diff options
Diffstat (limited to 'drivers/gpu/drm/amd')
197 files changed, 3914 insertions, 3137 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index db16b3e83694..cf62f43a03da 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -269,7 +269,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, uint64_t *size); int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv, bool *table_freed); + struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index fdee98fae2ba..4fb15750b9bb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -47,12 +47,6 @@ static struct { spinlock_t mem_limit_lock; } kfd_mem_limit; -/* Struct used for amdgpu_amdkfd_bo_validate */ -struct amdgpu_vm_parser { - uint32_t domain; - bool wait; -}; - static const char * const domain_bit_to_string[] = { "CPU", "GTT", @@ -348,11 +342,9 @@ validate_fail: return ret; } -static int amdgpu_amdkfd_validate(void *param, struct amdgpu_bo *bo) +static int amdgpu_amdkfd_validate_vm_bo(void *_unused, struct amdgpu_bo *bo) { - struct amdgpu_vm_parser *p = param; - - return amdgpu_amdkfd_bo_validate(bo, p->domain, p->wait); + return amdgpu_amdkfd_bo_validate(bo, bo->allowed_domains, false); } /* vm_validate_pt_pd_bos - Validate page table and directory BOs @@ -364,28 +356,23 @@ static int amdgpu_amdkfd_validate(void *param, struct amdgpu_bo *bo) */ static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm) { - struct amdgpu_bo *pd = vm->root.base.bo; + struct amdgpu_bo *pd = vm->root.bo; struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev); - struct amdgpu_vm_parser param; int ret; - param.domain = AMDGPU_GEM_DOMAIN_VRAM; - param.wait = false; - - ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate, - ¶m); + ret = amdgpu_vm_validate_pt_bos(adev, vm, amdgpu_amdkfd_validate_vm_bo, NULL); if (ret) { pr_err("failed to validate PT BOs\n"); return ret; } - ret = amdgpu_amdkfd_validate(¶m, pd); + ret = amdgpu_amdkfd_validate_vm_bo(NULL, pd); if (ret) { pr_err("failed to validate PD\n"); return ret; } - vm->pd_phys_addr = amdgpu_gmc_pd_addr(vm->root.base.bo); + vm->pd_phys_addr = amdgpu_gmc_pd_addr(vm->root.bo); if (vm->use_cpu_for_update) { ret = amdgpu_bo_kmap(pd, NULL); @@ -400,7 +387,7 @@ static int vm_validate_pt_pd_bos(struct amdgpu_vm *vm) static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync) { - struct amdgpu_bo *pd = vm->root.base.bo; + struct amdgpu_bo *pd = vm->root.bo; struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev); int ret; @@ -652,7 +639,7 @@ kfd_mem_attach_dmabuf(struct amdgpu_device *adev, struct kgd_mem *mem, } } - gobj = amdgpu_gem_prime_import(&adev->ddev, mem->dmabuf); + gobj = amdgpu_gem_prime_import(adev_to_drm(adev), mem->dmabuf); if (IS_ERR(gobj)) return PTR_ERR(gobj); @@ -1070,8 +1057,7 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, static int update_gpuvm_pte(struct kgd_mem *mem, struct kfd_mem_attachment *entry, - struct amdgpu_sync *sync, - bool *table_freed) + struct amdgpu_sync *sync) { struct amdgpu_bo_va *bo_va = entry->bo_va; struct amdgpu_device *adev = entry->adev; @@ -1082,7 +1068,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem, return ret; /* Update the page tables */ - ret = amdgpu_vm_bo_update(adev, bo_va, false, table_freed); + ret = amdgpu_vm_bo_update(adev, bo_va, false); if (ret) { pr_err("amdgpu_vm_bo_update failed\n"); return ret; @@ -1094,8 +1080,7 @@ static int update_gpuvm_pte(struct kgd_mem *mem, static int map_bo_to_gpuvm(struct kgd_mem *mem, struct kfd_mem_attachment *entry, struct amdgpu_sync *sync, - bool no_update_pte, - bool *table_freed) + bool no_update_pte) { int ret; @@ -1112,7 +1097,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem, if (no_update_pte) return 0; - ret = update_gpuvm_pte(mem, entry, sync, table_freed); + ret = update_gpuvm_pte(mem, entry, sync); if (ret) { pr_err("update_gpuvm_pte() failed\n"); goto update_gpuvm_pte_failed; @@ -1166,7 +1151,7 @@ static int process_sync_pds_resv(struct amdkfd_process_info *process_info, list_for_each_entry(peer_vm, &process_info->vm_list_head, vm_list_node) { - struct amdgpu_bo *pd = peer_vm->root.base.bo; + struct amdgpu_bo *pd = peer_vm->root.bo; ret = amdgpu_sync_resv(NULL, sync, pd->tbo.base.resv, AMDGPU_SYNC_NE_OWNER, @@ -1233,7 +1218,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, vm->process_info = *process_info; /* Validate page directory and attach eviction fence */ - ret = amdgpu_bo_reserve(vm->root.base.bo, true); + ret = amdgpu_bo_reserve(vm->root.bo, true); if (ret) goto reserve_pd_fail; ret = vm_validate_pt_pd_bos(vm); @@ -1241,16 +1226,16 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, pr_err("validate_pt_pd_bos() failed\n"); goto validate_pd_fail; } - ret = amdgpu_bo_sync_wait(vm->root.base.bo, + ret = amdgpu_bo_sync_wait(vm->root.bo, AMDGPU_FENCE_OWNER_KFD, false); if (ret) goto wait_pd_fail; - ret = dma_resv_reserve_shared(vm->root.base.bo->tbo.base.resv, 1); + ret = dma_resv_reserve_shared(vm->root.bo->tbo.base.resv, 1); if (ret) goto reserve_shared_fail; - amdgpu_bo_fence(vm->root.base.bo, + amdgpu_bo_fence(vm->root.bo, &vm->process_info->eviction_fence->base, true); - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); /* Update process info */ mutex_lock(&vm->process_info->lock); @@ -1264,7 +1249,7 @@ static int init_kfd_vm(struct amdgpu_vm *vm, void **process_info, reserve_shared_fail: wait_pd_fail: validate_pd_fail: - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); reserve_pd_fail: vm->process_info = NULL; if (info) { @@ -1319,7 +1304,7 @@ void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, struct amdgpu_vm *vm) { struct amdkfd_process_info *process_info = vm->process_info; - struct amdgpu_bo *pd = vm->root.base.bo; + struct amdgpu_bo *pd = vm->root.bo; if (!process_info) return; @@ -1375,7 +1360,7 @@ void amdgpu_amdkfd_gpuvm_release_process_vm(struct kgd_dev *kgd, void *drm_priv) uint64_t amdgpu_amdkfd_gpuvm_get_process_page_dir(void *drm_priv) { struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv); - struct amdgpu_bo *pd = avm->root.base.bo; + struct amdgpu_bo *pd = avm->root.bo; struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev); if (adev->asic_type < CHIP_VEGA10) @@ -1406,8 +1391,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( domain = alloc_domain = AMDGPU_GEM_DOMAIN_VRAM; alloc_flags = AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE; alloc_flags |= (flags & KFD_IOC_ALLOC_MEM_FLAGS_PUBLIC) ? - AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : - AMDGPU_GEM_CREATE_NO_CPU_ACCESS; + AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED : 0; } else if (flags & KFD_IOC_ALLOC_MEM_FLAGS_GTT) { domain = alloc_domain = AMDGPU_GEM_DOMAIN_GTT; alloc_flags = 0; @@ -1610,8 +1594,7 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( } int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - struct kgd_dev *kgd, struct kgd_mem *mem, - void *drm_priv, bool *table_freed) + struct kgd_dev *kgd, struct kgd_mem *mem, void *drm_priv) { struct amdgpu_device *adev = get_amdgpu_device(kgd); struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv); @@ -1699,7 +1682,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( entry->va, entry->va + bo_size, entry); ret = map_bo_to_gpuvm(mem, entry, ctx.sync, - is_invalid_userptr, table_freed); + is_invalid_userptr); if (ret) { pr_err("Failed to map bo to gpuvm\n"); goto out_unreserve; @@ -2149,7 +2132,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info) continue; kfd_mem_dmaunmap_attachment(mem, attachment); - ret = update_gpuvm_pte(mem, attachment, &sync, NULL); + ret = update_gpuvm_pte(mem, attachment, &sync); if (ret) { pr_err("%s: update PTE failed\n", __func__); /* make sure this gets validated again */ @@ -2355,7 +2338,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) continue; kfd_mem_dmaunmap_attachment(mem, attachment); - ret = update_gpuvm_pte(mem, attachment, &sync_obj, NULL); + ret = update_gpuvm_pte(mem, attachment, &sync_obj); if (ret) { pr_debug("Memory eviction: update PTE failed. Try again\n"); goto validate_map_fail; @@ -2402,7 +2385,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) /* 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.base.bo; + struct amdgpu_bo *bo = peer_vm->root.bo; amdgpu_bo_fence(bo, &process_info->eviction_fence->base, true); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 25655414e9c0..a152363b0254 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -799,7 +799,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false, NULL); + r = amdgpu_vm_bo_update(adev, fpriv->prt_va, false); if (r) return r; @@ -810,7 +810,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (amdgpu_mcbp || amdgpu_sriov_vf(adev)) { bo_va = fpriv->csa_va; BUG_ON(!bo_va); - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; @@ -829,7 +829,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (bo_va == NULL) continue; - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; @@ -850,7 +850,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) if (r) return r; - p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.base.bo); + p->job->vm_pd_addr = amdgpu_gmc_pd_addr(vm->root.bo); if (amdgpu_vm_debug) { /* Invalidate all BOs to test for userspace bugs */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index a9bbb0034e1e..536005bff24a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -1304,11 +1304,11 @@ static int amdgpu_debugfs_vm_info_show(struct seq_file *m, void *unused) seq_printf(m, "pid:%d\tProcess:%s ----------\n", vm->task_info.pid, vm->task_info.process_name); - r = amdgpu_bo_reserve(vm->root.base.bo, true); + r = amdgpu_bo_reserve(vm->root.bo, true); if (r) break; amdgpu_debugfs_vm_bo_info(vm, m); - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); } mutex_unlock(&dev->filelist_mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 6a242ec3f7ef..d303e88e3c23 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1369,6 +1369,38 @@ def_value: adev->pm.smu_prv_buffer_size = 0; } +static int amdgpu_device_init_apu_flags(struct amdgpu_device *adev) +{ + if (!(adev->flags & AMD_IS_APU) || + adev->asic_type < CHIP_RAVEN) + return 0; + + switch (adev->asic_type) { + case CHIP_RAVEN: + if (adev->pdev->device == 0x15dd) + adev->apu_flags |= AMD_APU_IS_RAVEN; + if (adev->pdev->device == 0x15d8) + adev->apu_flags |= AMD_APU_IS_PICASSO; + break; + case CHIP_RENOIR: + if ((adev->pdev->device == 0x1636) || + (adev->pdev->device == 0x164c)) + adev->apu_flags |= AMD_APU_IS_RENOIR; + else + adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE; + break; + case CHIP_VANGOGH: + adev->apu_flags |= AMD_APU_IS_VANGOGH; + break; + case CHIP_YELLOW_CARP: + break; + default: + return -EINVAL; + } + + return 0; +} + /** * amdgpu_device_check_arguments - validate module params * @@ -3386,6 +3418,10 @@ int amdgpu_device_init(struct amdgpu_device *adev, mutex_init(&adev->psp.mutex); mutex_init(&adev->notifier_lock); + r = amdgpu_device_init_apu_flags(adev); + if (r) + return r; + r = amdgpu_device_check_arguments(adev); if (r) return r; @@ -4124,6 +4160,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) { struct dma_fence *fence = NULL, *next = NULL; struct amdgpu_bo *shadow; + struct amdgpu_bo_vm *vmbo; long r = 1, tmo; if (amdgpu_sriov_runtime(adev)) @@ -4133,8 +4170,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) dev_info(adev->dev, "recover vram bo from shadow start\n"); mutex_lock(&adev->shadow_list_lock); - list_for_each_entry(shadow, &adev->shadow_list, shadow_list) { - + list_for_each_entry(vmbo, &adev->shadow_list, shadow_list) { + shadow = &vmbo->bo; /* No need to recover an evicted BO */ if (shadow->tbo.resource->mem_type != TTM_PL_TT || shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || @@ -4303,6 +4340,7 @@ bool amdgpu_device_should_recover_gpu(struct amdgpu_device *adev) case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: case CHIP_DIMGREY_CAVEFISH: + case CHIP_BEIGE_GOBY: case CHIP_VANGOGH: case CHIP_ALDEBARAN: break; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index e1b6f5891759..43e7b61d1c5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -325,7 +325,7 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev) return 0; } -int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, +int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int number_instance, int *major, int *minor, int *revision) { struct binary_header *bhdr; @@ -357,7 +357,7 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, for (j = 0; j < num_ips; j++) { ip = (struct ip *)(adev->mman.discovery_bin + ip_offset); - if (le16_to_cpu(ip->hw_id) == hw_id) { + if ((le16_to_cpu(ip->hw_id) == hw_id) && (ip->number_instance == number_instance)) { if (major) *major = ip->major; if (minor) @@ -373,6 +373,14 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, return -EINVAL; } + +int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance, + int *major, int *minor, int *revision) +{ + return amdgpu_discovery_get_ip_version(adev, VCN_HWID, + vcn_instance, major, minor, revision); +} + void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev) { struct binary_header *bhdr; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h index 1b1ae21b1037..48e6b88cfdfe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h @@ -30,8 +30,11 @@ void amdgpu_discovery_fini(struct amdgpu_device *adev); int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev); void amdgpu_discovery_harvest_ip(struct amdgpu_device *adev); -int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, +int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id, int number_instance, int *major, int *minor, int *revision); + +int amdgpu_discovery_get_vcn_version(struct amdgpu_device *adev, int vcn_instance, + int *major, int *minor, int *revision); int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev); #endif /* __AMDGPU_DISCOVERY__ */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index 2b6a66c849d4..8e5a7ac8c36f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -1046,11 +1046,12 @@ int amdgpu_display_gem_fb_init(struct drm_device *dev, rfb->base.obj[0] = obj; drm_helper_mode_fill_fb_struct(dev, &rfb->base, mode_cmd); - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + + ret = amdgpu_display_framebuffer_init(dev, rfb, mode_cmd, obj); if (ret) goto err; - ret = amdgpu_display_framebuffer_init(dev, rfb, mode_cmd, obj); + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); if (ret) goto err; @@ -1070,9 +1071,6 @@ int amdgpu_display_gem_fb_verify_and_init( rfb->base.obj[0] = obj; drm_helper_mode_fill_fb_struct(dev, &rfb->base, mode_cmd); - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); - if (ret) - goto err; /* Verify that the modifier is supported. */ if (!drm_any_plane_has_format(dev, mode_cmd->pixel_format, mode_cmd->modifier[0])) { @@ -1088,6 +1086,10 @@ int amdgpu_display_gem_fb_verify_and_init( if (ret) goto err; + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (ret) + goto err; + return 0; err: drm_dbg_kms(dev, "Failed to verify and init gem fb: %d\n", ret); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 23219fc3b28c..ae6ab93c868b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -105,9 +105,21 @@ static int amdgpu_dma_buf_pin(struct dma_buf_attachment *attach) { struct drm_gem_object *obj = attach->dmabuf->priv; struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj); + int r; /* pin buffer into GTT */ - return amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); + r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT); + if (r) + return r; + + if (bo->tbo.moving) { + r = dma_fence_wait(bo->tbo.moving, true); + if (r) { + amdgpu_bo_unpin(bo); + return r; + } + } + return 0; } /** @@ -383,7 +395,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; - struct dma_resv *resv = vm->root.base.bo->tbo.base.resv; + struct dma_resv *resv = vm->root.bo->tbo.base.resv; if (ticket) { /* When we get an error here it means that somebody diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index d2673119e0d1..a959624d576b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -160,6 +160,7 @@ int amdgpu_smu_pptable_id = -1; * highest. That helps saving some idle power. * DISABLE_FRACTIONAL_PWM (bit 2) disabled by default * PSR (bit 3) disabled by default + * EDP NO POWER SEQUENCING (bit 4) disabled by default */ uint amdgpu_dc_feature_mask = 2; uint amdgpu_dc_debug_mask; @@ -837,8 +838,23 @@ module_param_named(tmz, amdgpu_tmz, int, 0444); /** * DOC: freesync_video (uint) - * Enabled the optimization to adjust front porch timing to achieve seamless mode change experience - * when setting a freesync supported mode for which full modeset is not needed. + * Enable the optimization to adjust front porch timing to achieve seamless + * mode change experience when setting a freesync supported mode for which full + * modeset is not needed. + * + * The Display Core will add a set of modes derived from the base FreeSync + * video mode into the corresponding connector's mode list based on commonly + * used refresh rates and VRR range of the connected display, when users enable + * this feature. From the userspace perspective, they can see a seamless mode + * change experience when the change between different refresh rates under the + * same resolution. Additionally, userspace applications such as Video playback + * can read this modeset list and change the refresh rate based on the video + * frame rate. Finally, the userspace can also derive an appropriate mode for a + * particular refresh rate based on the FreeSync Mode and add it to the + * connector's mode list. + * + * Note: This is an experimental feature. + * * The default value: 0 (off). */ MODULE_PARM_DESC( @@ -1152,6 +1168,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, /* Renoir */ + {0x1002, 0x15E7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, {0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, @@ -1183,6 +1200,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x73E0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH}, {0x1002, 0x73E1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH}, {0x1002, 0x73E2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH}, + {0x1002, 0x73E3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH}, {0x1002, 0x73FF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH}, /* Aldebaran */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c index dbebbe16e3b3..d94c5419ec25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c @@ -69,13 +69,13 @@ void amdgpu_show_fdinfo(struct seq_file *m, struct file *f) dev = PCI_SLOT(adev->pdev->devfn); fn = PCI_FUNC(adev->pdev->devfn); - ret = amdgpu_bo_reserve(fpriv->vm.root.base.bo, false); + ret = amdgpu_bo_reserve(fpriv->vm.root.bo, false); if (ret) { DRM_ERROR("Fail to reserve bo\n"); return; } amdgpu_vm_get_memory(&fpriv->vm, &vram_mem, >t_mem, &cpu_mem); - amdgpu_bo_unreserve(fpriv->vm.root.base.bo); + amdgpu_bo_unreserve(fpriv->vm.root.bo); seq_printf(m, "pdev:\t%04x:%02x:%02x.%d\npasid:\t%u\n", domain, bus, dev, fn, fpriv->vm.pasid); seq_printf(m, "vram mem:\t%llu kB\n", vram_mem/1024UL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c index 1313784605b0..b36405170ff3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c @@ -300,7 +300,6 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset, * @adev: amdgpu_device pointer * @offset: offset into the GPU's gart aperture * @pages: number of pages to bind - * @pagelist: pages to bind * @dma_addr: DMA addresses of pages * @flags: page table entry flags * @@ -309,7 +308,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset, * Returns 0 for success, -EINVAL for failure. */ int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, - int pages, struct page **pagelist, dma_addr_t *dma_addr, + int pages, dma_addr_t *dma_addr, uint64_t flags) { if (!adev->gart.ready) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h index f53f6a7b9b60..78895413cf9f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h @@ -64,7 +64,6 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset, int pages, dma_addr_t *dma_addr, uint64_t flags, void *dst); int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset, - int pages, struct page **pagelist, - dma_addr_t *dma_addr, uint64_t flags); + int pages, dma_addr_t *dma_addr, uint64_t flags); void amdgpu_gart_invalidate_tlb(struct amdgpu_device *adev); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 0780e8d18992..a25160797b61 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -170,7 +170,7 @@ static int amdgpu_gem_object_open(struct drm_gem_object *obj, return -EPERM; if (abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID && - abo->tbo.base.resv != vm->root.base.bo->tbo.base.resv) + abo->tbo.base.resv != vm->root.bo->tbo.base.resv) return -EPERM; r = amdgpu_bo_reserve(abo, false); @@ -320,11 +320,11 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data, } if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) { - r = amdgpu_bo_reserve(vm->root.base.bo, false); + r = amdgpu_bo_reserve(vm->root.bo, false); if (r) return r; - resv = vm->root.base.bo->tbo.base.resv; + resv = vm->root.bo->tbo.base.resv; } initial_domain = (u32)(0xffffffff & args->in.domains); @@ -353,9 +353,9 @@ retry: if (!r) { struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); - abo->parent = amdgpu_bo_ref(vm->root.base.bo); + abo->parent = amdgpu_bo_ref(vm->root.bo); } - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); } if (r) return r; @@ -612,7 +612,7 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev, if (operation == AMDGPU_VA_OP_MAP || operation == AMDGPU_VA_OP_REPLACE) { - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) goto error; } @@ -842,7 +842,7 @@ int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data, } for (base = robj->vm_bo; base; base = base->next) if (amdgpu_xgmi_same_hive(amdgpu_ttm_adev(robj->tbo.bdev), - amdgpu_ttm_adev(base->vm->root.base.bo->tbo.bdev))) { + amdgpu_ttm_adev(base->vm->root.bo->tbo.bdev))) { r = -EINVAL; amdgpu_bo_unreserve(robj); goto out; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index 0174f7817ce2..d0b8d415b63b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -562,6 +562,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev) case CHIP_NAVI14: case CHIP_NAVI12: case CHIP_VANGOGH: + case CHIP_YELLOW_CARP: /* Don't enable it by default yet. */ if (amdgpu_tmz < 1) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c index 7dad44e73cf6..0d01cfaca77e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c @@ -278,6 +278,21 @@ static bool amdgpu_msi_ok(struct amdgpu_device *adev) return true; } +static void amdgpu_restore_msix(struct amdgpu_device *adev) +{ + u16 ctrl; + + pci_read_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, &ctrl); + if (!(ctrl & PCI_MSIX_FLAGS_ENABLE)) + return; + + /* VF FLR */ + ctrl &= ~PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl); + ctrl |= PCI_MSIX_FLAGS_ENABLE; + pci_write_config_word(adev->pdev, adev->pdev->msix_cap + PCI_MSIX_FLAGS, ctrl); +} + /** * amdgpu_irq_init - initialize interrupt handling * @@ -569,6 +584,9 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev) { int i, j, k; + if (amdgpu_sriov_vf(adev)) + amdgpu_restore_msix(adev); + for (i = 0; i < AMDGPU_IRQ_CLIENTID_MAX; ++i) { if (!adev->irq.client[i].sources) continue; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 425596c2f6f8..96ef3f1051d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -124,6 +124,22 @@ void amdgpu_register_gpu_instance(struct amdgpu_device *adev) mutex_unlock(&mgpu_info.mutex); } +static void amdgpu_get_audio_func(struct amdgpu_device *adev) +{ + struct pci_dev *p = NULL; + + p = pci_get_domain_bus_and_slot(pci_domain_nr(adev->pdev->bus), + adev->pdev->bus->number, 1); + if (p) { + pm_runtime_get_sync(&p->dev); + + pm_runtime_mark_last_busy(&p->dev); + pm_runtime_put_autosuspend(&p->dev); + + pci_dev_put(p); + } +} + /** * amdgpu_driver_load_kms - Main load function for KMS. * @@ -213,9 +229,35 @@ int amdgpu_driver_load_kms(struct amdgpu_device *adev, unsigned long flags) DPM_FLAG_MAY_SKIP_RESUME); pm_runtime_use_autosuspend(dev->dev); pm_runtime_set_autosuspend_delay(dev->dev, 5000); + pm_runtime_allow(dev->dev); + pm_runtime_mark_last_busy(dev->dev); pm_runtime_put_autosuspend(dev->dev); + + /* + * For runpm implemented via BACO, PMFW will handle the + * timing for BACO in and out: + * - put ASIC into BACO state only when both video and + * audio functions are in D3 state. + * - pull ASIC out of BACO state when either video or + * audio function is in D0 state. + * Also, at startup, PMFW assumes both functions are in + * D0 state. + * + * So if snd driver was loaded prior to amdgpu driver + * and audio function was put into D3 state, there will + * be no PMFW-aware D-state transition(D0->D3) on runpm + * suspend. Thus the BACO will be not correctly kicked in. + * + * Via amdgpu_get_audio_func(), the audio dev is put + * into D0 state. Then there will be a PMFW-aware D-state + * transition(D0->D3) on runpm suspend. + */ + if (amdgpu_device_supports_baco(dev) && + !(adev->flags & AMD_IS_APU) && + (adev->asic_type >= CHIP_NAVI10)) + amdgpu_get_audio_func(adev); } if (amdgpu_acpi_smart_shift_update(dev, AMDGPU_SS_DRV_LOAD)) @@ -1220,7 +1262,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, } pasid = fpriv->vm.pasid; - pd = amdgpu_bo_ref(fpriv->vm.root.base.bo); + pd = amdgpu_bo_ref(fpriv->vm.root.bo); amdgpu_ctx_mgr_fini(&fpriv->ctx_mgr); amdgpu_vm_fini(adev, &fpriv->vm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c index d6c54c7f7679..4b153daf283d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c @@ -160,7 +160,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, struct mm_struct *mm, struct page **pages, uint64_t start, uint64_t npages, struct hmm_range **phmm_range, bool readonly, - bool mmap_locked) + bool mmap_locked, void *owner) { struct hmm_range *hmm_range; unsigned long timeout; @@ -185,6 +185,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, hmm_range->hmm_pfns = pfns; hmm_range->start = start; hmm_range->end = start + npages * PAGE_SIZE; + hmm_range->dev_private_owner = owner; /* Assuming 512MB takes maxmium 1 second to fault page address */ timeout = max(npages >> 17, 1ULL) * HMM_RANGE_DEFAULT_TIMEOUT; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h index 7f7d37a457c3..14a3c1864085 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.h @@ -34,7 +34,7 @@ int amdgpu_hmm_range_get_pages(struct mmu_interval_notifier *notifier, struct mm_struct *mm, struct page **pages, uint64_t start, uint64_t npages, struct hmm_range **phmm_range, bool readonly, - bool mmap_locked); + bool mmap_locked, void *owner); int amdgpu_hmm_range_get_pages_done(struct hmm_range *hmm_range); #if defined(CONFIG_HMM_MIRROR) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h index 25ee53545837..45295dce5c3e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h @@ -93,6 +93,8 @@ struct amdgpu_nbio_funcs { void (*enable_aspm)(struct amdgpu_device *adev, bool enable); void (*program_aspm)(struct amdgpu_device *adev); + void (*apply_lc_spc_mode_wa)(struct amdgpu_device *adev); + void (*apply_l1_link_width_reconfig_wa)(struct amdgpu_device *adev); }; struct amdgpu_nbio { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c index 22fb4ab43eef..261283f5b424 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c @@ -54,29 +54,42 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) { - struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); - struct amdgpu_bo_user *ubo; amdgpu_bo_kunmap(bo); if (bo->tbo.base.import_attach) drm_prime_gem_destroy(&bo->tbo.base, bo->tbo.sg); drm_gem_object_release(&bo->tbo.base); + amdgpu_bo_unref(&bo->parent); + kvfree(bo); +} + +static void amdgpu_bo_user_destroy(struct ttm_buffer_object *tbo) +{ + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); + struct amdgpu_bo_user *ubo; + + ubo = to_amdgpu_bo_user(bo); + kfree(ubo->metadata); + amdgpu_bo_destroy(tbo); +} + +static void amdgpu_bo_vm_destroy(struct ttm_buffer_object *tbo) +{ + struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev); + struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo); + struct amdgpu_bo_vm *vmbo; + + vmbo = to_amdgpu_bo_vm(bo); /* in case amdgpu_device_recover_vram got NULL of bo->parent */ - if (!list_empty(&bo->shadow_list)) { + if (!list_empty(&vmbo->shadow_list)) { mutex_lock(&adev->shadow_list_lock); - list_del_init(&bo->shadow_list); + list_del_init(&vmbo->shadow_list); mutex_unlock(&adev->shadow_list_lock); } - amdgpu_bo_unref(&bo->parent); - - if (bo->tbo.type != ttm_bo_type_kernel) { - ubo = to_amdgpu_bo_user(bo); - kfree(ubo->metadata); - } - kvfree(bo); + amdgpu_bo_destroy(tbo); } /** @@ -91,8 +104,11 @@ static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo) */ bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo) { - if (bo->destroy == &amdgpu_bo_destroy) + if (bo->destroy == &amdgpu_bo_destroy || + bo->destroy == &amdgpu_bo_user_destroy || + bo->destroy == &amdgpu_bo_vm_destroy) return true; + return false; } @@ -545,7 +561,6 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (bo == NULL) return -ENOMEM; drm_gem_private_object_init(adev_to_drm(adev), &bo->tbo.base, size); - INIT_LIST_HEAD(&bo->shadow_list); bo->vm_bo = NULL; bo->preferred_domains = bp->preferred_domain ? bp->preferred_domain : bp->domain; @@ -568,9 +583,12 @@ int amdgpu_bo_create(struct amdgpu_device *adev, if (bp->type == ttm_bo_type_kernel) bo->tbo.priority = 1; + if (!bp->destroy) + bp->destroy = &amdgpu_bo_destroy; + r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type, &bo->placement, page_align, &ctx, NULL, - bp->resv, &amdgpu_bo_destroy); + bp->resv, bp->destroy); if (unlikely(r != 0)) return r; @@ -634,6 +652,7 @@ int amdgpu_bo_create_user(struct amdgpu_device *adev, int r; bp->bo_ptr_size = sizeof(struct amdgpu_bo_user); + bp->destroy = &amdgpu_bo_user_destroy; r = amdgpu_bo_create(adev, bp, &bo_ptr); if (r) return r; @@ -665,11 +684,13 @@ 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); return r; } @@ -714,12 +735,12 @@ retry: * * Insert a BO to the shadow list. */ -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo *bo) +void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo) { - struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); + struct amdgpu_device *adev = amdgpu_ttm_adev(vmbo->bo.tbo.bdev); mutex_lock(&adev->shadow_list_lock); - list_add_tail(&bo->shadow_list, &adev->shadow_list); + list_add_tail(&vmbo->shadow_list, &adev->shadow_list); mutex_unlock(&adev->shadow_list_lock); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index c03dfd298f45..e72f329e7f18 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -55,7 +55,8 @@ struct amdgpu_bo_param { u64 flags; enum ttm_bo_type type; bool no_wait_gpu; - struct dma_resv *resv; + struct dma_resv *resv; + void (*destroy)(struct ttm_buffer_object *bo); }; /* bo virtual addresses in a vm */ @@ -107,9 +108,6 @@ struct amdgpu_bo { #ifdef CONFIG_MMU_NOTIFIER struct mmu_interval_notifier notifier; #endif - - struct list_head shadow_list; - struct kgd_mem *kfd_bo; }; @@ -125,7 +123,8 @@ struct amdgpu_bo_user { struct amdgpu_bo_vm { struct amdgpu_bo bo; struct amdgpu_bo *shadow; - struct amdgpu_vm_pt entries[]; + struct list_head shadow_list; + struct amdgpu_vm_bo_base entries[]; }; static inline struct amdgpu_bo *ttm_to_amdgpu_bo(struct ttm_buffer_object *tbo) @@ -331,7 +330,7 @@ u64 amdgpu_bo_gpu_offset_no_check(struct amdgpu_bo *bo); int amdgpu_bo_validate(struct amdgpu_bo *bo); void amdgpu_bo_get_memory(struct amdgpu_bo *bo, uint64_t *vram_mem, uint64_t *gtt_mem, uint64_t *cpu_mem); -void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo *bo); +void amdgpu_bo_add_to_shadow_list(struct amdgpu_bo_vm *vmbo); int amdgpu_bo_restore_shadow(struct amdgpu_bo *shadow, struct dma_fence **fence); uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 6046123d0562..3ec5099ffeb6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -171,11 +171,81 @@ Err_out: return ret; } +/* + * Helper funciton to query psp runtime database entry + * + * @adev: amdgpu_device pointer + * @entry_type: the type of psp runtime database entry + * @db_entry: runtime database entry pointer + * + * Return false if runtime database doesn't exit or entry is invalid + * or true if the specific database entry is found, and copy to @db_entry + */ +static bool psp_get_runtime_db_entry(struct amdgpu_device *adev, + enum psp_runtime_entry_type entry_type, + void *db_entry) +{ + uint64_t db_header_pos, db_dir_pos; + struct psp_runtime_data_header db_header = {0}; + struct psp_runtime_data_directory db_dir = {0}; + bool ret = false; + int i; + + db_header_pos = adev->gmc.mc_vram_size - PSP_RUNTIME_DB_OFFSET; + db_dir_pos = db_header_pos + sizeof(struct psp_runtime_data_header); + + /* read runtime db header from vram */ + amdgpu_device_vram_access(adev, db_header_pos, (uint32_t *)&db_header, + sizeof(struct psp_runtime_data_header), false); + + if (db_header.cookie != PSP_RUNTIME_DB_COOKIE_ID) { + /* runtime db doesn't exist, exit */ + dev_warn(adev->dev, "PSP runtime database doesn't exist\n"); + return false; + } + + /* read runtime database entry from vram */ + amdgpu_device_vram_access(adev, db_dir_pos, (uint32_t *)&db_dir, + sizeof(struct psp_runtime_data_directory), false); + + if (db_dir.entry_count >= PSP_RUNTIME_DB_DIAG_ENTRY_MAX_COUNT) { + /* invalid db entry count, exit */ + dev_warn(adev->dev, "Invalid PSP runtime database entry count\n"); + return false; + } + + /* look up for requested entry type */ + for (i = 0; i < db_dir.entry_count && !ret; i++) { + if (db_dir.entry_list[i].entry_type == entry_type) { + switch (entry_type) { + case PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG: + if (db_dir.entry_list[i].size < sizeof(struct psp_runtime_boot_cfg_entry)) { + /* invalid db entry size */ + dev_warn(adev->dev, "Invalid PSP runtime database entry size\n"); + return false; + } + /* read runtime database entry */ + amdgpu_device_vram_access(adev, db_header_pos + db_dir.entry_list[i].offset, + (uint32_t *)db_entry, sizeof(struct psp_runtime_boot_cfg_entry), false); + ret = true; + break; + default: + ret = false; + break; + } + } + } + + return ret; +} + static int psp_sw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct psp_context *psp = &adev->psp; int ret; + struct psp_runtime_boot_cfg_entry boot_cfg_entry; + struct psp_memory_training_context *mem_training_ctx = &psp->mem_train_ctx; if (!amdgpu_sriov_vf(adev)) { ret = psp_init_microcode(psp); @@ -191,15 +261,39 @@ static int psp_sw_init(void *handle) } } - ret = psp_memory_training_init(psp); - if (ret) { - DRM_ERROR("Failed to initialize memory training!\n"); - return ret; + memset(&boot_cfg_entry, 0, sizeof(boot_cfg_entry)); + if (psp_get_runtime_db_entry(adev, + PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG, + &boot_cfg_entry)) { + psp->boot_cfg_bitmask = boot_cfg_entry.boot_cfg_bitmask; + if ((psp->boot_cfg_bitmask) & + BOOT_CFG_FEATURE_TWO_STAGE_DRAM_TRAINING) { + /* If psp runtime database exists, then + * only enable two stage memory training + * when TWO_STAGE_DRAM_TRAINING bit is set + * in runtime database */ + mem_training_ctx->enable_mem_training = true; + } + + } else { + /* If psp runtime database doesn't exist or + * is invalid, force enable two stage memory + * training */ + mem_training_ctx->enable_mem_training = true; } - ret = psp_mem_training(psp, PSP_MEM_TRAIN_COLD_BOOT); - if (ret) { - DRM_ERROR("Failed to process memory training!\n"); - return ret; + + if (mem_training_ctx->enable_mem_training) { + ret = psp_memory_training_init(psp); + if (ret) { + DRM_ERROR("Failed to initialize memory training!\n"); + return ret; + } + + ret = psp_mem_training(psp, PSP_MEM_TRAIN_COLD_BOOT); + if (ret) { + DRM_ERROR("Failed to process memory training!\n"); + return ret; + } } if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) { @@ -551,7 +645,30 @@ int psp_get_fw_attestation_records_addr(struct psp_context *psp, return ret; } -static int psp_boot_config_set(struct amdgpu_device *adev) +static int psp_boot_config_get(struct amdgpu_device *adev, uint32_t *boot_cfg) +{ + struct psp_context *psp = &adev->psp; + struct psp_gfx_cmd_resp *cmd = psp->cmd; + int ret; + + if (amdgpu_sriov_vf(adev)) + return 0; + + memset(cmd, 0, sizeof(struct psp_gfx_cmd_resp)); + + cmd->cmd_id = GFX_CMD_ID_BOOT_CFG; + cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_GET; + + ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); + if (!ret) { + *boot_cfg = + (cmd->resp.uresp.boot_cfg.boot_cfg & BOOT_CONFIG_GECC) ? 1 : 0; + } + + return ret; +} + +static int psp_boot_config_set(struct amdgpu_device *adev, uint32_t boot_cfg) { struct psp_context *psp = &adev->psp; struct psp_gfx_cmd_resp *cmd = psp->cmd; @@ -563,8 +680,8 @@ static int psp_boot_config_set(struct amdgpu_device *adev) cmd->cmd_id = GFX_CMD_ID_BOOT_CFG; cmd->cmd.boot_cfg.sub_cmd = BOOTCFG_CMD_SET; - cmd->cmd.boot_cfg.boot_config = BOOT_CONFIG_GECC; - cmd->cmd.boot_cfg.boot_config_valid = BOOT_CONFIG_GECC; + cmd->cmd.boot_cfg.boot_config = boot_cfg; + cmd->cmd.boot_cfg.boot_config_valid = boot_cfg; return psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr); } @@ -1212,19 +1329,62 @@ static int psp_ras_terminate(struct psp_context *psp) static int psp_ras_initialize(struct psp_context *psp) { int ret; + uint32_t boot_cfg = 0xFF; + struct amdgpu_device *adev = psp->adev; /* * TODO: bypass the initialize in sriov for now */ - if (amdgpu_sriov_vf(psp->adev)) + if (amdgpu_sriov_vf(adev)) return 0; - if (!psp->adev->psp.ta_ras_ucode_size || - !psp->adev->psp.ta_ras_start_addr) { - dev_info(psp->adev->dev, "RAS: optional ras ta ucode is not available\n"); + if (!adev->psp.ta_ras_ucode_size || + !adev->psp.ta_ras_start_addr) { + dev_info(adev->dev, "RAS: optional ras ta ucode is not available\n"); return 0; } + if (amdgpu_atomfirmware_dynamic_boot_config_supported(adev)) { + /* query GECC enablement status from boot config + * boot_cfg: 1: GECC is enabled or 0: GECC is disabled + */ + ret = psp_boot_config_get(adev, &boot_cfg); + if (ret) + dev_warn(adev->dev, "PSP get boot config failed\n"); + + if (!amdgpu_ras_is_supported(psp->adev, AMDGPU_RAS_BLOCK__UMC)) { + if (!boot_cfg) { + dev_info(adev->dev, "GECC is disabled\n"); + } else { + /* disable GECC in next boot cycle if ras is + * disabled by module parameter amdgpu_ras_enable + * and/or amdgpu_ras_mask, or boot_config_get call + * is failed + */ + ret = psp_boot_config_set(adev, 0); + if (ret) + dev_warn(adev->dev, "PSP set boot config failed\n"); + else + dev_warn(adev->dev, "GECC will be disabled in next boot cycle " + "if set amdgpu_ras_enable and/or amdgpu_ras_mask to 0x0\n"); + } + } else { + if (1 == boot_cfg) { + dev_info(adev->dev, "GECC is enabled\n"); + } else { + /* enable GECC in next boot cycle if it is disabled + * in boot config, or force enable GECC if failed to + * get boot configuration + */ + ret = psp_boot_config_set(adev, BOOT_CONFIG_GECC); + if (ret) + dev_warn(adev->dev, "PSP set boot config failed\n"); + else + dev_warn(adev->dev, "GECC will be enabled in next boot cycle\n"); + } + } + } + if (!psp->ras.ras_initialized) { ret = psp_ras_init_shared_buf(psp); if (ret) @@ -1945,12 +2105,6 @@ static int psp_hw_start(struct psp_context *psp) return ret; } - if (amdgpu_atomfirmware_dynamic_boot_config_supported(adev)) { - ret = psp_boot_config_set(adev); - if (ret) - dev_warn(adev->dev, "PSP set boot config failed\n"); - } - ret = psp_tmr_init(psp); if (ret) { DRM_ERROR("PSP tmr init failed!\n"); @@ -2188,10 +2342,7 @@ static int psp_load_smu_fw(struct psp_context *psp) if ((amdgpu_in_reset(adev) && ras && adev->ras_enabled && (adev->asic_type == CHIP_ARCTURUS || - adev->asic_type == CHIP_VEGA20)) || - (adev->in_runpm && - adev->asic_type >= CHIP_NAVI10 && - adev->asic_type <= CHIP_NAVI12)) { + adev->asic_type == CHIP_VEGA20))) { ret = amdgpu_dpm_set_mp1_state(adev, PP_MP1_STATE_UNLOAD); if (ret) { DRM_WARN("Failed to set MP1 state prepare for reload\n"); @@ -2562,10 +2713,12 @@ static int psp_resume(void *handle) DRM_INFO("PSP is resuming...\n"); - ret = psp_mem_training(psp, PSP_MEM_TRAIN_RESUME); - if (ret) { - DRM_ERROR("Failed to process memory training!\n"); - return ret; + if (psp->mem_train_ctx.enable_mem_training) { + ret = psp_mem_training(psp, PSP_MEM_TRAIN_RESUME); + if (ret) { + DRM_ERROR("Failed to process memory training!\n"); + return ret; + } } mutex_lock(&adev->firmware.mutex); @@ -2749,7 +2902,7 @@ int psp_init_asd_microcode(struct psp_context *psp, asd_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.asd_fw->data; adev->psp.asd_fw_version = le32_to_cpu(asd_hdr->header.ucode_version); - adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->ucode_feature_version); + adev->psp.asd_feature_version = le32_to_cpu(asd_hdr->sos.fw_version); adev->psp.asd_ucode_size = le32_to_cpu(asd_hdr->header.ucode_size_bytes); adev->psp.asd_start_addr = (uint8_t *)asd_hdr + le32_to_cpu(asd_hdr->header.ucode_array_offset_bytes); @@ -2785,7 +2938,7 @@ int psp_init_toc_microcode(struct psp_context *psp, toc_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.toc_fw->data; adev->psp.toc_fw_version = le32_to_cpu(toc_hdr->header.ucode_version); - adev->psp.toc_feature_version = le32_to_cpu(toc_hdr->ucode_feature_version); + adev->psp.toc_feature_version = le32_to_cpu(toc_hdr->sos.fw_version); adev->psp.toc_bin_size = le32_to_cpu(toc_hdr->header.ucode_size_bytes); adev->psp.toc_start_addr = (uint8_t *)toc_hdr + le32_to_cpu(toc_hdr->header.ucode_array_offset_bytes); @@ -2797,6 +2950,50 @@ out: return err; } +static int psp_init_sos_base_fw(struct amdgpu_device *adev) +{ + const struct psp_firmware_header_v1_0 *sos_hdr; + const struct psp_firmware_header_v1_3 *sos_hdr_v1_3; + uint8_t *ucode_array_start_addr; + + sos_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.sos_fw->data; + ucode_array_start_addr = (uint8_t *)sos_hdr + + le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes); + + if (adev->gmc.xgmi.connected_to_cpu || (adev->asic_type != CHIP_ALDEBARAN)) { + adev->psp.sos_fw_version = le32_to_cpu(sos_hdr->header.ucode_version); + adev->psp.sos_feature_version = le32_to_cpu(sos_hdr->sos.fw_version); + + adev->psp.sys_bin_size = le32_to_cpu(sos_hdr->sos.offset_bytes); + adev->psp.sys_start_addr = ucode_array_start_addr; + + adev->psp.sos_bin_size = le32_to_cpu(sos_hdr->sos.size_bytes); + adev->psp.sos_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr->sos.offset_bytes); + } else { + /* Load alternate PSP SOS FW */ + sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data; + + adev->psp.sos_fw_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version); + adev->psp.sos_feature_version = le32_to_cpu(sos_hdr_v1_3->sos_aux.fw_version); + + adev->psp.sys_bin_size = le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.size_bytes); + adev->psp.sys_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr_v1_3->sys_drv_aux.offset_bytes); + + adev->psp.sos_bin_size = le32_to_cpu(sos_hdr_v1_3->sos_aux.size_bytes); + adev->psp.sos_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr_v1_3->sos_aux.offset_bytes); + } + + if ((adev->psp.sys_bin_size == 0) || (adev->psp.sos_bin_size == 0)) { + dev_warn(adev->dev, "PSP SOS FW not available"); + return -EINVAL; + } + + return 0; +} + int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name) { @@ -2807,6 +3004,7 @@ int psp_init_sos_microcode(struct psp_context *psp, const struct psp_firmware_header_v1_2 *sos_hdr_v1_2; const struct psp_firmware_header_v1_3 *sos_hdr_v1_3; int err = 0; + uint8_t *ucode_array_start_addr; if (!chip_name) { dev_err(adev->dev, "invalid chip name for sos microcode\n"); @@ -2823,47 +3021,45 @@ int psp_init_sos_microcode(struct psp_context *psp, goto out; sos_hdr = (const struct psp_firmware_header_v1_0 *)adev->psp.sos_fw->data; + ucode_array_start_addr = (uint8_t *)sos_hdr + + le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes); amdgpu_ucode_print_psp_hdr(&sos_hdr->header); switch (sos_hdr->header.header_version_major) { case 1: - adev->psp.sos_fw_version = le32_to_cpu(sos_hdr->header.ucode_version); - adev->psp.sos_feature_version = le32_to_cpu(sos_hdr->ucode_feature_version); - adev->psp.sos_bin_size = le32_to_cpu(sos_hdr->sos_size_bytes); - adev->psp.sys_bin_size = le32_to_cpu(sos_hdr->sos_offset_bytes); - adev->psp.sys_start_addr = (uint8_t *)sos_hdr + - le32_to_cpu(sos_hdr->header.ucode_array_offset_bytes); - adev->psp.sos_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr->sos_offset_bytes); + err = psp_init_sos_base_fw(adev); + if (err) + goto out; + if (sos_hdr->header.header_version_minor == 1) { sos_hdr_v1_1 = (const struct psp_firmware_header_v1_1 *)adev->psp.sos_fw->data; - adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_1->toc_size_bytes); + adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_1->toc.size_bytes); adev->psp.toc_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_1->toc_offset_bytes); - adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_1->kdb_size_bytes); + le32_to_cpu(sos_hdr_v1_1->toc.offset_bytes); + adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_1->kdb.size_bytes); adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_1->kdb_offset_bytes); + le32_to_cpu(sos_hdr_v1_1->kdb.offset_bytes); } if (sos_hdr->header.header_version_minor == 2) { sos_hdr_v1_2 = (const struct psp_firmware_header_v1_2 *)adev->psp.sos_fw->data; - adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_2->kdb_size_bytes); + adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_2->kdb.size_bytes); adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_2->kdb_offset_bytes); + le32_to_cpu(sos_hdr_v1_2->kdb.offset_bytes); } if (sos_hdr->header.header_version_minor == 3) { sos_hdr_v1_3 = (const struct psp_firmware_header_v1_3 *)adev->psp.sos_fw->data; - adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.toc_size_bytes); - adev->psp.toc_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_3->v1_1.toc_offset_bytes); - adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.kdb_size_bytes); - adev->psp.kdb_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_3->v1_1.kdb_offset_bytes); - adev->psp.spl_bin_size = le32_to_cpu(sos_hdr_v1_3->spl_size_bytes); - adev->psp.spl_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_3->spl_offset_bytes); - adev->psp.rl_bin_size = le32_to_cpu(sos_hdr_v1_3->rl_size_bytes); - adev->psp.rl_start_addr = (uint8_t *)adev->psp.sys_start_addr + - le32_to_cpu(sos_hdr_v1_3->rl_offset_bytes); + adev->psp.toc_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.toc.size_bytes); + adev->psp.toc_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr_v1_3->v1_1.toc.offset_bytes); + adev->psp.kdb_bin_size = le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.size_bytes); + adev->psp.kdb_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr_v1_3->v1_1.kdb.offset_bytes); + adev->psp.spl_bin_size = le32_to_cpu(sos_hdr_v1_3->spl.size_bytes); + adev->psp.spl_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr_v1_3->spl.offset_bytes); + adev->psp.rl_bin_size = le32_to_cpu(sos_hdr_v1_3->rl.size_bytes); + adev->psp.rl_start_addr = ucode_array_start_addr + + le32_to_cpu(sos_hdr_v1_3->rl.offset_bytes); } break; default: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index e5023f1de7fd..3030ec24eb3b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -225,6 +225,61 @@ struct psp_memory_training_context { enum psp_memory_training_init_flag init; u32 training_cnt; + bool enable_mem_training; +}; + +/** PSP runtime DB **/ +#define PSP_RUNTIME_DB_SIZE_IN_BYTES 0x10000 +#define PSP_RUNTIME_DB_OFFSET 0x100000 +#define PSP_RUNTIME_DB_COOKIE_ID 0x0ed5 +#define PSP_RUNTIME_DB_VER_1 0x0100 +#define PSP_RUNTIME_DB_DIAG_ENTRY_MAX_COUNT 0x40 + +enum psp_runtime_entry_type { + PSP_RUNTIME_ENTRY_TYPE_INVALID = 0x0, + PSP_RUNTIME_ENTRY_TYPE_TEST = 0x1, + PSP_RUNTIME_ENTRY_TYPE_MGPU_COMMON = 0x2, /* Common mGPU runtime data */ + PSP_RUNTIME_ENTRY_TYPE_MGPU_WAFL = 0x3, /* WAFL runtime data */ + PSP_RUNTIME_ENTRY_TYPE_MGPU_XGMI = 0x4, /* XGMI runtime data */ + PSP_RUNTIME_ENTRY_TYPE_BOOT_CONFIG = 0x5, /* Boot Config runtime data */ +}; + +/* PSP runtime DB header */ +struct psp_runtime_data_header { + /* determine the existence of runtime db */ + uint16_t cookie; + /* version of runtime db */ + uint16_t version; +}; + +/* PSP runtime DB entry */ +struct psp_runtime_entry { + /* type of runtime db entry */ + uint32_t entry_type; + /* offset of entry in bytes */ + uint16_t offset; + /* size of entry in bytes */ + uint16_t size; +}; + +/* PSP runtime DB directory */ +struct psp_runtime_data_directory { + /* number of valid entries */ + uint16_t entry_count; + /* db entries*/ + struct psp_runtime_entry entry_list[PSP_RUNTIME_DB_DIAG_ENTRY_MAX_COUNT]; +}; + +/* PSP runtime DB boot config feature bitmask */ +enum psp_runtime_boot_cfg_feature { + BOOT_CFG_FEATURE_GECC = 0x1, + BOOT_CFG_FEATURE_TWO_STAGE_DRAM_TRAINING = 0x2, +}; + +/* PSP runtime DB boot config entry */ +struct psp_runtime_boot_cfg_entry { + uint32_t boot_cfg_bitmask; + uint32_t reserved; }; struct psp_context @@ -325,6 +380,8 @@ struct psp_context struct psp_securedisplay_context securedisplay_context; struct mutex mutex; struct psp_memory_training_context mem_train_ctx; + + uint32_t boot_cfg_bitmask; }; struct amdgpu_psp_funcs { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 9dfc1ebb41a9..fc66aca28594 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -809,7 +809,7 @@ static int amdgpu_ras_enable_all_features(struct amdgpu_device *adev, /* query/inject/cure begin */ int amdgpu_ras_query_error_status(struct amdgpu_device *adev, - struct ras_query_if *info) + struct ras_query_if *info) { struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); struct ras_err_data err_data = {0, 0, 0, NULL}; @@ -1043,17 +1043,32 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev, return ret; } -/* get the total error counts on all IPs */ -void amdgpu_ras_query_error_count(struct amdgpu_device *adev, - unsigned long *ce_count, - unsigned long *ue_count) +/** + * amdgpu_ras_query_error_count -- Get error counts of all IPs + * adev: pointer to AMD GPU device + * ce_count: pointer to an integer to be set to the count of correctible errors. + * ue_count: pointer to an integer to be set to the count of uncorrectible + * errors. + * + * If set, @ce_count or @ue_count, count and return the corresponding + * error counts in those integer pointers. Return 0 if the device + * supports RAS. Return -EOPNOTSUPP if the device doesn't support RAS. + */ +int amdgpu_ras_query_error_count(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_manager *obj; unsigned long ce, ue; if (!adev->ras_enabled || !con) - return; + return -EOPNOTSUPP; + + /* Don't count since no reporting. + */ + if (!ce_count && !ue_count) + return 0; ce = 0; ue = 0; @@ -1061,9 +1076,11 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev, struct ras_query_if info = { .head = obj->head, }; + int res; - if (amdgpu_ras_query_error_status(adev, &info)) - return; + res = amdgpu_ras_query_error_status(adev, &info); + if (res) + return res; ce += info.ce_count; ue += info.ue_count; @@ -1074,6 +1091,8 @@ void amdgpu_ras_query_error_count(struct amdgpu_device *adev, if (ue_count) *ue_count = ue; + + return 0; } /* query/inject/cure end */ @@ -1984,6 +2003,9 @@ int amdgpu_ras_recovery_init(struct amdgpu_device *adev) ret = amdgpu_ras_load_bad_pages(adev); if (ret) goto free; + + if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->send_hbm_bad_pages_num) + adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.num_recs); } return 0; @@ -2063,7 +2085,9 @@ static void amdgpu_ras_get_quirks(struct amdgpu_device *adev) return; if (strnstr(ctx->vbios_version, "D16406", - sizeof(ctx->vbios_version))) + sizeof(ctx->vbios_version)) || + strnstr(ctx->vbios_version, "D36002", + sizeof(ctx->vbios_version))) adev->ras_hw_enabled |= (1 << AMDGPU_RAS_BLOCK__GFX); } @@ -2122,7 +2146,7 @@ static void amdgpu_ras_counte_dw(struct work_struct *work) struct amdgpu_ras *con = container_of(work, struct amdgpu_ras, ras_counte_delay_work.work); struct amdgpu_device *adev = con->adev; - struct drm_device *dev = &adev->ddev; + struct drm_device *dev = adev_to_drm(adev); unsigned long ce_count, ue_count; int res; @@ -2132,9 +2156,10 @@ static void amdgpu_ras_counte_dw(struct work_struct *work) /* Cache new values. */ - amdgpu_ras_query_error_count(adev, &ce_count, &ue_count); - atomic_set(&con->ras_ce_count, ce_count); - atomic_set(&con->ras_ue_count, ue_count); + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + atomic_set(&con->ras_ce_count, ce_count); + atomic_set(&con->ras_ue_count, ue_count); + } pm_runtime_mark_last_busy(dev->dev); Out: @@ -2307,9 +2332,10 @@ int amdgpu_ras_late_init(struct amdgpu_device *adev, /* Those are the cached values at init. */ - amdgpu_ras_query_error_count(adev, &ce_count, &ue_count); - atomic_set(&con->ras_ce_count, ce_count); - atomic_set(&con->ras_ue_count, ue_count); + if (amdgpu_ras_query_error_count(adev, &ce_count, &ue_count) == 0) { + atomic_set(&con->ras_ce_count, ce_count); + atomic_set(&con->ras_ue_count, ue_count); + } return 0; cleanup: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 256cea5d34f2..b504ed8c9b50 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -490,9 +490,9 @@ int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev, void amdgpu_ras_resume(struct amdgpu_device *adev); void amdgpu_ras_suspend(struct amdgpu_device *adev); -void amdgpu_ras_query_error_count(struct amdgpu_device *adev, - unsigned long *ce_count, - unsigned long *ue_count); +int amdgpu_ras_query_error_count(struct amdgpu_device *adev, + unsigned long *ce_count, + unsigned long *ue_count); /* error handling functions */ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h index 0527772fe1b8..d855cb53c7e0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h @@ -176,10 +176,10 @@ TRACE_EVENT(amdgpu_cs_ioctl, TP_fast_assign( __entry->sched_job_id = job->base.id; - __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)) + __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)); __entry->context = job->base.s_fence->finished.context; __entry->seqno = job->base.s_fence->finished.seqno; - __assign_str(ring, to_amdgpu_ring(job->base.sched)->name) + __assign_str(ring, to_amdgpu_ring(job->base.sched)->name); __entry->num_ibs = job->num_ibs; ), TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u", @@ -201,10 +201,10 @@ TRACE_EVENT(amdgpu_sched_run_job, TP_fast_assign( __entry->sched_job_id = job->base.id; - __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)) + __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job)); __entry->context = job->base.s_fence->finished.context; __entry->seqno = job->base.s_fence->finished.seqno; - __assign_str(ring, to_amdgpu_ring(job->base.sched)->name) + __assign_str(ring, to_amdgpu_ring(job->base.sched)->name); __entry->num_ibs = job->num_ibs; ), TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u", @@ -229,7 +229,7 @@ TRACE_EVENT(amdgpu_vm_grab_id, TP_fast_assign( __entry->pasid = vm->pasid; - __assign_str(ring, ring->name) + __assign_str(ring, ring->name); __entry->vmid = job->vmid; __entry->vm_hub = ring->funcs->vmhub, __entry->pd_addr = job->vm_pd_addr; @@ -424,7 +424,7 @@ TRACE_EVENT(amdgpu_vm_flush, ), TP_fast_assign( - __assign_str(ring, ring->name) + __assign_str(ring, ring->name); __entry->vmid = vmid; __entry->vm_hub = ring->funcs->vmhub; __entry->pd_addr = pd_addr; @@ -525,7 +525,7 @@ TRACE_EVENT(amdgpu_ib_pipe_sync, ), TP_fast_assign( - __assign_str(ring, sched_job->base.sched->name) + __assign_str(ring, sched_job->base.sched->name); __entry->id = sched_job->base.id; __entry->fence = fence; __entry->ctx = fence->context; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index b46726e47bce..acd95d3a4434 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -592,10 +592,6 @@ static int amdgpu_ttm_io_mem_reserve(struct ttm_device *bdev, mem->bus.offset += adev->gmc.aper_base; mem->bus.is_iomem = true; - if (adev->gmc.xgmi.connected_to_cpu) - mem->bus.caching = ttm_cached; - else - mem->bus.caching = ttm_write_combined; break; default: return -EINVAL; @@ -683,23 +679,23 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages) return -ESRCH; mmap_read_lock(mm); - vma = find_vma(mm, start); - mmap_read_unlock(mm); - if (unlikely(!vma || start < vma->vm_start)) { + vma = vma_lookup(mm, start); + if (unlikely(!vma)) { r = -EFAULT; - goto out_putmm; + goto out_unlock; } if (unlikely((gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) && vma->vm_file)) { r = -EPERM; - goto out_putmm; + goto out_unlock; } readonly = amdgpu_ttm_tt_is_readonly(ttm); r = amdgpu_hmm_range_get_pages(&bo->notifier, mm, pages, start, ttm->num_pages, >t->range, readonly, - false); -out_putmm: + true, NULL); +out_unlock: + mmap_read_unlock(mm); mmput(mm); return r; @@ -843,7 +839,7 @@ static int amdgpu_ttm_gart_bind(struct amdgpu_device *adev, uint64_t page_idx = 1; r = amdgpu_gart_bind(adev, gtt->offset, page_idx, - ttm->pages, gtt->ttm.dma_address, flags); + gtt->ttm.dma_address, flags); if (r) goto gart_bind_fail; @@ -857,11 +853,10 @@ static int amdgpu_ttm_gart_bind(struct amdgpu_device *adev, r = amdgpu_gart_bind(adev, gtt->offset + (page_idx << PAGE_SHIFT), ttm->num_pages - page_idx, - &ttm->pages[page_idx], &(gtt->ttm.dma_address[page_idx]), flags); } else { r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages, - ttm->pages, gtt->ttm.dma_address, flags); + gtt->ttm.dma_address, flags); } gart_bind_fail: @@ -926,7 +921,8 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev, bo_mem->mem_type == AMDGPU_PL_OA) return -EINVAL; - if (!amdgpu_gtt_mgr_has_gart_addr(bo_mem)) { + if (bo_mem->mem_type != TTM_PL_TT || + !amdgpu_gtt_mgr_has_gart_addr(bo_mem)) { gtt->offset = AMDGPU_BO_INVALID_OFFSET; return 0; } @@ -937,7 +933,7 @@ static int amdgpu_ttm_backend_bind(struct ttm_device *bdev, /* bind pages into GART page tables */ gtt->offset = (u64)bo_mem->start << PAGE_SHIFT; r = amdgpu_gart_bind(adev, gtt->offset, ttm->num_pages, - ttm->pages, gtt->ttm.dma_address, flags); + gtt->ttm.dma_address, flags); if (r) DRM_ERROR("failed to bind %u pages at 0x%08llX\n", @@ -1131,8 +1127,6 @@ static int amdgpu_ttm_tt_populate(struct ttm_device *bdev, ttm->sg = kzalloc(sizeof(struct sg_table), GFP_KERNEL); if (!ttm->sg) return -ENOMEM; - - ttm->page_flags |= TTM_PAGE_FLAG_SG; return 0; } @@ -1158,7 +1152,6 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_device *bdev, amdgpu_ttm_tt_set_user_pages(ttm, NULL); kfree(ttm->sg); ttm->sg = NULL; - ttm->page_flags &= ~TTM_PAGE_FLAG_SG; return; } @@ -1192,6 +1185,9 @@ int amdgpu_ttm_tt_set_userptr(struct ttm_buffer_object *bo, return -ENOMEM; } + /* Set TTM_PAGE_FLAG_SG before populate but after create. */ + bo->ttm->page_flags |= TTM_PAGE_FLAG_SG; + gtt = (void *)bo->ttm; gtt->userptr = addr; gtt->userflags = flags; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 5eb84de588eb..2834981f8c08 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -257,36 +257,36 @@ void amdgpu_ucode_print_psp_hdr(const struct common_firmware_header *hdr) container_of(hdr, struct psp_firmware_header_v1_0, header); DRM_DEBUG("ucode_feature_version: %u\n", - le32_to_cpu(psp_hdr->ucode_feature_version)); + le32_to_cpu(psp_hdr->sos.fw_version)); DRM_DEBUG("sos_offset_bytes: %u\n", - le32_to_cpu(psp_hdr->sos_offset_bytes)); + le32_to_cpu(psp_hdr->sos.offset_bytes)); DRM_DEBUG("sos_size_bytes: %u\n", - le32_to_cpu(psp_hdr->sos_size_bytes)); + le32_to_cpu(psp_hdr->sos.size_bytes)); if (version_minor == 1) { const struct psp_firmware_header_v1_1 *psp_hdr_v1_1 = container_of(psp_hdr, struct psp_firmware_header_v1_1, v1_0); DRM_DEBUG("toc_header_version: %u\n", - le32_to_cpu(psp_hdr_v1_1->toc_header_version)); + le32_to_cpu(psp_hdr_v1_1->toc.fw_version)); DRM_DEBUG("toc_offset_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_1->toc_offset_bytes)); + le32_to_cpu(psp_hdr_v1_1->toc.offset_bytes)); DRM_DEBUG("toc_size_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_1->toc_size_bytes)); + le32_to_cpu(psp_hdr_v1_1->toc.size_bytes)); DRM_DEBUG("kdb_header_version: %u\n", - le32_to_cpu(psp_hdr_v1_1->kdb_header_version)); + le32_to_cpu(psp_hdr_v1_1->kdb.fw_version)); DRM_DEBUG("kdb_offset_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_1->kdb_offset_bytes)); + le32_to_cpu(psp_hdr_v1_1->kdb.offset_bytes)); DRM_DEBUG("kdb_size_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_1->kdb_size_bytes)); + le32_to_cpu(psp_hdr_v1_1->kdb.size_bytes)); } if (version_minor == 2) { const struct psp_firmware_header_v1_2 *psp_hdr_v1_2 = container_of(psp_hdr, struct psp_firmware_header_v1_2, v1_0); DRM_DEBUG("kdb_header_version: %u\n", - le32_to_cpu(psp_hdr_v1_2->kdb_header_version)); + le32_to_cpu(psp_hdr_v1_2->kdb.fw_version)); DRM_DEBUG("kdb_offset_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_2->kdb_offset_bytes)); + le32_to_cpu(psp_hdr_v1_2->kdb.offset_bytes)); DRM_DEBUG("kdb_size_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_2->kdb_size_bytes)); + le32_to_cpu(psp_hdr_v1_2->kdb.size_bytes)); } if (version_minor == 3) { const struct psp_firmware_header_v1_1 *psp_hdr_v1_1 = @@ -294,23 +294,23 @@ void amdgpu_ucode_print_psp_hdr(const struct common_firmware_header *hdr) const struct psp_firmware_header_v1_3 *psp_hdr_v1_3 = container_of(psp_hdr_v1_1, struct psp_firmware_header_v1_3, v1_1); DRM_DEBUG("toc_header_version: %u\n", - le32_to_cpu(psp_hdr_v1_3->v1_1.toc_header_version)); + le32_to_cpu(psp_hdr_v1_3->v1_1.toc.fw_version)); DRM_DEBUG("toc_offset_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_3->v1_1.toc_offset_bytes)); + le32_to_cpu(psp_hdr_v1_3->v1_1.toc.offset_bytes)); DRM_DEBUG("toc_size_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_3->v1_1.toc_size_bytes)); + le32_to_cpu(psp_hdr_v1_3->v1_1.toc.size_bytes)); DRM_DEBUG("kdb_header_version: %u\n", - le32_to_cpu(psp_hdr_v1_3->v1_1.kdb_header_version)); + le32_to_cpu(psp_hdr_v1_3->v1_1.kdb.fw_version)); DRM_DEBUG("kdb_offset_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_3->v1_1.kdb_offset_bytes)); + le32_to_cpu(psp_hdr_v1_3->v1_1.kdb.offset_bytes)); DRM_DEBUG("kdb_size_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_3->v1_1.kdb_size_bytes)); + le32_to_cpu(psp_hdr_v1_3->v1_1.kdb.size_bytes)); DRM_DEBUG("spl_header_version: %u\n", - le32_to_cpu(psp_hdr_v1_3->spl_header_version)); + le32_to_cpu(psp_hdr_v1_3->spl.fw_version)); DRM_DEBUG("spl_offset_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_3->spl_offset_bytes)); + le32_to_cpu(psp_hdr_v1_3->spl.offset_bytes)); DRM_DEBUG("spl_size_bytes: %u\n", - le32_to_cpu(psp_hdr_v1_3->spl_size_bytes)); + le32_to_cpu(psp_hdr_v1_3->spl.size_bytes)); } } else { DRM_ERROR("Unknown PSP ucode version: %u.%u\n", diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 2c42874f7784..270309e7f5f5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -71,43 +71,39 @@ struct smc_firmware_header_v2_1 { uint32_t pptable_entry_offset; }; +struct psp_fw_bin_desc { + uint32_t fw_version; + uint32_t offset_bytes; + uint32_t size_bytes; +}; + /* version_major=1, version_minor=0 */ struct psp_firmware_header_v1_0 { struct common_firmware_header header; - uint32_t ucode_feature_version; - uint32_t sos_offset_bytes; - uint32_t sos_size_bytes; + struct psp_fw_bin_desc sos; }; /* version_major=1, version_minor=1 */ struct psp_firmware_header_v1_1 { struct psp_firmware_header_v1_0 v1_0; - uint32_t toc_header_version; - uint32_t toc_offset_bytes; - uint32_t toc_size_bytes; - uint32_t kdb_header_version; - uint32_t kdb_offset_bytes; - uint32_t kdb_size_bytes; + struct psp_fw_bin_desc toc; + struct psp_fw_bin_desc kdb; }; /* version_major=1, version_minor=2 */ struct psp_firmware_header_v1_2 { struct psp_firmware_header_v1_0 v1_0; - uint32_t reserve[3]; - uint32_t kdb_header_version; - uint32_t kdb_offset_bytes; - uint32_t kdb_size_bytes; + struct psp_fw_bin_desc res; + struct psp_fw_bin_desc kdb; }; /* version_major=1, version_minor=3 */ struct psp_firmware_header_v1_3 { struct psp_firmware_header_v1_1 v1_1; - uint32_t spl_header_version; - uint32_t spl_offset_bytes; - uint32_t spl_size_bytes; - uint32_t rl_header_version; - uint32_t rl_offset_bytes; - uint32_t rl_size_bytes; + struct psp_fw_bin_desc spl; + struct psp_fw_bin_desc rl; + struct psp_fw_bin_desc sys_drv_aux; + struct psp_fw_bin_desc sos_aux; }; /* version_major=1, version_minor=0 */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index ea6f99be070b..f4489773715e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -94,6 +94,7 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev, struct amdgpu_iv_entry *entry) { struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; + struct amdgpu_ras *con = amdgpu_ras_get_context(adev); kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); if (adev->umc.ras_funcs && @@ -131,6 +132,9 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev, amdgpu_ras_add_bad_pages(adev, err_data->err_addr, err_data->err_addr_cnt); amdgpu_ras_save_bad_pages(adev); + + if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->send_hbm_bad_pages_num) + adev->smu.ppt_funcs->send_hbm_bad_pages_num(&adev->smu, con->eeprom_control.num_recs); } amdgpu_ras_reset_gpu(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h index bbcccf53080d..e5a75fb788dd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h @@ -22,6 +22,11 @@ #define __AMDGPU_UMC_H__ /* + * (addr / 256) * 4096, the higher 26 bits in ErrorAddr + * is the index of 4KB block + */ +#define ADDR_OF_4KB_BLOCK(addr) (((addr) & ~0xffULL) << 4) +/* * (addr / 256) * 8192, the higher 26 bits in ErrorAddr * is the index of 8KB block */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 647d2c31e8bd..6780df0fb265 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -288,6 +288,29 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) return 0; } +bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance) +{ + bool ret = false; + + int major; + int minor; + int revision; + + /* if cannot find IP data, then this VCN does not exist */ + if (amdgpu_discovery_get_vcn_version(adev, vcn_instance, &major, &minor, &revision) != 0) + return true; + + if ((type == VCN_ENCODE_RING) && (revision & VCN_BLOCK_ENCODE_DISABLE_MASK)) { + ret = true; + } else if ((type == VCN_DECODE_RING) && (revision & VCN_BLOCK_DECODE_DISABLE_MASK)) { + ret = true; + } else if ((type == VCN_UNIFIED_RING) && (revision & VCN_BLOCK_QUEUE_DISABLE_MASK)) { + ret = true; + } + + return ret; +} + int amdgpu_vcn_suspend(struct amdgpu_device *adev) { unsigned size; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index bc76cab67697..d74c62b49795 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -280,6 +280,16 @@ struct amdgpu_vcn_decode_buffer { uint32_t pad[30]; }; +#define VCN_BLOCK_ENCODE_DISABLE_MASK 0x80 +#define VCN_BLOCK_DECODE_DISABLE_MASK 0x40 +#define VCN_BLOCK_QUEUE_DISABLE_MASK 0xC0 + +enum vcn_ring_type { + VCN_ENCODE_RING, + VCN_DECODE_RING, + VCN_UNIFIED_RING, +}; + int amdgpu_vcn_sw_init(struct amdgpu_device *adev); int amdgpu_vcn_sw_fini(struct amdgpu_device *adev); int amdgpu_vcn_suspend(struct amdgpu_device *adev); @@ -287,6 +297,9 @@ int amdgpu_vcn_resume(struct amdgpu_device *adev); void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring); void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring); +bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, + enum vcn_ring_type type, uint32_t vcn_instance); + int amdgpu_vcn_dec_ring_test_ring(struct amdgpu_ring *ring); int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout); int amdgpu_vcn_dec_sw_ring_test_ring(struct amdgpu_ring *ring); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 18246b5b6ee3..078c068937fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -332,7 +332,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, base->next = bo->vm_bo; bo->vm_bo = base; - if (bo->tbo.base.resv != vm->root.base.bo->tbo.base.resv) + if (bo->tbo.base.resv != vm->root.bo->tbo.base.resv) return; vm->bulk_moveable = false; @@ -361,14 +361,14 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, * Helper to get the parent entry for the child page table. NULL if we are at * the root page directory. */ -static struct amdgpu_vm_pt *amdgpu_vm_pt_parent(struct amdgpu_vm_pt *pt) +static struct amdgpu_vm_bo_base *amdgpu_vm_pt_parent(struct amdgpu_vm_bo_base *pt) { - struct amdgpu_bo *parent = pt->base.bo->parent; + struct amdgpu_bo *parent = pt->bo->parent; if (!parent) return NULL; - return container_of(parent->vm_bo, struct amdgpu_vm_pt, base); + return parent->vm_bo; } /* @@ -376,8 +376,8 @@ static struct amdgpu_vm_pt *amdgpu_vm_pt_parent(struct amdgpu_vm_pt *pt) */ struct amdgpu_vm_pt_cursor { uint64_t pfn; - struct amdgpu_vm_pt *parent; - struct amdgpu_vm_pt *entry; + struct amdgpu_vm_bo_base *parent; + struct amdgpu_vm_bo_base *entry; unsigned level; }; @@ -416,17 +416,17 @@ static bool amdgpu_vm_pt_descendant(struct amdgpu_device *adev, { unsigned mask, shift, idx; - if (!cursor->entry->entries) + if ((cursor->level == AMDGPU_VM_PTB) || !cursor->entry || + !cursor->entry->bo) return false; - BUG_ON(!cursor->entry->base.bo); mask = amdgpu_vm_entries_mask(adev, cursor->level); shift = amdgpu_vm_level_shift(adev, cursor->level); ++cursor->level; idx = (cursor->pfn >> shift) & mask; cursor->parent = cursor->entry; - cursor->entry = &cursor->entry->entries[idx]; + cursor->entry = &to_amdgpu_bo_vm(cursor->entry->bo)->entries[idx]; return true; } @@ -453,7 +453,7 @@ static bool amdgpu_vm_pt_sibling(struct amdgpu_device *adev, shift = amdgpu_vm_level_shift(adev, cursor->level - 1); num_entries = amdgpu_vm_num_entries(adev, cursor->level - 1); - if (cursor->entry == &cursor->parent->entries[num_entries - 1]) + if (cursor->entry == &to_amdgpu_bo_vm(cursor->parent->bo)->entries[num_entries - 1]) return false; cursor->pfn += 1ULL << shift; @@ -539,7 +539,7 @@ static void amdgpu_vm_pt_first_dfs(struct amdgpu_device *adev, * True when the search should continue, false otherwise. */ static bool amdgpu_vm_pt_continue_dfs(struct amdgpu_vm_pt_cursor *start, - struct amdgpu_vm_pt *entry) + struct amdgpu_vm_bo_base *entry) { return entry && (!start || entry != start->entry); } @@ -590,7 +590,7 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, struct amdgpu_bo_list_entry *entry) { entry->priority = 0; - entry->tv.bo = &vm->root.base.bo->tbo; + entry->tv.bo = &vm->root.bo->tbo; /* Two for VM updates, one for TTM and one for the CS job */ entry->tv.num_shared = 4; entry->user_pages = NULL; @@ -622,7 +622,7 @@ void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo) for (bo_base = abo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; - if (abo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) + if (abo->tbo.base.resv == vm->root.bo->tbo.base.resv) vm->bulk_moveable = false; } @@ -781,11 +781,11 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, entries -= ats_entries; } else { - struct amdgpu_vm_pt *pt; + struct amdgpu_vm_bo_base *pt; - pt = container_of(ancestor->vm_bo, struct amdgpu_vm_pt, base); + pt = ancestor->vm_bo; ats_entries = amdgpu_vm_num_ats_entries(adev); - if ((pt - vm->root.entries) >= ats_entries) { + if ((pt - to_amdgpu_bo_vm(vm->root.bo)->entries) >= ats_entries) { ats_entries = 0; } else { ats_entries = entries; @@ -902,8 +902,8 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev, bp.type = ttm_bo_type_kernel; bp.no_wait_gpu = immediate; - if (vm->root.base.bo) - bp.resv = vm->root.base.bo->tbo.base.resv; + if (vm->root.bo) + bp.resv = vm->root.bo->tbo.base.resv; r = amdgpu_bo_create_vm(adev, &bp, vmbo); if (r) @@ -938,7 +938,7 @@ static int amdgpu_vm_pt_create(struct amdgpu_device *adev, } (*vmbo)->shadow->parent = amdgpu_bo_ref(bo); - amdgpu_bo_add_to_shadow_list((*vmbo)->shadow); + amdgpu_bo_add_to_shadow_list(*vmbo); return 0; } @@ -962,19 +962,13 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev, struct amdgpu_vm_pt_cursor *cursor, bool immediate) { - struct amdgpu_vm_pt *entry = cursor->entry; + struct amdgpu_vm_bo_base *entry = cursor->entry; struct amdgpu_bo *pt_bo; struct amdgpu_bo_vm *pt; int r; - if (entry->base.bo) { - if (cursor->level < AMDGPU_VM_PTB) - entry->entries = - to_amdgpu_bo_vm(entry->base.bo)->entries; - else - entry->entries = NULL; + if (entry->bo) return 0; - } r = amdgpu_vm_pt_create(adev, vm, cursor->level, immediate, &pt); if (r) @@ -984,13 +978,8 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev, * freeing them up in the wrong order. */ pt_bo = &pt->bo; - pt_bo->parent = amdgpu_bo_ref(cursor->parent->base.bo); - amdgpu_vm_bo_base_init(&entry->base, vm, pt_bo); - if (cursor->level < AMDGPU_VM_PTB) - entry->entries = pt->entries; - else - entry->entries = NULL; - + pt_bo->parent = amdgpu_bo_ref(cursor->parent->bo); + amdgpu_vm_bo_base_init(entry, vm, pt_bo); r = amdgpu_vm_clear_bo(adev, vm, pt, immediate); if (r) goto error_free_pt; @@ -1008,18 +997,17 @@ error_free_pt: * * @entry: PDE to free */ -static void amdgpu_vm_free_table(struct amdgpu_vm_pt *entry) +static void amdgpu_vm_free_table(struct amdgpu_vm_bo_base *entry) { struct amdgpu_bo *shadow; - if (entry->base.bo) { - shadow = amdgpu_bo_shadowed(entry->base.bo); - entry->base.bo->vm_bo = NULL; - list_del(&entry->base.vm_status); - amdgpu_bo_unref(&shadow); - amdgpu_bo_unref(&entry->base.bo); - } - entry->entries = NULL; + if (!entry->bo) + return; + shadow = amdgpu_bo_shadowed(entry->bo); + entry->bo->vm_bo = NULL; + list_del(&entry->vm_status); + amdgpu_bo_unref(&shadow); + amdgpu_bo_unref(&entry->bo); } /** @@ -1036,7 +1024,7 @@ static void amdgpu_vm_free_pts(struct amdgpu_device *adev, struct amdgpu_vm_pt_cursor *start) { struct amdgpu_vm_pt_cursor cursor; - struct amdgpu_vm_pt *entry; + struct amdgpu_vm_bo_base *entry; vm->bulk_moveable = false; @@ -1304,10 +1292,10 @@ uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr) */ static int amdgpu_vm_update_pde(struct amdgpu_vm_update_params *params, struct amdgpu_vm *vm, - struct amdgpu_vm_pt *entry) + struct amdgpu_vm_bo_base *entry) { - struct amdgpu_vm_pt *parent = amdgpu_vm_pt_parent(entry); - struct amdgpu_bo *bo = parent->base.bo, *pbo; + struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry); + struct amdgpu_bo *bo = parent->bo, *pbo; uint64_t pde, pt, flags; unsigned level; @@ -1315,8 +1303,8 @@ static int amdgpu_vm_update_pde(struct amdgpu_vm_update_params *params, pbo = pbo->parent; level += params->adev->vm_manager.root_level; - amdgpu_gmc_get_pde_for_bo(entry->base.bo, level, &pt, &flags); - pde = (entry - parent->entries) * 8; + amdgpu_gmc_get_pde_for_bo(entry->bo, level, &pt, &flags); + pde = (entry - to_amdgpu_bo_vm(parent->bo)->entries) * 8; return vm->update_funcs->update(params, to_amdgpu_bo_vm(bo), pde, pt, 1, 0, flags); } @@ -1333,11 +1321,11 @@ static void amdgpu_vm_invalidate_pds(struct amdgpu_device *adev, struct amdgpu_vm *vm) { struct amdgpu_vm_pt_cursor cursor; - struct amdgpu_vm_pt *entry; + struct amdgpu_vm_bo_base *entry; for_each_amdgpu_vm_pt_dfs_safe(adev, vm, NULL, cursor, entry) - if (entry->base.bo && !entry->base.moved) - amdgpu_vm_bo_relocated(&entry->base); + if (entry->bo && !entry->moved) + amdgpu_vm_bo_relocated(entry); } /** @@ -1371,11 +1359,12 @@ int amdgpu_vm_update_pdes(struct amdgpu_device *adev, return r; while (!list_empty(&vm->relocated)) { - struct amdgpu_vm_pt *entry; + struct amdgpu_vm_bo_base *entry; - entry = list_first_entry(&vm->relocated, struct amdgpu_vm_pt, - base.vm_status); - amdgpu_vm_bo_idle(&entry->base); + entry = list_first_entry(&vm->relocated, + struct amdgpu_vm_bo_base, + vm_status); + amdgpu_vm_bo_idle(entry); r = amdgpu_vm_update_pde(¶ms, vm, entry); if (r) @@ -1555,7 +1544,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, continue; } - pt = cursor.entry->base.bo; + pt = cursor.entry->bo; if (!pt) { /* We need all PDs and PTs for mapping something, */ if (flags & AMDGPU_PTE_VALID) @@ -1567,7 +1556,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, if (!amdgpu_vm_pt_ancestor(&cursor)) return -EINVAL; - pt = cursor.entry->base.bo; + pt = cursor.entry->bo; shift = parent_shift; frag_end = max(frag_end, ALIGN(frag_start + 1, 1ULL << shift)); @@ -1622,7 +1611,7 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, */ while (cursor.pfn < frag_start) { /* Make sure previous mapping is freed */ - if (cursor.entry->base.bo) { + if (cursor.entry->bo) { params->table_freed = true; amdgpu_vm_free_pts(adev, params->vm, &cursor); } @@ -1704,7 +1693,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, if (!unlocked && !dma_fence_is_signaled(vm->last_unlocked)) { struct dma_fence *tmp = dma_fence_get_stub(); - amdgpu_bo_fence(vm->root.base.bo, vm->last_unlocked, true); + amdgpu_bo_fence(vm->root.bo, vm->last_unlocked, true); swap(vm->last_unlocked, tmp); dma_fence_put(tmp); } @@ -1769,7 +1758,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, r = vm->update_funcs->commit(¶ms, fence); if (table_freed) - *table_freed = *table_freed || params.table_freed; + *table_freed = params.table_freed; error_unlock: amdgpu_vm_eviction_unlock(vm); @@ -1827,7 +1816,6 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, * @adev: amdgpu_device pointer * @bo_va: requested BO and VM object * @clear: if true clear the entries - * @table_freed: return true if page table is freed * * Fill in the page table entries for @bo_va. * @@ -1835,7 +1823,7 @@ void amdgpu_vm_get_memory(struct amdgpu_vm *vm, uint64_t *vram_mem, * 0 for success, -EINVAL for failure. */ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, - bool clear, bool *table_freed) + bool clear) { struct amdgpu_bo *bo = bo_va->base.bo; struct amdgpu_vm *vm = bo_va->base.vm; @@ -1850,7 +1838,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, if (clear || !bo) { mem = NULL; - resv = vm->root.base.bo->tbo.base.resv; + resv = vm->root.bo->tbo.base.resv; } else { struct drm_gem_object *obj = &bo->tbo.base; @@ -1881,7 +1869,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, } if (clear || (bo && bo->tbo.base.resv == - vm->root.base.bo->tbo.base.resv)) + vm->root.bo->tbo.base.resv)) last_update = &vm->last_update; else last_update = &bo_va->last_pt_update; @@ -1914,7 +1902,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, resv, mapping->start, mapping->last, update_flags, mapping->offset, mem, - pages_addr, last_update, table_freed); + pages_addr, last_update, NULL); if (r) return r; } @@ -1923,7 +1911,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, * the evicted list so that it gets validated again on the * next command submission. */ - if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) { + if (bo && bo->tbo.base.resv == vm->root.bo->tbo.base.resv) { uint32_t mem_type = bo->tbo.resource->mem_type; if (!(bo->preferred_domains & @@ -2060,7 +2048,7 @@ static void amdgpu_vm_free_mapping(struct amdgpu_device *adev, */ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) { - struct dma_resv *resv = vm->root.base.bo->tbo.base.resv; + struct dma_resv *resv = vm->root.bo->tbo.base.resv; struct dma_fence *excl, **shared; unsigned i, shared_count; int r; @@ -2106,7 +2094,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct dma_fence **fence) { - struct dma_resv *resv = vm->root.base.bo->tbo.base.resv; + struct dma_resv *resv = vm->root.bo->tbo.base.resv; struct amdgpu_bo_va_mapping *mapping; uint64_t init_pte_value = 0; struct dma_fence *f = NULL; @@ -2166,7 +2154,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, list_for_each_entry_safe(bo_va, tmp, &vm->moved, base.vm_status) { /* Per VM BOs never need to bo cleared in the page tables */ - r = amdgpu_vm_bo_update(adev, bo_va, false, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, false); if (r) return r; } @@ -2185,7 +2173,7 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, else clear = true; - r = amdgpu_vm_bo_update(adev, bo_va, clear, NULL); + r = amdgpu_vm_bo_update(adev, bo_va, clear); if (r) return r; @@ -2265,7 +2253,7 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev, if (mapping->flags & AMDGPU_PTE_PRT) amdgpu_vm_prt_get(adev); - if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv && + 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); } @@ -2627,7 +2615,7 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, struct amdgpu_vm_bo_base **base; if (bo) { - if (bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) + if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv) vm->bulk_moveable = false; for (base = &bo_va->base.bo->vm_bo; *base; @@ -2721,7 +2709,7 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, for (bo_base = bo->vm_bo; bo_base; bo_base = bo_base->next) { struct amdgpu_vm *vm = bo_base->vm; - if (evicted && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) { + if (evicted && bo->tbo.base.resv == vm->root.bo->tbo.base.resv) { amdgpu_vm_bo_evicted(bo_base); continue; } @@ -2732,7 +2720,7 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, if (bo->tbo.type == ttm_bo_type_kernel) amdgpu_vm_bo_relocated(bo_base); - else if (bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) + else if (bo->tbo.base.resv == vm->root.bo->tbo.base.resv) amdgpu_vm_bo_moved(bo_base); else amdgpu_vm_bo_invalidated(bo_base); @@ -2862,7 +2850,7 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, */ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) { - timeout = dma_resv_wait_timeout(vm->root.base.bo->tbo.base.resv, true, + timeout = dma_resv_wait_timeout(vm->root.bo->tbo.base.resv, true, true, timeout); if (timeout <= 0) return timeout; @@ -2948,13 +2936,13 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid) if (r) goto error_unreserve; - amdgpu_vm_bo_base_init(&vm->root.base, vm, root_bo); + amdgpu_vm_bo_base_init(&vm->root, vm, root_bo); r = amdgpu_vm_clear_bo(adev, vm, root, false); if (r) goto error_unreserve; - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); if (pasid) { unsigned long flags; @@ -2974,12 +2962,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid) return 0; error_unreserve: - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); error_free_root: amdgpu_bo_unref(&root->shadow); amdgpu_bo_unref(&root_bo); - vm->root.base.bo = NULL; + vm->root.bo = NULL; error_free_delayed: dma_fence_put(vm->last_unlocked); @@ -3005,17 +2993,14 @@ error_free_immediate: * 0 if this VM is clean */ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev, - struct amdgpu_vm *vm) + struct amdgpu_vm *vm) { enum amdgpu_vm_level root = adev->vm_manager.root_level; unsigned int entries = amdgpu_vm_num_entries(adev, root); unsigned int i = 0; - if (!(vm->root.entries)) - return 0; - for (i = 0; i < entries; i++) { - if (vm->root.entries[i].base.bo) + if (to_amdgpu_bo_vm(vm->root.bo)->entries[i].bo) return -EINVAL; } @@ -3049,7 +3034,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, bool pte_support_ats = (adev->asic_type == CHIP_RAVEN); int r; - r = amdgpu_bo_reserve(vm->root.base.bo, true); + r = amdgpu_bo_reserve(vm->root.bo, true); if (r) return r; @@ -3077,7 +3062,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (pte_support_ats != vm->pte_support_ats) { vm->pte_support_ats = pte_support_ats; r = amdgpu_vm_clear_bo(adev, vm, - to_amdgpu_bo_vm(vm->root.base.bo), + to_amdgpu_bo_vm(vm->root.bo), false); if (r) goto free_idr; @@ -3094,7 +3079,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (vm->use_cpu_for_update) { /* Sync with last SDMA update/clear before switching to CPU */ - r = amdgpu_bo_sync_wait(vm->root.base.bo, + r = amdgpu_bo_sync_wait(vm->root.bo, AMDGPU_FENCE_OWNER_UNDEFINED, true); if (r) goto free_idr; @@ -3122,7 +3107,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, } /* Free the shadow bo for compute VM */ - amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.base.bo)->shadow); + amdgpu_bo_unref(&to_amdgpu_bo_vm(vm->root.bo)->shadow); if (pasid) vm->pasid = pasid; @@ -3138,7 +3123,7 @@ free_idr: spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); } unreserve_bo: - amdgpu_bo_unreserve(vm->root.base.bo); + amdgpu_bo_unreserve(vm->root.bo); return r; } @@ -3181,7 +3166,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm); - root = amdgpu_bo_ref(vm->root.base.bo); + root = amdgpu_bo_ref(vm->root.bo); amdgpu_bo_reserve(root, true); if (vm->pasid) { unsigned long flags; @@ -3208,7 +3193,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) amdgpu_vm_free_pts(adev, vm, NULL); amdgpu_bo_unreserve(root); amdgpu_bo_unref(&root); - WARN_ON(vm->root.base.bo); + WARN_ON(vm->root.bo); drm_sched_entity_destroy(&vm->immediate); drm_sched_entity_destroy(&vm->delayed); @@ -3325,7 +3310,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) /* Wait vm idle to make sure the vmid set in SPM_VMID is * not referenced anymore. */ - r = amdgpu_bo_reserve(fpriv->vm.root.base.bo, true); + r = amdgpu_bo_reserve(fpriv->vm.root.bo, true); if (r) return r; @@ -3333,7 +3318,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) if (r < 0) return r; - amdgpu_bo_unreserve(fpriv->vm.root.base.bo); + amdgpu_bo_unreserve(fpriv->vm.root.bo); amdgpu_vmid_free_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB_0); break; default: @@ -3399,19 +3384,20 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, { bool is_compute_context = false; struct amdgpu_bo *root; + unsigned long irqflags; uint64_t value, flags; struct amdgpu_vm *vm; int r; - spin_lock(&adev->vm_manager.pasid_lock); + spin_lock_irqsave(&adev->vm_manager.pasid_lock, irqflags); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); if (vm) { - root = amdgpu_bo_ref(vm->root.base.bo); + root = amdgpu_bo_ref(vm->root.bo); is_compute_context = vm->is_compute_context; } else { root = NULL; } - spin_unlock(&adev->vm_manager.pasid_lock); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, irqflags); if (!root) return false; @@ -3429,11 +3415,11 @@ bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, goto error_unref; /* Double check that the VM still exists */ - spin_lock(&adev->vm_manager.pasid_lock); + spin_lock_irqsave(&adev->vm_manager.pasid_lock, irqflags); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); - if (vm && vm->root.base.bo != root) + if (vm && vm->root.bo != root) vm = NULL; - spin_unlock(&adev->vm_manager.pasid_lock); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, irqflags); if (!vm) goto error_unlock; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 1f089da1e615..f8fa653d4da7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -152,13 +152,6 @@ struct amdgpu_vm_bo_base { bool moved; }; -struct amdgpu_vm_pt { - struct amdgpu_vm_bo_base base; - - /* array of page tables, one for each directory entry */ - struct amdgpu_vm_pt *entries; -}; - /* provided by hw blocks that can write ptes, e.g., sdma */ struct amdgpu_vm_pte_funcs { /* number of dw to reserve per operation */ @@ -284,7 +277,7 @@ struct amdgpu_vm { struct list_head done; /* contains the page directory */ - struct amdgpu_vm_pt root; + struct amdgpu_vm_bo_base root; struct dma_fence *last_update; /* Scheduler entities for page table updates */ @@ -413,7 +406,7 @@ int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev, struct dma_fence **fence, bool *free_table); int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, - bool clear, bool *table_freed); + bool clear); bool amdgpu_vm_evictable(struct amdgpu_bo *bo); void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev, struct amdgpu_bo *bo, bool evicted); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c index 422958152c2b..dbb551762805 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c @@ -112,7 +112,7 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p, swap(p->vm->last_unlocked, f); dma_fence_put(tmp); } else { - amdgpu_bo_fence(p->vm->root.base.bo, f, true); + amdgpu_bo_fence(p->vm->root.bo, f, true); } if (fence && !p->immediate) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 436ec246a7da..2fd77c36a1ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -463,6 +463,11 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, if (i == 1) node->base.placement |= TTM_PL_FLAG_CONTIGUOUS; + if (adev->gmc.xgmi.connected_to_cpu) + node->base.bus.caching = ttm_cached; + else + node->base.bus.caching = ttm_write_combined; + atomic64_add(vis_usage, &mgr->vis_usage); *res = &node->base; return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c index 5b90efd6f6d0..3ac505d954c4 100644 --- a/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/athub_v2_0.c @@ -36,9 +36,12 @@ athub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *adev, { uint32_t def, data; + if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) + return; + def = data = RREG32_SOC15(ATHUB, 0, mmATHUB_MISC_CNTL); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) + if (enable) data |= ATHUB_MISC_CNTL__CG_ENABLE_MASK; else data &= ~ATHUB_MISC_CNTL__CG_ENABLE_MASK; @@ -53,10 +56,13 @@ athub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *adev, { uint32_t def, data; + if (!((adev->cg_flags & AMD_CG_SUPPORT_MC_LS) && + (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS))) + return; + def = data = RREG32_SOC15(ATHUB, 0, mmATHUB_MISC_CNTL); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) && - (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS)) + if (enable) data |= ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK; else data &= ~ATHUB_MISC_CNTL__CG_MEM_LS_ENABLE_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c index 33324427b555..7e0d8c092c7e 100644 --- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c +++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c @@ -766,7 +766,7 @@ static const struct amdgpu_irq_src_funcs dce_virtual_crtc_irq_funcs = { static void dce_virtual_set_irq_funcs(struct amdgpu_device *adev) { - adev->crtc_irq.num_types = AMDGPU_CRTC_IRQ_VBLANK6 + 1; + adev->crtc_irq.num_types = adev->mode_info.num_crtc; adev->crtc_irq.funcs = &dce_virtual_crtc_irq_funcs; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 2d56b60bc058..f5e9c022960b 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -5086,47 +5086,44 @@ static void gfx_v10_0_tcp_harvest(struct amdgpu_device *adev) 4 + /* RMI */ 1); /* SQG */ - if (adev->asic_type == CHIP_NAVI10 || - adev->asic_type == CHIP_NAVI14 || - adev->asic_type == CHIP_NAVI12) { - mutex_lock(&adev->grbm_idx_mutex); - for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { - for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { - gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff); - wgp_active_bitmap = gfx_v10_0_get_wgp_active_bitmap_per_sh(adev); - /* - * Set corresponding TCP bits for the inactive WGPs in - * GCRD_SA_TARGETS_DISABLE - */ - gcrd_targets_disable_tcp = 0; - /* Set TCP & SQC bits in UTCL1_UTCL0_INVREQ_DISABLE */ - utcl_invreq_disable = 0; - - for (k = 0; k < max_wgp_per_sh; k++) { - if (!(wgp_active_bitmap & (1 << k))) { - gcrd_targets_disable_tcp |= 3 << (2 * k); - utcl_invreq_disable |= (3 << (2 * k)) | - (3 << (2 * (max_wgp_per_sh + k))); - } + mutex_lock(&adev->grbm_idx_mutex); + for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { + for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff); + wgp_active_bitmap = gfx_v10_0_get_wgp_active_bitmap_per_sh(adev); + /* + * Set corresponding TCP bits for the inactive WGPs in + * GCRD_SA_TARGETS_DISABLE + */ + gcrd_targets_disable_tcp = 0; + /* Set TCP & SQC bits in UTCL1_UTCL0_INVREQ_DISABLE */ + utcl_invreq_disable = 0; + + for (k = 0; k < max_wgp_per_sh; k++) { + if (!(wgp_active_bitmap & (1 << k))) { + gcrd_targets_disable_tcp |= 3 << (2 * k); + gcrd_targets_disable_tcp |= 1 << (k + (max_wgp_per_sh * 2)); + utcl_invreq_disable |= (3 << (2 * k)) | + (3 << (2 * (max_wgp_per_sh + k))); } - - tmp = RREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE); - /* only override TCP & SQC bits */ - tmp &= 0xffffffff << (4 * max_wgp_per_sh); - tmp |= (utcl_invreq_disable & utcl_invreq_disable_mask); - WREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE, tmp); - - tmp = RREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE); - /* only override TCP bits */ - tmp &= 0xffffffff << (2 * max_wgp_per_sh); - tmp |= (gcrd_targets_disable_tcp & gcrd_targets_disable_mask); - WREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE, tmp); } - } - gfx_v10_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); - mutex_unlock(&adev->grbm_idx_mutex); + tmp = RREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE); + /* only override TCP & SQC bits */ + tmp &= (0xffffffffU << (4 * max_wgp_per_sh)); + tmp |= (utcl_invreq_disable & utcl_invreq_disable_mask); + WREG32_SOC15(GC, 0, mmUTCL1_UTCL0_INVREQ_DISABLE, tmp); + + tmp = RREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE); + /* only override TCP & SQC bits */ + tmp &= (0xffffffffU << (3 * max_wgp_per_sh)); + tmp |= (gcrd_targets_disable_tcp & gcrd_targets_disable_mask); + WREG32_SOC15(GC, 0, mmGCRD_SA_TARGETS_DISABLE, tmp); + } } + + gfx_v10_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff); + mutex_unlock(&adev->grbm_idx_mutex); } static void gfx_v10_0_get_tcc_info(struct amdgpu_device *adev) @@ -7404,7 +7401,10 @@ static int gfx_v10_0_hw_init(void *handle) * init golden registers and rlc resume may override some registers, * reconfig them here */ - gfx_v10_0_tcp_harvest(adev); + if (adev->asic_type == CHIP_NAVI10 || + adev->asic_type == CHIP_NAVI14 || + adev->asic_type == CHIP_NAVI12) + gfx_v10_0_tcp_harvest(adev); r = gfx_v10_0_cp_resume(adev); if (r) @@ -7777,6 +7777,9 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade { uint32_t data, def; + if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS))) + return; + /* It is disabled by HW by default */ if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { /* 0 - Disable some blocks' MGCG */ @@ -7791,6 +7794,7 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK); if (def != data) @@ -7813,13 +7817,15 @@ static void gfx_v10_0_update_medium_grain_clock_gating(struct amdgpu_device *ade WREG32_SOC15(GC, 0, mmCP_MEM_SLP_CNTL, data); } } - } else { + } else if (!enable || !(adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) { /* 1 - MGCG_OVERRIDE */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); data |= (RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK | RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK | - RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK); + RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK | + RLC_CGTT_MGCG_OVERRIDE__ENABLE_CGTS_LEGACY_MASK); if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); @@ -7845,22 +7851,34 @@ static void gfx_v10_0_update_3d_clock_gating(struct amdgpu_device *adev, { uint32_t data, def; + if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_3D_CGCG | AMD_CG_SUPPORT_GFX_3D_CGLS))) + return; + /* Enable 3D CGCG/CGLS */ - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG)) { + if (enable) { /* write cmd to clear cgcg/cgls ov */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); + /* unset CGCG override */ - data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG) + data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_GFX3D_CG_OVERRIDE_MASK; + /* update CGCG and CGLS override bits */ if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); + /* enable 3Dcgcg FSM(0x0000363f) */ def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D); - data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) | - RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK; + data = 0; + + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG) + data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) | + RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS) data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) | RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK; + if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data); @@ -7873,9 +7891,14 @@ static void gfx_v10_0_update_3d_clock_gating(struct amdgpu_device *adev, } else { /* Disable CGCG/CGLS */ def = data = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D); + /* disable cgcg, cgls should be disabled */ - data &= ~(RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK | - RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK); + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGCG) + data &= ~RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK; + + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS) + data &= ~RLC_CGCG_CGLS_CTRL_3D__CGLS_EN_MASK; + /* disable cgcg and cgls in FSM */ if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D, data); @@ -7887,25 +7910,35 @@ static void gfx_v10_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade { uint32_t def, data; - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG)) { + if (!(adev->cg_flags & (AMD_CG_SUPPORT_GFX_CGCG | AMD_CG_SUPPORT_GFX_CGLS))) + return; + + if (enable) { def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); + /* unset CGCG override */ - data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG) + data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGCG_OVERRIDE_MASK; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK; - else - data |= RLC_CGTT_MGCG_OVERRIDE__GFXIP_CGLS_OVERRIDE_MASK; + /* update CGCG and CGLS override bits */ if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data); /* enable cgcg FSM(0x0000363F) */ def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL); - data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) | - RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK; + data = 0; + + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG) + data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) | + RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK; + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) data |= (0x000F << RLC_CGCG_CGLS_CTRL__CGLS_REP_COMPANSAT_DELAY__SHIFT) | RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK; + if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data); @@ -7917,8 +7950,14 @@ static void gfx_v10_0_update_coarse_grain_clock_gating(struct amdgpu_device *ade WREG32_SOC15(GC, 0, mmCP_RB_WPTR_POLL_CNTL, data); } else { def = data = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL); + /* reset CGCG/CGLS bits */ - data &= ~(RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK | RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK); + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGCG) + data &= ~RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK; + + if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS) + data &= ~RLC_CGCG_CGLS_CTRL__CGLS_EN_MASK; + /* disable cgcg and cgls in FSM */ if (def != data) WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, data); @@ -7930,7 +7969,10 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev, { uint32_t def, data; - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_FGCG)) { + if (!(adev->cg_flags & AMD_CG_SUPPORT_GFX_FGCG)) + return; + + if (enable) { def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE); /* unset FGCG override */ data &= ~RLC_CGTT_MGCG_OVERRIDE__GFXIP_FGCG_OVERRIDE_MASK; @@ -7961,6 +8003,97 @@ static void gfx_v10_0_update_fine_grain_clock_gating(struct amdgpu_device *adev, } } +static void gfx_v10_0_apply_medium_grain_clock_gating_workaround(struct amdgpu_device *adev) +{ + uint32_t reg_data = 0; + uint32_t reg_idx = 0; + uint32_t i; + + const uint32_t tcp_ctrl_regs[] = { + mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP12_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP12_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP12_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP12_CU1_TCP_CTRL_REG + }; + + const uint32_t tcp_ctrl_regs_nv12[] = { + mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP00_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP01_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP01_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP02_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP02_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP10_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP10_CU1_TCP_CTRL_REG, + mmCGTS_SA0_WGP11_CU0_TCP_CTRL_REG, + mmCGTS_SA0_WGP11_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP00_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP00_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP01_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP01_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP02_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP02_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP10_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP10_CU1_TCP_CTRL_REG, + mmCGTS_SA1_WGP11_CU0_TCP_CTRL_REG, + mmCGTS_SA1_WGP11_CU1_TCP_CTRL_REG, + }; + + const uint32_t sm_ctlr_regs[] = { + mmCGTS_SA0_QUAD0_SM_CTRL_REG, + mmCGTS_SA0_QUAD1_SM_CTRL_REG, + mmCGTS_SA1_QUAD0_SM_CTRL_REG, + mmCGTS_SA1_QUAD1_SM_CTRL_REG + }; + + if (adev->asic_type == CHIP_NAVI12) { + for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs_nv12); i++) { + reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] + + tcp_ctrl_regs_nv12[i]; + reg_data = RREG32(reg_idx); + reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK; + WREG32(reg_idx, reg_data); + } + } else { + for (i = 0; i < ARRAY_SIZE(tcp_ctrl_regs); i++) { + reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_WGP00_CU0_TCP_CTRL_REG_BASE_IDX] + + tcp_ctrl_regs[i]; + reg_data = RREG32(reg_idx); + reg_data |= CGTS_SA0_WGP00_CU0_TCP_CTRL_REG__TCPI_LS_OVERRIDE_MASK; + WREG32(reg_idx, reg_data); + } + } + + for (i = 0; i < ARRAY_SIZE(sm_ctlr_regs); i++) { + reg_idx = adev->reg_offset[GC_HWIP][0][mmCGTS_SA0_QUAD0_SM_CTRL_REG_BASE_IDX] + + sm_ctlr_regs[i]; + reg_data = RREG32(reg_idx); + reg_data &= ~CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE_MASK; + reg_data |= 2 << CGTS_SA0_QUAD0_SM_CTRL_REG__SM_MODE__SHIFT; + WREG32(reg_idx, reg_data); + } +} + static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, bool enable) { @@ -7977,6 +8110,10 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, gfx_v10_0_update_3d_clock_gating(adev, enable); /* === CGCG + CGLS === */ gfx_v10_0_update_coarse_grain_clock_gating(adev, enable); + + if ((adev->asic_type >= CHIP_NAVI10) && + (adev->asic_type <= CHIP_NAVI12)) + gfx_v10_0_apply_medium_grain_clock_gating_workaround(adev); } else { /* CGCG/CGLS should be disabled before MGCG/MGLS * === CGCG + CGLS === @@ -9324,17 +9461,22 @@ static void gfx_v10_0_set_user_wgp_inactive_bitmap_per_sh(struct amdgpu_device * static u32 gfx_v10_0_get_wgp_active_bitmap_per_sh(struct amdgpu_device *adev) { - u32 data, wgp_bitmask; - data = RREG32_SOC15(GC, 0, mmCC_GC_SHADER_ARRAY_CONFIG); - data |= RREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG); + u32 disabled_mask = + ~amdgpu_gfx_create_bitmask(adev->gfx.config.max_cu_per_sh >> 1); + u32 efuse_setting = 0; + u32 vbios_setting = 0; + + efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SHADER_ARRAY_CONFIG); + efuse_setting &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK; + efuse_setting >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT; - data &= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK; - data >>= CC_GC_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT; + vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SHADER_ARRAY_CONFIG); + vbios_setting &= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_WGPS_MASK; + vbios_setting >>= GC_USER_SHADER_ARRAY_CONFIG__INACTIVE_WGPS__SHIFT; - wgp_bitmask = - amdgpu_gfx_create_bitmask(adev->gfx.config.max_cu_per_sh >> 1); + disabled_mask |= efuse_setting | vbios_setting; - return (~data) & wgp_bitmask; + return (~disabled_mask); } static u32 gfx_v10_0_get_cu_active_bitmap_per_sh(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c index c0352dcc89be..1769c4cba2ad 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c @@ -782,11 +782,6 @@ void gfx_v9_4_2_set_power_brake_sequence(struct amdgpu_device *adev) tmp = REG_SET_FIELD(tmp, GC_THROTTLE_CTRL1, PWRBRK_STALL_EN, 1); WREG32_SOC15(GC, 0, regGC_THROTTLE_CTRL1, tmp); - WREG32_SOC15(GC, 0, regDIDT_IND_INDEX, ixDIDT_SQ_THROTTLE_CTRL); - tmp = 0; - tmp = REG_SET_FIELD(tmp, DIDT_SQ_THROTTLE_CTRL, PWRBRK_STALL_EN, 1); - WREG32_SOC15(GC, 0, regDIDT_IND_DATA, tmp); - WREG32_SOC15(GC, 0, regGC_CAC_IND_INDEX, ixPWRBRK_STALL_PATTERN_CTRL); tmp = 0; tmp = REG_SET_FIELD(tmp, PWRBRK_STALL_PATTERN_CTRL, PWRBRK_END_STEP, 0x12); diff --git a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c index 7a15e669b68d..5793977953cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c +++ b/drivers/gpu/drm/amd/amdgpu/hdp_v5_0.c @@ -90,45 +90,56 @@ static void hdp_v5_0_update_mem_power_gating(struct amdgpu_device *adev, RC_MEM_POWER_SD_EN, 0); WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl); - /* only one clock gating mode (LS/DS/SD) can be enabled */ - if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) { - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, - HDP_MEM_POWER_CTRL, - IPH_MEM_POWER_LS_EN, enable); - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, - HDP_MEM_POWER_CTRL, - RC_MEM_POWER_LS_EN, enable); - } else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) { - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, - HDP_MEM_POWER_CTRL, - IPH_MEM_POWER_DS_EN, enable); - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, - HDP_MEM_POWER_CTRL, - RC_MEM_POWER_DS_EN, enable); - } else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) { - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, - HDP_MEM_POWER_CTRL, - IPH_MEM_POWER_SD_EN, enable); - /* RC should not use shut down mode, fallback to ds */ - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, - HDP_MEM_POWER_CTRL, - RC_MEM_POWER_DS_EN, enable); - } - - /* confirmed that IPH_MEM_POWER_CTRL_EN and RC_MEM_POWER_CTRL_EN have to - * be set for SRAM LS/DS/SD */ - if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS | - AMD_CG_SUPPORT_HDP_SD)) { - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL, - IPH_MEM_POWER_CTRL_EN, 1); - hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL, - RC_MEM_POWER_CTRL_EN, 1); + /* Already disabled above. The actions below are for "enabled" only */ + if (enable) { + /* only one clock gating mode (LS/DS/SD) can be enabled */ + if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) { + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + IPH_MEM_POWER_LS_EN, 1); + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + RC_MEM_POWER_LS_EN, 1); + } else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) { + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + IPH_MEM_POWER_DS_EN, 1); + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + RC_MEM_POWER_DS_EN, 1); + } else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_SD) { + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + IPH_MEM_POWER_SD_EN, 1); + /* RC should not use shut down mode, fallback to ds or ls if allowed */ + if (adev->cg_flags & AMD_CG_SUPPORT_HDP_DS) + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + RC_MEM_POWER_DS_EN, 1); + else if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, + HDP_MEM_POWER_CTRL, + RC_MEM_POWER_LS_EN, 1); + } + + /* confirmed that IPH_MEM_POWER_CTRL_EN and RC_MEM_POWER_CTRL_EN have to + * be set for SRAM LS/DS/SD */ + if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_DS | + AMD_CG_SUPPORT_HDP_SD)) { + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL, + IPH_MEM_POWER_CTRL_EN, 1); + hdp_mem_pwr_cntl = REG_SET_FIELD(hdp_mem_pwr_cntl, HDP_MEM_POWER_CTRL, + RC_MEM_POWER_CTRL_EN, 1); + WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl); + } } - WREG32_SOC15(HDP, 0, mmHDP_MEM_POWER_CTRL, hdp_mem_pwr_cntl); - - /* restore IPH & RC clock override after clock/power mode changing */ - WREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL, hdp_clk_cntl1); + /* disable IPH & RC clock override after clock/power mode changing */ + hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL, + IPH_MEM_CLK_SOFT_OVERRIDE, 0); + hdp_clk_cntl = REG_SET_FIELD(hdp_clk_cntl, HDP_CLK_CNTL, + RC_MEM_CLK_SOFT_OVERRIDE, 0); + WREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL, hdp_clk_cntl); } static void hdp_v5_0_update_medium_grain_clock_gating(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c index f7e93bbc4e15..7ded6b2f058e 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c @@ -568,6 +568,9 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad { uint32_t def, data, def1, data1; + if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) + return; + switch (adev->asic_type) { case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: @@ -582,7 +585,7 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad break; } - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG)) { + if (enable) { data |= MM_ATC_L2_MISC_CG__ENABLE_MASK; data1 &= ~(DAGB0_CNTL_MISC2__DISABLE_WRREQ_CG_MASK | @@ -627,6 +630,9 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade { uint32_t def, data; + if (!(adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) + return; + switch (adev->asic_type) { case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: @@ -639,7 +645,7 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade break; } - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_MC_LS)) + if (enable) data |= MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK; else data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK; diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c index 3ee481557fc9..ff2307d7ee0f 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c @@ -252,7 +252,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. */ - if (!down_read_trylock(&adev->reset_sem)) + if (!down_write_trylock(&adev->reset_sem)) return; amdgpu_virt_fini_data_exchange(adev); @@ -268,7 +268,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work) flr_done: atomic_set(&adev->in_gpu_reset, 0); - up_read(&adev->reset_sem); + up_write(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c index 48e588d3c409..9f7aac435d69 100644 --- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c +++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c @@ -273,7 +273,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) * otherwise the mailbox msg will be ruined/reseted by * the VF FLR. */ - if (!down_read_trylock(&adev->reset_sem)) + if (!down_write_trylock(&adev->reset_sem)) return; amdgpu_virt_fini_data_exchange(adev); @@ -289,7 +289,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work) flr_done: atomic_set(&adev->in_gpu_reset, 0); - up_read(&adev->reset_sem); + up_write(&adev->reset_sem); /* Trigger recovery for world switch failure if no TDR */ if (amdgpu_device_should_recover_gpu(adev) diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index 05ddec7ba7e2..7b79eeaa88aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -51,6 +51,8 @@ #define mmBIF_MMSCH1_DOORBELL_RANGE 0x01d8 #define mmBIF_MMSCH1_DOORBELL_RANGE_BASE_IDX 2 +#define smnPCIE_LC_LINK_WIDTH_CNTL 0x11140288 + static void nbio_v2_3_remap_hdp_registers(struct amdgpu_device *adev) { WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL, @@ -218,8 +220,11 @@ static void nbio_v2_3_update_medium_grain_clock_gating(struct amdgpu_device *ade { uint32_t def, data; + if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG)) + return; + def = data = RREG32_PCIE(smnCPM_CONTROL); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_MGCG)) { + if (enable) { data |= (CPM_CONTROL__LCLK_DYN_GATE_ENABLE_MASK | CPM_CONTROL__TXCLK_DYN_GATE_ENABLE_MASK | CPM_CONTROL__TXCLK_LCNT_GATE_ENABLE_MASK | @@ -244,8 +249,11 @@ static void nbio_v2_3_update_medium_grain_light_sleep(struct amdgpu_device *adev { uint32_t def, data; + if (!(adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) + return; + def = data = RREG32_PCIE(smnPCIE_CNTL2); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_BIF_LS)) { + if (enable) { data |= (PCIE_CNTL2__SLV_MEM_LS_EN_MASK | PCIE_CNTL2__MST_MEM_LS_EN_MASK | PCIE_CNTL2__REPLAY_MEM_LS_EN_MASK); @@ -463,6 +471,43 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) WREG32_PCIE(smnPCIE_LC_CNTL3, data); } +static void nbio_v2_3_apply_lc_spc_mode_wa(struct amdgpu_device *adev) +{ + uint32_t reg_data = 0; + uint32_t link_width = 0; + + if (!((adev->asic_type >= CHIP_NAVI10) && + (adev->asic_type <= CHIP_NAVI12))) + return; + + reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL); + link_width = (reg_data & PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK) + >> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT; + + /* + * Program PCIE_LC_CNTL6.LC_SPC_MODE_8GT to 0x2 (4 symbols per clock data) + * if link_width is 0x3 (x4) + */ + if (0x3 == link_width) { + reg_data = RREG32_PCIE(smnPCIE_LC_CNTL6); + reg_data &= ~PCIE_LC_CNTL6__LC_SPC_MODE_8GT_MASK; + reg_data |= (0x2 << PCIE_LC_CNTL6__LC_SPC_MODE_8GT__SHIFT); + WREG32_PCIE(smnPCIE_LC_CNTL6, reg_data); + } +} + +static void nbio_v2_3_apply_l1_link_width_reconfig_wa(struct amdgpu_device *adev) +{ + uint32_t reg_data = 0; + + if (adev->asic_type != CHIP_NAVI10) + return; + + reg_data = RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL); + reg_data |= PCIE_LC_LINK_WIDTH_CNTL__LC_L1_RECONFIG_EN_MASK; + WREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL, reg_data); +} + const struct amdgpu_nbio_funcs nbio_v2_3_funcs = { .get_hdp_flush_req_offset = nbio_v2_3_get_hdp_flush_req_offset, .get_hdp_flush_done_offset = nbio_v2_3_get_hdp_flush_done_offset, @@ -484,4 +529,6 @@ const struct amdgpu_nbio_funcs nbio_v2_3_funcs = { .remap_hdp_registers = nbio_v2_3_remap_hdp_registers, .enable_aspm = nbio_v2_3_enable_aspm, .program_aspm = nbio_v2_3_program_aspm, + .apply_lc_spc_mode_wa = nbio_v2_3_apply_lc_spc_mode_wa, + .apply_l1_link_width_reconfig_wa = nbio_v2_3_apply_l1_link_width_reconfig_wa, }; diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 455d0425787c..94a2c0742ee5 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -64,6 +64,13 @@ #include "smuio_v11_0.h" #include "smuio_v11_0_6.h" +#define codec_info_build(type, width, height, level) \ + .codec_type = type,\ + .max_width = width,\ + .max_height = height,\ + .max_pixels_per_frame = height * width,\ + .max_level = level, + static const struct amd_ip_funcs nv_common_ip_funcs; /* Navi */ @@ -309,6 +316,23 @@ static struct amdgpu_video_codecs sriov_sc_video_codecs_decode = .codec_array = sriov_sc_video_codecs_decode_array, }; +/* Beige Goby*/ +static const struct amdgpu_video_codec_info bg_video_codecs_decode_array[] = { + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)}, + {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)}, +}; + +static const struct amdgpu_video_codecs bg_video_codecs_decode = { + .codec_count = ARRAY_SIZE(bg_video_codecs_decode_array), + .codec_array = bg_video_codecs_decode_array, +}; + +static const struct amdgpu_video_codecs bg_video_codecs_encode = { + .codec_count = 0, + .codec_array = NULL, +}; + static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, const struct amdgpu_video_codecs **codecs) { @@ -335,6 +359,12 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode, else *codecs = &sc_video_codecs_decode; return 0; + case CHIP_BEIGE_GOBY: + if (encode) + *codecs = &bg_video_codecs_encode; + else + *codecs = &bg_video_codecs_decode; + return 0; case CHIP_NAVI10: case CHIP_NAVI14: case CHIP_NAVI12: @@ -1275,7 +1305,6 @@ static int nv_common_early_init(void *handle) break; case CHIP_VANGOGH: - adev->apu_flags |= AMD_APU_IS_VANGOGH; adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | AMD_CG_SUPPORT_GFX_CP_LS | @@ -1411,6 +1440,12 @@ static int nv_common_hw_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (adev->nbio.funcs->apply_lc_spc_mode_wa) + adev->nbio.funcs->apply_lc_spc_mode_wa(adev); + + if (adev->nbio.funcs->apply_l1_link_width_reconfig_wa) + adev->nbio.funcs->apply_l1_link_width_reconfig_wa(adev); + /* enable pcie gen2/3 link */ nv_pcie_gen3_enable(adev); /* enable aspm */ diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index f6d3180febc4..dd0dce254901 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -332,11 +332,16 @@ struct psp_gfx_uresp_fwar_db_info uint32_t fwar_db_addr_hi; }; +/* Command-specific response for boot config. */ +struct psp_gfx_uresp_bootcfg { + uint32_t boot_cfg; /* boot config data */ +}; + /* Union of command-specific responses for GPCOM ring. */ -union psp_gfx_uresp -{ - struct psp_gfx_uresp_reserved reserved; - struct psp_gfx_uresp_fwar_db_info fwar_db_info; +union psp_gfx_uresp { + struct psp_gfx_uresp_reserved reserved; + struct psp_gfx_uresp_bootcfg boot_cfg; + struct psp_gfx_uresp_fwar_db_info fwar_db_info; }; /* Structure of GFX Response buffer. diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index fc400d95b83b..bc133db2d538 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -461,6 +461,7 @@ static int psp_v11_0_ring_create(struct psp_context *psp, struct amdgpu_device *adev = psp->adev; if (amdgpu_sriov_vf(adev)) { + ring->ring_wptr = 0; ret = psp_v11_0_ring_stop(psp, ring_type); if (ret) { DRM_ERROR("psp_v11_0_ring_stop_sriov failed!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c index ce7377d2368f..b86dcbabb635 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c @@ -227,6 +227,7 @@ static int psp_v3_1_ring_create(struct psp_context *psp, psp_v3_1_reroute_ih(psp); if (amdgpu_sriov_vf(adev)) { + ring->ring_wptr = 0; ret = psp_v3_1_ring_stop(psp, ring_type); if (ret) { DRM_ERROR("psp_v3_1_ring_stop_sriov failed!\n"); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index ae5464e2535a..8931000dcd41 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -144,7 +144,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] = { SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003e0), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; @@ -288,7 +288,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = { SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_POWER_CNTL, 0x003fff07, 0x40000051), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003e0), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x03fbe1fe) }; @@ -1896,8 +1896,11 @@ static int sdma_v4_0_late_init(void *handle) sdma_v4_0_setup_ulv(adev); - if (adev->sdma.funcs && adev->sdma.funcs->reset_ras_error_count) - adev->sdma.funcs->reset_ras_error_count(adev); + if (!amdgpu_persistent_edc_harvesting_supported(adev)) { + if (adev->sdma.funcs && + adev->sdma.funcs->reset_ras_error_count) + adev->sdma.funcs->reset_ras_error_count(adev); + } if (adev->sdma.funcs && adev->sdma.funcs->ras_late_init) return adev->sdma.funcs->ras_late_init(adev, &ih_info); diff --git a/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c b/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c index e9c474c217ec..b6f1322f908c 100644 --- a/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/smuio_v11_0.c @@ -43,9 +43,12 @@ static void smuio_v11_0_update_rom_clock_gating(struct amdgpu_device *adev, bool if (adev->flags & AMD_IS_APU) return; + if (!(adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG)) + return; + def = data = RREG32_SOC15(SMUIO, 0, mmCGTT_ROM_CLK_CTRL0); - if (enable && (adev->cg_flags & AMD_CG_SUPPORT_ROM_MGCG)) + if (enable) data &= ~(CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE0_MASK | CGTT_ROM_CLK_CTRL0__SOFT_OVERRIDE1_MASK); else diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index de85577c9cfd..b02436401d46 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1360,10 +1360,7 @@ static int soc15_common_early_init(void *handle) break; case CHIP_RAVEN: adev->asic_funcs = &soc15_asic_funcs; - if (adev->pdev->device == 0x15dd) - adev->apu_flags |= AMD_APU_IS_RAVEN; - if (adev->pdev->device == 0x15d8) - adev->apu_flags |= AMD_APU_IS_PICASSO; + if (adev->rev_id >= 0x8) adev->apu_flags |= AMD_APU_IS_RAVEN2; @@ -1455,11 +1452,6 @@ static int soc15_common_early_init(void *handle) break; case CHIP_RENOIR: adev->asic_funcs = &soc15_asic_funcs; - if ((adev->pdev->device == 0x1636) || - (adev->pdev->device == 0x164c)) - adev->apu_flags |= AMD_APU_IS_RENOIR; - else - adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE; if (adev->apu_flags & AMD_APU_IS_RENOIR) adev->external_rev_id = adev->rev_id + 0x91; diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c index 89d20adfa001..af59a35788e3 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v8_7.c @@ -234,7 +234,7 @@ static void umc_v8_7_query_error_address(struct amdgpu_device *adev, err_addr &= ~((0x1ULL << lsb) - 1); /* translate umc channel address to soc pa, 3 parts are included */ - retired_page = ADDR_OF_8KB_BLOCK(err_addr) | + retired_page = ADDR_OF_4KB_BLOCK(err_addr) | ADDR_OF_256B_BLOCK(channel_index) | OFFSET_IN_256B_BLOCK(err_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 4c36fc5c9738..47d4f04cbd69 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -87,21 +87,18 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring); static int vcn_v3_0_early_init(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + int i; if (amdgpu_sriov_vf(adev)) { - adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID; + for (i = 0; i < VCN_INSTANCES_SIENNA_CICHLID; i++) + if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i)) + adev->vcn.num_vcn_inst++; adev->vcn.harvest_config = 0; adev->vcn.num_enc_rings = 1; - if (adev->asic_type == CHIP_BEIGE_GOBY) { - adev->vcn.num_vcn_inst = 1; - adev->vcn.num_enc_rings = 0; - } - } else { if (adev->asic_type == CHIP_SIENNA_CICHLID) { u32 harvest; - int i; adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID; for (i = 0; i < adev->vcn.num_vcn_inst; i++) { @@ -156,7 +153,8 @@ static int vcn_v3_0_sw_init(void *handle) adev->firmware.fw_size += ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE); - if (adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) { + if ((adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) || + (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)) { adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1; adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw; adev->firmware.fw_size += @@ -330,19 +328,17 @@ static int vcn_v3_0_hw_init(void *handle) continue; ring = &adev->vcn.inst[i].ring_dec; - if (ring->sched.ready) { - ring->wptr = 0; - ring->wptr_old = 0; - vcn_v3_0_dec_ring_set_wptr(ring); - } + ring->wptr = 0; + ring->wptr_old = 0; + vcn_v3_0_dec_ring_set_wptr(ring); + ring->sched.ready = true; for (j = 0; j < adev->vcn.num_enc_rings; ++j) { ring = &adev->vcn.inst[i].ring_enc[j]; - if (ring->sched.ready) { - ring->wptr = 0; - ring->wptr_old = 0; - vcn_v3_0_enc_ring_set_wptr(ring); - } + ring->wptr = 0; + ring->wptr_old = 0; + vcn_v3_0_enc_ring_set_wptr(ring); + ring->sched.ready = true; } } } else { @@ -1309,8 +1305,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) uint32_t table_size; uint32_t size, size_dw; - bool is_vcn_ready; - struct mmsch_v3_0_cmd_direct_write direct_wt = { {0} }; struct mmsch_v3_0_cmd_direct_read_modify_write @@ -1502,30 +1496,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev) } } - /* 6, check each VCN's init_status - * if it remains as 0, then this VCN is not assigned to current VF - * do not start ring for this VCN - */ - size = sizeof(struct mmsch_v3_0_init_header); - table_loc = (uint32_t *)table->cpu_addr; - memcpy(&header, (void *)table_loc, size); - - for (i = 0; i < adev->vcn.num_vcn_inst; i++) { - if (adev->vcn.harvest_config & (1 << i)) - continue; - - is_vcn_ready = (header.inst[i].init_status == 1); - if (!is_vcn_ready) - DRM_INFO("VCN(%d) engine is disabled by hypervisor\n", i); - - ring = &adev->vcn.inst[i].ring_dec; - ring->sched.ready = is_vcn_ready; - for (j = 0; j < adev->vcn.num_enc_rings; ++j) { - ring = &adev->vcn.inst[i].ring_enc[j]; - ring->sched.ready = is_vcn_ready; - } - } - return 0; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index cf483c0db687..e48acdd03c1a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1393,7 +1393,6 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, long err = 0; int i; uint32_t *devices_arr = NULL; - bool table_freed = false; dev = kfd_device_by_id(GET_GPU_ID(args->handle)); if (!dev) @@ -1451,8 +1450,7 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, goto get_mem_obj_from_handle_failed; } err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu( - peer->kgd, (struct kgd_mem *)mem, - peer_pdd->drm_priv, &table_freed); + peer->kgd, (struct kgd_mem *)mem, peer_pdd->drm_priv); if (err) { pr_err("Failed to map to gpu %d/%d\n", i, args->n_devices); @@ -1470,17 +1468,16 @@ static int kfd_ioctl_map_memory_to_gpu(struct file *filep, } /* Flush TLBs after waiting for the page table updates to complete */ - if (table_freed) { - for (i = 0; i < args->n_devices; i++) { - peer = kfd_device_by_id(devices_arr[i]); - if (WARN_ON_ONCE(!peer)) - continue; - peer_pdd = kfd_get_process_device_data(peer, p); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); - } + for (i = 0; i < args->n_devices; i++) { + peer = kfd_device_by_id(devices_arr[i]); + if (WARN_ON_ONCE(!peer)) + continue; + peer_pdd = kfd_get_process_device_data(peer, p); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + kfd_flush_tlb(peer_pdd, TLB_FLUSH_LEGACY); } + kfree(devices_arr); return err; @@ -1566,7 +1563,6 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, i, args->n_devices); goto unmap_memory_from_gpu_failed; } - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); args->n_success = i+1; } kfree(devices_arr); @@ -1780,9 +1776,6 @@ static int kfd_ioctl_svm(struct file *filep, struct kfd_process *p, void *data) struct kfd_ioctl_svm_args *args = data; int r = 0; - if (p->svm_disabled) - return -EPERM; - pr_debug("start 0x%llx size 0x%llx op 0x%x nattr 0x%x\n", args->start_addr, args->size, args->op, args->nattr); 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 edb14e4a9f33..16a1713808c2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -486,9 +486,6 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm, if (retval == -ETIME) qpd->reset_wavefronts = true; - - mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); - list_del(&q->list); if (list_empty(&qpd->queues_list)) { if (qpd->reset_wavefronts) { @@ -523,6 +520,8 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, int retval; uint64_t sdma_val = 0; struct kfd_process_device *pdd = qpd_to_pdd(qpd); + struct mqd_manager *mqd_mgr = + dqm->mqd_mgrs[get_mqd_type_from_queue_type(q->properties.type)]; /* Get the SDMA queue stats */ if ((q->properties.type == KFD_QUEUE_TYPE_SDMA) || @@ -540,6 +539,8 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm, pdd->sdma_past_activity_counter += sdma_val; dqm_unlock(dqm); + mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); + return retval; } @@ -1629,7 +1630,7 @@ out: static int process_termination_nocpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { - struct queue *q, *next; + struct queue *q; struct device_process_node *cur, *next_dpn; int retval = 0; bool found = false; @@ -1637,12 +1638,19 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm, dqm_lock(dqm); /* Clear all user mode queues */ - list_for_each_entry_safe(q, next, &qpd->queues_list, list) { + while (!list_empty(&qpd->queues_list)) { + struct mqd_manager *mqd_mgr; int ret; + q = list_first_entry(&qpd->queues_list, struct queue, list); + mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( + q->properties.type)]; ret = destroy_queue_nocpsch_locked(dqm, qpd, q); if (ret) retval = ret; + dqm_unlock(dqm); + mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); + dqm_lock(dqm); } /* Unregister process */ @@ -1674,36 +1682,34 @@ static int get_wave_state(struct device_queue_manager *dqm, u32 *save_area_used_size) { struct mqd_manager *mqd_mgr; - int r; dqm_lock(dqm); - if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE || - q->properties.is_active || !q->device->cwsr_enabled) { - r = -EINVAL; - goto dqm_unlock; - } - mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_CP]; - if (!mqd_mgr->get_wave_state) { - r = -EINVAL; - goto dqm_unlock; + if (q->properties.type != KFD_QUEUE_TYPE_COMPUTE || + q->properties.is_active || !q->device->cwsr_enabled || + !mqd_mgr->get_wave_state) { + dqm_unlock(dqm); + return -EINVAL; } - r = mqd_mgr->get_wave_state(mqd_mgr, q->mqd, ctl_stack, - ctl_stack_used_size, save_area_used_size); - -dqm_unlock: dqm_unlock(dqm); - return r; + + /* + * get_wave_state is outside the dqm lock to prevent circular locking + * and the queue should be protected against destruction by the process + * lock. + */ + return mqd_mgr->get_wave_state(mqd_mgr, q->mqd, ctl_stack, + ctl_stack_used_size, save_area_used_size); } static int process_termination_cpsch(struct device_queue_manager *dqm, struct qcm_process_device *qpd) { int retval; - struct queue *q, *next; + struct queue *q; struct kernel_queue *kq, *kq_next; struct mqd_manager *mqd_mgr; struct device_process_node *cur, *next_dpn; @@ -1760,24 +1766,26 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, qpd->reset_wavefronts = false; } - dqm_unlock(dqm); - - /* Outside the DQM lock because under the DQM lock we can't do - * reclaim or take other locks that others hold while reclaiming. - */ - if (found) - kfd_dec_compute_active(dqm->dev); - /* Lastly, free mqd resources. * Do free_mqd() after dqm_unlock to avoid circular locking. */ - list_for_each_entry_safe(q, next, &qpd->queues_list, list) { + while (!list_empty(&qpd->queues_list)) { + q = list_first_entry(&qpd->queues_list, struct queue, list); mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type( q->properties.type)]; list_del(&q->list); qpd->queue_count--; + dqm_unlock(dqm); mqd_mgr->free_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj); + dqm_lock(dqm); } + dqm_unlock(dqm); + + /* Outside the DQM lock because under the DQM lock we can't do + * reclaim or take other locks that others hold while reclaiming. + */ + if (found) + kfd_dec_compute_active(dqm->dev); return retval; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c index 91c50739b756..a9b329f0f862 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c @@ -405,10 +405,6 @@ int kfd_init_apertures(struct kfd_process *process) case CHIP_POLARIS12: case CHIP_VEGAM: kfd_init_apertures_vi(pdd, id); - /* VI GPUs cannot support SVM with only - * 40 bits of virtual address space. - */ - process->svm_disabled = true; break; case CHIP_VEGA10: case CHIP_VEGA12: diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c index 2660f03e63a7..dab290a4d19d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c @@ -218,7 +218,8 @@ svm_migrate_get_vram_page(struct svm_range *prange, unsigned long pfn) struct page *page; page = pfn_to_page(pfn); - page->zone_device_data = prange; + svm_range_bo_ref(prange->svm_bo); + page->zone_device_data = prange->svm_bo; get_page(page); lock_page(page); } @@ -293,15 +294,13 @@ 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]); - migrate->dst[i] |= MIGRATE_PFN_LOCKED; - - if (migrate->src[i] & MIGRATE_PFN_VALID) { - spage = migrate_pfn_to_page(migrate->src[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]); + migrate->dst[i] |= MIGRATE_PFN_LOCKED; src[i] = dma_map_page(dev, spage, 0, PAGE_SIZE, DMA_TO_DEVICE); r = dma_mapping_error(dev, src[i]); @@ -355,6 +354,20 @@ out_free_vram_pages: } } +#ifdef DEBUG_FORCE_MIXED_DOMAINS + for (i = 0, j = 0; i < npages; i += 4, j++) { + if (j & 1) + continue; + svm_migrate_put_vram_page(adev, dst[i]); + migrate->dst[i] = 0; + svm_migrate_put_vram_page(adev, dst[i + 1]); + migrate->dst[i + 1] = 0; + svm_migrate_put_vram_page(adev, dst[i + 2]); + migrate->dst[i + 2] = 0; + svm_migrate_put_vram_page(adev, dst[i + 3]); + migrate->dst[i + 3] = 0; + } +#endif out: return r; } @@ -365,20 +378,20 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, uint64_t end) { uint64_t npages = (end - start) >> PAGE_SHIFT; + struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; struct migrate_vma migrate; dma_addr_t *scratch; size_t size; void *buf; int r = -ENOMEM; - int retry = 0; memset(&migrate, 0, sizeof(migrate)); migrate.vma = vma; migrate.start = start; migrate.end = end; migrate.flags = MIGRATE_VMA_SELECT_SYSTEM; - migrate.pgmap_owner = adev; + migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev); size = 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t); size *= npages; @@ -390,7 +403,6 @@ svm_migrate_vma_to_vram(struct amdgpu_device *adev, struct svm_range *prange, migrate.dst = migrate.src + npages; scratch = (dma_addr_t *)(migrate.dst + npages); -retry: r = migrate_vma_setup(&migrate); if (r) { pr_debug("failed %d prepare migrate svms 0x%p [0x%lx 0x%lx]\n", @@ -398,17 +410,9 @@ retry: goto out_free; } if (migrate.cpages != npages) { - pr_debug("collect 0x%lx/0x%llx pages, retry\n", migrate.cpages, + pr_debug("Partial migration. 0x%lx/0x%llx pages can be migrated\n", + migrate.cpages, npages); - migrate_vma_finalize(&migrate); - if (retry++ >= 3) { - r = -ENOMEM; - pr_debug("failed %d migrate svms 0x%p [0x%lx 0x%lx]\n", - r, prange->svms, prange->start, prange->last); - goto out_free; - } - - goto retry; } if (migrate.cpages) { @@ -425,6 +429,12 @@ retry: out_free: kvfree(buf); out: + if (!r) { + pdd = svm_range_get_pdd_by_adev(prange, adev); + if (pdd) + WRITE_ONCE(pdd->page_in, pdd->page_in + migrate.cpages); + } + return r; } @@ -464,7 +474,7 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, prange->start, prange->last, best_loc); /* FIXME: workaround for page locking bug with invalid pages */ - svm_range_prefault(prange, mm); + svm_range_prefault(prange, mm, SVM_ADEV_PGMAP_OWNER(adev)); start = prange->start << PAGE_SHIFT; end = (prange->last + 1) << PAGE_SHIFT; @@ -493,15 +503,19 @@ svm_migrate_ram_to_vram(struct svm_range *prange, uint32_t best_loc, static void svm_migrate_page_free(struct page *page) { - /* Keep this function to avoid warning */ + struct svm_range_bo *svm_bo = page->zone_device_data; + + if (svm_bo) { + pr_debug("svm_bo ref left: %d\n", kref_read(&svm_bo->kref)); + svm_range_bo_unref(svm_bo); + } } static int svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct migrate_vma *migrate, struct dma_fence **mfence, - dma_addr_t *scratch) + dma_addr_t *scratch, uint64_t npages) { - uint64_t npages = migrate->cpages; struct device *dev = adev->dev; uint64_t *src; dma_addr_t *dst; @@ -518,15 +532,23 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, src = (uint64_t *)(scratch + npages); dst = scratch; - for (i = 0, j = 0; i < npages; i++, j++, addr += PAGE_SIZE) { + for (i = 0, j = 0; i < npages; i++, addr += PAGE_SIZE) { struct page *spage; spage = migrate_pfn_to_page(migrate->src[i]); - if (!spage) { - pr_debug("failed get spage svms 0x%p [0x%lx 0x%lx]\n", + if (!spage || !is_zone_device_page(spage)) { + pr_debug("invalid page. Could be in CPU already svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start, prange->last); - r = -ENOMEM; - goto out_oom; + if (j) { + r = svm_migrate_copy_memory_gart(adev, dst + i - j, + src + i - j, j, + FROM_VRAM_TO_RAM, + mfence); + if (r) + goto out_oom; + j = 0; + } + continue; } src[i] = svm_migrate_addr(adev, spage); if (i > 0 && src[i] != src[i - 1] + PAGE_SIZE) { @@ -559,6 +581,7 @@ svm_migrate_copy_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate->dst[i] = migrate_pfn(page_to_pfn(dpage)); migrate->dst[i] |= MIGRATE_PFN_LOCKED; + j++; } r = svm_migrate_copy_memory_gart(adev, dst + i - j, src + i - j, j, @@ -581,6 +604,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, struct vm_area_struct *vma, uint64_t start, uint64_t end) { uint64_t npages = (end - start) >> PAGE_SHIFT; + struct kfd_process_device *pdd; struct dma_fence *mfence = NULL; struct migrate_vma migrate; dma_addr_t *scratch; @@ -593,7 +617,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, migrate.start = start; migrate.end = end; migrate.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; - migrate.pgmap_owner = adev; + migrate.pgmap_owner = SVM_ADEV_PGMAP_OWNER(adev); size = 2 * sizeof(*migrate.src) + sizeof(uint64_t) + sizeof(dma_addr_t); size *= npages; @@ -616,7 +640,7 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, if (migrate.cpages) { r = svm_migrate_copy_to_ram(adev, prange, &migrate, &mfence, - scratch); + scratch, npages); migrate_vma_pages(&migrate); svm_migrate_copy_done(adev, mfence); migrate_vma_finalize(&migrate); @@ -630,6 +654,12 @@ svm_migrate_vma_to_ram(struct amdgpu_device *adev, struct svm_range *prange, out_free: kvfree(buf); out: + if (!r) { + pdd = svm_range_get_pdd_by_adev(prange, adev); + if (pdd) + WRITE_ONCE(pdd->page_out, + pdd->page_out + migrate.cpages); + } return r; } @@ -859,7 +889,7 @@ int svm_migrate_init(struct amdgpu_device *adev) pgmap->range.start = res->start; pgmap->range.end = res->end; pgmap->ops = &svm_migrate_pgmap_ops; - pgmap->owner = adev; + pgmap->owner = SVM_ADEV_PGMAP_OWNER(adev); pgmap->flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE; r = devm_memremap_pages(adev->dev, pgmap); if (IS_ERR(r)) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 329684ee5d6e..3426743ed228 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -730,6 +730,15 @@ struct kfd_process_device { * number of CU's a device has along with number of other competing processes */ struct attribute attr_cu_occupancy; + + /* sysfs counters for GPU retry fault and page migration tracking */ + struct kobject *kobj_counters; + struct attribute attr_faults; + struct attribute attr_page_in; + struct attribute attr_page_out; + uint64_t faults; + uint64_t page_in; + uint64_t page_out; }; #define qpd_to_pdd(x) container_of(x, struct kfd_process_device, qpd) @@ -743,6 +752,7 @@ struct svm_range_list { spinlock_t deferred_list_lock; atomic_t evicted_ranges; struct delayed_work restore_work; + DECLARE_BITMAP(bitmap_supported, MAX_GPU_INSTANCE); }; /* Process data */ @@ -826,7 +836,6 @@ struct kfd_process { /* shared virtual memory registered by this process */ struct svm_range_list svms; - bool svm_disabled; bool xnack_enabled; }; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index f1f40bba5c60..8a2c6fc438c0 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -416,6 +416,29 @@ static ssize_t kfd_procfs_stats_show(struct kobject *kobj, return 0; } +static ssize_t kfd_sysfs_counters_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct kfd_process_device *pdd; + + if (!strcmp(attr->name, "faults")) { + pdd = container_of(attr, struct kfd_process_device, + attr_faults); + return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->faults)); + } + if (!strcmp(attr->name, "page_in")) { + pdd = container_of(attr, struct kfd_process_device, + attr_page_in); + return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->page_in)); + } + if (!strcmp(attr->name, "page_out")) { + pdd = container_of(attr, struct kfd_process_device, + attr_page_out); + return sysfs_emit(buf, "%llu\n", READ_ONCE(pdd->page_out)); + } + return 0; +} + static struct attribute attr_queue_size = { .name = "size", .mode = KFD_SYSFS_FILE_MODE @@ -451,13 +474,18 @@ static const struct sysfs_ops procfs_stats_ops = { .show = kfd_procfs_stats_show, }; -static struct attribute *procfs_stats_attrs[] = { - NULL -}; - static struct kobj_type procfs_stats_type = { .sysfs_ops = &procfs_stats_ops, - .default_attrs = procfs_stats_attrs, + .release = kfd_procfs_kobj_release, +}; + +static const struct sysfs_ops sysfs_counters_ops = { + .show = kfd_sysfs_counters_show, +}; + +static struct kobj_type sysfs_counters_type = { + .sysfs_ops = &sysfs_counters_ops, + .release = kfd_procfs_kobj_release, }; int kfd_procfs_add_queue(struct queue *q) @@ -484,34 +512,31 @@ int kfd_procfs_add_queue(struct queue *q) return 0; } -static int kfd_sysfs_create_file(struct kfd_process *p, struct attribute *attr, +static void kfd_sysfs_create_file(struct kobject *kobj, struct attribute *attr, char *name) { - int ret = 0; + int ret; - if (!p || !attr || !name) - return -EINVAL; + if (!kobj || !attr || !name) + return; attr->name = name; attr->mode = KFD_SYSFS_FILE_MODE; sysfs_attr_init(attr); - ret = sysfs_create_file(p->kobj, attr); - - return ret; + ret = sysfs_create_file(kobj, attr); + if (ret) + pr_warn("Create sysfs %s/%s failed %d", kobj->name, name, ret); } -static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) +static void kfd_procfs_add_sysfs_stats(struct kfd_process *p) { - int ret = 0; + int ret; int i; char stats_dir_filename[MAX_SYSFS_FILENAME_LEN]; - if (!p) - return -EINVAL; - - if (!p->kobj) - return -EFAULT; + if (!p || !p->kobj) + return; /* * Create sysfs files for each GPU: @@ -521,63 +546,87 @@ static int kfd_procfs_add_sysfs_stats(struct kfd_process *p) */ for (i = 0; i < p->n_pdds; i++) { struct kfd_process_device *pdd = p->pdds[i]; - struct kobject *kobj_stats; snprintf(stats_dir_filename, MAX_SYSFS_FILENAME_LEN, "stats_%u", pdd->dev->id); - kobj_stats = kfd_alloc_struct(kobj_stats); - if (!kobj_stats) - return -ENOMEM; + pdd->kobj_stats = kfd_alloc_struct(pdd->kobj_stats); + if (!pdd->kobj_stats) + return; - ret = kobject_init_and_add(kobj_stats, - &procfs_stats_type, - p->kobj, - stats_dir_filename); + ret = kobject_init_and_add(pdd->kobj_stats, + &procfs_stats_type, + p->kobj, + stats_dir_filename); if (ret) { pr_warn("Creating KFD proc/stats_%s folder failed", - stats_dir_filename); - kobject_put(kobj_stats); - goto err; + stats_dir_filename); + kobject_put(pdd->kobj_stats); + pdd->kobj_stats = NULL; + return; } - pdd->kobj_stats = kobj_stats; - pdd->attr_evict.name = "evicted_ms"; - pdd->attr_evict.mode = KFD_SYSFS_FILE_MODE; - sysfs_attr_init(&pdd->attr_evict); - ret = sysfs_create_file(kobj_stats, &pdd->attr_evict); - if (ret) - pr_warn("Creating eviction stats for gpuid %d failed", - (int)pdd->dev->id); - + kfd_sysfs_create_file(pdd->kobj_stats, &pdd->attr_evict, + "evicted_ms"); /* Add sysfs file to report compute unit occupancy */ - if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) { - pdd->attr_cu_occupancy.name = "cu_occupancy"; - pdd->attr_cu_occupancy.mode = KFD_SYSFS_FILE_MODE; - sysfs_attr_init(&pdd->attr_cu_occupancy); - ret = sysfs_create_file(kobj_stats, - &pdd->attr_cu_occupancy); - if (ret) - pr_warn("Creating %s failed for gpuid: %d", - pdd->attr_cu_occupancy.name, - (int)pdd->dev->id); - } + if (pdd->dev->kfd2kgd->get_cu_occupancy) + kfd_sysfs_create_file(pdd->kobj_stats, + &pdd->attr_cu_occupancy, + "cu_occupancy"); } -err: - return ret; } - -static int kfd_procfs_add_sysfs_files(struct kfd_process *p) +static void kfd_procfs_add_sysfs_counters(struct kfd_process *p) { int ret = 0; int i; + char counters_dir_filename[MAX_SYSFS_FILENAME_LEN]; - if (!p) - return -EINVAL; + if (!p || !p->kobj) + return; - if (!p->kobj) - return -EFAULT; + /* + * Create sysfs files for each GPU which supports SVM + * - proc/<pid>/counters_<gpuid>/ + * - proc/<pid>/counters_<gpuid>/faults + * - proc/<pid>/counters_<gpuid>/page_in + * - proc/<pid>/counters_<gpuid>/page_out + */ + for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) { + struct kfd_process_device *pdd = p->pdds[i]; + struct kobject *kobj_counters; + + snprintf(counters_dir_filename, MAX_SYSFS_FILENAME_LEN, + "counters_%u", pdd->dev->id); + kobj_counters = kfd_alloc_struct(kobj_counters); + if (!kobj_counters) + return; + + ret = kobject_init_and_add(kobj_counters, &sysfs_counters_type, + p->kobj, counters_dir_filename); + if (ret) { + pr_warn("Creating KFD proc/%s folder failed", + counters_dir_filename); + kobject_put(kobj_counters); + return; + } + + pdd->kobj_counters = kobj_counters; + kfd_sysfs_create_file(kobj_counters, &pdd->attr_faults, + "faults"); + kfd_sysfs_create_file(kobj_counters, &pdd->attr_page_in, + "page_in"); + kfd_sysfs_create_file(kobj_counters, &pdd->attr_page_out, + "page_out"); + } +} + +static void kfd_procfs_add_sysfs_files(struct kfd_process *p) +{ + int i; + + if (!p || !p->kobj) + return; /* * Create sysfs files for each GPU: @@ -589,20 +638,14 @@ static int kfd_procfs_add_sysfs_files(struct kfd_process *p) snprintf(pdd->vram_filename, MAX_SYSFS_FILENAME_LEN, "vram_%u", pdd->dev->id); - ret = kfd_sysfs_create_file(p, &pdd->attr_vram, pdd->vram_filename); - if (ret) - pr_warn("Creating vram usage for gpu id %d failed", - (int)pdd->dev->id); + kfd_sysfs_create_file(p->kobj, &pdd->attr_vram, + pdd->vram_filename); snprintf(pdd->sdma_filename, MAX_SYSFS_FILENAME_LEN, "sdma_%u", pdd->dev->id); - ret = kfd_sysfs_create_file(p, &pdd->attr_sdma, pdd->sdma_filename); - if (ret) - pr_warn("Creating sdma usage for gpu id %d failed", - (int)pdd->dev->id); + kfd_sysfs_create_file(p->kobj, &pdd->attr_sdma, + pdd->sdma_filename); } - - return ret; } void kfd_procfs_del_queue(struct queue *q) @@ -671,8 +714,7 @@ static int kfd_process_alloc_gpuvm(struct kfd_process_device *pdd, if (err) goto err_alloc_mem; - err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, - pdd->drm_priv, NULL); + err = amdgpu_amdkfd_gpuvm_map_memory_to_gpu(kdev->kgd, mem, pdd->drm_priv); if (err) goto err_map_mem; @@ -800,28 +842,17 @@ struct kfd_process *kfd_create_process(struct file *filep) goto out; } - process->attr_pasid.name = "pasid"; - process->attr_pasid.mode = KFD_SYSFS_FILE_MODE; - sysfs_attr_init(&process->attr_pasid); - ret = sysfs_create_file(process->kobj, &process->attr_pasid); - if (ret) - pr_warn("Creating pasid for pid %d failed", - (int)process->lead_thread->pid); + kfd_sysfs_create_file(process->kobj, &process->attr_pasid, + "pasid"); process->kobj_queues = kobject_create_and_add("queues", process->kobj); if (!process->kobj_queues) pr_warn("Creating KFD proc/queues folder failed"); - ret = kfd_procfs_add_sysfs_stats(process); - if (ret) - pr_warn("Creating sysfs stats dir for pid %d failed", - (int)process->lead_thread->pid); - - ret = kfd_procfs_add_sysfs_files(process); - if (ret) - pr_warn("Creating sysfs usage file for pid %d failed", - (int)process->lead_thread->pid); + kfd_procfs_add_sysfs_stats(process); + kfd_procfs_add_sysfs_files(process); + kfd_procfs_add_sysfs_counters(process); } out: if (!IS_ERR(process)) @@ -964,6 +995,50 @@ static void kfd_process_destroy_pdds(struct kfd_process *p) p->n_pdds = 0; } +static void kfd_process_remove_sysfs(struct kfd_process *p) +{ + struct kfd_process_device *pdd; + int i; + + if (!p->kobj) + return; + + sysfs_remove_file(p->kobj, &p->attr_pasid); + kobject_del(p->kobj_queues); + kobject_put(p->kobj_queues); + p->kobj_queues = NULL; + + for (i = 0; i < p->n_pdds; i++) { + pdd = p->pdds[i]; + + sysfs_remove_file(p->kobj, &pdd->attr_vram); + sysfs_remove_file(p->kobj, &pdd->attr_sdma); + + sysfs_remove_file(pdd->kobj_stats, &pdd->attr_evict); + if (pdd->dev->kfd2kgd->get_cu_occupancy) + sysfs_remove_file(pdd->kobj_stats, + &pdd->attr_cu_occupancy); + kobject_del(pdd->kobj_stats); + kobject_put(pdd->kobj_stats); + pdd->kobj_stats = NULL; + } + + for_each_set_bit(i, p->svms.bitmap_supported, p->n_pdds) { + pdd = p->pdds[i]; + + sysfs_remove_file(pdd->kobj_counters, &pdd->attr_faults); + sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_in); + sysfs_remove_file(pdd->kobj_counters, &pdd->attr_page_out); + kobject_del(pdd->kobj_counters); + kobject_put(pdd->kobj_counters); + pdd->kobj_counters = NULL; + } + + kobject_del(p->kobj); + kobject_put(p->kobj); + p->kobj = NULL; +} + /* No process locking is needed in this function, because the process * is not findable any more. We must assume that no other thread is * using it any more, otherwise we couldn't safely free the process @@ -973,33 +1048,7 @@ static void kfd_process_wq_release(struct work_struct *work) { struct kfd_process *p = container_of(work, struct kfd_process, release_work); - int i; - - /* Remove the procfs files */ - if (p->kobj) { - sysfs_remove_file(p->kobj, &p->attr_pasid); - kobject_del(p->kobj_queues); - kobject_put(p->kobj_queues); - p->kobj_queues = NULL; - - for (i = 0; i < p->n_pdds; i++) { - struct kfd_process_device *pdd = p->pdds[i]; - - sysfs_remove_file(p->kobj, &pdd->attr_vram); - sysfs_remove_file(p->kobj, &pdd->attr_sdma); - sysfs_remove_file(p->kobj, &pdd->attr_evict); - if (pdd->dev->kfd2kgd->get_cu_occupancy != NULL) - sysfs_remove_file(p->kobj, &pdd->attr_cu_occupancy); - kobject_del(pdd->kobj_stats); - kobject_put(pdd->kobj_stats); - pdd->kobj_stats = NULL; - } - - kobject_del(p->kobj); - kobject_put(p->kobj); - p->kobj = NULL; - } - + kfd_process_remove_sysfs(p); kfd_iommu_unbind_process(p); kfd_process_free_outstanding_kfd_bos(p); @@ -1260,7 +1309,6 @@ static struct kfd_process *create_process(const struct task_struct *thread) process->mm = thread->mm; process->lead_thread = thread->group_leader; process->n_pdds = 0; - process->svm_disabled = false; INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker); INIT_DELAYED_WORK(&process->restore_work, restore_process_worker); process->last_restore_timestamp = get_jiffies_64(); 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 95a6c36cea4c..243dd1efcdbf 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -153,6 +153,7 @@ void pqm_uninit(struct process_queue_manager *pqm) if (pqn->q && pqn->q->gws) amdgpu_amdkfd_remove_gws_from_process(pqm->process->kgd_process_info, pqn->q->gws); + kfd_procfs_del_queue(pqn->q); uninit_queue(pqn->q); list_del(&pqn->process_queue_list); kfree(pqn); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index da569d417d1d..c7b364e4a287 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -119,28 +119,40 @@ static void svm_range_remove_notifier(struct svm_range *prange) } static int -svm_range_dma_map_dev(struct device *dev, dma_addr_t **dma_addr, - unsigned long *hmm_pfns, uint64_t npages) +svm_range_dma_map_dev(struct amdgpu_device *adev, struct svm_range *prange, + unsigned long *hmm_pfns, uint32_t gpuidx) { enum dma_data_direction dir = DMA_BIDIRECTIONAL; - dma_addr_t *addr = *dma_addr; + dma_addr_t *addr = prange->dma_addr[gpuidx]; + struct device *dev = adev->dev; struct page *page; int i, r; if (!addr) { - addr = kvmalloc_array(npages, sizeof(*addr), + addr = kvmalloc_array(prange->npages, sizeof(*addr), GFP_KERNEL | __GFP_ZERO); if (!addr) return -ENOMEM; - *dma_addr = addr; + prange->dma_addr[gpuidx] = addr; } - for (i = 0; i < npages; i++) { + for (i = 0; i < prange->npages; i++) { if (WARN_ONCE(addr[i] && !dma_mapping_error(dev, addr[i]), "leaking dma mapping\n")) dma_unmap_page(dev, addr[i], PAGE_SIZE, dir); page = hmm_pfn_to_page(hmm_pfns[i]); + if (is_zone_device_page(page)) { + struct amdgpu_device *bo_adev = + amdgpu_ttm_adev(prange->svm_bo->bo->tbo.bdev); + + addr[i] = (hmm_pfns[i] << PAGE_SHIFT) + + bo_adev->vm_manager.vram_base_offset - + bo_adev->kfd.dev->pgmap.range.start; + addr[i] |= SVM_RANGE_VRAM_DOMAIN; + pr_debug("vram address detected: 0x%llx\n", addr[i]); + continue; + } addr[i] = dma_map_page(dev, page, 0, PAGE_SIZE, dir); r = dma_mapping_error(dev, addr[i]); if (r) { @@ -175,8 +187,7 @@ svm_range_dma_map(struct svm_range *prange, unsigned long *bitmap, } adev = (struct amdgpu_device *)pdd->dev->kgd; - r = svm_range_dma_map_dev(adev->dev, &prange->dma_addr[gpuidx], - hmm_pfns, prange->npages); + r = svm_range_dma_map_dev(adev, prange, hmm_pfns, gpuidx); if (r) break; } @@ -281,7 +292,8 @@ svm_range *svm_range_new(struct svm_range_list *svms, uint64_t start, p = container_of(svms, struct kfd_process, svms); if (p->xnack_enabled) - bitmap_fill(prange->bitmap_access, MAX_GPU_INSTANCE); + bitmap_copy(prange->bitmap_access, svms->bitmap_supported, + MAX_GPU_INSTANCE); svm_range_set_default_attributes(&prange->preferred_loc, &prange->prefetch_loc, @@ -300,14 +312,6 @@ static bool svm_bo_ref_unless_zero(struct svm_range_bo *svm_bo) return true; } -static struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo) -{ - if (svm_bo) - kref_get(&svm_bo->kref); - - return svm_bo; -} - static void svm_range_bo_release(struct kref *kref) { struct svm_range_bo *svm_bo; @@ -346,7 +350,7 @@ static void svm_range_bo_release(struct kref *kref) kfree(svm_bo); } -static void svm_range_bo_unref(struct svm_range_bo *svm_bo) +void svm_range_bo_unref(struct svm_range_bo *svm_bo) { if (!svm_bo) return; @@ -563,6 +567,24 @@ svm_range_get_adev_by_id(struct svm_range *prange, uint32_t gpu_id) return (struct amdgpu_device *)pdd->dev->kgd; } +struct kfd_process_device * +svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev) +{ + struct kfd_process *p; + int32_t gpu_idx, gpuid; + int r; + + p = container_of(prange->svms, struct kfd_process, svms); + + r = kfd_process_gpuid_from_kgd(p, adev, &gpuid, &gpu_idx); + if (r) { + pr_debug("failed to get device id by adev %p\n", adev); + return NULL; + } + + return kfd_process_device_from_gpuidx(p, gpu_idx); +} + static int svm_range_bo_validate(void *param, struct amdgpu_bo *bo) { struct ttm_operation_ctx ctx = { false, false }; @@ -577,36 +599,25 @@ svm_range_check_attr(struct kfd_process *p, uint32_t nattr, struct kfd_ioctl_svm_attribute *attrs) { uint32_t i; - int gpuidx; for (i = 0; i < nattr; i++) { + uint32_t val = attrs[i].value; + int gpuidx = MAX_GPU_INSTANCE; + switch (attrs[i].type) { case KFD_IOCTL_SVM_ATTR_PREFERRED_LOC: - if (attrs[i].value != KFD_IOCTL_SVM_LOCATION_SYSMEM && - attrs[i].value != KFD_IOCTL_SVM_LOCATION_UNDEFINED && - kfd_process_gpuidx_from_gpuid(p, - attrs[i].value) < 0) { - pr_debug("no GPU 0x%x found\n", attrs[i].value); - return -EINVAL; - } + if (val != KFD_IOCTL_SVM_LOCATION_SYSMEM && + val != KFD_IOCTL_SVM_LOCATION_UNDEFINED) + gpuidx = kfd_process_gpuidx_from_gpuid(p, val); break; case KFD_IOCTL_SVM_ATTR_PREFETCH_LOC: - if (attrs[i].value != KFD_IOCTL_SVM_LOCATION_SYSMEM && - kfd_process_gpuidx_from_gpuid(p, - attrs[i].value) < 0) { - pr_debug("no GPU 0x%x found\n", attrs[i].value); - return -EINVAL; - } + if (val != KFD_IOCTL_SVM_LOCATION_SYSMEM) + gpuidx = kfd_process_gpuidx_from_gpuid(p, val); break; case KFD_IOCTL_SVM_ATTR_ACCESS: case KFD_IOCTL_SVM_ATTR_ACCESS_IN_PLACE: case KFD_IOCTL_SVM_ATTR_NO_ACCESS: - gpuidx = kfd_process_gpuidx_from_gpuid(p, - attrs[i].value); - if (gpuidx < 0) { - pr_debug("no GPU 0x%x found\n", attrs[i].value); - return -EINVAL; - } + gpuidx = kfd_process_gpuidx_from_gpuid(p, val); break; case KFD_IOCTL_SVM_ATTR_SET_FLAGS: break; @@ -618,6 +629,15 @@ svm_range_check_attr(struct kfd_process *p, pr_debug("unknown attr type 0x%x\n", attrs[i].type); return -EINVAL; } + + if (gpuidx < 0) { + pr_debug("no GPU 0x%x found\n", val); + return -EINVAL; + } else if (gpuidx < MAX_GPU_INSTANCE && + !test_bit(gpuidx, p->svms.bitmap_supported)) { + pr_debug("GPU 0x%x not supported\n", val); + return -EINVAL; + } } return 0; @@ -1003,21 +1023,22 @@ svm_range_split_by_granularity(struct kfd_process *p, struct mm_struct *mm, } static uint64_t -svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange) +svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange, + int domain) { struct amdgpu_device *bo_adev; uint32_t flags = prange->flags; uint32_t mapping_flags = 0; uint64_t pte_flags; - bool snoop = !prange->ttm_res; + bool snoop = (domain != SVM_RANGE_VRAM_DOMAIN); bool coherent = flags & KFD_IOCTL_SVM_FLAG_COHERENT; - if (prange->svm_bo && prange->ttm_res) + if (domain == SVM_RANGE_VRAM_DOMAIN) bo_adev = amdgpu_ttm_adev(prange->svm_bo->bo->tbo.bdev); switch (adev->asic_type) { case CHIP_ARCTURUS: - if (prange->svm_bo && prange->ttm_res) { + if (domain == SVM_RANGE_VRAM_DOMAIN) { if (bo_adev == adev) { mapping_flags |= coherent ? AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW; @@ -1033,7 +1054,7 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange) } break; case CHIP_ALDEBARAN: - if (prange->svm_bo && prange->ttm_res) { + if (domain == SVM_RANGE_VRAM_DOMAIN) { if (bo_adev == adev) { mapping_flags |= coherent ? AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW; @@ -1063,14 +1084,14 @@ svm_range_get_pte_flags(struct amdgpu_device *adev, struct svm_range *prange) mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE; pte_flags = AMDGPU_PTE_VALID; - pte_flags |= prange->ttm_res ? 0 : AMDGPU_PTE_SYSTEM; + pte_flags |= (domain == SVM_RANGE_VRAM_DOMAIN) ? 0 : AMDGPU_PTE_SYSTEM; pte_flags |= snoop ? AMDGPU_PTE_SNOOPED : 0; pte_flags |= amdgpu_gem_va_map_flags(adev, mapping_flags); pr_debug("svms 0x%p [0x%lx 0x%lx] vram %d PTE 0x%llx mapping 0x%x\n", prange->svms, prange->start, prange->last, - prange->ttm_res ? 1:0, pte_flags, mapping_flags); + (domain == SVM_RANGE_VRAM_DOMAIN) ? 1:0, pte_flags, mapping_flags); return pte_flags; } @@ -1141,31 +1162,41 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct amdgpu_bo_va bo_va; bool table_freed = false; uint64_t pte_flags; + unsigned long last_start; + int last_domain; int r = 0; + int64_t i; pr_debug("svms 0x%p [0x%lx 0x%lx]\n", prange->svms, prange->start, prange->last); - if (prange->svm_bo && prange->ttm_res) { + if (prange->svm_bo && prange->ttm_res) bo_va.is_xgmi = amdgpu_xgmi_same_hive(adev, bo_adev); - prange->mapping.bo_va = &bo_va; - } - prange->mapping.start = prange->start; - prange->mapping.last = prange->last; - prange->mapping.offset = prange->ttm_res ? prange->offset : 0; - pte_flags = svm_range_get_pte_flags(adev, prange); + last_start = prange->start; + for (i = 0; i < prange->npages; i++) { + last_domain = dma_addr[i] & SVM_RANGE_VRAM_DOMAIN; + dma_addr[i] &= ~SVM_RANGE_VRAM_DOMAIN; + if ((prange->start + i) < prange->last && + last_domain == (dma_addr[i + 1] & SVM_RANGE_VRAM_DOMAIN)) + continue; - r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL, - prange->mapping.start, - prange->mapping.last, pte_flags, - prange->mapping.offset, - prange->ttm_res, - dma_addr, &vm->last_update, - &table_freed); - if (r) { - pr_debug("failed %d to map to gpu 0x%lx\n", r, prange->start); - goto out; + pr_debug("Mapping range [0x%lx 0x%llx] on domain: %s\n", + last_start, prange->start + i, last_domain ? "GPU" : "CPU"); + pte_flags = svm_range_get_pte_flags(adev, prange, last_domain); + r = amdgpu_vm_bo_update_mapping(adev, bo_adev, vm, false, false, NULL, + last_start, + prange->start + i, pte_flags, + last_start - prange->start, + NULL, + dma_addr, + &vm->last_update, + &table_freed); + if (r) { + pr_debug("failed %d to map to gpu 0x%lx\n", r, prange->start); + goto out; + } + last_start = prange->start + i + 1; } r = amdgpu_vm_update_pdes(adev, vm, false); @@ -1186,7 +1217,6 @@ svm_range_map_to_gpu(struct amdgpu_device *adev, struct amdgpu_vm *vm, p->pasid, TLB_FLUSH_LEGACY); } out: - prange->mapping.bo_va = NULL; return r; } @@ -1274,7 +1304,7 @@ static int svm_range_reserve_bos(struct svm_validate_context *ctx) adev = (struct amdgpu_device *)pdd->dev->kgd; vm = drm_priv_to_vm(pdd->drm_priv); - ctx->tv[gpuidx].bo = &vm->root.base.bo->tbo; + ctx->tv[gpuidx].bo = &vm->root.bo->tbo; ctx->tv[gpuidx].num_shared = 4; list_add(&ctx->tv[gpuidx].head, &ctx->validate_list); } @@ -1320,6 +1350,17 @@ static void svm_range_unreserve_bos(struct svm_validate_context *ctx) ttm_eu_backoff_reservation(&ctx->ticket, &ctx->validate_list); } +static void *kfd_svm_page_owner(struct kfd_process *p, int32_t gpuidx) +{ + struct kfd_process_device *pdd; + struct amdgpu_device *adev; + + pdd = kfd_process_device_from_gpuidx(p, gpuidx); + adev = (struct amdgpu_device *)pdd->dev->kgd; + + return SVM_ADEV_PGMAP_OWNER(adev); +} + /* * Validation+GPU mapping with concurrent invalidation (MMU notifiers) * @@ -1350,6 +1391,9 @@ static int svm_range_validate_and_map(struct mm_struct *mm, { struct svm_validate_context ctx; struct hmm_range *hmm_range; + struct kfd_process *p; + void *owner; + int32_t idx; int r = 0; ctx.process = container_of(prange->svms, struct kfd_process, svms); @@ -1395,33 +1439,38 @@ static int svm_range_validate_and_map(struct mm_struct *mm, svm_range_reserve_bos(&ctx); - if (!prange->actual_loc) { - r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL, - prange->start << PAGE_SHIFT, - prange->npages, &hmm_range, - false, true); - if (r) { - pr_debug("failed %d to get svm range pages\n", r); - goto unreserve_out; - } - - r = svm_range_dma_map(prange, ctx.bitmap, - hmm_range->hmm_pfns); - if (r) { - pr_debug("failed %d to dma map range\n", r); - goto unreserve_out; + p = container_of(prange->svms, struct kfd_process, svms); + owner = kfd_svm_page_owner(p, find_first_bit(ctx.bitmap, + MAX_GPU_INSTANCE)); + for_each_set_bit(idx, ctx.bitmap, MAX_GPU_INSTANCE) { + if (kfd_svm_page_owner(p, idx) != owner) { + owner = NULL; + break; } + } + r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL, + prange->start << PAGE_SHIFT, + prange->npages, &hmm_range, + false, true, owner); + if (r) { + pr_debug("failed %d to get svm range pages\n", r); + goto unreserve_out; + } - prange->validated_once = true; + r = svm_range_dma_map(prange, ctx.bitmap, + hmm_range->hmm_pfns); + if (r) { + pr_debug("failed %d to dma map range\n", r); + goto unreserve_out; } + prange->validated_once = true; + svm_range_lock(prange); - if (!prange->actual_loc) { - if (amdgpu_hmm_range_get_pages_done(hmm_range)) { - pr_debug("hmm update the range, need validate again\n"); - r = -EAGAIN; - goto unlock_out; - } + if (amdgpu_hmm_range_get_pages_done(hmm_range)) { + pr_debug("hmm update the range, need validate again\n"); + r = -EAGAIN; + goto unlock_out; } if (!list_empty(&prange->child_list)) { pr_debug("range split by unmap in parallel, validate again\n"); @@ -1573,6 +1622,7 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm, unsigned long start, unsigned long last) { struct svm_range_list *svms = prange->svms; + struct svm_range *pchild; struct kfd_process *p; int r = 0; @@ -1584,7 +1634,19 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm, if (!p->xnack_enabled) { int evicted_ranges; - atomic_inc(&prange->invalid); + list_for_each_entry(pchild, &prange->child_list, child_list) { + mutex_lock_nested(&pchild->lock, 1); + if (pchild->start <= last && pchild->last >= start) { + pr_debug("increment pchild invalid [0x%lx 0x%lx]\n", + pchild->start, pchild->last); + atomic_inc(&pchild->invalid); + } + mutex_unlock(&pchild->lock); + } + + if (prange->start <= last && prange->last >= start) + atomic_inc(&prange->invalid); + evicted_ranges = atomic_inc_return(&svms->evicted_ranges); if (evicted_ranges != 1) return r; @@ -1601,7 +1663,6 @@ svm_range_evict(struct svm_range *prange, struct mm_struct *mm, schedule_delayed_work(&svms->restore_work, msecs_to_jiffies(AMDGPU_SVM_RANGE_RESTORE_DELAY_MS)); } else { - struct svm_range *pchild; unsigned long s, l; pr_debug("invalidate unmap svms 0x%p [0x%lx 0x%lx] from GPUs\n", @@ -1855,7 +1916,7 @@ static void svm_range_drain_retry_fault(struct svm_range_list *svms) p = container_of(svms, struct kfd_process, svms); - for (i = 0; i < p->n_pdds; i++) { + for_each_set_bit(i, svms->bitmap_supported, p->n_pdds) { pdd = p->pdds[i]; if (!pdd) continue; @@ -2312,6 +2373,33 @@ static bool svm_range_skip_recover(struct svm_range *prange) return false; } +static void +svm_range_count_fault(struct amdgpu_device *adev, struct kfd_process *p, + int32_t gpuidx) +{ + struct kfd_process_device *pdd; + + /* fault is on different page of same range + * or fault is skipped to recover later + * or fault is on invalid virtual address + */ + if (gpuidx == MAX_GPU_INSTANCE) { + uint32_t gpuid; + int r; + + r = kfd_process_gpuid_from_kgd(p, adev, &gpuid, &gpuidx); + if (r < 0) + return; + } + + /* fault is recovered + * or fault cannot recover because GPU no access on the range + */ + pdd = kfd_process_device_from_gpuidx(p, gpuidx); + if (pdd) + WRITE_ONCE(pdd->faults, pdd->faults + 1); +} + int svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, uint64_t addr) @@ -2321,10 +2409,16 @@ svm_range_restore_pages(struct amdgpu_device *adev, unsigned int pasid, struct svm_range *prange; struct kfd_process *p; uint64_t timestamp; - int32_t best_loc, gpuidx; + int32_t best_loc; + int32_t gpuidx = MAX_GPU_INSTANCE; bool write_locked = false; int r = 0; + if (!KFD_IS_SVM_API_SUPPORTED(adev->kfd.dev)) { + pr_debug("device does not support SVM\n"); + return -EFAULT; + } + p = kfd_lookup_process_by_pasid(pasid); if (!p) { pr_debug("kfd process not founded pasid 0x%x\n", pasid); @@ -2436,6 +2530,9 @@ out_unlock_range: out_unlock_svms: mutex_unlock(&svms->lock); mmap_read_unlock(mm); + + svm_range_count_fault(adev, p, gpuidx); + mmput(mm); out: kfd_unref_process(p); @@ -2472,6 +2569,7 @@ void svm_range_list_fini(struct kfd_process *p) int svm_range_list_init(struct kfd_process *p) { struct svm_range_list *svms = &p->svms; + int i; svms->objects = RB_ROOT_CACHED; mutex_init(&svms->lock); @@ -2482,6 +2580,10 @@ int svm_range_list_init(struct kfd_process *p) INIT_LIST_HEAD(&svms->deferred_range_list); spin_lock_init(&svms->deferred_list_lock); + for (i = 0; i < p->n_pdds; i++) + if (KFD_IS_SVM_API_SUPPORTED(p->pdds[i]->dev)) + bitmap_set(svms->bitmap_supported, i, 1); + return 0; } @@ -2653,7 +2755,8 @@ out: /* 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 svm_range_prefault(struct svm_range *prange, struct mm_struct *mm, + void *owner) { struct hmm_range *hmm_range; int r; @@ -2664,7 +2767,7 @@ void svm_range_prefault(struct svm_range *prange, struct mm_struct *mm) r = amdgpu_hmm_range_get_pages(&prange->notifier, mm, NULL, prange->start << PAGE_SHIFT, prange->npages, &hmm_range, - false, true); + false, true, owner); if (!r) { amdgpu_hmm_range_get_pages_done(hmm_range); prange->validated_once = true; @@ -2709,16 +2812,6 @@ svm_range_trigger_migration(struct mm_struct *mm, struct svm_range *prange, best_loc == prange->actual_loc) return 0; - /* - * Prefetch to GPU without host access flag, set actual_loc to gpu, then - * validate on gpu and map to gpus will be handled afterwards. - */ - if (best_loc && !prange->actual_loc && - !(prange->flags & KFD_IOCTL_SVM_FLAG_HOST_ACCESS)) { - prange->actual_loc = best_loc; - return 0; - } - if (!best_loc) { r = svm_migrate_vram_to_ram(prange, mm); *migrated = !r; @@ -2978,14 +3071,15 @@ svm_range_get_attr(struct kfd_process *p, uint64_t start, uint64_t size, svm_range_set_default_attributes(&location, &prefetch_loc, &granularity, &flags); if (p->xnack_enabled) - bitmap_fill(bitmap_access, MAX_GPU_INSTANCE); + bitmap_copy(bitmap_access, svms->bitmap_supported, + MAX_GPU_INSTANCE); else bitmap_zero(bitmap_access, MAX_GPU_INSTANCE); bitmap_zero(bitmap_aip, MAX_GPU_INSTANCE); goto fill_values; } - bitmap_fill(bitmap_access, MAX_GPU_INSTANCE); - bitmap_fill(bitmap_aip, MAX_GPU_INSTANCE); + bitmap_copy(bitmap_access, svms->bitmap_supported, MAX_GPU_INSTANCE); + bitmap_copy(bitmap_aip, svms->bitmap_supported, MAX_GPU_INSTANCE); while (node) { struct interval_tree_node *next; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h index 573f984b81fe..3fc1fd8b4fbc 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.h @@ -35,6 +35,10 @@ #include "amdgpu.h" #include "kfd_priv.h" +#define SVM_RANGE_VRAM_DOMAIN (1UL << 0) +#define SVM_ADEV_PGMAP_OWNER(adev)\ + ((adev)->hive ? (void *)(adev)->hive : (void *)(adev)) + struct svm_range_bo { struct amdgpu_bo *bo; struct kref kref; @@ -110,7 +114,6 @@ struct svm_range { struct list_head update_list; struct list_head remove_list; struct list_head insert_list; - struct amdgpu_bo_va_mapping mapping; uint64_t npages; dma_addr_t *dma_addr[MAX_GPU_INSTANCE]; struct ttm_resource *ttm_res; @@ -147,6 +150,14 @@ static inline void svm_range_unlock(struct svm_range *prange) mutex_unlock(&prange->lock); } +static inline struct svm_range_bo *svm_range_bo_ref(struct svm_range_bo *svm_bo) +{ + if (svm_bo) + kref_get(&svm_bo->kref); + + return svm_bo; +} + int svm_range_list_init(struct kfd_process *p); void svm_range_list_fini(struct kfd_process *p); int svm_ioctl(struct kfd_process *p, enum kfd_ioctl_svm_op op, uint64_t start, @@ -173,8 +184,17 @@ 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 svm_range_prefault(struct svm_range *prange, struct mm_struct *mm, + void *owner); +struct kfd_process_device * +svm_range_get_pdd_by_adev(struct svm_range *prange, struct amdgpu_device *adev); + +/* SVM API and HMM page migration work together, device memory type + * is initialized to not 0 when page migration register device memory. + */ +#define KFD_IS_SVM_API_SUPPORTED(dev) ((dev)->pgmap.type != 0) +void svm_range_bo_unref(struct svm_range_bo *svm_bo); #else struct kfd_process; @@ -201,6 +221,8 @@ static inline int svm_range_schedule_evict_svm_bo( return -EINVAL; } +#define KFD_IS_SVM_API_SUPPORTED(dev) false + #endif /* IS_ENABLED(CONFIG_HSA_AMD_SVM) */ #endif /* KFD_SVM_H_ */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index f668b8cc2b57..b1ce072aa20b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -36,6 +36,7 @@ #include "kfd_topology.h" #include "kfd_device_queue_manager.h" #include "kfd_iommu.h" +#include "kfd_svm.h" #include "amdgpu_amdkfd.h" #include "amdgpu_ras.h" @@ -1221,6 +1222,28 @@ static void kfd_set_iolink_no_atomics(struct kfd_topology_device *dev, } } +static void kfd_set_iolink_non_coherent(struct kfd_topology_device *to_dev, + struct kfd_iolink_properties *outbound_link, + struct kfd_iolink_properties *inbound_link) +{ + /* CPU -> GPU with PCIe */ + if (!to_dev->gpu && + inbound_link->iolink_type == CRAT_IOLINK_TYPE_PCIEXPRESS) + inbound_link->flags |= CRAT_IOLINK_FLAGS_NON_COHERENT; + + if (to_dev->gpu) { + /* GPU <-> GPU with PCIe and + * Vega20 with XGMI + */ + if (inbound_link->iolink_type == CRAT_IOLINK_TYPE_PCIEXPRESS || + (inbound_link->iolink_type == CRAT_IOLINK_TYPE_XGMI && + to_dev->gpu->device_info->asic_family == CHIP_VEGA20)) { + outbound_link->flags |= CRAT_IOLINK_FLAGS_NON_COHERENT; + inbound_link->flags |= CRAT_IOLINK_FLAGS_NON_COHERENT; + } + } +} + static void kfd_fill_iolink_non_crat_info(struct kfd_topology_device *dev) { struct kfd_iolink_properties *link, *inbound_link; @@ -1246,6 +1269,7 @@ static void kfd_fill_iolink_non_crat_info(struct kfd_topology_device *dev) inbound_link->flags = CRAT_IOLINK_FLAGS_ENABLED; kfd_set_iolink_no_atomics(peer_dev, dev, inbound_link); + kfd_set_iolink_non_coherent(peer_dev, link, inbound_link); } } } @@ -1441,10 +1465,7 @@ int kfd_topology_add_device(struct kfd_dev *gpu) dev->node_props.capability |= (adev->ras_enabled != 0) ? HSA_CAP_RASEVENTNOTIFY : 0; - /* SVM API and HMM page migration work together, device memory type - * is initialized to not 0 when page migration register device memory. - */ - if (adev->kfd.dev->pgmap.type != 0) + if (KFD_IS_SVM_API_SUPPORTED(adev->kfd.dev)) dev->node_props.capability |= HSA_CAP_SVMAPI_SUPPORTED; kfd_debug_print_topology(); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index 6bd6380b0ee0..8b48c6692007 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -54,8 +54,8 @@ #define HSA_CAP_ASIC_REVISION_SHIFT 22 #define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 #define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 - -#define HSA_CAP_RESERVED 0xf00f8000 +#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 +#define HSA_CAP_RESERVED 0xe00f8000 struct kfd_node_properties { uint64_t hive_id; @@ -101,8 +101,7 @@ struct kfd_node_properties { #define HSA_MEM_FLAGS_HOT_PLUGGABLE 0x00000001 #define HSA_MEM_FLAGS_NON_VOLATILE 0x00000002 -#define HSA_MEM_FLAGS_COHERENTHOSTACCESS 0x00000004 -#define HSA_MEM_FLAGS_RESERVED 0xfffffff8 +#define HSA_MEM_FLAGS_RESERVED 0xfffffffc struct kfd_mem_properties { struct list_head list; diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index 5b5f36c80efb..7dffc04a557e 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -31,13 +31,6 @@ config DRM_AMD_DC_SI by default. This includes Tahiti, Pitcairn, Cape Verde, Oland. Hainan is not supported by AMD DC and it has no physical DCE6. -config DRM_AMD_DC_DCN3_1 - bool "DCN 3.1 family" - depends on DRM_AMD_DC_DCN - help - Choose this option if you want to have - DCN3.1 family support for display engine - config DEBUG_KERNEL_DC bool "Enable kgdb break in DC" depends on DRM_AMD_DC diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile index 9a3b7bf8ab0b..91fb72c96545 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile @@ -28,7 +28,7 @@ AMDGPUDM = amdgpu_dm.o amdgpu_dm_irq.o amdgpu_dm_mst_types.o amdgpu_dm_color.o ifneq ($(CONFIG_DRM_AMD_DC),) -AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o +AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o amdgpu_dm_psr.o endif ifdef CONFIG_DRM_AMD_DC_HDCP 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 6fda0dfb78f8..d3a2a5ff57e9 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -58,6 +58,7 @@ #if defined(CONFIG_DEBUG_FS) #include "amdgpu_dm_debugfs.h" #endif +#include "amdgpu_dm_psr.h" #include "ivsrcid/ivsrcid_vislands30.h" @@ -109,10 +110,8 @@ MODULE_FIRMWARE(FIRMWARE_VANGOGH_DMUB); MODULE_FIRMWARE(FIRMWARE_DIMGREY_CAVEFISH_DMUB); #define FIRMWARE_BEIGE_GOBY_DMUB "amdgpu/beige_goby_dmcub.bin" MODULE_FIRMWARE(FIRMWARE_BEIGE_GOBY_DMUB); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) #define FIRMWARE_YELLOW_CARP_DMUB "amdgpu/yellow_carp_dmcub.bin" MODULE_FIRMWARE(FIRMWARE_YELLOW_CARP_DMUB); -#endif #define FIRMWARE_RAVEN_DMCU "amdgpu/raven_dmcu.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU); @@ -213,12 +212,6 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, static void handle_cursor_update(struct drm_plane *plane, struct drm_plane_state *old_plane_state); -static void amdgpu_dm_set_psr_caps(struct dc_link *link); -static bool amdgpu_dm_psr_enable(struct dc_stream_state *stream); -static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream); -static bool amdgpu_dm_psr_disable(struct dc_stream_state *stream); -static bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm); - static const struct drm_format_info * amd_get_format_info(const struct drm_mode_fb_cmd2 *cmd); @@ -1150,16 +1143,10 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id)) init_data.flags.disable_dmcu = true; break; -#if defined(CONFIG_DRM_AMD_DC_DCN) case CHIP_VANGOGH: - init_data.flags.gpu_vm_support = true; - break; -#endif -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case CHIP_YELLOW_CARP: init_data.flags.gpu_vm_support = true; break; -#endif default: break; } @@ -1173,6 +1160,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) if (amdgpu_dc_feature_mask & DC_DISABLE_FRACTIONAL_PWM_MASK) init_data.flags.disable_fractional_pwm = true; + if (amdgpu_dc_feature_mask & DC_EDP_NO_POWER_SEQUENCING) + init_data.flags.edp_no_power_sequencing = true; + init_data.flags.power_down_display_on_boot = true; INIT_LIST_HEAD(&adev->dm.da_list); @@ -1416,9 +1406,7 @@ static int load_dmcu_fw(struct amdgpu_device *adev) case CHIP_DIMGREY_CAVEFISH: case CHIP_BEIGE_GOBY: case CHIP_VANGOGH: -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case CHIP_YELLOW_CARP: -#endif return 0; case CHIP_NAVI12: fw_name_dmcu = FIRMWARE_NAVI12_DMCU; @@ -1537,12 +1525,10 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) dmub_asic = DMUB_ASIC_DCN303; fw_name_dmub = FIRMWARE_BEIGE_GOBY_DMUB; break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case CHIP_YELLOW_CARP: dmub_asic = DMUB_ASIC_DCN31; fw_name_dmub = FIRMWARE_YELLOW_CARP_DMUB; break; -#endif default: /* ASIC doesn't support DMUB. */ @@ -2237,7 +2223,7 @@ static int dm_resume(void *handle) = 0xffffffff; } } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) /* * Resource allocation happens for link encoders for newer ASIC in * dc_validate_global_state, so we need to revalidate it. @@ -3791,9 +3777,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case CHIP_YELLOW_CARP: -#endif case CHIP_RENOIR: if (register_outbox_irq_handlers(dm->adev)) { DRM_ERROR("DM: Failed to initialize IRQ\n"); @@ -3898,9 +3882,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) case CHIP_DIMGREY_CAVEFISH: case CHIP_BEIGE_GOBY: case CHIP_VANGOGH: -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case CHIP_YELLOW_CARP: -#endif if (dcn10_register_irq_handlers(dm->adev)) { DRM_ERROR("DM: Failed to initialize IRQ\n"); goto fail; @@ -4072,13 +4054,11 @@ static int dm_early_init(void *handle) adev->mode_info.num_hpd = 6; adev->mode_info.num_dig = 6; break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case CHIP_YELLOW_CARP: adev->mode_info.num_crtc = 4; adev->mode_info.num_hpd = 4; adev->mode_info.num_dig = 4; break; -#endif case CHIP_NAVI14: case CHIP_DIMGREY_CAVEFISH: adev->mode_info.num_crtc = 5; @@ -4316,9 +4296,7 @@ fill_gfx9_tiling_info_from_device(const struct amdgpu_device *adev, adev->asic_type == CHIP_NAVY_FLOUNDER || adev->asic_type == CHIP_DIMGREY_CAVEFISH || adev->asic_type == CHIP_BEIGE_GOBY || -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) adev->asic_type == CHIP_YELLOW_CARP || -#endif adev->asic_type == CHIP_VANGOGH) tiling_info->gfx9.num_pkrs = adev->gfx.config.gb_addr_config_fields.num_pkrs; } @@ -5651,6 +5629,36 @@ static void apply_dsc_policy_for_stream(struct amdgpu_dm_connector *aconnector, } #endif +/** + * DOC: FreeSync Video + * + * When a userspace application wants to play a video, the content follows a + * standard format definition that usually specifies the FPS for that format. + * The below list illustrates some video format and the expected FPS, + * respectively: + * + * - TV/NTSC (23.976 FPS) + * - Cinema (24 FPS) + * - TV/PAL (25 FPS) + * - TV/NTSC (29.97 FPS) + * - TV/NTSC (30 FPS) + * - Cinema HFR (48 FPS) + * - TV/PAL (50 FPS) + * - Commonly used (60 FPS) + * - Multiples of 24 (48,72,96 FPS) + * + * The list of standards video format is not huge and can be added to the + * connector modeset list beforehand. With that, userspace can leverage + * FreeSync to extends the front porch in order to attain the target refresh + * rate. Such a switch will happen seamlessly, without screen blanking or + * reprogramming of the output in any other way. If the userspace requests a + * modesetting change compatible with FreeSync modes that only differ in the + * refresh rate, DC will skip the full update and avoid blink during the + * transition. For example, the video player can change the modesetting from + * 60Hz to 30Hz for playing TV/NTSC content when it goes full screen without + * causing any display blink. This same concept can be applied to a mode + * setting change. + */ static struct drm_display_mode * get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector, bool use_probed_modes) @@ -5875,6 +5883,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector, stream->use_vsc_sdp_for_colorimetry = true; } mod_build_vsc_infopacket(stream, &stream->vsc_infopacket); + aconnector->psr_skip_count = AMDGPU_DM_PSR_ENTRY_DELAY; + } finish: dc_sink_release(sink); @@ -8688,7 +8698,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, else if ((acrtc_state->update_type == UPDATE_TYPE_FAST) && acrtc_state->stream->link->psr_settings.psr_feature_enabled && !acrtc_state->stream->link->psr_settings.psr_allow_active) { - amdgpu_dm_psr_enable(acrtc_state->stream); + struct amdgpu_dm_connector *aconn = (struct amdgpu_dm_connector *) + acrtc_state->stream->dm_stream_context; + + if (aconn->psr_skip_count > 0) + aconn->psr_skip_count--; + else + amdgpu_dm_psr_enable(acrtc_state->stream); } mutex_unlock(&dm->dc_lock); @@ -9175,7 +9191,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || \ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) /* restore the backlight level */ - if (dm->backlight_dev) + if (dm->backlight_dev && (amdgpu_dm_backlight_get_level(dm) != dm->brightness[0])) amdgpu_dm_backlight_set_level(dm, dm->brightness[0]); #endif /* @@ -10105,7 +10121,7 @@ static int validate_overlay(struct drm_atomic_state *state) int i; struct drm_plane *plane; struct drm_plane_state *new_plane_state; - struct drm_plane_state *primary_state, *cursor_state, *overlay_state = NULL; + struct drm_plane_state *primary_state, *overlay_state = NULL; /* Check if primary plane is contained inside overlay */ for_each_new_plane_in_state_reverse(state, plane, new_plane_state, i) { @@ -10135,14 +10151,6 @@ static int validate_overlay(struct drm_atomic_state *state) if (!primary_state->crtc) return 0; - /* check if cursor plane is enabled */ - cursor_state = drm_atomic_get_plane_state(state, overlay_state->crtc->cursor); - if (IS_ERR(cursor_state)) - return PTR_ERR(cursor_state); - - if (drm_atomic_plane_disabling(plane->state, cursor_state)) - return 0; - /* Perform the bounds check to ensure the overlay plane covers the primary */ if (primary_state->crtc_x < overlay_state->crtc_x || primary_state->crtc_y < overlay_state->crtc_y || @@ -10245,6 +10253,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev, dm_old_crtc_state->dsc_force_changed == false) continue; + ret = amdgpu_dm_verify_lut_sizes(new_crtc_state); + if (ret) + goto fail; + if (!new_crtc_state->enable) continue; @@ -10725,136 +10737,6 @@ update: freesync_capable); } -static void amdgpu_dm_set_psr_caps(struct dc_link *link) -{ - uint8_t dpcd_data[EDP_PSR_RECEIVER_CAP_SIZE]; - - if (!(link->connector_signal & SIGNAL_TYPE_EDP)) - return; - if (link->type == dc_connection_none) - return; - if (dm_helpers_dp_read_dpcd(NULL, link, DP_PSR_SUPPORT, - dpcd_data, sizeof(dpcd_data))) { - link->dpcd_caps.psr_caps.psr_version = dpcd_data[0]; - - if (dpcd_data[0] == 0) { - link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; - link->psr_settings.psr_feature_enabled = false; - } else { - link->psr_settings.psr_version = DC_PSR_VERSION_1; - link->psr_settings.psr_feature_enabled = true; - } - - DRM_INFO("PSR support:%d\n", link->psr_settings.psr_feature_enabled); - } -} - -/* - * amdgpu_dm_link_setup_psr() - configure psr link - * @stream: stream state - * - * Return: true if success - */ -static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream) -{ - struct dc_link *link = NULL; - struct psr_config psr_config = {0}; - struct psr_context psr_context = {0}; - bool ret = false; - - if (stream == NULL) - return false; - - link = stream->link; - - psr_config.psr_version = link->dpcd_caps.psr_caps.psr_version; - - if (psr_config.psr_version > 0) { - psr_config.psr_exit_link_training_required = 0x1; - psr_config.psr_frame_capture_indication_req = 0; - psr_config.psr_rfb_setup_time = 0x37; - psr_config.psr_sdp_transmit_line_num_deadline = 0x20; - psr_config.allow_smu_optimizations = 0x0; - - ret = dc_link_setup_psr(link, stream, &psr_config, &psr_context); - - } - DRM_DEBUG_DRIVER("PSR link: %d\n", link->psr_settings.psr_feature_enabled); - - return ret; -} - -/* - * amdgpu_dm_psr_enable() - enable psr f/w - * @stream: stream state - * - * Return: true if success - */ -bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) -{ - struct dc_link *link = stream->link; - unsigned int vsync_rate_hz = 0; - struct dc_static_screen_params params = {0}; - /* Calculate number of static frames before generating interrupt to - * enter PSR. - */ - // Init fail safe of 2 frames static - unsigned int num_frames_static = 2; - - DRM_DEBUG_DRIVER("Enabling psr...\n"); - - vsync_rate_hz = div64_u64(div64_u64(( - stream->timing.pix_clk_100hz * 100), - stream->timing.v_total), - stream->timing.h_total); - - /* Round up - * Calculate number of frames such that at least 30 ms of time has - * passed. - */ - if (vsync_rate_hz != 0) { - unsigned int frame_time_microsec = 1000000 / vsync_rate_hz; - num_frames_static = (30000 / frame_time_microsec) + 1; - } - - params.triggers.cursor_update = true; - params.triggers.overlay_update = true; - params.triggers.surface_update = true; - params.num_frames = num_frames_static; - - dc_stream_set_static_screen_params(link->ctx->dc, - &stream, 1, - ¶ms); - - return dc_link_set_psr_allow_active(link, true, false, false); -} - -/* - * amdgpu_dm_psr_disable() - disable psr f/w - * @stream: stream state - * - * Return: true if success - */ -static bool amdgpu_dm_psr_disable(struct dc_stream_state *stream) -{ - - DRM_DEBUG_DRIVER("Disabling psr...\n"); - - return dc_link_set_psr_allow_active(stream->link, false, true, false); -} - -/* - * amdgpu_dm_psr_disable() - disable psr f/w - * if psr is enabled on any stream - * - * Return: true if success - */ -static bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm) -{ - DRM_DEBUG_DRIVER("Disabling psr if psr is enabled on any stream\n"); - return dc_set_psr_allow_active(dm->dc, false); -} - void amdgpu_dm_trigger_timing_sync(struct drm_device *dev) { struct amdgpu_device *adev = drm_to_adev(dev); 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 22730e554209..9522d4ca299e 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -509,6 +509,8 @@ struct amdgpu_dm_connector { struct dsc_preferred_settings dsc_settings; /* Cached display modes */ struct drm_display_mode freesync_vid_base; + + int psr_skip_count; }; #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base) @@ -617,6 +619,7 @@ void amdgpu_dm_trigger_timing_sync(struct drm_device *dev); #define MAX_COLOR_LEGACY_LUT_ENTRIES 256 void amdgpu_dm_init_color_mod(void); +int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state); int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc); int amdgpu_dm_update_plane_color_mgmt(struct dm_crtc_state *crtc, struct dc_plane_state *dc_plane_state); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c index 157fe4efbb59..a022e5bb30a5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c @@ -285,6 +285,37 @@ static int __set_input_tf(struct dc_transfer_func *func, } /** + * Verifies that the Degamma and Gamma LUTs attached to the |crtc_state| are of + * the expected size. + * Returns 0 on success. + */ +int amdgpu_dm_verify_lut_sizes(const struct drm_crtc_state *crtc_state) +{ + const struct drm_color_lut *lut = NULL; + uint32_t size = 0; + + lut = __extract_blob_lut(crtc_state->degamma_lut, &size); + if (lut && size != MAX_COLOR_LUT_ENTRIES) { + DRM_DEBUG_DRIVER( + "Invalid Degamma LUT size. Should be %u but got %u.\n", + MAX_COLOR_LUT_ENTRIES, size); + return -EINVAL; + } + + lut = __extract_blob_lut(crtc_state->gamma_lut, &size); + if (lut && size != MAX_COLOR_LUT_ENTRIES && + size != MAX_COLOR_LEGACY_LUT_ENTRIES) { + DRM_DEBUG_DRIVER( + "Invalid Gamma LUT size. Should be %u (or %u for legacy) but got %u.\n", + MAX_COLOR_LUT_ENTRIES, MAX_COLOR_LEGACY_LUT_ENTRIES, + size); + return -EINVAL; + } + + return 0; +} + +/** * amdgpu_dm_update_crtc_color_mgmt: Maps DRM color management to DC stream. * @crtc: amdgpu_dm crtc state * @@ -317,14 +348,12 @@ int amdgpu_dm_update_crtc_color_mgmt(struct dm_crtc_state *crtc) bool is_legacy; int r; - degamma_lut = __extract_blob_lut(crtc->base.degamma_lut, °amma_size); - if (degamma_lut && degamma_size != MAX_COLOR_LUT_ENTRIES) - return -EINVAL; + r = amdgpu_dm_verify_lut_sizes(&crtc->base); + if (r) + return r; + degamma_lut = __extract_blob_lut(crtc->base.degamma_lut, °amma_size); regamma_lut = __extract_blob_lut(crtc->base.gamma_lut, ®amma_size); - if (regamma_lut && regamma_size != MAX_COLOR_LUT_ENTRIES && - regamma_size != MAX_COLOR_LEGACY_LUT_ENTRIES) - return -EINVAL; has_degamma = degamma_lut && !__is_lut_linear(degamma_lut, degamma_size); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 64c6ed50990d..e63c6885c757 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -467,13 +467,11 @@ static void update_config(void *handle, struct cp_psp_stream_config *config) display->dig_fe = config->dig_fe; link->dig_be = config->dig_be; link->ddc_line = aconnector->dc_link->ddc_hw_inst + 1; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) display->stream_enc_idx = config->stream_enc_idx; link->link_enc_idx = config->link_enc_idx; link->phy_idx = config->phy_idx; link->hdcp_supported_informational = dc_link_is_hdcp14(aconnector->dc_link, aconnector->dc_sink->sink_signal) ? 1 : 0; -#endif link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw; link->dp.assr_enabled = config->assr_enabled; link->dp.mst_enabled = config->mst_enabled; @@ -657,12 +655,10 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct INIT_DELAYED_WORK(&hdcp_work[i].property_validate_dwork, event_property_validate); hdcp_work[i].hdcp.config.psp.handle = &adev->psp; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) if (dc->ctx->dce_version == DCN_VERSION_3_1) { hdcp_work[i].hdcp.config.psp.caps.dtm_v3_supported = 1; hdcp_work[i].hdcp.config.psp.caps.opm_state_query_supported = false; } -#endif hdcp_work[i].hdcp.config.ddc.handle = dc_get_link_at_index(dc, i); hdcp_work[i].hdcp.config.ddc.funcs.write_i2c = lp_write_i2c; hdcp_work[i].hdcp.config.ddc.funcs.read_i2c = lp_read_i2c; 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 new file mode 100644 index 000000000000..70a554f1e725 --- /dev/null +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c @@ -0,0 +1,164 @@ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: AMD + * + */ + +#include "amdgpu_dm_psr.h" +#include "dc.h" +#include "dm_helpers.h" + +/* + * amdgpu_dm_set_psr_caps() - set link psr capabilities + * @link: link + * + */ +void amdgpu_dm_set_psr_caps(struct dc_link *link) +{ + uint8_t dpcd_data[EDP_PSR_RECEIVER_CAP_SIZE]; + + if (!(link->connector_signal & SIGNAL_TYPE_EDP)) + return; + if (link->type == dc_connection_none) + return; + if (dm_helpers_dp_read_dpcd(NULL, link, DP_PSR_SUPPORT, + dpcd_data, sizeof(dpcd_data))) { + link->dpcd_caps.psr_caps.psr_version = dpcd_data[0]; + + if (dpcd_data[0] == 0) { + link->psr_settings.psr_version = DC_PSR_VERSION_UNSUPPORTED; + link->psr_settings.psr_feature_enabled = false; + } else { + link->psr_settings.psr_version = DC_PSR_VERSION_1; + link->psr_settings.psr_feature_enabled = true; + } + + DRM_INFO("PSR support:%d\n", link->psr_settings.psr_feature_enabled); + } +} + +/* + * amdgpu_dm_link_setup_psr() - configure psr link + * @stream: stream state + * + * Return: true if success + */ +bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream) +{ + struct dc_link *link = NULL; + struct psr_config psr_config = {0}; + struct psr_context psr_context = {0}; + bool ret = false; + + if (stream == NULL) + return false; + + link = stream->link; + + psr_config.psr_version = link->dpcd_caps.psr_caps.psr_version; + + if (psr_config.psr_version > 0) { + psr_config.psr_exit_link_training_required = 0x1; + psr_config.psr_frame_capture_indication_req = 0; + psr_config.psr_rfb_setup_time = 0x37; + psr_config.psr_sdp_transmit_line_num_deadline = 0x20; + psr_config.allow_smu_optimizations = 0x0; + + ret = dc_link_setup_psr(link, stream, &psr_config, &psr_context); + + } + DRM_DEBUG_DRIVER("PSR link: %d\n", link->psr_settings.psr_feature_enabled); + + return ret; +} + +/* + * amdgpu_dm_psr_enable() - enable psr f/w + * @stream: stream state + * + * Return: true if success + */ +bool amdgpu_dm_psr_enable(struct dc_stream_state *stream) +{ + struct dc_link *link = stream->link; + unsigned int vsync_rate_hz = 0; + struct dc_static_screen_params params = {0}; + /* Calculate number of static frames before generating interrupt to + * enter PSR. + */ + // Init fail safe of 2 frames static + unsigned int num_frames_static = 2; + + DRM_DEBUG_DRIVER("Enabling psr...\n"); + + vsync_rate_hz = div64_u64(div64_u64(( + stream->timing.pix_clk_100hz * 100), + stream->timing.v_total), + stream->timing.h_total); + + /* Round up + * Calculate number of frames such that at least 30 ms of time has + * passed. + */ + if (vsync_rate_hz != 0) { + unsigned int frame_time_microsec = 1000000 / vsync_rate_hz; + num_frames_static = (30000 / frame_time_microsec) + 1; + } + + params.triggers.cursor_update = true; + params.triggers.overlay_update = true; + params.triggers.surface_update = true; + params.num_frames = num_frames_static; + + dc_stream_set_static_screen_params(link->ctx->dc, + &stream, 1, + ¶ms); + + return dc_link_set_psr_allow_active(link, true, false, false); +} + +/* + * amdgpu_dm_psr_disable() - disable psr f/w + * @stream: stream state + * + * Return: true if success + */ +bool amdgpu_dm_psr_disable(struct dc_stream_state *stream) +{ + + DRM_DEBUG_DRIVER("Disabling psr...\n"); + + return dc_link_set_psr_allow_active(stream->link, false, true, false); +} + +/* + * amdgpu_dm_psr_disable() - disable psr f/w + * if psr is enabled on any stream + * + * Return: true if success + */ +bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm) +{ + DRM_DEBUG_DRIVER("Disabling psr if psr is enabled on any stream\n"); + return dc_set_psr_allow_active(dm->dc, false); +} + diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h index b6c976a4d578..6806b3c9c84b 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0_1.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.h @@ -1,5 +1,5 @@ /* - * Copyright 2020 Advanced Micro Devices, Inc. + * Copyright 2021 Advanced Micro Devices, Inc. * * Permission is hereby granted, free of charge, to any person obtaining a * copy of this software and associated documentation files (the "Software"), @@ -19,39 +19,22 @@ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR * OTHER DEALINGS IN THE SOFTWARE. * + * Authors: AMD + * */ -#ifndef __SMU_V13_0_1_H__ -#define __SMU_V13_0_1_H__ - -#include "amdgpu_smu.h" - -#define SMU13_0_1_DRIVER_IF_VERSION_INV 0xFFFFFFFF -#define SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP 0x3 - -/* MP Apertures */ -#define MP0_Public 0x03800000 -#define MP0_SRAM 0x03900000 -#define MP1_Public 0x03b00000 -#define MP1_SRAM 0x03c00004 - -/* address block */ -#define smnMP1_FIRMWARE_FLAGS 0x3010024 - - -#if defined(SWSMU_CODE_LAYER_L2) || defined(SWSMU_CODE_LAYER_L3) - -int smu_v13_0_1_check_fw_status(struct smu_context *smu); - -int smu_v13_0_1_check_fw_version(struct smu_context *smu); -int smu_v13_0_1_fini_smc_tables(struct smu_context *smu); +#ifndef AMDGPU_DM_AMDGPU_DM_PSR_H_ +#define AMDGPU_DM_AMDGPU_DM_PSR_H_ -int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu); +#include "amdgpu.h" -int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu); +/* the number of pageflips before enabling psr */ +#define AMDGPU_DM_PSR_ENTRY_DELAY 5 -int smu_v13_0_1_set_driver_table_location(struct smu_context *smu); +void amdgpu_dm_set_psr_caps(struct dc_link *link); +bool amdgpu_dm_psr_enable(struct dc_stream_state *stream); +bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream); +bool amdgpu_dm_psr_disable(struct dc_stream_state *stream); +bool amdgpu_dm_psr_disable_all(struct amdgpu_display_manager *dm); -int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable); -#endif -#endif +#endif /* AMDGPU_DM_AMDGPU_DM_PSR_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile index 95aca9b0ef7f..943fcb164876 100644 --- a/drivers/gpu/drm/amd/display/dc/Makefile +++ b/drivers/gpu/drm/amd/display/dc/Makefile @@ -34,10 +34,8 @@ DC_LIBS += dcn30 DC_LIBS += dcn301 DC_LIBS += dcn302 DC_LIBS += dcn303 -ifdef CONFIG_DRM_AMD_DC_DCN3_1 DC_LIBS += dcn31 endif -endif DC_LIBS += dce120 @@ -60,7 +58,7 @@ include $(AMD_DC) DISPLAY_CORE = dc.o dc_stat.o dc_link.o dc_resource.o dc_hw_sequencer.o dc_sink.o \ dc_surface.o dc_link_hwss.o dc_link_dp.o dc_link_ddc.o dc_debug.o dc_stream.o \ -dc_link_enc_cfg.o +dc_link_enc_cfg.o dc_link_dpcd.o ifdef CONFIG_DRM_AMD_DC_DCN DISPLAY_CORE += dc_vm_helper.o 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 7d1c1b76d8d0..6dbde74c1e06 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c @@ -576,13 +576,11 @@ static struct device_id device_type_from_device_id(uint16_t device_id) result_device_id.device_type = DEVICE_TYPE_LCD; result_device_id.enum_id = 1; break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case ATOM_DISPLAY_LCD2_SUPPORT: result_device_id.device_type = DEVICE_TYPE_LCD; result_device_id.enum_id = 2; break; -#endif case ATOM_DISPLAY_DFP1_SUPPORT: result_device_id.device_type = DEVICE_TYPE_DFP; @@ -2140,7 +2138,7 @@ static enum bp_result get_integrated_info_v2_1( info_v2_1->edp1_info.edp_pwr_down_bloff_to_vary_bloff; info->edp1_info.edp_panel_bpc = info_v2_1->edp1_info.edp_panel_bpc; - info->edp1_info.edp_bootup_bl_level = + info->edp1_info.edp_bootup_bl_level = info_v2_1->edp1_info.edp_bootup_bl_level; info->edp2_info.edp_backlight_pwm_hz = le16_to_cpu(info_v2_1->edp2_info.edp_backlight_pwm_hz); @@ -2162,7 +2160,6 @@ static enum bp_result get_integrated_info_v2_1( return BP_RESULT_OK; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) static enum bp_result get_integrated_info_v2_2( struct bios_parser *bp, struct integrated_info *info) @@ -2262,7 +2259,7 @@ static enum bp_result get_integrated_info_v2_2( return BP_RESULT_OK; } -#endif + /* * construct_integrated_info * @@ -2310,11 +2307,9 @@ static enum bp_result construct_integrated_info( case 1: result = get_integrated_info_v2_1(bp, info); break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case 2: result = get_integrated_info_v2_2(bp, info); break; -#endif default: return result; } diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c index 3ac4dc01f8e1..cb3fd44cb1ed 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c @@ -72,13 +72,9 @@ bool dal_bios_parser_init_cmd_tbl_helper2( case DCN_VERSION_2_1: case DCN_VERSION_3_0: case DCN_VERSION_3_01: -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) - case DCN_VERSION_3_1: - *h = dal_cmd_tbl_helper_dce112_get_table2(); - return true; -#endif case DCN_VERSION_3_02: case DCN_VERSION_3_03: + case DCN_VERSION_3_1: *h = dal_cmd_tbl_helper_dce112_get_table2(); return true; #endif diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile index 713251547d1c..7fa0b007a7ea 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/Makefile @@ -135,9 +135,7 @@ endif AMD_DAL_CLK_MGR_DCN301 = $(addprefix $(AMDDALPATH)/dc/clk_mgr/dcn301/,$(CLK_MGR_DCN301)) AMD_DISPLAY_FILES += $(AMD_DAL_CLK_MGR_DCN301) -endif -ifdef CONFIG_DRM_AMD_DC_DCN3_1 ############################################################################### # DCN31 ############################################################################### diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index f652f491c419..bb31541f8072 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -41,9 +41,7 @@ #include "dcn21/rn_clk_mgr.h" #include "dcn30/dcn30_clk_mgr.h" #include "dcn301/vg_clk_mgr.h" -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) #include "dcn31/dcn31_clk_mgr.h" -#endif int clk_mgr_helper_get_active_display_cnt( @@ -273,9 +271,6 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p return &clk_mgr->base.base; } break; -#endif - -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case FAMILY_YELLOW_CARP: { struct clk_mgr_dcn31 *clk_mgr = kzalloc(sizeof(*clk_mgr), GFP_KERNEL); @@ -325,12 +320,10 @@ void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr_base) vg_clk_mgr_destroy(clk_mgr); break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case FAMILY_YELLOW_CARP: if (ASICREV_IS_YELLOW_CARP(clk_mgr_base->ctx->asic_id.hw_internal_rev)) dcn31_clk_mgr_destroy(clk_mgr); break; -#endif default: break; 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 59d17195bc22..6e0c5c664fdc 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 @@ -123,7 +123,7 @@ void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr, } } -void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr) +void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct dc_state *context) { int dpp_divider = DENTIST_DIVIDER_RANGE_SCALE_FACTOR * clk_mgr->base.dentist_vco_freq_khz / clk_mgr->base.clks.dppclk_khz; @@ -132,6 +132,68 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr) uint32_t dppclk_wdivider = dentist_get_did_from_divider(dpp_divider); uint32_t dispclk_wdivider = dentist_get_did_from_divider(disp_divider); + uint32_t current_dispclk_wdivider; + uint32_t i; + + REG_GET(DENTIST_DISPCLK_CNTL, + DENTIST_DISPCLK_WDIVIDER, ¤t_dispclk_wdivider); + + /* When changing divider to or from 127, some extra programming is required to prevent corruption */ + if (current_dispclk_wdivider == 127 && dispclk_wdivider != 127) { + 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]; + uint32_t fifo_level; + struct dccg *dccg = clk_mgr->base.ctx->dc->res_pool->dccg; + struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + int32_t N; + int32_t j; + + if (!pipe_ctx->stream) + continue; + /* Virtual encoders don't have this function */ + if (!stream_enc->funcs->get_fifo_cal_average_level) + continue; + fifo_level = stream_enc->funcs->get_fifo_cal_average_level( + stream_enc); + N = fifo_level / 4; + dccg->funcs->set_fifo_errdet_ovr_en( + dccg, + true); + for (j = 0; j < N - 4; j++) + dccg->funcs->otg_drop_pixel( + dccg, + pipe_ctx->stream_res.tg->inst); + dccg->funcs->set_fifo_errdet_ovr_en( + dccg, + false); + } + } 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); + 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; + struct stream_encoder *stream_enc = pipe_ctx->stream_res.stream_enc; + uint32_t fifo_level; + int32_t N; + int32_t j; + + if (!pipe_ctx->stream) + continue; + /* Virtual encoders don't have this function */ + if (!stream_enc->funcs->get_fifo_cal_average_level) + continue; + fifo_level = stream_enc->funcs->get_fifo_cal_average_level( + stream_enc); + N = fifo_level / 4; + dccg->funcs->set_fifo_errdet_ovr_en(dccg, true); + for (j = 0; j < 12 - N; j++) + dccg->funcs->otg_add_pixel(dccg, + pipe_ctx->stream_res.tg->inst); + dccg->funcs->set_fifo_errdet_ovr_en(dccg, false); + } + } REG_UPDATE(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider); @@ -251,11 +313,11 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base, if (dpp_clock_lowered) { // if clock is being lowered, increase DTO before lowering refclk dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); - dcn20_update_clocks_update_dentist(clk_mgr); + dcn20_update_clocks_update_dentist(clk_mgr, context); } else { // if clock is being raised, increase refclk before lowering DTO if (update_dppclk || update_dispclk) - dcn20_update_clocks_update_dentist(clk_mgr); + dcn20_update_clocks_update_dentist(clk_mgr, context); // always update dtos unless clock is lowered and not safe to lower dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); } @@ -324,10 +386,8 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr, // Both fclk and ref_dppclk run on the same scemi clock. clk_mgr_int->dccg->ref_dppclk = clk_mgr->clks.fclk_khz; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) /* TODO: set dtbclk in correct place */ clk_mgr->clks.dtbclk_en = false; -#endif dm_set_dcn_clocks(clk_mgr->ctx, &clk_mgr->clks); } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h index 0b9c045b0c8e..d254d0b6fba1 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h @@ -50,7 +50,8 @@ void dcn2_get_clock(struct clk_mgr *clk_mgr, enum dc_clock_type clock_type, struct dc_clock_config *clock_cfg); -void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr); +void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, + struct dc_state *context); void dcn2_read_clocks_from_hw_dentist(struct clk_mgr *clk_mgr_base); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c index 652fa89fae5f..513676a6f52b 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c @@ -334,11 +334,11 @@ static void dcn3_update_clocks(struct clk_mgr *clk_mgr_base, if (dpp_clock_lowered) { /* if clock is being lowered, increase DTO before lowering refclk */ dcn20_update_clocks_update_dpp_dto(clk_mgr, context, safe_to_lower); - dcn20_update_clocks_update_dentist(clk_mgr); + dcn20_update_clocks_update_dentist(clk_mgr, context); } else { /* if clock is being raised, increase refclk before lowering DTO */ if (update_dppclk || update_dispclk) - dcn20_update_clocks_update_dentist(clk_mgr); + dcn20_update_clocks_update_dentist(clk_mgr, context); /* There is a check inside dcn20_update_clocks_update_dpp_dto which ensures * that we do not lower dto when it is not safe to lower. We do not need to * compare the current and new dppclk before calling this function.*/ diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c index 66db5e988bc1..dad4a4c18bcf 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_smu.c @@ -31,8 +31,8 @@ #include "dcn31_smu.h" #include "yellow_carp_offset.h" -#include "mp/mp_13_0_1_offset.h" -#include "mp/mp_13_0_1_sh_mask.h" +#include "mp/mp_13_0_2_offset.h" +#include "mp/mp_13_0_2_sh_mask.h" #define REG(reg_name) \ (MP0_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index be1dbd3136ec..605e297b7a59 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1524,7 +1524,7 @@ static uint8_t get_stream_mask(struct dc *dc, struct dc_state *context) return stream_mask; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) void dc_z10_restore(struct dc *dc) { if (dc->hwss.z10_restore) @@ -1544,9 +1544,7 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c struct dc_stream_state *dc_streams[MAX_STREAMS] = {0}; #if defined(CONFIG_DRM_AMD_DC_DCN) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) dc_z10_restore(dc); -#endif dc_allow_idle_optimizations(dc, false); #endif @@ -2626,7 +2624,7 @@ static void commit_planes_for_stream(struct dc *dc, int i, j; struct pipe_ctx *top_pipe_to_program = NULL; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) dc_z10_restore(dc); #endif @@ -3085,7 +3083,7 @@ void dc_set_power_state( case DC_ACPI_CM_POWER_STATE_D0: dc_resource_state_construct(dc, dc->current_state); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) dc_z10_restore(dc); #endif if (dc->ctx->dmub_srv) 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 15f987a63025..9039fb134db5 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 @@ -409,13 +409,13 @@ void get_surface_tile_visual_confirm_color( struct tg_color *color) { uint32_t color_value = MAX_TG_COLOR_VALUE; - /* Determine the overscan color based on the top-most (desktop) plane's context */ - struct pipe_ctx *top_pipe_ctx = pipe_ctx; + /* Determine the overscan color based on the bottom-most plane's context */ + struct pipe_ctx *bottom_pipe_ctx = pipe_ctx; - while (top_pipe_ctx->top_pipe != NULL) - top_pipe_ctx = top_pipe_ctx->top_pipe; + while (bottom_pipe_ctx->bottom_pipe != NULL) + bottom_pipe_ctx = bottom_pipe_ctx->bottom_pipe; - switch (top_pipe_ctx->plane_state->tiling_info.gfx9.swizzle) { + switch (bottom_pipe_ctx->plane_state->tiling_info.gfx9.swizzle) { case DC_SW_LINEAR: /* LINEAR Surface - set border color to red */ color->color_r_cr = color_value; 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 0f91280883a6..6132b645bfd1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -49,6 +49,7 @@ #include "dmub/dmub_srv.h" #include "inc/hw/panel_cntl.h" #include "inc/link_enc_cfg.h" +#include "inc/link_dpcd.h" #define DC_LOGGER_INIT(logger) @@ -59,20 +60,6 @@ #define RETIMER_REDRIVER_INFO(...) \ DC_LOG_RETIMER_REDRIVER( \ __VA_ARGS__) -/******************************************************************************* - * Private structures - ******************************************************************************/ - -enum { - PEAK_FACTOR_X1000 = 1006, - /* - * Some receivers fail to train on first try and are good - * on subsequent tries. 2 retries should be plenty. If we - * don't have a successful training then we don't expect to - * ever get one. - */ - LINK_TRAINING_MAX_VERIFY_RETRY = 2 -}; /******************************************************************************* * Private functions @@ -718,11 +705,9 @@ static void read_current_link_settings_on_detect(struct dc_link *link) static bool detect_dp(struct dc_link *link, struct display_sink_capability *sink_caps, - bool *converter_disable_audio, - struct audio_support *audio_support, enum dc_detect_reason reason) { - bool boot = false; + struct audio_support *audio_support = &link->dc->res_pool->audio_support; sink_caps->signal = link_detect_sink(link, reason); sink_caps->transaction_type = @@ -745,60 +730,12 @@ static bool detect_dp(struct dc_link *link, * of this function). */ query_hdcp_capability(SIGNAL_TYPE_DISPLAY_PORT_MST, link); #endif - /* - * This call will initiate MST topology discovery. Which - * will detect MST ports and add new DRM connector DRM - * framework. Then read EDID via remote i2c over aux. In - * the end, will notify DRM detect result and save EDID - * into DRM framework. - * - * .detect is called by .fill_modes. - * .fill_modes is called by user mode ioctl - * DRM_IOCTL_MODE_GETCONNECTOR. - * - * .get_modes is called by .fill_modes. - * - * call .get_modes, AMDGPU DM implementation will create - * new dc_sink and add to dc_link. For long HPD plug - * in/out, MST has its own handle. - * - * Therefore, just after dc_create, link->sink is not - * created for MST until user mode app calls - * DRM_IOCTL_MODE_GETCONNECTOR. - * - * Need check ->sink usages in case ->sink = NULL - * TODO: s3 resume check - */ - if (reason == DETECT_REASON_BOOT) - boot = true; - - dm_helpers_dp_update_branch_info(link->ctx, link); - - if (!dm_helpers_dp_mst_start_top_mgr(link->ctx, - link, boot)) { - /* MST not supported */ - link->type = dc_connection_single; - sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT; - } } if (link->type != dc_connection_mst_branch && - is_dp_branch_device(link)) { + is_dp_branch_device(link)) /* DP SST branch */ link->type = dc_connection_sst_branch; - if (!link->dpcd_caps.sink_count.bits.SINK_COUNT) { - /* - * SST branch unplug processing for short irq - */ - link_disconnect_sink(link); - return true; - } - - if (is_dp_active_dongle(link) && - (link->dpcd_caps.dongle_type != - DISPLAY_DONGLE_DP_HDMI_CONVERTER)) - *converter_disable_audio = true; - } } else { /* DP passive dongles */ sink_caps->signal = dp_passive_dongle_detection(link->ddc, @@ -884,7 +821,7 @@ static bool dc_link_detect_helper(struct dc_link *link, { struct dc_sink_init_data sink_init_data = { 0 }; struct display_sink_capability sink_caps = { 0 }; - uint8_t i; + uint32_t i; bool converter_disable_audio = false; struct audio_support *aud_support = &link->dc->res_pool->audio_support; bool same_edid = false; @@ -893,7 +830,6 @@ static bool dc_link_detect_helper(struct dc_link *link, struct dc_sink *sink = NULL; struct dc_sink *prev_sink = NULL; struct dpcd_caps prev_dpcd_caps; - bool same_dpcd = true; enum dc_connection_type new_connection_type = dc_connection_none; enum dc_connection_type pre_connection_type = dc_connection_none; bool perform_dp_seamless_boot = false; @@ -904,9 +840,10 @@ static bool dc_link_detect_helper(struct dc_link *link, if (dc_is_virtual_signal(link->connector_signal)) return false; - if ((link->connector_signal == SIGNAL_TYPE_LVDS || - link->connector_signal == SIGNAL_TYPE_EDP) && - link->local_sink) { + if (((link->connector_signal == SIGNAL_TYPE_LVDS || + link->connector_signal == SIGNAL_TYPE_EDP) && + (!link->dc->config.allow_edp_hotplug_detection)) && + link->local_sink) { // need to re-write OUI and brightness in resume case if (link->connector_signal == SIGNAL_TYPE_EDP) { dpcd_set_source_specific_data(link); @@ -983,20 +920,59 @@ static bool dc_link_detect_helper(struct dc_link *link, return false; } - if (!detect_dp(link, &sink_caps, - &converter_disable_audio, - aud_support, reason)) { + if (!detect_dp(link, &sink_caps, reason)) { if (prev_sink) dc_sink_release(prev_sink); return false; } - // Check if dpcp block is the same - if (prev_sink) { - if (memcmp(&link->dpcd_caps, &prev_dpcd_caps, - sizeof(struct dpcd_caps))) - same_dpcd = false; + if (link->type == dc_connection_mst_branch) { + LINK_INFO("link=%d, mst branch is now Connected\n", + link->link_index); + /* Need to setup mst link_cap struct here + * otherwise dc_link_detect() will leave mst link_cap + * empty which leads to allocate_mst_payload() has "0" + * pbn_per_slot value leading to exception on dc_fixpt_div() + */ + dp_verify_mst_link_cap(link); + + /* + * This call will initiate MST topology discovery. Which + * will detect MST ports and add new DRM connector DRM + * framework. Then read EDID via remote i2c over aux. In + * the end, will notify DRM detect result and save EDID + * into DRM framework. + * + * .detect is called by .fill_modes. + * .fill_modes is called by user mode ioctl + * DRM_IOCTL_MODE_GETCONNECTOR. + * + * .get_modes is called by .fill_modes. + * + * call .get_modes, AMDGPU DM implementation will create + * new dc_sink and add to dc_link. For long HPD plug + * in/out, MST has its own handle. + * + * Therefore, just after dc_create, link->sink is not + * created for MST until user mode app calls + * DRM_IOCTL_MODE_GETCONNECTOR. + * + * Need check ->sink usages in case ->sink = NULL + * TODO: s3 resume check + */ + + dm_helpers_dp_update_branch_info(link->ctx, link); + if (dm_helpers_dp_mst_start_top_mgr(link->ctx, + link, reason == DETECT_REASON_BOOT)) { + if (prev_sink) + dc_sink_release(prev_sink); + return false; + } else { + link->type = dc_connection_sst_branch; + sink_caps.signal = SIGNAL_TYPE_DISPLAY_PORT; + } } + /* Active SST downstream branch device unplug*/ if (link->type == dc_connection_sst_branch && link->dpcd_caps.sink_count.bits.SINK_COUNT == 0) { @@ -1006,31 +982,23 @@ static bool dc_link_detect_helper(struct dc_link *link, return true; } + /* disable audio for non DP to HDMI active sst converter */ + if (link->type == dc_connection_sst_branch && + is_dp_active_dongle(link) && + (link->dpcd_caps.dongle_type != + DISPLAY_DONGLE_DP_HDMI_CONVERTER)) + converter_disable_audio = true; + // link switch from MST to non-MST stop topology manager if (pre_connection_type == dc_connection_mst_branch && - link->type != dc_connection_mst_branch) { + link->type != dc_connection_mst_branch) dm_helpers_dp_mst_stop_top_mgr(link->ctx, link); - } - if (link->type == dc_connection_mst_branch) { - LINK_INFO("link=%d, mst branch is now Connected\n", - link->link_index); - /* Need to setup mst link_cap struct here - * otherwise dc_link_detect() will leave mst link_cap - * empty which leads to allocate_mst_payload() has "0" - * pbn_per_slot value leading to exception on dc_fixpt_div() - */ - dp_verify_mst_link_cap(link); - - if (prev_sink) - dc_sink_release(prev_sink); - return false; - } // For seamless boot, to skip verify link cap, we read UEFI settings and set them as verified. if (reason == DETECT_REASON_BOOT && - !dc_ctx->dc->config.power_down_display_on_boot && - link->link_status.link_active) + !dc_ctx->dc->config.power_down_display_on_boot && + link->link_status.link_active) perform_dp_seamless_boot = true; if (perform_dp_seamless_boot) { @@ -1213,11 +1181,11 @@ static bool dc_link_detect_helper(struct dc_link *link, link->dongle_max_pix_clk = 0; } - LINK_INFO("link=%d, dc_sink_in=%p is now %s prev_sink=%p dpcd same=%d edid same=%d\n", + LINK_INFO("link=%d, dc_sink_in=%p is now %s prev_sink=%p edid same=%d\n", link->link_index, sink, (sink_caps.signal == SIGNAL_TYPE_NONE ? "Disconnected" : "Connected"), - prev_sink, same_dpcd, same_edid); + prev_sink, same_edid); if (prev_sink) dc_sink_release(prev_sink); @@ -1501,7 +1469,8 @@ static bool dc_link_construct(struct dc_link *link, link->connector_signal = SIGNAL_TYPE_EDP; if (link->hpd_gpio) { - link->irq_source_hpd = DC_IRQ_SOURCE_INVALID; + if (!link->dc->config.allow_edp_hotplug_detection) + link->irq_source_hpd = DC_IRQ_SOURCE_INVALID; link->irq_source_hpd_rx = dal_irq_get_rx_source(link->hpd_gpio); } @@ -2692,7 +2661,7 @@ bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, return false; link->psr_settings.psr_allow_active = allow_active; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) if (!allow_active) dc_z10_restore(dc); #endif @@ -2873,7 +2842,7 @@ bool dc_link_setup_psr(struct dc_link *link, psr_context->psr_level.u32all = 0; /*skip power down the single pipe since it blocks the cstate*/ -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) if (link->ctx->asic_id.chip_family >= FAMILY_RV) { psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true; if (link->ctx->asic_id.chip_family == FAMILY_YELLOW_CARP && !dc->debug.disable_z10) @@ -3222,7 +3191,7 @@ static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off) /*stream_enc_inst*/ config.dig_fe = (uint8_t) pipe_ctx->stream_res.stream_enc->stream_enc_inst; config.dig_be = pipe_ctx->stream->link->link_enc_hw_inst; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) config.stream_enc_idx = pipe_ctx->stream_res.stream_enc->id - ENGINE_ID_DIGA; config.link_enc_idx = pipe_ctx->stream->link->link_enc->transmitter - TRANSMITTER_UNIPHY_A; config.phy_idx = pipe_ctx->stream->link->link_enc->transmitter - TRANSMITTER_UNIPHY_A; 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 919c94de2a20..6da226bf11d5 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 @@ -25,6 +25,8 @@ static const uint8_t DP_VGA_LVDS_CONVERTER_ID_3[] = "dnomlA"; link->ctx->logger #define DC_TRACE_LEVEL_MESSAGE(...) /* do nothing */ +#include "link_dpcd.h" + /* maximum pre emphasis level allowed for each voltage swing level*/ static const enum dc_pre_emphasis voltage_swing_to_pre_emphasis[] = { PRE_EMPHASIS_LEVEL3, @@ -1663,6 +1665,7 @@ static enum link_training_result dp_perform_8b_10b_link_training( uint8_t repeater_cnt; uint8_t repeater_id; + uint8_t lane = 0; if (link->ctx->dc->work_arounds.lt_early_cr_pattern) start_clock_recovery_pattern_early(link, lt_settings, DPRX); @@ -1693,6 +1696,9 @@ static enum link_training_result dp_perform_8b_10b_link_training( repeater_training_done(link, repeater_id); } + + for (lane = 0; lane < (uint8_t)lt_settings->link_settings.lane_count; lane++) + lt_settings->lane_settings[lane].VOLTAGE_SWING = VOLTAGE_SWING_LEVEL0; } if (status == LINK_TRAINING_SUCCESS) { @@ -1755,42 +1761,6 @@ enum link_training_result dc_link_dp_perform_link_training( return status; } -static enum dp_panel_mode try_enable_assr(struct dc_stream_state *stream) -{ - struct dc_link *link = stream->link; - enum dp_panel_mode panel_mode = dp_get_panel_mode(link); -#ifdef CONFIG_DRM_AMD_DC_HDCP - struct cp_psp *cp_psp = &stream->ctx->cp_psp; -#endif - - /* ASSR must be supported on the panel */ - if (panel_mode == DP_PANEL_MODE_DEFAULT) - return panel_mode; - - /* eDP or internal DP only */ - if (link->connector_signal != SIGNAL_TYPE_EDP && - !(link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT && - link->is_internal_display)) - return DP_PANEL_MODE_DEFAULT; - -#ifdef CONFIG_DRM_AMD_DC_HDCP - if (cp_psp && cp_psp->funcs.enable_assr) { - if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { - /* since eDP implies ASSR on, change panel - * mode to disable ASSR - */ - panel_mode = DP_PANEL_MODE_DEFAULT; - } - } else - panel_mode = DP_PANEL_MODE_DEFAULT; - -#else - /* turn off ASSR if the implementation is not compiled in */ - panel_mode = DP_PANEL_MODE_DEFAULT; -#endif - return panel_mode; -} - bool perform_link_training_with_retries( const struct dc_link_settings *link_setting, bool skip_video_pattern, @@ -1799,14 +1769,14 @@ bool perform_link_training_with_retries( enum signal_type signal, bool do_fallback) { - uint8_t j; + int j; uint8_t delay_between_attempts = LINK_TRAINING_RETRY_DELAY; struct dc_stream_state *stream = pipe_ctx->stream; struct dc_link *link = stream->link; - enum dp_panel_mode panel_mode; + enum dp_panel_mode panel_mode = dp_get_panel_mode(link); struct link_encoder *link_enc; enum link_training_result status = LINK_TRAINING_CR_FAIL_LANE0; - struct dc_link_settings currnet_setting = *link_setting; + struct dc_link_settings current_setting = *link_setting; /* Dynamically assigned link encoders associated with stream rather than * link. @@ -1815,7 +1785,6 @@ bool perform_link_training_with_retries( link_enc = stream->link_enc; else link_enc = link->link_enc; - ASSERT(link_enc); /* We need to do this before the link training to ensure the idle pattern in SST * mode will be sent right after the link training @@ -1832,7 +1801,7 @@ bool perform_link_training_with_retries( link, signal, pipe_ctx->clock_source->id, - &currnet_setting); + ¤t_setting); if (stream->sink_patches.dppowerup_delay > 0) { int delay_dp_power_up_in_ms = stream->sink_patches.dppowerup_delay; @@ -1840,19 +1809,31 @@ bool perform_link_training_with_retries( msleep(delay_dp_power_up_in_ms); } - panel_mode = try_enable_assr(stream); +#ifdef CONFIG_DRM_AMD_DC_HDCP + if (panel_mode == DP_PANEL_MODE_EDP) { + struct cp_psp *cp_psp = &stream->ctx->cp_psp; + + if (cp_psp && cp_psp->funcs.enable_assr) { + if (!cp_psp->funcs.enable_assr(cp_psp->handle, link)) { + /* since eDP implies ASSR on, change panel + * mode to disable ASSR + */ + panel_mode = DP_PANEL_MODE_DEFAULT; + } + } else + panel_mode = DP_PANEL_MODE_DEFAULT; + } +#endif + dp_set_panel_mode(link, panel_mode); - DC_LOG_DETECTION_DP_CAPS("Link: %d ASSR enabled: %d\n", - link->link_index, - panel_mode != DP_PANEL_MODE_DEFAULT); if (link->aux_access_disabled) { - dc_link_dp_perform_link_training_skip_aux(link, &currnet_setting); + dc_link_dp_perform_link_training_skip_aux(link, ¤t_setting); return true; } else { status = dc_link_dp_perform_link_training( link, - &currnet_setting, + ¤t_setting, skip_video_pattern); if (status == LINK_TRAINING_SUCCESS) return true; @@ -1872,12 +1853,12 @@ bool perform_link_training_with_retries( if (status == LINK_TRAINING_ABORT) break; else if (do_fallback) { - decide_fallback_link_setting(*link_setting, &currnet_setting, status); + decide_fallback_link_setting(*link_setting, ¤t_setting, status); /* Fail link training if reduced link bandwidth no longer meets * stream requirements. */ if (dc_bandwidth_in_kbps_from_timing(&stream->timing) < - dc_link_bandwidth_kbps(link, &currnet_setting)) + dc_link_bandwidth_kbps(link, ¤t_setting)) break; } @@ -2326,7 +2307,7 @@ bool dp_verify_link_cap_with_retries( struct dc_link_settings *known_limit_link_setting, int attempts) { - uint8_t i = 0; + int i = 0; bool success = false; for (i = 0; i < attempts; i++) { @@ -3619,79 +3600,16 @@ static bool dpcd_read_sink_ext_caps(struct dc_link *link) return true; } -static bool retrieve_link_cap(struct dc_link *link) +bool dp_retrieve_lttpr_cap(struct dc_link *link) { - /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, - * which means size 16 will be good for both of those DPCD register block reads - */ - uint8_t dpcd_data[16]; uint8_t lttpr_dpcd_data[6]; - - /*Only need to read 1 byte starting from DP_DPRX_FEATURE_ENUMERATION_LIST. - */ - uint8_t dpcd_dprx_data = '\0'; - uint8_t dpcd_power_state = '\0'; - - struct dp_device_vendor_id sink_id; - union down_stream_port_count down_strm_port_count; - union edp_configuration_cap edp_config_cap; - union dp_downstream_port_present ds_port = { 0 }; - enum dc_status status = DC_ERROR_UNEXPECTED; - uint32_t read_dpcd_retry_cnt = 3; - int i; - struct dp_sink_hw_fw_revision dp_hw_fw_revision; - bool is_lttpr_present = false; - const uint32_t post_oui_delay = 30; // 30ms bool vbios_lttpr_enable = false; bool vbios_lttpr_interop = false; struct dc_bios *bios = link->dc->ctx->dc_bios; + enum dc_status status = DC_ERROR_UNEXPECTED; + bool is_lttpr_present = false; - memset(dpcd_data, '\0', sizeof(dpcd_data)); memset(lttpr_dpcd_data, '\0', sizeof(lttpr_dpcd_data)); - memset(&down_strm_port_count, - '\0', sizeof(union down_stream_port_count)); - memset(&edp_config_cap, '\0', - sizeof(union edp_configuration_cap)); - - /* if extended timeout is supported in hardware, - * default to LTTPR timeout (3.2ms) first as a W/A for DP link layer - * CTS 4.2.1.1 regression introduced by CTS specs requirement update. - */ - dc_link_aux_try_to_configure_timeout(link->ddc, - LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); - - status = core_link_read_dpcd(link, DP_SET_POWER, - &dpcd_power_state, sizeof(dpcd_power_state)); - - /* Delay 1 ms if AUX CH is in power down state. Based on spec - * section 2.3.1.2, if AUX CH may be powered down due to - * write to DPCD 600h = 2. Sink AUX CH is monitoring differential - * signal and may need up to 1 ms before being able to reply. - */ - if (status != DC_OK || dpcd_power_state == DP_SET_POWER_D3) - udelay(1000); - - dpcd_set_source_specific_data(link); - /* Sink may need to configure internals based on vendor, so allow some - * time before proceeding with possibly vendor specific transactions - */ - msleep(post_oui_delay); - - for (i = 0; i < read_dpcd_retry_cnt; i++) { - status = core_link_read_dpcd( - link, - DP_DPCD_REV, - dpcd_data, - sizeof(dpcd_data)); - if (status == DC_OK) - break; - } - - if (status != DC_OK) { - dm_error("%s: Read dpcd data failed.\n", __func__); - return false; - } - /* Query BIOS to determine if LTTPR functionality is forced on by system */ if (bios->funcs->get_lttpr_caps) { enum bp_result bp_query_result; @@ -3737,6 +3655,10 @@ static bool retrieve_link_cap(struct dc_link *link) DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, lttpr_dpcd_data, sizeof(lttpr_dpcd_data)); + if (status != DC_OK) { + dm_error("%s: Read LTTPR caps data failed.\n", __func__); + return false; + } link->dpcd_caps.lttpr_caps.revision.raw = lttpr_dpcd_data[DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV - @@ -3763,21 +3685,91 @@ static bool retrieve_link_cap(struct dc_link *link) 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.phy_repeater_cnt > 0 && - link->dpcd_caps.lttpr_caps.phy_repeater_cnt < 0xff && + is_lttpr_present = (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); - if (is_lttpr_present) + if (is_lttpr_present) { CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: "); - else + configure_lttpr_mode_transparent(link); + } else link->lttpr_mode = LTTPR_MODE_NON_LTTPR; } + return is_lttpr_present; +} + +static bool retrieve_link_cap(struct dc_link *link) +{ + /* DP_ADAPTER_CAP - DP_DPCD_REV + 1 == 16 and also DP_DSC_BITS_PER_PIXEL_INC - DP_DSC_SUPPORT + 1 == 16, + * which means size 16 will be good for both of those DPCD register block reads + */ + uint8_t dpcd_data[16]; + /*Only need to read 1 byte starting from DP_DPRX_FEATURE_ENUMERATION_LIST. + */ + uint8_t dpcd_dprx_data = '\0'; + uint8_t dpcd_power_state = '\0'; + + struct dp_device_vendor_id sink_id; + union down_stream_port_count down_strm_port_count; + union edp_configuration_cap edp_config_cap; + union dp_downstream_port_present ds_port = { 0 }; + enum dc_status status = DC_ERROR_UNEXPECTED; + uint32_t read_dpcd_retry_cnt = 3; + int i; + struct dp_sink_hw_fw_revision dp_hw_fw_revision; + const uint32_t post_oui_delay = 30; // 30ms + bool is_lttpr_present = false; + + memset(dpcd_data, '\0', sizeof(dpcd_data)); + memset(&down_strm_port_count, + '\0', sizeof(union down_stream_port_count)); + memset(&edp_config_cap, '\0', + sizeof(union edp_configuration_cap)); + + /* if extended timeout is supported in hardware, + * default to LTTPR timeout (3.2ms) first as a W/A for DP link layer + * CTS 4.2.1.1 regression introduced by CTS specs requirement update. + */ + dc_link_aux_try_to_configure_timeout(link->ddc, + LINK_AUX_DEFAULT_LTTPR_TIMEOUT_PERIOD); + + is_lttpr_present = dp_retrieve_lttpr_cap(link); + + status = core_link_read_dpcd(link, DP_SET_POWER, + &dpcd_power_state, sizeof(dpcd_power_state)); + + /* Delay 1 ms if AUX CH is in power down state. Based on spec + * section 2.3.1.2, if AUX CH may be powered down due to + * write to DPCD 600h = 2. Sink AUX CH is monitoring differential + * signal and may need up to 1 ms before being able to reply. + */ + if (status != DC_OK || dpcd_power_state == DP_SET_POWER_D3) + udelay(1000); + + dpcd_set_source_specific_data(link); + /* Sink may need to configure internals based on vendor, so allow some + * time before proceeding with possibly vendor specific transactions + */ + msleep(post_oui_delay); + + for (i = 0; i < read_dpcd_retry_cnt; i++) { + status = core_link_read_dpcd( + link, + DP_DPCD_REV, + dpcd_data, + sizeof(dpcd_data)); + if (status == DC_OK) + break; + } + + if (status != DC_OK) { + dm_error("%s: Read receiver caps dpcd data failed.\n", __func__); + return false; + } if (!is_lttpr_present) dc_link_aux_try_to_configure_timeout(link->ddc, LINK_AUX_DEFAULT_TIMEOUT_PERIOD); - { union training_aux_rd_interval aux_rd_interval; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c new file mode 100644 index 000000000000..fe234760a0f5 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dpcd.c @@ -0,0 +1,218 @@ +#include <inc/core_status.h> +#include <dc_link.h> +#include <inc/link_hwss.h> +#include <inc/link_dpcd.h> +#include "drm/drm_dp_helper.h" +#include <dc_dp_types.h> +#include "dm_helpers.h" + +#define END_ADDRESS(start, size) (start + size - 1) +#define ADDRESS_RANGE_SIZE(start, end) (end - start + 1) +struct dpcd_address_range { + uint32_t start; + uint32_t end; +}; + +static enum dc_status internal_link_read_dpcd( + struct dc_link *link, + uint32_t address, + uint8_t *data, + uint32_t size) +{ + if (!link->aux_access_disabled && + !dm_helpers_dp_read_dpcd(link->ctx, + link, address, data, size)) { + return DC_ERROR_UNEXPECTED; + } + + return DC_OK; +} + +static enum dc_status internal_link_write_dpcd( + struct dc_link *link, + uint32_t address, + const uint8_t *data, + uint32_t size) +{ + if (!link->aux_access_disabled && + !dm_helpers_dp_write_dpcd(link->ctx, + link, address, data, size)) { + return DC_ERROR_UNEXPECTED; + } + + return DC_OK; +} + +/* + * Partition the entire DPCD address space + * XXX: This partitioning must cover the entire DPCD address space, + * and must contain no gaps or overlapping address ranges. + */ +static const struct dpcd_address_range mandatory_dpcd_partitions[] = { + { 0, DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR1) - 1}, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR1), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR2) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR2), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR3) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR3), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR4) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR4), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR5) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR5), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR6) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR6), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR7) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR7), DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR8) - 1 }, + { DP_TRAINING_PATTERN_SET_PHY_REPEATER(DP_PHY_LTTPR8), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR1) - 1 }, + /* + * The FEC registers are contiguous + */ + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR1), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR1) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR2), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR2) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR3), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR3) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR4), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR4) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR5), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR5) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR6), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR6) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR7), DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR7) - 1 }, + { DP_FEC_STATUS_PHY_REPEATER(DP_PHY_LTTPR8), DP_LTTPR_MAX_ADD }, + /* all remaining DPCD addresses */ + { DP_LTTPR_MAX_ADD + 1, DP_DPCD_MAX_ADD } }; + +static inline bool do_addresses_intersect_with_range( + const struct dpcd_address_range *range, + const uint32_t start_address, + const uint32_t end_address) +{ + return start_address <= range->end && end_address >= range->start; +} + +static uint32_t dpcd_get_next_partition_size(const uint32_t address, const uint32_t size) +{ + const uint32_t end_address = END_ADDRESS(address, size); + uint32_t partition_iterator = 0; + + /* + * find current partition + * this loop spins forever if partition map above is not surjective + */ + while (!do_addresses_intersect_with_range(&mandatory_dpcd_partitions[partition_iterator], + address, end_address)) + partition_iterator++; + if (end_address < mandatory_dpcd_partitions[partition_iterator].end) + return size; + return ADDRESS_RANGE_SIZE(address, mandatory_dpcd_partitions[partition_iterator].end); +} + +/* + * Ranges of DPCD addresses that must be read in a single transaction + * XXX: Do not allow any two address ranges in this array to overlap + */ +static const struct dpcd_address_range mandatory_dpcd_blocks[] = { + { DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV, DP_PHY_REPEATER_EXTENDED_WAIT_TIMEOUT }}; + +/* + * extend addresses to read all mandatory blocks together + */ +static void dpcd_extend_address_range( + const uint32_t in_address, + uint8_t * const in_data, + const uint32_t in_size, + uint32_t *out_address, + uint8_t **out_data, + uint32_t *out_size) +{ + const uint32_t end_address = END_ADDRESS(in_address, in_size); + const struct dpcd_address_range *addr_range; + struct dpcd_address_range new_addr_range; + uint32_t i; + + new_addr_range.start = in_address; + new_addr_range.end = end_address; + for (i = 0; i < ARRAY_SIZE(mandatory_dpcd_blocks); i++) { + addr_range = &mandatory_dpcd_blocks[i]; + if (addr_range->start <= in_address && addr_range->end >= in_address) + new_addr_range.start = addr_range->start; + + if (addr_range->start <= end_address && addr_range->end >= end_address) + new_addr_range.end = addr_range->end; + } + *out_address = in_address; + *out_size = in_size; + *out_data = in_data; + if (new_addr_range.start != in_address || new_addr_range.end != end_address) { + *out_address = new_addr_range.start; + *out_size = ADDRESS_RANGE_SIZE(new_addr_range.start, new_addr_range.end); + *out_data = kzalloc(*out_size * sizeof(**out_data), GFP_KERNEL); + } +} + +/* + * Reduce the AUX reply down to the values the caller requested + */ +static void dpcd_reduce_address_range( + const uint32_t extended_address, + uint8_t * const extended_data, + const uint32_t extended_size, + const uint32_t reduced_address, + uint8_t * const reduced_data, + const uint32_t reduced_size) +{ + const uint32_t reduced_end_address = END_ADDRESS(reduced_address, reduced_size); + const uint32_t extended_end_address = END_ADDRESS(extended_address, extended_size); + const uint32_t offset = reduced_address - extended_address; + + if (extended_end_address == reduced_end_address && extended_address == reduced_address) + return; /* extended and reduced address ranges point to the same data */ + + memcpy(&extended_data[offset], reduced_data, reduced_size); + kfree(extended_data); +} + +enum dc_status core_link_read_dpcd( + struct dc_link *link, + uint32_t address, + uint8_t *data, + uint32_t size) +{ + uint32_t extended_address; + uint32_t partitioned_address; + uint8_t *extended_data; + uint32_t extended_size; + /* size of the remaining partitioned address space */ + uint32_t size_left_to_read; + enum dc_status status; + /* size of the next partition to be read from */ + uint32_t partition_size; + uint32_t data_index = 0; + + dpcd_extend_address_range(address, data, size, &extended_address, &extended_data, &extended_size); + partitioned_address = extended_address; + size_left_to_read = extended_size; + while (size_left_to_read) { + partition_size = dpcd_get_next_partition_size(partitioned_address, size_left_to_read); + status = internal_link_read_dpcd(link, partitioned_address, &extended_data[data_index], partition_size); + if (status != DC_OK) + break; + partitioned_address += partition_size; + data_index += partition_size; + size_left_to_read -= partition_size; + } + dpcd_reduce_address_range(extended_address, extended_data, extended_size, address, data, size); + return status; +} + +enum dc_status core_link_write_dpcd( + struct dc_link *link, + uint32_t address, + const uint8_t *data, + uint32_t size) +{ + uint32_t partition_size; + uint32_t data_index = 0; + enum dc_status status; + + while (size) { + partition_size = dpcd_get_next_partition_size(address, size); + status = internal_link_write_dpcd(link, address, &data[data_index], partition_size); + if (status != DC_OK) + break; + address += partition_size; + data_index += partition_size; + size -= partition_size; + } + return status; +} diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c index f7dfc8fefdfa..9c51cd09dcf1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c @@ -16,6 +16,7 @@ #include "resource.h" #include "link_enc_cfg.h" #include "clk_mgr.h" +#include "inc/link_dpcd.h" static uint8_t convert_to_count(uint8_t lttpr_repeater_count) { @@ -47,36 +48,6 @@ static inline bool is_immediate_downstream(struct dc_link *link, uint32_t offset return (convert_to_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == offset); } -enum dc_status core_link_read_dpcd( - struct dc_link *link, - uint32_t address, - uint8_t *data, - uint32_t size) -{ - if (!link->aux_access_disabled && - !dm_helpers_dp_read_dpcd(link->ctx, - link, address, data, size)) { - return DC_ERROR_UNEXPECTED; - } - - return DC_OK; -} - -enum dc_status core_link_write_dpcd( - struct dc_link *link, - uint32_t address, - const uint8_t *data, - uint32_t size) -{ - if (!link->aux_access_disabled && - !dm_helpers_dp_write_dpcd(link->ctx, - link, address, data, size)) { - return DC_ERROR_UNEXPECTED; - } - - return DC_OK; -} - void dp_receiver_power_ctrl(struct dc_link *link, bool on) { uint8_t state; 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 5fe4c5f80b54..a6a67244a322 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -58,9 +58,7 @@ #include "dcn301/dcn301_resource.h" #include "dcn302/dcn302_resource.h" #include "dcn303/dcn303_resource.h" -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) -#include "../dcn31/dcn31_resource.h" -#endif +#include "dcn31/dcn31_resource.h" #endif #define DC_LOGGER_INIT(logger) @@ -141,9 +139,7 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id) case FAMILY_VGH: dc_version = DCN_VERSION_3_01; break; -#endif -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case FAMILY_YELLOW_CARP: if (ASICREV_IS_YELLOW_CARP(asic_id.hw_internal_rev)) dc_version = DCN_VERSION_3_1; @@ -233,12 +229,10 @@ struct resource_pool *dc_create_resource_pool(struct dc *dc, case DCN_VERSION_3_03: res_pool = dcn303_create_resource_pool(init_data, dc); break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case DCN_VERSION_3_1: res_pool = dcn31_create_resource_pool(init_data, dc); break; #endif -#endif default: break; } @@ -445,7 +439,7 @@ bool resource_are_vblanks_synchronizable( { uint32_t base60_refresh_rates[] = {10, 20, 5}; uint8_t i; - uint8_t rr_count = sizeof(base60_refresh_rates)/sizeof(base60_refresh_rates[0]); + uint8_t rr_count = ARRAY_SIZE(base60_refresh_rates); uint64_t frame_time_diff; if (stream1->ctx->dc->config.vblank_alignment_dto_params && @@ -2142,7 +2136,7 @@ enum dc_status dc_validate_global_state( if (!new_ctx) return DC_ERROR_UNEXPECTED; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) /* * Update link encoder to stream assignment. 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 5420fda47bb7..45931ee14a6e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -294,9 +294,7 @@ bool dc_stream_set_cursor_attributes( stream->cursor_attributes = *attributes; #if defined(CONFIG_DRM_AMD_DC_DCN) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) dc_z10_restore(dc); -#endif /* disable idle optimizations while updating cursor */ if (dc->idle_optimizations_allowed) { dc_allow_idle_optimizations(dc, false); @@ -358,9 +356,7 @@ bool dc_stream_set_cursor_position( dc = stream->ctx->dc; res_ctx = &dc->current_state->res_ctx; #if defined(CONFIG_DRM_AMD_DC_DCN) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) dc_z10_restore(dc); -#endif /* disable idle optimizations if enabling cursor */ if (dc->idle_optimizations_allowed && !stream->cursor_position.enable && position->enable) { diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h index a70697898025..45640f1c26c4 100644 --- a/drivers/gpu/drm/amd/display/dc/dc.h +++ b/drivers/gpu/drm/amd/display/dc/dc.h @@ -45,7 +45,7 @@ /* forward declaration */ struct aux_payload; -#define DC_VER "3.2.139" +#define DC_VER "3.2.141" #define MAX_SURFACES 3 #define MAX_PLANES 6 @@ -297,12 +297,14 @@ struct dc_config { bool allow_seamless_boot_optimization; bool power_down_display_on_boot; bool edp_not_connected; + bool edp_no_power_sequencing; bool force_enum_edp; bool forced_clocks; bool allow_lttpr_non_transparent_mode; bool multi_mon_pp_mclk_switch; bool disable_dmcu; bool enable_4to1MPC; + bool allow_edp_hotplug_detection; #if defined(CONFIG_DRM_AMD_DC_DCN) bool clamp_min_dcfclk; #endif @@ -351,7 +353,7 @@ enum dcn_pwr_state { DCN_PWR_STATE_LOW_POWER = 3, }; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) enum dcn_z9_support_state { DCN_Z9_SUPPORT_UNKNOWN, DCN_Z9_SUPPORT_ALLOW, @@ -375,7 +377,7 @@ struct dc_clocks { int phyclk_khz; int dramclk_khz; bool p_state_change_support; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) enum dcn_z9_support_state z9_support; bool dtbclk_en; #endif @@ -500,7 +502,7 @@ struct dc_debug_options { bool disable_pplib_clock_request; bool disable_clock_gate; bool disable_mem_low_power; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) bool pstate_enabled; #endif bool disable_dmcu; @@ -521,8 +523,6 @@ struct dc_debug_options { unsigned int force_odm_combine; //bit vector based on otg inst #if defined(CONFIG_DRM_AMD_DC_DCN) unsigned int force_odm_combine_4to1; //bit vector based on otg inst -#endif -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) bool disable_z9_mpc; #endif unsigned int force_fclk_khz; @@ -566,7 +566,7 @@ struct dc_debug_options { bool force_enable_edp_fec; /* FEC/PSR1 sequence enable delay in 100us */ uint8_t fec_enable_delay_in100us; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) bool disable_z10; bool enable_sw_cntl_psr; #endif @@ -594,7 +594,7 @@ struct dc_phy_addr_space_config { uint64_t page_table_start_addr; uint64_t page_table_end_addr; uint64_t page_table_base_addr; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) bool base_addr_is_mc_addr; #endif } gart_config; @@ -1334,7 +1334,7 @@ void dc_hardware_release(struct dc *dc); #endif bool dc_set_psr_allow_active(struct dc *dc, bool enable); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) void dc_z10_restore(struct dc *dc); #endif 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 48ca23e1e599..360f3199ea6f 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -86,6 +86,7 @@ void dc_dmub_srv_cmd_queue(struct dc_dmub_srv *dc_dmub_srv, error: DC_ERROR("Error queuing DMUB command: status=%d\n", status); + dc_dmub_srv_log_diagnostic_data(dc_dmub_srv); } void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv) @@ -95,8 +96,10 @@ void dc_dmub_srv_cmd_execute(struct dc_dmub_srv *dc_dmub_srv) enum dmub_status status; status = dmub_srv_cmd_execute(dmub); - if (status != DMUB_STATUS_OK) + if (status != DMUB_STATUS_OK) { DC_ERROR("Error starting DMUB execution: status=%d\n", status); + dc_dmub_srv_log_diagnostic_data(dc_dmub_srv); + } } void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv) @@ -106,8 +109,10 @@ void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv) enum dmub_status status; status = dmub_srv_wait_for_idle(dmub, 100000); - if (status != DMUB_STATUS_OK) + if (status != DMUB_STATUS_OK) { DC_ERROR("Error waiting for DMUB idle: status=%d\n", status); + dc_dmub_srv_log_diagnostic_data(dc_dmub_srv); + } } void dc_dmub_srv_send_inbox0_cmd(struct dc_dmub_srv *dmub_srv, @@ -180,7 +185,7 @@ bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv, dmub, DMUB_GPINT__IDLE_OPT_NOTIFY_STREAM_MASK, stream_mask, timeout) == DMUB_STATUS_OK; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + bool dc_dmub_srv_is_restore_required(struct dc_dmub_srv *dc_dmub_srv) { struct dmub_srv *dmub; @@ -202,7 +207,6 @@ bool dc_dmub_srv_is_restore_required(struct dc_dmub_srv *dc_dmub_srv) return boot_status.bits.restore_required; } -#endif bool dc_dmub_srv_get_dmub_outbox0_msg(const struct dc *dc, struct dmcub_trace_buf_entry *entry) { @@ -214,3 +218,94 @@ void dc_dmub_trace_event_control(struct dc *dc, bool enable) { dm_helpers_dmub_outbox_interrupt_control(dc->ctx, enable); } + +bool dc_dmub_srv_get_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv, struct dmub_diagnostic_data *diag_data) +{ + if (!dc_dmub_srv || !dc_dmub_srv->dmub || !diag_data) + return false; + return dmub_srv_get_diagnostic_data(dc_dmub_srv->dmub, diag_data); +} + +void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv) +{ + struct dmub_diagnostic_data diag_data = {0}; + + if (!dc_dmub_srv || !dc_dmub_srv->dmub) { + DC_LOG_ERROR("%s: invalid parameters.", __func__); + return; + } + + if (!dc_dmub_srv_get_diagnostic_data(dc_dmub_srv, &diag_data)) { + DC_LOG_ERROR("%s: dc_dmub_srv_get_diagnostic_data failed.", __func__); + return; + } + + DC_LOG_DEBUG( + "DMCUB STATE\n" + " dmcub_version : %08x\n" + " scratch [0] : %08x\n" + " scratch [1] : %08x\n" + " scratch [2] : %08x\n" + " scratch [3] : %08x\n" + " scratch [4] : %08x\n" + " scratch [5] : %08x\n" + " scratch [6] : %08x\n" + " scratch [7] : %08x\n" + " scratch [8] : %08x\n" + " scratch [9] : %08x\n" + " scratch [10] : %08x\n" + " scratch [11] : %08x\n" + " scratch [12] : %08x\n" + " scratch [13] : %08x\n" + " scratch [14] : %08x\n" + " scratch [15] : %08x\n" + " pc : %08x\n" + " unk_fault_addr : %08x\n" + " inst_fault_addr : %08x\n" + " data_fault_addr : %08x\n" + " inbox1_rptr : %08x\n" + " inbox1_wptr : %08x\n" + " inbox1_size : %08x\n" + " inbox0_rptr : %08x\n" + " inbox0_wptr : %08x\n" + " inbox0_size : %08x\n" + " is_enabled : %d\n" + " is_soft_reset : %d\n" + " is_secure_reset : %d\n" + " is_traceport_en : %d\n" + " is_cw0_en : %d\n" + " is_cw6_en : %d\n", + diag_data.dmcub_version, + diag_data.scratch[0], + diag_data.scratch[1], + diag_data.scratch[2], + diag_data.scratch[3], + diag_data.scratch[4], + diag_data.scratch[5], + diag_data.scratch[6], + diag_data.scratch[7], + diag_data.scratch[8], + diag_data.scratch[9], + diag_data.scratch[10], + diag_data.scratch[11], + diag_data.scratch[12], + diag_data.scratch[13], + diag_data.scratch[14], + diag_data.scratch[15], + diag_data.pc, + diag_data.undefined_address_fault_addr, + diag_data.inst_fetch_fault_addr, + diag_data.data_write_fault_addr, + diag_data.inbox1_rptr, + diag_data.inbox1_wptr, + diag_data.inbox1_size, + diag_data.inbox0_rptr, + diag_data.inbox0_wptr, + diag_data.inbox0_size, + diag_data.is_dmcub_enabled, + diag_data.is_dmcub_soft_reset, + diag_data.is_dmcub_secure_reset, + diag_data.is_traceport_en, + diag_data.is_cw0_enabled, + diag_data.is_cw6_enabled); +} 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 f5489c7aa770..3e35eee7188c 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h @@ -62,13 +62,16 @@ bool dc_dmub_srv_cmd_with_reply_data(struct dc_dmub_srv *dc_dmub_srv, union dmub bool dc_dmub_srv_notify_stream_mask(struct dc_dmub_srv *dc_dmub_srv, unsigned int stream_mask); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) bool dc_dmub_srv_is_restore_required(struct dc_dmub_srv *dc_dmub_srv); -#endif + bool dc_dmub_srv_get_dmub_outbox0_msg(const struct dc *dc, struct dmcub_trace_buf_entry *entry); void dc_dmub_trace_event_control(struct dc *dc, bool enable); void dc_dmub_srv_send_inbox0_cmd(struct dc_dmub_srv *dmub_srv, union dmub_inbox0_data_register data); +bool dc_dmub_srv_get_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv, struct dmub_diagnostic_data *dmub_oca); + +void dc_dmub_srv_log_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv); + #endif /* _DMUB_DC_SRV_H_ */ 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 83d97dfe328f..2fb88e54a4bf 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c @@ -615,7 +615,8 @@ int dce_aux_transfer_dmub_raw(struct ddc_service *ddc, } #define AUX_MAX_RETRIES 7 -#define AUX_MAX_DEFER_RETRIES 7 +#define AUX_MIN_DEFER_RETRIES 7 +#define AUX_MAX_DEFER_TIMEOUT_MS 50 #define AUX_MAX_I2C_DEFER_RETRIES 7 #define AUX_MAX_INVALID_REPLY_RETRIES 2 #define AUX_MAX_TIMEOUT_RETRIES 3 @@ -628,6 +629,10 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, bool payload_reply = true; enum aux_return_code_type operation_result; bool retry_on_defer = false; + struct ddc *ddc_pin = ddc->ddc_pin; + struct dce_aux *aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]; + struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(aux_engine); + uint32_t defer_time_in_ms = 0; int aux_ack_retries = 0, aux_defer_retries = 0, @@ -660,19 +665,27 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, break; case AUX_TRANSACTION_REPLY_AUX_DEFER: + /* polling_timeout_period is in us */ + defer_time_in_ms += aux110->polling_timeout_period / 1000; + ++aux_defer_retries; + fallthrough; case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER: retry_on_defer = true; fallthrough; case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK: - if (++aux_defer_retries >= AUX_MAX_DEFER_RETRIES) { + if (aux_defer_retries >= AUX_MIN_DEFER_RETRIES + && defer_time_in_ms >= AUX_MAX_DEFER_TIMEOUT_MS) { goto fail; } else { if ((*payload->reply == AUX_TRANSACTION_REPLY_AUX_DEFER) || (*payload->reply == AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER)) { - if (payload->defer_delay > 1) + if (payload->defer_delay > 1) { msleep(payload->defer_delay); - else if (payload->defer_delay <= 1) + defer_time_in_ms += payload->defer_delay; + } else if (payload->defer_delay <= 1) { udelay(payload->defer_delay * 1000); + defer_time_in_ms += payload->defer_delay; + } } } break; @@ -701,7 +714,7 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc, // Check whether a DEFER had occurred before the timeout. // If so, treat timeout as a DEFER. if (retry_on_defer) { - if (++aux_defer_retries >= AUX_MAX_DEFER_RETRIES) + if (++aux_defer_retries >= AUX_MIN_DEFER_RETRIES) goto fail; else if (payload->defer_delay > 0) msleep(payload->defer_delay); diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h index 8817a834383a..df6539e4c730 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h @@ -1106,22 +1106,18 @@ struct dce_hwseq_registers { type PANEL_DIGON_OVRD;\ type PANEL_PWRSEQ_TARGET_STATE_R; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) #define HWSEQ_DCN31_REG_FIELD_LIST(type) \ type DOMAIN_POWER_FORCEON;\ type DOMAIN_POWER_GATE;\ type DOMAIN_PGFSM_PWR_STATUS;\ type HPO_HDMISTREAMCLK_G_GATE_DIS; -#endif struct dce_hwseq_shift { HWSEQ_REG_FIELD_LIST(uint8_t) HWSEQ_DCN_REG_FIELD_LIST(uint8_t) HWSEQ_DCN3_REG_FIELD_LIST(uint8_t) HWSEQ_DCN301_REG_FIELD_LIST(uint8_t) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) HWSEQ_DCN31_REG_FIELD_LIST(uint8_t) -#endif }; struct dce_hwseq_mask { @@ -1129,9 +1125,7 @@ struct dce_hwseq_mask { HWSEQ_DCN_REG_FIELD_LIST(uint32_t) HWSEQ_DCN3_REG_FIELD_LIST(uint32_t) HWSEQ_DCN301_REG_FIELD_LIST(uint32_t) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) HWSEQ_DCN31_REG_FIELD_LIST(uint32_t) -#endif }; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c index a524f471e0d7..6d1b01c267b7 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.c @@ -264,18 +264,25 @@ static void set_speed( struct dce_i2c_hw *dce_i2c_hw, uint32_t speed) { - uint32_t xtal_ref_div = 0; + uint32_t xtal_ref_div = 0, ref_base_div = 0; uint32_t prescale = 0; + uint32_t i2c_ref_clock = 0; if (speed == 0) return; - REG_GET(MICROSECOND_TIME_BASE_DIV, XTAL_REF_DIV, &xtal_ref_div); + REG_GET_2(MICROSECOND_TIME_BASE_DIV, MICROSECOND_TIME_BASE_DIV, &ref_base_div, + XTAL_REF_DIV, &xtal_ref_div); if (xtal_ref_div == 0) xtal_ref_div = 2; - prescale = ((dce_i2c_hw->reference_frequency * 2) / xtal_ref_div) / speed; + if (ref_base_div == 0) + i2c_ref_clock = (dce_i2c_hw->reference_frequency * 2); + else + i2c_ref_clock = ref_base_div * 1000; + + prescale = (i2c_ref_clock / xtal_ref_div) / speed; if (dce_i2c_hw->masks->DC_I2C_DDC1_START_STOP_TIMING_CNTL) REG_UPDATE_N(SPEED, 3, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h index 2309f2bb162c..3f45ecd189a2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_i2c_hw.h @@ -139,6 +139,7 @@ enum { I2C_SF(DC_I2C_DATA, DC_I2C_INDEX, mask_sh),\ I2C_SF(DC_I2C_DATA, DC_I2C_INDEX_WRITE, mask_sh),\ I2C_SF(MICROSECOND_TIME_BASE_DIV, XTAL_REF_DIV, mask_sh),\ + I2C_SF(MICROSECOND_TIME_BASE_DIV, MICROSECOND_TIME_BASE_DIV, mask_sh),\ I2C_SF(DC_I2C_ARBITRATION, DC_I2C_REG_RW_CNTL_STATUS, mask_sh) #define I2C_COMMON_MASK_SH_LIST_DCE110(mask_sh)\ @@ -182,6 +183,7 @@ struct dce_i2c_shift { uint8_t DC_I2C_INDEX; uint8_t DC_I2C_INDEX_WRITE; uint8_t XTAL_REF_DIV; + uint8_t MICROSECOND_TIME_BASE_DIV; uint8_t DC_I2C_DDC1_SEND_RESET_LENGTH; uint8_t DC_I2C_REG_RW_CNTL_STATUS; uint8_t I2C_LIGHT_SLEEP_FORCE; @@ -225,6 +227,7 @@ struct dce_i2c_mask { uint32_t DC_I2C_INDEX; uint32_t DC_I2C_INDEX_WRITE; uint32_t XTAL_REF_DIV; + uint32_t MICROSECOND_TIME_BASE_DIV; uint32_t DC_I2C_DDC1_SEND_RESET_LENGTH; uint32_t DC_I2C_REG_RW_CNTL_STATUS; uint32_t I2C_LIGHT_SLEEP_FORCE; 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 53dd305fa6b0..62d595ded866 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 @@ -48,7 +48,7 @@ #include "link_encoder.h" #include "link_hwss.h" #include "dc_link_dp.h" -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) #include "dccg.h" #endif #include "clock_source.h" @@ -65,7 +65,6 @@ #include "atomfirmware.h" -#include "dce110_hw_sequencer.h" #include "dcn10/dcn10_hw_sequencer.h" #define GAMMA_HW_POINTS_NUM 256 @@ -1023,8 +1022,20 @@ void dce110_edp_backlight_control( /* dc_service_sleep_in_milliseconds(50); */ /*edp 1.2*/ panel_instance = link->panel_cntl->inst; - if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) - edp_receiver_ready_T7(link); + + if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_ON) { + if (!link->dc->config.edp_no_power_sequencing) + /* + * Sometimes, DP receiver chip power-controlled externally by an + * Embedded Controller could be treated and used as eDP, + * if it drives mobile display. In this case, + * we shouldn't be doing power-sequencing, hence we can skip + * waiting for T7-ready. + */ + edp_receiver_ready_T7(link); + else + DC_LOG_DC("edp_receiver_ready_T7 skipped\n"); + } if (ctx->dc->ctx->dmub_srv && ctx->dc->debug.dmub_command_table) { @@ -1049,8 +1060,19 @@ void dce110_edp_backlight_control( dc_link_backlight_enable_aux(link, enable); /*edp 1.2*/ - if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_OFF) - edp_add_delay_for_T9(link); + if (cntl.action == TRANSMITTER_CONTROL_BACKLIGHT_OFF) { + if (!link->dc->config.edp_no_power_sequencing) + /* + * Sometimes, DP receiver chip power-controlled externally by an + * Embedded Controller could be treated and used as eDP, + * if it drives mobile display. In this case, + * we shouldn't be doing power-sequencing, hence we can skip + * waiting for T9-ready. + */ + edp_add_delay_for_T9(link); + else + DC_LOG_DC("edp_receiver_ready_T9 skipped\n"); + } if (!enable && link->dpcd_sink_ext_caps.bits.oled) msleep(OLED_PRE_T11_DELAY); @@ -2091,7 +2113,7 @@ static void dce110_setup_audio_dto( build_audio_output(context, pipe_ctx, &audio_output); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) +#if defined(CONFIG_DRM_AMD_DC_DCN) /* For DCN3.1, audio to HPO FRL encoder is using audio DTBCLK DTO */ if (dc->res_pool->dccg && dc->res_pool->dccg->funcs->set_audio_dtbclk_dto) { /* disable audio DTBCLK DTO */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h index 9a1f40eb5c47..71b3a6949001 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h @@ -1497,8 +1497,6 @@ void dpp1_cnv_setup ( enum dc_color_space input_color_space, struct cnv_alpha_2bit_lut *alpha_2bit_lut); -void dpp1_full_bypass(struct dpp *dpp_base); - void dpp1_dppclk_control( struct dpp *dpp_base, bool dppclk_div, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h index 83c3f944e9ab..8d7e92d5d3e4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h @@ -139,7 +139,6 @@ struct dcn_hubbub_registers { uint32_t DCHVM_CLK_CTRL; uint32_t DCHVM_RIOMMU_CTRL0; uint32_t DCHVM_RIOMMU_STAT0; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint32_t DCHUBBUB_DET0_CTRL; uint32_t DCHUBBUB_DET1_CTRL; uint32_t DCHUBBUB_DET2_CTRL; @@ -155,7 +154,6 @@ struct dcn_hubbub_registers { uint32_t DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_C; uint32_t DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_D; uint32_t DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D; -#endif }; /* set field name */ @@ -292,7 +290,7 @@ struct dcn_hubbub_registers { type HOSTVM_POWERSTATUS; \ type RIOMMU_ACTIVE; \ type HOSTVM_PREFETCH_DONE -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + #define HUBBUB_RET_REG_FIELD_LIST(type) \ type DET_DEPTH;\ type DET0_SIZE;\ @@ -315,25 +313,20 @@ struct dcn_hubbub_registers { type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_C;\ type DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_Z8_D;\ type DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_Z8_D -#endif struct dcn_hubbub_shift { DCN_HUBBUB_REG_FIELD_LIST(uint8_t); HUBBUB_STUTTER_REG_FIELD_LIST(uint8_t); HUBBUB_HVM_REG_FIELD_LIST(uint8_t); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) HUBBUB_RET_REG_FIELD_LIST(uint8_t); -#endif }; struct dcn_hubbub_mask { DCN_HUBBUB_REG_FIELD_LIST(uint32_t); HUBBUB_STUTTER_REG_FIELD_LIST(uint32_t); HUBBUB_HVM_REG_FIELD_LIST(uint32_t); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) HUBBUB_RET_REG_FIELD_LIST(uint32_t); -#endif }; struct dc; 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 3b175af97388..c545eddabdcc 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 @@ -54,6 +54,8 @@ #include "dce/dmub_hw_lock_mgr.h" #include "dc_trace.h" #include "dce/dmub_outbox.h" +#include "inc/dc_link_dp.h" +#include "inc/link_dpcd.h" #define DC_LOGGER_INIT(logger) @@ -1403,6 +1405,9 @@ void dcn10_init_hw(struct dc *dc) if (dc->links[i]->connector_signal != SIGNAL_TYPE_DISPLAY_PORT) continue; + /* DP 2.0 requires that LTTPR Caps be read first */ + dp_retrieve_lttpr_cap(dc->links[i]); + /* * If any of the displays are lit up turn them off. * The reason is that some MST hubs cannot be turned off @@ -3240,10 +3245,17 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) * about the actual size being incorrect, that's a limitation of * the hardware. */ - x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width / - pipe_ctx->plane_state->dst_rect.width; - y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height / - pipe_ctx->plane_state->dst_rect.height; + if (param.rotation == ROTATION_ANGLE_90 || param.rotation == ROTATION_ANGLE_270) { + x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.height / + pipe_ctx->plane_state->dst_rect.width; + y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.width / + pipe_ctx->plane_state->dst_rect.height; + } else { + x_pos = (x_pos - x_plane) * pipe_ctx->plane_state->src_rect.width / + pipe_ctx->plane_state->dst_rect.width; + y_pos = (y_pos - y_plane) * pipe_ctx->plane_state->src_rect.height / + pipe_ctx->plane_state->dst_rect.height; + } /** * If the cursor's source viewport is clipped then we need to diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h index ba47553081a7..d8b22618b79e 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h @@ -160,14 +160,12 @@ struct dcn10_link_enc_registers { uint32_t PHYA_LINK_CNTL2; uint32_t PHYB_LINK_CNTL2; uint32_t PHYC_LINK_CNTL2; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint32_t DIO_LINKA_CNTL; uint32_t DIO_LINKB_CNTL; uint32_t DIO_LINKC_CNTL; uint32_t DIO_LINKD_CNTL; uint32_t DIO_LINKE_CNTL; uint32_t DIO_LINKF_CNTL; -#endif }; #define LE_SF(reg_name, field_name, post_fix)\ @@ -467,29 +465,24 @@ struct dcn10_link_enc_registers { type DPCS_TX_DATA_SWAP_10_BIT;\ type DPCS_TX_DATA_ORDER_INVERT_18_BIT;\ type RDPCS_TX_CLK_EN -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + #define DCN31_LINK_ENCODER_REG_FIELD_LIST(type) \ type ENC_TYPE_SEL;\ type HPO_DP_ENC_SEL;\ type HPO_HDMI_ENC_SEL -#endif struct dcn10_link_enc_shift { DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t); DCN20_LINK_ENCODER_REG_FIELD_LIST(uint8_t); DCN30_LINK_ENCODER_REG_FIELD_LIST(uint8_t); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCN31_LINK_ENCODER_REG_FIELD_LIST(uint8_t); -#endif }; struct dcn10_link_enc_mask { DCN_LINK_ENCODER_REG_FIELD_LIST(uint32_t); DCN20_LINK_ENCODER_REG_FIELD_LIST(uint32_t); DCN30_LINK_ENCODER_REG_FIELD_LIST(uint32_t); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCN31_LINK_ENCODER_REG_FIELD_LIST(uint32_t); -#endif }; struct dcn10_link_encoder { diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h index 76b334644f9e..0d86df97878c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h @@ -52,6 +52,7 @@ SRI(AFMT_60958_1, DIG, id), \ SRI(AFMT_60958_2, DIG, id), \ SRI(DIG_FE_CNTL, DIG, id), \ + SRI(DIG_FIFO_STATUS, DIG, id), \ SRI(HDMI_CONTROL, DIG, id), \ SRI(HDMI_DB_CONTROL, DIG, id), \ SRI(HDMI_GC, DIG, id), \ @@ -124,6 +125,7 @@ struct dcn10_stream_enc_registers { uint32_t AFMT_60958_2; uint32_t DIG_FE_CNTL; uint32_t DIG_FE_CNTL2; + uint32_t DIG_FIFO_STATUS; uint32_t DP_MSE_RATE_CNTL; uint32_t DP_MSE_RATE_UPDATE; uint32_t DP_PIXEL_FORMAT; @@ -266,6 +268,17 @@ struct dcn10_stream_enc_registers { SE_SF(DIG0_DIG_FE_CNTL, TMDS_COLOR_FORMAT, mask_sh),\ SE_SF(DIG0_DIG_FE_CNTL, DIG_STEREOSYNC_SELECT, mask_sh),\ SE_SF(DIG0_DIG_FE_CNTL, DIG_STEREOSYNC_GATE_EN, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_LEVEL_ERROR, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_USE_OVERWRITE_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_OVERWRITE_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_ERROR_ACK, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_CAL_AVERAGE_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_MAXIMUM_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_MINIMUM_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_READ_CLOCK_SRC, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_CALIBRATED, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_FORCE_RECAL_AVERAGE, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_FORCE_RECOMP_MINMAX, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_LOCK_STATUS, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_CONFLICT, mask_sh),\ SE_SF(DIG0_AFMT_VBI_PACKET_CONTROL, AFMT_GENERIC_CONFLICT_CLR, mask_sh),\ @@ -488,6 +501,17 @@ struct dcn10_stream_enc_registers { type DP_VID_N_MUL;\ type DP_VID_M_DOUBLE_VALUE_EN;\ type DIG_SOURCE_SELECT;\ + type DIG_FIFO_LEVEL_ERROR;\ + type DIG_FIFO_USE_OVERWRITE_LEVEL;\ + type DIG_FIFO_OVERWRITE_LEVEL;\ + type DIG_FIFO_ERROR_ACK;\ + type DIG_FIFO_CAL_AVERAGE_LEVEL;\ + type DIG_FIFO_MAXIMUM_LEVEL;\ + type DIG_FIFO_MINIMUM_LEVEL;\ + type DIG_FIFO_READ_CLOCK_SRC;\ + type DIG_FIFO_CALIBRATED;\ + type DIG_FIFO_FORCE_RECAL_AVERAGE;\ + type DIG_FIFO_FORCE_RECOMP_MINMAX;\ type DIG_CLOCK_PATTERN #define SE_REG_FIELD_LIST_DCN2_0(type) \ 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 62904d7ca100..ede65100a050 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h @@ -140,7 +140,6 @@ type PHYCSYMCLK_FORCE_EN;\ type PHYCSYMCLK_FORCE_SRC_SEL; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) #define DCCG31_REG_FIELD_LIST(type) \ type PHYDSYMCLK_FORCE_EN;\ type PHYDSYMCLK_FORCE_SRC_SEL;\ @@ -171,22 +170,17 @@ type DCCG_AUDIO_DTO_SEL;\ type DCCG_AUDIO_DTO0_SOURCE_SEL;\ type DENTIST_DISPCLK_CHG_MODE; -#endif struct dccg_shift { DCCG_REG_FIELD_LIST(uint8_t) DCCG3_REG_FIELD_LIST(uint8_t) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCCG31_REG_FIELD_LIST(uint8_t) -#endif }; struct dccg_mask { DCCG_REG_FIELD_LIST(uint32_t) DCCG3_REG_FIELD_LIST(uint32_t) -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCCG31_REG_FIELD_LIST(uint32_t) -#endif }; struct dccg_registers { @@ -199,7 +193,6 @@ struct dccg_registers { uint32_t PHYASYMCLK_CLOCK_CNTL; uint32_t PHYBSYMCLK_CLOCK_CNTL; uint32_t PHYCSYMCLK_CLOCK_CNTL; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint32_t PHYDSYMCLK_CLOCK_CNTL; uint32_t PHYESYMCLK_CLOCK_CNTL; uint32_t DTBCLK_DTO_MODULO[MAX_PIPES]; @@ -212,7 +205,6 @@ struct dccg_registers { uint32_t SYMCLK32_SE_CNTL; uint32_t SYMCLK32_LE_CNTL; uint32_t DENTIST_DISPCLK_CNTL; -#endif }; struct dcn_dccg { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h index a4fc70fa0957..10af257d90ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h @@ -83,7 +83,6 @@ struct dcn20_hubbub { int num_vmid; struct dcn20_vmid vmid[16]; unsigned int detile_buf_size; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) unsigned int crb_size_segs; unsigned int compbuf_size_segments; unsigned int pixel_chunk_size; @@ -91,7 +90,6 @@ struct dcn20_hubbub { unsigned int det1_size; unsigned int det2_size; unsigned int det3_size; -#endif }; void hubbub2_construct(struct dcn20_hubbub *hubbub, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h index 2652d6abe9e3..eea2254b15e4 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.h @@ -216,32 +216,22 @@ type ROW_TTU_MODE; \ type NUM_PKRS -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 #define DCN31_HUBP_REG_FIELD_VARIABLE_LIST(type) \ DCN30_HUBP_REG_FIELD_VARIABLE_LIST(type);\ type HUBP_UNBOUNDED_REQ_MODE;\ type CURSOR_REQ_MODE;\ type HUBP_SOFT_RESET -#endif struct dcn_hubp2_registers { DCN30_HUBP_REG_COMMON_VARIABLE_LIST; }; struct dcn_hubp2_shift { -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCN31_HUBP_REG_FIELD_VARIABLE_LIST(uint8_t); -#else - DCN30_HUBP_REG_FIELD_VARIABLE_LIST(uint8_t); -#endif }; struct dcn_hubp2_mask { -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCN31_HUBP_REG_FIELD_VARIABLE_LIST(uint32_t); -#else - DCN30_HUBP_REG_FIELD_VARIABLE_LIST(uint32_t); -#endif }; struct dcn20_hubp { 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 d0d6a94e4992..5c2853654cca 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1270,9 +1270,7 @@ static void dcn20_detect_pipe_changes(struct pipe_ctx *old_pipe, struct pipe_ctx new_pipe->update_flags.bits.gamut_remap = 1; new_pipe->update_flags.bits.scaler = 1; new_pipe->update_flags.bits.viewport = 1; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) new_pipe->update_flags.bits.det_size = 1; -#endif if (!new_pipe->top_pipe && !new_pipe->prev_odm_pipe) { new_pipe->update_flags.bits.odm = 1; new_pipe->update_flags.bits.global_sync = 1; @@ -1307,10 +1305,9 @@ static void dcn20_detect_pipe_changes(struct pipe_ctx *old_pipe, struct pipe_ctx new_pipe->update_flags.bits.global_sync = 1; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) if (old_pipe->det_buffer_size_kb != new_pipe->det_buffer_size_kb) new_pipe->update_flags.bits.det_size = 1; -#endif + /* * Detect opp / tg change, only set on change, not on enable * Assume mpcc inst = pipe index, if not this code needs to be updated @@ -1426,10 +1423,9 @@ static void dcn20_update_dchubp_dpp( &pipe_ctx->ttu_regs, &pipe_ctx->rq_regs, &pipe_ctx->pipe_dlg_param); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + if (hubp->funcs->set_unbounded_requesting) hubp->funcs->set_unbounded_requesting(hubp, pipe_ctx->unbounded_req); -#endif } if (pipe_ctx->update_flags.bits.hubp_interdependent) hubp->funcs->hubp_setup_interdependent( @@ -1609,11 +1605,9 @@ static void dcn20_program_pipe( dc->res_pool->hubbub->funcs->force_wm_propagate_to_pipes(dc->res_pool->hubbub); } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) if (dc->res_pool->hubbub->funcs->program_det_size && pipe_ctx->update_flags.bits.det_size) dc->res_pool->hubbub->funcs->program_det_size( dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->det_buffer_size_kb); -#endif if (pipe_ctx->update_flags.raw || pipe_ctx->plane_state->update_flags.raw || pipe_ctx->stream->update_flags.raw) dcn20_update_dchubp_dpp(dc, pipe_ctx, context); @@ -1705,12 +1699,10 @@ void dcn20_program_front_end_for_ctx( for (i = 0; i < dc->res_pool->pipe_count; i++) if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable || context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) { - #if defined(CONFIG_DRM_AMD_DC_DCN3_1) struct hubbub *hubbub = dc->res_pool->hubbub; if (hubbub->funcs->program_det_size && context->res_ctx.pipe_ctx[i].update_flags.bits.disable) hubbub->funcs->program_det_size(hubbub, dc->current_state->res_ctx.pipe_ctx[i].plane_res.hubp->inst, 0); - #endif hws->funcs.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]); DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx); } @@ -1828,11 +1820,9 @@ void dcn20_prepare_bandwidth( &context->bw_ctx.bw.dcn.watermarks, dc->res_pool->ref_clocks.dchub_ref_clock_inKhz / 1000, false); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) /* decrease compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, false); -#endif } void dcn20_optimize_bandwidth( @@ -1851,11 +1841,9 @@ void dcn20_optimize_bandwidth( dc->clk_mgr, context, true); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) /* increase compbuf size */ if (hubbub->funcs->program_compbuf_size) hubbub->funcs->program_compbuf_size(hubbub, context->bw_ctx.bw.dcn.compbuf_size_kb, true); -#endif } bool dcn20_update_bandwidth( @@ -2561,10 +2549,9 @@ void dcn20_fpga_init_hw(struct dc *dc) tg->funcs->tg_init(tg); } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + if (dc->res_pool->hubbub->funcs->init_crb) dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub); -#endif } #ifndef TRIM_FSFT bool dcn20_optimize_timing_for_fsft(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 1b670c5de1aa..1b05a37b674d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -3069,7 +3069,6 @@ static void dcn20_calculate_wm( 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; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) static bool is_dtbclk_required(struct dc *dc, struct dc_state *context) { int i; @@ -3079,7 +3078,6 @@ static bool is_dtbclk_required(struct dc *dc, struct dc_state *context) } return false; } -#endif void dcn20_calculate_dlg_params( struct dc *dc, struct dc_state *context, @@ -3088,9 +3086,7 @@ void dcn20_calculate_dlg_params( int vlevel) { int i, pipe_idx; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) int plane_count; -#endif /* Writeback MCIF_WB arbitration parameters */ dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt); @@ -3105,7 +3101,7 @@ void dcn20_calculate_dlg_params( context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != dm_dram_clock_change_unsupported; context->bw_ctx.bw.dcn.clk.dppclk_khz = 0; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + context->bw_ctx.bw.dcn.clk.z9_support = (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) ? DCN_Z9_SUPPORT_ALLOW : DCN_Z9_SUPPORT_DISALLOW; @@ -3119,7 +3115,6 @@ void dcn20_calculate_dlg_params( context->bw_ctx.bw.dcn.clk.z9_support = DCN_Z9_SUPPORT_ALLOW; context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context); -#endif if (context->bw_ctx.bw.dcn.clk.dispclk_khz < dc->debug.min_disp_clk_khz) context->bw_ctx.bw.dcn.clk.dispclk_khz = dc->debug.min_disp_clk_khz; @@ -3131,10 +3126,9 @@ void dcn20_calculate_dlg_params( pipes[pipe_idx].pipe.dest.vupdate_offset = get_vupdate_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); pipes[pipe_idx].pipe.dest.vupdate_width = get_vupdate_width(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); pipes[pipe_idx].pipe.dest.vready_offset = get_vready_offset(&context->bw_ctx.dml, pipes, pipe_cnt, pipe_idx); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) - context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes; - context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode; -#endif + context->res_ctx.pipe_ctx[i].det_buffer_size_kb = context->bw_ctx.dml.ip.det_buffer_size_kbytes; + context->res_ctx.pipe_ctx[i].unbounded_req = pipes[pipe_idx].pipe.src.unbounded_req_mode; + if (context->bw_ctx.bw.dcn.clk.dppclk_khz < pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000) context->bw_ctx.bw.dcn.clk.dppclk_khz = pipes[pipe_idx].clks_cfg.dppclk_mhz * 1000; context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz = @@ -3148,10 +3142,8 @@ void dcn20_calculate_dlg_params( context->bw_ctx.bw.dcn.clk.max_supported_dppclk_khz = context->bw_ctx.dml.soc.clock_limits[vlevel].dppclk_mhz * 1000; context->bw_ctx.bw.dcn.clk.max_supported_dispclk_khz = context->bw_ctx.dml.soc.clock_limits[vlevel].dispclk_mhz * 1000; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) context->bw_ctx.bw.dcn.compbuf_size_kb = context->bw_ctx.dml.ip.config_return_buffer_size_in_kbytes - context->bw_ctx.dml.ip.det_buffer_size_kbytes * pipe_idx; -#endif for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) { bool cstate_en = context->bw_ctx.dml.vba.PrefetchMode[vlevel][context->bw_ctx.dml.vba.maxMpcComb] != 2; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c index 4075ae111530..e6307397e0d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c @@ -552,6 +552,17 @@ void enc2_stream_encoder_dp_set_stream_attribute( DP_SST_SDP_SPLITTING, enable_sdp_splitting); } +uint32_t enc2_get_fifo_cal_average_level( + struct stream_encoder *enc) +{ + struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); + uint32_t fifo_level; + + REG_GET(DIG_FIFO_STATUS, + DIG_FIFO_CAL_AVERAGE_LEVEL, &fifo_level); + return fifo_level; +} + static const struct stream_encoder_funcs dcn20_str_enc_funcs = { .dp_set_odm_combine = enc2_dp_set_odm_combine, @@ -598,6 +609,7 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = { .dp_set_dsc_pps_info_packet = enc2_dp_set_dsc_pps_info_packet, .set_dynamic_metadata = enc2_set_dynamic_metadata, .hdmi_reset_stream_attribute = enc1_reset_hdmi_stream_attribute, + .get_fifo_cal_average_level = enc2_get_fifo_cal_average_level, }; void dcn20_stream_encoder_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h index 9a881e639709..f3d1a0237bda 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.h @@ -112,4 +112,7 @@ void enc2_set_dynamic_metadata(struct stream_encoder *enc, uint32_t hubp_requestor_id, enum dynamic_metadata_mode dmdata_mode); +uint32_t enc2_get_fifo_cal_average_level( + struct stream_encoder *enc); + #endif /* __DC_STREAM_ENCODER_DCN20_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c index 72bee637c1e4..8487516819ef 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.c @@ -823,6 +823,8 @@ static const struct stream_encoder_funcs dcn30_str_enc_funcs = { .dp_set_dsc_pps_info_packet = enc3_dp_set_dsc_pps_info_packet, .set_dynamic_metadata = enc2_set_dynamic_metadata, .hdmi_reset_stream_attribute = enc1_reset_hdmi_stream_attribute, + + .get_fifo_cal_average_level = enc2_get_fifo_cal_average_level, }; void dcn30_dio_stream_encoder_construct( diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.h index 9566b9037458..e2c264ecb20f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dio_stream_encoder.h @@ -106,6 +106,7 @@ SRI(DP_SEC_METADATA_TRANSMISSION, DP, id), \ SRI(HDMI_METADATA_PACKET_CONTROL, DIG, id), \ SRI(DIG_FE_CNTL, DIG, id), \ + SRI(DIG_FIFO_STATUS, DIG, id), \ SRI(DIG_CLOCK_PATTERN, DIG, id) @@ -167,6 +168,17 @@ SE_SF(DIG0_DIG_FE_CNTL, TMDS_COLOR_FORMAT, mask_sh),\ SE_SF(DIG0_DIG_FE_CNTL, DIG_STEREOSYNC_SELECT, mask_sh),\ SE_SF(DIG0_DIG_FE_CNTL, DIG_STEREOSYNC_GATE_EN, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_LEVEL_ERROR, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_USE_OVERWRITE_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_OVERWRITE_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_ERROR_ACK, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_CAL_AVERAGE_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_MAXIMUM_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_MINIMUM_LEVEL, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_READ_CLOCK_SRC, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_CALIBRATED, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_FORCE_RECAL_AVERAGE, mask_sh),\ + SE_SF(DIG0_DIG_FIFO_STATUS, DIG_FIFO_FORCE_RECOMP_MINMAX, mask_sh),\ SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP4_ENABLE, mask_sh),\ SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP5_ENABLE, mask_sh),\ SE_SF(DP0_DP_SEC_CNTL, DP_SEC_GSP6_ENABLE, mask_sh),\ 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 ef5d0b778a72..c68e3a708a33 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -48,6 +48,8 @@ #include "dc_dmub_srv.h" #include "link_hwss.h" #include "dpcd_defs.h" +#include "inc/dc_link_dp.h" +#include "inc/link_dpcd.h" @@ -529,6 +531,8 @@ void dcn30_init_hw(struct dc *dc) for (i = 0; i < dc->link_count; i++) { if (dc->links[i]->connector_signal != SIGNAL_TYPE_DISPLAY_PORT) continue; + /* DP 2.0 states that LTTPR regs must be read first */ + dp_retrieve_lttpr_cap(dc->links[i]); /* if any of the displays are lit up turn them off */ status = core_link_read_dpcd(dc->links[i], DP_SET_POWER, @@ -651,10 +655,8 @@ void dcn30_init_hw(struct dc *dc) if (dc->res_pool->hubbub->funcs->force_pstate_change_control) dc->res_pool->hubbub->funcs->force_pstate_change_control( dc->res_pool->hubbub, false, false); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) if (dc->res_pool->hubbub->funcs->init_crb) dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub); -#endif } 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 b16d19a25d88..16a75ba0ca82 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c @@ -164,8 +164,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_02_soc = { .min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */ .num_states = 1, - .sr_exit_time_us = 15.5, - .sr_enter_plus_exit_time_us = 20, + .sr_exit_time_us = 26.5, + .sr_enter_plus_exit_time_us = 31, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, @@ -1102,6 +1102,26 @@ static bool init_soc_bounding_box(struct dc *dc, struct resource_pool *pool) loaded_ip->max_num_dpp = pool->pipe_count; loaded_ip->clamp_min_dcfclk = dc->config.clamp_min_dcfclk; dcn20_patch_bounding_box(dc, loaded_bb); + + if (dc->ctx->dc_bios->funcs->get_soc_bb_info) { + struct bp_soc_bb_info bb_info = { 0 }; + + if (dc->ctx->dc_bios->funcs->get_soc_bb_info( + dc->ctx->dc_bios, &bb_info) == BP_RESULT_OK) { + if (bb_info.dram_clock_change_latency_100ns > 0) + dcn3_02_soc.dram_clock_change_latency_us = + bb_info.dram_clock_change_latency_100ns * 10; + + if (bb_info.dram_sr_enter_exit_latency_100ns > 0) + dcn3_02_soc.sr_enter_plus_exit_time_us = + bb_info.dram_sr_enter_exit_latency_100ns * 10; + + if (bb_info.dram_sr_exit_latency_100ns > 0) + dcn3_02_soc.sr_exit_time_us = + bb_info.dram_sr_exit_latency_100ns * 10; + } + } + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.c index dc33ec8b7bdb..b48b732aa647 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.c @@ -38,3 +38,8 @@ void dcn303_dsc_pg_control(struct dce_hwseq *hws, unsigned int dsc_inst, bool po { /*DCN303 removes PG registers*/ } + +void dcn303_enable_power_gating_plane(struct dce_hwseq *hws, bool enable) +{ + /*DCN303 removes PG registers*/ +} diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.h index fc6cab720b6d..8b69a3b76c11 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.h +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_hwseq.h @@ -13,5 +13,6 @@ void dcn303_dpp_pg_control(struct dce_hwseq *hws, unsigned int dpp_inst, bool power_on); void dcn303_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on); void dcn303_dsc_pg_control(struct dce_hwseq *hws, unsigned int dsc_inst, bool power_on); +void dcn303_enable_power_gating_plane(struct dce_hwseq *hws, bool enable); #endif /* __DC_HWSS_DCN303_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_init.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_init.c index 86d4b303d02f..aa5dbbade2bd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_init.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_init.c @@ -16,4 +16,5 @@ void dcn303_hw_sequencer_construct(struct dc *dc) dc->hwseq->funcs.dpp_pg_control = dcn303_dpp_pg_control; dc->hwseq->funcs.hubp_pg_control = dcn303_hubp_pg_control; dc->hwseq->funcs.dsc_pg_control = dcn303_dsc_pg_control; + dc->hwseq->funcs.enable_power_gating_plane = dcn303_enable_power_gating_plane; } 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 758f89ba0192..34b89464ae02 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c @@ -146,8 +146,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_03_soc = { .min_dcfclk = 500.0, /* TODO: set this to actual min DCFCLK */ .num_states = 1, - .sr_exit_time_us = 15.5, - .sr_enter_plus_exit_time_us = 20, + .sr_exit_time_us = 26.5, + .sr_enter_plus_exit_time_us = 31, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, @@ -1028,6 +1028,26 @@ static bool init_soc_bounding_box(struct dc *dc, struct resource_pool *pool) loaded_ip->max_num_dpp = pool->pipe_count; loaded_ip->clamp_min_dcfclk = dc->config.clamp_min_dcfclk; dcn20_patch_bounding_box(dc, loaded_bb); + + if (dc->ctx->dc_bios->funcs->get_soc_bb_info) { + struct bp_soc_bb_info bb_info = { 0 }; + + if (dc->ctx->dc_bios->funcs->get_soc_bb_info( + dc->ctx->dc_bios, &bb_info) == BP_RESULT_OK) { + if (bb_info.dram_clock_change_latency_100ns > 0) + dcn3_03_soc.dram_clock_change_latency_us = + bb_info.dram_clock_change_latency_100ns * 10; + + if (bb_info.dram_sr_enter_exit_latency_100ns > 0) + dcn3_03_soc.sr_enter_plus_exit_time_us = + bb_info.dram_sr_enter_exit_latency_100ns * 10; + + if (bb_info.dram_sr_exit_latency_100ns > 0) + dcn3_03_soc.sr_exit_time_us = + bb_info.dram_sr_exit_latency_100ns * 10; + } + } + return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/Makefile b/drivers/gpu/drm/amd/display/dc/dcn31/Makefile index 5dcdc5a858fe..4bab97acb155 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn31/Makefile @@ -28,6 +28,7 @@ endif CFLAGS_$(AMDDALPATH)/dc/dcn31/dcn31_resource.o += -mhard-float endif +ifdef CONFIG_X86 ifdef IS_OLD_GCC # Stack alignment mismatch, proceed with caution. # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 @@ -36,6 +37,7 @@ CFLAGS_$(AMDDALPATH)/dc/dcn31/dcn31_resource.o += -mpreferred-stack-boundary=4 else CFLAGS_$(AMDDALPATH)/dc/dcn31/dcn31_resource.o += -msse2 endif +endif AMD_DAL_DCN31 = $(addprefix $(AMDDALPATH)/dc/dcn31/,$(DCN31)) 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 c0e544d7556f..836864a5a5dc 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c @@ -33,7 +33,6 @@ #include "clk_mgr.h" #include "reg_helper.h" #include "abm.h" -#include "clk_mgr.h" #include "hubp.h" #include "dchubbub.h" #include "timing_generator.h" @@ -47,6 +46,7 @@ #include "dpcd_defs.h" #include "dce/dmub_outbox.h" #include "dc_link_dp.h" +#include "inc/link_dpcd.h" #define DC_LOGGER_INIT(logger) @@ -299,10 +299,8 @@ void dcn31_init_hw(struct dc *dc) if (dc->res_pool->hubbub->funcs->force_pstate_change_control) dc->res_pool->hubbub->funcs->force_pstate_change_control( dc->res_pool->hubbub, false, false); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) if (dc->res_pool->hubbub->funcs->init_crb) dc->res_pool->hubbub->funcs->init_crb(dc->res_pool->hubbub); -#endif } void dcn31_dsc_pg_control( @@ -392,7 +390,7 @@ void dcn31_update_info_frame(struct pipe_ctx *pipe_ctx) is_hdmi_tmds = dc_is_hdmi_tmds_signal(pipe_ctx->stream->signal); is_dp = dc_is_dp_signal(pipe_ctx->stream->signal); - if (!is_hdmi_tmds) + if (!is_hdmi_tmds && !is_dp) return; if (is_hdmi_tmds) 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 0d6cb6caad81..c67bc9544f5d 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c @@ -934,7 +934,6 @@ static const struct dc_debug_options debug_defaults_drv = { .dmub_command_table = true, .pstate_enabled = true, .use_max_lb = true, - .pstate_enabled = true, .enable_mem_low_power = { .bits = { .vga = false, diff --git a/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h b/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h index 8381c8f9ddb7..a9170b9f84d3 100644 --- a/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h +++ b/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h @@ -32,11 +32,9 @@ struct cp_psp_stream_config { uint8_t otg_inst; uint8_t dig_be; uint8_t dig_fe; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint8_t link_enc_idx; uint8_t stream_enc_idx; uint8_t phy_idx; -#endif uint8_t assr_enabled; uint8_t mst_enabled; void *dm_stream_ctx; diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile index 11ab03abc0fe..45862167e6ce 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile @@ -50,6 +50,10 @@ dml_ccflags += -msse2 endif endif +ifneq ($(CONFIG_FRAME_WARN),0) +frame_warn_flag := -Wframe-larger-than=2048 +endif + CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) ifdef CONFIG_DRM_AMD_DC_DCN @@ -60,12 +64,10 @@ CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20v2.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn20/display_rq_dlg_calc_20v2.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_ccflags) CFLAGS_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_ccflags) -CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) -Wframe-larger-than=2048 +CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_ccflags) -ifdef CONFIG_DRM_AMD_DC_DCN3_1 -CFLAGS_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_ccflags) -Wframe-larger-than=2048 +CFLAGS_$(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 := $(dml_ccflags) -endif CFLAGS_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_ccflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_vba.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn20/display_mode_vba_20.o := $(dml_rcflags) @@ -76,10 +78,8 @@ CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_mode_vba_21.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn21/display_rq_dlg_calc_21.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_mode_vba_30.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn30/display_rq_dlg_calc_30.o := $(dml_rcflags) -ifdef CONFIG_DRM_AMD_DC_DCN3_1 CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_mode_vba_31.o := $(dml_rcflags) CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/dcn31/display_rq_dlg_calc_31.o := $(dml_rcflags) -endif CFLAGS_REMOVE_$(AMDDALPATH)/dc/dml/display_mode_lib.o := $(dml_rcflags) endif CFLAGS_$(AMDDALPATH)/dc/dml/dml1_display_rq_dlg_calc.o := $(dml_ccflags) @@ -94,10 +94,8 @@ DML += display_mode_vba.o dcn20/display_rq_dlg_calc_20.o dcn20/display_mode_vba_ 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/display_mode_vba_30.o dcn30/display_rq_dlg_calc_30.o -ifdef CONFIG_DRM_AMD_DC_DCN3_1 DML += dcn31/display_mode_vba_31.o dcn31/display_rq_dlg_calc_31.o endif -endif AMD_DAL_DML = $(addprefix $(AMDDALPATH)/dc/dml/,$(DML)) 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 d655655baaba..a9667068c690 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 @@ -23,7 +23,6 @@ * */ -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 #include "dc.h" #include "dc_link.h" #include "../display_mode_lib.h" @@ -2668,6 +2667,8 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman (double) v->WritebackDelay[v->VoltageLevel][k] / (v->HTotal[k] / v->PixelClock[k]), 1)); + if (v->MaxVStartupLines[k] > 1023) + v->MaxVStartupLines[k] = 1023; #ifdef __DML_VBA_DEBUG__ dml_print("DML::%s: k=%d MaxVStartupLines = %d\n", __func__, k, v->MaxVStartupLines[k]); @@ -3536,7 +3537,7 @@ static bool CalculateBytePerPixelAnd256BBlockSizes( *BytePerPixelDETC = 0; *BytePerPixelY = 4; *BytePerPixelC = 0; - } else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16) { + } else if (SourcePixelFormat == dm_444_16) { *BytePerPixelDETY = 2; *BytePerPixelDETC = 0; *BytePerPixelY = 2; @@ -5064,6 +5065,8 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l / (v->HTotal[k] / v->PixelClock[k]), 1.0)); + if (v->MaximumVStartup[i][j][k] > 1023) + v->MaximumVStartup[i][j][k] = 1023; v->MaxMaxVStartup[i][j] = dml_max(v->MaxMaxVStartup[i][j], v->MaximumVStartup[i][j][k]); } } @@ -5674,7 +5677,7 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l for (k = 0; k < v->NumberOfActivePlanes; k++) { if (v->ViewportWidth[k] > v->SurfaceWidthY[k] || v->ViewportHeight[k] > v->SurfaceHeightY[k]) { ViewportExceedsSurface = true; - if (v->SourcePixelFormat[k] != dm_444_64 && v->SourcePixelFormat[k] != dm_444_32 && v->SourcePixelFormat[k] != dm_444_16 + if (v->SourcePixelFormat[k] != dm_444_64 && v->SourcePixelFormat[k] != dm_444_32 && v->SourcePixelFormat[k] != dm_444_16 && v->SourcePixelFormat[k] != dm_444_8 && v->SourcePixelFormat[k] != dm_rgbe) { if (v->ViewportWidthChroma[k] > v->SurfaceWidthC[k] @@ -7505,4 +7508,3 @@ static bool UnboundedRequest(enum unbounded_requesting_policy UseUnboundedReques return (ret_val); } -#endif /* CONFIG_DRM_AMD_DC_DCN3_1 */ diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c index cb15525ddb49..3def093ef88e 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_rq_dlg_calc_31.c @@ -23,8 +23,6 @@ * */ -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 - #include "../display_mode_lib.h" #include "../display_mode_vba.h" #include "../dml_inline_defs.h" @@ -52,7 +50,7 @@ static bool CalculateBytePerPixelAnd256BBlockSizes( *BytePerPixelDETC = 0; *BytePerPixelY = 4; *BytePerPixelC = 0; - } else if (SourcePixelFormat == dm_444_16 || SourcePixelFormat == dm_444_16) { + } else if (SourcePixelFormat == dm_444_16) { *BytePerPixelDETY = 2; *BytePerPixelDETC = 0; *BytePerPixelY = 2; @@ -1724,4 +1722,3 @@ void dml31_rq_dlg_get_dlg_reg( dml_print("DML_DLG: Calculation for pipe[%d] end\n", pipe_idx); } -#endif 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 9bb3b00e8be1..8a5bd919aec8 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 @@ -33,11 +33,9 @@ #include "dcn21/display_rq_dlg_calc_21.h" #include "dcn30/display_mode_vba_30.h" #include "dcn30/display_rq_dlg_calc_30.h" -#include "dml_logger.h" -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 #include "dcn31/display_mode_vba_31.h" #include "dcn31/display_rq_dlg_calc_31.h" -#endif +#include "dml_logger.h" const struct dml_funcs dml20_funcs = { .validate = dml20_ModeSupportAndSystemConfigurationFull, @@ -66,14 +64,13 @@ const struct dml_funcs dml30_funcs = { .rq_dlg_get_dlg_reg = dml30_rq_dlg_get_dlg_reg, .rq_dlg_get_rq_reg = dml30_rq_dlg_get_rq_reg }; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + const struct dml_funcs dml31_funcs = { .validate = dml31_ModeSupportAndSystemConfigurationFull, .recalculate = dml31_recalculate, .rq_dlg_get_dlg_reg = dml31_rq_dlg_get_dlg_reg, .rq_dlg_get_rq_reg = dml31_rq_dlg_get_rq_reg }; -#endif void dml_init_instance(struct display_mode_lib *lib, const struct _vcs_dpi_soc_bounding_box_st *soc_bb, @@ -96,13 +93,11 @@ void dml_init_instance(struct display_mode_lib *lib, case DML_PROJECT_DCN30: lib->funcs = dml30_funcs; break; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case DML_PROJECT_DCN31: case DML_PROJECT_DCN31_FPGA: lib->funcs = dml31_funcs; break; -#endif default: 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 7b7f1500a91e..d42a0aeca6be 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 @@ -38,10 +38,8 @@ enum dml_project { DML_PROJECT_NAVI10v2, DML_PROJECT_DCN21, DML_PROJECT_DCN30, -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 DML_PROJECT_DCN31, DML_PROJECT_DCN31_FPGA, -#endif }; struct display_mode_lib; 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 bdd075576573..64daa0507393 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 @@ -74,10 +74,8 @@ struct _vcs_dpi_soc_bounding_box_st { unsigned int num_states; double sr_exit_time_us; double sr_enter_plus_exit_time_us; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 double sr_exit_z8_time_us; double sr_enter_plus_exit_z8_time_us; -#endif double urgent_latency_us; double urgent_latency_pixel_data_only_us; double urgent_latency_pixel_mixed_with_vm_data_us; @@ -213,14 +211,12 @@ struct _vcs_dpi_ip_params_st { unsigned int is_line_buffer_bpp_fixed; unsigned int line_buffer_fixed_bpp; unsigned int dcc_supported; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 unsigned int config_return_buffer_size_in_kbytes; unsigned int compressed_buffer_segment_size_in_kbytes; unsigned int meta_fifo_size_in_kentries; unsigned int zero_size_buffer_entries; unsigned int compbuf_reserved_space_64b; unsigned int compbuf_reserved_space_zs; -#endif unsigned int IsLineBufferBppFixed; unsigned int LineBufferFixedBpp; 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 345d2d409a6e..d3b1b6d4ce2f 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 @@ -89,12 +89,10 @@ dml_get_attr_func(wm_memory_trip, mode_lib->vba.UrgentLatency); dml_get_attr_func(wm_writeback_urgent, mode_lib->vba.WritebackUrgentWatermark); dml_get_attr_func(wm_stutter_exit, mode_lib->vba.StutterExitWatermark); dml_get_attr_func(wm_stutter_enter_exit, mode_lib->vba.StutterEnterPlusExitWatermark); -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 dml_get_attr_func(wm_z8_stutter_exit, mode_lib->vba.Z8StutterExitWatermark); dml_get_attr_func(wm_z8_stutter_enter_exit, mode_lib->vba.Z8StutterEnterPlusExitWatermark); dml_get_attr_func(stutter_efficiency_z8, mode_lib->vba.Z8StutterEfficiency); dml_get_attr_func(stutter_num_bursts_z8, mode_lib->vba.Z8NumberOfStutterBurstsPerFrame); -#endif dml_get_attr_func(wm_dram_clock_change, mode_lib->vba.DRAMClockChangeWatermark); dml_get_attr_func(wm_writeback_dram_clock_change, mode_lib->vba.WritebackDRAMClockChangeWatermark); dml_get_attr_func(stutter_efficiency, mode_lib->vba.StutterEfficiency); @@ -159,15 +157,12 @@ dml_get_pipe_attr_func(refcyc_per_meta_chunk_vblank_l_in_us, mode_lib->vba.TimeP dml_get_pipe_attr_func(refcyc_per_meta_chunk_vblank_c_in_us, mode_lib->vba.TimePerChromaMetaChunkVBlank); dml_get_pipe_attr_func(refcyc_per_meta_chunk_flip_l_in_us, mode_lib->vba.TimePerMetaChunkFlip); dml_get_pipe_attr_func(refcyc_per_meta_chunk_flip_c_in_us, mode_lib->vba.TimePerChromaMetaChunkFlip); - dml_get_pipe_attr_func(vstartup, mode_lib->vba.VStartup); dml_get_pipe_attr_func(vupdate_offset, mode_lib->vba.VUpdateOffsetPix); dml_get_pipe_attr_func(vupdate_width, mode_lib->vba.VUpdateWidthPix); dml_get_pipe_attr_func(vready_offset, mode_lib->vba.VReadyOffsetPix); -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 dml_get_pipe_attr_func(vready_at_or_after_vsync, mode_lib->vba.VREADY_AT_OR_AFTER_VSYNC); dml_get_pipe_attr_func(min_dst_y_next_start, mode_lib->vba.MIN_DST_Y_NEXT_START); -#endif double get_total_immediate_flip_bytes( struct display_mode_lib *mode_lib, @@ -236,7 +231,6 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib) mode_lib->vba.WritebackLatency = soc->writeback_latency_us; mode_lib->vba.SRExitTime = soc->sr_exit_time_us; mode_lib->vba.SREnterPlusExitTime = soc->sr_enter_plus_exit_time_us; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 mode_lib->vba.PercentOfIdealFabricAndSDPPortBWReceivedAfterUrgLatency = soc->pct_ideal_sdp_bw_after_urgent; mode_lib->vba.PercentOfIdealDRAMBWReceivedAfterUrgLatencyPixelMixedWithVMData = soc->pct_ideal_dram_sdp_bw_after_urgent_pixel_and_vm; mode_lib->vba.PercentOfIdealDRAMBWReceivedAfterUrgLatencyPixelDataOnly = soc->pct_ideal_dram_sdp_bw_after_urgent_pixel_only; @@ -245,7 +239,6 @@ static void fetch_socbb_params(struct display_mode_lib *mode_lib) soc->max_avg_sdp_bw_use_normal_percent; mode_lib->vba.SRExitZ8Time = soc->sr_exit_z8_time_us; mode_lib->vba.SREnterPlusExitZ8Time = soc->sr_enter_plus_exit_z8_time_us; -#endif mode_lib->vba.DRAMClockChangeLatency = soc->dram_clock_change_latency_us; mode_lib->vba.DummyPStateCheck = soc->dram_clock_change_latency_us == soc->dummy_pstate_latency_us; mode_lib->vba.DRAMClockChangeSupportsVActive = !soc->disable_dram_clock_change_vactive_support || @@ -320,7 +313,6 @@ static void fetch_ip_params(struct display_mode_lib *mode_lib) mode_lib->vba.MaxPSCLToLBThroughput = ip->max_pscl_lb_bw_pix_per_clk; mode_lib->vba.ROBBufferSizeInKByte = ip->rob_buffer_size_kbytes; mode_lib->vba.DETBufferSizeInKByte[0] = ip->det_buffer_size_kbytes; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 mode_lib->vba.ConfigReturnBufferSizeInKByte = ip->config_return_buffer_size_in_kbytes; mode_lib->vba.CompressedBufferSegmentSizeInkByte = ip->compressed_buffer_segment_size_in_kbytes; mode_lib->vba.MetaFIFOSizeInKEntries = ip->meta_fifo_size_in_kentries; @@ -329,7 +321,6 @@ static void fetch_ip_params(struct display_mode_lib *mode_lib) mode_lib->vba.COMPBUF_RESERVED_SPACE_ZS = ip->compbuf_reserved_space_zs; mode_lib->vba.MaximumDSCBitsPerComponent = ip->maximum_dsc_bits_per_component; mode_lib->vba.DSC422NativeSupport = ip->dsc422_native_support; -#endif mode_lib->vba.PixelChunkSizeInKByte = ip->pixel_chunk_size_kbytes; mode_lib->vba.MetaChunkSize = ip->meta_chunk_size_kbytes; @@ -419,7 +410,6 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) visited[j] = true; mode_lib->vba.pipe_plane[j] = mode_lib->vba.NumberOfActivePlanes; - mode_lib->vba.DPPPerPlane[mode_lib->vba.NumberOfActivePlanes] = 1; mode_lib->vba.SourceScan[mode_lib->vba.NumberOfActivePlanes] = (enum scan_direction_class) (src->source_scan); @@ -459,11 +449,9 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) mode_lib->vba.VTAPsChroma[mode_lib->vba.NumberOfActivePlanes] = taps->vtaps_c; mode_lib->vba.HTotal[mode_lib->vba.NumberOfActivePlanes] = dst->htotal; mode_lib->vba.VTotal[mode_lib->vba.NumberOfActivePlanes] = dst->vtotal; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 mode_lib->vba.VFrontPorch[mode_lib->vba.NumberOfActivePlanes] = dst->vfront_porch; 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; -#endif mode_lib->vba.DCCEnable[mode_lib->vba.NumberOfActivePlanes] = src->dcc_use_global ? ip->dcc_supported : src->dcc && ip->dcc_supported; @@ -710,13 +698,11 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib) } } -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 mode_lib->vba.UseUnboundedRequesting = dm_unbounded_requesting; for (k = 0; k < mode_lib->vba.cache_num_pipes; ++k) { if (pipes[k].pipe.src.unbounded_req_mode == 0) mode_lib->vba.UseUnboundedRequesting = dm_unbounded_requesting_disable; } -#endif // TODO: ODMCombineEnabled => 2 * DPPPerPlane...actually maybe not since all pipes are specified // Do we want the dscclk to automatically be halved? Guess not since the value is specified mode_lib->vba.SynchronizedVBlank = pipes[0].pipe.dest.synchronized_vblank_all_planes; 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 fad7bb57e668..d18a021d4d32 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 @@ -39,12 +39,10 @@ dml_get_attr_decl(wm_memory_trip); dml_get_attr_decl(wm_writeback_urgent); dml_get_attr_decl(wm_stutter_exit); dml_get_attr_decl(wm_stutter_enter_exit); -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 dml_get_attr_decl(wm_z8_stutter_exit); dml_get_attr_decl(wm_z8_stutter_enter_exit); dml_get_attr_decl(stutter_efficiency_z8); dml_get_attr_decl(stutter_num_bursts_z8); -#endif dml_get_attr_decl(wm_dram_clock_change); dml_get_attr_decl(wm_writeback_dram_clock_change); dml_get_attr_decl(stutter_efficiency_no_vblank); @@ -108,10 +106,8 @@ dml_get_pipe_attr_decl(vstartup); dml_get_pipe_attr_decl(vupdate_offset); dml_get_pipe_attr_decl(vupdate_width); dml_get_pipe_attr_decl(vready_offset); -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 dml_get_pipe_attr_decl(vready_at_or_after_vsync); dml_get_pipe_attr_decl(min_dst_y_next_start); -#endif double get_total_immediate_flip_bytes( struct display_mode_lib *mode_lib, @@ -933,7 +929,6 @@ struct vba_vars_st { bool ClampMinDCFCLK; bool AllowDramClockChangeOneDisplayVactive; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 double MaxAveragePercentOfIdealFabricAndSDPPortBWDisplayCanUseInNormalSystemOperation; double PercentOfIdealFabricAndSDPPortBWReceivedAfterUrgLatency; double PercentOfIdealDRAMBWReceivedAfterUrgLatencyPixelMixedWithVMData; @@ -974,7 +969,6 @@ struct vba_vars_st { int Z8NumberOfStutterBurstsPerFrame; unsigned int MaximumDSCBitsPerComponent; unsigned int NotEnoughUrgentLatencyHidingA[DC__VOLTAGE_STATES][2]; -#endif }; bool CalculateMinAndMaxPrefetchMode( diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c index fbf71ff0a402..c5c840a06050 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c @@ -112,9 +112,7 @@ bool dal_hw_factory_init( case DCN_VERSION_3_01: case DCN_VERSION_3_02: case DCN_VERSION_3_03: -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case DCN_VERSION_3_1: -#endif dal_hw_factory_dcn30_init(factory); return true; #endif diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c index 89794687f6a0..4a9848308766 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c @@ -107,9 +107,7 @@ bool dal_hw_translate_init( case DCN_VERSION_3_01: case DCN_VERSION_3_02: case DCN_VERSION_3_03: -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case DCN_VERSION_3_1: -#endif dal_hw_translate_dcn30_init(translate); return true; #endif diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c index 51855a2624cf..4233955e3c47 100644 --- a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c +++ b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c @@ -33,6 +33,7 @@ #include "core_types.h" #include "dc_link_ddc.h" #include "link_hwss.h" +#include "inc/link_dpcd.h" #define DC_LOGGER \ link->ctx->logger 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 0d1c3260b68e..45a6216dfa2a 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -338,9 +338,7 @@ union pipe_update_flags { uint32_t scaler : 1; uint32_t viewport : 1; uint32_t plane_changed : 1; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint32_t det_size : 1; -#endif } bits; uint32_t raw; }; @@ -368,11 +366,9 @@ struct pipe_ctx { struct _vcs_dpi_display_ttu_regs_st ttu_regs; struct _vcs_dpi_display_rq_regs_st rq_regs; struct _vcs_dpi_display_pipe_dest_params_st pipe_dlg_param; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) int det_buffer_size_kb; bool unbounded_req; #endif -#endif union pipe_update_flags update_flags; struct dwbc *dwbc; struct mcif_wb *mcif_wb; @@ -422,9 +418,7 @@ struct dcn_bw_output { struct dc_clocks clk; struct dcn_watermark_set watermarks; struct dcn_bw_writeback bw_writeback; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) int compbuf_size_kb; -#endif }; 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 883c3af51022..e2b58ec9912d 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 @@ -42,7 +42,15 @@ enum { /* to avoid infinite loop where-in the receiver * switches between different VS */ - LINK_TRAINING_MAX_CR_RETRY = 100 + LINK_TRAINING_MAX_CR_RETRY = 100, + /* + * Some receivers fail to train on first try and are good + * on subsequent tries. 2 retries should be plenty. If we + * don't have a successful training then we don't expect to + * ever get one. + */ + LINK_TRAINING_MAX_VERIFY_RETRY = 2, + PEAK_FACTOR_X1000 = 1006, }; bool dp_verify_link_cap( @@ -182,4 +190,5 @@ enum dc_status dpcd_configure_lttpr_mode( struct link_training_settings *lt_settings); 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); #endif /* __DC_LINK_DP_H__ */ 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 90dbe26bf954..a17e5de3b100 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 @@ -91,9 +91,7 @@ struct clk_limit_table_entry { unsigned int dispclk_mhz; unsigned int dppclk_mhz; unsigned int phyclk_mhz; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 unsigned int wck_ratio; -#endif }; /* This table is contiguous */ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h index fc11f8e1ab59..0afa2364a986 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h @@ -29,7 +29,6 @@ #include "dc_types.h" #include "hw_shared.h" -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) enum phyd32clk_clock_source { PHYD32CLKA, PHYD32CLKB, @@ -55,18 +54,15 @@ enum dentist_dispclk_change_mode { DISPCLK_CHANGE_MODE_IMMEDIATE, DISPCLK_CHANGE_MODE_RAMPING, }; -#endif struct dccg { struct dc_context *ctx; const struct dccg_funcs *funcs; int pipe_dppclk_khz[MAX_PIPES]; int ref_dppclk; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) int dtbclk_khz[MAX_PIPES]; int audio_dtbclk_khz; int ref_dtbclk_khz; -#endif }; struct dccg_funcs { @@ -83,7 +79,6 @@ struct dccg_funcs { void (*otg_drop_pixel)(struct dccg *dccg, uint32_t otg_inst); void (*dccg_init)(struct dccg *dccg); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) void (*set_physymclk)( struct dccg *dccg, @@ -105,7 +100,6 @@ struct dccg_funcs { void (*set_dispclk_change_mode)( struct dccg *dccg, enum dentist_dispclk_change_mode change_mode); -#endif }; #endif //__DAL_DCCG_H__ diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h index d2611b865695..0638b337f143 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h @@ -152,11 +152,9 @@ struct hubbub_funcs { void (*force_pstate_change_control)(struct hubbub *hubbub, bool force, bool allow); void (*init_watermarks)(struct hubbub *hubbub); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) void (*program_det_size)(struct hubbub *hubbub, int hubp_inst, unsigned det_buffer_size_in_kbyte); void (*program_compbuf_size)(struct hubbub *hubbub, unsigned compbuf_size_kb, bool safe_to_increase); void (*init_crb)(struct hubbub *hubbub); -#endif }; struct hubbub { diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h index f643fe3ed064..9eaf345aa2a1 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h @@ -127,13 +127,11 @@ struct link_enc_state { }; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) - enum encoder_type_select { - ENCODER_TYPE_DIG = 0, - ENCODER_TYPE_HDMI_FRL = 1, - ENCODER_TYPE_DP_128B132B = 2 - }; -#endif +enum encoder_type_select { + ENCODER_TYPE_DIG = 0, + ENCODER_TYPE_HDMI_FRL = 1, + ENCODER_TYPE_DP_128B132B = 2 +}; struct link_encoder_funcs { void (*read_state)( @@ -193,12 +191,10 @@ struct link_encoder_funcs { enum signal_type (*get_dig_mode)( struct link_encoder *enc); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) void (*set_dio_phy_mux)( struct link_encoder *enc, enum encoder_type_select sel, uint32_t hpo_inst); -#endif }; /* diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h index dd562dcd03b2..8798cfa11a4d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h @@ -33,10 +33,8 @@ struct dchub_init_data; struct cstate_pstate_watermarks_st { uint32_t cstate_exit_ns; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 uint32_t cstate_exit_z8_ns; uint32_t cstate_enter_plus_exit_z8_ns; -#endif uint32_t cstate_enter_plus_exit_ns; uint32_t pstate_change_ns; }; diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h index 47c7e4c3a51b..564ea6a727b0 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h @@ -237,6 +237,9 @@ struct stream_encoder_funcs { void (*dp_set_odm_combine)( struct stream_encoder *enc, bool odm_combine); + + uint32_t (*get_fifo_cal_average_level)( + struct stream_encoder *enc); }; #endif /* STREAM_ENCODER_H_ */ 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 8f06e273e703..03f47f23fb65 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 @@ -173,9 +173,7 @@ struct timing_generator_funcs { bool (*enable_crtc)(struct timing_generator *tg); bool (*disable_crtc)(struct timing_generator *tg); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) bool (*immediate_disable_crtc)(struct timing_generator *tg); -#endif bool (*is_counter_moving)(struct timing_generator *tg); void (*get_position)(struct timing_generator *tg, struct crtc_position *position); 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 e3ab4e43f673..5ab008e62b82 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h @@ -236,9 +236,7 @@ struct hw_sequencer_funcs { const struct tg_color *solid_color, int width, int height, int offset); -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) void (*z10_restore)(struct dc *dc); -#endif void (*update_visual_confirm_color)(struct dc *dc, struct pipe_ctx *pipe_ctx, diff --git a/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h b/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h new file mode 100644 index 000000000000..d4d52ef1b165 --- /dev/null +++ b/drivers/gpu/drm/amd/display/dc/inc/link_dpcd.h @@ -0,0 +1,18 @@ +#ifndef __LINK_DPCD_H__ +#define __LINK_DPCD_H__ +#include <inc/core_status.h> +#include <dc_link.h> +#include <inc/link_hwss.h> + +enum dc_status core_link_read_dpcd( + struct dc_link *link, + uint32_t address, + uint8_t *data, + uint32_t size); + +enum dc_status core_link_write_dpcd( + struct dc_link *link, + uint32_t address, + const uint8_t *data, + uint32_t size); +#endif 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 33590a728fc5..fc1d289bb9fe 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h +++ b/drivers/gpu/drm/amd/display/dc/inc/link_hwss.h @@ -26,20 +26,6 @@ #ifndef __DC_LINK_HWSS_H__ #define __DC_LINK_HWSS_H__ -#include "inc/core_status.h" - -enum dc_status core_link_read_dpcd( - struct dc_link *link, - uint32_t address, - uint8_t *data, - uint32_t size); - -enum dc_status core_link_write_dpcd( - struct dc_link *link, - uint32_t address, - const uint8_t *data, - uint32_t size); - struct gpio *get_hpd_gpio(struct dc_bios *dcb, struct graphics_object_id link_id, struct gpio_service *gpio_service); diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile index ea4943c5d552..0d09181227c5 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/Makefile +++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile @@ -117,9 +117,7 @@ IRQ_DCN3_03 = irq_service_dcn303.o AMD_DAL_IRQ_DCN3_03 = $(addprefix $(AMDDALPATH)/dc/irq/dcn303/,$(IRQ_DCN3_03)) AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCN3_03) -endif -ifdef CONFIG_DRM_AMD_DC_DCN3_1 ############################################################################### # DCN 31 ############################################################################### diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn31/irq_service_dcn31.h b/drivers/gpu/drm/amd/display/dc/irq/dcn31/irq_service_dcn31.h index d6c845f6bfbf..67efbfe9b7aa 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn31/irq_service_dcn31.h +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn31/irq_service_dcn31.h @@ -23,8 +23,6 @@ * */ -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) - #ifndef __DAL_IRQ_SERVICE_DCN31_H__ #define __DAL_IRQ_SERVICE_DCN31_H__ @@ -34,4 +32,3 @@ struct irq_service *dal_irq_service_dcn31_create( struct irq_service_init_data *init_data); #endif /* __DAL_IRQ_SERVICE_DCN31_H__ */ -#endif /* CONFIG_DRM_AMD_DC_DCN3_1 */ diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c index 5f245bde54ff..a2a4fbeb83f8 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c +++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c @@ -119,7 +119,7 @@ bool dal_irq_service_set( dal_irq_service_ack(irq_service, source); - if (info->funcs->set) + if (info->funcs && info->funcs->set) return info->funcs->set(irq_service, info, enable); dal_irq_service_set_generic(irq_service, info, enable); @@ -153,7 +153,7 @@ bool dal_irq_service_ack( return false; } - if (info->funcs->ack) + if (info->funcs && info->funcs->ack) return info->funcs->ack(irq_service, info); dal_irq_service_ack_generic(irq_service, info); diff --git a/drivers/gpu/drm/amd/display/dc/irq_types.h b/drivers/gpu/drm/amd/display/dc/irq_types.h index 5f9346622301..1139b9eb9f6f 100644 --- a/drivers/gpu/drm/amd/display/dc/irq_types.h +++ b/drivers/gpu/drm/amd/display/dc/irq_types.h @@ -165,7 +165,7 @@ enum irq_type }; #define DAL_VALID_IRQ_SRC_NUM(src) \ - ((src) <= DAL_IRQ_SOURCES_NUMBER && (src) > DC_IRQ_SOURCE_INVALID) + ((src) < DAL_IRQ_SOURCES_NUMBER && (src) > DC_IRQ_SOURCE_INVALID) /* Number of Page Flip IRQ Sources. */ #define DAL_PFLIP_IRQ_SRC_NUM \ diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index 7634e8d94543..abbf7ae584c9 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -73,9 +73,7 @@ extern "C" { /* Forward declarations */ struct dmub_srv; struct dmub_srv_common_regs; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 struct dmub_srv_dcn31_regs; -#endif struct dmcub_trace_buf_entry; @@ -97,9 +95,7 @@ enum dmub_asic { DMUB_ASIC_DCN301, DMUB_ASIC_DCN302, DMUB_ASIC_DCN303, -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 DMUB_ASIC_DCN31, -#endif DMUB_ASIC_MAX, }; @@ -238,9 +234,32 @@ struct dmub_srv_hw_params { uint32_t psp_version; bool load_inst_const; bool skip_panel_power_sequence; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 bool disable_z10; -#endif +}; + +/** + * struct dmub_diagnostic_data - Diagnostic data retrieved from DMCUB for + * debugging purposes, including logging, crash analysis, etc. + */ +struct dmub_diagnostic_data { + uint32_t dmcub_version; + uint32_t scratch[16]; + uint32_t pc; + uint32_t undefined_address_fault_addr; + uint32_t inst_fetch_fault_addr; + uint32_t data_write_fault_addr; + uint32_t inbox1_rptr; + uint32_t inbox1_wptr; + uint32_t inbox1_size; + uint32_t inbox0_rptr; + uint32_t inbox0_wptr; + uint32_t inbox0_size; + uint8_t is_dmcub_enabled : 1; + uint8_t is_dmcub_soft_reset : 1; + uint8_t is_dmcub_secure_reset : 1; + uint8_t is_traceport_en : 1; + uint8_t is_cw0_enabled : 1; + uint8_t is_cw6_enabled : 1; }; /** @@ -335,6 +354,8 @@ struct dmub_srv_hw_funcs { void (*send_inbox0_cmd)(struct dmub_srv *dmub, union dmub_inbox0_data_register data); uint32_t (*get_current_time)(struct dmub_srv *dmub); + + void (*get_diagnostic_data)(struct dmub_srv *dmub, struct dmub_diagnostic_data *dmub_oca); }; /** @@ -373,9 +394,7 @@ struct dmub_srv { /* private: internal use only */ const struct dmub_srv_common_regs *regs; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 const struct dmub_srv_dcn31_regs *regs_dcn31; -#endif struct dmub_srv_base_funcs funcs; struct dmub_srv_hw_funcs hw_funcs; @@ -685,6 +704,8 @@ enum dmub_status dmub_srv_cmd_with_reply_data(struct dmub_srv *dmub, bool dmub_srv_get_outbox0_msg(struct dmub_srv *dmub, struct dmcub_trace_buf_entry *entry); +bool dmub_srv_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data); + #if defined(__cplusplus) } #endif 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 ff1f4ec1531e..7c4734f905d9 100644 --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h @@ -47,10 +47,10 @@ /* Firmware versioning. */ #ifdef DMUB_EXPOSE_VERSION -#define DMUB_FW_VERSION_GIT_HASH 0xefd666c1 +#define DMUB_FW_VERSION_GIT_HASH 0xf3da2b656 #define DMUB_FW_VERSION_MAJOR 0 #define DMUB_FW_VERSION_MINOR 0 -#define DMUB_FW_VERSION_REVISION 69 +#define DMUB_FW_VERSION_REVISION 71 #define DMUB_FW_VERSION_TEST 0 #define DMUB_FW_VERSION_VBIOS 0 #define DMUB_FW_VERSION_HOTFIX 0 @@ -309,6 +309,7 @@ struct dmcub_trace_buf_entry { * Current scratch register usage is as follows: * * SCRATCH0: FW Boot Status register + * SCRATCH5: LVTMA Status Register * SCRATCH15: FW Boot Options register */ @@ -335,6 +336,21 @@ enum dmub_fw_boot_status_bit { DMUB_FW_BOOT_STATUS_BIT_RESTORE_REQUIRED = (1 << 3), /**< 1 if driver should call restore */ }; +/* Register bit definition for SCRATCH5 */ +union dmub_lvtma_status { + struct { + uint32_t psp_ok : 1; + uint32_t edp_on : 1; + uint32_t reserved : 30; + } bits; + uint32_t all; +}; + +enum dmub_lvtma_status_bit { + DMUB_LVTMA_STATUS_BIT_PSP_OK = (1 << 0), + DMUB_LVTMA_STATUS_BIT_EDP_ON = (1 << 1), +}; + /** * union dmub_fw_boot_options - Boot option definitions for SCRATCH15 */ @@ -346,11 +362,7 @@ union dmub_fw_boot_options { uint32_t skip_phy_access : 1; /**< 1 if PHY access should be skipped */ uint32_t disable_clk_gate: 1; /**< 1 if clock gating should be disabled */ uint32_t skip_phy_init_panel_sequence: 1; /**< 1 to skip panel init seq */ -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 uint32_t z10_disable: 1; /**< 1 to disable z10 */ -#else - uint32_t reserved_unreleased: 1; /**< reserved for an unreleased feature */ -#endif uint32_t reserved : 25; /**< reserved */ } bits; /**< boot bits */ uint32_t all; /**< 32-bit access to bits */ @@ -615,7 +627,6 @@ enum dmub_cmd_type { * Command type used for OUTBOX1 notification enable */ DMUB_CMD__OUTBOX1_ENABLE = 71, -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 /** * Command type used for all idle optimization commands. */ @@ -628,7 +639,10 @@ enum dmub_cmd_type { * Command type used for all panel control commands. */ DMUB_CMD__PANEL_CNTL = 74, -#endif + /** + * Command type used for EDID CEA parsing + */ + DMUB_CMD__EDID_CEA = 79, /** * Command type used for all VBIOS interface commands. */ @@ -834,8 +848,6 @@ struct dmub_rb_cmd_mall { uint8_t reserved2; /**< Reserved bits */ }; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 - /** * enum dmub_cmd_idle_opt_type - Idle optimization command type. */ @@ -880,7 +892,7 @@ struct dmub_rb_cmd_clk_mgr_notify_clocks { struct dmub_cmd_header header; /**< header */ struct dmub_clocks clocks; /**< clock data */ }; -#endif + /** * struct dmub_cmd_digx_encoder_control_data - Encoder control data. */ @@ -2091,7 +2103,6 @@ struct dmub_rb_cmd_drr_update { struct dmub_optc_state dmub_optc_state_req; }; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 /** * enum dmub_cmd_panel_cntl_type - Panel control command. */ @@ -2126,7 +2137,6 @@ struct dmub_rb_cmd_panel_cntl { struct dmub_cmd_header header; /**< header */ struct dmub_cmd_panel_cntl_data data; /**< payload */ }; -#endif /** * Data passed from driver to FW in a DMUB_CMD__VBIOS_LVTMA_CONTROL command. @@ -2153,6 +2163,68 @@ struct dmub_rb_cmd_lvtma_control { }; /** + * Maximum number of bytes a chunk sent to DMUB for parsing + */ +#define DMUB_EDID_CEA_DATA_CHUNK_BYTES 8 + +/** + * Represent a chunk of CEA blocks sent to DMUB for parsing + */ +struct dmub_cmd_send_edid_cea { + uint16_t offset; /**< offset into the CEA block */ + uint8_t length; /**< number of bytes in payload to copy as part of CEA block */ + uint16_t total_length; /**< total length of the CEA block */ + uint8_t payload[DMUB_EDID_CEA_DATA_CHUNK_BYTES]; /**< data chunk of the CEA block */ + uint8_t pad[3]; /**< padding and for future expansion */ +}; + +/** + * Result of VSDB parsing from CEA block + */ +struct dmub_cmd_edid_cea_amd_vsdb { + uint8_t vsdb_found; /**< 1 if parsing has found valid AMD VSDB */ + uint8_t freesync_supported; /**< 1 if Freesync is supported */ + uint16_t amd_vsdb_version; /**< AMD VSDB version */ + uint16_t min_frame_rate; /**< Maximum frame rate */ + uint16_t max_frame_rate; /**< Minimum frame rate */ +}; + +/** + * Result of sending a CEA chunk + */ +struct dmub_cmd_edid_cea_ack { + uint16_t offset; /**< offset of the chunk into the CEA block */ + uint8_t success; /**< 1 if this sending of chunk succeeded */ + uint8_t pad; /**< padding and for future expansion */ +}; + +/** + * Specify whether the result is an ACK/NACK or the parsing has finished + */ +enum dmub_cmd_edid_cea_reply_type { + DMUB_CMD__EDID_CEA_AMD_VSDB = 1, /**< VSDB parsing has finished */ + DMUB_CMD__EDID_CEA_ACK = 2, /**< acknowledges the CEA sending is OK or failing */ +}; + +/** + * Definition of a DMUB_CMD__EDID_CEA command. + */ +struct dmub_rb_cmd_edid_cea { + struct dmub_cmd_header header; /**< Command header */ + union dmub_cmd_edid_cea_data { + struct dmub_cmd_send_edid_cea input; /**< input to send CEA chunks */ + struct dmub_cmd_edid_cea_output { /**< output with results */ + uint8_t type; /**< dmub_cmd_edid_cea_reply_type */ + union { + struct dmub_cmd_edid_cea_amd_vsdb amd_vsdb; + struct dmub_cmd_edid_cea_ack ack; + }; + } output; /**< output to retrieve ACK/NACK or VSDB parsing results */ + } data; /**< Command data */ + +}; + +/** * union dmub_rb_cmd - DMUB inbox command. */ union dmub_rb_cmd { @@ -2225,7 +2297,6 @@ union dmub_rb_cmd { * Definition of a DMUB_CMD__MALL command. */ struct dmub_rb_cmd_mall mall; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 /** * Definition of a DMUB_CMD__IDLE_OPT_DCN_RESTORE command. */ @@ -2240,7 +2311,6 @@ union dmub_rb_cmd { * Definition of DMUB_CMD__PANEL_CNTL commands. */ struct dmub_rb_cmd_panel_cntl panel_cntl; -#endif /** * Definition of a DMUB_CMD__ABM_SET_PIPE command. */ @@ -2290,6 +2360,10 @@ union dmub_rb_cmd { * Definition of a DMUB_CMD__VBIOS_LVTMA_CONTROL command. */ struct dmub_rb_cmd_lvtma_control lvtma_control; + /** + * Definition of a DMUB_CMD__EDID_CEA command. + */ + struct dmub_rb_cmd_edid_cea edid_cea; }; /** diff --git a/drivers/gpu/drm/amd/display/dmub/src/Makefile b/drivers/gpu/drm/amd/display/dmub/src/Makefile index 80b9fe225208..0495bcdd3463 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/Makefile +++ b/drivers/gpu/drm/amd/display/dmub/src/Makefile @@ -21,12 +21,8 @@ # DMUB = dmub_srv.o dmub_srv_stat.o dmub_reg.o dmub_dcn20.o dmub_dcn21.o -DMUB += dmub_dcn30.o dmub_dcn301.o -DMUB += dmub_dcn302.o -DMUB += dmub_dcn303.o -ifdef CONFIG_DRM_AMD_DC_DCN3_1 +DMUB += dmub_dcn30.o dmub_dcn301.o dmub_dcn302.o dmub_dcn303.o DMUB += dmub_dcn31.o -endif AMD_DAL_DMUB = $(addprefix $(AMDDALPATH)/dmub/src/,$(DMUB)) diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c index 8cdc1c75394e..a6540e27044d 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.c @@ -40,7 +40,10 @@ const struct dmub_srv_common_regs dmub_srv_dcn20_regs = { #define DMUB_SR(reg) REG_OFFSET(reg), - { DMUB_COMMON_REGS() }, + { + DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() + }, #undef DMUB_SR #define DMUB_SF(reg, field) FD_MASK(reg, field), @@ -404,3 +407,63 @@ uint32_t dmub_dcn20_get_current_time(struct dmub_srv *dmub) { return REG_READ(DMCUB_TIMER_CURRENT); } + +void dmub_dcn20_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data) +{ + uint32_t is_dmub_enabled, is_soft_reset, is_sec_reset; + uint32_t is_traceport_enabled, is_cw0_enabled, is_cw6_enabled; + + if (!dmub || !diag_data) + return; + + memset(diag_data, 0, sizeof(*diag_data)); + + diag_data->dmcub_version = dmub->fw_version; + + diag_data->scratch[0] = REG_READ(DMCUB_SCRATCH0); + diag_data->scratch[1] = REG_READ(DMCUB_SCRATCH1); + diag_data->scratch[2] = REG_READ(DMCUB_SCRATCH2); + diag_data->scratch[3] = REG_READ(DMCUB_SCRATCH3); + diag_data->scratch[4] = REG_READ(DMCUB_SCRATCH4); + diag_data->scratch[5] = REG_READ(DMCUB_SCRATCH5); + diag_data->scratch[6] = REG_READ(DMCUB_SCRATCH6); + diag_data->scratch[7] = REG_READ(DMCUB_SCRATCH7); + diag_data->scratch[8] = REG_READ(DMCUB_SCRATCH8); + diag_data->scratch[9] = REG_READ(DMCUB_SCRATCH9); + diag_data->scratch[10] = REG_READ(DMCUB_SCRATCH10); + diag_data->scratch[11] = REG_READ(DMCUB_SCRATCH11); + diag_data->scratch[12] = REG_READ(DMCUB_SCRATCH12); + diag_data->scratch[13] = REG_READ(DMCUB_SCRATCH13); + diag_data->scratch[14] = REG_READ(DMCUB_SCRATCH14); + diag_data->scratch[15] = REG_READ(DMCUB_SCRATCH15); + + diag_data->undefined_address_fault_addr = REG_READ(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR); + diag_data->inst_fetch_fault_addr = REG_READ(DMCUB_INST_FETCH_FAULT_ADDR); + diag_data->data_write_fault_addr = REG_READ(DMCUB_DATA_WRITE_FAULT_ADDR); + + diag_data->inbox1_rptr = REG_READ(DMCUB_INBOX1_RPTR); + diag_data->inbox1_wptr = REG_READ(DMCUB_INBOX1_WPTR); + diag_data->inbox1_size = REG_READ(DMCUB_INBOX1_SIZE); + + diag_data->inbox0_rptr = REG_READ(DMCUB_INBOX0_RPTR); + diag_data->inbox0_wptr = REG_READ(DMCUB_INBOX0_WPTR); + diag_data->inbox0_size = REG_READ(DMCUB_INBOX0_SIZE); + + REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_dmub_enabled); + diag_data->is_dmcub_enabled = is_dmub_enabled; + + REG_GET(DMCUB_CNTL, DMCUB_SOFT_RESET, &is_soft_reset); + diag_data->is_dmcub_soft_reset = is_soft_reset; + + REG_GET(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS, &is_sec_reset); + diag_data->is_dmcub_secure_reset = is_sec_reset; + + REG_GET(DMCUB_CNTL, DMCUB_TRACEPORT_EN, &is_traceport_enabled); + diag_data->is_traceport_en = is_traceport_enabled; + + REG_GET(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE, &is_cw0_enabled); + diag_data->is_cw0_enabled = is_cw0_enabled; + + REG_GET(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE, &is_cw6_enabled); + diag_data->is_cw6_enabled = is_cw6_enabled; +} diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h index f772f8b348ea..c2e5831ac52c 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn20.h @@ -36,6 +36,9 @@ struct dmub_srv; DMUB_SR(DMCUB_CNTL) \ DMUB_SR(DMCUB_MEM_CNTL) \ DMUB_SR(DMCUB_SEC_CNTL) \ + DMUB_SR(DMCUB_INBOX0_SIZE) \ + DMUB_SR(DMCUB_INBOX0_RPTR) \ + DMUB_SR(DMCUB_INBOX0_WPTR) \ DMUB_SR(DMCUB_INBOX1_BASE_ADDRESS) \ DMUB_SR(DMCUB_INBOX1_SIZE) \ DMUB_SR(DMCUB_INBOX1_RPTR) \ @@ -108,7 +111,12 @@ struct dmub_srv; DMUB_SR(DCN_VM_FB_LOCATION_BASE) \ DMUB_SR(DCN_VM_FB_OFFSET) \ DMUB_SR(DMCUB_INTERRUPT_ACK) \ - DMUB_SR(DMCUB_TIMER_CURRENT) + DMUB_SR(DMCUB_TIMER_CURRENT) \ + DMUB_SR(DMCUB_INST_FETCH_FAULT_ADDR) \ + DMUB_SR(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR) \ + DMUB_SR(DMCUB_DATA_WRITE_FAULT_ADDR) + +#define DMCUB_INTERNAL_REGS() #define DMUB_COMMON_FIELDS() \ DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \ @@ -118,6 +126,7 @@ struct dmub_srv; DMUB_SF(DMCUB_MEM_CNTL, DMCUB_MEM_WRITE_SPACE) \ DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET) \ DMUB_SF(DMCUB_SEC_CNTL, DMCUB_MEM_UNIT_ID) \ + DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS) \ DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_TOP_ADDRESS) \ DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE) \ DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_TOP_ADDRESS) \ @@ -147,6 +156,7 @@ struct dmub_srv; struct dmub_srv_common_reg_offset { #define DMUB_SR(reg) uint32_t reg; DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() #undef DMUB_SR }; @@ -234,4 +244,6 @@ bool dmub_dcn20_use_cached_trace_buffer(struct dmub_srv *dmub); uint32_t dmub_dcn20_get_current_time(struct dmub_srv *dmub); +void dmub_dcn20_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *dmub_oca); + #endif /* _DMUB_DCN20_H_ */ diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c index 1cf67b3e4771..51bb9bceb1b1 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn21.c @@ -39,7 +39,10 @@ const struct dmub_srv_common_regs dmub_srv_dcn21_regs = { #define DMUB_SR(reg) REG_OFFSET(reg), - { DMUB_COMMON_REGS() }, + { + DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() + }, #undef DMUB_SR #define DMUB_SF(reg, field) FD_MASK(reg, field), diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn30.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn30.c index fb11c8d39208..81dae75e9ff8 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn30.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn30.c @@ -40,7 +40,10 @@ const struct dmub_srv_common_regs dmub_srv_dcn30_regs = { #define DMUB_SR(reg) REG_OFFSET(reg), - { DMUB_COMMON_REGS() }, + { + DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() + }, #undef DMUB_SR #define DMUB_SF(reg, field) FD_MASK(reg, field), diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn301.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn301.c index 197398257692..84c3ab3becc5 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn301.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn301.c @@ -39,7 +39,10 @@ const struct dmub_srv_common_regs dmub_srv_dcn301_regs = { #define DMUB_SR(reg) REG_OFFSET(reg), - { DMUB_COMMON_REGS() }, + { + DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() + }, #undef DMUB_SR #define DMUB_SF(reg, field) FD_MASK(reg, field), diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn302.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn302.c index f5db4437a882..8c02575e168d 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn302.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn302.c @@ -39,7 +39,10 @@ const struct dmub_srv_common_regs dmub_srv_dcn302_regs = { #define DMUB_SR(reg) REG_OFFSET(reg), - { DMUB_COMMON_REGS() }, + { + DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() + }, #undef DMUB_SR #define DMUB_SF(reg, field) FD_MASK(reg, field), diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn303.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn303.c index 9331e1719901..b42369984473 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn303.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn303.c @@ -21,7 +21,10 @@ const struct dmub_srv_common_regs dmub_srv_dcn303_regs = { #define DMUB_SR(reg) REG_OFFSET(reg), - { DMUB_COMMON_REGS() }, + { + DMUB_COMMON_REGS() + DMCUB_INTERNAL_REGS() + }, #undef DMUB_SR #define DMUB_SF(reg, field) FD_MASK(reg, field), 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 8c886ece71f6..973de346410d 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.c @@ -352,3 +352,63 @@ uint32_t dmub_dcn31_get_current_time(struct dmub_srv *dmub) { return REG_READ(DMCUB_TIMER_CURRENT); } + +void dmub_dcn31_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data) +{ + uint32_t is_dmub_enabled, is_soft_reset, is_sec_reset; + uint32_t is_traceport_enabled, is_cw0_enabled, is_cw6_enabled; + + if (!dmub || !diag_data) + return; + + memset(diag_data, 0, sizeof(*diag_data)); + + diag_data->dmcub_version = dmub->fw_version; + + diag_data->scratch[0] = REG_READ(DMCUB_SCRATCH0); + diag_data->scratch[1] = REG_READ(DMCUB_SCRATCH1); + diag_data->scratch[2] = REG_READ(DMCUB_SCRATCH2); + diag_data->scratch[3] = REG_READ(DMCUB_SCRATCH3); + diag_data->scratch[4] = REG_READ(DMCUB_SCRATCH4); + diag_data->scratch[5] = REG_READ(DMCUB_SCRATCH5); + diag_data->scratch[6] = REG_READ(DMCUB_SCRATCH6); + diag_data->scratch[7] = REG_READ(DMCUB_SCRATCH7); + diag_data->scratch[8] = REG_READ(DMCUB_SCRATCH8); + diag_data->scratch[9] = REG_READ(DMCUB_SCRATCH9); + diag_data->scratch[10] = REG_READ(DMCUB_SCRATCH10); + diag_data->scratch[11] = REG_READ(DMCUB_SCRATCH11); + diag_data->scratch[12] = REG_READ(DMCUB_SCRATCH12); + diag_data->scratch[13] = REG_READ(DMCUB_SCRATCH13); + diag_data->scratch[14] = REG_READ(DMCUB_SCRATCH14); + diag_data->scratch[15] = REG_READ(DMCUB_SCRATCH15); + + diag_data->undefined_address_fault_addr = REG_READ(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR); + diag_data->inst_fetch_fault_addr = REG_READ(DMCUB_INST_FETCH_FAULT_ADDR); + diag_data->data_write_fault_addr = REG_READ(DMCUB_DATA_WRITE_FAULT_ADDR); + + diag_data->inbox1_rptr = REG_READ(DMCUB_INBOX1_RPTR); + diag_data->inbox1_wptr = REG_READ(DMCUB_INBOX1_WPTR); + diag_data->inbox1_size = REG_READ(DMCUB_INBOX1_SIZE); + + diag_data->inbox0_rptr = REG_READ(DMCUB_INBOX0_RPTR); + diag_data->inbox0_wptr = REG_READ(DMCUB_INBOX0_WPTR); + diag_data->inbox0_size = REG_READ(DMCUB_INBOX0_SIZE); + + REG_GET(DMCUB_CNTL, DMCUB_ENABLE, &is_dmub_enabled); + diag_data->is_dmcub_enabled = is_dmub_enabled; + + REG_GET(DMCUB_CNTL2, DMCUB_SOFT_RESET, &is_soft_reset); + diag_data->is_dmcub_soft_reset = is_soft_reset; + + REG_GET(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS, &is_sec_reset); + diag_data->is_dmcub_secure_reset = is_sec_reset; + + REG_GET(DMCUB_CNTL, DMCUB_TRACEPORT_EN, &is_traceport_enabled); + diag_data->is_traceport_en = is_traceport_enabled; + + REG_GET(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE, &is_cw0_enabled); + diag_data->is_cw0_enabled = is_cw0_enabled; + + REG_GET(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE, &is_cw6_enabled); + diag_data->is_cw6_enabled = is_cw6_enabled; +} diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h index 2829c3e9a310..9456a6a2d518 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn31.h @@ -36,6 +36,9 @@ struct dmub_srv; DMUB_SR(DMCUB_CNTL) \ DMUB_SR(DMCUB_CNTL2) \ DMUB_SR(DMCUB_SEC_CNTL) \ + DMUB_SR(DMCUB_INBOX0_SIZE) \ + DMUB_SR(DMCUB_INBOX0_RPTR) \ + DMUB_SR(DMCUB_INBOX0_WPTR) \ DMUB_SR(DMCUB_INBOX1_BASE_ADDRESS) \ DMUB_SR(DMCUB_INBOX1_SIZE) \ DMUB_SR(DMCUB_INBOX1_RPTR) \ @@ -103,11 +106,15 @@ struct dmub_srv; DMUB_SR(DMCUB_SCRATCH14) \ DMUB_SR(DMCUB_SCRATCH15) \ DMUB_SR(DMCUB_GPINT_DATAIN1) \ + DMUB_SR(DMCUB_GPINT_DATAOUT) \ DMUB_SR(CC_DC_PIPE_DIS) \ DMUB_SR(MMHUBBUB_SOFT_RESET) \ DMUB_SR(DCN_VM_FB_LOCATION_BASE) \ DMUB_SR(DCN_VM_FB_OFFSET) \ - DMUB_SR(DMCUB_TIMER_CURRENT) + DMUB_SR(DMCUB_TIMER_CURRENT) \ + DMUB_SR(DMCUB_INST_FETCH_FAULT_ADDR) \ + DMUB_SR(DMCUB_UNDEFINED_ADDRESS_FAULT_ADDR) \ + DMUB_SR(DMCUB_DATA_WRITE_FAULT_ADDR) #define DMUB_DCN31_FIELDS() \ DMUB_SF(DMCUB_CNTL, DMCUB_ENABLE) \ @@ -115,6 +122,7 @@ struct dmub_srv; DMUB_SF(DMCUB_CNTL2, DMCUB_SOFT_RESET) \ DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET) \ DMUB_SF(DMCUB_SEC_CNTL, DMCUB_MEM_UNIT_ID) \ + DMUB_SF(DMCUB_SEC_CNTL, DMCUB_SEC_RESET_STATUS) \ DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_TOP_ADDRESS) \ DMUB_SF(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE) \ DMUB_SF(DMCUB_REGION3_CW1_TOP_ADDRESS, DMCUB_REGION3_CW1_TOP_ADDRESS) \ @@ -138,11 +146,13 @@ struct dmub_srv; DMUB_SF(CC_DC_PIPE_DIS, DC_DMCUB_ENABLE) \ DMUB_SF(MMHUBBUB_SOFT_RESET, DMUIF_SOFT_RESET) \ DMUB_SF(DCN_VM_FB_LOCATION_BASE, FB_BASE) \ - DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET) + DMUB_SF(DCN_VM_FB_OFFSET, FB_OFFSET) \ + DMUB_SF(DMCUB_INBOX0_WPTR, DMCUB_INBOX0_WPTR) struct dmub_srv_dcn31_reg_offset { #define DMUB_SR(reg) uint32_t reg; DMUB_DCN31_REGS() + DMCUB_INTERNAL_REGS() #undef DMUB_SR }; @@ -227,4 +237,6 @@ void dmub_dcn31_set_outbox0_rptr(struct dmub_srv *dmub, uint32_t rptr_offset); uint32_t dmub_dcn31_get_current_time(struct dmub_srv *dmub); +void dmub_dcn31_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data); + #endif /* _DMUB_DCN31_H_ */ diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index 681500f42c91..2bdbd7406f56 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -31,9 +31,7 @@ #include "dmub_dcn301.h" #include "dmub_dcn302.h" #include "dmub_dcn303.h" -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 #include "dmub_dcn31.h" -#endif #include "os_types.h" /* * Note: the DMUB service is standalone. No additional headers should be @@ -176,6 +174,8 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) funcs->get_outbox0_wptr = dmub_dcn20_get_outbox0_wptr; funcs->set_outbox0_rptr = dmub_dcn20_set_outbox0_rptr; + funcs->get_diagnostic_data = dmub_dcn20_get_diagnostic_data; + if (asic == DMUB_ASIC_DCN21) { dmub->regs = &dmub_srv_dcn21_regs; @@ -206,9 +206,9 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) funcs->setup_windows = dmub_dcn30_setup_windows; } break; -#ifdef CONFIG_DRM_AMD_DC_DCN3_1 case DMUB_ASIC_DCN31: + dmub->regs_dcn31 = &dmub_srv_dcn31_regs; funcs->reset = dmub_dcn31_reset; funcs->reset_release = dmub_dcn31_reset_release; funcs->backdoor_load = dmub_dcn31_backdoor_load; @@ -232,14 +232,11 @@ static bool dmub_srv_hw_setup(struct dmub_srv *dmub, enum dmub_asic asic) funcs->get_outbox0_wptr = dmub_dcn31_get_outbox0_wptr; funcs->set_outbox0_rptr = dmub_dcn31_set_outbox0_rptr; - if (asic == DMUB_ASIC_DCN31) { - dmub->regs_dcn31 = &dmub_srv_dcn31_regs; - } + funcs->get_diagnostic_data = dmub_dcn31_get_diagnostic_data; funcs->get_current_time = dmub_dcn31_get_current_time; break; -#endif default: return false; @@ -794,3 +791,11 @@ bool dmub_srv_get_outbox0_msg(struct dmub_srv *dmub, struct dmcub_trace_buf_entr return dmub_rb_out_trace_buffer_front(&dmub->outbox0_rb, (void *)entry); } + +bool dmub_srv_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data) +{ + if (!dmub || !dmub->hw_funcs.get_diagnostic_data || !diag_data) + return false; + dmub->hw_funcs.get_diagnostic_data(dmub, diag_data); + return true; +} 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 d615a8e00f8c..381c17caace1 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -224,7 +224,6 @@ enum { #define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF)) #endif -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) #define FAMILY_YELLOW_CARP 146 #define YELLOW_CARP_A0 0x01 @@ -234,7 +233,6 @@ enum { #ifndef ASICREV_IS_YELLOW_CARP #define ASICREV_IS_YELLOW_CARP(eChipRev) ((eChipRev >= YELLOW_CARP_A0) && (eChipRev < YELLOW_CARP_UNKNOWN)) #endif -#endif /* diff --git a/drivers/gpu/drm/amd/display/include/dal_types.h b/drivers/gpu/drm/amd/display/include/dal_types.h index 59453ced9ece..fe75ec834892 100644 --- a/drivers/gpu/drm/amd/display/include/dal_types.h +++ b/drivers/gpu/drm/amd/display/include/dal_types.h @@ -55,9 +55,7 @@ enum dce_version { DCN_VERSION_3_01, DCN_VERSION_3_02, DCN_VERSION_3_03, -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) DCN_VERSION_3_1, -#endif DCN_VERSION_MAX }; diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c index 62dd89cf70bb..1a0f7c3dc964 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c @@ -172,10 +172,8 @@ char *mod_hdcp_status_to_str(int32_t status) return "MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE"; case MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE: return "MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE"; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) case MOD_HDCP_STATUS_UNSUPPORTED_PSP_VER_FAILURE: return "MOD_HDCP_STATUS_UNSUPPORTED_PSP_VER_FAILURE"; -#endif default: return "MOD_HDCP_STATUS_UNKNOWN"; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index fc88fe249a50..1b02056bc8bd 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -44,13 +44,9 @@ static void hdcp2_message_init(struct mod_hdcp *hdcp, in->process.msg3_desc.msg_id = TA_HDCP_HDCP2_MSG_ID__NULL_MESSAGE; in->process.msg3_desc.msg_size = 0; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v2( struct mod_hdcp *hdcp, uint8_t index) -#else -enum mod_hdcp_status mod_hdcp_remove_display_from_topology( - struct mod_hdcp *hdcp, uint8_t index) -#endif { struct psp_context *psp = hdcp->config.psp.handle; struct ta_dtm_shared_memory *dtm_cmd; @@ -84,7 +80,7 @@ enum mod_hdcp_status mod_hdcp_remove_display_from_topology( mutex_unlock(&psp->dtm_context.mutex); return status; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + static enum mod_hdcp_status mod_hdcp_remove_display_from_topology_v3( struct mod_hdcp *hdcp, uint8_t index) { @@ -136,14 +132,9 @@ enum mod_hdcp_status mod_hdcp_remove_display_from_topology( return status; } -#endif -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v2( struct mod_hdcp *hdcp, struct mod_hdcp_display *display) -#else -enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, - struct mod_hdcp_display *display) -#endif { struct psp_context *psp = hdcp->config.psp.handle; struct ta_dtm_shared_memory *dtm_cmd; @@ -189,7 +180,6 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, return status; } -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) static enum mod_hdcp_status mod_hdcp_add_display_to_topology_v3( struct mod_hdcp *hdcp, struct mod_hdcp_display *display) { @@ -254,7 +244,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, return status; } -#endif + enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp) { diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h index b0b2544eaa9d..2937b4b61461 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h @@ -44,12 +44,8 @@ enum bgd_security_hdcp2_content_type { enum ta_dtm_command { TA_DTM_COMMAND__UNUSED_1 = 1, TA_DTM_COMMAND__TOPOLOGY_UPDATE_V2, -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) TA_DTM_COMMAND__TOPOLOGY_ASSR_ENABLE, TA_DTM_COMMAND__TOPOLOGY_UPDATE_V3 -#else - TA_DTM_COMMAND__TOPOLOGY_ASSR_ENABLE -#endif }; /* DTM related enumerations */ @@ -91,7 +87,6 @@ struct ta_dtm_topology_update_input_v2 { uint32_t max_hdcp_supported_version; }; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) /* For security reason/HW may change value, these encoder type enum values are not HW register values */ /* Security code will check real HW register values and these SW enum values */ enum ta_dtm_encoder_type { @@ -117,7 +112,7 @@ struct ta_dtm_topology_update_input_v3 { uint32_t phy_id; uint32_t link_hdcp_cap; }; -#endif + struct ta_dtm_topology_assr_enable { uint32_t display_topology_dig_be_index; }; @@ -131,9 +126,7 @@ struct ta_dtm_topology_assr_enable { union ta_dtm_cmd_input { struct ta_dtm_topology_update_input_v2 topology_update_v2; struct ta_dtm_topology_assr_enable topology_assr_enable; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) struct ta_dtm_topology_update_input_v3 topology_update_v3; -#endif }; union ta_dtm_cmd_output { @@ -313,10 +306,8 @@ enum ta_hdcp2_version { TA_HDCP2_VERSION_UNKNOWN = 0, TA_HDCP2_VERSION_2_0 = 20, TA_HDCP2_VERSION_2_1 = 21, -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) + TA_HDCP2_VERSION_2_2 = 22, TA_HDCP2_VERSION_2_3 = 23, -#endif - TA_HDCP2_VERSION_2_2 = 22 }; /* input/output structures for HDCP commands */ diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h index 2197c269e0a7..c590493fd293 100644 --- a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h +++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h @@ -97,9 +97,7 @@ enum mod_hdcp_status { MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST, MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE, MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE, -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) MOD_HDCP_STATUS_UNSUPPORTED_PSP_VER_FAILURE, -#endif }; struct mod_hdcp_displayport { @@ -123,13 +121,11 @@ enum mod_hdcp_display_state { MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED }; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) struct mod_hdcp_psp_caps { uint8_t dtm_v3_supported; uint8_t opm_state_query_supported; }; -#endif enum mod_hdcp_display_disable_option { MOD_HDCP_DISPLAY_NOT_DISABLE = 0, MOD_HDCP_DISPLAY_DISABLE_AUTHENTICATION, @@ -162,9 +158,7 @@ struct mod_hdcp_ddc { struct mod_hdcp_psp { void *handle; void *funcs; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) struct mod_hdcp_psp_caps caps; -#endif }; struct mod_hdcp_display_adjustment { @@ -240,9 +234,7 @@ struct mod_hdcp_display { uint8_t index; uint8_t controller; uint8_t dig_fe; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint8_t stream_enc_idx; -#endif union { uint8_t vc_id; }; @@ -255,11 +247,9 @@ struct mod_hdcp_link { enum mod_hdcp_operation_mode mode; uint8_t dig_be; uint8_t ddc_line; -#if defined(CONFIG_DRM_AMD_DC_DCN3_1) uint8_t link_enc_idx; uint8_t phy_idx; uint8_t hdcp_supported_informational; -#endif union { struct mod_hdcp_displayport dp; struct mod_hdcp_hdmi hdmi; diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 5e7331be1c0d..2b00f334e93d 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -87,19 +87,19 @@ struct abm_parameters { }; static const struct abm_parameters abm_settings_config0[abm_defines_max_level] = { -// min_red max_red bright_pos dark_pos bright_gain contrast dev min_knee max_knee blStart blRed - {0xff, 0xbf, 0x20, 0x00, 0xff, 0x99, 0xb3, 0x40, 0xe0, 0xCCCC, 0xCCCC}, - {0xde, 0x85, 0x20, 0x00, 0xff, 0x90, 0xa8, 0x40, 0xdf, 0xCCCC, 0xCCCC}, - {0xb0, 0x50, 0x20, 0x00, 0xc0, 0x88, 0x78, 0x70, 0xa0, 0xCCCC, 0xCCCC}, - {0x82, 0x40, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xCCCC, 0xCCCC}, +// min_red max_red bright_pos dark_pos bright_gain contrast dev min_knee max_knee blRed blStart + {0xff, 0xbf, 0x20, 0x00, 0xff, 0x99, 0xb3, 0x40, 0xe0, 0xf777, 0xcccc}, + {0xde, 0x85, 0x20, 0x00, 0xe0, 0x90, 0xa8, 0x40, 0xc8, 0xf777, 0xcccc}, + {0xb0, 0x50, 0x20, 0x00, 0xc0, 0x88, 0x78, 0x70, 0xa0, 0xeeee, 0x9999}, + {0x82, 0x40, 0x20, 0x00, 0x00, 0xb8, 0xb3, 0x70, 0x70, 0xe333, 0xb333}, }; static const struct abm_parameters abm_settings_config1[abm_defines_max_level] = { -// min_red max_red bright_pos dark_pos bright_gain contrast dev min_knee max_knee blStart blRed - {0xf0, 0xd9, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xCCCC, 0xCCCC}, - {0xcd, 0xa5, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xCCCC, 0xCCCC}, - {0x99, 0x65, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xCCCC, 0xCCCC}, - {0x82, 0x4d, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xCCCC, 0xCCCC}, +// min_red max_red bright_pos dark_pos bright_gain contrast dev min_knee max_knee blRed blStart + {0xf0, 0xd9, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xcccc, 0xcccc}, + {0xcd, 0xa5, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xcccc, 0xcccc}, + {0x99, 0x65, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xcccc, 0xcccc}, + {0x82, 0x4d, 0x20, 0x00, 0x00, 0xff, 0xb3, 0x70, 0x70, 0xcccc, 0xcccc}, }; static const struct abm_parameters * const abm_settings[] = { diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 332b0df53e52..ff1d3d4a6488 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -223,10 +223,12 @@ enum amd_harvest_ip_mask { }; enum DC_FEATURE_MASK { - DC_FBC_MASK = 0x1, - DC_MULTI_MON_PP_MCLK_SWITCH_MASK = 0x2, - DC_DISABLE_FRACTIONAL_PWM_MASK = 0x4, - DC_PSR_MASK = 0x8, + //Default value can be found at "uint amdgpu_dc_feature_mask" + DC_FBC_MASK = (1 << 0), //0x1, disabled by default + DC_MULTI_MON_PP_MCLK_SWITCH_MASK = (1 << 1), //0x2, enabled by default + DC_DISABLE_FRACTIONAL_PWM_MASK = (1 << 2), //0x4, disabled by default + DC_PSR_MASK = (1 << 3), //0x8, disabled by default + DC_EDP_NO_POWER_SEQUENCING = (1 << 4), //0x10, disabled by default }; enum DC_DEBUG_MASK { diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_1_sh_mask.h index 2a622c13817b..59155007c186 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_1_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_0_1_sh_mask.h @@ -29292,6 +29292,7 @@ #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_OVERWRITE_LEVEL_MASK 0x000000FCL #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_ERROR_ACK_MASK 0x00000100L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_CAL_AVERAGE_LEVEL_MASK 0x0000FC00L +#define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MAXIMUM_LEVEL_MASK 0x001F0000L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MINIMUM_LEVEL_MASK 0x03C00000L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_READ_CLOCK_SRC_MASK 0x04000000L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_CALIBRATED_MASK 0x20000000L @@ -34431,6 +34432,7 @@ #define DIG3_DIG_FIFO_STATUS__DIG_FIFO_OVERWRITE_LEVEL__SHIFT 0x2 #define DIG3_DIG_FIFO_STATUS__DIG_FIFO_ERROR_ACK__SHIFT 0x8 #define DIG3_DIG_FIFO_STATUS__DIG_FIFO_CAL_AVERAGE_LEVEL__SHIFT 0xa +#define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MAXIMUM_LEVEL__SHIFT 0x10 #define DIG3_DIG_FIFO_STATUS__DIG_FIFO_MINIMUM_LEVEL__SHIFT 0x16 #define DIG3_DIG_FIFO_STATUS__DIG_FIFO_READ_CLOCK_SRC__SHIFT 0x1a #define DIG3_DIG_FIFO_STATUS__DIG_FIFO_CALIBRATED__SHIFT 0x1d diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h index 7b2e5833e345..e5fd0121ceff 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_3_1_2_sh_mask.h @@ -33869,6 +33869,7 @@ #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_OVERWRITE_LEVEL__SHIFT 0x2 #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_ERROR_ACK__SHIFT 0x8 #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_CAL_AVERAGE_LEVEL__SHIFT 0xa +#define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MAXIMUM_LEVEL__SHIFT 0x10 #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MINIMUM_LEVEL__SHIFT 0x16 #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_READ_CLOCK_SRC__SHIFT 0x1a #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_CALIBRATED__SHIFT 0x1d @@ -33879,6 +33880,7 @@ #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_OVERWRITE_LEVEL_MASK 0x000000FCL #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_ERROR_ACK_MASK 0x00000100L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_CAL_AVERAGE_LEVEL_MASK 0x0000FC00L +#define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MAXIMUM_LEVEL_MASK 0x001F0000L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_MINIMUM_LEVEL_MASK 0x03C00000L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_READ_CLOCK_SRC_MASK 0x04000000L #define DIG0_DIG_FIFO_STATUS__DIG_FIFO_CALIBRATED_MASK 0x20000000L diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h deleted file mode 100644 index dfacc6b5d89d..000000000000 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_offset.h +++ /dev/null @@ -1,355 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * - */ -#ifndef _mp_13_0_1_OFFSET_HEADER -#define _mp_13_0_1_OFFSET_HEADER - - - -// addressBlock: mp_SmuMp0_SmnDec -// base address: 0x0 -#define regMP0_SMN_C2PMSG_32 0x0060 -#define regMP0_SMN_C2PMSG_32_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_33 0x0061 -#define regMP0_SMN_C2PMSG_33_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_34 0x0062 -#define regMP0_SMN_C2PMSG_34_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_35 0x0063 -#define regMP0_SMN_C2PMSG_35_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_36 0x0064 -#define regMP0_SMN_C2PMSG_36_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_37 0x0065 -#define regMP0_SMN_C2PMSG_37_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_38 0x0066 -#define regMP0_SMN_C2PMSG_38_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_39 0x0067 -#define regMP0_SMN_C2PMSG_39_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_40 0x0068 -#define regMP0_SMN_C2PMSG_40_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_41 0x0069 -#define regMP0_SMN_C2PMSG_41_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_42 0x006a -#define regMP0_SMN_C2PMSG_42_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_43 0x006b -#define regMP0_SMN_C2PMSG_43_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_44 0x006c -#define regMP0_SMN_C2PMSG_44_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_45 0x006d -#define regMP0_SMN_C2PMSG_45_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_46 0x006e -#define regMP0_SMN_C2PMSG_46_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_47 0x006f -#define regMP0_SMN_C2PMSG_47_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_48 0x0070 -#define regMP0_SMN_C2PMSG_48_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_49 0x0071 -#define regMP0_SMN_C2PMSG_49_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_50 0x0072 -#define regMP0_SMN_C2PMSG_50_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_51 0x0073 -#define regMP0_SMN_C2PMSG_51_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_52 0x0074 -#define regMP0_SMN_C2PMSG_52_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_53 0x0075 -#define regMP0_SMN_C2PMSG_53_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_54 0x0076 -#define regMP0_SMN_C2PMSG_54_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_55 0x0077 -#define regMP0_SMN_C2PMSG_55_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_56 0x0078 -#define regMP0_SMN_C2PMSG_56_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_57 0x0079 -#define regMP0_SMN_C2PMSG_57_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_58 0x007a -#define regMP0_SMN_C2PMSG_58_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_59 0x007b -#define regMP0_SMN_C2PMSG_59_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_60 0x007c -#define regMP0_SMN_C2PMSG_60_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_61 0x007d -#define regMP0_SMN_C2PMSG_61_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_62 0x007e -#define regMP0_SMN_C2PMSG_62_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_63 0x007f -#define regMP0_SMN_C2PMSG_63_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_64 0x0080 -#define regMP0_SMN_C2PMSG_64_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_65 0x0081 -#define regMP0_SMN_C2PMSG_65_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_66 0x0082 -#define regMP0_SMN_C2PMSG_66_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_67 0x0083 -#define regMP0_SMN_C2PMSG_67_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_68 0x0084 -#define regMP0_SMN_C2PMSG_68_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_69 0x0085 -#define regMP0_SMN_C2PMSG_69_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_70 0x0086 -#define regMP0_SMN_C2PMSG_70_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_71 0x0087 -#define regMP0_SMN_C2PMSG_71_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_72 0x0088 -#define regMP0_SMN_C2PMSG_72_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_73 0x0089 -#define regMP0_SMN_C2PMSG_73_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_74 0x008a -#define regMP0_SMN_C2PMSG_74_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_75 0x008b -#define regMP0_SMN_C2PMSG_75_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_76 0x008c -#define regMP0_SMN_C2PMSG_76_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_77 0x008d -#define regMP0_SMN_C2PMSG_77_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_78 0x008e -#define regMP0_SMN_C2PMSG_78_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_79 0x008f -#define regMP0_SMN_C2PMSG_79_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_80 0x0090 -#define regMP0_SMN_C2PMSG_80_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_81 0x0091 -#define regMP0_SMN_C2PMSG_81_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_82 0x0092 -#define regMP0_SMN_C2PMSG_82_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_83 0x0093 -#define regMP0_SMN_C2PMSG_83_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_84 0x0094 -#define regMP0_SMN_C2PMSG_84_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_85 0x0095 -#define regMP0_SMN_C2PMSG_85_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_86 0x0096 -#define regMP0_SMN_C2PMSG_86_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_87 0x0097 -#define regMP0_SMN_C2PMSG_87_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_88 0x0098 -#define regMP0_SMN_C2PMSG_88_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_89 0x0099 -#define regMP0_SMN_C2PMSG_89_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_90 0x009a -#define regMP0_SMN_C2PMSG_90_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_91 0x009b -#define regMP0_SMN_C2PMSG_91_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_92 0x009c -#define regMP0_SMN_C2PMSG_92_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_93 0x009d -#define regMP0_SMN_C2PMSG_93_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_94 0x009e -#define regMP0_SMN_C2PMSG_94_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_95 0x009f -#define regMP0_SMN_C2PMSG_95_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_96 0x00a0 -#define regMP0_SMN_C2PMSG_96_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_97 0x00a1 -#define regMP0_SMN_C2PMSG_97_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_98 0x00a2 -#define regMP0_SMN_C2PMSG_98_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_99 0x00a3 -#define regMP0_SMN_C2PMSG_99_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_100 0x00a4 -#define regMP0_SMN_C2PMSG_100_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_101 0x00a5 -#define regMP0_SMN_C2PMSG_101_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_102 0x00a6 -#define regMP0_SMN_C2PMSG_102_BASE_IDX 0 -#define regMP0_SMN_C2PMSG_103 0x00a7 -#define regMP0_SMN_C2PMSG_103_BASE_IDX 0 -#define regMP0_SMN_IH_CREDIT 0x00c1 -#define regMP0_SMN_IH_CREDIT_BASE_IDX 0 -#define regMP0_SMN_IH_SW_INT 0x00c2 -#define regMP0_SMN_IH_SW_INT_BASE_IDX 0 -#define regMP0_SMN_IH_SW_INT_CTRL 0x00c3 -#define regMP0_SMN_IH_SW_INT_CTRL_BASE_IDX 0 - - -// addressBlock: mp_SmuMp1_SmnDec -// base address: 0x0 -#define regMP1_SMN_C2PMSG_32 0x0260 -#define regMP1_SMN_C2PMSG_32_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_33 0x0261 -#define regMP1_SMN_C2PMSG_33_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_34 0x0262 -#define regMP1_SMN_C2PMSG_34_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_35 0x0263 -#define regMP1_SMN_C2PMSG_35_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_36 0x0264 -#define regMP1_SMN_C2PMSG_36_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_37 0x0265 -#define regMP1_SMN_C2PMSG_37_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_38 0x0266 -#define regMP1_SMN_C2PMSG_38_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_39 0x0267 -#define regMP1_SMN_C2PMSG_39_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_40 0x0268 -#define regMP1_SMN_C2PMSG_40_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_41 0x0269 -#define regMP1_SMN_C2PMSG_41_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_42 0x026a -#define regMP1_SMN_C2PMSG_42_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_43 0x026b -#define regMP1_SMN_C2PMSG_43_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_44 0x026c -#define regMP1_SMN_C2PMSG_44_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_45 0x026d -#define regMP1_SMN_C2PMSG_45_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_46 0x026e -#define regMP1_SMN_C2PMSG_46_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_47 0x026f -#define regMP1_SMN_C2PMSG_47_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_48 0x0270 -#define regMP1_SMN_C2PMSG_48_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_49 0x0271 -#define regMP1_SMN_C2PMSG_49_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_50 0x0272 -#define regMP1_SMN_C2PMSG_50_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_51 0x0273 -#define regMP1_SMN_C2PMSG_51_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_52 0x0274 -#define regMP1_SMN_C2PMSG_52_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_53 0x0275 -#define regMP1_SMN_C2PMSG_53_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_54 0x0276 -#define regMP1_SMN_C2PMSG_54_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_55 0x0277 -#define regMP1_SMN_C2PMSG_55_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_56 0x0278 -#define regMP1_SMN_C2PMSG_56_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_57 0x0279 -#define regMP1_SMN_C2PMSG_57_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_58 0x027a -#define regMP1_SMN_C2PMSG_58_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_59 0x027b -#define regMP1_SMN_C2PMSG_59_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_60 0x027c -#define regMP1_SMN_C2PMSG_60_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_61 0x027d -#define regMP1_SMN_C2PMSG_61_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_62 0x027e -#define regMP1_SMN_C2PMSG_62_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_63 0x027f -#define regMP1_SMN_C2PMSG_63_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_64 0x0280 -#define regMP1_SMN_C2PMSG_64_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_65 0x0281 -#define regMP1_SMN_C2PMSG_65_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_66 0x0282 -#define regMP1_SMN_C2PMSG_66_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_67 0x0283 -#define regMP1_SMN_C2PMSG_67_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_68 0x0284 -#define regMP1_SMN_C2PMSG_68_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_69 0x0285 -#define regMP1_SMN_C2PMSG_69_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_70 0x0286 -#define regMP1_SMN_C2PMSG_70_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_71 0x0287 -#define regMP1_SMN_C2PMSG_71_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_72 0x0288 -#define regMP1_SMN_C2PMSG_72_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_73 0x0289 -#define regMP1_SMN_C2PMSG_73_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_74 0x028a -#define regMP1_SMN_C2PMSG_74_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_75 0x028b -#define regMP1_SMN_C2PMSG_75_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_76 0x028c -#define regMP1_SMN_C2PMSG_76_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_77 0x028d -#define regMP1_SMN_C2PMSG_77_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_78 0x028e -#define regMP1_SMN_C2PMSG_78_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_79 0x028f -#define regMP1_SMN_C2PMSG_79_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_80 0x0290 -#define regMP1_SMN_C2PMSG_80_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_81 0x0291 -#define regMP1_SMN_C2PMSG_81_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_82 0x0292 -#define regMP1_SMN_C2PMSG_82_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_83 0x0293 -#define regMP1_SMN_C2PMSG_83_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_84 0x0294 -#define regMP1_SMN_C2PMSG_84_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_85 0x0295 -#define regMP1_SMN_C2PMSG_85_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_86 0x0296 -#define regMP1_SMN_C2PMSG_86_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_87 0x0297 -#define regMP1_SMN_C2PMSG_87_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_88 0x0298 -#define regMP1_SMN_C2PMSG_88_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_89 0x0299 -#define regMP1_SMN_C2PMSG_89_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_90 0x029a -#define regMP1_SMN_C2PMSG_90_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_91 0x029b -#define regMP1_SMN_C2PMSG_91_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_92 0x029c -#define regMP1_SMN_C2PMSG_92_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_93 0x029d -#define regMP1_SMN_C2PMSG_93_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_94 0x029e -#define regMP1_SMN_C2PMSG_94_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_95 0x029f -#define regMP1_SMN_C2PMSG_95_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_96 0x02a0 -#define regMP1_SMN_C2PMSG_96_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_97 0x02a1 -#define regMP1_SMN_C2PMSG_97_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_98 0x02a2 -#define regMP1_SMN_C2PMSG_98_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_99 0x02a3 -#define regMP1_SMN_C2PMSG_99_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_100 0x02a4 -#define regMP1_SMN_C2PMSG_100_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_101 0x02a5 -#define regMP1_SMN_C2PMSG_101_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_102 0x02a6 -#define regMP1_SMN_C2PMSG_102_BASE_IDX 0 -#define regMP1_SMN_C2PMSG_103 0x02a7 -#define regMP1_SMN_C2PMSG_103_BASE_IDX 0 -#define regMP1_SMN_IH_CREDIT 0x02c1 -#define regMP1_SMN_IH_CREDIT_BASE_IDX 0 -#define regMP1_SMN_IH_SW_INT 0x02c2 -#define regMP1_SMN_IH_SW_INT_BASE_IDX 0 -#define regMP1_SMN_IH_SW_INT_CTRL 0x02c3 -#define regMP1_SMN_IH_SW_INT_CTRL_BASE_IDX 0 -#define regMP1_SMN_FPS_CNT 0x02c4 -#define regMP1_SMN_FPS_CNT_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH0 0x0340 -#define regMP1_SMN_EXT_SCRATCH0_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH1 0x0341 -#define regMP1_SMN_EXT_SCRATCH1_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH2 0x0342 -#define regMP1_SMN_EXT_SCRATCH2_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH3 0x0343 -#define regMP1_SMN_EXT_SCRATCH3_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH4 0x0344 -#define regMP1_SMN_EXT_SCRATCH4_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH5 0x0345 -#define regMP1_SMN_EXT_SCRATCH5_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH6 0x0346 -#define regMP1_SMN_EXT_SCRATCH6_BASE_IDX 0 -#define regMP1_SMN_EXT_SCRATCH7 0x0347 -#define regMP1_SMN_EXT_SCRATCH7_BASE_IDX 0 - - -#endif diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h deleted file mode 100644 index 2d5e8b58e693..000000000000 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_1_sh_mask.h +++ /dev/null @@ -1,531 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - * - * - */ -#ifndef _mp_13_0_1_SH_MASK_HEADER -#define _mp_13_0_1_SH_MASK_HEADER - - -// addressBlock: mp_SmuMp0_SmnDec -//MP0_SMN_C2PMSG_32 -#define MP0_SMN_C2PMSG_32__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_33 -#define MP0_SMN_C2PMSG_33__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_34 -#define MP0_SMN_C2PMSG_34__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_35 -#define MP0_SMN_C2PMSG_35__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_36 -#define MP0_SMN_C2PMSG_36__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_37 -#define MP0_SMN_C2PMSG_37__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_38 -#define MP0_SMN_C2PMSG_38__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_39 -#define MP0_SMN_C2PMSG_39__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_40 -#define MP0_SMN_C2PMSG_40__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_41 -#define MP0_SMN_C2PMSG_41__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_42 -#define MP0_SMN_C2PMSG_42__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_43 -#define MP0_SMN_C2PMSG_43__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_44 -#define MP0_SMN_C2PMSG_44__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_45 -#define MP0_SMN_C2PMSG_45__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_46 -#define MP0_SMN_C2PMSG_46__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_47 -#define MP0_SMN_C2PMSG_47__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_48 -#define MP0_SMN_C2PMSG_48__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_49 -#define MP0_SMN_C2PMSG_49__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_50 -#define MP0_SMN_C2PMSG_50__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_51 -#define MP0_SMN_C2PMSG_51__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_52 -#define MP0_SMN_C2PMSG_52__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_53 -#define MP0_SMN_C2PMSG_53__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_54 -#define MP0_SMN_C2PMSG_54__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_55 -#define MP0_SMN_C2PMSG_55__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_56 -#define MP0_SMN_C2PMSG_56__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_57 -#define MP0_SMN_C2PMSG_57__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_58 -#define MP0_SMN_C2PMSG_58__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_59 -#define MP0_SMN_C2PMSG_59__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_60 -#define MP0_SMN_C2PMSG_60__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_61 -#define MP0_SMN_C2PMSG_61__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_62 -#define MP0_SMN_C2PMSG_62__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_63 -#define MP0_SMN_C2PMSG_63__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_64 -#define MP0_SMN_C2PMSG_64__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_65 -#define MP0_SMN_C2PMSG_65__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_66 -#define MP0_SMN_C2PMSG_66__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_67 -#define MP0_SMN_C2PMSG_67__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_68 -#define MP0_SMN_C2PMSG_68__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_69 -#define MP0_SMN_C2PMSG_69__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_70 -#define MP0_SMN_C2PMSG_70__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_71 -#define MP0_SMN_C2PMSG_71__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_72 -#define MP0_SMN_C2PMSG_72__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_73 -#define MP0_SMN_C2PMSG_73__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_74 -#define MP0_SMN_C2PMSG_74__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_75 -#define MP0_SMN_C2PMSG_75__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_76 -#define MP0_SMN_C2PMSG_76__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_77 -#define MP0_SMN_C2PMSG_77__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_78 -#define MP0_SMN_C2PMSG_78__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_79 -#define MP0_SMN_C2PMSG_79__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_80 -#define MP0_SMN_C2PMSG_80__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_81 -#define MP0_SMN_C2PMSG_81__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_82 -#define MP0_SMN_C2PMSG_82__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_83 -#define MP0_SMN_C2PMSG_83__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_84 -#define MP0_SMN_C2PMSG_84__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_85 -#define MP0_SMN_C2PMSG_85__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_86 -#define MP0_SMN_C2PMSG_86__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_87 -#define MP0_SMN_C2PMSG_87__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_88 -#define MP0_SMN_C2PMSG_88__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_89 -#define MP0_SMN_C2PMSG_89__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_90 -#define MP0_SMN_C2PMSG_90__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_91 -#define MP0_SMN_C2PMSG_91__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_92 -#define MP0_SMN_C2PMSG_92__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_93 -#define MP0_SMN_C2PMSG_93__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_94 -#define MP0_SMN_C2PMSG_94__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_95 -#define MP0_SMN_C2PMSG_95__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_96 -#define MP0_SMN_C2PMSG_96__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_97 -#define MP0_SMN_C2PMSG_97__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_98 -#define MP0_SMN_C2PMSG_98__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_99 -#define MP0_SMN_C2PMSG_99__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_100 -#define MP0_SMN_C2PMSG_100__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_101 -#define MP0_SMN_C2PMSG_101__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_102 -#define MP0_SMN_C2PMSG_102__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_C2PMSG_103 -#define MP0_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 -#define MP0_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL -//MP0_SMN_IH_CREDIT -#define MP0_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 -#define MP0_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 -#define MP0_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L -#define MP0_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L -//MP0_SMN_IH_SW_INT -#define MP0_SMN_IH_SW_INT__ID__SHIFT 0x0 -#define MP0_SMN_IH_SW_INT__VALID__SHIFT 0x8 -#define MP0_SMN_IH_SW_INT__ID_MASK 0x000000FFL -#define MP0_SMN_IH_SW_INT__VALID_MASK 0x00000100L -//MP0_SMN_IH_SW_INT_CTRL -#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0 -#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8 -#define MP0_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L -#define MP0_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L - - -// addressBlock: mp_SmuMp1Pub_CruDec -//MP1_FIRMWARE_FLAGS -#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT 0x0 -#define MP1_FIRMWARE_FLAGS__RESERVED__SHIFT 0x1 -#define MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK 0x00000001L -#define MP1_FIRMWARE_FLAGS__RESERVED_MASK 0xFFFFFFFEL - - -// addressBlock: mp_SmuMp1_SmnDec -//MP1_SMN_C2PMSG_32 -#define MP1_SMN_C2PMSG_32__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_32__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_33 -#define MP1_SMN_C2PMSG_33__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_33__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_34 -#define MP1_SMN_C2PMSG_34__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_34__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_35 -#define MP1_SMN_C2PMSG_35__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_35__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_36 -#define MP1_SMN_C2PMSG_36__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_36__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_37 -#define MP1_SMN_C2PMSG_37__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_37__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_38 -#define MP1_SMN_C2PMSG_38__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_38__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_39 -#define MP1_SMN_C2PMSG_39__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_39__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_40 -#define MP1_SMN_C2PMSG_40__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_40__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_41 -#define MP1_SMN_C2PMSG_41__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_41__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_42 -#define MP1_SMN_C2PMSG_42__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_42__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_43 -#define MP1_SMN_C2PMSG_43__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_43__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_44 -#define MP1_SMN_C2PMSG_44__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_44__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_45 -#define MP1_SMN_C2PMSG_45__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_45__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_46 -#define MP1_SMN_C2PMSG_46__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_46__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_47 -#define MP1_SMN_C2PMSG_47__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_47__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_48 -#define MP1_SMN_C2PMSG_48__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_48__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_49 -#define MP1_SMN_C2PMSG_49__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_49__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_50 -#define MP1_SMN_C2PMSG_50__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_50__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_51 -#define MP1_SMN_C2PMSG_51__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_51__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_52 -#define MP1_SMN_C2PMSG_52__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_52__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_53 -#define MP1_SMN_C2PMSG_53__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_53__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_54 -#define MP1_SMN_C2PMSG_54__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_54__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_55 -#define MP1_SMN_C2PMSG_55__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_55__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_56 -#define MP1_SMN_C2PMSG_56__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_56__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_57 -#define MP1_SMN_C2PMSG_57__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_57__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_58 -#define MP1_SMN_C2PMSG_58__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_58__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_59 -#define MP1_SMN_C2PMSG_59__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_59__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_60 -#define MP1_SMN_C2PMSG_60__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_60__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_61 -#define MP1_SMN_C2PMSG_61__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_61__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_62 -#define MP1_SMN_C2PMSG_62__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_62__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_63 -#define MP1_SMN_C2PMSG_63__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_63__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_64 -#define MP1_SMN_C2PMSG_64__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_64__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_65 -#define MP1_SMN_C2PMSG_65__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_65__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_66 -#define MP1_SMN_C2PMSG_66__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_66__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_67 -#define MP1_SMN_C2PMSG_67__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_67__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_68 -#define MP1_SMN_C2PMSG_68__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_68__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_69 -#define MP1_SMN_C2PMSG_69__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_69__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_70 -#define MP1_SMN_C2PMSG_70__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_70__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_71 -#define MP1_SMN_C2PMSG_71__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_71__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_72 -#define MP1_SMN_C2PMSG_72__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_72__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_73 -#define MP1_SMN_C2PMSG_73__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_73__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_74 -#define MP1_SMN_C2PMSG_74__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_74__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_75 -#define MP1_SMN_C2PMSG_75__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_75__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_76 -#define MP1_SMN_C2PMSG_76__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_76__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_77 -#define MP1_SMN_C2PMSG_77__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_77__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_78 -#define MP1_SMN_C2PMSG_78__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_78__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_79 -#define MP1_SMN_C2PMSG_79__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_79__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_80 -#define MP1_SMN_C2PMSG_80__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_80__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_81 -#define MP1_SMN_C2PMSG_81__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_81__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_82 -#define MP1_SMN_C2PMSG_82__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_82__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_83 -#define MP1_SMN_C2PMSG_83__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_83__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_84 -#define MP1_SMN_C2PMSG_84__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_84__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_85 -#define MP1_SMN_C2PMSG_85__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_85__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_86 -#define MP1_SMN_C2PMSG_86__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_86__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_87 -#define MP1_SMN_C2PMSG_87__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_87__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_88 -#define MP1_SMN_C2PMSG_88__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_88__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_89 -#define MP1_SMN_C2PMSG_89__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_89__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_90 -#define MP1_SMN_C2PMSG_90__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_90__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_91 -#define MP1_SMN_C2PMSG_91__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_91__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_92 -#define MP1_SMN_C2PMSG_92__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_92__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_93 -#define MP1_SMN_C2PMSG_93__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_93__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_94 -#define MP1_SMN_C2PMSG_94__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_94__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_95 -#define MP1_SMN_C2PMSG_95__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_95__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_96 -#define MP1_SMN_C2PMSG_96__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_96__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_97 -#define MP1_SMN_C2PMSG_97__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_97__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_98 -#define MP1_SMN_C2PMSG_98__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_98__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_99 -#define MP1_SMN_C2PMSG_99__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_99__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_100 -#define MP1_SMN_C2PMSG_100__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_100__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_101 -#define MP1_SMN_C2PMSG_101__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_101__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_102 -#define MP1_SMN_C2PMSG_102__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_102__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_C2PMSG_103 -#define MP1_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 -#define MP1_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL -//MP1_SMN_IH_CREDIT -#define MP1_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 -#define MP1_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 -#define MP1_SMN_IH_CREDIT__CREDIT_VALUE_MASK 0x00000003L -#define MP1_SMN_IH_CREDIT__CLIENT_ID_MASK 0x00FF0000L -//MP1_SMN_IH_SW_INT -#define MP1_SMN_IH_SW_INT__ID__SHIFT 0x0 -#define MP1_SMN_IH_SW_INT__VALID__SHIFT 0x8 -#define MP1_SMN_IH_SW_INT__ID_MASK 0x000000FFL -#define MP1_SMN_IH_SW_INT__VALID_MASK 0x00000100L -//MP1_SMN_IH_SW_INT_CTRL -#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK__SHIFT 0x0 -#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK__SHIFT 0x8 -#define MP1_SMN_IH_SW_INT_CTRL__INT_MASK_MASK 0x00000001L -#define MP1_SMN_IH_SW_INT_CTRL__INT_ACK_MASK 0x00000100L -//MP1_SMN_FPS_CNT -#define MP1_SMN_FPS_CNT__COUNT__SHIFT 0x0 -#define MP1_SMN_FPS_CNT__COUNT_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH0 -#define MP1_SMN_EXT_SCRATCH0__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH0__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH1 -#define MP1_SMN_EXT_SCRATCH1__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH1__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH2 -#define MP1_SMN_EXT_SCRATCH2__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH2__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH3 -#define MP1_SMN_EXT_SCRATCH3__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH3__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH4 -#define MP1_SMN_EXT_SCRATCH4__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH4__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH5 -#define MP1_SMN_EXT_SCRATCH5__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH5__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH6 -#define MP1_SMN_EXT_SCRATCH6__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH6__DATA_MASK 0xFFFFFFFFL -//MP1_SMN_EXT_SCRATCH7 -#define MP1_SMN_EXT_SCRATCH7__DATA__SHIFT 0x0 -#define MP1_SMN_EXT_SCRATCH7__DATA_MASK 0xFFFFFFFFL - - -#endif diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 9f73a2f586d8..e38b191c7b7c 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -560,7 +560,7 @@ struct gpu_metrics_v1_2 { uint16_t current_vclk1; uint16_t current_dclk1; - /* Throttle status */ + /* Throttle status (ASIC dependent) */ uint32_t throttle_status; /* Fans */ @@ -648,6 +648,9 @@ struct gpu_metrics_v1_3 { uint16_t voltage_mem; uint16_t padding1; + + /* Throttle status (ASIC independent) */ + uint64_t indep_throttle_status; }; /* @@ -754,4 +757,57 @@ struct gpu_metrics_v2_1 { uint16_t padding[3]; }; +struct gpu_metrics_v2_2 { + 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; +}; + #endif diff --git a/drivers/gpu/drm/amd/include/navi10_enum.h b/drivers/gpu/drm/amd/include/navi10_enum.h index d5ead9680c6e..84bcb96f76ea 100644 --- a/drivers/gpu/drm/amd/include/navi10_enum.h +++ b/drivers/gpu/drm/amd/include/navi10_enum.h @@ -430,7 +430,7 @@ ARRAY_2D_DEPTH = 0x00000001, */ typedef enum ENUM_NUM_SIMD_PER_CU { -NUM_SIMD_PER_CU = 0x00000004, +NUM_SIMD_PER_CU = 0x00000002, } ENUM_NUM_SIMD_PER_CU; /* diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index b2335a1d3f98..769f58d5ae1a 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -411,7 +411,8 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev, struct amdgpu_device *adev = drm_to_adev(ddev); const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; struct pp_states_info data; - int i, buf_len, ret; + uint32_t i; + int buf_len, ret; if (amdgpu_in_reset(adev)) return -EPERM; @@ -433,9 +434,9 @@ static ssize_t amdgpu_get_pp_num_states(struct device *dev, pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); - buf_len = snprintf(buf, PAGE_SIZE, "states: %d\n", data.nums); + buf_len = sysfs_emit(buf, "states: %d\n", data.nums); for (i = 0; i < data.nums; i++) - buf_len += snprintf(buf + buf_len, PAGE_SIZE, "%d %s\n", i, + buf_len += sysfs_emit_at(buf, buf_len, "%d %s\n", i, (data.states[i] == POWER_STATE_TYPE_INTERNAL_BOOT) ? "boot" : (data.states[i] == POWER_STATE_TYPE_BATTERY) ? "battery" : (data.states[i] == POWER_STATE_TYPE_BALANCED) ? "balanced" : @@ -923,7 +924,7 @@ static ssize_t amdgpu_get_pp_od_clk_voltage(struct device *dev, size += amdgpu_dpm_print_clock_levels(adev, OD_RANGE, buf+size); size += amdgpu_dpm_print_clock_levels(adev, OD_CCLK, buf+size); } else { - size = snprintf(buf, PAGE_SIZE, "\n"); + size = sysfs_emit(buf, "\n"); } pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); @@ -1009,7 +1010,7 @@ static ssize_t amdgpu_get_pp_features(struct device *dev, if (adev->powerplay.pp_funcs->get_ppfeature_status) size = amdgpu_dpm_get_ppfeature_status(adev, buf); else - size = snprintf(buf, PAGE_SIZE, "\n"); + size = sysfs_emit(buf, "\n"); pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); @@ -1070,7 +1071,7 @@ static ssize_t amdgpu_get_pp_dpm_clock(struct device *dev, if (adev->powerplay.pp_funcs->print_clock_levels) size = amdgpu_dpm_print_clock_levels(adev, type, buf); else - size = snprintf(buf, PAGE_SIZE, "\n"); + size = sysfs_emit(buf, "\n"); pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); @@ -1469,7 +1470,7 @@ static ssize_t amdgpu_get_pp_power_profile_mode(struct device *dev, if (adev->powerplay.pp_funcs->get_power_profile_mode) size = amdgpu_dpm_get_power_profile_mode(adev, buf); else - size = snprintf(buf, PAGE_SIZE, "\n"); + size = sysfs_emit(buf, "\n"); pm_runtime_mark_last_busy(ddev->dev); pm_runtime_put_autosuspend(ddev->dev); @@ -2901,14 +2902,15 @@ static ssize_t amdgpu_hwmon_show_power_cap_min(struct device *dev, return sprintf(buf, "%i\n", 0); } -static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev, - struct device_attribute *attr, - char *buf) + +static ssize_t amdgpu_hwmon_show_power_cap_generic(struct device *dev, + struct device_attribute *attr, + char *buf, + enum pp_power_limit_level pp_limit_level) { struct amdgpu_device *adev = dev_get_drvdata(dev); const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; enum pp_power_type power_type = to_sensor_dev_attr(attr)->index; - enum pp_power_limit_level pp_limit_level = PP_PWR_LIMIT_MAX; uint32_t limit; ssize_t size; int r; @@ -2918,22 +2920,22 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev, if (adev->in_suspend && !adev->in_runpm) return -EPERM; + if ( !(pp_funcs && pp_funcs->get_power_limit)) + return -ENODATA; + r = pm_runtime_get_sync(adev_to_drm(adev)->dev); if (r < 0) { pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); return r; } - if (pp_funcs && pp_funcs->get_power_limit) - r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, - pp_limit_level, power_type); - else - r = -ENODATA; + r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, + pp_limit_level, power_type); if (!r) - size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000); + size = sysfs_emit(buf, "%u\n", limit * 1000000); else - size = snprintf(buf, PAGE_SIZE, "\n"); + size = sysfs_emit(buf, "\n"); pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); @@ -2941,85 +2943,31 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev, return size; } -static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev, + +static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev, struct device_attribute *attr, char *buf) { - struct amdgpu_device *adev = dev_get_drvdata(dev); - const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - enum pp_power_type power_type = to_sensor_dev_attr(attr)->index; - enum pp_power_limit_level pp_limit_level = PP_PWR_LIMIT_CURRENT; - uint32_t limit; - ssize_t size; - int r; + return amdgpu_hwmon_show_power_cap_generic(dev, attr, buf, PP_PWR_LIMIT_MAX); - if (amdgpu_in_reset(adev)) - return -EPERM; - if (adev->in_suspend && !adev->in_runpm) - return -EPERM; - - r = pm_runtime_get_sync(adev_to_drm(adev)->dev); - if (r < 0) { - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - return r; - } - - if (pp_funcs && pp_funcs->get_power_limit) - r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, - pp_limit_level, power_type); - else - r = -ENODATA; - - if (!r) - size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000); - else - size = snprintf(buf, PAGE_SIZE, "\n"); +} - pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); +static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return amdgpu_hwmon_show_power_cap_generic(dev, attr, buf, PP_PWR_LIMIT_CURRENT); - return size; } static ssize_t amdgpu_hwmon_show_power_cap_default(struct device *dev, struct device_attribute *attr, char *buf) { - struct amdgpu_device *adev = dev_get_drvdata(dev); - const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; - enum pp_power_type power_type = to_sensor_dev_attr(attr)->index; - enum pp_power_limit_level pp_limit_level = PP_PWR_LIMIT_DEFAULT; - uint32_t limit; - ssize_t size; - int r; - - if (amdgpu_in_reset(adev)) - return -EPERM; - if (adev->in_suspend && !adev->in_runpm) - return -EPERM; + return amdgpu_hwmon_show_power_cap_generic(dev, attr, buf, PP_PWR_LIMIT_DEFAULT); - r = pm_runtime_get_sync(adev_to_drm(adev)->dev); - if (r < 0) { - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - return r; - } - - if (pp_funcs && pp_funcs->get_power_limit) - r = pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, - pp_limit_level, power_type); - else - r = -ENODATA; - - if (!r) - size = snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000); - else - size = snprintf(buf, PAGE_SIZE, "\n"); - - pm_runtime_mark_last_busy(adev_to_drm(adev)->dev); - pm_runtime_put_autosuspend(adev_to_drm(adev)->dev); - - return size; } + static ssize_t amdgpu_hwmon_show_power_label(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h index 2f7f688424aa..3e89852e4820 100644 --- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h @@ -35,6 +35,48 @@ #define SMU_DPM_USER_PROFILE_RESTORE (1 << 0) +// Power Throttlers +#define SMU_THROTTLER_PPT0_BIT 0 +#define SMU_THROTTLER_PPT1_BIT 1 +#define SMU_THROTTLER_PPT2_BIT 2 +#define SMU_THROTTLER_PPT3_BIT 3 +#define SMU_THROTTLER_SPL_BIT 4 +#define SMU_THROTTLER_FPPT_BIT 5 +#define SMU_THROTTLER_SPPT_BIT 6 +#define SMU_THROTTLER_SPPT_APU_BIT 7 + +// Current Throttlers +#define SMU_THROTTLER_TDC_GFX_BIT 16 +#define SMU_THROTTLER_TDC_SOC_BIT 17 +#define SMU_THROTTLER_TDC_MEM_BIT 18 +#define SMU_THROTTLER_TDC_VDD_BIT 19 +#define SMU_THROTTLER_TDC_CVIP_BIT 20 +#define SMU_THROTTLER_EDC_CPU_BIT 21 +#define SMU_THROTTLER_EDC_GFX_BIT 22 +#define SMU_THROTTLER_APCC_BIT 23 + +// Temperature +#define SMU_THROTTLER_TEMP_GPU_BIT 32 +#define SMU_THROTTLER_TEMP_CORE_BIT 33 +#define SMU_THROTTLER_TEMP_MEM_BIT 34 +#define SMU_THROTTLER_TEMP_EDGE_BIT 35 +#define SMU_THROTTLER_TEMP_HOTSPOT_BIT 36 +#define SMU_THROTTLER_TEMP_SOC_BIT 37 +#define SMU_THROTTLER_TEMP_VR_GFX_BIT 38 +#define SMU_THROTTLER_TEMP_VR_SOC_BIT 39 +#define SMU_THROTTLER_TEMP_VR_MEM0_BIT 40 +#define SMU_THROTTLER_TEMP_VR_MEM1_BIT 41 +#define SMU_THROTTLER_TEMP_LIQUID0_BIT 42 +#define SMU_THROTTLER_TEMP_LIQUID1_BIT 43 +#define SMU_THROTTLER_VRHOT0_BIT 44 +#define SMU_THROTTLER_VRHOT1_BIT 45 +#define SMU_THROTTLER_PROCHOT_CPU_BIT 46 +#define SMU_THROTTLER_PROCHOT_GFX_BIT 47 + +// Other +#define SMU_THROTTLER_PPM_BIT 56 +#define SMU_THROTTLER_FIT_BIT 57 + struct smu_hw_power_state { unsigned int magic; }; @@ -723,7 +765,10 @@ struct pptable_funcs { /** * @get_power_limit: Get the device's power limits. */ - int (*get_power_limit)(struct smu_context *smu); + int (*get_power_limit)(struct smu_context *smu, + uint32_t *current_power_limit, + uint32_t *default_power_limit, + uint32_t *max_power_limit); /** * @get_ppt_limit: Get the device's ppt limits. @@ -932,7 +977,9 @@ struct pptable_funcs { * @disable_all_features_with_exception: Disable all features with * exception to those in &mask. */ - int (*disable_all_features_with_exception)(struct smu_context *smu, enum smu_feature_mask mask); + int (*disable_all_features_with_exception)(struct smu_context *smu, + bool no_hw_disablement, + enum smu_feature_mask mask); /** * @notify_display_change: Enable fast memory clock switching. @@ -1185,6 +1232,12 @@ struct pptable_funcs { */ int (*wait_for_event)(struct smu_context *smu, enum smu_event_type event, uint64_t event_arg); + + /** + * @sned_hbm_bad_pages_num: message SMU to update bad page number + * of SMUBUS table. + */ + int (*send_hbm_bad_pages_num)(struct smu_context *smu, uint32_t size); }; typedef enum { diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h index a3b28979bc82..1962a5877191 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h @@ -244,6 +244,9 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) int smu_v11_0_baco_enter(struct smu_context *smu); int smu_v11_0_baco_exit(struct smu_context *smu); +int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, + enum smu_v11_0_baco_seq baco_seq); + int smu_v11_0_mode1_reset(struct smu_context *smu); int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type, diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h index 6119a36b2cba..3fea2430dec0 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_v13_0.h @@ -26,6 +26,7 @@ #include "amdgpu_smu.h" #define SMU13_DRIVER_IF_VERSION_INV 0xFFFFFFFF +#define SMU13_DRIVER_IF_VERSION_YELLOW_CARP 0x03 #define SMU13_DRIVER_IF_VERSION_ALDE 0x07 /* MP Apertures */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index b4ea8b233240..ebe672142808 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -688,7 +688,10 @@ static int smu_late_init(void *handle) return ret; } - ret = smu_get_asic_power_limits(smu); + ret = smu_get_asic_power_limits(smu, + &smu->current_power_limit, + &smu->default_power_limit, + &smu->max_power_limit); if (ret) { dev_err(adev->dev, "Failed to get asic power limits!\n"); return ret; @@ -1379,15 +1382,20 @@ static int smu_disable_dpms(struct smu_context *smu) if (smu->uploading_custom_pp_table && (adev->asic_type >= CHIP_NAVI10) && (adev->asic_type <= CHIP_DIMGREY_CAVEFISH)) - return 0; + return smu_disable_all_features_with_exception(smu, + true, + SMU_FEATURE_COUNT); /* * For Sienna_Cichlid, PMFW will handle the features disablement properly * on BACO in. Driver involvement is unnecessary. */ - if ((adev->asic_type == CHIP_SIENNA_CICHLID) && + if (((adev->asic_type == CHIP_SIENNA_CICHLID) || + ((adev->asic_type >= CHIP_NAVI10) && (adev->asic_type <= CHIP_NAVI12))) && use_baco) - return 0; + return smu_disable_all_features_with_exception(smu, + true, + SMU_FEATURE_BACO_BIT); /* * For gpu reset, runpm and hibernation through BACO, @@ -1395,6 +1403,7 @@ static int smu_disable_dpms(struct smu_context *smu) */ if (use_baco && smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT)) { ret = smu_disable_all_features_with_exception(smu, + false, SMU_FEATURE_BACO_BIT); if (ret) dev_err(adev->dev, "Failed to disable smu features except BACO.\n"); @@ -1444,10 +1453,14 @@ static int smu_hw_fini(void *handle) if (smu->is_apu) { smu_powergate_sdma(&adev->smu, true); - smu_dpm_set_vcn_enable(smu, false); - smu_dpm_set_jpeg_enable(smu, false); } + smu_dpm_set_vcn_enable(smu, false); + smu_dpm_set_jpeg_enable(smu, false); + + adev->vcn.cur_state = AMD_PG_STATE_GATE; + adev->jpeg.cur_state = AMD_PG_STATE_GATE; + if (!smu->pm_enabled) return 0; @@ -2232,6 +2245,15 @@ int smu_get_power_limit(void *handle, } else { switch (limit_level) { case SMU_PPT_LIMIT_CURRENT: + if ((smu->adev->asic_type == CHIP_ALDEBARAN) || + (smu->adev->asic_type == CHIP_SIENNA_CICHLID) || + (smu->adev->asic_type == CHIP_NAVY_FLOUNDER) || + (smu->adev->asic_type == CHIP_DIMGREY_CAVEFISH) || + (smu->adev->asic_type == CHIP_BEIGE_GOBY)) + ret = smu_get_asic_power_limits(smu, + &smu->current_power_limit, + NULL, + NULL); *limit = smu->current_power_limit; break; case SMU_PPT_LIMIT_DEFAULT: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 5959019f51ad..094df6f87cfc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -211,6 +211,26 @@ static const struct cmn2asic_mapping arcturus_workload_map[PP_SMC_POWER_PROFILE_ WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; +static const uint8_t arcturus_throttler_map[] = { + [THROTTLER_TEMP_EDGE_BIT] = (SMU_THROTTLER_TEMP_EDGE_BIT), + [THROTTLER_TEMP_HOTSPOT_BIT] = (SMU_THROTTLER_TEMP_HOTSPOT_BIT), + [THROTTLER_TEMP_MEM_BIT] = (SMU_THROTTLER_TEMP_MEM_BIT), + [THROTTLER_TEMP_VR_GFX_BIT] = (SMU_THROTTLER_TEMP_VR_GFX_BIT), + [THROTTLER_TEMP_VR_MEM_BIT] = (SMU_THROTTLER_TEMP_VR_MEM0_BIT), + [THROTTLER_TEMP_VR_SOC_BIT] = (SMU_THROTTLER_TEMP_VR_SOC_BIT), + [THROTTLER_TDC_GFX_BIT] = (SMU_THROTTLER_TDC_GFX_BIT), + [THROTTLER_TDC_SOC_BIT] = (SMU_THROTTLER_TDC_SOC_BIT), + [THROTTLER_PPT0_BIT] = (SMU_THROTTLER_PPT0_BIT), + [THROTTLER_PPT1_BIT] = (SMU_THROTTLER_PPT1_BIT), + [THROTTLER_PPT2_BIT] = (SMU_THROTTLER_PPT2_BIT), + [THROTTLER_PPT3_BIT] = (SMU_THROTTLER_PPT3_BIT), + [THROTTLER_PPM_BIT] = (SMU_THROTTLER_PPM_BIT), + [THROTTLER_FIT_BIT] = (SMU_THROTTLER_FIT_BIT), + [THROTTLER_APCC_BIT] = (SMU_THROTTLER_APCC_BIT), + [THROTTLER_VRHOT0_BIT] = (SMU_THROTTLER_VRHOT0_BIT), + [THROTTLER_VRHOT1_BIT] = (SMU_THROTTLER_VRHOT1_BIT), +}; + static int arcturus_tables_init(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; @@ -237,7 +257,7 @@ static int arcturus_tables_init(struct smu_context *smu) return -ENOMEM; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_1); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_3); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) { kfree(smu_table->metrics_table); @@ -1174,7 +1194,10 @@ static int arcturus_get_fan_parameters(struct smu_context *smu) return 0; } -static int arcturus_get_power_limit(struct smu_context *smu) +static int arcturus_get_power_limit(struct smu_context *smu, + uint32_t *current_power_limit, + uint32_t *default_power_limit, + uint32_t *max_power_limit) { struct smu_11_0_powerplay_table *powerplay_table = (struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table; @@ -1190,17 +1213,24 @@ static int arcturus_get_power_limit(struct smu_context *smu) power_limit = pptable->SocketPowerLimitAc[PPT_THROTTLER_PPT0]; } - smu->current_power_limit = smu->default_power_limit = power_limit; - if (smu->od_enabled) { - od_percent = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + if (current_power_limit) + *current_power_limit = power_limit; + if (default_power_limit) + *default_power_limit = power_limit; + + if (max_power_limit) { + if (smu->od_enabled) { + od_percent = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - dev_dbg(smu->adev->dev, "ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_percent, power_limit); + dev_dbg(smu->adev->dev, "ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_percent, power_limit); + + power_limit *= (100 + od_percent); + power_limit /= 100; + } - power_limit *= (100 + od_percent); - power_limit /= 100; + *max_power_limit = power_limit; } - smu->max_power_limit = power_limit; return 0; } @@ -2278,8 +2308,8 @@ static ssize_t arcturus_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v1_1 *gpu_metrics = - (struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v1_3 *gpu_metrics = + (struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table; SmuMetrics_t metrics; int ret = 0; @@ -2289,7 +2319,7 @@ static ssize_t arcturus_get_gpu_metrics(struct smu_context *smu, if (ret) return ret; - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1); + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3); gpu_metrics->temperature_edge = metrics.TemperatureEdge; gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot; @@ -2318,6 +2348,9 @@ static ssize_t arcturus_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + arcturus_throttler_map); gpu_metrics->current_fan_speed = metrics.CurrFanSpeed; @@ -2330,7 +2363,7 @@ static ssize_t arcturus_get_gpu_metrics(struct smu_context *smu, *table = (void *)gpu_metrics; - return sizeof(struct gpu_metrics_v1_1); + return sizeof(struct gpu_metrics_v1_3); } static const struct pptable_funcs arcturus_ppt_funcs = { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 74a8c676e22c..1ba42b69ce74 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -80,10 +80,10 @@ static struct cmn2asic_msg_mapping navi10_message_map[SMU_MSG_MAX_COUNT] = { MSG_MAP(SetAllowedFeaturesMaskHigh, PPSMC_MSG_SetAllowedFeaturesMaskHigh, 0), MSG_MAP(EnableAllSmuFeatures, PPSMC_MSG_EnableAllSmuFeatures, 0), MSG_MAP(DisableAllSmuFeatures, PPSMC_MSG_DisableAllSmuFeatures, 0), - MSG_MAP(EnableSmuFeaturesLow, PPSMC_MSG_EnableSmuFeaturesLow, 1), - MSG_MAP(EnableSmuFeaturesHigh, PPSMC_MSG_EnableSmuFeaturesHigh, 1), - MSG_MAP(DisableSmuFeaturesLow, PPSMC_MSG_DisableSmuFeaturesLow, 1), - MSG_MAP(DisableSmuFeaturesHigh, PPSMC_MSG_DisableSmuFeaturesHigh, 1), + MSG_MAP(EnableSmuFeaturesLow, PPSMC_MSG_EnableSmuFeaturesLow, 0), + MSG_MAP(EnableSmuFeaturesHigh, PPSMC_MSG_EnableSmuFeaturesHigh, 0), + MSG_MAP(DisableSmuFeaturesLow, PPSMC_MSG_DisableSmuFeaturesLow, 0), + MSG_MAP(DisableSmuFeaturesHigh, PPSMC_MSG_DisableSmuFeaturesHigh, 0), MSG_MAP(GetEnabledSmuFeaturesLow, PPSMC_MSG_GetEnabledSmuFeaturesLow, 1), MSG_MAP(GetEnabledSmuFeaturesHigh, PPSMC_MSG_GetEnabledSmuFeaturesHigh, 1), MSG_MAP(SetWorkloadMask, PPSMC_MSG_SetWorkloadMask, 1), @@ -238,6 +238,28 @@ static struct cmn2asic_mapping navi10_workload_map[PP_SMC_POWER_PROFILE_COUNT] = WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; +static const uint8_t navi1x_throttler_map[] = { + [THROTTLER_TEMP_EDGE_BIT] = (SMU_THROTTLER_TEMP_EDGE_BIT), + [THROTTLER_TEMP_HOTSPOT_BIT] = (SMU_THROTTLER_TEMP_HOTSPOT_BIT), + [THROTTLER_TEMP_MEM_BIT] = (SMU_THROTTLER_TEMP_MEM_BIT), + [THROTTLER_TEMP_VR_GFX_BIT] = (SMU_THROTTLER_TEMP_VR_GFX_BIT), + [THROTTLER_TEMP_VR_MEM0_BIT] = (SMU_THROTTLER_TEMP_VR_MEM0_BIT), + [THROTTLER_TEMP_VR_MEM1_BIT] = (SMU_THROTTLER_TEMP_VR_MEM1_BIT), + [THROTTLER_TEMP_VR_SOC_BIT] = (SMU_THROTTLER_TEMP_VR_SOC_BIT), + [THROTTLER_TEMP_LIQUID0_BIT] = (SMU_THROTTLER_TEMP_LIQUID0_BIT), + [THROTTLER_TEMP_LIQUID1_BIT] = (SMU_THROTTLER_TEMP_LIQUID1_BIT), + [THROTTLER_TDC_GFX_BIT] = (SMU_THROTTLER_TDC_GFX_BIT), + [THROTTLER_TDC_SOC_BIT] = (SMU_THROTTLER_TDC_SOC_BIT), + [THROTTLER_PPT0_BIT] = (SMU_THROTTLER_PPT0_BIT), + [THROTTLER_PPT1_BIT] = (SMU_THROTTLER_PPT1_BIT), + [THROTTLER_PPT2_BIT] = (SMU_THROTTLER_PPT2_BIT), + [THROTTLER_PPT3_BIT] = (SMU_THROTTLER_PPT3_BIT), + [THROTTLER_FIT_BIT] = (SMU_THROTTLER_FIT_BIT), + [THROTTLER_PPM_BIT] = (SMU_THROTTLER_PPM_BIT), + [THROTTLER_APCC_BIT] = (SMU_THROTTLER_APCC_BIT), +}; + + static bool is_asic_secure(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -446,30 +468,6 @@ static int navi10_store_powerplay_table(struct smu_context *smu) return 0; } -static int navi10_set_mp1_state(struct smu_context *smu, - enum pp_mp1_state mp1_state) -{ - struct amdgpu_device *adev = smu->adev; - uint32_t mp1_fw_flags; - int ret = 0; - - ret = smu_cmn_set_mp1_state(smu, mp1_state); - if (ret) - return ret; - - if (mp1_state == PP_MP1_STATE_UNLOAD) { - mp1_fw_flags = RREG32_PCIE(MP1_Public | - (smnMP1_FIRMWARE_FLAGS & 0xffffffff)); - - mp1_fw_flags &= ~MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK; - - WREG32_PCIE(MP1_Public | - (smnMP1_FIRMWARE_FLAGS & 0xffffffff), mp1_fw_flags); - } - - return 0; -} - static int navi10_setup_pptable(struct smu_context *smu) { int ret = 0; @@ -2138,7 +2136,10 @@ static int navi10_display_disable_memory_clock_switch(struct smu_context *smu, return ret; } -static int navi10_get_power_limit(struct smu_context *smu) +static int navi10_get_power_limit(struct smu_context *smu, + uint32_t *current_power_limit, + uint32_t *default_power_limit, + uint32_t *max_power_limit) { struct smu_11_0_powerplay_table *powerplay_table = (struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table; @@ -2155,18 +2156,25 @@ static int navi10_get_power_limit(struct smu_context *smu) power_limit = pptable->SocketPowerLimitAc[PPT_THROTTLER_PPT0]; } - smu->current_power_limit = smu->default_power_limit = power_limit; - if (smu->od_enabled && - navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) { - od_percent = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); + if (current_power_limit) + *current_power_limit = power_limit; + if (default_power_limit) + *default_power_limit = power_limit; - dev_dbg(smu->adev->dev, "ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_percent, power_limit); + if (max_power_limit) { + if (smu->od_enabled && + navi10_od_feature_is_supported(od_settings, SMU_11_0_ODCAP_POWER_LIMIT)) { + od_percent = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]); - power_limit *= (100 + od_percent); - power_limit /= 100; + dev_dbg(smu->adev->dev, "ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_percent, power_limit); + + power_limit *= (100 + od_percent); + power_limit /= 100; + } + + *max_power_limit = power_limit; } - smu->max_power_limit = power_limit; return 0; } @@ -2257,6 +2265,29 @@ static int navi10_overdrive_get_gfx_clk_base_voltage(struct smu_context *smu, return 0; } +static int navi10_baco_enter(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm) + return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO); + else + return smu_v11_0_baco_enter(smu); +} + +static int navi10_baco_exit(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm) { + /* Wait for PMFW handling for the Dstate change */ + msleep(10); + return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); + } else { + return smu_v11_0_baco_exit(smu); + } +} + static int navi10_set_default_od_settings(struct smu_context *smu) { OverDriveTable_t *od_table = @@ -2676,6 +2707,9 @@ static ssize_t navi10_get_legacy_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + navi1x_throttler_map); gpu_metrics->current_fan_speed = metrics.CurrFanSpeed; @@ -2753,6 +2787,9 @@ static ssize_t navi10_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + navi1x_throttler_map); gpu_metrics->current_fan_speed = metrics.CurrFanSpeed; @@ -2829,6 +2866,9 @@ static ssize_t navi12_get_legacy_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + navi1x_throttler_map); gpu_metrics->current_fan_speed = metrics.CurrFanSpeed; @@ -2911,6 +2951,9 @@ static ssize_t navi12_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + navi1x_throttler_map); gpu_metrics->current_fan_speed = metrics.CurrFanSpeed; @@ -3095,8 +3138,8 @@ static const struct pptable_funcs navi10_ppt_funcs = { .baco_is_support = smu_v11_0_baco_is_support, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, - .baco_enter = smu_v11_0_baco_enter, - .baco_exit = smu_v11_0_baco_exit, + .baco_enter = navi10_baco_enter, + .baco_exit = navi10_baco_exit, .get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq, .set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range, .set_default_od_settings = navi10_set_default_od_settings, @@ -3112,7 +3155,7 @@ static const struct pptable_funcs navi10_ppt_funcs = { .get_fan_parameters = navi10_get_fan_parameters, .post_init = navi10_post_smu_init, .interrupt_work = smu_v11_0_interrupt_work, - .set_mp1_state = navi10_set_mp1_state, + .set_mp1_state = smu_cmn_set_mp1_state, }; void navi10_set_ppt_funcs(struct smu_context *smu) 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 f01e919e1f89..c751f717a0da 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 @@ -239,6 +239,27 @@ static struct cmn2asic_mapping sienna_cichlid_workload_map[PP_SMC_POWER_PROFILE_ WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; +static const uint8_t sienna_cichlid_throttler_map[] = { + [THROTTLER_TEMP_EDGE_BIT] = (SMU_THROTTLER_TEMP_EDGE_BIT), + [THROTTLER_TEMP_HOTSPOT_BIT] = (SMU_THROTTLER_TEMP_HOTSPOT_BIT), + [THROTTLER_TEMP_MEM_BIT] = (SMU_THROTTLER_TEMP_MEM_BIT), + [THROTTLER_TEMP_VR_GFX_BIT] = (SMU_THROTTLER_TEMP_VR_GFX_BIT), + [THROTTLER_TEMP_VR_MEM0_BIT] = (SMU_THROTTLER_TEMP_VR_MEM0_BIT), + [THROTTLER_TEMP_VR_MEM1_BIT] = (SMU_THROTTLER_TEMP_VR_MEM1_BIT), + [THROTTLER_TEMP_VR_SOC_BIT] = (SMU_THROTTLER_TEMP_VR_SOC_BIT), + [THROTTLER_TEMP_LIQUID0_BIT] = (SMU_THROTTLER_TEMP_LIQUID0_BIT), + [THROTTLER_TEMP_LIQUID1_BIT] = (SMU_THROTTLER_TEMP_LIQUID1_BIT), + [THROTTLER_TDC_GFX_BIT] = (SMU_THROTTLER_TDC_GFX_BIT), + [THROTTLER_TDC_SOC_BIT] = (SMU_THROTTLER_TDC_SOC_BIT), + [THROTTLER_PPT0_BIT] = (SMU_THROTTLER_PPT0_BIT), + [THROTTLER_PPT1_BIT] = (SMU_THROTTLER_PPT1_BIT), + [THROTTLER_PPT2_BIT] = (SMU_THROTTLER_PPT2_BIT), + [THROTTLER_PPT3_BIT] = (SMU_THROTTLER_PPT3_BIT), + [THROTTLER_FIT_BIT] = (SMU_THROTTLER_FIT_BIT), + [THROTTLER_PPM_BIT] = (SMU_THROTTLER_PPM_BIT), + [THROTTLER_APCC_BIT] = (SMU_THROTTLER_APCC_BIT), +}; + static int sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu, uint32_t *feature_mask, uint32_t num) @@ -449,7 +470,7 @@ static int sienna_cichlid_tables_init(struct smu_context *smu) goto err0_out; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_1); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_3); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) goto err1_out; @@ -1770,7 +1791,10 @@ static int sienna_cichlid_display_disable_memory_clock_switch(struct smu_context return ret; } -static int sienna_cichlid_get_power_limit(struct smu_context *smu) +static int sienna_cichlid_get_power_limit(struct smu_context *smu, + uint32_t *current_power_limit, + uint32_t *default_power_limit, + uint32_t *max_power_limit) { struct smu_11_0_7_powerplay_table *powerplay_table = (struct smu_11_0_7_powerplay_table *)smu->smu_table.power_play_table; @@ -1783,17 +1807,23 @@ static int sienna_cichlid_get_power_limit(struct smu_context *smu) power_limit = table_member[PPT_THROTTLER_PPT0]; } - smu->current_power_limit = smu->default_power_limit = power_limit; - if (smu->od_enabled) { - od_percent = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); + if (current_power_limit) + *current_power_limit = power_limit; + if (default_power_limit) + *default_power_limit = power_limit; + + if (max_power_limit) { + if (smu->od_enabled) { + od_percent = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_7_ODSETTING_POWERPERCENTAGE]); - dev_dbg(smu->adev->dev, "ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_percent, power_limit); + dev_dbg(smu->adev->dev, "ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_percent, power_limit); - power_limit *= (100 + od_percent); - power_limit /= 100; + power_limit *= (100 + od_percent); + power_limit /= 100; + } + *max_power_limit = power_limit; } - smu->max_power_limit = power_limit; return 0; } @@ -2100,6 +2130,29 @@ static int sienna_cichlid_run_btc(struct smu_context *smu) return smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL); } +static int sienna_cichlid_baco_enter(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm) + return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO); + else + return smu_v11_0_baco_enter(smu); +} + +static int sienna_cichlid_baco_exit(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->in_runpm) { + /* Wait for PMFW handling for the Dstate change */ + msleep(10); + return smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); + } else { + return smu_v11_0_baco_exit(smu); + } +} + static bool sienna_cichlid_is_mode1_reset_supported(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; @@ -3620,8 +3673,8 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v1_1 *gpu_metrics = - (struct gpu_metrics_v1_1 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v1_3 *gpu_metrics = + (struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table; SmuMetricsExternal_t metrics_external; SmuMetrics_t *metrics = &(metrics_external.SmuMetrics); @@ -3635,7 +3688,7 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, if (ret) return ret; - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 1); + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3); gpu_metrics->temperature_edge = metrics->TemperatureEdge; gpu_metrics->temperature_hotspot = metrics->TemperatureHotspot; @@ -3670,6 +3723,9 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk1 = metrics->CurrClock[PPCLK_DCLK_1]; gpu_metrics->throttle_status = metrics->ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics->ThrottlerStatus, + sienna_cichlid_throttler_map); gpu_metrics->current_fan_speed = metrics->CurrFanSpeed; @@ -3692,7 +3748,7 @@ static ssize_t sienna_cichlid_get_gpu_metrics(struct smu_context *smu, *table = (void *)gpu_metrics; - return sizeof(struct gpu_metrics_v1_1); + return sizeof(struct gpu_metrics_v1_3); } static int sienna_cichlid_enable_mgpu_fan_boost(struct smu_context *smu) @@ -3875,8 +3931,8 @@ static const struct pptable_funcs sienna_cichlid_ppt_funcs = { .baco_is_support = smu_v11_0_baco_is_support, .baco_get_state = smu_v11_0_baco_get_state, .baco_set_state = smu_v11_0_baco_set_state, - .baco_enter = smu_v11_0_baco_enter, - .baco_exit = smu_v11_0_baco_exit, + .baco_enter = sienna_cichlid_baco_enter, + .baco_exit = sienna_cichlid_baco_exit, .mode1_reset_is_support = sienna_cichlid_is_mode1_reset_supported, .mode1_reset = smu_v11_0_mode1_reset, .get_dpm_ultimate_freq = sienna_cichlid_get_dpm_ultimate_freq, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c index e1e1c268f661..0a5d46ac9ccd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/smu_v11_0.c @@ -1474,7 +1474,8 @@ int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu) return smu_cmn_send_smc_msg(smu, SMU_MSG_BacoAudioD3PME, NULL); } -static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v11_0_baco_seq baco_seq) +int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, + enum smu_v11_0_baco_seq baco_seq) { return smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_ArmD3, baco_seq, NULL); } @@ -1527,6 +1528,7 @@ int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state) case CHIP_SIENNA_CICHLID: case CHIP_NAVY_FLOUNDER: case CHIP_DIMGREY_CAVEFISH: + case CHIP_BEIGE_GOBY: if (amdgpu_runtime_pm == 2) ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_EnterBaco, @@ -1578,16 +1580,8 @@ out: int smu_v11_0_baco_enter(struct smu_context *smu) { - struct amdgpu_device *adev = smu->adev; int ret = 0; - /* Arcturus does not need this audio workaround */ - if (adev->asic_type != CHIP_ARCTURUS) { - ret = smu_v11_0_baco_set_armd3_sequence(smu, BACO_SEQ_BACO); - if (ret) - return ret; - } - ret = smu_v11_0_baco_set_state(smu, SMU_BACO_STATE_ENTER); if (ret) return ret; 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 77f532a49e37..18681dc458da 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -190,6 +190,20 @@ static struct cmn2asic_mapping vangogh_workload_map[PP_SMC_POWER_PROFILE_COUNT] WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; +static const uint8_t vangogh_throttler_map[] = { + [THROTTLER_STATUS_BIT_SPL] = (SMU_THROTTLER_SPL_BIT), + [THROTTLER_STATUS_BIT_FPPT] = (SMU_THROTTLER_FPPT_BIT), + [THROTTLER_STATUS_BIT_SPPT] = (SMU_THROTTLER_SPPT_BIT), + [THROTTLER_STATUS_BIT_SPPT_APU] = (SMU_THROTTLER_SPPT_APU_BIT), + [THROTTLER_STATUS_BIT_THM_CORE] = (SMU_THROTTLER_TEMP_CORE_BIT), + [THROTTLER_STATUS_BIT_THM_GFX] = (SMU_THROTTLER_TEMP_GPU_BIT), + [THROTTLER_STATUS_BIT_THM_SOC] = (SMU_THROTTLER_TEMP_SOC_BIT), + [THROTTLER_STATUS_BIT_TDC_VDD] = (SMU_THROTTLER_TDC_VDD_BIT), + [THROTTLER_STATUS_BIT_TDC_SOC] = (SMU_THROTTLER_TDC_SOC_BIT), + [THROTTLER_STATUS_BIT_TDC_GFX] = (SMU_THROTTLER_TDC_GFX_BIT), + [THROTTLER_STATUS_BIT_TDC_CVIP] = (SMU_THROTTLER_TDC_CVIP_BIT), +}; + static int vangogh_tables_init(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; @@ -226,7 +240,7 @@ 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_1); + 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; @@ -1632,8 +1646,8 @@ static ssize_t vangogh_get_legacy_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v2_1 *gpu_metrics = - (struct gpu_metrics_v2_1 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v2_2 *gpu_metrics = + (struct gpu_metrics_v2_2 *)smu_table->gpu_metrics_table; SmuMetrics_legacy_t metrics; int ret = 0; @@ -1641,7 +1655,7 @@ static ssize_t vangogh_get_legacy_gpu_metrics(struct smu_context *smu, if (ret) return ret; - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 1); + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 2); gpu_metrics->temperature_gfx = metrics.GfxTemperature; gpu_metrics->temperature_soc = metrics.SocTemperature; @@ -1674,20 +1688,23 @@ static ssize_t vangogh_get_legacy_gpu_metrics(struct smu_context *smu, 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_1); + return sizeof(struct gpu_metrics_v2_2); } static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v2_1 *gpu_metrics = - (struct gpu_metrics_v2_1 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v2_2 *gpu_metrics = + (struct gpu_metrics_v2_2 *)smu_table->gpu_metrics_table; SmuMetrics_t metrics; int ret = 0; @@ -1695,7 +1712,7 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, if (ret) return ret; - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 1); + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 2); gpu_metrics->temperature_gfx = metrics.Current.GfxTemperature; gpu_metrics->temperature_soc = metrics.Current.SocTemperature; @@ -1735,12 +1752,15 @@ static ssize_t vangogh_get_gpu_metrics(struct smu_context *smu, 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_1); + return sizeof(struct gpu_metrics_v2_2); } static ssize_t vangogh_common_get_gpu_metrics(struct smu_context *smu, @@ -2051,7 +2071,10 @@ static int vangogh_mode2_reset(struct smu_context *smu) return vangogh_mode_reset(smu, SMU_RESET_MODE_2); } -static int vangogh_get_power_limit(struct smu_context *smu) +static int vangogh_get_power_limit(struct smu_context *smu, + uint32_t *current_power_limit, + uint32_t *default_power_limit, + uint32_t *max_power_limit) { struct smu_11_5_power_context *power_context = smu->smu_power.power_context; @@ -2067,8 +2090,12 @@ static int vangogh_get_power_limit(struct smu_context *smu) return ret; } /* convert from milliwatt to watt */ - smu->current_power_limit = smu->default_power_limit = ppt_limit / 1000; - smu->max_power_limit = 29; + if (current_power_limit) + *current_power_limit = ppt_limit / 1000; + if (default_power_limit) + *default_power_limit = ppt_limit / 1000; + if (max_power_limit) + *max_power_limit = 29; ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetFastPPTLimit, &ppt_limit); if (ret) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c index 1c399c4ab4dc..9a9c24a6ec35 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c @@ -128,6 +128,22 @@ static struct cmn2asic_mapping renoir_workload_map[PP_SMC_POWER_PROFILE_COUNT] = WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM, WORKLOAD_PPLIB_CUSTOM_BIT), }; +static const uint8_t renoir_throttler_map[] = { + [THROTTLER_STATUS_BIT_SPL] = (SMU_THROTTLER_SPL_BIT), + [THROTTLER_STATUS_BIT_FPPT] = (SMU_THROTTLER_FPPT_BIT), + [THROTTLER_STATUS_BIT_SPPT] = (SMU_THROTTLER_SPPT_BIT), + [THROTTLER_STATUS_BIT_SPPT_APU] = (SMU_THROTTLER_SPPT_APU_BIT), + [THROTTLER_STATUS_BIT_THM_CORE] = (SMU_THROTTLER_TEMP_CORE_BIT), + [THROTTLER_STATUS_BIT_THM_GFX] = (SMU_THROTTLER_TEMP_GPU_BIT), + [THROTTLER_STATUS_BIT_THM_SOC] = (SMU_THROTTLER_TEMP_SOC_BIT), + [THROTTLER_STATUS_BIT_TDC_VDD] = (SMU_THROTTLER_TDC_VDD_BIT), + [THROTTLER_STATUS_BIT_TDC_SOC] = (SMU_THROTTLER_TDC_SOC_BIT), + [THROTTLER_STATUS_BIT_PROCHOT_CPU] = (SMU_THROTTLER_PROCHOT_CPU_BIT), + [THROTTLER_STATUS_BIT_PROCHOT_GFX] = (SMU_THROTTLER_PROCHOT_GFX_BIT), + [THROTTLER_STATUS_BIT_EDC_CPU] = (SMU_THROTTLER_EDC_CPU_BIT), + [THROTTLER_STATUS_BIT_EDC_GFX] = (SMU_THROTTLER_EDC_GFX_BIT), +}; + static int renoir_init_smc_tables(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; @@ -153,7 +169,7 @@ static int renoir_init_smc_tables(struct smu_context *smu) if (!smu_table->watermarks_table) goto err2_out; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_1); + 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 err3_out; @@ -1164,6 +1180,28 @@ static int renoir_get_smu_metrics_data(struct smu_context *smu, case METRICS_VOLTAGE_VDDSOC: *value = metrics->Voltage[1]; break; + case METRICS_SS_APU_SHARE: + /* return the percentage of APU power with respect to APU's power limit. + * percentage is reported, this isn't boost value. Smartshift power + * boost/shift is only when the percentage is more than 100. + */ + if (metrics->StapmOriginalLimit > 0) + *value = (metrics->ApuPower * 100) / metrics->StapmOriginalLimit; + else + *value = 0; + break; + case METRICS_SS_DGPU_SHARE: + /* return the percentage of dGPU power with respect to dGPU's power limit. + * percentage is reported, this isn't boost value. Smartshift power + * boost/shift is only when the percentage is more than 100. + */ + if ((metrics->dGpuPower > 0) && + (metrics->StapmCurrentLimit > metrics->StapmOriginalLimit)) + *value = (metrics->dGpuPower * 100) / + (metrics->StapmCurrentLimit - metrics->StapmOriginalLimit); + else + *value = 0; + break; default: *value = UINT_MAX; break; @@ -1235,6 +1273,18 @@ static int renoir_read_sensor(struct smu_context *smu, (uint32_t *)data); *size = 4; break; + case AMDGPU_PP_SENSOR_SS_APU_SHARE: + ret = renoir_get_smu_metrics_data(smu, + METRICS_SS_APU_SHARE, + (uint32_t *)data); + *size = 4; + break; + case AMDGPU_PP_SENSOR_SS_DGPU_SHARE: + ret = renoir_get_smu_metrics_data(smu, + METRICS_SS_DGPU_SHARE, + (uint32_t *)data); + *size = 4; + break; default: ret = -EOPNOTSUPP; break; @@ -1264,8 +1314,8 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v2_1 *gpu_metrics = - (struct gpu_metrics_v2_1 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v2_2 *gpu_metrics = + (struct gpu_metrics_v2_2 *)smu_table->gpu_metrics_table; SmuMetrics_t metrics; int ret = 0; @@ -1273,7 +1323,7 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu, if (ret) return ret; - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 1); + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 2); gpu_metrics->temperature_gfx = metrics.GfxTemperature; gpu_metrics->temperature_soc = metrics.SocTemperature; @@ -1311,6 +1361,9 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_l3clk[1] = metrics.L3Frequency[1]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + renoir_throttler_map); gpu_metrics->fan_pwm = metrics.FanPwm; @@ -1318,7 +1371,7 @@ static ssize_t renoir_get_gpu_metrics(struct smu_context *smu, *table = (void *)gpu_metrics; - return sizeof(struct gpu_metrics_v2_1); + return sizeof(struct gpu_metrics_v2_2); } static int renoir_gfx_state_change_set(struct smu_context *smu, uint32_t state) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile b/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile index 9b3a8503f5cd..d4c4c495762c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/Makefile @@ -23,7 +23,7 @@ # Makefile for the 'smu manager' sub-component of powerplay. # It provides the smu management services for the driver. -SMU13_MGR = smu_v13_0.o aldebaran_ppt.o smu_v13_0_1.o yellow_carp_ppt.o +SMU13_MGR = smu_v13_0.o aldebaran_ppt.o yellow_carp_ppt.o AMD_SWSMU_SMU13MGR = $(addprefix $(AMD_SWSMU_PATH)/smu13/,$(SMU13_MGR)) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index 6ee9c4186f02..9316a726195c 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -191,6 +191,20 @@ static const struct cmn2asic_mapping aldebaran_table_map[SMU_TABLE_COUNT] = { TAB_MAP(I2C_COMMANDS), }; +static const uint8_t aldebaran_throttler_map[] = { + [THROTTLER_PPT0_BIT] = (SMU_THROTTLER_PPT0_BIT), + [THROTTLER_PPT1_BIT] = (SMU_THROTTLER_PPT1_BIT), + [THROTTLER_TDC_GFX_BIT] = (SMU_THROTTLER_TDC_GFX_BIT), + [THROTTLER_TDC_SOC_BIT] = (SMU_THROTTLER_TDC_SOC_BIT), + [THROTTLER_TDC_HBM_BIT] = (SMU_THROTTLER_TDC_MEM_BIT), + [THROTTLER_TEMP_GPU_BIT] = (SMU_THROTTLER_TEMP_GPU_BIT), + [THROTTLER_TEMP_MEM_BIT] = (SMU_THROTTLER_TEMP_MEM_BIT), + [THROTTLER_TEMP_VR_GFX_BIT] = (SMU_THROTTLER_TEMP_VR_GFX_BIT), + [THROTTLER_TEMP_VR_SOC_BIT] = (SMU_THROTTLER_TEMP_VR_SOC_BIT), + [THROTTLER_TEMP_VR_MEM_BIT] = (SMU_THROTTLER_TEMP_VR_MEM0_BIT), + [THROTTLER_APCC_BIT] = (SMU_THROTTLER_APCC_BIT), +}; + static int aldebaran_tables_init(struct smu_context *smu) { struct smu_table_context *smu_table = &smu->smu_table; @@ -213,7 +227,7 @@ static int aldebaran_tables_init(struct smu_context *smu) return -ENOMEM; smu_table->metrics_time = 0; - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_2); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v1_3); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) { kfree(smu_table->metrics_table); @@ -510,6 +524,16 @@ static int aldebaran_freqs_in_same_level(int32_t frequency1, return (abs(frequency1 - frequency2) <= EPSILON); } +static bool aldebaran_is_primary(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + + if (adev->smuio.funcs && adev->smuio.funcs->get_die_id) + return adev->smuio.funcs->get_die_id(adev) == 0; + + return true; +} + static int aldebaran_get_smu_metrics_data(struct smu_context *smu, MetricsMember_t member, uint32_t *value) @@ -563,7 +587,10 @@ static int aldebaran_get_smu_metrics_data(struct smu_context *smu, *value = metrics->AverageUclkActivity; break; case METRICS_AVERAGE_SOCKETPOWER: - *value = metrics->AverageSocketPower << 8; + /* Valid power data is available only from primary die */ + *value = aldebaran_is_primary(smu) ? + metrics->AverageSocketPower << 8 : + 0; break; case METRICS_TEMPERATURE_EDGE: *value = metrics->TemperatureEdge * @@ -1132,7 +1159,10 @@ static int aldebaran_read_sensor(struct smu_context *smu, return ret; } -static int aldebaran_get_power_limit(struct smu_context *smu) +static int aldebaran_get_power_limit(struct smu_context *smu, + uint32_t *current_power_limit, + uint32_t *default_power_limit, + uint32_t *max_power_limit) { PPTable_t *pptable = smu->smu_table.driver_pptable; uint32_t power_limit = 0; @@ -1141,24 +1171,46 @@ static int aldebaran_get_power_limit(struct smu_context *smu) if (!smu_cmn_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) return -EINVAL; - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetPptLimit, &power_limit); + /* Valid power data is available only from primary die. + * For secondary die show the value as 0. + */ + if (aldebaran_is_primary(smu)) { + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_GetPptLimit, + &power_limit); - if (ret) { - /* the last hope to figure out the ppt limit */ - if (!pptable) { - dev_err(smu->adev->dev, "Cannot get PPT limit due to pptable missing!"); - return -EINVAL; + if (ret) { + /* the last hope to figure out the ppt limit */ + if (!pptable) { + dev_err(smu->adev->dev, + "Cannot get PPT limit due to pptable missing!"); + return -EINVAL; + } + power_limit = pptable->PptLimit; } - power_limit = pptable->PptLimit; } - smu->current_power_limit = smu->default_power_limit = power_limit; - if (pptable) - smu->max_power_limit = pptable->PptLimit; + if (current_power_limit) + *current_power_limit = power_limit; + if (default_power_limit) + *default_power_limit = power_limit; + + if (max_power_limit) { + if (pptable) + *max_power_limit = pptable->PptLimit; + } return 0; } +static int aldebaran_set_power_limit(struct smu_context *smu, uint32_t n) +{ + /* Power limit can be set only through primary die */ + if (aldebaran_is_primary(smu)) + return smu_v13_0_set_power_limit(smu, n); + + return -EINVAL; +} + static int aldebaran_system_features_control(struct smu_context *smu, bool enable) { int ret; @@ -1706,8 +1758,8 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, void **table) { struct smu_table_context *smu_table = &smu->smu_table; - struct gpu_metrics_v1_2 *gpu_metrics = - (struct gpu_metrics_v1_2 *)smu_table->gpu_metrics_table; + struct gpu_metrics_v1_3 *gpu_metrics = + (struct gpu_metrics_v1_3 *)smu_table->gpu_metrics_table; SmuMetrics_t metrics; int i, ret = 0; @@ -1717,7 +1769,7 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, if (ret) return ret; - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 2); + smu_cmn_init_soft_gpu_metrics(gpu_metrics, 1, 3); gpu_metrics->temperature_edge = metrics.TemperatureEdge; gpu_metrics->temperature_hotspot = metrics.TemperatureHotspot; @@ -1730,10 +1782,16 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, gpu_metrics->average_umc_activity = metrics.AverageUclkActivity; gpu_metrics->average_mm_activity = 0; - gpu_metrics->average_socket_power = metrics.AverageSocketPower; - gpu_metrics->energy_accumulator = + /* Valid power data is available only from primary die */ + if (aldebaran_is_primary(smu)) { + gpu_metrics->average_socket_power = metrics.AverageSocketPower; + gpu_metrics->energy_accumulator = (uint64_t)metrics.EnergyAcc64bitHigh << 32 | metrics.EnergyAcc64bitLow; + } else { + gpu_metrics->average_socket_power = 0; + gpu_metrics->energy_accumulator = 0; + } gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency; gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency; @@ -1748,6 +1806,9 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, gpu_metrics->current_dclk0 = metrics.CurrClock[PPCLK_DCLK]; gpu_metrics->throttle_status = metrics.ThrottlerStatus; + gpu_metrics->indep_throttle_status = + smu_cmn_get_indep_throttler_status(metrics.ThrottlerStatus, + aldebaran_throttler_map); gpu_metrics->current_fan_speed = 0; @@ -1769,7 +1830,7 @@ static ssize_t aldebaran_get_gpu_metrics(struct smu_context *smu, *table = (void *)gpu_metrics; - return sizeof(struct gpu_metrics_v1_2); + return sizeof(struct gpu_metrics_v1_3); } static int aldebaran_mode2_reset(struct smu_context *smu) @@ -1862,6 +1923,20 @@ static int aldebaran_set_mp1_state(struct smu_context *smu, } } +static int aldebaran_smu_send_hbm_bad_page_num(struct smu_context *smu, + uint32_t size) +{ + int ret = 0; + + /* message SMU to update the bad page number on SMUBUS */ + ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_SetNumBadHbmPagesRetired, size, NULL); + if (ret) + dev_err(smu->adev->dev, "[%s] failed to message SMU to update HBM bad pages number\n", + __func__); + + return ret; +} + static const struct pptable_funcs aldebaran_ppt_funcs = { /* init dpm */ .get_allowed_feature_mask = aldebaran_get_allowed_feature_mask, @@ -1898,7 +1973,7 @@ static const struct pptable_funcs aldebaran_ppt_funcs = { .get_enabled_mask = smu_cmn_get_enabled_mask, .feature_is_enabled = smu_cmn_feature_is_enabled, .disable_all_features_with_exception = smu_cmn_disable_all_features_with_exception, - .set_power_limit = smu_v13_0_set_power_limit, + .set_power_limit = aldebaran_set_power_limit, .init_max_sustainable_clocks = smu_v13_0_init_max_sustainable_clocks, .enable_thermal_alert = smu_v13_0_enable_thermal_alert, .disable_thermal_alert = smu_v13_0_disable_thermal_alert, @@ -1924,6 +1999,7 @@ static const struct pptable_funcs aldebaran_ppt_funcs = { .wait_for_event = smu_v13_0_wait_for_event, .i2c_init = aldebaran_i2c_control_init, .i2c_fini = aldebaran_i2c_control_fini, + .send_hbm_bad_pages_num = aldebaran_smu_send_hbm_bad_page_num, }; void aldebaran_set_ppt_funcs(struct smu_context *smu) 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 a3dc7194aaf8..a421ba85bd6d 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 @@ -210,6 +210,9 @@ int smu_v13_0_check_fw_version(struct smu_context *smu) case CHIP_ALDEBARAN: smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE; break; + case CHIP_YELLOW_CARP: + smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_YELLOW_CARP; + break; default: dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type); smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_INV; @@ -694,6 +697,27 @@ failed: return ret; } +int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable) +{ + int ret = 0; + struct amdgpu_device *adev = smu->adev; + + switch (adev->asic_type) { + case CHIP_YELLOW_CARP: + if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) + return 0; + if (enable) + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL); + else + ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL); + break; + default: + break; + } + + return ret; +} + int smu_v13_0_system_features_control(struct smu_context *smu, bool en) { diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c deleted file mode 100644 index 61917b49f2bf..000000000000 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_1.c +++ /dev/null @@ -1,311 +0,0 @@ -/* - * Copyright 2020 Advanced Micro Devices, Inc. - * - * Permission is hereby granted, free of charge, to any person obtaining a - * copy of this software and associated documentation files (the "Software"), - * to deal in the Software without restriction, including without limitation - * the rights to use, copy, modify, merge, publish, distribute, sublicense, - * and/or sell copies of the Software, and to permit persons to whom the - * Software is furnished to do so, subject to the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL - * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR - * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, - * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR - * OTHER DEALINGS IN THE SOFTWARE. - */ - -//#include <linux/reboot.h> - -#define SWSMU_CODE_LAYER_L3 - -#include "amdgpu.h" -#include "amdgpu_smu.h" -#include "smu_v13_0_1.h" -#include "soc15_common.h" -#include "smu_cmn.h" -#include "atomfirmware.h" -#include "amdgpu_atomfirmware.h" -#include "amdgpu_atombios.h" -#include "atom.h" - -#include "asic_reg/mp/mp_13_0_1_offset.h" -#include "asic_reg/mp/mp_13_0_1_sh_mask.h" - -/* - * DO NOT use these for err/warn/info/debug messages. - * Use dev_err, dev_warn, dev_info and dev_dbg instead. - * They are more MGPU friendly. - */ -#undef pr_err -#undef pr_warn -#undef pr_info -#undef pr_debug - -int smu_v13_0_1_check_fw_status(struct smu_context *smu) -{ - struct amdgpu_device *adev = smu->adev; - uint32_t mp1_fw_flags; - - mp1_fw_flags = RREG32_PCIE(MP1_Public | - (smnMP1_FIRMWARE_FLAGS & 0xffffffff)); - - if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >> - MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT) - return 0; - - return -EIO; -} - -int smu_v13_0_1_check_fw_version(struct smu_context *smu) -{ - uint32_t if_version = 0xff, smu_version = 0xff; - uint16_t smu_major; - uint8_t smu_minor, smu_debug; - int ret = 0; - - ret = smu_cmn_get_smc_version(smu, &if_version, &smu_version); - if (ret) - return ret; - - smu_major = (smu_version >> 16) & 0xffff; - smu_minor = (smu_version >> 8) & 0xff; - smu_debug = (smu_version >> 0) & 0xff; - - switch (smu->adev->asic_type) { - case CHIP_YELLOW_CARP: - smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_YELLOW_CARP; - break; - - default: - dev_err(smu->adev->dev, "smu unsupported asic type:%d.\n", smu->adev->asic_type); - smu->smc_driver_if_version = SMU13_0_1_DRIVER_IF_VERSION_INV; - break; - } - - dev_info(smu->adev->dev, "smu fw reported version = 0x%08x (%d.%d.%d)\n", - smu_version, smu_major, smu_minor, smu_debug); - - /* - * 1. if_version mismatch is not critical as our fw is designed - * to be backward compatible. - * 2. New fw usually brings some optimizations. But that's visible - * only on the paired driver. - * Considering above, we just leave user a warning message instead - * of halt driver loading. - */ - if (if_version != smu->smc_driver_if_version) { - dev_info(smu->adev->dev, "smu driver if version = 0x%08x, smu fw if version = 0x%08x, " - "smu fw version = 0x%08x (%d.%d.%d)\n", - smu->smc_driver_if_version, if_version, - smu_version, smu_major, smu_minor, smu_debug); - dev_warn(smu->adev->dev, "SMU driver if version not matched\n"); - } - - return ret; -} - -int smu_v13_0_1_fini_smc_tables(struct smu_context *smu) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - kfree(smu_table->clocks_table); - smu_table->clocks_table = NULL; - - kfree(smu_table->metrics_table); - smu_table->metrics_table = NULL; - - kfree(smu_table->watermarks_table); - smu_table->watermarks_table = NULL; - - return 0; -} - -static int smu_v13_0_1_atom_get_smu_clockinfo(struct amdgpu_device *adev, - uint8_t clk_id, - uint8_t syspll_id, - uint32_t *clk_freq) -{ - struct atom_get_smu_clock_info_parameters_v3_1 input = {0}; - struct atom_get_smu_clock_info_output_parameters_v3_1 *output; - int ret, index; - - input.clk_id = clk_id; - input.syspll_id = syspll_id; - input.command = GET_SMU_CLOCK_INFO_V3_1_GET_CLOCK_FREQ; - index = get_index_into_master_table(atom_master_list_of_command_functions_v2_1, - getsmuclockinfo); - - ret = amdgpu_atom_execute_table(adev->mode_info.atom_context, index, - (uint32_t *)&input); - if (ret) - return -EINVAL; - - output = (struct atom_get_smu_clock_info_output_parameters_v3_1 *)&input; - *clk_freq = le32_to_cpu(output->atom_smu_outputclkfreq.smu_clock_freq_hz) / 10000; - - return 0; -} - -int smu_v13_0_1_get_vbios_bootup_values(struct smu_context *smu) -{ - int ret, index; - uint16_t size; - uint8_t frev, crev; - struct atom_common_table_header *header; - struct atom_firmware_info_v3_4 *v_3_4; - struct atom_firmware_info_v3_3 *v_3_3; - struct atom_firmware_info_v3_1 *v_3_1; - - index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1, - firmwareinfo); - - ret = amdgpu_atombios_get_data_table(smu->adev, index, &size, &frev, &crev, - (uint8_t **)&header); - if (ret) - return ret; - - if (header->format_revision != 3) { - dev_err(smu->adev->dev, "unknown atom_firmware_info version! for smu13\n"); - return -EINVAL; - } - - switch (header->content_revision) { - case 0: - case 1: - case 2: - v_3_1 = (struct atom_firmware_info_v3_1 *)header; - smu->smu_table.boot_values.revision = v_3_1->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_1->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_1->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_1->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_1->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_1->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_1->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_1->coolingsolution_id; - break; - case 3: - v_3_3 = (struct atom_firmware_info_v3_3 *)header; - smu->smu_table.boot_values.revision = v_3_3->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_3->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_3->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_3->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_3->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_3->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_3->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_3->coolingsolution_id; - break; - case 4: - default: - v_3_4 = (struct atom_firmware_info_v3_4 *)header; - smu->smu_table.boot_values.revision = v_3_4->firmware_revision; - smu->smu_table.boot_values.gfxclk = v_3_4->bootup_sclk_in10khz; - smu->smu_table.boot_values.uclk = v_3_4->bootup_mclk_in10khz; - smu->smu_table.boot_values.socclk = 0; - smu->smu_table.boot_values.dcefclk = 0; - smu->smu_table.boot_values.vddc = v_3_4->bootup_vddc_mv; - smu->smu_table.boot_values.vddci = v_3_4->bootup_vddci_mv; - smu->smu_table.boot_values.mvddc = v_3_4->bootup_mvddc_mv; - smu->smu_table.boot_values.vdd_gfx = v_3_4->bootup_vddgfx_mv; - smu->smu_table.boot_values.cooling_id = v_3_4->coolingsolution_id; - break; - } - - smu->smu_table.boot_values.format_revision = header->format_revision; - smu->smu_table.boot_values.content_revision = header->content_revision; - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_SOCCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.socclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_DCEFCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.dcefclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_ECLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.eclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_VCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.vclk); - - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL0_DCLK_ID, - (uint8_t)0, - &smu->smu_table.boot_values.dclk); - - if ((smu->smu_table.boot_values.format_revision == 3) && - (smu->smu_table.boot_values.content_revision >= 2)) - smu_v13_0_1_atom_get_smu_clockinfo(smu->adev, - (uint8_t)SMU11_SYSPLL1_0_FCLK_ID, - (uint8_t)SMU11_SYSPLL1_2_ID, - &smu->smu_table.boot_values.fclk); - - return 0; -} - -int smu_v13_0_1_set_default_dpm_tables(struct smu_context *smu) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false); -} - -int smu_v13_0_1_set_driver_table_location(struct smu_context *smu) -{ - struct smu_table *driver_table = &smu->smu_table.driver_table; - int ret = 0; - - if (!driver_table->mc_address) - return 0; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetDriverDramAddrHigh, - upper_32_bits(driver_table->mc_address), - NULL); - - if (ret) - return ret; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_SetDriverDramAddrLow, - lower_32_bits(driver_table->mc_address), - NULL); - - return ret; -} - -int smu_v13_0_1_gfx_off_control(struct smu_context *smu, bool enable) -{ - int ret = 0; - struct amdgpu_device *adev = smu->adev; - - switch (adev->asic_type) { - case CHIP_YELLOW_CARP: - if (!(adev->pm.pp_feature & PP_GFXOFF_MASK)) - return 0; - if (enable) - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_AllowGfxOff, NULL); - else - ret = smu_cmn_send_smc_msg(smu, SMU_MSG_DisallowGfxOff, NULL); - break; - default: - break; - } - - return ret; -} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c index 0cd7902d5172..0cfeb9fc7c03 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c @@ -25,7 +25,7 @@ #include "amdgpu.h" #include "amdgpu_smu.h" -#include "smu_v13_0_1.h" +#include "smu_v13_0.h" #include "smu13_driver_if_yellow_carp.h" #include "yellow_carp_ppt.h" #include "smu_v13_0_1_ppsmc.h" @@ -186,13 +186,30 @@ err0_out: return -ENOMEM; } +static int yellow_carp_fini_smc_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + kfree(smu_table->clocks_table); + smu_table->clocks_table = NULL; + + kfree(smu_table->metrics_table); + smu_table->metrics_table = NULL; + + kfree(smu_table->watermarks_table); + smu_table->watermarks_table = NULL; + + return 0; +} + static int yellow_carp_system_features_control(struct smu_context *smu, bool en) { struct smu_feature *feature = &smu->smu_feature; + struct amdgpu_device *adev = smu->adev; uint32_t feature_mask[2]; int ret = 0; - if (!en) + if (!en && !adev->in_s0ix) ret = smu_cmn_send_smc_msg(smu, SMU_MSG_PrepareMp1ForUnload, NULL); bitmap_zero(feature->enabled, feature->feature_num); @@ -281,13 +298,9 @@ static int yellow_carp_mode_reset(struct smu_context *smu, int type) if (index < 0) return index == -EACCES ? 0 : index; - mutex_lock(&smu->message_lock); - - ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, type); - - mutex_unlock(&smu->message_lock); - - mdelay(10); + ret = smu_cmn_send_smc_msg_with_param(smu, (uint16_t)index, type, NULL); + if (ret) + dev_err(smu->adev->dev, "Failed to mode reset!\n"); return ret; } @@ -356,6 +369,28 @@ static int yellow_carp_get_smu_metrics_data(struct smu_context *smu, case METRICS_VOLTAGE_VDDSOC: *value = metrics->Voltage[1]; break; + case METRICS_SS_APU_SHARE: + /* return the percentage of APU power with respect to APU's power limit. + * percentage is reported, this isn't boost value. Smartshift power + * boost/shift is only when the percentage is more than 100. + */ + if (metrics->StapmOpnLimit > 0) + *value = (metrics->ApuPower * 100) / metrics->StapmOpnLimit; + else + *value = 0; + break; + case METRICS_SS_DGPU_SHARE: + /* return the percentage of dGPU power with respect to dGPU's power limit. + * percentage is reported, this isn't boost value. Smartshift power + * boost/shift is only when the percentage is more than 100. + */ + if ((metrics->dGpuPower > 0) && + (metrics->StapmCurrentLimit > metrics->StapmOpnLimit)) + *value = (metrics->dGpuPower * 100) / + (metrics->StapmCurrentLimit - metrics->StapmOpnLimit); + else + *value = 0; + break; default: *value = UINT_MAX; break; @@ -427,6 +462,18 @@ static int yellow_carp_read_sensor(struct smu_context *smu, (uint32_t *)data); *size = 4; break; + case AMDGPU_PP_SENSOR_SS_APU_SHARE: + ret = yellow_carp_get_smu_metrics_data(smu, + METRICS_SS_APU_SHARE, + (uint32_t *)data); + *size = 4; + break; + case AMDGPU_PP_SENSOR_SS_DGPU_SHARE: + ret = yellow_carp_get_smu_metrics_data(smu, + METRICS_SS_DGPU_SHARE, + (uint32_t *)data); + *size = 4; + break; default: ret = -EOPNOTSUPP; break; @@ -624,6 +671,13 @@ static ssize_t yellow_carp_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v2_1); } +static int yellow_carp_set_default_dpm_tables(struct smu_context *smu) +{ + struct smu_table_context *smu_table = &smu->smu_table; + + return smu_cmn_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false); +} + static int yellow_carp_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABLE_COMMAND type, long input[], uint32_t size) { @@ -1168,17 +1222,17 @@ static int yellow_carp_set_fine_grain_gfx_freq_parameters(struct smu_context *sm } static const struct pptable_funcs yellow_carp_ppt_funcs = { - .check_fw_status = smu_v13_0_1_check_fw_status, - .check_fw_version = smu_v13_0_1_check_fw_version, + .check_fw_status = smu_v13_0_check_fw_status, + .check_fw_version = smu_v13_0_check_fw_version, .init_smc_tables = yellow_carp_init_smc_tables, - .fini_smc_tables = smu_v13_0_1_fini_smc_tables, - .get_vbios_bootup_values = smu_v13_0_1_get_vbios_bootup_values, + .fini_smc_tables = yellow_carp_fini_smc_tables, + .get_vbios_bootup_values = smu_v13_0_get_vbios_bootup_values, .system_features_control = yellow_carp_system_features_control, .send_smc_msg_with_param = smu_cmn_send_smc_msg_with_param, .send_smc_msg = smu_cmn_send_smc_msg, .dpm_set_vcn_enable = yellow_carp_dpm_set_vcn_enable, .dpm_set_jpeg_enable = yellow_carp_dpm_set_jpeg_enable, - .set_default_dpm_table = smu_v13_0_1_set_default_dpm_tables, + .set_default_dpm_table = yellow_carp_set_default_dpm_tables, .read_sensor = yellow_carp_read_sensor, .is_dpm_running = yellow_carp_is_dpm_running, .set_watermarks_table = yellow_carp_set_watermarks_table, @@ -1187,8 +1241,8 @@ static const struct pptable_funcs yellow_carp_ppt_funcs = { .get_gpu_metrics = yellow_carp_get_gpu_metrics, .get_enabled_mask = smu_cmn_get_enabled_32_bits_mask, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, - .set_driver_table_location = smu_v13_0_1_set_driver_table_location, - .gfx_off_control = smu_v13_0_1_gfx_off_control, + .set_driver_table_location = smu_v13_0_set_driver_table_location, + .gfx_off_control = smu_v13_0_gfx_off_control, .post_init = yellow_carp_post_smu_init, .mode2_reset = yellow_carp_mode2_reset, .get_dpm_ultimate_freq = yellow_carp_get_dpm_ultimate_freq, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 0882a1dd6797..e802f9a95f08 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -398,6 +398,19 @@ int smu_cmn_get_enabled_32_bits_mask(struct smu_context *smu, } +uint64_t smu_cmn_get_indep_throttler_status( + const unsigned long dep_status, + const uint8_t *throttler_map) +{ + uint64_t indep_status = 0; + uint8_t dep_bit = 0; + + for_each_set_bit(dep_bit, &dep_status, 32) + indep_status |= 1ULL << throttler_map[dep_bit]; + + return indep_status; +} + int smu_cmn_feature_update_enable_state(struct smu_context *smu, uint64_t feature_mask, bool enabled) @@ -575,23 +588,52 @@ int smu_cmn_set_pp_feature_mask(struct smu_context *smu, return ret; } +/** + * smu_cmn_disable_all_features_with_exception - disable all dpm features + * except this specified by + * @mask + * + * @smu: smu_context pointer + * @no_hw_disablement: whether real dpm disablement should be performed + * true: update the cache(about dpm enablement state) only + * false: real dpm disablement plus cache update + * @mask: the dpm feature which should not be disabled + * SMU_FEATURE_COUNT: no exception, all dpm features + * to disable + * + * Returns: + * 0 on success or a negative error code on failure. + */ int smu_cmn_disable_all_features_with_exception(struct smu_context *smu, + bool no_hw_disablement, enum smu_feature_mask mask) { + struct smu_feature *feature = &smu->smu_feature; uint64_t features_to_disable = U64_MAX; int skipped_feature_id; - skipped_feature_id = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_FEATURE, - mask); - if (skipped_feature_id < 0) - return -EINVAL; + if (mask != SMU_FEATURE_COUNT) { + skipped_feature_id = smu_cmn_to_asic_specific_index(smu, + CMN2ASIC_MAPPING_FEATURE, + mask); + if (skipped_feature_id < 0) + return -EINVAL; - features_to_disable &= ~(1ULL << skipped_feature_id); + features_to_disable &= ~(1ULL << skipped_feature_id); + } - return smu_cmn_feature_update_enable_state(smu, - features_to_disable, - 0); + if (no_hw_disablement) { + mutex_lock(&feature->mutex); + bitmap_andnot(feature->enabled, feature->enabled, + (unsigned long *)(&features_to_disable), SMU_FEATURE_MAX); + mutex_unlock(&feature->mutex); + + return 0; + } else { + return smu_cmn_feature_update_enable_state(smu, + features_to_disable, + 0); + } } int smu_cmn_get_smc_version(struct smu_context *smu, @@ -773,6 +815,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) case METRICS_VERSION(2, 1): structure_size = sizeof(struct gpu_metrics_v2_1); break; + case METRICS_VERSION(2, 2): + structure_size = sizeof(struct gpu_metrics_v2_2); + break; default: return; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h index da6ff6f024f9..9add5f16ff56 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.h @@ -60,6 +60,10 @@ int smu_cmn_get_enabled_32_bits_mask(struct smu_context *smu, uint32_t *feature_mask, uint32_t num); +uint64_t smu_cmn_get_indep_throttler_status( + const unsigned long dep_status, + const uint8_t *throttler_map); + int smu_cmn_feature_update_enable_state(struct smu_context *smu, uint64_t feature_mask, bool enabled); @@ -75,6 +79,7 @@ int smu_cmn_set_pp_feature_mask(struct smu_context *smu, uint64_t new_mask); int smu_cmn_disable_all_features_with_exception(struct smu_context *smu, + bool no_hw_disablement, enum smu_feature_mask mask); int smu_cmn_get_smc_version(struct smu_context *smu, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h index 68d9464ababc..59f9cfff3d61 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_internal.h @@ -57,7 +57,7 @@ #define smu_feature_set_allowed_mask(smu) smu_ppt_funcs(set_allowed_mask, 0, smu) #define smu_feature_get_enabled_mask(smu, mask, num) smu_ppt_funcs(get_enabled_mask, 0, smu, mask, num) #define smu_feature_is_enabled(smu, mask) smu_ppt_funcs(feature_is_enabled, 0, smu, mask) -#define smu_disable_all_features_with_exception(smu, mask) smu_ppt_funcs(disable_all_features_with_exception, 0, smu, mask) +#define smu_disable_all_features_with_exception(smu, no_hw_disablement, mask) smu_ppt_funcs(disable_all_features_with_exception, 0, smu, no_hw_disablement, mask) #define smu_is_dpm_running(smu) smu_ppt_funcs(is_dpm_running, 0 , smu) #define smu_notify_display_change(smu) smu_ppt_funcs(notify_display_change, 0, smu) #define smu_populate_umd_state_clk(smu) smu_ppt_funcs(populate_umd_state_clk, 0, smu) @@ -82,7 +82,7 @@ #define smu_i2c_fini(smu, control) smu_ppt_funcs(i2c_fini, 0, smu, control) #define smu_get_unique_id(smu) smu_ppt_funcs(get_unique_id, 0, smu) #define smu_log_thermal_throttling(smu) smu_ppt_funcs(log_thermal_throttling_event, 0, smu) -#define smu_get_asic_power_limits(smu) smu_ppt_funcs(get_power_limit, 0, smu) +#define smu_get_asic_power_limits(smu, current, default, max) smu_ppt_funcs(get_power_limit, 0, smu, current, default, max) #define smu_get_pp_feature_mask(smu, buf) smu_ppt_funcs(get_pp_feature_mask, 0, smu, buf) #define smu_set_pp_feature_mask(smu, new_mask) smu_ppt_funcs(set_pp_feature_mask, 0, smu, new_mask) #define smu_gfx_ulv_control(smu, enablement) smu_ppt_funcs(gfx_ulv_control, 0, smu, enablement) |