ddb_alloc; + } + + return max(num_active == 1 ? 32 : 8, min_ddb_alloc); +} + +static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg) +{ + skl_ddb_entry_init(entry, + REG_FIELD_GET(PLANE_BUF_START_MASK, reg), + REG_FIELD_GET(PLANE_BUF_END_MASK, reg)); + if (entry->end) + entry->end++; +} + +static void +skl_ddb_get_hw_plane_state(struct drm_i915_private *i915, + const enum pipe pipe, + const enum plane_id plane_id, + struct skl_ddb_entry *ddb, + struct skl_ddb_entry *ddb_y) +{ + u32 val; + + /* Cursor doesn't support NV12/planar, so no extra calculation needed */ + if (plane_id == PLANE_CURSOR) { + val = intel_uncore_read(&i915->uncore, CUR_BUF_CFG(pipe)); + skl_ddb_entry_init_from_hw(ddb, val); + return; + } + + val = intel_uncore_read(&i915->uncore, PLANE_BUF_CFG(pipe, plane_id)); + skl_ddb_entry_init_from_hw(ddb, val); + + if (DISPLAY_VER(i915) >= 11) + return; + + val = intel_uncore_read(&i915->uncore, PLANE_NV12_BUF_CFG(pipe, plane_id)); + skl_ddb_entry_init_from_hw(ddb_y, val); +} + +static void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc, + struct skl_ddb_entry *ddb, + struct skl_ddb_entry *ddb_y) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + enum intel_display_power_domain power_domain; + enum pipe pipe = crtc->pipe; + intel_wakeref_t wakeref; + enum plane_id plane_id; + + power_domain = POWER_DOMAIN_PIPE(pipe); + wakeref = intel_display_power_get_if_enabled(i915, power_domain); + if (!wakeref) + return; + + for_each_plane_id_on_crtc(crtc, plane_id) + skl_ddb_get_hw_plane_state(i915, pipe, + plane_id, + &ddb[plane_id], + &ddb_y[plane_id]); + + intel_display_power_put(i915, power_domain, wakeref); +} + +struct dbuf_slice_conf_entry { + u8 active_pipes; + u8 dbuf_mask[I915_MAX_PIPES]; + bool join_mbus; +}; + +/* + * Table taken from Bspec 12716 + * Pipes do have some preferred DBuf slice affinity, + * plus there are some hardcoded requirements on how + * those should be distributed for multipipe scenarios. + * For more DBuf slices algorithm can get even more messy + * and less readable, so decided to use a table almost + * as is from BSpec itself - that way it is at least easier + * to compare, change and check. + */ +static const struct dbuf_slice_conf_entry icl_allowed_dbufs[] = +/* Autogenerated with igt/tools/intel_dbuf_map tool: */ +{ + { + .active_pipes = BIT(PIPE_A), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + }, + }, + { + .active_pipes = BIT(PIPE_B), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_C), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + }, + }, + {} +}; + +/* + * Table taken from Bspec 49255 + * Pipes do have some preferred DBuf slice affinity, + * plus there are some hardcoded requirements on how + * those should be distributed for multipipe scenarios. + * For more DBuf slices algorithm can get even more messy + * and less readable, so decided to use a table almost + * as is from BSpec itself - that way it is at least easier + * to compare, change and check. + */ +static const struct dbuf_slice_conf_entry tgl_allowed_dbufs[] = +/* Autogenerated with igt/tools/intel_dbuf_map tool: */ +{ + { + .active_pipes = BIT(PIPE_A), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S1), + }, + }, + { + .active_pipes = BIT(PIPE_C), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S2) | BIT(DBUF_S1), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_D), + .dbuf_mask = { + [PIPE_D] = BIT(DBUF_S2) | BIT(DBUF_S1), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S1), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S1), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S1), + [PIPE_C] = BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S2), + }, + }, + {} +}; + +static const struct dbuf_slice_conf_entry dg2_allowed_dbufs[] = { + { + .active_pipes = BIT(PIPE_A), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_C), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_D), + .dbuf_mask = { + [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S3), + [PIPE_D] = BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3), + [PIPE_D] = BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3), + [PIPE_D] = BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1), + [PIPE_B] = BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3), + [PIPE_D] = BIT(DBUF_S4), + }, + }, + {} +}; + +static const struct dbuf_slice_conf_entry adlp_allowed_dbufs[] = { + /* + * Keep the join_mbus cases first so check_mbus_joined() + * will prefer them over the !join_mbus cases. + */ + { + .active_pipes = BIT(PIPE_A), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4), + }, + .join_mbus = true, + }, + { + .active_pipes = BIT(PIPE_B), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4), + }, + .join_mbus = true, + }, + { + .active_pipes = BIT(PIPE_A), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + .join_mbus = false, + }, + { + .active_pipes = BIT(PIPE_B), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + .join_mbus = false, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_C), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + }, + }, + { + .active_pipes = BIT(PIPE_D), + .dbuf_mask = { + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + { + .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .dbuf_mask = { + [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), + [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), + [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), + }, + }, + {} + +}; + +static bool check_mbus_joined(u8 active_pipes, + const struct dbuf_slice_conf_entry *dbuf_slices) +{ + int i; + + for (i = 0; dbuf_slices[i].active_pipes != 0; i++) { + if (dbuf_slices[i].active_pipes == active_pipes) + return dbuf_slices[i].join_mbus; + } + return false; +} + +static bool adlp_check_mbus_joined(u8 active_pipes) +{ + return check_mbus_joined(active_pipes, adlp_allowed_dbufs); +} + +static u8 compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus, + const struct dbuf_slice_conf_entry *dbuf_slices) +{ + int i; + + for (i = 0; dbuf_slices[i].active_pipes != 0; i++) { + if (dbuf_slices[i].active_pipes == active_pipes && + dbuf_slices[i].join_mbus == join_mbus) + return dbuf_slices[i].dbuf_mask[pipe]; + } + return 0; +} + +/* + * This function finds an entry with same enabled pipe configuration and + * returns correspondent DBuf slice mask as stated in BSpec for particular + * platform. + */ +static u8 icl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) +{ + /* + * FIXME: For ICL this is still a bit unclear as prev BSpec revision + * required calculating "pipe ratio" in order to determine + * if one or two slices can be used for single pipe configurations + * as additional constraint to the existing table. + * However based on recent info, it should be not "pipe ratio" + * but rather ratio between pixel_rate and cdclk with additional + * constants, so for now we are using only table until this is + * clarified. Also this is the reason why crtc_state param is + * still here - we will need it once those additional constraints + * pop up. + */ + return compute_dbuf_slices(pipe, active_pipes, join_mbus, + icl_allowed_dbufs); +} + +static u8 tgl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) +{ + return compute_dbuf_slices(pipe, active_pipes, join_mbus, + tgl_allowed_dbufs); +} + +static u8 adlp_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) +{ + return compute_dbuf_slices(pipe, active_pipes, join_mbus, + adlp_allowed_dbufs); +} + +static u8 dg2_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) +{ + return compute_dbuf_slices(pipe, active_pipes, join_mbus, + dg2_allowed_dbufs); +} + +static u8 skl_compute_dbuf_slices(struct intel_crtc *crtc, u8 active_pipes, bool join_mbus) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; + + if (IS_DG2(i915)) + return dg2_compute_dbuf_slices(pipe, active_pipes, join_mbus); + else if (DISPLAY_VER(i915) >= 13) + return adlp_compute_dbuf_slices(pipe, active_pipes, join_mbus); + else if (DISPLAY_VER(i915) == 12) + return tgl_compute_dbuf_slices(pipe, active_pipes, join_mbus); + else if (DISPLAY_VER(i915) == 11) + return icl_compute_dbuf_slices(pipe, active_pipes, join_mbus); + /* + * For anything else just return one slice yet. + * Should be extended for other platforms. + */ + return active_pipes & BIT(pipe) ? BIT(DBUF_S1) : 0; +} + +static bool +use_minimal_wm0_only(const struct intel_crtc_state *crtc_state, + struct intel_plane *plane) +{ + struct drm_i915_private *i915 = to_i915(plane->base.dev); + + return DISPLAY_VER(i915) >= 13 && + crtc_state->uapi.async_flip && + plane->async_flip; +} + +static u64 +skl_total_relative_data_rate(const struct intel_crtc_state *crtc_state) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + enum plane_id plane_id; + u64 data_rate = 0; + + for_each_plane_id_on_crtc(crtc, plane_id) { + if (plane_id == PLANE_CURSOR) + continue; + + data_rate += crtc_state->rel_data_rate[plane_id]; + + if (DISPLAY_VER(i915) < 11) + data_rate += crtc_state->rel_data_rate_y[plane_id]; + } + + return data_rate; +} + +static const struct skl_wm_level * +skl_plane_wm_level(const struct skl_pipe_wm *pipe_wm, + enum plane_id plane_id, + int level) +{ + const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + + if (level == 0 && pipe_wm->use_sagv_wm) + return &wm->sagv.wm0; + + return &wm->wm[level]; +} + +static const struct skl_wm_level * +skl_plane_trans_wm(const struct skl_pipe_wm *pipe_wm, + enum plane_id plane_id) +{ + const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + + if (pipe_wm->use_sagv_wm) + return &wm->sagv.trans_wm; + + return &wm->trans_wm; +} + +/* + * We only disable the watermarks for each plane if + * they exceed the ddb allocation of said plane. This + * is done so that we don't end up touching cursor + * watermarks needlessly when some other plane reduces + * our max possible watermark level. + * + * Bspec has this to say about the PLANE_WM enable bit: + * "All the watermarks at this level for all enabled + * planes must be enabled before the level will be used." + * So this is actually safe to do. + */ +static void +skl_check_wm_level(struct skl_wm_level *wm, const struct skl_ddb_entry *ddb) +{ + if (wm->min_ddb_alloc > skl_ddb_entry_size(ddb)) + memset(wm, 0, sizeof(*wm)); +} + +static void +skl_check_nv12_wm_level(struct skl_wm_level *wm, struct skl_wm_level *uv_wm, + const struct skl_ddb_entry *ddb_y, const struct skl_ddb_entry *ddb) +{ + if (wm->min_ddb_alloc > skl_ddb_entry_size(ddb_y) || + uv_wm->min_ddb_alloc > skl_ddb_entry_size(ddb)) { + memset(wm, 0, sizeof(*wm)); + memset(uv_wm, 0, sizeof(*uv_wm)); + } +} + +static bool icl_need_wm1_wa(struct drm_i915_private *i915, + enum plane_id plane_id) +{ + /* + * Wa_1408961008:icl, ehl + * Wa_14012656716:tgl, adl + * Underruns with WM1+ disabled + */ + return DISPLAY_VER(i915) == 11 || + (IS_DISPLAY_VER(i915, 12, 13) && plane_id == PLANE_CURSOR); +} + +struct skl_plane_ddb_iter { + u64 data_rate; + u16 start, size; +}; + +static void +skl_allocate_plane_ddb(struct skl_plane_ddb_iter *iter, + struct skl_ddb_entry *ddb, + const struct skl_wm_level *wm, + u64 data_rate) +{ + u16 size, extra = 0; + + if (data_rate) { + extra = min_t(u16, iter->size, + DIV64_U64_ROUND_UP(iter->size * data_rate, + iter->data_rate)); + iter->size -= extra; + iter->data_rate -= data_rate; + } + + /* + * Keep ddb entry of all disabled planes explicitly zeroed + * to avoid skl_ddb_add_affected_planes() adding them to + * the state when other planes change their allocations. + */ + size = wm->min_ddb_alloc + extra; + if (size) + iter->start = skl_ddb_entry_init(ddb, iter->start, + iter->start + size); +} + +static int +skl_crtc_allocate_plane_ddb(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_dbuf_state *dbuf_state = + intel_atomic_get_new_dbuf_state(state); + const struct skl_ddb_entry *alloc = &dbuf_state->ddb[crtc->pipe]; + int num_active = hweight8(dbuf_state->active_pipes); + struct skl_plane_ddb_iter iter; + enum plane_id plane_id; + u16 cursor_size; + u32 blocks; + int level; + + /* Clear the partitioning for disabled planes. */ + memset(crtc_state->wm.skl.plane_ddb, 0, sizeof(crtc_state->wm.skl.plane_ddb)); + memset(crtc_state->wm.skl.plane_ddb_y, 0, sizeof(crtc_state->wm.skl.plane_ddb_y)); + + if (!crtc_state->hw.active) + return 0; + + iter.start = alloc->start; + iter.size = skl_ddb_entry_size(alloc); + if (iter.size == 0) + return 0; + + /* Allocate fixed number of blocks for cursor. */ + cursor_size = skl_cursor_allocation(crtc_state, num_active); + iter.size -= cursor_size; + skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[PLANE_CURSOR], + alloc->end - cursor_size, alloc->end); + + iter.data_rate = skl_total_relative_data_rate(crtc_state); + + /* + * Find the highest watermark level for which we can satisfy the block + * requirement of active planes. + */ + for (level = ilk_wm_max_level(i915); level >= 0; level--) { + blocks = 0; + for_each_plane_id_on_crtc(crtc, plane_id) { + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + + if (plane_id == PLANE_CURSOR) { + const struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + + if (wm->wm[level].min_ddb_alloc > skl_ddb_entry_size(ddb)) { + drm_WARN_ON(&i915->drm, + wm->wm[level].min_ddb_alloc != U16_MAX); + blocks = U32_MAX; + break; + } + continue; + } + + blocks += wm->wm[level].min_ddb_alloc; + blocks += wm->uv_wm[level].min_ddb_alloc; + } + + if (blocks <= iter.size) { + iter.size -= blocks; + break; + } + } + + if (level < 0) { + drm_dbg_kms(&i915->drm, + "Requested display configuration exceeds system DDB limitations"); + drm_dbg_kms(&i915->drm, "minimum required %d/%d\n", + blocks, iter.size); + return -EINVAL; + } + + /* avoid the WARN later when we don't allocate any extra DDB */ + if (iter.data_rate == 0) + iter.size = 0; + + /* + * Grant each plane the blocks it requires at the highest achievable + * watermark level, plus an extra share of the leftover blocks + * proportional to its relative data rate. + */ + for_each_plane_id_on_crtc(crtc, plane_id) { + struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + struct skl_ddb_entry *ddb_y = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; + const struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + + if (plane_id == PLANE_CURSOR) + continue; + + if (DISPLAY_VER(i915) < 11 && + crtc_state->nv12_planes & BIT(plane_id)) { + skl_allocate_plane_ddb(&iter, ddb_y, &wm->wm[level], + crtc_state->rel_data_rate_y[plane_id]); + skl_allocate_plane_ddb(&iter, ddb, &wm->uv_wm[level], + crtc_state->rel_data_rate[plane_id]); + } else { + skl_allocate_plane_ddb(&iter, ddb, &wm->wm[level], + crtc_state->rel_data_rate[plane_id]); + } + } + drm_WARN_ON(&i915->drm, iter.size != 0 || iter.data_rate != 0); + + /* + * When we calculated watermark values we didn't know how high + * of a level we'd actually be able to hit, so we just marked + * all levels as "enabled." Go back now and disable the ones + * that aren't actually possible. + */ + for (level++; level <= ilk_wm_max_level(i915); level++) { + for_each_plane_id_on_crtc(crtc, plane_id) { + const struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + const struct skl_ddb_entry *ddb_y = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; + struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + + if (DISPLAY_VER(i915) < 11 && + crtc_state->nv12_planes & BIT(plane_id)) + skl_check_nv12_wm_level(&wm->wm[level], + &wm->uv_wm[level], + ddb_y, ddb); + else + skl_check_wm_level(&wm->wm[level], ddb); + + if (icl_need_wm1_wa(i915, plane_id) && + level == 1 && wm->wm[0].enable) { + wm->wm[level].blocks = wm->wm[0].blocks; + wm->wm[level].lines = wm->wm[0].lines; + wm->wm[level].ignore_lines = wm->wm[0].ignore_lines; + } + } + } + + /* + * Go back and disable the transition and SAGV watermarks + * if it turns out we don't have enough DDB blocks for them. + */ + for_each_plane_id_on_crtc(crtc, plane_id) { + const struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + const struct skl_ddb_entry *ddb_y = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; + struct skl_plane_wm *wm = + &crtc_state->wm.skl.optimal.planes[plane_id]; + + if (DISPLAY_VER(i915) < 11 && + crtc_state->nv12_planes & BIT(plane_id)) { + skl_check_wm_level(&wm->trans_wm, ddb_y); + } else { + WARN_ON(skl_ddb_entry_size(ddb_y)); + + skl_check_wm_level(&wm->trans_wm, ddb); + } + + skl_check_wm_level(&wm->sagv.wm0, ddb); + skl_check_wm_level(&wm->sagv.trans_wm, ddb); + } + + return 0; +} + +/* + * The max latency should be 257 (max the punit can code is 255 and we add 2us + * for the read latency) and cpp should always be <= 8, so that + * should allow pixel_rate up to ~2 GHz which seems sufficient since max + * 2xcdclk is 1350 MHz and the pixel rate should never exceed that. + */ +static uint_fixed_16_16_t +skl_wm_method1(const struct drm_i915_private *i915, u32 pixel_rate, + u8 cpp, u32 latency, u32 dbuf_block_size) +{ + u32 wm_intermediate_val; + uint_fixed_16_16_t ret; + + if (latency == 0) + return FP_16_16_MAX; + + wm_intermediate_val = latency * pixel_rate * cpp; + ret = div_fixed16(wm_intermediate_val, 1000 * dbuf_block_size); + + if (DISPLAY_VER(i915) >= 10) + ret = add_fixed16_u32(ret, 1); + + return ret; +} + +static uint_fixed_16_16_t +skl_wm_method2(u32 pixel_rate, u32 pipe_htotal, u32 latency, + uint_fixed_16_16_t plane_blocks_per_line) +{ + u32 wm_intermediate_val; + uint_fixed_16_16_t ret; + + if (latency == 0) + return FP_16_16_MAX; + + wm_intermediate_val = latency * pixel_rate; + wm_intermediate_val = DIV_ROUND_UP(wm_intermediate_val, + pipe_htotal * 1000); + ret = mul_u32_fixed16(wm_intermediate_val, plane_blocks_per_line); + return ret; +} + +static uint_fixed_16_16_t +intel_get_linetime_us(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + u32 pixel_rate; + u32 crtc_htotal; + uint_fixed_16_16_t linetime_us; + + if (!crtc_state->hw.active) + return u32_to_fixed16(0); + + pixel_rate = crtc_state->pixel_rate; + + if (drm_WARN_ON(&i915->drm, pixel_rate == 0)) + return u32_to_fixed16(0); + + crtc_htotal = crtc_state->hw.pipe_mode.crtc_htotal; + linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate); + + return linetime_us; +} + +static int +skl_compute_wm_params(const struct intel_crtc_state *crtc_state, + int width, const struct drm_format_info *format, + u64 modifier, unsigned int rotation, + u32 plane_pixel_rate, struct skl_wm_params *wp, + int color_plane) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + u32 interm_pbpl; + + /* only planar format has two planes */ + if (color_plane == 1 && + !intel_format_info_is_yuv_semiplanar(format, modifier)) { + drm_dbg_kms(&i915->drm, + "Non planar format have single plane\n"); + return -EINVAL; + } + + wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED || + modifier == I915_FORMAT_MOD_4_TILED || + modifier == I915_FORMAT_MOD_Yf_TILED || + modifier == I915_FORMAT_MOD_Y_TILED_CCS || + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC; + wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; + wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_MC_CCS || + modifier == I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC; + wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); + + wp->width = width; + if (color_plane == 1 && wp->is_planar) + wp->width /= 2; + + wp->cpp = format->cpp[color_plane]; + wp->plane_pixel_rate = plane_pixel_rate; + + if (DISPLAY_VER(i915) >= 11 && + modifier == I915_FORMAT_MOD_Yf_TILED && wp->cpp == 1) + wp->dbuf_block_size = 256; + else + wp->dbuf_block_size = 512; + + if (drm_rotation_90_or_270(rotation)) { + switch (wp->cpp) { + case 1: + wp->y_min_scanlines = 16; + break; + case 2: + wp->y_min_scanlines = 8; + break; + case 4: + wp->y_min_scanlines = 4; + break; + default: + MISSING_CASE(wp->cpp); + return -EINVAL; + } + } else { + wp->y_min_scanlines = 4; + } + + if (skl_needs_memory_bw_wa(i915)) + wp->y_min_scanlines *= 2; + + wp->plane_bytes_per_line = wp->width * wp->cpp; + if (wp->y_tiled) { + interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line * + wp->y_min_scanlines, + wp->dbuf_block_size); + + if (DISPLAY_VER(i915) >= 10) + interm_pbpl++; + + wp->plane_blocks_per_line = div_fixed16(interm_pbpl, + wp->y_min_scanlines); + } else { + interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, + wp->dbuf_block_size); + + if (!wp->x_tiled || DISPLAY_VER(i915) >= 10) + interm_pbpl++; + + wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl); + } + + wp->y_tile_minimum = mul_u32_fixed16(wp->y_min_scanlines, + wp->plane_blocks_per_line); + + wp->linetime_us = fixed16_to_u32_round_up(intel_get_linetime_us(crtc_state)); + + return 0; +} + +static int +skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + struct skl_wm_params *wp, int color_plane) +{ + const struct drm_framebuffer *fb = plane_state->hw.fb; + int width; + + /* + * Src coordinates are already rotated by 270 degrees for + * the 90/270 degree plane rotation cases (to match the + * GTT mapping), hence no need to account for rotation here. + */ + width = drm_rect_width(&plane_state->uapi.src) >> 16; + + return skl_compute_wm_params(crtc_state, width, + fb->format, fb->modifier, + plane_state->hw.rotation, + intel_plane_pixel_rate(crtc_state, plane_state), + wp, color_plane); +} + +static bool skl_wm_has_lines(struct drm_i915_private *i915, int level) +{ + if (DISPLAY_VER(i915) >= 10) + return true; + + /* The number of lines are ignored for the level 0 watermark. */ + return level > 0; +} + +static int skl_wm_max_lines(struct drm_i915_private *i915) +{ + if (DISPLAY_VER(i915) >= 13) + return 255; + else + return 31; +} + +static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, + struct intel_plane *plane, + int level, + unsigned int latency, + const struct skl_wm_params *wp, + const struct skl_wm_level *result_prev, + struct skl_wm_level *result /* out */) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + uint_fixed_16_16_t method1, method2; + uint_fixed_16_16_t selected_result; + u32 blocks, lines, min_ddb_alloc = 0; + + if (latency == 0 || + (use_minimal_wm0_only(crtc_state, plane) && level > 0)) { + /* reject it */ + result->min_ddb_alloc = U16_MAX; + return; + } + + /* + * WaIncreaseLatencyIPCEnabled: kbl,cfl + * Display WA #1141: kbl,cfl + */ + if ((IS_KABYLAKE(i915) || IS_COFFEELAKE(i915) || IS_COMETLAKE(i915)) && + skl_watermark_ipc_enabled(i915)) + latency += 4; + + if (skl_needs_memory_bw_wa(i915) && wp->x_tiled) + latency += 15; + + method1 = skl_wm_method1(i915, wp->plane_pixel_rate, + wp->cpp, latency, wp->dbuf_block_size); + method2 = skl_wm_method2(wp->plane_pixel_rate, + crtc_state->hw.pipe_mode.crtc_htotal, + latency, + wp->plane_blocks_per_line); + + if (wp->y_tiled) { + selected_result = max_fixed16(method2, wp->y_tile_minimum); + } else { + if ((wp->cpp * crtc_state->hw.pipe_mode.crtc_htotal / + wp->dbuf_block_size < 1) && + (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) { + selected_result = method2; + } else if (latency >= wp->linetime_us) { + if (DISPLAY_VER(i915) == 9) + selected_result = min_fixed16(method1, method2); + else + selected_result = method2; + } else { + selected_result = method1; + } + } + + blocks = fixed16_to_u32_round_up(selected_result) + 1; + /* + * Lets have blocks at minimum equivalent to plane_blocks_per_line + * as there will be at minimum one line for lines configuration. This + * is a work around for FIFO underruns observed with resolutions like + * 4k 60 Hz in single channel DRAM configurations. + * + * As per the Bspec 49325, if the ddb allocation can hold at least + * one plane_blocks_per_line, we should have selected method2 in + * the above logic. Assuming that modern versions have enough dbuf + * and method2 guarantees blocks equivalent to at least 1 line, + * select the blocks as plane_blocks_per_line. + * + * TODO: Revisit the logic when we have better understanding on DRAM + * channels' impact on the level 0 memory latency and the relevant + * wm calculations. + */ + if (skl_wm_has_lines(i915, level)) + blocks = max(blocks, + fixed16_to_u32_round_up(wp->plane_blocks_per_line)); + lines = div_round_up_fixed16(selected_result, + wp->plane_blocks_per_line); + + if (DISPLAY_VER(i915) == 9) { + /* Display WA #1125: skl,bxt,kbl */ + if (level == 0 && wp->rc_surface) + blocks += fixed16_to_u32_round_up(wp->y_tile_minimum); + + /* Display WA #1126: skl,bxt,kbl */ + if (level >= 1 && level <= 7) { + if (wp->y_tiled) { + blocks += fixed16_to_u32_round_up(wp->y_tile_minimum); + lines += wp->y_min_scanlines; + } else { + blocks++; + } + + /* + * Make sure result blocks for higher latency levels are + * at least as high as level below the current level. + * Assumption in DDB algorithm optimization for special + * cases. Also covers Display WA #1125 for RC. + */ + if (result_prev->blocks > blocks) + blocks = result_prev->blocks; + } + } + + if (DISPLAY_VER(i915) >= 11) { + if (wp->y_tiled) { + int extra_lines; + + if (lines % wp->y_min_scanlines == 0) + extra_lines = wp->y_min_scanlines; + else + extra_lines = wp->y_min_scanlines * 2 - + lines % wp->y_min_scanlines; + + min_ddb_alloc = mul_round_up_u32_fixed16(lines + extra_lines, + wp->plane_blocks_per_line); + } else { + min_ddb_alloc = blocks + DIV_ROUND_UP(blocks, 10); + } + } + + if (!skl_wm_has_lines(i915, level)) + lines = 0; + + if (lines > skl_wm_max_lines(i915)) { + /* reject it */ + result->min_ddb_alloc = U16_MAX; + return; + } + + /* + * If lines is valid, assume we can use this watermark level + * for now. We'll come back and disable it after we calculate the + * DDB allocation if it turns out we don't actually have enough + * blocks to satisfy it. + */ + result->blocks = blocks; + result->lines = lines; + /* Bspec says: value >= plane ddb allocation -> invalid, hence the +1 here */ + result->min_ddb_alloc = max(min_ddb_alloc, blocks) + 1; + result->enable = true; + + if (DISPLAY_VER(i915) < 12 && i915->display.sagv.block_time_us) + result->can_sagv = latency >= i915->display.sagv.block_time_us; +} + +static void +skl_compute_wm_levels(const struct intel_crtc_state *crtc_state, + struct intel_plane *plane, + const struct skl_wm_params *wm_params, + struct skl_wm_level *levels) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + int level, max_level = ilk_wm_max_level(i915); + struct skl_wm_level *result_prev = &levels[0]; + + for (level = 0; level <= max_level; level++) { + struct skl_wm_level *result = &levels[level]; + unsigned int latency = i915->display.wm.skl_latency[level]; + + skl_compute_plane_wm(crtc_state, plane, level, latency, + wm_params, result_prev, result); + + result_prev = result; + } +} + +static void tgl_compute_sagv_wm(const struct intel_crtc_state *crtc_state, + struct intel_plane *plane, + const struct skl_wm_params *wm_params, + struct skl_plane_wm *plane_wm) +{ + struct drm_i915_private *i915 = to_i915(crtc_state->uapi.crtc->dev); + struct skl_wm_level *sagv_wm = &plane_wm->sagv.wm0; + struct skl_wm_level *levels = plane_wm->wm; + unsigned int latency = 0; + + if (i915->display.sagv.block_time_us) + latency = i915->display.sagv.block_time_us + i915->display.wm.skl_latency[0]; + + skl_compute_plane_wm(crtc_state, plane, 0, latency, + wm_params, &levels[0], + sagv_wm); +} + +static void skl_compute_transition_wm(struct drm_i915_private *i915, + struct skl_wm_level *trans_wm, + const struct skl_wm_level *wm0, + const struct skl_wm_params *wp) +{ + u16 trans_min, trans_amount, trans_y_tile_min; + u16 wm0_blocks, trans_offset, blocks; + + /* Transition WM don't make any sense if ipc is disabled */ + if (!skl_watermark_ipc_enabled(i915)) + return; + + /* + * WaDisableTWM:skl,kbl,cfl,bxt + * Transition WM are not recommended by HW team for GEN9 + */ + if (DISPLAY_VER(i915) == 9) + return; + + if (DISPLAY_VER(i915) >= 11) + trans_min = 4; + else + trans_min = 14; + + /* Display WA #1140: glk,cnl */ + if (DISPLAY_VER(i915) == 10) + trans_amount = 0; + else + trans_amount = 10; /* This is configurable amount */ + + trans_offset = trans_min + trans_amount; + + /* + * The spec asks for Selected Result Blocks for wm0 (the real value), + * not Result Blocks (the integer value). Pay attention to the capital + * letters. The value wm_l0->blocks is actually Result Blocks, but + * since Result Blocks is the ceiling of Selected Result Blocks plus 1, + * and since we later will have to get the ceiling of the sum in the + * transition watermarks calculation, we can just pretend Selected + * Result Blocks is Result Blocks minus 1 and it should work for the + * current platforms. + */ + wm0_blocks = wm0->blocks - 1; + + if (wp->y_tiled) { + trans_y_tile_min = + (u16)mul_round_up_u32_fixed16(2, wp->y_tile_minimum); + blocks = max(wm0_blocks, trans_y_tile_min) + trans_offset; + } else { + blocks = wm0_blocks + trans_offset; + } + blocks++; + + /* + * Just assume we can enable the transition watermark. After + * computing the DDB we'll come back and disable it if that + * assumption turns out to be false. + */ + trans_wm->blocks = blocks; + trans_wm->min_ddb_alloc = max_t(u16, wm0->min_ddb_alloc, blocks + 1); + trans_wm->enable = true; +} + +static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + struct intel_plane *plane, int color_plane) +{ + struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane->id]; + struct skl_wm_params wm_params; + int ret; + + ret = skl_compute_plane_wm_params(crtc_state, plane_state, + &wm_params, color_plane); + if (ret) + return ret; + + skl_compute_wm_levels(crtc_state, plane, &wm_params, wm->wm); + + skl_compute_transition_wm(i915, &wm->trans_wm, + &wm->wm[0], &wm_params); + + if (DISPLAY_VER(i915) >= 12) { + tgl_compute_sagv_wm(crtc_state, plane, &wm_params, wm); + + skl_compute_transition_wm(i915, &wm->sagv.trans_wm, + &wm->sagv.wm0, &wm_params); + } + + return 0; +} + +static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state, + struct intel_plane *plane) +{ + struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane->id]; + struct skl_wm_params wm_params; + int ret; + + wm->is_planar = true; + + /* uv plane watermarks must also be validated for NV12/Planar */ + ret = skl_compute_plane_wm_params(crtc_state, plane_state, + &wm_params, 1); + if (ret) + return ret; + + skl_compute_wm_levels(crtc_state, plane, &wm_params, wm->uv_wm); + + return 0; +} + +static int skl_build_plane_wm(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + enum plane_id plane_id = plane->id; + struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id]; + const struct drm_framebuffer *fb = plane_state->hw.fb; + int ret; + + memset(wm, 0, sizeof(*wm)); + + if (!intel_wm_plane_visible(crtc_state, plane_state)) + return 0; + + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane, 0); + if (ret) + return ret; + + if (fb->format->is_yuv && fb->format->num_planes > 1) { + ret = skl_build_plane_wm_uv(crtc_state, plane_state, + plane); + if (ret) + return ret; + } + + return 0; +} + +static int icl_build_plane_wm(struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) +{ + struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); + struct drm_i915_private *i915 = to_i915(plane->base.dev); + enum plane_id plane_id = plane->id; + struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id]; + int ret; + + /* Watermarks calculated in master */ + if (plane_state->planar_slave) + return 0; + + memset(wm, 0, sizeof(*wm)); + + if (plane_state->planar_linked_plane) { + const struct drm_framebuffer *fb = plane_state->hw.fb; + + drm_WARN_ON(&i915->drm, + !intel_wm_plane_visible(crtc_state, plane_state)); + drm_WARN_ON(&i915->drm, !fb->format->is_yuv || + fb->format->num_planes == 1); + + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane_state->planar_linked_plane, 0); + if (ret) + return ret; + + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane, 1); + if (ret) + return ret; + } else if (intel_wm_plane_visible(crtc_state, plane_state)) { + ret = skl_build_plane_wm_single(crtc_state, plane_state, + plane, 0); + if (ret) + return ret; + } + + return 0; +} + +static int skl_build_pipe_wm(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_crtc_state *crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + const struct intel_plane_state *plane_state; + struct intel_plane *plane; + int ret, i; + + for_each_new_intel_plane_in_state(state, plane, plane_state, i) { + /* + * FIXME should perhaps check {old,new}_plane_crtc->hw.crtc + * instead but we don't populate that correctly for NV12 Y + * planes so for now hack this. + */ + if (plane->pipe != crtc->pipe) + continue; + + if (DISPLAY_VER(i915) >= 11) + ret = icl_build_plane_wm(crtc_state, plane_state); + else + ret = skl_build_plane_wm(crtc_state, plane_state); + if (ret) + return ret; + } + + crtc_state->wm.skl.optimal = crtc_state->wm.skl.raw; + + return 0; +} + +static void skl_ddb_entry_write(struct drm_i915_private *i915, + i915_reg_t reg, + const struct skl_ddb_entry *entry) +{ + if (entry->end) + intel_de_write_fw(i915, reg, + PLANE_BUF_END(entry->end - 1) | + PLANE_BUF_START(entry->start)); + else + intel_de_write_fw(i915, reg, 0); +} + +static void skl_write_wm_level(struct drm_i915_private *i915, + i915_reg_t reg, + const struct skl_wm_level *level) +{ + u32 val = 0; + + if (level->enable) + val |= PLANE_WM_EN; + if (level->ignore_lines) + val |= PLANE_WM_IGNORE_LINES; + val |= REG_FIELD_PREP(PLANE_WM_BLOCKS_MASK, level->blocks); + val |= REG_FIELD_PREP(PLANE_WM_LINES_MASK, level->lines); + + intel_de_write_fw(i915, reg, val); +} + +void skl_write_plane_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(plane->base.dev); + int level, max_level = ilk_wm_max_level(i915); + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal; + const struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + const struct skl_ddb_entry *ddb_y = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; + + for (level = 0; level <= max_level; level++) + skl_write_wm_level(i915, PLANE_WM(pipe, plane_id, level), + skl_plane_wm_level(pipe_wm, plane_id, level)); + + skl_write_wm_level(i915, PLANE_WM_TRANS(pipe, plane_id), + skl_plane_trans_wm(pipe_wm, plane_id)); + + if (HAS_HW_SAGV_WM(i915)) { + const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + + skl_write_wm_level(i915, PLANE_WM_SAGV(pipe, plane_id), + &wm->sagv.wm0); + skl_write_wm_level(i915, PLANE_WM_SAGV_TRANS(pipe, plane_id), + &wm->sagv.trans_wm); + } + + skl_ddb_entry_write(i915, + PLANE_BUF_CFG(pipe, plane_id), ddb); + + if (DISPLAY_VER(i915) < 11) + skl_ddb_entry_write(i915, + PLANE_NV12_BUF_CFG(pipe, plane_id), ddb_y); +} + +void skl_write_cursor_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *i915 = to_i915(plane->base.dev); + int level, max_level = ilk_wm_max_level(i915); + enum plane_id plane_id = plane->id; + enum pipe pipe = plane->pipe; + const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal; + const struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + + for (level = 0; level <= max_level; level++) + skl_write_wm_level(i915, CUR_WM(pipe, level), + skl_plane_wm_level(pipe_wm, plane_id, level)); + + skl_write_wm_level(i915, CUR_WM_TRANS(pipe), + skl_plane_trans_wm(pipe_wm, plane_id)); + + if (HAS_HW_SAGV_WM(i915)) { + const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; + + skl_write_wm_level(i915, CUR_WM_SAGV(pipe), + &wm->sagv.wm0); + skl_write_wm_level(i915, CUR_WM_SAGV_TRANS(pipe), + &wm->sagv.trans_wm); + } + + skl_ddb_entry_write(i915, CUR_BUF_CFG(pipe), ddb); +} + +static bool skl_wm_level_equals(const struct skl_wm_level *l1, + const struct skl_wm_level *l2) +{ + return l1->enable == l2->enable && + l1->ignore_lines == l2->ignore_lines && + l1->lines == l2->lines && + l1->blocks == l2->blocks; +} + +static bool skl_plane_wm_equals(struct drm_i915_private *i915, + const struct skl_plane_wm *wm1, + const struct skl_plane_wm *wm2) +{ + int level, max_level = ilk_wm_max_level(i915); + + for (level = 0; level <= max_level; level++) { + /* + * We don't check uv_wm as the hardware doesn't actually + * use it. It only gets used for calculating the required + * ddb allocation. + */ + if (!skl_wm_level_equals(&wm1->wm[level], &wm2->wm[level])) + return false; + } + + return skl_wm_level_equals(&wm1->trans_wm, &wm2->trans_wm) && + skl_wm_level_equals(&wm1->sagv.wm0, &wm2->sagv.wm0) && + skl_wm_level_equals(&wm1->sagv.trans_wm, &wm2->sagv.trans_wm); +} + +static bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a, + const struct skl_ddb_entry *b) +{ + return a->start < b->end && b->start < a->end; +} + +static void skl_ddb_entry_union(struct skl_ddb_entry *a, + const struct skl_ddb_entry *b) +{ + if (a->end && b->end) { + a->start = min(a->start, b->start); + a->end = max(a->end, b->end); + } else if (b->end) { + a->start = b->start; + a->end = b->end; + } +} + +bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, + const struct skl_ddb_entry *entries, + int num_entries, int ignore_idx) +{ + int i; + + for (i = 0; i < num_entries; i++) { + if (i != ignore_idx && + skl_ddb_entries_overlap(ddb, &entries[i])) + return true; + } + + return false; +} + +static int +skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state, + struct intel_crtc_state *new_crtc_state) +{ + struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->uapi.state); + struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct intel_plane *plane; + + for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { + struct intel_plane_state *plane_state; + enum plane_id plane_id = plane->id; + + if (skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb[plane_id], + &new_crtc_state->wm.skl.plane_ddb[plane_id]) && + skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_y[plane_id], + &new_crtc_state->wm.skl.plane_ddb_y[plane_id])) + continue; + + plane_state = intel_atomic_get_plane_state(state, plane); + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + + new_crtc_state->update_planes |= BIT(plane_id); + } + + return 0; +} + +static u8 intel_dbuf_enabled_slices(const struct intel_dbuf_state *dbuf_state) +{ + struct drm_i915_private *i915 = to_i915(dbuf_state->base.state->base.dev); + u8 enabled_slices; + enum pipe pipe; + + /* + * FIXME: For now we always enable slice S1 as per + * the Bspec display initialization sequence. + */ + enabled_slices = BIT(DBUF_S1); + + for_each_pipe(i915, pipe) + enabled_slices |= dbuf_state->slices[pipe]; + + return enabled_slices; +} + +static int +skl_compute_ddb(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_dbuf_state *old_dbuf_state; + struct intel_dbuf_state *new_dbuf_state = NULL; + const struct intel_crtc_state *old_crtc_state; + struct intel_crtc_state *new_crtc_state; + struct intel_crtc *crtc; + int ret, i; + + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + new_dbuf_state = intel_atomic_get_dbuf_state(state); + if (IS_ERR(new_dbuf_state)) + return PTR_ERR(new_dbuf_state); + + old_dbuf_state = intel_atomic_get_old_dbuf_state(state); + break; + } + + if (!new_dbuf_state) + return 0; + + new_dbuf_state->active_pipes = + intel_calc_active_pipes(state, old_dbuf_state->active_pipes); + + if (old_dbuf_state->active_pipes != new_dbuf_state->active_pipes) { + ret = intel_atomic_lock_global_state(&new_dbuf_state->base); + if (ret) + return ret; + } + + if (HAS_MBUS_JOINING(i915)) + new_dbuf_state->joined_mbus = + adlp_check_mbus_joined(new_dbuf_state->active_pipes); + + for_each_intel_crtc(&i915->drm, crtc) { + enum pipe pipe = crtc->pipe; + + new_dbuf_state->slices[pipe] = + skl_compute_dbuf_slices(crtc, new_dbuf_state->active_pipes, + new_dbuf_state->joined_mbus); + + if (old_dbuf_state->slices[pipe] == new_dbuf_state->slices[pipe]) + continue; + + ret = intel_atomic_lock_global_state(&new_dbuf_state->base); + if (ret) + return ret; + } + + new_dbuf_state->enabled_slices = intel_dbuf_enabled_slices(new_dbuf_state); + + if (old_dbuf_state->enabled_slices != new_dbuf_state->enabled_slices || + old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { + ret = intel_atomic_serialize_global_state(&new_dbuf_state->base); + if (ret) + return ret; + + if (old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { + /* TODO: Implement vblank synchronized MBUS joining changes */ + ret = intel_modeset_all_pipes(state); + if (ret) + return ret; + } + + drm_dbg_kms(&i915->drm, + "Enabled dbuf slices 0x%x -> 0x%x (total dbuf slices 0x%x), mbus joined? %s->%s\n", + old_dbuf_state->enabled_slices, + new_dbuf_state->enabled_slices, + INTEL_INFO(i915)->display.dbuf.slice_mask, + str_yes_no(old_dbuf_state->joined_mbus), + str_yes_no(new_dbuf_state->joined_mbus)); + } + + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + enum pipe pipe = crtc->pipe; + + new_dbuf_state->weight[pipe] = intel_crtc_ddb_weight(new_crtc_state); + + if (old_dbuf_state->weight[pipe] == new_dbuf_state->weight[pipe]) + continue; + + ret = intel_atomic_lock_global_state(&new_dbuf_state->base); + if (ret) + return ret; + } + + for_each_intel_crtc(&i915->drm, crtc) { + ret = skl_crtc_allocate_ddb(state, crtc); + if (ret) + return ret; + } + + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, + new_crtc_state, i) { + ret = skl_crtc_allocate_plane_ddb(state, crtc); + if (ret) + return ret; + + ret = skl_ddb_add_affected_planes(old_crtc_state, + new_crtc_state); + if (ret) + return ret; + } + + return 0; +} + +static char enast(bool enable) +{ + return enable ? '*' : ' '; +} + +static void +skl_print_wm_changes(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_crtc_state *old_crtc_state; + const struct intel_crtc_state *new_crtc_state; + struct intel_plane *plane; + struct intel_crtc *crtc; + int i; + + if (!drm_debug_enabled(DRM_UT_KMS)) + return; + + for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, + new_crtc_state, i) { + const struct skl_pipe_wm *old_pipe_wm, *new_pipe_wm; + + old_pipe_wm = &old_crtc_state->wm.skl.optimal; + new_pipe_wm = &new_crtc_state->wm.skl.optimal; + + for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { + enum plane_id plane_id = plane->id; + const struct skl_ddb_entry *old, *new; + + old = &old_crtc_state->wm.skl.plane_ddb[plane_id]; + new = &new_crtc_state->wm.skl.plane_ddb[plane_id]; + + if (skl_ddb_entry_equal(old, new)) + continue; + + drm_dbg_kms(&i915->drm, + "[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n", + plane->base.base.id, plane->base.name, + old->start, old->end, new->start, new->end, + skl_ddb_entry_size(old), skl_ddb_entry_size(new)); + } + + for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { + enum plane_id plane_id = plane->id; + const struct skl_plane_wm *old_wm, *new_wm; + + old_wm = &old_pipe_wm->planes[plane_id]; + new_wm = &new_pipe_wm->planes[plane_id]; + + if (skl_plane_wm_equals(i915, old_wm, new_wm)) + continue; + + drm_dbg_kms(&i915->drm, + "[PLANE:%d:%s] level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm,%cstwm" + " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm,%cstwm\n", + plane->base.base.id, plane->base.name, + enast(old_wm->wm[0].enable), enast(old_wm->wm[1].enable), + enast(old_wm->wm[2].enable), enast(old_wm->wm[3].enable), + enast(old_wm->wm[4].enable), enast(old_wm->wm[5].enable), + enast(old_wm->wm[6].enable), enast(old_wm->wm[7].enable), + enast(old_wm->trans_wm.enable), + enast(old_wm->sagv.wm0.enable), + enast(old_wm->sagv.trans_wm.enable), + enast(new_wm->wm[0].enable), enast(new_wm->wm[1].enable), + enast(new_wm->wm[2].enable), enast(new_wm->wm[3].enable), + enast(new_wm->wm[4].enable), enast(new_wm->wm[5].enable), + enast(new_wm->wm[6].enable), enast(new_wm->wm[7].enable), + enast(new_wm->trans_wm.enable), + enast(new_wm->sagv.wm0.enable), + enast(new_wm->sagv.trans_wm.enable)); + + drm_dbg_kms(&i915->drm, + "[PLANE:%d:%s] lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%4d" + " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%4d\n", + plane->base.base.id, plane->base.name, + enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].lines, + enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].lines, + enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].lines, + enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].lines, + enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].lines, + enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].lines, + enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].lines, + enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].lines, + enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.lines, + enast(old_wm->sagv.wm0.ignore_lines), old_wm->sagv.wm0.lines, + enast(old_wm->sagv.trans_wm.ignore_lines), old_wm->sagv.trans_wm.lines, + enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].lines, + enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].lines, + enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].lines, + enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].lines, + enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].lines, + enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].lines, + enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].lines, + enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].lines, + enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.lines, + enast(new_wm->sagv.wm0.ignore_lines), new_wm->sagv.wm0.lines, + enast(new_wm->sagv.trans_wm.ignore_lines), new_wm->sagv.trans_wm.lines); + + drm_dbg_kms(&i915->drm, + "[PLANE:%d:%s] blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d" + " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d\n", + plane->base.base.id, plane->base.name, + old_wm->wm[0].blocks, old_wm->wm[1].blocks, + old_wm->wm[2].blocks, old_wm->wm[3].blocks, + old_wm->wm[4].blocks, old_wm->wm[5].blocks, + old_wm->wm[6].blocks, old_wm->wm[7].blocks, + old_wm->trans_wm.blocks, + old_wm->sagv.wm0.blocks, + old_wm->sagv.trans_wm.blocks, + new_wm->wm[0].blocks, new_wm->wm[1].blocks, + new_wm->wm[2].blocks, new_wm->wm[3].blocks, + new_wm->wm[4].blocks, new_wm->wm[5].blocks, + new_wm->wm[6].blocks, new_wm->wm[7].blocks, + new_wm->trans_wm.blocks, + new_wm->sagv.wm0.blocks, + new_wm->sagv.trans_wm.blocks); + + drm_dbg_kms(&i915->drm, + "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d" + " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d\n", + plane->base.base.id, plane->base.name, + old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc, + old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc, + old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc, + old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc, + old_wm->trans_wm.min_ddb_alloc, + old_wm->sagv.wm0.min_ddb_alloc, + old_wm->sagv.trans_wm.min_ddb_alloc, + new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc, + new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc, + new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc, + new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc, + new_wm->trans_wm.min_ddb_alloc, + new_wm->sagv.wm0.min_ddb_alloc, + new_wm->sagv.trans_wm.min_ddb_alloc); + } + } +} + +static bool skl_plane_selected_wm_equals(struct intel_plane *plane, + const struct skl_pipe_wm *old_pipe_wm, + const struct skl_pipe_wm *new_pipe_wm) +{ + struct drm_i915_private *i915 = to_i915(plane->base.dev); + int level, max_level = ilk_wm_max_level(i915); + + for (level = 0; level <= max_level; level++) { + /* + * We don't check uv_wm as the hardware doesn't actually + * use it. It only gets used for calculating the required + * ddb allocation. + */ + if (!skl_wm_level_equals(skl_plane_wm_level(old_pipe_wm, plane->id, level), + skl_plane_wm_level(new_pipe_wm, plane->id, level))) + return false; + } + + if (HAS_HW_SAGV_WM(i915)) { + const struct skl_plane_wm *old_wm = &old_pipe_wm->planes[plane->id]; + const struct skl_plane_wm *new_wm = &new_pipe_wm->planes[plane->id]; + + if (!skl_wm_level_equals(&old_wm->sagv.wm0, &new_wm->sagv.wm0) || + !skl_wm_level_equals(&old_wm->sagv.trans_wm, &new_wm->sagv.trans_wm)) + return false; + } + + return skl_wm_level_equals(skl_plane_trans_wm(old_pipe_wm, plane->id), + skl_plane_trans_wm(new_pipe_wm, plane->id)); +} + +/* + * To make sure the cursor watermark registers are always consistent + * with our computed state the following scenario needs special + * treatment: + * + * 1. enable cursor + * 2. move cursor entirely offscreen + * 3. disable cursor + * + * Step 2. does call .disable_plane() but does not zero the watermarks + * (since we consider an offscreen cursor still active for the purposes + * of watermarks). Step 3. would not normally call .disable_plane() + * because the actual plane visibility isn't changing, and we don't + * deallocate the cursor ddb until the pipe gets disabled. So we must + * force step 3. to call .disable_plane() to update the watermark + * registers properly. + * + * Other planes do not suffer from this issues as their watermarks are + * calculated based on the actual plane visibility. The only time this + * can trigger for the other planes is during the initial readout as the + * default value of the watermarks registers is not zero. + */ +static int skl_wm_add_affected_planes(struct intel_atomic_state *state, + struct intel_crtc *crtc) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + const struct intel_crtc_state *old_crtc_state = + intel_atomic_get_old_crtc_state(state, crtc); + struct intel_crtc_state *new_crtc_state = + intel_atomic_get_new_crtc_state(state, crtc); + struct intel_plane *plane; + + for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { + struct intel_plane_state *plane_state; + enum plane_id plane_id = plane->id; + + /* + * Force a full wm update for every plane on modeset. + * Required because the reset value of the wm registers + * is non-zero, whereas we want all disabled planes to + * have zero watermarks. So if we turn off the relevant + * power well the hardware state will go out of sync + * with the software state. + */ + if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) && + skl_plane_selected_wm_equals(plane, + &old_crtc_state->wm.skl.optimal, + &new_crtc_state->wm.skl.optimal)) + continue; + + plane_state = intel_atomic_get_plane_state(state, plane); + if (IS_ERR(plane_state)) + return PTR_ERR(plane_state); + + new_crtc_state->update_planes |= BIT(plane_id); + } + + return 0; +} + +static int +skl_compute_wm(struct intel_atomic_state *state) +{ + struct intel_crtc *crtc; + struct intel_crtc_state *new_crtc_state; + int ret, i; + + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + ret = skl_build_pipe_wm(state, crtc); + if (ret) + return ret; + } + + ret = skl_compute_ddb(state); + if (ret) + return ret; + + ret = intel_compute_sagv_mask(state); + if (ret) + return ret; + + /* + * skl_compute_ddb() will have adjusted the final watermarks + * based on how much ddb is available. Now we can actually + * check if the final watermarks changed. + */ + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + ret = skl_wm_add_affected_planes(state, crtc); + if (ret) + return ret; + } + + skl_print_wm_changes(state); + + return 0; +} + +static void skl_wm_level_from_reg_val(u32 val, struct skl_wm_level *level) +{ + level->enable = val & PLANE_WM_EN; + level->ignore_lines = val & PLANE_WM_IGNORE_LINES; + level->blocks = REG_FIELD_GET(PLANE_WM_BLOCKS_MASK, val); + level->lines = REG_FIELD_GET(PLANE_WM_LINES_MASK, val); +} + +static void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc, + struct skl_pipe_wm *out) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + enum pipe pipe = crtc->pipe; + int level, max_level; + enum plane_id plane_id; + u32 val; + + max_level = ilk_wm_max_level(i915); + + for_each_plane_id_on_crtc(crtc, plane_id) { + struct skl_plane_wm *wm = &out->planes[plane_id]; + + for (level = 0; level <= max_level; level++) { + if (plane_id != PLANE_CURSOR) + val = intel_uncore_read(&i915->uncore, PLANE_WM(pipe, plane_id, level)); + else + val = intel_uncore_read(&i915->uncore, CUR_WM(pipe, level)); + + skl_wm_level_from_reg_val(val, &wm->wm[level]); + } + + if (plane_id != PLANE_CURSOR) + val = intel_uncore_read(&i915->uncore, PLANE_WM_TRANS(pipe, plane_id)); + else + val = intel_uncore_read(&i915->uncore, CUR_WM_TRANS(pipe)); + + skl_wm_level_from_reg_val(val, &wm->trans_wm); + + if (HAS_HW_SAGV_WM(i915)) { + if (plane_id != PLANE_CURSOR) + val = intel_uncore_read(&i915->uncore, + PLANE_WM_SAGV(pipe, plane_id)); + else + val = intel_uncore_read(&i915->uncore, + CUR_WM_SAGV(pipe)); + + skl_wm_level_from_reg_val(val, &wm->sagv.wm0); + + if (plane_id != PLANE_CURSOR) + val = intel_uncore_read(&i915->uncore, + PLANE_WM_SAGV_TRANS(pipe, plane_id)); + else + val = intel_uncore_read(&i915->uncore, + CUR_WM_SAGV_TRANS(pipe)); + + skl_wm_level_from_reg_val(val, &wm->sagv.trans_wm); + } else if (DISPLAY_VER(i915) >= 12) { + wm->sagv.wm0 = wm->wm[0]; + wm->sagv.trans_wm = wm->trans_wm; + } + } +} + +void skl_wm_get_hw_state(struct drm_i915_private *i915) +{ + struct intel_dbuf_state *dbuf_state = + to_intel_dbuf_state(i915->display.dbuf.obj.state); + struct intel_crtc *crtc; + + if (HAS_MBUS_JOINING(i915)) + dbuf_state->joined_mbus = intel_de_read(i915, MBUS_CTL) & MBUS_JOIN; + + for_each_intel_crtc(&i915->drm, crtc) { + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + enum pipe pipe = crtc->pipe; + unsigned int mbus_offset; + enum plane_id plane_id; + u8 slices; + + memset(&crtc_state->wm.skl.optimal, 0, + sizeof(crtc_state->wm.skl.optimal)); + if (crtc_state->hw.active) + skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal); + crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal; + + memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe])); + + for_each_plane_id_on_crtc(crtc, plane_id) { + struct skl_ddb_entry *ddb = + &crtc_state->wm.skl.plane_ddb[plane_id]; + struct skl_ddb_entry *ddb_y = + &crtc_state->wm.skl.plane_ddb_y[plane_id]; + + if (!crtc_state->hw.active) + continue; + + skl_ddb_get_hw_plane_state(i915, crtc->pipe, + plane_id, ddb, ddb_y); + + skl_ddb_entry_union(&dbuf_state->ddb[pipe], ddb); + skl_ddb_entry_union(&dbuf_state->ddb[pipe], ddb_y); + } + + dbuf_state->weight[pipe] = intel_crtc_ddb_weight(crtc_state); + + /* + * Used for checking overlaps, so we need absolute + * offsets instead of MBUS relative offsets. + */ + slices = skl_compute_dbuf_slices(crtc, dbuf_state->active_pipes, + dbuf_state->joined_mbus); + mbus_offset = mbus_ddb_offset(i915, slices); + crtc_state->wm.skl.ddb.start = mbus_offset + dbuf_state->ddb[pipe].start; + crtc_state->wm.skl.ddb.end = mbus_offset + dbuf_state->ddb[pipe].end; + + /* The slices actually used by the planes on the pipe */ + dbuf_state->slices[pipe] = + skl_ddb_dbuf_slice_mask(i915, &crtc_state->wm.skl.ddb); + + drm_dbg_kms(&i915->drm, + "[CRTC:%d:%s] dbuf slices 0x%x, ddb (%d - %d), active pipes 0x%x, mbus joined: %s\n", + crtc->base.base.id, crtc->base.name, + dbuf_state->slices[pipe], dbuf_state->ddb[pipe].start, + dbuf_state->ddb[pipe].end, dbuf_state->active_pipes, + str_yes_no(dbuf_state->joined_mbus)); + } + + dbuf_state->enabled_slices = i915->display.dbuf.enabled_slices; +} + +static bool skl_dbuf_is_misconfigured(struct drm_i915_private *i915) +{ + const struct intel_dbuf_state *dbuf_state = + to_intel_dbuf_state(i915->display.dbuf.obj.state); + struct skl_ddb_entry entries[I915_MAX_PIPES] = {}; + struct intel_crtc *crtc; + + for_each_intel_crtc(&i915->drm, crtc) { + const struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + + entries[crtc->pipe] = crtc_state->wm.skl.ddb; + } + + for_each_intel_crtc(&i915->drm, crtc) { + const struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + u8 slices; + + slices = skl_compute_dbuf_slices(crtc, dbuf_state->active_pipes, + dbuf_state->joined_mbus); + if (dbuf_state->slices[crtc->pipe] & ~slices) + return true; + + if (skl_ddb_allocation_overlaps(&crtc_state->wm.skl.ddb, entries, + I915_MAX_PIPES, crtc->pipe)) + return true; + } + + return false; +} + +void skl_wm_sanitize(struct drm_i915_private *i915) +{ + struct intel_crtc *crtc; + + /* + * On TGL/RKL (at least) the BIOS likes to assign the planes + * to the wrong DBUF slices. This will cause an infinite loop + * in skl_commit_modeset_enables() as it can't find a way to + * transition between the old bogus DBUF layout to the new + * proper DBUF layout without DBUF allocation overlaps between + * the planes (which cannot be allowed or else the hardware + * may hang). If we detect a bogus DBUF layout just turn off + * all the planes so that skl_commit_modeset_enables() can + * simply ignore them. + */ + if (!skl_dbuf_is_misconfigured(i915)) + return; + + drm_dbg_kms(&i915->drm, "BIOS has misprogrammed the DBUF, disabling all planes\n"); + + for_each_intel_crtc(&i915->drm, crtc) { + struct intel_plane *plane = to_intel_plane(crtc->base.primary); + const struct intel_plane_state *plane_state = + to_intel_plane_state(plane->base.state); + struct intel_crtc_state *crtc_state = + to_intel_crtc_state(crtc->base.state); + + if (plane_state->uapi.visible) + intel_plane_disable_noatomic(crtc, plane); + + drm_WARN_ON(&i915->drm, crtc_state->active_planes != 0); + + memset(&crtc_state->wm.skl.ddb, 0, sizeof(crtc_state->wm.skl.ddb)); + } +} + +void intel_wm_state_verify(struct intel_crtc *crtc, + struct intel_crtc_state *new_crtc_state) +{ + struct drm_i915_private *i915 = to_i915(crtc->base.dev); + struct skl_hw_state { + struct skl_ddb_entry ddb[I915_MAX_PLANES]; + struct skl_ddb_entry ddb_y[I915_MAX_PLANES]; + struct skl_pipe_wm wm; + } *hw; + const struct skl_pipe_wm *sw_wm = &new_crtc_state->wm.skl.optimal; + int level, max_level = ilk_wm_max_level(i915); + struct intel_plane *plane; + u8 hw_enabled_slices; + + if (DISPLAY_VER(i915) < 9 || !new_crtc_state->hw.active) + return; + + hw = kzalloc(sizeof(*hw), GFP_KERNEL); + if (!hw) + return; + + skl_pipe_wm_get_hw_state(crtc, &hw->wm); + + skl_pipe_ddb_get_hw_state(crtc, hw->ddb, hw->ddb_y); + + hw_enabled_slices = intel_enabled_dbuf_slices_mask(i915); + + if (DISPLAY_VER(i915) >= 11 && + hw_enabled_slices != i915->display.dbuf.enabled_slices) + drm_err(&i915->drm, + "mismatch in DBUF Slices (expected 0x%x, got 0x%x)\n", + i915->display.dbuf.enabled_slices, + hw_enabled_slices); + + for_each_intel_plane_on_crtc(&i915->drm, crtc, plane) { + const struct skl_ddb_entry *hw_ddb_entry, *sw_ddb_entry; + const struct skl_wm_level *hw_wm_level, *sw_wm_level; + + /* Watermarks */ + for (level = 0; level <= max_level; level++) { + hw_wm_level = &hw->wm.planes[plane->id].wm[level]; + sw_wm_level = skl_plane_wm_level(sw_wm, plane->id, level); + + if (skl_wm_level_equals(hw_wm_level, sw_wm_level)) + continue; + + drm_err(&i915->drm, + "[PLANE:%d:%s] mismatch in WM%d (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", + plane->base.base.id, plane->base.name, level, + sw_wm_level->enable, + sw_wm_level->blocks, + sw_wm_level->lines, + hw_wm_level->enable, + hw_wm_level->blocks, + hw_wm_level->lines); + } + + hw_wm_level = &hw->wm.planes[plane->id].trans_wm; + sw_wm_level = skl_plane_trans_wm(sw_wm, plane->id); + + if (!skl_wm_level_equals(hw_wm_level, sw_wm_level)) { + drm_err(&i915->drm, + "[PLANE:%d:%s] mismatch in trans WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", + plane->base.base.id, plane->base.name, + sw_wm_level->enable, + sw_wm_level->blocks, + sw_wm_level->lines, + hw_wm_level->enable, + hw_wm_level->blocks, + hw_wm_level->lines); + } + + hw_wm_level = &hw->wm.planes[plane->id].sagv.wm0; + sw_wm_level = &sw_wm->planes[plane->id].sagv.wm0; + + if (HAS_HW_SAGV_WM(i915) && + !skl_wm_level_equals(hw_wm_level, sw_wm_level)) { + drm_err(&i915->drm, + "[PLANE:%d:%s] mismatch in SAGV WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", + plane->base.base.id, plane->base.name, + sw_wm_level->enable, + sw_wm_level->blocks, + sw_wm_level->lines, + hw_wm_level->enable, + hw_wm_level->blocks, + hw_wm_level->lines); + } + + hw_wm_level = &hw->wm.planes[plane->id].sagv.trans_wm; + sw_wm_level = &sw_wm->planes[plane->id].sagv.trans_wm; + + if (HAS_HW_SAGV_WM(i915) && + !skl_wm_level_equals(hw_wm_level, sw_wm_level)) { + drm_err(&i915->drm, + "[PLANE:%d:%s] mismatch in SAGV trans WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", + plane->base.base.id, plane->base.name, + sw_wm_level->enable, + sw_wm_level->blocks, + sw_wm_level->lines, + hw_wm_level->enable, + hw_wm_level->blocks, + hw_wm_level->lines); + } + + /* DDB */ + hw_ddb_entry = &hw->ddb[PLANE_CURSOR]; + sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb[PLANE_CURSOR]; + + if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) { + drm_err(&i915->drm, + "[PLANE:%d:%s] mismatch in DDB (expected (%u,%u), found (%u,%u))\n", + plane->base.base.id, plane->base.name, + sw_ddb_entry->start, sw_ddb_entry->end, + hw_ddb_entry->start, hw_ddb_entry->end); + } + } + + kfree(hw); +} + +bool skl_watermark_ipc_enabled(struct drm_i915_private *i915) +{ + return i915->display.wm.ipc_enabled; +} + +void skl_watermark_ipc_update(struct drm_i915_private *i915) +{ + if (!HAS_IPC(i915)) + return; + + intel_uncore_rmw(&i915->uncore, DISP_ARB_CTL2, DISP_IPC_ENABLE, + skl_watermark_ipc_enabled(i915) ? DISP_IPC_ENABLE : 0); +} + +static bool skl_watermark_ipc_can_enable(struct drm_i915_private *i915) +{ + /* Display WA #0477 WaDisableIPC: skl */ + if (IS_SKYLAKE(i915)) + return false; + + /* Display WA #1141: SKL:all KBL:all CFL */ + if (IS_KABYLAKE(i915) || + IS_COFFEELAKE(i915) || + IS_COMETLAKE(i915)) + return i915->dram_info.symmetric_memory; + + return true; +} + +void skl_watermark_ipc_init(struct drm_i915_private *i915) +{ + if (!HAS_IPC(i915)) + return; + + i915->display.wm.ipc_enabled = skl_watermark_ipc_can_enable(i915); + + skl_watermark_ipc_update(i915); +} + +static void +adjust_wm_latency(struct drm_i915_private *i915, + u16 wm[], int max_level, int read_latency) +{ + bool wm_lv_0_adjust_needed = i915->dram_info.wm_lv_0_adjust_needed; + int i, level; + + /* + * If a level n (n > 1) has a 0us latency, all levels m (m >= n) + * need to be disabled. We make sure to sanitize the values out + * of the punit to satisfy this requirement. + */ + for (level = 1; level <= max_level; level++) { + if (wm[level] == 0) { + for (i = level + 1; i <= max_level; i++) + wm[i] = 0; + + max_level = level - 1; + break; + } + } + + /* + * WaWmMemoryReadLatency + * + * punit doesn't take into account the read latency so we need + * to add proper adjustement to each valid level we retrieve + * from the punit when level 0 response data is 0us. + */ + if (wm[0] == 0) { + for (level = 0; level <= max_level; level++) + wm[level] += read_latency; + } + + /* + * WA Level-0 adjustment for 16GB DIMMs: SKL+ + * If we could not get dimm info enable this WA to prevent from + * any underrun. If not able to get Dimm info assume 16GB dimm + * to avoid any underrun. + */ + if (wm_lv_0_adjust_needed) + wm[0] += 1; +} + +static void mtl_read_wm_latency(struct drm_i915_private *i915, u16 wm[]) +{ + struct intel_uncore *uncore = &i915->uncore; + int max_level = ilk_wm_max_level(i915); + u32 val; + + val = intel_uncore_read(uncore, MTL_LATENCY_LP0_LP1); + wm[0] = REG_FIELD_GET(MTL_LATENCY_LEVEL_EVEN_MASK, val); + wm[1] = REG_FIELD_GET(MTL_LATENCY_LEVEL_ODD_MASK, val); + + val = intel_uncore_read(uncore, MTL_LATENCY_LP2_LP3); + wm[2] = REG_FIELD_GET(MTL_LATENCY_LEVEL_EVEN_MASK, val); + wm[3] = REG_FIELD_GET(MTL_LATENCY_LEVEL_ODD_MASK, val); + + val = intel_uncore_read(uncore, MTL_LATENCY_LP4_LP5); + wm[4] = REG_FIELD_GET(MTL_LATENCY_LEVEL_EVEN_MASK, val); + wm[5] = REG_FIELD_GET(MTL_LATENCY_LEVEL_ODD_MASK, val); + + adjust_wm_latency(i915, wm, max_level, 6); +} + +static void skl_read_wm_latency(struct drm_i915_private *i915, u16 wm[]) +{ + int max_level = ilk_wm_max_level(i915); + int read_latency = DISPLAY_VER(i915) >= 12 ? 3 : 2; + int mult = IS_DG2(i915) ? 2 : 1; + u32 val; + int ret; + + /* read the first set of memory latencies[0:3] */ + val = 0; /* data0 to be programmed to 0 for first set */ + ret = snb_pcode_read(&i915->uncore, GEN9_PCODE_READ_MEM_LATENCY, &val, NULL); + if (ret) { + drm_err(&i915->drm, "SKL Mailbox read error = %d\n", ret); + return; + } + + wm[0] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_0_4_MASK, val) * mult; + wm[1] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_1_5_MASK, val) * mult; + wm[2] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_2_6_MASK, val) * mult; + wm[3] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_3_7_MASK, val) * mult; + + /* read the second set of memory latencies[4:7] */ + val = 1; /* data0 to be programmed to 1 for second set */ + ret = snb_pcode_read(&i915->uncore, GEN9_PCODE_READ_MEM_LATENCY, &val, NULL); + if (ret) { + drm_err(&i915->drm, "SKL Mailbox read error = %d\n", ret); + return; + } + + wm[4] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_0_4_MASK, val) * mult; + wm[5] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_1_5_MASK, val) * mult; + wm[6] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_2_6_MASK, val) * mult; + wm[7] = REG_FIELD_GET(GEN9_MEM_LATENCY_LEVEL_3_7_MASK, val) * mult; + + adjust_wm_latency(i915, wm, max_level, read_latency); +} + +static void skl_setup_wm_latency(struct drm_i915_private *i915) +{ + if (DISPLAY_VER(i915) >= 14) + mtl_read_wm_latency(i915, i915->display.wm.skl_latency); + else + skl_read_wm_latency(i915, i915->display.wm.skl_latency); + + intel_print_wm_latency(i915, "Gen9 Plane", i915->display.wm.skl_latency); +} + +static const struct intel_wm_funcs skl_wm_funcs = { + .compute_global_watermarks = skl_compute_wm, +}; + +void skl_wm_init(struct drm_i915_private *i915) +{ + intel_sagv_init(i915); + + skl_setup_wm_latency(i915); + + i915->display.funcs.wm = &skl_wm_funcs; +} + +static struct intel_global_state *intel_dbuf_duplicate_state(struct intel_global_obj *obj) +{ + struct intel_dbuf_state *dbuf_state; + + dbuf_state = kmemdup(obj->state, sizeof(*dbuf_state), GFP_KERNEL); + if (!dbuf_state) + return NULL; + + return &dbuf_state->base; +} + +static void intel_dbuf_destroy_state(struct intel_global_obj *obj, + struct intel_global_state *state) +{ + kfree(state); +} + +static const struct intel_global_state_funcs intel_dbuf_funcs = { + .atomic_duplicate_state = intel_dbuf_duplicate_state, + .atomic_destroy_state = intel_dbuf_destroy_state, +}; + +struct intel_dbuf_state * +intel_atomic_get_dbuf_state(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + struct intel_global_state *dbuf_state; + + dbuf_state = intel_atomic_get_global_obj_state(state, &i915->display.dbuf.obj); + if (IS_ERR(dbuf_state)) + return ERR_CAST(dbuf_state); + + return to_intel_dbuf_state(dbuf_state); +} + +int intel_dbuf_init(struct drm_i915_private *i915) +{ + struct intel_dbuf_state *dbuf_state; + + dbuf_state = kzalloc(sizeof(*dbuf_state), GFP_KERNEL); + if (!dbuf_state) + return -ENOMEM; + + intel_atomic_global_obj_init(i915, &i915->display.dbuf.obj, + &dbuf_state->base, &intel_dbuf_funcs); + + return 0; +} + +/* + * Configure MBUS_CTL and all DBUF_CTL_S of each slice to join_mbus state before + * update the request state of all DBUS slices. + */ +static void update_mbus_pre_enable(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + u32 mbus_ctl, dbuf_min_tracker_val; + enum dbuf_slice slice; + const struct intel_dbuf_state *dbuf_state = + intel_atomic_get_new_dbuf_state(state); + + if (!HAS_MBUS_JOINING(i915)) + return; + + /* + * TODO: Implement vblank synchronized MBUS joining changes. + * Must be properly coordinated with dbuf reprogramming. + */ + if (dbuf_state->joined_mbus) { + mbus_ctl = MBUS_HASHING_MODE_1x4 | MBUS_JOIN | + MBUS_JOIN_PIPE_SELECT_NONE; + dbuf_min_tracker_val = DBUF_MIN_TRACKER_STATE_SERVICE(3); + } else { + mbus_ctl = MBUS_HASHING_MODE_2x2 | + MBUS_JOIN_PIPE_SELECT_NONE; + dbuf_min_tracker_val = DBUF_MIN_TRACKER_STATE_SERVICE(1); + } + + intel_de_rmw(i915, MBUS_CTL, + MBUS_HASHING_MODE_MASK | MBUS_JOIN | + MBUS_JOIN_PIPE_SELECT_MASK, mbus_ctl); + + for_each_dbuf_slice(i915, slice) + intel_de_rmw(i915, DBUF_CTL_S(slice), + DBUF_MIN_TRACKER_STATE_SERVICE_MASK, + dbuf_min_tracker_val); +} + +void intel_dbuf_pre_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_dbuf_state *new_dbuf_state = + intel_atomic_get_new_dbuf_state(state); + const struct intel_dbuf_state *old_dbuf_state = + intel_atomic_get_old_dbuf_state(state); + + if (!new_dbuf_state || + (new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices && + new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus)) + return; + + WARN_ON(!new_dbuf_state->base.changed); + + update_mbus_pre_enable(state); + gen9_dbuf_slices_update(i915, + old_dbuf_state->enabled_slices | + new_dbuf_state->enabled_slices); +} + +void intel_dbuf_post_plane_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_dbuf_state *new_dbuf_state = + intel_atomic_get_new_dbuf_state(state); + const struct intel_dbuf_state *old_dbuf_state = + intel_atomic_get_old_dbuf_state(state); + + if (!new_dbuf_state || + (new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices && + new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus)) + return; + + WARN_ON(!new_dbuf_state->base.changed); + + gen9_dbuf_slices_update(i915, + new_dbuf_state->enabled_slices); +} + +static bool xelpdp_is_only_pipe_per_dbuf_bank(enum pipe pipe, u8 active_pipes) +{ + switch (pipe) { + case PIPE_A: + return !(active_pipes & BIT(PIPE_D)); + case PIPE_D: + return !(active_pipes & BIT(PIPE_A)); + case PIPE_B: + return !(active_pipes & BIT(PIPE_C)); + case PIPE_C: + return !(active_pipes & BIT(PIPE_B)); + default: /* to suppress compiler warning */ + MISSING_CASE(pipe); + break; + } + + return false; +} + +void intel_mbus_dbox_update(struct intel_atomic_state *state) +{ + struct drm_i915_private *i915 = to_i915(state->base.dev); + const struct intel_dbuf_state *new_dbuf_state, *old_dbuf_state; + const struct intel_crtc_state *new_crtc_state; + const struct intel_crtc *crtc; + u32 val = 0; + int i; + + if (DISPLAY_VER(i915) < 11) + return; + + new_dbuf_state = intel_atomic_get_new_dbuf_state(state); + old_dbuf_state = intel_atomic_get_old_dbuf_state(state); + if (!new_dbuf_state || + (new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus && + new_dbuf_state->active_pipes == old_dbuf_state->active_pipes)) + return; + + if (DISPLAY_VER(i915) >= 14) + val |= MBUS_DBOX_I_CREDIT(2); + + if (DISPLAY_VER(i915) >= 12) { + val |= MBUS_DBOX_B2B_TRANSACTIONS_MAX(16); + val |= MBUS_DBOX_B2B_TRANSACTIONS_DELAY(1); + val |= MBUS_DBOX_REGULATE_B2B_TRANSACTIONS_EN; + } + + if (DISPLAY_VER(i915) >= 14) + val |= new_dbuf_state->joined_mbus ? MBUS_DBOX_A_CREDIT(12) : + MBUS_DBOX_A_CREDIT(8); + else if (IS_ALDERLAKE_P(i915)) + /* Wa_22010947358:adl-p */ + val |= new_dbuf_state->joined_mbus ? MBUS_DBOX_A_CREDIT(6) : + MBUS_DBOX_A_CREDIT(4); + else + val |= MBUS_DBOX_A_CREDIT(2); + + if (DISPLAY_VER(i915) >= 14) { + val |= MBUS_DBOX_B_CREDIT(0xA); + } else if (IS_ALDERLAKE_P(i915)) { + val |= MBUS_DBOX_BW_CREDIT(2); + val |= MBUS_DBOX_B_CREDIT(8); + } else if (DISPLAY_VER(i915) >= 12) { + val |= MBUS_DBOX_BW_CREDIT(2); + val |= MBUS_DBOX_B_CREDIT(12); + } else { + val |= MBUS_DBOX_BW_CREDIT(1); + val |= MBUS_DBOX_B_CREDIT(8); + } + + for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { + u32 pipe_val = val; + + if (!new_crtc_state->hw.active) + continue; + + if (DISPLAY_VER(i915) >= 14) { + if (xelpdp_is_only_pipe_per_dbuf_bank(crtc->pipe, + new_dbuf_state->active_pipes)) + pipe_val |= MBUS_DBOX_BW_8CREDITS_MTL; + else + pipe_val |= MBUS_DBOX_BW_4CREDITS_MTL; + } + + intel_de_write(i915, PIPE_MBUS_DBOX_CTL(crtc->pipe), pipe_val); + } +} + +static int skl_watermark_ipc_status_show(struct seq_file *m, void *data) +{ + struct drm_i915_private *i915 = m->private; + + seq_printf(m, "Isochronous Priority Control: %s\n", + str_yes_no(skl_watermark_ipc_enabled(i915))); + return 0; +} + +static int skl_watermark_ipc_status_open(struct inode *inode, struct file *file) +{ + struct drm_i915_private *i915 = inode->i_private; + + return single_open(file, skl_watermark_ipc_status_show, i915); +} + +static ssize_t skl_watermark_ipc_status_write(struct file *file, + const char __user *ubuf, + size_t len, loff_t *offp) +{ + struct seq_file *m = file->private_data; + struct drm_i915_private *i915 = m->private; + intel_wakeref_t wakeref; + bool enable; + int ret; + + ret = kstrtobool_from_user(ubuf, len, &enable); + if (ret < 0) + return ret; + + with_intel_runtime_pm(&i915->runtime_pm, wakeref) { + if (!skl_watermark_ipc_enabled(i915) && enable) + drm_info(&i915->drm, + "Enabling IPC: WM will be proper only after next commit\n"); + i915->display.wm.ipc_enabled = enable; + skl_watermark_ipc_update(i915); + } + + return len; +} + +static const struct file_operations skl_watermark_ipc_status_fops = { + .owner = THIS_MODULE, + .open = skl_watermark_ipc_status_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = skl_watermark_ipc_status_write +}; + +void skl_watermark_ipc_debugfs_register(struct drm_i915_private *i915) +{ + struct drm_minor *minor = i915->drm.primary; + + if (!HAS_IPC(i915)) + return; + + debugfs_create_file("i915_ipc_status", 0644, minor->debugfs_root, i915, + &skl_watermark_ipc_status_fops); +} diff --git a/drivers/gpu/drm/i915/display/skl_watermark.h b/drivers/gpu/drm/i915/display/skl_watermark.h new file mode 100644 index 000000000000..7a5a4e67cd73 --- /dev/null +++ b/drivers/gpu/drm/i915/display/skl_watermark.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2022 Intel Corporation + */ + +#ifndef __SKL_WATERMARK_H__ +#define __SKL_WATERMARK_H__ + +#include <linux/types.h> + +#include "intel_display.h" +#include "intel_global_state.h" +#include "intel_pm_types.h" + +struct drm_i915_private; +struct intel_atomic_state; +struct intel_bw_state; +struct intel_crtc; +struct intel_crtc_state; +struct intel_plane; + +u8 intel_enabled_dbuf_slices_mask(struct drm_i915_private *i915); + +void intel_sagv_pre_plane_update(struct intel_atomic_state *state); +void intel_sagv_post_plane_update(struct intel_atomic_state *state); +bool intel_can_enable_sagv(struct drm_i915_private *i915, + const struct intel_bw_state *bw_state); + +u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *i915, + const struct skl_ddb_entry *entry); + +void skl_write_plane_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); +void skl_write_cursor_wm(struct intel_plane *plane, + const struct intel_crtc_state *crtc_state); + +bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, + const struct skl_ddb_entry *entries, + int num_entries, int ignore_idx); + +void skl_wm_get_hw_state(struct drm_i915_private *i915); +void skl_wm_sanitize(struct drm_i915_private *i915); + +void intel_wm_state_verify(struct intel_crtc *crtc, + struct intel_crtc_state *new_crtc_state); + +void skl_watermark_ipc_init(struct drm_i915_private *i915); +void skl_watermark_ipc_update(struct drm_i915_private *i915); +bool skl_watermark_ipc_enabled(struct drm_i915_private *i915); +void skl_watermark_ipc_debugfs_register(struct drm_i915_private *i915); + +void skl_wm_init(struct drm_i915_private *i915); + +struct intel_dbuf_state { + struct intel_global_state base; + + struct skl_ddb_entry ddb[I915_MAX_PIPES]; + unsigned int weight[I915_MAX_PIPES]; + u8 slices[I915_MAX_PIPES]; + u8 enabled_slices; + u8 active_pipes; + bool joined_mbus; +}; + +struct intel_dbuf_state * +intel_atomic_get_dbuf_state(struct intel_atomic_state *state); + +#define to_intel_dbuf_state(x) container_of((x), struct intel_dbuf_state, base) +#define intel_atomic_get_old_dbuf_state(state) \ + to_intel_dbuf_state(intel_atomic_get_old_global_obj_state(state, &to_i915(state->base.dev)->display.dbuf.obj)) +#define intel_atomic_get_new_dbuf_state(state) \ + to_intel_dbuf_state(intel_atomic_get_new_global_obj_state(state, &to_i915(state->base.dev)->display.dbuf.obj)) + +int intel_dbuf_init(struct drm_i915_private *i915); +void intel_dbuf_pre_plane_update(struct intel_atomic_state *state); +void intel_dbuf_post_plane_update(struct intel_atomic_state *state); +void intel_mbus_dbox_update(struct intel_atomic_state *state); + +#endif /* __SKL_WATERMARK_H__ */ + diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index b9b1fed99874..b3f5ca280ef2 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -822,9 +822,9 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state, u32 val; /* Disable DPOunit clock gating, can stall pipe */ - val = intel_de_read(dev_priv, DSPCLK_GATE_D); + val = intel_de_read(dev_priv, DSPCLK_GATE_D(dev_priv)); val |= DPOUNIT_CLOCK_GATE_DISABLE; - intel_de_write(dev_priv, DSPCLK_GATE_D, val); + intel_de_write(dev_priv, DSPCLK_GATE_D(dev_priv), val); } if (!IS_GEMINILAKE(dev_priv)) @@ -998,9 +998,9 @@ static void intel_dsi_post_disable(struct intel_atomic_state *state, vlv_dsi_pll_disable(encoder); - val = intel_de_read(dev_priv, DSPCLK_GATE_D); + val = intel_de_read(dev_priv, DSPCLK_GATE_D(dev_priv)); val &= ~DPOUNIT_CLOCK_GATE_DISABLE; - intel_de_write(dev_priv, DSPCLK_GATE_D, val); + intel_de_write(dev_priv, DSPCLK_GATE_D(dev_priv), val); } /* Assert reset */ @@ -1277,13 +1277,12 @@ static void intel_dsi_get_config(struct intel_encoder *encoder, pclk = vlv_dsi_get_pclk(encoder, pipe_config); } - if (intel_dsi->dual_link) - pclk *= 2; + pipe_config->port_clock = pclk; - if (pclk) { - pipe_config->hw.adjusted_mode.crtc_clock = pclk; - pipe_config->port_clock = pclk; - } + /* FIXME definitely not right for burst/cmd mode/pixel overlap */ + pipe_config->hw.adjusted_mode.crtc_clock = pclk; + if (intel_dsi->dual_link) + pipe_config->hw.adjusted_mode.crtc_clock *= 2; } /* return txclkesc cycles in terms of divider and duration in us */ @@ -1872,9 +1871,9 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv) return; if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - dev_priv->mipi_mmio_base = BXT_MIPI_BASE; + dev_priv->display.dsi.mmio_base = BXT_MIPI_BASE; else - dev_priv->mipi_mmio_base = VLV_MIPI_BASE; + dev_priv->display.dsi.mmio_base = VLV_MIPI_BASE; intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL); if (!intel_dsi) @@ -1933,8 +1932,11 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv) else intel_dsi->ports = BIT(port); - intel_dsi->dcs_backlight_ports = intel_connector->panel.vbt.dsi.bl_ports; - intel_dsi->dcs_cabc_ports = intel_connector->panel.vbt.dsi.cabc_ports; + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.bl_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.bl_ports &= intel_dsi->ports; + + if (drm_WARN_ON(&dev_priv->drm, intel_connector->panel.vbt.dsi.cabc_ports & ~intel_dsi->ports)) + intel_connector->panel.vbt.dsi.cabc_ports &= intel_dsi->ports; /* Create a DSI host (and a device) for each port. */ for_each_dsi_port(port, intel_dsi->ports) { diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c index 5894b0138343..af7402127cd9 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_pll.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi_pll.c @@ -113,6 +113,61 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv, return 0; } +static int vlv_dsi_pclk(struct intel_encoder *encoder, + struct intel_crtc_state *config) +{ + struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); + int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format); + u32 dsi_clock; + u32 pll_ctl, pll_div; + u32 m = 0, p = 0, n; + int refclk = IS_CHERRYVIEW(dev_priv) ? 100000 : 25000; + int i; + + pll_ctl = config->dsi_pll.ctrl; + pll_div = config->dsi_pll.div; + + /* mask out other bits and extract the P1 divisor */ + pll_ctl &= DSI_PLL_P1_POST_DIV_MASK; + pll_ctl = pll_ctl >> (DSI_PLL_P1_POST_DIV_SHIFT - 2); + + /* N1 divisor */ + n = (pll_div & DSI_PLL_N1_DIV_MASK) >> DSI_PLL_N1_DIV_SHIFT; + n = 1 << n; /* register has log2(N1) */ + + /* mask out the other bits and extract the M1 divisor */ + pll_div &= DSI_PLL_M1_DIV_MASK; + pll_div = pll_div >> DSI_PLL_M1_DIV_SHIFT; + + while (pll_ctl) { + pll_ctl = pll_ctl >> 1; + p++; + } + p--; + + if (!p) { + drm_err(&dev_priv->drm, "wrong P1 divisor\n"); + return 0; + } + + for (i = 0; i < ARRAY_SIZE(lfsr_converts); i++) { + if (lfsr_converts[i] == pll_div) + break; + } + + if (i == ARRAY_SIZE(lfsr_converts)) { + drm_err(&dev_priv->drm, "wrong m_seed programmed\n"); + return 0; + } + + m = i + 62; + + dsi_clock = (m * refclk) / (p * n); + + return DIV_ROUND_CLOSEST(dsi_clock * intel_dsi->lane_count, bpp); +} + /* * XXX: The muxing and gating is hard coded for now. Need to add support for * sharing PLLs with two DSI outputs. @@ -122,8 +177,7 @@ int vlv_dsi_pll_compute(struct intel_encoder *encoder, { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); - int ret; - u32 dsi_clk; + int pclk, dsi_clk, ret; dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format, intel_dsi->lane_count); @@ -145,6 +199,14 @@ int vlv_dsi_pll_compute(struct intel_encoder *encoder, drm_dbg_kms(&dev_priv->drm, "dsi pll div %08x, ctrl %08x\n", config->dsi_pll.div, config->dsi_pll.ctrl); + pclk = vlv_dsi_pclk(encoder, config); + config->port_clock = pclk; + + /* FIXME definitely not right for burst/cmd mode/pixel overlap */ + config->hw.adjusted_mode.crtc_clock = pclk; + if (intel_dsi->dual_link) + config->hw.adjusted_mode.crtc_clock *= 2; + return 0; } @@ -262,13 +324,7 @@ u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, struct intel_crtc_state *config) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); - int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format); - u32 dsi_clock, pclk; u32 pll_ctl, pll_div; - u32 m = 0, p = 0, n; - int refclk = IS_CHERRYVIEW(dev_priv) ? 100000 : 25000; - int i; drm_dbg_kms(&dev_priv->drm, "\n"); @@ -280,65 +336,31 @@ u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, config->dsi_pll.ctrl = pll_ctl & ~DSI_PLL_LOCK; config->dsi_pll.div = pll_div; - /* mask out other bits and extract the P1 divisor */ - pll_ctl &= DSI_PLL_P1_POST_DIV_MASK; - pll_ctl = pll_ctl >> (DSI_PLL_P1_POST_DIV_SHIFT - 2); - - /* N1 divisor */ - n = (pll_div & DSI_PLL_N1_DIV_MASK) >> DSI_PLL_N1_DIV_SHIFT; - n = 1 << n; /* register has log2(N1) */ - - /* mask out the other bits and extract the M1 divisor */ - pll_div &= DSI_PLL_M1_DIV_MASK; - pll_div = pll_div >> DSI_PLL_M1_DIV_SHIFT; - - while (pll_ctl) { - pll_ctl = pll_ctl >> 1; - p++; - } - p--; - - if (!p) { - drm_err(&dev_priv->drm, "wrong P1 divisor\n"); - return 0; - } - - for (i = 0; i < ARRAY_SIZE(lfsr_converts); i++) { - if (lfsr_converts[i] == pll_div) - break; - } - - if (i == ARRAY_SIZE(lfsr_converts)) { - drm_err(&dev_priv->drm, "wrong m_seed programmed\n"); - return 0; - } - - m = i + 62; + return vlv_dsi_pclk(encoder, config); +} - dsi_clock = (m * refclk) / (p * n); +static int bxt_dsi_pclk(struct intel_encoder *encoder, + const struct intel_crtc_state *config) +{ + struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); + int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format); + u32 dsi_ratio, dsi_clk; - pclk = DIV_ROUND_CLOSEST(dsi_clock * intel_dsi->lane_count, bpp); + dsi_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK; + dsi_clk = (dsi_ratio * BXT_REF_CLOCK_KHZ) / 2; - return pclk; + return DIV_ROUND_CLOSEST(dsi_clk * intel_dsi->lane_count, bpp); } u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, struct intel_crtc_state *config) { - u32 pclk; - u32 dsi_clk; - u32 dsi_ratio; - struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); - int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format); + u32 pclk; config->dsi_pll.ctrl = intel_de_read(dev_priv, BXT_DSI_PLL_CTL); - dsi_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK; - - dsi_clk = (dsi_ratio * BXT_REF_CLOCK_KHZ) / 2; - - pclk = DIV_ROUND_CLOSEST(dsi_clk * intel_dsi->lane_count, bpp); + pclk = bxt_dsi_pclk(encoder, config); drm_dbg(&dev_priv->drm, "Calculated pclk=%u\n", pclk); return pclk; @@ -463,6 +485,7 @@ int bxt_dsi_pll_compute(struct intel_encoder *encoder, struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder); u8 dsi_ratio, dsi_ratio_min, dsi_ratio_max; u32 dsi_clk; + int pclk; dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format, intel_dsi->lane_count); @@ -502,6 +525,14 @@ int bxt_dsi_pll_compute(struct intel_encoder *encoder, if (IS_BROXTON(dev_priv) && dsi_ratio <= 50) config->dsi_pll.ctrl |= BXT_DSI_PLL_PVD_RATIO_1; + pclk = bxt_dsi_pclk(encoder, config); + config->port_clock = pclk; + + /* FIXME definitely not right for burst/cmd mode/pixel overlap */ + config->hw.adjusted_mode.crtc_clock = pclk; + if (intel_dsi->dual_link) + config->hw.adjusted_mode.crtc_clock *= 2; + return 0; } diff --git a/drivers/gpu/drm/i915/display/vlv_dsi_regs.h b/drivers/gpu/drm/i915/display/vlv_dsi_regs.h index 356e51515346..e065b8f2ee08 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi_regs.h +++ b/drivers/gpu/drm/i915/display/vlv_dsi_regs.h @@ -11,6 +11,8 @@ #define VLV_MIPI_BASE VLV_DISPLAY_BASE #define BXT_MIPI_BASE 0x60000 +#define _MIPI_MMIO_BASE(__i915) ((__i915)->display.dsi.mmio_base) + #define _MIPI_PORT(port, a, c) (((port) == PORT_A) ? a : c) /* ports A and C only */ #define _MMIO_MIPI(port, a, c) _MMIO(_MIPI_PORT(port, a, c)) @@ -96,8 +98,8 @@ /* MIPI DSI Controller and D-PHY registers */ -#define _MIPIA_DEVICE_READY (dev_priv->mipi_mmio_base + 0xb000) -#define _MIPIC_DEVICE_READY (dev_priv->mipi_mmio_base + 0xb800) +#define _MIPIA_DEVICE_READY (_MIPI_MMIO_BASE(dev_priv) + 0xb000) +#define _MIPIC_DEVICE_READY (_MIPI_MMIO_BASE(dev_priv) + 0xb800) #define MIPI_DEVICE_READY(port) _MMIO_MIPI(port, _MIPIA_DEVICE_READY, _MIPIC_DEVICE_READY) #define BUS_POSSESSION (1 << 3) /* set to give bus to receiver */ #define ULPS_STATE_MASK (3 << 1) @@ -106,11 +108,11 @@ #define ULPS_STATE_NORMAL_OPERATION (0 << 1) #define DEVICE_READY (1 << 0) -#define _MIPIA_INTR_STAT (dev_priv->mipi_mmio_base + 0xb004) -#define _MIPIC_INTR_STAT (dev_priv->mipi_mmio_base + 0xb804) +#define _MIPIA_INTR_STAT (_MIPI_MMIO_BASE(dev_priv) + 0xb004) +#define _MIPIC_INTR_STAT (_MIPI_MMIO_BASE(dev_priv) + 0xb804) #define MIPI_INTR_STAT(port) _MMIO_MIPI(port, _MIPIA_INTR_STAT, _MIPIC_INTR_STAT) -#define _MIPIA_INTR_EN (dev_priv->mipi_mmio_base + 0xb008) -#define _MIPIC_INTR_EN (dev_priv->mipi_mmio_base + 0xb808) +#define _MIPIA_INTR_EN (_MIPI_MMIO_BASE(dev_priv) + 0xb008) +#define _MIPIC_INTR_EN (_MIPI_MMIO_BASE(dev_priv) + 0xb808) #define MIPI_INTR_EN(port) _MMIO_MIPI(port, _MIPIA_INTR_EN, _MIPIC_INTR_EN) #define TEARING_EFFECT (1 << 31) #define SPL_PKT_SENT_INTERRUPT (1 << 30) @@ -145,8 +147,8 @@ #define RXSOT_SYNC_ERROR (1 << 1) #define RXSOT_ERROR (1 << 0) -#define _MIPIA_DSI_FUNC_PRG (dev_priv->mipi_mmio_base + 0xb00c) -#define _MIPIC_DSI_FUNC_PRG (dev_priv->mipi_mmio_base + 0xb80c) +#define _MIPIA_DSI_FUNC_PRG (_MIPI_MMIO_BASE(dev_priv) + 0xb00c) +#define _MIPIC_DSI_FUNC_PRG (_MIPI_MMIO_BASE(dev_priv) + 0xb80c) #define MIPI_DSI_FUNC_PRG(port) _MMIO_MIPI(port, _MIPIA_DSI_FUNC_PRG, _MIPIC_DSI_FUNC_PRG) #define CMD_MODE_DATA_WIDTH_MASK (7 << 13) #define CMD_MODE_NOT_SUPPORTED (0 << 13) @@ -168,76 +170,76 @@ #define DATA_LANES_PRG_REG_SHIFT 0 #define DATA_LANES_PRG_REG_MASK (7 << 0) -#define _MIPIA_HS_TX_TIMEOUT (dev_priv->mipi_mmio_base + 0xb010) -#define _MIPIC_HS_TX_TIMEOUT (dev_priv->mipi_mmio_base + 0xb810) +#define _MIPIA_HS_TX_TIMEOUT (_MIPI_MMIO_BASE(dev_priv) + 0xb010) +#define _MIPIC_HS_TX_TIMEOUT (_MIPI_MMIO_BASE(dev_priv) + 0xb810) #define MIPI_HS_TX_TIMEOUT(port) _MMIO_MIPI(port, _MIPIA_HS_TX_TIMEOUT, _MIPIC_HS_TX_TIMEOUT) #define HIGH_SPEED_TX_TIMEOUT_COUNTER_MASK 0xffffff -#define _MIPIA_LP_RX_TIMEOUT (dev_priv->mipi_mmio_base + 0xb014) -#define _MIPIC_LP_RX_TIMEOUT (dev_priv->mipi_mmio_base + 0xb814) +#define _MIPIA_LP_RX_TIMEOUT (_MIPI_MMIO_BASE(dev_priv) + 0xb014) +#define _MIPIC_LP_RX_TIMEOUT (_MIPI_MMIO_BASE(dev_priv) + 0xb814) #define MIPI_LP_RX_TIMEOUT(port) _MMIO_MIPI(port, _MIPIA_LP_RX_TIMEOUT, _MIPIC_LP_RX_TIMEOUT) #define LOW_POWER_RX_TIMEOUT_COUNTER_MASK 0xffffff -#define _MIPIA_TURN_AROUND_TIMEOUT (dev_priv->mipi_mmio_base + 0xb018) -#define _MIPIC_TURN_AROUND_TIMEOUT (dev_priv->mipi_mmio_base + 0xb818) +#define _MIPIA_TURN_AROUND_TIMEOUT (_MIPI_MMIO_BASE(dev_priv) + 0xb018) +#define _MIPIC_TURN_AROUND_TIMEOUT (_MIPI_MMIO_BASE(dev_priv) + 0xb818) #define MIPI_TURN_AROUND_TIMEOUT(port) _MMIO_MIPI(port, _MIPIA_TURN_AROUND_TIMEOUT, _MIPIC_TURN_AROUND_TIMEOUT) #define TURN_AROUND_TIMEOUT_MASK 0x3f -#define _MIPIA_DEVICE_RESET_TIMER (dev_priv->mipi_mmio_base + 0xb01c) -#define _MIPIC_DEVICE_RESET_TIMER (dev_priv->mipi_mmio_base + 0xb81c) +#define _MIPIA_DEVICE_RESET_TIMER (_MIPI_MMIO_BASE(dev_priv) + 0xb01c) +#define _MIPIC_DEVICE_RESET_TIMER (_MIPI_MMIO_BASE(dev_priv) + 0xb81c) #define MIPI_DEVICE_RESET_TIMER(port) _MMIO_MIPI(port, _MIPIA_DEVICE_RESET_TIMER, _MIPIC_DEVICE_RESET_TIMER) #define DEVICE_RESET_TIMER_MASK 0xffff -#define _MIPIA_DPI_RESOLUTION (dev_priv->mipi_mmio_base + 0xb020) -#define _MIPIC_DPI_RESOLUTION (dev_priv->mipi_mmio_base + 0xb820) +#define _MIPIA_DPI_RESOLUTION (_MIPI_MMIO_BASE(dev_priv) + 0xb020) +#define _MIPIC_DPI_RESOLUTION (_MIPI_MMIO_BASE(dev_priv) + 0xb820) #define MIPI_DPI_RESOLUTION(port) _MMIO_MIPI(port, _MIPIA_DPI_RESOLUTION, _MIPIC_DPI_RESOLUTION) #define VERTICAL_ADDRESS_SHIFT 16 #define VERTICAL_ADDRESS_MASK (0xffff << 16) #define HORIZONTAL_ADDRESS_SHIFT 0 #define HORIZONTAL_ADDRESS_MASK 0xffff -#define _MIPIA_DBI_FIFO_THROTTLE (dev_priv->mipi_mmio_base + 0xb024) -#define _MIPIC_DBI_FIFO_THROTTLE (dev_priv->mipi_mmio_base + 0xb824) +#define _MIPIA_DBI_FIFO_THROTTLE (_MIPI_MMIO_BASE(dev_priv) + 0xb024) +#define _MIPIC_DBI_FIFO_THROTTLE (_MIPI_MMIO_BASE(dev_priv) + 0xb824) #define MIPI_DBI_FIFO_THROTTLE(port) _MMIO_MIPI(port, _MIPIA_DBI_FIFO_THROTTLE, _MIPIC_DBI_FIFO_THROTTLE) #define DBI_FIFO_EMPTY_HALF (0 << 0) #define DBI_FIFO_EMPTY_QUARTER (1 << 0) #define DBI_FIFO_EMPTY_7_LOCATIONS (2 << 0) /* regs below are bits 15:0 */ -#define _MIPIA_HSYNC_PADDING_COUNT (dev_priv->mipi_mmio_base + 0xb028) -#define _MIPIC_HSYNC_PADDING_COUNT (dev_priv->mipi_mmio_base + 0xb828) +#define _MIPIA_HSYNC_PADDING_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb028) +#define _MIPIC_HSYNC_PADDING_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb828) #define MIPI_HSYNC_PADDING_COUNT(port) _MMIO_MIPI(port, _MIPIA_HSYNC_PADDING_COUNT, _MIPIC_HSYNC_PADDING_COUNT) -#define _MIPIA_HBP_COUNT (dev_priv->mipi_mmio_base + 0xb02c) -#define _MIPIC_HBP_COUNT (dev_priv->mipi_mmio_base + 0xb82c) +#define _MIPIA_HBP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb02c) +#define _MIPIC_HBP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb82c) #define MIPI_HBP_COUNT(port) _MMIO_MIPI(port, _MIPIA_HBP_COUNT, _MIPIC_HBP_COUNT) -#define _MIPIA_HFP_COUNT (dev_priv->mipi_mmio_base + 0xb030) -#define _MIPIC_HFP_COUNT (dev_priv->mipi_mmio_base + 0xb830) +#define _MIPIA_HFP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb030) +#define _MIPIC_HFP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb830) #define MIPI_HFP_COUNT(port) _MMIO_MIPI(port, _MIPIA_HFP_COUNT, _MIPIC_HFP_COUNT) -#define _MIPIA_HACTIVE_AREA_COUNT (dev_priv->mipi_mmio_base + 0xb034) -#define _MIPIC_HACTIVE_AREA_COUNT (dev_priv->mipi_mmio_base + 0xb834) +#define _MIPIA_HACTIVE_AREA_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb034) +#define _MIPIC_HACTIVE_AREA_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb834) #define MIPI_HACTIVE_AREA_COUNT(port) _MMIO_MIPI(port, _MIPIA_HACTIVE_AREA_COUNT, _MIPIC_HACTIVE_AREA_COUNT) -#define _MIPIA_VSYNC_PADDING_COUNT (dev_priv->mipi_mmio_base + 0xb038) -#define _MIPIC_VSYNC_PADDING_COUNT (dev_priv->mipi_mmio_base + 0xb838) +#define _MIPIA_VSYNC_PADDING_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb038) +#define _MIPIC_VSYNC_PADDING_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb838) #define MIPI_VSYNC_PADDING_COUNT(port) _MMIO_MIPI(port, _MIPIA_VSYNC_PADDING_COUNT, _MIPIC_VSYNC_PADDING_COUNT) -#define _MIPIA_VBP_COUNT (dev_priv->mipi_mmio_base + 0xb03c) -#define _MIPIC_VBP_COUNT (dev_priv->mipi_mmio_base + 0xb83c) +#define _MIPIA_VBP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb03c) +#define _MIPIC_VBP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb83c) #define MIPI_VBP_COUNT(port) _MMIO_MIPI(port, _MIPIA_VBP_COUNT, _MIPIC_VBP_COUNT) -#define _MIPIA_VFP_COUNT (dev_priv->mipi_mmio_base + 0xb040) -#define _MIPIC_VFP_COUNT (dev_priv->mipi_mmio_base + 0xb840) +#define _MIPIA_VFP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb040) +#define _MIPIC_VFP_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb840) #define MIPI_VFP_COUNT(port) _MMIO_MIPI(port, _MIPIA_VFP_COUNT, _MIPIC_VFP_COUNT) -#define _MIPIA_HIGH_LOW_SWITCH_COUNT (dev_priv->mipi_mmio_base + 0xb044) -#define _MIPIC_HIGH_LOW_SWITCH_COUNT (dev_priv->mipi_mmio_base + 0xb844) +#define _MIPIA_HIGH_LOW_SWITCH_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb044) +#define _MIPIC_HIGH_LOW_SWITCH_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb844) #define MIPI_HIGH_LOW_SWITCH_COUNT(port) _MMIO_MIPI(port, _MIPIA_HIGH_LOW_SWITCH_COUNT, _MIPIC_HIGH_LOW_SWITCH_COUNT) -#define _MIPIA_DPI_CONTROL (dev_priv->mipi_mmio_base + 0xb048) -#define _MIPIC_DPI_CONTROL (dev_priv->mipi_mmio_base + 0xb848) +#define _MIPIA_DPI_CONTROL (_MIPI_MMIO_BASE(dev_priv) + 0xb048) +#define _MIPIC_DPI_CONTROL (_MIPI_MMIO_BASE(dev_priv) + 0xb848) #define MIPI_DPI_CONTROL(port) _MMIO_MIPI(port, _MIPIA_DPI_CONTROL, _MIPIC_DPI_CONTROL) #define DPI_LP_MODE (1 << 6) #define BACKLIGHT_OFF (1 << 5) @@ -247,27 +249,27 @@ #define TURN_ON (1 << 1) #define SHUTDOWN (1 << 0) -#define _MIPIA_DPI_DATA (dev_priv->mipi_mmio_base + 0xb04c) -#define _MIPIC_DPI_DATA (dev_priv->mipi_mmio_base + 0xb84c) +#define _MIPIA_DPI_DATA (_MIPI_MMIO_BASE(dev_priv) + 0xb04c) +#define _MIPIC_DPI_DATA (_MIPI_MMIO_BASE(dev_priv) + 0xb84c) #define MIPI_DPI_DATA(port) _MMIO_MIPI(port, _MIPIA_DPI_DATA, _MIPIC_DPI_DATA) #define COMMAND_BYTE_SHIFT 0 #define COMMAND_BYTE_MASK (0x3f << 0) -#define _MIPIA_INIT_COUNT (dev_priv->mipi_mmio_base + 0xb050) -#define _MIPIC_INIT_COUNT (dev_priv->mipi_mmio_base + 0xb850) +#define _MIPIA_INIT_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb050) +#define _MIPIC_INIT_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb850) #define MIPI_INIT_COUNT(port) _MMIO_MIPI(port, _MIPIA_INIT_COUNT, _MIPIC_INIT_COUNT) #define MASTER_INIT_TIMER_SHIFT 0 #define MASTER_INIT_TIMER_MASK (0xffff << 0) -#define _MIPIA_MAX_RETURN_PKT_SIZE (dev_priv->mipi_mmio_base + 0xb054) -#define _MIPIC_MAX_RETURN_PKT_SIZE (dev_priv->mipi_mmio_base + 0xb854) +#define _MIPIA_MAX_RETURN_PKT_SIZE (_MIPI_MMIO_BASE(dev_priv) + 0xb054) +#define _MIPIC_MAX_RETURN_PKT_SIZE (_MIPI_MMIO_BASE(dev_priv) + 0xb854) #define MIPI_MAX_RETURN_PKT_SIZE(port) _MMIO_MIPI(port, \ _MIPIA_MAX_RETURN_PKT_SIZE, _MIPIC_MAX_RETURN_PKT_SIZE) #define MAX_RETURN_PKT_SIZE_SHIFT 0 #define MAX_RETURN_PKT_SIZE_MASK (0x3ff << 0) -#define _MIPIA_VIDEO_MODE_FORMAT (dev_priv->mipi_mmio_base + 0xb058) -#define _MIPIC_VIDEO_MODE_FORMAT (dev_priv->mipi_mmio_base + 0xb858) +#define _MIPIA_VIDEO_MODE_FORMAT (_MIPI_MMIO_BASE(dev_priv) + 0xb058) +#define _MIPIC_VIDEO_MODE_FORMAT (_MIPI_MMIO_BASE(dev_priv) + 0xb858) #define MIPI_VIDEO_MODE_FORMAT(port) _MMIO_MIPI(port, _MIPIA_VIDEO_MODE_FORMAT, _MIPIC_VIDEO_MODE_FORMAT) #define RANDOM_DPI_DISPLAY_RESOLUTION (1 << 4) #define DISABLE_VIDEO_BTA (1 << 3) @@ -276,8 +278,8 @@ #define VIDEO_MODE_NON_BURST_WITH_SYNC_EVENTS (2 << 0) #define VIDEO_MODE_BURST (3 << 0) -#define _MIPIA_EOT_DISABLE (dev_priv->mipi_mmio_base + 0xb05c) -#define _MIPIC_EOT_DISABLE (dev_priv->mipi_mmio_base + 0xb85c) +#define _MIPIA_EOT_DISABLE (_MIPI_MMIO_BASE(dev_priv) + 0xb05c) +#define _MIPIC_EOT_DISABLE (_MIPI_MMIO_BASE(dev_priv) + 0xb85c) #define MIPI_EOT_DISABLE(port) _MMIO_MIPI(port, _MIPIA_EOT_DISABLE, _MIPIC_EOT_DISABLE) #define BXT_DEFEATURE_DPI_FIFO_CTR (1 << 9) #define BXT_DPHY_DEFEATURE_EN (1 << 8) @@ -290,35 +292,35 @@ #define CLOCKSTOP (1 << 1) #define EOT_DISABLE (1 << 0) -#define _MIPIA_LP_BYTECLK (dev_priv->mipi_mmio_base + 0xb060) -#define _MIPIC_LP_BYTECLK (dev_priv->mipi_mmio_base + 0xb860) +#define _MIPIA_LP_BYTECLK (_MIPI_MMIO_BASE(dev_priv) + 0xb060) +#define _MIPIC_LP_BYTECLK (_MIPI_MMIO_BASE(dev_priv) + 0xb860) #define MIPI_LP_BYTECLK(port) _MMIO_MIPI(port, _MIPIA_LP_BYTECLK, _MIPIC_LP_BYTECLK) #define LP_BYTECLK_SHIFT 0 #define LP_BYTECLK_MASK (0xffff << 0) -#define _MIPIA_TLPX_TIME_COUNT (dev_priv->mipi_mmio_base + 0xb0a4) -#define _MIPIC_TLPX_TIME_COUNT (dev_priv->mipi_mmio_base + 0xb8a4) +#define _MIPIA_TLPX_TIME_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb0a4) +#define _MIPIC_TLPX_TIME_COUNT (_MIPI_MMIO_BASE(dev_priv) + 0xb8a4) #define MIPI_TLPX_TIME_COUNT(port) _MMIO_MIPI(port, _MIPIA_TLPX_TIME_COUNT, _MIPIC_TLPX_TIME_COUNT) -#define _MIPIA_CLK_LANE_TIMING (dev_priv->mipi_mmio_base + 0xb098) -#define _MIPIC_CLK_LANE_TIMING (dev_priv->mipi_mmio_base + 0xb898) +#define _MIPIA_CLK_LANE_TIMING (_MIPI_MMIO_BASE(dev_priv) + 0xb098) +#define _MIPIC_CLK_LANE_TIMING (_MIPI_MMIO_BASE(dev_priv) + 0xb898) #define MIPI_CLK_LANE_TIMING(port) _MMIO_MIPI(port, _MIPIA_CLK_LANE_TIMING, _MIPIC_CLK_LANE_TIMING) /* bits 31:0 */ -#define _MIPIA_LP_GEN_DATA (dev_priv->mipi_mmio_base + 0xb064) -#define _MIPIC_LP_GEN_DATA (dev_priv->mipi_mmio_base + 0xb864) +#define _MIPIA_LP_GEN_DATA (_MIPI_MMIO_BASE(dev_priv) + 0xb064) +#define _MIPIC_LP_GEN_DATA (_MIPI_MMIO_BASE(dev_priv) + 0xb864) #define MIPI_LP_GEN_DATA(port) _MMIO_MIPI(port, _MIPIA_LP_GEN_DATA, _MIPIC_LP_GEN_DATA) /* bits 31:0 */ -#define _MIPIA_HS_GEN_DATA (dev_priv->mipi_mmio_base + 0xb068) -#define _MIPIC_HS_GEN_DATA (dev_priv->mipi_mmio_base + 0xb868) +#define _MIPIA_HS_GEN_DATA (_MIPI_MMIO_BASE(dev_priv) + 0xb068) +#define _MIPIC_HS_GEN_DATA (_MIPI_MMIO_BASE(dev_priv) + 0xb868) #define MIPI_HS_GEN_DATA(port) _MMIO_MIPI(port, _MIPIA_HS_GEN_DATA, _MIPIC_HS_GEN_DATA) -#define _MIPIA_LP_GEN_CTRL (dev_priv->mipi_mmio_base + 0xb06c) -#define _MIPIC_LP_GEN_CTRL (dev_priv->mipi_mmio_base + 0xb86c) +#define _MIPIA_LP_GEN_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb06c) +#define _MIPIC_LP_GEN_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb86c) #define MIPI_LP_GEN_CTRL(port) _MMIO_MIPI(port, _MIPIA_LP_GEN_CTRL, _MIPIC_LP_GEN_CTRL) -#define _MIPIA_HS_GEN_CTRL (dev_priv->mipi_mmio_base + 0xb070) -#define _MIPIC_HS_GEN_CTRL (dev_priv->mipi_mmio_base + 0xb870) +#define _MIPIA_HS_GEN_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb070) +#define _MIPIC_HS_GEN_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb870) #define MIPI_HS_GEN_CTRL(port) _MMIO_MIPI(port, _MIPIA_HS_GEN_CTRL, _MIPIC_HS_GEN_CTRL) #define LONG_PACKET_WORD_COUNT_SHIFT 8 #define LONG_PACKET_WORD_COUNT_MASK (0xffff << 8) @@ -330,8 +332,8 @@ #define DATA_TYPE_MASK (0x3f << 0) /* data type values, see include/video/mipi_display.h */ -#define _MIPIA_GEN_FIFO_STAT (dev_priv->mipi_mmio_base + 0xb074) -#define _MIPIC_GEN_FIFO_STAT (dev_priv->mipi_mmio_base + 0xb874) +#define _MIPIA_GEN_FIFO_STAT (_MIPI_MMIO_BASE(dev_priv) + 0xb074) +#define _MIPIC_GEN_FIFO_STAT (_MIPI_MMIO_BASE(dev_priv) + 0xb874) #define MIPI_GEN_FIFO_STAT(port) _MMIO_MIPI(port, _MIPIA_GEN_FIFO_STAT, _MIPIC_GEN_FIFO_STAT) #define DPI_FIFO_EMPTY (1 << 28) #define DBI_FIFO_EMPTY (1 << 27) @@ -348,15 +350,15 @@ #define HS_DATA_FIFO_HALF_EMPTY (1 << 1) #define HS_DATA_FIFO_FULL (1 << 0) -#define _MIPIA_HS_LS_DBI_ENABLE (dev_priv->mipi_mmio_base + 0xb078) -#define _MIPIC_HS_LS_DBI_ENABLE (dev_priv->mipi_mmio_base + 0xb878) +#define _MIPIA_HS_LS_DBI_ENABLE (_MIPI_MMIO_BASE(dev_priv) + 0xb078) +#define _MIPIC_HS_LS_DBI_ENABLE (_MIPI_MMIO_BASE(dev_priv) + 0xb878) #define MIPI_HS_LP_DBI_ENABLE(port) _MMIO_MIPI(port, _MIPIA_HS_LS_DBI_ENABLE, _MIPIC_HS_LS_DBI_ENABLE) #define DBI_HS_LP_MODE_MASK (1 << 0) #define DBI_LP_MODE (1 << 0) #define DBI_HS_MODE (0 << 0) -#define _MIPIA_DPHY_PARAM (dev_priv->mipi_mmio_base + 0xb080) -#define _MIPIC_DPHY_PARAM (dev_priv->mipi_mmio_base + 0xb880) +#define _MIPIA_DPHY_PARAM (_MIPI_MMIO_BASE(dev_priv) + 0xb080) +#define _MIPIC_DPHY_PARAM (_MIPI_MMIO_BASE(dev_priv) + 0xb880) #define MIPI_DPHY_PARAM(port) _MMIO_MIPI(port, _MIPIA_DPHY_PARAM, _MIPIC_DPHY_PARAM) #define EXIT_ZERO_COUNT_SHIFT 24 #define EXIT_ZERO_COUNT_MASK (0x3f << 24) @@ -367,34 +369,34 @@ #define PREPARE_COUNT_SHIFT 0 #define PREPARE_COUNT_MASK (0x3f << 0) -#define _MIPIA_DBI_BW_CTRL (dev_priv->mipi_mmio_base + 0xb084) -#define _MIPIC_DBI_BW_CTRL (dev_priv->mipi_mmio_base + 0xb884) +#define _MIPIA_DBI_BW_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb084) +#define _MIPIC_DBI_BW_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb884) #define MIPI_DBI_BW_CTRL(port) _MMIO_MIPI(port, _MIPIA_DBI_BW_CTRL, _MIPIC_DBI_BW_CTRL) -#define _MIPIA_CLK_LANE_SWITCH_TIME_CNT (dev_priv->mipi_mmio_base + 0xb088) -#define _MIPIC_CLK_LANE_SWITCH_TIME_CNT (dev_priv->mipi_mmio_base + 0xb888) +#define _MIPIA_CLK_LANE_SWITCH_TIME_CNT (_MIPI_MMIO_BASE(dev_priv) + 0xb088) +#define _MIPIC_CLK_LANE_SWITCH_TIME_CNT (_MIPI_MMIO_BASE(dev_priv) + 0xb888) #define MIPI_CLK_LANE_SWITCH_TIME_CNT(port) _MMIO_MIPI(port, _MIPIA_CLK_LANE_SWITCH_TIME_CNT, _MIPIC_CLK_LANE_SWITCH_TIME_CNT) #define LP_HS_SSW_CNT_SHIFT 16 #define LP_HS_SSW_CNT_MASK (0xffff << 16) #define HS_LP_PWR_SW_CNT_SHIFT 0 #define HS_LP_PWR_SW_CNT_MASK (0xffff << 0) -#define _MIPIA_STOP_STATE_STALL (dev_priv->mipi_mmio_base + 0xb08c) -#define _MIPIC_STOP_STATE_STALL (dev_priv->mipi_mmio_base + 0xb88c) +#define _MIPIA_STOP_STATE_STALL (_MIPI_MMIO_BASE(dev_priv) + 0xb08c) +#define _MIPIC_STOP_STATE_STALL (_MIPI_MMIO_BASE(dev_priv) + 0xb88c) #define MIPI_STOP_STATE_STALL(port) _MMIO_MIPI(port, _MIPIA_STOP_STATE_STALL, _MIPIC_STOP_STATE_STALL) #define STOP_STATE_STALL_COUNTER_SHIFT 0 #define STOP_STATE_STALL_COUNTER_MASK (0xff << 0) -#define _MIPIA_INTR_STAT_REG_1 (dev_priv->mipi_mmio_base + 0xb090) -#define _MIPIC_INTR_STAT_REG_1 (dev_priv->mipi_mmio_base + 0xb890) +#define _MIPIA_INTR_STAT_REG_1 (_MIPI_MMIO_BASE(dev_priv) + 0xb090) +#define _MIPIC_INTR_STAT_REG_1 (_MIPI_MMIO_BASE(dev_priv) + 0xb890) #define MIPI_INTR_STAT_REG_1(port) _MMIO_MIPI(port, _MIPIA_INTR_STAT_REG_1, _MIPIC_INTR_STAT_REG_1) -#define _MIPIA_INTR_EN_REG_1 (dev_priv->mipi_mmio_base + 0xb094) -#define _MIPIC_INTR_EN_REG_1 (dev_priv->mipi_mmio_base + 0xb894) +#define _MIPIA_INTR_EN_REG_1 (_MIPI_MMIO_BASE(dev_priv) + 0xb094) +#define _MIPIC_INTR_EN_REG_1 (_MIPI_MMIO_BASE(dev_priv) + 0xb894) #define MIPI_INTR_EN_REG_1(port) _MMIO_MIPI(port, _MIPIA_INTR_EN_REG_1, _MIPIC_INTR_EN_REG_1) #define RX_CONTENTION_DETECTED (1 << 0) /* XXX: only pipe A ?!? */ -#define MIPIA_DBI_TYPEC_CTRL (dev_priv->mipi_mmio_base + 0xb100) +#define MIPIA_DBI_TYPEC_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb100) #define DBI_TYPEC_ENABLE (1 << 31) #define DBI_TYPEC_WIP (1 << 30) #define DBI_TYPEC_OPTION_SHIFT 28 @@ -407,8 +409,8 @@ /* MIPI adapter registers */ -#define _MIPIA_CTRL (dev_priv->mipi_mmio_base + 0xb104) -#define _MIPIC_CTRL (dev_priv->mipi_mmio_base + 0xb904) +#define _MIPIA_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb104) +#define _MIPIC_CTRL (_MIPI_MMIO_BASE(dev_priv) + 0xb904) #define MIPI_CTRL(port) _MMIO_MIPI(port, _MIPIA_CTRL, _MIPIC_CTRL) #define ESCAPE_CLOCK_DIVIDER_SHIFT 5 /* A only */ #define ESCAPE_CLOCK_DIVIDER_MASK (3 << 5) @@ -440,21 +442,21 @@ #define GLK_MIPIIO_PORT_POWERED (1 << 1) /* RO */ #define GLK_MIPIIO_ENABLE (1 << 0) -#define _MIPIA_DATA_ADDRESS (dev_priv->mipi_mmio_base + 0xb108) -#define _MIPIC_DATA_ADDRESS (dev_priv->mipi_mmio_base + 0xb908) +#define _MIPIA_DATA_ADDRESS (_MIPI_MMIO_BASE(dev_priv) + 0xb108) +#define _MIPIC_DATA_ADDRESS (_MIPI_MMIO_BASE(dev_priv) + 0xb908) #define MIPI_DATA_ADDRESS(port) _MMIO_MIPI(port, _MIPIA_DATA_ADDRESS, _MIPIC_DATA_ADDRESS) #define DATA_MEM_ADDRESS_SHIFT 5 #define DATA_MEM_ADDRESS_MASK (0x7ffffff << 5) #define DATA_VALID (1 << 0) -#define _MIPIA_DATA_LENGTH (dev_priv->mipi_mmio_base + 0xb10c) -#define _MIPIC_DATA_LENGTH (dev_priv->mipi_mmio_base + 0xb90c) +#define _MIPIA_DATA_LENGTH (_MIPI_MMIO_BASE(dev_priv) + 0xb10c) +#define _MIPIC_DATA_LENGTH (_MIPI_MMIO_BASE(dev_priv) + 0xb90c) #define MIPI_DATA_LENGTH(port) _MMIO_MIPI(port, _MIPIA_DATA_LENGTH, _MIPIC_DATA_LENGTH) #define DATA_LENGTH_SHIFT 0 #define DATA_LENGTH_MASK (0xfffff << 0) -#define _MIPIA_COMMAND_ADDRESS (dev_priv->mipi_mmio_base + 0xb110) -#define _MIPIC_COMMAND_ADDRESS (dev_priv->mipi_mmio_base + 0xb910) +#define _MIPIA_COMMAND_ADDRESS (_MIPI_MMIO_BASE(dev_priv) + 0xb110) +#define _MIPIC_COMMAND_ADDRESS (_MIPI_MMIO_BASE(dev_priv) + 0xb910) #define MIPI_COMMAND_ADDRESS(port) _MMIO_MIPI(port, _MIPIA_COMMAND_ADDRESS, _MIPIC_COMMAND_ADDRESS) #define COMMAND_MEM_ADDRESS_SHIFT 5 #define COMMAND_MEM_ADDRESS_MASK (0x7ffffff << 5) @@ -462,18 +464,18 @@ #define MEMORY_WRITE_DATA_FROM_PIPE_RENDERING (1 << 1) #define COMMAND_VALID (1 << 0) -#define _MIPIA_COMMAND_LENGTH (dev_priv->mipi_mmio_base + 0xb114) -#define _MIPIC_COMMAND_LENGTH (dev_priv->mipi_mmio_base + 0xb914) +#define _MIPIA_COMMAND_LENGTH (_MIPI_MMIO_BASE(dev_priv) + 0xb114) +#define _MIPIC_COMMAND_LENGTH (_MIPI_MMIO_BASE(dev_priv) + 0xb914) #define MIPI_COMMAND_LENGTH(port) _MMIO_MIPI(port, _MIPIA_COMMAND_LENGTH, _MIPIC_COMMAND_LENGTH) #define COMMAND_LENGTH_SHIFT(n) (8 * (n)) /* n: 0...3 */ #define COMMAND_LENGTH_MASK(n) (0xff << (8 * (n))) -#define _MIPIA_READ_DATA_RETURN0 (dev_priv->mipi_mmio_base + 0xb118) -#define _MIPIC_READ_DATA_RETURN0 (dev_priv->mipi_mmio_base + 0xb918) +#define _MIPIA_READ_DATA_RETURN0 (_MIPI_MMIO_BASE(dev_priv) + 0xb118) +#define _MIPIC_READ_DATA_RETURN0 (_MIPI_MMIO_BASE(dev_priv) + 0xb918) #define MIPI_READ_DATA_RETURN(port, n) _MMIO(_MIPI(port, _MIPIA_READ_DATA_RETURN0, _MIPIC_READ_DATA_RETURN0) + 4 * (n)) /* n: 0...7 */ -#define _MIPIA_READ_DATA_VALID (dev_priv->mipi_mmio_base + 0xb138) -#define _MIPIC_READ_DATA_VALID (dev_priv->mipi_mmio_base + 0xb938) +#define _MIPIA_READ_DATA_VALID (_MIPI_MMIO_BASE(dev_priv) + 0xb138) +#define _MIPIC_READ_DATA_VALID (_MIPI_MMIO_BASE(dev_priv) + 0xb938) #define MIPI_READ_DATA_VALID(port) _MMIO_MIPI(port, _MIPIA_READ_DATA_VALID, _MIPIC_READ_DATA_VALID) #define READ_DATA_VALID(n) (1 << (n)) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index dabdfe09f5e5..1e29b1e6d186 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -1269,6 +1269,10 @@ static void i915_gem_context_release_work(struct work_struct *work) trace_i915_context_free(ctx); GEM_BUG_ON(!i915_gem_context_is_closed(ctx)); + spin_lock(&ctx->i915->gem.contexts.lock); + list_del(&ctx->link); + spin_unlock(&ctx->i915->gem.contexts.lock); + if (ctx->syncobj) drm_syncobj_put(ctx->syncobj); @@ -1383,14 +1387,8 @@ kill_engines(struct i915_gem_engines *engines, bool exit, bool persistent) */ for_each_gem_engine(ce, engines, it) { struct intel_engine_cs *engine; - bool skip = false; - - if (exit) - skip = intel_context_set_exiting(ce); - else if (!persistent) - skip = intel_context_exit_nonpersistent(ce, NULL); - if (skip) + if ((exit || !persistent) && intel_context_revoke(ce)) continue; /* Already marked. */ /* @@ -1521,10 +1519,6 @@ static void context_close(struct i915_gem_context *ctx) ctx->file_priv = ERR_PTR(-EBADF); - spin_lock(&ctx->i915->gem.contexts.lock); - list_del(&ctx->link); - spin_unlock(&ctx->i915->gem.contexts.lock); - client = ctx->client; if (client) { spin_lock(&client->ctx_lock); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index cd75b0ca2555..845023c14eb3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -2424,7 +2424,7 @@ gen8_dispatch_bsd_engine(struct drm_i915_private *dev_priv, /* Check whether the file_priv has already selected one ring. */ if ((int)file_priv->bsd_engine < 0) file_priv->bsd_engine = - get_random_int() % num_vcs_engines(dev_priv); + prandom_u32_max(num_vcs_engines(dev_priv)); return file_priv->bsd_engine; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h index 1b88ea13435c..5a7a14e85c3f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h @@ -12,8 +12,6 @@ struct drm_i915_private; struct drm_i915_gem_object; struct intel_memory_region; -extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops; - void __iomem * i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index 3218981488cc..73d9eda1d6b7 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -413,7 +413,7 @@ retry: vma->mmo = mmo; if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) - intel_wakeref_auto(&to_gt(i915)->ggtt->userfault_wakeref, + intel_wakeref_auto(&to_gt(i915)->userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); if (write) { @@ -550,6 +550,20 @@ out: intel_runtime_pm_put(&i915->runtime_pm, wakeref); } +void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object *obj) +{ + struct ttm_buffer_object *bo = i915_gem_to_ttm(obj); + struct ttm_device *bdev = bo->bdev; + + drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping); + + if (obj->userfault_count) { + /* rpm wakeref provide exclusive access */ + list_del(&obj->userfault_link); + obj->userfault_count = 0; + } +} + void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj) { struct i915_mmap_offset *mmo, *mn; @@ -573,6 +587,13 @@ void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj) spin_lock(&obj->mmo.lock); } spin_unlock(&obj->mmo.lock); + + if (obj->userfault_count) { + mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); + list_del(&obj->userfault_link); + mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); + obj->userfault_count = 0; + } } static struct i915_mmap_offset * diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.h b/drivers/gpu/drm/i915/gem/i915_gem_mman.h index efee9e0d2508..1fa91b3033b3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.h @@ -27,6 +27,7 @@ int i915_gem_dumb_mmap_offset(struct drm_file *file_priv, void __i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj); void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj); +void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object *obj); void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj); #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c index 7cab89618bad..6b8710ba8ded 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c @@ -238,7 +238,7 @@ static void __i915_gem_object_free_mmaps(struct drm_i915_gem_object *obj) { /* Skip serialisation and waking the device if known to be not used. */ - if (obj->userfault_count) + if (obj->userfault_count && !IS_DGFX(to_i915(obj->base.dev))) i915_gem_object_release_mmap_gtt(obj); if (!RB_EMPTY_ROOT(&obj->mmo.offsets)) { @@ -667,6 +667,41 @@ int i915_gem_object_migrate(struct drm_i915_gem_object *obj, struct i915_gem_ww_ctx *ww, enum intel_region_id id) { + return __i915_gem_object_migrate(obj, ww, id, obj->flags); +} + +/** + * __i915_gem_object_migrate - Migrate an object to the desired region id, with + * control of the extra flags + * @obj: The object to migrate. + * @ww: An optional struct i915_gem_ww_ctx. If NULL, the backend may + * not be successful in evicting other objects to make room for this object. + * @id: The region id to migrate to. + * @flags: The object flags. Normally just obj->flags. + * + * Attempt to migrate the object to the desired memory region. The + * object backend must support migration and the object may not be + * pinned, (explicitly pinned pages or pinned vmas). The object must + * be locked. + * On successful completion, the object will have pages pointing to + * memory in the new region, but an async migration task may not have + * completed yet, and to accomplish that, i915_gem_object_wait_migration() + * must be called. + * + * Note: the @ww parameter is not used yet, but included to make sure + * callers put some effort into obtaining a valid ww ctx if one is + * available. + * + * Return: 0 on success. Negative error code on failure. In particular may + * return -ENXIO on lack of region space, -EDEADLK for deadlock avoidance + * if @ww is set, -EINTR or -ERESTARTSYS if signal pending, and + * -EBUSY if the object is pinned. + */ +int __i915_gem_object_migrate(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww, + enum intel_region_id id, + unsigned int flags) +{ struct drm_i915_private *i915 = to_i915(obj->base.dev); struct intel_memory_region *mr; @@ -686,7 +721,7 @@ int i915_gem_object_migrate(struct drm_i915_gem_object *obj, return 0; } - return obj->ops->migrate(obj, mr); + return obj->ops->migrate(obj, mr, flags); } /** diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index 7317d4102955..1723af9b0f6a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -608,6 +608,10 @@ bool i915_gem_object_migratable(struct drm_i915_gem_object *obj); int i915_gem_object_migrate(struct drm_i915_gem_object *obj, struct i915_gem_ww_ctx *ww, enum intel_region_id id); +int __i915_gem_object_migrate(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww, + enum intel_region_id id, + unsigned int flags); bool i915_gem_object_can_migrate(struct drm_i915_gem_object *obj, enum intel_region_id id); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index 9f6b14ec189a..d0d6772e6f36 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -107,7 +107,8 @@ struct drm_i915_gem_object_ops { * pinning or for as long as the object lock is held. */ int (*migrate)(struct drm_i915_gem_object *obj, - struct intel_memory_region *mr); + struct intel_memory_region *mr, + unsigned int flags); void (*release)(struct drm_i915_gem_object *obj); @@ -298,7 +299,8 @@ struct drm_i915_gem_object { }; /** - * Whether the object is currently in the GGTT mmap. + * Whether the object is currently in the GGTT or any other supported + * fake offset mmap backed by lmem. */ unsigned int userfault_count; struct list_head userfault_link; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index 8357dbdcab5c..4df50b049cea 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -20,7 +20,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, unsigned int sg_page_sizes) { struct drm_i915_private *i915 = to_i915(obj->base.dev); - unsigned long supported = INTEL_INFO(i915)->page_sizes; + unsigned long supported = RUNTIME_INFO(i915)->page_sizes; bool shrinkable; int i; @@ -66,7 +66,7 @@ void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj, shrinkable = i915_gem_object_is_shrinkable(obj); if (i915_gem_object_is_tiled(obj) && - i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) { + i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) { GEM_BUG_ON(i915_gem_object_has_tiling_quirk(obj)); i915_gem_object_set_tiling_quirk(obj); GEM_BUG_ON(!list_empty(&obj->mm.link)); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c index 00359ec9d58b..3428f735e786 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c @@ -24,7 +24,7 @@ void i915_gem_suspend(struct drm_i915_private *i915) { GEM_TRACE("%s\n", dev_name(i915->drm.dev)); - intel_wakeref_auto(&to_gt(i915)->ggtt->userfault_wakeref, 0); + intel_wakeref_auto(&to_gt(i915)->userfault_wakeref, 0); flush_workqueue(i915->wq); /* diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 166d0a4b9e8c..acc561c0f0aa 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -18,10 +18,12 @@ #include "gt/intel_region_lmem.h" #include "i915_drv.h" #include "i915_gem_stolen.h" +#include "i915_pci.h" #include "i915_reg.h" #include "i915_utils.h" #include "i915_vgpu.h" #include "intel_mchbar_regs.h" +#include "intel_pci_config.h" /* * The BIOS typically reserves some of the system's memory for the exclusive @@ -428,48 +430,29 @@ static int i915_gem_init_stolen(struct intel_memory_region *mem) reserved_base = stolen_top; reserved_size = 0; - switch (GRAPHICS_VER(i915)) { - case 2: - case 3: - break; - case 4: - if (!IS_G4X(i915)) - break; - fallthrough; - case 5: - g4x_get_stolen_reserved(i915, uncore, + if (GRAPHICS_VER(i915) >= 11) { + icl_get_stolen_reserved(i915, uncore, &reserved_base, &reserved_size); - break; - case 6: - gen6_get_stolen_reserved(i915, uncore, - &reserved_base, &reserved_size); - break; - case 7: - if (IS_VALLEYVIEW(i915)) - vlv_get_stolen_reserved(i915, uncore, - &reserved_base, &reserved_size); - else - gen7_get_stolen_reserved(i915, uncore, - &reserved_base, &reserved_size); - break; - case 8: - case 9: + } else if (GRAPHICS_VER(i915) >= 8) { if (IS_LP(i915)) chv_get_stolen_reserved(i915, uncore, &reserved_base, &reserved_size); else bdw_get_stolen_reserved(i915, uncore, &reserved_base, &reserved_size); - break; - default: - MISSING_CASE(GRAPHICS_VER(i915)); - fallthrough; - case 11: - case 12: - icl_get_stolen_reserved(i915, uncore, - &reserved_base, - &reserved_size); - break; + } else if (GRAPHICS_VER(i915) >= 7) { + if (IS_VALLEYVIEW(i915)) + vlv_get_stolen_reserved(i915, uncore, + &reserved_base, &reserved_size); + else + gen7_get_stolen_reserved(i915, uncore, + &reserved_base, &reserved_size); + } else if (GRAPHICS_VER(i915) >= 6) { + gen6_get_stolen_reserved(i915, uncore, + &reserved_base, &reserved_size); + } else if (GRAPHICS_VER(i915) >= 5 || IS_G4X(i915)) { + g4x_get_stolen_reserved(i915, uncore, + &reserved_base, &reserved_size); } /* @@ -827,10 +810,13 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, if (WARN_ON_ONCE(instance)) return ERR_PTR(-ENODEV); + if (!i915_pci_resource_valid(pdev, GEN12_LMEM_BAR)) + return ERR_PTR(-ENXIO); + /* Use DSM base address instead for stolen memory */ dsm_base = intel_uncore_read64(uncore, GEN12_DSMBASE); if (IS_DG1(uncore->i915)) { - lmem_size = pci_resource_len(pdev, 2); + lmem_size = pci_resource_len(pdev, GEN12_LMEM_BAR); if (WARN_ON(lmem_size < dsm_base)) return ERR_PTR(-ENODEV); } else { @@ -842,11 +828,11 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type, } dsm_size = lmem_size - dsm_base; - if (pci_resource_len(pdev, 2) < lmem_size) { + if (pci_resource_len(pdev, GEN12_LMEM_BAR) < lmem_size) { io_start = 0; io_size = 0; } else { - io_start = pci_resource_start(pdev, 2) + dsm_base; + io_start = pci_resource_start(pdev, GEN12_LMEM_BAR) + dsm_base; io_size = dsm_size; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c index 85518b28cd72..fd42b89b7162 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_tiling.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_tiling.c @@ -278,7 +278,7 @@ i915_gem_object_set_tiling(struct drm_i915_gem_object *obj, */ if (i915_gem_object_has_pages(obj) && obj->mm.madv == I915_MADV_WILLNEED && - i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) { + i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) { if (tiling == I915_TILING_NONE) { GEM_BUG_ON(!i915_gem_object_has_tiling_quirk(obj)); i915_gem_object_clear_tiling_quirk(obj); @@ -458,7 +458,7 @@ i915_gem_get_tiling_ioctl(struct drm_device *dev, void *data, } /* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */ - if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES) + if (dev_priv->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) args->phys_swizzle_mode = I915_BIT_6_SWIZZLE_UNKNOWN; else args->phys_swizzle_mode = args->swizzle_mode; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index f64a3deb12fc..4f861782c3e8 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -509,9 +509,18 @@ static int i915_ttm_shrink(struct drm_i915_gem_object *obj, unsigned int flags) static void i915_ttm_delete_mem_notify(struct ttm_buffer_object *bo) { struct drm_i915_gem_object *obj = i915_ttm_to_gem(bo); + intel_wakeref_t wakeref = 0; + + if (bo->resource && likely(obj)) { + /* ttm_bo_release() already has dma_resv_lock */ + if (i915_ttm_cpu_maps_iomem(bo->resource)) + wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm); - if (likely(obj)) { __i915_gem_object_pages_fini(obj); + + if (wakeref) + intel_runtime_pm_put(&to_i915(obj->base.dev)->runtime_pm, wakeref); + i915_ttm_free_cached_io_rsgt(obj); } } @@ -839,9 +848,10 @@ static int __i915_ttm_migrate(struct drm_i915_gem_object *obj, } static int i915_ttm_migrate(struct drm_i915_gem_object *obj, - struct intel_memory_region *mr) + struct intel_memory_region *mr, + unsigned int flags) { - return __i915_ttm_migrate(obj, mr, obj->flags); + return __i915_ttm_migrate(obj, mr, flags); } static void i915_ttm_put_pages(struct drm_i915_gem_object *obj, @@ -981,6 +991,7 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) struct ttm_buffer_object *bo = area->vm_private_data; struct drm_device *dev = bo->base.dev; struct drm_i915_gem_object *obj; + intel_wakeref_t wakeref = 0; vm_fault_t ret; int idx; @@ -1002,6 +1013,9 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } + if (i915_ttm_cpu_maps_iomem(bo->resource)) + wakeref = intel_runtime_pm_get(&to_i915(obj->base.dev)->runtime_pm); + if (!i915_ttm_resource_mappable(bo->resource)) { int err = -ENODEV; int i; @@ -1023,7 +1037,8 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) if (err) { drm_dbg(dev, "Unable to make resource CPU accessible\n"); dma_resv_unlock(bo->base.resv); - return VM_FAULT_SIGBUS; + ret = VM_FAULT_SIGBUS; + goto out_rpm; } } @@ -1034,12 +1049,30 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) } else { ret = ttm_bo_vm_dummy_page(vmf, vmf->vma->vm_page_prot); } + if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) - return ret; + goto out_rpm; + + /* ttm_bo_vm_reserve() already has dma_resv_lock */ + if (ret == VM_FAULT_NOPAGE && wakeref && !obj->userfault_count) { + obj->userfault_count = 1; + mutex_lock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); + list_add(&obj->userfault_link, &to_gt(to_i915(obj->base.dev))->lmem_userfault_list); + mutex_unlock(&to_gt(to_i915(obj->base.dev))->lmem_userfault_lock); + } + + if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) + intel_wakeref_auto(&to_gt(to_i915(obj->base.dev))->userfault_wakeref, + msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); i915_ttm_adjust_lru(obj); dma_resv_unlock(bo->base.resv); + +out_rpm: + if (wakeref) + intel_runtime_pm_put(&to_i915(obj->base.dev)->runtime_pm, wakeref); + return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 8423df021b71..d4398948f016 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -426,12 +426,11 @@ static const struct drm_i915_gem_object_ops i915_gem_userptr_ops = { static int probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { - const unsigned long end = addr + len; + VMA_ITERATOR(vmi, mm, addr); struct vm_area_struct *vma; - int ret = -EFAULT; mmap_read_lock(mm); - for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) { + for_each_vma_range(vmi, vma, addr + len) { /* Check for holes, note that we also update the addr below */ if (vma->vm_start > addr) break; @@ -439,16 +438,13 @@ probe_range(struct mm_struct *mm, unsigned long addr, unsigned long len) if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) break; - if (vma->vm_end >= end) { - ret = 0; - break; - } - addr = vma->vm_end; } mmap_read_unlock(mm); - return ret; + if (vma) + return -EFAULT; + return 0; } /* diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c index 72ce2c9f42fd..c570cf780079 100644 --- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c +++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c @@ -358,7 +358,7 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single) static int igt_check_page_sizes(struct i915_vma *vma) { struct drm_i915_private *i915 = vma->vm->i915; - unsigned int supported = INTEL_INFO(i915)->page_sizes; + unsigned int supported = RUNTIME_INFO(i915)->page_sizes; struct drm_i915_gem_object *obj = vma->obj; int err; @@ -419,7 +419,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg) { struct i915_ppgtt *ppgtt = arg; struct drm_i915_private *i915 = ppgtt->vm.i915; - unsigned int saved_mask = INTEL_INFO(i915)->page_sizes; + unsigned int saved_mask = RUNTIME_INFO(i915)->page_sizes; struct drm_i915_gem_object *obj; struct i915_vma *vma; int i, j, single; @@ -438,7 +438,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg) combination |= page_sizes[j]; } - mkwrite_device_info(i915)->page_sizes = combination; + RUNTIME_INFO(i915)->page_sizes = combination; for (single = 0; single <= 1; ++single) { obj = fake_huge_pages_object(i915, combination, !!single); @@ -485,7 +485,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg) out_put: i915_gem_object_put(obj); out_device: - mkwrite_device_info(i915)->page_sizes = saved_mask; + RUNTIME_INFO(i915)->page_sizes = saved_mask; return err; } @@ -495,7 +495,7 @@ static int igt_mock_memory_region_huge_pages(void *arg) const unsigned int flags[] = { 0, I915_BO_ALLOC_CONTIGUOUS }; struct i915_ppgtt *ppgtt = arg; struct drm_i915_private *i915 = ppgtt->vm.i915; - unsigned long supported = INTEL_INFO(i915)->page_sizes; + unsigned long supported = RUNTIME_INFO(i915)->page_sizes; struct intel_memory_region *mem; struct drm_i915_gem_object *obj; struct i915_vma *vma; @@ -573,7 +573,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg) { struct i915_ppgtt *ppgtt = arg; struct drm_i915_private *i915 = ppgtt->vm.i915; - unsigned long supported = INTEL_INFO(i915)->page_sizes; + unsigned long supported = RUNTIME_INFO(i915)->page_sizes; struct drm_i915_gem_object *obj; int bit; int err; @@ -1390,7 +1390,7 @@ out_put: static int igt_ppgtt_sanity_check(void *arg) { struct drm_i915_private *i915 = arg; - unsigned int supported = INTEL_INFO(i915)->page_sizes; + unsigned int supported = RUNTIME_INFO(i915)->page_sizes; struct { igt_create_fn fn; unsigned int flags; @@ -1764,8 +1764,8 @@ int i915_gem_huge_page_mock_selftests(void) return -ENOMEM; /* Pretend to be a device which supports the 48b PPGTT */ - mkwrite_device_info(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL; - mkwrite_device_info(dev_priv)->ppgtt_size = 48; + RUNTIME_INFO(dev_priv)->ppgtt_type = INTEL_PPGTT_FULL; + RUNTIME_INFO(dev_priv)->ppgtt_size = 48; ppgtt = i915_ppgtt_create(to_gt(dev_priv), 0); if (IS_ERR(ppgtt)) { diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c index 3cfc621ef363..9a6a6b5b722b 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c @@ -711,7 +711,7 @@ static bool bad_swizzling(struct drm_i915_private *i915) { struct i915_ggtt *ggtt = to_gt(i915)->ggtt; - if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) + if (i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) return true; if (has_bit17_swizzle(ggtt->bit_6_swizzle_x) || diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c index 55bf23dc0e54..b73c91aa5450 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c @@ -367,7 +367,7 @@ static int igt_partial_tiling(void *arg) unsigned int pitch; struct tile tile; - if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) + if (i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) /* * The swizzling pattern is actually unknown as it * varies based on physical address of each page. @@ -464,7 +464,7 @@ static int igt_smoke_tiling(void *arg) * Remember to look at the st_seed if we see a flip-flop in BAT! */ - if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) + if (i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) return 0; obj = huge_gem_object(i915, diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index 1bb766c79dcb..5aaacc53fa4c 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -247,6 +247,7 @@ err_scratch1: i915_gem_object_put(vm->scratch[1]); err_scratch0: i915_gem_object_put(vm->scratch[0]); + vm->scratch[0] = NULL; return ret; } @@ -268,9 +269,10 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm) gen6_ppgtt_free_pd(ppgtt); free_scratch(vm); - mutex_destroy(&ppgtt->flush); + if (ppgtt->base.pd) + free_pd(&ppgtt->base.vm, ppgtt->base.pd); - free_pd(&ppgtt->base.vm, ppgtt->base.pd); + mutex_destroy(&ppgtt->flush); } static void pd_vma_bind(struct i915_address_space *vm, @@ -449,19 +451,17 @@ struct i915_ppgtt *gen6_ppgtt_create(struct intel_gt *gt) err = gen6_ppgtt_init_scratch(ppgtt); if (err) - goto err_free; + goto err_put; ppgtt->base.pd = gen6_alloc_top_pd(ppgtt); if (IS_ERR(ppgtt->base.pd)) { err = PTR_ERR(ppgtt->base.pd); - goto err_scratch; + goto err_put; } return &ppgtt->base; -err_scratch: - free_scratch(&ppgtt->base.vm); -err_free: - kfree(ppgtt); +err_put: + i915_vm_put(&ppgtt->base.vm); return ERR_PTR(err); } diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c index 98645797962f..e49fa6fa6aee 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.c @@ -165,10 +165,12 @@ static u32 preparser_disable(bool state) return MI_ARB_CHECK | 1 << 8 | state; } -u32 *gen12_emit_aux_table_inv(u32 *cs, const i915_reg_t inv_reg) +u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg) { + u32 gsi_offset = gt->uncore->gsi_offset; + *cs++ = MI_LOAD_REGISTER_IMM(1) | MI_LRI_MMIO_REMAP_EN; - *cs++ = i915_mmio_reg_offset(inv_reg); + *cs++ = i915_mmio_reg_offset(inv_reg) + gsi_offset; *cs++ = AUX_INV; *cs++ = MI_NOOP; @@ -254,7 +256,8 @@ int gen12_emit_flush_rcs(struct i915_request *rq, u32 mode) if (!HAS_FLAT_CCS(rq->engine->i915)) { /* hsdes: 1809175790 */ - cs = gen12_emit_aux_table_inv(cs, GEN12_GFX_CCS_AUX_NV); + cs = gen12_emit_aux_table_inv(rq->engine->gt, + cs, GEN12_GFX_CCS_AUX_NV); } *cs++ = preparser_disable(false); @@ -313,9 +316,11 @@ int gen12_emit_flush_xcs(struct i915_request *rq, u32 mode) if (aux_inv) { /* hsdes: 1809175790 */ if (rq->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(cs, GEN12_VD0_AUX_NV); + cs = gen12_emit_aux_table_inv(rq->engine->gt, + cs, GEN12_VD0_AUX_NV); else - cs = gen12_emit_aux_table_inv(cs, GEN12_VE0_AUX_NV); + cs = gen12_emit_aux_table_inv(rq->engine->gt, + cs, GEN12_VE0_AUX_NV); } if (mode & EMIT_INVALIDATE) diff --git a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h index 32e3d2b831bb..e4d24c811dd6 100644 --- a/drivers/gpu/drm/i915/gt/gen8_engine_cs.h +++ b/drivers/gpu/drm/i915/gt/gen8_engine_cs.h @@ -13,6 +13,7 @@ #include "intel_gt_regs.h" #include "intel_gpu_commands.h" +struct intel_gt; struct i915_request; int gen8_emit_flush_rcs(struct i915_request *rq, u32 mode); @@ -45,7 +46,7 @@ u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen11_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); u32 *gen12_emit_fini_breadcrumb_rcs(struct i915_request *rq, u32 *cs); -u32 *gen12_emit_aux_table_inv(u32 *cs, const i915_reg_t inv_reg); +u32 *gen12_emit_aux_table_inv(struct intel_gt *gt, u32 *cs, const i915_reg_t inv_reg); static inline u32 * __gen8_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u32 offset) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index c7bd5d71b03e..2128b7a72a25 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -196,7 +196,10 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm) if (intel_vgpu_active(vm->i915)) gen8_ppgtt_notify_vgt(ppgtt, false); - __gen8_ppgtt_cleanup(vm, ppgtt->pd, gen8_pd_top_count(vm), vm->top); + if (ppgtt->pd) + __gen8_ppgtt_cleanup(vm, ppgtt->pd, + gen8_pd_top_count(vm), vm->top); + free_scratch(vm); } @@ -803,8 +806,10 @@ static int gen8_init_scratch(struct i915_address_space *vm) struct drm_i915_gem_object *obj; obj = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K); - if (IS_ERR(obj)) + if (IS_ERR(obj)) { + ret = PTR_ERR(obj); goto free_scratch; + } ret = map_pt_dma(vm, obj); if (ret) { @@ -823,7 +828,8 @@ static int gen8_init_scratch(struct i915_address_space *vm) free_scratch: while (i--) i915_gem_object_put(vm->scratch[i]); - return -ENOMEM; + vm->scratch[0] = NULL; + return ret; } static int gen8_preallocate_top_level_pdp(struct i915_ppgtt *ppgtt) @@ -901,6 +907,7 @@ err_pd: struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, unsigned long lmem_pt_obj_flags) { + struct i915_page_directory *pd; struct i915_ppgtt *ppgtt; int err; @@ -946,21 +953,7 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, ppgtt->vm.alloc_scratch_dma = alloc_pt_dma; } - err = gen8_init_scratch(&ppgtt->vm); - if (err) - goto err_free; - - ppgtt->pd = gen8_alloc_top_pd(&ppgtt->vm); - if (IS_ERR(ppgtt->pd)) { - err = PTR_ERR(ppgtt->pd); - goto err_free_scratch; - } - - if (!i915_vm_is_4lvl(&ppgtt->vm)) { - err = gen8_preallocate_top_level_pdp(ppgtt); - if (err) - goto err_free_pd; - } + ppgtt->vm.pte_encode = gen8_pte_encode; ppgtt->vm.bind_async_flags = I915_VMA_LOCAL_BIND; ppgtt->vm.insert_entries = gen8_ppgtt_insert; @@ -971,22 +964,31 @@ struct i915_ppgtt *gen8_ppgtt_create(struct intel_gt *gt, ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc; ppgtt->vm.clear_range = gen8_ppgtt_clear; ppgtt->vm.foreach = gen8_ppgtt_foreach; + ppgtt->vm.cleanup = gen8_ppgtt_cleanup; - ppgtt->vm.pte_encode = gen8_pte_encode; + err = gen8_init_scratch(&ppgtt->vm); + if (err) + goto err_put; + + pd = gen8_alloc_top_pd(&ppgtt->vm); + if (IS_ERR(pd)) { + err = PTR_ERR(pd); + goto err_put; + } + ppgtt->pd = pd; + + if (!i915_vm_is_4lvl(&ppgtt->vm)) { + err = gen8_preallocate_top_level_pdp(ppgtt); + if (err) + goto err_put; + } if (intel_vgpu_active(gt->i915)) gen8_ppgtt_notify_vgt(ppgtt, true); - ppgtt->vm.cleanup = gen8_ppgtt_cleanup; - return ppgtt; -err_free_pd: - __gen8_ppgtt_cleanup(&ppgtt->vm, ppgtt->pd, - gen8_pd_top_count(&ppgtt->vm), ppgtt->vm.top); -err_free_scratch: - free_scratch(&ppgtt->vm); -err_free: - kfree(ppgtt); +err_put: + i915_vm_put(&ppgtt->vm); return ERR_PTR(err); } diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c index 654a092ed3d6..e94365b08f1e 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.c +++ b/drivers/gpu/drm/i915/gt/intel_context.c @@ -614,13 +614,12 @@ bool intel_context_ban(struct intel_context *ce, struct i915_request *rq) return ret; } -bool intel_context_exit_nonpersistent(struct intel_context *ce, - struct i915_request *rq) +bool intel_context_revoke(struct intel_context *ce) { bool ret = intel_context_set_exiting(ce); if (ce->ops->revoke) - ce->ops->revoke(ce, rq, ce->engine->props.preempt_timeout_ms); + ce->ops->revoke(ce, NULL, ce->engine->props.preempt_timeout_ms); return ret; } diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h index 8e2d70630c49..be09fb2e883a 100644 --- a/drivers/gpu/drm/i915/gt/intel_context.h +++ b/drivers/gpu/drm/i915/gt/intel_context.h @@ -329,8 +329,7 @@ static inline bool intel_context_set_exiting(struct intel_context *ce) return test_and_set_bit(CONTEXT_EXITING, &ce->flags); } -bool intel_context_exit_nonpersistent(struct intel_context *ce, - struct i915_request *rq); +bool intel_context_revoke(struct intel_context *ce); static inline bool intel_context_force_single_submission(const struct intel_context *ce) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 17e7f20bbb48..1f7188129cd1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -654,16 +654,83 @@ bool gen11_vdbox_has_sfc(struct intel_gt *gt, */ if ((gt->info.sfc_mask & BIT(physical_vdbox / 2)) == 0) return false; - else if (GRAPHICS_VER(i915) == 12) + else if (MEDIA_VER(i915) >= 12) return (physical_vdbox % 2 == 0) || !(BIT(physical_vdbox - 1) & vdbox_mask); - else if (GRAPHICS_VER(i915) == 11) + else if (MEDIA_VER(i915) == 11) return logical_vdbox % 2 == 0; - MISSING_CASE(GRAPHICS_VER(i915)); return false; } +static void engine_mask_apply_media_fuses(struct intel_gt *gt) +{ + struct drm_i915_private *i915 = gt->i915; + unsigned int logical_vdbox = 0; + unsigned int i; + u32 media_fuse, fuse1; + u16 vdbox_mask; + u16 vebox_mask; + + if (MEDIA_VER(gt->i915) < 11) + return; + + /* + * On newer platforms the fusing register is called 'enable' and has + * enable semantics, while on older platforms it is called 'disable' + * and bits have disable semantices. + */ + media_fuse = intel_uncore_read(gt->uncore, GEN11_GT_VEBOX_VDBOX_DISABLE); + if (MEDIA_VER_FULL(i915) < IP_VER(12, 50)) + media_fuse = ~media_fuse; + + vdbox_mask = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK; + vebox_mask = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >> + GEN11_GT_VEBOX_DISABLE_SHIFT; + + if (MEDIA_VER_FULL(i915) >= IP_VER(12, 50)) { + fuse1 = intel_uncore_read(gt->uncore, HSW_PAVP_FUSE1); + gt->info.sfc_mask = REG_FIELD_GET(XEHP_SFC_ENABLE_MASK, fuse1); + } else { + gt->info.sfc_mask = ~0; + } + + for (i = 0; i < I915_MAX_VCS; i++) { + if (!HAS_ENGINE(gt, _VCS(i))) { + vdbox_mask &= ~BIT(i); + continue; + } + + if (!(BIT(i) & vdbox_mask)) { + gt->info.engine_mask &= ~BIT(_VCS(i)); + drm_dbg(&i915->drm, "vcs%u fused off\n", i); + continue; + } + + if (gen11_vdbox_has_sfc(gt, i, logical_vdbox, vdbox_mask)) + gt->info.vdbox_sfc_access |= BIT(i); + logical_vdbox++; + } + drm_dbg(&i915->drm, "vdbox enable: %04x, instances: %04lx\n", + vdbox_mask, VDBOX_MASK(gt)); + GEM_BUG_ON(vdbox_mask != VDBOX_MASK(gt)); + + for (i = 0; i < I915_MAX_VECS; i++) { + if (!HAS_ENGINE(gt, _VECS(i))) { + vebox_mask &= ~BIT(i); + continue; + } + + if (!(BIT(i) & vebox_mask)) { + gt->info.engine_mask &= ~BIT(_VECS(i)); + drm_dbg(&i915->drm, "vecs%u fused off\n", i); + } + } + drm_dbg(&i915->drm, "vebox enable: %04x, instances: %04lx\n", + vebox_mask, VEBOX_MASK(gt)); + GEM_BUG_ON(vebox_mask != VEBOX_MASK(gt)); +} + static void engine_mask_apply_compute_fuses(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; @@ -672,6 +739,9 @@ static void engine_mask_apply_compute_fuses(struct intel_gt *gt) unsigned long ccs_mask; unsigned int i; + if (GRAPHICS_VER(i915) < 11) + return; + if (hweight32(CCS_MASK(gt)) <= 1) return; @@ -694,6 +764,10 @@ static void engine_mask_apply_copy_fuses(struct intel_gt *gt) unsigned long meml3_mask; unsigned long quad; + if (!(GRAPHICS_VER_FULL(i915) >= IP_VER(12, 60) && + GRAPHICS_VER_FULL(i915) < IP_VER(12, 70))) + return; + meml3_mask = intel_uncore_read(gt->uncore, GEN10_MIRROR_FUSE3); meml3_mask = REG_FIELD_GET(GEN12_MEML3_EN_MASK, meml3_mask); @@ -727,75 +801,11 @@ static void engine_mask_apply_copy_fuses(struct intel_gt *gt) */ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt) { - struct drm_i915_private *i915 = gt->i915; struct intel_gt_info *info = >->info; - struct intel_uncore *uncore = gt->uncore; - unsigned int logical_vdbox = 0; - unsigned int i; - u32 media_fuse, fuse1; - u16 vdbox_mask; - u16 vebox_mask; - - info->engine_mask = INTEL_INFO(i915)->platform_engine_mask; - - if (GRAPHICS_VER(i915) < 11) - return info->engine_mask; - /* - * On newer platforms the fusing register is called 'enable' and has - * enable semantics, while on older platforms it is called 'disable' - * and bits have disable semantices. - */ - media_fuse = intel_uncore_read(uncore, GEN11_GT_VEBOX_VDBOX_DISABLE); - if (GRAPHICS_VER_FULL(i915) < IP_VER(12, 50)) - media_fuse = ~media_fuse; - - vdbox_mask = media_fuse & GEN11_GT_VDBOX_DISABLE_MASK; - vebox_mask = (media_fuse & GEN11_GT_VEBOX_DISABLE_MASK) >> - GEN11_GT_VEBOX_DISABLE_SHIFT; - - if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) { - fuse1 = intel_uncore_read(uncore, HSW_PAVP_FUSE1); - gt->info.sfc_mask = REG_FIELD_GET(XEHP_SFC_ENABLE_MASK, fuse1); - } else { - gt->info.sfc_mask = ~0; - } - - for (i = 0; i < I915_MAX_VCS; i++) { - if (!HAS_ENGINE(gt, _VCS(i))) { - vdbox_mask &= ~BIT(i); - continue; - } - - if (!(BIT(i) & vdbox_mask)) { - info->engine_mask &= ~BIT(_VCS(i)); - drm_dbg(&i915->drm, "vcs%u fused off\n", i); - continue; - } - - if (gen11_vdbox_has_sfc(gt, i, logical_vdbox, vdbox_mask)) - gt->info.vdbox_sfc_access |= BIT(i); - logical_vdbox++; - } - drm_dbg(&i915->drm, "vdbox enable: %04x, instances: %04lx\n", - vdbox_mask, VDBOX_MASK(gt)); - GEM_BUG_ON(vdbox_mask != VDBOX_MASK(gt)); - - for (i = 0; i < I915_MAX_VECS; i++) { - if (!HAS_ENGINE(gt, _VECS(i))) { - vebox_mask &= ~BIT(i); - continue; - } - - if (!(BIT(i) & vebox_mask)) { - info->engine_mask &= ~BIT(_VECS(i)); - drm_dbg(&i915->drm, "vecs%u fused off\n", i); - } - } - drm_dbg(&i915->drm, "vebox enable: %04x, instances: %04lx\n", - vebox_mask, VEBOX_MASK(gt)); - GEM_BUG_ON(vebox_mask != VEBOX_MASK(gt)); + GEM_BUG_ON(!info->engine_mask); + engine_mask_apply_media_fuses(gt); engine_mask_apply_compute_fuses(gt); engine_mask_apply_copy_fuses(gt); @@ -1688,9 +1698,9 @@ bool intel_engine_irq_enable(struct intel_engine_cs *engine) return false; /* Caller disables interrupts */ - spin_lock(&engine->gt->irq_lock); + spin_lock(engine->gt->irq_lock); engine->irq_enable(engine); - spin_unlock(&engine->gt->irq_lock); + spin_unlock(engine->gt->irq_lock); return true; } @@ -1701,9 +1711,9 @@ void intel_engine_irq_disable(struct intel_engine_cs *engine) return; /* Caller disables interrupts */ - spin_lock(&engine->gt->irq_lock); + spin_lock(engine->gt->irq_lock); engine->irq_disable(engine); - spin_unlock(&engine->gt->irq_lock); + spin_unlock(engine->gt->irq_lock); } void intel_engines_reset_default_submission(struct intel_gt *gt) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_regs.h b/drivers/gpu/drm/i915/gt/intel_engine_regs.h index 889f0df3940b..fe1a0d5fd4b1 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_regs.h @@ -110,6 +110,7 @@ #define RING_SBBSTATE(base) _MMIO((base) + 0x118) /* hsw+ */ #define RING_SBBADDR_UDW(base) _MMIO((base) + 0x11c) /* gen8+ */ #define RING_BBADDR(base) _MMIO((base) + 0x140) +#define RING_BB_OFFSET(base) _MMIO((base) + 0x158) #define RING_BBADDR_UDW(base) _MMIO((base) + 0x168) /* gen8+ */ #define CCID(base) _MMIO((base) + 0x180) #define CCID_EN BIT(0) diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index 633a7e5dba3b..6b5d4ea22b67 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -166,6 +166,21 @@ struct intel_engine_execlists { struct timer_list preempt; /** + * @preempt_target: active request at the time of the preemption request + * + * We force a preemption to occur if the pending contexts have not + * been promoted to active upon receipt of the CS ack event within + * the timeout. This timeout maybe chosen based on the target, + * using a very short timeout if the context is no longer schedulable. + * That short timeout may not be applicable to other contexts, so + * if a context switch should happen within before the preemption + * timeout, we may shoot early at an innocent context. To prevent this, + * we record which context was active at the time of the preemption + * request and only reset that context upon the timeout. + */ + const struct i915_request *preempt_target; + + /** * @ccid: identifier for contexts submitted to this engine */ u32 ccid; diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index 4b909cb88cdf..c718e6dc40b5 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -1241,6 +1241,9 @@ static unsigned long active_preempt_timeout(struct intel_engine_cs *engine, if (!rq) return 0; + /* Only allow ourselves to force reset the currently active context */ + engine->execlists.preempt_target = rq; + /* Force a fast reset for terminated contexts (ignoring sysfs!) */ if (unlikely(intel_context_is_banned(rq->context) || bad_request(rq))) return INTEL_CONTEXT_BANNED_PREEMPT_TIMEOUT_MS; @@ -2427,8 +2430,24 @@ static void execlists_submission_tasklet(struct tasklet_struct *t) GEM_BUG_ON(inactive - post > ARRAY_SIZE(post)); if (unlikely(preempt_timeout(engine))) { + const struct i915_request *rq = *engine->execlists.active; + + /* + * If after the preempt-timeout expired, we are still on the + * same active request/context as before we initiated the + * preemption, reset the engine. + * + * However, if we have processed a CS event to switch contexts, + * but not yet processed the CS event for the pending + * preemption, reset the timer allowing the new context to + * gracefully exit. + */ cancel_timer(&engine->execlists.preempt); - engine->execlists.error_interrupt |= ERROR_PREEMPT; + if (rq == engine->execlists.preempt_target) + engine->execlists.error_interrupt |= ERROR_PREEMPT; + else + set_timer_ms(&engine->execlists.preempt, + active_preempt_timeout(engine, rq)); } if (unlikely(READ_ONCE(engine->execlists.error_interrupt))) { diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt.c b/drivers/gpu/drm/i915/gt/intel_ggtt.c index 15a915bb4088..2049a00417af 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt.c @@ -16,7 +16,9 @@ #include "intel_ggtt_gmch.h" #include "intel_gt.h" #include "intel_gt_regs.h" +#include "intel_pci_config.h" #include "i915_drv.h" +#include "i915_pci.h" #include "i915_scatterlist.h" #include "i915_utils.h" #include "i915_vgpu.h" @@ -869,8 +871,8 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size) u32 pte_flags; int ret; - GEM_WARN_ON(pci_resource_len(pdev, 0) != gen6_gttmmadr_size(i915)); - phys_addr = pci_resource_start(pdev, 0) + gen6_gttadr_offset(i915); + GEM_WARN_ON(pci_resource_len(pdev, GTTMMADR_BAR) != gen6_gttmmadr_size(i915)); + phys_addr = pci_resource_start(pdev, GTTMMADR_BAR) + gen6_gttadr_offset(i915); /* * On BXT+/ICL+ writes larger than 64 bit to the GTT pagetable range @@ -930,7 +932,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt) u16 snb_gmch_ctl; if (!HAS_LMEM(i915)) { - ggtt->gmadr = pci_resource(pdev, 2); + if (!i915_pci_resource_valid(pdev, GTT_APERTURE_BAR)) + return -ENXIO; + + ggtt->gmadr = pci_resource(pdev, GTT_APERTURE_BAR); ggtt->mappable_end = resource_size(&ggtt->gmadr); } @@ -1084,7 +1089,10 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt) unsigned int size; u16 snb_gmch_ctl; - ggtt->gmadr = pci_resource(pdev, 2); + if (!i915_pci_resource_valid(pdev, GTT_APERTURE_BAR)) + return -ENXIO; + + ggtt->gmadr = pci_resource(pdev, GTT_APERTURE_BAR); ggtt->mappable_end = resource_size(&ggtt->gmadr); /* @@ -1267,10 +1275,16 @@ bool i915_ggtt_resume_vm(struct i915_address_space *vm) atomic_read(&vma->flags) & I915_VMA_BIND_MASK; GEM_BUG_ON(!was_bound); - if (!retained_ptes) + if (!retained_ptes) { + /* + * Clear the bound flags of the vma resource to allow + * ptes to be repopulated. + */ + vma->resource->bound_flags = 0; vma->ops->bind_vma(vm, NULL, vma->resource, obj ? obj->cache_level : 0, was_bound); + } if (obj) { /* only used during resume => exclusive access */ write_domain_objs |= fetch_and_zero(&obj->write_domain); obj->read_domains |= I915_GEM_DOMAIN_GTT; diff --git a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c index 6ebda3d65086..ea775e601686 100644 --- a/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c +++ b/drivers/gpu/drm/i915/gt/intel_ggtt_fencing.c @@ -727,7 +727,7 @@ static void detect_bit_6_swizzle(struct i915_ggtt *ggtt) * bit17 dependent, and so we need to also prevent the pages * from being moved. */ - i915->quirks |= QUIRK_PIN_SWIZZLED_PAGES; + i915->gem_quirks |= GEM_QUIRK_PIN_SWIZZLED_PAGES; swizzle_x = I915_BIT_6_SWIZZLE_NONE; swizzle_y = I915_BIT_6_SWIZZLE_NONE; } @@ -842,7 +842,6 @@ void intel_ggtt_init_fences(struct i915_ggtt *ggtt) INIT_LIST_HEAD(&ggtt->fence_list); INIT_LIST_HEAD(&ggtt->userfault_list); - intel_wakeref_auto_init(&ggtt->userfault_wakeref, uncore->rpm); detect_bit_6_swizzle(ggtt); diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.c b/drivers/gpu/drm/i915/gt/intel_gsc.c index 0e494028b81d..7af6db3194dd 100644 --- a/drivers/gpu/drm/i915/gt/intel_gsc.c +++ b/drivers/gpu/drm/i915/gt/intel_gsc.c @@ -7,6 +7,7 @@ #include <linux/mei_aux.h> #include "i915_drv.h" #include "i915_reg.h" +#include "gem/i915_gem_region.h" #include "gt/intel_gsc.h" #include "gt/intel_gt.h" @@ -36,10 +37,56 @@ static int gsc_irq_init(int irq) return irq_set_chip_data(irq, NULL); } +static int +gsc_ext_om_alloc(struct intel_gsc *gsc, struct intel_gsc_intf *intf, size_t size) +{ + struct intel_gt *gt = gsc_to_gt(gsc); + struct drm_i915_gem_object *obj; + int err; + + obj = i915_gem_object_create_lmem(gt->i915, size, + I915_BO_ALLOC_CONTIGUOUS | + I915_BO_ALLOC_CPU_CLEAR); + if (IS_ERR(obj)) { + drm_err(>->i915->drm, "Failed to allocate gsc memory\n"); + return PTR_ERR(obj); + } + + err = i915_gem_object_pin_pages_unlocked(obj); + if (err) { + drm_err(>->i915->drm, "Failed to pin pages for gsc memory\n"); + goto out_put; + } + + intf->gem_obj = obj; + + return 0; + +out_put: + i915_gem_object_put(obj); + return err; +} + +static void gsc_ext_om_destroy(struct intel_gsc_intf *intf) +{ + struct drm_i915_gem_object *obj = fetch_and_zero(&intf->gem_obj); + + if (!obj) + return; + + if (i915_gem_object_has_pinned_pages(obj)) + i915_gem_object_unpin_pages(obj); + + i915_gem_object_put(obj); +} + struct gsc_def { const char *name; unsigned long bar; size_t bar_size; + bool use_polling; + bool slow_firmware; + size_t lmem_size; }; /* gsc resources and definitions (HECI1 and HECI2) */ @@ -54,11 +101,25 @@ static const struct gsc_def gsc_def_dg1[] = { } }; +static const struct gsc_def gsc_def_xehpsdv[] = { + { + /* HECI1 not enabled on the device. */ + }, + { + .name = "mei-gscfi", + .bar = DG1_GSC_HECI2_BASE, + .bar_size = GSC_BAR_LENGTH, + .use_polling = true, + .slow_firmware = true, + } +}; + static const struct gsc_def gsc_def_dg2[] = { { .name = "mei-gsc", .bar = DG2_GSC_HECI1_BASE, .bar_size = GSC_BAR_LENGTH, + .lmem_size = SZ_4M, }, { .name = "mei-gscfi", @@ -75,26 +136,32 @@ static void gsc_release_dev(struct device *dev) kfree(adev); } -static void gsc_destroy_one(struct intel_gsc_intf *intf) +static void gsc_destroy_one(struct drm_i915_private *i915, + struct intel_gsc *gsc, unsigned int intf_id) { + struct intel_gsc_intf *intf = &gsc->intf[intf_id]; + if (intf->adev) { auxiliary_device_delete(&intf->adev->aux_dev); auxiliary_device_uninit(&intf->adev->aux_dev); intf->adev = NULL; } + if (intf->irq >= 0) irq_free_desc(intf->irq); intf->irq = -1; + + gsc_ext_om_destroy(intf); } -static void gsc_init_one(struct drm_i915_private *i915, - struct intel_gsc_intf *intf, +static void gsc_init_one(struct drm_i915_private *i915, struct intel_gsc *gsc, unsigned int intf_id) { struct pci_dev *pdev = to_pci_dev(i915->drm.dev); struct mei_aux_device *adev; struct auxiliary_device *aux_dev; const struct gsc_def *def; + struct intel_gsc_intf *intf = &gsc->intf[intf_id]; int ret; intf->irq = -1; @@ -105,6 +172,8 @@ static void gsc_init_one(struct drm_i915_private *i915, if (IS_DG1(i915)) { def = &gsc_def_dg1[intf_id]; + } else if (IS_XEHPSDV(i915)) { + def = &gsc_def_xehpsdv[intf_id]; } else if (IS_DG2(i915)) { def = &gsc_def_dg2[intf_id]; } else { @@ -117,10 +186,14 @@ static void gsc_init_one(struct drm_i915_private *i915, return; } + /* skip irq initialization */ + if (def->use_polling) + goto add_device; + intf->irq = irq_alloc_desc(0); if (intf->irq < 0) { drm_err(&i915->drm, "gsc irq error %d\n", intf->irq); - return; + goto fail; } ret = gsc_irq_init(intf->irq); @@ -129,16 +202,31 @@ static void gsc_init_one(struct drm_i915_private *i915, goto fail; } +add_device: adev = kzalloc(sizeof(*adev), GFP_KERNEL); if (!adev) goto fail; + if (def->lmem_size) { + drm_dbg(&i915->drm, "setting up GSC lmem\n"); + + if (gsc_ext_om_alloc(gsc, intf, def->lmem_size)) { + drm_err(&i915->drm, "setting up gsc extended operational memory failed\n"); + kfree(adev); + goto fail; + } + + adev->ext_op_mem.start = i915_gem_object_get_dma_address(intf->gem_obj, 0); + adev->ext_op_mem.end = adev->ext_op_mem.start + def->lmem_size; + } + adev->irq = intf->irq; adev->bar.parent = &pdev->resource[0]; adev->bar.start = def->bar + pdev->resource[0].start; adev->bar.end = adev->bar.start + def->bar_size - 1; adev->bar.flags = IORESOURCE_MEM; adev->bar.desc = IORES_DESC_NONE; + adev->slow_firmware = def->slow_firmware; aux_dev = &adev->aux_dev; aux_dev->name = def->name; @@ -165,7 +253,7 @@ static void gsc_init_one(struct drm_i915_private *i915, return; fail: - gsc_destroy_one(intf); + gsc_destroy_one(i915, gsc, intf->id); } static void gsc_irq_handler(struct intel_gt *gt, unsigned int intf_id) @@ -182,10 +270,8 @@ static void gsc_irq_handler(struct intel_gt *gt, unsigned int intf_id) return; } - if (gt->gsc.intf[intf_id].irq < 0) { - drm_err_ratelimited(>->i915->drm, "GSC irq: irq not set"); + if (gt->gsc.intf[intf_id].irq < 0) return; - } ret = generic_handle_irq(gt->gsc.intf[intf_id].irq); if (ret) @@ -208,7 +294,7 @@ void intel_gsc_init(struct intel_gsc *gsc, struct drm_i915_private *i915) return; for (i = 0; i < INTEL_GSC_NUM_INTERFACES; i++) - gsc_init_one(i915, &gsc->intf[i], i); + gsc_init_one(i915, gsc, i); } void intel_gsc_fini(struct intel_gsc *gsc) @@ -220,5 +306,5 @@ void intel_gsc_fini(struct intel_gsc *gsc) return; for (i = 0; i < INTEL_GSC_NUM_INTERFACES; i++) - gsc_destroy_one(&gsc->intf[i]); + gsc_destroy_one(gt->i915, gsc, i); } diff --git a/drivers/gpu/drm/i915/gt/intel_gsc.h b/drivers/gpu/drm/i915/gt/intel_gsc.h index 68582f912b21..fcac1775e9c3 100644 --- a/drivers/gpu/drm/i915/gt/intel_gsc.h +++ b/drivers/gpu/drm/i915/gt/intel_gsc.h @@ -20,11 +20,14 @@ struct mei_aux_device; /** * struct intel_gsc - graphics security controller + * + * @gem_obj: scratch memory GSC operations * @intf : gsc interface */ struct intel_gsc { struct intel_gsc_intf { struct mei_aux_device *adev; + struct drm_i915_gem_object *gem_obj; int irq; unsigned int id; } intf[INTEL_GSC_NUM_INTERFACES]; diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c index f435e06125aa..d0b03a928b9a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.c +++ b/drivers/gpu/drm/i915/gt/intel_gt.c @@ -26,18 +26,22 @@ #include "intel_gt_requests.h" #include "intel_migrate.h" #include "intel_mocs.h" +#include "intel_pci_config.h" #include "intel_pm.h" #include "intel_rc6.h" #include "intel_renderstate.h" #include "intel_rps.h" +#include "intel_sa_media.h" #include "intel_gt_sysfs.h" #include "intel_uncore.h" #include "shmem_utils.h" -static void __intel_gt_init_early(struct intel_gt *gt) +void intel_gt_common_init_early(struct intel_gt *gt) { - spin_lock_init(>->irq_lock); + spin_lock_init(gt->irq_lock); + INIT_LIST_HEAD(>->lmem_userfault_list); + mutex_init(>->lmem_userfault_lock); INIT_LIST_HEAD(>->closed_vma); spin_lock_init(>->closed_lock); @@ -57,14 +61,19 @@ static void __intel_gt_init_early(struct intel_gt *gt) } /* Preliminary initialization of Tile 0 */ -void intel_root_gt_init_early(struct drm_i915_private *i915) +int intel_root_gt_init_early(struct drm_i915_private *i915) { struct intel_gt *gt = to_gt(i915); gt->i915 = i915; gt->uncore = &i915->uncore; + gt->irq_lock = drmm_kzalloc(&i915->drm, sizeof(*gt->irq_lock), GFP_KERNEL); + if (!gt->irq_lock) + return -ENOMEM; - __intel_gt_init_early(gt); + intel_gt_common_init_early(gt); + + return 0; } static int intel_gt_probe_lmem(struct intel_gt *gt) @@ -780,26 +789,25 @@ static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr) int ret; if (!gt_is_root(gt)) { - struct intel_uncore_mmio_debug *mmio_debug; struct intel_uncore *uncore; + spinlock_t *irq_lock; - uncore = kzalloc(sizeof(*uncore), GFP_KERNEL); + uncore = drmm_kzalloc(>->i915->drm, sizeof(*uncore), GFP_KERNEL); if (!uncore) return -ENOMEM; - mmio_debug = kzalloc(sizeof(*mmio_debug), GFP_KERNEL); - if (!mmio_debug) { - kfree(uncore); + irq_lock = drmm_kzalloc(>->i915->drm, sizeof(*irq_lock), GFP_KERNEL); + if (!irq_lock) return -ENOMEM; - } gt->uncore = uncore; - gt->uncore->debug = mmio_debug; + gt->irq_lock = irq_lock; - __intel_gt_init_early(gt); + intel_gt_common_init_early(gt); } intel_uncore_init_early(gt->uncore, gt); + intel_wakeref_auto_init(>->userfault_wakeref, gt->uncore->rpm); ret = intel_uncore_setup_mmio(gt->uncore, phys_addr); if (ret) @@ -810,27 +818,17 @@ static int intel_gt_tile_setup(struct intel_gt *gt, phys_addr_t phys_addr) return 0; } -static void -intel_gt_tile_cleanup(struct intel_gt *gt) -{ - intel_uncore_cleanup_mmio(gt->uncore); - - if (!gt_is_root(gt)) { - kfree(gt->uncore->debug); - kfree(gt->uncore); - kfree(gt); - } -} - int intel_gt_probe_all(struct drm_i915_private *i915) { struct pci_dev *pdev = to_pci_dev(i915->drm.dev); struct intel_gt *gt = &i915->gt0; + const struct intel_gt_definition *gtdef; phys_addr_t phys_addr; unsigned int mmio_bar; + unsigned int i; int ret; - mmio_bar = GRAPHICS_VER(i915) == 2 ? 1 : 0; + mmio_bar = GRAPHICS_VER(i915) == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR; phys_addr = pci_resource_start(pdev, mmio_bar); /* @@ -838,14 +836,74 @@ int intel_gt_probe_all(struct drm_i915_private *i915) * and it has been already initialized early during probe * in i915_driver_probe() */ + gt->i915 = i915; + gt->name = "Primary GT"; + gt->info.engine_mask = RUNTIME_INFO(i915)->platform_engine_mask; + + drm_dbg(&i915->drm, "Setting up %s\n", gt->name); ret = intel_gt_tile_setup(gt, phys_addr); if (ret) return ret; i915->gt[0] = gt; - /* TODO: add more tiles */ + if (!HAS_EXTRA_GT_LIST(i915)) + return 0; + + for (i = 1, gtdef = &INTEL_INFO(i915)->extra_gt_list[i - 1]; + gtdef->name != NULL; + i++, gtdef = &INTEL_INFO(i915)->extra_gt_list[i - 1]) { + gt = drmm_kzalloc(&i915->drm, sizeof(*gt), GFP_KERNEL); + if (!gt) { + ret = -ENOMEM; + goto err; + } + + gt->i915 = i915; + gt->name = gtdef->name; + gt->type = gtdef->type; + gt->info.engine_mask = gtdef->engine_mask; + gt->info.id = i; + + drm_dbg(&i915->drm, "Setting up %s\n", gt->name); + if (GEM_WARN_ON(range_overflows_t(resource_size_t, + gtdef->mapping_base, + SZ_16M, + pci_resource_len(pdev, mmio_bar)))) { + ret = -ENODEV; + goto err; + } + + switch (gtdef->type) { + case GT_TILE: + ret = intel_gt_tile_setup(gt, phys_addr + gtdef->mapping_base); + break; + + case GT_MEDIA: + ret = intel_sa_mediagt_setup(gt, phys_addr + gtdef->mapping_base, + gtdef->gsi_offset); + break; + + case GT_PRIMARY: + /* Primary GT should not appear in extra GT list */ + default: + MISSING_CASE(gtdef->type); + ret = -ENODEV; + } + + if (ret) + goto err; + + i915->gt[i] = gt; + } + return 0; + +err: + i915_probe_error(i915, "Failed to initialize %s! (%d)\n", gtdef->name, ret); + intel_gt_release_all(i915); + + return ret; } int intel_gt_tiles_init(struct drm_i915_private *i915) @@ -868,10 +926,8 @@ void intel_gt_release_all(struct drm_i915_private *i915) struct intel_gt *gt; unsigned int id; - for_each_gt(gt, i915, id) { - intel_gt_tile_cleanup(gt); + for_each_gt(gt, i915, id) i915->gt[id] = NULL; - } } void intel_gt_info_print(const struct intel_gt_info *info, diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h index 40b06adf509a..2ee582e287c8 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt.h +++ b/drivers/gpu/drm/i915/gt/intel_gt.h @@ -44,7 +44,8 @@ static inline struct intel_gt *gsc_to_gt(struct intel_gsc *gsc) return container_of(gsc, struct intel_gt, gsc); } -void intel_root_gt_init_early(struct drm_i915_private *i915); +void intel_gt_common_init_early(struct intel_gt *gt); +int intel_root_gt_init_early(struct drm_i915_private *i915); int intel_gt_assign_ggtt(struct intel_gt *gt); int intel_gt_init_mmio(struct intel_gt *gt); int __must_check intel_gt_init_hw(struct intel_gt *gt); @@ -54,7 +55,6 @@ void intel_gt_driver_register(struct intel_gt *gt); void intel_gt_driver_unregister(struct intel_gt *gt); void intel_gt_driver_remove(struct intel_gt *gt); void intel_gt_driver_release(struct intel_gt *gt); - void intel_gt_driver_late_release_all(struct drm_i915_private *i915); int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c index d5d1b04dbcad..3f656d3dba9a 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_clock_utils.c @@ -26,26 +26,6 @@ static u32 read_reference_ts_freq(struct intel_uncore *uncore) return base_freq + frac_freq; } -static u32 gen9_get_crystal_clock_freq(struct intel_uncore *uncore, - u32 rpm_config_reg) -{ - u32 f19_2_mhz = 19200000; - u32 f24_mhz = 24000000; - u32 crystal_clock = - (rpm_config_reg & GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_MASK) >> - GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_SHIFT; - - switch (crystal_clock) { - case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_19_2_MHZ: - return f19_2_mhz; - case GEN9_RPM_CONFIG0_CRYSTAL_CLOCK_FREQ_24_MHZ: - return f24_mhz; - default: - MISSING_CASE(crystal_clock); - return 0; - } -} - static u32 gen11_get_crystal_clock_freq(struct intel_uncore *uncore, u32 rpm_config_reg) { @@ -72,98 +52,106 @@ static u32 gen11_get_crystal_clock_freq(struct intel_uncore *uncore, } } -static u32 read_clock_frequency(struct intel_uncore *uncore) +static u32 gen11_read_clock_frequency(struct intel_uncore *uncore) { - u32 f12_5_mhz = 12500000; - u32 f19_2_mhz = 19200000; - u32 f24_mhz = 24000000; + u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE); + u32 freq = 0; + + /* + * Note that on gen11+, the clock frequency may be reconfigured. + * We do not, and we assume nobody else does. + * + * First figure out the reference frequency. There are 2 ways + * we can compute the frequency, either through the + * TIMESTAMP_OVERRIDE register or through RPM_CONFIG. CTC_MODE + * tells us which one we should use. + */ + if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) { + freq = read_reference_ts_freq(uncore); + } else { + u32 c0 = intel_uncore_read(uncore, RPM_CONFIG0); + + freq = gen11_get_crystal_clock_freq(uncore, c0); - if (GRAPHICS_VER(uncore->i915) <= 4) { - /* - * PRMs say: - * - * "The value in this register increments once every 16 - * hclks." (through the “Clocking Configuration” - * (“CLKCFG”) MCHBAR register) - */ - return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000 / 16; - } else if (GRAPHICS_VER(uncore->i915) <= 8) { /* - * PRMs say: - * - * "The PCU TSC counts 10ns increments; this timestamp - * reflects bits 38:3 of the TSC (i.e. 80ns granularity, - * rolling over every 1.5 hours). + * Now figure out how the command stream's timestamp + * register increments from this frequency (it might + * increment only every few clock cycle). */ - return f12_5_mhz; - } else if (GRAPHICS_VER(uncore->i915) <= 9) { - u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE); - u32 freq = 0; - - if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) { - freq = read_reference_ts_freq(uncore); - } else { - freq = IS_GEN9_LP(uncore->i915) ? f19_2_mhz : f24_mhz; - - /* - * Now figure out how the command stream's timestamp - * register increments from this frequency (it might - * increment only every few clock cycle). - */ - freq >>= 3 - ((ctc_reg & CTC_SHIFT_PARAMETER_MASK) >> - CTC_SHIFT_PARAMETER_SHIFT); - } - - return freq; - } else if (GRAPHICS_VER(uncore->i915) <= 12) { - u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE); - u32 freq = 0; + freq >>= 3 - ((c0 & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >> + GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT); + } + + return freq; +} + +static u32 gen9_read_clock_frequency(struct intel_uncore *uncore) +{ + u32 ctc_reg = intel_uncore_read(uncore, CTC_MODE); + u32 freq = 0; + + if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) { + freq = read_reference_ts_freq(uncore); + } else { + freq = IS_GEN9_LP(uncore->i915) ? 19200000 : 24000000; /* - * First figure out the reference frequency. There are 2 ways - * we can compute the frequency, either through the - * TIMESTAMP_OVERRIDE register or through RPM_CONFIG. CTC_MODE - * tells us which one we should use. + * Now figure out how the command stream's timestamp + * register increments from this frequency (it might + * increment only every few clock cycle). */ - if ((ctc_reg & CTC_SOURCE_PARAMETER_MASK) == CTC_SOURCE_DIVIDE_LOGIC) { - freq = read_reference_ts_freq(uncore); - } else { - u32 c0 = intel_uncore_read(uncore, RPM_CONFIG0); - - if (GRAPHICS_VER(uncore->i915) >= 11) - freq = gen11_get_crystal_clock_freq(uncore, c0); - else - freq = gen9_get_crystal_clock_freq(uncore, c0); - - /* - * Now figure out how the command stream's timestamp - * register increments from this frequency (it might - * increment only every few clock cycle). - */ - freq >>= 3 - ((c0 & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >> - GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT); - } - - return freq; + freq >>= 3 - ((ctc_reg & CTC_SHIFT_PARAMETER_MASK) >> + CTC_SHIFT_PARAMETER_SHIFT); } - MISSING_CASE("Unknown gen, unable to read command streamer timestamp frequency\n"); - return 0; + return freq; } -void intel_gt_init_clock_frequency(struct intel_gt *gt) +static u32 gen5_read_clock_frequency(struct intel_uncore *uncore) { /* - * Note that on gen11+, the clock frequency may be reconfigured. - * We do not, and we assume nobody else does. + * PRMs say: + * + * "The PCU TSC counts 10ns increments; this timestamp + * reflects bits 38:3 of the TSC (i.e. 80ns granularity, + * rolling over every 1.5 hours). + */ + return 12500000; +} + +static u32 gen2_read_clock_frequency(struct intel_uncore *uncore) +{ + /* + * PRMs say: + * + * "The value in this register increments once every 16 + * hclks." (through the “Clocking Configuration” + * (“CLKCFG”) MCHBAR register) */ + return RUNTIME_INFO(uncore->i915)->rawclk_freq * 1000 / 16; +} + +static u32 read_clock_frequency(struct intel_uncore *uncore) +{ + if (GRAPHICS_VER(uncore->i915) >= 11) + return gen11_read_clock_frequency(uncore); + else if (GRAPHICS_VER(uncore->i915) >= 9) + return gen9_read_clock_frequency(uncore); + else if (GRAPHICS_VER(uncore->i915) >= 5) + return gen5_read_clock_frequency(uncore); + else + return gen2_read_clock_frequency(uncore); +} + +void intel_gt_init_clock_frequency(struct intel_gt *gt) +{ gt->clock_frequency = read_clock_frequency(gt->uncore); - if (gt->clock_frequency) - gt->clock_period_ns = intel_gt_clock_interval_to_ns(gt, 1); /* Icelake appears to use another fixed frequency for CTX_TIMESTAMP */ if (GRAPHICS_VER(gt->i915) == 11) gt->clock_period_ns = NSEC_PER_SEC / 13750000; + else if (gt->clock_frequency) + gt->clock_period_ns = intel_gt_clock_interval_to_ns(gt, 1); GT_TRACE(gt, "Using clock frequency: %dkHz, period: %dns, wrap: %lldms\n", diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c index 3a72d4fd0214..f26882fdc24c 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c @@ -29,7 +29,7 @@ gen11_gt_engine_identity(struct intel_gt *gt, u32 timeout_ts; u32 ident; - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); raw_reg_write(regs, GEN11_IIR_REG_SELECTOR(bank), BIT(bit)); @@ -59,11 +59,17 @@ static void gen11_other_irq_handler(struct intel_gt *gt, const u8 instance, const u16 iir) { + struct intel_gt *media_gt = gt->i915->media_gt; + if (instance == OTHER_GUC_INSTANCE) return guc_irq_handler(>->uc.guc, iir); + if (instance == OTHER_MEDIA_GUC_INSTANCE && media_gt) + return guc_irq_handler(&media_gt->uc.guc, iir); if (instance == OTHER_GTPM_INSTANCE) return gen11_rps_irq_handler(>->rps, iir); + if (instance == OTHER_MEDIA_GTPM_INSTANCE && media_gt) + return gen11_rps_irq_handler(&media_gt->rps, iir); if (instance == OTHER_KCR_INSTANCE) return intel_pxp_irq_handler(>->pxp, iir); @@ -81,6 +87,18 @@ gen11_engine_irq_handler(struct intel_gt *gt, const u8 class, { struct intel_engine_cs *engine; + /* + * Platforms with standalone media have their media engines in another + * GT. + */ + if (MEDIA_VER(gt->i915) >= 13 && + (class == VIDEO_DECODE_CLASS || class == VIDEO_ENHANCEMENT_CLASS)) { + if (!gt->i915->media_gt) + goto err; + + gt = gt->i915->media_gt; + } + if (instance <= MAX_ENGINE_INSTANCE) engine = gt->engine_class[class][instance]; else @@ -89,6 +107,7 @@ gen11_engine_irq_handler(struct intel_gt *gt, const u8 class, if (likely(engine)) return intel_engine_cs_irq(engine, iir); +err: WARN_ONCE(1, "unhandled engine interrupt class=0x%x, instance=0x%x\n", class, instance); } @@ -120,7 +139,7 @@ gen11_gt_bank_handler(struct intel_gt *gt, const unsigned int bank) unsigned long intr_dw; unsigned int bit; - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); intr_dw = raw_reg_read(regs, GEN11_GT_INTR_DW(bank)); @@ -138,14 +157,14 @@ void gen11_gt_irq_handler(struct intel_gt *gt, const u32 master_ctl) { unsigned int bank; - spin_lock(>->irq_lock); + spin_lock(gt->irq_lock); for (bank = 0; bank < 2; bank++) { if (master_ctl & GEN11_GT_DW_IRQ(bank)) gen11_gt_bank_handler(gt, bank); } - spin_unlock(>->irq_lock); + spin_unlock(gt->irq_lock); } bool gen11_gt_reset_one_iir(struct intel_gt *gt, @@ -154,7 +173,7 @@ bool gen11_gt_reset_one_iir(struct intel_gt *gt, void __iomem * const regs = gt->uncore->regs; u32 dw; - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); dw = raw_reg_read(regs, GEN11_GT_INTR_DW(bank)); if (dw & BIT(bit)) { @@ -310,9 +329,9 @@ static void gen7_parity_error_irq_handler(struct intel_gt *gt, u32 iir) if (!HAS_L3_DPF(gt->i915)) return; - spin_lock(>->irq_lock); + spin_lock(gt->irq_lock); gen5_gt_disable_irq(gt, GT_PARITY_ERROR(gt->i915)); - spin_unlock(>->irq_lock); + spin_unlock(gt->irq_lock); if (iir & GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1) gt->i915->l3_parity.which_slice |= 1 << 1; @@ -434,7 +453,7 @@ static void gen5_gt_update_irq(struct intel_gt *gt, u32 interrupt_mask, u32 enabled_irq_mask) { - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); GEM_BUG_ON(enabled_irq_mask & ~interrupt_mask); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c index 40bdd4cb629f..108b9e76c32e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_debugfs.c @@ -504,8 +504,8 @@ void intel_gt_pm_frequency_dump(struct intel_gt *gt, struct drm_printer *p) drm_puts(p, "no P-state info available\n"); } - drm_printf(p, "Current CD clock frequency: %d kHz\n", i915->cdclk.hw.cdclk); - drm_printf(p, "Max CD clock frequency: %d kHz\n", i915->max_cdclk_freq); + drm_printf(p, "Current CD clock frequency: %d kHz\n", i915->display.cdclk.hw.cdclk); + drm_printf(p, "Max CD clock frequency: %d kHz\n", i915->display.cdclk.max_cdclk_freq); drm_printf(p, "Max pixel clock frequency: %d kHz\n", i915->max_dotclk_freq); intel_runtime_pm_put(uncore->rpm, wakeref); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c index 11060f5a4c89..52f2a28b2058 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_pm_irq.c @@ -37,7 +37,7 @@ static void gen6_gt_pm_update_irq(struct intel_gt *gt, WARN_ON(enabled_irq_mask & ~interrupt_mask); - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); new_val = gt->pm_imr; new_val &= ~interrupt_mask; @@ -64,7 +64,7 @@ void gen6_gt_pm_reset_iir(struct intel_gt *gt, u32 reset_mask) struct intel_uncore *uncore = gt->uncore; i915_reg_t reg = GRAPHICS_VER(gt->i915) >= 8 ? GEN8_GT_IIR(2) : GEN6_PMIIR; - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); intel_uncore_write(uncore, reg, reset_mask); intel_uncore_write(uncore, reg, reset_mask); @@ -92,7 +92,7 @@ static void write_pm_ier(struct intel_gt *gt) void gen6_gt_pm_enable_irq(struct intel_gt *gt, u32 enable_mask) { - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); gt->pm_ier |= enable_mask; write_pm_ier(gt); @@ -101,7 +101,7 @@ void gen6_gt_pm_enable_irq(struct intel_gt *gt, u32 enable_mask) void gen6_gt_pm_disable_irq(struct intel_gt *gt, u32 disable_mask) { - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); gt->pm_ier &= ~disable_mask; gen6_gt_pm_mask_irq(gt, disable_mask); diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h index d414785003cc..2275ee47da95 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h @@ -1554,6 +1554,8 @@ #define OTHER_GTPM_INSTANCE 1 #define OTHER_KCR_INSTANCE 4 #define OTHER_GSC_INSTANCE 6 +#define OTHER_MEDIA_GUC_INSTANCE 16 +#define OTHER_MEDIA_GTPM_INSTANCE 17 #define GEN11_IIR_REG_SELECTOR(x) _MMIO(0x190070 + ((x) * 4)) @@ -1578,4 +1580,12 @@ #define GEN12_SFC_DONE(n) _MMIO(0x1cc000 + (n) * 0x1000) +/* + * Standalone Media's non-engine GT registers are located at their regular GT + * offsets plus 0x380000. This extra offset is stored inside the intel_uncore + * structure so that the existing code can be used for both GTs without + * modification. + */ +#define MTL_MEDIA_GSI_BASE 0x380000 + #endif /* __INTEL_GT_REGS__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c index e066cc33d9f2..180dd6f3ef57 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c +++ b/drivers/gpu/drm/i915/gt/intel_gt_sysfs_pm.c @@ -545,8 +545,7 @@ static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_ratl, RATL_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_thermalert, VR_THERMALERT_MASK); static INTEL_GT_RPS_BOOL_ATTR_RO(throttle_reason_vr_tdc, VR_TDC_MASK); -static const struct attribute *freq_attrs[] = { - &dev_attr_punit_req_freq_mhz.attr, +static const struct attribute *throttle_reason_attrs[] = { &attr_throttle_reason_status.attr, &attr_throttle_reason_pl1.attr, &attr_throttle_reason_pl2.attr, @@ -791,12 +790,20 @@ void intel_gt_sysfs_pm_init(struct intel_gt *gt, struct kobject *kobj) if (!is_object_gt(kobj)) return; - ret = sysfs_create_files(kobj, freq_attrs); + ret = sysfs_create_file(kobj, &dev_attr_punit_req_freq_mhz.attr); if (ret) drm_warn(>->i915->drm, - "failed to create gt%u throttle sysfs files (%pe)", + "failed to create gt%u punit_req_freq_mhz sysfs (%pe)", gt->info.id, ERR_PTR(ret)); + if (GRAPHICS_VER(gt->i915) >= 11) { + ret = sysfs_create_files(kobj, throttle_reason_attrs); + if (ret) + drm_warn(>->i915->drm, + "failed to create gt%u throttle sysfs files (%pe)", + gt->info.id, ERR_PTR(ret)); + } + if (HAS_MEDIA_RATIO_MODE(gt->i915) && intel_uc_uses_guc_slpc(>->uc)) { ret = sysfs_create_files(kobj, media_perf_power_attrs); if (ret) diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h index 4d56f7d5a3be..f19c2de77ff6 100644 --- a/drivers/gpu/drm/i915/gt/intel_gt_types.h +++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h @@ -81,8 +81,17 @@ struct gt_defaults { u32 max_freq; }; +enum intel_gt_type { + GT_PRIMARY, + GT_TILE, + GT_MEDIA, +}; + struct intel_gt { struct drm_i915_private *i915; + const char *name; + enum intel_gt_type type; + struct intel_uncore *uncore; struct i915_ggtt *ggtt; @@ -132,6 +141,20 @@ struct intel_gt { struct intel_wakeref wakeref; atomic_t user_wakeref; + /** + * Protects access to lmem usefault list. + * It is required, if we are outside of the runtime suspend path, + * access to @lmem_userfault_list requires always first grabbing the + * runtime pm, to ensure we can't race against runtime suspend. + * Once we have that we also need to grab @lmem_userfault_lock, + * at which point we have exclusive access. + * The runtime suspend path is special since it doesn't really hold any locks, + * but instead has exclusive access by virtue of all other accesses requiring + * holding the runtime pm wakeref. + */ + struct mutex lmem_userfault_lock; + struct list_head lmem_userfault_list; + struct list_head closed_vma; spinlock_t closed_lock; /* guards the list of closed_vma */ @@ -147,6 +170,9 @@ struct intel_gt { */ intel_wakeref_t awake; + /* Manual runtime pm autosuspend delay for user GGTT/lmem mmaps */ + struct intel_wakeref_auto userfault_wakeref; + u32 clock_frequency; u32 clock_period_ns; @@ -154,7 +180,7 @@ struct intel_gt { struct intel_rc6 rc6; struct intel_rps rps; - spinlock_t irq_lock; + spinlock_t *irq_lock; u32 gt_imr; u32 pm_ier; u32 pm_imr; @@ -262,6 +288,14 @@ struct intel_gt { struct kobject *sysfs_defaults; }; +struct intel_gt_definition { + enum intel_gt_type type; + char *name; + u32 mapping_base; + u32 gsi_offset; + intel_engine_mask_t engine_mask; +}; + enum intel_gt_scratch_field { /* 8 bytes */ INTEL_GT_SCRATCH_FIELD_DEFAULT = 0, diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index b67831833c9a..2eaeba14319e 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -405,6 +405,9 @@ void free_scratch(struct i915_address_space *vm) { int i; + if (!vm->scratch[0]) + return; + for (i = 0; i <= vm->top; i++) i915_gem_object_put(vm->scratch[i]); } diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.h b/drivers/gpu/drm/i915/gt/intel_gtt.h index e639434e97fd..c0ca53cba9f0 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.h +++ b/drivers/gpu/drm/i915/gt/intel_gtt.h @@ -386,9 +386,6 @@ struct i915_ggtt { */ struct list_head userfault_list; - /* Manual runtime pm autosuspend delay for user GGTT mmaps */ - struct intel_wakeref_auto userfault_wakeref; - struct mutex error_mutex; struct drm_mm_node error_capture; struct drm_mm_node uc_fw; diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 070cec4ff8a4..3955292483a6 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -662,6 +662,21 @@ static int lrc_ring_mi_mode(const struct intel_engine_cs *engine) return -1; } +static int lrc_ring_bb_offset(const struct intel_engine_cs *engine) +{ + if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) + return 0x80; + else if (GRAPHICS_VER(engine->i915) >= 12) + return 0x70; + else if (GRAPHICS_VER(engine->i915) >= 9) + return 0x64; + else if (GRAPHICS_VER(engine->i915) >= 8 && + engine->class == RENDER_CLASS) + return 0xc4; + else + return -1; +} + static int lrc_ring_gpr0(const struct intel_engine_cs *engine) { if (GRAPHICS_VER_FULL(engine->i915) >= IP_VER(12, 50)) @@ -768,6 +783,7 @@ static void init_common_regs(u32 * const regs, bool inhibit) { u32 ctl; + int loc; ctl = _MASKED_BIT_ENABLE(CTX_CTRL_INHIBIT_SYN_CTX_SWITCH); ctl |= _MASKED_BIT_DISABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT); @@ -779,6 +795,10 @@ static void init_common_regs(u32 * const regs, regs[CTX_CONTEXT_CONTROL] = ctl; regs[CTX_TIMESTAMP] = ce->stats.runtime.last; + + loc = lrc_ring_bb_offset(engine); + if (loc != -1) + regs[loc + 1] = 0; } static void init_wa_bb_regs(u32 * const regs, @@ -1278,7 +1298,8 @@ gen12_emit_indirect_ctx_rcs(const struct intel_context *ce, u32 *cs) /* hsdes: 1809175790 */ if (!HAS_FLAT_CCS(ce->engine->i915)) - cs = gen12_emit_aux_table_inv(cs, GEN12_GFX_CCS_AUX_NV); + cs = gen12_emit_aux_table_inv(ce->engine->gt, + cs, GEN12_GFX_CCS_AUX_NV); /* Wa_16014892111 */ if (IS_DG2(ce->engine->i915)) @@ -1304,9 +1325,11 @@ gen12_emit_indirect_ctx_xcs(const struct intel_context *ce, u32 *cs) /* hsdes: 1809175790 */ if (!HAS_FLAT_CCS(ce->engine->i915)) { if (ce->engine->class == VIDEO_DECODE_CLASS) - cs = gen12_emit_aux_table_inv(cs, GEN12_VD0_AUX_NV); + cs = gen12_emit_aux_table_inv(ce->engine->gt, + cs, GEN12_VD0_AUX_NV); else if (ce->engine->class == VIDEO_ENHANCEMENT_CLASS) - cs = gen12_emit_aux_table_inv(cs, GEN12_VE0_AUX_NV); + cs = gen12_emit_aux_table_inv(ce->engine->gt, + cs, GEN12_VE0_AUX_NV); } return cs; diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index c6ebe2781076..152244d7f62a 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -207,6 +207,14 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { MOCS_ENTRY(15, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(2) | LE_AOM(1), \ L3_3_WB), \ + /* Bypass LLC - Uncached (EHL+) */ \ + MOCS_ENTRY(16, \ + LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ + L3_1_UC), \ + /* Bypass LLC - L3 (Read-Only) (EHL+) */ \ + MOCS_ENTRY(17, \ + LE_1_UC | LE_TC_1_LLC | LE_SCF(1), \ + L3_3_WB), \ /* Self-Snoop - L3 + LLC */ \ MOCS_ENTRY(18, \ LE_3_WB | LE_TC_1_LLC | LE_LRUM(3) | LE_SSE(3), \ diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c index 6ee8d1127016..7ecfa672f738 100644 --- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c @@ -312,7 +312,7 @@ void ppgtt_init(struct i915_ppgtt *ppgtt, struct intel_gt *gt, ppgtt->vm.gt = gt; ppgtt->vm.i915 = i915; ppgtt->vm.dma = i915->drm.dev; - ppgtt->vm.total = BIT_ULL(INTEL_INFO(i915)->ppgtt_size); + ppgtt->vm.total = BIT_ULL(RUNTIME_INFO(i915)->ppgtt_size); ppgtt->vm.lmem_pt_obj_flags = lmem_pt_obj_flags; dma_resv_init(&ppgtt->vm._resv); diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c index aa6aed837194..f3ad93db0b21 100644 --- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c +++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c @@ -4,8 +4,10 @@ */ #include "i915_drv.h" +#include "i915_pci.h" #include "i915_reg.h" #include "intel_memory_region.h" +#include "intel_pci_config.h" #include "intel_region_lmem.h" #include "intel_region_ttm.h" #include "gem/i915_gem_lmem.h" @@ -45,7 +47,6 @@ _resize_bar(struct drm_i915_private *i915, int resno, resource_size_t size) drm_info(&i915->drm, "BAR%d resized to %dM\n", resno, 1 << bar_size); } -#define LMEM_BAR_NUM 2 static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t lmem_size) { struct pci_dev *pdev = to_pci_dev(i915->drm.dev); @@ -56,15 +57,14 @@ static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t u32 pci_cmd; int i; - current_size = roundup_pow_of_two(pci_resource_len(pdev, LMEM_BAR_NUM)); + current_size = roundup_pow_of_two(pci_resource_len(pdev, GEN12_LMEM_BAR)); if (i915->params.lmem_bar_size) { u32 bar_sizes; rebar_size = i915->params.lmem_bar_size * (resource_size_t)SZ_1M; - bar_sizes = pci_rebar_get_possible_sizes(pdev, - LMEM_BAR_NUM); + bar_sizes = pci_rebar_get_possible_sizes(pdev, GEN12_LMEM_BAR); if (rebar_size == current_size) return; @@ -107,7 +107,7 @@ static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t pci_write_config_dword(pdev, PCI_COMMAND, pci_cmd & ~PCI_COMMAND_MEMORY); - _resize_bar(i915, LMEM_BAR_NUM, rebar_size); + _resize_bar(i915, GEN12_LMEM_BAR, rebar_size); pci_assign_unassigned_bus_resources(pdev->bus); pci_write_config_dword(pdev, PCI_COMMAND, pci_cmd); @@ -202,6 +202,9 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) if (!IS_DGFX(i915)) return ERR_PTR(-ENODEV); + if (!i915_pci_resource_valid(pdev, GEN12_LMEM_BAR)) + return ERR_PTR(-ENXIO); + if (HAS_FLAT_CCS(i915)) { resource_size_t lmem_range; u64 tile_stolen, flat_ccs_base; @@ -236,8 +239,8 @@ static struct intel_memory_region *setup_lmem(struct intel_gt *gt) mul_u32_u32(i915->params.lmem_size, SZ_1M)); } - io_start = pci_resource_start(pdev, 2); - io_size = min(pci_resource_len(pdev, 2), lmem_size); + io_start = pci_resource_start(pdev, GEN12_LMEM_BAR); + io_size = min(pci_resource_len(pdev, GEN12_LMEM_BAR), lmem_size); if (!io_size) return ERR_PTR(-EIO); diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c index 6fadde4ee7bf..6b86250c31ab 100644 --- a/drivers/gpu/drm/i915/gt/intel_rps.c +++ b/drivers/gpu/drm/i915/gt/intel_rps.c @@ -194,9 +194,9 @@ static void rps_enable_interrupts(struct intel_rps *rps) rps_reset_ei(rps); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen6_gt_pm_enable_irq(gt, rps->pm_events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); intel_uncore_write(gt->uncore, GEN6_PMINTRMSK, rps_pm_mask(rps, rps->last_freq)); @@ -217,14 +217,14 @@ static void rps_reset_interrupts(struct intel_rps *rps) { struct intel_gt *gt = rps_to_gt(rps); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); if (GRAPHICS_VER(gt->i915) >= 11) gen11_rps_reset_interrupts(rps); else gen6_rps_reset_interrupts(rps); rps->pm_iir = 0; - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } static void rps_disable_interrupts(struct intel_rps *rps) @@ -234,9 +234,9 @@ static void rps_disable_interrupts(struct intel_rps *rps) intel_uncore_write(gt->uncore, GEN6_PMINTRMSK, rps_pm_sanitize_mask(rps, ~0u)); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); intel_synchronize_irq(gt->i915); @@ -1797,10 +1797,10 @@ static void rps_work(struct work_struct *work) int new_freq, adj, min, max; u32 pm_iir = 0; - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); pm_iir = fetch_and_zero(&rps->pm_iir) & rps->pm_events; client_boost = atomic_read(&rps->num_waiters); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); /* Make sure we didn't queue anything we're not going to process. */ if (!pm_iir && !client_boost) @@ -1873,9 +1873,9 @@ static void rps_work(struct work_struct *work) mutex_unlock(&rps->lock); out: - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen6_gt_pm_unmask_irq(gt, rps->pm_events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) @@ -1883,7 +1883,7 @@ void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) struct intel_gt *gt = rps_to_gt(rps); const u32 events = rps->pm_events & pm_iir; - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); if (unlikely(!events)) return; @@ -1903,7 +1903,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) events = pm_iir & rps->pm_events; if (events) { - spin_lock(>->irq_lock); + spin_lock(gt->irq_lock); GT_TRACE(gt, "irq events:%x\n", events); @@ -1911,7 +1911,7 @@ void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir) rps->pm_iir |= events; schedule_work(&rps->work); - spin_unlock(>->irq_lock); + spin_unlock(gt->irq_lock); } if (GRAPHICS_VER(gt->i915) >= 8) diff --git a/drivers/gpu/drm/i915/gt/intel_sa_media.c b/drivers/gpu/drm/i915/gt/intel_sa_media.c new file mode 100644 index 000000000000..e8f3d18c12b8 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_sa_media.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2021 Intel Corporation + */ + +#include <drm/drm_managed.h> + +#include "i915_drv.h" +#include "gt/intel_gt.h" +#include "gt/intel_sa_media.h" + +int intel_sa_mediagt_setup(struct intel_gt *gt, phys_addr_t phys_addr, + u32 gsi_offset) +{ + struct drm_i915_private *i915 = gt->i915; + struct intel_uncore *uncore; + + uncore = drmm_kzalloc(&i915->drm, sizeof(*uncore), GFP_KERNEL); + if (!uncore) + return -ENOMEM; + + uncore->gsi_offset = gsi_offset; + + gt->irq_lock = to_gt(i915)->irq_lock; + intel_gt_common_init_early(gt); + intel_uncore_init_early(uncore, gt); + + /* + * Standalone media shares the general MMIO space with the primary + * GT. We'll re-use the primary GT's mapping. + */ + uncore->regs = i915->uncore.regs; + if (drm_WARN_ON(&i915->drm, uncore->regs == NULL)) + return -EIO; + + gt->uncore = uncore; + gt->phys_addr = phys_addr; + + /* + * For current platforms we can assume there's only a single + * media GT and cache it for quick lookup. + */ + drm_WARN_ON(&i915->drm, i915->media_gt); + i915->media_gt = gt; + + return 0; +} diff --git a/drivers/gpu/drm/i915/gt/intel_sa_media.h b/drivers/gpu/drm/i915/gt/intel_sa_media.h new file mode 100644 index 000000000000..3afb310de932 --- /dev/null +++ b/drivers/gpu/drm/i915/gt/intel_sa_media.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2021 Intel Corporation + */ +#ifndef __INTEL_SA_MEDIA__ +#define __INTEL_SA_MEDIA__ + +#include <linux/types.h> + +struct intel_gt; + +int intel_sa_mediagt_setup(struct intel_gt *gt, phys_addr_t phys_addr, + u32 gsi_offset); + +#endif /* __INTEL_SA_MEDIA_H__ */ diff --git a/drivers/gpu/drm/i915/gt/intel_sseu.c b/drivers/gpu/drm/i915/gt/intel_sseu.c index c6d3050604c8..66f21c735d54 100644 --- a/drivers/gpu/drm/i915/gt/intel_sseu.c +++ b/drivers/gpu/drm/i915/gt/intel_sseu.c @@ -382,7 +382,6 @@ static void cherryview_sseu_info_init(struct intel_gt *gt) static void gen9_sseu_info_init(struct intel_gt *gt) { struct drm_i915_private *i915 = gt->i915; - struct intel_device_info *info = mkwrite_device_info(i915); struct sseu_dev_info *sseu = >->info.sseu; struct intel_uncore *uncore = gt->uncore; u32 fuse2, eu_disable, subslice_mask; @@ -471,10 +470,10 @@ static void gen9_sseu_info_init(struct intel_gt *gt) if (IS_GEN9_LP(i915)) { #define IS_SS_DISABLED(ss) (!(sseu->subslice_mask.hsw[0] & BIT(ss))) - info->has_pooled_eu = hweight8(sseu->subslice_mask.hsw[0]) == 3; + RUNTIME_INFO(i915)->has_pooled_eu = hweight8(sseu->subslice_mask.hsw[0]) == 3; sseu->min_eu_in_pool = 0; - if (info->has_pooled_eu) { + if (HAS_POOLED_EU(i915)) { if (IS_SS_DISABLED(2) || IS_SS_DISABLED(0)) sseu->min_eu_in_pool = 3; else if (IS_SS_DISABLED(1)) diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c index 1109088fe8f6..82d3f8058995 100644 --- a/drivers/gpu/drm/i915/gt/selftest_lrc.c +++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c @@ -27,6 +27,9 @@ #define NUM_GPR 16 #define NUM_GPR_DW (NUM_GPR * 2) /* each GPR is 2 dwords */ +#define LRI_HEADER MI_INSTR(0x22, 0) +#define LRI_LENGTH_MASK GENMASK(7, 0) + static struct i915_vma *create_scratch(struct intel_gt *gt) { return __vm_create_scratch_for_read_pinned(>->ggtt->vm, PAGE_SIZE); @@ -202,7 +205,7 @@ static int live_lrc_layout(void *arg) continue; } - if ((lri & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) { + if ((lri & GENMASK(31, 23)) != LRI_HEADER) { pr_err("%s: Expected LRI command at dword %d, found %08x\n", engine->name, dw, lri); err = -EINVAL; @@ -357,6 +360,11 @@ static int live_lrc_fixed(void *arg) lrc_ring_cmd_buf_cctl(engine), "RING_CMD_BUF_CCTL" }, + { + i915_mmio_reg_offset(RING_BB_OFFSET(engine->mmio_base)), + lrc_ring_bb_offset(engine), + "RING_BB_OFFSET" + }, { }, }, *t; u32 *hw; @@ -987,18 +995,40 @@ store_context(struct intel_context *ce, struct i915_vma *scratch) hw = defaults; hw += LRC_STATE_OFFSET / sizeof(*hw); do { - u32 len = hw[dw] & 0x7f; + u32 len = hw[dw] & LRI_LENGTH_MASK; + + /* + * Keep it simple, skip parsing complex commands + * + * At present, there are no more MI_LOAD_REGISTER_IMM + * commands after the first 3D state command. Rather + * than include a table (see i915_cmd_parser.c) of all + * the possible commands and their instruction lengths + * (or mask for variable length instructions), assume + * we have gathered the complete list of registers and + * bail out. + */ + if ((hw[dw] >> INSTR_CLIENT_SHIFT) != INSTR_MI_CLIENT) + break; if (hw[dw] == 0) { dw++; continue; } - if ((hw[dw] & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) { + if ((hw[dw] & GENMASK(31, 23)) != LRI_HEADER) { + /* Assume all other MI commands match LRI length mask */ dw += len + 2; continue; } + if (!len) { + pr_err("%s: invalid LRI found in context image\n", + ce->engine->name); + igt_hexdump(defaults, PAGE_SIZE); + break; + } + dw++; len = (len + 1) / 2; while (len--) { @@ -1150,18 +1180,29 @@ static struct i915_vma *load_context(struct intel_context *ce, u32 poison) hw = defaults; hw += LRC_STATE_OFFSET / sizeof(*hw); do { - u32 len = hw[dw] & 0x7f; + u32 len = hw[dw] & LRI_LENGTH_MASK; + + /* For simplicity, break parsing at the first complex command */ + if ((hw[dw] >> INSTR_CLIENT_SHIFT) != INSTR_MI_CLIENT) + break; if (hw[dw] == 0) { dw++; continue; } - if ((hw[dw] & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) { + if ((hw[dw] & GENMASK(31, 23)) != LRI_HEADER) { dw += len + 2; continue; } + if (!len) { + pr_err("%s: invalid LRI found in context image\n", + ce->engine->name); + igt_hexdump(defaults, PAGE_SIZE); + break; + } + dw++; len = (len + 1) / 2; *cs++ = MI_LOAD_REGISTER_IMM(len); @@ -1292,18 +1333,29 @@ static int compare_isolation(struct intel_engine_cs *engine, hw = defaults; hw += LRC_STATE_OFFSET / sizeof(*hw); do { - u32 len = hw[dw] & 0x7f; + u32 len = hw[dw] & LRI_LENGTH_MASK; + + /* For simplicity, break parsing at the first complex command */ + if ((hw[dw] >> INSTR_CLIENT_SHIFT) != INSTR_MI_CLIENT) + break; if (hw[dw] == 0) { dw++; continue; } - if ((hw[dw] & GENMASK(31, 23)) != MI_INSTR(0x22, 0)) { + if ((hw[dw] & GENMASK(31, 23)) != LRI_HEADER) { dw += len + 2; continue; } + if (!len) { + pr_err("%s: invalid LRI found in context image\n", + engine->name); + igt_hexdump(defaults, PAGE_SIZE); + break; + } + dw++; len = (len + 1) / 2; while (len--) { @@ -1343,6 +1395,30 @@ err_A0: return err; } +static struct i915_vma * +create_result_vma(struct i915_address_space *vm, unsigned long sz) +{ + struct i915_vma *vma; + void *ptr; + + vma = create_user_vma(vm, sz); + if (IS_ERR(vma)) + return vma; + + /* Set the results to a known value distinct from the poison */ + ptr = i915_gem_object_pin_map_unlocked(vma->obj, I915_MAP_WC); + if (IS_ERR(ptr)) { + i915_vma_put(vma); + return ERR_CAST(ptr); + } + + memset(ptr, POISON_INUSE, vma->size); + i915_gem_object_flush_map(vma->obj); + i915_gem_object_unpin_map(vma->obj); + + return vma; +} + static int __lrc_isolation(struct intel_engine_cs *engine, u32 poison) { u32 *sema = memset32(engine->status_page.addr + 1000, 0, 1); @@ -1361,13 +1437,13 @@ static int __lrc_isolation(struct intel_engine_cs *engine, u32 poison) goto err_A; } - ref[0] = create_user_vma(A->vm, SZ_64K); + ref[0] = create_result_vma(A->vm, SZ_64K); if (IS_ERR(ref[0])) { err = PTR_ERR(ref[0]); goto err_B; } - ref[1] = create_user_vma(A->vm, SZ_64K); + ref[1] = create_result_vma(A->vm, SZ_64K); if (IS_ERR(ref[1])) { err = PTR_ERR(ref[1]); goto err_ref0; @@ -1389,13 +1465,13 @@ static int __lrc_isolation(struct intel_engine_cs *engine, u32 poison) } i915_request_put(rq); - result[0] = create_user_vma(A->vm, SZ_64K); + result[0] = create_result_vma(A->vm, SZ_64K); if (IS_ERR(result[0])) { err = PTR_ERR(result[0]); goto err_ref1; } - result[1] = create_user_vma(A->vm, SZ_64K); + result[1] = create_result_vma(A->vm, SZ_64K); if (IS_ERR(result[1])) { err = PTR_ERR(result[1]); goto err_result0; @@ -1408,18 +1484,17 @@ static int __lrc_isolation(struct intel_engine_cs *engine, u32 poison) } err = poison_registers(B, poison, sema); - if (err) { - WRITE_ONCE(*sema, -1); - i915_request_put(rq); - goto err_result1; - } - - if (i915_request_wait(rq, 0, HZ / 2) < 0) { - i915_request_put(rq); + if (err == 0 && i915_request_wait(rq, 0, HZ / 2) < 0) { + pr_err("%s(%s): wait for results timed out\n", + __func__, engine->name); err = -ETIME; - goto err_result1; } + + /* Always cancel the semaphore wait, just in case the GPU gets stuck */ + WRITE_ONCE(*sema, -1); i915_request_put(rq); + if (err) + goto err_result1; err = compare_isolation(engine, ref, result, A, poison); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c index 24451d000a6a..bac06e3d6f2c 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c @@ -82,9 +82,9 @@ static void gen9_reset_guc_interrupts(struct intel_guc *guc) assert_rpm_wakelock_held(>->i915->runtime_pm); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen6_gt_pm_reset_iir(gt, gt->pm_guc_events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } static void gen9_enable_guc_interrupts(struct intel_guc *guc) @@ -93,11 +93,11 @@ static void gen9_enable_guc_interrupts(struct intel_guc *guc) assert_rpm_wakelock_held(>->i915->runtime_pm); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) & gt->pm_guc_events); gen6_gt_pm_enable_irq(gt, gt->pm_guc_events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } static void gen9_disable_guc_interrupts(struct intel_guc *guc) @@ -106,11 +106,11 @@ static void gen9_disable_guc_interrupts(struct intel_guc *guc) assert_rpm_wakelock_held(>->i915->runtime_pm); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen6_gt_pm_disable_irq(gt, gt->pm_guc_events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); intel_synchronize_irq(gt->i915); gen9_reset_guc_interrupts(guc); @@ -120,9 +120,9 @@ static void gen11_reset_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen11_gt_reset_one_iir(gt, 0, GEN11_GUC); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } static void gen11_enable_guc_interrupts(struct intel_guc *guc) @@ -130,25 +130,25 @@ static void gen11_enable_guc_interrupts(struct intel_guc *guc) struct intel_gt *gt = guc_to_gt(guc); u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC)); intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, events); intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } static void gen11_disable_guc_interrupts(struct intel_guc *guc) { struct intel_gt *gt = guc_to_gt(guc); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0); intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); intel_synchronize_irq(gt->i915); gen11_reset_guc_interrupts(guc); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c index b071973ac41c..55d3ef93e86f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c @@ -36,24 +36,6 @@ struct guc_log_section { const char *name; }; -static s32 scale_log_param(struct intel_guc_log *log, const struct guc_log_section *section, - s32 param) -{ - /* -1 means default */ - if (param < 0) - return section->default_val; - - /* Check for 32-bit overflow */ - if (param >= SZ_4K) { - drm_err(&guc_to_gt(log_to_guc(log))->i915->drm, "Size too large for GuC %s log: %dMB!", - section->name, param); - return section->default_val; - } - - /* Param units are 1MB */ - return param * SZ_1M; -} - static void _guc_log_init_sizes(struct intel_guc_log *log) { struct intel_guc *guc = log_to_guc(log); @@ -78,15 +60,10 @@ static void _guc_log_init_sizes(struct intel_guc_log *log) "capture", } }; - s32 params[GUC_LOG_SECTIONS_LIMIT] = { - GUC_LOG_DEFAULT_CRASH_BUFFER_SIZE / SZ_1M, - GUC_LOG_DEFAULT_DEBUG_BUFFER_SIZE / SZ_1M, - GUC_LOG_DEFAULT_CAPTURE_BUFFER_SIZE / SZ_1M, - }; int i; for (i = 0; i < GUC_LOG_SECTIONS_LIMIT; i++) - log->sizes[i].bytes = scale_log_param(log, sections + i, params[i]); + log->sizes[i].bytes = sections[i].default_val; /* If debug size > 1MB then bump default crash size to keep the same units */ if (log->sizes[GUC_LOG_SECTIONS_DEBUG].bytes >= SZ_1M && diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index 64c4e83153f4..1db59eeb34db 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -684,7 +684,7 @@ static int __guc_add_request(struct intel_guc *guc, struct i915_request *rq) * Corner case where requests were sitting in the priority list or a * request resubmitted after the context was banned. */ - if (unlikely(intel_context_is_banned(ce))) { + if (unlikely(!intel_context_is_schedulable(ce))) { i915_request_put(i915_request_mark_eio(rq)); intel_engine_signal_breadcrumbs(ce->engine); return 0; @@ -870,15 +870,15 @@ static int guc_wq_item_append(struct intel_guc *guc, struct i915_request *rq) { struct intel_context *ce = request_to_scheduling_context(rq); - int ret = 0; + int ret; - if (likely(!intel_context_is_banned(ce))) { - ret = __guc_wq_item_append(rq); + if (unlikely(!intel_context_is_schedulable(ce))) + return 0; - if (unlikely(ret == -EBUSY)) { - guc->stalled_request = rq; - guc->submission_stall_reason = STALL_MOVE_LRC_TAIL; - } + ret = __guc_wq_item_append(rq); + if (unlikely(ret == -EBUSY)) { + guc->stalled_request = rq; + guc->submission_stall_reason = STALL_MOVE_LRC_TAIL; } return ret; @@ -897,7 +897,7 @@ static bool multi_lrc_submit(struct i915_request *rq) * submitting all the requests generated in parallel. */ return test_bit(I915_FENCE_FLAG_SUBMIT_PARALLEL, &rq->fence.flags) || - intel_context_is_banned(ce); + !intel_context_is_schedulable(ce); } static int guc_dequeue_one_context(struct intel_guc *guc) @@ -966,7 +966,7 @@ register_context: struct intel_context *ce = request_to_scheduling_context(last); if (unlikely(!ctx_id_mapped(guc, ce->guc_id.id) && - !intel_context_is_banned(ce))) { + intel_context_is_schedulable(ce))) { ret = try_context_registration(ce, false); if (unlikely(ret == -EPIPE)) { goto deadlk; @@ -1438,7 +1438,12 @@ void intel_guc_busyness_park(struct intel_gt *gt) if (!guc_submission_initialized(guc)) return; - cancel_delayed_work(&guc->timestamp.work); + /* + * There is a race with suspend flow where the worker runs after suspend + * and causes an unclaimed register access warning. Cancel the worker + * synchronously here. + */ + cancel_delayed_work_sync(&guc->timestamp.work); /* * Before parking, we should sample engine busyness stats if we need to. @@ -1532,8 +1537,8 @@ void intel_guc_submission_reset_prepare(struct intel_guc *guc) __reset_guc_busyness_stats(guc); /* Flush IRQ handler */ - spin_lock_irq(&guc_to_gt(guc)->irq_lock); - spin_unlock_irq(&guc_to_gt(guc)->irq_lock); + spin_lock_irq(guc_to_gt(guc)->irq_lock); + spin_unlock_irq(guc_to_gt(guc)->irq_lock); guc_flush_submissions(guc); guc_flush_destroyed_contexts(guc); @@ -1571,7 +1576,7 @@ static void guc_reset_state(struct intel_context *ce, u32 head, bool scrub) { struct intel_engine_cs *engine = __context_to_physical_engine(ce); - if (intel_context_is_banned(ce)) + if (!intel_context_is_schedulable(ce)) return; GEM_BUG_ON(!intel_context_is_pinned(ce)); @@ -4419,12 +4424,12 @@ static void guc_handle_context_reset(struct intel_guc *guc, { trace_intel_context_reset(ce); - if (likely(!intel_context_is_banned(ce))) { + if (likely(intel_context_is_schedulable(ce))) { capture_error_state(guc, ce); guc_context_replay(ce); } else { drm_info(&guc_to_gt(guc)->i915->drm, - "Ignoring context reset notification of banned context 0x%04X on %s", + "Ignoring context reset notification of exiting context 0x%04X on %s", ce->guc_id.id, ce->engine->name); } } diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c index abf4e142596d..dbd048b77e19 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c @@ -245,9 +245,9 @@ static int guc_enable_communication(struct intel_guc *guc) intel_guc_enable_interrupts(guc); /* check for CT messages received before we enabled interrupts */ - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); intel_guc_ct_event_handler(&guc->ct); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); drm_dbg(&i915->drm, "GuC communication enabled\n"); diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c index af425916cdf6..b91ad4aede1f 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c @@ -72,12 +72,14 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, * security fixes, etc. to be enabled. */ #define INTEL_GUC_FIRMWARE_DEFS(fw_def, guc_maj, guc_mmp) \ - fw_def(DG2, 0, guc_mmp(dg2, 70, 4, 1)) \ + fw_def(DG2, 0, guc_maj(dg2, 70, 5)) \ + fw_def(ALDERLAKE_P, 0, guc_maj(adlp, 70, 5)) \ fw_def(ALDERLAKE_P, 0, guc_mmp(adlp, 70, 1, 1)) \ fw_def(ALDERLAKE_P, 0, guc_mmp(adlp, 69, 0, 3)) \ + fw_def(ALDERLAKE_S, 0, guc_maj(tgl, 70, 5)) \ fw_def(ALDERLAKE_S, 0, guc_mmp(tgl, 70, 1, 1)) \ fw_def(ALDERLAKE_S, 0, guc_mmp(tgl, 69, 0, 3)) \ - fw_def(DG1, 0, guc_mmp(dg1, 70, 1, 1)) \ + fw_def(DG1, 0, guc_maj(dg1, 70, 5)) \ fw_def(ROCKETLAKE, 0, guc_mmp(tgl, 70, 1, 1)) \ fw_def(TIGERLAKE, 0, guc_mmp(tgl, 70, 1, 1)) \ fw_def(JASPERLAKE, 0, guc_mmp(ehl, 70, 1, 1)) \ @@ -92,9 +94,11 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw, fw_def(SKYLAKE, 0, guc_mmp(skl, 70, 1, 1)) #define INTEL_HUC_FIRMWARE_DEFS(fw_def, huc_raw, huc_mmp) \ + fw_def(ALDERLAKE_P, 0, huc_raw(tgl)) \ fw_def(ALDERLAKE_P, 0, huc_mmp(tgl, 7, 9, 3)) \ + fw_def(ALDERLAKE_S, 0, huc_raw(tgl)) \ fw_def(ALDERLAKE_S, 0, huc_mmp(tgl, 7, 9, 3)) \ - fw_def(DG1, 0, huc_mmp(dg1, 7, 9, 3)) \ + fw_def(DG1, 0, huc_raw(dg1)) \ fw_def(ROCKETLAKE, 0, huc_mmp(tgl, 7, 9, 3)) \ fw_def(TIGERLAKE, 0, huc_mmp(tgl, 7, 9, 3)) \ fw_def(JASPERLAKE, 0, huc_mmp(ehl, 9, 0, 0)) \ @@ -232,6 +236,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) u32 fw_count; u8 rev = INTEL_REVID(i915); int i; + bool found; /* * The only difference between the ADL GuC FWs is the HWConfig support. @@ -246,6 +251,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) fw_blobs = blobs_all[uc_fw->type].blobs; fw_count = blobs_all[uc_fw->type].count; + found = false; for (i = 0; i < fw_count && p <= fw_blobs[i].p; i++) { const struct uc_fw_blob *blob = &fw_blobs[i].blob; @@ -266,9 +272,15 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) uc_fw->file_wanted.path = blob->path; uc_fw->file_wanted.major_ver = blob->major; uc_fw->file_wanted.minor_ver = blob->minor; + found = true; break; } + if (!found && uc_fw->file_selected.path) { + /* Failed to find a match for the last attempt?! */ + uc_fw->file_selected.path = NULL; + } + /* make sure the list is ordered as expected */ if (IS_ENABLED(CONFIG_DRM_I915_SELFTEST) && !verified) { verified = true; @@ -322,7 +334,7 @@ __uc_fw_auto_select(struct drm_i915_private *i915, struct intel_uc_fw *uc_fw) continue; bad: - drm_err(&i915->drm, "\x1B[35;1mInvalid FW blob order: %s r%u %s%d.%d.%d comes before %s r%u %s%d.%d.%d\n", + drm_err(&i915->drm, "Invalid FW blob order: %s r%u %s%d.%d.%d comes before %s r%u %s%d.%d.%d\n", intel_platform_name(fw_blobs[i - 1].p), fw_blobs[i - 1].rev, fw_blobs[i - 1].blob.legacy ? "L" : "v", fw_blobs[i - 1].blob.major, @@ -553,10 +565,14 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) err = firmware_request_nowarn(&fw, uc_fw->file_selected.path, dev); memcpy(&file_ideal, &uc_fw->file_wanted, sizeof(file_ideal)); - if (!err || intel_uc_fw_is_overridden(uc_fw)) - goto done; + + /* Any error is terminal if overriding. Don't bother searching for older versions */ + if (err && intel_uc_fw_is_overridden(uc_fw)) + goto fail; while (err == -ENOENT) { + old_ver = true; + __uc_fw_auto_select(i915, uc_fw); if (!uc_fw->file_selected.path) { /* @@ -576,8 +592,6 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw) if (err) goto fail; - old_ver = true; -done: if (uc_fw->loaded_via_gsc) err = check_gsc_manifest(fw, uc_fw); else diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c index 557f3314291a..076c779f776a 100644 --- a/drivers/gpu/drm/i915/gvt/aperture_gm.c +++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c @@ -240,13 +240,13 @@ static void free_resource(struct intel_vgpu *vgpu) } static int alloc_resource(struct intel_vgpu *vgpu, - struct intel_vgpu_creation_params *param) + const struct intel_vgpu_config *conf) { struct intel_gvt *gvt = vgpu->gvt; unsigned long request, avail, max, taken; const char *item; - if (!param->low_gm_sz || !param->high_gm_sz || !param->fence_sz) { + if (!conf->low_mm || !conf->high_mm || !conf->fence) { gvt_vgpu_err("Invalid vGPU creation params\n"); return -EINVAL; } @@ -255,7 +255,7 @@ static int alloc_resource(struct intel_vgpu *vgpu, max = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE; taken = gvt->gm.vgpu_allocated_low_gm_size; avail = max - taken; - request = MB_TO_BYTES(param->low_gm_sz); + request = conf->low_mm; if (request > avail) goto no_enough_resource; @@ -266,7 +266,7 @@ static int alloc_resource(struct intel_vgpu *vgpu, max = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE; taken = gvt->gm.vgpu_allocated_high_gm_size; avail = max - taken; - request = MB_TO_BYTES(param->high_gm_sz); + request = conf->high_mm; if (request > avail) goto no_enough_resource; @@ -277,16 +277,16 @@ static int alloc_resource(struct intel_vgpu *vgpu, max = gvt_fence_sz(gvt) - HOST_FENCE; taken = gvt->fence.vgpu_allocated_fence_num; avail = max - taken; - request = param->fence_sz; + request = conf->fence; if (request > avail) goto no_enough_resource; vgpu_fence_sz(vgpu) = request; - gvt->gm.vgpu_allocated_low_gm_size += MB_TO_BYTES(param->low_gm_sz); - gvt->gm.vgpu_allocated_high_gm_size += MB_TO_BYTES(param->high_gm_sz); - gvt->fence.vgpu_allocated_fence_num += param->fence_sz; + gvt->gm.vgpu_allocated_low_gm_size += conf->low_mm; + gvt->gm.vgpu_allocated_high_gm_size += conf->high_mm; + gvt->fence.vgpu_allocated_fence_num += conf->fence; return 0; no_enough_resource: @@ -298,7 +298,7 @@ no_enough_resource: } /** - * inte_gvt_free_vgpu_resource - free HW resource owned by a vGPU + * intel_vgpu_free_resource() - free HW resource owned by a vGPU * @vgpu: a vGPU * * This function is used to free the HW resource owned by a vGPU. @@ -328,7 +328,7 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu) } /** - * intel_alloc_vgpu_resource - allocate HW resource for a vGPU + * intel_vgpu_alloc_resource() - allocate HW resource for a vGPU * @vgpu: vGPU * @param: vGPU creation params * @@ -340,11 +340,11 @@ void intel_vgpu_reset_resource(struct intel_vgpu *vgpu) * */ int intel_vgpu_alloc_resource(struct intel_vgpu *vgpu, - struct intel_vgpu_creation_params *param) + const struct intel_vgpu_config *conf) { int ret; - ret = alloc_resource(vgpu, param); + ret = alloc_resource(vgpu, conf); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/gvt/cfg_space.c b/drivers/gpu/drm/i915/gvt/cfg_space.c index dad3a6054335..eef3bba8a41b 100644 --- a/drivers/gpu/drm/i915/gvt/cfg_space.c +++ b/drivers/gpu/drm/i915/gvt/cfg_space.c @@ -33,6 +33,7 @@ #include "i915_drv.h" #include "gvt.h" +#include "intel_pci_config.h" enum { INTEL_GVT_PCI_BAR_GTTMMIO = 0, @@ -353,9 +354,9 @@ void intel_vgpu_init_cfg_space(struct intel_vgpu *vgpu, memset(vgpu_cfg_space(vgpu) + INTEL_GVT_PCI_OPREGION, 0, 4); vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_GTTMMIO].size = - pci_resource_len(pdev, 0); + pci_resource_len(pdev, GTTMMADR_BAR); vgpu->cfg_space.bar[INTEL_GVT_PCI_BAR_APERTURE].size = - pci_resource_len(pdev, 2); + pci_resource_len(pdev, GTT_APERTURE_BAR); memset(vgpu_cfg_space(vgpu) + PCI_ROM_ADDRESS, 0, 4); diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c index a30ba2d7b7ba..1b509c1a1e33 100644 --- a/drivers/gpu/drm/i915/gvt/edid.c +++ b/drivers/gpu/drm/i915/gvt/edid.c @@ -32,9 +32,10 @@ * */ +#include "display/intel_gmbus_regs.h" +#include "gvt.h" #include "i915_drv.h" #include "i915_reg.h" -#include "gvt.h" #define GMBUS1_TOTAL_BYTES_SHIFT 16 #define GMBUS1_TOTAL_BYTES_MASK 0x1ff diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index b4f69364f9a1..ce0eb03709c3 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -2341,7 +2341,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off, gvt_vgpu_err("fail to populate guest ggtt entry\n"); /* guest driver may read/write the entry when partial * update the entry in this situation p2m will fail - * settting the shadow entry to point to a scratch page + * setting the shadow entry to point to a scratch page */ ops->set_pfn(&m, gvt->gtt.scratch_mfn); } else diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h index 705689e64011..dbf8d7470b2c 100644 --- a/drivers/gpu/drm/i915/gvt/gvt.h +++ b/drivers/gpu/drm/i915/gvt/gvt.h @@ -36,6 +36,7 @@ #include <uapi/linux/pci_regs.h> #include <linux/kvm_host.h> #include <linux/vfio.h> +#include <linux/mdev.h> #include "i915_drv.h" #include "intel_gvt.h" @@ -172,6 +173,7 @@ struct intel_vgpu_submission { #define KVMGT_DEBUGFS_FILENAME "kvmgt_nr_cache_entries" struct intel_vgpu { + struct vfio_device vfio_device; struct intel_gvt *gvt; struct mutex vgpu_lock; int id; @@ -211,7 +213,6 @@ struct intel_vgpu { u32 scan_nonprivbb; - struct vfio_device vfio_device; struct vfio_region *region; int num_regions; struct eventfd_ctx *intx_trigger; @@ -294,15 +295,25 @@ struct intel_gvt_firmware { bool firmware_loaded; }; -#define NR_MAX_INTEL_VGPU_TYPES 20 -struct intel_vgpu_type { - char name[16]; - unsigned int avail_instance; - unsigned int low_gm_size; - unsigned int high_gm_size; +struct intel_vgpu_config { + unsigned int low_mm; + unsigned int high_mm; unsigned int fence; + + /* + * A vGPU with a weight of 8 will get twice as much GPU as a vGPU with + * a weight of 4 on a contended host, different vGPU type has different + * weight set. Legal weights range from 1 to 16. + */ unsigned int weight; - enum intel_vgpu_edid resolution; + enum intel_vgpu_edid edid; + const char *name; +}; + +struct intel_vgpu_type { + struct mdev_type type; + char name[16]; + const struct intel_vgpu_config *conf; }; struct intel_gvt { @@ -326,6 +337,8 @@ struct intel_gvt { struct intel_gvt_workload_scheduler scheduler; struct notifier_block shadow_ctx_notifier_block[I915_NUM_ENGINES]; DECLARE_HASHTABLE(cmd_table, GVT_CMD_HASH_BITS); + struct mdev_parent parent; + struct mdev_type **mdev_types; struct intel_vgpu_type *types; unsigned int num_types; struct intel_vgpu *idle_vgpu; @@ -436,19 +449,8 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt); /* ring context size i.e. the first 0x50 dwords*/ #define RING_CTX_SIZE 320 -struct intel_vgpu_creation_params { - __u64 low_gm_sz; /* in MB */ - __u64 high_gm_sz; /* in MB */ - __u64 fence_sz; - __u64 resolution; - __s32 primary; - __u64 vgpu_id; - - __u32 weight; -}; - int intel_vgpu_alloc_resource(struct intel_vgpu *vgpu, - struct intel_vgpu_creation_params *param); + const struct intel_vgpu_config *conf); void intel_vgpu_reset_resource(struct intel_vgpu *vgpu); void intel_vgpu_free_resource(struct intel_vgpu *vgpu); void intel_vgpu_write_fence(struct intel_vgpu *vgpu, @@ -494,8 +496,8 @@ void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt); struct intel_vgpu *intel_gvt_create_idle_vgpu(struct intel_gvt *gvt); void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu); -struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, - struct intel_vgpu_type *type); +int intel_gvt_create_vgpu(struct intel_vgpu *vgpu, + const struct intel_vgpu_config *conf); void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu); void intel_gvt_release_vgpu(struct intel_vgpu *vgpu); void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr, diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index beea5895e499..daac2050d77d 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -498,7 +498,7 @@ static u32 bdw_vgpu_get_dp_bitrate(struct intel_vgpu *vgpu, enum port port) switch (wrpll_ctl & WRPLL_REF_MASK) { case WRPLL_REF_PCH_SSC: - refclk = vgpu->gvt->gt->i915->dpll.ref_clks.ssc; + refclk = vgpu->gvt->gt->i915->display.dpll.ref_clks.ssc; break; case WRPLL_REF_LCPLL: refclk = 2700000; @@ -529,7 +529,7 @@ out: static u32 bxt_vgpu_get_dp_bitrate(struct intel_vgpu *vgpu, enum port port) { u32 dp_br = 0; - int refclk = vgpu->gvt->gt->i915->dpll.ref_clks.nssc; + int refclk = vgpu->gvt->gt->i915->display.dpll.ref_clks.nssc; enum dpio_phy phy = DPIO_PHY0; enum dpio_channel ch = DPIO_CH0; struct dpll clock = {0}; @@ -905,7 +905,7 @@ static int update_fdi_rx_iir_status(struct intel_vgpu *vgpu, else if (FDI_RX_IMR_TO_PIPE(offset) != INVALID_INDEX) index = FDI_RX_IMR_TO_PIPE(offset); else { - gvt_vgpu_err("Unsupport registers %x\n", offset); + gvt_vgpu_err("Unsupported registers %x\n", offset); return -EINVAL; } @@ -3052,7 +3052,7 @@ int intel_vgpu_default_mmio_read(struct intel_vgpu *vgpu, unsigned int offset, } /** - * intel_t_default_mmio_write - default MMIO write handler + * intel_vgpu_default_mmio_write() - default MMIO write handler * @vgpu: a vGPU * @offset: access offset * @p_data: write data buffer diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index e3cd58946477..7a45e5360caf 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -34,7 +34,6 @@ */ #include <linux/init.h> -#include <linux/device.h> #include <linux/mm.h> #include <linux/kthread.h> #include <linux/sched/mm.h> @@ -43,7 +42,6 @@ #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/eventfd.h> -#include <linux/uuid.h> #include <linux/mdev.h> #include <linux/debugfs.h> @@ -115,117 +113,18 @@ static void kvmgt_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot, struct kvm_page_track_notifier_node *node); -static ssize_t available_instances_show(struct mdev_type *mtype, - struct mdev_type_attribute *attr, - char *buf) +static ssize_t intel_vgpu_show_description(struct mdev_type *mtype, char *buf) { - struct intel_vgpu_type *type; - unsigned int num = 0; - struct intel_gvt *gvt = kdev_to_i915(mtype_get_parent_dev(mtype))->gvt; - - type = &gvt->types[mtype_get_type_group_id(mtype)]; - if (!type) - num = 0; - else - num = type->avail_instance; - - return sprintf(buf, "%u\n", num); -} - -static ssize_t device_api_show(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf) -{ - return sprintf(buf, "%s\n", VFIO_DEVICE_API_PCI_STRING); -} - -static ssize_t description_show(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf) -{ - struct intel_vgpu_type *type; - struct intel_gvt *gvt = kdev_to_i915(mtype_get_parent_dev(mtype))->gvt; - - type = &gvt->types[mtype_get_type_group_id(mtype)]; - if (!type) - return 0; + struct intel_vgpu_type *type = + container_of(mtype, struct intel_vgpu_type, type); return sprintf(buf, "low_gm_size: %dMB\nhigh_gm_size: %dMB\n" "fence: %d\nresolution: %s\n" "weight: %d\n", - BYTES_TO_MB(type->low_gm_size), - BYTES_TO_MB(type->high_gm_size), - type->fence, vgpu_edid_str(type->resolution), - type->weight); -} - -static ssize_t name_show(struct mdev_type *mtype, - struct mdev_type_attribute *attr, char *buf) -{ - struct intel_vgpu_type *type; - struct intel_gvt *gvt = kdev_to_i915(mtype_get_parent_dev(mtype))->gvt; - - type = &gvt->types[mtype_get_type_group_id(mtype)]; - if (!type) - return 0; - - return sprintf(buf, "%s\n", type->name); -} - -static MDEV_TYPE_ATTR_RO(available_instances); -static MDEV_TYPE_ATTR_RO(device_api); -static MDEV_TYPE_ATTR_RO(description); -static MDEV_TYPE_ATTR_RO(name); - -static struct attribute *gvt_type_attrs[] = { - &mdev_type_attr_available_instances.attr, - &mdev_type_attr_device_api.attr, - &mdev_type_attr_description.attr, - &mdev_type_attr_name.attr, - NULL, -}; - -static struct attribute_group *gvt_vgpu_type_groups[] = { - [0 ... NR_MAX_INTEL_VGPU_TYPES - 1] = NULL, -}; - -static int intel_gvt_init_vgpu_type_groups(struct intel_gvt *gvt) -{ - int i, j; - struct intel_vgpu_type *type; - struct attribute_group *group; - - for (i = 0; i < gvt->num_types; i++) { - type = &gvt->types[i]; - - group = kzalloc(sizeof(struct attribute_group), GFP_KERNEL); - if (!group) - goto unwind; - - group->name = type->name; - group->attrs = gvt_type_attrs; - gvt_vgpu_type_groups[i] = group; - } - - return 0; - -unwind: - for (j = 0; j < i; j++) { - group = gvt_vgpu_type_groups[j]; - kfree(group); - } - - return -ENOMEM; -} - -static void intel_gvt_cleanup_vgpu_type_groups(struct intel_gvt *gvt) -{ - int i; - struct attribute_group *group; - - for (i = 0; i < gvt->num_types; i++) { - group = gvt_vgpu_type_groups[i]; - gvt_vgpu_type_groups[i] = NULL; - kfree(group); - } + BYTES_TO_MB(type->conf->low_mm), + BYTES_TO_MB(type->conf->high_mm), + type->conf->fence, vgpu_edid_str(type->conf->edid), + type->conf->weight); } static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn, @@ -1546,7 +1445,28 @@ static const struct attribute_group *intel_vgpu_groups[] = { NULL, }; +static int intel_vgpu_init_dev(struct vfio_device *vfio_dev) +{ + struct mdev_device *mdev = to_mdev_device(vfio_dev->dev); + struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); + struct intel_vgpu_type *type = + container_of(mdev->type, struct intel_vgpu_type, type); + + vgpu->gvt = kdev_to_i915(mdev->type->parent->dev)->gvt; + return intel_gvt_create_vgpu(vgpu, type->conf); +} + +static void intel_vgpu_release_dev(struct vfio_device *vfio_dev) +{ + struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev); + + intel_gvt_destroy_vgpu(vgpu); + vfio_free_device(vfio_dev); +} + static const struct vfio_device_ops intel_vgpu_dev_ops = { + .init = intel_vgpu_init_dev, + .release = intel_vgpu_release_dev, .open_device = intel_vgpu_open_device, .close_device = intel_vgpu_close_device, .read = intel_vgpu_read, @@ -1558,35 +1478,28 @@ static const struct vfio_device_ops intel_vgpu_dev_ops = { static int intel_vgpu_probe(struct mdev_device *mdev) { - struct device *pdev = mdev_parent_dev(mdev); - struct intel_gvt *gvt = kdev_to_i915(pdev)->gvt; - struct intel_vgpu_type *type; struct intel_vgpu *vgpu; int ret; - type = &gvt->types[mdev_get_type_group_id(mdev)]; - if (!type) - return -EINVAL; - - vgpu = intel_gvt_create_vgpu(gvt, type); + vgpu = vfio_alloc_device(intel_vgpu, vfio_device, &mdev->dev, + &intel_vgpu_dev_ops); if (IS_ERR(vgpu)) { gvt_err("failed to create intel vgpu: %ld\n", PTR_ERR(vgpu)); return PTR_ERR(vgpu); } - vfio_init_group_dev(&vgpu->vfio_device, &mdev->dev, - &intel_vgpu_dev_ops); - dev_set_drvdata(&mdev->dev, vgpu); ret = vfio_register_emulated_iommu_dev(&vgpu->vfio_device); - if (ret) { - intel_gvt_destroy_vgpu(vgpu); - return ret; - } + if (ret) + goto out_put_vdev; gvt_dbg_core("intel_vgpu_create succeeded for mdev: %s\n", dev_name(mdev_dev(mdev))); return 0; + +out_put_vdev: + vfio_put_device(&vgpu->vfio_device); + return ret; } static void intel_vgpu_remove(struct mdev_device *mdev) @@ -1595,18 +1508,43 @@ static void intel_vgpu_remove(struct mdev_device *mdev) if (WARN_ON_ONCE(vgpu->attached)) return; - intel_gvt_destroy_vgpu(vgpu); + + vfio_unregister_group_dev(&vgpu->vfio_device); + vfio_put_device(&vgpu->vfio_device); +} + +static unsigned int intel_vgpu_get_available(struct mdev_type *mtype) +{ + struct intel_vgpu_type *type = + container_of(mtype, struct intel_vgpu_type, type); + struct intel_gvt *gvt = kdev_to_i915(mtype->parent->dev)->gvt; + unsigned int low_gm_avail, high_gm_avail, fence_avail; + + mutex_lock(&gvt->lock); + low_gm_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE - + gvt->gm.vgpu_allocated_low_gm_size; + high_gm_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE - + gvt->gm.vgpu_allocated_high_gm_size; + fence_avail = gvt_fence_sz(gvt) - HOST_FENCE - + gvt->fence.vgpu_allocated_fence_num; + mutex_unlock(&gvt->lock); + + return min3(low_gm_avail / type->conf->low_mm, + high_gm_avail / type->conf->high_mm, + fence_avail / type->conf->fence); } static struct mdev_driver intel_vgpu_mdev_driver = { + .device_api = VFIO_DEVICE_API_PCI_STRING, .driver = { .name = "intel_vgpu_mdev", .owner = THIS_MODULE, .dev_groups = intel_vgpu_groups, }, - .probe = intel_vgpu_probe, - .remove = intel_vgpu_remove, - .supported_type_groups = gvt_vgpu_type_groups, + .probe = intel_vgpu_probe, + .remove = intel_vgpu_remove, + .get_available = intel_vgpu_get_available, + .show_description = intel_vgpu_show_description, }; int intel_gvt_page_track_add(struct intel_vgpu *info, u64 gfn) @@ -1904,8 +1842,7 @@ static void intel_gvt_clean_device(struct drm_i915_private *i915) if (drm_WARN_ON(&i915->drm, !gvt)) return; - mdev_unregister_device(i915->drm.dev); - intel_gvt_cleanup_vgpu_type_groups(gvt); + mdev_unregister_parent(&gvt->parent); intel_gvt_destroy_idle_vgpu(gvt->idle_vgpu); intel_gvt_clean_vgpu_types(gvt); @@ -2005,19 +1942,15 @@ static int intel_gvt_init_device(struct drm_i915_private *i915) intel_gvt_debugfs_init(gvt); - ret = intel_gvt_init_vgpu_type_groups(gvt); + ret = mdev_register_parent(&gvt->parent, i915->drm.dev, + &intel_vgpu_mdev_driver, + gvt->mdev_types, gvt->num_types); if (ret) goto out_destroy_idle_vgpu; - ret = mdev_register_device(i915->drm.dev, &intel_vgpu_mdev_driver); - if (ret) - goto out_cleanup_vgpu_type_groups; - gvt_dbg_core("gvt device initialization is done\n"); return 0; -out_cleanup_vgpu_type_groups: - intel_gvt_cleanup_vgpu_type_groups(gvt); out_destroy_idle_vgpu: intel_gvt_destroy_idle_vgpu(gvt->idle_vgpu); intel_gvt_debugfs_clean(gvt); diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index c85bafe7539e..1c6e941c9666 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -546,7 +546,7 @@ static void switch_mmio(struct intel_vgpu *pre, } /** - * intel_gvt_switch_render_mmio - switch mmio context of specific engine + * intel_gvt_switch_mmio - switch mmio context of specific engine * @pre: the last vGPU that own the engine * @next: the vGPU to switch to * @engine: the engine diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 46da19b3225d..56c71474008a 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -73,24 +73,21 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu) drm_WARN_ON(&i915->drm, sizeof(struct vgt_if) != VGT_PVINFO_SIZE); } +/* + * vGPU type name is defined as GVTg_Vx_y which contains the physical GPU + * generation type (e.g V4 as BDW server, V5 as SKL server). + * + * Depening on the physical SKU resource, we might see vGPU types like + * GVTg_V4_8, GVTg_V4_4, GVTg_V4_2, etc. We can create different types of + * vGPU on same physical GPU depending on available resource. Each vGPU + * type will have a different number of avail_instance to indicate how + * many vGPU instance can be created for this type. + */ #define VGPU_MAX_WEIGHT 16 #define VGPU_WEIGHT(vgpu_num) \ (VGPU_MAX_WEIGHT / (vgpu_num)) -static const struct { - unsigned int low_mm; - unsigned int high_mm; - unsigned int fence; - - /* A vGPU with a weight of 8 will get twice as much GPU as a vGPU - * with a weight of 4 on a contended host, different vGPU type has - * different weight set. Legal weights range from 1 to 16. - */ - unsigned int weight; - enum intel_vgpu_edid edid; - const char *name; -} vgpu_types[] = { -/* Fixed vGPU type table */ +static const struct intel_vgpu_config intel_vgpu_configs[] = { { MB_TO_BYTES(64), MB_TO_BYTES(384), 4, VGPU_WEIGHT(8), GVT_EDID_1024_768, "8" }, { MB_TO_BYTES(128), MB_TO_BYTES(512), 4, VGPU_WEIGHT(4), GVT_EDID_1920_1200, "4" }, { MB_TO_BYTES(256), MB_TO_BYTES(1024), 4, VGPU_WEIGHT(2), GVT_EDID_1920_1200, "2" }, @@ -106,102 +103,58 @@ static const struct { */ int intel_gvt_init_vgpu_types(struct intel_gvt *gvt) { - unsigned int num_types; - unsigned int i, low_avail, high_avail; - unsigned int min_low; - - /* vGPU type name is defined as GVTg_Vx_y which contains - * physical GPU generation type (e.g V4 as BDW server, V5 as - * SKL server). - * - * Depend on physical SKU resource, might see vGPU types like - * GVTg_V4_8, GVTg_V4_4, GVTg_V4_2, etc. We can create - * different types of vGPU on same physical GPU depending on - * available resource. Each vGPU type will have "avail_instance" - * to indicate how many vGPU instance can be created for this - * type. - * - */ - low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE; - high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE; - num_types = ARRAY_SIZE(vgpu_types); + unsigned int low_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE; + unsigned int high_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE; + unsigned int num_types = ARRAY_SIZE(intel_vgpu_configs); + unsigned int i; gvt->types = kcalloc(num_types, sizeof(struct intel_vgpu_type), GFP_KERNEL); if (!gvt->types) return -ENOMEM; - min_low = MB_TO_BYTES(32); - for (i = 0; i < num_types; ++i) { - if (low_avail / vgpu_types[i].low_mm == 0) - break; - - gvt->types[i].low_gm_size = vgpu_types[i].low_mm; - gvt->types[i].high_gm_size = vgpu_types[i].high_mm; - gvt->types[i].fence = vgpu_types[i].fence; + gvt->mdev_types = kcalloc(num_types, sizeof(*gvt->mdev_types), + GFP_KERNEL); + if (!gvt->mdev_types) + goto out_free_types; - if (vgpu_types[i].weight < 1 || - vgpu_types[i].weight > VGPU_MAX_WEIGHT) - return -EINVAL; + for (i = 0; i < num_types; ++i) { + const struct intel_vgpu_config *conf = &intel_vgpu_configs[i]; - gvt->types[i].weight = vgpu_types[i].weight; - gvt->types[i].resolution = vgpu_types[i].edid; - gvt->types[i].avail_instance = min(low_avail / vgpu_types[i].low_mm, - high_avail / vgpu_types[i].high_mm); + if (low_avail / conf->low_mm == 0) + break; + if (conf->weight < 1 || conf->weight > VGPU_MAX_WEIGHT) + goto out_free_mdev_types; - if (GRAPHICS_VER(gvt->gt->i915) == 8) - sprintf(gvt->types[i].name, "GVTg_V4_%s", - vgpu_types[i].name); - else if (GRAPHICS_VER(gvt->gt->i915) == 9) - sprintf(gvt->types[i].name, "GVTg_V5_%s", - vgpu_types[i].name); + sprintf(gvt->types[i].name, "GVTg_V%u_%s", + GRAPHICS_VER(gvt->gt->i915) == 8 ? 4 : 5, conf->name); + gvt->types[i].conf = conf; gvt_dbg_core("type[%d]: %s avail %u low %u high %u fence %u weight %u res %s\n", i, gvt->types[i].name, - gvt->types[i].avail_instance, - gvt->types[i].low_gm_size, - gvt->types[i].high_gm_size, gvt->types[i].fence, - gvt->types[i].weight, - vgpu_edid_str(gvt->types[i].resolution)); + min(low_avail / conf->low_mm, + high_avail / conf->high_mm), + conf->low_mm, conf->high_mm, conf->fence, + conf->weight, vgpu_edid_str(conf->edid)); + + gvt->mdev_types[i] = &gvt->types[i].type; + gvt->mdev_types[i]->sysfs_name = gvt->types[i].name; } gvt->num_types = i; return 0; -} -void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt) -{ +out_free_mdev_types: + kfree(gvt->mdev_types); +out_free_types: kfree(gvt->types); + return -EINVAL; } -static void intel_gvt_update_vgpu_types(struct intel_gvt *gvt) +void intel_gvt_clean_vgpu_types(struct intel_gvt *gvt) { - int i; - unsigned int low_gm_avail, high_gm_avail, fence_avail; - unsigned int low_gm_min, high_gm_min, fence_min; - - /* Need to depend on maxium hw resource size but keep on - * static config for now. - */ - low_gm_avail = gvt_aperture_sz(gvt) - HOST_LOW_GM_SIZE - - gvt->gm.vgpu_allocated_low_gm_size; - high_gm_avail = gvt_hidden_sz(gvt) - HOST_HIGH_GM_SIZE - - gvt->gm.vgpu_allocated_high_gm_size; - fence_avail = gvt_fence_sz(gvt) - HOST_FENCE - - gvt->fence.vgpu_allocated_fence_num; - - for (i = 0; i < gvt->num_types; i++) { - low_gm_min = low_gm_avail / gvt->types[i].low_gm_size; - high_gm_min = high_gm_avail / gvt->types[i].high_gm_size; - fence_min = fence_avail / gvt->types[i].fence; - gvt->types[i].avail_instance = min(min(low_gm_min, high_gm_min), - fence_min); - - gvt_dbg_core("update type[%d]: %s avail %u low %u high %u fence %u\n", - i, gvt->types[i].name, - gvt->types[i].avail_instance, gvt->types[i].low_gm_size, - gvt->types[i].high_gm_size, gvt->types[i].fence); - } + kfree(gvt->mdev_types); + kfree(gvt->types); } /** @@ -298,12 +251,6 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu) intel_vgpu_clean_mmio(vgpu); intel_vgpu_dmabuf_cleanup(vgpu); mutex_unlock(&vgpu->vgpu_lock); - - mutex_lock(&gvt->lock); - intel_gvt_update_vgpu_types(gvt); - mutex_unlock(&gvt->lock); - - vfree(vgpu); } #define IDLE_VGPU_IDR 0 @@ -363,42 +310,38 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu) vfree(vgpu); } -static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, - struct intel_vgpu_creation_params *param) +int intel_gvt_create_vgpu(struct intel_vgpu *vgpu, + const struct intel_vgpu_config *conf) { + struct intel_gvt *gvt = vgpu->gvt; struct drm_i915_private *dev_priv = gvt->gt->i915; - struct intel_vgpu *vgpu; int ret; - gvt_dbg_core("low %llu MB high %llu MB fence %llu\n", - param->low_gm_sz, param->high_gm_sz, - param->fence_sz); - - vgpu = vzalloc(sizeof(*vgpu)); - if (!vgpu) - return ERR_PTR(-ENOMEM); + gvt_dbg_core("low %u MB high %u MB fence %u\n", + BYTES_TO_MB(conf->low_mm), BYTES_TO_MB(conf->high_mm), + conf->fence); + mutex_lock(&gvt->lock); ret = idr_alloc(&gvt->vgpu_idr, vgpu, IDLE_VGPU_IDR + 1, GVT_MAX_VGPU, GFP_KERNEL); if (ret < 0) - goto out_free_vgpu; + goto out_unlock;; vgpu->id = ret; - vgpu->gvt = gvt; - vgpu->sched_ctl.weight = param->weight; + vgpu->sched_ctl.weight = conf->weight; mutex_init(&vgpu->vgpu_lock); mutex_init(&vgpu->dmabuf_lock); INIT_LIST_HEAD(&vgpu->dmabuf_obj_list_head); INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL); idr_init_base(&vgpu->object_idr, 1); - intel_vgpu_init_cfg_space(vgpu, param->primary); + intel_vgpu_init_cfg_space(vgpu, 1); vgpu->d3_entered = false; ret = intel_vgpu_init_mmio(vgpu); if (ret) goto out_clean_idr; - ret = intel_vgpu_alloc_resource(vgpu, param); + ret = intel_vgpu_alloc_resource(vgpu, conf); if (ret) goto out_clean_vgpu_mmio; @@ -412,7 +355,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_gtt; - ret = intel_vgpu_init_display(vgpu, param->resolution); + ret = intel_vgpu_init_display(vgpu, conf->edid); if (ret) goto out_clean_opregion; @@ -437,7 +380,9 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - return vgpu; + intel_gvt_update_reg_whitelist(vgpu); + mutex_unlock(&gvt->lock); + return 0; out_clean_sched_policy: intel_vgpu_clean_sched_policy(vgpu); @@ -455,48 +400,9 @@ out_clean_vgpu_mmio: intel_vgpu_clean_mmio(vgpu); out_clean_idr: idr_remove(&gvt->vgpu_idr, vgpu->id); -out_free_vgpu: - vfree(vgpu); - return ERR_PTR(ret); -} - -/** - * intel_gvt_create_vgpu - create a virtual GPU - * @gvt: GVT device - * @type: type of the vGPU to create - * - * This function is called when user wants to create a virtual GPU. - * - * Returns: - * pointer to intel_vgpu, error pointer if failed. - */ -struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt, - struct intel_vgpu_type *type) -{ - struct intel_vgpu_creation_params param; - struct intel_vgpu *vgpu; - - param.primary = 1; - param.low_gm_sz = type->low_gm_size; - param.high_gm_sz = type->high_gm_size; - param.fence_sz = type->fence; - param.weight = type->weight; - param.resolution = type->resolution; - - /* XXX current param based on MB */ - param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz); - param.high_gm_sz = BYTES_TO_MB(param.high_gm_sz); - - mutex_lock(&gvt->lock); - vgpu = __intel_gvt_create_vgpu(gvt, ¶m); - if (!IS_ERR(vgpu)) { - /* calculate left instance change for types */ - intel_gvt_update_vgpu_types(gvt); - intel_gvt_update_reg_whitelist(vgpu); - } +out_unlock: mutex_unlock(&gvt->lock); - - return vgpu; + return ret; } /** diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 3a8450058548..ae987e92251d 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -66,8 +66,7 @@ static int i915_capabilities(struct seq_file *m, void *data) seq_printf(m, "pch: %d\n", INTEL_PCH_TYPE(i915)); - intel_device_info_print_static(INTEL_INFO(i915), &p); - intel_device_info_print_runtime(RUNTIME_INFO(i915), &p); + intel_device_info_print(INTEL_INFO(i915), RUNTIME_INFO(i915), &p); i915_print_iommu_status(i915, &p); intel_gt_info_print(&to_gt(i915)->info, &p); intel_driver_caps_print(&i915->caps, &p); @@ -411,7 +410,7 @@ static int i915_swizzle_info(struct seq_file *m, void *data) seq_printf(m, "bit6 swizzle for Y-tiling = %s\n", swizzle_string(to_gt(dev_priv)->ggtt->bit_6_swizzle_y)); - if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES) + if (dev_priv->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) seq_puts(m, "L-shaped memory detected\n"); /* On BDW+, swizzling is not used. See detect_bit_6_swizzle() */ @@ -493,7 +492,7 @@ static int i915_runtime_pm_status(struct seq_file *m, void *unused) seq_puts(m, "Runtime power management not supported\n"); seq_printf(m, "Runtime power status: %s\n", - str_enabled_disabled(!dev_priv->power_domains.init_wakeref)); + str_enabled_disabled(!dev_priv->display.power.domains.init_wakeref)); seq_printf(m, "GPU idle: %s\n", str_yes_no(!to_gt(dev_priv)->awake)); seq_printf(m, "IRQs disabled: %s\n", diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c index deb8a8b76965..c459eb362c47 100644 --- a/drivers/gpu/drm/i915/i915_driver.c +++ b/drivers/gpu/drm/i915/i915_driver.c @@ -61,6 +61,7 @@ #include "display/intel_pps.h" #include "display/intel_sprite.h" #include "display/intel_vga.h" +#include "display/skl_watermark.h" #include "gem/i915_gem_context.h" #include "gem/i915_gem_create.h" @@ -105,6 +106,12 @@ static const char irst_name[] = "INT3392"; static const struct drm_driver i915_drm_driver; +static void i915_release_bridge_dev(struct drm_device *dev, + void *bridge) +{ + pci_dev_put(bridge); +} + static int i915_get_bridge_dev(struct drm_i915_private *dev_priv) { int domain = pci_domain_nr(to_pci_dev(dev_priv->drm.dev)->bus); @@ -115,7 +122,9 @@ static int i915_get_bridge_dev(struct drm_i915_private *dev_priv) drm_err(&dev_priv->drm, "bridge device not found\n"); return -EIO; } - return 0; + + return drmm_add_action_or_reset(&dev_priv->drm, i915_release_bridge_dev, + dev_priv->bridge_dev); } /* Allocate space for the MCH regs if needed, return nonzero on error */ @@ -252,8 +261,8 @@ static int i915_workqueues_init(struct drm_i915_private *dev_priv) if (dev_priv->wq == NULL) goto out_err; - dev_priv->hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0); - if (dev_priv->hotplug.dp_wq == NULL) + dev_priv->display.hotplug.dp_wq = alloc_ordered_workqueue("i915-dp", 0); + if (dev_priv->display.hotplug.dp_wq == NULL) goto out_free_wq; return 0; @@ -268,7 +277,7 @@ out_err: static void i915_workqueues_cleanup(struct drm_i915_private *dev_priv) { - destroy_workqueue(dev_priv->hotplug.dp_wq); + destroy_workqueue(dev_priv->display.hotplug.dp_wq); destroy_workqueue(dev_priv->wq); } @@ -302,8 +311,13 @@ static void intel_detect_preproduction_hw(struct drm_i915_private *dev_priv) static void sanitize_gpu(struct drm_i915_private *i915) { - if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) - __intel_gt_reset(to_gt(i915), ALL_ENGINES); + if (!INTEL_INFO(i915)->gpu_reset_clobbers_display) { + struct intel_gt *gt; + unsigned int i; + + for_each_gt(gt, i915, i) + __intel_gt_reset(gt, ALL_ENGINES); + } } /** @@ -326,19 +340,19 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) intel_device_info_subplatform_init(dev_priv); intel_step_init(dev_priv); - intel_uncore_mmio_debug_init_early(&dev_priv->mmio_debug); + intel_uncore_mmio_debug_init_early(dev_priv); spin_lock_init(&dev_priv->irq_lock); spin_lock_init(&dev_priv->gpu_error.lock); - mutex_init(&dev_priv->backlight_lock); + mutex_init(&dev_priv->display.backlight.lock); mutex_init(&dev_priv->sb_lock); cpu_latency_qos_add_request(&dev_priv->sb_qos, PM_QOS_DEFAULT_VALUE); - mutex_init(&dev_priv->audio.mutex); - mutex_init(&dev_priv->wm.wm_mutex); - mutex_init(&dev_priv->pps_mutex); - mutex_init(&dev_priv->hdcp_comp_mutex); + mutex_init(&dev_priv->display.audio.mutex); + mutex_init(&dev_priv->display.wm.wm_mutex); + mutex_init(&dev_priv->display.pps.mutex); + mutex_init(&dev_priv->display.hdcp.comp_mutex); i915_memcpy_init_early(dev_priv); intel_runtime_pm_init_early(&dev_priv->runtime_pm); @@ -357,7 +371,9 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv) intel_wopcm_init_early(&dev_priv->wopcm); - intel_root_gt_init_early(dev_priv); + ret = intel_root_gt_init_early(dev_priv); + if (ret < 0) + goto err_rootgt; i915_drm_clients_init(&dev_priv->clients, dev_priv); @@ -382,6 +398,7 @@ err_gem: i915_gem_cleanup_early(dev_priv); intel_gt_driver_late_release_all(dev_priv); i915_drm_clients_fini(&dev_priv->clients); +err_rootgt: intel_region_ttm_device_fini(dev_priv); err_ttm: vlv_suspend_cleanup(dev_priv); @@ -423,7 +440,8 @@ static void i915_driver_late_release(struct drm_i915_private *dev_priv) */ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) { - int ret; + struct intel_gt *gt; + int ret, i; if (i915_inject_probe_failure(dev_priv)) return -ENODEV; @@ -432,17 +450,27 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) if (ret < 0) return ret; - ret = intel_uncore_init_mmio(&dev_priv->uncore); - if (ret) - return ret; + for_each_gt(gt, dev_priv, i) { + ret = intel_uncore_init_mmio(gt->uncore); + if (ret) + return ret; + + ret = drmm_add_action_or_reset(&dev_priv->drm, + intel_uncore_fini_mmio, + gt->uncore); + if (ret) + return ret; + } /* Try to make sure MCHBAR is enabled before poking at it */ intel_setup_mchbar(dev_priv); intel_device_info_runtime_init(dev_priv); - ret = intel_gt_init_mmio(to_gt(dev_priv)); - if (ret) - goto err_uncore; + for_each_gt(gt, dev_priv, i) { + ret = intel_gt_init_mmio(gt); + if (ret) + goto err_uncore; + } /* As early as possible, scrub existing GPU state before clobbering */ sanitize_gpu(dev_priv); @@ -451,8 +479,6 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv) err_uncore: intel_teardown_mchbar(dev_priv); - intel_uncore_fini_mmio(&dev_priv->uncore); - pci_dev_put(dev_priv->bridge_dev); return ret; } @@ -464,8 +490,6 @@ err_uncore: static void i915_driver_mmio_release(struct drm_i915_private *dev_priv) { intel_teardown_mchbar(dev_priv); - intel_uncore_fini_mmio(&dev_priv->uncore); - pci_dev_put(dev_priv->bridge_dev); } /** @@ -715,6 +739,8 @@ static void i915_driver_hw_remove(struct drm_i915_private *dev_priv) static void i915_driver_register(struct drm_i915_private *dev_priv) { struct drm_device *dev = &dev_priv->drm; + struct intel_gt *gt; + unsigned int i; i915_gem_driver_register(dev_priv); i915_pmu_register(dev_priv); @@ -734,7 +760,8 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) /* Depends on sysfs having been initialized */ i915_perf_register(dev_priv); - intel_gt_driver_register(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) + intel_gt_driver_register(gt); intel_display_driver_register(dev_priv); @@ -753,6 +780,9 @@ static void i915_driver_register(struct drm_i915_private *dev_priv) */ static void i915_driver_unregister(struct drm_i915_private *dev_priv) { + struct intel_gt *gt; + unsigned int i; + i915_switcheroo_unregister(dev_priv); intel_unregister_dsm_handler(); @@ -762,7 +792,8 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv) intel_display_driver_unregister(dev_priv); - intel_gt_driver_unregister(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) + intel_gt_driver_unregister(gt); i915_perf_unregister(dev_priv); i915_pmu_unregister(dev_priv); @@ -784,6 +815,8 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv) { if (drm_debug_enabled(DRM_UT_DRIVER)) { struct drm_printer p = drm_debug_printer("i915 device info:"); + struct intel_gt *gt; + unsigned int i; drm_printf(&p, "pciid=0x%04x rev=0x%02x platform=%s (subplatform=0x%x) gen=%i\n", INTEL_DEVID(dev_priv), @@ -793,10 +826,11 @@ static void i915_welcome_messages(struct drm_i915_private *dev_priv) INTEL_INFO(dev_priv)->platform), GRAPHICS_VER(dev_priv)); - intel_device_info_print_static(INTEL_INFO(dev_priv), &p); - intel_device_info_print_runtime(RUNTIME_INFO(dev_priv), &p); + intel_device_info_print(INTEL_INFO(dev_priv), + RUNTIME_INFO(dev_priv), &p); i915_print_iommu_status(dev_priv, &p); - intel_gt_info_print(&to_gt(dev_priv)->info, &p); + for_each_gt(gt, dev_priv, i) + intel_gt_info_print(>->info, &p); } if (IS_ENABLED(CONFIG_DRM_I915_DEBUG)) @@ -814,6 +848,7 @@ i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent) const struct intel_device_info *match_info = (struct intel_device_info *)ent->driver_data; struct intel_device_info *device_info; + struct intel_runtime_info *runtime; struct drm_i915_private *i915; i915 = devm_drm_dev_alloc(&pdev->dev, &i915_drm_driver, @@ -829,7 +864,11 @@ i915_driver_create(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the write-once "constant" device info */ device_info = mkwrite_device_info(i915); memcpy(device_info, match_info, sizeof(*device_info)); - RUNTIME_INFO(i915)->device_id = pdev->device; + + /* Initialize initial runtime info from static const data and pdev. */ + runtime = RUNTIME_INFO(i915); + memcpy(runtime, &INTEL_INFO(i915)->__runtime, sizeof(*runtime)); + runtime->device_id = pdev->device; return i915; } @@ -948,7 +987,9 @@ out_fini: void i915_driver_remove(struct drm_i915_private *i915) { - disable_rpm_wakeref_asserts(&i915->runtime_pm); + intel_wakeref_t wakeref; + + wakeref = intel_runtime_pm_get(&i915->runtime_pm); i915_driver_unregister(i915); @@ -972,18 +1013,19 @@ void i915_driver_remove(struct drm_i915_private *i915) i915_driver_hw_remove(i915); - enable_rpm_wakeref_asserts(&i915->runtime_pm); + intel_runtime_pm_put(&i915->runtime_pm, wakeref); } static void i915_driver_release(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; + intel_wakeref_t wakeref; if (!dev_priv->do_release) return; - disable_rpm_wakeref_asserts(rpm); + wakeref = intel_runtime_pm_get(rpm); i915_gem_driver_release(dev_priv); @@ -994,7 +1036,8 @@ static void i915_driver_release(struct drm_device *dev) i915_driver_mmio_release(dev_priv); - enable_rpm_wakeref_asserts(rpm); + intel_runtime_pm_put(rpm, wakeref); + intel_runtime_pm_driver_release(rpm); i915_driver_late_release(dev_priv); @@ -1206,13 +1249,15 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation) struct drm_i915_private *dev_priv = to_i915(dev); struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; - int ret; + struct intel_gt *gt; + int ret, i; disable_rpm_wakeref_asserts(rpm); i915_gem_suspend_late(dev_priv); - intel_uncore_suspend(&dev_priv->uncore); + for_each_gt(gt, dev_priv, i) + intel_uncore_suspend(gt->uncore); intel_power_domains_suspend(dev_priv, get_suspend_mode(dev_priv, hibernation)); @@ -1344,7 +1389,8 @@ static int i915_drm_resume_early(struct drm_device *dev) { struct drm_i915_private *dev_priv = to_i915(dev); struct pci_dev *pdev = to_pci_dev(dev_priv->drm.dev); - int ret; + struct intel_gt *gt; + int ret, i; /* * We have a resume ordering issue with the snd-hda driver also @@ -1398,9 +1444,10 @@ static int i915_drm_resume_early(struct drm_device *dev) drm_err(&dev_priv->drm, "Resume prepare failed: %d, continuing anyway\n", ret); - intel_uncore_resume_early(&dev_priv->uncore); - - intel_gt_check_and_clear_faults(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) { + intel_uncore_resume_early(gt->uncore); + intel_gt_check_and_clear_faults(gt); + } intel_display_power_resume_early(dev_priv); @@ -1580,7 +1627,8 @@ static int intel_runtime_suspend(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; - int ret; + struct intel_gt *gt; + int ret, i; if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_RUNTIME_PM(dev_priv))) return -ENODEV; @@ -1595,11 +1643,13 @@ static int intel_runtime_suspend(struct device *kdev) */ i915_gem_runtime_suspend(dev_priv); - intel_gt_runtime_suspend(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) + intel_gt_runtime_suspend(gt); intel_runtime_pm_disable_interrupts(dev_priv); - intel_uncore_suspend(&dev_priv->uncore); + for_each_gt(gt, dev_priv, i) + intel_uncore_suspend(gt->uncore); intel_display_power_suspend(dev_priv); @@ -1663,7 +1713,8 @@ static int intel_runtime_resume(struct device *kdev) { struct drm_i915_private *dev_priv = kdev_to_i915(kdev); struct intel_runtime_pm *rpm = &dev_priv->runtime_pm; - int ret; + struct intel_gt *gt; + int ret, i; if (drm_WARN_ON_ONCE(&dev_priv->drm, !HAS_RUNTIME_PM(dev_priv))) return -ENODEV; @@ -1683,7 +1734,8 @@ static int intel_runtime_resume(struct device *kdev) ret = vlv_resume_prepare(dev_priv, true); - intel_uncore_runtime_resume(&dev_priv->uncore); + for_each_gt(gt, dev_priv, i) + intel_uncore_runtime_resume(gt->uncore); intel_runtime_pm_enable_interrupts(dev_priv); @@ -1691,7 +1743,8 @@ static int intel_runtime_resume(struct device *kdev) * No point of rolling back things in case of an error, as the best * we can do is to hope that things will still work (and disable RPM). */ - intel_gt_runtime_resume(to_gt(dev_priv)); + for_each_gt(gt, dev_priv, i) + intel_gt_runtime_resume(gt); /* * On VLV/CHV display interrupts are part of the display @@ -1703,7 +1756,7 @@ static int intel_runtime_resume(struct device *kdev) intel_hpd_poll_disable(dev_priv); } - intel_enable_ipc(dev_priv); + skl_watermark_ipc_update(dev_priv); enable_rpm_wakeref_asserts(rpm); diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 7c0a34a33fec..bdc81db76dbd 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -34,20 +34,10 @@ #include <linux/pm_qos.h> -#include <drm/drm_connector.h> #include <drm/ttm/ttm_device.h> -#include "display/intel_cdclk.h" #include "display/intel_display.h" -#include "display/intel_display_power.h" -#include "display/intel_dmc.h" -#include "display/intel_dpll_mgr.h" -#include "display/intel_dsb.h" -#include "display/intel_fbc.h" -#include "display/intel_frontbuffer.h" -#include "display/intel_global_state.h" -#include "display/intel_gmbus.h" -#include "display/intel_opregion.h" +#include "display/intel_display_core.h" #include "gem/i915_gem_context_types.h" #include "gem/i915_gem_lmem.h" @@ -70,80 +60,24 @@ #include "intel_device_info.h" #include "intel_memory_region.h" #include "intel_pch.h" -#include "intel_pm_types.h" #include "intel_runtime_pm.h" #include "intel_step.h" #include "intel_uncore.h" #include "intel_wopcm.h" -struct dpll; struct drm_i915_clock_gating_funcs; struct drm_i915_gem_object; struct drm_i915_private; -struct intel_atomic_state; -struct intel_audio_funcs; -struct intel_cdclk_config; -struct intel_cdclk_funcs; -struct intel_cdclk_state; -struct intel_cdclk_vals; -struct intel_color_funcs; struct intel_connector; -struct intel_crtc; struct intel_dp; -struct intel_dpll_funcs; struct intel_encoder; -struct intel_fbdev; -struct intel_fdi_funcs; -struct intel_gmbus; -struct intel_hotplug_funcs; -struct intel_initial_plane_config; struct intel_limit; -struct intel_overlay; struct intel_overlay_error_state; struct vlv_s0ix_state; /* Threshold == 5 for long IRQs, 50 for short */ #define HPD_STORM_DEFAULT_THRESHOLD 50 -struct i915_hotplug { - struct delayed_work hotplug_work; - - const u32 *hpd, *pch_hpd; - - struct { - unsigned long last_jiffies; - int count; - enum { - HPD_ENABLED = 0, - HPD_DISABLED = 1, - HPD_MARK_DISABLED = 2 - } state; - } stats[HPD_NUM_PINS]; - u32 event_bits; - u32 retry_bits; - struct delayed_work reenable_work; - - u32 long_port_mask; - u32 short_port_mask; - struct work_struct dig_port_work; - - struct work_struct poll_init_work; - bool poll_enabled; - - unsigned int hpd_storm_threshold; - /* Whether or not to count short HPD IRQs in HPD storms */ - u8 hpd_short_storm_enabled; - - /* - * if we get a HPD irq from DP and a HPD irq from non-DP - * the non-DP HPD could block the workqueue on a mode config - * mutex getting, that userspace may have taken. However - * userspace is waiting on the DP workqueue to run which is - * blocked behind the non-DP one. - */ - struct workqueue_struct *dp_wq; -}; - #define I915_GEM_GPU_DOMAINS \ (I915_GEM_DOMAIN_RENDER | \ I915_GEM_DOMAIN_SAMPLER | \ @@ -151,55 +85,9 @@ struct i915_hotplug { I915_GEM_DOMAIN_INSTRUCTION | \ I915_GEM_DOMAIN_VERTEX) -struct sdvo_device_mapping { - u8 initialized; - u8 dvo_port; - u8 slave_addr; - u8 dvo_wiring; - u8 i2c_pin; - u8 ddc_pin; -}; - -/* functions used for watermark calcs for display. */ -struct drm_i915_wm_disp_funcs { - /* update_wm is for legacy wm management */ - void (*update_wm)(struct drm_i915_private *dev_priv); - int (*compute_pipe_wm)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - int (*compute_intermediate_wm)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*initial_watermarks)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*atomic_update_watermarks)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*optimize_watermarks)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - int (*compute_global_watermarks)(struct intel_atomic_state *state); -}; - -struct drm_i915_display_funcs { - /* Returns the active state of the crtc, and if the crtc is active, - * fills out the pipe-config with the hw state. */ - bool (*get_pipe_config)(struct intel_crtc *, - struct intel_crtc_state *); - void (*get_initial_plane_config)(struct intel_crtc *, - struct intel_initial_plane_config *); - void (*crtc_enable)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*crtc_disable)(struct intel_atomic_state *state, - struct intel_crtc *crtc); - void (*commit_modeset_enables)(struct intel_atomic_state *state); -}; - #define I915_COLOR_UNEVICTABLE (-1) /* a non-vma sharing the address space */ -#define QUIRK_LVDS_SSC_DISABLE (1<<1) -#define QUIRK_INVERT_BRIGHTNESS (1<<2) -#define QUIRK_BACKLIGHT_PRESENT (1<<3) -#define QUIRK_PIN_SWIZZLED_PAGES (1<<5) -#define QUIRK_INCREASE_T12_DELAY (1<<6) -#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7) -#define QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK (1<<8) +#define GEM_QUIRK_PIN_SWIZZLED_PAGES BIT(0) struct i915_suspend_saved_registers { u32 saveDSPARB; @@ -289,51 +177,8 @@ i915_fence_timeout(const struct drm_i915_private *i915) return i915_fence_context_timeout(i915, U64_MAX); } -/* Amount of SAGV/QGV points, BSpec precisely defines this */ -#define I915_NUM_QGV_POINTS 8 - #define HAS_HW_SAGV_WM(i915) (DISPLAY_VER(i915) >= 13 && !IS_DGFX(i915)) -/* Amount of PSF GV points, BSpec precisely defines this */ -#define I915_NUM_PSF_GV_POINTS 3 - -struct intel_vbt_data { - /* bdb version */ - u16 version; - - /* Feature bits */ - unsigned int int_tv_support:1; - unsigned int int_crt_support:1; - unsigned int lvds_use_ssc:1; - unsigned int int_lvds_support:1; - unsigned int display_clock_mode:1; - unsigned int fdi_rx_polarity_inverted:1; - int lvds_ssc_freq; - enum drm_panel_orientation orientation; - - bool override_afc_startup; - u8 override_afc_startup_val; - - int crt_ddc_pin; - - struct list_head display_devices; - struct list_head bdb_blocks; - - struct intel_bios_encoder_data *ports[I915_MAX_PORTS]; /* Non-NULL if port present. */ - struct sdvo_device_mapping sdvo_mappings[2]; -}; - -struct i915_frontbuffer_tracking { - spinlock_t lock; - - /* - * Tracking bits for delayed frontbuffer flushing du to gpu activity or - * scheduled flips. - */ - unsigned busy_bits; - unsigned flip_bits; -}; - struct i915_virtual_gpu { struct mutex lock; /* serialises sending of g2v_notify command pkts */ bool active; @@ -348,32 +193,11 @@ struct i915_selftest_stash { struct ida mock_region_instances; }; -/* intel_audio.c private */ -struct intel_audio_private { - /* Display internal audio functions */ - const struct intel_audio_funcs *funcs; - - /* hda/i915 audio component */ - struct i915_audio_component *component; - bool component_registered; - /* mutex for audio/video sync */ - struct mutex mutex; - int power_refcount; - u32 freq_cntrl; - - /* Used to save the pipe-to-encoder mapping for audio */ - struct intel_encoder *encoder_map[I915_MAX_PIPES]; - - /* necessary resource sharing with HDMI LPE audio driver. */ - struct { - struct platform_device *platdev; - int irq; - } lpe; -}; - struct drm_i915_private { struct drm_device drm; + struct intel_display display; + /* FIXME: Device release actions should all be moved to drmm_ */ bool do_release; @@ -417,27 +241,6 @@ struct drm_i915_private { struct intel_wopcm wopcm; - struct intel_dmc dmc; - - struct intel_gmbus *gmbus[GMBUS_NUM_PINS]; - - /** gmbus_mutex protects against concurrent usage of the single hw gmbus - * controller on different i2c buses. */ - struct mutex gmbus_mutex; - - /** - * Base address of where the gmbus and gpio blocks are located (either - * on PCH or on SoC for platforms without PCH). - */ - u32 gpio_mmio_base; - - /* MMIO base address for MIPI regs */ - u32 mipi_mmio_base; - - u32 pps_mmio_base; - - wait_queue_head_t gmbus_wait_queue; - struct pci_dev *bridge_dev; struct rb_root uabi_engines; @@ -461,48 +264,15 @@ struct drm_i915_private { }; u32 pipestat_irq_mask[I915_MAX_PIPES]; - struct i915_hotplug hotplug; - struct intel_fbc *fbc[I915_MAX_FBCS]; - struct intel_opregion opregion; - struct intel_vbt_data vbt; - bool preserve_bios_swizzle; - /* overlay */ - struct intel_overlay *overlay; - - /* backlight registers and fields in struct intel_panel */ - struct mutex backlight_lock; - - /* protects panel power sequencer state */ - struct mutex pps_mutex; - unsigned int fsb_freq, mem_freq, is_ddr3; unsigned int skl_preferred_vco_freq; - unsigned int max_cdclk_freq; unsigned int max_dotclk_freq; unsigned int hpll_freq; - unsigned int fdi_pll_freq; unsigned int czclk_freq; - struct { - /* The current hardware cdclk configuration */ - struct intel_cdclk_config hw; - - /* cdclk, divider, and ratio table from bspec */ - const struct intel_cdclk_vals *table; - - struct intel_global_obj obj; - } cdclk; - - struct { - /* The current hardware dbuf configuration */ - u8 enabled_slices; - - struct intel_global_obj obj; - } dbuf; - /** * wq - Driver workqueue for GEM. * @@ -512,40 +282,14 @@ struct drm_i915_private { */ struct workqueue_struct *wq; - /* ordered wq for modesets */ - struct workqueue_struct *modeset_wq; - /* unbound hipri wq for page flips/plane updates */ - struct workqueue_struct *flip_wq; - /* pm private clock gating functions */ const struct drm_i915_clock_gating_funcs *clock_gating_funcs; - /* pm display functions */ - const struct drm_i915_wm_disp_funcs *wm_disp; - - /* irq display functions */ - const struct intel_hotplug_funcs *hotplug_funcs; - - /* fdi display functions */ - const struct intel_fdi_funcs *fdi_funcs; - - /* display pll funcs */ - const struct intel_dpll_funcs *dpll_funcs; - - /* Display functions */ - const struct drm_i915_display_funcs *display; - - /* Display internal color functions */ - const struct intel_color_funcs *color_funcs; - - /* Display CDCLK functions */ - const struct intel_cdclk_funcs *cdclk_funcs; - /* PCH chipset type */ enum intel_pch pch_type; unsigned short pch_id; - unsigned long quirks; + unsigned long gem_quirks; struct drm_atomic_state *modeset_restore_state; struct drm_modeset_acquire_ctx reset_ctx; @@ -554,34 +298,8 @@ struct drm_i915_private { /* Kernel Modesetting */ - /** - * dpll and cdclk state is protected by connection_mutex - * dpll.lock serializes intel_{prepare,enable,disable}_shared_dpll. - * Must be global rather than per dpll, because on some platforms plls - * share registers. - */ - struct { - struct mutex lock; - - int num_shared_dpll; - struct intel_shared_dpll shared_dplls[I915_NUM_PLLS]; - const struct intel_dpll_mgr *mgr; - - struct { - int nssc; - int ssc; - } ref_clks; - } dpll; - struct list_head global_obj_list; - struct i915_frontbuffer_tracking fb_tracking; - - struct intel_atomic_helper { - struct llist_head free_list; - struct work_struct free_work; - } atomic_helper; - bool mchbar_need_disable; struct intel_l3_parity l3_parity; @@ -600,21 +318,8 @@ struct drm_i915_private { */ u32 edram_size_mb; - struct i915_power_domains power_domains; - struct i915_gpu_error gpu_error; - /* list of fbdev register on this device */ - struct intel_fbdev *fbdev; - struct work_struct fbdev_suspend_work; - - struct drm_property *broadcast_rgb_property; - struct drm_property *force_audio_property; - - u32 fdi_rx_config; - - /* Shadow for DISPLAY_PHY_CONTROL which can't be safely read */ - u32 chv_phy_control; /* * Shadows for CHV DPLL_MD regs to keep the state * checker somewhat working in the presence hardware @@ -627,51 +332,6 @@ struct drm_i915_private { struct i915_suspend_saved_registers regfile; struct vlv_s0ix_state *vlv_s0ix_state; - enum { - I915_SAGV_UNKNOWN = 0, - I915_SAGV_DISABLED, - I915_SAGV_ENABLED, - I915_SAGV_NOT_CONTROLLED - } sagv_status; - - u32 sagv_block_time_us; - - struct { - /* - * Raw watermark latency values: - * in 0.1us units for WM0, - * in 0.5us units for WM1+. - */ - /* primary */ - u16 pri_latency[5]; - /* sprite */ - u16 spr_latency[5]; - /* cursor */ - u16 cur_latency[5]; - /* - * Raw watermark memory latency values - * for SKL for all 8 levels - * in 1us units. - */ - u16 skl_latency[8]; - - /* current hardware state */ - union { - struct ilk_wm_values hw; - struct vlv_wm_values vlv; - struct g4x_wm_values g4x; - }; - - u8 max_level; - - /* - * Should be held around atomic WM register writing; also - * protects * intel_crtc->wm.active and - * crtc_state->wm.need_postvbl_update. - */ - struct mutex wm_mutex; - } wm; - struct dram_info { bool wm_lv_0_adjust_needed; u8 num_channels; @@ -689,18 +349,6 @@ struct drm_i915_private { u8 num_psf_gv_points; } dram_info; - struct intel_bw_info { - /* for each QGV point */ - unsigned int deratedbw[I915_NUM_QGV_POINTS]; - /* for each PSF GV point */ - unsigned int psf_bw[I915_NUM_PSF_GV_POINTS]; - u8 num_qgv_points; - u8 num_psf_gv_points; - u8 num_planes; - } max_bw[6]; - - struct intel_global_obj bw_obj; - struct intel_runtime_pm runtime_pm; struct i915_perf perf; @@ -716,6 +364,9 @@ struct drm_i915_private { struct kobject *sysfs_gt; + /* Quick lookup of media GT (current platforms only have one) */ + struct intel_gt *media_gt; + struct { struct i915_gem_contexts { spinlock_t lock; /* locks list */ @@ -733,9 +384,6 @@ struct drm_i915_private { struct file *mmap_singleton; } gem; - /* Window2 specifies time required to program DSB (Window2) in number of scan lines */ - u8 window2_delay; - u8 pch_ssc_use; /* For i915gm/i945gm vblank irq workaround */ @@ -743,31 +391,16 @@ struct drm_i915_private { bool irq_enabled; - union { - /* perform PHY state sanity checks? */ - bool chv_phy_assert[2]; - - /* - * DG2: Mask of PHYs that were not calibrated by the firmware - * and should not be used. - */ - u8 snps_phy_failed_calibration; - }; - - bool ipc_enabled; - - struct intel_audio_private audio; + /* + * DG2: Mask of PHYs that were not calibrated by the firmware + * and should not be used. + */ + u8 snps_phy_failed_calibration; struct i915_pmu pmu; struct i915_drm_clients clients; - struct i915_hdcp_comp_master *hdcp_master; - bool hdcp_comp_added; - - /* Mutex to protect the above hdcp component related values. */ - struct mutex hdcp_comp_mutex; - /* The TTM device structure. */ struct ttm_device bdev; @@ -826,28 +459,6 @@ static inline struct intel_gt *to_gt(struct drm_i915_private *i915) (engine__) && (engine__)->uabi_class == (class__); \ (engine__) = rb_to_uabi_engine(rb_next(&(engine__)->uabi_node))) -#define I915_GTT_OFFSET_NONE ((u32)-1) - -/* - * Frontbuffer tracking bits. Set in obj->frontbuffer_bits while a gem bo is - * considered to be the frontbuffer for the given plane interface-wise. This - * doesn't mean that the hw necessarily already scans it out, but that any - * rendering (by the cpu or gpu) will land in the frontbuffer eventually. - * - * We have one bit per pipe and per scanout plane type. - */ -#define INTEL_FRONTBUFFER_BITS_PER_PIPE 8 -#define INTEL_FRONTBUFFER(pipe, plane_id) ({ \ - BUILD_BUG_ON(INTEL_FRONTBUFFER_BITS_PER_PIPE * I915_MAX_PIPES > 32); \ - BUILD_BUG_ON(I915_MAX_PLANES > INTEL_FRONTBUFFER_BITS_PER_PIPE); \ - BIT((plane_id) + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)); \ -}) -#define INTEL_FRONTBUFFER_OVERLAY(pipe) \ - BIT(INTEL_FRONTBUFFER_BITS_PER_PIPE - 1 + INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)) -#define INTEL_FRONTBUFFER_ALL_MASK(pipe) \ - GENMASK(INTEL_FRONTBUFFER_BITS_PER_PIPE * ((pipe) + 1) - 1, \ - INTEL_FRONTBUFFER_BITS_PER_PIPE * (pipe)) - #define INTEL_INFO(dev_priv) (&(dev_priv)->__info) #define RUNTIME_INFO(dev_priv) (&(dev_priv)->__runtime) #define DRIVER_CAPS(dev_priv) (&(dev_priv)->caps) @@ -856,19 +467,19 @@ static inline struct intel_gt *to_gt(struct drm_i915_private *i915) #define IP_VER(ver, rel) ((ver) << 8 | (rel)) -#define GRAPHICS_VER(i915) (INTEL_INFO(i915)->graphics.ver) -#define GRAPHICS_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->graphics.ver, \ - INTEL_INFO(i915)->graphics.rel) +#define GRAPHICS_VER(i915) (RUNTIME_INFO(i915)->graphics.ip.ver) +#define GRAPHICS_VER_FULL(i915) IP_VER(RUNTIME_INFO(i915)->graphics.ip.ver, \ + RUNTIME_INFO(i915)->graphics.ip.rel) #define IS_GRAPHICS_VER(i915, from, until) \ (GRAPHICS_VER(i915) >= (from) && GRAPHICS_VER(i915) <= (until)) -#define MEDIA_VER(i915) (INTEL_INFO(i915)->media.ver) -#define MEDIA_VER_FULL(i915) IP_VER(INTEL_INFO(i915)->media.ver, \ - INTEL_INFO(i915)->media.rel) +#define MEDIA_VER(i915) (RUNTIME_INFO(i915)->media.ip.ver) +#define MEDIA_VER_FULL(i915) IP_VER(RUNTIME_INFO(i915)->media.ip.ver, \ + RUNTIME_INFO(i915)->media.ip.rel) #define IS_MEDIA_VER(i915, from, until) \ (MEDIA_VER(i915) >= (from) && MEDIA_VER(i915) <= (until)) -#define DISPLAY_VER(i915) (INTEL_INFO(i915)->display.ver) +#define DISPLAY_VER(i915) (RUNTIME_INFO(i915)->display.ip.ver) #define IS_DISPLAY_VER(i915, from, until) \ (DISPLAY_VER(i915) >= (from) && DISPLAY_VER(i915) <= (until)) @@ -1210,7 +821,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_EXECLISTS(dev_priv) HAS_LOGICAL_RING_CONTEXTS(dev_priv) -#define INTEL_PPGTT(dev_priv) (INTEL_INFO(dev_priv)->ppgtt_type) +#define INTEL_PPGTT(dev_priv) (RUNTIME_INFO(dev_priv)->ppgtt_type) #define HAS_PPGTT(dev_priv) \ (INTEL_PPGTT(dev_priv) != INTEL_PPGTT_NONE) #define HAS_FULL_PPGTT(dev_priv) \ @@ -1218,7 +829,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_PAGE_SIZES(dev_priv, sizes) ({ \ GEM_BUG_ON((sizes) == 0); \ - ((sizes) & ~INTEL_INFO(dev_priv)->page_sizes) == 0; \ + ((sizes) & ~RUNTIME_INFO(dev_priv)->page_sizes) == 0; \ }) #define HAS_OVERLAY(dev_priv) (INTEL_INFO(dev_priv)->display.has_overlay) @@ -1249,13 +860,15 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define I915_HAS_HOTPLUG(dev_priv) (INTEL_INFO(dev_priv)->display.has_hotplug) #define HAS_FW_BLC(dev_priv) (DISPLAY_VER(dev_priv) > 2) -#define HAS_FBC(dev_priv) (INTEL_INFO(dev_priv)->display.fbc_mask != 0) +#define HAS_FBC(dev_priv) (RUNTIME_INFO(dev_priv)->fbc_mask != 0) #define HAS_CUR_FBC(dev_priv) (!HAS_GMCH(dev_priv) && DISPLAY_VER(dev_priv) >= 7) #define HAS_IPS(dev_priv) (IS_HSW_ULT(dev_priv) || IS_BROADWELL(dev_priv)) #define HAS_DP_MST(dev_priv) (INTEL_INFO(dev_priv)->display.has_dp_mst) -#define HAS_DP20(dev_priv) (IS_DG2(dev_priv)) +#define HAS_DP20(dev_priv) (IS_DG2(dev_priv) || DISPLAY_VER(dev_priv) >= 14) + +#define HAS_DOUBLE_BUFFERED_M_N(dev_priv) (DISPLAY_VER(dev_priv) >= 9 || IS_BROADWELL(dev_priv)) #define HAS_CDCLK_CRAWL(dev_priv) (INTEL_INFO(dev_priv)->display.has_cdclk_crawl) #define HAS_DDI(dev_priv) (INTEL_INFO(dev_priv)->display.has_ddi) @@ -1264,7 +877,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_PSR_HW_TRACKING(dev_priv) \ (INTEL_INFO(dev_priv)->display.has_psr_hw_tracking) #define HAS_PSR2_SEL_FETCH(dev_priv) (DISPLAY_VER(dev_priv) >= 12) -#define HAS_TRANSCODER(dev_priv, trans) ((INTEL_INFO(dev_priv)->display.cpu_transcoder_mask & BIT(trans)) != 0) +#define HAS_TRANSCODER(dev_priv, trans) ((RUNTIME_INFO(dev_priv)->cpu_transcoder_mask & BIT(trans)) != 0) #define HAS_RC6(dev_priv) (INTEL_INFO(dev_priv)->has_rc6) #define HAS_RC6p(dev_priv) (INTEL_INFO(dev_priv)->has_rc6p) @@ -1272,7 +885,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_RPS(dev_priv) (INTEL_INFO(dev_priv)->has_rps) -#define HAS_DMC(dev_priv) (INTEL_INFO(dev_priv)->display.has_dmc) +#define HAS_DMC(dev_priv) (RUNTIME_INFO(dev_priv)->has_dmc) #define HAS_HECI_PXP(dev_priv) \ (INTEL_INFO(dev_priv)->has_heci_pxp) @@ -1302,9 +915,11 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_IPC(dev_priv) (INTEL_INFO(dev_priv)->display.has_ipc) -#define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i)) +#define HAS_REGION(i915, i) (RUNTIME_INFO(i915)->memory_regions & (i)) #define HAS_LMEM(i915) HAS_REGION(i915, REGION_LMEM) +#define HAS_EXTRA_GT_LIST(dev_priv) (INTEL_INFO(dev_priv)->extra_gt_list) + /* * Platform has the dedicated compression control state for each lmem surfaces * stored in lmem to support the 3D and media compression formats. @@ -1313,7 +928,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_GT_UC(dev_priv) (INTEL_INFO(dev_priv)->has_gt_uc) -#define HAS_POOLED_EU(dev_priv) (INTEL_INFO(dev_priv)->has_pooled_eu) +#define HAS_POOLED_EU(dev_priv) (RUNTIME_INFO(dev_priv)->has_pooled_eu) #define HAS_GLOBAL_MOCS_REGISTERS(dev_priv) (INTEL_INFO(dev_priv)->has_global_mocs) @@ -1335,9 +950,9 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define GT_FREQUENCY_MULTIPLIER 50 #define GEN9_FREQ_SCALER 3 -#define INTEL_NUM_PIPES(dev_priv) (hweight8(INTEL_INFO(dev_priv)->display.pipe_mask)) +#define INTEL_NUM_PIPES(dev_priv) (hweight8(RUNTIME_INFO(dev_priv)->pipe_mask)) -#define HAS_DISPLAY(dev_priv) (INTEL_INFO(dev_priv)->display.pipe_mask != 0) +#define HAS_DISPLAY(dev_priv) (RUNTIME_INFO(dev_priv)->pipe_mask != 0) #define HAS_VRR(i915) (DISPLAY_VER(i915) >= 11) @@ -1355,85 +970,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915, #define HAS_D12_PLANE_MINIMIZATION(dev_priv) (IS_ROCKETLAKE(dev_priv) || \ IS_ALDERLAKE_S(dev_priv)) -#define HAS_MBUS_JOINING(i915) (IS_ALDERLAKE_P(i915)) +#define HAS_MBUS_JOINING(i915) (IS_ALDERLAKE_P(i915) || DISPLAY_VER(i915) >= 14) #define HAS_3D_PIPELINE(i915) (INTEL_INFO(i915)->has_3d_pipeline) #define HAS_ONE_EU_PER_FUSE_BIT(i915) (INTEL_INFO(i915)->has_one_eu_per_fuse_bit) -/* i915_gem.c */ -void i915_gem_init_early(struct drm_i915_private *dev_priv); -void i915_gem_cleanup_early(struct drm_i915_private *dev_priv); - -static inline void i915_gem_drain_freed_objects(struct drm_i915_private *i915) -{ - /* - * A single pass should suffice to release all the freed objects (along - * most call paths) , but be a little more paranoid in that freeing - * the objects does take a little amount of time, during which the rcu - * callbacks could have added new objects into the freed list, and - * armed the work again. - */ - while (atomic_read(&i915->mm.free_count)) { - flush_work(&i915->mm.free_work); - flush_delayed_work(&i915->bdev.wq); - rcu_barrier(); - } -} - -static inline void i915_gem_drain_workqueue(struct drm_i915_private *i915) -{ - /* - * Similar to objects above (see i915_gem_drain_freed-objects), in - * general we have workers that are armed by RCU and then rearm - * themselves in their callbacks. To be paranoid, we need to - * drain the workqueue a second time after waiting for the RCU - * grace period so that we catch work queued via RCU from the first - * pass. As neither drain_workqueue() nor flush_workqueue() report - * a result, we make an assumption that we only don't require more - * than 3 passes to catch all _recursive_ RCU delayed work. - * - */ - int pass = 3; - do { - flush_workqueue(i915->wq); - rcu_barrier(); - i915_gem_drain_freed_objects(i915); - } while (--pass); - drain_workqueue(i915->wq); -} - -struct i915_vma * __must_check -i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj, - struct i915_gem_ww_ctx *ww, - const struct i915_gtt_view *view, - u64 size, u64 alignment, u64 flags); - -struct i915_vma * __must_check -i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, - const struct i915_gtt_view *view, - u64 size, u64 alignment, u64 flags); - -int i915_gem_object_unbind(struct drm_i915_gem_object *obj, - unsigned long flags); -#define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0) -#define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1) -#define I915_GEM_OBJECT_UNBIND_TEST BIT(2) -#define I915_GEM_OBJECT_UNBIND_VM_TRYLOCK BIT(3) -#define I915_GEM_OBJECT_UNBIND_ASYNC BIT(4) - -void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv); - -int __must_check i915_gem_set_global_seqno(struct drm_device *dev, u32 seqno); - -int __must_check i915_gem_init(struct drm_i915_private *dev_priv); -void i915_gem_driver_register(struct drm_i915_private *i915); -void i915_gem_driver_unregister(struct drm_i915_private *i915); -void i915_gem_driver_remove(struct drm_i915_private *dev_priv); -void i915_gem_driver_release(struct drm_i915_private *dev_priv); - -int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file); - /* intel_device_info.c */ static inline struct intel_device_info * mkwrite_device_info(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index a3373699835d..2bdddb61ebd7 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -842,6 +842,10 @@ void i915_gem_runtime_suspend(struct drm_i915_private *i915) &to_gt(i915)->ggtt->userfault_list, userfault_link) __i915_gem_object_release_mmap_gtt(obj); + list_for_each_entry_safe(obj, on, + &to_gt(i915)->lmem_userfault_list, userfault_link) + i915_gem_object_runtime_pm_release_mmap_offset(obj); + /* * The fence will be lost when the device powers down. If any were * in use by hardware (i.e. they are pinned), we should not be powering @@ -1035,7 +1039,7 @@ i915_gem_madvise_ioctl(struct drm_device *dev, void *data, if (i915_gem_object_has_pages(obj) && i915_gem_object_is_tiled(obj) && - i915->quirks & QUIRK_PIN_SWIZZLED_PAGES) { + i915->gem_quirks & GEM_QUIRK_PIN_SWIZZLED_PAGES) { if (obj->mm.madv == I915_MADV_WILLNEED) { GEM_BUG_ON(!i915_gem_object_has_tiling_quirk(obj)); i915_gem_object_clear_tiling_quirk(obj); @@ -1085,14 +1089,50 @@ out: return err; } +/* + * A single pass should suffice to release all the freed objects (along most + * call paths), but be a little more paranoid in that freeing the objects does + * take a little amount of time, during which the rcu callbacks could have added + * new objects into the freed list, and armed the work again. + */ +void i915_gem_drain_freed_objects(struct drm_i915_private *i915) +{ + while (atomic_read(&i915->mm.free_count)) { + flush_work(&i915->mm.free_work); + flush_delayed_work(&i915->bdev.wq); + rcu_barrier(); + } +} + +/* + * Similar to objects above (see i915_gem_drain_freed-objects), in general we + * have workers that are armed by RCU and then rearm themselves in their + * callbacks. To be paranoid, we need to drain the workqueue a second time after + * waiting for the RCU grace period so that we catch work queued via RCU from + * the first pass. As neither drain_workqueue() nor flush_workqueue() report a + * result, we make an assumption that we only don't require more than 3 passes + * to catch all _recursive_ RCU delayed work. + */ +void i915_gem_drain_workqueue(struct drm_i915_private *i915) +{ + int i; + + for (i = 0; i < 3; i++) { + flush_workqueue(i915->wq); + rcu_barrier(); + i915_gem_drain_freed_objects(i915); + } + + drain_workqueue(i915->wq); +} + int i915_gem_init(struct drm_i915_private *dev_priv) { int ret; /* We need to fallback to 4K pages if host doesn't support huge gtt. */ if (intel_vgpu_active(dev_priv) && !intel_vgpu_has_huge_gtt(dev_priv)) - mkwrite_device_info(dev_priv)->page_sizes = - I915_GTT_PAGE_SIZE_4K; + RUNTIME_INFO(dev_priv)->page_sizes = I915_GTT_PAGE_SIZE_4K; ret = i915_gem_init_userptr(dev_priv); if (ret) @@ -1173,7 +1213,7 @@ void i915_gem_driver_unregister(struct drm_i915_private *i915) void i915_gem_driver_remove(struct drm_i915_private *dev_priv) { - intel_wakeref_auto_fini(&to_gt(dev_priv)->ggtt->userfault_wakeref); + intel_wakeref_auto_fini(&to_gt(dev_priv)->userfault_wakeref); i915_gem_suspend_late(dev_priv); intel_gt_driver_remove(to_gt(dev_priv)); @@ -1191,7 +1231,8 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv) intel_uc_cleanup_firmwares(&to_gt(dev_priv)->uc); - i915_gem_drain_freed_objects(dev_priv); + /* Flush any outstanding work, including i915_gem_context.release_work. */ + i915_gem_drain_workqueue(dev_priv); drm_WARN_ON(&dev_priv->drm, !list_empty(&dev_priv->gem.contexts.list)); } @@ -1213,7 +1254,7 @@ void i915_gem_init_early(struct drm_i915_private *dev_priv) i915_gem_init__mm(dev_priv); i915_gem_init__contexts(dev_priv); - spin_lock_init(&dev_priv->fb_tracking.lock); + spin_lock_init(&dev_priv->display.fb_tracking.lock); } void i915_gem_cleanup_early(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h index 68d8d52bd541..a5cdf6662d01 100644 --- a/drivers/gpu/drm/i915/i915_gem.h +++ b/drivers/gpu/drm/i915/i915_gem.h @@ -26,12 +26,55 @@ #define __I915_GEM_H__ #include <linux/bug.h> +#include <linux/types.h> #include <drm/drm_drv.h> #include "i915_utils.h" +struct drm_file; +struct drm_i915_gem_object; struct drm_i915_private; +struct i915_gem_ww_ctx; +struct i915_gtt_view; +struct i915_vma; + +void i915_gem_init_early(struct drm_i915_private *i915); +void i915_gem_cleanup_early(struct drm_i915_private *i915); + +void i915_gem_drain_freed_objects(struct drm_i915_private *i915); +void i915_gem_drain_workqueue(struct drm_i915_private *i915); + +struct i915_vma * __must_check +i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj, + struct i915_gem_ww_ctx *ww, + const struct i915_gtt_view *view, + u64 size, u64 alignment, u64 flags); + +struct i915_vma * __must_check +i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj, + const struct i915_gtt_view *view, + u64 size, u64 alignment, u64 flags); + +int i915_gem_object_unbind(struct drm_i915_gem_object *obj, + unsigned long flags); +#define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0) +#define I915_GEM_OBJECT_UNBIND_BARRIER BIT(1) +#define I915_GEM_OBJECT_UNBIND_TEST BIT(2) +#define I915_GEM_OBJECT_UNBIND_VM_TRYLOCK BIT(3) +#define I915_GEM_OBJECT_UNBIND_ASYNC BIT(4) + +void i915_gem_runtime_suspend(struct drm_i915_private *i915); + +int __must_check i915_gem_init(struct drm_i915_private *i915); +void i915_gem_driver_register(struct drm_i915_private *i915); +void i915_gem_driver_unregister(struct drm_i915_private *i915); +void i915_gem_driver_remove(struct drm_i915_private *i915); +void i915_gem_driver_release(struct drm_i915_private *i915); + +int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file); + +/* FIXME: All of the below belong somewhere else. */ #ifdef CONFIG_DRM_I915_DEBUG_GEM diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c index 329ff75b80b9..7bd1861ddbdf 100644 --- a/drivers/gpu/drm/i915/i915_gem_gtt.c +++ b/drivers/gpu/drm/i915/i915_gem_gtt.c @@ -137,12 +137,12 @@ static u64 random_offset(u64 start, u64 end, u64 len, u64 align) range = round_down(end - len, align) - round_up(start, align); if (range) { if (sizeof(unsigned long) == sizeof(u64)) { - addr = get_random_long(); + addr = get_random_u64(); } else { - addr = get_random_int(); + addr = get_random_u32(); if (range > U32_MAX) { addr <<= 32; - addr |= get_random_int(); + addr |= get_random_u32(); } } div64_u64_rem(addr, range, &addr); diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c index 6fd15b39570c..342c8ca6414e 100644 --- a/drivers/gpu/drm/i915/i915_getparam.c +++ b/drivers/gpu/drm/i915/i915_getparam.c @@ -36,7 +36,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data, value = to_gt(i915)->ggtt->num_fences; break; case I915_PARAM_HAS_OVERLAY: - value = !!i915->overlay; + value = !!i915->display.overlay; break; case I915_PARAM_HAS_BSD: value = !!intel_engine_lookup_user(i915, diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 16d8b7ba65dc..9ea2fe34e7d3 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -646,8 +646,7 @@ static void err_print_capabilities(struct drm_i915_error_state_buf *m, { struct drm_printer p = i915_error_printer(m); - intel_device_info_print_static(&error->device_info, &p); - intel_device_info_print_runtime(&error->runtime_info, &p); + intel_device_info_print(&error->device_info, &error->runtime_info, &p); intel_driver_caps_print(&error->driver_caps, &p); } diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c index 783a6ca41a61..86a42d9e8041 100644 --- a/drivers/gpu/drm/i915/i915_irq.c +++ b/drivers/gpu/drm/i915/i915_irq.c @@ -185,7 +185,7 @@ static const u32 hpd_sde_dg1[HPD_NUM_PINS] = { static void intel_hpd_init_pins(struct drm_i915_private *dev_priv) { - struct i915_hotplug *hpd = &dev_priv->hotplug; + struct intel_hotplug *hpd = &dev_priv->display.hotplug; if (HAS_GMCH(dev_priv)) { if (IS_G4X(dev_priv) || IS_VALLEYVIEW(dev_priv) || @@ -595,7 +595,7 @@ void i915_disable_pipestat(struct drm_i915_private *dev_priv, static bool i915_has_asle(struct drm_i915_private *dev_priv) { - if (!dev_priv->opregion.asle) + if (!dev_priv->display.opregion.asle) return false; return IS_PINEVIEW(dev_priv) || IS_MOBILE(dev_priv); @@ -1104,9 +1104,9 @@ static void ivb_parity_work(struct work_struct *work) out: drm_WARN_ON(&dev_priv->drm, dev_priv->l3_parity.which_slice); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen5_gt_enable_irq(gt, GT_PARITY_ERROR(dev_priv)); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); mutex_unlock(&dev_priv->drm.struct_mutex); } @@ -1272,7 +1272,7 @@ static u32 intel_hpd_enabled_irqs(struct drm_i915_private *dev_priv, u32 enabled_irqs = 0; for_each_intel_encoder(&dev_priv->drm, encoder) - if (dev_priv->hotplug.stats[encoder->hpd_pin].state == HPD_ENABLED) + if (dev_priv->display.hotplug.stats[encoder->hpd_pin].state == HPD_ENABLED) enabled_irqs |= hpd[encoder->hpd_pin]; return enabled_irqs; @@ -1304,12 +1304,12 @@ static u32 intel_hpd_hotplug_enables(struct drm_i915_private *i915, static void gmbus_irq_handler(struct drm_i915_private *dev_priv) { - wake_up_all(&dev_priv->gmbus_wait_queue); + wake_up_all(&dev_priv->display.gmbus.wait_queue); } static void dp_aux_irq_handler(struct drm_i915_private *dev_priv) { - wake_up_all(&dev_priv->gmbus_wait_queue); + wake_up_all(&dev_priv->display.gmbus.wait_queue); } #if defined(CONFIG_DEBUG_FS) @@ -1637,7 +1637,7 @@ static void i9xx_hpd_irq_handler(struct drm_i915_private *dev_priv, if (hotplug_trigger) { intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, hotplug_trigger, - dev_priv->hotplug.hpd, + dev_priv->display.hotplug.hpd, i9xx_port_hotplug_long_detect); intel_hpd_irq_handler(dev_priv, pin_mask, long_mask); @@ -1841,7 +1841,7 @@ static void ibx_hpd_irq_handler(struct drm_i915_private *dev_priv, intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, - dev_priv->hotplug.pch_hpd, + dev_priv->display.hotplug.pch_hpd, pch_port_hotplug_long_detect); intel_hpd_irq_handler(dev_priv, pin_mask, long_mask); @@ -1986,7 +1986,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, ddi_hotplug_trigger, dig_hotplug_reg, - dev_priv->hotplug.pch_hpd, + dev_priv->display.hotplug.pch_hpd, icp_ddi_port_hotplug_long_detect); } @@ -1998,7 +1998,7 @@ static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, tc_hotplug_trigger, dig_hotplug_reg, - dev_priv->hotplug.pch_hpd, + dev_priv->display.hotplug.pch_hpd, icp_tc_port_hotplug_long_detect); } @@ -2024,7 +2024,7 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, - dev_priv->hotplug.pch_hpd, + dev_priv->display.hotplug.pch_hpd, spt_port_hotplug_long_detect); } @@ -2036,7 +2036,7 @@ static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug2_trigger, dig_hotplug_reg, - dev_priv->hotplug.pch_hpd, + dev_priv->display.hotplug.pch_hpd, spt_port_hotplug2_long_detect); } @@ -2057,7 +2057,7 @@ static void ilk_hpd_irq_handler(struct drm_i915_private *dev_priv, intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, - dev_priv->hotplug.hpd, + dev_priv->display.hotplug.hpd, ilk_port_hotplug_long_detect); intel_hpd_irq_handler(dev_priv, pin_mask, long_mask); @@ -2237,7 +2237,7 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv, intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, hotplug_trigger, dig_hotplug_reg, - dev_priv->hotplug.hpd, + dev_priv->display.hotplug.hpd, bxt_port_hotplug_long_detect); intel_hpd_irq_handler(dev_priv, pin_mask, long_mask); @@ -2257,7 +2257,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc, dig_hotplug_reg, - dev_priv->hotplug.hpd, + dev_priv->display.hotplug.hpd, gen11_port_hotplug_long_detect); } @@ -2269,7 +2269,7 @@ static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir) intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tbt, dig_hotplug_reg, - dev_priv->hotplug.hpd, + dev_priv->display.hotplug.hpd, gen11_port_hotplug_long_detect); } @@ -2653,9 +2653,9 @@ static irqreturn_t gen8_irq_handler(int irq, void *arg) } static u32 -gen11_gu_misc_irq_ack(struct intel_gt *gt, const u32 master_ctl) +gen11_gu_misc_irq_ack(struct drm_i915_private *i915, const u32 master_ctl) { - void __iomem * const regs = gt->uncore->regs; + void __iomem * const regs = i915->uncore.regs; u32 iir; if (!(master_ctl & GEN11_GU_MISC_IRQ)) @@ -2669,10 +2669,10 @@ gen11_gu_misc_irq_ack(struct intel_gt *gt, const u32 master_ctl) } static void -gen11_gu_misc_irq_handler(struct intel_gt *gt, const u32 iir) +gen11_gu_misc_irq_handler(struct drm_i915_private *i915, const u32 iir) { if (iir & GEN11_GU_MISC_GSE) - intel_opregion_asle_intr(gt->i915); + intel_opregion_asle_intr(i915); } static inline u32 gen11_master_intr_disable(void __iomem * const regs) @@ -2736,11 +2736,11 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg) if (master_ctl & GEN11_DISPLAY_IRQ) gen11_display_irq_handler(i915); - gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl); + gu_misc_iir = gen11_gu_misc_irq_ack(i915, master_ctl); gen11_master_intr_enable(regs); - gen11_gu_misc_irq_handler(gt, gu_misc_iir); + gen11_gu_misc_irq_handler(i915, gu_misc_iir); pmu_irq_stats(i915, IRQ_HANDLED); @@ -2801,11 +2801,11 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg) if (master_ctl & GEN11_DISPLAY_IRQ) gen11_display_irq_handler(i915); - gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl); + gu_misc_iir = gen11_gu_misc_irq_ack(i915, master_ctl); dg1_master_intr_enable(regs); - gen11_gu_misc_irq_handler(gt, gu_misc_iir); + gen11_gu_misc_irq_handler(i915, gu_misc_iir); pmu_irq_stats(i915, IRQ_HANDLED); @@ -3313,8 +3313,8 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd); - hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.pch_hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.pch_hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.pch_hpd); ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); @@ -3383,8 +3383,8 @@ static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd); - hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.pch_hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.pch_hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.pch_hpd); if (INTEL_PCH_TYPE(dev_priv) <= PCH_TGP) intel_uncore_write(&dev_priv->uncore, SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ); @@ -3460,8 +3460,8 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv) u32 hotplug_irqs, enabled_irqs; u32 val; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.hpd); val = intel_uncore_read(&dev_priv->uncore, GEN11_DE_HPD_IMR); val &= ~hotplug_irqs; @@ -3538,8 +3538,8 @@ static void spt_hpd_irq_setup(struct drm_i915_private *dev_priv) if (INTEL_PCH_TYPE(dev_priv) >= PCH_CNP) intel_uncore_write(&dev_priv->uncore, SHPD_FILTER_CNT, SHPD_FILTER_CNT_500_ADJ); - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.pch_hpd); - hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.pch_hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.pch_hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.pch_hpd); ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs); @@ -3578,8 +3578,8 @@ static void ilk_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.hpd); if (DISPLAY_VER(dev_priv) >= 8) bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); @@ -3636,8 +3636,8 @@ static void bxt_hpd_irq_setup(struct drm_i915_private *dev_priv) { u32 hotplug_irqs, enabled_irqs; - enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->hotplug.hpd); - hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->hotplug.hpd); + enabled_irqs = intel_hpd_enabled_irqs(dev_priv, dev_priv->display.hotplug.hpd); + hotplug_irqs = intel_hpd_hotplug_irqs(dev_priv, dev_priv->display.hotplug.hpd); bdw_update_port_irq(dev_priv, hotplug_irqs, enabled_irqs); @@ -4370,8 +4370,8 @@ HPD_FUNCS(ilk); void intel_hpd_irq_setup(struct drm_i915_private *i915) { - if (i915->display_irqs_enabled && i915->hotplug_funcs) - i915->hotplug_funcs->hpd_irq_setup(i915); + if (i915->display_irqs_enabled && i915->display.funcs.hotplug) + i915->display.funcs.hotplug->hpd_irq_setup(i915); } /** @@ -4413,33 +4413,33 @@ void intel_irq_init(struct drm_i915_private *dev_priv) if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) dev_priv->display_irqs_enabled = false; - dev_priv->hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD; + dev_priv->display.hotplug.hpd_storm_threshold = HPD_STORM_DEFAULT_THRESHOLD; /* If we have MST support, we want to avoid doing short HPD IRQ storm * detection, as short HPD storms will occur as a natural part of * sideband messaging with MST. * On older platforms however, IRQ storms can occur with both long and * short pulses, as seen on some G4x systems. */ - dev_priv->hotplug.hpd_short_storm_enabled = !HAS_DP_MST(dev_priv); + dev_priv->display.hotplug.hpd_short_storm_enabled = !HAS_DP_MST(dev_priv); if (HAS_GMCH(dev_priv)) { if (I915_HAS_HOTPLUG(dev_priv)) - dev_priv->hotplug_funcs = &i915_hpd_funcs; + dev_priv->display.funcs.hotplug = &i915_hpd_funcs; } else { if (HAS_PCH_DG2(dev_priv)) - dev_priv->hotplug_funcs = &icp_hpd_funcs; + dev_priv->display.funcs.hotplug = &icp_hpd_funcs; else if (HAS_PCH_DG1(dev_priv)) - dev_priv->hotplug_funcs = &dg1_hpd_funcs; + dev_priv->display.funcs.hotplug = &dg1_hpd_funcs; else if (DISPLAY_VER(dev_priv) >= 11) - dev_priv->hotplug_funcs = &gen11_hpd_funcs; + dev_priv->display.funcs.hotplug = &gen11_hpd_funcs; else if (IS_GEMINILAKE(dev_priv) || IS_BROXTON(dev_priv)) - dev_priv->hotplug_funcs = &bxt_hpd_funcs; + dev_priv->display.funcs.hotplug = &bxt_hpd_funcs; else if (INTEL_PCH_TYPE(dev_priv) >= PCH_ICP) - dev_priv->hotplug_funcs = &icp_hpd_funcs; + dev_priv->display.funcs.hotplug = &icp_hpd_funcs; else if (INTEL_PCH_TYPE(dev_priv) >= PCH_SPT) - dev_priv->hotplug_funcs = &spt_hpd_funcs; + dev_priv->display.funcs.hotplug = &spt_hpd_funcs; else - dev_priv->hotplug_funcs = &ilk_hpd_funcs; + dev_priv->display.funcs.hotplug = &ilk_hpd_funcs; } } diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c index 6fc475a5db61..d1e4d528cb17 100644 --- a/drivers/gpu/drm/i915/i915_params.c +++ b/drivers/gpu/drm/i915/i915_params.c @@ -29,6 +29,18 @@ #include "i915_params.h" #include "i915_drv.h" +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"); + #define i915_param_named(name, T, perm, desc) \ module_param_named(name, i915_modparams.name, T, perm); \ MODULE_PARM_DESC(name, desc) diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 59a579ed03bb..cd4487a1d3be 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -26,16 +26,22 @@ #include <drm/drm_drv.h> #include <drm/i915_pciids.h> +#include "gt/intel_gt_regs.h" +#include "gt/intel_sa_media.h" + #include "i915_driver.h" #include "i915_drv.h" #include "i915_pci.h" #include "i915_reg.h" +#include "intel_pci_config.h" #define PLATFORM(x) .platform = (x) #define GEN(x) \ - .graphics.ver = (x), \ - .media.ver = (x), \ - .display.ver = (x) + .__runtime.graphics.ip.ver = (x), \ + .__runtime.media.ip.ver = (x), \ + .__runtime.display.ip.ver = (x) + +#define NO_DISPLAY .__runtime.pipe_mask = 0 #define I845_PIPE_OFFSETS \ .display.pipe_offsets = { \ @@ -159,16 +165,16 @@ /* Keep in gen based order, and chronological order within a gen */ #define GEN_DEFAULT_PAGE_SIZES \ - .page_sizes = I915_GTT_PAGE_SIZE_4K + .__runtime.page_sizes = I915_GTT_PAGE_SIZE_4K #define GEN_DEFAULT_REGIONS \ - .memory_regions = REGION_SMEM | REGION_STOLEN_SMEM + .__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_SMEM #define I830_FEATURES \ GEN(2), \ .is_mobile = 1, \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_overlay = 1, \ .display.cursor_needs_physical = 1, \ .display.overlay_needs_physical = 1, \ @@ -177,7 +183,7 @@ .has_3d_pipeline = 1, \ .hws_needs_physical = 1, \ .unfenced_needs_alignment = 1, \ - .platform_engine_mask = BIT(RCS0), \ + .__runtime.platform_engine_mask = BIT(RCS0), \ .has_snoop = true, \ .has_coherent_ggtt = false, \ .dma_mask_size = 32, \ @@ -189,8 +195,8 @@ #define I845_FEATURES \ GEN(2), \ - .display.pipe_mask = BIT(PIPE_A), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A), \ + .__runtime.pipe_mask = BIT(PIPE_A), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A), \ .display.has_overlay = 1, \ .display.overlay_needs_physical = 1, \ .display.has_gmch = 1, \ @@ -198,7 +204,7 @@ .gpu_reset_clobbers_display = true, \ .hws_needs_physical = 1, \ .unfenced_needs_alignment = 1, \ - .platform_engine_mask = BIT(RCS0), \ + .__runtime.platform_engine_mask = BIT(RCS0), \ .has_snoop = true, \ .has_coherent_ggtt = false, \ .dma_mask_size = 32, \ @@ -221,22 +227,22 @@ static const struct intel_device_info i845g_info = { static const struct intel_device_info i85x_info = { I830_FEATURES, PLATFORM(INTEL_I85X), - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), }; static const struct intel_device_info i865g_info = { I845_FEATURES, PLATFORM(INTEL_I865G), - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), }; #define GEN3_FEATURES \ GEN(3), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_gmch = 1, \ .gpu_reset_clobbers_display = true, \ - .platform_engine_mask = BIT(RCS0), \ + .__runtime.platform_engine_mask = BIT(RCS0), \ .has_3d_pipeline = 1, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -266,7 +272,7 @@ static const struct intel_device_info i915gm_info = { .display.has_overlay = 1, .display.overlay_needs_physical = 1, .display.supports_tv = 1, - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), .hws_needs_physical = 1, .unfenced_needs_alignment = 1, }; @@ -291,7 +297,7 @@ static const struct intel_device_info i945gm_info = { .display.has_overlay = 1, .display.overlay_needs_physical = 1, .display.supports_tv = 1, - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), .hws_needs_physical = 1, .unfenced_needs_alignment = 1, }; @@ -323,12 +329,12 @@ static const struct intel_device_info pnv_m_info = { #define GEN4_FEATURES \ GEN(4), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ .display.has_gmch = 1, \ .gpu_reset_clobbers_display = true, \ - .platform_engine_mask = BIT(RCS0), \ + .__runtime.platform_engine_mask = BIT(RCS0), \ .has_3d_pipeline = 1, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -351,7 +357,7 @@ static const struct intel_device_info i965gm_info = { GEN4_FEATURES, PLATFORM(INTEL_I965GM), .is_mobile = 1, - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), .display.has_overlay = 1, .display.supports_tv = 1, .hws_needs_physical = 1, @@ -361,7 +367,7 @@ static const struct intel_device_info i965gm_info = { static const struct intel_device_info g45_info = { GEN4_FEATURES, PLATFORM(INTEL_G45), - .platform_engine_mask = BIT(RCS0) | BIT(VCS0), + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0), .gpu_reset_clobbers_display = false, }; @@ -369,18 +375,18 @@ static const struct intel_device_info gm45_info = { GEN4_FEATURES, PLATFORM(INTEL_GM45), .is_mobile = 1, - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), .display.supports_tv = 1, - .platform_engine_mask = BIT(RCS0) | BIT(VCS0), + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0), .gpu_reset_clobbers_display = false, }; #define GEN5_FEATURES \ GEN(5), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ - .platform_engine_mask = BIT(RCS0) | BIT(VCS0), \ + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0), \ .has_3d_pipeline = 1, \ .has_snoop = true, \ .has_coherent_ggtt = true, \ @@ -403,16 +409,16 @@ static const struct intel_device_info ilk_m_info = { PLATFORM(INTEL_IRONLAKE), .is_mobile = 1, .has_rps = true, - .display.fbc_mask = BIT(INTEL_FBC_A), + .__runtime.fbc_mask = BIT(INTEL_FBC_A), }; #define GEN6_FEATURES \ GEN(6), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), \ .display.has_hotplug = 1, \ - .display.fbc_mask = BIT(INTEL_FBC_A), \ - .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ + .__runtime.fbc_mask = BIT(INTEL_FBC_A), \ + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ .has_3d_pipeline = 1, \ .has_coherent_ggtt = true, \ .has_llc = 1, \ @@ -420,8 +426,8 @@ static const struct intel_device_info ilk_m_info = { .has_rc6p = 1, \ .has_rps = true, \ .dma_mask_size = 40, \ - .ppgtt_type = INTEL_PPGTT_ALIASING, \ - .ppgtt_size = 31, \ + .__runtime.ppgtt_type = INTEL_PPGTT_ALIASING, \ + .__runtime.ppgtt_size = 31, \ I9XX_PIPE_OFFSETS, \ I9XX_CURSOR_OFFSETS, \ ILK_COLORS, \ @@ -460,11 +466,11 @@ static const struct intel_device_info snb_m_gt2_info = { #define GEN7_FEATURES \ GEN(7), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), \ .display.has_hotplug = 1, \ - .display.fbc_mask = BIT(INTEL_FBC_A), \ - .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ + .__runtime.fbc_mask = BIT(INTEL_FBC_A), \ + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), \ .has_3d_pipeline = 1, \ .has_coherent_ggtt = true, \ .has_llc = 1, \ @@ -473,8 +479,8 @@ static const struct intel_device_info snb_m_gt2_info = { .has_reset_engine = true, \ .has_rps = true, \ .dma_mask_size = 40, \ - .ppgtt_type = INTEL_PPGTT_ALIASING, \ - .ppgtt_size = 31, \ + .__runtime.ppgtt_type = INTEL_PPGTT_ALIASING, \ + .__runtime.ppgtt_size = 31, \ IVB_PIPE_OFFSETS, \ IVB_CURSOR_OFFSETS, \ IVB_COLORS, \ @@ -515,9 +521,8 @@ static const struct intel_device_info ivb_m_gt2_info = { static const struct intel_device_info ivb_q_info = { GEN7_FEATURES, PLATFORM(INTEL_IVYBRIDGE), + NO_DISPLAY, .gt = 2, - .display.pipe_mask = 0, /* legal, last one wins */ - .display.cpu_transcoder_mask = 0, .has_l3_dpf = 1, }; @@ -525,8 +530,8 @@ static const struct intel_device_info vlv_info = { PLATFORM(INTEL_VALLEYVIEW), GEN(7), .is_lp = 1, - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B), + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B), .has_runtime_pm = 1, .has_rc6 = 1, .has_reset_engine = true, @@ -534,11 +539,11 @@ static const struct intel_device_info vlv_info = { .display.has_gmch = 1, .display.has_hotplug = 1, .dma_mask_size = 40, - .ppgtt_type = INTEL_PPGTT_ALIASING, - .ppgtt_size = 31, + .__runtime.ppgtt_type = INTEL_PPGTT_ALIASING, + .__runtime.ppgtt_size = 31, .has_snoop = true, .has_coherent_ggtt = false, - .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0), .display.mmio_offset = VLV_DISPLAY_BASE, I9XX_PIPE_OFFSETS, I9XX_CURSOR_OFFSETS, @@ -549,8 +554,8 @@ static const struct intel_device_info vlv_info = { #define G75_FEATURES \ GEN7_FEATURES, \ - .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP), \ .display.has_ddi = 1, \ .display.has_fpga_dbg = 1, \ @@ -584,8 +589,8 @@ static const struct intel_device_info hsw_gt3_info = { GEN(8), \ .has_logical_ring_contexts = 1, \ .dma_mask_size = 39, \ - .ppgtt_type = INTEL_PPGTT_FULL, \ - .ppgtt_size = 48, \ + .__runtime.ppgtt_type = INTEL_PPGTT_FULL, \ + .__runtime.ppgtt_size = 48, \ .has_64bit_reloc = 1 #define BDW_PLATFORM \ @@ -613,18 +618,18 @@ static const struct intel_device_info bdw_rsvd_info = { static const struct intel_device_info bdw_gt3_info = { BDW_PLATFORM, .gt = 3, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1), }; static const struct intel_device_info chv_info = { PLATFORM(INTEL_CHERRYVIEW), GEN(8), - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), .display.has_hotplug = 1, .is_lp = 1, - .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), .has_64bit_reloc = 1, .has_runtime_pm = 1, .has_rc6 = 1, @@ -632,8 +637,8 @@ static const struct intel_device_info chv_info = { .has_logical_ring_contexts = 1, .display.has_gmch = 1, .dma_mask_size = 39, - .ppgtt_type = INTEL_PPGTT_FULL, - .ppgtt_size = 32, + .__runtime.ppgtt_type = INTEL_PPGTT_FULL, + .__runtime.ppgtt_size = 32, .has_reset_engine = 1, .has_snoop = true, .has_coherent_ggtt = false, @@ -646,16 +651,16 @@ static const struct intel_device_info chv_info = { }; #define GEN9_DEFAULT_PAGE_SIZES \ - .page_sizes = I915_GTT_PAGE_SIZE_4K | \ - I915_GTT_PAGE_SIZE_64K + .__runtime.page_sizes = I915_GTT_PAGE_SIZE_4K | \ + I915_GTT_PAGE_SIZE_64K #define GEN9_FEATURES \ GEN8_FEATURES, \ GEN(9), \ GEN9_DEFAULT_PAGE_SIZES, \ - .display.has_dmc = 1, \ + .__runtime.has_dmc = 1, \ .has_gt_uc = 1, \ - .display.has_hdcp = 1, \ + .__runtime.has_hdcp = 1, \ .display.has_ipc = 1, \ .display.has_psr = 1, \ .display.has_psr_hw_tracking = 1, \ @@ -678,7 +683,7 @@ static const struct intel_device_info skl_gt2_info = { #define SKL_GT3_PLUS_PLATFORM \ SKL_PLATFORM, \ - .platform_engine_mask = \ + .__runtime.platform_engine_mask = \ BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1) @@ -697,29 +702,29 @@ static const struct intel_device_info skl_gt4_info = { .is_lp = 1, \ .display.dbuf.slice_mask = BIT(DBUF_S1), \ .display.has_hotplug = 1, \ - .platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0), \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \ BIT(TRANSCODER_DSI_A) | BIT(TRANSCODER_DSI_C), \ .has_3d_pipeline = 1, \ .has_64bit_reloc = 1, \ .display.has_ddi = 1, \ .display.has_fpga_dbg = 1, \ - .display.fbc_mask = BIT(INTEL_FBC_A), \ - .display.has_hdcp = 1, \ + .__runtime.fbc_mask = BIT(INTEL_FBC_A), \ + .__runtime.has_hdcp = 1, \ .display.has_psr = 1, \ .display.has_psr_hw_tracking = 1, \ .has_runtime_pm = 1, \ - .display.has_dmc = 1, \ + .__runtime.has_dmc = 1, \ .has_rc6 = 1, \ .has_rps = true, \ .display.has_dp_mst = 1, \ .has_logical_ring_contexts = 1, \ .has_gt_uc = 1, \ .dma_mask_size = 39, \ - .ppgtt_type = INTEL_PPGTT_FULL, \ - .ppgtt_size = 48, \ + .__runtime.ppgtt_type = INTEL_PPGTT_FULL, \ + .__runtime.ppgtt_size = 48, \ .has_reset_engine = 1, \ .has_snoop = true, \ .has_coherent_ggtt = false, \ @@ -739,7 +744,7 @@ static const struct intel_device_info bxt_info = { static const struct intel_device_info glk_info = { GEN9_LP_FEATURES, PLATFORM(INTEL_GEMINILAKE), - .display.ver = 10, + .__runtime.display.ip.ver = 10, .display.dbuf.size = 1024 - 4, /* 4 blocks for bypass path allocation */ GLK_COLORS, }; @@ -761,7 +766,7 @@ static const struct intel_device_info kbl_gt2_info = { static const struct intel_device_info kbl_gt3_info = { KBL_PLATFORM, .gt = 3, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1), }; @@ -782,7 +787,7 @@ static const struct intel_device_info cfl_gt2_info = { static const struct intel_device_info cfl_gt3_info = { CFL_PLATFORM, .gt = 3, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(VCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS1), }; @@ -801,15 +806,15 @@ static const struct intel_device_info cml_gt2_info = { }; #define GEN11_DEFAULT_PAGE_SIZES \ - .page_sizes = I915_GTT_PAGE_SIZE_4K | \ - I915_GTT_PAGE_SIZE_64K | \ - I915_GTT_PAGE_SIZE_2M + .__runtime.page_sizes = I915_GTT_PAGE_SIZE_4K | \ + I915_GTT_PAGE_SIZE_64K | \ + I915_GTT_PAGE_SIZE_2M #define GEN11_FEATURES \ GEN9_FEATURES, \ GEN11_DEFAULT_PAGE_SIZES, \ .display.abox_mask = BIT(0), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_EDP) | \ BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \ .display.pipe_offsets = { \ @@ -832,37 +837,37 @@ static const struct intel_device_info cml_gt2_info = { ICL_COLORS, \ .display.dbuf.size = 2048, \ .display.dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2), \ - .display.has_dsc = 1, \ + .__runtime.has_dsc = 1, \ .has_coherent_ggtt = false, \ .has_logical_ring_elsq = 1 static const struct intel_device_info icl_info = { GEN11_FEATURES, PLATFORM(INTEL_ICELAKE), - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2), }; static const struct intel_device_info ehl_info = { GEN11_FEATURES, PLATFORM(INTEL_ELKHARTLAKE), - .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VCS0) | BIT(VECS0), - .ppgtt_size = 36, + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VCS0) | BIT(VECS0), + .__runtime.ppgtt_size = 36, }; static const struct intel_device_info jsl_info = { GEN11_FEATURES, PLATFORM(INTEL_JASPERLAKE), - .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VCS0) | BIT(VECS0), - .ppgtt_size = 36, + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VCS0) | BIT(VECS0), + .__runtime.ppgtt_size = 36, }; #define GEN12_FEATURES \ GEN11_FEATURES, \ GEN(12), \ .display.abox_mask = GENMASK(2, 1), \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | \ BIT(TRANSCODER_C) | BIT(TRANSCODER_D) | \ BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), \ .display.pipe_offsets = { \ @@ -890,7 +895,7 @@ static const struct intel_device_info tgl_info = { GEN12_FEATURES, PLATFORM(INTEL_TIGERLAKE), .display.has_modular_fia = 1, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2), }; @@ -898,17 +903,17 @@ static const struct intel_device_info rkl_info = { GEN12_FEATURES, PLATFORM(INTEL_ROCKETLAKE), .display.abox_mask = BIT(0), - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C), .display.has_hti = 1, .display.has_psr_hw_tracking = 0, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0), }; #define DGFX_FEATURES \ - .memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \ + .__runtime.memory_regions = REGION_SMEM | REGION_LMEM | REGION_STOLEN_LMEM, \ .has_llc = 0, \ .has_pxp = 0, \ .has_snoop = 1, \ @@ -918,24 +923,24 @@ static const struct intel_device_info rkl_info = { static const struct intel_device_info dg1_info = { GEN12_FEATURES, DGFX_FEATURES, - .graphics.rel = 10, + .__runtime.graphics.ip.rel = 10, PLATFORM(INTEL_DG1), - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), .require_force_probe = 1, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2), /* Wa_16011227922 */ - .ppgtt_size = 47, + .__runtime.ppgtt_size = 47, }; static const struct intel_device_info adl_s_info = { GEN12_FEATURES, PLATFORM(INTEL_ALDERLAKE_S), - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), .display.has_hti = 1, .display.has_psr_hw_tracking = 0, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2), .dma_mask_size = 39, }; @@ -951,18 +956,18 @@ static const struct intel_device_info adl_s_info = { .display.dbuf.slice_mask = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | \ BIT(DBUF_S4), \ .display.has_ddi = 1, \ - .display.has_dmc = 1, \ + .__runtime.has_dmc = 1, \ .display.has_dp_mst = 1, \ .display.has_dsb = 1, \ - .display.has_dsc = 1, \ - .display.fbc_mask = BIT(INTEL_FBC_A), \ + .__runtime.has_dsc = 1, \ + .__runtime.fbc_mask = BIT(INTEL_FBC_A), \ .display.has_fpga_dbg = 1, \ - .display.has_hdcp = 1, \ + .__runtime.has_hdcp = 1, \ .display.has_hotplug = 1, \ .display.has_ipc = 1, \ .display.has_psr = 1, \ - .display.ver = 13, \ - .display.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ + .__runtime.display.ip.ver = 13, \ + .__runtime.pipe_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), \ .display.pipe_offsets = { \ [TRANSCODER_A] = PIPE_A_OFFSET, \ [TRANSCODER_B] = PIPE_B_OFFSET, \ @@ -985,28 +990,28 @@ static const struct intel_device_info adl_p_info = { GEN12_FEATURES, XE_LPD_FEATURES, PLATFORM(INTEL_ALDERLAKE_P), - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C) | BIT(TRANSCODER_D) | BIT(TRANSCODER_DSI_0) | BIT(TRANSCODER_DSI_1), .display.has_cdclk_crawl = 1, .display.has_modular_fia = 1, .display.has_psr_hw_tracking = 0, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VCS0) | BIT(VCS2), - .ppgtt_size = 48, + .__runtime.ppgtt_size = 48, .dma_mask_size = 39, }; #undef GEN #define XE_HP_PAGE_SIZES \ - .page_sizes = I915_GTT_PAGE_SIZE_4K | \ - I915_GTT_PAGE_SIZE_64K | \ - I915_GTT_PAGE_SIZE_2M + .__runtime.page_sizes = I915_GTT_PAGE_SIZE_4K | \ + I915_GTT_PAGE_SIZE_64K | \ + I915_GTT_PAGE_SIZE_2M #define XE_HP_FEATURES \ - .graphics.ver = 12, \ - .graphics.rel = 50, \ + .__runtime.graphics.ip.ver = 12, \ + .__runtime.graphics.ip.rel = 50, \ XE_HP_PAGE_SIZES, \ .dma_mask_size = 46, \ .has_3d_pipeline = 1, \ @@ -1022,12 +1027,12 @@ static const struct intel_device_info adl_p_info = { .has_reset_engine = 1, \ .has_rps = 1, \ .has_runtime_pm = 1, \ - .ppgtt_size = 48, \ - .ppgtt_type = INTEL_PPGTT_FULL + .__runtime.ppgtt_size = 48, \ + .__runtime.ppgtt_type = INTEL_PPGTT_FULL #define XE_HPM_FEATURES \ - .media.ver = 12, \ - .media.rel = 50 + .__runtime.media.ip.ver = 12, \ + .__runtime.media.ip.rel = 50 __maybe_unused static const struct intel_device_info xehpsdv_info = { @@ -1035,11 +1040,11 @@ static const struct intel_device_info xehpsdv_info = { XE_HPM_FEATURES, DGFX_FEATURES, PLATFORM(INTEL_XEHPSDV), - .display = { }, + NO_DISPLAY, .has_64k_pages = 1, .needs_compact_pt = 1, .has_media_ratio_mode = 1, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(VECS0) | BIT(VECS1) | BIT(VECS2) | BIT(VECS3) | BIT(VCS0) | BIT(VCS1) | BIT(VCS2) | BIT(VCS3) | @@ -1052,8 +1057,8 @@ static const struct intel_device_info xehpsdv_info = { XE_HP_FEATURES, \ XE_HPM_FEATURES, \ DGFX_FEATURES, \ - .graphics.rel = 55, \ - .media.rel = 55, \ + .__runtime.graphics.ip.rel = 55, \ + .__runtime.media.ip.rel = 55, \ PLATFORM(INTEL_DG2), \ .has_4tile = 1, \ .has_64k_pages = 1, \ @@ -1061,7 +1066,7 @@ static const struct intel_device_info xehpsdv_info = { .has_heci_pxp = 1, \ .needs_compact_pt = 1, \ .has_media_ratio_mode = 1, \ - .platform_engine_mask = \ + .__runtime.platform_engine_mask = \ BIT(RCS0) | BIT(BCS0) | \ BIT(VECS0) | BIT(VECS1) | \ BIT(VCS0) | BIT(VCS2) | \ @@ -1070,14 +1075,14 @@ static const struct intel_device_info xehpsdv_info = { static const struct intel_device_info dg2_info = { DG2_FEATURES, XE_LPD_FEATURES, - .display.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | + .__runtime.cpu_transcoder_mask = BIT(TRANSCODER_A) | BIT(TRANSCODER_B) | BIT(TRANSCODER_C) | BIT(TRANSCODER_D), .require_force_probe = 1, }; static const struct intel_device_info ats_m_info = { DG2_FEATURES, - .display = { 0 }, + NO_DISPLAY, .require_force_probe = 1, .tuning_thread_rr_after_dep = 1, }; @@ -1096,12 +1101,12 @@ static const struct intel_device_info pvc_info = { XE_HPC_FEATURES, XE_HPM_FEATURES, DGFX_FEATURES, - .graphics.rel = 60, - .media.rel = 60, + .__runtime.graphics.ip.rel = 60, + .__runtime.media.ip.rel = 60, PLATFORM(INTEL_PONTEVECCHIO), - .display = { 0 }, + NO_DISPLAY, .has_flat_ccs = 0, - .platform_engine_mask = + .__runtime.platform_engine_mask = BIT(BCS0) | BIT(VCS0) | BIT(CCS0) | BIT(CCS1) | BIT(CCS2) | BIT(CCS3), @@ -1110,8 +1115,19 @@ static const struct intel_device_info pvc_info = { #define XE_LPDP_FEATURES \ XE_LPD_FEATURES, \ - .display.ver = 14, \ - .display.has_cdclk_crawl = 1 + .__runtime.display.ip.ver = 14, \ + .display.has_cdclk_crawl = 1, \ + .__runtime.fbc_mask = BIT(INTEL_FBC_A) | BIT(INTEL_FBC_B) + +static const struct intel_gt_definition xelpmp_extra_gt[] = { + { + .type = GT_MEDIA, + .name = "Standalone Media GT", + .gsi_offset = MTL_MEDIA_GSI_BASE, + .engine_mask = BIT(VECS0) | BIT(VCS0) | BIT(VCS2), + }, + {} +}; __maybe_unused static const struct intel_device_info mtl_info = { @@ -1121,15 +1137,16 @@ static const struct intel_device_info mtl_info = { * Real graphics IP version will be obtained from hardware GMD_ID * register. Value provided here is just for sanity checking. */ - .graphics.ver = 12, - .graphics.rel = 70, - .media.ver = 13, + .__runtime.graphics.ip.ver = 12, + .__runtime.graphics.ip.rel = 70, + .__runtime.media.ip.ver = 13, PLATFORM(INTEL_METEORLAKE), .display.has_modular_fia = 1, + .extra_gt_list = xelpmp_extra_gt, .has_flat_ccs = 0, .has_snoop = 1, - .memory_regions = REGION_SMEM | REGION_STOLEN_LMEM, - .platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(CCS0), + .__runtime.memory_regions = REGION_SMEM | REGION_STOLEN_LMEM, + .__runtime.platform_engine_mask = BIT(RCS0) | BIT(BCS0) | BIT(CCS0), .require_force_probe = 1, }; @@ -1263,6 +1280,27 @@ static bool force_probe(u16 device_id, const char *devices) return ret; } +bool i915_pci_resource_valid(struct pci_dev *pdev, int bar) +{ + if (!pci_resource_flags(pdev, bar)) + return false; + + if (pci_resource_flags(pdev, bar) & IORESOURCE_UNSET) + return false; + + if (!pci_resource_len(pdev, bar)) + return false; + + return true; +} + +static bool intel_mmio_bar_valid(struct pci_dev *pdev, struct intel_device_info *intel_info) +{ + int gttmmaddr_bar = intel_info->__runtime.graphics.ip.ver == 2 ? GEN2_GTTMMADR_BAR : GTTMMADR_BAR; + + return i915_pci_resource_valid(pdev, gttmmaddr_bar); +} + static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct intel_device_info *intel_info = @@ -1288,6 +1326,9 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (PCI_FUNC(pdev->devfn)) return -ENODEV; + if (!intel_mmio_bar_valid(pdev, intel_info)) + return -ENXIO; + /* Detect if we need to wait for other drivers early on */ if (intel_modeset_probe_defer(pdev)) return -EPROBE_DEFER; diff --git a/drivers/gpu/drm/i915/i915_pci.h b/drivers/gpu/drm/i915/i915_pci.h index ee048c238174..8dfe19f9a775 100644 --- a/drivers/gpu/drm/i915/i915_pci.h +++ b/drivers/gpu/drm/i915/i915_pci.h @@ -6,7 +6,13 @@ #ifndef __I915_PCI_H__ #define __I915_PCI_H__ +#include <linux/types.h> + +struct pci_dev; + int i915_pci_register_driver(void); void i915_pci_unregister_driver(void); +bool i915_pci_resource_valid(struct pci_dev *pdev, int bar); + #endif /* __I915_PCI_H__ */ diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index f3c23fe9ad9c..0defbb43ceea 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -1376,7 +1376,8 @@ static void i915_oa_stream_destroy(struct i915_perf_stream *stream) { struct i915_perf *perf = stream->perf; - BUG_ON(stream != perf->exclusive_stream); + if (WARN_ON(stream != perf->exclusive_stream)) + return; /* * Unset exclusive_stream first, it will be checked while disabling diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 3168d7007e10..0b287a59dc2f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1125,8 +1125,12 @@ #define MBUS_DBOX_REGULATE_B2B_TRANSACTIONS_EN REG_BIT(16) /* tgl+ */ #define MBUS_DBOX_BW_CREDIT_MASK REG_GENMASK(15, 14) #define MBUS_DBOX_BW_CREDIT(x) REG_FIELD_PREP(MBUS_DBOX_BW_CREDIT_MASK, x) +#define MBUS_DBOX_BW_4CREDITS_MTL REG_FIELD_PREP(MBUS_DBOX_BW_CREDIT_MASK, 0x2) +#define MBUS_DBOX_BW_8CREDITS_MTL REG_FIELD_PREP(MBUS_DBOX_BW_CREDIT_MASK, 0x3) #define MBUS_DBOX_B_CREDIT_MASK REG_GENMASK(12, 8) #define MBUS_DBOX_B_CREDIT(x) REG_FIELD_PREP(MBUS_DBOX_B_CREDIT_MASK, x) +#define MBUS_DBOX_I_CREDIT_MASK REG_GENMASK(7, 5) +#define MBUS_DBOX_I_CREDIT(x) REG_FIELD_PREP(MBUS_DBOX_I_CREDIT_MASK, x) #define MBUS_DBOX_A_CREDIT_MASK REG_GENMASK(3, 0) #define MBUS_DBOX_A_CREDIT(x) REG_FIELD_PREP(MBUS_DBOX_A_CREDIT_MASK, x) @@ -1462,69 +1466,6 @@ #define FBC_REND_CACHE_CLEAN REG_BIT(1) /* - * GPIO regs - */ -#define GPIO(gpio) _MMIO(dev_priv->gpio_mmio_base + 0x5010 + \ - 4 * (gpio)) - -# define GPIO_CLOCK_DIR_MASK (1 << 0) -# define GPIO_CLOCK_DIR_IN (0 << 1) -# define GPIO_CLOCK_DIR_OUT (1 << 1) -# define GPIO_CLOCK_VAL_MASK (1 << 2) -# define GPIO_CLOCK_VAL_OUT (1 << 3) -# define GPIO_CLOCK_VAL_IN (1 << 4) -# define GPIO_CLOCK_PULLUP_DISABLE (1 << 5) -# define GPIO_DATA_DIR_MASK (1 << 8) -# define GPIO_DATA_DIR_IN (0 << 9) -# define GPIO_DATA_DIR_OUT (1 << 9) -# define GPIO_DATA_VAL_MASK (1 << 10) -# define GPIO_DATA_VAL_OUT (1 << 11) -# define GPIO_DATA_VAL_IN (1 << 12) -# define GPIO_DATA_PULLUP_DISABLE (1 << 13) - -#define GMBUS0 _MMIO(dev_priv->gpio_mmio_base + 0x5100) /* clock/port select */ -#define GMBUS_AKSV_SELECT (1 << 11) -#define GMBUS_RATE_100KHZ (0 << 8) -#define GMBUS_RATE_50KHZ (1 << 8) -#define GMBUS_RATE_400KHZ (2 << 8) /* reserved on Pineview */ -#define GMBUS_RATE_1MHZ (3 << 8) /* reserved on Pineview */ -#define GMBUS_HOLD_EXT (1 << 7) /* 300ns hold time, rsvd on Pineview */ -#define GMBUS_BYTE_CNT_OVERRIDE (1 << 6) - -#define GMBUS1 _MMIO(dev_priv->gpio_mmio_base + 0x5104) /* command/status */ -#define GMBUS_SW_CLR_INT (1 << 31) -#define GMBUS_SW_RDY (1 << 30) -#define GMBUS_ENT (1 << 29) /* enable timeout */ -#define GMBUS_CYCLE_NONE (0 << 25) -#define GMBUS_CYCLE_WAIT (1 << 25) -#define GMBUS_CYCLE_INDEX (2 << 25) -#define GMBUS_CYCLE_STOP (4 << 25) -#define GMBUS_BYTE_COUNT_SHIFT 16 -#define GMBUS_BYTE_COUNT_MAX 256U -#define GEN9_GMBUS_BYTE_COUNT_MAX 511U -#define GMBUS_SLAVE_INDEX_SHIFT 8 -#define GMBUS_SLAVE_ADDR_SHIFT 1 -#define GMBUS_SLAVE_READ (1 << 0) -#define GMBUS_SLAVE_WRITE (0 << 0) -#define GMBUS2 _MMIO(dev_priv->gpio_mmio_base + 0x5108) /* status */ -#define GMBUS_INUSE (1 << 15) -#define GMBUS_HW_WAIT_PHASE (1 << 14) -#define GMBUS_STALL_TIMEOUT (1 << 13) -#define GMBUS_INT (1 << 12) -#define GMBUS_HW_RDY (1 << 11) -#define GMBUS_SATOER (1 << 10) -#define GMBUS_ACTIVE (1 << 9) -#define GMBUS3 _MMIO(dev_priv->gpio_mmio_base + 0x510c) /* data buffer bytes 3-0 */ -#define GMBUS4 _MMIO(dev_priv->gpio_mmio_base + 0x5110) /* interrupt mask (Pineview+) */ -#define GMBUS_SLAVE_TIMEOUT_EN (1 << 4) -#define GMBUS_NAK_EN (1 << 3) -#define GMBUS_IDLE_EN (1 << 2) -#define GMBUS_HW_WAIT_EN (1 << 1) -#define GMBUS_HW_RDY_EN (1 << 0) -#define GMBUS5 _MMIO(dev_priv->gpio_mmio_base + 0x5120) /* byte index */ -#define GMBUS_2BYTE_INDEX_EN (1 << 31) - -/* * Clock control & power management */ #define _DPLL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x6014) @@ -1700,7 +1641,7 @@ #define DSTATE_PLL_D3_OFF (1 << 3) #define DSTATE_GFX_CLOCK_GATING (1 << 1) #define DSTATE_DOT_CLOCK_GATING (1 << 0) -#define DSPCLK_GATE_D _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x6200) +#define DSPCLK_GATE_D(__i915) _MMIO(DISPLAY_MMIO_BASE(__i915) + 0x6200) # define DPUNIT_B_CLOCK_GATE_DISABLE (1 << 30) /* 965 */ # define VSUNIT_CLOCK_GATE_DISABLE (1 << 29) /* 965 */ # define VRHUNIT_CLOCK_GATE_DISABLE (1 << 28) /* 965 */ @@ -1857,14 +1798,14 @@ #define GT0_PERF_LIMIT_REASONS _MMIO(0x1381a8) #define GT0_PERF_LIMIT_REASONS_MASK 0xde3 -#define PROCHOT_MASK REG_BIT(1) -#define THERMAL_LIMIT_MASK REG_BIT(2) -#define RATL_MASK REG_BIT(6) -#define VR_THERMALERT_MASK REG_BIT(7) -#define VR_TDC_MASK REG_BIT(8) -#define POWER_LIMIT_4_MASK REG_BIT(9) -#define POWER_LIMIT_1_MASK REG_BIT(11) -#define POWER_LIMIT_2_MASK REG_BIT(12) +#define PROCHOT_MASK REG_BIT(0) +#define THERMAL_LIMIT_MASK REG_BIT(1) +#define RATL_MASK REG_BIT(5) +#define VR_THERMALERT_MASK REG_BIT(6) +#define VR_TDC_MASK REG_BIT(7) +#define POWER_LIMIT_4_MASK REG_BIT(8) +#define POWER_LIMIT_1_MASK REG_BIT(10) +#define POWER_LIMIT_2_MASK REG_BIT(11) #define CHV_CLK_CTL1 _MMIO(0x101100) #define VLV_CLK_CTL2 _MMIO(0x101104) @@ -1916,6 +1857,13 @@ #define CLKGATE_DIS_PSL(pipe) \ _MMIO_PIPE(pipe, _CLKGATE_DIS_PSL_A, _CLKGATE_DIS_PSL_B) +#define _CLKGATE_DIS_PSL_EXT_A 0x4654C +#define _CLKGATE_DIS_PSL_EXT_B 0x46550 +#define PIPEDMC_GATING_DIS REG_BIT(12) + +#define CLKGATE_DIS_PSL_EXT(pipe) \ + _MMIO_PIPE(pipe, _CLKGATE_DIS_PSL_EXT_A, _CLKGATE_DIS_PSL_EXT_B) + /* * Display engine regs */ @@ -2209,10 +2157,18 @@ #define TRANS_PSR_IIR(tran) _MMIO_TRANS2(tran, _PSR_IIR_A) #define _EDP_PSR_TRANS_SHIFT(trans) ((trans) == TRANSCODER_EDP ? \ 0 : ((trans) - TRANSCODER_A + 1) * 8) -#define EDP_PSR_TRANS_MASK(trans) (0x7 << _EDP_PSR_TRANS_SHIFT(trans)) -#define EDP_PSR_ERROR(trans) (0x4 << _EDP_PSR_TRANS_SHIFT(trans)) -#define EDP_PSR_POST_EXIT(trans) (0x2 << _EDP_PSR_TRANS_SHIFT(trans)) -#define EDP_PSR_PRE_ENTRY(trans) (0x1 << _EDP_PSR_TRANS_SHIFT(trans)) +#define TGL_PSR_MASK REG_GENMASK(2, 0) +#define TGL_PSR_ERROR REG_BIT(2) +#define TGL_PSR_POST_EXIT REG_BIT(1) +#define TGL_PSR_PRE_ENTRY REG_BIT(0) +#define EDP_PSR_MASK(trans) (TGL_PSR_MASK << \ + _EDP_PSR_TRANS_SHIFT(trans)) +#define EDP_PSR_ERROR(trans) (TGL_PSR_ERROR << \ + _EDP_PSR_TRANS_SHIFT(trans)) +#define EDP_PSR_POST_EXIT(trans) (TGL_PSR_POST_EXIT << \ + _EDP_PSR_TRANS_SHIFT(trans)) +#define EDP_PSR_PRE_ENTRY(trans) (TGL_PSR_PRE_ENTRY << \ + _EDP_PSR_TRANS_SHIFT(trans)) #define _SRD_AUX_DATA_A 0x60814 #define _SRD_AUX_DATA_EDP 0x6f814 @@ -2822,7 +2778,7 @@ #define VLV_PPS_BASE (VLV_DISPLAY_BASE + PPS_BASE) #define PCH_PPS_BASE 0xC7200 -#define _MMIO_PPS(pps_idx, reg) _MMIO(dev_priv->pps_mmio_base - \ +#define _MMIO_PPS(pps_idx, reg) _MMIO(dev_priv->display.pps.mmio_base - \ PPS_BASE + (reg) + \ (pps_idx) * 0x100) @@ -2918,118 +2874,6 @@ #define PFIT_AUTO_RATIOS _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61238) -#define _VLV_BLC_PWM_CTL2_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61250) -#define _VLV_BLC_PWM_CTL2_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61350) -#define VLV_BLC_PWM_CTL2(pipe) _MMIO_PIPE(pipe, _VLV_BLC_PWM_CTL2_A, \ - _VLV_BLC_PWM_CTL2_B) - -#define _VLV_BLC_PWM_CTL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61254) -#define _VLV_BLC_PWM_CTL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61354) -#define VLV_BLC_PWM_CTL(pipe) _MMIO_PIPE(pipe, _VLV_BLC_PWM_CTL_A, \ - _VLV_BLC_PWM_CTL_B) - -#define _VLV_BLC_HIST_CTL_A (DISPLAY_MMIO_BASE(dev_priv) + 0x61260) -#define _VLV_BLC_HIST_CTL_B (DISPLAY_MMIO_BASE(dev_priv) + 0x61360) -#define VLV_BLC_HIST_CTL(pipe) _MMIO_PIPE(pipe, _VLV_BLC_HIST_CTL_A, \ - _VLV_BLC_HIST_CTL_B) - -/* Backlight control */ -#define BLC_PWM_CTL2 _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61250) /* 965+ only */ -#define BLM_PWM_ENABLE (1 << 31) -#define BLM_COMBINATION_MODE (1 << 30) /* gen4 only */ -#define BLM_PIPE_SELECT (1 << 29) -#define BLM_PIPE_SELECT_IVB (3 << 29) -#define BLM_PIPE_A (0 << 29) -#define BLM_PIPE_B (1 << 29) -#define BLM_PIPE_C (2 << 29) /* ivb + */ -#define BLM_TRANSCODER_A BLM_PIPE_A /* hsw */ -#define BLM_TRANSCODER_B BLM_PIPE_B -#define BLM_TRANSCODER_C BLM_PIPE_C -#define BLM_TRANSCODER_EDP (3 << 29) -#define BLM_PIPE(pipe) ((pipe) << 29) -#define BLM_POLARITY_I965 (1 << 28) /* gen4 only */ -#define BLM_PHASE_IN_INTERUPT_STATUS (1 << 26) -#define BLM_PHASE_IN_ENABLE (1 << 25) -#define BLM_PHASE_IN_INTERUPT_ENABL (1 << 24) -#define BLM_PHASE_IN_TIME_BASE_SHIFT (16) -#define BLM_PHASE_IN_TIME_BASE_MASK (0xff << 16) -#define BLM_PHASE_IN_COUNT_SHIFT (8) -#define BLM_PHASE_IN_COUNT_MASK (0xff << 8) -#define BLM_PHASE_IN_INCR_SHIFT (0) -#define BLM_PHASE_IN_INCR_MASK (0xff << 0) -#define BLC_PWM_CTL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61254) -/* - * This is the most significant 15 bits of the number of backlight cycles in a - * complete cycle of the modulated backlight control. - * - * The actual value is this field multiplied by two. - */ -#define BACKLIGHT_MODULATION_FREQ_SHIFT (17) -#define BACKLIGHT_MODULATION_FREQ_MASK (0x7fff << 17) -#define BLM_LEGACY_MODE (1 << 16) /* gen2 only */ -/* - * This is the number of cycles out of the backlight modulation cycle for which - * the backlight is on. - * - * This field must be no greater than the number of cycles in the complete - * backlight modulation cycle. - */ -#define BACKLIGHT_DUTY_CYCLE_SHIFT (0) -#define BACKLIGHT_DUTY_CYCLE_MASK (0xffff) -#define BACKLIGHT_DUTY_CYCLE_MASK_PNV (0xfffe) -#define BLM_POLARITY_PNV (1 << 0) /* pnv only */ - -#define BLC_HIST_CTL _MMIO(DISPLAY_MMIO_BASE(dev_priv) + 0x61260) -#define BLM_HISTOGRAM_ENABLE (1 << 31) - -/* New registers for PCH-split platforms. Safe where new bits show up, the - * register layout machtes with gen4 BLC_PWM_CTL[12]. */ -#define BLC_PWM_CPU_CTL2 _MMIO(0x48250) -#define BLC_PWM_CPU_CTL _MMIO(0x48254) - -#define HSW_BLC_PWM2_CTL _MMIO(0x48350) - -/* PCH CTL1 is totally different, all but the below bits are reserved. CTL2 is - * like the normal CTL from gen4 and earlier. Hooray for confusing naming. */ -#define BLC_PWM_PCH_CTL1 _MMIO(0xc8250) -#define BLM_PCH_PWM_ENABLE (1 << 31) -#define BLM_PCH_OVERRIDE_ENABLE (1 << 30) -#define BLM_PCH_POLARITY (1 << 29) -#define BLC_PWM_PCH_CTL2 _MMIO(0xc8254) - -#define UTIL_PIN_CTL _MMIO(0x48400) -#define UTIL_PIN_ENABLE (1 << 31) -#define UTIL_PIN_PIPE_MASK (3 << 29) -#define UTIL_PIN_PIPE(x) ((x) << 29) -#define UTIL_PIN_MODE_MASK (0xf << 24) -#define UTIL_PIN_MODE_DATA (0 << 24) -#define UTIL_PIN_MODE_PWM (1 << 24) -#define UTIL_PIN_MODE_VBLANK (4 << 24) -#define UTIL_PIN_MODE_VSYNC (5 << 24) -#define UTIL_PIN_MODE_EYE_LEVEL (8 << 24) -#define UTIL_PIN_OUTPUT_DATA (1 << 23) -#define UTIL_PIN_POLARITY (1 << 22) -#define UTIL_PIN_DIRECTION_INPUT (1 << 19) -#define UTIL_PIN_INPUT_DATA (1 << 16) - -/* BXT backlight register definition. */ -#define _BXT_BLC_PWM_CTL1 0xC8250 -#define BXT_BLC_PWM_ENABLE (1 << 31) -#define BXT_BLC_PWM_POLARITY (1 << 29) -#define _BXT_BLC_PWM_FREQ1 0xC8254 -#define _BXT_BLC_PWM_DUTY1 0xC8258 - -#define _BXT_BLC_PWM_CTL2 0xC8350 -#define _BXT_BLC_PWM_FREQ2 0xC8354 -#define _BXT_BLC_PWM_DUTY2 0xC8358 - -#define BXT_BLC_PWM_CTL(controller) _MMIO_PIPE(controller, \ - _BXT_BLC_PWM_CTL1, _BXT_BLC_PWM_CTL2) -#define BXT_BLC_PWM_FREQ(controller) _MMIO_PIPE(controller, \ - _BXT_BLC_PWM_FREQ1, _BXT_BLC_PWM_FREQ2) -#define BXT_BLC_PWM_DUTY(controller) _MMIO_PIPE(controller, \ - _BXT_BLC_PWM_DUTY1, _BXT_BLC_PWM_DUTY2) - #define PCH_GTC_CTL _MMIO(0xe7000) #define PCH_GTC_ENABLE (1 << 31) @@ -3619,6 +3463,34 @@ #define DP_AUX_CH_CTL(aux_ch) _MMIO_PORT(aux_ch, _DPA_AUX_CH_CTL, _DPB_AUX_CH_CTL) #define DP_AUX_CH_DATA(aux_ch, i) _MMIO(_PORT(aux_ch, _DPA_AUX_CH_DATA1, _DPB_AUX_CH_DATA1) + (i) * 4) /* 5 registers */ +#define _XELPDP_USBC1_AUX_CH_CTL 0x16F210 +#define _XELPDP_USBC2_AUX_CH_CTL 0x16F410 +#define _XELPDP_USBC3_AUX_CH_CTL 0x16F610 +#define _XELPDP_USBC4_AUX_CH_CTL 0x16F810 + +#define XELPDP_DP_AUX_CH_CTL(aux_ch) _MMIO(_PICK(aux_ch, \ + _DPA_AUX_CH_CTL, \ + _DPB_AUX_CH_CTL, \ + 0, /* port/aux_ch C is non-existent */ \ + _XELPDP_USBC1_AUX_CH_CTL, \ + _XELPDP_USBC2_AUX_CH_CTL, \ + _XELPDP_USBC3_AUX_CH_CTL, \ + _XELPDP_USBC4_AUX_CH_CTL)) + +#define _XELPDP_USBC1_AUX_CH_DATA1 0x16F214 +#define _XELPDP_USBC2_AUX_CH_DATA1 0x16F414 +#define _XELPDP_USBC3_AUX_CH_DATA1 0x16F614 +#define _XELPDP_USBC4_AUX_CH_DATA1 0x16F814 + +#define XELPDP_DP_AUX_CH_DATA(aux_ch, i) _MMIO(_PICK(aux_ch, \ + _DPA_AUX_CH_DATA1, \ + _DPB_AUX_CH_DATA1, \ + 0, /* port/aux_ch C is non-existent */ \ + _XELPDP_USBC1_AUX_CH_DATA1, \ + _XELPDP_USBC2_AUX_CH_DATA1, \ + _XELPDP_USBC3_AUX_CH_DATA1, \ + _XELPDP_USBC4_AUX_CH_DATA1) + (i) * 4) + #define DP_AUX_CH_CTL_SEND_BUSY (1 << 31) #define DP_AUX_CH_CTL_DONE (1 << 30) #define DP_AUX_CH_CTL_INTERRUPT (1 << 29) @@ -3631,6 +3503,8 @@ #define DP_AUX_CH_CTL_RECEIVE_ERROR (1 << 25) #define DP_AUX_CH_CTL_MESSAGE_SIZE_MASK (0x1f << 20) #define DP_AUX_CH_CTL_MESSAGE_SIZE_SHIFT 20 +#define XELPDP_DP_AUX_CH_CTL_POWER_REQUEST REG_BIT(19) +#define XELPDP_DP_AUX_CH_CTL_POWER_STATUS REG_BIT(18) #define DP_AUX_CH_CTL_PRECHARGE_2US_MASK (0xf << 16) #define DP_AUX_CH_CTL_PRECHARGE_2US_SHIFT 16 #define DP_AUX_CH_CTL_AUX_AKSV_SELECT (1 << 15) @@ -5862,6 +5736,13 @@ [TRANSCODER_B] = _CHICKEN_TRANS_B, \ [TRANSCODER_C] = _CHICKEN_TRANS_C, \ [TRANSCODER_D] = _CHICKEN_TRANS_D)) + +#define _MTL_CHICKEN_TRANS_A 0x604e0 +#define _MTL_CHICKEN_TRANS_B 0x614e0 +#define MTL_CHICKEN_TRANS(trans) _MMIO_TRANS((trans), \ + _MTL_CHICKEN_TRANS_A, \ + _MTL_CHICKEN_TRANS_B) + #define HSW_FRAME_START_DELAY_MASK REG_GENMASK(28, 27) #define HSW_FRAME_START_DELAY(x) REG_FIELD_PREP(HSW_FRAME_START_DELAY_MASK, x) #define VSC_DATA_SEL_SOFTWARE_CONTROL REG_BIT(25) /* GLK */ @@ -5926,7 +5807,8 @@ _BW_BUDDY1_PAGE_MASK)) #define HSW_NDE_RSTWRN_OPT _MMIO(0x46408) -#define RESET_PCH_HANDSHAKE_ENABLE (1 << 4) +#define MTL_RESET_PICA_HANDSHAKE_EN REG_BIT(6) +#define RESET_PCH_HANDSHAKE_ENABLE REG_BIT(4) #define GEN8_CHICKEN_DCPR_1 _MMIO(0x46430) #define SKL_SELECT_ALTERNATE_DC_EXIT REG_BIT(30) @@ -6718,10 +6600,10 @@ #define GEN6_DECODE_RC6_VID(vids) (((vids) * 5) + 245) #define BDW_PCODE_DISPLAY_FREQ_CHANGE_REQ 0x18 #define GEN9_PCODE_READ_MEM_LATENCY 0x6 -#define GEN9_MEM_LATENCY_LEVEL_MASK 0xFF -#define GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT 8 -#define GEN9_MEM_LATENCY_LEVEL_2_6_SHIFT 16 -#define GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT 24 +#define GEN9_MEM_LATENCY_LEVEL_3_7_MASK REG_GENMASK(31, 24) +#define GEN9_MEM_LATENCY_LEVEL_2_6_MASK REG_GENMASK(23, 16) +#define GEN9_MEM_LATENCY_LEVEL_1_5_MASK REG_GENMASK(15, 8) +#define GEN9_MEM_LATENCY_LEVEL_0_4_MASK REG_GENMASK(7, 0) #define SKL_PCODE_LOAD_HDCP_KEYS 0x5 #define SKL_PCODE_CDCLK_CONTROL 0x7 #define SKL_CDCLK_PREPARE_FOR_CHANGE 0x3 @@ -6937,265 +6819,6 @@ enum skl_power_gate { #define ICL_AUX_ANAOVRD1_LDO_BYPASS (1 << 7) #define ICL_AUX_ANAOVRD1_ENABLE (1 << 0) -/* HDCP Key Registers */ -#define HDCP_KEY_CONF _MMIO(0x66c00) -#define HDCP_AKSV_SEND_TRIGGER BIT(31) -#define HDCP_CLEAR_KEYS_TRIGGER BIT(30) -#define HDCP_KEY_LOAD_TRIGGER BIT(8) -#define HDCP_KEY_STATUS _MMIO(0x66c04) -#define HDCP_FUSE_IN_PROGRESS BIT(7) -#define HDCP_FUSE_ERROR BIT(6) -#define HDCP_FUSE_DONE BIT(5) -#define HDCP_KEY_LOAD_STATUS BIT(1) -#define HDCP_KEY_LOAD_DONE BIT(0) -#define HDCP_AKSV_LO _MMIO(0x66c10) -#define HDCP_AKSV_HI _MMIO(0x66c14) - -/* HDCP Repeater Registers */ -#define HDCP_REP_CTL _MMIO(0x66d00) -#define HDCP_TRANSA_REP_PRESENT BIT(31) -#define HDCP_TRANSB_REP_PRESENT BIT(30) -#define HDCP_TRANSC_REP_PRESENT BIT(29) -#define HDCP_TRANSD_REP_PRESENT BIT(28) -#define HDCP_DDIB_REP_PRESENT BIT(30) -#define HDCP_DDIA_REP_PRESENT BIT(29) -#define HDCP_DDIC_REP_PRESENT BIT(28) -#define HDCP_DDID_REP_PRESENT BIT(27) -#define HDCP_DDIF_REP_PRESENT BIT(26) -#define HDCP_DDIE_REP_PRESENT BIT(25) -#define HDCP_TRANSA_SHA1_M0 (1 << 20) -#define HDCP_TRANSB_SHA1_M0 (2 << 20) -#define HDCP_TRANSC_SHA1_M0 (3 << 20) -#define HDCP_TRANSD_SHA1_M0 (4 << 20) -#define HDCP_DDIB_SHA1_M0 (1 << 20) -#define HDCP_DDIA_SHA1_M0 (2 << 20) -#define HDCP_DDIC_SHA1_M0 (3 << 20) -#define HDCP_DDID_SHA1_M0 (4 << 20) -#define HDCP_DDIF_SHA1_M0 (5 << 20) -#define HDCP_DDIE_SHA1_M0 (6 << 20) /* Bspec says 5? */ -#define HDCP_SHA1_BUSY BIT(16) -#define HDCP_SHA1_READY BIT(17) -#define HDCP_SHA1_COMPLETE BIT(18) -#define HDCP_SHA1_V_MATCH BIT(19) -#define HDCP_SHA1_TEXT_32 (1 << 1) -#define HDCP_SHA1_COMPLETE_HASH (2 << 1) -#define HDCP_SHA1_TEXT_24 (4 << 1) -#define HDCP_SHA1_TEXT_16 (5 << 1) -#define HDCP_SHA1_TEXT_8 (6 << 1) -#define HDCP_SHA1_TEXT_0 (7 << 1) -#define HDCP_SHA_V_PRIME_H0 _MMIO(0x66d04) -#define HDCP_SHA_V_PRIME_H1 _MMIO(0x66d08) -#define HDCP_SHA_V_PRIME_H2 _MMIO(0x66d0C) -#define HDCP_SHA_V_PRIME_H3 _MMIO(0x66d10) -#define HDCP_SHA_V_PRIME_H4 _MMIO(0x66d14) -#define HDCP_SHA_V_PRIME(h) _MMIO((0x66d04 + (h) * 4)) -#define HDCP_SHA_TEXT _MMIO(0x66d18) - -/* HDCP Auth Registers */ -#define _PORTA_HDCP_AUTHENC 0x66800 -#define _PORTB_HDCP_AUTHENC 0x66500 -#define _PORTC_HDCP_AUTHENC 0x66600 -#define _PORTD_HDCP_AUTHENC 0x66700 -#define _PORTE_HDCP_AUTHENC 0x66A00 -#define _PORTF_HDCP_AUTHENC 0x66900 -#define _PORT_HDCP_AUTHENC(port, x) _MMIO(_PICK(port, \ - _PORTA_HDCP_AUTHENC, \ - _PORTB_HDCP_AUTHENC, \ - _PORTC_HDCP_AUTHENC, \ - _PORTD_HDCP_AUTHENC, \ - _PORTE_HDCP_AUTHENC, \ - _PORTF_HDCP_AUTHENC) + (x)) -#define PORT_HDCP_CONF(port) _PORT_HDCP_AUTHENC(port, 0x0) -#define _TRANSA_HDCP_CONF 0x66400 -#define _TRANSB_HDCP_CONF 0x66500 -#define TRANS_HDCP_CONF(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_CONF, \ - _TRANSB_HDCP_CONF) -#define HDCP_CONF(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_CONF(trans) : \ - PORT_HDCP_CONF(port)) - -#define HDCP_CONF_CAPTURE_AN BIT(0) -#define HDCP_CONF_AUTH_AND_ENC (BIT(1) | BIT(0)) -#define PORT_HDCP_ANINIT(port) _PORT_HDCP_AUTHENC(port, 0x4) -#define _TRANSA_HDCP_ANINIT 0x66404 -#define _TRANSB_HDCP_ANINIT 0x66504 -#define TRANS_HDCP_ANINIT(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP_ANINIT, \ - _TRANSB_HDCP_ANINIT) -#define HDCP_ANINIT(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_ANINIT(trans) : \ - PORT_HDCP_ANINIT(port)) - -#define PORT_HDCP_ANLO(port) _PORT_HDCP_AUTHENC(port, 0x8) -#define _TRANSA_HDCP_ANLO 0x66408 -#define _TRANSB_HDCP_ANLO 0x66508 -#define TRANS_HDCP_ANLO(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_ANLO, \ - _TRANSB_HDCP_ANLO) -#define HDCP_ANLO(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_ANLO(trans) : \ - PORT_HDCP_ANLO(port)) - -#define PORT_HDCP_ANHI(port) _PORT_HDCP_AUTHENC(port, 0xC) -#define _TRANSA_HDCP_ANHI 0x6640C -#define _TRANSB_HDCP_ANHI 0x6650C -#define TRANS_HDCP_ANHI(trans) _MMIO_TRANS(trans, _TRANSA_HDCP_ANHI, \ - _TRANSB_HDCP_ANHI) -#define HDCP_ANHI(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_ANHI(trans) : \ - PORT_HDCP_ANHI(port)) - -#define PORT_HDCP_BKSVLO(port) _PORT_HDCP_AUTHENC(port, 0x10) -#define _TRANSA_HDCP_BKSVLO 0x66410 -#define _TRANSB_HDCP_BKSVLO 0x66510 -#define TRANS_HDCP_BKSVLO(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP_BKSVLO, \ - _TRANSB_HDCP_BKSVLO) -#define HDCP_BKSVLO(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_BKSVLO(trans) : \ - PORT_HDCP_BKSVLO(port)) - -#define PORT_HDCP_BKSVHI(port) _PORT_HDCP_AUTHENC(port, 0x14) -#define _TRANSA_HDCP_BKSVHI 0x66414 -#define _TRANSB_HDCP_BKSVHI 0x66514 -#define TRANS_HDCP_BKSVHI(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP_BKSVHI, \ - _TRANSB_HDCP_BKSVHI) -#define HDCP_BKSVHI(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_BKSVHI(trans) : \ - PORT_HDCP_BKSVHI(port)) - -#define PORT_HDCP_RPRIME(port) _PORT_HDCP_AUTHENC(port, 0x18) -#define _TRANSA_HDCP_RPRIME 0x66418 -#define _TRANSB_HDCP_RPRIME 0x66518 -#define TRANS_HDCP_RPRIME(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP_RPRIME, \ - _TRANSB_HDCP_RPRIME) -#define HDCP_RPRIME(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_RPRIME(trans) : \ - PORT_HDCP_RPRIME(port)) - -#define PORT_HDCP_STATUS(port) _PORT_HDCP_AUTHENC(port, 0x1C) -#define _TRANSA_HDCP_STATUS 0x6641C -#define _TRANSB_HDCP_STATUS 0x6651C -#define TRANS_HDCP_STATUS(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP_STATUS, \ - _TRANSB_HDCP_STATUS) -#define HDCP_STATUS(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP_STATUS(trans) : \ - PORT_HDCP_STATUS(port)) - -#define HDCP_STATUS_STREAM_A_ENC BIT(31) -#define HDCP_STATUS_STREAM_B_ENC BIT(30) -#define HDCP_STATUS_STREAM_C_ENC BIT(29) -#define HDCP_STATUS_STREAM_D_ENC BIT(28) -#define HDCP_STATUS_AUTH BIT(21) -#define HDCP_STATUS_ENC BIT(20) -#define HDCP_STATUS_RI_MATCH BIT(19) -#define HDCP_STATUS_R0_READY BIT(18) -#define HDCP_STATUS_AN_READY BIT(17) -#define HDCP_STATUS_CIPHER BIT(16) -#define HDCP_STATUS_FRAME_CNT(x) (((x) >> 8) & 0xff) - -/* HDCP2.2 Registers */ -#define _PORTA_HDCP2_BASE 0x66800 -#define _PORTB_HDCP2_BASE 0x66500 -#define _PORTC_HDCP2_BASE 0x66600 -#define _PORTD_HDCP2_BASE 0x66700 -#define _PORTE_HDCP2_BASE 0x66A00 -#define _PORTF_HDCP2_BASE 0x66900 -#define _PORT_HDCP2_BASE(port, x) _MMIO(_PICK((port), \ - _PORTA_HDCP2_BASE, \ - _PORTB_HDCP2_BASE, \ - _PORTC_HDCP2_BASE, \ - _PORTD_HDCP2_BASE, \ - _PORTE_HDCP2_BASE, \ - _PORTF_HDCP2_BASE) + (x)) - -#define PORT_HDCP2_AUTH(port) _PORT_HDCP2_BASE(port, 0x98) -#define _TRANSA_HDCP2_AUTH 0x66498 -#define _TRANSB_HDCP2_AUTH 0x66598 -#define TRANS_HDCP2_AUTH(trans) _MMIO_TRANS(trans, _TRANSA_HDCP2_AUTH, \ - _TRANSB_HDCP2_AUTH) -#define AUTH_LINK_AUTHENTICATED BIT(31) -#define AUTH_LINK_TYPE BIT(30) -#define AUTH_FORCE_CLR_INPUTCTR BIT(19) -#define AUTH_CLR_KEYS BIT(18) -#define HDCP2_AUTH(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP2_AUTH(trans) : \ - PORT_HDCP2_AUTH(port)) - -#define PORT_HDCP2_CTL(port) _PORT_HDCP2_BASE(port, 0xB0) -#define _TRANSA_HDCP2_CTL 0x664B0 -#define _TRANSB_HDCP2_CTL 0x665B0 -#define TRANS_HDCP2_CTL(trans) _MMIO_TRANS(trans, _TRANSA_HDCP2_CTL, \ - _TRANSB_HDCP2_CTL) -#define CTL_LINK_ENCRYPTION_REQ BIT(31) -#define HDCP2_CTL(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP2_CTL(trans) : \ - PORT_HDCP2_CTL(port)) - -#define PORT_HDCP2_STATUS(port) _PORT_HDCP2_BASE(port, 0xB4) -#define _TRANSA_HDCP2_STATUS 0x664B4 -#define _TRANSB_HDCP2_STATUS 0x665B4 -#define TRANS_HDCP2_STATUS(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP2_STATUS, \ - _TRANSB_HDCP2_STATUS) -#define LINK_TYPE_STATUS BIT(22) -#define LINK_AUTH_STATUS BIT(21) -#define LINK_ENCRYPTION_STATUS BIT(20) -#define HDCP2_STATUS(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP2_STATUS(trans) : \ - PORT_HDCP2_STATUS(port)) - -#define _PIPEA_HDCP2_STREAM_STATUS 0x668C0 -#define _PIPEB_HDCP2_STREAM_STATUS 0x665C0 -#define _PIPEC_HDCP2_STREAM_STATUS 0x666C0 -#define _PIPED_HDCP2_STREAM_STATUS 0x667C0 -#define PIPE_HDCP2_STREAM_STATUS(pipe) _MMIO(_PICK((pipe), \ - _PIPEA_HDCP2_STREAM_STATUS, \ - _PIPEB_HDCP2_STREAM_STATUS, \ - _PIPEC_HDCP2_STREAM_STATUS, \ - _PIPED_HDCP2_STREAM_STATUS)) - -#define _TRANSA_HDCP2_STREAM_STATUS 0x664C0 -#define _TRANSB_HDCP2_STREAM_STATUS 0x665C0 -#define TRANS_HDCP2_STREAM_STATUS(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP2_STREAM_STATUS, \ - _TRANSB_HDCP2_STREAM_STATUS) -#define STREAM_ENCRYPTION_STATUS BIT(31) -#define STREAM_TYPE_STATUS BIT(30) -#define HDCP2_STREAM_STATUS(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP2_STREAM_STATUS(trans) : \ - PIPE_HDCP2_STREAM_STATUS(pipe)) - -#define _PORTA_HDCP2_AUTH_STREAM 0x66F00 -#define _PORTB_HDCP2_AUTH_STREAM 0x66F04 -#define PORT_HDCP2_AUTH_STREAM(port) _MMIO_PORT(port, \ - _PORTA_HDCP2_AUTH_STREAM, \ - _PORTB_HDCP2_AUTH_STREAM) -#define _TRANSA_HDCP2_AUTH_STREAM 0x66F00 -#define _TRANSB_HDCP2_AUTH_STREAM 0x66F04 -#define TRANS_HDCP2_AUTH_STREAM(trans) _MMIO_TRANS(trans, \ - _TRANSA_HDCP2_AUTH_STREAM, \ - _TRANSB_HDCP2_AUTH_STREAM) -#define AUTH_STREAM_TYPE BIT(31) -#define HDCP2_AUTH_STREAM(dev_priv, trans, port) \ - (GRAPHICS_VER(dev_priv) >= 12 ? \ - TRANS_HDCP2_AUTH_STREAM(trans) : \ - PORT_HDCP2_AUTH_STREAM(port)) - /* Per-pipe DDI Function Control */ #define _TRANS_DDI_FUNC_CTL_A 0x60400 #define _TRANS_DDI_FUNC_CTL_B 0x61400 @@ -7503,16 +7126,16 @@ enum skl_power_gate { /* CDCLK_CTL */ #define CDCLK_CTL _MMIO(0x46000) -#define CDCLK_FREQ_SEL_MASK (3 << 26) -#define CDCLK_FREQ_450_432 (0 << 26) -#define CDCLK_FREQ_540 (1 << 26) -#define CDCLK_FREQ_337_308 (2 << 26) -#define CDCLK_FREQ_675_617 (3 << 26) -#define BXT_CDCLK_CD2X_DIV_SEL_MASK (3 << 22) -#define BXT_CDCLK_CD2X_DIV_SEL_1 (0 << 22) -#define BXT_CDCLK_CD2X_DIV_SEL_1_5 (1 << 22) -#define BXT_CDCLK_CD2X_DIV_SEL_2 (2 << 22) -#define BXT_CDCLK_CD2X_DIV_SEL_4 (3 << 22) +#define CDCLK_FREQ_SEL_MASK REG_GENMASK(27, 26) +#define CDCLK_FREQ_450_432 REG_FIELD_PREP(CDCLK_FREQ_SEL_MASK, 0) +#define CDCLK_FREQ_540 REG_FIELD_PREP(CDCLK_FREQ_SEL_MASK, 1) +#define CDCLK_FREQ_337_308 REG_FIELD_PREP(CDCLK_FREQ_SEL_MASK, 2) +#define CDCLK_FREQ_675_617 REG_FIELD_PREP(CDCLK_FREQ_SEL_MASK, 3) +#define BXT_CDCLK_CD2X_DIV_SEL_MASK REG_GENMASK(23, 22) +#define BXT_CDCLK_CD2X_DIV_SEL_1 REG_FIELD_PREP(BXT_CDCLK_CD2X_DIV_SEL_MASK, 0) +#define BXT_CDCLK_CD2X_DIV_SEL_1_5 REG_FIELD_PREP(BXT_CDCLK_CD2X_DIV_SEL_MASK, 1) +#define BXT_CDCLK_CD2X_DIV_SEL_2 REG_FIELD_PREP(BXT_CDCLK_CD2X_DIV_SEL_MASK, 2) +#define BXT_CDCLK_CD2X_DIV_SEL_4 REG_FIELD_PREP(BXT_CDCLK_CD2X_DIV_SEL_MASK, 3) #define BXT_CDCLK_CD2X_PIPE(pipe) ((pipe) << 20) #define CDCLK_DIVMUX_CD_OVERRIDE (1 << 19) #define BXT_CDCLK_CD2X_PIPE_NONE BXT_CDCLK_CD2X_PIPE(3) @@ -8367,6 +7990,7 @@ enum skl_power_gate { #define ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB, \ _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC) +#define DSC_ALT_ICH_SEL (1 << 20) #define DSC_VBR_ENABLE (1 << 19) #define DSC_422_ENABLE (1 << 18) #define DSC_COLOR_SPACE_CONVERSION (1 << 17) @@ -8717,4 +8341,27 @@ enum skl_power_gate { #define GEN12_CULLBIT2 _MMIO(0x7030) #define GEN12_STATE_ACK_DEBUG _MMIO(0x20BC) +#define MTL_LATENCY_LP0_LP1 _MMIO(0x45780) +#define MTL_LATENCY_LP2_LP3 _MMIO(0x45784) +#define MTL_LATENCY_LP4_LP5 _MMIO(0x45788) +#define MTL_LATENCY_LEVEL_EVEN_MASK REG_GENMASK(12, 0) +#define MTL_LATENCY_LEVEL_ODD_MASK REG_GENMASK(28, 16) + +#define MTL_LATENCY_SAGV _MMIO(0x4578b) +#define MTL_LATENCY_QCLK_SAGV REG_GENMASK(12, 0) + +#define MTL_MEM_SS_INFO_GLOBAL _MMIO(0x45700) +#define MTL_N_OF_ENABLED_QGV_POINTS_MASK REG_GENMASK(11, 8) +#define MTL_N_OF_POPULATED_CH_MASK REG_GENMASK(7, 4) +#define MTL_DDR_TYPE_MASK REG_GENMASK(3, 0) + +#define MTL_MEM_SS_INFO_QGV_POINT_LOW(point) _MMIO(0x45710 + (point) * 2) +#define MTL_TRCD_MASK REG_GENMASK(31, 24) +#define MTL_TRP_MASK REG_GENMASK(23, 16) +#define MTL_DCLK_MASK REG_GENMASK(15, 0) + +#define MTL_MEM_SS_INFO_QGV_POINT_HIGH(point) _MMIO(0x45714 + (point) * 2) +#define MTL_TRAS_MASK REG_GENMASK(16, 8) +#define MTL_TRDPRE_MASK REG_GENMASK(7, 0) + #endif /* _I915_REG_H_ */ diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index ae984c66c48a..6fc0d1b89690 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -241,8 +241,6 @@ void __i915_sw_fence_init(struct i915_sw_fence *fence, const char *name, struct lock_class_key *key) { - BUG_ON(!fn); - __init_waitqueue_head(&fence->wait, name, key); fence->fn = fn; #ifdef CONFIG_DRM_I915_SW_FENCE_CHECK_DAG diff --git a/drivers/gpu/drm/i915/i915_sw_fence.h b/drivers/gpu/drm/i915/i915_sw_fence.h index a7c603bc1b01..619fc5a22f0c 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.h +++ b/drivers/gpu/drm/i915/i915_sw_fence.h @@ -48,11 +48,15 @@ void __i915_sw_fence_init(struct i915_sw_fence *fence, do { \ static struct lock_class_key __key; \ \ + BUILD_BUG_ON((fn) == NULL); \ __i915_sw_fence_init((fence), (fn), #fence, &__key); \ } while (0) #else #define i915_sw_fence_init(fence, fn) \ - __i915_sw_fence_init((fence), (fn), NULL, NULL) +do { \ + BUILD_BUG_ON((fn) == NULL); \ + __i915_sw_fence_init((fence), (fn), NULL, NULL); \ +} while (0) #endif void i915_sw_fence_reinit(struct i915_sw_fence *fence); diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h index c10d68cdc3ca..6c14d13364bf 100644 --- a/drivers/gpu/drm/i915/i915_utils.h +++ b/drivers/gpu/drm/i915/i915_utils.h @@ -360,10 +360,6 @@ wait_remaining_ms_from_jiffies(unsigned long timestamp_jiffies, int to_wait_ms) #define KHz(x) (1000 * (x)) #define MHz(x) KHz(1000 * (x)) -#define KBps(x) (1000 * (x)) -#define MBps(x) KBps(1000 * (x)) -#define GBps(x) ((u64)1000 * MBps((x))) - void add_taint_for_CI(struct drm_i915_private *i915, unsigned int taint); static inline void __add_taint_for_CI(unsigned int taint) { diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c index d98fbbd589aa..20575eb77ea7 100644 --- a/drivers/gpu/drm/i915/intel_device_info.c +++ b/drivers/gpu/drm/i915/intel_device_info.c @@ -88,46 +88,57 @@ const char *intel_platform_name(enum intel_platform platform) return platform_names[platform]; } -void intel_device_info_print_static(const struct intel_device_info *info, - struct drm_printer *p) +void intel_device_info_print(const struct intel_device_info *info, + const struct intel_runtime_info *runtime, + struct drm_printer *p) { - if (info->graphics.rel) - drm_printf(p, "graphics version: %u.%02u\n", info->graphics.ver, - info->graphics.rel); + if (runtime->graphics.ip.rel) + drm_printf(p, "graphics version: %u.%02u\n", + runtime->graphics.ip.ver, + runtime->graphics.ip.rel); else - drm_printf(p, "graphics version: %u\n", info->graphics.ver); + drm_printf(p, "graphics version: %u\n", + runtime->graphics.ip.ver); - if (info->media.rel) - drm_printf(p, "media version: %u.%02u\n", info->media.ver, info->media.rel); + if (runtime->media.ip.rel) + drm_printf(p, "media version: %u.%02u\n", + runtime->media.ip.ver, + runtime->media.ip.rel); else - drm_printf(p, "media version: %u\n", info->media.ver); + drm_printf(p, "media version: %u\n", + runtime->media.ip.ver); - if (info->display.rel) - drm_printf(p, "display version: %u.%02u\n", info->display.ver, info->display.rel); + if (runtime->display.ip.rel) + drm_printf(p, "display version: %u.%02u\n", + runtime->display.ip.ver, + runtime->display.ip.rel); else - drm_printf(p, "display version: %u\n", info->display.ver); + drm_printf(p, "display version: %u\n", + runtime->display.ip.ver); drm_printf(p, "gt: %d\n", info->gt); - drm_printf(p, "memory-regions: %x\n", info->memory_regions); - drm_printf(p, "page-sizes: %x\n", info->page_sizes); + drm_printf(p, "memory-regions: %x\n", runtime->memory_regions); + drm_printf(p, "page-sizes: %x\n", runtime->page_sizes); drm_printf(p, "platform: %s\n", intel_platform_name(info->platform)); - drm_printf(p, "ppgtt-size: %d\n", info->ppgtt_size); - drm_printf(p, "ppgtt-type: %d\n", info->ppgtt_type); + drm_printf(p, "ppgtt-size: %d\n", runtime->ppgtt_size); + drm_printf(p, "ppgtt-type: %d\n", runtime->ppgtt_type); drm_printf(p, "dma_mask_size: %u\n", info->dma_mask_size); #define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, str_yes_no(info->name)) DEV_INFO_FOR_EACH_FLAG(PRINT_FLAG); #undef PRINT_FLAG + drm_printf(p, "has_pooled_eu: %s\n", str_yes_no(runtime->has_pooled_eu)); + #define PRINT_FLAG(name) drm_printf(p, "%s: %s\n", #name, str_yes_no(info->display.name)) DEV_INFO_DISPLAY_FOR_EACH_FLAG(PRINT_FLAG); #undef PRINT_FLAG -} -void intel_device_info_print_runtime(const struct intel_runtime_info *info, - struct drm_printer *p) -{ - drm_printf(p, "rawclk rate: %u kHz\n", info->rawclk_freq); + drm_printf(p, "has_hdcp: %s\n", str_yes_no(runtime->has_hdcp)); + drm_printf(p, "has_dmc: %s\n", str_yes_no(runtime->has_dmc)); + drm_printf(p, "has_dsc: %s\n", str_yes_no(runtime->has_dsc)); + + drm_printf(p, "rawclk rate: %u kHz\n", runtime->rawclk_freq); } #undef INTEL_VGA_DEVICE @@ -364,55 +375,55 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) !(sfuse_strap & SFUSE_STRAP_FUSE_LOCK))) { drm_info(&dev_priv->drm, "Display fused off, disabling\n"); - info->display.pipe_mask = 0; - info->display.cpu_transcoder_mask = 0; - info->display.fbc_mask = 0; + runtime->pipe_mask = 0; + runtime->cpu_transcoder_mask = 0; + runtime->fbc_mask = 0; } else if (fuse_strap & IVB_PIPE_C_DISABLE) { drm_info(&dev_priv->drm, "PipeC fused off\n"); - info->display.pipe_mask &= ~BIT(PIPE_C); - info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_C); + runtime->pipe_mask &= ~BIT(PIPE_C); + runtime->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } } else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) { u32 dfsm = intel_de_read(dev_priv, SKL_DFSM); if (dfsm & SKL_DFSM_PIPE_A_DISABLE) { - info->display.pipe_mask &= ~BIT(PIPE_A); - info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_A); - info->display.fbc_mask &= ~BIT(INTEL_FBC_A); + runtime->pipe_mask &= ~BIT(PIPE_A); + runtime->cpu_transcoder_mask &= ~BIT(TRANSCODER_A); + runtime->fbc_mask &= ~BIT(INTEL_FBC_A); } if (dfsm & SKL_DFSM_PIPE_B_DISABLE) { - info->display.pipe_mask &= ~BIT(PIPE_B); - info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_B); + runtime->pipe_mask &= ~BIT(PIPE_B); + runtime->cpu_transcoder_mask &= ~BIT(TRANSCODER_B); } if (dfsm & SKL_DFSM_PIPE_C_DISABLE) { - info->display.pipe_mask &= ~BIT(PIPE_C); - info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_C); + runtime->pipe_mask &= ~BIT(PIPE_C); + runtime->cpu_transcoder_mask &= ~BIT(TRANSCODER_C); } if (DISPLAY_VER(dev_priv) >= 12 && (dfsm & TGL_DFSM_PIPE_D_DISABLE)) { - info->display.pipe_mask &= ~BIT(PIPE_D); - info->display.cpu_transcoder_mask &= ~BIT(TRANSCODER_D); + runtime->pipe_mask &= ~BIT(PIPE_D); + runtime->cpu_transcoder_mask &= ~BIT(TRANSCODER_D); } if (dfsm & SKL_DFSM_DISPLAY_HDCP_DISABLE) - info->display.has_hdcp = 0; + runtime->has_hdcp = 0; if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE) - info->display.fbc_mask = 0; + runtime->fbc_mask = 0; if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE)) - info->display.has_dmc = 0; + runtime->has_dmc = 0; if (DISPLAY_VER(dev_priv) >= 10 && (dfsm & GLK_DFSM_DISPLAY_DSC_DISABLE)) - info->display.has_dsc = 0; + runtime->has_dsc = 0; } if (GRAPHICS_VER(dev_priv) == 6 && i915_vtd_active(dev_priv)) { drm_info(&dev_priv->drm, "Disabling ppGTT for VT-d support\n"); - info->ppgtt_type = INTEL_PPGTT_NONE; + runtime->ppgtt_type = INTEL_PPGTT_NONE; } runtime->rawclk_freq = intel_read_rawclk(dev_priv); @@ -422,8 +433,14 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv) dev_priv->drm.driver_features &= ~(DRIVER_MODESET | DRIVER_ATOMIC); memset(&info->display, 0, sizeof(info->display)); + + runtime->cpu_transcoder_mask = 0; memset(runtime->num_sprites, 0, sizeof(runtime->num_sprites)); memset(runtime->num_scalers, 0, sizeof(runtime->num_scalers)); + runtime->fbc_mask = 0; + runtime->has_hdcp = false; + runtime->has_dmc = false; + runtime->has_dsc = false; } } diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h index e681bc6ed8e9..d638235e1d26 100644 --- a/drivers/gpu/drm/i915/intel_device_info.h +++ b/drivers/gpu/drm/i915/intel_device_info.h @@ -37,6 +37,7 @@ struct drm_printer; struct drm_i915_private; +struct intel_gt_definition; /* Keep in gen based order, and chronological order within a gen */ enum intel_platform { @@ -164,7 +165,6 @@ enum intel_ppgtt_type { func(has_media_ratio_mode); \ func(has_mslice_steering); \ func(has_one_eu_per_fuse_bit); \ - func(has_pooled_eu); \ func(has_pxp); \ func(has_rc6); \ func(has_rc6p); \ @@ -180,14 +180,11 @@ enum intel_ppgtt_type { /* Keep in alphabetical order */ \ func(cursor_needs_physical); \ func(has_cdclk_crawl); \ - func(has_dmc); \ func(has_ddi); \ func(has_dp_mst); \ func(has_dsb); \ - func(has_dsc); \ func(has_fpga_dbg); \ func(has_gmch); \ - func(has_hdcp); \ func(has_hotplug); \ func(has_hti); \ func(has_ipc); \ @@ -203,23 +200,67 @@ struct ip_version { u8 rel; }; -struct intel_device_info { - struct ip_version graphics; - struct ip_version media; +struct intel_runtime_info { + struct { + struct ip_version ip; + } graphics; + struct { + struct ip_version ip; + } media; + struct { + struct ip_version ip; + } display; + + /* + * Platform mask is used for optimizing or-ed IS_PLATFORM calls into + * single runtime conditionals, and also to provide groundwork for + * future per platform, or per SKU build optimizations. + * + * Array can be extended when necessary if the corresponding + * BUILD_BUG_ON is hit. + */ + u32 platform_mask[2]; + + u16 device_id; intel_engine_mask_t platform_engine_mask; /* Engines supported by the HW */ - enum intel_platform platform; + u32 rawclk_freq; - unsigned int dma_mask_size; /* available DMA address bits */ + struct intel_step_info step; + + unsigned int page_sizes; /* page sizes supported by the HW */ enum intel_ppgtt_type ppgtt_type; unsigned int ppgtt_size; /* log2, e.g. 31/32/48 bits */ - unsigned int page_sizes; /* page sizes supported by the HW */ - u32 memory_regions; /* regions supported by the HW */ + bool has_pooled_eu; + + /* display */ + struct { + u8 pipe_mask; + u8 cpu_transcoder_mask; + + u8 num_sprites[I915_MAX_PIPES]; + u8 num_scalers[I915_MAX_PIPES]; + + u8 fbc_mask; + + bool has_hdcp; + bool has_dmc; + bool has_dsc; + }; +}; + +struct intel_device_info { + enum intel_platform platform; + + unsigned int dma_mask_size; /* available DMA address bits */ + + const struct intel_gt_definition *extra_gt_list; + u8 gt; /* GT number, 0 if undefined */ #define DEFINE_FLAG(name) u8 name:1 @@ -227,12 +268,6 @@ struct intel_device_info { #undef DEFINE_FLAG struct { - u8 ver; - u8 rel; - - u8 pipe_mask; - u8 cpu_transcoder_mask; - u8 fbc_mask; u8 abox_mask; struct { @@ -259,27 +294,11 @@ struct intel_device_info { u32 gamma_lut_tests; } color; } display; -}; -struct intel_runtime_info { /* - * Platform mask is used for optimizing or-ed IS_PLATFORM calls into - * into single runtime conditionals, and also to provide groundwork - * for future per platform, or per SKU build optimizations. - * - * Array can be extended when necessary if the corresponding - * BUILD_BUG_ON is hit. + * Initial runtime info. Do not access outside of i915_driver_create(). */ - u32 platform_mask[2]; - - u16 device_id; - - u8 num_sprites[I915_MAX_PIPES]; - u8 num_scalers[I915_MAX_PIPES]; - - u32 rawclk_freq; - - struct intel_step_info step; + const struct intel_runtime_info __runtime; }; struct intel_driver_caps { @@ -292,10 +311,9 @@ const char *intel_platform_name(enum intel_platform platform); void intel_device_info_subplatform_init(struct drm_i915_private *dev_priv); void intel_device_info_runtime_init(struct drm_i915_private *dev_priv); -void intel_device_info_print_static(const struct intel_device_info *info, - struct drm_printer *p); -void intel_device_info_print_runtime(const struct intel_runtime_info *info, - struct drm_printer *p); +void intel_device_info_print(const struct intel_device_info *info, + const struct intel_runtime_info *runtime, + struct drm_printer *p); void intel_driver_caps_print(const struct intel_driver_caps *caps, struct drm_printer *p); diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c index 437447119770..2403ccd52c74 100644 --- a/drivers/gpu/drm/i915/intel_dram.c +++ b/drivers/gpu/drm/i915/intel_dram.c @@ -466,6 +466,43 @@ static int gen12_get_dram_info(struct drm_i915_private *i915) return icl_pcode_read_mem_global_info(i915); } +static int xelpdp_get_dram_info(struct drm_i915_private *i915) +{ + u32 val = intel_uncore_read(&i915->uncore, MTL_MEM_SS_INFO_GLOBAL); + struct dram_info *dram_info = &i915->dram_info; + + val = REG_FIELD_GET(MTL_DDR_TYPE_MASK, val); + switch (val) { + case 0: + dram_info->type = INTEL_DRAM_DDR4; + break; + case 1: + dram_info->type = INTEL_DRAM_DDR5; + break; + case 2: + dram_info->type = INTEL_DRAM_LPDDR5; + break; + case 3: + dram_info->type = INTEL_DRAM_LPDDR4; + break; + case 4: + dram_info->type = INTEL_DRAM_DDR3; + break; + case 5: + dram_info->type = INTEL_DRAM_LPDDR3; + break; + default: + MISSING_CASE(val); + return -EINVAL; + } + + dram_info->num_channels = REG_FIELD_GET(MTL_N_OF_POPULATED_CH_MASK, val); + dram_info->num_qgv_points = REG_FIELD_GET(MTL_N_OF_ENABLED_QGV_POINTS_MASK, val); + /* PSF GV points not supported in D14+ */ + + return 0; +} + void intel_dram_detect(struct drm_i915_private *i915) { struct dram_info *dram_info = &i915->dram_info; @@ -480,7 +517,9 @@ void intel_dram_detect(struct drm_i915_private *i915) */ dram_info->wm_lv_0_adjust_needed = !IS_GEN9_LP(i915); - if (GRAPHICS_VER(i915) >= 12) + if (DISPLAY_VER(i915) >= 14) + ret = xelpdp_get_dram_info(i915); + else if (GRAPHICS_VER(i915) >= 12) ret = gen12_get_dram_info(i915); else if (GRAPHICS_VER(i915) >= 11) ret = gen11_get_dram_info(i915); diff --git a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c index 157e166672d7..8279dc580a3e 100644 --- a/drivers/gpu/drm/i915/intel_gvt_mmio_table.c +++ b/drivers/gpu/drm/i915/intel_gvt_mmio_table.c @@ -4,6 +4,7 @@ */ #include "display/intel_audio_regs.h" +#include "display/intel_backlight_regs.h" #include "display/intel_dmc_regs.h" #include "display/vlv_dsi_pll_regs.h" #include "gt/intel_gt_regs.h" @@ -1076,7 +1077,8 @@ static int iterate_skl_plus_mmio(struct intel_gvt_mmio_table_iter *iter) MMIO_D(GEN8_HDC_CHICKEN1); MMIO_D(GEN9_WM_CHICKEN3); - if (IS_KABYLAKE(dev_priv) || IS_COFFEELAKE(dev_priv)) + if (IS_KABYLAKE(dev_priv) || + IS_COFFEELAKE(dev_priv) || IS_COMETLAKE(dev_priv)) MMIO_D(GAMT_CHKN_BIT_REG); if (!IS_BROXTON(dev_priv)) MMIO_D(GEN9_CTX_PREEMPT_REG); diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c index 0fec25be146a..ba9843cb1b13 100644 --- a/drivers/gpu/drm/i915/intel_pch.c +++ b/drivers/gpu/drm/i915/intel_pch.c @@ -138,6 +138,11 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id) drm_WARN_ON(&dev_priv->drm, !IS_ALDERLAKE_S(dev_priv) && !IS_ALDERLAKE_P(dev_priv)); return PCH_ADP; + case INTEL_PCH_MTP_DEVICE_ID_TYPE: + case INTEL_PCH_MTP2_DEVICE_ID_TYPE: + drm_dbg_kms(&dev_priv->drm, "Found Meteor Lake PCH\n"); + drm_WARN_ON(&dev_priv->drm, !IS_METEORLAKE(dev_priv)); + return PCH_MTP; default: return PCH_NONE; } @@ -166,7 +171,9 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv, * make an educated guess as to which PCH is really there. */ - if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) + if (IS_METEORLAKE(dev_priv)) + id = INTEL_PCH_MTP_DEVICE_ID_TYPE; + else if (IS_ALDERLAKE_S(dev_priv) || IS_ALDERLAKE_P(dev_priv)) id = INTEL_PCH_ADP_DEVICE_ID_TYPE; else if (IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv)) id = INTEL_PCH_TGP_DEVICE_ID_TYPE; diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h index 7c8ce9781d1a..32aff5a70d04 100644 --- a/drivers/gpu/drm/i915/intel_pch.h +++ b/drivers/gpu/drm/i915/intel_pch.h @@ -25,6 +25,7 @@ enum intel_pch { PCH_ICP, /* Ice Lake/Jasper Lake PCH */ PCH_TGP, /* Tiger Lake/Mule Creek Canyon PCH */ PCH_ADP, /* Alder Lake PCH */ + PCH_MTP, /* Meteor Lake PCH */ /* Fake PCHs, functionality handled on the same PCI dev */ PCH_DG1 = 1024, @@ -57,12 +58,15 @@ enum intel_pch { #define INTEL_PCH_ADP2_DEVICE_ID_TYPE 0x5180 #define INTEL_PCH_ADP3_DEVICE_ID_TYPE 0x7A00 #define INTEL_PCH_ADP4_DEVICE_ID_TYPE 0x5480 +#define INTEL_PCH_MTP_DEVICE_ID_TYPE 0x7E00 +#define INTEL_PCH_MTP2_DEVICE_ID_TYPE 0xAE00 #define INTEL_PCH_P2X_DEVICE_ID_TYPE 0x7100 #define INTEL_PCH_P3X_DEVICE_ID_TYPE 0x7000 #define INTEL_PCH_QEMU_DEVICE_ID_TYPE 0x2900 /* qemu q35 has 2918 */ #define INTEL_PCH_TYPE(dev_priv) ((dev_priv)->pch_type) #define INTEL_PCH_ID(dev_priv) ((dev_priv)->pch_id) +#define HAS_PCH_MTP(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_MTP) #define HAS_PCH_DG2(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_DG2) #define HAS_PCH_ADP(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_ADP) #define HAS_PCH_DG1(dev_priv) (INTEL_PCH_TYPE(dev_priv) == PCH_DG1) diff --git a/drivers/gpu/drm/i915/intel_pci_config.h b/drivers/gpu/drm/i915/intel_pci_config.h index 12cd9d4f23de..4977a524ce6f 100644 --- a/drivers/gpu/drm/i915/intel_pci_config.h +++ b/drivers/gpu/drm/i915/intel_pci_config.h @@ -6,6 +6,13 @@ #ifndef __INTEL_PCI_CONFIG_H__ #define __INTEL_PCI_CONFIG_H__ +/* PCI BARs */ +#define GTTMMADR_BAR 0 +#define GEN2_GTTMMADR_BAR 1 +#define GFXMEM_BAR 2 +#define GTT_APERTURE_BAR GFXMEM_BAR +#define GEN12_LMEM_BAR GFXMEM_BAR + /* BSM in include/drm/i915_drm.h */ #define MCHBAR_I915 0x44 diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index ef7553b494ea..8f86f56e7ca4 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -25,60 +25,22 @@ * */ -#include <linux/module.h> -#include <linux/string_helpers.h> -#include <linux/pm_runtime.h> - -#include <drm/drm_atomic_helper.h> -#include <drm/drm_blend.h> -#include <drm/drm_fourcc.h> - -#include "display/intel_atomic.h" -#include "display/intel_atomic_plane.h" -#include "display/intel_bw.h" #include "display/intel_de.h" #include "display/intel_display_trace.h" -#include "display/intel_display_types.h" -#include "display/intel_fb.h" -#include "display/intel_fbc.h" -#include "display/intel_sprite.h" -#include "display/skl_universal_plane.h" +#include "display/skl_watermark.h" #include "gt/intel_engine_regs.h" #include "gt/intel_gt_regs.h" -#include "gt/intel_llc.h" #include "i915_drv.h" -#include "i915_fixed.h" -#include "i915_irq.h" #include "intel_mchbar_regs.h" -#include "intel_pcode.h" #include "intel_pm.h" #include "vlv_sideband.h" -#include "../../../platform/x86/intel_ips.h" - -static void skl_sagv_disable(struct drm_i915_private *dev_priv); struct drm_i915_clock_gating_funcs { void (*init_clock_gating)(struct drm_i915_private *i915); }; -/* Stores plane specific WM parameters */ -struct skl_wm_params { - bool x_tiled, y_tiled; - bool rc_surface; - bool is_planar; - u32 width; - u8 cpp; - u32 plane_pixel_rate; - u32 y_min_scanlines; - u32 plane_bytes_per_line; - uint_fixed_16_16_t plane_blocks_per_line; - uint_fixed_16_16_t y_tile_minimum; - u32 linetime_us; - u32 dbuf_block_size; -}; - /* used in computing the new watermarks state */ struct intel_wm_config { unsigned int num_pipes_active; @@ -468,13 +430,13 @@ bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable) { bool ret; - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); ret = _intel_set_memory_cxsr(dev_priv, enable); if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - dev_priv->wm.vlv.cxsr = enable; + dev_priv->display.wm.vlv.cxsr = enable; else if (IS_G4X(dev_priv)) - dev_priv->wm.g4x.cxsr = enable; - mutex_unlock(&dev_priv->wm.wm_mutex); + dev_priv->display.wm.g4x.cxsr = enable; + mutex_unlock(&dev_priv->display.wm.wm_mutex); return ret; } @@ -834,11 +796,11 @@ static bool is_enabling(int old, int new, int threshold) static int intel_wm_num_levels(struct drm_i915_private *dev_priv) { - return dev_priv->wm.max_level + 1; + return dev_priv->display.wm.max_level + 1; } -static bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) +bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state) { struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); @@ -1093,11 +1055,11 @@ static void vlv_write_wm_values(struct drm_i915_private *dev_priv, static void g4x_setup_wm_latency(struct drm_i915_private *dev_priv) { /* all latencies in usec */ - dev_priv->wm.pri_latency[G4X_WM_LEVEL_NORMAL] = 5; - dev_priv->wm.pri_latency[G4X_WM_LEVEL_SR] = 12; - dev_priv->wm.pri_latency[G4X_WM_LEVEL_HPLL] = 35; + dev_priv->display.wm.pri_latency[G4X_WM_LEVEL_NORMAL] = 5; + dev_priv->display.wm.pri_latency[G4X_WM_LEVEL_SR] = 12; + dev_priv->display.wm.pri_latency[G4X_WM_LEVEL_HPLL] = 35; - dev_priv->wm.max_level = G4X_WM_LEVEL_HPLL; + dev_priv->display.wm.max_level = G4X_WM_LEVEL_HPLL; } static int g4x_plane_fifo_size(enum plane_id plane_id, int level) @@ -1150,7 +1112,7 @@ static u16 g4x_compute_wm(const struct intel_crtc_state *crtc_state, struct drm_i915_private *dev_priv = to_i915(plane->base.dev); const struct drm_display_mode *pipe_mode = &crtc_state->hw.pipe_mode; - unsigned int latency = dev_priv->wm.pri_latency[level] * 10; + unsigned int latency = dev_priv->display.wm.pri_latency[level] * 10; unsigned int pixel_rate, htotal, cpp, width, wm; if (latency == 0) @@ -1324,7 +1286,7 @@ static bool g4x_raw_crtc_wm_is_valid(const struct intel_crtc_state *crtc_state, { struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - if (level > dev_priv->wm.max_level) + if (level > dev_priv->display.wm.max_level) return false; return g4x_raw_plane_wm_is_valid(crtc_state, PLANE_PRIMARY, level) && @@ -1583,7 +1545,7 @@ static void g4x_merge_wm(struct drm_i915_private *dev_priv, static void g4x_program_watermarks(struct drm_i915_private *dev_priv) { - struct g4x_wm_values *old_wm = &dev_priv->wm.g4x; + struct g4x_wm_values *old_wm = &dev_priv->display.wm.g4x; struct g4x_wm_values new_wm = {}; g4x_merge_wm(dev_priv, &new_wm); @@ -1609,10 +1571,10 @@ static void g4x_initial_watermarks(struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); crtc->wm.active.g4x = crtc_state->wm.g4x.intermediate; g4x_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } static void g4x_optimize_watermarks(struct intel_atomic_state *state, @@ -1625,10 +1587,10 @@ static void g4x_optimize_watermarks(struct intel_atomic_state *state, if (!crtc_state->wm.need_postvbl_update) return; - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); crtc->wm.active.g4x = crtc_state->wm.g4x.optimal; g4x_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } /* latency must be in 0.1us units. */ @@ -1650,15 +1612,15 @@ static unsigned int vlv_wm_method2(unsigned int pixel_rate, static void vlv_setup_wm_latency(struct drm_i915_private *dev_priv) { /* all latencies in usec */ - dev_priv->wm.pri_latency[VLV_WM_LEVEL_PM2] = 3; + dev_priv->display.wm.pri_latency[VLV_WM_LEVEL_PM2] = 3; - dev_priv->wm.max_level = VLV_WM_LEVEL_PM2; + dev_priv->display.wm.max_level = VLV_WM_LEVEL_PM2; if (IS_CHERRYVIEW(dev_priv)) { - dev_priv->wm.pri_latency[VLV_WM_LEVEL_PM5] = 12; - dev_priv->wm.pri_latency[VLV_WM_LEVEL_DDR_DVFS] = 33; + dev_priv->display.wm.pri_latency[VLV_WM_LEVEL_PM5] = 12; + dev_priv->display.wm.pri_latency[VLV_WM_LEVEL_DDR_DVFS] = 33; - dev_priv->wm.max_level = VLV_WM_LEVEL_DDR_DVFS; + dev_priv->display.wm.max_level = VLV_WM_LEVEL_DDR_DVFS; } } @@ -1672,7 +1634,7 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state, &crtc_state->hw.pipe_mode; unsigned int pixel_rate, htotal, cpp, width, wm; - if (dev_priv->wm.pri_latency[level] == 0) + if (dev_priv->display.wm.pri_latency[level] == 0) return USHRT_MAX; if (!intel_wm_plane_visible(crtc_state, plane_state)) @@ -1693,7 +1655,7 @@ static u16 vlv_compute_wm_level(const struct intel_crtc_state *crtc_state, wm = 63; } else { wm = vlv_wm_method2(pixel_rate, htotal, width, cpp, - dev_priv->wm.pri_latency[level] * 10); + dev_priv->display.wm.pri_latency[level] * 10); } return min_t(unsigned int, wm, USHRT_MAX); @@ -2158,7 +2120,7 @@ static void vlv_merge_wm(struct drm_i915_private *dev_priv, struct intel_crtc *crtc; int num_active_pipes = 0; - wm->level = dev_priv->wm.max_level; + wm->level = dev_priv->display.wm.max_level; wm->cxsr = true; for_each_intel_crtc(&dev_priv->drm, crtc) { @@ -2197,7 +2159,7 @@ static void vlv_merge_wm(struct drm_i915_private *dev_priv, static void vlv_program_watermarks(struct drm_i915_private *dev_priv) { - struct vlv_wm_values *old_wm = &dev_priv->wm.vlv; + struct vlv_wm_values *old_wm = &dev_priv->display.wm.vlv; struct vlv_wm_values new_wm = {}; vlv_merge_wm(dev_priv, &new_wm); @@ -2235,10 +2197,10 @@ static void vlv_initial_watermarks(struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); crtc->wm.active.vlv = crtc_state->wm.vlv.intermediate; vlv_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } static void vlv_optimize_watermarks(struct intel_atomic_state *state, @@ -2251,10 +2213,10 @@ static void vlv_optimize_watermarks(struct intel_atomic_state *state, if (!crtc_state->wm.need_postvbl_update) return; - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); crtc->wm.active.vlv = crtc_state->wm.vlv.optimal; vlv_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } static void i965_update_wm(struct drm_i915_private *dev_priv) @@ -2835,9 +2797,9 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, const struct intel_plane_state *curstate, struct intel_wm_level *result) { - u16 pri_latency = dev_priv->wm.pri_latency[level]; - u16 spr_latency = dev_priv->wm.spr_latency[level]; - u16 cur_latency = dev_priv->wm.cur_latency[level]; + u16 pri_latency = dev_priv->display.wm.pri_latency[level]; + u16 spr_latency = dev_priv->display.wm.spr_latency[level]; + u16 cur_latency = dev_priv->display.wm.cur_latency[level]; /* WM1+ latency values stored in 0.5us units */ if (level > 0) { @@ -2861,119 +2823,43 @@ static void ilk_compute_wm_level(const struct drm_i915_private *dev_priv, result->enable = true; } -static void intel_read_wm_latency(struct drm_i915_private *dev_priv, - u16 wm[]) +static void hsw_read_wm_latency(struct drm_i915_private *i915, u16 wm[]) { - struct intel_uncore *uncore = &dev_priv->uncore; - - if (DISPLAY_VER(dev_priv) >= 9) { - u32 val; - int ret, i; - int level, max_level = ilk_wm_max_level(dev_priv); - int mult = IS_DG2(dev_priv) ? 2 : 1; - - /* read the first set of memory latencies[0:3] */ - val = 0; /* data0 to be programmed to 0 for first set */ - ret = snb_pcode_read(&dev_priv->uncore, GEN9_PCODE_READ_MEM_LATENCY, - &val, NULL); + u64 sskpd; - if (ret) { - drm_err(&dev_priv->drm, - "SKL Mailbox read error = %d\n", ret); - return; - } - - wm[0] = (val & GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - wm[1] = ((val >> GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT) & - GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - wm[2] = ((val >> GEN9_MEM_LATENCY_LEVEL_2_6_SHIFT) & - GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - wm[3] = ((val >> GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT) & - GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - - /* read the second set of memory latencies[4:7] */ - val = 1; /* data0 to be programmed to 1 for second set */ - ret = snb_pcode_read(&dev_priv->uncore, GEN9_PCODE_READ_MEM_LATENCY, - &val, NULL); - if (ret) { - drm_err(&dev_priv->drm, - "SKL Mailbox read error = %d\n", ret); - return; - } + sskpd = intel_uncore_read64(&i915->uncore, MCH_SSKPD); - wm[4] = (val & GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - wm[5] = ((val >> GEN9_MEM_LATENCY_LEVEL_1_5_SHIFT) & - GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - wm[6] = ((val >> GEN9_MEM_LATENCY_LEVEL_2_6_SHIFT) & - GEN9_MEM_LATENCY_LEVEL_MASK) * mult; - wm[7] = ((val >> GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT) & - GEN9_MEM_LATENCY_LEVEL_MASK) * mult; + wm[0] = REG_FIELD_GET64(SSKPD_NEW_WM0_MASK_HSW, sskpd); + if (wm[0] == 0) + wm[0] = REG_FIELD_GET64(SSKPD_OLD_WM0_MASK_HSW, sskpd); + wm[1] = REG_FIELD_GET64(SSKPD_WM1_MASK_HSW, sskpd); + wm[2] = REG_FIELD_GET64(SSKPD_WM2_MASK_HSW, sskpd); + wm[3] = REG_FIELD_GET64(SSKPD_WM3_MASK_HSW, sskpd); + wm[4] = REG_FIELD_GET64(SSKPD_WM4_MASK_HSW, sskpd); +} - /* - * If a level n (n > 1) has a 0us latency, all levels m (m >= n) - * need to be disabled. We make sure to sanitize the values out - * of the punit to satisfy this requirement. - */ - for (level = 1; level <= max_level; level++) { - if (wm[level] == 0) { - for (i = level + 1; i <= max_level; i++) - wm[i] = 0; +static void snb_read_wm_latency(struct drm_i915_private *i915, u16 wm[]) +{ + u32 sskpd; - max_level = level - 1; + sskpd = intel_uncore_read(&i915->uncore, MCH_SSKPD); - break; - } - } + wm[0] = REG_FIELD_GET(SSKPD_WM0_MASK_SNB, sskpd); + wm[1] = REG_FIELD_GET(SSKPD_WM1_MASK_SNB, sskpd); + wm[2] = REG_FIELD_GET(SSKPD_WM2_MASK_SNB, sskpd); + wm[3] = REG_FIELD_GET(SSKPD_WM3_MASK_SNB, sskpd); +} - /* - * WaWmMemoryReadLatency - * - * punit doesn't take into account the read latency so we need - * to add proper adjustement to each valid level we retrieve - * from the punit when level 0 response data is 0us. - */ - if (wm[0] == 0) { - u8 adjust = DISPLAY_VER(dev_priv) >= 12 ? 3 : 2; +static void ilk_read_wm_latency(struct drm_i915_private *i915, u16 wm[]) +{ + u32 mltr; - for (level = 0; level <= max_level; level++) - wm[level] += adjust; - } + mltr = intel_uncore_read(&i915->uncore, MLTR_ILK); - /* - * WA Level-0 adjustment for 16GB DIMMs: SKL+ - * If we could not get dimm info enable this WA to prevent from - * any underrun. If not able to get Dimm info assume 16GB dimm - * to avoid any underrun. - */ - if (dev_priv->dram_info.wm_lv_0_adjust_needed) - wm[0] += 1; - } else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) { - u64 sskpd = intel_uncore_read64(uncore, MCH_SSKPD); - - wm[0] = REG_FIELD_GET64(SSKPD_NEW_WM0_MASK_HSW, sskpd); - if (wm[0] == 0) - wm[0] = REG_FIELD_GET64(SSKPD_OLD_WM0_MASK_HSW, sskpd); - wm[1] = REG_FIELD_GET64(SSKPD_WM1_MASK_HSW, sskpd); - wm[2] = REG_FIELD_GET64(SSKPD_WM2_MASK_HSW, sskpd); - wm[3] = REG_FIELD_GET64(SSKPD_WM3_MASK_HSW, sskpd); - wm[4] = REG_FIELD_GET64(SSKPD_WM4_MASK_HSW, sskpd); - } else if (DISPLAY_VER(dev_priv) >= 6) { - u32 sskpd = intel_uncore_read(uncore, MCH_SSKPD); - - wm[0] = REG_FIELD_GET(SSKPD_WM0_MASK_SNB, sskpd); - wm[1] = REG_FIELD_GET(SSKPD_WM1_MASK_SNB, sskpd); - wm[2] = REG_FIELD_GET(SSKPD_WM2_MASK_SNB, sskpd); - wm[3] = REG_FIELD_GET(SSKPD_WM3_MASK_SNB, sskpd); - } else if (DISPLAY_VER(dev_priv) >= 5) { - u32 mltr = intel_uncore_read(uncore, MLTR_ILK); - - /* ILK primary LP0 latency is 700 ns */ - wm[0] = 7; - wm[1] = REG_FIELD_GET(MLTR_WM1_MASK, mltr); - wm[2] = REG_FIELD_GET(MLTR_WM2_MASK, mltr); - } else { - MISSING_CASE(INTEL_DEVID(dev_priv)); - } + /* ILK primary LP0 latency is 700 ns */ + wm[0] = 7; + wm[1] = REG_FIELD_GET(MLTR_WM1_MASK, mltr); + wm[2] = REG_FIELD_GET(MLTR_WM2_MASK, mltr); } static void intel_fixup_spr_wm_latency(struct drm_i915_private *dev_priv, @@ -3007,9 +2893,8 @@ int ilk_wm_max_level(const struct drm_i915_private *dev_priv) return 2; } -static void intel_print_wm_latency(struct drm_i915_private *dev_priv, - const char *name, - const u16 wm[]) +void intel_print_wm_latency(struct drm_i915_private *dev_priv, + const char *name, const u16 wm[]) { int level, max_level = ilk_wm_max_level(dev_priv); @@ -3061,18 +2946,18 @@ static void snb_wm_latency_quirk(struct drm_i915_private *dev_priv) * The BIOS provided WM memory latency values are often * inadequate for high resolution displays. Adjust them. */ - changed = ilk_increase_wm_latency(dev_priv, dev_priv->wm.pri_latency, 12); - changed |= ilk_increase_wm_latency(dev_priv, dev_priv->wm.spr_latency, 12); - changed |= ilk_increase_wm_latency(dev_priv, dev_priv->wm.cur_latency, 12); + changed = ilk_increase_wm_latency(dev_priv, dev_priv->display.wm.pri_latency, 12); + changed |= ilk_increase_wm_latency(dev_priv, dev_priv->display.wm.spr_latency, 12); + changed |= ilk_increase_wm_latency(dev_priv, dev_priv->display.wm.cur_latency, 12); if (!changed) return; drm_dbg_kms(&dev_priv->drm, "WM latency values increased to avoid potential underruns\n"); - intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency); - intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency); - intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency); + intel_print_wm_latency(dev_priv, "Primary", dev_priv->display.wm.pri_latency); + intel_print_wm_latency(dev_priv, "Sprite", dev_priv->display.wm.spr_latency); + intel_print_wm_latency(dev_priv, "Cursor", dev_priv->display.wm.cur_latency); } static void snb_wm_lp3_irq_quirk(struct drm_i915_private *dev_priv) @@ -3088,37 +2973,42 @@ static void snb_wm_lp3_irq_quirk(struct drm_i915_private *dev_priv) * interrupts only. To play it safe we disable LP3 * watermarks entirely. */ - if (dev_priv->wm.pri_latency[3] == 0 && - dev_priv->wm.spr_latency[3] == 0 && - dev_priv->wm.cur_latency[3] == 0) + if (dev_priv->display.wm.pri_latency[3] == 0 && + dev_priv->display.wm.spr_latency[3] == 0 && + dev_priv->display.wm.cur_latency[3] == 0) return; - dev_priv->wm.pri_latency[3] = 0; - dev_priv->wm.spr_latency[3] = 0; - dev_priv->wm.cur_latency[3] = 0; + dev_priv->display.wm.pri_latency[3] = 0; + dev_priv->display.wm.spr_latency[3] = 0; + dev_priv->display.wm.cur_latency[3] = 0; drm_dbg_kms(&dev_priv->drm, "LP3 watermarks disabled due to potential for lost interrupts\n"); - intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency); - intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency); - intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency); + intel_print_wm_latency(dev_priv, "Primary", dev_priv->display.wm.pri_latency); + intel_print_wm_latency(dev_priv, "Sprite", dev_priv->display.wm.spr_latency); + intel_print_wm_latency(dev_priv, "Cursor", dev_priv->display.wm.cur_latency); } static void ilk_setup_wm_latency(struct drm_i915_private *dev_priv) { - intel_read_wm_latency(dev_priv, dev_priv->wm.pri_latency); + if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) + hsw_read_wm_latency(dev_priv, dev_priv->display.wm.pri_latency); + else if (DISPLAY_VER(dev_priv) >= 6) + snb_read_wm_latency(dev_priv, dev_priv->display.wm.pri_latency); + else + ilk_read_wm_latency(dev_priv, dev_priv->display.wm.pri_latency); - memcpy(dev_priv->wm.spr_latency, dev_priv->wm.pri_latency, - sizeof(dev_priv->wm.pri_latency)); - memcpy(dev_priv->wm.cur_latency, dev_priv->wm.pri_latency, - sizeof(dev_priv->wm.pri_latency)); + memcpy(dev_priv->display.wm.spr_latency, dev_priv->display.wm.pri_latency, + sizeof(dev_priv->display.wm.pri_latency)); + memcpy(dev_priv->display.wm.cur_latency, dev_priv->display.wm.pri_latency, + sizeof(dev_priv->display.wm.pri_latency)); - intel_fixup_spr_wm_latency(dev_priv, dev_priv->wm.spr_latency); - intel_fixup_cur_wm_latency(dev_priv, dev_priv->wm.cur_latency); + intel_fixup_spr_wm_latency(dev_priv, dev_priv->display.wm.spr_latency); + intel_fixup_cur_wm_latency(dev_priv, dev_priv->display.wm.cur_latency); - intel_print_wm_latency(dev_priv, "Primary", dev_priv->wm.pri_latency); - intel_print_wm_latency(dev_priv, "Sprite", dev_priv->wm.spr_latency); - intel_print_wm_latency(dev_priv, "Cursor", dev_priv->wm.cur_latency); + intel_print_wm_latency(dev_priv, "Primary", dev_priv->display.wm.pri_latency); + intel_print_wm_latency(dev_priv, "Sprite", dev_priv->display.wm.spr_latency); + intel_print_wm_latency(dev_priv, "Cursor", dev_priv->display.wm.cur_latency); if (DISPLAY_VER(dev_priv) == 6) { snb_wm_latency_quirk(dev_priv); @@ -3126,12 +3016,6 @@ static void ilk_setup_wm_latency(struct drm_i915_private *dev_priv) } } -static void skl_setup_wm_latency(struct drm_i915_private *dev_priv) -{ - intel_read_wm_latency(dev_priv, dev_priv->wm.skl_latency); - intel_print_wm_latency(dev_priv, "Gen9 Plane", dev_priv->wm.skl_latency); -} - static bool ilk_validate_pipe_wm(const struct drm_i915_private *dev_priv, struct intel_pipe_wm *pipe_wm) { @@ -3386,7 +3270,7 @@ static unsigned int ilk_wm_lp_latency(struct drm_i915_private *dev_priv, if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) return 2 * level; else - return dev_priv->wm.pri_latency[level]; + return dev_priv->display.wm.pri_latency[level]; } static void ilk_compute_wm_results(struct drm_i915_private *dev_priv, @@ -3538,7 +3422,7 @@ static unsigned int ilk_compute_wm_dirty(struct drm_i915_private *dev_priv, static bool _ilk_disable_lp_wm(struct drm_i915_private *dev_priv, unsigned int dirty) { - struct ilk_wm_values *previous = &dev_priv->wm.hw; + struct ilk_wm_values *previous = &dev_priv->display.wm.hw; bool changed = false; if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] & WM_LP_ENABLE) { @@ -3572,7 +3456,7 @@ static bool _ilk_disable_lp_wm(struct drm_i915_private *dev_priv, static void ilk_write_wm_values(struct drm_i915_private *dev_priv, struct ilk_wm_values *results) { - struct ilk_wm_values *previous = &dev_priv->wm.hw; + struct ilk_wm_values *previous = &dev_priv->display.wm.hw; unsigned int dirty; u32 val; @@ -3634,7 +3518,7 @@ static void ilk_write_wm_values(struct drm_i915_private *dev_priv, if (dirty & WM_DIRTY_LP(3) && previous->wm_lp[2] != results->wm_lp[2]) intel_uncore_write(&dev_priv->uncore, WM3_LP_ILK, results->wm_lp[2]); - dev_priv->wm.hw = *results; + dev_priv->display.wm.hw = *results; } bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv) @@ -3642,2765 +3526,6 @@ bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv) return _ilk_disable_lp_wm(dev_priv, WM_DIRTY_LP_ALL); } -u8 intel_enabled_dbuf_slices_mask(struct drm_i915_private *dev_priv) -{ - u8 enabled_slices = 0; - enum dbuf_slice slice; - - for_each_dbuf_slice(dev_priv, slice) { - if (intel_uncore_read(&dev_priv->uncore, - DBUF_CTL_S(slice)) & DBUF_POWER_STATE) - enabled_slices |= BIT(slice); - } - - return enabled_slices; -} - -/* - * FIXME: We still don't have the proper code detect if we need to apply the WA, - * so assume we'll always need it in order to avoid underruns. - */ -static bool skl_needs_memory_bw_wa(struct drm_i915_private *dev_priv) -{ - return DISPLAY_VER(dev_priv) == 9; -} - -static bool -intel_has_sagv(struct drm_i915_private *dev_priv) -{ - return DISPLAY_VER(dev_priv) >= 9 && !IS_LP(dev_priv) && - dev_priv->sagv_status != I915_SAGV_NOT_CONTROLLED; -} - -static u32 -intel_sagv_block_time(struct drm_i915_private *dev_priv) -{ - if (DISPLAY_VER(dev_priv) >= 12) { - u32 val = 0; - int ret; - - ret = snb_pcode_read(&dev_priv->uncore, - GEN12_PCODE_READ_SAGV_BLOCK_TIME_US, - &val, NULL); - if (ret) { - drm_dbg_kms(&dev_priv->drm, "Couldn't read SAGV block time!\n"); - return 0; - } - - return val; - } else if (DISPLAY_VER(dev_priv) == 11) { - return 10; - } else if (DISPLAY_VER(dev_priv) == 9 && !IS_LP(dev_priv)) { - return 30; - } else { - return 0; - } -} - -static void intel_sagv_init(struct drm_i915_private *i915) -{ - if (!intel_has_sagv(i915)) - i915->sagv_status = I915_SAGV_NOT_CONTROLLED; - - /* - * Probe to see if we have working SAGV control. - * For icl+ this was already determined by intel_bw_init_hw(). - */ - if (DISPLAY_VER(i915) < 11) - skl_sagv_disable(i915); - - drm_WARN_ON(&i915->drm, i915->sagv_status == I915_SAGV_UNKNOWN); - - i915->sagv_block_time_us = intel_sagv_block_time(i915); - - drm_dbg_kms(&i915->drm, "SAGV supported: %s, original SAGV block time: %u us\n", - str_yes_no(intel_has_sagv(i915)), i915->sagv_block_time_us); - - /* avoid overflow when adding with wm0 latency/etc. */ - if (drm_WARN(&i915->drm, i915->sagv_block_time_us > U16_MAX, - "Excessive SAGV block time %u, ignoring\n", - i915->sagv_block_time_us)) - i915->sagv_block_time_us = 0; - - if (!intel_has_sagv(i915)) - i915->sagv_block_time_us = 0; -} - -/* - * SAGV dynamically adjusts the system agent voltage and clock frequencies - * depending on power and performance requirements. The display engine access - * to system memory is blocked during the adjustment time. Because of the - * blocking time, having this enabled can cause full system hangs and/or pipe - * underruns if we don't meet all of the following requirements: - * - * - <= 1 pipe enabled - * - All planes can enable watermarks for latencies >= SAGV engine block time - * - We're not using an interlaced display configuration - */ -static void skl_sagv_enable(struct drm_i915_private *dev_priv) -{ - int ret; - - if (!intel_has_sagv(dev_priv)) - return; - - if (dev_priv->sagv_status == I915_SAGV_ENABLED) - return; - - drm_dbg_kms(&dev_priv->drm, "Enabling SAGV\n"); - ret = snb_pcode_write(&dev_priv->uncore, GEN9_PCODE_SAGV_CONTROL, - GEN9_SAGV_ENABLE); - - /* We don't need to wait for SAGV when enabling */ - - /* - * Some skl systems, pre-release machines in particular, - * don't actually have SAGV. - */ - if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) { - drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n"); - dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED; - return; - } else if (ret < 0) { - drm_err(&dev_priv->drm, "Failed to enable SAGV\n"); - return; - } - - dev_priv->sagv_status = I915_SAGV_ENABLED; -} - -static void skl_sagv_disable(struct drm_i915_private *dev_priv) -{ - int ret; - - if (!intel_has_sagv(dev_priv)) - return; - - if (dev_priv->sagv_status == I915_SAGV_DISABLED) - return; - - drm_dbg_kms(&dev_priv->drm, "Disabling SAGV\n"); - /* bspec says to keep retrying for at least 1 ms */ - ret = skl_pcode_request(&dev_priv->uncore, GEN9_PCODE_SAGV_CONTROL, - GEN9_SAGV_DISABLE, - GEN9_SAGV_IS_DISABLED, GEN9_SAGV_IS_DISABLED, - 1); - /* - * Some skl systems, pre-release machines in particular, - * don't actually have SAGV. - */ - if (IS_SKYLAKE(dev_priv) && ret == -ENXIO) { - drm_dbg(&dev_priv->drm, "No SAGV found on system, ignoring\n"); - dev_priv->sagv_status = I915_SAGV_NOT_CONTROLLED; - return; - } else if (ret < 0) { - drm_err(&dev_priv->drm, "Failed to disable SAGV (%d)\n", ret); - return; - } - - dev_priv->sagv_status = I915_SAGV_DISABLED; -} - -static void skl_sagv_pre_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *i915 = to_i915(state->base.dev); - const struct intel_bw_state *new_bw_state = - intel_atomic_get_new_bw_state(state); - - if (!new_bw_state) - return; - - if (!intel_can_enable_sagv(i915, new_bw_state)) - skl_sagv_disable(i915); -} - -static void skl_sagv_post_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *i915 = to_i915(state->base.dev); - const struct intel_bw_state *new_bw_state = - intel_atomic_get_new_bw_state(state); - - if (!new_bw_state) - return; - - if (intel_can_enable_sagv(i915, new_bw_state)) - skl_sagv_enable(i915); -} - -static void icl_sagv_pre_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_bw_state *old_bw_state = - intel_atomic_get_old_bw_state(state); - const struct intel_bw_state *new_bw_state = - intel_atomic_get_new_bw_state(state); - u16 old_mask, new_mask; - - if (!new_bw_state) - return; - - old_mask = old_bw_state->qgv_points_mask; - new_mask = old_bw_state->qgv_points_mask | new_bw_state->qgv_points_mask; - - if (old_mask == new_mask) - return; - - WARN_ON(!new_bw_state->base.changed); - - drm_dbg_kms(&dev_priv->drm, "Restricting QGV points: 0x%x -> 0x%x\n", - old_mask, new_mask); - - /* - * Restrict required qgv points before updating the configuration. - * According to BSpec we can't mask and unmask qgv points at the same - * time. Also masking should be done before updating the configuration - * and unmasking afterwards. - */ - icl_pcode_restrict_qgv_points(dev_priv, new_mask); -} - -static void icl_sagv_post_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_bw_state *old_bw_state = - intel_atomic_get_old_bw_state(state); - const struct intel_bw_state *new_bw_state = - intel_atomic_get_new_bw_state(state); - u16 old_mask, new_mask; - - if (!new_bw_state) - return; - - old_mask = old_bw_state->qgv_points_mask | new_bw_state->qgv_points_mask; - new_mask = new_bw_state->qgv_points_mask; - - if (old_mask == new_mask) - return; - - WARN_ON(!new_bw_state->base.changed); - - drm_dbg_kms(&dev_priv->drm, "Relaxing QGV points: 0x%x -> 0x%x\n", - old_mask, new_mask); - - /* - * Allow required qgv points after updating the configuration. - * According to BSpec we can't mask and unmask qgv points at the same - * time. Also masking should be done before updating the configuration - * and unmasking afterwards. - */ - icl_pcode_restrict_qgv_points(dev_priv, new_mask); -} - -void intel_sagv_pre_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *i915 = to_i915(state->base.dev); - - /* - * Just return if we can't control SAGV or don't have it. - * This is different from situation when we have SAGV but just can't - * afford it due to DBuf limitation - in case if SAGV is completely - * disabled in a BIOS, we are not even allowed to send a PCode request, - * as it will throw an error. So have to check it here. - */ - if (!intel_has_sagv(i915)) - return; - - if (DISPLAY_VER(i915) >= 11) - icl_sagv_pre_plane_update(state); - else - skl_sagv_pre_plane_update(state); -} - -void intel_sagv_post_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *i915 = to_i915(state->base.dev); - - /* - * Just return if we can't control SAGV or don't have it. - * This is different from situation when we have SAGV but just can't - * afford it due to DBuf limitation - in case if SAGV is completely - * disabled in a BIOS, we are not even allowed to send a PCode request, - * as it will throw an error. So have to check it here. - */ - if (!intel_has_sagv(i915)) - return; - - if (DISPLAY_VER(i915) >= 11) - icl_sagv_post_plane_update(state); - else - skl_sagv_post_plane_update(state); -} - -static bool skl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum plane_id plane_id; - int max_level = INT_MAX; - - if (!intel_has_sagv(dev_priv)) - return false; - - if (!crtc_state->hw.active) - return true; - - if (crtc_state->hw.pipe_mode.flags & DRM_MODE_FLAG_INTERLACE) - return false; - - for_each_plane_id_on_crtc(crtc, plane_id) { - const struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - int level; - - /* Skip this plane if it's not enabled */ - if (!wm->wm[0].enable) - continue; - - /* Find the highest enabled wm level for this plane */ - for (level = ilk_wm_max_level(dev_priv); - !wm->wm[level].enable; --level) - { } - - /* Highest common enabled wm level for all planes */ - max_level = min(level, max_level); - } - - /* No enabled planes? */ - if (max_level == INT_MAX) - return true; - - for_each_plane_id_on_crtc(crtc, plane_id) { - const struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - - /* - * All enabled planes must have enabled a common wm level that - * can tolerate memory latencies higher than sagv_block_time_us - */ - if (wm->wm[0].enable && !wm->wm[max_level].can_sagv) - return false; - } - - return true; -} - -static bool tgl_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - enum plane_id plane_id; - - if (!crtc_state->hw.active) - return true; - - for_each_plane_id_on_crtc(crtc, plane_id) { - const struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - - if (wm->wm[0].enable && !wm->sagv.wm0.enable) - return false; - } - - return true; -} - -static bool intel_crtc_can_enable_sagv(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - - if (DISPLAY_VER(dev_priv) >= 12) - return tgl_crtc_can_enable_sagv(crtc_state); - else - return skl_crtc_can_enable_sagv(crtc_state); -} - -bool intel_can_enable_sagv(struct drm_i915_private *dev_priv, - const struct intel_bw_state *bw_state) -{ - if (DISPLAY_VER(dev_priv) < 11 && - bw_state->active_pipes && !is_power_of_2(bw_state->active_pipes)) - return false; - - return bw_state->pipe_sagv_reject == 0; -} - -static int intel_compute_sagv_mask(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - int ret; - struct intel_crtc *crtc; - struct intel_crtc_state *new_crtc_state; - struct intel_bw_state *new_bw_state = NULL; - const struct intel_bw_state *old_bw_state = NULL; - int i; - - for_each_new_intel_crtc_in_state(state, crtc, - new_crtc_state, i) { - new_bw_state = intel_atomic_get_bw_state(state); - if (IS_ERR(new_bw_state)) - return PTR_ERR(new_bw_state); - - old_bw_state = intel_atomic_get_old_bw_state(state); - - if (intel_crtc_can_enable_sagv(new_crtc_state)) - new_bw_state->pipe_sagv_reject &= ~BIT(crtc->pipe); - else - new_bw_state->pipe_sagv_reject |= BIT(crtc->pipe); - } - - if (!new_bw_state) - return 0; - - new_bw_state->active_pipes = - intel_calc_active_pipes(state, old_bw_state->active_pipes); - - if (new_bw_state->active_pipes != old_bw_state->active_pipes) { - ret = intel_atomic_lock_global_state(&new_bw_state->base); - if (ret) - return ret; - } - - if (intel_can_enable_sagv(dev_priv, new_bw_state) != - intel_can_enable_sagv(dev_priv, old_bw_state)) { - ret = intel_atomic_serialize_global_state(&new_bw_state->base); - if (ret) - return ret; - } else if (new_bw_state->pipe_sagv_reject != old_bw_state->pipe_sagv_reject) { - ret = intel_atomic_lock_global_state(&new_bw_state->base); - if (ret) - return ret; - } - - for_each_new_intel_crtc_in_state(state, crtc, - new_crtc_state, i) { - struct skl_pipe_wm *pipe_wm = &new_crtc_state->wm.skl.optimal; - - /* - * We store use_sagv_wm in the crtc state rather than relying on - * that bw state since we have no convenient way to get at the - * latter from the plane commit hooks (especially in the legacy - * cursor case) - */ - pipe_wm->use_sagv_wm = !HAS_HW_SAGV_WM(dev_priv) && - DISPLAY_VER(dev_priv) >= 12 && - intel_can_enable_sagv(dev_priv, new_bw_state); - } - - return 0; -} - -static u16 skl_ddb_entry_init(struct skl_ddb_entry *entry, - u16 start, u16 end) -{ - entry->start = start; - entry->end = end; - - return end; -} - -static int intel_dbuf_slice_size(struct drm_i915_private *dev_priv) -{ - return INTEL_INFO(dev_priv)->display.dbuf.size / - hweight8(INTEL_INFO(dev_priv)->display.dbuf.slice_mask); -} - -static void -skl_ddb_entry_for_slices(struct drm_i915_private *dev_priv, u8 slice_mask, - struct skl_ddb_entry *ddb) -{ - int slice_size = intel_dbuf_slice_size(dev_priv); - - if (!slice_mask) { - ddb->start = 0; - ddb->end = 0; - return; - } - - ddb->start = (ffs(slice_mask) - 1) * slice_size; - ddb->end = fls(slice_mask) * slice_size; - - WARN_ON(ddb->start >= ddb->end); - WARN_ON(ddb->end > INTEL_INFO(dev_priv)->display.dbuf.size); -} - -static unsigned int mbus_ddb_offset(struct drm_i915_private *i915, u8 slice_mask) -{ - struct skl_ddb_entry ddb; - - if (slice_mask & (BIT(DBUF_S1) | BIT(DBUF_S2))) - slice_mask = BIT(DBUF_S1); - else if (slice_mask & (BIT(DBUF_S3) | BIT(DBUF_S4))) - slice_mask = BIT(DBUF_S3); - - skl_ddb_entry_for_slices(i915, slice_mask, &ddb); - - return ddb.start; -} - -u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *dev_priv, - const struct skl_ddb_entry *entry) -{ - int slice_size = intel_dbuf_slice_size(dev_priv); - enum dbuf_slice start_slice, end_slice; - u8 slice_mask = 0; - - if (!skl_ddb_entry_size(entry)) - return 0; - - start_slice = entry->start / slice_size; - end_slice = (entry->end - 1) / slice_size; - - /* - * Per plane DDB entry can in a really worst case be on multiple slices - * but single entry is anyway contigious. - */ - while (start_slice <= end_slice) { - slice_mask |= BIT(start_slice); - start_slice++; - } - - return slice_mask; -} - -static unsigned int intel_crtc_ddb_weight(const struct intel_crtc_state *crtc_state) -{ - const struct drm_display_mode *pipe_mode = &crtc_state->hw.pipe_mode; - int hdisplay, vdisplay; - - if (!crtc_state->hw.active) - return 0; - - /* - * Watermark/ddb requirement highly depends upon width of the - * framebuffer, So instead of allocating DDB equally among pipes - * distribute DDB based on resolution/width of the display. - */ - drm_mode_get_hv_timing(pipe_mode, &hdisplay, &vdisplay); - - return hdisplay; -} - -static void intel_crtc_dbuf_weights(const struct intel_dbuf_state *dbuf_state, - enum pipe for_pipe, - unsigned int *weight_start, - unsigned int *weight_end, - unsigned int *weight_total) -{ - struct drm_i915_private *dev_priv = - to_i915(dbuf_state->base.state->base.dev); - enum pipe pipe; - - *weight_start = 0; - *weight_end = 0; - *weight_total = 0; - - for_each_pipe(dev_priv, pipe) { - int weight = dbuf_state->weight[pipe]; - - /* - * Do not account pipes using other slice sets - * luckily as of current BSpec slice sets do not partially - * intersect(pipes share either same one slice or same slice set - * i.e no partial intersection), so it is enough to check for - * equality for now. - */ - if (dbuf_state->slices[pipe] != dbuf_state->slices[for_pipe]) - continue; - - *weight_total += weight; - if (pipe < for_pipe) { - *weight_start += weight; - *weight_end += weight; - } else if (pipe == for_pipe) { - *weight_end += weight; - } - } -} - -static int -skl_crtc_allocate_ddb(struct intel_atomic_state *state, struct intel_crtc *crtc) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - unsigned int weight_total, weight_start, weight_end; - const struct intel_dbuf_state *old_dbuf_state = - intel_atomic_get_old_dbuf_state(state); - struct intel_dbuf_state *new_dbuf_state = - intel_atomic_get_new_dbuf_state(state); - struct intel_crtc_state *crtc_state; - struct skl_ddb_entry ddb_slices; - enum pipe pipe = crtc->pipe; - unsigned int mbus_offset = 0; - u32 ddb_range_size; - u32 dbuf_slice_mask; - u32 start, end; - int ret; - - if (new_dbuf_state->weight[pipe] == 0) { - skl_ddb_entry_init(&new_dbuf_state->ddb[pipe], 0, 0); - goto out; - } - - dbuf_slice_mask = new_dbuf_state->slices[pipe]; - - skl_ddb_entry_for_slices(dev_priv, dbuf_slice_mask, &ddb_slices); - mbus_offset = mbus_ddb_offset(dev_priv, dbuf_slice_mask); - ddb_range_size = skl_ddb_entry_size(&ddb_slices); - - intel_crtc_dbuf_weights(new_dbuf_state, pipe, - &weight_start, &weight_end, &weight_total); - - start = ddb_range_size * weight_start / weight_total; - end = ddb_range_size * weight_end / weight_total; - - skl_ddb_entry_init(&new_dbuf_state->ddb[pipe], - ddb_slices.start - mbus_offset + start, - ddb_slices.start - mbus_offset + end); - -out: - if (old_dbuf_state->slices[pipe] == new_dbuf_state->slices[pipe] && - skl_ddb_entry_equal(&old_dbuf_state->ddb[pipe], - &new_dbuf_state->ddb[pipe])) - return 0; - - ret = intel_atomic_lock_global_state(&new_dbuf_state->base); - if (ret) - return ret; - - crtc_state = intel_atomic_get_crtc_state(&state->base, crtc); - if (IS_ERR(crtc_state)) - return PTR_ERR(crtc_state); - - /* - * Used for checking overlaps, so we need absolute - * offsets instead of MBUS relative offsets. - */ - crtc_state->wm.skl.ddb.start = mbus_offset + new_dbuf_state->ddb[pipe].start; - crtc_state->wm.skl.ddb.end = mbus_offset + new_dbuf_state->ddb[pipe].end; - - drm_dbg_kms(&dev_priv->drm, - "[CRTC:%d:%s] dbuf slices 0x%x -> 0x%x, ddb (%d - %d) -> (%d - %d), active pipes 0x%x -> 0x%x\n", - crtc->base.base.id, crtc->base.name, - old_dbuf_state->slices[pipe], new_dbuf_state->slices[pipe], - old_dbuf_state->ddb[pipe].start, old_dbuf_state->ddb[pipe].end, - new_dbuf_state->ddb[pipe].start, new_dbuf_state->ddb[pipe].end, - old_dbuf_state->active_pipes, new_dbuf_state->active_pipes); - - return 0; -} - -static int skl_compute_wm_params(const struct intel_crtc_state *crtc_state, - int width, const struct drm_format_info *format, - u64 modifier, unsigned int rotation, - u32 plane_pixel_rate, struct skl_wm_params *wp, - int color_plane); - -static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, - struct intel_plane *plane, - int level, - unsigned int latency, - const struct skl_wm_params *wp, - const struct skl_wm_level *result_prev, - struct skl_wm_level *result /* out */); - -static unsigned int -skl_cursor_allocation(const struct intel_crtc_state *crtc_state, - int num_active) -{ - struct intel_plane *plane = to_intel_plane(crtc_state->uapi.crtc->cursor); - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - int level, max_level = ilk_wm_max_level(dev_priv); - struct skl_wm_level wm = {}; - int ret, min_ddb_alloc = 0; - struct skl_wm_params wp; - - ret = skl_compute_wm_params(crtc_state, 256, - drm_format_info(DRM_FORMAT_ARGB8888), - DRM_FORMAT_MOD_LINEAR, - DRM_MODE_ROTATE_0, - crtc_state->pixel_rate, &wp, 0); - drm_WARN_ON(&dev_priv->drm, ret); - - for (level = 0; level <= max_level; level++) { - unsigned int latency = dev_priv->wm.skl_latency[level]; - - skl_compute_plane_wm(crtc_state, plane, level, latency, &wp, &wm, &wm); - if (wm.min_ddb_alloc == U16_MAX) - break; - - min_ddb_alloc = wm.min_ddb_alloc; - } - - return max(num_active == 1 ? 32 : 8, min_ddb_alloc); -} - -static void skl_ddb_entry_init_from_hw(struct skl_ddb_entry *entry, u32 reg) -{ - skl_ddb_entry_init(entry, - REG_FIELD_GET(PLANE_BUF_START_MASK, reg), - REG_FIELD_GET(PLANE_BUF_END_MASK, reg)); - if (entry->end) - entry->end++; -} - -static void -skl_ddb_get_hw_plane_state(struct drm_i915_private *dev_priv, - const enum pipe pipe, - const enum plane_id plane_id, - struct skl_ddb_entry *ddb, - struct skl_ddb_entry *ddb_y) -{ - u32 val; - - /* Cursor doesn't support NV12/planar, so no extra calculation needed */ - if (plane_id == PLANE_CURSOR) { - val = intel_uncore_read(&dev_priv->uncore, CUR_BUF_CFG(pipe)); - skl_ddb_entry_init_from_hw(ddb, val); - return; - } - - val = intel_uncore_read(&dev_priv->uncore, PLANE_BUF_CFG(pipe, plane_id)); - skl_ddb_entry_init_from_hw(ddb, val); - - if (DISPLAY_VER(dev_priv) >= 11) - return; - - val = intel_uncore_read(&dev_priv->uncore, PLANE_NV12_BUF_CFG(pipe, plane_id)); - skl_ddb_entry_init_from_hw(ddb_y, val); -} - -static void skl_pipe_ddb_get_hw_state(struct intel_crtc *crtc, - struct skl_ddb_entry *ddb, - struct skl_ddb_entry *ddb_y) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum intel_display_power_domain power_domain; - enum pipe pipe = crtc->pipe; - intel_wakeref_t wakeref; - enum plane_id plane_id; - - power_domain = POWER_DOMAIN_PIPE(pipe); - wakeref = intel_display_power_get_if_enabled(dev_priv, power_domain); - if (!wakeref) - return; - - for_each_plane_id_on_crtc(crtc, plane_id) - skl_ddb_get_hw_plane_state(dev_priv, pipe, - plane_id, - &ddb[plane_id], - &ddb_y[plane_id]); - - intel_display_power_put(dev_priv, power_domain, wakeref); -} - -struct dbuf_slice_conf_entry { - u8 active_pipes; - u8 dbuf_mask[I915_MAX_PIPES]; - bool join_mbus; -}; - -/* - * Table taken from Bspec 12716 - * Pipes do have some preferred DBuf slice affinity, - * plus there are some hardcoded requirements on how - * those should be distributed for multipipe scenarios. - * For more DBuf slices algorithm can get even more messy - * and less readable, so decided to use a table almost - * as is from BSpec itself - that way it is at least easier - * to compare, change and check. - */ -static const struct dbuf_slice_conf_entry icl_allowed_dbufs[] = -/* Autogenerated with igt/tools/intel_dbuf_map tool: */ -{ - { - .active_pipes = BIT(PIPE_A), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - }, - }, - { - .active_pipes = BIT(PIPE_B), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_C), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - }, - }, - {} -}; - -/* - * Table taken from Bspec 49255 - * Pipes do have some preferred DBuf slice affinity, - * plus there are some hardcoded requirements on how - * those should be distributed for multipipe scenarios. - * For more DBuf slices algorithm can get even more messy - * and less readable, so decided to use a table almost - * as is from BSpec itself - that way it is at least easier - * to compare, change and check. - */ -static const struct dbuf_slice_conf_entry tgl_allowed_dbufs[] = -/* Autogenerated with igt/tools/intel_dbuf_map tool: */ -{ - { - .active_pipes = BIT(PIPE_A), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S2), - [PIPE_B] = BIT(DBUF_S1), - }, - }, - { - .active_pipes = BIT(PIPE_C), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S2) | BIT(DBUF_S1), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_D), - .dbuf_mask = { - [PIPE_D] = BIT(DBUF_S2) | BIT(DBUF_S1), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S1), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S1), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S1), - [PIPE_C] = BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S2), - }, - }, - {} -}; - -static const struct dbuf_slice_conf_entry dg2_allowed_dbufs[] = { - { - .active_pipes = BIT(PIPE_A), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_C), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_D), - .dbuf_mask = { - [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S3), - [PIPE_D] = BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3), - [PIPE_D] = BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3), - [PIPE_D] = BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1), - [PIPE_B] = BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3), - [PIPE_D] = BIT(DBUF_S4), - }, - }, - {} -}; - -static const struct dbuf_slice_conf_entry adlp_allowed_dbufs[] = { - /* - * Keep the join_mbus cases first so check_mbus_joined() - * will prefer them over the !join_mbus cases. - */ - { - .active_pipes = BIT(PIPE_A), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4), - }, - .join_mbus = true, - }, - { - .active_pipes = BIT(PIPE_B), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S1) | BIT(DBUF_S2) | BIT(DBUF_S3) | BIT(DBUF_S4), - }, - .join_mbus = true, - }, - { - .active_pipes = BIT(PIPE_A), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - .join_mbus = false, - }, - { - .active_pipes = BIT(PIPE_B), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - .join_mbus = false, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_C), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - }, - }, - { - .active_pipes = BIT(PIPE_D), - .dbuf_mask = { - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - { - .active_pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D), - .dbuf_mask = { - [PIPE_A] = BIT(DBUF_S1) | BIT(DBUF_S2), - [PIPE_B] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_C] = BIT(DBUF_S3) | BIT(DBUF_S4), - [PIPE_D] = BIT(DBUF_S1) | BIT(DBUF_S2), - }, - }, - {} - -}; - -static bool check_mbus_joined(u8 active_pipes, - const struct dbuf_slice_conf_entry *dbuf_slices) -{ - int i; - - for (i = 0; dbuf_slices[i].active_pipes != 0; i++) { - if (dbuf_slices[i].active_pipes == active_pipes) - return dbuf_slices[i].join_mbus; - } - return false; -} - -static bool adlp_check_mbus_joined(u8 active_pipes) -{ - return check_mbus_joined(active_pipes, adlp_allowed_dbufs); -} - -static u8 compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus, - const struct dbuf_slice_conf_entry *dbuf_slices) -{ - int i; - - for (i = 0; dbuf_slices[i].active_pipes != 0; i++) { - if (dbuf_slices[i].active_pipes == active_pipes && - dbuf_slices[i].join_mbus == join_mbus) - return dbuf_slices[i].dbuf_mask[pipe]; - } - return 0; -} - -/* - * This function finds an entry with same enabled pipe configuration and - * returns correspondent DBuf slice mask as stated in BSpec for particular - * platform. - */ -static u8 icl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) -{ - /* - * FIXME: For ICL this is still a bit unclear as prev BSpec revision - * required calculating "pipe ratio" in order to determine - * if one or two slices can be used for single pipe configurations - * as additional constraint to the existing table. - * However based on recent info, it should be not "pipe ratio" - * but rather ratio between pixel_rate and cdclk with additional - * constants, so for now we are using only table until this is - * clarified. Also this is the reason why crtc_state param is - * still here - we will need it once those additional constraints - * pop up. - */ - return compute_dbuf_slices(pipe, active_pipes, join_mbus, - icl_allowed_dbufs); -} - -static u8 tgl_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) -{ - return compute_dbuf_slices(pipe, active_pipes, join_mbus, - tgl_allowed_dbufs); -} - -static u8 adlp_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) -{ - return compute_dbuf_slices(pipe, active_pipes, join_mbus, - adlp_allowed_dbufs); -} - -static u8 dg2_compute_dbuf_slices(enum pipe pipe, u8 active_pipes, bool join_mbus) -{ - return compute_dbuf_slices(pipe, active_pipes, join_mbus, - dg2_allowed_dbufs); -} - -static u8 skl_compute_dbuf_slices(struct intel_crtc *crtc, u8 active_pipes, bool join_mbus) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum pipe pipe = crtc->pipe; - - if (IS_DG2(dev_priv)) - return dg2_compute_dbuf_slices(pipe, active_pipes, join_mbus); - else if (IS_ALDERLAKE_P(dev_priv)) - return adlp_compute_dbuf_slices(pipe, active_pipes, join_mbus); - else if (DISPLAY_VER(dev_priv) == 12) - return tgl_compute_dbuf_slices(pipe, active_pipes, join_mbus); - else if (DISPLAY_VER(dev_priv) == 11) - return icl_compute_dbuf_slices(pipe, active_pipes, join_mbus); - /* - * For anything else just return one slice yet. - * Should be extended for other platforms. - */ - return active_pipes & BIT(pipe) ? BIT(DBUF_S1) : 0; -} - -static bool -use_minimal_wm0_only(const struct intel_crtc_state *crtc_state, - struct intel_plane *plane) -{ - struct drm_i915_private *i915 = to_i915(plane->base.dev); - - return DISPLAY_VER(i915) >= 13 && - crtc_state->uapi.async_flip && - plane->async_flip; -} - -static u64 -skl_total_relative_data_rate(const struct intel_crtc_state *crtc_state) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *i915 = to_i915(crtc->base.dev); - enum plane_id plane_id; - u64 data_rate = 0; - - for_each_plane_id_on_crtc(crtc, plane_id) { - if (plane_id == PLANE_CURSOR) - continue; - - data_rate += crtc_state->rel_data_rate[plane_id]; - - if (DISPLAY_VER(i915) < 11) - data_rate += crtc_state->rel_data_rate_y[plane_id]; - } - - return data_rate; -} - -static const struct skl_wm_level * -skl_plane_wm_level(const struct skl_pipe_wm *pipe_wm, - enum plane_id plane_id, - int level) -{ - const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; - - if (level == 0 && pipe_wm->use_sagv_wm) - return &wm->sagv.wm0; - - return &wm->wm[level]; -} - -static const struct skl_wm_level * -skl_plane_trans_wm(const struct skl_pipe_wm *pipe_wm, - enum plane_id plane_id) -{ - const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; - - if (pipe_wm->use_sagv_wm) - return &wm->sagv.trans_wm; - - return &wm->trans_wm; -} - -/* - * We only disable the watermarks for each plane if - * they exceed the ddb allocation of said plane. This - * is done so that we don't end up touching cursor - * watermarks needlessly when some other plane reduces - * our max possible watermark level. - * - * Bspec has this to say about the PLANE_WM enable bit: - * "All the watermarks at this level for all enabled - * planes must be enabled before the level will be used." - * So this is actually safe to do. - */ -static void -skl_check_wm_level(struct skl_wm_level *wm, const struct skl_ddb_entry *ddb) -{ - if (wm->min_ddb_alloc > skl_ddb_entry_size(ddb)) - memset(wm, 0, sizeof(*wm)); -} - -static void -skl_check_nv12_wm_level(struct skl_wm_level *wm, struct skl_wm_level *uv_wm, - const struct skl_ddb_entry *ddb_y, const struct skl_ddb_entry *ddb) -{ - if (wm->min_ddb_alloc > skl_ddb_entry_size(ddb_y) || - uv_wm->min_ddb_alloc > skl_ddb_entry_size(ddb)) { - memset(wm, 0, sizeof(*wm)); - memset(uv_wm, 0, sizeof(*uv_wm)); - } -} - -static bool icl_need_wm1_wa(struct drm_i915_private *i915, - enum plane_id plane_id) -{ - /* - * Wa_1408961008:icl, ehl - * Wa_14012656716:tgl, adl - * Underruns with WM1+ disabled - */ - return DISPLAY_VER(i915) == 11 || - (IS_DISPLAY_VER(i915, 12, 13) && plane_id == PLANE_CURSOR); -} - -struct skl_plane_ddb_iter { - u64 data_rate; - u16 start, size; -}; - -static void -skl_allocate_plane_ddb(struct skl_plane_ddb_iter *iter, - struct skl_ddb_entry *ddb, - const struct skl_wm_level *wm, - u64 data_rate) -{ - u16 size, extra = 0; - - if (data_rate) { - extra = min_t(u16, iter->size, - DIV64_U64_ROUND_UP(iter->size * data_rate, - iter->data_rate)); - iter->size -= extra; - iter->data_rate -= data_rate; - } - - /* - * Keep ddb entry of all disabled planes explicitly zeroed - * to avoid skl_ddb_add_affected_planes() adding them to - * the state when other planes change their allocations. - */ - size = wm->min_ddb_alloc + extra; - if (size) - iter->start = skl_ddb_entry_init(ddb, iter->start, - iter->start + size); -} - -static int -skl_crtc_allocate_plane_ddb(struct intel_atomic_state *state, - struct intel_crtc *crtc) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - const struct intel_dbuf_state *dbuf_state = - intel_atomic_get_new_dbuf_state(state); - const struct skl_ddb_entry *alloc = &dbuf_state->ddb[crtc->pipe]; - int num_active = hweight8(dbuf_state->active_pipes); - struct skl_plane_ddb_iter iter; - enum plane_id plane_id; - u16 cursor_size; - u32 blocks; - int level; - - /* Clear the partitioning for disabled planes. */ - memset(crtc_state->wm.skl.plane_ddb, 0, sizeof(crtc_state->wm.skl.plane_ddb)); - memset(crtc_state->wm.skl.plane_ddb_y, 0, sizeof(crtc_state->wm.skl.plane_ddb_y)); - - if (!crtc_state->hw.active) - return 0; - - iter.start = alloc->start; - iter.size = skl_ddb_entry_size(alloc); - if (iter.size == 0) - return 0; - - /* Allocate fixed number of blocks for cursor. */ - cursor_size = skl_cursor_allocation(crtc_state, num_active); - iter.size -= cursor_size; - skl_ddb_entry_init(&crtc_state->wm.skl.plane_ddb[PLANE_CURSOR], - alloc->end - cursor_size, alloc->end); - - iter.data_rate = skl_total_relative_data_rate(crtc_state); - - /* - * Find the highest watermark level for which we can satisfy the block - * requirement of active planes. - */ - for (level = ilk_wm_max_level(dev_priv); level >= 0; level--) { - blocks = 0; - for_each_plane_id_on_crtc(crtc, plane_id) { - const struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - - if (plane_id == PLANE_CURSOR) { - const struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - - if (wm->wm[level].min_ddb_alloc > skl_ddb_entry_size(ddb)) { - drm_WARN_ON(&dev_priv->drm, - wm->wm[level].min_ddb_alloc != U16_MAX); - blocks = U32_MAX; - break; - } - continue; - } - - blocks += wm->wm[level].min_ddb_alloc; - blocks += wm->uv_wm[level].min_ddb_alloc; - } - - if (blocks <= iter.size) { - iter.size -= blocks; - break; - } - } - - if (level < 0) { - drm_dbg_kms(&dev_priv->drm, - "Requested display configuration exceeds system DDB limitations"); - drm_dbg_kms(&dev_priv->drm, "minimum required %d/%d\n", - blocks, iter.size); - return -EINVAL; - } - - /* avoid the WARN later when we don't allocate any extra DDB */ - if (iter.data_rate == 0) - iter.size = 0; - - /* - * Grant each plane the blocks it requires at the highest achievable - * watermark level, plus an extra share of the leftover blocks - * proportional to its relative data rate. - */ - for_each_plane_id_on_crtc(crtc, plane_id) { - struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - struct skl_ddb_entry *ddb_y = - &crtc_state->wm.skl.plane_ddb_y[plane_id]; - const struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - - if (plane_id == PLANE_CURSOR) - continue; - - if (DISPLAY_VER(dev_priv) < 11 && - crtc_state->nv12_planes & BIT(plane_id)) { - skl_allocate_plane_ddb(&iter, ddb_y, &wm->wm[level], - crtc_state->rel_data_rate_y[plane_id]); - skl_allocate_plane_ddb(&iter, ddb, &wm->uv_wm[level], - crtc_state->rel_data_rate[plane_id]); - } else { - skl_allocate_plane_ddb(&iter, ddb, &wm->wm[level], - crtc_state->rel_data_rate[plane_id]); - } - } - drm_WARN_ON(&dev_priv->drm, iter.size != 0 || iter.data_rate != 0); - - /* - * When we calculated watermark values we didn't know how high - * of a level we'd actually be able to hit, so we just marked - * all levels as "enabled." Go back now and disable the ones - * that aren't actually possible. - */ - for (level++; level <= ilk_wm_max_level(dev_priv); level++) { - for_each_plane_id_on_crtc(crtc, plane_id) { - const struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - const struct skl_ddb_entry *ddb_y = - &crtc_state->wm.skl.plane_ddb_y[plane_id]; - struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - - if (DISPLAY_VER(dev_priv) < 11 && - crtc_state->nv12_planes & BIT(plane_id)) - skl_check_nv12_wm_level(&wm->wm[level], - &wm->uv_wm[level], - ddb_y, ddb); - else - skl_check_wm_level(&wm->wm[level], ddb); - - if (icl_need_wm1_wa(dev_priv, plane_id) && - level == 1 && wm->wm[0].enable) { - wm->wm[level].blocks = wm->wm[0].blocks; - wm->wm[level].lines = wm->wm[0].lines; - wm->wm[level].ignore_lines = wm->wm[0].ignore_lines; - } - } - } - - /* - * Go back and disable the transition and SAGV watermarks - * if it turns out we don't have enough DDB blocks for them. - */ - for_each_plane_id_on_crtc(crtc, plane_id) { - const struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - const struct skl_ddb_entry *ddb_y = - &crtc_state->wm.skl.plane_ddb_y[plane_id]; - struct skl_plane_wm *wm = - &crtc_state->wm.skl.optimal.planes[plane_id]; - - if (DISPLAY_VER(dev_priv) < 11 && - crtc_state->nv12_planes & BIT(plane_id)) { - skl_check_wm_level(&wm->trans_wm, ddb_y); - } else { - WARN_ON(skl_ddb_entry_size(ddb_y)); - - skl_check_wm_level(&wm->trans_wm, ddb); - } - - skl_check_wm_level(&wm->sagv.wm0, ddb); - skl_check_wm_level(&wm->sagv.trans_wm, ddb); - } - - return 0; -} - -/* - * The max latency should be 257 (max the punit can code is 255 and we add 2us - * for the read latency) and cpp should always be <= 8, so that - * should allow pixel_rate up to ~2 GHz which seems sufficient since max - * 2xcdclk is 1350 MHz and the pixel rate should never exceed that. -*/ -static uint_fixed_16_16_t -skl_wm_method1(const struct drm_i915_private *dev_priv, u32 pixel_rate, - u8 cpp, u32 latency, u32 dbuf_block_size) -{ - u32 wm_intermediate_val; - uint_fixed_16_16_t ret; - - if (latency == 0) - return FP_16_16_MAX; - - wm_intermediate_val = latency * pixel_rate * cpp; - ret = div_fixed16(wm_intermediate_val, 1000 * dbuf_block_size); - - if (DISPLAY_VER(dev_priv) >= 10) - ret = add_fixed16_u32(ret, 1); - - return ret; -} - -static uint_fixed_16_16_t -skl_wm_method2(u32 pixel_rate, u32 pipe_htotal, u32 latency, - uint_fixed_16_16_t plane_blocks_per_line) -{ - u32 wm_intermediate_val; - uint_fixed_16_16_t ret; - - if (latency == 0) - return FP_16_16_MAX; - - wm_intermediate_val = latency * pixel_rate; - wm_intermediate_val = DIV_ROUND_UP(wm_intermediate_val, - pipe_htotal * 1000); - ret = mul_u32_fixed16(wm_intermediate_val, plane_blocks_per_line); - return ret; -} - -static uint_fixed_16_16_t -intel_get_linetime_us(const struct intel_crtc_state *crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - u32 pixel_rate; - u32 crtc_htotal; - uint_fixed_16_16_t linetime_us; - - if (!crtc_state->hw.active) - return u32_to_fixed16(0); - - pixel_rate = crtc_state->pixel_rate; - - if (drm_WARN_ON(&dev_priv->drm, pixel_rate == 0)) - return u32_to_fixed16(0); - - crtc_htotal = crtc_state->hw.pipe_mode.crtc_htotal; - linetime_us = div_fixed16(crtc_htotal * 1000, pixel_rate); - - return linetime_us; -} - -static int -skl_compute_wm_params(const struct intel_crtc_state *crtc_state, - int width, const struct drm_format_info *format, - u64 modifier, unsigned int rotation, - u32 plane_pixel_rate, struct skl_wm_params *wp, - int color_plane) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - u32 interm_pbpl; - - /* only planar format has two planes */ - if (color_plane == 1 && - !intel_format_info_is_yuv_semiplanar(format, modifier)) { - drm_dbg_kms(&dev_priv->drm, - "Non planar format have single plane\n"); - return -EINVAL; - } - - wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED || - modifier == I915_FORMAT_MOD_4_TILED || - modifier == I915_FORMAT_MOD_Yf_TILED || - modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; - wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; - wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; - wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier); - - wp->width = width; - if (color_plane == 1 && wp->is_planar) - wp->width /= 2; - - wp->cpp = format->cpp[color_plane]; - wp->plane_pixel_rate = plane_pixel_rate; - - if (DISPLAY_VER(dev_priv) >= 11 && - modifier == I915_FORMAT_MOD_Yf_TILED && wp->cpp == 1) - wp->dbuf_block_size = 256; - else - wp->dbuf_block_size = 512; - - if (drm_rotation_90_or_270(rotation)) { - switch (wp->cpp) { - case 1: - wp->y_min_scanlines = 16; - break; - case 2: - wp->y_min_scanlines = 8; - break; - case 4: - wp->y_min_scanlines = 4; - break; - default: - MISSING_CASE(wp->cpp); - return -EINVAL; - } - } else { - wp->y_min_scanlines = 4; - } - - if (skl_needs_memory_bw_wa(dev_priv)) - wp->y_min_scanlines *= 2; - - wp->plane_bytes_per_line = wp->width * wp->cpp; - if (wp->y_tiled) { - interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line * - wp->y_min_scanlines, - wp->dbuf_block_size); - - if (DISPLAY_VER(dev_priv) >= 10) - interm_pbpl++; - - wp->plane_blocks_per_line = div_fixed16(interm_pbpl, - wp->y_min_scanlines); - } else { - interm_pbpl = DIV_ROUND_UP(wp->plane_bytes_per_line, - wp->dbuf_block_size); - - if (!wp->x_tiled || DISPLAY_VER(dev_priv) >= 10) - interm_pbpl++; - - wp->plane_blocks_per_line = u32_to_fixed16(interm_pbpl); - } - - wp->y_tile_minimum = mul_u32_fixed16(wp->y_min_scanlines, - wp->plane_blocks_per_line); - - wp->linetime_us = fixed16_to_u32_round_up( - intel_get_linetime_us(crtc_state)); - - return 0; -} - -static int -skl_compute_plane_wm_params(const struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state, - struct skl_wm_params *wp, int color_plane) -{ - const struct drm_framebuffer *fb = plane_state->hw.fb; - int width; - - /* - * Src coordinates are already rotated by 270 degrees for - * the 90/270 degree plane rotation cases (to match the - * GTT mapping), hence no need to account for rotation here. - */ - width = drm_rect_width(&plane_state->uapi.src) >> 16; - - return skl_compute_wm_params(crtc_state, width, - fb->format, fb->modifier, - plane_state->hw.rotation, - intel_plane_pixel_rate(crtc_state, plane_state), - wp, color_plane); -} - -static bool skl_wm_has_lines(struct drm_i915_private *dev_priv, int level) -{ - if (DISPLAY_VER(dev_priv) >= 10) - return true; - - /* The number of lines are ignored for the level 0 watermark. */ - return level > 0; -} - -static int skl_wm_max_lines(struct drm_i915_private *dev_priv) -{ - if (DISPLAY_VER(dev_priv) >= 13) - return 255; - else - return 31; -} - -static void skl_compute_plane_wm(const struct intel_crtc_state *crtc_state, - struct intel_plane *plane, - int level, - unsigned int latency, - const struct skl_wm_params *wp, - const struct skl_wm_level *result_prev, - struct skl_wm_level *result /* out */) -{ - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - uint_fixed_16_16_t method1, method2; - uint_fixed_16_16_t selected_result; - u32 blocks, lines, min_ddb_alloc = 0; - - if (latency == 0 || - (use_minimal_wm0_only(crtc_state, plane) && level > 0)) { - /* reject it */ - result->min_ddb_alloc = U16_MAX; - return; - } - - /* - * WaIncreaseLatencyIPCEnabled: kbl,cfl - * Display WA #1141: kbl,cfl - */ - if ((IS_KABYLAKE(dev_priv) || - IS_COFFEELAKE(dev_priv) || - IS_COMETLAKE(dev_priv)) && - dev_priv->ipc_enabled) - latency += 4; - - if (skl_needs_memory_bw_wa(dev_priv) && wp->x_tiled) - latency += 15; - - method1 = skl_wm_method1(dev_priv, wp->plane_pixel_rate, - wp->cpp, latency, wp->dbuf_block_size); - method2 = skl_wm_method2(wp->plane_pixel_rate, - crtc_state->hw.pipe_mode.crtc_htotal, - latency, - wp->plane_blocks_per_line); - - if (wp->y_tiled) { - selected_result = max_fixed16(method2, wp->y_tile_minimum); - } else { - if ((wp->cpp * crtc_state->hw.pipe_mode.crtc_htotal / - wp->dbuf_block_size < 1) && - (wp->plane_bytes_per_line / wp->dbuf_block_size < 1)) { - selected_result = method2; - } else if (latency >= wp->linetime_us) { - if (DISPLAY_VER(dev_priv) == 9) - selected_result = min_fixed16(method1, method2); - else - selected_result = method2; - } else { - selected_result = method1; - } - } - - blocks = fixed16_to_u32_round_up(selected_result) + 1; - /* - * Lets have blocks at minimum equivalent to plane_blocks_per_line - * as there will be at minimum one line for lines configuration. This - * is a work around for FIFO underruns observed with resolutions like - * 4k 60 Hz in single channel DRAM configurations. - * - * As per the Bspec 49325, if the ddb allocation can hold at least - * one plane_blocks_per_line, we should have selected method2 in - * the above logic. Assuming that modern versions have enough dbuf - * and method2 guarantees blocks equivalent to at least 1 line, - * select the blocks as plane_blocks_per_line. - * - * TODO: Revisit the logic when we have better understanding on DRAM - * channels' impact on the level 0 memory latency and the relevant - * wm calculations. - */ - if (skl_wm_has_lines(dev_priv, level)) - blocks = max(blocks, - fixed16_to_u32_round_up(wp->plane_blocks_per_line)); - lines = div_round_up_fixed16(selected_result, - wp->plane_blocks_per_line); - - if (DISPLAY_VER(dev_priv) == 9) { - /* Display WA #1125: skl,bxt,kbl */ - if (level == 0 && wp->rc_surface) - blocks += fixed16_to_u32_round_up(wp->y_tile_minimum); - - /* Display WA #1126: skl,bxt,kbl */ - if (level >= 1 && level <= 7) { - if (wp->y_tiled) { - blocks += fixed16_to_u32_round_up(wp->y_tile_minimum); - lines += wp->y_min_scanlines; - } else { - blocks++; - } - - /* - * Make sure result blocks for higher latency levels are - * atleast as high as level below the current level. - * Assumption in DDB algorithm optimization for special - * cases. Also covers Display WA #1125 for RC. - */ - if (result_prev->blocks > blocks) - blocks = result_prev->blocks; - } - } - - if (DISPLAY_VER(dev_priv) >= 11) { - if (wp->y_tiled) { - int extra_lines; - - if (lines % wp->y_min_scanlines == 0) - extra_lines = wp->y_min_scanlines; - else - extra_lines = wp->y_min_scanlines * 2 - - lines % wp->y_min_scanlines; - - min_ddb_alloc = mul_round_up_u32_fixed16(lines + extra_lines, - wp->plane_blocks_per_line); - } else { - min_ddb_alloc = blocks + DIV_ROUND_UP(blocks, 10); - } - } - - if (!skl_wm_has_lines(dev_priv, level)) - lines = 0; - - if (lines > skl_wm_max_lines(dev_priv)) { - /* reject it */ - result->min_ddb_alloc = U16_MAX; - return; - } - - /* - * If lines is valid, assume we can use this watermark level - * for now. We'll come back and disable it after we calculate the - * DDB allocation if it turns out we don't actually have enough - * blocks to satisfy it. - */ - result->blocks = blocks; - result->lines = lines; - /* Bspec says: value >= plane ddb allocation -> invalid, hence the +1 here */ - result->min_ddb_alloc = max(min_ddb_alloc, blocks) + 1; - result->enable = true; - - if (DISPLAY_VER(dev_priv) < 12 && dev_priv->sagv_block_time_us) - result->can_sagv = latency >= dev_priv->sagv_block_time_us; -} - -static void -skl_compute_wm_levels(const struct intel_crtc_state *crtc_state, - struct intel_plane *plane, - const struct skl_wm_params *wm_params, - struct skl_wm_level *levels) -{ - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - int level, max_level = ilk_wm_max_level(dev_priv); - struct skl_wm_level *result_prev = &levels[0]; - - for (level = 0; level <= max_level; level++) { - struct skl_wm_level *result = &levels[level]; - unsigned int latency = dev_priv->wm.skl_latency[level]; - - skl_compute_plane_wm(crtc_state, plane, level, latency, - wm_params, result_prev, result); - - result_prev = result; - } -} - -static void tgl_compute_sagv_wm(const struct intel_crtc_state *crtc_state, - struct intel_plane *plane, - const struct skl_wm_params *wm_params, - struct skl_plane_wm *plane_wm) -{ - struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev); - struct skl_wm_level *sagv_wm = &plane_wm->sagv.wm0; - struct skl_wm_level *levels = plane_wm->wm; - unsigned int latency = 0; - - if (dev_priv->sagv_block_time_us) - latency = dev_priv->sagv_block_time_us + dev_priv->wm.skl_latency[0]; - - skl_compute_plane_wm(crtc_state, plane, 0, latency, - wm_params, &levels[0], - sagv_wm); -} - -static void skl_compute_transition_wm(struct drm_i915_private *dev_priv, - struct skl_wm_level *trans_wm, - const struct skl_wm_level *wm0, - const struct skl_wm_params *wp) -{ - u16 trans_min, trans_amount, trans_y_tile_min; - u16 wm0_blocks, trans_offset, blocks; - - /* Transition WM don't make any sense if ipc is disabled */ - if (!dev_priv->ipc_enabled) - return; - - /* - * WaDisableTWM:skl,kbl,cfl,bxt - * Transition WM are not recommended by HW team for GEN9 - */ - if (DISPLAY_VER(dev_priv) == 9) - return; - - if (DISPLAY_VER(dev_priv) >= 11) - trans_min = 4; - else - trans_min = 14; - - /* Display WA #1140: glk,cnl */ - if (DISPLAY_VER(dev_priv) == 10) - trans_amount = 0; - else - trans_amount = 10; /* This is configurable amount */ - - trans_offset = trans_min + trans_amount; - - /* - * The spec asks for Selected Result Blocks for wm0 (the real value), - * not Result Blocks (the integer value). Pay attention to the capital - * letters. The value wm_l0->blocks is actually Result Blocks, but - * since Result Blocks is the ceiling of Selected Result Blocks plus 1, - * and since we later will have to get the ceiling of the sum in the - * transition watermarks calculation, we can just pretend Selected - * Result Blocks is Result Blocks minus 1 and it should work for the - * current platforms. - */ - wm0_blocks = wm0->blocks - 1; - - if (wp->y_tiled) { - trans_y_tile_min = - (u16)mul_round_up_u32_fixed16(2, wp->y_tile_minimum); - blocks = max(wm0_blocks, trans_y_tile_min) + trans_offset; - } else { - blocks = wm0_blocks + trans_offset; - } - blocks++; - - /* - * Just assume we can enable the transition watermark. After - * computing the DDB we'll come back and disable it if that - * assumption turns out to be false. - */ - trans_wm->blocks = blocks; - trans_wm->min_ddb_alloc = max_t(u16, wm0->min_ddb_alloc, blocks + 1); - trans_wm->enable = true; -} - -static int skl_build_plane_wm_single(struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state, - struct intel_plane *plane, int color_plane) -{ - struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane->id]; - struct skl_wm_params wm_params; - int ret; - - ret = skl_compute_plane_wm_params(crtc_state, plane_state, - &wm_params, color_plane); - if (ret) - return ret; - - skl_compute_wm_levels(crtc_state, plane, &wm_params, wm->wm); - - skl_compute_transition_wm(dev_priv, &wm->trans_wm, - &wm->wm[0], &wm_params); - - if (DISPLAY_VER(dev_priv) >= 12) { - tgl_compute_sagv_wm(crtc_state, plane, &wm_params, wm); - - skl_compute_transition_wm(dev_priv, &wm->sagv.trans_wm, - &wm->sagv.wm0, &wm_params); - } - - return 0; -} - -static int skl_build_plane_wm_uv(struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state, - struct intel_plane *plane) -{ - struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane->id]; - struct skl_wm_params wm_params; - int ret; - - wm->is_planar = true; - - /* uv plane watermarks must also be validated for NV12/Planar */ - ret = skl_compute_plane_wm_params(crtc_state, plane_state, - &wm_params, 1); - if (ret) - return ret; - - skl_compute_wm_levels(crtc_state, plane, &wm_params, wm->uv_wm); - - return 0; -} - -static int skl_build_plane_wm(struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) -{ - struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); - enum plane_id plane_id = plane->id; - struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id]; - const struct drm_framebuffer *fb = plane_state->hw.fb; - int ret; - - memset(wm, 0, sizeof(*wm)); - - if (!intel_wm_plane_visible(crtc_state, plane_state)) - return 0; - - ret = skl_build_plane_wm_single(crtc_state, plane_state, - plane, 0); - if (ret) - return ret; - - if (fb->format->is_yuv && fb->format->num_planes > 1) { - ret = skl_build_plane_wm_uv(crtc_state, plane_state, - plane); - if (ret) - return ret; - } - - return 0; -} - -static int icl_build_plane_wm(struct intel_crtc_state *crtc_state, - const struct intel_plane_state *plane_state) -{ - struct intel_plane *plane = to_intel_plane(plane_state->uapi.plane); - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - enum plane_id plane_id = plane->id; - struct skl_plane_wm *wm = &crtc_state->wm.skl.raw.planes[plane_id]; - int ret; - - /* Watermarks calculated in master */ - if (plane_state->planar_slave) - return 0; - - memset(wm, 0, sizeof(*wm)); - - if (plane_state->planar_linked_plane) { - const struct drm_framebuffer *fb = plane_state->hw.fb; - - drm_WARN_ON(&dev_priv->drm, - !intel_wm_plane_visible(crtc_state, plane_state)); - drm_WARN_ON(&dev_priv->drm, !fb->format->is_yuv || - fb->format->num_planes == 1); - - ret = skl_build_plane_wm_single(crtc_state, plane_state, - plane_state->planar_linked_plane, 0); - if (ret) - return ret; - - ret = skl_build_plane_wm_single(crtc_state, plane_state, - plane, 1); - if (ret) - return ret; - } else if (intel_wm_plane_visible(crtc_state, plane_state)) { - ret = skl_build_plane_wm_single(crtc_state, plane_state, - plane, 0); - if (ret) - return ret; - } - - return 0; -} - -static int skl_build_pipe_wm(struct intel_atomic_state *state, - struct intel_crtc *crtc) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_crtc_state *crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - const struct intel_plane_state *plane_state; - struct intel_plane *plane; - int ret, i; - - for_each_new_intel_plane_in_state(state, plane, plane_state, i) { - /* - * FIXME should perhaps check {old,new}_plane_crtc->hw.crtc - * instead but we don't populate that correctly for NV12 Y - * planes so for now hack this. - */ - if (plane->pipe != crtc->pipe) - continue; - - if (DISPLAY_VER(dev_priv) >= 11) - ret = icl_build_plane_wm(crtc_state, plane_state); - else - ret = skl_build_plane_wm(crtc_state, plane_state); - if (ret) - return ret; - } - - crtc_state->wm.skl.optimal = crtc_state->wm.skl.raw; - - return 0; -} - -static void skl_ddb_entry_write(struct drm_i915_private *dev_priv, - i915_reg_t reg, - const struct skl_ddb_entry *entry) -{ - if (entry->end) - intel_de_write_fw(dev_priv, reg, - PLANE_BUF_END(entry->end - 1) | - PLANE_BUF_START(entry->start)); - else - intel_de_write_fw(dev_priv, reg, 0); -} - -static void skl_write_wm_level(struct drm_i915_private *dev_priv, - i915_reg_t reg, - const struct skl_wm_level *level) -{ - u32 val = 0; - - if (level->enable) - val |= PLANE_WM_EN; - if (level->ignore_lines) - val |= PLANE_WM_IGNORE_LINES; - val |= REG_FIELD_PREP(PLANE_WM_BLOCKS_MASK, level->blocks); - val |= REG_FIELD_PREP(PLANE_WM_LINES_MASK, level->lines); - - intel_de_write_fw(dev_priv, reg, val); -} - -void skl_write_plane_wm(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - int level, max_level = ilk_wm_max_level(dev_priv); - enum plane_id plane_id = plane->id; - enum pipe pipe = plane->pipe; - const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal; - const struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - const struct skl_ddb_entry *ddb_y = - &crtc_state->wm.skl.plane_ddb_y[plane_id]; - - for (level = 0; level <= max_level; level++) - skl_write_wm_level(dev_priv, PLANE_WM(pipe, plane_id, level), - skl_plane_wm_level(pipe_wm, plane_id, level)); - - skl_write_wm_level(dev_priv, PLANE_WM_TRANS(pipe, plane_id), - skl_plane_trans_wm(pipe_wm, plane_id)); - - if (HAS_HW_SAGV_WM(dev_priv)) { - const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; - - skl_write_wm_level(dev_priv, PLANE_WM_SAGV(pipe, plane_id), - &wm->sagv.wm0); - skl_write_wm_level(dev_priv, PLANE_WM_SAGV_TRANS(pipe, plane_id), - &wm->sagv.trans_wm); - } - - skl_ddb_entry_write(dev_priv, - PLANE_BUF_CFG(pipe, plane_id), ddb); - - if (DISPLAY_VER(dev_priv) < 11) - skl_ddb_entry_write(dev_priv, - PLANE_NV12_BUF_CFG(pipe, plane_id), ddb_y); -} - -void skl_write_cursor_wm(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(plane->base.dev); - int level, max_level = ilk_wm_max_level(dev_priv); - enum plane_id plane_id = plane->id; - enum pipe pipe = plane->pipe; - const struct skl_pipe_wm *pipe_wm = &crtc_state->wm.skl.optimal; - const struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - - for (level = 0; level <= max_level; level++) - skl_write_wm_level(dev_priv, CUR_WM(pipe, level), - skl_plane_wm_level(pipe_wm, plane_id, level)); - - skl_write_wm_level(dev_priv, CUR_WM_TRANS(pipe), - skl_plane_trans_wm(pipe_wm, plane_id)); - - if (HAS_HW_SAGV_WM(dev_priv)) { - const struct skl_plane_wm *wm = &pipe_wm->planes[plane_id]; - - skl_write_wm_level(dev_priv, CUR_WM_SAGV(pipe), - &wm->sagv.wm0); - skl_write_wm_level(dev_priv, CUR_WM_SAGV_TRANS(pipe), - &wm->sagv.trans_wm); - } - - skl_ddb_entry_write(dev_priv, CUR_BUF_CFG(pipe), ddb); -} - -static bool skl_wm_level_equals(const struct skl_wm_level *l1, - const struct skl_wm_level *l2) -{ - return l1->enable == l2->enable && - l1->ignore_lines == l2->ignore_lines && - l1->lines == l2->lines && - l1->blocks == l2->blocks; -} - -static bool skl_plane_wm_equals(struct drm_i915_private *dev_priv, - const struct skl_plane_wm *wm1, - const struct skl_plane_wm *wm2) -{ - int level, max_level = ilk_wm_max_level(dev_priv); - - for (level = 0; level <= max_level; level++) { - /* - * We don't check uv_wm as the hardware doesn't actually - * use it. It only gets used for calculating the required - * ddb allocation. - */ - if (!skl_wm_level_equals(&wm1->wm[level], &wm2->wm[level])) - return false; - } - - return skl_wm_level_equals(&wm1->trans_wm, &wm2->trans_wm) && - skl_wm_level_equals(&wm1->sagv.wm0, &wm2->sagv.wm0) && - skl_wm_level_equals(&wm1->sagv.trans_wm, &wm2->sagv.trans_wm); -} - -static bool skl_ddb_entries_overlap(const struct skl_ddb_entry *a, - const struct skl_ddb_entry *b) -{ - return a->start < b->end && b->start < a->end; -} - -static void skl_ddb_entry_union(struct skl_ddb_entry *a, - const struct skl_ddb_entry *b) -{ - if (a->end && b->end) { - a->start = min(a->start, b->start); - a->end = max(a->end, b->end); - } else if (b->end) { - a->start = b->start; - a->end = b->end; - } -} - -bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, - const struct skl_ddb_entry *entries, - int num_entries, int ignore_idx) -{ - int i; - - for (i = 0; i < num_entries; i++) { - if (i != ignore_idx && - skl_ddb_entries_overlap(ddb, &entries[i])) - return true; - } - - return false; -} - -static int -skl_ddb_add_affected_planes(const struct intel_crtc_state *old_crtc_state, - struct intel_crtc_state *new_crtc_state) -{ - struct intel_atomic_state *state = to_intel_atomic_state(new_crtc_state->uapi.state); - struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->uapi.crtc); - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct intel_plane *plane; - - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { - struct intel_plane_state *plane_state; - enum plane_id plane_id = plane->id; - - if (skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb[plane_id], - &new_crtc_state->wm.skl.plane_ddb[plane_id]) && - skl_ddb_entry_equal(&old_crtc_state->wm.skl.plane_ddb_y[plane_id], - &new_crtc_state->wm.skl.plane_ddb_y[plane_id])) - continue; - - plane_state = intel_atomic_get_plane_state(state, plane); - if (IS_ERR(plane_state)) - return PTR_ERR(plane_state); - - new_crtc_state->update_planes |= BIT(plane_id); - } - - return 0; -} - -static u8 intel_dbuf_enabled_slices(const struct intel_dbuf_state *dbuf_state) -{ - struct drm_i915_private *dev_priv = to_i915(dbuf_state->base.state->base.dev); - u8 enabled_slices; - enum pipe pipe; - - /* - * FIXME: For now we always enable slice S1 as per - * the Bspec display initialization sequence. - */ - enabled_slices = BIT(DBUF_S1); - - for_each_pipe(dev_priv, pipe) - enabled_slices |= dbuf_state->slices[pipe]; - - return enabled_slices; -} - -static int -skl_compute_ddb(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_dbuf_state *old_dbuf_state; - struct intel_dbuf_state *new_dbuf_state = NULL; - const struct intel_crtc_state *old_crtc_state; - struct intel_crtc_state *new_crtc_state; - struct intel_crtc *crtc; - int ret, i; - - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { - new_dbuf_state = intel_atomic_get_dbuf_state(state); - if (IS_ERR(new_dbuf_state)) - return PTR_ERR(new_dbuf_state); - - old_dbuf_state = intel_atomic_get_old_dbuf_state(state); - break; - } - - if (!new_dbuf_state) - return 0; - - new_dbuf_state->active_pipes = - intel_calc_active_pipes(state, old_dbuf_state->active_pipes); - - if (old_dbuf_state->active_pipes != new_dbuf_state->active_pipes) { - ret = intel_atomic_lock_global_state(&new_dbuf_state->base); - if (ret) - return ret; - } - - if (HAS_MBUS_JOINING(dev_priv)) - new_dbuf_state->joined_mbus = - adlp_check_mbus_joined(new_dbuf_state->active_pipes); - - for_each_intel_crtc(&dev_priv->drm, crtc) { - enum pipe pipe = crtc->pipe; - - new_dbuf_state->slices[pipe] = - skl_compute_dbuf_slices(crtc, new_dbuf_state->active_pipes, - new_dbuf_state->joined_mbus); - - if (old_dbuf_state->slices[pipe] == new_dbuf_state->slices[pipe]) - continue; - - ret = intel_atomic_lock_global_state(&new_dbuf_state->base); - if (ret) - return ret; - } - - new_dbuf_state->enabled_slices = intel_dbuf_enabled_slices(new_dbuf_state); - - if (old_dbuf_state->enabled_slices != new_dbuf_state->enabled_slices || - old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { - ret = intel_atomic_serialize_global_state(&new_dbuf_state->base); - if (ret) - return ret; - - if (old_dbuf_state->joined_mbus != new_dbuf_state->joined_mbus) { - /* TODO: Implement vblank synchronized MBUS joining changes */ - ret = intel_modeset_all_pipes(state); - if (ret) - return ret; - } - - drm_dbg_kms(&dev_priv->drm, - "Enabled dbuf slices 0x%x -> 0x%x (total dbuf slices 0x%x), mbus joined? %s->%s\n", - old_dbuf_state->enabled_slices, - new_dbuf_state->enabled_slices, - INTEL_INFO(dev_priv)->display.dbuf.slice_mask, - str_yes_no(old_dbuf_state->joined_mbus), - str_yes_no(new_dbuf_state->joined_mbus)); - } - - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { - enum pipe pipe = crtc->pipe; - - new_dbuf_state->weight[pipe] = intel_crtc_ddb_weight(new_crtc_state); - - if (old_dbuf_state->weight[pipe] == new_dbuf_state->weight[pipe]) - continue; - - ret = intel_atomic_lock_global_state(&new_dbuf_state->base); - if (ret) - return ret; - } - - for_each_intel_crtc(&dev_priv->drm, crtc) { - ret = skl_crtc_allocate_ddb(state, crtc); - if (ret) - return ret; - } - - for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { - ret = skl_crtc_allocate_plane_ddb(state, crtc); - if (ret) - return ret; - - ret = skl_ddb_add_affected_planes(old_crtc_state, - new_crtc_state); - if (ret) - return ret; - } - - return 0; -} - -static char enast(bool enable) -{ - return enable ? '*' : ' '; -} - -static void -skl_print_wm_changes(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_crtc_state *old_crtc_state; - const struct intel_crtc_state *new_crtc_state; - struct intel_plane *plane; - struct intel_crtc *crtc; - int i; - - if (!drm_debug_enabled(DRM_UT_KMS)) - return; - - for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state, - new_crtc_state, i) { - const struct skl_pipe_wm *old_pipe_wm, *new_pipe_wm; - - old_pipe_wm = &old_crtc_state->wm.skl.optimal; - new_pipe_wm = &new_crtc_state->wm.skl.optimal; - - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { - enum plane_id plane_id = plane->id; - const struct skl_ddb_entry *old, *new; - - old = &old_crtc_state->wm.skl.plane_ddb[plane_id]; - new = &new_crtc_state->wm.skl.plane_ddb[plane_id]; - - if (skl_ddb_entry_equal(old, new)) - continue; - - drm_dbg_kms(&dev_priv->drm, - "[PLANE:%d:%s] ddb (%4d - %4d) -> (%4d - %4d), size %4d -> %4d\n", - plane->base.base.id, plane->base.name, - old->start, old->end, new->start, new->end, - skl_ddb_entry_size(old), skl_ddb_entry_size(new)); - } - - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { - enum plane_id plane_id = plane->id; - const struct skl_plane_wm *old_wm, *new_wm; - - old_wm = &old_pipe_wm->planes[plane_id]; - new_wm = &new_pipe_wm->planes[plane_id]; - - if (skl_plane_wm_equals(dev_priv, old_wm, new_wm)) - continue; - - drm_dbg_kms(&dev_priv->drm, - "[PLANE:%d:%s] level %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm,%cstwm" - " -> %cwm0,%cwm1,%cwm2,%cwm3,%cwm4,%cwm5,%cwm6,%cwm7,%ctwm,%cswm,%cstwm\n", - plane->base.base.id, plane->base.name, - enast(old_wm->wm[0].enable), enast(old_wm->wm[1].enable), - enast(old_wm->wm[2].enable), enast(old_wm->wm[3].enable), - enast(old_wm->wm[4].enable), enast(old_wm->wm[5].enable), - enast(old_wm->wm[6].enable), enast(old_wm->wm[7].enable), - enast(old_wm->trans_wm.enable), - enast(old_wm->sagv.wm0.enable), - enast(old_wm->sagv.trans_wm.enable), - enast(new_wm->wm[0].enable), enast(new_wm->wm[1].enable), - enast(new_wm->wm[2].enable), enast(new_wm->wm[3].enable), - enast(new_wm->wm[4].enable), enast(new_wm->wm[5].enable), - enast(new_wm->wm[6].enable), enast(new_wm->wm[7].enable), - enast(new_wm->trans_wm.enable), - enast(new_wm->sagv.wm0.enable), - enast(new_wm->sagv.trans_wm.enable)); - - drm_dbg_kms(&dev_priv->drm, - "[PLANE:%d:%s] lines %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%4d" - " -> %c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%3d,%c%4d\n", - plane->base.base.id, plane->base.name, - enast(old_wm->wm[0].ignore_lines), old_wm->wm[0].lines, - enast(old_wm->wm[1].ignore_lines), old_wm->wm[1].lines, - enast(old_wm->wm[2].ignore_lines), old_wm->wm[2].lines, - enast(old_wm->wm[3].ignore_lines), old_wm->wm[3].lines, - enast(old_wm->wm[4].ignore_lines), old_wm->wm[4].lines, - enast(old_wm->wm[5].ignore_lines), old_wm->wm[5].lines, - enast(old_wm->wm[6].ignore_lines), old_wm->wm[6].lines, - enast(old_wm->wm[7].ignore_lines), old_wm->wm[7].lines, - enast(old_wm->trans_wm.ignore_lines), old_wm->trans_wm.lines, - enast(old_wm->sagv.wm0.ignore_lines), old_wm->sagv.wm0.lines, - enast(old_wm->sagv.trans_wm.ignore_lines), old_wm->sagv.trans_wm.lines, - enast(new_wm->wm[0].ignore_lines), new_wm->wm[0].lines, - enast(new_wm->wm[1].ignore_lines), new_wm->wm[1].lines, - enast(new_wm->wm[2].ignore_lines), new_wm->wm[2].lines, - enast(new_wm->wm[3].ignore_lines), new_wm->wm[3].lines, - enast(new_wm->wm[4].ignore_lines), new_wm->wm[4].lines, - enast(new_wm->wm[5].ignore_lines), new_wm->wm[5].lines, - enast(new_wm->wm[6].ignore_lines), new_wm->wm[6].lines, - enast(new_wm->wm[7].ignore_lines), new_wm->wm[7].lines, - enast(new_wm->trans_wm.ignore_lines), new_wm->trans_wm.lines, - enast(new_wm->sagv.wm0.ignore_lines), new_wm->sagv.wm0.lines, - enast(new_wm->sagv.trans_wm.ignore_lines), new_wm->sagv.trans_wm.lines); - - drm_dbg_kms(&dev_priv->drm, - "[PLANE:%d:%s] blocks %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d" - " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d\n", - plane->base.base.id, plane->base.name, - old_wm->wm[0].blocks, old_wm->wm[1].blocks, - old_wm->wm[2].blocks, old_wm->wm[3].blocks, - old_wm->wm[4].blocks, old_wm->wm[5].blocks, - old_wm->wm[6].blocks, old_wm->wm[7].blocks, - old_wm->trans_wm.blocks, - old_wm->sagv.wm0.blocks, - old_wm->sagv.trans_wm.blocks, - new_wm->wm[0].blocks, new_wm->wm[1].blocks, - new_wm->wm[2].blocks, new_wm->wm[3].blocks, - new_wm->wm[4].blocks, new_wm->wm[5].blocks, - new_wm->wm[6].blocks, new_wm->wm[7].blocks, - new_wm->trans_wm.blocks, - new_wm->sagv.wm0.blocks, - new_wm->sagv.trans_wm.blocks); - - drm_dbg_kms(&dev_priv->drm, - "[PLANE:%d:%s] min_ddb %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d" - " -> %4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%4d,%5d\n", - plane->base.base.id, plane->base.name, - old_wm->wm[0].min_ddb_alloc, old_wm->wm[1].min_ddb_alloc, - old_wm->wm[2].min_ddb_alloc, old_wm->wm[3].min_ddb_alloc, - old_wm->wm[4].min_ddb_alloc, old_wm->wm[5].min_ddb_alloc, - old_wm->wm[6].min_ddb_alloc, old_wm->wm[7].min_ddb_alloc, - old_wm->trans_wm.min_ddb_alloc, - old_wm->sagv.wm0.min_ddb_alloc, - old_wm->sagv.trans_wm.min_ddb_alloc, - new_wm->wm[0].min_ddb_alloc, new_wm->wm[1].min_ddb_alloc, - new_wm->wm[2].min_ddb_alloc, new_wm->wm[3].min_ddb_alloc, - new_wm->wm[4].min_ddb_alloc, new_wm->wm[5].min_ddb_alloc, - new_wm->wm[6].min_ddb_alloc, new_wm->wm[7].min_ddb_alloc, - new_wm->trans_wm.min_ddb_alloc, - new_wm->sagv.wm0.min_ddb_alloc, - new_wm->sagv.trans_wm.min_ddb_alloc); - } - } -} - -static bool skl_plane_selected_wm_equals(struct intel_plane *plane, - const struct skl_pipe_wm *old_pipe_wm, - const struct skl_pipe_wm *new_pipe_wm) -{ - struct drm_i915_private *i915 = to_i915(plane->base.dev); - int level, max_level = ilk_wm_max_level(i915); - - for (level = 0; level <= max_level; level++) { - /* - * We don't check uv_wm as the hardware doesn't actually - * use it. It only gets used for calculating the required - * ddb allocation. - */ - if (!skl_wm_level_equals(skl_plane_wm_level(old_pipe_wm, plane->id, level), - skl_plane_wm_level(new_pipe_wm, plane->id, level))) - return false; - } - - if (HAS_HW_SAGV_WM(i915)) { - const struct skl_plane_wm *old_wm = &old_pipe_wm->planes[plane->id]; - const struct skl_plane_wm *new_wm = &new_pipe_wm->planes[plane->id]; - - if (!skl_wm_level_equals(&old_wm->sagv.wm0, &new_wm->sagv.wm0) || - !skl_wm_level_equals(&old_wm->sagv.trans_wm, &new_wm->sagv.trans_wm)) - return false; - } - - return skl_wm_level_equals(skl_plane_trans_wm(old_pipe_wm, plane->id), - skl_plane_trans_wm(new_pipe_wm, plane->id)); -} - -/* - * To make sure the cursor watermark registers are always consistent - * with our computed state the following scenario needs special - * treatment: - * - * 1. enable cursor - * 2. move cursor entirely offscreen - * 3. disable cursor - * - * Step 2. does call .disable_plane() but does not zero the watermarks - * (since we consider an offscreen cursor still active for the purposes - * of watermarks). Step 3. would not normally call .disable_plane() - * because the actual plane visibility isn't changing, and we don't - * deallocate the cursor ddb until the pipe gets disabled. So we must - * force step 3. to call .disable_plane() to update the watermark - * registers properly. - * - * Other planes do not suffer from this issues as their watermarks are - * calculated based on the actual plane visibility. The only time this - * can trigger for the other planes is during the initial readout as the - * default value of the watermarks registers is not zero. - */ -static int skl_wm_add_affected_planes(struct intel_atomic_state *state, - struct intel_crtc *crtc) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - const struct intel_crtc_state *old_crtc_state = - intel_atomic_get_old_crtc_state(state, crtc); - struct intel_crtc_state *new_crtc_state = - intel_atomic_get_new_crtc_state(state, crtc); - struct intel_plane *plane; - - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { - struct intel_plane_state *plane_state; - enum plane_id plane_id = plane->id; - - /* - * Force a full wm update for every plane on modeset. - * Required because the reset value of the wm registers - * is non-zero, whereas we want all disabled planes to - * have zero watermarks. So if we turn off the relevant - * power well the hardware state will go out of sync - * with the software state. - */ - if (!drm_atomic_crtc_needs_modeset(&new_crtc_state->uapi) && - skl_plane_selected_wm_equals(plane, - &old_crtc_state->wm.skl.optimal, - &new_crtc_state->wm.skl.optimal)) - continue; - - plane_state = intel_atomic_get_plane_state(state, plane); - if (IS_ERR(plane_state)) - return PTR_ERR(plane_state); - - new_crtc_state->update_planes |= BIT(plane_id); - } - - return 0; -} - -static int -skl_compute_wm(struct intel_atomic_state *state) -{ - struct intel_crtc *crtc; - struct intel_crtc_state *new_crtc_state; - int ret, i; - - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { - ret = skl_build_pipe_wm(state, crtc); - if (ret) - return ret; - } - - ret = skl_compute_ddb(state); - if (ret) - return ret; - - ret = intel_compute_sagv_mask(state); - if (ret) - return ret; - - /* - * skl_compute_ddb() will have adjusted the final watermarks - * based on how much ddb is available. Now we can actually - * check if the final watermarks changed. - */ - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { - ret = skl_wm_add_affected_planes(state, crtc); - if (ret) - return ret; - } - - skl_print_wm_changes(state); - - return 0; -} - static void ilk_compute_wm_config(struct drm_i915_private *dev_priv, struct intel_wm_config *config) { @@ -6458,10 +3583,10 @@ static void ilk_initial_watermarks(struct intel_atomic_state *state, const struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc); - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); crtc->wm.active.ilk = crtc_state->wm.ilk.intermediate; ilk_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } static void ilk_optimize_watermarks(struct intel_atomic_state *state, @@ -6474,210 +3599,17 @@ static void ilk_optimize_watermarks(struct intel_atomic_state *state, if (!crtc_state->wm.need_postvbl_update) return; - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); crtc->wm.active.ilk = crtc_state->wm.ilk.optimal; ilk_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); -} - -static void skl_wm_level_from_reg_val(u32 val, struct skl_wm_level *level) -{ - level->enable = val & PLANE_WM_EN; - level->ignore_lines = val & PLANE_WM_IGNORE_LINES; - level->blocks = REG_FIELD_GET(PLANE_WM_BLOCKS_MASK, val); - level->lines = REG_FIELD_GET(PLANE_WM_LINES_MASK, val); -} - -static void skl_pipe_wm_get_hw_state(struct intel_crtc *crtc, - struct skl_pipe_wm *out) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - enum pipe pipe = crtc->pipe; - int level, max_level; - enum plane_id plane_id; - u32 val; - - max_level = ilk_wm_max_level(dev_priv); - - for_each_plane_id_on_crtc(crtc, plane_id) { - struct skl_plane_wm *wm = &out->planes[plane_id]; - - for (level = 0; level <= max_level; level++) { - if (plane_id != PLANE_CURSOR) - val = intel_uncore_read(&dev_priv->uncore, PLANE_WM(pipe, plane_id, level)); - else - val = intel_uncore_read(&dev_priv->uncore, CUR_WM(pipe, level)); - - skl_wm_level_from_reg_val(val, &wm->wm[level]); - } - - if (plane_id != PLANE_CURSOR) - val = intel_uncore_read(&dev_priv->uncore, PLANE_WM_TRANS(pipe, plane_id)); - else - val = intel_uncore_read(&dev_priv->uncore, CUR_WM_TRANS(pipe)); - - skl_wm_level_from_reg_val(val, &wm->trans_wm); - - if (HAS_HW_SAGV_WM(dev_priv)) { - if (plane_id != PLANE_CURSOR) - val = intel_uncore_read(&dev_priv->uncore, - PLANE_WM_SAGV(pipe, plane_id)); - else - val = intel_uncore_read(&dev_priv->uncore, - CUR_WM_SAGV(pipe)); - - skl_wm_level_from_reg_val(val, &wm->sagv.wm0); - - if (plane_id != PLANE_CURSOR) - val = intel_uncore_read(&dev_priv->uncore, - PLANE_WM_SAGV_TRANS(pipe, plane_id)); - else - val = intel_uncore_read(&dev_priv->uncore, - CUR_WM_SAGV_TRANS(pipe)); - - skl_wm_level_from_reg_val(val, &wm->sagv.trans_wm); - } else if (DISPLAY_VER(dev_priv) >= 12) { - wm->sagv.wm0 = wm->wm[0]; - wm->sagv.trans_wm = wm->trans_wm; - } - } -} - -void skl_wm_get_hw_state(struct drm_i915_private *dev_priv) -{ - struct intel_dbuf_state *dbuf_state = - to_intel_dbuf_state(dev_priv->dbuf.obj.state); - struct intel_crtc *crtc; - - if (HAS_MBUS_JOINING(dev_priv)) - dbuf_state->joined_mbus = intel_de_read(dev_priv, MBUS_CTL) & MBUS_JOIN; - - for_each_intel_crtc(&dev_priv->drm, crtc) { - struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - enum pipe pipe = crtc->pipe; - unsigned int mbus_offset; - enum plane_id plane_id; - u8 slices; - - skl_pipe_wm_get_hw_state(crtc, &crtc_state->wm.skl.optimal); - crtc_state->wm.skl.raw = crtc_state->wm.skl.optimal; - - memset(&dbuf_state->ddb[pipe], 0, sizeof(dbuf_state->ddb[pipe])); - - for_each_plane_id_on_crtc(crtc, plane_id) { - struct skl_ddb_entry *ddb = - &crtc_state->wm.skl.plane_ddb[plane_id]; - struct skl_ddb_entry *ddb_y = - &crtc_state->wm.skl.plane_ddb_y[plane_id]; - - skl_ddb_get_hw_plane_state(dev_priv, crtc->pipe, - plane_id, ddb, ddb_y); - - skl_ddb_entry_union(&dbuf_state->ddb[pipe], ddb); - skl_ddb_entry_union(&dbuf_state->ddb[pipe], ddb_y); - } - - dbuf_state->weight[pipe] = intel_crtc_ddb_weight(crtc_state); - - /* - * Used for checking overlaps, so we need absolute - * offsets instead of MBUS relative offsets. - */ - slices = skl_compute_dbuf_slices(crtc, dbuf_state->active_pipes, - dbuf_state->joined_mbus); - mbus_offset = mbus_ddb_offset(dev_priv, slices); - crtc_state->wm.skl.ddb.start = mbus_offset + dbuf_state->ddb[pipe].start; - crtc_state->wm.skl.ddb.end = mbus_offset + dbuf_state->ddb[pipe].end; - - /* The slices actually used by the planes on the pipe */ - dbuf_state->slices[pipe] = - skl_ddb_dbuf_slice_mask(dev_priv, &crtc_state->wm.skl.ddb); - - drm_dbg_kms(&dev_priv->drm, - "[CRTC:%d:%s] dbuf slices 0x%x, ddb (%d - %d), active pipes 0x%x, mbus joined: %s\n", - crtc->base.base.id, crtc->base.name, - dbuf_state->slices[pipe], dbuf_state->ddb[pipe].start, - dbuf_state->ddb[pipe].end, dbuf_state->active_pipes, - str_yes_no(dbuf_state->joined_mbus)); - } - - dbuf_state->enabled_slices = dev_priv->dbuf.enabled_slices; -} - -static bool skl_dbuf_is_misconfigured(struct drm_i915_private *i915) -{ - const struct intel_dbuf_state *dbuf_state = - to_intel_dbuf_state(i915->dbuf.obj.state); - struct skl_ddb_entry entries[I915_MAX_PIPES] = {}; - struct intel_crtc *crtc; - - for_each_intel_crtc(&i915->drm, crtc) { - const struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - - entries[crtc->pipe] = crtc_state->wm.skl.ddb; - } - - for_each_intel_crtc(&i915->drm, crtc) { - const struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - u8 slices; - - slices = skl_compute_dbuf_slices(crtc, dbuf_state->active_pipes, - dbuf_state->joined_mbus); - if (dbuf_state->slices[crtc->pipe] & ~slices) - return true; - - if (skl_ddb_allocation_overlaps(&crtc_state->wm.skl.ddb, entries, - I915_MAX_PIPES, crtc->pipe)) - return true; - } - - return false; -} - -void skl_wm_sanitize(struct drm_i915_private *i915) -{ - struct intel_crtc *crtc; - - /* - * On TGL/RKL (at least) the BIOS likes to assign the planes - * to the wrong DBUF slices. This will cause an infinite loop - * in skl_commit_modeset_enables() as it can't find a way to - * transition between the old bogus DBUF layout to the new - * proper DBUF layout without DBUF allocation overlaps between - * the planes (which cannot be allowed or else the hardware - * may hang). If we detect a bogus DBUF layout just turn off - * all the planes so that skl_commit_modeset_enables() can - * simply ignore them. - */ - if (!skl_dbuf_is_misconfigured(i915)) - return; - - drm_dbg_kms(&i915->drm, "BIOS has misprogrammed the DBUF, disabling all planes\n"); - - for_each_intel_crtc(&i915->drm, crtc) { - struct intel_plane *plane = to_intel_plane(crtc->base.primary); - const struct intel_plane_state *plane_state = - to_intel_plane_state(plane->base.state); - struct intel_crtc_state *crtc_state = - to_intel_crtc_state(crtc->base.state); - - if (plane_state->uapi.visible) - intel_plane_disable_noatomic(crtc, plane); - - drm_WARN_ON(&i915->drm, crtc_state->active_planes != 0); - - memset(&crtc_state->wm.skl.ddb, 0, sizeof(crtc_state->wm.skl.ddb)); - } + mutex_unlock(&dev_priv->display.wm.wm_mutex); } static void ilk_pipe_wm_get_hw_state(struct intel_crtc *crtc) { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = to_i915(dev); - struct ilk_wm_values *hw = &dev_priv->wm.hw; + struct ilk_wm_values *hw = &dev_priv->display.wm.hw; struct intel_crtc_state *crtc_state = to_intel_crtc_state(crtc->base.state); struct intel_pipe_wm *active = &crtc_state->wm.ilk.optimal; enum pipe pipe = crtc->pipe; @@ -6825,7 +3757,7 @@ static void vlv_read_wm_values(struct drm_i915_private *dev_priv, void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct g4x_wm_values *wm = &dev_priv->wm.g4x; + struct g4x_wm_values *wm = &dev_priv->display.wm.g4x; struct intel_crtc *crtc; g4x_read_wm_values(dev_priv, wm); @@ -6919,7 +3851,7 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv) struct intel_plane *plane; struct intel_crtc *crtc; - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); for_each_intel_plane(&dev_priv->drm, plane) { struct intel_crtc *crtc = @@ -6967,12 +3899,12 @@ void g4x_wm_sanitize(struct drm_i915_private *dev_priv) g4x_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct vlv_wm_values *wm = &dev_priv->wm.vlv; + struct vlv_wm_values *wm = &dev_priv->display.wm.vlv; struct intel_crtc *crtc; u32 val; @@ -7006,7 +3938,7 @@ void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv) drm_dbg_kms(&dev_priv->drm, "Punit not acking DDR DVFS request, " "assuming DDR DVFS is disabled\n"); - dev_priv->wm.max_level = VLV_WM_LEVEL_PM5; + dev_priv->display.wm.max_level = VLV_WM_LEVEL_PM5; } else { val = vlv_punit_read(dev_priv, PUNIT_REG_DDR_SETUP2); if ((val & FORCE_DDR_HIGH_FREQ) == 0) @@ -7075,7 +4007,7 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv) struct intel_plane *plane; struct intel_crtc *crtc; - mutex_lock(&dev_priv->wm.wm_mutex); + mutex_lock(&dev_priv->display.wm.wm_mutex); for_each_intel_plane(&dev_priv->drm, plane) { struct intel_crtc *crtc = @@ -7116,7 +4048,7 @@ void vlv_wm_sanitize(struct drm_i915_private *dev_priv) vlv_program_watermarks(dev_priv); - mutex_unlock(&dev_priv->wm.wm_mutex); + mutex_unlock(&dev_priv->display.wm.wm_mutex); } /* @@ -7137,7 +4069,7 @@ static void ilk_init_lp_watermarks(struct drm_i915_private *dev_priv) void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv) { - struct ilk_wm_values *hw = &dev_priv->wm.hw; + struct ilk_wm_values *hw = &dev_priv->display.wm.hw; struct intel_crtc *crtc; ilk_init_lp_watermarks(dev_priv); @@ -7166,168 +4098,6 @@ void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv) !(intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL) & DISP_FBC_WM_DIS); } -void intel_wm_state_verify(struct intel_crtc *crtc, - struct intel_crtc_state *new_crtc_state) -{ - struct drm_i915_private *dev_priv = to_i915(crtc->base.dev); - struct skl_hw_state { - struct skl_ddb_entry ddb[I915_MAX_PLANES]; - struct skl_ddb_entry ddb_y[I915_MAX_PLANES]; - struct skl_pipe_wm wm; - } *hw; - const struct skl_pipe_wm *sw_wm = &new_crtc_state->wm.skl.optimal; - int level, max_level = ilk_wm_max_level(dev_priv); - struct intel_plane *plane; - u8 hw_enabled_slices; - - if (DISPLAY_VER(dev_priv) < 9 || !new_crtc_state->hw.active) - return; - - hw = kzalloc(sizeof(*hw), GFP_KERNEL); - if (!hw) - return; - - skl_pipe_wm_get_hw_state(crtc, &hw->wm); - - skl_pipe_ddb_get_hw_state(crtc, hw->ddb, hw->ddb_y); - - hw_enabled_slices = intel_enabled_dbuf_slices_mask(dev_priv); - - if (DISPLAY_VER(dev_priv) >= 11 && - hw_enabled_slices != dev_priv->dbuf.enabled_slices) - drm_err(&dev_priv->drm, - "mismatch in DBUF Slices (expected 0x%x, got 0x%x)\n", - dev_priv->dbuf.enabled_slices, - hw_enabled_slices); - - for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) { - const struct skl_ddb_entry *hw_ddb_entry, *sw_ddb_entry; - const struct skl_wm_level *hw_wm_level, *sw_wm_level; - - /* Watermarks */ - for (level = 0; level <= max_level; level++) { - hw_wm_level = &hw->wm.planes[plane->id].wm[level]; - sw_wm_level = skl_plane_wm_level(sw_wm, plane->id, level); - - if (skl_wm_level_equals(hw_wm_level, sw_wm_level)) - continue; - - drm_err(&dev_priv->drm, - "[PLANE:%d:%s] mismatch in WM%d (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", - plane->base.base.id, plane->base.name, level, - sw_wm_level->enable, - sw_wm_level->blocks, - sw_wm_level->lines, - hw_wm_level->enable, - hw_wm_level->blocks, - hw_wm_level->lines); - } - - hw_wm_level = &hw->wm.planes[plane->id].trans_wm; - sw_wm_level = skl_plane_trans_wm(sw_wm, plane->id); - - if (!skl_wm_level_equals(hw_wm_level, sw_wm_level)) { - drm_err(&dev_priv->drm, - "[PLANE:%d:%s] mismatch in trans WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", - plane->base.base.id, plane->base.name, - sw_wm_level->enable, - sw_wm_level->blocks, - sw_wm_level->lines, - hw_wm_level->enable, - hw_wm_level->blocks, - hw_wm_level->lines); - } - - hw_wm_level = &hw->wm.planes[plane->id].sagv.wm0; - sw_wm_level = &sw_wm->planes[plane->id].sagv.wm0; - - if (HAS_HW_SAGV_WM(dev_priv) && - !skl_wm_level_equals(hw_wm_level, sw_wm_level)) { - drm_err(&dev_priv->drm, - "[PLANE:%d:%s] mismatch in SAGV WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", - plane->base.base.id, plane->base.name, - sw_wm_level->enable, - sw_wm_level->blocks, - sw_wm_level->lines, - hw_wm_level->enable, - hw_wm_level->blocks, - hw_wm_level->lines); - } - - hw_wm_level = &hw->wm.planes[plane->id].sagv.trans_wm; - sw_wm_level = &sw_wm->planes[plane->id].sagv.trans_wm; - - if (HAS_HW_SAGV_WM(dev_priv) && - !skl_wm_level_equals(hw_wm_level, sw_wm_level)) { - drm_err(&dev_priv->drm, - "[PLANE:%d:%s] mismatch in SAGV trans WM (expected e=%d b=%u l=%u, got e=%d b=%u l=%u)\n", - plane->base.base.id, plane->base.name, - sw_wm_level->enable, - sw_wm_level->blocks, - sw_wm_level->lines, - hw_wm_level->enable, - hw_wm_level->blocks, - hw_wm_level->lines); - } - - /* DDB */ - hw_ddb_entry = &hw->ddb[PLANE_CURSOR]; - sw_ddb_entry = &new_crtc_state->wm.skl.plane_ddb[PLANE_CURSOR]; - - if (!skl_ddb_entry_equal(hw_ddb_entry, sw_ddb_entry)) { - drm_err(&dev_priv->drm, - "[PLANE:%d:%s] mismatch in DDB (expected (%u,%u), found (%u,%u))\n", - plane->base.base.id, plane->base.name, - sw_ddb_entry->start, sw_ddb_entry->end, - hw_ddb_entry->start, hw_ddb_entry->end); - } - } - - kfree(hw); -} - -void intel_enable_ipc(struct drm_i915_private *dev_priv) -{ - u32 val; - - if (!HAS_IPC(dev_priv)) - return; - - val = intel_uncore_read(&dev_priv->uncore, DISP_ARB_CTL2); - - if (dev_priv->ipc_enabled) - val |= DISP_IPC_ENABLE; - else - val &= ~DISP_IPC_ENABLE; - - intel_uncore_write(&dev_priv->uncore, DISP_ARB_CTL2, val); -} - -static bool intel_can_enable_ipc(struct drm_i915_private *dev_priv) -{ - /* Display WA #0477 WaDisableIPC: skl */ - if (IS_SKYLAKE(dev_priv)) - return false; - - /* Display WA #1141: SKL:all KBL:all CFL */ - if (IS_KABYLAKE(dev_priv) || - IS_COFFEELAKE(dev_priv) || - IS_COMETLAKE(dev_priv)) - return dev_priv->dram_info.symmetric_memory; - - return true; -} - -void intel_init_ipc(struct drm_i915_private *dev_priv) -{ - if (!HAS_IPC(dev_priv)) - return; - - dev_priv->ipc_enabled = intel_can_enable_ipc(dev_priv); - - intel_enable_ipc(dev_priv); -} - static void ibx_init_clock_gating(struct drm_i915_private *dev_priv) { /* @@ -7435,7 +4205,7 @@ static void cpt_init_clock_gating(struct drm_i915_private *dev_priv) val = intel_uncore_read(&dev_priv->uncore, TRANS_CHICKEN2(pipe)); val |= TRANS_CHICKEN2_TIMING_OVERRIDE; val &= ~TRANS_CHICKEN2_FDI_POLARITY_REVERSED; - if (dev_priv->vbt.fdi_rx_polarity_inverted) + if (dev_priv->display.vbt.fdi_rx_polarity_inverted) val |= TRANS_CHICKEN2_FDI_POLARITY_REVERSED; val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER; val &= ~TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH; @@ -7586,9 +4356,8 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) static void gen12lp_init_clock_gating(struct drm_i915_private *dev_priv) { - /* Wa_1409120013:tgl,rkl,adl-s,dg1,dg2 */ - if (IS_TIGERLAKE(dev_priv) || IS_ROCKETLAKE(dev_priv) || - IS_ALDERLAKE_S(dev_priv) || IS_DG1(dev_priv) || IS_DG2(dev_priv)) + /* Wa_1409120013 */ + if (DISPLAY_VER(dev_priv) == 12) intel_uncore_write(&dev_priv->uncore, ILK_DPFC_CHICKEN(INTEL_FBC_A), DPFC_CHICKEN_COMP_DUMMY_PIXEL); @@ -7965,7 +4734,7 @@ static void g4x_init_clock_gating(struct drm_i915_private *dev_priv) OVCUNIT_CLOCK_GATE_DISABLE; if (IS_GM45(dev_priv)) dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE; - intel_uncore_write(&dev_priv->uncore, DSPCLK_GATE_D, dspclk_gate); + intel_uncore_write(&dev_priv->uncore, DSPCLK_GATE_D(dev_priv), dspclk_gate); g4x_disable_trickle_feed(dev_priv); } @@ -7976,7 +4745,7 @@ static void i965gm_init_clock_gating(struct drm_i915_private *dev_priv) intel_uncore_write(uncore, RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE); intel_uncore_write(uncore, RENCLK_GATE_D2, 0); - intel_uncore_write(uncore, DSPCLK_GATE_D, 0); + intel_uncore_write(uncore, DSPCLK_GATE_D(dev_priv), 0); intel_uncore_write(uncore, RAMCLK_GATE_D, 0); intel_uncore_write16(uncore, DEUC, 0); intel_uncore_write(uncore, @@ -8168,18 +4937,14 @@ void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv) } } -static const struct drm_i915_wm_disp_funcs skl_wm_funcs = { - .compute_global_watermarks = skl_compute_wm, -}; - -static const struct drm_i915_wm_disp_funcs ilk_wm_funcs = { +static const struct intel_wm_funcs ilk_wm_funcs = { .compute_pipe_wm = ilk_compute_pipe_wm, .compute_intermediate_wm = ilk_compute_intermediate_wm, .initial_watermarks = ilk_initial_watermarks, .optimize_watermarks = ilk_optimize_watermarks, }; -static const struct drm_i915_wm_disp_funcs vlv_wm_funcs = { +static const struct intel_wm_funcs vlv_wm_funcs = { .compute_pipe_wm = vlv_compute_pipe_wm, .compute_intermediate_wm = vlv_compute_intermediate_wm, .initial_watermarks = vlv_initial_watermarks, @@ -8187,67 +4952,67 @@ static const struct drm_i915_wm_disp_funcs vlv_wm_funcs = { .atomic_update_watermarks = vlv_atomic_update_fifo, }; -static const struct drm_i915_wm_disp_funcs g4x_wm_funcs = { +static const struct intel_wm_funcs g4x_wm_funcs = { .compute_pipe_wm = g4x_compute_pipe_wm, .compute_intermediate_wm = g4x_compute_intermediate_wm, .initial_watermarks = g4x_initial_watermarks, .optimize_watermarks = g4x_optimize_watermarks, }; -static const struct drm_i915_wm_disp_funcs pnv_wm_funcs = { +static const struct intel_wm_funcs pnv_wm_funcs = { .update_wm = pnv_update_wm, }; -static const struct drm_i915_wm_disp_funcs i965_wm_funcs = { +static const struct intel_wm_funcs i965_wm_funcs = { .update_wm = i965_update_wm, }; -static const struct drm_i915_wm_disp_funcs i9xx_wm_funcs = { +static const struct intel_wm_funcs i9xx_wm_funcs = { .update_wm = i9xx_update_wm, }; -static const struct drm_i915_wm_disp_funcs i845_wm_funcs = { +static const struct intel_wm_funcs i845_wm_funcs = { .update_wm = i845_update_wm, }; -static const struct drm_i915_wm_disp_funcs nop_funcs = { +static const struct intel_wm_funcs nop_funcs = { }; /* Set up chip specific power management-related functions */ void intel_init_pm(struct drm_i915_private *dev_priv) { + if (DISPLAY_VER(dev_priv) >= 9) { + skl_wm_init(dev_priv); + return; + } + /* For cxsr */ if (IS_PINEVIEW(dev_priv)) pnv_get_mem_freq(dev_priv); else if (GRAPHICS_VER(dev_priv) == 5) ilk_get_mem_freq(dev_priv); - intel_sagv_init(dev_priv); - /* For FIFO watermark updates */ - if (DISPLAY_VER(dev_priv) >= 9) { - skl_setup_wm_latency(dev_priv); - dev_priv->wm_disp = &skl_wm_funcs; - } else if (HAS_PCH_SPLIT(dev_priv)) { + if (HAS_PCH_SPLIT(dev_priv)) { ilk_setup_wm_latency(dev_priv); - if ((DISPLAY_VER(dev_priv) == 5 && dev_priv->wm.pri_latency[1] && - dev_priv->wm.spr_latency[1] && dev_priv->wm.cur_latency[1]) || - (DISPLAY_VER(dev_priv) != 5 && dev_priv->wm.pri_latency[0] && - dev_priv->wm.spr_latency[0] && dev_priv->wm.cur_latency[0])) { - dev_priv->wm_disp = &ilk_wm_funcs; + if ((DISPLAY_VER(dev_priv) == 5 && dev_priv->display.wm.pri_latency[1] && + dev_priv->display.wm.spr_latency[1] && dev_priv->display.wm.cur_latency[1]) || + (DISPLAY_VER(dev_priv) != 5 && dev_priv->display.wm.pri_latency[0] && + dev_priv->display.wm.spr_latency[0] && dev_priv->display.wm.cur_latency[0])) { + dev_priv->display.funcs.wm = &ilk_wm_funcs; } else { drm_dbg_kms(&dev_priv->drm, "Failed to read display plane latency. " "Disable CxSR\n"); - dev_priv->wm_disp = &nop_funcs; + dev_priv->display.funcs.wm = &nop_funcs; } } else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) { vlv_setup_wm_latency(dev_priv); - dev_priv->wm_disp = &vlv_wm_funcs; + dev_priv->display.funcs.wm = &vlv_wm_funcs; } else if (IS_G4X(dev_priv)) { g4x_setup_wm_latency(dev_priv); - dev_priv->wm_disp = &g4x_wm_funcs; + dev_priv->display.funcs.wm = &g4x_wm_funcs; } else if (IS_PINEVIEW(dev_priv)) { if (!intel_get_cxsr_latency(!IS_MOBILE(dev_priv), dev_priv->is_ddr3, @@ -8261,22 +5026,22 @@ void intel_init_pm(struct drm_i915_private *dev_priv) dev_priv->fsb_freq, dev_priv->mem_freq); /* Disable CxSR and never update its watermark again */ intel_set_memory_cxsr(dev_priv, false); - dev_priv->wm_disp = &nop_funcs; + dev_priv->display.funcs.wm = &nop_funcs; } else - dev_priv->wm_disp = &pnv_wm_funcs; + dev_priv->display.funcs.wm = &pnv_wm_funcs; } else if (DISPLAY_VER(dev_priv) == 4) { - dev_priv->wm_disp = &i965_wm_funcs; + dev_priv->display.funcs.wm = &i965_wm_funcs; } else if (DISPLAY_VER(dev_priv) == 3) { - dev_priv->wm_disp = &i9xx_wm_funcs; + dev_priv->display.funcs.wm = &i9xx_wm_funcs; } else if (DISPLAY_VER(dev_priv) == 2) { if (INTEL_NUM_PIPES(dev_priv) == 1) - dev_priv->wm_disp = &i845_wm_funcs; + dev_priv->display.funcs.wm = &i845_wm_funcs; else - dev_priv->wm_disp = &i9xx_wm_funcs; + dev_priv->display.funcs.wm = &i9xx_wm_funcs; } else { drm_err(&dev_priv->drm, "unexpected fall-through in %s\n", __func__); - dev_priv->wm_disp = &nop_funcs; + dev_priv->display.funcs.wm = &nop_funcs; } } @@ -8285,183 +5050,3 @@ void intel_pm_setup(struct drm_i915_private *dev_priv) dev_priv->runtime_pm.suspended = false; atomic_set(&dev_priv->runtime_pm.wakeref_count, 0); } - -static struct intel_global_state *intel_dbuf_duplicate_state(struct intel_global_obj *obj) -{ - struct intel_dbuf_state *dbuf_state; - - dbuf_state = kmemdup(obj->state, sizeof(*dbuf_state), GFP_KERNEL); - if (!dbuf_state) - return NULL; - - return &dbuf_state->base; -} - -static void intel_dbuf_destroy_state(struct intel_global_obj *obj, - struct intel_global_state *state) -{ - kfree(state); -} - -static const struct intel_global_state_funcs intel_dbuf_funcs = { - .atomic_duplicate_state = intel_dbuf_duplicate_state, - .atomic_destroy_state = intel_dbuf_destroy_state, -}; - -struct intel_dbuf_state * -intel_atomic_get_dbuf_state(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - struct intel_global_state *dbuf_state; - - dbuf_state = intel_atomic_get_global_obj_state(state, &dev_priv->dbuf.obj); - if (IS_ERR(dbuf_state)) - return ERR_CAST(dbuf_state); - - return to_intel_dbuf_state(dbuf_state); -} - -int intel_dbuf_init(struct drm_i915_private *dev_priv) -{ - struct intel_dbuf_state *dbuf_state; - - dbuf_state = kzalloc(sizeof(*dbuf_state), GFP_KERNEL); - if (!dbuf_state) - return -ENOMEM; - - intel_atomic_global_obj_init(dev_priv, &dev_priv->dbuf.obj, - &dbuf_state->base, &intel_dbuf_funcs); - - return 0; -} - -/* - * Configure MBUS_CTL and all DBUF_CTL_S of each slice to join_mbus state before - * update the request state of all DBUS slices. - */ -static void update_mbus_pre_enable(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - u32 mbus_ctl, dbuf_min_tracker_val; - enum dbuf_slice slice; - const struct intel_dbuf_state *dbuf_state = - intel_atomic_get_new_dbuf_state(state); - - if (!HAS_MBUS_JOINING(dev_priv)) - return; - - /* - * TODO: Implement vblank synchronized MBUS joining changes. - * Must be properly coordinated with dbuf reprogramming. - */ - if (dbuf_state->joined_mbus) { - mbus_ctl = MBUS_HASHING_MODE_1x4 | MBUS_JOIN | - MBUS_JOIN_PIPE_SELECT_NONE; - dbuf_min_tracker_val = DBUF_MIN_TRACKER_STATE_SERVICE(3); - } else { - mbus_ctl = MBUS_HASHING_MODE_2x2 | - MBUS_JOIN_PIPE_SELECT_NONE; - dbuf_min_tracker_val = DBUF_MIN_TRACKER_STATE_SERVICE(1); - } - - intel_de_rmw(dev_priv, MBUS_CTL, - MBUS_HASHING_MODE_MASK | MBUS_JOIN | - MBUS_JOIN_PIPE_SELECT_MASK, mbus_ctl); - - for_each_dbuf_slice(dev_priv, slice) - intel_de_rmw(dev_priv, DBUF_CTL_S(slice), - DBUF_MIN_TRACKER_STATE_SERVICE_MASK, - dbuf_min_tracker_val); -} - -void intel_dbuf_pre_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_dbuf_state *new_dbuf_state = - intel_atomic_get_new_dbuf_state(state); - const struct intel_dbuf_state *old_dbuf_state = - intel_atomic_get_old_dbuf_state(state); - - if (!new_dbuf_state || - ((new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices) - && (new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus))) - return; - - WARN_ON(!new_dbuf_state->base.changed); - - update_mbus_pre_enable(state); - gen9_dbuf_slices_update(dev_priv, - old_dbuf_state->enabled_slices | - new_dbuf_state->enabled_slices); -} - -void intel_dbuf_post_plane_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *dev_priv = to_i915(state->base.dev); - const struct intel_dbuf_state *new_dbuf_state = - intel_atomic_get_new_dbuf_state(state); - const struct intel_dbuf_state *old_dbuf_state = - intel_atomic_get_old_dbuf_state(state); - - if (!new_dbuf_state || - ((new_dbuf_state->enabled_slices == old_dbuf_state->enabled_slices) - && (new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus))) - return; - - WARN_ON(!new_dbuf_state->base.changed); - - gen9_dbuf_slices_update(dev_priv, - new_dbuf_state->enabled_slices); -} - -void intel_mbus_dbox_update(struct intel_atomic_state *state) -{ - struct drm_i915_private *i915 = to_i915(state->base.dev); - const struct intel_dbuf_state *new_dbuf_state, *old_dbuf_state; - const struct intel_crtc_state *new_crtc_state; - const struct intel_crtc *crtc; - u32 val = 0; - int i; - - if (DISPLAY_VER(i915) < 11) - return; - - new_dbuf_state = intel_atomic_get_new_dbuf_state(state); - old_dbuf_state = intel_atomic_get_old_dbuf_state(state); - if (!new_dbuf_state || - (new_dbuf_state->joined_mbus == old_dbuf_state->joined_mbus && - new_dbuf_state->active_pipes == old_dbuf_state->active_pipes)) - return; - - if (DISPLAY_VER(i915) >= 12) { - val |= MBUS_DBOX_B2B_TRANSACTIONS_MAX(16); - val |= MBUS_DBOX_B2B_TRANSACTIONS_DELAY(1); - val |= MBUS_DBOX_REGULATE_B2B_TRANSACTIONS_EN; - } - - /* Wa_22010947358:adl-p */ - if (IS_ALDERLAKE_P(i915)) - val |= new_dbuf_state->joined_mbus ? MBUS_DBOX_A_CREDIT(6) : - MBUS_DBOX_A_CREDIT(4); - else - val |= MBUS_DBOX_A_CREDIT(2); - - if (IS_ALDERLAKE_P(i915)) { - val |= MBUS_DBOX_BW_CREDIT(2); - val |= MBUS_DBOX_B_CREDIT(8); - } else if (DISPLAY_VER(i915) >= 12) { - val |= MBUS_DBOX_BW_CREDIT(2); - val |= MBUS_DBOX_B_CREDIT(12); - } else { - val |= MBUS_DBOX_BW_CREDIT(1); - val |= MBUS_DBOX_B_CREDIT(8); - } - - for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) { - if (!new_crtc_state->hw.active || - !intel_crtc_needs_modeset(new_crtc_state)) - continue; - - intel_de_write(i915, PIPE_MBUS_DBOX_CTL(crtc->pipe), val); - } -} diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h index 945503ae493e..c09b872d65c8 100644 --- a/drivers/gpu/drm/i915/intel_pm.h +++ b/drivers/gpu/drm/i915/intel_pm.h @@ -8,22 +8,9 @@ #include <linux/types.h> -#include "display/intel_display.h" -#include "display/intel_global_state.h" - -#include "i915_drv.h" - -struct drm_device; struct drm_i915_private; -struct i915_request; -struct intel_atomic_state; -struct intel_bw_state; -struct intel_crtc; struct intel_crtc_state; -struct intel_plane; -struct skl_ddb_entry; -struct skl_pipe_wm; -struct skl_wm_level; +struct intel_plane_state; void intel_init_clock_gating(struct drm_i915_private *dev_priv); void intel_suspend_hw(struct drm_i915_private *dev_priv); @@ -34,56 +21,14 @@ void intel_pm_setup(struct drm_i915_private *dev_priv); void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv); void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv); void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv); -void skl_wm_get_hw_state(struct drm_i915_private *dev_priv); -void intel_wm_state_verify(struct intel_crtc *crtc, - struct intel_crtc_state *new_crtc_state); -u8 intel_enabled_dbuf_slices_mask(struct drm_i915_private *dev_priv); -void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv); -u32 skl_ddb_dbuf_slice_mask(struct drm_i915_private *dev_priv, - const struct skl_ddb_entry *entry); void g4x_wm_sanitize(struct drm_i915_private *dev_priv); void vlv_wm_sanitize(struct drm_i915_private *dev_priv); -void skl_wm_sanitize(struct drm_i915_private *dev_priv); -bool intel_can_enable_sagv(struct drm_i915_private *dev_priv, - const struct intel_bw_state *bw_state); -void intel_sagv_pre_plane_update(struct intel_atomic_state *state); -void intel_sagv_post_plane_update(struct intel_atomic_state *state); -bool skl_ddb_allocation_overlaps(const struct skl_ddb_entry *ddb, - const struct skl_ddb_entry *entries, - int num_entries, int ignore_idx); -void skl_write_plane_wm(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state); -void skl_write_cursor_wm(struct intel_plane *plane, - const struct intel_crtc_state *crtc_state); bool ilk_disable_lp_wm(struct drm_i915_private *dev_priv); -void intel_init_ipc(struct drm_i915_private *dev_priv); -void intel_enable_ipc(struct drm_i915_private *dev_priv); +bool intel_wm_plane_visible(const struct intel_crtc_state *crtc_state, + const struct intel_plane_state *plane_state); +void intel_print_wm_latency(struct drm_i915_private *dev_priv, + const char *name, const u16 wm[]); bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable); -struct intel_dbuf_state { - struct intel_global_state base; - - struct skl_ddb_entry ddb[I915_MAX_PIPES]; - unsigned int weight[I915_MAX_PIPES]; - u8 slices[I915_MAX_PIPES]; - u8 enabled_slices; - u8 active_pipes; - bool joined_mbus; -}; - -struct intel_dbuf_state * -intel_atomic_get_dbuf_state(struct intel_atomic_state *state); - -#define to_intel_dbuf_state(x) container_of((x), struct intel_dbuf_state, base) -#define intel_atomic_get_old_dbuf_state(state) \ - to_intel_dbuf_state(intel_atomic_get_old_global_obj_state(state, &to_i915(state->base.dev)->dbuf.obj)) -#define intel_atomic_get_new_dbuf_state(state) \ - to_intel_dbuf_state(intel_atomic_get_new_global_obj_state(state, &to_i915(state->base.dev)->dbuf.obj)) - -int intel_dbuf_init(struct drm_i915_private *dev_priv); -void intel_dbuf_pre_plane_update(struct intel_atomic_state *state); -void intel_dbuf_post_plane_update(struct intel_atomic_state *state); -void intel_mbus_dbox_update(struct intel_atomic_state *state); - #endif /* __INTEL_PM_H__ */ diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index c7ef5f2ff2e1..5cd423c7b646 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -21,6 +21,7 @@ * IN THE SOFTWARE. */ +#include <drm/drm_managed.h> #include <linux/pm_runtime.h> #include "gt/intel_engine_regs.h" @@ -44,29 +45,47 @@ fw_domains_get(struct intel_uncore *uncore, enum forcewake_domains fw_domains) } void -intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug) +intel_uncore_mmio_debug_init_early(struct drm_i915_private *i915) { - spin_lock_init(&mmio_debug->lock); - mmio_debug->unclaimed_mmio_check = 1; + spin_lock_init(&i915->mmio_debug.lock); + i915->mmio_debug.unclaimed_mmio_check = 1; + + i915->uncore.debug = &i915->mmio_debug; } -static void mmio_debug_suspend(struct intel_uncore_mmio_debug *mmio_debug) +static void mmio_debug_suspend(struct intel_uncore *uncore) { - lockdep_assert_held(&mmio_debug->lock); + if (!uncore->debug) + return; + + spin_lock(&uncore->debug->lock); /* Save and disable mmio debugging for the user bypass */ - if (!mmio_debug->suspend_count++) { - mmio_debug->saved_mmio_check = mmio_debug->unclaimed_mmio_check; - mmio_debug->unclaimed_mmio_check = 0; + if (!uncore->debug->suspend_count++) { + uncore->debug->saved_mmio_check = uncore->debug->unclaimed_mmio_check; + uncore->debug->unclaimed_mmio_check = 0; } + + spin_unlock(&uncore->debug->lock); } -static void mmio_debug_resume(struct intel_uncore_mmio_debug *mmio_debug) +static bool check_for_unclaimed_mmio(struct intel_uncore *uncore); + +static void mmio_debug_resume(struct intel_uncore *uncore) { - lockdep_assert_held(&mmio_debug->lock); + if (!uncore->debug) + return; + + spin_lock(&uncore->debug->lock); + + if (!--uncore->debug->suspend_count) + uncore->debug->unclaimed_mmio_check = uncore->debug->saved_mmio_check; - if (!--mmio_debug->suspend_count) - mmio_debug->unclaimed_mmio_check = mmio_debug->saved_mmio_check; + if (check_for_unclaimed_mmio(uncore)) + drm_info(&uncore->i915->drm, + "Invalid mmio detected during user access\n"); + + spin_unlock(&uncore->debug->lock); } static const char * const forcewake_domain_names[] = { @@ -677,9 +696,7 @@ void intel_uncore_forcewake_user_get(struct intel_uncore *uncore) spin_lock_irq(&uncore->lock); if (!uncore->user_forcewake_count++) { intel_uncore_forcewake_get__locked(uncore, FORCEWAKE_ALL); - spin_lock(&uncore->debug->lock); - mmio_debug_suspend(uncore->debug); - spin_unlock(&uncore->debug->lock); + mmio_debug_suspend(uncore); } spin_unlock_irq(&uncore->lock); } @@ -695,14 +712,7 @@ void intel_uncore_forcewake_user_put(struct intel_uncore *uncore) { spin_lock_irq(&uncore->lock); if (!--uncore->user_forcewake_count) { - spin_lock(&uncore->debug->lock); - mmio_debug_resume(uncore->debug); - - if (check_for_unclaimed_mmio(uncore)) - drm_info(&uncore->i915->drm, - "Invalid mmio detected during user access\n"); - spin_unlock(&uncore->debug->lock); - + mmio_debug_resume(uncore); intel_uncore_forcewake_put__locked(uncore, FORCEWAKE_ALL); } spin_unlock_irq(&uncore->lock); @@ -918,6 +928,9 @@ find_fw_domain(struct intel_uncore *uncore, u32 offset) { const struct intel_forcewake_range *entry; + if (IS_GSI_REG(offset)) + offset += uncore->gsi_offset; + entry = BSEARCH(offset, uncore->fw_domains_table, uncore->fw_domains_table_entries, @@ -1133,6 +1146,9 @@ static bool is_shadowed(struct intel_uncore *uncore, u32 offset) if (drm_WARN_ON(&uncore->i915->drm, !uncore->shadowed_reg_table)) return false; + if (IS_GSI_REG(offset)) + offset += uncore->gsi_offset; + return BSEARCH(offset, uncore->shadowed_reg_table, uncore->shadowed_reg_table_entries, @@ -1704,7 +1720,7 @@ unclaimed_reg_debug(struct intel_uncore *uncore, const bool read, const bool before) { - if (likely(!uncore->i915->params.mmio_debug)) + if (likely(!uncore->i915->params.mmio_debug) || !uncore->debug) return; /* interrupts are disabled and re-enabled around uncore->lock usage */ @@ -1985,8 +2001,8 @@ static int __fw_domain_init(struct intel_uncore *uncore, d->uncore = uncore; d->wake_count = 0; - d->reg_set = uncore->regs + i915_mmio_reg_offset(reg_set); - d->reg_ack = uncore->regs + i915_mmio_reg_offset(reg_ack); + d->reg_set = uncore->regs + i915_mmio_reg_offset(reg_set) + uncore->gsi_offset; + d->reg_ack = uncore->regs + i915_mmio_reg_offset(reg_ack) + uncore->gsi_offset; d->id = domain_id; @@ -2070,7 +2086,7 @@ static int intel_uncore_fw_domains_init(struct intel_uncore *uncore) if (GRAPHICS_VER(i915) >= 11) { /* we'll prune the domains of missing engines later */ - intel_engine_mask_t emask = INTEL_INFO(i915)->platform_engine_mask; + intel_engine_mask_t emask = RUNTIME_INFO(i915)->platform_engine_mask; int i; uncore->fw_get_funcs = &uncore_get_fallback; @@ -2223,6 +2239,11 @@ static int i915_pmic_bus_access_notifier(struct notifier_block *nb, return NOTIFY_OK; } +static void uncore_unmap_mmio(struct drm_device *drm, void *regs) +{ + iounmap(regs); +} + int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr) { struct drm_i915_private *i915 = uncore->i915; @@ -2251,12 +2272,7 @@ int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr) return -EIO; } - return 0; -} - -void intel_uncore_cleanup_mmio(struct intel_uncore *uncore) -{ - iounmap(uncore->regs); + return drmm_add_action_or_reset(&i915->drm, uncore_unmap_mmio, uncore->regs); } void intel_uncore_init_early(struct intel_uncore *uncore, @@ -2266,7 +2282,6 @@ void intel_uncore_init_early(struct intel_uncore *uncore, uncore->i915 = gt->i915; uncore->gt = gt; uncore->rpm = >->i915->runtime_pm; - uncore->debug = >->i915->mmio_debug; } static void uncore_raw_init(struct intel_uncore *uncore) @@ -2446,8 +2461,11 @@ void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore, } } -void intel_uncore_fini_mmio(struct intel_uncore *uncore) +/* Called via drm-managed action */ +void intel_uncore_fini_mmio(struct drm_device *dev, void *data) { + struct intel_uncore *uncore = data; + if (intel_uncore_has_forcewake(uncore)) { iosf_mbi_punit_acquire(); iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( @@ -2577,6 +2595,9 @@ bool intel_uncore_unclaimed_mmio(struct intel_uncore *uncore) { bool ret; + if (!uncore->debug) + return false; + spin_lock_irq(&uncore->debug->lock); ret = check_for_unclaimed_mmio(uncore); spin_unlock_irq(&uncore->debug->lock); @@ -2589,6 +2610,9 @@ intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore) { bool ret = false; + if (drm_WARN_ON(&uncore->i915->drm, !uncore->debug)) + return false; + spin_lock_irq(&uncore->debug->lock); if (unlikely(uncore->debug->unclaimed_mmio_check <= 0)) diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h index b1fa912a65e7..5022bac80b67 100644 --- a/drivers/gpu/drm/i915/intel_uncore.h +++ b/drivers/gpu/drm/i915/intel_uncore.h @@ -33,6 +33,7 @@ #include "i915_reg_defs.h" +struct drm_device; struct drm_i915_private; struct intel_runtime_pm; struct intel_uncore; @@ -135,6 +136,16 @@ struct intel_uncore { spinlock_t lock; /** lock is also taken in irq contexts. */ + /* + * Do we need to apply an additional offset to reach the beginning + * of the basic non-engine GT registers (referred to as "GSI" on + * newer platforms, or "GT block" on older platforms)? If so, we'll + * track that here and apply it transparently to registers in the + * appropriate range to maintain compatibility with our existing + * register definitions and GT code. + */ + u32 gsi_offset; + unsigned int flags; #define UNCORE_HAS_FORCEWAKE BIT(0) #define UNCORE_HAS_FPGA_DBG_UNCLAIMED BIT(1) @@ -210,8 +221,7 @@ intel_uncore_has_fifo(const struct intel_uncore *uncore) return uncore->flags & UNCORE_HAS_FIFO; } -void -intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug); +void intel_uncore_mmio_debug_init_early(struct drm_i915_private *i915); void intel_uncore_init_early(struct intel_uncore *uncore, struct intel_gt *gt); int intel_uncore_setup_mmio(struct intel_uncore *uncore, phys_addr_t phys_addr); @@ -221,7 +231,7 @@ void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore, bool intel_uncore_unclaimed_mmio(struct intel_uncore *uncore); bool intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore); void intel_uncore_cleanup_mmio(struct intel_uncore *uncore); -void intel_uncore_fini_mmio(struct intel_uncore *uncore); +void intel_uncore_fini_mmio(struct drm_device *dev, void *data); void intel_uncore_suspend(struct intel_uncore *uncore); void intel_uncore_resume_early(struct intel_uncore *uncore); void intel_uncore_runtime_resume(struct intel_uncore *uncore); @@ -294,19 +304,27 @@ intel_wait_for_register_fw(struct intel_uncore *uncore, 2, timeout_ms, NULL); } +#define IS_GSI_REG(reg) ((reg) < 0x40000) + /* register access functions */ #define __raw_read(x__, s__) \ static inline u##x__ __raw_uncore_read##x__(const struct intel_uncore *uncore, \ i915_reg_t reg) \ { \ - return read##s__(uncore->regs + i915_mmio_reg_offset(reg)); \ + u32 offset = i915_mmio_reg_offset(reg); \ + if (IS_GSI_REG(offset)) \ + offset += uncore->gsi_offset; \ + return read##s__(uncore->regs + offset); \ } #define __raw_write(x__, s__) \ static inline void __raw_uncore_write##x__(const struct intel_uncore *uncore, \ i915_reg_t reg, u##x__ val) \ { \ - write##s__(val, uncore->regs + i915_mmio_reg_offset(reg)); \ + u32 offset = i915_mmio_reg_offset(reg); \ + if (IS_GSI_REG(offset)) \ + offset += uncore->gsi_offset; \ + write##s__(val, uncore->regs + offset); \ } __raw_read(8, b) __raw_read(16, w) @@ -447,6 +465,18 @@ static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore, return (reg_val & mask) != expected_val ? -EINVAL : 0; } +/* + * The raw_reg_{read,write} macros are intended as a micro-optimization for + * interrupt handlers so that the pointer indirection on uncore->regs can + * be computed once (and presumably cached in a register) instead of generating + * extra load instructions for each MMIO access. + * + * Given that these macros are only intended for non-GSI interrupt registers + * (and the goal is to avoid extra instructions generated by the compiler), + * these macros do not account for uncore->gsi_offset. Any caller that needs + * to use these macros on a GSI register is responsible for adding the + * appropriate GSI offset to the 'base' parameter. + */ #define raw_reg_read(base, reg) \ readl(base + i915_mmio_reg_offset(reg)) #define raw_reg_write(base, reg, value) \ diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp.c b/drivers/gpu/drm/i915/pxp/intel_pxp.c index 17109c513259..69cdaaddc4a9 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp.c @@ -169,11 +169,11 @@ static void pxp_queue_termination(struct intel_pxp *pxp) * We want to get the same effect as if we received a termination * interrupt, so just pretend that we did. */ - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); intel_pxp_mark_termination_in_progress(pxp); pxp->session_events |= PXP_TERMINATION_REQUEST; queue_work(system_unbound_wq, &pxp->session_work); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } static bool pxp_component_bound(struct intel_pxp *pxp) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c index e888b5124a07..4359e8be4101 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_debugfs.c @@ -47,9 +47,9 @@ static int pxp_terminate_set(void *data, u64 val) return -ENODEV; /* simulate a termination interrupt */ - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); intel_pxp_irq_handler(pxp, GEN12_DISPLAY_PXP_STATE_TERMINATED_INTERRUPT); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); if (!wait_for_completion_timeout(&pxp->termination, msecs_to_jiffies(100))) diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c index 04745f914407..c28be430718a 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_irq.c @@ -25,7 +25,7 @@ void intel_pxp_irq_handler(struct intel_pxp *pxp, u16 iir) if (GEM_WARN_ON(!intel_pxp_is_enabled(pxp))) return; - lockdep_assert_held(>->irq_lock); + lockdep_assert_held(gt->irq_lock); if (unlikely(!iir)) return; @@ -55,16 +55,16 @@ static inline void __pxp_set_interrupts(struct intel_gt *gt, u32 interrupts) static inline void pxp_irq_reset(struct intel_gt *gt) { - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); gen11_gt_reset_one_iir(gt, 0, GEN11_KCR); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } void intel_pxp_irq_enable(struct intel_pxp *pxp) { struct intel_gt *gt = pxp_to_gt(pxp); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); if (!pxp->irq_enabled) WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_KCR)); @@ -72,7 +72,7 @@ void intel_pxp_irq_enable(struct intel_pxp *pxp) __pxp_set_interrupts(gt, GEN12_PXP_INTERRUPTS); pxp->irq_enabled = true; - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); } void intel_pxp_irq_disable(struct intel_pxp *pxp) @@ -88,12 +88,12 @@ void intel_pxp_irq_disable(struct intel_pxp *pxp) */ GEM_WARN_ON(intel_pxp_is_active(pxp)); - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); pxp->irq_enabled = false; __pxp_set_interrupts(gt, 0); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); intel_synchronize_irq(gt->i915); pxp_irq_reset(gt); diff --git a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c index 92b00b4de240..1bb5b5249157 100644 --- a/drivers/gpu/drm/i915/pxp/intel_pxp_session.c +++ b/drivers/gpu/drm/i915/pxp/intel_pxp_session.c @@ -144,9 +144,9 @@ void intel_pxp_session_work(struct work_struct *work) intel_wakeref_t wakeref; u32 events = 0; - spin_lock_irq(>->irq_lock); + spin_lock_irq(gt->irq_lock); events = fetch_and_zero(&pxp->session_events); - spin_unlock_irq(>->irq_lock); + spin_unlock_irq(gt->irq_lock); if (!events) return; diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c index c4e932368b37..39da0fb0d6d2 100644 --- a/drivers/gpu/drm/i915/selftests/i915_selftest.c +++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c @@ -135,7 +135,7 @@ static int __run_selftests(const char *name, int err = 0; while (!i915_selftest.random_seed) - i915_selftest.random_seed = get_random_int(); + i915_selftest.random_seed = get_random_u32(); i915_selftest.timeout_jiffies = i915_selftest.timeout_ms ? diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index 9c31a16f8380..fff11c90f1fa 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -115,6 +115,7 @@ static struct dev_pm_domain pm_domain = { static void mock_gt_probe(struct drm_i915_private *i915) { i915->gt[0] = &i915->gt0; + i915->gt[0]->name = "Mock GT"; } struct drm_i915_private *mock_gem_device(void) @@ -172,14 +173,14 @@ struct drm_i915_private *mock_gem_device(void) /* Using the global GTT may ask questions about KMS users, so prepare */ drm_mode_config_init(&i915->drm); - mkwrite_device_info(i915)->graphics.ver = -1; + RUNTIME_INFO(i915)->graphics.ip.ver = -1; - mkwrite_device_info(i915)->page_sizes = + RUNTIME_INFO(i915)->page_sizes = I915_GTT_PAGE_SIZE_4K | I915_GTT_PAGE_SIZE_64K | I915_GTT_PAGE_SIZE_2M; - mkwrite_device_info(i915)->memory_regions = REGION_SMEM; + RUNTIME_INFO(i915)->memory_regions = REGION_SMEM; intel_memory_regions_hw_probe(i915); spin_lock_init(&i915->gpu_error.lock); @@ -209,7 +210,7 @@ struct drm_i915_private *mock_gem_device(void) mock_init_ggtt(to_gt(i915)); to_gt(i915)->vm = i915_vm_get(&to_gt(i915)->ggtt->vm); - mkwrite_device_info(i915)->platform_engine_mask = BIT(0); + RUNTIME_INFO(i915)->platform_engine_mask = BIT(0); to_gt(i915)->info.engine_mask = BIT(0); to_gt(i915)->engine[RCS0] = mock_engine(i915, "mock", RCS0); diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c index 630a4e301ef6..508a6d994e83 100644 --- a/drivers/gpu/drm/mediatek/mtk_dpi.c +++ b/drivers/gpu/drm/mediatek/mtk_dpi.c @@ -11,7 +11,6 @@ #include <linux/media-bus-format.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/of_graph.h> #include <linux/pinctrl/consumer.h> #include <linux/platform_device.h> diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 2d72cc5ddaba..6b6d5335c834 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -157,7 +157,7 @@ static void mtk_dither_config(struct device *dev, unsigned int w, { struct mtk_ddp_comp_dev *priv = dev_get_drvdata(dev); - mtk_ddp_write(cmdq_pkt, h << 16 | w, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_SIZE); + mtk_ddp_write(cmdq_pkt, w << 16 | h, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_SIZE); mtk_ddp_write(cmdq_pkt, DITHER_RELAY_MODE, &priv->cmdq_reg, priv->regs, DISP_REG_DITHER_CFG); mtk_dither_set_common(priv->regs, &priv->cmdq_reg, bpc, DISP_REG_DITHER_CFG, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 5f02f8d0e4fc..91f58db5915f 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -833,11 +833,8 @@ static int mtk_drm_sys_prepare(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); struct drm_device *drm = private->drm; - int ret; - - ret = drm_mode_config_helper_suspend(drm); - return ret; + return drm_mode_config_helper_suspend(drm); } static void mtk_drm_sys_complete(struct device *dev) diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 9cc406e1eee1..3b7d13028fb6 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -685,6 +685,16 @@ static void mtk_dsi_poweroff(struct mtk_dsi *dsi) if (--dsi->refcount != 0) return; + /* + * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since + * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(), + * which needs irq for vblank, and mtk_dsi_stop() will disable irq. + * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(), + * after dsi is fully set. + */ + mtk_dsi_stop(dsi); + + mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500); mtk_dsi_reset_engine(dsi); mtk_dsi_lane0_ulp_mode_enter(dsi); mtk_dsi_clk_ulp_mode_enter(dsi); @@ -735,17 +745,6 @@ static void mtk_output_dsi_disable(struct mtk_dsi *dsi) if (!dsi->enabled) return; - /* - * mtk_dsi_stop() and mtk_dsi_start() is asymmetric, since - * mtk_dsi_stop() should be called after mtk_drm_crtc_atomic_disable(), - * which needs irq for vblank, and mtk_dsi_stop() will disable irq. - * mtk_dsi_start() needs to be called in mtk_output_dsi_enable(), - * after dsi is fully set. - */ - mtk_dsi_stop(dsi); - - mtk_dsi_switch_to_cmd_mode(dsi, VM_DONE_INT_FLAG, 500); - dsi->enabled = false; } @@ -808,10 +807,13 @@ static void mtk_dsi_bridge_atomic_post_disable(struct drm_bridge *bridge, static const struct drm_bridge_funcs mtk_dsi_bridge_funcs = { .attach = mtk_dsi_bridge_attach, + .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state, .atomic_disable = mtk_dsi_bridge_atomic_disable, + .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state, .atomic_enable = mtk_dsi_bridge_atomic_enable, .atomic_pre_enable = mtk_dsi_bridge_atomic_pre_enable, .atomic_post_disable = mtk_dsi_bridge_atomic_post_disable, + .atomic_reset = drm_atomic_helper_bridge_reset, .mode_set = mtk_dsi_bridge_mode_set, }; diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index 3196189429bc..4c80b6896dc3 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -16,7 +16,6 @@ #include <linux/mutex.h> #include <linux/of_platform.h> #include <linux/of.h> -#include <linux/of_gpio.h> #include <linux/of_graph.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index dfd6a9f33dda..815dfe30492b 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -169,7 +169,7 @@ static void meson_plane_atomic_update(struct drm_plane *plane, /* Enable OSD and BLK0, set max global alpha */ priv->viu.osd1_ctrl_stat = OSD_ENABLE | - (0xFF << OSD_GLOBAL_ALPHA_SHIFT) | + (0x100 << OSD_GLOBAL_ALPHA_SHIFT) | OSD_BLK0_ENABLE; priv->viu.osd1_ctrl_stat2 = readl(priv->io_base + diff --git a/drivers/gpu/drm/meson/meson_viu.c b/drivers/gpu/drm/meson/meson_viu.c index bb7e109534de..d4b907889a21 100644 --- a/drivers/gpu/drm/meson/meson_viu.c +++ b/drivers/gpu/drm/meson/meson_viu.c @@ -94,7 +94,7 @@ static void meson_viu_set_g12a_osd1_matrix(struct meson_drm *priv, priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF11_12)); writel(((m[9] & 0x1fff) << 16) | (m[10] & 0x1fff), priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF20_21)); - writel((m[11] & 0x1fff) << 16, + writel((m[11] & 0x1fff), priv->io_base + _REG(VPP_WRAP_OSD1_MATRIX_COEF22)); writel(((m[18] & 0xfff) << 16) | (m[19] & 0xfff), diff --git a/drivers/gpu/drm/mgag200/mgag200_drv.c b/drivers/gpu/drm/mgag200/mgag200_drv.c index 4d38b8e18030..ece6cd102dbb 100644 --- a/drivers/gpu/drm/mgag200/mgag200_drv.c +++ b/drivers/gpu/drm/mgag200/mgag200_drv.c @@ -263,7 +263,11 @@ mgag200_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (ret) return ret; - drm_fbdev_generic_setup(dev, 0); + /* + * FIXME: A 24-bit color depth does not work with 24 bpp on + * G200ER. Force 32 bpp. + */ + drm_fbdev_generic_setup(dev, 32); return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 0ab0e1dd8bbb..2c8b9899625b 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -68,7 +68,7 @@ static void a3xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ OUT_PKT3(ring, CP_EVENT_WRITE, 3); - OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); + OUT_RING(ring, CACHE_FLUSH_TS | CP_EVENT_WRITE_0_IRQ); OUT_RING(ring, rbmemptr(ring, fence)); OUT_RING(ring, submit->seqno); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 0c6b2a6d0b4c..7cb8d9849c07 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -62,7 +62,7 @@ static void a4xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) /* BIT(31) of CACHE_FLUSH_TS triggers CACHE_FLUSH_TS IRQ from GPU */ OUT_PKT3(ring, CP_EVENT_WRITE, 3); - OUT_RING(ring, CACHE_FLUSH_TS | BIT(31)); + OUT_RING(ring, CACHE_FLUSH_TS | CP_EVENT_WRITE_0_IRQ); OUT_RING(ring, rbmemptr(ring, fence)); OUT_RING(ring, submit->seqno); diff --git a/drivers/gpu/drm/msm/adreno/a6xx.xml.h b/drivers/gpu/drm/msm/adreno/a6xx.xml.h index b03e2c413ab1..beea4a7fc1df 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx.xml.h +++ b/drivers/gpu/drm/msm/adreno/a6xx.xml.h @@ -1413,6 +1413,10 @@ static inline uint32_t REG_A6XX_RBBM_PERFCTR_RBBM_SEL(uint32_t i0) { return 0x00 #define REG_A6XX_RBBM_GBIF_CLIENT_QOS_CNTL 0x00000011 +#define REG_A6XX_RBBM_GBIF_HALT 0x00000016 + +#define REG_A6XX_RBBM_GBIF_HALT_ACK 0x00000017 + #define REG_A6XX_RBBM_WAIT_FOR_GPU_IDLE_CMD 0x0000001c #define A6XX_RBBM_WAIT_FOR_GPU_IDLE_CMD_WAIT_GPU_IDLE 0x00000001 diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 310a317885a1..e033d6a67a20 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -873,9 +873,47 @@ static void a6xx_gmu_rpmh_off(struct a6xx_gmu *gmu) (val & 1), 100, 1000); } +#define GBIF_CLIENT_HALT_MASK BIT(0) +#define GBIF_ARB_HALT_MASK BIT(1) + +static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) +{ + struct msm_gpu *gpu = &adreno_gpu->base; + + if (!a6xx_has_gbif(adreno_gpu)) { + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); + spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & + 0xf) == 0xf); + gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); + + return; + } + + /* Halt the gx side of GBIF */ + gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 1); + spin_until(gpu_read(gpu, REG_A6XX_RBBM_GBIF_HALT_ACK) & 1); + + /* Halt new client requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); + + /* Halt all AXI requests on GBIF */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); + spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & + (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); + + /* The GBIF halt needs to be explicitly cleared */ + gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); +} + /* Force the GMU off in case it isn't responsive */ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) { + struct a6xx_gpu *a6xx_gpu = container_of(gmu, struct a6xx_gpu, gmu); + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; + struct msm_gpu *gpu = &adreno_gpu->base; + /* Flush all the queues */ a6xx_hfi_stop(gmu); @@ -887,6 +925,15 @@ static void a6xx_gmu_force_off(struct a6xx_gmu *gmu) /* Make sure there are no outstanding RPMh votes */ a6xx_gmu_rpmh_off(gmu); + + /* Halt the gmu cm3 core */ + gmu_write(gmu, REG_A6XX_GMU_CM3_SYSRESET, 1); + + a6xx_bus_clear_pending_transactions(adreno_gpu); + + /* Reset GPU core blocks */ + gpu_write(gpu, REG_A6XX_RBBM_SW_RESET_CMD, 1); + udelay(100); } static void a6xx_gmu_set_initial_freq(struct msm_gpu *gpu, struct a6xx_gmu *gmu) @@ -1014,36 +1061,6 @@ bool a6xx_gmu_isidle(struct a6xx_gmu *gmu) return true; } -#define GBIF_CLIENT_HALT_MASK BIT(0) -#define GBIF_ARB_HALT_MASK BIT(1) - -static void a6xx_bus_clear_pending_transactions(struct adreno_gpu *adreno_gpu) -{ - struct msm_gpu *gpu = &adreno_gpu->base; - - if (!a6xx_has_gbif(adreno_gpu)) { - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0xf); - spin_until((gpu_read(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL1) & - 0xf) == 0xf); - gpu_write(gpu, REG_A6XX_VBIF_XIN_HALT_CTRL0, 0); - - return; - } - - /* Halt new client requests on GBIF */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_CLIENT_HALT_MASK); - spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & - (GBIF_CLIENT_HALT_MASK)) == GBIF_CLIENT_HALT_MASK); - - /* Halt all AXI requests on GBIF */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, GBIF_ARB_HALT_MASK); - spin_until((gpu_read(gpu, REG_A6XX_GBIF_HALT_ACK) & - (GBIF_ARB_HALT_MASK)) == GBIF_ARB_HALT_MASK); - - /* The GBIF halt needs to be explicitly cleared */ - gpu_write(gpu, REG_A6XX_GBIF_HALT, 0x0); -} - /* Gracefully try to shut down the GMU and by extension the GPU */ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) { @@ -1069,7 +1086,11 @@ static void a6xx_gmu_shutdown(struct a6xx_gmu *gmu) a6xx_bus_clear_pending_transactions(adreno_gpu); /* tell the GMU we want to slumber */ - a6xx_gmu_notify_slumber(gmu); + ret = a6xx_gmu_notify_slumber(gmu); + if (ret) { + a6xx_gmu_force_off(gmu); + return; + } ret = gmu_poll_timeout(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_STATUS, val, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 4d501100b9e4..fdc578016e0b 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -10,6 +10,7 @@ #include <linux/bitfield.h> #include <linux/devfreq.h> +#include <linux/reset.h> #include <linux/soc/qcom/llcc-qcom.h> #define GPU_PAS_ID 13 @@ -146,7 +147,7 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu, */ OUT_PKT7(ring, CP_EVENT_WRITE, 1); - OUT_RING(ring, 0x31); + OUT_RING(ring, CACHE_INVALIDATE); if (!sysprof) { /* @@ -987,6 +988,10 @@ static int hw_init(struct msm_gpu *gpu) /* Make sure the GMU keeps the GPU on while we set it up */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + /* Clear GBIF halt in case GX domain was not collapsed */ + if (a6xx_has_gbif(adreno_gpu)) + gpu_write(gpu, REG_A6XX_RBBM_GBIF_HALT, 0); + gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_CNTL, 0); /* @@ -1261,7 +1266,7 @@ static void a6xx_recover(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); - int i; + int i, active_submits; adreno_dump_info(gpu); @@ -1272,14 +1277,46 @@ static void a6xx_recover(struct msm_gpu *gpu) if (hang_debug) a6xx_dump(gpu); + /* Halt SQE first */ + gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3); + /* * Turn off keep alive that might have been enabled by the hang * interrupt */ gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 0); - gpu->funcs->pm_suspend(gpu); - gpu->funcs->pm_resume(gpu); + pm_runtime_dont_use_autosuspend(&gpu->pdev->dev); + + /* active_submit won't change until we make a submission */ + mutex_lock(&gpu->active_lock); + active_submits = gpu->active_submits; + + /* + * Temporarily clear active_submits count to silence a WARN() in the + * runtime suspend cb + */ + gpu->active_submits = 0; + + /* Drop the rpm refcount from active submits */ + if (active_submits) + pm_runtime_put(&gpu->pdev->dev); + + /* And the final one from recover worker */ + pm_runtime_put_sync(&gpu->pdev->dev); + + /* Call into gpucc driver to poll for cx gdsc collapse */ + reset_control_reset(gpu->cx_collapse); + + pm_runtime_use_autosuspend(&gpu->pdev->dev); + + if (active_submits) + pm_runtime_get(&gpu->pdev->dev); + + pm_runtime_get_sync(&gpu->pdev->dev); + + gpu->active_submits = active_submits; + mutex_unlock(&gpu->active_lock); msm_gpu_hw_init(gpu); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 781dcd3fb283..13ce321283ff 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -412,7 +412,6 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, struct dpu_format *format; struct dpu_hw_ctl *ctl = mixer->lm_ctl; - u32 flush_mask; uint32_t stage_idx, lm_idx; int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 }; bool bg_alpha_enable = false; @@ -420,6 +419,8 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, memset(fetch_active, 0, sizeof(fetch_active)); drm_atomic_crtc_for_each_plane(plane, crtc) { + enum dpu_sspp sspp_idx; + state = plane->state; if (!state) continue; @@ -430,14 +431,14 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, pstate = to_dpu_plane_state(state); fb = state->fb; - dpu_plane_get_ctl_flush(plane, ctl, &flush_mask); - set_bit(dpu_plane_pipe(plane), fetch_active); + sspp_idx = dpu_plane_pipe(plane); + set_bit(sspp_idx, fetch_active); DRM_DEBUG_ATOMIC("crtc %d stage:%d - plane %d sspp %d fb %d\n", crtc->base.id, pstate->stage, plane->base.id, - dpu_plane_pipe(plane) - SSPP_VIG0, + sspp_idx - SSPP_VIG0, state->fb ? state->fb->base.id : -1); format = to_dpu_format(msm_framebuffer_format(pstate->base.fb)); @@ -447,13 +448,13 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, stage_idx = zpos_cnt[pstate->stage]++; stage_cfg->stage[pstate->stage][stage_idx] = - dpu_plane_pipe(plane); + sspp_idx; stage_cfg->multirect_index[pstate->stage][stage_idx] = pstate->multirect_index; trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane), state, pstate, stage_idx, - dpu_plane_pipe(plane) - SSPP_VIG0, + sspp_idx - SSPP_VIG0, format->base.pixel_format, fb ? fb->modifier : 0); @@ -462,7 +463,8 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc, _dpu_crtc_setup_blend_cfg(mixer + lm_idx, pstate, format); - mixer[lm_idx].flush_mask |= flush_mask; + mixer[lm_idx].lm_ctl->ops.update_pending_flush_sspp(mixer[lm_idx].lm_ctl, + sspp_idx); if (bg_alpha_enable && !format->alpha_enable) mixer[lm_idx].mixer_op_mode = 0; @@ -496,7 +498,6 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) for (i = 0; i < cstate->num_mixers; i++) { mixer[i].mixer_op_mode = 0; - mixer[i].flush_mask = 0; if (mixer[i].lm_ctl->ops.clear_all_blendstages) mixer[i].lm_ctl->ops.clear_all_blendstages( mixer[i].lm_ctl); @@ -513,17 +514,14 @@ static void _dpu_crtc_blend_setup(struct drm_crtc *crtc) lm->ops.setup_alpha_out(lm, mixer[i].mixer_op_mode); - mixer[i].flush_mask |= ctl->ops.get_bitmask_mixer(ctl, - mixer[i].hw_lm->idx); - /* stage config flush mask */ - ctl->ops.update_pending_flush(ctl, mixer[i].flush_mask); + ctl->ops.update_pending_flush_mixer(ctl, + mixer[i].hw_lm->idx); - DRM_DEBUG_ATOMIC("lm %d, op_mode 0x%X, ctl %d, flush mask 0x%x\n", + DRM_DEBUG_ATOMIC("lm %d, op_mode 0x%X, ctl %d\n", mixer[i].hw_lm->idx - LM_0, mixer[i].mixer_op_mode, - ctl->idx - CTL_0, - mixer[i].flush_mask); + ctl->idx - CTL_0); ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx, &stage_cfg); @@ -767,16 +765,9 @@ static void _dpu_crtc_setup_cp_blocks(struct drm_crtc *crtc) dspp->ops.setup_pcc(dspp, &cfg); } - mixer[i].flush_mask |= ctl->ops.get_bitmask_dspp(ctl, - mixer[i].hw_dspp->idx); - /* stage config flush mask */ - ctl->ops.update_pending_flush(ctl, mixer[i].flush_mask); - - DRM_DEBUG_ATOMIC("lm %d, ctl %d, flush mask 0x%x\n", - mixer[i].hw_lm->idx - DSPP_0, - ctl->idx - CTL_0, - mixer[i].flush_mask); + ctl->ops.update_pending_flush_dspp(ctl, + mixer[i].hw_dspp->idx); } } @@ -1235,17 +1226,8 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, } for (i = 1; i < SSPP_MAX; i++) { - if (pipe_staged[i]) { + if (pipe_staged[i]) dpu_plane_clear_multirect(pipe_staged[i]); - - if (is_dpu_plane_virtual(pipe_staged[i]->plane)) { - DPU_ERROR( - "r1 only virt plane:%d not supported\n", - pipe_staged[i]->plane->base.id); - rc = -EINVAL; - goto end; - } - } } z_pos = -1; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h index 9b67645c2574..539b68b1626a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h @@ -97,7 +97,6 @@ struct dpu_crtc_mixer { struct dpu_hw_ctl *lm_ctl; struct dpu_hw_dspp *hw_dspp; u32 mixer_op_mode; - u32 flush_mask; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index c682d4e02d1b..9c6817b5a194 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -162,7 +162,7 @@ enum dpu_enc_rc_states { * @vsync_event_work: worker to handle vsync event for autorefresh * @topology: topology of the display * @idle_timeout: idle timeout duration in milliseconds - * @dsc: msm_display_dsc_config pointer, for DSC-enabled encoders + * @dsc: drm_dsc_config pointer, for DSC-enabled encoders */ struct dpu_encoder_virt { struct drm_encoder base; @@ -208,7 +208,7 @@ struct dpu_encoder_virt { bool wide_bus_en; /* DSC configuration */ - struct msm_display_dsc_config *dsc; + struct drm_dsc_config *dsc; }; #define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base) @@ -1791,12 +1791,12 @@ static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work) } static u32 -dpu_encoder_dsc_initial_line_calc(struct msm_display_dsc_config *dsc, +dpu_encoder_dsc_initial_line_calc(struct drm_dsc_config *dsc, u32 enc_ip_width) { int ssm_delay, total_pixels, soft_slice_per_enc; - soft_slice_per_enc = enc_ip_width / dsc->drm->slice_width; + soft_slice_per_enc = enc_ip_width / dsc->slice_width; /* * minimum number of initial line pixels is a sum of: @@ -1808,16 +1808,16 @@ dpu_encoder_dsc_initial_line_calc(struct msm_display_dsc_config *dsc, * 5. 6 additional pixels as the output of the rate buffer is * 48 bits wide */ - ssm_delay = ((dsc->drm->bits_per_component < 10) ? 84 : 92); - total_pixels = ssm_delay * 3 + dsc->drm->initial_xmit_delay + 47; + ssm_delay = ((dsc->bits_per_component < 10) ? 84 : 92); + total_pixels = ssm_delay * 3 + dsc->initial_xmit_delay + 47; if (soft_slice_per_enc > 1) total_pixels += (ssm_delay * 3); - return DIV_ROUND_UP(total_pixels, dsc->drm->slice_width); + return DIV_ROUND_UP(total_pixels, dsc->slice_width); } static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_dsc *hw_dsc, struct dpu_hw_pingpong *hw_pp, - struct msm_display_dsc_config *dsc, + struct drm_dsc_config *dsc, u32 common_mode, u32 initial_lines) { @@ -1835,7 +1835,7 @@ static void dpu_encoder_dsc_pipe_cfg(struct dpu_hw_dsc *hw_dsc, } static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, - struct msm_display_dsc_config *dsc) + struct drm_dsc_config *dsc) { /* coding only for 2LM, 2enc, 1 dsc config */ struct dpu_encoder_phys *enc_master = dpu_enc->cur_master; @@ -1858,14 +1858,15 @@ static void dpu_encoder_prep_dsc(struct dpu_encoder_virt *dpu_enc, } } - pic_width = dsc->drm->pic_width; + dsc_common_mode = 0; + pic_width = dsc->pic_width; dsc_common_mode = DSC_MODE_MULTIPLEX | DSC_MODE_SPLIT_PANEL; if (enc_master->intf_mode == INTF_MODE_VIDEO) dsc_common_mode |= DSC_MODE_VIDEO; - this_frame_slices = pic_width / dsc->drm->slice_width; - intf_ip_w = this_frame_slices * dsc->drm->slice_width; + this_frame_slices = pic_width / dsc->slice_width; + intf_ip_w = this_frame_slices * dsc->slice_width; /* * dsc merge case: when using 2 encoders for the same stream, @@ -1980,7 +1981,6 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) { struct dpu_hw_mixer_cfg mixer; int i, num_lm; - u32 flush_mask = 0; struct dpu_global_state *global_state; struct dpu_hw_blk *hw_lm[2]; struct dpu_hw_mixer *hw_mixer[2]; @@ -1999,9 +1999,8 @@ static void dpu_encoder_helper_reset_mixers(struct dpu_encoder_phys *phys_enc) for (i = 0; i < num_lm; i++) { hw_mixer[i] = to_dpu_hw_mixer(hw_lm[i]); - flush_mask = phys_enc->hw_ctl->ops.get_bitmask_mixer(ctl, hw_mixer[i]->idx); - if (phys_enc->hw_ctl->ops.update_pending_flush) - phys_enc->hw_ctl->ops.update_pending_flush(ctl, flush_mask); + if (phys_enc->hw_ctl->ops.update_pending_flush_mixer) + phys_enc->hw_ctl->ops.update_pending_flush_mixer(ctl, hw_mixer[i]->idx); /* clear all blendstages */ if (phys_enc->hw_ctl->ops.setup_blendstage) @@ -2061,6 +2060,12 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc) intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); + + if (phys_enc->hw_intf) + intf_cfg.intf = phys_enc->hw_intf->idx; + if (phys_enc->hw_wb) + intf_cfg.wb = phys_enc->hw_wb->idx; + if (phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h index d4d1ecd416e3..9e7236ef34e6 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h @@ -36,7 +36,7 @@ struct msm_display_info { uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY]; bool is_cmd_mode; bool is_te_using_watchdog_timer; - struct msm_display_dsc_config *dsc; + struct drm_dsc_config *dsc; }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c index 0239a811d5ec..27f029fdc682 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c @@ -1333,7 +1333,7 @@ static const struct dpu_vbif_dynamic_ot_cfg msm8998_ot_rdwr_cfg[] = { static const struct dpu_vbif_cfg msm8998_vbif[] = { { - .name = "vbif_0", .id = VBIF_0, + .name = "vbif_rt", .id = VBIF_RT, .base = 0, .len = 0x1040, .default_ot_rd_limit = 32, .default_ot_wr_limit = 32, @@ -1363,7 +1363,7 @@ static const struct dpu_vbif_cfg msm8998_vbif[] = { static const struct dpu_vbif_cfg sdm845_vbif[] = { { - .name = "vbif_0", .id = VBIF_0, + .name = "vbif_rt", .id = VBIF_RT, .base = 0, .len = 0x1040, .features = BIT(DPU_VBIF_QOS_REMAP), .xin_halt_timeout = 0x4000, @@ -1939,11 +1939,6 @@ static const struct dpu_mdss_hw_cfg_handler cfg_handler[] = { const struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev) { int i; - struct dpu_mdss_cfg *dpu_cfg; - - dpu_cfg = kzalloc(sizeof(*dpu_cfg), GFP_KERNEL); - if (!dpu_cfg) - return ERR_PTR(-ENOMEM); for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) { if (cfg_handler[i].hw_rev == hw_rev) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h index 71fe4c505f5b..38aa38ab1568 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h @@ -76,7 +76,7 @@ enum { /** * MDP TOP BLOCK features - * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be be done per pipe + * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be done per pipe * @DPU_MDP_10BIT_SUPPORT, Chipset supports 10 bit pixel formats * @DPU_MDP_BWC, MDSS HW supports Bandwidth compression. * @DPU_MDP_UBWC_1_0, This chipsets supports Universal Bandwidth diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c index e12b7fa48a7b..a35ecb6676c8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c @@ -150,92 +150,84 @@ static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx) DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask); } -static uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx, +static void dpu_hw_ctl_update_pending_flush_sspp(struct dpu_hw_ctl *ctx, enum dpu_sspp sspp) { - uint32_t flushbits = 0; - switch (sspp) { case SSPP_VIG0: - flushbits = BIT(0); + ctx->pending_flush_mask |= BIT(0); break; case SSPP_VIG1: - flushbits = BIT(1); + ctx->pending_flush_mask |= BIT(1); break; case SSPP_VIG2: - flushbits = BIT(2); + ctx->pending_flush_mask |= BIT(2); break; case SSPP_VIG3: - flushbits = BIT(18); + ctx->pending_flush_mask |= BIT(18); break; case SSPP_RGB0: - flushbits = BIT(3); + ctx->pending_flush_mask |= BIT(3); break; case SSPP_RGB1: - flushbits = BIT(4); + ctx->pending_flush_mask |= BIT(4); break; case SSPP_RGB2: - flushbits = BIT(5); + ctx->pending_flush_mask |= BIT(5); break; case SSPP_RGB3: - flushbits = BIT(19); + ctx->pending_flush_mask |= BIT(19); break; case SSPP_DMA0: - flushbits = BIT(11); + ctx->pending_flush_mask |= BIT(11); break; case SSPP_DMA1: - flushbits = BIT(12); + ctx->pending_flush_mask |= BIT(12); break; case SSPP_DMA2: - flushbits = BIT(24); + ctx->pending_flush_mask |= BIT(24); break; case SSPP_DMA3: - flushbits = BIT(25); + ctx->pending_flush_mask |= BIT(25); break; case SSPP_CURSOR0: - flushbits = BIT(22); + ctx->pending_flush_mask |= BIT(22); break; case SSPP_CURSOR1: - flushbits = BIT(23); + ctx->pending_flush_mask |= BIT(23); break; default: break; } - - return flushbits; } -static uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx, +static void dpu_hw_ctl_update_pending_flush_mixer(struct dpu_hw_ctl *ctx, enum dpu_lm lm) { - uint32_t flushbits = 0; - switch (lm) { case LM_0: - flushbits = BIT(6); + ctx->pending_flush_mask |= BIT(6); break; case LM_1: - flushbits = BIT(7); + ctx->pending_flush_mask |= BIT(7); break; case LM_2: - flushbits = BIT(8); + ctx->pending_flush_mask |= BIT(8); break; case LM_3: - flushbits = BIT(9); + ctx->pending_flush_mask |= BIT(9); break; case LM_4: - flushbits = BIT(10); + ctx->pending_flush_mask |= BIT(10); break; case LM_5: - flushbits = BIT(20); + ctx->pending_flush_mask |= BIT(20); break; default: - return -EINVAL; + break; } - flushbits |= CTL_FLUSH_MASK_CTL; - - return flushbits; + ctx->pending_flush_mask |= CTL_FLUSH_MASK_CTL; } static void dpu_hw_ctl_update_pending_flush_intf(struct dpu_hw_ctl *ctx, @@ -294,29 +286,25 @@ static void dpu_hw_ctl_update_pending_flush_merge_3d_v1(struct dpu_hw_ctl *ctx, ctx->pending_flush_mask |= BIT(MERGE_3D_IDX); } -static uint32_t dpu_hw_ctl_get_bitmask_dspp(struct dpu_hw_ctl *ctx, +static void dpu_hw_ctl_update_pending_flush_dspp(struct dpu_hw_ctl *ctx, enum dpu_dspp dspp) { - uint32_t flushbits = 0; - switch (dspp) { case DSPP_0: - flushbits = BIT(13); + ctx->pending_flush_mask |= BIT(13); break; case DSPP_1: - flushbits = BIT(14); + ctx->pending_flush_mask |= BIT(14); break; case DSPP_2: - flushbits = BIT(15); + ctx->pending_flush_mask |= BIT(15); break; case DSPP_3: - flushbits = BIT(21); + ctx->pending_flush_mask |= BIT(21); break; default: - return 0; + break; } - - return flushbits; } static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us) @@ -685,9 +673,9 @@ static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops, ops->wait_reset_status = dpu_hw_ctl_wait_reset_status; ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages; ops->setup_blendstage = dpu_hw_ctl_setup_blendstage; - ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp; - ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer; - ops->get_bitmask_dspp = dpu_hw_ctl_get_bitmask_dspp; + ops->update_pending_flush_sspp = dpu_hw_ctl_update_pending_flush_sspp; + ops->update_pending_flush_mixer = dpu_hw_ctl_update_pending_flush_mixer; + ops->update_pending_flush_dspp = dpu_hw_ctl_update_pending_flush_dspp; if (cap & BIT(DPU_CTL_FETCH_ACTIVE)) ops->set_active_pipes = dpu_hw_ctl_set_fetch_pipe_active; }; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index 7d9ad6a3f9f6..96c012ec8467 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -130,6 +130,32 @@ struct dpu_hw_ctl_ops { enum dpu_merge_3d blk); /** + * OR in the given flushbits to the cached pending_flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @blk : SSPP block index + */ + void (*update_pending_flush_sspp)(struct dpu_hw_ctl *ctx, + enum dpu_sspp blk); + + /** + * OR in the given flushbits to the cached pending_flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @blk : LM block index + */ + void (*update_pending_flush_mixer)(struct dpu_hw_ctl *ctx, + enum dpu_lm blk); + + /** + * OR in the given flushbits to the cached pending_flush_mask + * No effect on hardware + * @ctx : ctl path ctx pointer + * @blk : DSPP block index + */ + void (*update_pending_flush_dspp)(struct dpu_hw_ctl *ctx, + enum dpu_dspp blk); + /** * Write the value of the pending_flush_mask to hardware * @ctx : ctl path ctx pointer */ @@ -171,15 +197,6 @@ struct dpu_hw_ctl_ops { */ int (*wait_reset_status)(struct dpu_hw_ctl *ctx); - uint32_t (*get_bitmask_sspp)(struct dpu_hw_ctl *ctx, - enum dpu_sspp blk); - - uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx, - enum dpu_lm blk); - - uint32_t (*get_bitmask_dspp)(struct dpu_hw_ctl *ctx, - enum dpu_dspp blk); - /** * Set all blend stages to disabled * @ctx : ctl path ctx pointer diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c index 411689ae6382..f2ddcfb6f7ee 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c @@ -37,7 +37,7 @@ static void dpu_hw_dsc_disable(struct dpu_hw_dsc *dsc) } static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc, - struct msm_display_dsc_config *dsc, + struct drm_dsc_config *dsc, u32 mode, u32 initial_lines) { @@ -52,89 +52,89 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc, if (is_cmd_mode) initial_lines += 1; - slice_last_group_size = 3 - (dsc->drm->slice_width % 3); + slice_last_group_size = 3 - (dsc->slice_width % 3); data = (initial_lines << 20); data |= ((slice_last_group_size - 1) << 18); /* bpp is 6.4 format, 4 LSBs bits are for fractional part */ - data |= dsc->drm->bits_per_pixel << 12; - lsb = dsc->drm->bits_per_pixel % 4; - bpp = dsc->drm->bits_per_pixel / 4; + data |= dsc->bits_per_pixel << 12; + lsb = dsc->bits_per_pixel % 4; + bpp = dsc->bits_per_pixel / 4; bpp *= 4; bpp <<= 4; bpp |= lsb; data |= bpp << 8; - data |= (dsc->drm->block_pred_enable << 7); - data |= (dsc->drm->line_buf_depth << 3); - data |= (dsc->drm->simple_422 << 2); - data |= (dsc->drm->convert_rgb << 1); - data |= dsc->drm->bits_per_component; + data |= (dsc->block_pred_enable << 7); + data |= (dsc->line_buf_depth << 3); + data |= (dsc->simple_422 << 2); + data |= (dsc->convert_rgb << 1); + data |= dsc->bits_per_component; DPU_REG_WRITE(c, DSC_ENC, data); - data = dsc->drm->pic_width << 16; - data |= dsc->drm->pic_height; + data = dsc->pic_width << 16; + data |= dsc->pic_height; DPU_REG_WRITE(c, DSC_PICTURE, data); - data = dsc->drm->slice_width << 16; - data |= dsc->drm->slice_height; + data = dsc->slice_width << 16; + data |= dsc->slice_height; DPU_REG_WRITE(c, DSC_SLICE, data); - data = dsc->drm->slice_chunk_size << 16; + data = dsc->slice_chunk_size << 16; DPU_REG_WRITE(c, DSC_CHUNK_SIZE, data); - data = dsc->drm->initial_dec_delay << 16; - data |= dsc->drm->initial_xmit_delay; + data = dsc->initial_dec_delay << 16; + data |= dsc->initial_xmit_delay; DPU_REG_WRITE(c, DSC_DELAY, data); - data = dsc->drm->initial_scale_value; + data = dsc->initial_scale_value; DPU_REG_WRITE(c, DSC_SCALE_INITIAL, data); - data = dsc->drm->scale_decrement_interval; + data = dsc->scale_decrement_interval; DPU_REG_WRITE(c, DSC_SCALE_DEC_INTERVAL, data); - data = dsc->drm->scale_increment_interval; + data = dsc->scale_increment_interval; DPU_REG_WRITE(c, DSC_SCALE_INC_INTERVAL, data); - data = dsc->drm->first_line_bpg_offset; + data = dsc->first_line_bpg_offset; DPU_REG_WRITE(c, DSC_FIRST_LINE_BPG_OFFSET, data); - data = dsc->drm->nfl_bpg_offset << 16; - data |= dsc->drm->slice_bpg_offset; + data = dsc->nfl_bpg_offset << 16; + data |= dsc->slice_bpg_offset; DPU_REG_WRITE(c, DSC_BPG_OFFSET, data); - data = dsc->drm->initial_offset << 16; - data |= dsc->drm->final_offset; + data = dsc->initial_offset << 16; + data |= dsc->final_offset; DPU_REG_WRITE(c, DSC_DSC_OFFSET, data); - det_thresh_flatness = 7 + 2 * (dsc->drm->bits_per_component - 8); + det_thresh_flatness = 7 + 2 * (dsc->bits_per_component - 8); data = det_thresh_flatness << 10; - data |= dsc->drm->flatness_max_qp << 5; - data |= dsc->drm->flatness_min_qp; + data |= dsc->flatness_max_qp << 5; + data |= dsc->flatness_min_qp; DPU_REG_WRITE(c, DSC_FLATNESS, data); - data = dsc->drm->rc_model_size; + data = dsc->rc_model_size; DPU_REG_WRITE(c, DSC_RC_MODEL_SIZE, data); - data = dsc->drm->rc_tgt_offset_low << 18; - data |= dsc->drm->rc_tgt_offset_high << 14; - data |= dsc->drm->rc_quant_incr_limit1 << 9; - data |= dsc->drm->rc_quant_incr_limit0 << 4; - data |= dsc->drm->rc_edge_factor; + data = dsc->rc_tgt_offset_low << 18; + data |= dsc->rc_tgt_offset_high << 14; + data |= dsc->rc_quant_incr_limit1 << 9; + data |= dsc->rc_quant_incr_limit0 << 4; + data |= dsc->rc_edge_factor; DPU_REG_WRITE(c, DSC_RC, data); } static void dpu_hw_dsc_config_thresh(struct dpu_hw_dsc *hw_dsc, - struct msm_display_dsc_config *dsc) + struct drm_dsc_config *dsc) { - struct drm_dsc_rc_range_parameters *rc = dsc->drm->rc_range_params; + struct drm_dsc_rc_range_parameters *rc = dsc->rc_range_params; struct dpu_hw_blk_reg_map *c = &hw_dsc->hw; u32 off; int i; off = DSC_RC_BUF_THRESH; for (i = 0; i < DSC_NUM_BUF_RANGES - 1 ; i++) { - DPU_REG_WRITE(c, off, dsc->drm->rc_buf_thresh[i]); + DPU_REG_WRITE(c, off, dsc->rc_buf_thresh[i]); off += 4; } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h index 45e4118f1fa2..c0b77fe1a696 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.h @@ -31,7 +31,7 @@ struct dpu_hw_dsc_ops { * @initial_lines: amount of initial lines to be used */ void (*dsc_config)(struct dpu_hw_dsc *hw_dsc, - struct msm_display_dsc_config *dsc, + struct drm_dsc_config *dsc, u32 mode, u32 initial_lines); @@ -41,7 +41,7 @@ struct dpu_hw_dsc_ops { * @dsc: panel dsc parameters */ void (*dsc_config_thresh)(struct dpu_hw_dsc *hw_dsc, - struct msm_display_dsc_config *dsc); + struct drm_dsc_config *dsc); }; struct dpu_hw_dsc { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h index 9f402be55fbf..d3b0ed0a9c6c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h @@ -273,11 +273,9 @@ enum dpu_wd_timer { }; enum dpu_vbif { - VBIF_0, - VBIF_1, + VBIF_RT, + VBIF_NRT, VBIF_MAX, - VBIF_RT = VBIF_0, - VBIF_NRT = VBIF_1 }; /** diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c index 102c21bb4192..691c471b08c2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c @@ -780,8 +780,7 @@ static const struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp, } struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx, - void __iomem *addr, const struct dpu_mdss_cfg *catalog, - bool is_virtual_pipe) + void __iomem *addr, const struct dpu_mdss_cfg *catalog) { struct dpu_hw_pipe *hw_pipe; const struct dpu_sspp_cfg *cfg; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h index 78b1bc9e004f..0c95b7e64f6c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h @@ -377,11 +377,9 @@ struct dpu_kms; * @idx: Pipe index for which driver object is required * @addr: Mapped register io address of MDP * @catalog : Pointer to mdss catalog data - * @is_virtual_pipe: is this pipe virtual pipe */ struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx, - void __iomem *addr, const struct dpu_mdss_cfg *catalog, - bool is_virtual_pipe); + void __iomem *addr, const struct dpu_mdss_cfg *catalog); /** * dpu_hw_sspp_destroy(): Destroys SSPP driver context diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c index 008e1420e6e5..5e6e2626151e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c @@ -384,12 +384,9 @@ static int dpu_kms_parse_data_bus_icc_path(struct dpu_kms *dpu_kms) struct icc_path *path1; struct drm_device *dev = dpu_kms->dev; struct device *dpu_dev = dev->dev; - struct device *mdss_dev = dpu_dev->parent; - /* Interconnects are a part of MDSS device tree binding, not the - * MDP/DPU device. */ - path0 = of_icc_get(mdss_dev, "mdp0-mem"); - path1 = of_icc_get(mdss_dev, "mdp1-mem"); + path0 = msm_icc_get(dpu_dev, "mdp0-mem"); + path1 = msm_icc_get(dpu_dev, "mdp1-mem"); if (IS_ERR_OR_NULL(path0)) return PTR_ERR_OR_ZERO(path0); @@ -782,7 +779,7 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms) catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR)); plane = dpu_plane_init(dev, catalog->sspp[i].id, type, - (1UL << max_crtc_count) - 1, 0); + (1UL << max_crtc_count) - 1); if (IS_ERR(plane)) { DPU_ERROR("dpu_plane_init failed\n"); ret = PTR_ERR(plane); @@ -826,12 +823,10 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms) _dpu_kms_mmu_destroy(dpu_kms); if (dpu_kms->catalog) { - for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { - u32 vbif_idx = dpu_kms->catalog->vbif[i].id; - - if ((vbif_idx < VBIF_MAX) && dpu_kms->hw_vbif[vbif_idx]) { - dpu_hw_vbif_destroy(dpu_kms->hw_vbif[vbif_idx]); - dpu_kms->hw_vbif[vbif_idx] = NULL; + for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { + if (dpu_kms->hw_vbif[i]) { + dpu_hw_vbif_destroy(dpu_kms->hw_vbif[i]); + dpu_kms->hw_vbif[i] = NULL; } } } @@ -902,12 +897,10 @@ static void dpu_kms_mdp_snapshot(struct msm_disp_state *disp_state, struct msm_k int i; struct dpu_kms *dpu_kms; const struct dpu_mdss_cfg *cat; - struct dpu_hw_mdp *top; dpu_kms = to_dpu_kms(kms); cat = dpu_kms->catalog; - top = dpu_kms->hw_mdp; pm_runtime_get_sync(&dpu_kms->pdev->dev); @@ -1113,12 +1106,10 @@ static int dpu_kms_hw_init(struct msm_kms *kms) for (i = 0; i < dpu_kms->catalog->vbif_count; i++) { u32 vbif_idx = dpu_kms->catalog->vbif[i].id; - dpu_kms->hw_vbif[i] = dpu_hw_vbif_init(vbif_idx, + dpu_kms->hw_vbif[vbif_idx] = dpu_hw_vbif_init(vbif_idx, dpu_kms->vbif[vbif_idx], dpu_kms->catalog); - if (IS_ERR_OR_NULL(dpu_kms->hw_vbif[vbif_idx])) { + if (IS_ERR(dpu_kms->hw_vbif[vbif_idx])) { rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]); - if (!dpu_kms->hw_vbif[vbif_idx]) - rc = -EINVAL; DPU_ERROR("failed to init vbif %d: %d\n", vbif_idx, rc); dpu_kms->hw_vbif[vbif_idx] = NULL; goto power_error; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index a617a3d8b1bc..658005f609f4 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -91,7 +91,7 @@ enum dpu_plane_qos { /* * struct dpu_plane - local dpu plane structure * @aspace: address space pointer - * @mplane_list: List of multirect planes of the same pipe + * @csc_ptr: Points to dpu_csc_cfg structure to use for current * @catalog: Points to dpu catalog structure * @revalidate: force revalidation of all the plane properties */ @@ -106,8 +106,6 @@ struct dpu_plane { uint32_t color_fill; bool is_error; bool is_rt_pipe; - bool is_virtual; - struct list_head mplane_list; const struct dpu_mdss_cfg *catalog; }; @@ -225,7 +223,7 @@ static void _dpu_plane_calc_clk(struct drm_plane *plane, struct dpu_hw_pipe_cfg static int _dpu_plane_calc_fill_level(struct drm_plane *plane, const struct dpu_format *fmt, u32 src_width) { - struct dpu_plane *pdpu, *tmp; + struct dpu_plane *pdpu; struct dpu_plane_state *pstate; u32 fixed_buff_size; u32 total_fl; @@ -239,19 +237,7 @@ static int _dpu_plane_calc_fill_level(struct drm_plane *plane, pstate = to_dpu_plane_state(plane->state); fixed_buff_size = pdpu->catalog->caps->pixel_ram_size; - list_for_each_entry(tmp, &pdpu->mplane_list, mplane_list) { - u32 tmp_width; - - if (!tmp->base.state->visible) - continue; - tmp_width = drm_rect_width(&tmp->base.state->src) >> 16; - DPU_DEBUG("plane%d/%d src_width:%d/%d\n", - pdpu->base.base.id, tmp->base.base.id, - src_width, - tmp_width); - src_width = max_t(u32, src_width, - tmp_width); - } + /* FIXME: in multirect case account for the src_width of all the planes */ if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) { if (fmt->chroma_sample == DPU_CHROMA_420) { @@ -854,13 +840,8 @@ int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane) } done: - if (dpu_plane[R0]->is_virtual) { - pstate[R0]->multirect_index = DPU_SSPP_RECT_1; - pstate[R1]->multirect_index = DPU_SSPP_RECT_0; - } else { - pstate[R0]->multirect_index = DPU_SSPP_RECT_0; - pstate[R1]->multirect_index = DPU_SSPP_RECT_1; - } + pstate[R0]->multirect_index = DPU_SSPP_RECT_0; + pstate[R1]->multirect_index = DPU_SSPP_RECT_1; DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n", pstate[R0]->multirect_mode, pstate[R0]->multirect_index); @@ -869,18 +850,6 @@ done: return 0; } -/** - * dpu_plane_get_ctl_flush - get control flush for the given plane - * @plane: Pointer to drm plane structure - * @ctl: Pointer to hardware control driver - * @flush_sspp: Pointer to sspp flush control word - */ -void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl, - u32 *flush_sspp) -{ - *flush_sspp = ctl->ops.get_bitmask_sspp(ctl, dpu_plane_pipe(plane)); -} - static int dpu_plane_prepare_fb(struct drm_plane *plane, struct drm_plane_state *new_state) { @@ -1266,19 +1235,13 @@ static void dpu_plane_sspp_atomic_update(struct drm_plane *plane) static void _dpu_plane_atomic_disable(struct drm_plane *plane) { - struct dpu_plane *pdpu = to_dpu_plane(plane); struct drm_plane_state *state = plane->state; struct dpu_plane_state *pstate = to_dpu_plane_state(state); - trace_dpu_plane_disable(DRMID(plane), is_dpu_plane_virtual(plane), + trace_dpu_plane_disable(DRMID(plane), false, pstate->multirect_mode); pstate->pending = true; - - if (is_dpu_plane_virtual(plane) && - pdpu->pipe_hw && pdpu->pipe_hw->ops.setup_multirect) - pdpu->pipe_hw->ops.setup_multirect(pdpu->pipe_hw, - DPU_SSPP_RECT_SOLO, DPU_SSPP_MULTIRECT_NONE); } static void dpu_plane_atomic_update(struct drm_plane *plane, @@ -1493,22 +1456,16 @@ enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane) return plane ? to_dpu_plane(plane)->pipe : SSPP_NONE; } -bool is_dpu_plane_virtual(struct drm_plane *plane) -{ - return plane ? to_dpu_plane(plane)->is_virtual : false; -} - /* initialize plane */ struct drm_plane *dpu_plane_init(struct drm_device *dev, uint32_t pipe, enum drm_plane_type type, - unsigned long possible_crtcs, u32 master_plane_id) + unsigned long possible_crtcs) { - struct drm_plane *plane = NULL, *master_plane = NULL; + struct drm_plane *plane = NULL; const uint32_t *format_list; struct dpu_plane *pdpu; struct msm_drm_private *priv = dev->dev_private; struct dpu_kms *kms = to_dpu_kms(priv->kms); - int zpos_max = DPU_ZPOS_MAX; uint32_t num_formats; uint32_t supported_rotations; int ret = -EINVAL; @@ -1524,18 +1481,9 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, /* cache local stuff for later */ plane = &pdpu->base; pdpu->pipe = pipe; - pdpu->is_virtual = (master_plane_id != 0); - INIT_LIST_HEAD(&pdpu->mplane_list); - master_plane = drm_plane_find(dev, NULL, master_plane_id); - if (master_plane) { - struct dpu_plane *mpdpu = to_dpu_plane(master_plane); - - list_add_tail(&pdpu->mplane_list, &mpdpu->mplane_list); - } /* initialize underlying h/w driver */ - pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog, - master_plane_id != 0); + pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog); if (IS_ERR(pdpu->pipe_hw)) { DPU_ERROR("[%u]SSPP init failed\n", pipe); ret = PTR_ERR(pdpu->pipe_hw); @@ -1545,14 +1493,8 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, goto clean_sspp; } - if (pdpu->is_virtual) { - format_list = pdpu->pipe_hw->cap->sblk->virt_format_list; - num_formats = pdpu->pipe_hw->cap->sblk->virt_num_formats; - } - else { - format_list = pdpu->pipe_hw->cap->sblk->format_list; - num_formats = pdpu->pipe_hw->cap->sblk->num_formats; - } + format_list = pdpu->pipe_hw->cap->sblk->format_list; + num_formats = pdpu->pipe_hw->cap->sblk->num_formats; ret = drm_universal_plane_init(dev, plane, 0xff, &dpu_plane_funcs, format_list, num_formats, @@ -1562,14 +1504,7 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, pdpu->catalog = kms->catalog; - if (kms->catalog->mixer_count && - kms->catalog->mixer[0].sblk->maxblendstages) { - zpos_max = kms->catalog->mixer[0].sblk->maxblendstages - 1; - if (zpos_max > DPU_STAGE_MAX - DPU_STAGE_0 - 1) - zpos_max = DPU_STAGE_MAX - DPU_STAGE_0 - 1; - } - - ret = drm_plane_create_zpos_property(plane, 0, 0, zpos_max); + ret = drm_plane_create_zpos_property(plane, 0, 0, DPU_ZPOS_MAX); if (ret) DPU_ERROR("failed to install zpos property, rc = %d\n", ret); @@ -1594,15 +1529,14 @@ struct drm_plane *dpu_plane_init(struct drm_device *dev, mutex_init(&pdpu->lock); - DPU_DEBUG("%s created for pipe:%u id:%u virtual:%u\n", plane->name, - pipe, plane->base.id, master_plane_id); + DPU_DEBUG("%s created for pipe:%u id:%u\n", plane->name, + pipe, plane->base.id); return plane; clean_sspp: if (pdpu && pdpu->pipe_hw) dpu_hw_sspp_destroy(pdpu->pipe_hw); clean_plane: - list_del(&pdpu->mplane_list); kfree(pdpu); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h index e1463107a6fc..b7b1b05199c2 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h @@ -65,23 +65,6 @@ struct dpu_multirect_plane_states { enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane); /** - * is_dpu_plane_virtual - check for virtual plane - * @plane: Pointer to DRM plane object - * returns: true - if the plane is virtual - * false - if the plane is primary - */ -bool is_dpu_plane_virtual(struct drm_plane *plane); - -/** - * dpu_plane_get_ctl_flush - get control flush mask - * @plane: Pointer to DRM plane object - * @ctl: Pointer to control hardware - * @flush_sspp: Pointer to sspp flush control word - */ -void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl, - u32 *flush_sspp); - -/** * dpu_plane_flush - final plane operations before commit flush * @plane: Pointer to drm plane structure */ @@ -99,14 +82,11 @@ void dpu_plane_set_error(struct drm_plane *plane, bool error); * @pipe: dpu hardware pipe identifier * @type: Plane type - PRIMARY/OVERLAY/CURSOR * @possible_crtcs: bitmask of crtc that can be attached to the given pipe - * @master_plane_id: primary plane id of a multirect pipe. 0 value passed for - * a regular plane initialization. A non-zero primary plane - * id will be passed for a virtual pipe initialization. * */ struct drm_plane *dpu_plane_init(struct drm_device *dev, uint32_t pipe, enum drm_plane_type type, - unsigned long possible_crtcs, u32 master_plane_id); + unsigned long possible_crtcs); /** * dpu_plane_validate_multirecti_v2 - validate the multirect planes diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c index 21d20373eb8b..1305e250b71e 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c @@ -11,6 +11,26 @@ #include "dpu_hw_vbif.h" #include "dpu_trace.h" +static struct dpu_hw_vbif *dpu_get_vbif(struct dpu_kms *dpu_kms, enum dpu_vbif vbif_idx) +{ + if (vbif_idx < ARRAY_SIZE(dpu_kms->hw_vbif)) + return dpu_kms->hw_vbif[vbif_idx]; + + return NULL; +} + +static const char *dpu_vbif_name(enum dpu_vbif idx) +{ + switch (idx) { + case VBIF_RT: + return "VBIF_RT"; + case VBIF_NRT: + return "VBIF_NRT"; + default: + return "??"; + } +} + /** * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt * @vbif: Pointer to hardware vbif driver @@ -42,12 +62,12 @@ static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id) if (!status) { rc = -ETIMEDOUT; - DPU_ERROR("VBIF %d client %d not halting. TIMEDOUT.\n", - vbif->idx - VBIF_0, xin_id); + DPU_ERROR("%s client %d not halting. TIMEDOUT.\n", + dpu_vbif_name(vbif->idx), xin_id); } else { rc = 0; - DRM_DEBUG_ATOMIC("VBIF %d client %d is halted\n", - vbif->idx - VBIF_0, xin_id); + DRM_DEBUG_ATOMIC("%s client %d is halted\n", + dpu_vbif_name(vbif->idx), xin_id); } return rc; @@ -87,8 +107,8 @@ static void _dpu_vbif_apply_dynamic_ot_limit(struct dpu_hw_vbif *vbif, } } - DRM_DEBUG_ATOMIC("vbif:%d xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n", - vbif->idx - VBIF_0, params->xin_id, + DRM_DEBUG_ATOMIC("%s xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n", + dpu_vbif_name(vbif->idx), params->xin_id, params->width, params->height, params->frame_rate, pps, *ot_lim); } @@ -133,8 +153,8 @@ static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif, } exit: - DRM_DEBUG_ATOMIC("vbif:%d xin:%d ot_lim:%d\n", - vbif->idx - VBIF_0, params->xin_id, ot_lim); + DRM_DEBUG_ATOMIC("%s xin:%d ot_lim:%d\n", + dpu_vbif_name(vbif->idx), params->xin_id, ot_lim); return ot_lim; } @@ -148,20 +168,15 @@ exit: void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, struct dpu_vbif_set_ot_params *params) { - struct dpu_hw_vbif *vbif = NULL; + struct dpu_hw_vbif *vbif; struct dpu_hw_mdp *mdp; bool forced_on = false; u32 ot_lim; - int ret, i; + int ret; mdp = dpu_kms->hw_mdp; - for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { - if (dpu_kms->hw_vbif[i] && - dpu_kms->hw_vbif[i]->idx == params->vbif_idx) - vbif = dpu_kms->hw_vbif[i]; - } - + vbif = dpu_get_vbif(dpu_kms, params->vbif_idx); if (!vbif || !mdp) { DRM_DEBUG_ATOMIC("invalid arguments vbif %d mdp %d\n", vbif != NULL, mdp != NULL); @@ -204,7 +219,7 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms, void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, struct dpu_vbif_set_qos_params *params) { - struct dpu_hw_vbif *vbif = NULL; + struct dpu_hw_vbif *vbif; struct dpu_hw_mdp *mdp; bool forced_on = false; const struct dpu_vbif_qos_tbl *qos_tbl; @@ -216,13 +231,7 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, } mdp = dpu_kms->hw_mdp; - for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) { - if (dpu_kms->hw_vbif[i] && - dpu_kms->hw_vbif[i]->idx == params->vbif_idx) { - vbif = dpu_kms->hw_vbif[i]; - break; - } - } + vbif = dpu_get_vbif(dpu_kms, params->vbif_idx); if (!vbif || !vbif->cap) { DPU_ERROR("invalid vbif %d\n", params->vbif_idx); @@ -245,8 +254,8 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms, forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true); for (i = 0; i < qos_tbl->npriority_lvl; i++) { - DRM_DEBUG_ATOMIC("vbif:%d xin:%d lvl:%d/%d\n", - params->vbif_idx, params->xin_id, i, + DRM_DEBUG_ATOMIC("%s xin:%d lvl:%d/%d\n", + dpu_vbif_name(params->vbif_idx), params->xin_id, i, qos_tbl->priority_lvl[i]); vbif->ops.set_qos_remap(vbif, params->xin_id, i, qos_tbl->priority_lvl[i]); @@ -266,8 +275,8 @@ void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms) if (vbif && vbif->ops.clear_errors) { vbif->ops.clear_errors(vbif, &pnd, &src); if (pnd || src) { - DRM_DEBUG_KMS("VBIF %d: pnd 0x%X, src 0x%X\n", - vbif->idx - VBIF_0, pnd, src); + DRM_DEBUG_KMS("%s: pnd 0x%X, src 0x%X\n", + dpu_vbif_name(vbif->idx), pnd, src); } } } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c index d2a48caf9d27..b0d21838a134 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c @@ -902,12 +902,9 @@ fail: static int mdp5_setup_interconnect(struct platform_device *pdev) { - /* Interconnects are a part of MDSS device tree binding, not the - * MDP5 device. */ - struct device *mdss_dev = pdev->dev.parent; - struct icc_path *path0 = of_icc_get(mdss_dev, "mdp0-mem"); - struct icc_path *path1 = of_icc_get(mdss_dev, "mdp1-mem"); - struct icc_path *path_rot = of_icc_get(mdss_dev, "rotator-mem"); + struct icc_path *path0 = msm_icc_get(&pdev->dev, "mdp0-mem"); + struct icc_path *path1 = msm_icc_get(&pdev->dev, "mdp1-mem"); + struct icc_path *path_rot = msm_icc_get(&pdev->dev, "rotator-mem"); if (IS_ERR(path0)) return PTR_ERR(path0); diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c index 7257515871a9..676279d0ca8d 100644 --- a/drivers/gpu/drm/msm/dp/dp_catalog.c +++ b/drivers/gpu/drm/msm/dp/dp_catalog.c @@ -431,7 +431,7 @@ void dp_catalog_ctrl_config_msa(struct dp_catalog *dp_catalog, if (rate == link_rate_hbr3) pixel_div = 6; - else if (rate == 1620000 || rate == 270000) + else if (rate == 162000 || rate == 270000) pixel_div = 2; else if (rate == link_rate_hbr2) pixel_div = 4; diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index ab6aa13b1639..3854c9f1f7e9 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1214,7 +1214,7 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl, if (ret) return ret; - dp_ctrl_train_pattern_set(ctrl, pattern | DP_RECOVERED_CLOCK_OUT_EN); + dp_ctrl_train_pattern_set(ctrl, pattern); for (tries = 0; tries <= maximum_retries; tries++) { drm_dp_link_train_channel_eq_delay(ctrl->aux, ctrl->panel->dpcd); @@ -1238,8 +1238,6 @@ static int dp_ctrl_link_train_2(struct dp_ctrl_private *ctrl, return -ETIMEDOUT; } -static int dp_ctrl_reinitialize_mainlink(struct dp_ctrl_private *ctrl); - static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, int *training_step) { @@ -1358,25 +1356,7 @@ static int dp_ctrl_enable_mainlink_clocks(struct dp_ctrl_private *ctrl) if (ret) DRM_ERROR("Unable to start link clocks. ret=%d\n", ret); - drm_dbg_dp(ctrl->drm_dev, "link rate=%d pixel_clk=%d\n", - ctrl->link->link_params.rate, ctrl->dp_ctrl.pixel_rate); - - return ret; -} - -static int dp_ctrl_enable_stream_clocks(struct dp_ctrl_private *ctrl) -{ - int ret = 0; - - dp_ctrl_set_clock_rate(ctrl, DP_STREAM_PM, "stream_pixel", - ctrl->dp_ctrl.pixel_rate * 1000); - - ret = dp_power_clk_enable(ctrl->power, DP_STREAM_PM, true); - if (ret) - DRM_ERROR("Unabled to start pixel clocks. ret=%d\n", ret); - - drm_dbg_dp(ctrl->drm_dev, "link rate=%d pixel_clk=%d\n", - ctrl->link->link_params.rate, ctrl->dp_ctrl.pixel_rate); + drm_dbg_dp(ctrl->drm_dev, "link rate=%d\n", ctrl->link->link_params.rate); return ret; } @@ -1520,8 +1500,6 @@ static int dp_ctrl_link_maintenance(struct dp_ctrl_private *ctrl) ctrl->link->phy_params.p_level = 0; ctrl->link->phy_params.v_level = 0; - ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; - ret = dp_ctrl_setup_main_link(ctrl, &training_step); if (ret) goto end; @@ -1535,38 +1513,6 @@ end: return ret; } -static int dp_ctrl_on_stream_phy_test_report(struct dp_ctrl *dp_ctrl); - -static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl) -{ - int ret = 0; - - if (!ctrl->link->phy_params.phy_test_pattern_sel) { - drm_dbg_dp(ctrl->drm_dev, - "no test pattern selected by sink\n"); - return ret; - } - - /* - * The global reset will need DP link related clocks to be - * running. Add the global reset just before disabling the - * link clocks and core clocks. - */ - ret = dp_ctrl_off(&ctrl->dp_ctrl); - if (ret) { - DRM_ERROR("failed to disable DP controller\n"); - return ret; - } - - ret = dp_ctrl_on_link(&ctrl->dp_ctrl); - if (!ret) - ret = dp_ctrl_on_stream_phy_test_report(&ctrl->dp_ctrl); - else - DRM_ERROR("failed to enable DP link controller\n"); - - return ret; -} - static bool dp_ctrl_send_phy_test_pattern(struct dp_ctrl_private *ctrl) { bool success = false; @@ -1619,6 +1565,48 @@ static bool dp_ctrl_send_phy_test_pattern(struct dp_ctrl_private *ctrl) return success; } +static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl) +{ + int ret; + unsigned long pixel_rate; + + if (!ctrl->link->phy_params.phy_test_pattern_sel) { + drm_dbg_dp(ctrl->drm_dev, + "no test pattern selected by sink\n"); + return 0; + } + + /* + * The global reset will need DP link related clocks to be + * running. Add the global reset just before disabling the + * link clocks and core clocks. + */ + ret = dp_ctrl_off(&ctrl->dp_ctrl); + if (ret) { + DRM_ERROR("failed to disable DP controller\n"); + return ret; + } + + ret = dp_ctrl_on_link(&ctrl->dp_ctrl); + if (ret) { + DRM_ERROR("failed to enable DP link controller\n"); + return ret; + } + + pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; + dp_ctrl_set_clock_rate(ctrl, DP_STREAM_PM, "stream_pixel", pixel_rate * 1000); + + ret = dp_power_clk_enable(ctrl->power, DP_STREAM_PM, true); + if (ret) { + DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); + return ret; + } + + dp_ctrl_send_phy_test_pattern(ctrl); + + return 0; +} + void dp_ctrl_handle_sink_request(struct dp_ctrl *dp_ctrl) { struct dp_ctrl_private *ctrl; @@ -1689,11 +1677,12 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl) { int rc = 0; struct dp_ctrl_private *ctrl; - u32 rate = 0; + u32 rate; int link_train_max_retries = 5; u32 const phy_cts_pixel_clk_khz = 148500; u8 link_status[DP_LINK_STATUS_SIZE]; unsigned int training_step; + unsigned long pixel_rate; if (!dp_ctrl) return -EINVAL; @@ -1701,25 +1690,24 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl) ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); rate = ctrl->panel->link_info.rate; + pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; dp_power_clk_enable(ctrl->power, DP_CORE_PM, true); if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) { drm_dbg_dp(ctrl->drm_dev, "using phy test link parameters\n"); - if (!ctrl->panel->dp_mode.drm_mode.clock) - ctrl->dp_ctrl.pixel_rate = phy_cts_pixel_clk_khz; + if (!pixel_rate) + pixel_rate = phy_cts_pixel_clk_khz; } else { ctrl->link->link_params.rate = rate; ctrl->link->link_params.num_lanes = ctrl->panel->link_info.num_lanes; - ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; } - drm_dbg_dp(ctrl->drm_dev, "rate=%d, num_lanes=%d, pixel_rate=%d\n", + drm_dbg_dp(ctrl->drm_dev, "rate=%d, num_lanes=%d, pixel_rate=%lu\n", ctrl->link->link_params.rate, ctrl->link->link_params.num_lanes, - ctrl->dp_ctrl.pixel_rate); - + pixel_rate); rc = dp_ctrl_enable_mainlink_clocks(ctrl); if (rc) @@ -1816,31 +1804,12 @@ static int dp_ctrl_link_retrain(struct dp_ctrl_private *ctrl) return dp_ctrl_setup_main_link(ctrl, &training_step); } -static int dp_ctrl_on_stream_phy_test_report(struct dp_ctrl *dp_ctrl) -{ - int ret; - struct dp_ctrl_private *ctrl; - - ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); - - ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; - - ret = dp_ctrl_enable_stream_clocks(ctrl); - if (ret) { - DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); - return ret; - } - - dp_ctrl_send_phy_test_pattern(ctrl); - - return 0; -} - int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl, bool force_link_train) { int ret = 0; bool mainlink_ready = false; struct dp_ctrl_private *ctrl; + unsigned long pixel_rate; unsigned long pixel_rate_orig; if (!dp_ctrl) @@ -1848,15 +1817,14 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl, bool force_link_train) ctrl = container_of(dp_ctrl, struct dp_ctrl_private, dp_ctrl); - ctrl->dp_ctrl.pixel_rate = ctrl->panel->dp_mode.drm_mode.clock; + pixel_rate = pixel_rate_orig = ctrl->panel->dp_mode.drm_mode.clock; - pixel_rate_orig = ctrl->dp_ctrl.pixel_rate; if (dp_ctrl->wide_bus_en) - ctrl->dp_ctrl.pixel_rate >>= 1; + pixel_rate >>= 1; - drm_dbg_dp(ctrl->drm_dev, "rate=%d, num_lanes=%d, pixel_rate=%d\n", + drm_dbg_dp(ctrl->drm_dev, "rate=%d, num_lanes=%d, pixel_rate=%lu\n", ctrl->link->link_params.rate, - ctrl->link->link_params.num_lanes, ctrl->dp_ctrl.pixel_rate); + ctrl->link->link_params.num_lanes, pixel_rate); if (!dp_power_clk_status(ctrl->power, DP_CTRL_PM)) { /* link clk is off */ ret = dp_ctrl_enable_mainlink_clocks(ctrl); @@ -1866,9 +1834,11 @@ int dp_ctrl_on_stream(struct dp_ctrl *dp_ctrl, bool force_link_train) } } - ret = dp_ctrl_enable_stream_clocks(ctrl); + dp_ctrl_set_clock_rate(ctrl, DP_STREAM_PM, "stream_pixel", pixel_rate * 1000); + + ret = dp_power_clk_enable(ctrl->power, DP_STREAM_PM, true); if (ret) { - DRM_ERROR("Failed to start pixel clocks. ret=%d\n", ret); + DRM_ERROR("Unable to start pixel clocks. ret=%d\n", ret); goto end; } diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.h b/drivers/gpu/drm/msm/dp/dp_ctrl.h index b563e2e3bfe5..9f29734af81c 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.h +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.h @@ -16,7 +16,6 @@ struct dp_ctrl { bool orientation; atomic_t aborted; - u32 pixel_rate; bool wide_bus_en; }; diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 36f0af02749f..36bb6191d2f0 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -786,7 +786,7 @@ static int dp_link_process_link_training_request(struct dp_link_private *link) link->request.test_lane_count); link->dp_link.link_params.num_lanes = link->request.test_lane_count; - link->dp_link.link_params.rate = + link->dp_link.link_params.rate = drm_dp_bw_code_to_link_rate(link->request.test_link_rate); return 0; @@ -965,8 +965,7 @@ static int dp_link_process_link_status_update(struct dp_link_private *link) if (channel_eq_done && clock_recovery_done) return -EINVAL; - - return 0; + return 0; } /** diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c index 1625328fa430..39bbabb5daf6 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.c +++ b/drivers/gpu/drm/msm/dsi/dsi.c @@ -6,14 +6,6 @@ #include "dsi.h" #include "dsi_cfg.h" -struct drm_encoder *msm_dsi_get_encoder(struct msm_dsi *msm_dsi) -{ - if (!msm_dsi || !msm_dsi_device_connected(msm_dsi)) - return NULL; - - return msm_dsi->encoder; -} - bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi) { unsigned long host_flags = msm_dsi_host_get_mode_flags(msm_dsi->host); @@ -21,7 +13,7 @@ bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi) return !(host_flags & MIPI_DSI_MODE_VIDEO); } -struct msm_display_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi) +struct drm_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi) { return msm_dsi_host_get_dsc_config(msm_dsi->host); } @@ -220,7 +212,6 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev, struct drm_encoder *encoder) { struct msm_drm_private *priv; - struct drm_bridge *ext_bridge; int ret; if (WARN_ON(!encoder) || WARN_ON(!msm_dsi) || WARN_ON(!dev)) @@ -254,26 +245,10 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev, goto fail; } - /* - * check if the dsi encoder output is connected to a panel or an - * external bridge. We create a connector only if we're connected to a - * drm_panel device. When we're connected to an external bridge, we - * assume that the drm_bridge driver will create the connector itself. - */ - ext_bridge = msm_dsi_host_get_bridge(msm_dsi->host); - - if (ext_bridge) - msm_dsi->connector = - msm_dsi_manager_ext_bridge_init(msm_dsi->id); - else - msm_dsi->connector = - msm_dsi_manager_connector_init(msm_dsi->id); - - if (IS_ERR(msm_dsi->connector)) { - ret = PTR_ERR(msm_dsi->connector); + ret = msm_dsi_manager_ext_bridge_init(msm_dsi->id); + if (ret) { DRM_DEV_ERROR(dev->dev, "failed to create dsi connector: %d\n", ret); - msm_dsi->connector = NULL; goto fail; } @@ -287,12 +262,6 @@ fail: msm_dsi->bridge = NULL; } - /* don't destroy connector if we didn't make it */ - if (msm_dsi->connector && !msm_dsi->external_bridge) - msm_dsi->connector->funcs->destroy(msm_dsi->connector); - - msm_dsi->connector = NULL; - return ret; } diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h index 580a1e6358bf..2a96b4fe7839 100644 --- a/drivers/gpu/drm/msm/dsi/dsi.h +++ b/drivers/gpu/drm/msm/dsi/dsi.h @@ -12,7 +12,6 @@ #include <drm/drm_bridge.h> #include <drm/drm_crtc.h> #include <drm/drm_mipi_dsi.h> -#include <drm/drm_panel.h> #include "msm_drv.h" #include "disp/msm_disp_snapshot.h" @@ -30,27 +29,12 @@ enum msm_dsi_phy_usecase { MSM_DSI_PHY_SLAVE, }; -#define DSI_DEV_REGULATOR_MAX 8 #define DSI_BUS_CLK_MAX 4 -/* Regulators for DSI devices */ -struct dsi_reg_entry { - char name[32]; - int enable_load; - int disable_load; -}; - -struct dsi_reg_config { - int num; - struct dsi_reg_entry regs[DSI_DEV_REGULATOR_MAX]; -}; - struct msm_dsi { struct drm_device *dev; struct platform_device *pdev; - /* connector managed by us when we're connected to a drm_panel */ - struct drm_connector *connector; /* internal dsi bridge attached to MDP interface */ struct drm_bridge *bridge; @@ -58,10 +42,8 @@ struct msm_dsi { struct msm_dsi_phy *phy; /* - * panel/external_bridge connected to dsi bridge output, only one of the - * two can be valid at a time + * external_bridge connected to dsi bridge output */ - struct drm_panel *panel; struct drm_bridge *external_bridge; struct device *phy_dev; @@ -76,8 +58,7 @@ struct msm_dsi { /* dsi manager */ struct drm_bridge *msm_dsi_manager_bridge_init(u8 id); void msm_dsi_manager_bridge_destroy(struct drm_bridge *bridge); -struct drm_connector *msm_dsi_manager_connector_init(u8 id); -struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id); +int msm_dsi_manager_ext_bridge_init(u8 id); int msm_dsi_manager_cmd_xfer(int id, const struct mipi_dsi_msg *msg); bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len); int msm_dsi_manager_register(struct msm_dsi *msm_dsi); @@ -87,11 +68,9 @@ void msm_dsi_manager_tpg_enable(void); /* msm dsi */ static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi) { - return msm_dsi->panel || msm_dsi->external_bridge; + return msm_dsi->external_bridge; } -struct drm_encoder *msm_dsi_get_encoder(struct msm_dsi *msm_dsi); - /* dsi host */ struct msm_dsi_host; int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host, @@ -116,9 +95,7 @@ int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host, const struct drm_display_mode *mode); enum drm_mode_status msm_dsi_host_check_dsc(struct mipi_dsi_host *host, const struct drm_display_mode *mode); -struct drm_panel *msm_dsi_host_get_panel(struct mipi_dsi_host *host); unsigned long msm_dsi_host_get_mode_flags(struct mipi_dsi_host *host); -struct drm_bridge *msm_dsi_host_get_bridge(struct mipi_dsi_host *host); int msm_dsi_host_register(struct mipi_dsi_host *host); void msm_dsi_host_unregister(struct mipi_dsi_host *host); void msm_dsi_host_set_phy_mode(struct mipi_dsi_host *host, @@ -154,7 +131,7 @@ int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_bonded_dsi); int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_bonded_dsi); void msm_dsi_host_snapshot(struct msm_disp_state *disp_state, struct mipi_dsi_host *host); void msm_dsi_host_test_pattern_en(struct mipi_dsi_host *host); -struct msm_display_dsc_config *msm_dsi_host_get_dsc_config(struct mipi_dsi_host *host); +struct drm_dsc_config *msm_dsi_host_get_dsc_config(struct mipi_dsi_host *host); /* dsi phy */ struct msm_dsi_phy; diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c index 2c23324a2296..7e97c239ed48 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c @@ -9,16 +9,16 @@ static const char * const dsi_v2_bus_clk_names[] = { "core_mmss", "iface", "bus", }; +static const struct regulator_bulk_data apq8064_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 100000 }, /* 1.2 V */ + { .supply = "avdd", .init_load_uA = 10000 }, /* 3.0 V */ + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ +}; + static const struct msm_dsi_config apq8064_dsi_cfg = { .io_offset = 0, - .reg_cfg = { - .num = 3, - .regs = { - {"vdda", 100000, 100}, /* 1.2 V */ - {"avdd", 10000, 100}, /* 3.0 V */ - {"vddio", 100000, 100}, /* 1.8 V */ - }, - }, + .regulator_data = apq8064_dsi_regulators, + .num_regulators = ARRAY_SIZE(apq8064_dsi_regulators), .bus_clk_names = dsi_v2_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_v2_bus_clk_names), .io_start = { 0x4700000, 0x5800000 }, @@ -29,16 +29,16 @@ static const char * const dsi_6g_bus_clk_names[] = { "mdp_core", "iface", "bus", "core_mmss", }; +static const struct regulator_bulk_data msm8974_apq8084_regulators[] = { + { .supply = "vdd", .init_load_uA = 150000 }, /* 3.0 V */ + { .supply = "vdda", .init_load_uA = 100000 }, /* 1.2 V */ + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ +}; + static const struct msm_dsi_config msm8974_apq8084_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 3, - .regs = { - {"vdd", 150000, 100}, /* 3.0 V */ - {"vdda", 100000, 100}, /* 1.2 V */ - {"vddio", 100000, 100}, /* 1.8 V */ - }, - }, + .regulator_data = msm8974_apq8084_regulators, + .num_regulators = ARRAY_SIZE(msm8974_apq8084_regulators), .bus_clk_names = dsi_6g_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_6g_bus_clk_names), .io_start = { 0xfd922800, 0xfd922b00 }, @@ -49,15 +49,15 @@ static const char * const dsi_8916_bus_clk_names[] = { "mdp_core", "iface", "bus", }; +static const struct regulator_bulk_data msm8916_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 100000 }, /* 1.2 V */ + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ +}; + static const struct msm_dsi_config msm8916_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 2, - .regs = { - {"vdda", 100000, 100}, /* 1.2 V */ - {"vddio", 100000, 100}, /* 1.8 V */ - }, - }, + .regulator_data = msm8916_dsi_regulators, + .num_regulators = ARRAY_SIZE(msm8916_dsi_regulators), .bus_clk_names = dsi_8916_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_8916_bus_clk_names), .io_start = { 0x1a98000 }, @@ -68,34 +68,34 @@ static const char * const dsi_8976_bus_clk_names[] = { "mdp_core", "iface", "bus", }; +static const struct regulator_bulk_data msm8976_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 100000 }, /* 1.2 V */ + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ +}; + static const struct msm_dsi_config msm8976_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 2, - .regs = { - {"vdda", 100000, 100}, /* 1.2 V */ - {"vddio", 100000, 100}, /* 1.8 V */ - }, - }, + .regulator_data = msm8976_dsi_regulators, + .num_regulators = ARRAY_SIZE(msm8976_dsi_regulators), .bus_clk_names = dsi_8976_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_8976_bus_clk_names), .io_start = { 0x1a94000, 0x1a96000 }, .num_dsi = 2, }; +static const struct regulator_bulk_data msm8994_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 100000 }, /* 1.25 V */ + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ + { .supply = "vcca", .init_load_uA = 10000 }, /* 1.0 V */ + { .supply = "vdd", .init_load_uA = 100000 }, /* 1.8 V */ + { .supply = "lab_reg", .init_load_uA = -1 }, + { .supply = "ibb_reg", .init_load_uA = -1 }, +}; + static const struct msm_dsi_config msm8994_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 6, - .regs = { - {"vdda", 100000, 100}, /* 1.25 V */ - {"vddio", 100000, 100}, /* 1.8 V */ - {"vcca", 10000, 100}, /* 1.0 V */ - {"vdd", 100000, 100}, /* 1.8 V */ - {"lab_reg", -1, -1}, - {"ibb_reg", -1, -1}, - }, - }, + .regulator_data = msm8994_dsi_regulators, + .num_regulators = ARRAY_SIZE(msm8994_dsi_regulators), .bus_clk_names = dsi_6g_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_6g_bus_clk_names), .io_start = { 0xfd998000, 0xfd9a0000 }, @@ -106,16 +106,16 @@ static const char * const dsi_8996_bus_clk_names[] = { "mdp_core", "iface", "bus", "core_mmss", }; +static const struct regulator_bulk_data msm8996_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 18160 }, /* 1.25 V */ + { .supply = "vcca", .init_load_uA = 17000 }, /* 0.925 V */ + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ +}; + static const struct msm_dsi_config msm8996_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 2, - .regs = { - {"vdda", 18160, 1 }, /* 1.25 V */ - {"vcca", 17000, 32 }, /* 0.925 V */ - {"vddio", 100000, 100 },/* 1.8 V */ - }, - }, + .regulator_data = msm8996_dsi_regulators, + .num_regulators = ARRAY_SIZE(msm8996_dsi_regulators), .bus_clk_names = dsi_8996_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_8996_bus_clk_names), .io_start = { 0x994000, 0x996000 }, @@ -126,15 +126,15 @@ static const char * const dsi_msm8998_bus_clk_names[] = { "iface", "bus", "core", }; +static const struct regulator_bulk_data msm8998_dsi_regulators[] = { + { .supply = "vdd", .init_load_uA = 367000 }, /* 0.9 V */ + { .supply = "vdda", .init_load_uA = 62800 }, /* 1.2 V */ +}; + static const struct msm_dsi_config msm8998_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 2, - .regs = { - {"vdd", 367000, 16 }, /* 0.9 V */ - {"vdda", 62800, 2 }, /* 1.2 V */ - }, - }, + .regulator_data = msm8998_dsi_regulators, + .num_regulators = ARRAY_SIZE(msm8998_dsi_regulators), .bus_clk_names = dsi_msm8998_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_msm8998_bus_clk_names), .io_start = { 0xc994000, 0xc996000 }, @@ -145,14 +145,14 @@ static const char * const dsi_sdm660_bus_clk_names[] = { "iface", "bus", "core", "core_mmss", }; +static const struct regulator_bulk_data sdm660_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 12560 }, /* 1.2 V */ +}; + static const struct msm_dsi_config sdm660_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 2, - .regs = { - {"vdda", 12560, 4 }, /* 1.2 V */ - }, - }, + .regulator_data = sdm660_dsi_regulators, + .num_regulators = ARRAY_SIZE(sdm660_dsi_regulators), .bus_clk_names = dsi_sdm660_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_sdm660_bus_clk_names), .io_start = { 0xc994000, 0xc996000 }, @@ -167,28 +167,28 @@ static const char * const dsi_sc7180_bus_clk_names[] = { "iface", "bus", }; +static const struct regulator_bulk_data sdm845_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 21800 }, /* 1.2 V */ +}; + static const struct msm_dsi_config sdm845_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 1, - .regs = { - {"vdda", 21800, 4 }, /* 1.2 V */ - }, - }, + .regulator_data = sdm845_dsi_regulators, + .num_regulators = ARRAY_SIZE(sdm845_dsi_regulators), .bus_clk_names = dsi_sdm845_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_sdm845_bus_clk_names), .io_start = { 0xae94000, 0xae96000 }, .num_dsi = 2, }; +static const struct regulator_bulk_data sc7180_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 21800 }, /* 1.2 V */ +}; + static const struct msm_dsi_config sc7180_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 1, - .regs = { - {"vdda", 21800, 4 }, /* 1.2 V */ - }, - }, + .regulator_data = sc7180_dsi_regulators, + .num_regulators = ARRAY_SIZE(sc7180_dsi_regulators), .bus_clk_names = dsi_sc7180_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_sc7180_bus_clk_names), .io_start = { 0xae94000 }, @@ -199,14 +199,14 @@ static const char * const dsi_sc7280_bus_clk_names[] = { "iface", "bus", }; +static const struct regulator_bulk_data sc7280_dsi_regulators[] = { + { .supply = "vdda", .init_load_uA = 8350 }, /* 1.2 V */ +}; + static const struct msm_dsi_config sc7280_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 1, - .regs = { - {"vdda", 8350, 0 }, /* 1.2 V */ - }, - }, + .regulator_data = sc7280_dsi_regulators, + .num_regulators = ARRAY_SIZE(sc7280_dsi_regulators), .bus_clk_names = dsi_sc7280_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_sc7280_bus_clk_names), .io_start = { 0xae94000 }, @@ -217,14 +217,14 @@ static const char * const dsi_qcm2290_bus_clk_names[] = { "iface", "bus", }; +static const struct regulator_bulk_data qcm2290_dsi_cfg_regulators[] = { + { .supply = "vdda", .init_load_uA = 21800 }, /* 1.2 V */ +}; + static const struct msm_dsi_config qcm2290_dsi_cfg = { .io_offset = DSI_6G_REG_SHIFT, - .reg_cfg = { - .num = 1, - .regs = { - {"vdda", 21800, 4 }, /* 1.2 V */ - }, - }, + .regulator_data = qcm2290_dsi_cfg_regulators, + .num_regulators = ARRAY_SIZE(qcm2290_dsi_cfg_regulators), .bus_clk_names = dsi_qcm2290_bus_clk_names, .num_bus_clks = ARRAY_SIZE(dsi_qcm2290_bus_clk_names), .io_start = { 0x5e94000 }, diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h index fe54a999968b..8f04e685a74e 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h +++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h @@ -32,7 +32,8 @@ struct msm_dsi_config { u32 io_offset; - struct dsi_reg_config reg_cfg; + const struct regulator_bulk_data *regulator_data; + int num_regulators; const char * const *bus_clk_names; const int num_bus_clks; const resource_size_t io_start[DSI_MAX]; diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index a34078497af1..7fbf391c024f 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -33,7 +33,7 @@ #define DSI_RESET_TOGGLE_DELAY_MS 20 -static int dsi_populate_dsc_params(struct msm_display_dsc_config *dsc); +static int dsi_populate_dsc_params(struct drm_dsc_config *dsc); static int dsi_get_version(const void __iomem *base, u32 *major, u32 *minor) { @@ -108,7 +108,7 @@ struct msm_dsi_host { void __iomem *ctrl_base; phys_addr_t ctrl_size; - struct regulator_bulk_data supplies[DSI_DEV_REGULATOR_MAX]; + struct regulator_bulk_data *supplies; int num_bus_clks; struct clk_bulk_data bus_clks[DSI_BUS_CLK_MAX]; @@ -144,7 +144,6 @@ struct msm_dsi_host { u32 err_work_state; struct work_struct err_work; - struct work_struct hpd_work; struct workqueue_struct *workqueue; /* DSI 6G TX buffer*/ @@ -161,10 +160,9 @@ struct msm_dsi_host { struct regmap *sfpb; struct drm_display_mode *mode; - struct msm_display_dsc_config *dsc; + struct drm_dsc_config *dsc; /* connected device info */ - struct device_node *device_node; unsigned int channel; unsigned int lanes; enum mipi_dsi_pixel_format format; @@ -205,9 +203,6 @@ static inline void dsi_write(struct msm_dsi_host *msm_host, u32 reg, u32 data) msm_writel(data, msm_host->ctrl_base + reg); } -static int dsi_host_regulator_enable(struct msm_dsi_host *msm_host); -static void dsi_host_regulator_disable(struct msm_dsi_host *msm_host); - static const struct msm_dsi_cfg_handler *dsi_get_config( struct msm_dsi_host *msm_host) { @@ -258,76 +253,6 @@ static inline struct msm_dsi_host *to_msm_dsi_host(struct mipi_dsi_host *host) return container_of(host, struct msm_dsi_host, base); } -static void dsi_host_regulator_disable(struct msm_dsi_host *msm_host) -{ - struct regulator_bulk_data *s = msm_host->supplies; - const struct dsi_reg_entry *regs = msm_host->cfg_hnd->cfg->reg_cfg.regs; - int num = msm_host->cfg_hnd->cfg->reg_cfg.num; - int i; - - DBG(""); - for (i = num - 1; i >= 0; i--) - if (regs[i].disable_load >= 0) - regulator_set_load(s[i].consumer, - regs[i].disable_load); - - regulator_bulk_disable(num, s); -} - -static int dsi_host_regulator_enable(struct msm_dsi_host *msm_host) -{ - struct regulator_bulk_data *s = msm_host->supplies; - const struct dsi_reg_entry *regs = msm_host->cfg_hnd->cfg->reg_cfg.regs; - int num = msm_host->cfg_hnd->cfg->reg_cfg.num; - int ret, i; - - DBG(""); - for (i = 0; i < num; i++) { - if (regs[i].enable_load >= 0) { - ret = regulator_set_load(s[i].consumer, - regs[i].enable_load); - if (ret < 0) { - pr_err("regulator %d set op mode failed, %d\n", - i, ret); - goto fail; - } - } - } - - ret = regulator_bulk_enable(num, s); - if (ret < 0) { - pr_err("regulator enable failed, %d\n", ret); - goto fail; - } - - return 0; - -fail: - for (i--; i >= 0; i--) - regulator_set_load(s[i].consumer, regs[i].disable_load); - return ret; -} - -static int dsi_regulator_init(struct msm_dsi_host *msm_host) -{ - struct regulator_bulk_data *s = msm_host->supplies; - const struct dsi_reg_entry *regs = msm_host->cfg_hnd->cfg->reg_cfg.regs; - int num = msm_host->cfg_hnd->cfg->reg_cfg.num; - int i, ret; - - for (i = 0; i < num; i++) - s[i].supply = regs[i].name; - - ret = devm_regulator_bulk_get(&msm_host->pdev->dev, num, s); - if (ret < 0) { - pr_err("%s: failed to init regulator, ret=%d\n", - __func__, ret); - return ret; - } - - return 0; -} - int dsi_clk_init_v2(struct msm_dsi_host *msm_host) { struct platform_device *pdev = msm_host->pdev; @@ -916,7 +841,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable, static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mode, u32 hdisplay) { - struct msm_display_dsc_config *dsc = msm_host->dsc; + struct drm_dsc_config *dsc = msm_host->dsc; u32 reg, intf_width, reg_ctrl, reg_ctrl2; u32 slice_per_intf, total_bytes_per_intf; u32 pkt_per_line; @@ -927,24 +852,24 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod * compress mode registers */ intf_width = hdisplay; - slice_per_intf = DIV_ROUND_UP(intf_width, dsc->drm->slice_width); + slice_per_intf = DIV_ROUND_UP(intf_width, dsc->slice_width); /* If slice_per_pkt is greater than slice_per_intf * then default to 1. This can happen during partial * update. */ - if (slice_per_intf > dsc->drm->slice_count) - dsc->drm->slice_count = 1; + if (slice_per_intf > dsc->slice_count) + dsc->slice_count = 1; - slice_per_intf = DIV_ROUND_UP(hdisplay, dsc->drm->slice_width); - bytes_in_slice = DIV_ROUND_UP(dsc->drm->slice_width * dsc->drm->bits_per_pixel, 8); + slice_per_intf = DIV_ROUND_UP(hdisplay, dsc->slice_width); + bytes_in_slice = DIV_ROUND_UP(dsc->slice_width * dsc->bits_per_pixel, 8); - dsc->drm->slice_chunk_size = bytes_in_slice; + dsc->slice_chunk_size = bytes_in_slice; total_bytes_per_intf = bytes_in_slice * slice_per_intf; eol_byte_num = total_bytes_per_intf % 3; - pkt_per_line = slice_per_intf / dsc->drm->slice_count; + pkt_per_line = slice_per_intf / dsc->slice_count; if (is_cmd_mode) /* packet data type */ reg = DSI_COMMAND_COMPRESSION_MODE_CTRL_STREAM0_DATATYPE(MIPI_DSI_DCS_LONG_WRITE); @@ -1009,7 +934,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) } if (msm_host->dsc) { - struct msm_display_dsc_config *dsc = msm_host->dsc; + struct drm_dsc_config *dsc = msm_host->dsc; /* update dsc params with timing params */ if (!dsc || !mode->hdisplay || !mode->vdisplay) { @@ -1018,9 +943,9 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_bonded_dsi) return; } - dsc->drm->pic_width = mode->hdisplay; - dsc->drm->pic_height = mode->vdisplay; - DBG("Mode %dx%d\n", dsc->drm->pic_width, dsc->drm->pic_height); + dsc->pic_width = mode->hdisplay; + dsc->pic_height = mode->vdisplay; + DBG("Mode %dx%d\n", dsc->pic_width, dsc->pic_height); /* we do the calculations for dsc parameters here so that * panel can use these parameters @@ -1500,14 +1425,6 @@ static int dsi_cmds2buf_tx(struct msm_dsi_host *msm_host, return len; } -static void dsi_hpd_worker(struct work_struct *work) -{ - struct msm_dsi_host *msm_host = - container_of(work, struct msm_dsi_host, hpd_work); - - drm_helper_hpd_irq_event(msm_host->dev); -} - static void dsi_err_worker(struct work_struct *work) { struct msm_dsi_host *msm_host = @@ -1686,6 +1603,8 @@ static int dsi_host_attach(struct mipi_dsi_host *host, msm_host->lanes = dsi->lanes; msm_host->format = dsi->format; msm_host->mode_flags = dsi->mode_flags; + if (dsi->dsc) + msm_host->dsc = dsi->dsc; /* Some gpios defined in panel DT need to be controlled by host */ ret = dsi_host_init_panel_gpios(msm_host, &dsi->dev); @@ -1697,8 +1616,6 @@ static int dsi_host_attach(struct mipi_dsi_host *host, return ret; DBG("id=%d", msm_host->id); - if (msm_host->dev) - queue_work(msm_host->workqueue, &msm_host->hpd_work); return 0; } @@ -1710,11 +1627,7 @@ static int dsi_host_detach(struct mipi_dsi_host *host, dsi_dev_detach(msm_host->pdev); - msm_host->device_node = NULL; - DBG("id=%d", msm_host->id); - if (msm_host->dev) - queue_work(msm_host->workqueue, &msm_host->hpd_work); return 0; } @@ -1841,7 +1754,7 @@ static char bpg_offset[DSC_NUM_BUF_RANGES] = { 2, 0, 0, -2, -4, -6, -8, -8, -8, -10, -10, -12, -12, -12, -12 }; -static int dsi_populate_dsc_params(struct msm_display_dsc_config *dsc) +static int dsi_populate_dsc_params(struct drm_dsc_config *dsc) { int mux_words_size; int groups_per_line, groups_total; @@ -1854,98 +1767,98 @@ static int dsi_populate_dsc_params(struct msm_display_dsc_config *dsc) int final_value, final_scale; int i; - dsc->drm->rc_model_size = 8192; - dsc->drm->first_line_bpg_offset = 12; - dsc->drm->rc_edge_factor = 6; - dsc->drm->rc_tgt_offset_high = 3; - dsc->drm->rc_tgt_offset_low = 3; - dsc->drm->simple_422 = 0; - dsc->drm->convert_rgb = 1; - dsc->drm->vbr_enable = 0; + dsc->rc_model_size = 8192; + dsc->first_line_bpg_offset = 12; + dsc->rc_edge_factor = 6; + dsc->rc_tgt_offset_high = 3; + dsc->rc_tgt_offset_low = 3; + dsc->simple_422 = 0; + dsc->convert_rgb = 1; + dsc->vbr_enable = 0; /* handle only bpp = bpc = 8 */ for (i = 0; i < DSC_NUM_BUF_RANGES - 1 ; i++) - dsc->drm->rc_buf_thresh[i] = dsi_dsc_rc_buf_thresh[i]; + dsc->rc_buf_thresh[i] = dsi_dsc_rc_buf_thresh[i]; for (i = 0; i < DSC_NUM_BUF_RANGES; i++) { - dsc->drm->rc_range_params[i].range_min_qp = min_qp[i]; - dsc->drm->rc_range_params[i].range_max_qp = max_qp[i]; - dsc->drm->rc_range_params[i].range_bpg_offset = bpg_offset[i]; + dsc->rc_range_params[i].range_min_qp = min_qp[i]; + dsc->rc_range_params[i].range_max_qp = max_qp[i]; + dsc->rc_range_params[i].range_bpg_offset = bpg_offset[i]; } - dsc->drm->initial_offset = 6144; /* Not bpp 12 */ - if (dsc->drm->bits_per_pixel != 8) - dsc->drm->initial_offset = 2048; /* bpp = 12 */ + dsc->initial_offset = 6144; /* Not bpp 12 */ + if (dsc->bits_per_pixel != 8) + dsc->initial_offset = 2048; /* bpp = 12 */ mux_words_size = 48; /* bpc == 8/10 */ - if (dsc->drm->bits_per_component == 12) + if (dsc->bits_per_component == 12) mux_words_size = 64; - dsc->drm->initial_xmit_delay = 512; - dsc->drm->initial_scale_value = 32; - dsc->drm->first_line_bpg_offset = 12; - dsc->drm->line_buf_depth = dsc->drm->bits_per_component + 1; + dsc->initial_xmit_delay = 512; + dsc->initial_scale_value = 32; + dsc->first_line_bpg_offset = 12; + dsc->line_buf_depth = dsc->bits_per_component + 1; /* bpc 8 */ - dsc->drm->flatness_min_qp = 3; - dsc->drm->flatness_max_qp = 12; - dsc->drm->rc_quant_incr_limit0 = 11; - dsc->drm->rc_quant_incr_limit1 = 11; - dsc->drm->mux_word_size = DSC_MUX_WORD_SIZE_8_10_BPC; + dsc->flatness_min_qp = 3; + dsc->flatness_max_qp = 12; + dsc->rc_quant_incr_limit0 = 11; + dsc->rc_quant_incr_limit1 = 11; + dsc->mux_word_size = DSC_MUX_WORD_SIZE_8_10_BPC; /* FIXME: need to call drm_dsc_compute_rc_parameters() so that rest of * params are calculated */ - groups_per_line = DIV_ROUND_UP(dsc->drm->slice_width, 3); - dsc->drm->slice_chunk_size = dsc->drm->slice_width * dsc->drm->bits_per_pixel / 8; - if ((dsc->drm->slice_width * dsc->drm->bits_per_pixel) % 8) - dsc->drm->slice_chunk_size++; + groups_per_line = DIV_ROUND_UP(dsc->slice_width, 3); + dsc->slice_chunk_size = dsc->slice_width * dsc->bits_per_pixel / 8; + if ((dsc->slice_width * dsc->bits_per_pixel) % 8) + dsc->slice_chunk_size++; /* rbs-min */ - min_rate_buffer_size = dsc->drm->rc_model_size - dsc->drm->initial_offset + - dsc->drm->initial_xmit_delay * dsc->drm->bits_per_pixel + - groups_per_line * dsc->drm->first_line_bpg_offset; + min_rate_buffer_size = dsc->rc_model_size - dsc->initial_offset + + dsc->initial_xmit_delay * dsc->bits_per_pixel + + groups_per_line * dsc->first_line_bpg_offset; - hrd_delay = DIV_ROUND_UP(min_rate_buffer_size, dsc->drm->bits_per_pixel); + hrd_delay = DIV_ROUND_UP(min_rate_buffer_size, dsc->bits_per_pixel); - dsc->drm->initial_dec_delay = hrd_delay - dsc->drm->initial_xmit_delay; + dsc->initial_dec_delay = hrd_delay - dsc->initial_xmit_delay; - dsc->drm->initial_scale_value = 8 * dsc->drm->rc_model_size / - (dsc->drm->rc_model_size - dsc->drm->initial_offset); + dsc->initial_scale_value = 8 * dsc->rc_model_size / + (dsc->rc_model_size - dsc->initial_offset); - slice_bits = 8 * dsc->drm->slice_chunk_size * dsc->drm->slice_height; + slice_bits = 8 * dsc->slice_chunk_size * dsc->slice_height; - groups_total = groups_per_line * dsc->drm->slice_height; + groups_total = groups_per_line * dsc->slice_height; - data = dsc->drm->first_line_bpg_offset * 2048; + data = dsc->first_line_bpg_offset * 2048; - dsc->drm->nfl_bpg_offset = DIV_ROUND_UP(data, (dsc->drm->slice_height - 1)); + dsc->nfl_bpg_offset = DIV_ROUND_UP(data, (dsc->slice_height - 1)); - pre_num_extra_mux_bits = 3 * (mux_words_size + (4 * dsc->drm->bits_per_component + 4) - 2); + pre_num_extra_mux_bits = 3 * (mux_words_size + (4 * dsc->bits_per_component + 4) - 2); num_extra_mux_bits = pre_num_extra_mux_bits - (mux_words_size - ((slice_bits - pre_num_extra_mux_bits) % mux_words_size)); - data = 2048 * (dsc->drm->rc_model_size - dsc->drm->initial_offset + num_extra_mux_bits); - dsc->drm->slice_bpg_offset = DIV_ROUND_UP(data, groups_total); + data = 2048 * (dsc->rc_model_size - dsc->initial_offset + num_extra_mux_bits); + dsc->slice_bpg_offset = DIV_ROUND_UP(data, groups_total); /* bpp * 16 + 0.5 */ - data = dsc->drm->bits_per_pixel * 16; + data = dsc->bits_per_pixel * 16; data *= 2; data++; data /= 2; target_bpp_x16 = data; - data = (dsc->drm->initial_xmit_delay * target_bpp_x16) / 16; - final_value = dsc->drm->rc_model_size - data + num_extra_mux_bits; - dsc->drm->final_offset = final_value; + data = (dsc->initial_xmit_delay * target_bpp_x16) / 16; + final_value = dsc->rc_model_size - data + num_extra_mux_bits; + dsc->final_offset = final_value; - final_scale = 8 * dsc->drm->rc_model_size / (dsc->drm->rc_model_size - final_value); + final_scale = 8 * dsc->rc_model_size / (dsc->rc_model_size - final_value); - data = (final_scale - 9) * (dsc->drm->nfl_bpg_offset + dsc->drm->slice_bpg_offset); - dsc->drm->scale_increment_interval = (2048 * dsc->drm->final_offset) / data; + data = (final_scale - 9) * (dsc->nfl_bpg_offset + dsc->slice_bpg_offset); + dsc->scale_increment_interval = (2048 * dsc->final_offset) / data; - dsc->drm->scale_decrement_interval = groups_per_line / (dsc->drm->initial_scale_value - 8); + dsc->scale_decrement_interval = groups_per_line / (dsc->initial_scale_value - 8); return 0; } @@ -1954,7 +1867,7 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) { struct device *dev = &msm_host->pdev->dev; struct device_node *np = dev->of_node; - struct device_node *endpoint, *device_node; + struct device_node *endpoint; int ret = 0; /* @@ -1977,16 +1890,6 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) goto err; } - /* Get panel node from the output port's endpoint data */ - device_node = of_graph_get_remote_node(np, 1, 0); - if (!device_node) { - DRM_DEV_DEBUG(dev, "%s: no valid device\n", __func__); - ret = -ENODEV; - goto err; - } - - msm_host->device_node = device_node; - if (of_property_read_bool(np, "syscon-sfpb")) { msm_host->sfpb = syscon_regmap_lookup_by_phandle(np, "syscon-sfpb"); @@ -1997,8 +1900,6 @@ static int dsi_host_parse_dt(struct msm_dsi_host *msm_host) } } - of_node_put(device_node); - err: of_node_put(endpoint); @@ -2028,6 +1929,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) { struct msm_dsi_host *msm_host = NULL; struct platform_device *pdev = msm_dsi->pdev; + const struct msm_dsi_config *cfg; int ret; msm_host = devm_kzalloc(&pdev->dev, sizeof(*msm_host), GFP_KERNEL); @@ -2060,6 +1962,7 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) pr_err("%s: get config failed\n", __func__); goto fail; } + cfg = msm_host->cfg_hnd->cfg; msm_host->id = dsi_host_get_id(msm_host); if (msm_host->id < 0) { @@ -2069,13 +1972,13 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) } /* fixup base address by io offset */ - msm_host->ctrl_base += msm_host->cfg_hnd->cfg->io_offset; + msm_host->ctrl_base += cfg->io_offset; - ret = dsi_regulator_init(msm_host); - if (ret) { - pr_err("%s: regulator init failed\n", __func__); + ret = devm_regulator_bulk_get_const(&pdev->dev, cfg->num_regulators, + cfg->regulator_data, + &msm_host->supplies); + if (ret) goto fail; - } ret = dsi_clk_init(msm_host); if (ret) { @@ -2126,7 +2029,6 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) /* setup workqueue */ msm_host->workqueue = alloc_ordered_workqueue("dsi_drm_work", 0); INIT_WORK(&msm_host->err_work, dsi_err_worker); - INIT_WORK(&msm_host->hpd_work, dsi_hpd_worker); msm_dsi->id = msm_host->id; @@ -2159,23 +2061,9 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host, { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd; - struct drm_panel *panel; int ret; msm_host->dev = dev; - panel = msm_dsi_host_get_panel(&msm_host->base); - - if (!IS_ERR(panel) && panel->dsc) { - struct msm_display_dsc_config *dsc = msm_host->dsc; - - if (!dsc) { - dsc = devm_kzalloc(&msm_host->pdev->dev, sizeof(*dsc), GFP_KERNEL); - if (!dsc) - return -ENOMEM; - dsc->drm = panel->dsc; - msm_host->dsc = dsc; - } - } ret = cfg_hnd->ops->tx_buf_alloc(msm_host, SZ_4K); if (ret) { @@ -2556,7 +2444,8 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host, msm_dsi_sfpb_config(msm_host, true); - ret = dsi_host_regulator_enable(msm_host); + ret = regulator_bulk_enable(msm_host->cfg_hnd->cfg->num_regulators, + msm_host->supplies); if (ret) { pr_err("%s:Failed to enable vregs.ret=%d\n", __func__, ret); @@ -2596,7 +2485,8 @@ fail_disable_clk: cfg_hnd->ops->link_clk_disable(msm_host); pm_runtime_put(&msm_host->pdev->dev); fail_disable_reg: - dsi_host_regulator_disable(msm_host); + regulator_bulk_disable(msm_host->cfg_hnd->cfg->num_regulators, + msm_host->supplies); unlock_ret: mutex_unlock(&msm_host->dev_mutex); return ret; @@ -2623,7 +2513,8 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host) cfg_hnd->ops->link_clk_disable(msm_host); pm_runtime_put(&msm_host->pdev->dev); - dsi_host_regulator_disable(msm_host); + regulator_bulk_disable(msm_host->cfg_hnd->cfg->num_regulators, + msm_host->supplies); msm_dsi_sfpb_config(msm_host, false); @@ -2659,45 +2550,33 @@ enum drm_mode_status msm_dsi_host_check_dsc(struct mipi_dsi_host *host, const struct drm_display_mode *mode) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); - struct msm_display_dsc_config *dsc = msm_host->dsc; + struct drm_dsc_config *dsc = msm_host->dsc; int pic_width = mode->hdisplay; int pic_height = mode->vdisplay; if (!msm_host->dsc) return MODE_OK; - if (pic_width % dsc->drm->slice_width) { + if (pic_width % dsc->slice_width) { pr_err("DSI: pic_width %d has to be multiple of slice %d\n", - pic_width, dsc->drm->slice_width); + pic_width, dsc->slice_width); return MODE_H_ILLEGAL; } - if (pic_height % dsc->drm->slice_height) { + if (pic_height % dsc->slice_height) { pr_err("DSI: pic_height %d has to be multiple of slice %d\n", - pic_height, dsc->drm->slice_height); + pic_height, dsc->slice_height); return MODE_V_ILLEGAL; } return MODE_OK; } -struct drm_panel *msm_dsi_host_get_panel(struct mipi_dsi_host *host) -{ - return of_drm_find_panel(to_msm_dsi_host(host)->device_node); -} - unsigned long msm_dsi_host_get_mode_flags(struct mipi_dsi_host *host) { return to_msm_dsi_host(host)->mode_flags; } -struct drm_bridge *msm_dsi_host_get_bridge(struct mipi_dsi_host *host) -{ - struct msm_dsi_host *msm_host = to_msm_dsi_host(host); - - return of_drm_find_bridge(msm_host->device_node); -} - void msm_dsi_host_snapshot(struct msm_disp_state *disp_state, struct mipi_dsi_host *host) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); @@ -2771,7 +2650,7 @@ void msm_dsi_host_test_pattern_en(struct mipi_dsi_host *host) DSI_TEST_PATTERN_GEN_CMD_STREAM0_TRIGGER_SW_TRIGGER); } -struct msm_display_dsc_config *msm_dsi_host_get_dsc_config(struct mipi_dsi_host *host) +struct drm_dsc_config *msm_dsi_host_get_dsc_config(struct mipi_dsi_host *host) { struct msm_dsi_host *msm_host = to_msm_dsi_host(host); diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c index cb84d185d73a..3a1417397283 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_manager.c +++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c @@ -141,14 +141,11 @@ static int enable_phy(struct msm_dsi *msm_dsi, struct msm_dsi_phy_shared_timings *shared_timings) { struct msm_dsi_phy_clk_request clk_req; - int ret; bool is_bonded_dsi = IS_BONDED_DSI(); msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_bonded_dsi); - ret = msm_dsi_phy_enable(msm_dsi->phy, &clk_req, shared_timings); - - return ret; + return msm_dsi_phy_enable(msm_dsi->phy, &clk_req, shared_timings); } static int @@ -214,39 +211,26 @@ static void dsi_mgr_phy_disable(int id) } } -struct dsi_connector { - struct drm_connector base; - int id; -}; - struct dsi_bridge { struct drm_bridge base; int id; }; -#define to_dsi_connector(x) container_of(x, struct dsi_connector, base) #define to_dsi_bridge(x) container_of(x, struct dsi_bridge, base) -static inline int dsi_mgr_connector_get_id(struct drm_connector *connector) -{ - struct dsi_connector *dsi_connector = to_dsi_connector(connector); - return dsi_connector->id; -} - static int dsi_mgr_bridge_get_id(struct drm_bridge *bridge) { struct dsi_bridge *dsi_bridge = to_dsi_bridge(bridge); return dsi_bridge->id; } -static int msm_dsi_manager_panel_init(struct drm_connector *conn, u8 id) +static void msm_dsi_manager_set_split_display(u8 id) { - struct msm_drm_private *priv = conn->dev->dev_private; - struct msm_kms *kms = priv->kms; struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct msm_dsi *other_dsi = dsi_mgr_get_other_dsi(id); + struct msm_drm_private *priv = msm_dsi->dev->dev_private; + struct msm_kms *kms = priv->kms; struct msm_dsi *master_dsi, *slave_dsi; - struct drm_panel *panel; if (IS_BONDED_DSI() && !IS_MASTER_DSI_LINK(id)) { master_dsi = other_dsi; @@ -256,89 +240,18 @@ static int msm_dsi_manager_panel_init(struct drm_connector *conn, u8 id) slave_dsi = other_dsi; } - /* - * There is only 1 panel in the global panel list for bonded DSI mode. - * Therefore slave dsi should get the drm_panel instance from master - * dsi. - */ - panel = msm_dsi_host_get_panel(master_dsi->host); - if (IS_ERR(panel)) { - DRM_ERROR("Could not find panel for %u (%ld)\n", msm_dsi->id, - PTR_ERR(panel)); - return PTR_ERR(panel); - } - - if (!panel || !IS_BONDED_DSI()) - goto out; - - drm_object_attach_property(&conn->base, - conn->dev->mode_config.tile_property, 0); + if (!msm_dsi->external_bridge || !IS_BONDED_DSI()) + return; /* * Set split display info to kms once bonded DSI panel is connected to * both hosts. */ - if (other_dsi && other_dsi->panel && kms->funcs->set_split_display) { + if (other_dsi && other_dsi->external_bridge && kms->funcs->set_split_display) { kms->funcs->set_split_display(kms, master_dsi->encoder, slave_dsi->encoder, msm_dsi_is_cmd_mode(msm_dsi)); } - -out: - msm_dsi->panel = panel; - return 0; -} - -static enum drm_connector_status dsi_mgr_connector_detect( - struct drm_connector *connector, bool force) -{ - int id = dsi_mgr_connector_get_id(connector); - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - - return msm_dsi->panel ? connector_status_connected : - connector_status_disconnected; -} - -static void dsi_mgr_connector_destroy(struct drm_connector *connector) -{ - struct dsi_connector *dsi_connector = to_dsi_connector(connector); - - DBG(""); - - drm_connector_cleanup(connector); - - kfree(dsi_connector); -} - -static int dsi_mgr_connector_get_modes(struct drm_connector *connector) -{ - int id = dsi_mgr_connector_get_id(connector); - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - struct drm_panel *panel = msm_dsi->panel; - int num; - - if (!panel) - return 0; - - /* - * In bonded DSI mode, we have one connector that can be - * attached to the drm_panel. - */ - num = drm_panel_get_modes(panel, connector); - if (!num) - return 0; - - return num; -} - -static struct drm_encoder * -dsi_mgr_connector_best_encoder(struct drm_connector *connector) -{ - int id = dsi_mgr_connector_get_id(connector); - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - - DBG(""); - return msm_dsi_get_encoder(msm_dsi); } static void dsi_mgr_bridge_power_on(struct drm_bridge *bridge) @@ -403,7 +316,6 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; - struct drm_panel *panel = msm_dsi->panel; bool is_bonded_dsi = IS_BONDED_DSI(); int ret; @@ -418,18 +330,6 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) if (!dsi_mgr_power_on_early(bridge)) dsi_mgr_bridge_power_on(bridge); - /* Always call panel functions once, because even for dual panels, - * there is only one drm_panel instance. - */ - if (panel) { - ret = drm_panel_prepare(panel); - if (ret) { - pr_err("%s: prepare panel %d failed, %d\n", __func__, - id, ret); - goto panel_prep_fail; - } - } - ret = msm_dsi_host_enable(host); if (ret) { pr_err("%s: enable host %d failed, %d\n", __func__, id, ret); @@ -449,9 +349,6 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge) host1_en_fail: msm_dsi_host_disable(host); host_en_fail: - if (panel) - drm_panel_unprepare(panel); -panel_prep_fail: return; } @@ -469,62 +366,12 @@ void msm_dsi_manager_tpg_enable(void) } } -static void dsi_mgr_bridge_enable(struct drm_bridge *bridge) -{ - int id = dsi_mgr_bridge_get_id(bridge); - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - struct drm_panel *panel = msm_dsi->panel; - bool is_bonded_dsi = IS_BONDED_DSI(); - int ret; - - DBG("id=%d", id); - if (!msm_dsi_device_connected(msm_dsi)) - return; - - /* Do nothing with the host if it is slave-DSI in case of bonded DSI */ - if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id)) - return; - - if (panel) { - ret = drm_panel_enable(panel); - if (ret) { - pr_err("%s: enable panel %d failed, %d\n", __func__, id, - ret); - } - } -} - -static void dsi_mgr_bridge_disable(struct drm_bridge *bridge) -{ - int id = dsi_mgr_bridge_get_id(bridge); - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - struct drm_panel *panel = msm_dsi->panel; - bool is_bonded_dsi = IS_BONDED_DSI(); - int ret; - - DBG("id=%d", id); - if (!msm_dsi_device_connected(msm_dsi)) - return; - - /* Do nothing with the host if it is slave-DSI in case of bonded DSI */ - if (is_bonded_dsi && !IS_MASTER_DSI_LINK(id)) - return; - - if (panel) { - ret = drm_panel_disable(panel); - if (ret) - pr_err("%s: Panel %d OFF failed, %d\n", __func__, id, - ret); - } -} - static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) { int id = dsi_mgr_bridge_get_id(bridge); struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct msm_dsi *msm_dsi1 = dsi_mgr_get_dsi(DSI_1); struct mipi_dsi_host *host = msm_dsi->host; - struct drm_panel *panel = msm_dsi->panel; bool is_bonded_dsi = IS_BONDED_DSI(); int ret; @@ -551,13 +398,6 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge) pr_err("%s: host1 disable failed, %d\n", __func__, ret); } - if (panel) { - ret = drm_panel_unprepare(panel); - if (ret) - pr_err("%s: Panel %d unprepare failed,%d\n", __func__, - id, ret); - } - msm_dsi_host_disable_irq(host); if (is_bonded_dsi && msm_dsi1) msm_dsi_host_disable_irq(msm_dsi1->host); @@ -614,76 +454,13 @@ static enum drm_mode_status dsi_mgr_bridge_mode_valid(struct drm_bridge *bridge, return msm_dsi_host_check_dsc(host, mode); } -static const struct drm_connector_funcs dsi_mgr_connector_funcs = { - .detect = dsi_mgr_connector_detect, - .fill_modes = drm_helper_probe_single_connector_modes, - .destroy = dsi_mgr_connector_destroy, - .reset = drm_atomic_helper_connector_reset, - .atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state, - .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, -}; - -static const struct drm_connector_helper_funcs dsi_mgr_conn_helper_funcs = { - .get_modes = dsi_mgr_connector_get_modes, - .best_encoder = dsi_mgr_connector_best_encoder, -}; - static const struct drm_bridge_funcs dsi_mgr_bridge_funcs = { .pre_enable = dsi_mgr_bridge_pre_enable, - .enable = dsi_mgr_bridge_enable, - .disable = dsi_mgr_bridge_disable, .post_disable = dsi_mgr_bridge_post_disable, .mode_set = dsi_mgr_bridge_mode_set, .mode_valid = dsi_mgr_bridge_mode_valid, }; -/* initialize connector when we're connected to a drm_panel */ -struct drm_connector *msm_dsi_manager_connector_init(u8 id) -{ - struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); - struct drm_connector *connector = NULL; - struct dsi_connector *dsi_connector; - int ret; - - dsi_connector = kzalloc(sizeof(*dsi_connector), GFP_KERNEL); - if (!dsi_connector) - return ERR_PTR(-ENOMEM); - - dsi_connector->id = id; - - connector = &dsi_connector->base; - - ret = drm_connector_init(msm_dsi->dev, connector, - &dsi_mgr_connector_funcs, DRM_MODE_CONNECTOR_DSI); - if (ret) - return ERR_PTR(ret); - - drm_connector_helper_add(connector, &dsi_mgr_conn_helper_funcs); - - /* Enable HPD to let hpd event is handled - * when panel is attached to the host. - */ - connector->polled = DRM_CONNECTOR_POLL_HPD; - - /* Display driver doesn't support interlace now. */ - connector->interlace_allowed = 0; - connector->doublescan_allowed = 0; - - drm_connector_attach_encoder(connector, msm_dsi->encoder); - - ret = msm_dsi_manager_panel_init(connector, id); - if (ret) { - DRM_DEV_ERROR(msm_dsi->dev->dev, "init panel failed %d\n", ret); - goto fail; - } - - return connector; - -fail: - connector->funcs->destroy(connector); - return ERR_PTR(ret); -} - /* initialize bridge */ struct drm_bridge *msm_dsi_manager_bridge_init(u8 id) { @@ -722,18 +499,21 @@ fail: return ERR_PTR(ret); } -struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id) +int msm_dsi_manager_ext_bridge_init(u8 id) { struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id); struct drm_device *dev = msm_dsi->dev; - struct drm_connector *connector; struct drm_encoder *encoder; struct drm_bridge *int_bridge, *ext_bridge; int ret; int_bridge = msm_dsi->bridge; - ext_bridge = msm_dsi->external_bridge = - msm_dsi_host_get_bridge(msm_dsi->host); + ext_bridge = devm_drm_of_get_bridge(&msm_dsi->pdev->dev, + msm_dsi->pdev->dev.of_node, 1, 0); + if (IS_ERR(ext_bridge)) + return PTR_ERR(ext_bridge); + + msm_dsi->external_bridge = ext_bridge; encoder = msm_dsi->encoder; @@ -745,36 +525,32 @@ struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id) ret = drm_bridge_attach(encoder, ext_bridge, int_bridge, DRM_BRIDGE_ATTACH_NO_CONNECTOR); if (ret == -EINVAL) { - struct drm_connector *connector; - struct list_head *connector_list; - - /* link the internal dsi bridge to the external bridge */ - drm_bridge_attach(encoder, ext_bridge, int_bridge, 0); - /* - * we need the drm_connector created by the external bridge - * driver (or someone else) to feed it to our driver's - * priv->connector[] list, mainly for msm_fbdev_init() + * link the internal dsi bridge to the external bridge, + * connector is created by the next bridge. */ - connector_list = &dev->mode_config.connector_list; + ret = drm_bridge_attach(encoder, ext_bridge, int_bridge, 0); + if (ret < 0) + return ret; + } else { + struct drm_connector *connector; - list_for_each_entry(connector, connector_list, head) { - if (drm_connector_has_possible_encoder(connector, encoder)) - return connector; + /* We are in charge of the connector, create one now. */ + connector = drm_bridge_connector_init(dev, encoder); + if (IS_ERR(connector)) { + DRM_ERROR("Unable to create bridge connector\n"); + return PTR_ERR(connector); } - return ERR_PTR(-ENODEV); - } - - connector = drm_bridge_connector_init(dev, encoder); - if (IS_ERR(connector)) { - DRM_ERROR("Unable to create bridge connector\n"); - return ERR_CAST(connector); + ret = drm_connector_attach_encoder(connector, encoder); + if (ret < 0) + return ret; } - drm_connector_attach_encoder(connector, encoder); + /* The pipeline is ready, ping encoders if necessary */ + msm_dsi_manager_set_split_display(id); - return connector; + return 0; } void msm_dsi_manager_bridge_destroy(struct drm_bridge *bridge) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index a39de3bdc7fa..7fc0975cb869 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -347,7 +347,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, } else { timing->shared_timings.clk_pre = linear_inter(tmax, tmin, pcnt2, 0, false); - timing->shared_timings.clk_pre_inc_by_2 = 0; + timing->shared_timings.clk_pre_inc_by_2 = 0; } timing->ta_go = 3; @@ -507,82 +507,6 @@ int msm_dsi_cphy_timing_calc_v4(struct msm_dsi_dphy_timing *timing, return 0; } -static int dsi_phy_regulator_init(struct msm_dsi_phy *phy) -{ - struct regulator_bulk_data *s = phy->supplies; - const struct dsi_reg_entry *regs = phy->cfg->reg_cfg.regs; - struct device *dev = &phy->pdev->dev; - int num = phy->cfg->reg_cfg.num; - int i, ret; - - for (i = 0; i < num; i++) - s[i].supply = regs[i].name; - - ret = devm_regulator_bulk_get(dev, num, s); - if (ret < 0) { - if (ret != -EPROBE_DEFER) { - DRM_DEV_ERROR(dev, - "%s: failed to init regulator, ret=%d\n", - __func__, ret); - } - - return ret; - } - - return 0; -} - -static void dsi_phy_regulator_disable(struct msm_dsi_phy *phy) -{ - struct regulator_bulk_data *s = phy->supplies; - const struct dsi_reg_entry *regs = phy->cfg->reg_cfg.regs; - int num = phy->cfg->reg_cfg.num; - int i; - - DBG(""); - for (i = num - 1; i >= 0; i--) - if (regs[i].disable_load >= 0) - regulator_set_load(s[i].consumer, regs[i].disable_load); - - regulator_bulk_disable(num, s); -} - -static int dsi_phy_regulator_enable(struct msm_dsi_phy *phy) -{ - struct regulator_bulk_data *s = phy->supplies; - const struct dsi_reg_entry *regs = phy->cfg->reg_cfg.regs; - struct device *dev = &phy->pdev->dev; - int num = phy->cfg->reg_cfg.num; - int ret, i; - - DBG(""); - for (i = 0; i < num; i++) { - if (regs[i].enable_load >= 0) { - ret = regulator_set_load(s[i].consumer, - regs[i].enable_load); - if (ret < 0) { - DRM_DEV_ERROR(dev, - "regulator %d set op mode failed, %d\n", - i, ret); - goto fail; - } - } - } - - ret = regulator_bulk_enable(num, s); - if (ret < 0) { - DRM_DEV_ERROR(dev, "regulator enable failed, %d\n", ret); - goto fail; - } - - return 0; - -fail: - for (i--; i >= 0; i--) - regulator_set_load(s[i].consumer, regs[i].disable_load); - return ret; -} - static int dsi_phy_enable_resource(struct msm_dsi_phy *phy) { struct device *dev = &phy->pdev->dev; @@ -697,12 +621,9 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) phy->pdev = pdev; phy->id = dsi_phy_get_id(phy); - if (phy->id < 0) { - ret = phy->id; - DRM_DEV_ERROR(dev, "%s: couldn't identify PHY index, %d\n", - __func__, ret); - goto fail; - } + if (phy->id < 0) + return dev_err_probe(dev, phy->id, + "Couldn't identify PHY index\n"); phy->regulator_ldo_mode = of_property_read_bool(dev->of_node, "qcom,dsi-phy-regulator-ldo-mode"); @@ -710,86 +631,71 @@ static int dsi_phy_driver_probe(struct platform_device *pdev) phy->cphy_mode = (phy_type == PHY_TYPE_CPHY); phy->base = msm_ioremap_size(pdev, "dsi_phy", &phy->base_size); - if (IS_ERR(phy->base)) { - DRM_DEV_ERROR(dev, "%s: failed to map phy base\n", __func__); - ret = -ENOMEM; - goto fail; - } + if (IS_ERR(phy->base)) + return dev_err_probe(dev, PTR_ERR(phy->base), + "Failed to map phy base\n"); phy->pll_base = msm_ioremap_size(pdev, "dsi_pll", &phy->pll_size); - if (IS_ERR(phy->pll_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map pll base\n", __func__); - ret = -ENOMEM; - goto fail; - } + if (IS_ERR(phy->pll_base)) + return dev_err_probe(dev, PTR_ERR(phy->pll_base), + "Failed to map pll base\n"); if (phy->cfg->has_phy_lane) { phy->lane_base = msm_ioremap_size(pdev, "dsi_phy_lane", &phy->lane_size); - if (IS_ERR(phy->lane_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy lane base\n", __func__); - ret = -ENOMEM; - goto fail; - } + if (IS_ERR(phy->lane_base)) + return dev_err_probe(dev, PTR_ERR(phy->lane_base), + "Failed to map phy lane base\n"); } if (phy->cfg->has_phy_regulator) { phy->reg_base = msm_ioremap_size(pdev, "dsi_phy_regulator", &phy->reg_size); - if (IS_ERR(phy->reg_base)) { - DRM_DEV_ERROR(&pdev->dev, "%s: failed to map phy regulator base\n", __func__); - ret = -ENOMEM; - goto fail; - } + if (IS_ERR(phy->reg_base)) + return dev_err_probe(dev, PTR_ERR(phy->reg_base), + "Failed to map phy regulator base\n"); } if (phy->cfg->ops.parse_dt_properties) { ret = phy->cfg->ops.parse_dt_properties(phy); if (ret) - goto fail; + return ret; } - ret = dsi_phy_regulator_init(phy); + ret = devm_regulator_bulk_get_const(dev, phy->cfg->num_regulators, + phy->cfg->regulator_data, + &phy->supplies); if (ret) - goto fail; + return ret; phy->ahb_clk = msm_clk_get(pdev, "iface"); - if (IS_ERR(phy->ahb_clk)) { - DRM_DEV_ERROR(dev, "%s: Unable to get ahb clk\n", __func__); - ret = PTR_ERR(phy->ahb_clk); - goto fail; - } + if (IS_ERR(phy->ahb_clk)) + return dev_err_probe(dev, PTR_ERR(phy->ahb_clk), + "Unable to get ahb clk\n"); /* PLL init will call into clk_register which requires * register access, so we need to enable power and ahb clock. */ ret = dsi_phy_enable_resource(phy); if (ret) - goto fail; + return ret; if (phy->cfg->ops.pll_init) { ret = phy->cfg->ops.pll_init(phy); - if (ret) { - DRM_DEV_INFO(dev, - "%s: pll init failed: %d, need separate pll clk driver\n", - __func__, ret); - goto fail; - } + if (ret) + return dev_err_probe(dev, ret, + "PLL init failed; need separate clk driver\n"); } ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, phy->provided_clocks); - if (ret) { - DRM_DEV_ERROR(dev, "%s: failed to register clk provider: %d\n", __func__, ret); - goto fail; - } + if (ret) + return dev_err_probe(dev, ret, + "Failed to register clk provider\n"); dsi_phy_disable_resource(phy); platform_set_drvdata(pdev, phy); return 0; - -fail: - return ret; } static struct platform_driver dsi_phy_platform_driver = { @@ -829,7 +735,7 @@ int msm_dsi_phy_enable(struct msm_dsi_phy *phy, goto res_en_fail; } - ret = dsi_phy_regulator_enable(phy); + ret = regulator_bulk_enable(phy->cfg->num_regulators, phy->supplies); if (ret) { DRM_DEV_ERROR(dev, "%s: regulator enable failed, %d\n", __func__, ret); @@ -866,7 +772,7 @@ pll_restor_fail: if (phy->cfg->ops.disable) phy->cfg->ops.disable(phy); phy_en_fail: - dsi_phy_regulator_disable(phy); + regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); reg_en_fail: dsi_phy_disable_resource(phy); res_en_fail: @@ -880,7 +786,7 @@ void msm_dsi_phy_disable(struct msm_dsi_phy *phy) phy->cfg->ops.disable(phy); - dsi_phy_regulator_disable(phy); + regulator_bulk_disable(phy->cfg->num_regulators, phy->supplies); dsi_phy_disable_resource(phy); } diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h index dc91b43d5a38..60a99c6525b2 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h @@ -29,7 +29,8 @@ struct msm_dsi_phy_ops { }; struct msm_dsi_phy_cfg { - struct dsi_reg_config reg_cfg; + const struct regulator_bulk_data *regulator_data; + int num_regulators; struct msm_dsi_phy_ops ops; unsigned long min_pll_rate; @@ -98,7 +99,7 @@ struct msm_dsi_phy { int id; struct clk *ahb_clk; - struct regulator_bulk_data supplies[DSI_DEV_REGULATOR_MAX]; + struct regulator_bulk_data *supplies; struct msm_dsi_dphy_timing timing; const struct msm_dsi_phy_cfg *cfg; diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c index 08b015ea1b1e..27b592c776a3 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c @@ -188,19 +188,19 @@ static void dsi_pll_ssc_commit(struct dsi_pll_10nm *pll, struct dsi_pll_config * pr_debug("SSC is enabled\n"); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_STEPSIZE_LOW_1, - config->ssc_stepsize & 0xff); + config->ssc_stepsize & 0xff); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, - config->ssc_stepsize >> 8); + config->ssc_stepsize >> 8); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_PER_LOW_1, - config->ssc_div_per & 0xff); + config->ssc_div_per & 0xff); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_PER_HIGH_1, - config->ssc_div_per >> 8); + config->ssc_div_per >> 8); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_ADJPER_LOW_1, - config->ssc_adj_per & 0xff); + config->ssc_adj_per & 0xff); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_DIV_ADJPER_HIGH_1, - config->ssc_adj_per >> 8); + config->ssc_adj_per >> 8); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_SSC_CONTROL, - SSC_EN | (config->ssc_center ? SSC_CENTER : 0)); + SSC_EN | (config->ssc_center ? SSC_CENTER : 0)); } } @@ -215,16 +215,19 @@ static void dsi_pll_config_hzindep_reg(struct dsi_pll_10nm *pll) dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FEEDBACK_DIVIDER, 0x4e); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CALIBRATION_SETTINGS, 0x40); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_BAND_SEL_CAL_SETTINGS_THREE, - 0xba); - dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, 0x0c); + 0xba); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FREQ_DETECT_SETTINGS_ONE, + 0x0c); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_OUTDIV, 0x00); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CORE_OVERRIDE, 0x00); - dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, 0x08); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_DIGITAL_TIMERS_TWO, + 0x08); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_PROP_GAIN_RATE_1, 0x08); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_BAND_SET_RATE_1, 0xc0); - dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, 0xfa); + dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_INT_GAIN_IFILT_BAND_1, + 0xfa); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_FL_INT_GAIN_PFILT_BAND_1, - 0x4c); + 0x4c); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_OVERRIDE, 0x80); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PFILT, 0x29); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_IFILT, 0x3f); @@ -236,18 +239,18 @@ static void dsi_pll_commit(struct dsi_pll_10nm *pll, struct dsi_pll_config *conf dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_DECIMAL_DIV_START_1, - config->decimal_div_start); + config->decimal_div_start); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_LOW_1, - config->frac_div_start & 0xff); + config->frac_div_start & 0xff); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_MID_1, - (config->frac_div_start & 0xff00) >> 8); + (config->frac_div_start & 0xff00) >> 8); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_FRAC_DIV_START_HIGH_1, - (config->frac_div_start & 0x30000) >> 16); + (config->frac_div_start & 0x30000) >> 16); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCKDET_RATE_1, 64); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CMODE, 0x10); dsi_phy_write(base + REG_DSI_10nm_PHY_PLL_CLOCK_INVERTERS, - config->pll_clock_inverters); + config->pll_clock_inverters); } static int dsi_pll_10nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, @@ -306,7 +309,7 @@ static void dsi_pll_disable_pll_bias(struct dsi_pll_10nm *pll) dsi_phy_write(pll->phy->pll_base + REG_DSI_10nm_PHY_PLL_SYSTEM_MUXES, 0); dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0, - data & ~BIT(5)); + data & ~BIT(5)); ndelay(250); } @@ -315,7 +318,7 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_10nm *pll) u32 data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0); dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CTRL_0, - data | BIT(5)); + data | BIT(5)); dsi_phy_write(pll->phy->pll_base + REG_DSI_10nm_PHY_PLL_SYSTEM_MUXES, 0xc0); ndelay(250); } @@ -326,7 +329,7 @@ static void dsi_pll_disable_global_clk(struct dsi_pll_10nm *pll) data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, - data & ~BIT(5)); + data & ~BIT(5)); } static void dsi_pll_enable_global_clk(struct dsi_pll_10nm *pll) @@ -335,7 +338,7 @@ static void dsi_pll_enable_global_clk(struct dsi_pll_10nm *pll) data = dsi_phy_read(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); dsi_phy_write(pll->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG1, - data | BIT(5)); + data | BIT(5)); } static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) @@ -356,7 +359,7 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) /* Start PLL */ dsi_phy_write(pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_PLL_CNTRL, - 0x01); + 0x01); /* * ensure all PLL configurations are written prior to checking @@ -378,10 +381,10 @@ static int dsi_pll_10nm_vco_prepare(struct clk_hw *hw) dsi_pll_enable_global_clk(pll_10nm->slave); dsi_phy_write(pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, - 0x01); + 0x01); if (pll_10nm->slave) dsi_phy_write(pll_10nm->slave->phy->base + - REG_DSI_10nm_PHY_CMN_RBUF_CTRL, 0x01); + REG_DSI_10nm_PHY_CMN_RBUF_CTRL, 0x01); error: return rc; @@ -486,7 +489,7 @@ static void dsi_10nm_pll_save_state(struct msm_dsi_phy *phy) u32 cmn_clk_cfg0, cmn_clk_cfg1; cached->pll_out_div = dsi_phy_read(pll_10nm->phy->pll_base + - REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE); + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE); cached->pll_out_div &= 0x3; cmn_clk_cfg0 = dsi_phy_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG0); @@ -515,7 +518,7 @@ static int dsi_10nm_pll_restore_state(struct msm_dsi_phy *phy) dsi_phy_write(pll_10nm->phy->pll_base + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, val); dsi_phy_write(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG0, - cached->bit_clk_div | (cached->pix_clk_div << 4)); + cached->bit_clk_div | (cached->pix_clk_div << 4)); val = dsi_phy_read(phy_base + REG_DSI_10nm_PHY_CMN_CLK_CFG1); val &= ~0x3; @@ -571,64 +574,59 @@ static int dsi_10nm_set_usecase(struct msm_dsi_phy *phy) */ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm, struct clk_hw **provided_clocks) { - char clk_name[32], parent[32], vco_name[32]; - char parent2[32], parent3[32], parent4[32]; + char clk_name[32]; struct clk_init_data vco_init = { .parent_data = &(const struct clk_parent_data) { .fw_name = "ref", }, .num_parents = 1, - .name = vco_name, + .name = clk_name, .flags = CLK_IGNORE_UNUSED, .ops = &clk_ops_dsi_pll_10nm_vco, }; struct device *dev = &pll_10nm->phy->pdev->dev; - struct clk_hw *hw; + struct clk_hw *hw, *pll_out_div, *pll_bit, *pll_by_2_bit; + struct clk_hw *pll_post_out_div, *pclk_mux; int ret; DBG("DSI%d", pll_10nm->phy->id); - snprintf(vco_name, 32, "dsi%dvco_clk", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dvco_clk", pll_10nm->phy->id); pll_10nm->clk_hw.init = &vco_init; ret = devm_clk_hw_register(dev, &pll_10nm->clk_hw); if (ret) return ret; - snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%dvco_clk", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_out_div_clk", pll_10nm->phy->id); - hw = devm_clk_hw_register_divider(dev, clk_name, - parent, CLK_SET_RATE_PARENT, - pll_10nm->phy->pll_base + - REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, - 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_out_div = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + &pll_10nm->clk_hw, CLK_SET_RATE_PARENT, + pll_10nm->phy->pll_base + + REG_DSI_10nm_PHY_PLL_PLL_OUTDIV_RATE, + 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); + if (IS_ERR(pll_out_div)) { + ret = PTR_ERR(pll_out_div); goto fail; } - snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_bit_clk", pll_10nm->phy->id); /* BIT CLK: DIV_CTRL_3_0 */ - hw = devm_clk_hw_register_divider(dev, clk_name, parent, - CLK_SET_RATE_PARENT, - pll_10nm->phy->base + - REG_DSI_10nm_PHY_CMN_CLK_CFG0, - 0, 4, CLK_DIVIDER_ONE_BASED, - &pll_10nm->postdiv_lock); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_bit = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + pll_out_div, CLK_SET_RATE_PARENT, + pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG0, + 0, 4, CLK_DIVIDER_ONE_BASED, &pll_10nm->postdiv_lock); + if (IS_ERR(pll_bit)) { + ret = PTR_ERR(pll_bit); goto fail; } - snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_phy_pll_out_byteclk", pll_10nm->phy->id); /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, - CLK_SET_RATE_PARENT, 1, 8); + hw = devm_clk_hw_register_fixed_factor_parent_hw(dev, clk_name, + pll_bit, CLK_SET_RATE_PARENT, 1, 8); if (IS_ERR(hw)) { ret = PTR_ERR(hw); goto fail; @@ -636,52 +634,45 @@ static int pll_10nm_register(struct dsi_pll_10nm *pll_10nm, struct clk_hw **prov provided_clocks[DSI_BYTE_PLL_CLK] = hw; - snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_by_2_bit_clk", pll_10nm->phy->id); - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 2); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_by_2_bit = devm_clk_hw_register_fixed_factor_parent_hw(dev, + clk_name, pll_bit, 0, 1, 2); + if (IS_ERR(pll_by_2_bit)) { + ret = PTR_ERR(pll_by_2_bit); goto fail; } - snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_post_out_div_clk", pll_10nm->phy->id); - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 4); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_post_out_div = devm_clk_hw_register_fixed_factor_parent_hw(dev, + clk_name, pll_out_div, 0, 1, 4); + if (IS_ERR(pll_post_out_div)) { + ret = PTR_ERR(pll_post_out_div); goto fail; } - snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_10nm->phy->id); - snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_10nm->phy->id); - snprintf(parent3, 32, "dsi%d_pll_out_div_clk", pll_10nm->phy->id); - snprintf(parent4, 32, "dsi%d_pll_post_out_div_clk", pll_10nm->phy->id); - - hw = devm_clk_hw_register_mux(dev, clk_name, - ((const char *[]){ - parent, parent2, parent3, parent4 - }), 4, 0, pll_10nm->phy->base + - REG_DSI_10nm_PHY_CMN_CLK_CFG1, - 0, 2, 0, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pclk_mux", pll_10nm->phy->id); + + pclk_mux = devm_clk_hw_register_mux_parent_hws(dev, clk_name, + ((const struct clk_hw *[]){ + pll_bit, + pll_by_2_bit, + pll_out_div, + pll_post_out_div, + }), 4, 0, pll_10nm->phy->base + + REG_DSI_10nm_PHY_CMN_CLK_CFG1, 0, 2, 0, NULL); + if (IS_ERR(pclk_mux)) { + ret = PTR_ERR(pclk_mux); goto fail; } - snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_10nm->phy->id); - snprintf(parent, 32, "dsi%d_pclk_mux", pll_10nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_phy_pll_out_dsiclk", pll_10nm->phy->id); /* PIX CLK DIV : DIV_CTRL_7_4*/ - hw = devm_clk_hw_register_divider(dev, clk_name, parent, - 0, pll_10nm->phy->base + - REG_DSI_10nm_PHY_CMN_CLK_CFG0, - 4, 4, CLK_DIVIDER_ONE_BASED, - &pll_10nm->postdiv_lock); + hw = devm_clk_hw_register_divider_parent_hw(dev, clk_name, pclk_mux, + 0, pll_10nm->phy->base + REG_DSI_10nm_PHY_CMN_CLK_CFG0, + 4, 4, CLK_DIVIDER_ONE_BASED, &pll_10nm->postdiv_lock); if (IS_ERR(hw)) { ret = PTR_ERR(hw); goto fail; @@ -1028,14 +1019,14 @@ static int dsi_10nm_phy_parse_dt(struct msm_dsi_phy *phy) return 0; } +static const struct regulator_bulk_data dsi_phy_10nm_regulators[] = { + { .supply = "vdds", .init_load_uA = 36000 }, +}; + const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vdds", 36000, 32}, - }, - }, + .regulator_data = dsi_phy_10nm_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_10nm_regulators), .ops = { .enable = dsi_10nm_phy_enable, .disable = dsi_10nm_phy_disable, @@ -1052,12 +1043,8 @@ const struct msm_dsi_phy_cfg dsi_phy_10nm_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_10nm_8998_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vdds", 36000, 32}, - }, - }, + .regulator_data = dsi_phy_10nm_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_10nm_regulators), .ops = { .enable = dsi_10nm_phy_enable, .disable = dsi_10nm_phy_disable, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c index 8199c53567f4..0f8f4ca46429 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c @@ -711,7 +711,7 @@ static int dsi_14nm_pll_restore_state(struct msm_dsi_phy *phy) cached_state->vco_rate, 0); if (ret) { DRM_DEV_ERROR(&pll_14nm->phy->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); + "restore vco rate failed. ret=%d\n", ret); return ret; } @@ -764,14 +764,14 @@ static int dsi_14nm_set_usecase(struct msm_dsi_phy *phy) static struct clk_hw *pll_14nm_postdiv_register(struct dsi_pll_14nm *pll_14nm, const char *name, - const char *parent_name, + const struct clk_hw *parent_hw, unsigned long flags, u8 shift) { struct dsi_pll_14nm_postdiv *pll_postdiv; struct device *dev = &pll_14nm->phy->pdev->dev; struct clk_init_data postdiv_init = { - .parent_names = (const char *[]) { parent_name }, + .parent_hws = (const struct clk_hw *[]) { parent_hw }, .num_parents = 1, .name = name, .flags = flags, @@ -800,72 +800,70 @@ static struct clk_hw *pll_14nm_postdiv_register(struct dsi_pll_14nm *pll_14nm, static int pll_14nm_register(struct dsi_pll_14nm *pll_14nm, struct clk_hw **provided_clocks) { - char clk_name[32], parent[32], vco_name[32]; + char clk_name[32]; struct clk_init_data vco_init = { .parent_data = &(const struct clk_parent_data) { .fw_name = "ref", }, .num_parents = 1, - .name = vco_name, + .name = clk_name, .flags = CLK_IGNORE_UNUSED, .ops = &clk_ops_dsi_pll_14nm_vco, }; struct device *dev = &pll_14nm->phy->pdev->dev; - struct clk_hw *hw; + struct clk_hw *hw, *n1_postdiv, *n1_postdivby2; int ret; DBG("DSI%d", pll_14nm->phy->id); - snprintf(vco_name, 32, "dsi%dvco_clk", pll_14nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dvco_clk", pll_14nm->phy->id); pll_14nm->clk_hw.init = &vco_init; ret = devm_clk_hw_register(dev, &pll_14nm->clk_hw); if (ret) return ret; - snprintf(clk_name, 32, "dsi%dn1_postdiv_clk", pll_14nm->phy->id); - snprintf(parent, 32, "dsi%dvco_clk", pll_14nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dn1_postdiv_clk", pll_14nm->phy->id); /* N1 postdiv, bits 0-3 in REG_DSI_14nm_PHY_CMN_CLK_CFG0 */ - hw = pll_14nm_postdiv_register(pll_14nm, clk_name, parent, - CLK_SET_RATE_PARENT, 0); - if (IS_ERR(hw)) - return PTR_ERR(hw); + n1_postdiv = pll_14nm_postdiv_register(pll_14nm, clk_name, + &pll_14nm->clk_hw, CLK_SET_RATE_PARENT, 0); + if (IS_ERR(n1_postdiv)) + return PTR_ERR(n1_postdiv); - snprintf(clk_name, 32, "dsi%dpllbyte", pll_14nm->phy->id); - snprintf(parent, 32, "dsi%dn1_postdiv_clk", pll_14nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dpllbyte", pll_14nm->phy->id); /* DSI Byte clock = VCO_CLK / N1 / 8 */ - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, - CLK_SET_RATE_PARENT, 1, 8); + hw = devm_clk_hw_register_fixed_factor_parent_hw(dev, clk_name, + n1_postdiv, CLK_SET_RATE_PARENT, 1, 8); if (IS_ERR(hw)) return PTR_ERR(hw); provided_clocks[DSI_BYTE_PLL_CLK] = hw; - snprintf(clk_name, 32, "dsi%dn1_postdivby2_clk", pll_14nm->phy->id); - snprintf(parent, 32, "dsi%dn1_postdiv_clk", pll_14nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dn1_postdivby2_clk", pll_14nm->phy->id); /* * Skip the mux for now, force DSICLK_SEL to 1, Add a /2 divider * on the way. Don't let it set parent. */ - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 1, 2); - if (IS_ERR(hw)) - return PTR_ERR(hw); + n1_postdivby2 = devm_clk_hw_register_fixed_factor_parent_hw(dev, + clk_name, n1_postdiv, 0, 1, 2); + if (IS_ERR(n1_postdivby2)) + return PTR_ERR(n1_postdivby2); - snprintf(clk_name, 32, "dsi%dpll", pll_14nm->phy->id); - snprintf(parent, 32, "dsi%dn1_postdivby2_clk", pll_14nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dpll", pll_14nm->phy->id); /* DSI pixel clock = VCO_CLK / N1 / 2 / N2 * This is the output of N2 post-divider, bits 4-7 in * REG_DSI_14nm_PHY_CMN_CLK_CFG0. Don't let it set parent. */ - hw = pll_14nm_postdiv_register(pll_14nm, clk_name, parent, 0, 4); + hw = pll_14nm_postdiv_register(pll_14nm, clk_name, n1_postdivby2, + 0, 4); if (IS_ERR(hw)) return PTR_ERR(hw); - provided_clocks[DSI_PIXEL_PLL_CLK] = hw; + provided_clocks[DSI_PIXEL_PLL_CLK] = hw; return 0; } @@ -952,7 +950,8 @@ static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, if (msm_dsi_dphy_timing_calc_v2(timing, clk_req)) { DRM_DEV_ERROR(&phy->pdev->dev, - "%s: D-PHY timing calculation failed\n", __func__); + "%s: D-PHY timing calculation failed\n", + __func__); return -EINVAL; } @@ -1005,7 +1004,7 @@ static int dsi_14nm_phy_enable(struct msm_dsi_phy *phy, ret = dsi_14nm_set_usecase(phy); if (ret) { DRM_DEV_ERROR(&phy->pdev->dev, "%s: set pll usecase failed, %d\n", - __func__, ret); + __func__, ret); return ret; } @@ -1024,14 +1023,18 @@ static void dsi_14nm_phy_disable(struct msm_dsi_phy *phy) wmb(); } +static const struct regulator_bulk_data dsi_phy_14nm_17mA_regulators[] = { + { .supply = "vcca", .init_load_uA = 17000 }, +}; + +static const struct regulator_bulk_data dsi_phy_14nm_73p4mA_regulators[] = { + { .supply = "vcca", .init_load_uA = 73400 }, +}; + const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vcca", 17000, 32}, - }, - }, + .regulator_data = dsi_phy_14nm_17mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_14nm_17mA_regulators), .ops = { .enable = dsi_14nm_phy_enable, .disable = dsi_14nm_phy_disable, @@ -1047,12 +1050,8 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vcca", 73400, 32}, - }, - }, + .regulator_data = dsi_phy_14nm_73p4mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_14nm_73p4mA_regulators), .ops = { .enable = dsi_14nm_phy_enable, .disable = dsi_14nm_phy_disable, @@ -1068,12 +1067,8 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_660_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vcca", 17000, 32}, - }, - }, + .regulator_data = dsi_phy_14nm_17mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_14nm_17mA_regulators), .ops = { .enable = dsi_14nm_phy_enable, .disable = dsi_14nm_phy_disable, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c index ee7c418a1c29..c9752b991744 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_20nm.c @@ -129,15 +129,15 @@ static void dsi_20nm_phy_disable(struct msm_dsi_phy *phy) dsi_20nm_phy_regulator_ctrl(phy, false); } +static const struct regulator_bulk_data dsi_phy_20nm_regulators[] = { + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ + { .supply = "vcca", .init_load_uA = 10000 }, /* 1.0 V */ +}; + const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs = { .has_phy_regulator = true, - .reg_cfg = { - .num = 2, - .regs = { - {"vddio", 100000, 100}, /* 1.8 V */ - {"vcca", 10000, 100}, /* 1.0 V */ - }, - }, + .regulator_data = dsi_phy_20nm_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_20nm_regulators), .ops = { .enable = dsi_20nm_phy_enable, .disable = dsi_20nm_phy_disable, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c index 48eab80b548e..4c1bf55c5f38 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c @@ -104,7 +104,7 @@ static void pll_28nm_software_reset(struct dsi_pll_28nm *pll_28nm) * reset bit off and back on. */ dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_TEST_CFG, - DSI_28nm_PHY_PLL_TEST_CFG_PLL_SW_RESET, 1); + DSI_28nm_PHY_PLL_TEST_CFG_PLL_SW_RESET, 1); dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_TEST_CFG, 0x00, 1); } @@ -201,9 +201,9 @@ static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate, dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG1, sdm_cfg1); dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG2, - DSI_28nm_PHY_PLL_SDM_CFG2_FREQ_SEED_7_0(sdm_cfg2)); + DSI_28nm_PHY_PLL_SDM_CFG2_FREQ_SEED_7_0(sdm_cfg2)); dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG3, - DSI_28nm_PHY_PLL_SDM_CFG3_FREQ_SEED_15_8(sdm_cfg3)); + DSI_28nm_PHY_PLL_SDM_CFG3_FREQ_SEED_15_8(sdm_cfg3)); dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_SDM_CFG4, 0x00); /* Add hardware recommended delay for correct PLL configuration */ @@ -316,12 +316,12 @@ static int _dsi_pll_28nm_vco_prepare_hpm(struct dsi_pll_28nm *pll_28nm) for (i = 0; i < 2; i++) { /* DSI Uniphy lock detect setting */ dsi_phy_write_udelay(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, - 0x0c, 100); + 0x0c, 100); dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_LKDET_CFG2, 0x0d); /* poll for PLL ready status */ - locked = pll_28nm_poll_for_ready(pll_28nm, - max_reads, timeout_us); + locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, + timeout_us); if (locked) break; @@ -508,28 +508,28 @@ static int dsi_28nm_pll_restore_state(struct msm_dsi_phy *phy) } dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG, - cached_state->postdiv3); + cached_state->postdiv3); dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, - cached_state->postdiv1); + cached_state->postdiv1); dsi_phy_write(base + REG_DSI_28nm_PHY_PLL_VREG_CFG, - cached_state->byte_mux); + cached_state->byte_mux); return 0; } static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **provided_clocks) { - char clk_name[32], parent1[32], parent2[32], vco_name[32]; + char clk_name[32]; struct clk_init_data vco_init = { .parent_data = &(const struct clk_parent_data) { .fw_name = "ref", .name = "xo", }, .num_parents = 1, - .name = vco_name, + .name = clk_name, .flags = CLK_IGNORE_UNUSED, }; struct device *dev = &pll_28nm->phy->pdev->dev; - struct clk_hw *hw; + struct clk_hw *hw, *analog_postdiv, *indirect_path_div2, *byte_mux; int ret; DBG("%d", pll_28nm->phy->id); @@ -539,55 +539,49 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov else vco_init.ops = &clk_ops_dsi_pll_28nm_vco_hpm; - snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dvco_clk", pll_28nm->phy->id); pll_28nm->clk_hw.init = &vco_init; ret = devm_clk_hw_register(dev, &pll_28nm->clk_hw); if (ret) return ret; - snprintf(clk_name, 32, "dsi%danalog_postdiv_clk", pll_28nm->phy->id); - snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->phy->id); - hw = devm_clk_hw_register_divider(dev, clk_name, - parent1, CLK_SET_RATE_PARENT, + snprintf(clk_name, sizeof(clk_name), "dsi%danalog_postdiv_clk", pll_28nm->phy->id); + analog_postdiv = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + &pll_28nm->clk_hw, CLK_SET_RATE_PARENT, pll_28nm->phy->pll_base + - REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, + REG_DSI_28nm_PHY_PLL_POSTDIV1_CFG, 0, 4, 0, NULL); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - snprintf(clk_name, 32, "dsi%dindirect_path_div2_clk", pll_28nm->phy->id); - snprintf(parent1, 32, "dsi%danalog_postdiv_clk", pll_28nm->phy->id); - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, - parent1, CLK_SET_RATE_PARENT, - 1, 2); - if (IS_ERR(hw)) - return PTR_ERR(hw); - - snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id); - snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->phy->id); - hw = devm_clk_hw_register_divider(dev, clk_name, - parent1, 0, pll_28nm->phy->pll_base + + if (IS_ERR(analog_postdiv)) + return PTR_ERR(analog_postdiv); + + snprintf(clk_name, sizeof(clk_name), "dsi%dindirect_path_div2_clk", pll_28nm->phy->id); + indirect_path_div2 = devm_clk_hw_register_fixed_factor_parent_hw(dev, + clk_name, analog_postdiv, CLK_SET_RATE_PARENT, 1, 2); + if (IS_ERR(indirect_path_div2)) + return PTR_ERR(indirect_path_div2); + + snprintf(clk_name, sizeof(clk_name), "dsi%dpll", pll_28nm->phy->id); + hw = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + &pll_28nm->clk_hw, 0, pll_28nm->phy->pll_base + REG_DSI_28nm_PHY_PLL_POSTDIV3_CFG, - 0, 8, 0, NULL); + 0, 8, 0, NULL); if (IS_ERR(hw)) return PTR_ERR(hw); provided_clocks[DSI_PIXEL_PLL_CLK] = hw; - snprintf(clk_name, 32, "dsi%dbyte_mux", pll_28nm->phy->id); - snprintf(parent1, 32, "dsi%dvco_clk", pll_28nm->phy->id); - snprintf(parent2, 32, "dsi%dindirect_path_div2_clk", pll_28nm->phy->id); - hw = devm_clk_hw_register_mux(dev, clk_name, - ((const char *[]){ - parent1, parent2 + snprintf(clk_name, sizeof(clk_name), "dsi%dbyte_mux", pll_28nm->phy->id); + byte_mux = devm_clk_hw_register_mux_parent_hws(dev, clk_name, + ((const struct clk_hw *[]){ + &pll_28nm->clk_hw, + indirect_path_div2, }), 2, CLK_SET_RATE_PARENT, pll_28nm->phy->pll_base + - REG_DSI_28nm_PHY_PLL_VREG_CFG, 1, 1, 0, NULL); - if (IS_ERR(hw)) - return PTR_ERR(hw); + REG_DSI_28nm_PHY_PLL_VREG_CFG, 1, 1, 0, NULL); + if (IS_ERR(byte_mux)) + return PTR_ERR(byte_mux); - snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id); - snprintf(parent1, 32, "dsi%dbyte_mux", pll_28nm->phy->id); - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, - parent1, CLK_SET_RATE_PARENT, 1, 4); + snprintf(clk_name, sizeof(clk_name), "dsi%dpllbyte", pll_28nm->phy->id); + hw = devm_clk_hw_register_fixed_factor_parent_hw(dev, clk_name, + byte_mux, CLK_SET_RATE_PARENT, 1, 4); if (IS_ERR(hw)) return PTR_ERR(hw); provided_clocks[DSI_BYTE_PLL_CLK] = hw; @@ -627,31 +621,31 @@ static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy, void __iomem *base = phy->base; dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_0, - DSI_28nm_PHY_TIMING_CTRL_0_CLK_ZERO(timing->clk_zero)); + DSI_28nm_PHY_TIMING_CTRL_0_CLK_ZERO(timing->clk_zero)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_1, - DSI_28nm_PHY_TIMING_CTRL_1_CLK_TRAIL(timing->clk_trail)); + DSI_28nm_PHY_TIMING_CTRL_1_CLK_TRAIL(timing->clk_trail)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_2, - DSI_28nm_PHY_TIMING_CTRL_2_CLK_PREPARE(timing->clk_prepare)); + DSI_28nm_PHY_TIMING_CTRL_2_CLK_PREPARE(timing->clk_prepare)); if (timing->clk_zero & BIT(8)) dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_3, - DSI_28nm_PHY_TIMING_CTRL_3_CLK_ZERO_8); + DSI_28nm_PHY_TIMING_CTRL_3_CLK_ZERO_8); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_4, - DSI_28nm_PHY_TIMING_CTRL_4_HS_EXIT(timing->hs_exit)); + DSI_28nm_PHY_TIMING_CTRL_4_HS_EXIT(timing->hs_exit)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_5, - DSI_28nm_PHY_TIMING_CTRL_5_HS_ZERO(timing->hs_zero)); + DSI_28nm_PHY_TIMING_CTRL_5_HS_ZERO(timing->hs_zero)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_6, - DSI_28nm_PHY_TIMING_CTRL_6_HS_PREPARE(timing->hs_prepare)); + DSI_28nm_PHY_TIMING_CTRL_6_HS_PREPARE(timing->hs_prepare)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_7, - DSI_28nm_PHY_TIMING_CTRL_7_HS_TRAIL(timing->hs_trail)); + DSI_28nm_PHY_TIMING_CTRL_7_HS_TRAIL(timing->hs_trail)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_8, - DSI_28nm_PHY_TIMING_CTRL_8_HS_RQST(timing->hs_rqst)); + DSI_28nm_PHY_TIMING_CTRL_8_HS_RQST(timing->hs_rqst)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_9, - DSI_28nm_PHY_TIMING_CTRL_9_TA_GO(timing->ta_go) | - DSI_28nm_PHY_TIMING_CTRL_9_TA_SURE(timing->ta_sure)); + DSI_28nm_PHY_TIMING_CTRL_9_TA_GO(timing->ta_go) | + DSI_28nm_PHY_TIMING_CTRL_9_TA_SURE(timing->ta_sure)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_10, - DSI_28nm_PHY_TIMING_CTRL_10_TA_GET(timing->ta_get)); + DSI_28nm_PHY_TIMING_CTRL_10_TA_GET(timing->ta_get)); dsi_phy_write(base + REG_DSI_28nm_PHY_TIMING_CTRL_11, - DSI_28nm_PHY_TIMING_CTRL_11_TRIG3_CMD(0)); + DSI_28nm_PHY_TIMING_CTRL_11_TRIG3_CMD(0)); } static void dsi_28nm_phy_regulator_enable_dcdc(struct msm_dsi_phy *phy) @@ -713,7 +707,8 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, if (msm_dsi_dphy_timing_calc(timing, clk_req)) { DRM_DEV_ERROR(&phy->pdev->dev, - "%s: D-PHY timing calculation failed\n", __func__); + "%s: D-PHY timing calculation failed\n", + __func__); return -EINVAL; } @@ -769,14 +764,14 @@ static void dsi_28nm_phy_disable(struct msm_dsi_phy *phy) wmb(); } +static const struct regulator_bulk_data dsi_phy_28nm_regulators[] = { + { .supply = "vddio", .init_load_uA = 100000 }, +}; + const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = { .has_phy_regulator = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vddio", 100000, 100}, - }, - }, + .regulator_data = dsi_phy_28nm_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_28nm_regulators), .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, @@ -792,12 +787,8 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = { .has_phy_regulator = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vddio", 100000, 100}, - }, - }, + .regulator_data = dsi_phy_28nm_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_28nm_regulators), .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, @@ -813,12 +804,8 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = { .has_phy_regulator = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vddio", 100000, 100}, /* 1.8 V */ - }, - }, + .regulator_data = dsi_phy_28nm_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_28nm_regulators), .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c index fc56cdcc9ad6..26c08047e20c 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm_8960.c @@ -104,29 +104,29 @@ static int dsi_pll_28nm_clk_set_rate(struct clk_hw *hw, unsigned long rate, fb_divider = (temp * VCO_PREF_DIV_RATIO) / val; fb_divider = fb_divider / 2 - 1; dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_1, - fb_divider & 0xff); + fb_divider & 0xff); val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2); val |= (fb_divider >> 8) & 0x07; dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_2, - val); + val); val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3); val |= (VCO_PREF_DIV_RATIO - 1) & 0x3f; dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_3, - val); + val); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_6, - 0xf); + 0xf); val = dsi_phy_read(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8); val |= 0x7 << 4; dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, - val); + val); return 0; } @@ -206,7 +206,7 @@ static int dsi_pll_28nm_vco_prepare(struct clk_hw *hw) /* enable the PLL */ dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_0, - DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE); + DSI_28nm_8960_PHY_PLL_CTRL_0_ENABLE); locked = pll_28nm_poll_for_ready(pll_28nm, max_reads, timeout_us); @@ -367,23 +367,23 @@ static int dsi_28nm_pll_restore_state(struct msm_dsi_phy *phy) cached_state->vco_rate, 0); if (ret) { DRM_DEV_ERROR(&pll_28nm->phy->pdev->dev, - "restore vco rate failed. ret=%d\n", ret); + "restore vco rate failed. ret=%d\n", ret); return ret; } dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10, - cached_state->postdiv3); + cached_state->postdiv3); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9, - cached_state->postdiv2); + cached_state->postdiv2); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_PLL_CTRL_8, - cached_state->postdiv1); + cached_state->postdiv1); return 0; } static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **provided_clocks) { - char *clk_name, *parent_name, *vco_name; + char clk_name[32]; struct clk_init_data vco_init = { .parent_data = &(const struct clk_parent_data) { .fw_name = "ref", @@ -404,20 +404,8 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov if (!bytediv) return -ENOMEM; - vco_name = devm_kzalloc(dev, 32, GFP_KERNEL); - if (!vco_name) - return -ENOMEM; - - parent_name = devm_kzalloc(dev, 32, GFP_KERNEL); - if (!parent_name) - return -ENOMEM; - - clk_name = devm_kzalloc(dev, 32, GFP_KERNEL); - if (!clk_name) - return -ENOMEM; - - snprintf(vco_name, 32, "dsi%dvco_clk", pll_28nm->phy->id); - vco_init.name = vco_name; + snprintf(clk_name, sizeof(clk_name), "dsi%dvco_clk", pll_28nm->phy->id); + vco_init.name = clk_name; pll_28nm->clk_hw.init = &vco_init; @@ -429,13 +417,14 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov bytediv->hw.init = &bytediv_init; bytediv->reg = pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_CTRL_9; - snprintf(parent_name, 32, "dsi%dvco_clk", pll_28nm->phy->id); - snprintf(clk_name, 32, "dsi%dpllbyte", pll_28nm->phy->id + 1); + snprintf(clk_name, sizeof(clk_name), "dsi%dpllbyte", pll_28nm->phy->id + 1); bytediv_init.name = clk_name; bytediv_init.ops = &clk_bytediv_ops; bytediv_init.flags = CLK_SET_RATE_PARENT; - bytediv_init.parent_names = (const char * const *) &parent_name; + bytediv_init.parent_hws = (const struct clk_hw*[]){ + &pll_28nm->clk_hw, + }; bytediv_init.num_parents = 1; /* DIV2 */ @@ -444,12 +433,12 @@ static int pll_28nm_register(struct dsi_pll_28nm *pll_28nm, struct clk_hw **prov return ret; provided_clocks[DSI_BYTE_PLL_CLK] = &bytediv->hw; - snprintf(clk_name, 32, "dsi%dpll", pll_28nm->phy->id + 1); + snprintf(clk_name, sizeof(clk_name), "dsi%dpll", pll_28nm->phy->id + 1); /* DIV3 */ - hw = devm_clk_hw_register_divider(dev, clk_name, - parent_name, 0, pll_28nm->phy->pll_base + + hw = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + &pll_28nm->clk_hw, 0, pll_28nm->phy->pll_base + REG_DSI_28nm_8960_PHY_PLL_CTRL_10, - 0, 8, 0, NULL); + 0, 8, 0, NULL); if (IS_ERR(hw)) return PTR_ERR(hw); provided_clocks[DSI_PIXEL_PLL_CLK] = hw; @@ -489,29 +478,29 @@ static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy, void __iomem *base = phy->base; dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_0, - DSI_28nm_8960_PHY_TIMING_CTRL_0_CLK_ZERO(timing->clk_zero)); + DSI_28nm_8960_PHY_TIMING_CTRL_0_CLK_ZERO(timing->clk_zero)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_1, - DSI_28nm_8960_PHY_TIMING_CTRL_1_CLK_TRAIL(timing->clk_trail)); + DSI_28nm_8960_PHY_TIMING_CTRL_1_CLK_TRAIL(timing->clk_trail)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_2, - DSI_28nm_8960_PHY_TIMING_CTRL_2_CLK_PREPARE(timing->clk_prepare)); + DSI_28nm_8960_PHY_TIMING_CTRL_2_CLK_PREPARE(timing->clk_prepare)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_3, 0x0); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_4, - DSI_28nm_8960_PHY_TIMING_CTRL_4_HS_EXIT(timing->hs_exit)); + DSI_28nm_8960_PHY_TIMING_CTRL_4_HS_EXIT(timing->hs_exit)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_5, - DSI_28nm_8960_PHY_TIMING_CTRL_5_HS_ZERO(timing->hs_zero)); + DSI_28nm_8960_PHY_TIMING_CTRL_5_HS_ZERO(timing->hs_zero)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_6, - DSI_28nm_8960_PHY_TIMING_CTRL_6_HS_PREPARE(timing->hs_prepare)); + DSI_28nm_8960_PHY_TIMING_CTRL_6_HS_PREPARE(timing->hs_prepare)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_7, - DSI_28nm_8960_PHY_TIMING_CTRL_7_HS_TRAIL(timing->hs_trail)); + DSI_28nm_8960_PHY_TIMING_CTRL_7_HS_TRAIL(timing->hs_trail)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_8, - DSI_28nm_8960_PHY_TIMING_CTRL_8_HS_RQST(timing->hs_rqst)); + DSI_28nm_8960_PHY_TIMING_CTRL_8_HS_RQST(timing->hs_rqst)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_9, - DSI_28nm_8960_PHY_TIMING_CTRL_9_TA_GO(timing->ta_go) | - DSI_28nm_8960_PHY_TIMING_CTRL_9_TA_SURE(timing->ta_sure)); + DSI_28nm_8960_PHY_TIMING_CTRL_9_TA_GO(timing->ta_go) | + DSI_28nm_8960_PHY_TIMING_CTRL_9_TA_SURE(timing->ta_sure)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_10, - DSI_28nm_8960_PHY_TIMING_CTRL_10_TA_GET(timing->ta_get)); + DSI_28nm_8960_PHY_TIMING_CTRL_10_TA_GET(timing->ta_get)); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_TIMING_CTRL_11, - DSI_28nm_8960_PHY_TIMING_CTRL_11_TRIG3_CMD(0)); + DSI_28nm_8960_PHY_TIMING_CTRL_11_TRIG3_CMD(0)); } static void dsi_28nm_phy_regulator_init(struct msm_dsi_phy *phy) @@ -523,7 +512,7 @@ static void dsi_28nm_phy_regulator_init(struct msm_dsi_phy *phy) dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_2, 1); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_3, 0); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CTRL_4, - 0x100); + 0x100); } static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy) @@ -544,7 +533,7 @@ static void dsi_28nm_phy_calibration(struct msm_dsi_phy *phy) int i = 5000; dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_REGULATOR_CAL_PWR_CFG, - 0x3); + 0x3); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_SW_CFG_2, 0x0); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_MISC_CAL_HW_CFG_1, 0x5a); @@ -577,11 +566,11 @@ static void dsi_28nm_phy_lane_config(struct msm_dsi_phy *phy) dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_CFG_1(i), 0x45); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_CFG_2(i), 0x00); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_TEST_DATAPATH(i), - 0x00); + 0x00); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_TEST_STR_0(i), - 0x01); + 0x01); dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LN_TEST_STR_1(i), - 0x66); + 0x66); } dsi_phy_write(base + REG_DSI_28nm_8960_PHY_LNCK_CFG_0, 0x40); @@ -602,7 +591,8 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, if (msm_dsi_dphy_timing_calc(timing, clk_req)) { DRM_DEV_ERROR(&phy->pdev->dev, - "%s: D-PHY timing calculation failed\n", __func__); + "%s: D-PHY timing calculation failed\n", + __func__); return -EINVAL; } @@ -648,14 +638,14 @@ static void dsi_28nm_phy_disable(struct msm_dsi_phy *phy) wmb(); } +static const struct regulator_bulk_data dsi_phy_28nm_8960_regulators[] = { + { .supply = "vddio", .init_load_uA = 100000 }, /* 1.8 V */ +}; + const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs = { .has_phy_regulator = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vddio", 100000, 100}, /* 1.8 V */ - }, - }, + .regulator_data = dsi_phy_28nm_8960_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_28nm_8960_regulators), .ops = { .enable = dsi_28nm_phy_enable, .disable = dsi_28nm_phy_disable, diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c index 66ed1919a1db..9e7fa7d88ead 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c @@ -176,19 +176,19 @@ static void dsi_pll_ssc_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *c pr_debug("SSC is enabled\n"); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_LOW_1, - config->ssc_stepsize & 0xff); + config->ssc_stepsize & 0xff); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_STEPSIZE_HIGH_1, - config->ssc_stepsize >> 8); + config->ssc_stepsize >> 8); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_LOW_1, - config->ssc_div_per & 0xff); + config->ssc_div_per & 0xff); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_DIV_PER_HIGH_1, - config->ssc_div_per >> 8); + config->ssc_div_per >> 8); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_LOW_1, - config->ssc_adj_per & 0xff); + config->ssc_adj_per & 0xff); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_ADJPER_HIGH_1, - config->ssc_adj_per >> 8); + config->ssc_adj_per >> 8); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_SSC_CONTROL, - SSC_EN | (config->ssc_center ? SSC_CENTER : 0)); + SSC_EN | (config->ssc_center ? SSC_CENTER : 0)); } } @@ -208,7 +208,7 @@ static void dsi_pll_config_hzindep_reg(struct dsi_pll_7nm *pll) } dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE_1, - analog_controls_five_1); + analog_controls_five_1); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_VCO_CONFIG_1, vco_config_1); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_FIVE, 0x01); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_ANALOG_CONTROLS_TWO, 0x03); @@ -245,17 +245,20 @@ static void dsi_pll_commit(struct dsi_pll_7nm *pll, struct dsi_pll_config *confi void __iomem *base = pll->phy->pll_base; dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CORE_INPUT_OVERRIDE, 0x12); - dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1, config->decimal_div_start); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_DECIMAL_DIV_START_1, + config->decimal_div_start); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_LOW_1, - config->frac_div_start & 0xff); + config->frac_div_start & 0xff); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_MID_1, - (config->frac_div_start & 0xff00) >> 8); + (config->frac_div_start & 0xff00) >> 8); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_FRAC_DIV_START_HIGH_1, - (config->frac_div_start & 0x30000) >> 16); + (config->frac_div_start & 0x30000) >> 16); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCKDET_RATE_1, 0x40); dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_PLL_LOCK_DELAY, 0x06); - dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, pll->phy->cphy_mode ? 0x00 : 0x10); - dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, config->pll_clock_inverters); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CMODE_1, + pll->phy->cphy_mode ? 0x00 : 0x10); + dsi_phy_write(base + REG_DSI_7nm_PHY_PLL_CLOCK_INVERTERS, + config->pll_clock_inverters); } static int dsi_pll_7nm_vco_set_rate(struct clk_hw *hw, unsigned long rate, @@ -341,7 +344,7 @@ static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll) data = dsi_phy_read(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); dsi_phy_write(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, - data | BIT(5) | BIT(4)); + data | BIT(5) | BIT(4)); } static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll) @@ -500,7 +503,7 @@ static void dsi_7nm_pll_save_state(struct msm_dsi_phy *phy) u32 cmn_clk_cfg0, cmn_clk_cfg1; cached->pll_out_div = dsi_phy_read(pll_7nm->phy->pll_base + - REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE); cached->pll_out_div &= 0x3; cmn_clk_cfg0 = dsi_phy_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0); @@ -529,7 +532,7 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy) dsi_phy_write(pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, val); dsi_phy_write(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0, - cached->bit_clk_div | (cached->pix_clk_div << 4)); + cached->bit_clk_div | (cached->pix_clk_div << 4)); val = dsi_phy_read(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); val &= ~0x3; @@ -585,65 +588,60 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy) */ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provided_clocks) { - char clk_name[32], parent[32], vco_name[32]; - char parent2[32]; + char clk_name[32]; struct clk_init_data vco_init = { .parent_data = &(const struct clk_parent_data) { .fw_name = "ref", }, .num_parents = 1, - .name = vco_name, + .name = clk_name, .flags = CLK_IGNORE_UNUSED, .ops = &clk_ops_dsi_pll_7nm_vco, }; struct device *dev = &pll_7nm->phy->pdev->dev; - struct clk_hw *hw; + struct clk_hw *hw, *pll_out_div, *pll_bit, *pll_by_2_bit; + struct clk_hw *pll_post_out_div, *phy_pll_out_dsi_parent; int ret; DBG("DSI%d", pll_7nm->phy->id); - snprintf(vco_name, 32, "dsi%dvco_clk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%dvco_clk", pll_7nm->phy->id); pll_7nm->clk_hw.init = &vco_init; ret = devm_clk_hw_register(dev, &pll_7nm->clk_hw); if (ret) return ret; - snprintf(clk_name, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); - snprintf(parent, 32, "dsi%dvco_clk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_out_div_clk", pll_7nm->phy->id); - hw = devm_clk_hw_register_divider(dev, clk_name, - parent, CLK_SET_RATE_PARENT, - pll_7nm->phy->pll_base + - REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, - 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_out_div = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + &pll_7nm->clk_hw, CLK_SET_RATE_PARENT, + pll_7nm->phy->pll_base + + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE, + 0, 2, CLK_DIVIDER_POWER_OF_TWO, NULL); + if (IS_ERR(pll_out_div)) { + ret = PTR_ERR(pll_out_div); goto fail; } - snprintf(clk_name, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_bit_clk", pll_7nm->phy->id); /* BIT CLK: DIV_CTRL_3_0 */ - hw = devm_clk_hw_register_divider(dev, clk_name, parent, - CLK_SET_RATE_PARENT, - pll_7nm->phy->base + - REG_DSI_7nm_PHY_CMN_CLK_CFG0, - 0, 4, CLK_DIVIDER_ONE_BASED, - &pll_7nm->postdiv_lock); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_bit = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + pll_out_div, CLK_SET_RATE_PARENT, + pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + 0, 4, CLK_DIVIDER_ONE_BASED, &pll_7nm->postdiv_lock); + if (IS_ERR(pll_bit)) { + ret = PTR_ERR(pll_bit); goto fail; } - snprintf(clk_name, 32, "dsi%d_phy_pll_out_byteclk", pll_7nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_phy_pll_out_byteclk", pll_7nm->phy->id); /* DSI Byte clock = VCO_CLK / OUT_DIV / BIT_DIV / 8 */ - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, - CLK_SET_RATE_PARENT, 1, - pll_7nm->phy->cphy_mode ? 7 : 8); + hw = devm_clk_hw_register_fixed_factor_parent_hw(dev, clk_name, + pll_bit, CLK_SET_RATE_PARENT, 1, + pll_7nm->phy->cphy_mode ? 7 : 8); if (IS_ERR(hw)) { ret = PTR_ERR(hw); goto fail; @@ -651,25 +649,25 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide provided_clocks[DSI_BYTE_PLL_CLK] = hw; - snprintf(clk_name, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id); - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, - 0, 1, 2); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_by_2_bit = devm_clk_hw_register_fixed_factor_parent_hw(dev, + clk_name, pll_bit, 0, 1, 2); + if (IS_ERR(pll_by_2_bit)) { + ret = PTR_ERR(pll_by_2_bit); goto fail; } - snprintf(clk_name, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_out_div_clk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id); if (pll_7nm->phy->cphy_mode) - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 2, 7); + pll_post_out_div = devm_clk_hw_register_fixed_factor_parent_hw( + dev, clk_name, pll_out_div, 0, 2, 7); else - hw = devm_clk_hw_register_fixed_factor(dev, clk_name, parent, 0, 1, 4); - if (IS_ERR(hw)) { - ret = PTR_ERR(hw); + pll_post_out_div = devm_clk_hw_register_fixed_factor_parent_hw( + dev, clk_name, pll_out_div, 0, 1, 4); + if (IS_ERR(pll_post_out_div)) { + ret = PTR_ERR(pll_post_out_div); goto fail; } @@ -682,34 +680,32 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide data = dsi_phy_read(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1); dsi_phy_write(pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, data | 3); - snprintf(parent, 32, "dsi%d_pll_post_out_div_clk", pll_7nm->phy->id); + phy_pll_out_dsi_parent = pll_post_out_div; } else { - snprintf(clk_name, 32, "dsi%d_pclk_mux", pll_7nm->phy->id); - snprintf(parent, 32, "dsi%d_pll_bit_clk", pll_7nm->phy->id); - snprintf(parent2, 32, "dsi%d_pll_by_2_bit_clk", pll_7nm->phy->id); - - hw = devm_clk_hw_register_mux(dev, clk_name, - ((const char *[]){ - parent, parent2, - }), 2, 0, pll_7nm->phy->base + + snprintf(clk_name, sizeof(clk_name), "dsi%d_pclk_mux", pll_7nm->phy->id); + + hw = devm_clk_hw_register_mux_parent_hws(dev, clk_name, + ((const struct clk_hw *[]){ + pll_bit, + pll_by_2_bit, + }), 2, 0, pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1, - 0, 1, 0, NULL); + 0, 1, 0, NULL); if (IS_ERR(hw)) { ret = PTR_ERR(hw); goto fail; } - snprintf(parent, 32, "dsi%d_pclk_mux", pll_7nm->phy->id); + phy_pll_out_dsi_parent = hw; } - snprintf(clk_name, 32, "dsi%d_phy_pll_out_dsiclk", pll_7nm->phy->id); + snprintf(clk_name, sizeof(clk_name), "dsi%d_phy_pll_out_dsiclk", pll_7nm->phy->id); /* PIX CLK DIV : DIV_CTRL_7_4*/ - hw = devm_clk_hw_register_divider(dev, clk_name, parent, - 0, pll_7nm->phy->base + - REG_DSI_7nm_PHY_CMN_CLK_CFG0, - 4, 4, CLK_DIVIDER_ONE_BASED, - &pll_7nm->postdiv_lock); + hw = devm_clk_hw_register_divider_parent_hw(dev, clk_name, + phy_pll_out_dsi_parent, 0, + pll_7nm->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG0, + 4, 4, CLK_DIVIDER_ONE_BASED, &pll_7nm->postdiv_lock); if (IS_ERR(hw)) { ret = PTR_ERR(hw); goto fail; @@ -841,7 +837,7 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, ret = msm_dsi_dphy_timing_calc_v4(timing, clk_req); if (ret) { DRM_DEV_ERROR(&phy->pdev->dev, - "%s: PHY timing calculation failed\n", __func__); + "%s: PHY timing calculation failed\n", __func__); return -EINVAL; } @@ -960,10 +956,10 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_0, 0x00); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_4, timing->hs_exit); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_5, - timing->shared_timings.clk_pre); + timing->shared_timings.clk_pre); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_6, timing->clk_prepare); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_7, - timing->shared_timings.clk_post); + timing->shared_timings.clk_post); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_8, timing->hs_rqst); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_9, 0x02); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10, 0x04); @@ -982,9 +978,9 @@ static int dsi_7nm_phy_enable(struct msm_dsi_phy *phy, dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_10, 0x04); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_11, 0x00); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_12, - timing->shared_timings.clk_pre); + timing->shared_timings.clk_pre); dsi_phy_write(base + REG_DSI_7nm_PHY_CMN_TIMING_CTRL_13, - timing->shared_timings.clk_post); + timing->shared_timings.clk_post); } /* DSI lane settings */ @@ -1036,14 +1032,18 @@ static void dsi_7nm_phy_disable(struct msm_dsi_phy *phy) DBG("DSI%d PHY disabled", phy->id); } +static const struct regulator_bulk_data dsi_phy_7nm_36mA_regulators[] = { + { .supply = "vdds", .init_load_uA = 36000 }, +}; + +static const struct regulator_bulk_data dsi_phy_7nm_37750uA_regulators[] = { + { .supply = "vdds", .init_load_uA = 37550 }, +}; + const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vdds", 36000, 32}, - }, - }, + .regulator_data = dsi_phy_7nm_36mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_7nm_36mA_regulators), .ops = { .enable = dsi_7nm_phy_enable, .disable = dsi_7nm_phy_disable, @@ -1065,12 +1065,8 @@ const struct msm_dsi_phy_cfg dsi_phy_7nm_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vdds", 36000, 32}, - }, - }, + .regulator_data = dsi_phy_7nm_36mA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_7nm_36mA_regulators), .ops = { .enable = dsi_7nm_phy_enable, .disable = dsi_7nm_phy_disable, @@ -1087,12 +1083,8 @@ const struct msm_dsi_phy_cfg dsi_phy_7nm_8150_cfgs = { const struct msm_dsi_phy_cfg dsi_phy_7nm_7280_cfgs = { .has_phy_lane = true, - .reg_cfg = { - .num = 1, - .regs = { - {"vdds", 37550, 0}, - }, - }, + .regulator_data = dsi_phy_7nm_37750uA_regulators, + .num_regulators = ARRAY_SIZE(dsi_phy_7nm_37750uA_regulators), .ops = { .enable = dsi_7nm_phy_enable, .disable = dsi_7nm_phy_disable, diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c index b06d9d25a189..4dd055416620 100644 --- a/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c +++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy_8996.c @@ -691,15 +691,13 @@ static const struct clk_ops hdmi_8996_pll_ops = { .is_enabled = hdmi_8996_pll_is_enabled, }; -static const char * const hdmi_pll_parents[] = { - "xo", -}; - static const struct clk_init_data pll_init = { .name = "hdmipll", .ops = &hdmi_8996_pll_ops, - .parent_names = hdmi_pll_parents, - .num_parents = ARRAY_SIZE(hdmi_pll_parents), + .parent_data = (const struct clk_parent_data[]){ + { .fw_name = "xo", .name = "xo_board" }, + }, + .num_parents = 1, .flags = CLK_IGNORE_UNUSED, }; @@ -707,8 +705,7 @@ int msm_hdmi_pll_8996_init(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct hdmi_pll_8996 *pll; - struct clk *clk; - int i; + int i, ret; pll = devm_kzalloc(dev, sizeof(*pll), GFP_KERNEL); if (!pll) @@ -735,10 +732,16 @@ int msm_hdmi_pll_8996_init(struct platform_device *pdev) } pll->clk_hw.init = &pll_init; - clk = devm_clk_register(dev, &pll->clk_hw); - if (IS_ERR(clk)) { + ret = devm_clk_hw_register(dev, &pll->clk_hw); + if (ret) { DRM_DEV_ERROR(dev, "failed to register pll clock\n"); - return -EINVAL; + return ret; + } + + ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, &pll->clk_hw); + if (ret) { + DRM_DEV_ERROR(dev, "%s: failed to register clk provider: %d\n", __func__, ret); + return ret; } return 0; diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c index 7d2dab260f86..95f4374ae21c 100644 --- a/drivers/gpu/drm/msm/msm_debugfs.c +++ b/drivers/gpu/drm/msm/msm_debugfs.c @@ -7,6 +7,7 @@ #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> +#include <linux/fault-inject.h> #include <drm/drm_debugfs.h> #include <drm/drm_file.h> @@ -326,6 +327,13 @@ void msm_debugfs_init(struct drm_minor *minor) if (priv->kms && priv->kms->funcs->debugfs_init) priv->kms->funcs->debugfs_init(priv->kms, minor); + +#ifdef CONFIG_FAULT_INJECTION + fault_create_debugfs_attr("fail_gem_alloc", minor->debugfs_root, + &fail_gem_alloc); + fault_create_debugfs_attr("fail_gem_iova", minor->debugfs_root, + &fail_gem_iova); +#endif } #endif diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 226d8d4629d2..28034c21f6bc 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -6,6 +6,7 @@ */ #include <linux/dma-mapping.h> +#include <linux/fault-inject.h> #include <linux/kthread.h> #include <linux/sched/mm.h> #include <linux/uaccess.h> @@ -78,6 +79,11 @@ static bool modeset = true; MODULE_PARM_DESC(modeset, "Use kernel modesetting [KMS] (1=on (default), 0=disable)"); module_param(modeset, bool, 0600); +#ifdef CONFIG_FAULT_INJECTION +DECLARE_FAULT_ATTR(fail_gem_alloc); +DECLARE_FAULT_ATTR(fail_gem_iova); +#endif + static irqreturn_t msm_irq(int irq, void *arg) { struct drm_device *dev = arg; @@ -418,14 +424,18 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) INIT_LIST_HEAD(&priv->objects); mutex_init(&priv->obj_lock); - INIT_LIST_HEAD(&priv->inactive_willneed); - INIT_LIST_HEAD(&priv->inactive_dontneed); - INIT_LIST_HEAD(&priv->inactive_unpinned); - mutex_init(&priv->mm_lock); + /* + * Initialize the LRUs: + */ + mutex_init(&priv->lru.lock); + drm_gem_lru_init(&priv->lru.unbacked, &priv->lru.lock); + drm_gem_lru_init(&priv->lru.pinned, &priv->lru.lock); + drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock); + drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock); /* Teach lockdep about lock ordering wrt. shrinker: */ fs_reclaim_acquire(GFP_KERNEL); - might_lock(&priv->mm_lock); + might_lock(&priv->lru.lock); fs_reclaim_release(GFP_KERNEL); drm_mode_config_init(ddev); @@ -469,6 +479,8 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) } } + drm_helper_move_panel_connectors_to_head(ddev); + ddev->mode_config.funcs = &mode_config_funcs; ddev->mode_config.helper_private = &mode_config_helper_funcs; @@ -697,6 +709,9 @@ static int msm_ioctl_gem_new(struct drm_device *dev, void *data, flags |= MSM_BO_WC; } + if (should_fail(&fail_gem_alloc, args->size)) + return -ENOMEM; + return msm_gem_new_handle(dev, file, args->size, args->flags, &args->handle, NULL); } @@ -758,6 +773,9 @@ static int msm_ioctl_gem_info_iova(struct drm_device *dev, if (!priv->gpu) return -EINVAL; + if (should_fail(&fail_gem_iova, obj->size)) + return -ENOMEM; + /* * Don't pin the memory here - just get an address so that userspace can * be productive @@ -779,6 +797,9 @@ static int msm_ioctl_gem_info_set_iova(struct drm_device *dev, if (priv->gpu->aspace == ctx->aspace) return -EOPNOTSUPP; + if (should_fail(&fail_gem_iova, obj->size)) + return -ENOMEM; + return msm_gem_set_iova(obj, ctx->aspace, iova); } @@ -883,13 +904,13 @@ static int wait_fence(struct msm_gpu_submitqueue *queue, uint32_t fence_id, * retired, so if the fence is not found it means there is nothing * to wait for */ - ret = mutex_lock_interruptible(&queue->lock); + ret = mutex_lock_interruptible(&queue->idr_lock); if (ret) return ret; fence = idr_find(&queue->fence_idr, fence_id); if (fence) fence = dma_fence_get_rcu(fence); - mutex_unlock(&queue->lock); + mutex_unlock(&queue->idr_lock); if (!fence) return 0; diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 7d5fb0fc22dd..b2ea262296a4 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -33,6 +33,13 @@ #include <drm/msm_drm.h> #include <drm/drm_gem.h> +#ifdef CONFIG_FAULT_INJECTION +extern struct fault_attr fail_gem_alloc; +extern struct fault_attr fail_gem_iova; +#else +# define should_fail(attr, size) 0 +#endif + struct msm_kms; struct msm_gpu; struct msm_mmu; @@ -95,11 +102,6 @@ struct msm_drm_thread { struct kthread_worker *worker; }; -/* DSC config */ -struct msm_display_dsc_config { - struct drm_dsc_config *drm; -}; - struct msm_drm_private { struct drm_device *dev; @@ -141,28 +143,60 @@ struct msm_drm_private { struct mutex obj_lock; /** - * LRUs of inactive GEM objects. Every bo is either in one of the - * inactive lists (depending on whether or not it is shrinkable) or - * gpu->active_list (for the gpu it is active on[1]), or transiently - * on a temporary list as the shrinker is running. + * lru: * - * Note that inactive_willneed also contains pinned and vmap'd bos, - * but the number of pinned-but-not-active objects is small (scanout - * buffers, ringbuffer, etc). + * The various LRU's that a GEM object is in at various stages of + * it's lifetime. Objects start out in the unbacked LRU. When + * pinned (for scannout or permanently mapped GPU buffers, like + * ringbuffer, memptr, fw, etc) it moves to the pinned LRU. When + * unpinned, it moves into willneed or dontneed LRU depending on + * madvise state. When backing pages are evicted (willneed) or + * purged (dontneed) it moves back into the unbacked LRU. * - * These lists are protected by mm_lock (which should be acquired - * before per GEM object lock). One should *not* hold mm_lock in - * get_pages()/vmap()/etc paths, as they can trigger the shrinker. - * - * [1] if someone ever added support for the old 2d cores, there could be - * more than one gpu object + * The dontneed LRU is considered by the shrinker for objects + * that are candidate for purging, and the willneed LRU is + * considered for objects that could be evicted. */ - struct list_head inactive_willneed; /* inactive + potentially unpin/evictable */ - struct list_head inactive_dontneed; /* inactive + shrinkable */ - struct list_head inactive_unpinned; /* inactive + purged or unpinned */ - long shrinkable_count; /* write access under mm_lock */ - long evictable_count; /* write access under mm_lock */ - struct mutex mm_lock; + struct { + /** + * unbacked: + * + * The LRU for GEM objects without backing pages allocated. + * This mostly exists so that objects are always is one + * LRU. + */ + struct drm_gem_lru unbacked; + + /** + * pinned: + * + * The LRU for pinned GEM objects + */ + struct drm_gem_lru pinned; + + /** + * willneed: + * + * The LRU for unpinned GEM objects which are in madvise + * WILLNEED state (ie. can be evicted) + */ + struct drm_gem_lru willneed; + + /** + * dontneed: + * + * The LRU for unpinned GEM objects which are in madvise + * DONTNEED state (ie. can be purged) + */ + struct drm_gem_lru dontneed; + + /** + * lock: + * + * Protects manipulation of all of the LRUs. + */ + struct mutex lock; + } lru; struct workqueue_struct *wq; @@ -289,7 +323,7 @@ void msm_dsi_snapshot(struct msm_disp_state *disp_state, struct msm_dsi *msm_dsi bool msm_dsi_is_cmd_mode(struct msm_dsi *msm_dsi); bool msm_dsi_is_bonded_dsi(struct msm_dsi *msm_dsi); bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi); -struct msm_display_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi); +struct drm_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi); #else static inline void __init msm_dsi_register(void) { @@ -319,7 +353,7 @@ static inline bool msm_dsi_is_master_dsi(struct msm_dsi *msm_dsi) return false; } -static inline struct msm_display_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi) +static inline struct drm_dsc_config *msm_dsi_get_dsc_config(struct msm_dsi *msm_dsi) { return NULL; } @@ -432,6 +466,8 @@ void __iomem *msm_ioremap_size(struct platform_device *pdev, const char *name, phys_addr_t *size); void __iomem *msm_ioremap_quiet(struct platform_device *pdev, const char *name); +struct icc_path *msm_icc_get(struct device *dev, const char *name); + #define msm_writel(data, addr) writel((data), (addr)) #define msm_readl(addr) readl((addr)) diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c index 8ddbd2e001d4..1dee0d18abbb 100644 --- a/drivers/gpu/drm/msm/msm_gem.c +++ b/drivers/gpu/drm/msm/msm_gem.c @@ -19,7 +19,7 @@ #include "msm_gpu.h" #include "msm_mmu.h" -static void update_inactive(struct msm_gem_object *msm_obj); +static void update_lru(struct drm_gem_object *obj); static dma_addr_t physaddr(struct drm_gem_object *obj) { @@ -97,7 +97,7 @@ static struct page **get_pages(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); if (!msm_obj->pages) { struct drm_device *dev = obj->dev; @@ -132,7 +132,7 @@ static struct page **get_pages(struct drm_gem_object *obj) if (msm_obj->flags & MSM_BO_WC) sync_for_device(msm_obj); - update_inactive(msm_obj); + update_lru(obj); } return msm_obj->pages; @@ -174,40 +174,45 @@ static void put_pages(struct drm_gem_object *obj) put_pages_vram(obj); msm_obj->pages = NULL; + update_lru(obj); } } -struct page **msm_gem_get_pages(struct drm_gem_object *obj) +static struct page **msm_gem_pin_pages_locked(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); struct page **p; - msm_gem_lock(obj); + msm_gem_assert_locked(obj); if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) { - msm_gem_unlock(obj); return ERR_PTR(-EBUSY); } p = get_pages(obj); - if (!IS_ERR(p)) { - msm_obj->pin_count++; - update_inactive(msm_obj); + to_msm_bo(obj)->pin_count++; + update_lru(obj); } - msm_gem_unlock(obj); return p; } -void msm_gem_put_pages(struct drm_gem_object *obj) +struct page **msm_gem_pin_pages(struct drm_gem_object *obj) { - struct msm_gem_object *msm_obj = to_msm_bo(obj); + struct page **p; msm_gem_lock(obj); - msm_obj->pin_count--; - GEM_WARN_ON(msm_obj->pin_count < 0); - update_inactive(msm_obj); + p = msm_gem_pin_pages_locked(obj); + msm_gem_unlock(obj); + + return p; +} + +void msm_gem_unpin_pages(struct drm_gem_object *obj) +{ + msm_gem_lock(obj); + msm_gem_unpin_locked(obj); msm_gem_unlock(obj); } @@ -273,7 +278,7 @@ static uint64_t mmap_offset(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; int ret; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); /* Make it mmapable */ ret = drm_gem_create_mmap_offset(obj); @@ -302,7 +307,7 @@ static struct msm_gem_vma *add_vma(struct drm_gem_object *obj, struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); vma = kzalloc(sizeof(*vma), GFP_KERNEL); if (!vma) @@ -321,7 +326,7 @@ static struct msm_gem_vma *lookup_vma(struct drm_gem_object *obj, struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); list_for_each_entry(vma, &msm_obj->vmas, list) { if (vma->aspace == aspace) @@ -352,7 +357,7 @@ put_iova_spaces(struct drm_gem_object *obj, bool close) struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); list_for_each_entry(vma, &msm_obj->vmas, list) { if (vma->aspace) { @@ -370,7 +375,7 @@ put_iova_vmas(struct drm_gem_object *obj) struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_gem_vma *vma, *tmp; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); list_for_each_entry_safe(vma, tmp, &msm_obj->vmas, list) { del_vma(vma); @@ -383,7 +388,7 @@ static struct msm_gem_vma *get_vma_locked(struct drm_gem_object *obj, { struct msm_gem_vma *vma; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); vma = lookup_vma(obj, aspace); @@ -423,19 +428,18 @@ int msm_gem_pin_vma_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma) if (msm_obj->flags & MSM_BO_CACHED_COHERENT) prot |= IOMMU_CACHE; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); if (GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED)) return -EBUSY; - pages = get_pages(obj); + pages = msm_gem_pin_pages_locked(obj); if (IS_ERR(pages)) return PTR_ERR(pages); ret = msm_gem_map_vma(vma->aspace, vma, prot, msm_obj->sgt, obj->size); - - if (!ret) - msm_obj->pin_count++; + if (ret) + msm_gem_unpin_locked(obj); return ret; } @@ -444,12 +448,12 @@ void msm_gem_unpin_locked(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); msm_obj->pin_count--; GEM_WARN_ON(msm_obj->pin_count < 0); - update_inactive(msm_obj); + update_lru(obj); } struct msm_gem_vma *msm_gem_get_vma_locked(struct drm_gem_object *obj, @@ -465,7 +469,7 @@ static int get_and_pin_iova_range_locked(struct drm_gem_object *obj, struct msm_gem_vma *vma; int ret; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); vma = get_vma_locked(obj, aspace, range_start, range_end); if (IS_ERR(vma)) @@ -626,7 +630,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) struct msm_gem_object *msm_obj = to_msm_bo(obj); int ret = 0; - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); if (obj->import_attach) return ERR_PTR(-ENODEV); @@ -658,7 +662,7 @@ static void *get_vaddr(struct drm_gem_object *obj, unsigned madv) goto fail; } - update_inactive(msm_obj); + update_lru(obj); } return msm_obj->vaddr; @@ -699,7 +703,7 @@ void msm_gem_put_vaddr_locked(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); GEM_WARN_ON(msm_obj->vmap_count < 1); msm_obj->vmap_count--; @@ -729,8 +733,7 @@ int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv) /* If the obj is inactive, we might need to move it * between inactive lists */ - if (msm_obj->active_count == 0) - update_inactive(msm_obj); + update_lru(obj); msm_gem_unlock(obj); @@ -742,7 +745,7 @@ void msm_gem_purge(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); GEM_WARN_ON(!is_purgeable(msm_obj)); /* Get rid of any iommu mapping(s): */ @@ -757,7 +760,6 @@ void msm_gem_purge(struct drm_gem_object *obj) put_iova_vmas(obj); msm_obj->madv = __MSM_MADV_PURGED; - update_inactive(msm_obj); drm_gem_free_mmap_offset(obj); @@ -780,10 +782,8 @@ void msm_gem_evict(struct drm_gem_object *obj) struct drm_device *dev = obj->dev; struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); GEM_WARN_ON(is_unevictable(msm_obj)); - GEM_WARN_ON(!msm_obj->evictable); - GEM_WARN_ON(msm_obj->active_count); /* Get rid of any iommu mapping(s): */ put_iova_spaces(obj, false); @@ -791,15 +791,13 @@ void msm_gem_evict(struct drm_gem_object *obj) drm_vma_node_unmap(&obj->vma_node, dev->anon_inode->i_mapping); put_pages(obj); - - update_inactive(msm_obj); } void msm_gem_vunmap(struct drm_gem_object *obj) { struct msm_gem_object *msm_obj = to_msm_bo(obj); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(obj); if (!msm_obj->vaddr || GEM_WARN_ON(!is_vunmapable(msm_obj))) return; @@ -808,66 +806,37 @@ void msm_gem_vunmap(struct drm_gem_object *obj) msm_obj->vaddr = NULL; } -void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu) +static void update_lru(struct drm_gem_object *obj) { - struct msm_gem_object *msm_obj = to_msm_bo(obj); struct msm_drm_private *priv = obj->dev->dev_private; - - might_sleep(); - GEM_WARN_ON(!msm_gem_is_locked(obj)); - GEM_WARN_ON(msm_obj->madv != MSM_MADV_WILLNEED); - GEM_WARN_ON(msm_obj->dontneed); - - if (msm_obj->active_count++ == 0) { - mutex_lock(&priv->mm_lock); - if (msm_obj->evictable) - mark_unevictable(msm_obj); - list_move_tail(&msm_obj->mm_list, &gpu->active_list); - mutex_unlock(&priv->mm_lock); - } -} - -void msm_gem_active_put(struct drm_gem_object *obj) -{ struct msm_gem_object *msm_obj = to_msm_bo(obj); - might_sleep(); - GEM_WARN_ON(!msm_gem_is_locked(obj)); + msm_gem_assert_locked(&msm_obj->base); - if (--msm_obj->active_count == 0) { - update_inactive(msm_obj); + if (!msm_obj->pages) { + GEM_WARN_ON(msm_obj->pin_count); + GEM_WARN_ON(msm_obj->vmap_count); + + drm_gem_lru_move_tail(&priv->lru.unbacked, obj); + } else if (msm_obj->pin_count || msm_obj->vmap_count) { + drm_gem_lru_move_tail(&priv->lru.pinned, obj); + } else if (msm_obj->madv == MSM_MADV_WILLNEED) { + drm_gem_lru_move_tail(&priv->lru.willneed, obj); + } else { + GEM_WARN_ON(msm_obj->madv != MSM_MADV_DONTNEED); + + drm_gem_lru_move_tail(&priv->lru.dontneed, obj); } } -static void update_inactive(struct msm_gem_object *msm_obj) +bool msm_gem_active(struct drm_gem_object *obj) { - struct msm_drm_private *priv = msm_obj->base.dev->dev_private; - - GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base)); + msm_gem_assert_locked(obj); - if (msm_obj->active_count != 0) - return; - - mutex_lock(&priv->mm_lock); - - if (msm_obj->dontneed) - mark_unpurgeable(msm_obj); - if (msm_obj->evictable) - mark_unevictable(msm_obj); - - list_del(&msm_obj->mm_list); - if ((msm_obj->madv == MSM_MADV_WILLNEED) && msm_obj->sgt) { - list_add_tail(&msm_obj->mm_list, &priv->inactive_willneed); - mark_evictable(msm_obj); - } else if (msm_obj->madv == MSM_MADV_DONTNEED) { - list_add_tail(&msm_obj->mm_list, &priv->inactive_dontneed); - mark_purgeable(msm_obj); - } else { - GEM_WARN_ON((msm_obj->madv != __MSM_MADV_PURGED) && msm_obj->sgt); - list_add_tail(&msm_obj->mm_list, &priv->inactive_unpinned); - } + if (to_msm_bo(obj)->pin_count) + return true; - mutex_unlock(&priv->mm_lock); + return !dma_resv_test_signaled(obj->resv, dma_resv_usage_rw(true)); } int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout) @@ -910,7 +879,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, stats->all.count++; stats->all.size += obj->size; - if (is_active(msm_obj)) { + if (msm_gem_active(obj)) { stats->active.count++; stats->active.size += obj->size; } @@ -938,7 +907,7 @@ void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m, } seq_printf(m, "%08x: %c %2d (%2d) %08llx %p", - msm_obj->flags, is_active(msm_obj) ? 'A' : 'I', + msm_obj->flags, msm_gem_active(obj) ? 'A' : 'I', obj->name, kref_read(&obj->refcount), off, msm_obj->vaddr); @@ -1015,15 +984,6 @@ static void msm_gem_free_object(struct drm_gem_object *obj) list_del(&msm_obj->node); mutex_unlock(&priv->obj_lock); - mutex_lock(&priv->mm_lock); - if (msm_obj->dontneed) - mark_unpurgeable(msm_obj); - list_del(&msm_obj->mm_list); - mutex_unlock(&priv->mm_lock); - - /* object should not be on active list: */ - GEM_WARN_ON(is_active(msm_obj)); - put_iova_spaces(obj, true); if (obj->import_attach) { @@ -1183,13 +1143,6 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32 to_msm_bo(obj)->vram_node = &vma->node; - /* Call chain get_pages() -> update_inactive() tries to - * access msm_obj->mm_list, but it is not initialized yet. - * To avoid NULL pointer dereference error, initialize - * mm_list to be empty. - */ - INIT_LIST_HEAD(&msm_obj->mm_list); - msm_gem_lock(obj); pages = get_pages(obj); msm_gem_unlock(obj); @@ -1212,9 +1165,7 @@ struct drm_gem_object *msm_gem_new(struct drm_device *dev, uint32_t size, uint32 mapping_set_gfp_mask(obj->filp->f_mapping, GFP_HIGHUSER); } - mutex_lock(&priv->mm_lock); - list_add_tail(&msm_obj->mm_list, &priv->inactive_unpinned); - mutex_unlock(&priv->mm_lock); + drm_gem_lru_move_tail(&priv->lru.unbacked, obj); mutex_lock(&priv->obj_lock); list_add_tail(&msm_obj->node, &priv->objects); @@ -1270,9 +1221,7 @@ struct drm_gem_object *msm_gem_import(struct drm_device *dev, msm_gem_unlock(obj); - mutex_lock(&priv->mm_lock); - list_add_tail(&msm_obj->mm_list, &priv->inactive_unpinned); - mutex_unlock(&priv->mm_lock); + drm_gem_lru_move_tail(&priv->lru.pinned, obj); mutex_lock(&priv->obj_lock); list_add_tail(&msm_obj->node, &priv->objects); diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h index 432032ad4aed..c4844cf3a585 100644 --- a/drivers/gpu/drm/msm/msm_gem.h +++ b/drivers/gpu/drm/msm/msm_gem.h @@ -94,16 +94,6 @@ struct msm_gem_object { uint8_t madv; /** - * Is object on inactive_dontneed list (ie. counted in priv->shrinkable_count)? - */ - bool dontneed : 1; - - /** - * Is object evictable (ie. counted in priv->evictable_count)? - */ - bool evictable : 1; - - /** * count of active vmap'ing */ uint8_t vmap_count; @@ -114,17 +104,6 @@ struct msm_gem_object { */ struct list_head node; - /** - * An object is either: - * inactive - on priv->inactive_dontneed or priv->inactive_willneed - * (depending on purgeability status) - * active - on one one of the gpu's active_list.. well, at - * least for now we don't have (I don't think) hw sync between - * 2d and 3d one devices which have both, meaning we need to - * block on submit if a bo is already on other ring - */ - struct list_head mm_list; - struct page **pages; struct sg_table *sgt; void *vaddr; @@ -138,7 +117,6 @@ struct msm_gem_object { char name[32]; /* Identifier to print for the debugfs files */ - int active_count; int pin_count; }; #define to_msm_bo(x) container_of(x, struct msm_gem_object, base) @@ -159,8 +137,8 @@ int msm_gem_get_and_pin_iova(struct drm_gem_object *obj, struct msm_gem_address_space *aspace, uint64_t *iova); void msm_gem_unpin_iova(struct drm_gem_object *obj, struct msm_gem_address_space *aspace); -struct page **msm_gem_get_pages(struct drm_gem_object *obj); -void msm_gem_put_pages(struct drm_gem_object *obj); +struct page **msm_gem_pin_pages(struct drm_gem_object *obj); +void msm_gem_unpin_pages(struct drm_gem_object *obj); int msm_gem_dumb_create(struct drm_file *file, struct drm_device *dev, struct drm_mode_create_dumb *args); int msm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev, @@ -171,8 +149,7 @@ void *msm_gem_get_vaddr_active(struct drm_gem_object *obj); void msm_gem_put_vaddr_locked(struct drm_gem_object *obj); void msm_gem_put_vaddr(struct drm_gem_object *obj); int msm_gem_madvise(struct drm_gem_object *obj, unsigned madv); -void msm_gem_active_get(struct drm_gem_object *obj, struct msm_gpu *gpu); -void msm_gem_active_put(struct drm_gem_object *obj); +bool msm_gem_active(struct drm_gem_object *obj); int msm_gem_cpu_prep(struct drm_gem_object *obj, uint32_t op, ktime_t *timeout); int msm_gem_cpu_fini(struct drm_gem_object *obj); int msm_gem_new_handle(struct drm_device *dev, struct drm_file *file, @@ -208,12 +185,6 @@ msm_gem_lock(struct drm_gem_object *obj) dma_resv_lock(obj->resv, NULL); } -static inline bool __must_check -msm_gem_trylock(struct drm_gem_object *obj) -{ - return dma_resv_trylock(obj->resv); -} - static inline int msm_gem_lock_interruptible(struct drm_gem_object *obj) { @@ -226,8 +197,8 @@ msm_gem_unlock(struct drm_gem_object *obj) dma_resv_unlock(obj->resv); } -static inline bool -msm_gem_is_locked(struct drm_gem_object *obj) +static inline void +msm_gem_assert_locked(struct drm_gem_object *obj) { /* * Destroying the object is a special case.. msm_gem_free_object() @@ -241,13 +212,10 @@ msm_gem_is_locked(struct drm_gem_object *obj) * Unfortunately lockdep is not aware of this detail. So when the * refcount drops to zero, we pretend it is already locked. */ - return dma_resv_is_locked(obj->resv) || (kref_read(&obj->refcount) == 0); -} - -static inline bool is_active(struct msm_gem_object *msm_obj) -{ - GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base)); - return msm_obj->active_count; + lockdep_assert_once( + (kref_read(&obj->refcount) == 0) || + (lockdep_is_held(&obj->resv->lock.base) != LOCK_STATE_NOT_HELD) + ); } /* imported/exported objects are not purgeable: */ @@ -264,81 +232,15 @@ static inline bool is_purgeable(struct msm_gem_object *msm_obj) static inline bool is_vunmapable(struct msm_gem_object *msm_obj) { - GEM_WARN_ON(!msm_gem_is_locked(&msm_obj->base)); + msm_gem_assert_locked(&msm_obj->base); return (msm_obj->vmap_count == 0) && msm_obj->vaddr; } -static inline void mark_purgeable(struct msm_gem_object *msm_obj) -{ - struct msm_drm_private *priv = msm_obj->base.dev->dev_private; - - GEM_WARN_ON(!mutex_is_locked(&priv->mm_lock)); - - if (is_unpurgeable(msm_obj)) - return; - - if (GEM_WARN_ON(msm_obj->dontneed)) - return; - - priv->shrinkable_count += msm_obj->base.size >> PAGE_SHIFT; - msm_obj->dontneed = true; -} - -static inline void mark_unpurgeable(struct msm_gem_object *msm_obj) -{ - struct msm_drm_private *priv = msm_obj->base.dev->dev_private; - - GEM_WARN_ON(!mutex_is_locked(&priv->mm_lock)); - - if (is_unpurgeable(msm_obj)) - return; - - if (GEM_WARN_ON(!msm_obj->dontneed)) - return; - - priv->shrinkable_count -= msm_obj->base.size >> PAGE_SHIFT; - GEM_WARN_ON(priv->shrinkable_count < 0); - msm_obj->dontneed = false; -} - static inline bool is_unevictable(struct msm_gem_object *msm_obj) { return is_unpurgeable(msm_obj) || msm_obj->vaddr; } -static inline void mark_evictable(struct msm_gem_object *msm_obj) -{ - struct msm_drm_private *priv = msm_obj->base.dev->dev_private; - - WARN_ON(!mutex_is_locked(&priv->mm_lock)); - - if (is_unevictable(msm_obj)) - return; - - if (WARN_ON(msm_obj->evictable)) - return; - - priv->evictable_count += msm_obj->base.size >> PAGE_SHIFT; - msm_obj->evictable = true; -} - -static inline void mark_unevictable(struct msm_gem_object *msm_obj) -{ - struct msm_drm_private *priv = msm_obj->base.dev->dev_private; - - WARN_ON(!mutex_is_locked(&priv->mm_lock)); - - if (is_unevictable(msm_obj)) - return; - - if (WARN_ON(!msm_obj->evictable)) - return; - - priv->evictable_count -= msm_obj->base.size >> PAGE_SHIFT; - WARN_ON(priv->evictable_count < 0); - msm_obj->evictable = false; -} - void msm_gem_purge(struct drm_gem_object *obj); void msm_gem_evict(struct drm_gem_object *obj); void msm_gem_vunmap(struct drm_gem_object *obj); @@ -390,9 +292,8 @@ struct msm_gem_submit { /* make sure these don't conflict w/ MSM_SUBMIT_BO_x */ #define BO_VALID 0x8000 /* is current addr in cmdstream correct/valid? */ #define BO_LOCKED 0x4000 /* obj lock is held */ -#define BO_ACTIVE 0x2000 /* active refcnt is held */ -#define BO_OBJ_PINNED 0x1000 /* obj (pages) is pinned and on active list */ -#define BO_VMA_PINNED 0x0800 /* vma (virtual address) is pinned */ +#define BO_OBJ_PINNED 0x2000 /* obj (pages) is pinned and on active list */ +#define BO_VMA_PINNED 0x1000 /* vma (virtual address) is pinned */ uint32_t flags; union { struct msm_gem_object *obj; diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c index dcc8a573bc76..c1d91863df05 100644 --- a/drivers/gpu/drm/msm/msm_gem_prime.c +++ b/drivers/gpu/drm/msm/msm_gem_prime.c @@ -63,12 +63,12 @@ struct drm_gem_object *msm_gem_prime_import_sg_table(struct drm_device *dev, int msm_gem_prime_pin(struct drm_gem_object *obj) { if (!obj->import_attach) - msm_gem_get_pages(obj); + msm_gem_pin_pages(obj); return 0; } void msm_gem_prime_unpin(struct drm_gem_object *obj) { if (!obj->import_attach) - msm_gem_put_pages(obj); + msm_gem_unpin_pages(obj); } diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 0317055e3253..1de14e67f96b 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -24,103 +24,77 @@ static bool can_swap(void) return enable_eviction && get_nr_swap_pages() > 0; } +static bool can_block(struct shrink_control *sc) +{ + if (!(sc->gfp_mask & __GFP_DIRECT_RECLAIM)) + return false; + return current_is_kswapd() || (sc->gfp_mask & __GFP_RECLAIM); +} + static unsigned long msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc) { struct msm_drm_private *priv = container_of(shrinker, struct msm_drm_private, shrinker); - unsigned count = priv->shrinkable_count; + unsigned count = priv->lru.dontneed.count; if (can_swap()) - count += priv->evictable_count; + count += priv->lru.willneed.count; return count; } static bool -purge(struct msm_gem_object *msm_obj) +purge(struct drm_gem_object *obj) { - if (!is_purgeable(msm_obj)) + if (!is_purgeable(to_msm_bo(obj))) return false; - /* - * This will move the obj out of still_in_list to - * the purged list - */ - msm_gem_purge(&msm_obj->base); + if (msm_gem_active(obj)) + return false; + + msm_gem_purge(obj); return true; } static bool -evict(struct msm_gem_object *msm_obj) +evict(struct drm_gem_object *obj) { - if (is_unevictable(msm_obj)) + if (is_unevictable(to_msm_bo(obj))) + return false; + + if (msm_gem_active(obj)) return false; - msm_gem_evict(&msm_obj->base); + msm_gem_evict(obj); return true; } -static unsigned long -scan(struct msm_drm_private *priv, unsigned nr_to_scan, struct list_head *list, - bool (*shrink)(struct msm_gem_object *msm_obj)) +static bool +wait_for_idle(struct drm_gem_object *obj) { - unsigned freed = 0; - struct list_head still_in_list; - - INIT_LIST_HEAD(&still_in_list); - - mutex_lock(&priv->mm_lock); - - while (freed < nr_to_scan) { - struct msm_gem_object *msm_obj = list_first_entry_or_null( - list, typeof(*msm_obj), mm_list); - - if (!msm_obj) - break; - - list_move_tail(&msm_obj->mm_list, &still_in_list); - - /* - * If it is in the process of being freed, msm_gem_free_object - * can be blocked on mm_lock waiting to remove it. So just - * skip it. - */ - if (!kref_get_unless_zero(&msm_obj->base.refcount)) - continue; - - /* - * Now that we own a reference, we can drop mm_lock for the - * rest of the loop body, to reduce contention with the - * retire_submit path (which could make more objects purgeable) - */ - - mutex_unlock(&priv->mm_lock); - - /* - * Note that this still needs to be trylock, since we can - * hit shrinker in response to trying to get backing pages - * for this obj (ie. while it's lock is already held) - */ - if (!msm_gem_trylock(&msm_obj->base)) - goto tail; - - if (shrink(msm_obj)) - freed += msm_obj->base.size >> PAGE_SHIFT; + enum dma_resv_usage usage = dma_resv_usage_rw(true); + return dma_resv_wait_timeout(obj->resv, usage, false, 1000) > 0; +} - msm_gem_unlock(&msm_obj->base); +static bool +active_purge(struct drm_gem_object *obj) +{ + if (!wait_for_idle(obj)) + return false; -tail: - drm_gem_object_put(&msm_obj->base); - mutex_lock(&priv->mm_lock); - } + return purge(obj); +} - list_splice_tail(&still_in_list, list); - mutex_unlock(&priv->mm_lock); +static bool +active_evict(struct drm_gem_object *obj) +{ + if (!wait_for_idle(obj)) + return false; - return freed; + return evict(obj); } static unsigned long @@ -128,21 +102,34 @@ msm_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc) { struct msm_drm_private *priv = container_of(shrinker, struct msm_drm_private, shrinker); - unsigned long freed; - - freed = scan(priv, sc->nr_to_scan, &priv->inactive_dontneed, purge); - - if (freed > 0) - trace_msm_gem_purge(freed << PAGE_SHIFT); - - if (can_swap() && freed < sc->nr_to_scan) { - int evicted = scan(priv, sc->nr_to_scan - freed, - &priv->inactive_willneed, evict); + struct { + struct drm_gem_lru *lru; + bool (*shrink)(struct drm_gem_object *obj); + bool cond; + unsigned long freed; + } stages[] = { + /* Stages of progressively more aggressive/expensive reclaim: */ + { &priv->lru.dontneed, purge, true }, + { &priv->lru.willneed, evict, can_swap() }, + { &priv->lru.dontneed, active_purge, can_block(sc) }, + { &priv->lru.willneed, active_evict, can_swap() && can_block(sc) }, + }; + long nr = sc->nr_to_scan; + unsigned long freed = 0; - if (evicted > 0) - trace_msm_gem_evict(evicted << PAGE_SHIFT); + for (unsigned i = 0; (nr > 0) && (i < ARRAY_SIZE(stages)); i++) { + if (!stages[i].cond) + continue; + stages[i].freed = + drm_gem_lru_scan(stages[i].lru, nr, stages[i].shrink); + nr -= stages[i].freed; + freed += stages[i].freed; + } - freed += evicted; + if (freed) { + trace_msm_gem_shrink(sc->nr_to_scan, stages[0].freed, + stages[1].freed, stages[2].freed, + stages[3].freed); } return (freed > 0) ? freed : SHRINK_STOP; @@ -173,12 +160,12 @@ msm_gem_shrinker_shrink(struct drm_device *dev, unsigned long nr_to_scan) static const int vmap_shrink_limit = 15; static bool -vmap_shrink(struct msm_gem_object *msm_obj) +vmap_shrink(struct drm_gem_object *obj) { - if (!is_vunmapable(msm_obj)) + if (!is_vunmapable(to_msm_bo(obj))) return false; - msm_gem_vunmap(&msm_obj->base); + msm_gem_vunmap(obj); return true; } @@ -188,17 +175,18 @@ msm_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr) { struct msm_drm_private *priv = container_of(nb, struct msm_drm_private, vmap_notifier); - struct list_head *mm_lists[] = { - &priv->inactive_dontneed, - &priv->inactive_willneed, - priv->gpu ? &priv->gpu->active_list : NULL, + struct drm_gem_lru *lrus[] = { + &priv->lru.dontneed, + &priv->lru.willneed, + &priv->lru.pinned, NULL, }; unsigned idx, unmapped = 0; - for (idx = 0; mm_lists[idx] && unmapped < vmap_shrink_limit; idx++) { - unmapped += scan(priv, vmap_shrink_limit - unmapped, - mm_lists[idx], vmap_shrink); + for (idx = 0; lrus[idx] && unmapped < vmap_shrink_limit; idx++) { + unmapped += drm_gem_lru_scan(lrus[idx], + vmap_shrink_limit - unmapped, + vmap_shrink); } *(unsigned long *)ptr += unmapped; diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c index c9e4aeb14f4a..5599d93ec0d2 100644 --- a/drivers/gpu/drm/msm/msm_gem_submit.c +++ b/drivers/gpu/drm/msm/msm_gem_submit.c @@ -26,6 +26,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, struct msm_gpu_submitqueue *queue, uint32_t nr_bos, uint32_t nr_cmds) { + static atomic_t ident = ATOMIC_INIT(0); struct msm_gem_submit *submit; uint64_t sz; int ret; @@ -36,7 +37,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, if (sz > SIZE_MAX) return ERR_PTR(-ENOMEM); - submit = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + submit = kzalloc(sz, GFP_KERNEL); if (!submit) return ERR_PTR(-ENOMEM); @@ -52,9 +53,13 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev, submit->gpu = gpu; submit->cmd = (void *)&submit->bos[nr_bos]; submit->queue = queue; + submit->pid = get_pid(task_pid(current)); submit->ring = gpu->rb[queue->ring_nr]; submit->fault_dumped = false; + /* Get a unique identifier for the submission for logging purposes */ + submit->ident = atomic_inc_return(&ident) - 1; + INIT_LIST_HEAD(&submit->node); return submit; @@ -67,9 +72,9 @@ void __msm_gem_submit_destroy(struct kref *kref) unsigned i; if (submit->fence_id) { - mutex_lock(&submit->queue->lock); + mutex_lock(&submit->queue->idr_lock); idr_remove(&submit->queue->fence_idr, submit->fence_id); - mutex_unlock(&submit->queue->lock); + mutex_unlock(&submit->queue->idr_lock); } dma_fence_put(submit->user_fence); @@ -238,17 +243,13 @@ static void submit_cleanup_bo(struct msm_gem_submit *submit, int i, if (flags & BO_OBJ_PINNED) msm_gem_unpin_locked(obj); - if (flags & BO_ACTIVE) - msm_gem_active_put(obj); - if (flags & BO_LOCKED) dma_resv_unlock(obj->resv); } static void submit_unlock_unpin_bo(struct msm_gem_submit *submit, int i) { - unsigned cleanup_flags = BO_VMA_PINNED | BO_OBJ_PINNED | - BO_ACTIVE | BO_LOCKED; + unsigned cleanup_flags = BO_VMA_PINNED | BO_OBJ_PINNED | BO_LOCKED; submit_cleanup_bo(submit, i, cleanup_flags); if (!(submit->bos[i].flags & BO_VALID)) @@ -353,18 +354,6 @@ static int submit_pin_objects(struct msm_gem_submit *submit) submit->valid = true; - /* - * Increment active_count first, so if under memory pressure, we - * don't inadvertently evict a bo needed by the submit in order - * to pin an earlier bo in the same submit. - */ - for (i = 0; i < submit->nr_bos; i++) { - struct drm_gem_object *obj = &submit->bos[i].obj->base; - - msm_gem_active_get(obj, submit->gpu); - submit->bos[i].flags |= BO_ACTIVE; - } - for (i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = &submit->bos[i].obj->base; struct msm_gem_vma *vma; @@ -512,11 +501,11 @@ out: */ static void submit_cleanup(struct msm_gem_submit *submit, bool error) { - unsigned cleanup_flags = BO_LOCKED; + unsigned cleanup_flags = BO_LOCKED | BO_OBJ_PINNED; unsigned i; if (error) - cleanup_flags |= BO_VMA_PINNED | BO_OBJ_PINNED | BO_ACTIVE; + cleanup_flags |= BO_VMA_PINNED; for (i = 0; i < submit->nr_bos; i++) { struct msm_gem_object *msm_obj = submit->bos[i].obj; @@ -533,10 +522,6 @@ void msm_submit_retire(struct msm_gem_submit *submit) for (i = 0; i < submit->nr_bos; i++) { struct drm_gem_object *obj = &submit->bos[i].obj->base; - msm_gem_lock(obj); - /* Note, VMA already fence-unpinned before submit: */ - submit_cleanup_bo(submit, i, BO_OBJ_PINNED | BO_ACTIVE); - msm_gem_unlock(obj); drm_gem_object_put(obj); } } @@ -718,7 +703,6 @@ static void msm_process_post_deps(struct msm_submit_post_dep *post_deps, int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct drm_file *file) { - static atomic_t ident = ATOMIC_INIT(0); struct msm_drm_private *priv = dev->dev_private; struct drm_msm_gem_submit *args = data; struct msm_file_private *ctx = file->driver_priv; @@ -729,10 +713,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, struct msm_submit_post_dep *post_deps = NULL; struct drm_syncobj **syncobjs_to_reset = NULL; int out_fence_fd = -1; - struct pid *pid = get_pid(task_pid(current)); bool has_ww_ticket = false; unsigned i; - int ret, submitid; + int ret; if (!gpu) return -ENXIO; @@ -764,35 +747,26 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, if (!queue) return -ENOENT; - /* Get a unique identifier for the submission for logging purposes */ - submitid = atomic_inc_return(&ident) - 1; - ring = gpu->rb[queue->ring_nr]; - trace_msm_gpu_submit(pid_nr(pid), ring->id, submitid, - args->nr_bos, args->nr_cmds); - - ret = mutex_lock_interruptible(&queue->lock); - if (ret) - goto out_post_unlock; if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) { out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { ret = out_fence_fd; - goto out_unlock; + return ret; } } - submit = submit_create(dev, gpu, queue, args->nr_bos, - args->nr_cmds); - if (IS_ERR(submit)) { - ret = PTR_ERR(submit); - submit = NULL; - goto out_unlock; - } + submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds); + if (IS_ERR(submit)) + return PTR_ERR(submit); + + trace_msm_gpu_submit(pid_nr(submit->pid), ring->id, submit->ident, + args->nr_bos, args->nr_cmds); - submit->pid = pid; - submit->ident = submitid; + ret = mutex_lock_interruptible(&queue->lock); + if (ret) + goto out_post_unlock; if (args->flags & MSM_SUBMIT_SUDO) submit->in_rb = true; @@ -887,6 +861,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, submit->nr_cmds = i; + mutex_lock(&queue->idr_lock); + /* * If using userspace provided seqno fence, validate that the id * is available before arming sched job. Since access to fence_idr @@ -895,6 +871,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, */ if ((args->flags & MSM_SUBMIT_FENCE_SN_IN) && idr_find(&queue->fence_idr, args->fence)) { + mutex_unlock(&queue->idr_lock); ret = -EINVAL; goto out; } @@ -927,6 +904,9 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data, submit->user_fence, 1, INT_MAX, GFP_KERNEL); } + + mutex_unlock(&queue->idr_lock); + if (submit->fence_id < 0) { ret = submit->fence_id; submit->fence_id = 0; @@ -965,9 +945,9 @@ out_unlock: if (ret && (out_fence_fd >= 0)) put_unused_fd(out_fence_fd); mutex_unlock(&queue->lock); +out_post_unlock: if (submit) msm_gem_submit_put(submit); -out_post_unlock: if (!IS_ERR_OR_NULL(post_deps)) { for (i = 0; i < args->nr_out_syncobjs; ++i) { kfree(post_deps[i].chain); diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index c2bfcf3f1f40..0098ee8438aa 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -16,6 +16,7 @@ #include <generated/utsrelease.h> #include <linux/string_helpers.h> #include <linux/devcoredump.h> +#include <linux/reset.h> #include <linux/sched/task.h> /* @@ -394,7 +395,6 @@ static void recover_worker(struct kthread_work *work) /* Record the crash state */ pm_runtime_get_sync(&gpu->pdev->dev); msm_gpu_crashstate_capture(gpu, submit, comm, cmd); - pm_runtime_put_sync(&gpu->pdev->dev); kfree(cmd); kfree(comm); @@ -423,9 +423,7 @@ static void recover_worker(struct kthread_work *work) /* retire completed submits, plus the one that hung: */ retire_submits(gpu); - pm_runtime_get_sync(&gpu->pdev->dev); gpu->funcs->recover(gpu); - pm_runtime_put_sync(&gpu->pdev->dev); /* * Replay all remaining submits starting with highest priority @@ -442,6 +440,8 @@ static void recover_worker(struct kthread_work *work) } } + pm_runtime_put(&gpu->pdev->dev); + mutex_unlock(&gpu->lock); msm_gpu_retire(gpu); @@ -664,11 +664,12 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring, mutex_lock(&gpu->active_lock); gpu->active_submits--; WARN_ON(gpu->active_submits < 0); - if (!gpu->active_submits) + if (!gpu->active_submits) { msm_devfreq_idle(gpu); - mutex_unlock(&gpu->active_lock); + pm_runtime_put_autosuspend(&gpu->pdev->dev); + } - pm_runtime_put_autosuspend(&gpu->pdev->dev); + mutex_unlock(&gpu->active_lock); msm_gem_submit_put(submit); } @@ -757,14 +758,17 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) /* Update devfreq on transition from idle->active: */ mutex_lock(&gpu->active_lock); - if (!gpu->active_submits) + if (!gpu->active_submits) { + pm_runtime_get(&gpu->pdev->dev); msm_devfreq_active(gpu); + } gpu->active_submits++; mutex_unlock(&gpu->active_lock); gpu->funcs->submit(gpu, submit); gpu->cur_ctx_seqno = submit->queue->ctx->seqno; + pm_runtime_put(&gpu->pdev->dev); hangcheck_timer_reset(gpu); } @@ -846,7 +850,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, sched_set_fifo_low(gpu->worker->task); - INIT_LIST_HEAD(&gpu->active_list); mutex_init(&gpu->active_lock); mutex_init(&gpu->lock); init_waitqueue_head(&gpu->retire_event); @@ -901,6 +904,9 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, if (IS_ERR(gpu->gpu_cx)) gpu->gpu_cx = NULL; + gpu->cx_collapse = devm_reset_control_get_optional_exclusive(&pdev->dev, + "cx_collapse"); + gpu->pdev = pdev; platform_set_drvdata(pdev, &gpu->adreno_smmu); @@ -974,8 +980,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu) DBG("%s", gpu->name); - WARN_ON(!list_empty(&gpu->active_list)); - for (i = 0; i < ARRAY_SIZE(gpu->rb); i++) { msm_ringbuffer_destroy(gpu->rb[i]); gpu->rb[i] = NULL; diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 4d935fedd2ac..ff911e7305ce 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -13,6 +13,7 @@ #include <linux/interconnect.h> #include <linux/pm_opp.h> #include <linux/regulator/consumer.h> +#include <linux/reset.h> #include "msm_drv.h" #include "msm_fence.h" @@ -187,12 +188,6 @@ struct msm_gpu { */ int cur_ctx_seqno; - /* - * List of GEM active objects on this gpu. Protected by - * msm_drm_private::mm_lock - */ - struct list_head active_list; - /** * lock: * @@ -277,6 +272,9 @@ struct msm_gpu { bool hw_apriv; struct thermal_cooling_device *cooling; + + /* To poll for cx gdsc collapse during gpu recovery */ + struct reset_control *cx_collapse; }; static inline struct msm_gpu *dev_to_gpu(struct device *dev) @@ -466,7 +464,8 @@ static inline int msm_gpu_convert_priority(struct msm_gpu *gpu, int prio, * @node: node in the context's list of submitqueues * @fence_idr: maps fence-id to dma_fence for userspace visible fence * seqno, protected by submitqueue lock - * @lock: submitqueue lock + * @idr_lock: for serializing access to fence_idr + * @lock: submitqueue lock for serializing submits on a queue * @ref: reference count * @entity: the submit job-queue */ @@ -479,6 +478,7 @@ struct msm_gpu_submitqueue { struct msm_file_private *ctx; struct list_head node; struct idr fence_idr; + struct mutex idr_lock; struct mutex lock; struct kref ref; struct drm_sched_entity *entity; diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index d1f70426f554..85c443a37e4e 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -213,6 +213,8 @@ void msm_devfreq_init(struct msm_gpu *gpu) if (IS_ERR(df->devfreq)) { DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n"); + dev_pm_qos_remove_request(&df->idle_freq); + dev_pm_qos_remove_request(&df->boost_freq); df->devfreq = NULL; return; } diff --git a/drivers/gpu/drm/msm/msm_gpu_trace.h b/drivers/gpu/drm/msm/msm_gpu_trace.h index ca0b08d7875b..ac40d857bc45 100644 --- a/drivers/gpu/drm/msm/msm_gpu_trace.h +++ b/drivers/gpu/drm/msm/msm_gpu_trace.h @@ -115,29 +115,27 @@ TRACE_EVENT(msm_gmu_freq_change, ); -TRACE_EVENT(msm_gem_purge, - TP_PROTO(u32 bytes), - TP_ARGS(bytes), +TRACE_EVENT(msm_gem_shrink, + TP_PROTO(u32 nr_to_scan, u32 purged, u32 evicted, + u32 active_purged, u32 active_evicted), + TP_ARGS(nr_to_scan, purged, evicted, active_purged, active_evicted), TP_STRUCT__entry( - __field(u32, bytes) + __field(u32, nr_to_scan) + __field(u32, purged) + __field(u32, evicted) + __field(u32, active_purged) + __field(u32, active_evicted) ), TP_fast_assign( - __entry->bytes = bytes; + __entry->nr_to_scan = nr_to_scan; + __entry->purged = purged; + __entry->evicted = evicted; + __entry->active_purged = active_purged; + __entry->active_evicted = active_evicted; ), - TP_printk("Purging %u bytes", __entry->bytes) -); - - -TRACE_EVENT(msm_gem_evict, - TP_PROTO(u32 bytes), - TP_ARGS(bytes), - TP_STRUCT__entry( - __field(u32, bytes) - ), - TP_fast_assign( - __entry->bytes = bytes; - ), - TP_printk("Evicting %u bytes", __entry->bytes) + TP_printk("nr_to_scan=%u pg, purged=%u pg, evicted=%u pg, active_purged=%u pg, active_evicted=%u pg", + __entry->nr_to_scan, __entry->purged, __entry->evicted, + __entry->active_purged, __entry->active_evicted) ); diff --git a/drivers/gpu/drm/msm/msm_io_utils.c b/drivers/gpu/drm/msm/msm_io_utils.c index 7b504617833a..d02cd29ce829 100644 --- a/drivers/gpu/drm/msm/msm_io_utils.c +++ b/drivers/gpu/drm/msm/msm_io_utils.c @@ -5,6 +5,8 @@ * Author: Rob Clark <robdclark@gmail.com> */ +#include <linux/interconnect.h> + #include "msm_drv.h" /* @@ -124,3 +126,23 @@ void msm_hrtimer_work_init(struct msm_hrtimer_work *work, work->worker = worker; kthread_init_work(&work->work, fn); } + +struct icc_path *msm_icc_get(struct device *dev, const char *name) +{ + struct device *mdss_dev = dev->parent; + struct icc_path *path; + + path = of_icc_get(dev, name); + if (path) + return path; + + /* + * If there are no interconnects attached to the corresponding device + * node, of_icc_get() will return NULL. + * + * If the MDP5/DPU device node doesn't have interconnects, lookup the + * path in the parent (MDSS) device. + */ + return of_icc_get(mdss_dev, name); + +} diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c index a54ed354578b..5577cea7c009 100644 --- a/drivers/gpu/drm/msm/msm_iommu.c +++ b/drivers/gpu/drm/msm/msm_iommu.c @@ -21,6 +21,7 @@ struct msm_iommu_pagetable { struct msm_mmu base; struct msm_mmu *parent; struct io_pgtable_ops *pgtbl_ops; + unsigned long pgsize_bitmap; /* Bitmap of page sizes in use */ phys_addr_t ttbr; u32 asid; }; @@ -29,23 +30,84 @@ static struct msm_iommu_pagetable *to_pagetable(struct msm_mmu *mmu) return container_of(mmu, struct msm_iommu_pagetable, base); } +/* based on iommu_pgsize() in iommu.c: */ +static size_t calc_pgsize(struct msm_iommu_pagetable *pagetable, + unsigned long iova, phys_addr_t paddr, + size_t size, size_t *count) +{ + unsigned int pgsize_idx, pgsize_idx_next; + unsigned long pgsizes; + size_t offset, pgsize, pgsize_next; + unsigned long addr_merge = paddr | iova; + + /* Page sizes supported by the hardware and small enough for @size */ + pgsizes = pagetable->pgsize_bitmap & GENMASK(__fls(size), 0); + + /* Constrain the page sizes further based on the maximum alignment */ + if (likely(addr_merge)) + pgsizes &= GENMASK(__ffs(addr_merge), 0); + + /* Make sure we have at least one suitable page size */ + BUG_ON(!pgsizes); + + /* Pick the biggest page size remaining */ + pgsize_idx = __fls(pgsizes); + pgsize = BIT(pgsize_idx); + if (!count) + return pgsize; + + /* Find the next biggest support page size, if it exists */ + pgsizes = pagetable->pgsize_bitmap & ~GENMASK(pgsize_idx, 0); + if (!pgsizes) + goto out_set_count; + + pgsize_idx_next = __ffs(pgsizes); + pgsize_next = BIT(pgsize_idx_next); + + /* + * There's no point trying a bigger page size unless the virtual + * and physical addresses are similarly offset within the larger page. + */ + if ((iova ^ paddr) & (pgsize_next - 1)) + goto out_set_count; + + /* Calculate the offset to the next page size alignment boundary */ + offset = pgsize_next - (addr_merge & (pgsize_next - 1)); + + /* + * If size is big enough to accommodate the larger page, reduce + * the number of smaller pages. + */ + if (offset + pgsize_next <= size) + size = offset; + +out_set_count: + *count = size >> pgsize_idx; + return pgsize; +} + static int msm_iommu_pagetable_unmap(struct msm_mmu *mmu, u64 iova, size_t size) { struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); struct io_pgtable_ops *ops = pagetable->pgtbl_ops; - size_t unmapped = 0; - /* Unmap the block one page at a time */ while (size) { - unmapped += ops->unmap(ops, iova, 4096, NULL); - iova += 4096; - size -= 4096; + size_t unmapped, pgsize, count; + + pgsize = calc_pgsize(pagetable, iova, iova, size, &count); + + unmapped = ops->unmap_pages(ops, iova, pgsize, count, NULL); + if (!unmapped) + break; + + iova += unmapped; + size -= unmapped; } iommu_flush_iotlb_all(to_msm_iommu(pagetable->parent)->domain); - return (unmapped == size) ? 0 : -EINVAL; + return (size == 0) ? 0 : -EINVAL; } static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova, @@ -54,7 +116,6 @@ static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova, struct msm_iommu_pagetable *pagetable = to_pagetable(mmu); struct io_pgtable_ops *ops = pagetable->pgtbl_ops; struct scatterlist *sg; - size_t mapped = 0; u64 addr = iova; unsigned int i; @@ -62,17 +123,26 @@ static int msm_iommu_pagetable_map(struct msm_mmu *mmu, u64 iova, size_t size = sg->length; phys_addr_t phys = sg_phys(sg); - /* Map the block one page at a time */ while (size) { - if (ops->map(ops, addr, phys, 4096, prot, GFP_KERNEL)) { - msm_iommu_pagetable_unmap(mmu, iova, mapped); + size_t pgsize, count, mapped = 0; + int ret; + + pgsize = calc_pgsize(pagetable, addr, phys, size, &count); + + ret = ops->map_pages(ops, addr, phys, pgsize, count, + prot, GFP_KERNEL, &mapped); + + /* map_pages could fail after mapping some of the pages, + * so update the counters before error handling. + */ + phys += mapped; + addr += mapped; + size -= mapped; + + if (ret) { + msm_iommu_pagetable_unmap(mmu, iova, addr - iova); return -EINVAL; } - - phys += 4096; - addr += 4096; - size -= 4096; - mapped += 4096; } } @@ -207,6 +277,7 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent) /* Needed later for TLB flush */ pagetable->parent = parent; + pagetable->pgsize_bitmap = ttbr0_cfg.pgsize_bitmap; pagetable->ttbr = ttbr0_cfg.arm_lpae_s1_cfg.ttbr; /* diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c index a92ffde53f0b..db2f847c8535 100644 --- a/drivers/gpu/drm/msm/msm_rd.c +++ b/drivers/gpu/drm/msm/msm_rd.c @@ -196,6 +196,9 @@ static int rd_open(struct inode *inode, struct file *file) file->private_data = rd; rd->open = true; + /* Reset fifo to clear any previously unread data: */ + rd->fifo.head = rd->fifo.tail = 0; + /* the parsing tools need to know gpu-id to know which * register database to load. * diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 56eecb4a72dc..cad4c3525f0b 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -29,8 +29,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) msm_gem_unlock(obj); } - pm_runtime_get_sync(&gpu->pdev->dev); - /* TODO move submit path over to using a per-ring lock.. */ mutex_lock(&gpu->lock); @@ -38,8 +36,6 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job) mutex_unlock(&gpu->lock); - pm_runtime_put(&gpu->pdev->dev); - return dma_fence_get(submit->hw_fence); } diff --git a/drivers/gpu/drm/msm/msm_submitqueue.c b/drivers/gpu/drm/msm/msm_submitqueue.c index f486a3cd4e55..c6929e205b51 100644 --- a/drivers/gpu/drm/msm/msm_submitqueue.c +++ b/drivers/gpu/drm/msm/msm_submitqueue.c @@ -200,6 +200,7 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_file_private *ctx, *id = queue->id; idr_init(&queue->fence_idr); + mutex_init(&queue->idr_lock); mutex_init(&queue->lock); list_add_tail(&queue->node, &ctx->submitqueues); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 35bb0bb3fe61..126b3c6e12f9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -822,6 +822,15 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, if (ret == 0) { ret = nouveau_fence_new(chan, false, &fence); if (ret == 0) { + /* TODO: figure out a better solution here + * + * wait on the fence here explicitly as going through + * ttm_bo_move_accel_cleanup somehow doesn't seem to do it. + * + * Without this the operation can timeout and we'll fallback to a + * software copy, which might take several minutes to finish. + */ + nouveau_fence_wait(fence, false, false); ret = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false, diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 16356611b5b9..5fe209107246 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -139,44 +139,24 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence) } } -static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, - struct vm_fault *vmf, struct migrate_vma *args, - dma_addr_t *dma_addr) +static int nouveau_dmem_copy_one(struct nouveau_drm *drm, struct page *spage, + struct page *dpage, dma_addr_t *dma_addr) { struct device *dev = drm->dev->dev; - struct page *dpage, *spage; - struct nouveau_svmm *svmm; - - spage = migrate_pfn_to_page(args->src[0]); - if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) - return 0; - dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); - if (!dpage) - return VM_FAULT_SIGBUS; lock_page(dpage); *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) - goto error_free_page; + return -EIO; - svmm = spage->zone_device_data; - mutex_lock(&svmm->mutex); - nouveau_svmm_invalidate(svmm, args->start, args->end); if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, - NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) - goto error_dma_unmap; - mutex_unlock(&svmm->mutex); + NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) { + dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + return -EIO; + } - args->dst[0] = migrate_pfn(page_to_pfn(dpage)); return 0; - -error_dma_unmap: - mutex_unlock(&svmm->mutex); - dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); -error_free_page: - __free_page(dpage); - return VM_FAULT_SIGBUS; } static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) @@ -184,9 +164,11 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) struct nouveau_drm *drm = page_to_drm(vmf->page); struct nouveau_dmem *dmem = drm->dmem; struct nouveau_fence *fence; + struct nouveau_svmm *svmm; + struct page *spage, *dpage; unsigned long src = 0, dst = 0; dma_addr_t dma_addr = 0; - vm_fault_t ret; + vm_fault_t ret = 0; struct migrate_vma args = { .vma = vmf->vma, .start = vmf->address, @@ -207,9 +189,25 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) if (!args.cpages) return 0; - ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr); - if (ret || dst == 0) + spage = migrate_pfn_to_page(src); + if (!spage || !(src & MIGRATE_PFN_MIGRATE)) + goto done; + + dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + if (!dpage) + goto done; + + dst = migrate_pfn(page_to_pfn(dpage)); + + svmm = spage->zone_device_data; + mutex_lock(&svmm->mutex); + nouveau_svmm_invalidate(svmm, args.start, args.end); + ret = nouveau_dmem_copy_one(drm, spage, dpage, &dma_addr); + mutex_unlock(&svmm->mutex); + if (ret) { + ret = VM_FAULT_SIGBUS; goto done; + } nouveau_fence_new(dmem->migrate.chan, false, &fence); migrate_vma_pages(&args); @@ -326,7 +324,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) return NULL; } - lock_page(page); + zone_device_page_init(page); return page; } @@ -369,6 +367,52 @@ nouveau_dmem_suspend(struct nouveau_drm *drm) mutex_unlock(&drm->dmem->mutex); } +/* + * Evict all pages mapping a chunk. + */ +static void +nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) +{ + unsigned long i, npages = range_len(&chunk->pagemap.range) >> PAGE_SHIFT; + unsigned long *src_pfns, *dst_pfns; + dma_addr_t *dma_addrs; + struct nouveau_fence *fence; + + src_pfns = kcalloc(npages, sizeof(*src_pfns), GFP_KERNEL); + dst_pfns = kcalloc(npages, sizeof(*dst_pfns), GFP_KERNEL); + dma_addrs = kcalloc(npages, sizeof(*dma_addrs), GFP_KERNEL); + + migrate_device_range(src_pfns, chunk->pagemap.range.start >> PAGE_SHIFT, + npages); + + for (i = 0; i < npages; i++) { + if (src_pfns[i] & MIGRATE_PFN_MIGRATE) { + struct page *dpage; + + /* + * _GFP_NOFAIL because the GPU is going away and there + * is nothing sensible we can do if we can't copy the + * data back. + */ + dpage = alloc_page(GFP_HIGHUSER | __GFP_NOFAIL); + dst_pfns[i] = migrate_pfn(page_to_pfn(dpage)); + nouveau_dmem_copy_one(chunk->drm, + migrate_pfn_to_page(src_pfns[i]), dpage, + &dma_addrs[i]); + } + } + + nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence); + migrate_device_pages(src_pfns, dst_pfns, npages); + nouveau_dmem_fence_done(&fence); + migrate_device_finalize(src_pfns, dst_pfns, npages); + kfree(src_pfns); + kfree(dst_pfns); + for (i = 0; i < npages; i++) + dma_unmap_page(chunk->drm->dev->dev, dma_addrs[i], PAGE_SIZE, DMA_BIDIRECTIONAL); + kfree(dma_addrs); +} + void nouveau_dmem_fini(struct nouveau_drm *drm) { @@ -380,8 +424,10 @@ nouveau_dmem_fini(struct nouveau_drm *drm) mutex_lock(&drm->dmem->mutex); list_for_each_entry_safe(chunk, tmp, &drm->dmem->chunks, list) { + nouveau_dmem_evict_chunk(chunk); nouveau_bo_unpin(chunk->bo); nouveau_bo_ref(NULL, &chunk->bo); + WARN_ON(chunk->callocated); list_del(&chunk->list); memunmap_pages(&chunk->pagemap); release_mem_region(chunk->pagemap.range.start, diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 561309d447e0..fd99ec0f4257 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -28,6 +28,7 @@ #include <linux/pm_runtime.h> #include <linux/vga_switcheroo.h> #include <linux/mmu_notifier.h> +#include <linux/dynamic_debug.h> #include <drm/drm_aperture.h> #include <drm/drm_crtc_helper.h> @@ -70,6 +71,18 @@ #include "nouveau_svm.h" #include "nouveau_dmem.h" +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"); + MODULE_PARM_DESC(config, "option string to pass to driver core"); static char *nouveau_config; module_param_named(config, nouveau_config, charp, 0400); diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index 4b546b02d3ae..4b39d1dd9140 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -1285,7 +1285,8 @@ static const struct panel_desc innolux_n116bca_ea1 = { }, .delay = { .hpd_absent = 200, - .prepare_to_enable = 80, + .enable = 80, + .disable = 50, .unprepare = 500, }, }; diff --git a/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c b/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c index cb5cb27462df..36a46cb7fe1c 100644 --- a/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c +++ b/drivers/gpu/drm/panel/panel-olimex-lcd-olinuxino.c @@ -288,7 +288,7 @@ static int lcd_olinuxino_probe(struct i2c_client *client, return 0; } -static int lcd_olinuxino_remove(struct i2c_client *client) +static void lcd_olinuxino_remove(struct i2c_client *client) { struct lcd_olinuxino *panel = i2c_get_clientdata(client); @@ -296,8 +296,6 @@ static int lcd_olinuxino_remove(struct i2c_client *client) drm_panel_disable(&panel->panel); drm_panel_unprepare(&panel->panel); - - return 0; } static const struct of_device_id lcd_olinuxino_of_ids[] = { diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c index a6dc5ab182fa..79f852465a84 100644 --- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c +++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c @@ -446,7 +446,7 @@ error: return -ENODEV; } -static int rpi_touchscreen_remove(struct i2c_client *i2c) +static void rpi_touchscreen_remove(struct i2c_client *i2c) { struct rpi_touchscreen *ts = i2c_get_clientdata(i2c); @@ -455,8 +455,6 @@ static int rpi_touchscreen_remove(struct i2c_client *i2c) drm_panel_remove(&ts->base); mipi_dsi_device_unregister(ts->dsi); - - return 0; } static int rpi_touchscreen_dsi_probe(struct mipi_dsi_device *dsi) diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 252fd66011cc..2944228a8e2c 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2252,7 +2252,7 @@ static const struct panel_desc innolux_g121i1_l01 = { .enable = 200, .disable = 20, }, - .bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG, + .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, .connector_type = DRM_MODE_CONNECTOR_LVDS, }; diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c index 5110cd9b2425..fe5f12f16a63 100644 --- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c +++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c @@ -131,6 +131,17 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev) return PTR_ERR(opp); panfrost_devfreq_profile.initial_freq = cur_freq; + + /* + * Set the recommend OPP this will enable and configure the regulator + * if any and will avoid a switch off by regulator_late_cleanup() + */ + ret = dev_pm_opp_set_opp(dev, opp); + if (ret) { + DRM_DEV_ERROR(dev, "Couldn't set recommended OPP\n"); + return ret; + } + dev_pm_opp_put(opp); /* diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index ac006bed4743..8ef25ab305ae 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -2056,7 +2056,7 @@ static void ci_clear_vc(struct radeon_device *rdev) static int ci_upload_firmware(struct radeon_device *rdev) { struct ci_power_info *pi = ci_get_pi(rdev); - int i, ret; + int i; for (i = 0; i < rdev->usec_timeout; i++) { if (RREG32_SMC(RCU_UC_EVENTS) & BOOT_SEQ_DONE) @@ -2067,9 +2067,7 @@ static int ci_upload_firmware(struct radeon_device *rdev) ci_stop_smc_clock(rdev); ci_reset_smc(rdev); - ret = ci_load_smc_ucode(rdev, pi->sram_end); - - return ret; + return ci_load_smc_ucode(rdev, pi->sram_end); } diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c index a28d5ceab628..6cbe1ab81aba 100644 --- a/drivers/gpu/drm/radeon/radeon_drv.c +++ b/drivers/gpu/drm/radeon/radeon_drv.c @@ -512,14 +512,11 @@ long radeon_drm_ioctl(struct file *filp, static long radeon_kms_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { unsigned int nr = DRM_IOCTL_NR(cmd); - int ret; if (nr < DRM_COMMAND_BASE) return drm_compat_ioctl(filp, cmd, arg); - ret = radeon_drm_ioctl(filp, cmd, arg); - - return ret; + return radeon_drm_ioctl(filp, cmd, arg); } #endif diff --git a/drivers/gpu/drm/rcar-du/Makefile b/drivers/gpu/drm/rcar-du/Makefile index e7275b5e7ec8..6f132325c8b7 100644 --- a/drivers/gpu/drm/rcar-du/Makefile +++ b/drivers/gpu/drm/rcar-du/Makefile @@ -14,10 +14,3 @@ obj-$(CONFIG_DRM_RCAR_DU) += rcar-du-drm.o obj-$(CONFIG_DRM_RCAR_DW_HDMI) += rcar_dw_hdmi.o obj-$(CONFIG_DRM_RCAR_LVDS) += rcar_lvds.o obj-$(CONFIG_DRM_RCAR_MIPI_DSI) += rcar_mipi_dsi.o - -# 'remote-endpoint' is fixed up at run-time -DTC_FLAGS_rcar_du_of_lvds_r8a7790 += -Wno-graph_endpoint -DTC_FLAGS_rcar_du_of_lvds_r8a7791 += -Wno-graph_endpoint -DTC_FLAGS_rcar_du_of_lvds_r8a7793 += -Wno-graph_endpoint -DTC_FLAGS_rcar_du_of_lvds_r8a7795 += -Wno-graph_endpoint -DTC_FLAGS_rcar_du_of_lvds_r8a7796 += -Wno-graph_endpoint diff --git a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c index fd3b94649a01..3619e1ddeb62 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_crtc.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_crtc.c @@ -29,6 +29,7 @@ #include "rcar_du_regs.h" #include "rcar_du_vsp.h" #include "rcar_lvds.h" +#include "rcar_mipi_dsi.h" static u32 rcar_du_crtc_read(struct rcar_du_crtc *rcrtc, u32 reg) { @@ -744,7 +745,19 @@ static void rcar_du_crtc_atomic_enable(struct drm_crtc *crtc, const struct drm_display_mode *mode = &crtc->state->adjusted_mode; - rcar_lvds_clk_enable(bridge, mode->clock * 1000); + rcar_lvds_pclk_enable(bridge, mode->clock * 1000); + } + + /* + * Similarly to LVDS, on V3U the dot clock is provided by the DSI + * encoder, and we need to enable the DSI clocks before enabling the CRTC. + */ + if ((rcdu->info->dsi_clk_mask & BIT(rcrtc->index)) && + (rstate->outputs & + (BIT(RCAR_DU_OUTPUT_DSI0) | BIT(RCAR_DU_OUTPUT_DSI1)))) { + struct drm_bridge *bridge = rcdu->dsi[rcrtc->index]; + + rcar_mipi_dsi_pclk_enable(bridge, state); } rcar_du_crtc_start(rcrtc); @@ -777,7 +790,20 @@ static void rcar_du_crtc_atomic_disable(struct drm_crtc *crtc, * Disable the LVDS clock output, see * rcar_du_crtc_atomic_enable(). */ - rcar_lvds_clk_disable(bridge); + rcar_lvds_pclk_disable(bridge); + } + + if ((rcdu->info->dsi_clk_mask & BIT(rcrtc->index)) && + (rstate->outputs & + (BIT(RCAR_DU_OUTPUT_DSI0) | BIT(RCAR_DU_OUTPUT_DSI1)))) { + struct drm_bridge *bridge = rcdu->dsi[rcrtc->index]; + + /* + * Disable the DSI clock output, see + * rcar_du_crtc_atomic_enable(). + */ + + rcar_mipi_dsi_pclk_disable(bridge); } spin_lock_irq(&crtc->dev->event_lock); diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.c b/drivers/gpu/drm/rcar-du/rcar_du_drv.c index 00ac233a115e..a2776f1d6f2c 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.c @@ -27,7 +27,6 @@ #include "rcar_du_drv.h" #include "rcar_du_kms.h" -#include "rcar_du_regs.h" /* ----------------------------------------------------------------------------- * Device Information @@ -507,7 +506,8 @@ static const struct rcar_du_device_info rcar_du_r8a7799x_info = { static const struct rcar_du_device_info rcar_du_r8a779a0_info = { .gen = 3, .features = RCAR_DU_FEATURE_CRTC_IRQ - | RCAR_DU_FEATURE_VSP1_SOURCE, + | RCAR_DU_FEATURE_VSP1_SOURCE + | RCAR_DU_FEATURE_NO_BLENDING, .channels_mask = BIT(1) | BIT(0), .routes = { /* R8A779A0 has two MIPI DSI outputs. */ diff --git a/drivers/gpu/drm/rcar-du/rcar_du_drv.h b/drivers/gpu/drm/rcar-du/rcar_du_drv.h index bfad7775d9a1..5cfa2bb7ad93 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_drv.h +++ b/drivers/gpu/drm/rcar-du/rcar_du_drv.h @@ -31,6 +31,7 @@ struct rcar_du_device; #define RCAR_DU_FEATURE_VSP1_SOURCE BIT(2) /* Has inputs from VSP1 */ #define RCAR_DU_FEATURE_INTERLACED BIT(3) /* HW supports interlaced */ #define RCAR_DU_FEATURE_TVM_SYNC BIT(4) /* Has TV switch/sync modes */ +#define RCAR_DU_FEATURE_NO_BLENDING BIT(5) /* PnMR.SPIM does not have ALP nor EOR bits */ #define RCAR_DU_QUIRK_ALIGN_128B BIT(0) /* Align pitches to 128 bytes */ @@ -91,6 +92,7 @@ struct rcar_du_device_info { #define RCAR_DU_MAX_GROUPS DIV_ROUND_UP(RCAR_DU_MAX_CRTCS, 2) #define RCAR_DU_MAX_VSPS 4 #define RCAR_DU_MAX_LVDS 2 +#define RCAR_DU_MAX_DSI 2 struct rcar_du_device { struct device *dev; @@ -107,6 +109,7 @@ struct rcar_du_device { struct platform_device *cmms[RCAR_DU_MAX_CRTCS]; struct rcar_du_vsp vsps[RCAR_DU_MAX_VSPS]; struct drm_bridge *lvds[RCAR_DU_MAX_LVDS]; + struct drm_bridge *dsi[RCAR_DU_MAX_DSI]; struct { struct drm_property *colorkey; diff --git a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c index 60d6be78323b..b1787be31e92 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_encoder.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_encoder.c @@ -9,18 +9,13 @@ #include <linux/export.h> #include <linux/of.h> -#include <linux/slab.h> #include <drm/drm_bridge.h> #include <drm/drm_bridge_connector.h> -#include <drm/drm_crtc.h> -#include <drm/drm_managed.h> -#include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_panel.h> #include "rcar_du_drv.h" #include "rcar_du_encoder.h" -#include "rcar_du_kms.h" #include "rcar_lvds.h" /* ----------------------------------------------------------------------------- @@ -84,6 +79,10 @@ int rcar_du_encoder_init(struct rcar_du_device *rcdu, if (output == RCAR_DU_OUTPUT_LVDS0 || output == RCAR_DU_OUTPUT_LVDS1) rcdu->lvds[output - RCAR_DU_OUTPUT_LVDS0] = bridge; + + if (output == RCAR_DU_OUTPUT_DSI0 || + output == RCAR_DU_OUTPUT_DSI1) + rcdu->dsi[output - RCAR_DU_OUTPUT_DSI0] = bridge; } /* diff --git a/drivers/gpu/drm/rcar-du/rcar_du_kms.c b/drivers/gpu/drm/rcar-du/rcar_du_kms.c index 21881fb5e84a..8c2719efda2a 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_kms.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_kms.c @@ -405,8 +405,8 @@ rcar_du_fb_create(struct drm_device *dev, struct drm_file *file_priv, format = rcar_du_format_info(mode_cmd->pixel_format); if (format == NULL) { - dev_dbg(dev->dev, "unsupported pixel format %08x\n", - mode_cmd->pixel_format); + dev_dbg(dev->dev, "unsupported pixel format %p4cc\n", + &mode_cmd->pixel_format); return ERR_PTR(-EINVAL); } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_plane.c b/drivers/gpu/drm/rcar-du/rcar_du_plane.c index 9e1f0cbbf642..d759e0192181 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_plane.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_plane.c @@ -506,8 +506,15 @@ static void rcar_du_plane_setup_format_gen3(struct rcar_du_group *rgrp, unsigned int index, const struct rcar_du_plane_state *state) { - rcar_du_plane_write(rgrp, index, PnMR, - PnMR_SPIM_TP_OFF | state->format->pnmr); + struct rcar_du_device *rcdu = rgrp->dev; + u32 pnmr = state->format->pnmr | PnMR_SPIM_TP_OFF; + + if (rcdu->info->features & RCAR_DU_FEATURE_NO_BLENDING) { + /* No blending. ALP and EOR are not supported. */ + pnmr &= ~(PnMR_SPIM_ALP | PnMR_SPIM_EOR); + } + + rcar_du_plane_write(rgrp, index, PnMR, pnmr); rcar_du_plane_write(rgrp, index, PnDDCR4, state->format->edf | PnDDCR4_CODE); @@ -521,7 +528,6 @@ static void rcar_du_plane_setup_format_gen3(struct rcar_du_group *rgrp, * register to 0 to avoid this. */ - /* TODO: Check if alpha-blending should be disabled in PnMR. */ rcar_du_plane_write(rgrp, index, PnALPHAR, 0); } @@ -619,8 +625,8 @@ int __rcar_du_plane_atomic_check(struct drm_plane *plane, *format = rcar_du_format_info(state->fb->format->format); if (*format == NULL) { - dev_dbg(dev->dev, "%s: unsupported format %08x\n", __func__, - state->fb->format->format); + dev_dbg(dev->dev, "%s: unsupported format %p4cc\n", __func__, + &state->fb->format->format); return -EINVAL; } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c index 10b7f1d0877a..e465aef41585 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_vsp.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_vsp.c @@ -152,6 +152,7 @@ static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane) .alpha = state->state.alpha >> 8, .zpos = state->state.zpos, }; + u32 fourcc = state->format->fourcc; unsigned int i; cfg.src.left = state->state.src.x1 >> 16; @@ -168,9 +169,27 @@ static void rcar_du_vsp_plane_setup(struct rcar_du_vsp_plane *plane) cfg.mem[i] = sg_dma_address(state->sg_tables[i].sgl) + fb->offsets[i]; - format = rcar_du_format_info(state->format->fourcc); + if (state->state.pixel_blend_mode == DRM_MODE_BLEND_PIXEL_NONE) { + switch (fourcc) { + case DRM_FORMAT_ARGB1555: + fourcc = DRM_FORMAT_XRGB1555; + break; + + case DRM_FORMAT_ARGB4444: + fourcc = DRM_FORMAT_XRGB4444; + break; + + case DRM_FORMAT_ARGB8888: + fourcc = DRM_FORMAT_XRGB8888; + break; + } + } + + format = rcar_du_format_info(fourcc); cfg.pixelformat = format->v4l2; + cfg.premult = state->state.pixel_blend_mode == DRM_MODE_BLEND_PREMULTI; + vsp1_du_atomic_update(plane->vsp->vsp, crtc->vsp_pipe, plane->index, &cfg); } @@ -436,6 +455,11 @@ int rcar_du_vsp_init(struct rcar_du_vsp *vsp, struct device_node *np, drm_plane_create_zpos_property(&plane->plane, i, 0, num_planes - 1); + drm_plane_create_blend_mode_property(&plane->plane, + BIT(DRM_MODE_BLEND_PIXEL_NONE) | + BIT(DRM_MODE_BLEND_PREMULTI) | + BIT(DRM_MODE_BLEND_COVERAGE)); + vsp->num_planes++; } diff --git a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c index 25f50a297c11..8cd37d7b8ae2 100644 --- a/drivers/gpu/drm/rcar-du/rcar_du_writeback.c +++ b/drivers/gpu/drm/rcar-du/rcar_du_writeback.c @@ -166,8 +166,8 @@ static int rcar_du_wb_enc_atomic_check(struct drm_encoder *encoder, wb_state->format = rcar_du_format_info(fb->format->format); if (wb_state->format == NULL) { - dev_dbg(dev->dev, "%s: unsupported format %08x\n", __func__, - fb->format->format); + dev_dbg(dev->dev, "%s: unsupported format %p4cc\n", __func__, + &fb->format->format); return -EINVAL; } diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c index d85aa4bc7f84..81a060c2fe3f 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.c +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c @@ -306,7 +306,7 @@ static void rcar_lvds_pll_setup_d3_e3(struct rcar_lvds *lvds, unsigned int freq) * Clock - D3/E3 only */ -int rcar_lvds_clk_enable(struct drm_bridge *bridge, unsigned long freq) +int rcar_lvds_pclk_enable(struct drm_bridge *bridge, unsigned long freq) { struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge); int ret; @@ -324,9 +324,9 @@ int rcar_lvds_clk_enable(struct drm_bridge *bridge, unsigned long freq) return 0; } -EXPORT_SYMBOL_GPL(rcar_lvds_clk_enable); +EXPORT_SYMBOL_GPL(rcar_lvds_pclk_enable); -void rcar_lvds_clk_disable(struct drm_bridge *bridge) +void rcar_lvds_pclk_disable(struct drm_bridge *bridge) { struct rcar_lvds *lvds = bridge_to_rcar_lvds(bridge); @@ -339,7 +339,7 @@ void rcar_lvds_clk_disable(struct drm_bridge *bridge) clk_disable_unprepare(lvds->clocks.mod); } -EXPORT_SYMBOL_GPL(rcar_lvds_clk_disable); +EXPORT_SYMBOL_GPL(rcar_lvds_pclk_disable); /* ----------------------------------------------------------------------------- * Bridge diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.h b/drivers/gpu/drm/rcar-du/rcar_lvds.h index 3097bf749bec..bee7033b60d6 100644 --- a/drivers/gpu/drm/rcar-du/rcar_lvds.h +++ b/drivers/gpu/drm/rcar-du/rcar_lvds.h @@ -13,17 +13,17 @@ struct drm_bridge; #if IS_ENABLED(CONFIG_DRM_RCAR_LVDS) -int rcar_lvds_clk_enable(struct drm_bridge *bridge, unsigned long freq); -void rcar_lvds_clk_disable(struct drm_bridge *bridge); +int rcar_lvds_pclk_enable(struct drm_bridge *bridge, unsigned long freq); +void rcar_lvds_pclk_disable(struct drm_bridge *bridge); bool rcar_lvds_dual_link(struct drm_bridge *bridge); bool rcar_lvds_is_connected(struct drm_bridge *bridge); #else -static inline int rcar_lvds_clk_enable(struct drm_bridge *bridge, - unsigned long freq) +static inline int rcar_lvds_pclk_enable(struct drm_bridge *bridge, + unsigned long freq) { return -ENOSYS; } -static inline void rcar_lvds_clk_disable(struct drm_bridge *bridge) { } +static inline void rcar_lvds_pclk_disable(struct drm_bridge *bridge) { } static inline bool rcar_lvds_dual_link(struct drm_bridge *bridge) { return false; diff --git a/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.c b/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.c index 62f7eb84ab01..a7f2b7f66a17 100644 --- a/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.c +++ b/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.c @@ -25,6 +25,7 @@ #include <drm/drm_panel.h> #include <drm/drm_probe_helper.h> +#include "rcar_mipi_dsi.h" #include "rcar_mipi_dsi_regs.h" struct rcar_mipi_dsi { @@ -414,7 +415,7 @@ static int rcar_mipi_dsi_startup(struct rcar_mipi_dsi *dsi, /* Enable DOT clock */ vclkset = VCLKSET_CKEN; - rcar_mipi_dsi_set(dsi, VCLKSET, vclkset); + rcar_mipi_dsi_write(dsi, VCLKSET, vclkset); if (dsi_format == 24) vclkset |= VCLKSET_BPP_24; @@ -429,7 +430,7 @@ static int rcar_mipi_dsi_startup(struct rcar_mipi_dsi *dsi, vclkset |= VCLKSET_COLOR_RGB | VCLKSET_DIV(setup_info.div) | VCLKSET_LANE(dsi->lanes - 1); - rcar_mipi_dsi_set(dsi, VCLKSET, vclkset); + rcar_mipi_dsi_write(dsi, VCLKSET, vclkset); /* After setting VCLKSET register, enable VCLKEN */ rcar_mipi_dsi_set(dsi, VCLKEN, VCLKEN_CKEN); @@ -441,9 +442,21 @@ static int rcar_mipi_dsi_startup(struct rcar_mipi_dsi *dsi, static void rcar_mipi_dsi_shutdown(struct rcar_mipi_dsi *dsi) { + /* Disable VCLKEN */ + rcar_mipi_dsi_write(dsi, VCLKSET, 0); + + /* Disable DOT clock */ + rcar_mipi_dsi_write(dsi, VCLKSET, 0); + rcar_mipi_dsi_clr(dsi, PHYSETUP, PHYSETUP_RSTZ); rcar_mipi_dsi_clr(dsi, PHYSETUP, PHYSETUP_SHUTDOWNZ); + /* CFGCLK disable */ + rcar_mipi_dsi_clr(dsi, CFGCLKSET, CFGCLKSET_CKEN); + + /* LPCLK disable */ + rcar_mipi_dsi_clr(dsi, LPCLKSET, LPCLKSET_CKEN); + dev_dbg(dsi->dev, "DSI device is shutdown\n"); } @@ -542,6 +555,34 @@ static int rcar_mipi_dsi_start_video(struct rcar_mipi_dsi *dsi) return 0; } +static void rcar_mipi_dsi_stop_video(struct rcar_mipi_dsi *dsi) +{ + u32 status; + int ret; + + /* Disable transmission in video mode. */ + rcar_mipi_dsi_clr(dsi, TXVMCR, TXVMCR_EN_VIDEO); + + ret = read_poll_timeout(rcar_mipi_dsi_read, status, + !(status & TXVMSR_ACT), + 2000, 100000, false, dsi, TXVMSR); + if (ret < 0) { + dev_err(dsi->dev, "Failed to disable video transmission\n"); + return; + } + + /* Assert video FIFO clear. */ + rcar_mipi_dsi_set(dsi, TXVMCR, TXVMCR_VFCLR); + + ret = read_poll_timeout(rcar_mipi_dsi_read, status, + !(status & TXVMSR_VFRDY), + 2000, 100000, false, dsi, TXVMSR); + if (ret < 0) { + dev_err(dsi->dev, "Failed to assert video FIFO clear\n"); + return; + } +} + /* ----------------------------------------------------------------------------- * Bridge */ @@ -558,7 +599,22 @@ static int rcar_mipi_dsi_attach(struct drm_bridge *bridge, static void rcar_mipi_dsi_atomic_enable(struct drm_bridge *bridge, struct drm_bridge_state *old_bridge_state) { - struct drm_atomic_state *state = old_bridge_state->base.state; + struct rcar_mipi_dsi *dsi = bridge_to_rcar_mipi_dsi(bridge); + + rcar_mipi_dsi_start_video(dsi); +} + +static void rcar_mipi_dsi_atomic_disable(struct drm_bridge *bridge, + struct drm_bridge_state *old_bridge_state) +{ + struct rcar_mipi_dsi *dsi = bridge_to_rcar_mipi_dsi(bridge); + + rcar_mipi_dsi_stop_video(dsi); +} + +void rcar_mipi_dsi_pclk_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ struct rcar_mipi_dsi *dsi = bridge_to_rcar_mipi_dsi(bridge); const struct drm_display_mode *mode; struct drm_connector *connector; @@ -586,8 +642,6 @@ static void rcar_mipi_dsi_atomic_enable(struct drm_bridge *bridge, if (ret < 0) goto err_dsi_start_hs; - rcar_mipi_dsi_start_video(dsi); - return; err_dsi_start_hs: @@ -595,15 +649,16 @@ err_dsi_start_hs: err_dsi_startup: rcar_mipi_dsi_clk_disable(dsi); } +EXPORT_SYMBOL_GPL(rcar_mipi_dsi_pclk_enable); -static void rcar_mipi_dsi_atomic_disable(struct drm_bridge *bridge, - struct drm_bridge_state *old_bridge_state) +void rcar_mipi_dsi_pclk_disable(struct drm_bridge *bridge) { struct rcar_mipi_dsi *dsi = bridge_to_rcar_mipi_dsi(bridge); rcar_mipi_dsi_shutdown(dsi); rcar_mipi_dsi_clk_disable(dsi); } +EXPORT_SYMBOL_GPL(rcar_mipi_dsi_pclk_disable); static enum drm_mode_status rcar_mipi_dsi_bridge_mode_valid(struct drm_bridge *bridge, diff --git a/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.h b/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.h new file mode 100644 index 000000000000..528a196e6edd --- /dev/null +++ b/drivers/gpu/drm/rcar-du/rcar_mipi_dsi.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * R-Car DSI Encoder + * + * Copyright (C) 2022 Renesas Electronics Corporation + * + * Contact: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> + */ + +#ifndef __RCAR_MIPI_DSI_H__ +#define __RCAR_MIPI_DSI_H__ + +struct drm_atomic_state; +struct drm_bridge; + +#if IS_ENABLED(CONFIG_DRM_RCAR_MIPI_DSI) +void rcar_mipi_dsi_pclk_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state); +void rcar_mipi_dsi_pclk_disable(struct drm_bridge *bridge); +#else +static inline void rcar_mipi_dsi_pclk_enable(struct drm_bridge *bridge, + struct drm_atomic_state *state) +{ +} + +static inline void rcar_mipi_dsi_pclk_disable(struct drm_bridge *bridge) +{ +} +#endif /* CONFIG_DRM_RCAR_MIPI_DSI */ + +#endif /* __RCAR_MIPI_DSI_H__ */ diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c index c204e9b95c1f..518ee13b1d6f 100644 --- a/drivers/gpu/drm/rockchip/cdn-dp-core.c +++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c @@ -283,8 +283,9 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector) return ret; } -static int cdn_dp_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) +static enum drm_mode_status +cdn_dp_connector_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) { struct cdn_dp_device *dp = connector_to_dp(connector); struct drm_display_info *display_info = &dp->connector.display_info; diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c index 552426d5d3a2..aac20be5ac08 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c @@ -1438,11 +1438,15 @@ static void rk3568_set_intf_mux(struct vop2_video_port *vp, int id, die &= ~RK3568_SYS_DSP_INFACE_EN_HDMI_MUX; die |= RK3568_SYS_DSP_INFACE_EN_HDMI | FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_HDMI_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__HDMI_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__HDMI_PIN_POL, polflags); break; case ROCKCHIP_VOP2_EP_EDP0: die &= ~RK3568_SYS_DSP_INFACE_EN_EDP_MUX; die |= RK3568_SYS_DSP_INFACE_EN_EDP | FIELD_PREP(RK3568_SYS_DSP_INFACE_EN_EDP_MUX, vp->id); + dip &= ~RK3568_DSP_IF_POL__EDP_PIN_POL; + dip |= FIELD_PREP(RK3568_DSP_IF_POL__EDP_PIN_POL, polflags); break; case ROCKCHIP_VOP2_EP_MIPI0: die &= ~RK3568_SYS_DSP_INFACE_EN_MIPI0_MUX; diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 4cc59bae38dd..2fab218d7082 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -919,8 +919,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) job = list_first_entry_or_null(&sched->pending_list, struct drm_sched_job, list); - if (job && (!job->s_fence->parent || - dma_fence_is_signaled(job->s_fence->parent))) { + if (job && dma_fence_is_signaled(&job->s_fence->finished)) { /* remove job from pending_list */ list_del_init(&job->list); @@ -930,9 +929,9 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) next = list_first_entry_or_null(&sched->pending_list, typeof(*next), list); - if (next && job->s_fence->parent) { + if (next) { next->s_fence->scheduled.timestamp = - job->s_fence->parent->timestamp; + job->s_fence->finished.timestamp; /* start TO timer for next job */ drm_sched_start_timeout(sched); } diff --git a/drivers/gpu/drm/solomon/ssd130x-i2c.c b/drivers/gpu/drm/solomon/ssd130x-i2c.c index 1e0fcec7be47..ddfa0bb5d9c9 100644 --- a/drivers/gpu/drm/solomon/ssd130x-i2c.c +++ b/drivers/gpu/drm/solomon/ssd130x-i2c.c @@ -39,13 +39,11 @@ static int ssd130x_i2c_probe(struct i2c_client *client) return 0; } -static int ssd130x_i2c_remove(struct i2c_client *client) +static void ssd130x_i2c_remove(struct i2c_client *client) { struct ssd130x_device *ssd130x = i2c_get_clientdata(client); ssd130x_remove(ssd130x); - - return 0; } static void ssd130x_i2c_shutdown(struct i2c_client *client) diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index 7a2b2d6bc3fe..62f69589a72d 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -729,7 +729,7 @@ static void drm_test_buddy_alloc_limit(struct kunit *test) static int drm_buddy_init_test(struct kunit *test) { while (!random_seed) - random_seed = get_random_int(); + random_seed = get_random_u32(); return 0; } diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c index 659d1af4dca7..c4b66eeae203 100644 --- a/drivers/gpu/drm/tests/drm_mm_test.c +++ b/drivers/gpu/drm/tests/drm_mm_test.c @@ -2212,7 +2212,7 @@ err_nodes: static int drm_mm_init_test(struct kunit *test) { while (!random_seed) - random_seed = get_random_int(); + random_seed = get_random_u32(); return 0; } diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 497ee1fdbad7..fa04e62202c1 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -239,16 +239,19 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo, if (bo->type != ttm_bo_type_sg) fbo->base.base.resv = &fbo->base.base._resv; - if (fbo->base.resource) { - ttm_resource_set_bo(fbo->base.resource, &fbo->base); - bo->resource = NULL; - } - dma_resv_init(&fbo->base.base._resv); fbo->base.base.dev = NULL; ret = dma_resv_trylock(&fbo->base.base._resv); WARN_ON(!ret); + if (fbo->base.resource) { + ttm_resource_set_bo(fbo->base.resource, &fbo->base); + bo->resource = NULL; + ttm_bo_set_bulk_move(&fbo->base, NULL); + } else { + fbo->base.bulk_move = NULL; + } + ret = dma_resv_reserve_fences(&fbo->base.base._resv, 1); if (ret) { kfree(fbo); |