diff options
Diffstat (limited to 'drivers/gpu/drm')
52 files changed, 848 insertions, 527 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 91820838b63b..8b4ca2576a3d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -363,9 +363,6 @@ struct amdgpu_ip_block_version { const struct amd_ip_funcs *funcs; }; -#define HW_REV(_Major, _Minor, _Rev) \ - ((((uint32_t) (_Major)) << 16) | ((uint32_t) (_Minor) << 8) | ((uint32_t) (_Rev))) - struct amdgpu_ip_block { struct amdgpu_ip_block_status status; const struct amdgpu_ip_block_version *version; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index bd1d4b2b6b16..23448359838b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -425,6 +425,32 @@ validate_fail: return ret; } +static int amdgpu_amdkfd_bo_validate_and_fence(struct amdgpu_bo *bo, + uint32_t domain, + struct dma_fence *fence) +{ + int ret = amdgpu_bo_reserve(bo, false); + + if (ret) + return ret; + + ret = amdgpu_amdkfd_bo_validate(bo, domain, true); + if (ret) + goto unreserve_out; + + ret = dma_resv_reserve_fences(bo->tbo.base.resv, 1); + if (ret) + goto unreserve_out; + + dma_resv_add_fence(bo->tbo.base.resv, fence, + DMA_RESV_USAGE_BOOKKEEP); + +unreserve_out: + amdgpu_bo_unreserve(bo); + + return ret; +} + static int amdgpu_amdkfd_validate_vm_bo(void *_unused, struct amdgpu_bo *bo) { return amdgpu_amdkfd_bo_validate(bo, bo->allowed_domains, false); @@ -1784,6 +1810,15 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( } bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT; bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT; + } else { + mutex_lock(&avm->process_info->lock); + if (avm->process_info->eviction_fence && + !dma_fence_is_signaled(&avm->process_info->eviction_fence->base)) + ret = amdgpu_amdkfd_bo_validate_and_fence(bo, domain, + &avm->process_info->eviction_fence->base); + mutex_unlock(&avm->process_info->lock); + if (ret) + goto err_validate_bo; } if (offset) @@ -1793,6 +1828,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu( allocate_init_user_pages_failed: err_pin_bo: +err_validate_bo: remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info); drm_vma_node_revoke(&gobj->vma_node, drm_priv); err_node_allow: @@ -1866,10 +1902,6 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( if (unlikely(ret)) return ret; - /* The eviction fence should be removed by the last unmap. - * TODO: Log an error condition if the bo still has the eviction fence - * attached - */ amdgpu_amdkfd_remove_eviction_fence(mem->bo, process_info->eviction_fence); pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va, @@ -1998,19 +2030,6 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( if (unlikely(ret)) goto out_unreserve; - if (mem->mapped_to_gpu_memory == 0 && - !amdgpu_ttm_tt_get_usermm(bo->tbo.ttm)) { - /* Validate BO only once. The eviction fence gets added to BO - * the first time it is mapped. Validate will wait for all - * background evictions to complete. - */ - ret = amdgpu_amdkfd_bo_validate(bo, domain, true); - if (ret) { - pr_debug("Validate failed\n"); - goto out_unreserve; - } - } - list_for_each_entry(entry, &mem->attachments, list) { if (entry->bo_va->base.vm != avm || entry->is_mapped) continue; @@ -2037,10 +2056,6 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( mem->mapped_to_gpu_memory); } - if (!amdgpu_ttm_tt_get_usermm(bo->tbo.ttm) && !bo->tbo.pin_count) - dma_resv_add_fence(bo->tbo.base.resv, - &avm->process_info->eviction_fence->base, - DMA_RESV_USAGE_BOOKKEEP); ret = unreserve_bo_and_vms(&ctx, false, false); goto out; @@ -2074,7 +2089,6 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv) { struct amdgpu_vm *avm = drm_priv_to_vm(drm_priv); - struct amdkfd_process_info *process_info = avm->process_info; unsigned long bo_size = mem->bo->tbo.base.size; struct kfd_mem_attachment *entry; struct bo_vm_reservation_context ctx; @@ -2115,15 +2129,6 @@ int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( mem->mapped_to_gpu_memory); } - /* If BO is unmapped from all VMs, unfence it. It can be evicted if - * required. - */ - if (mem->mapped_to_gpu_memory == 0 && - !amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm) && - !mem->bo->tbo.pin_count) - amdgpu_amdkfd_remove_eviction_fence(mem->bo, - process_info->eviction_fence); - unreserve_out: unreserve_bo_and_vms(&ctx, false, false); out: @@ -2351,8 +2356,20 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct amdgpu_device *adev, amdgpu_sync_create(&(*mem)->sync); (*mem)->is_imported = true; + mutex_lock(&avm->process_info->lock); + if (avm->process_info->eviction_fence && + !dma_fence_is_signaled(&avm->process_info->eviction_fence->base)) + ret = amdgpu_amdkfd_bo_validate_and_fence(bo, (*mem)->domain, + &avm->process_info->eviction_fence->base); + mutex_unlock(&avm->process_info->lock); + if (ret) + goto err_remove_mem; + return 0; +err_remove_mem: + remove_kgd_mem_from_kfd_bo_list(*mem, avm->process_info); + drm_vma_node_revoke(&obj->vma_node, drm_priv); err_free_mem: kfree(*mem); err_put_obj: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index 38ccec913f00..f3a09ecb7699 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -29,6 +29,7 @@ #include "amdgpu.h" #include "atom.h" +#include <linux/device.h> #include <linux/pci.h> #include <linux/slab.h> #include <linux/acpi.h> @@ -287,6 +288,10 @@ static bool amdgpu_atrm_get_bios(struct amdgpu_device *adev) if (adev->flags & AMD_IS_APU) return false; + /* ATRM is for on-platform devices only */ + if (dev_is_removable(&adev->pdev->dev)) + return false; + while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) { dhandle = ACPI_HANDLE(&pdev->dev); if (!dhandle) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 122472d88756..0245de81cabd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -1116,6 +1116,11 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) return r; } + /* FIXME: In theory this loop shouldn't be needed any more when + * amdgpu_vm_handle_moved handles all moved BOs that are reserved + * with p->ticket. But removing it caused test regressions, so I'm + * leaving it here for now. + */ amdgpu_bo_list_for_each_entry(e, p->bo_list) { bo_va = e->bo_va; if (bo_va == NULL) @@ -1130,7 +1135,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p) return r; } - r = amdgpu_vm_handle_moved(adev, vm); + r = amdgpu_vm_handle_moved(adev, vm, &p->exec.ticket); if (r) return r; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index d5f78179b2b6..fd8cd8e2d3f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -41,6 +41,7 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_probe_helper.h> #include <drm/amdgpu_drm.h> +#include <linux/device.h> #include <linux/vgaarb.h> #include <linux/vga_switcheroo.h> #include <linux/efi.h> @@ -1073,6 +1074,8 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev) amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(11, 0, 0)) { amdgpu_psp_wait_for_bootloader(adev); ret = amdgpu_atomfirmware_asic_init(adev, true); + /* TODO: check the return val and stop device initialization if boot fails */ + amdgpu_psp_query_boot_status(adev); return ret; } else { return amdgpu_atom_asic_init(adev->mode_info.atom_context); @@ -2223,7 +2226,6 @@ out: */ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) { - struct drm_device *dev = adev_to_drm(adev); struct pci_dev *parent; int i, r; bool total; @@ -2294,7 +2296,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev) (amdgpu_is_atpx_hybrid() || amdgpu_has_atpx_dgpu_power_cntl()) && ((adev->flags & AMD_IS_APU) == 0) && - !pci_is_thunderbolt_attached(to_pci_dev(dev->dev))) + !dev_is_removable(&adev->pdev->dev)) adev->flags |= AMD_IS_PX; if (!(adev->flags & AMD_IS_APU)) { @@ -3962,13 +3964,23 @@ int amdgpu_device_init(struct amdgpu_device *adev, } } } else { - tmp = amdgpu_reset_method; - /* It should do a default reset when loading or reloading the driver, - * regardless of the module parameter reset_method. - */ - amdgpu_reset_method = AMD_RESET_METHOD_NONE; - r = amdgpu_asic_reset(adev); - amdgpu_reset_method = tmp; + switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) { + case IP_VERSION(13, 0, 0): + case IP_VERSION(13, 0, 7): + case IP_VERSION(13, 0, 10): + r = psp_gpu_reset(adev); + break; + default: + tmp = amdgpu_reset_method; + /* It should do a default reset when loading or reloading the driver, + * regardless of the module parameter reset_method. + */ + amdgpu_reset_method = AMD_RESET_METHOD_NONE; + r = amdgpu_asic_reset(adev); + amdgpu_reset_method = tmp; + break; + } + if (r) { dev_err(adev->dev, "asic reset on init failed\n"); goto failed; @@ -4132,7 +4144,7 @@ fence_driver_init: px = amdgpu_device_supports_px(ddev); - if (px || (!pci_is_thunderbolt_attached(adev->pdev) && + if (px || (!dev_is_removable(&adev->pdev->dev) && apple_gmux_detect(NULL, NULL))) vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, px); @@ -4282,7 +4294,7 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev) px = amdgpu_device_supports_px(adev_to_drm(adev)); - if (px || (!pci_is_thunderbolt_attached(adev->pdev) && + if (px || (!dev_is_removable(&adev->pdev->dev) && apple_gmux_detect(NULL, NULL))) vga_switcheroo_unregister_client(adev->pdev); @@ -5566,10 +5578,6 @@ skip_hw_reset: drm_sched_start(&ring->sched, true); } - if (adev->enable_mes && - amdgpu_ip_version(adev, GC_HWIP, 0) != IP_VERSION(11, 0, 3)) - amdgpu_mes_self_test(tmp_adev); - if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) drm_helper_resume_force_mode(adev_to_drm(tmp_adev)); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c index b6a53e8429b2..0431eafa86b5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c @@ -99,6 +99,7 @@ MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY); #define mmRCC_CONFIG_MEMSIZE 0xde3 +#define mmMP0_SMN_C2PMSG_33 0x16061 #define mmMM_INDEX 0x0 #define mmMM_INDEX_HI 0x6 #define mmMM_DATA 0x1 @@ -239,8 +240,26 @@ static int amdgpu_discovery_read_binary_from_sysmem(struct amdgpu_device *adev, static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev, uint8_t *binary) { - uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; - int ret = 0; + uint64_t vram_size; + u32 msg; + int i, ret = 0; + + /* It can take up to a second for IFWI init to complete on some dGPUs, + * but generally it should be in the 60-100ms range. Normally this starts + * as soon as the device gets power so by the time the OS loads this has long + * completed. However, when a card is hotplugged via e.g., USB4, we need to + * wait for this to complete. Once the C2PMSG is updated, we can + * continue. + */ + if (dev_is_removable(&adev->pdev->dev)) { + for (i = 0; i < 1000; i++) { + msg = RREG32(mmMP0_SMN_C2PMSG_33); + if (msg & 0x80000000) + break; + msleep(1); + } + } + vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20; if (vram_size) { uint64_t pos = vram_size - DISCOVERY_TMR_OFFSET; @@ -2449,6 +2468,9 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev) if (amdgpu_ip_version(adev, XGMI_HWIP, 0) == IP_VERSION(4, 8, 0)) adev->gmc.xgmi.supported = true; + if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) + adev->ip_versions[XGMI_HWIP][0] = IP_VERSION(6, 4, 0); + /* set NBIO version */ switch (amdgpu_ip_version(adev, NBIO_HWIP, 0)) { case IP_VERSION(6, 1, 0): diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index b5e28fa3f414..e7e87a3b2601 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -409,7 +409,7 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) if (!r) r = amdgpu_vm_clear_freed(adev, vm, NULL); if (!r) - r = amdgpu_vm_handle_moved(adev, vm); + r = amdgpu_vm_handle_moved(adev, vm, ticket); if (r && r != -EBUSY) DRM_ERROR("Failed to invalidate VM page tables (%d))\n", diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 6cc6e3991410..3095a3a864af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -2041,6 +2041,14 @@ static const struct pci_device_id pciidlist[] = { MODULE_DEVICE_TABLE(pci, pciidlist); +static const struct amdgpu_asic_type_quirk asic_type_quirks[] = { + /* differentiate between P10 and P11 asics with the same DID */ + {0x67FF, 0xE3, CHIP_POLARIS10}, + {0x67FF, 0xE7, CHIP_POLARIS10}, + {0x67FF, 0xF3, CHIP_POLARIS10}, + {0x67FF, 0xF7, CHIP_POLARIS10}, +}; + static const struct drm_driver amdgpu_kms_driver; static void amdgpu_get_secondary_funcs(struct amdgpu_device *adev) @@ -2083,6 +2091,22 @@ static void amdgpu_init_debug_options(struct amdgpu_device *adev) } } +static unsigned long amdgpu_fix_asic_type(struct pci_dev *pdev, unsigned long flags) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(asic_type_quirks); i++) { + if (pdev->device == asic_type_quirks[i].device && + pdev->revision == asic_type_quirks[i].revision) { + flags &= ~AMD_ASIC_MASK; + flags |= asic_type_quirks[i].type; + break; + } + } + + return flags; +} + static int amdgpu_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { @@ -2110,15 +2134,8 @@ static int amdgpu_pci_probe(struct pci_dev *pdev, "See modparam exp_hw_support\n"); return -ENODEV; } - /* differentiate between P10 and P11 asics with the same DID */ - if (pdev->device == 0x67FF && - (pdev->revision == 0xE3 || - pdev->revision == 0xE7 || - pdev->revision == 0xF3 || - pdev->revision == 0xF7)) { - flags &= ~AMD_ASIC_MASK; - flags |= CHIP_POLARIS10; - } + + flags = amdgpu_fix_asic_type(pdev, flags); /* Due to hardware bugs, S/G Display on raven requires a 1:1 IOMMU mapping, * however, SME requires an indirect IOMMU mapping because the encryption diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index c92e0aba69e1..a2a29dcb2422 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -385,9 +385,11 @@ int amdgpu_gfx_mqd_sw_init(struct amdgpu_device *adev, struct amdgpu_ring *ring = &kiq->ring; u32 domain = AMDGPU_GEM_DOMAIN_GTT; +#if !defined(CONFIG_ARM) && !defined(CONFIG_ARM64) /* Only enable on gfx10 and 11 for now to avoid changing behavior on older chips */ if (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(10, 0, 0)) domain |= AMDGPU_GEM_DOMAIN_VRAM; +#endif /* create MQD for KIQ */ if (!adev->enable_mes_kiq && !ring->mqd_obj) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 59f10b353b3a..9ddbf1494326 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -557,8 +557,20 @@ static void amdgpu_mes_queue_init_mqd(struct amdgpu_device *adev, mqd_prop.hqd_queue_priority = p->hqd_queue_priority; mqd_prop.hqd_active = false; + if (p->queue_type == AMDGPU_RING_TYPE_GFX || + p->queue_type == AMDGPU_RING_TYPE_COMPUTE) { + mutex_lock(&adev->srbm_mutex); + amdgpu_gfx_select_me_pipe_q(adev, p->ring->me, p->ring->pipe, 0, 0, 0); + } + mqd_mgr->init_mqd(adev, q->mqd_cpu_ptr, &mqd_prop); + if (p->queue_type == AMDGPU_RING_TYPE_GFX || + p->queue_type == AMDGPU_RING_TYPE_COMPUTE) { + amdgpu_gfx_select_me_pipe_q(adev, 0, 0, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); + } + amdgpu_bo_unreserve(q->mqd_obj); } @@ -994,9 +1006,13 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, switch (queue_type) { case AMDGPU_RING_TYPE_GFX: ring->funcs = adev->gfx.gfx_ring[0].funcs; + ring->me = adev->gfx.gfx_ring[0].me; + ring->pipe = adev->gfx.gfx_ring[0].pipe; break; case AMDGPU_RING_TYPE_COMPUTE: ring->funcs = adev->gfx.compute_ring[0].funcs; + ring->me = adev->gfx.compute_ring[0].me; + ring->pipe = adev->gfx.compute_ring[0].pipe; break; case AMDGPU_RING_TYPE_SDMA: ring->funcs = adev->sdma.instance[0].ring.funcs; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 648bd5e12830..32b701cc0376 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -2120,6 +2120,21 @@ int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev) return ret; } +int amdgpu_psp_query_boot_status(struct amdgpu_device *adev) +{ + struct psp_context *psp = &adev->psp; + int ret = 0; + + if (amdgpu_sriov_vf(adev) || (adev->flags & AMD_IS_APU)) + return 0; + + if (psp->funcs && + psp->funcs->query_boot_status) + ret = psp->funcs->query_boot_status(psp); + + return ret; +} + static int psp_hw_start(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 7111dd32e66f..5d36ad3f48c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -134,6 +134,7 @@ struct psp_funcs { int (*update_spirom)(struct psp_context *psp, uint64_t fw_pri_mc_addr); int (*vbflash_stat)(struct psp_context *psp); int (*fatal_error_recovery_quirk)(struct psp_context *psp); + int (*query_boot_status)(struct psp_context *psp); }; struct ta_funcs { @@ -537,4 +538,6 @@ int is_psp_fw_valid(struct psp_bin_desc bin); int amdgpu_psp_wait_for_bootloader(struct amdgpu_device *adev); +int amdgpu_psp_query_boot_status(struct amdgpu_device *adev); + #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 303fbb6a48b6..b7fe5951b166 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1222,6 +1222,8 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev, struct amdgpu_ras_block_object *block_obj = amdgpu_ras_get_ras_block(adev, block, 0); struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); const struct amdgpu_mca_smu_funcs *mca_funcs = adev->mca.mca_funcs; + struct amdgpu_hive_info *hive; + int hive_ras_recovery = 0; if (!block_obj || !block_obj->hw_ops) { dev_dbg_once(adev->dev, "%s doesn't config RAS function\n", @@ -1229,15 +1231,22 @@ int amdgpu_ras_reset_error_count(struct amdgpu_device *adev, return -EOPNOTSUPP; } - /* skip ras error reset in gpu reset */ - if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery)) && - mca_funcs && mca_funcs->mca_set_debug_mode) - return -EOPNOTSUPP; - if (!amdgpu_ras_is_supported(adev, block) || !amdgpu_ras_get_mca_debug_mode(adev)) return -EOPNOTSUPP; + hive = amdgpu_get_xgmi_hive(adev); + if (hive) { + hive_ras_recovery = atomic_read(&hive->ras_recovery); + amdgpu_put_xgmi_hive(hive); + } + + /* skip ras error reset in gpu reset */ + if ((amdgpu_in_reset(adev) || atomic_read(&ras->in_recovery) || + hive_ras_recovery) && + mca_funcs && mca_funcs->mca_set_debug_mode) + return -EOPNOTSUPP; + if (block_obj->hw_ops->reset_ras_error_count) block_obj->hw_ops->reset_ras_error_count(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index f74347cc087a..d65e21914d8c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -166,8 +166,12 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev, } } - if (reset) + if (reset) { + /* use mode-2 reset for poison consumption */ + if (!entry) + con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET; amdgpu_ras_reset_gpu(adev); + } } kfree(err_data->err_addr); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 3cd5977c0709..904252456d25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1373,6 +1373,7 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, * * @adev: amdgpu_device pointer * @vm: requested vm + * @ticket: optional reservation ticket used to reserve the VM * * Make sure all BOs which are moved are updated in the PTs. * @@ -1382,11 +1383,12 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, * PTs have to be reserved! */ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, - struct amdgpu_vm *vm) + struct amdgpu_vm *vm, + struct ww_acquire_ctx *ticket) { struct amdgpu_bo_va *bo_va; struct dma_resv *resv; - bool clear; + bool clear, unlock; int r; spin_lock(&vm->status_lock); @@ -1409,17 +1411,24 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev, spin_unlock(&vm->status_lock); /* Try to reserve the BO to avoid clearing its ptes */ - if (!adev->debug_vm && dma_resv_trylock(resv)) + if (!adev->debug_vm && dma_resv_trylock(resv)) { clear = false; + unlock = true; + /* The caller is already holding the reservation lock */ + } else if (ticket && dma_resv_locking_ctx(resv) == ticket) { + clear = false; + unlock = false; /* Somebody else is using the BO right now */ - else + } else { clear = true; + unlock = false; + } r = amdgpu_vm_bo_update(adev, bo_va, clear); if (r) return r; - if (!clear) + if (unlock) dma_resv_unlock(resv); spin_lock(&vm->status_lock); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 9c7b5d33b56e..2cd86d2bf73f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -443,7 +443,8 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev, struct amdgpu_vm *vm, struct dma_fence **fence); int amdgpu_vm_handle_moved(struct amdgpu_device *adev, - struct amdgpu_vm *vm); + struct amdgpu_vm *vm, + struct ww_acquire_ctx *ticket); void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, struct amdgpu_vm *vm, struct amdgpu_bo *bo); int amdgpu_vm_update_range(struct amdgpu_device *adev, struct amdgpu_vm *vm, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 18f58efc9dc7..08916538a615 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -77,7 +77,16 @@ static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head) return true; } +static inline u64 amdgpu_vram_mgr_blocks_size(struct list_head *head) +{ + struct drm_buddy_block *block; + u64 size = 0; + list_for_each_entry(block, head, link) + size += amdgpu_vram_mgr_block_size(block); + + return size; +} /** * DOC: mem_info_vram_total @@ -516,6 +525,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, mutex_unlock(&mgr->lock); vres->base.start = 0; + size = max_t(u64, amdgpu_vram_mgr_blocks_size(&vres->blocks), + vres->base.size); list_for_each_entry(block, &vres->blocks, link) { unsigned long start; @@ -523,8 +534,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man, amdgpu_vram_mgr_block_size(block); start >>= PAGE_SHIFT; - if (start > PFN_UP(vres->base.size)) - start -= PFN_UP(vres->base.size); + if (start > PFN_UP(size)) + start -= PFN_UP(size); else start = 0; vres->base.start = max(vres->base.start, start); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index d9ccacd06fba..c8a3bf01743f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3498,6 +3498,8 @@ static void gfx_v10_0_ring_invalidate_tlbs(struct amdgpu_ring *ring, static void gfx_v10_0_update_spm_vmid_internal(struct amdgpu_device *adev, unsigned int vmid); +static int gfx_v10_0_set_powergating_state(void *handle, + enum amd_powergating_state state); static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask) { amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6)); @@ -6465,11 +6467,18 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring) nv_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { + mutex_lock(&adev->srbm_mutex); + nv_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0); + if (ring->doorbell_index == adev->doorbell_index.gfx_ring0 << 1) + gfx_v10_0_cp_gfx_set_doorbell(adev, ring); + + nv_grbm_select(adev, 0, 0, 0, 0); + mutex_unlock(&adev->srbm_mutex); /* restore mqd with the backup copy */ if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; *ring->wptr_cpu_addr = 0; @@ -6743,7 +6752,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring) if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.kiq[0].mqd_backup) - memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; @@ -6766,7 +6775,7 @@ static int gfx_v10_0_kiq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.kiq[0].mqd_backup) - memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); } return 0; @@ -6787,11 +6796,11 @@ static int gfx_v10_0_kcq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); @@ -7172,6 +7181,13 @@ static int gfx_v10_0_hw_fini(void *handle) amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0); amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0); + /* WA added for Vangogh asic fixing the SMU suspend failure + * It needs to set power gating again during gfxoff control + * otherwise the gfxoff disallowing will be failed to set. + */ + if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(10, 3, 1)) + gfx_v10_0_set_powergating_state(handle, AMD_PG_STATE_UNGATE); + if (!adev->no_hw_access) { if (amdgpu_async_gfx_ring) { if (amdgpu_gfx_disable_kgq(adev, 0)) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index fd22943685f7..0c6133cc5e57 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -155,6 +155,7 @@ static void gfx11_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue { amdgpu_ring_write(kiq_ring, PACKET3(PACKET3_SET_RESOURCES, 6)); amdgpu_ring_write(kiq_ring, PACKET3_SET_RESOURCES_VMID_MASK(0) | + PACKET3_SET_RESOURCES_UNMAP_LATENTY(0xa) | /* unmap_latency: 0xa (~ 1s) */ PACKET3_SET_RESOURCES_QUEUE_TYPE(0)); /* vmid_mask:0 queue_type:0 (KIQ) */ amdgpu_ring_write(kiq_ring, lower_32_bits(queue_mask)); /* queue mask lo */ amdgpu_ring_write(kiq_ring, upper_32_bits(queue_mask)); /* queue mask hi */ @@ -3714,11 +3715,11 @@ static int gfx_v11_0_gfx_init_queue(struct amdgpu_ring *ring) soc21_grbm_select(adev, 0, 0, 0, 0); mutex_unlock(&adev->srbm_mutex); if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore mqd with the backup copy */ if (adev->gfx.me.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset the ring */ ring->wptr = 0; *ring->wptr_cpu_addr = 0; @@ -4007,7 +4008,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring *ring) if (amdgpu_in_reset(adev)) { /* for GPU_RESET case */ /* reset MQD to a clean status */ if (adev->gfx.kiq[0].mqd_backup) - memcpy(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.kiq[0].mqd_backup, sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; @@ -4030,7 +4031,7 @@ static int gfx_v11_0_kiq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.kiq[0].mqd_backup) - memcpy(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.kiq[0].mqd_backup, mqd, sizeof(*mqd)); } return 0; @@ -4051,11 +4052,11 @@ static int gfx_v11_0_kcq_init_queue(struct amdgpu_ring *ring) mutex_unlock(&adev->srbm_mutex); if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); + memcpy_fromio(adev->gfx.mec.mqd_backup[mqd_idx], mqd, sizeof(*mqd)); } else { /* restore MQD to a clean status */ if (adev->gfx.mec.mqd_backup[mqd_idx]) - memcpy(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); + memcpy_toio(mqd, adev->gfx.mec.mqd_backup[mqd_idx], sizeof(*mqd)); /* reset ring buffer */ ring->wptr = 0; atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0); diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c index e523627cfe25..df218d5ca775 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c @@ -28,6 +28,7 @@ #include "nbio/nbio_2_3_offset.h" #include "nbio/nbio_2_3_sh_mask.h" #include <uapi/linux/kfd_ioctl.h> +#include <linux/device.h> #include <linux/pci.h> #define smnPCIE_CONFIG_CNTL 0x11180044 @@ -361,7 +362,7 @@ static void nbio_v2_3_enable_aspm(struct amdgpu_device *adev, data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; - if (pci_is_thunderbolt_attached(adev->pdev)) + if (dev_is_removable(&adev->pdev->dev)) data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; else data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; @@ -480,7 +481,7 @@ static void nbio_v2_3_program_aspm(struct amdgpu_device *adev) def = data = RREG32_PCIE(smnPCIE_LC_CNTL); data |= NAVI10_PCIE__LC_L0S_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L0S_INACTIVITY__SHIFT; - if (pci_is_thunderbolt_attached(adev->pdev)) + if (dev_is_removable(&adev->pdev->dev)) data |= NAVI10_PCIE__LC_L1_INACTIVITY_TBT_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; else data |= NAVI10_PCIE__LC_L1_INACTIVITY_DEFAULT << PCIE_LC_CNTL__LC_L1_INACTIVITY__SHIFT; diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 4142e2fcd866..3cf4684d0d3f 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -759,6 +759,83 @@ static int psp_v13_0_fatal_error_recovery_quirk(struct psp_context *psp) return 0; } + +static void psp_v13_0_boot_error_reporting(struct amdgpu_device *adev, + uint32_t inst, + uint32_t boot_error) +{ + uint32_t socket_id; + uint32_t aid_id; + uint32_t hbm_id; + uint32_t reg_data; + + socket_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, SOCKET_ID); + aid_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, AID_ID); + hbm_id = REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, HBM_ID); + + reg_data = RREG32_SOC15(MP0, inst, regMP0_SMN_C2PMSG_109); + dev_info(adev->dev, "socket: %d, aid: %d, firmware boot failed, fw status is 0x%x\n", + socket_id, aid_id, reg_data); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_MEM_TRAINING)) + dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, memory training failed\n", + socket_id, aid_id, hbm_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_FW_LOAD)) + dev_info(adev->dev, "socket: %d, aid: %d, firmware load failed at boot time\n", + socket_id, aid_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_WAFL_LINK_TRAINING)) + dev_info(adev->dev, "socket: %d, aid: %d, wafl link training failed\n", + socket_id, aid_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_XGMI_LINK_TRAINING)) + dev_info(adev->dev, "socket: %d, aid: %d, xgmi link training failed\n", + socket_id, aid_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_USR_CP_LINK_TRAINING)) + dev_info(adev->dev, "socket: %d, aid: %d, usr cp link training failed\n", + socket_id, aid_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_USR_DP_LINK_TRAINING)) + dev_info(adev->dev, "socket: %d, aid: %d, usr dp link training failed\n", + socket_id, aid_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_HBM_MEM_TEST)) + dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm memory test failed\n", + socket_id, aid_id, hbm_id); + + if (REG_GET_FIELD(boot_error, MP0_SMN_C2PMSG_126, GPU_ERR_HBM_BIST_TEST)) + dev_info(adev->dev, "socket: %d, aid: %d, hbm: %d, hbm bist test failed\n", + socket_id, aid_id, hbm_id); +} + +static int psp_v13_0_query_boot_status(struct psp_context *psp) +{ + struct amdgpu_device *adev = psp->adev; + int inst_mask = adev->aid_mask; + uint32_t reg_data; + uint32_t i; + int ret = 0; + + if (amdgpu_ip_version(adev, MP0_HWIP, 0) != IP_VERSION(13, 0, 6)) + return 0; + + if (RREG32_SOC15(MP0, 0, regMP0_SMN_C2PMSG_59) < 0x00a10007) + return 0; + + for_each_inst(i, inst_mask) { + reg_data = RREG32_SOC15(MP0, i, regMP0_SMN_C2PMSG_126); + if (!REG_GET_FIELD(reg_data, MP0_SMN_C2PMSG_126, BOOT_STATUS)) { + psp_v13_0_boot_error_reporting(adev, i, reg_data); + ret = -EINVAL; + break; + } + } + + return ret; +} + static const struct psp_funcs psp_v13_0_funcs = { .init_microcode = psp_v13_0_init_microcode, .wait_for_bootloader = psp_v13_0_wait_for_bootloader_steady_state, @@ -781,6 +858,7 @@ static const struct psp_funcs psp_v13_0_funcs = { .update_spirom = psp_v13_0_update_spirom, .vbflash_stat = psp_v13_0_vbflash_status, .fatal_error_recovery_quirk = psp_v13_0_fatal_error_recovery_quirk, + .query_boot_status = psp_v13_0_query_boot_status, }; void psp_v13_0_set_psp_funcs(struct psp_context *psp) diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c index 743d2f68b090..770b4b4e3138 100644 --- a/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/umc_v12_0.c @@ -91,8 +91,7 @@ static void umc_v12_0_reset_error_count(struct amdgpu_device *adev) static bool umc_v12_0_is_uncorrectable_error(uint64_t mc_umc_status) { return ((REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Val) == 1) && - (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, Deferred) == 1 || - REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 || + (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, PCC) == 1 || REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UC) == 1 || REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, TCC) == 1)); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 0e792a8496d6..cd8e459201f1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -1404,6 +1404,66 @@ static int kfd_fill_gpu_cache_info_from_gfx_config(struct kfd_dev *kdev, return i; } +static int kfd_fill_gpu_cache_info_from_gfx_config_v2(struct kfd_dev *kdev, + struct kfd_gpu_cache_info *pcache_info) +{ + struct amdgpu_device *adev = kdev->adev; + int i = 0; + + /* TCP L1 Cache per CU */ + if (adev->gfx.config.gc_tcp_size_per_cu) { + pcache_info[i].cache_size = adev->gfx.config.gc_tcp_size_per_cu; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = 1; + i++; + } + /* Scalar L1 Instruction Cache per SQC */ + if (adev->gfx.config.gc_l1_instruction_cache_size_per_sqc) { + pcache_info[i].cache_size = + adev->gfx.config.gc_l1_instruction_cache_size_per_sqc; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_INST_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_cu_per_sqc; + i++; + } + /* Scalar L1 Data Cache per SQC */ + if (adev->gfx.config.gc_l1_data_cache_size_per_sqc) { + pcache_info[i].cache_size = adev->gfx.config.gc_l1_data_cache_size_per_sqc; + pcache_info[i].cache_level = 1; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.gc_num_cu_per_sqc; + i++; + } + /* L2 Data Cache per GPU (Total Tex Cache) */ + if (adev->gfx.config.gc_tcc_size) { + pcache_info[i].cache_size = adev->gfx.config.gc_tcc_size; + pcache_info[i].cache_level = 2; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; + i++; + } + /* L3 Data Cache per GPU */ + if (adev->gmc.mall_size) { + pcache_info[i].cache_size = adev->gmc.mall_size / 1024; + pcache_info[i].cache_level = 3; + pcache_info[i].flags = (CRAT_CACHE_FLAGS_ENABLED | + CRAT_CACHE_FLAGS_DATA_CACHE | + CRAT_CACHE_FLAGS_SIMD_CACHE); + pcache_info[i].num_cu_shared = adev->gfx.config.max_cu_per_sh; + i++; + } + return i; +} + int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pcache_info) { int num_of_cache_types = 0; @@ -1461,10 +1521,14 @@ int kfd_get_gpu_cache_info(struct kfd_node *kdev, struct kfd_gpu_cache_info **pc num_of_cache_types = ARRAY_SIZE(vega20_cache_info); break; case IP_VERSION(9, 4, 2): - case IP_VERSION(9, 4, 3): *pcache_info = aldebaran_cache_info; num_of_cache_types = ARRAY_SIZE(aldebaran_cache_info); break; + case IP_VERSION(9, 4, 3): + num_of_cache_types = + kfd_fill_gpu_cache_info_from_gfx_config_v2(kdev->kfd, + *pcache_info); + break; case IP_VERSION(9, 1, 0): case IP_VERSION(9, 2, 2): *pcache_info = raven_cache_info; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 4e530791507e..dc7c8312e8c7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -1602,10 +1602,13 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext, unsigned int cu_sibling_map_mask; int first_active_cu; int i, j, k, xcc, start, end; + int num_xcc = NUM_XCC(knode->xcc_mask); struct kfd_cache_properties *pcache = NULL; + enum amdgpu_memory_partition mode; + struct amdgpu_device *adev = knode->adev; start = ffs(knode->xcc_mask) - 1; - end = start + NUM_XCC(knode->xcc_mask); + end = start + num_xcc; cu_sibling_map_mask = cu_info->bitmap[start][0][0]; cu_sibling_map_mask &= ((1 << pcache_info[cache_type].num_cu_shared) - 1); @@ -1624,7 +1627,18 @@ static int fill_in_l2_l3_pcache(struct kfd_cache_properties **props_ext, pcache->processor_id_low = cu_processor_id + (first_active_cu - 1); pcache->cache_level = pcache_info[cache_type].cache_level; - pcache->cache_size = pcache_info[cache_type].cache_size; + + if (KFD_GC_VERSION(knode) == IP_VERSION(9, 4, 3)) + mode = adev->gmc.gmc_funcs->query_mem_partition_mode(adev); + else + mode = UNKNOWN_MEMORY_PARTITION_MODE; + + if (pcache->cache_level == 2) + pcache->cache_size = pcache_info[cache_type].cache_size * num_xcc; + else if (mode) + pcache->cache_size = pcache_info[cache_type].cache_size / mode; + else + pcache->cache_size = pcache_info[cache_type].cache_size; if (pcache_info[cache_type].flags & CRAT_CACHE_FLAGS_DATA_CACHE) pcache->cache_type |= HSA_CACHE_TYPE_DATA; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 74c21d98b4de..4360a696f10a 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -4348,7 +4348,6 @@ static bool full_update_required(struct dc *dc, srf_updates[i].in_transfer_func || srf_updates[i].func_shaper || srf_updates[i].lut3d_func || - srf_updates[i].blend_tf || srf_updates[i].surface->force_full_update || (srf_updates[i].flip_addr && srf_updates[i].flip_addr->address.tmz_surface != srf_updates[i].surface->address.tmz_surface) || 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 6ed40b6c6178..4bdf105d1d71 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c @@ -533,7 +533,7 @@ uint32_t dc_stream_get_vblank_counter(const struct dc_stream_state *stream) for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; - if (res_ctx->pipe_ctx[i].stream != stream) + if (res_ctx->pipe_ctx[i].stream != stream || !tg) continue; return tg->funcs->get_frame_count(tg); @@ -592,7 +592,7 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream, for (i = 0; i < MAX_PIPES; i++) { struct timing_generator *tg = res_ctx->pipe_ctx[i].stream_res.tg; - if (res_ctx->pipe_ctx[i].stream != stream) + if (res_ctx->pipe_ctx[i].stream != stream || !tg) continue; tg->funcs->get_scanoutpos(tg, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c index 50dc83404644..11f7746f3a65 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c @@ -613,16 +613,19 @@ static void dpp3_program_blnd_pwl( REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, rgb[i].red_reg); REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, last_base_value_red); } else { + REG_SET(CM_BLNDGAM_LUT_INDEX, 0, CM_BLNDGAM_LUT_INDEX, 0); REG_UPDATE(CM_BLNDGAM_LUT_CONTROL, CM_BLNDGAM_LUT_WRITE_COLOR_MASK, 4); for (i = 0 ; i < num; i++) REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, rgb[i].red_reg); REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, last_base_value_red); + REG_SET(CM_BLNDGAM_LUT_INDEX, 0, CM_BLNDGAM_LUT_INDEX, 0); REG_UPDATE(CM_BLNDGAM_LUT_CONTROL, CM_BLNDGAM_LUT_WRITE_COLOR_MASK, 2); for (i = 0 ; i < num; i++) REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, rgb[i].green_reg); REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, last_base_value_green); + REG_SET(CM_BLNDGAM_LUT_INDEX, 0, CM_BLNDGAM_LUT_INDEX, 0); REG_UPDATE(CM_BLNDGAM_LUT_CONTROL, CM_BLNDGAM_LUT_WRITE_COLOR_MASK, 1); for (i = 0 ; i < num; i++) REG_SET(CM_BLNDGAM_LUT_DATA, 0, CM_BLNDGAM_LUT_DATA, rgb[i].blue_reg); diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c index 2861d974fcf6..75547ce86c09 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.c @@ -316,7 +316,7 @@ bool hubp3_program_surface_flip_and_addr( return true; } -static void hubp3_program_tiling( +void hubp3_program_tiling( struct dcn20_hubp *hubp2, const union dc_tiling_info *info, const enum surface_pixel_format pixel_format) diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h index 8a32772d4e91..b010531a7fe8 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hubp.h @@ -278,6 +278,11 @@ void hubp3_setup( struct _vcs_dpi_display_rq_regs_st *rq_regs, struct _vcs_dpi_display_pipe_dest_params_st *pipe_dest); +void hubp3_program_tiling( + struct dcn20_hubp *hubp2, + const union dc_tiling_info *info, + const enum surface_pixel_format pixel_format); + void hubp3_dcc_control(struct hubp *hubp, bool enable, enum hubp_ind_block_size blk_size); diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c index 1d052f08aff5..994b21ed272f 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c +++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_mpc.c @@ -237,16 +237,19 @@ void mpc32_program_post1dlut_pwl( REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, rgb[i].red_reg); REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, last_base_value_red); } else { + REG_SET(MPCC_MCM_1DLUT_LUT_INDEX[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_INDEX, 0); REG_UPDATE(MPCC_MCM_1DLUT_LUT_CONTROL[mpcc_id], MPCC_MCM_1DLUT_LUT_WRITE_COLOR_MASK, 4); for (i = 0 ; i < num; i++) REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, rgb[i].red_reg); REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, last_base_value_red); + REG_SET(MPCC_MCM_1DLUT_LUT_INDEX[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_INDEX, 0); REG_UPDATE(MPCC_MCM_1DLUT_LUT_CONTROL[mpcc_id], MPCC_MCM_1DLUT_LUT_WRITE_COLOR_MASK, 2); for (i = 0 ; i < num; i++) REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, rgb[i].green_reg); REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, last_base_value_green); + REG_SET(MPCC_MCM_1DLUT_LUT_INDEX[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_INDEX, 0); REG_UPDATE(MPCC_MCM_1DLUT_LUT_CONTROL[mpcc_id], MPCC_MCM_1DLUT_LUT_WRITE_COLOR_MASK, 1); for (i = 0 ; i < num; i++) REG_SET(MPCC_MCM_1DLUT_LUT_DATA[mpcc_id], 0, MPCC_MCM_1DLUT_LUT_DATA, rgb[i].blue_reg); diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.c index 1ed58660779e..771fcd0d3b99 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.c @@ -53,11 +53,146 @@ static void hubp35_init(struct hubp *hubp) /*do nothing for now for dcn3.5 or later*/ } + +void hubp35_program_pixel_format( + struct hubp *hubp, + enum surface_pixel_format format) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + uint32_t green_bar = 1; + uint32_t red_bar = 3; + uint32_t blue_bar = 2; + + /* swap for ABGR format */ + if (format == SURFACE_PIXEL_FORMAT_GRPH_ABGR8888 + || format == SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010 + || format == SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010_XR_BIAS + || format == SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616 + || format == SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F) { + red_bar = 2; + blue_bar = 3; + } + + REG_UPDATE_3(HUBPRET_CONTROL, + CROSSBAR_SRC_Y_G, green_bar, + CROSSBAR_SRC_CB_B, blue_bar, + CROSSBAR_SRC_CR_R, red_bar); + + /* Mapping is same as ipp programming (cnvc) */ + + switch (format) { + case SURFACE_PIXEL_FORMAT_GRPH_ARGB1555: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 1); + break; + case SURFACE_PIXEL_FORMAT_GRPH_RGB565: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 3); + break; + case SURFACE_PIXEL_FORMAT_GRPH_ARGB8888: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR8888: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 8); + break; + case SURFACE_PIXEL_FORMAT_GRPH_ARGB2101010: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR2101010_XR_BIAS: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 10); + break; + case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616: /* we use crossbar already */ + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 26); /* ARGB16161616_UNORM */ + break; + case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F: + case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:/*we use crossbar already*/ + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 24); + break; + + case SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 65); + break; + case SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 64); + break; + case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 67); + break; + case SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 66); + break; + case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 12); + break; + case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FIX: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 112); + break; + case SURFACE_PIXEL_FORMAT_GRPH_BGR101111_FIX: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 113); + break; + case SURFACE_PIXEL_FORMAT_VIDEO_ACrYCb2101010: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 114); + break; + case SURFACE_PIXEL_FORMAT_GRPH_RGB111110_FLOAT: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 118); + break; + case SURFACE_PIXEL_FORMAT_GRPH_BGR101111_FLOAT: + REG_UPDATE(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 119); + break; + case SURFACE_PIXEL_FORMAT_GRPH_RGBE: + REG_UPDATE_2(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 116, + ALPHA_PLANE_EN, 0); + break; + case SURFACE_PIXEL_FORMAT_GRPH_RGBE_ALPHA: + REG_UPDATE_2(DCSURF_SURFACE_CONFIG, + SURFACE_PIXEL_FORMAT, 116, + ALPHA_PLANE_EN, 1); + break; + default: + BREAK_TO_DEBUGGER(); + break; + } + + /* don't see the need of program the xbar in DCN 1.0 */ +} + +void hubp35_program_surface_config( + struct hubp *hubp, + enum surface_pixel_format format, + union dc_tiling_info *tiling_info, + struct plane_size *plane_size, + enum dc_rotation_angle rotation, + struct dc_plane_dcc_param *dcc, + bool horizontal_mirror, + unsigned int compat_level) +{ + struct dcn20_hubp *hubp2 = TO_DCN20_HUBP(hubp); + + hubp3_dcc_control_sienna_cichlid(hubp, dcc); + hubp3_program_tiling(hubp2, tiling_info, format); + hubp2_program_size(hubp, format, plane_size, dcc); + hubp2_program_rotation(hubp, rotation, horizontal_mirror); + hubp35_program_pixel_format(hubp, format); +} + struct hubp_funcs dcn35_hubp_funcs = { .hubp_enable_tripleBuffer = hubp2_enable_triplebuffer, .hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled, .hubp_program_surface_flip_and_addr = hubp3_program_surface_flip_and_addr, - .hubp_program_surface_config = hubp3_program_surface_config, + .hubp_program_surface_config = hubp35_program_surface_config, .hubp_is_flip_pending = hubp2_is_flip_pending, .hubp_setup = hubp3_setup, .hubp_setup_interdependent = hubp2_setup_interdependent, diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.h index 3d830f93141e..586b43aa5834 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_hubp.h @@ -58,4 +58,18 @@ bool hubp35_construct( void hubp35_set_fgcg(struct hubp *hubp, bool enable); +void hubp35_program_pixel_format( + struct hubp *hubp, + enum surface_pixel_format format); + +void hubp35_program_surface_config( + struct hubp *hubp, + enum surface_pixel_format format, + union dc_tiling_info *tiling_info, + struct plane_size *plane_size, + enum dc_rotation_angle rotation, + struct dc_plane_dcc_param *dcc, + bool horizontal_mirror, + unsigned int compat_level); + #endif /* __DC_HUBP_DCN35_H__ */ diff --git a/drivers/gpu/drm/amd/display/dc/dml2/Makefile b/drivers/gpu/drm/amd/display/dc/dml2/Makefile index 70ae5eba624e..acff3449b8d7 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dml2/Makefile @@ -60,8 +60,12 @@ endif endif ifneq ($(CONFIG_FRAME_WARN),0) +ifeq ($(filter y,$(CONFIG_KASAN)$(CONFIG_KCSAN)),y) +frame_warn_flag := -Wframe-larger-than=3072 +else frame_warn_flag := -Wframe-larger-than=2048 endif +endif CFLAGS_$(AMDDALPATH)/dc/dml2/display_mode_core.o := $(dml2_ccflags) $(frame_warn_flag) CFLAGS_$(AMDDALPATH)/dc/dml2/display_mode_util.o := $(dml2_ccflags) diff --git a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_2_sh_mask.h index 6e29a185de51..765d9ca2316f 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_2_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/mp/mp_13_0_2_sh_mask.h @@ -242,6 +242,34 @@ //MP0_SMN_C2PMSG_103 #define MP0_SMN_C2PMSG_103__CONTENT__SHIFT 0x0 #define MP0_SMN_C2PMSG_103__CONTENT_MASK 0xFFFFFFFFL +//MP0_SMN_C2PMSG_109 +#define MP0_SMN_C2PMSG_109__CONTENT__SHIFT 0x0 +#define MP0_SMN_C2PMSG_109__CONTENT_MASK 0xFFFFFFFFL +//MP0_SMN_C2PMSG_126 +#define MP0_SMN_C2PMSG_126__GPU_ERR_MEM_TRAINING__SHIFT 0x0 +#define MP0_SMN_C2PMSG_126__GPU_ERR_FW_LOAD__SHIFT 0x1 +#define MP0_SMN_C2PMSG_126__GPU_ERR_WAFL_LINK_TRAINING__SHIFT 0x2 +#define MP0_SMN_C2PMSG_126__GPU_ERR_XGMI_LINK_TRAINING__SHIFT 0x3 +#define MP0_SMN_C2PMSG_126__GPU_ERR_USR_CP_LINK_TRAINING__SHIFT 0x4 +#define MP0_SMN_C2PMSG_126__GPU_ERR_USR_DP_LINK_TRAINING__SHIFT 0x5 +#define MP0_SMN_C2PMSG_126__GPU_ERR_HBM_MEM_TEST__SHIFT 0x6 +#define MP0_SMN_C2PMSG_126__GPU_ERR_HBM_BIST_TEST__SHIFT 0x7 +#define MP0_SMN_C2PMSG_126__SOCKET_ID__SHIFT 0x8 +#define MP0_SMN_C2PMSG_126__AID_ID__SHIFT 0xb +#define MP0_SMN_C2PMSG_126__HBM_ID__SHIFT 0xd +#define MP0_SMN_C2PMSG_126__BOOT_STATUS__SHIFT 0x1f +#define MP0_SMN_C2PMSG_126__GPU_ERR_MEM_TRAINING_MASK 0x00000001L +#define MP0_SMN_C2PMSG_126__GPU_ERR_FW_LOAD_MASK 0x00000002L +#define MP0_SMN_C2PMSG_126__GPU_ERR_WAFL_LINK_TRAINING_MASK 0x00000004L +#define MP0_SMN_C2PMSG_126__GPU_ERR_XGMI_LINK_TRAINING_MASK 0x00000008L +#define MP0_SMN_C2PMSG_126__GPU_ERR_USR_CP_LINK_TRAINING_MASK 0x00000010L +#define MP0_SMN_C2PMSG_126__GPU_ERR_USR_DP_LINK_TRAINING_MASK 0x00000020L +#define MP0_SMN_C2PMSG_126__GPU_ERR_HBM_MEM_TEST_MASK 0x00000040L +#define MP0_SMN_C2PMSG_126__GPU_ERR_HBM_BIST_TEST_MASK 0x00000080L +#define MP0_SMN_C2PMSG_126__SOCKET_ID_MASK 0x00000700L +#define MP0_SMN_C2PMSG_126__AID_ID_MASK 0x00001800L +#define MP0_SMN_C2PMSG_126__HBM_ID_MASK 0x00002000L +#define MP0_SMN_C2PMSG_126__BOOT_STATUS_MASK 0x80000000L //MP0_SMN_IH_CREDIT #define MP0_SMN_IH_CREDIT__CREDIT_VALUE__SHIFT 0x0 #define MP0_SMN_IH_CREDIT__CLIENT_ID__SHIFT 0x10 diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h index 3201808c2dd8..cd3c40a86029 100644 --- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h @@ -1080,33 +1080,35 @@ struct gpu_metrics_v3_0 { uint16_t average_ipu_activity[8]; /* time filtered per-core C0 residency % [0-100]*/ uint16_t average_core_c0_activity[16]; - /* time filtered DRAM read bandwidth [GB/sec] */ + /* time filtered DRAM read bandwidth [MB/sec] */ uint16_t average_dram_reads; - /* time filtered DRAM write bandwidth [GB/sec] */ + /* time filtered DRAM write bandwidth [MB/sec] */ uint16_t average_dram_writes; /* Driver attached timestamp (in ns) */ uint64_t system_clock_counter; /* Power/Energy */ - /* average dGPU + APU power on A + A platform */ + /* time filtered power used for PPT/STAPM [APU+dGPU] [mW] */ uint32_t average_socket_power; - /* average IPU power [W] */ + /* time filtered IPU power [mW] */ uint16_t average_ipu_power; - /* average APU power [W] */ + /* time filtered APU power [mW] */ uint32_t average_apu_power; - /* average dGPU power [W] */ + /* time filtered GFX power [mW] */ + uint32_t average_gfx_power; + /* time filtered dGPU power [mW] */ uint32_t average_dgpu_power; - /* sum of core power across all cores in the socket [W] */ - uint32_t average_core_power; - /* calculated core power [W] */ - uint16_t core_power[16]; - /* maximum IRM defined STAPM power limit [W] */ + /* time filtered sum of core power across all cores in the socket [mW] */ + uint32_t average_all_core_power; + /* calculated core power [mW] */ + uint16_t average_core_power[16]; + /* maximum IRM defined STAPM power limit [mW] */ uint16_t stapm_power_limit; - /* time filtered STAPM power limit [W] */ + /* time filtered STAPM power limit [mW] */ uint16_t current_stapm_power_limit; - /* Average clocks */ + /* time filtered clocks [MHz] */ uint16_t average_gfxclk_frequency; uint16_t average_socclk_frequency; uint16_t average_vpeclk_frequency; @@ -1115,7 +1117,7 @@ struct gpu_metrics_v3_0 { uint16_t average_vclk_frequency; /* Current clocks */ - /* target core frequency */ + /* target core frequency [MHz] */ uint16_t current_coreclk[16]; /* CCLK frequency limit enforced on classic cores [MHz] */ uint16_t current_core_maxfreq; diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 517b9fb4624c..4ba9195c83c5 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -3288,10 +3288,6 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, uint32_t gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0); uint32_t tmp; - /* under multi-vf mode, the hwmon attributes are all not supported */ - if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) - return 0; - /* under pp one vf mode manage of hwmon attributes is not supported */ if (amdgpu_sriov_is_pp_one_vf(adev)) effective_mode &= ~S_IWUSR; @@ -4162,6 +4158,7 @@ err_out: int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) { + enum amdgpu_sriov_vf_mode mode; uint32_t mask = 0; int ret; @@ -4173,17 +4170,21 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev) if (adev->pm.dpm_enabled == 0) return 0; - adev->pm.int_hwmon_dev = hwmon_device_register_with_groups(adev->dev, - DRIVER_NAME, adev, - hwmon_groups); - if (IS_ERR(adev->pm.int_hwmon_dev)) { - ret = PTR_ERR(adev->pm.int_hwmon_dev); - dev_err(adev->dev, - "Unable to register hwmon device: %d\n", ret); - return ret; + mode = amdgpu_virt_get_sriov_vf_mode(adev); + + /* under multi-vf mode, the hwmon attributes are all not supported */ + if (mode != SRIOV_VF_MODE_MULTI_VF) { + adev->pm.int_hwmon_dev = hwmon_device_register_with_groups(adev->dev, + DRIVER_NAME, adev, + hwmon_groups); + if (IS_ERR(adev->pm.int_hwmon_dev)) { + ret = PTR_ERR(adev->pm.int_hwmon_dev); + dev_err(adev->dev, "Unable to register hwmon device: %d\n", ret); + return ret; + } } - switch (amdgpu_virt_get_sriov_vf_mode(adev)) { + switch (mode) { case SRIOV_VF_MODE_ONE_VF: mask = ATTR_FLAG_ONEVF; break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 9e4f8a4104a3..914c15387157 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -1022,6 +1022,9 @@ static int pp_get_power_limit(void *handle, uint32_t *limit, *limit /= 100; } break; + case PP_PWR_LIMIT_MIN: + *limit = 0; + break; default: ret = -EOPNOTSUPP; break; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h index 9fcad69a9f34..2cf2a7b12623 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pptable_v1_0.h @@ -367,7 +367,7 @@ typedef struct _ATOM_Tonga_VCE_State_Record { typedef struct _ATOM_Tonga_VCE_State_Table { UCHAR ucRevId; UCHAR ucNumEntries; - ATOM_Tonga_VCE_State_Record entries[1]; + ATOM_Tonga_VCE_State_Record entries[]; } ATOM_Tonga_VCE_State_Table; typedef struct _ATOM_Tonga_PowerTune_Table { @@ -481,7 +481,7 @@ typedef struct _ATOM_Tonga_Hard_Limit_Record { typedef struct _ATOM_Tonga_Hard_Limit_Table { UCHAR ucRevId; UCHAR ucNumEntries; - ATOM_Tonga_Hard_Limit_Record entries[1]; + ATOM_Tonga_Hard_Limit_Record entries[]; } ATOM_Tonga_Hard_Limit_Table; typedef struct _ATOM_Tonga_GPIO_Table { diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_pptable.h b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_pptable.h index 8b0590b834cc..de2926df5ed7 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_pptable.h +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_pptable.h @@ -129,7 +129,7 @@ typedef struct _ATOM_Vega10_State { typedef struct _ATOM_Vega10_State_Array { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Vega10_State states[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_State states[]; /* Dynamically allocate entries. */ } ATOM_Vega10_State_Array; typedef struct _ATOM_Vega10_CLK_Dependency_Record { @@ -169,37 +169,37 @@ typedef struct _ATOM_Vega10_GFXCLK_Dependency_Table { typedef struct _ATOM_Vega10_MCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Vega10_MCLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_MCLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_MCLK_Dependency_Table; typedef struct _ATOM_Vega10_SOCCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Vega10_CLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_CLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_SOCCLK_Dependency_Table; typedef struct _ATOM_Vega10_DCEFCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Vega10_CLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_CLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_DCEFCLK_Dependency_Table; typedef struct _ATOM_Vega10_PIXCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Vega10_CLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_CLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_PIXCLK_Dependency_Table; typedef struct _ATOM_Vega10_DISPCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries.*/ - ATOM_Vega10_CLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_CLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_DISPCLK_Dependency_Table; typedef struct _ATOM_Vega10_PHYCLK_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries. */ - ATOM_Vega10_CLK_Dependency_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_CLK_Dependency_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_PHYCLK_Dependency_Table; typedef struct _ATOM_Vega10_MM_Dependency_Record { @@ -213,7 +213,7 @@ typedef struct _ATOM_Vega10_MM_Dependency_Record { typedef struct _ATOM_Vega10_MM_Dependency_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries */ - ATOM_Vega10_MM_Dependency_Record entries[1]; /* Dynamically allocate entries */ + ATOM_Vega10_MM_Dependency_Record entries[]; /* Dynamically allocate entries */ } ATOM_Vega10_MM_Dependency_Table; typedef struct _ATOM_Vega10_PCIE_Record { @@ -225,7 +225,7 @@ typedef struct _ATOM_Vega10_PCIE_Record { typedef struct _ATOM_Vega10_PCIE_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries */ - ATOM_Vega10_PCIE_Record entries[1]; /* Dynamically allocate entries. */ + ATOM_Vega10_PCIE_Record entries[]; /* Dynamically allocate entries. */ } ATOM_Vega10_PCIE_Table; typedef struct _ATOM_Vega10_Voltage_Lookup_Record { @@ -235,7 +235,7 @@ typedef struct _ATOM_Vega10_Voltage_Lookup_Record { typedef struct _ATOM_Vega10_Voltage_Lookup_Table { UCHAR ucRevId; UCHAR ucNumEntries; /* Number of entries */ - ATOM_Vega10_Voltage_Lookup_Record entries[1]; /* Dynamically allocate entries */ + ATOM_Vega10_Voltage_Lookup_Record entries[]; /* Dynamically allocate entries */ } ATOM_Vega10_Voltage_Lookup_Table; typedef struct _ATOM_Vega10_Fan_Table { @@ -327,7 +327,7 @@ typedef struct _ATOM_Vega10_VCE_State_Record { typedef struct _ATOM_Vega10_VCE_State_Table { UCHAR ucRevId; UCHAR ucNumEntries; - ATOM_Vega10_VCE_State_Record entries[1]; + ATOM_Vega10_VCE_State_Record entries[]; } ATOM_Vega10_VCE_State_Table; typedef struct _ATOM_Vega10_PowerTune_Table { @@ -427,7 +427,7 @@ typedef struct _ATOM_Vega10_Hard_Limit_Record { typedef struct _ATOM_Vega10_Hard_Limit_Table { UCHAR ucRevId; UCHAR ucNumEntries; - ATOM_Vega10_Hard_Limit_Record entries[1]; + ATOM_Vega10_Hard_Limit_Record entries[]; } ATOM_Vega10_Hard_Limit_Table; typedef struct _Vega10_PPTable_Generic_SubTable_Header { diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 9f86c1fecbb1..23b00eddc1af 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -733,7 +733,7 @@ static int smu_early_init(void *handle) smu->adev = adev; smu->pm_enabled = !!amdgpu_dpm; smu->is_apu = false; - smu->smu_baco.state = SMU_BACO_STATE_EXIT; + smu->smu_baco.state = SMU_BACO_STATE_NONE; smu->smu_baco.platform_support = false; smu->user_dpm_profile.fan_mode = -1; @@ -1742,10 +1742,31 @@ static int smu_smc_hw_cleanup(struct smu_context *smu) return 0; } +static int smu_reset_mp1_state(struct smu_context *smu) +{ + struct amdgpu_device *adev = smu->adev; + int ret = 0; + + if ((!adev->in_runpm) && (!adev->in_suspend) && + (!amdgpu_in_reset(adev))) + switch (amdgpu_ip_version(adev, MP1_HWIP, 0)) { + case IP_VERSION(13, 0, 0): + case IP_VERSION(13, 0, 7): + case IP_VERSION(13, 0, 10): + ret = smu_set_mp1_state(smu, PP_MP1_STATE_UNLOAD); + break; + default: + break; + } + + return ret; +} + static int smu_hw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct smu_context *smu = adev->powerplay.pp_handle; + int ret; if (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) return 0; @@ -1763,7 +1784,15 @@ static int smu_hw_fini(void *handle) adev->pm.dpm_enabled = false; - return smu_smc_hw_cleanup(smu); + ret = smu_smc_hw_cleanup(smu); + if (ret) + return ret; + + ret = smu_reset_mp1_state(smu); + if (ret) + return ret; + + return 0; } static void smu_late_fini(void *handle) diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h index 839553a86aa2..8def291b18bc 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h @@ -419,6 +419,7 @@ enum smu_reset_mode { enum smu_baco_state { SMU_BACO_STATE_ENTER = 0, SMU_BACO_STATE_EXIT, + SMU_BACO_STATE_NONE, }; struct smu_baco_context { diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h index b483c8e096e7..22f88842a7fd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu14_driver_if_v14_0_0.h @@ -150,97 +150,39 @@ typedef struct { } DpmClocks_t; typedef struct { - uint16_t CoreFrequency[16]; //Target core frequency [MHz] - uint16_t CorePower[16]; //CAC calculated core power [W] [Q8.8] - uint16_t CoreTemperature[16]; //TSEN measured core temperature [C] [Q8.8] - uint16_t GfxTemperature; //TSEN measured GFX temperature [C] [Q8.8] - uint16_t SocTemperature; //TSEN measured SOC temperature [C] [Q8.8] - uint16_t StapmOpnLimit; //Maximum IRM defined STAPM power limit [W] [Q8.8] - uint16_t StapmCurrentLimit; //Time filtered STAPM power limit [W] [Q8.8] - uint16_t InfrastructureCpuMaxFreq; //CCLK frequency limit enforced on classic cores [MHz] - uint16_t InfrastructureGfxMaxFreq; //GFXCLK frequency limit enforced on GFX [MHz] - uint16_t SkinTemp; //Maximum skin temperature reported by APU and HS2 chassis sensors [C] [Q8.8] - uint16_t AverageGfxclkFrequency; //Time filtered target GFXCLK frequency [MHz] - uint16_t AverageFclkFrequency; //Time filtered target FCLK frequency [MHz] - uint16_t AverageGfxActivity; //Time filtered GFX busy % [0-100] [Q8.8] - uint16_t AverageSocclkFrequency; //Time filtered target SOCCLK frequency [MHz] - uint16_t AverageVclkFrequency; //Time filtered target VCLK frequency [MHz] - uint16_t AverageVcnActivity; //Time filtered VCN busy % [0-100] [Q8.8] - uint16_t AverageVpeclkFrequency; //Time filtered target VPECLK frequency [MHz] - uint16_t AverageIpuclkFrequency; //Time filtered target IPUCLK frequency [MHz] - uint16_t AverageIpuBusy[8]; //Time filtered IPU per-column busy % [0-100] [Q8.8] - uint16_t AverageDRAMReads; //Time filtered DRAM read bandwidth [GB/sec] [Q8.8] - uint16_t AverageDRAMWrites; //Time filtered DRAM write bandwidth [GB/sec] [Q8.8] - uint16_t AverageCoreC0Residency[16]; //Time filtered per-core C0 residency % [0-100] [Q8.8] - uint16_t IpuPower; //Time filtered IPU power [W] [Q8.8] - uint32_t ApuPower; //Time filtered APU power [W] [Q24.8] - uint32_t dGpuPower; //Time filtered dGPU power [W] [Q24.8] - uint32_t AverageSocketPower; //Time filtered power used for PPT/STAPM [APU+dGPU] [W] [Q24.8] - uint32_t AverageCorePower; //Time filtered sum of core power across all cores in the socket [W] [Q24.8] - uint32_t FilterAlphaValue; //Metrics table alpha filter time constant [us] - uint32_t MetricsCounter; //Counter that is incremented on every metrics table update [PM_TIMER cycles] + uint16_t CoreFrequency[16]; //Target core frequency [MHz] + uint16_t CorePower[16]; //CAC calculated core power [mW] + uint16_t CoreTemperature[16]; //TSEN measured core temperature [centi-C] + uint16_t GfxTemperature; //TSEN measured GFX temperature [centi-C] + uint16_t SocTemperature; //TSEN measured SOC temperature [centi-C] + uint16_t StapmOpnLimit; //Maximum IRM defined STAPM power limit [mW] + uint16_t StapmCurrentLimit; //Time filtered STAPM power limit [mW] + uint16_t InfrastructureCpuMaxFreq; //CCLK frequency limit enforced on classic cores [MHz] + uint16_t InfrastructureGfxMaxFreq; //GFXCLK frequency limit enforced on GFX [MHz] + uint16_t SkinTemp; //Maximum skin temperature reported by APU and HS2 chassis sensors [centi-C] + uint16_t GfxclkFrequency; //Time filtered target GFXCLK frequency [MHz] + uint16_t FclkFrequency; //Time filtered target FCLK frequency [MHz] + uint16_t GfxActivity; //Time filtered GFX busy % [0-100] + uint16_t SocclkFrequency; //Time filtered target SOCCLK frequency [MHz] + uint16_t VclkFrequency; //Time filtered target VCLK frequency [MHz] + uint16_t VcnActivity; //Time filtered VCN busy % [0-100] + uint16_t VpeclkFrequency; //Time filtered target VPECLK frequency [MHz] + uint16_t IpuclkFrequency; //Time filtered target IPUCLK frequency [MHz] + uint16_t IpuBusy[8]; //Time filtered IPU per-column busy % [0-100] + uint16_t DRAMReads; //Time filtered DRAM read bandwidth [MB/sec] + uint16_t DRAMWrites; //Time filtered DRAM write bandwidth [MB/sec] + uint16_t CoreC0Residency[16]; //Time filtered per-core C0 residency % [0-100] + uint16_t IpuPower; //Time filtered IPU power [mW] + uint32_t ApuPower; //Time filtered APU power [mW] + uint32_t GfxPower; //Time filtered GFX power [mW] + uint32_t dGpuPower; //Time filtered dGPU power [mW] + uint32_t SocketPower; //Time filtered power used for PPT/STAPM [APU+dGPU] [mW] + uint32_t AllCorePower; //Time filtered sum of core power across all cores in the socket [mW] + uint32_t FilterAlphaValue; //Metrics table alpha filter time constant [us] + uint32_t MetricsCounter; //Counter that is incremented on every metrics table update [PM_TIMER cycles] + uint32_t spare[16]; } SmuMetrics_t; -typedef struct { - uint16_t GfxclkFrequency; //[MHz] - uint16_t SocclkFrequency; //[MHz] - uint16_t VclkFrequency; //[MHz] - uint16_t DclkFrequency; //[MHz] - uint16_t MemclkFrequency; //[MHz] - uint16_t spare; - uint16_t UvdActivity; //[centi] - uint16_t GfxActivity; //[centi] - - uint16_t Voltage[2]; //[mV] indices: VDDCR_VDD, VDDCR_SOC - uint16_t Current[2]; //[mA] indices: VDDCR_VDD, VDDCR_SOC - uint16_t Power[2]; //[mW] indices: VDDCR_VDD, VDDCR_SOC - - uint16_t CoreFrequency[8]; //[MHz] - uint16_t CorePower[8]; //[mW] - uint16_t CoreTemperature[8]; //[centi-Celsius] - uint16_t L3Frequency[2]; //[MHz] - uint16_t L3Temperature[2]; //[centi-Celsius] - - uint16_t spare2[24]; - - uint16_t GfxTemperature; //[centi-Celsius] - uint16_t SocTemperature; //[centi-Celsius] - uint16_t ThrottlerStatus; - - uint16_t CurrentSocketPower; //[mW] - uint16_t StapmOpnLimit; //[W] - uint16_t StapmCurrentLimit; //[W] - uint32_t ApuPower; //[mW] - uint32_t dGpuPower; //[mW] - - uint16_t VddTdcValue; //[mA] - uint16_t SocTdcValue; //[mA] - uint16_t VddEdcValue; //[mA] - uint16_t SocEdcValue; //[mA] - - uint16_t InfrastructureCpuMaxFreq; //[MHz] - uint16_t InfrastructureGfxMaxFreq; //[MHz] - - uint16_t SkinTemp; - uint16_t DeviceState; - uint16_t CurTemp; //[centi-Celsius] - uint16_t FilterAlphaValue; //[m] - - uint16_t AverageGfxclkFrequency; - uint16_t AverageFclkFrequency; - uint16_t AverageGfxActivity; - uint16_t AverageSocclkFrequency; - uint16_t AverageVclkFrequency; - uint16_t AverageVcnActivity; - uint16_t AverageDRAMReads; //Filtered DF Bandwidth::DRAM Reads - uint16_t AverageDRAMWrites; //Filtered DF Bandwidth::DRAM Writes - uint16_t AverageSocketPower; //Filtered value of CurrentSocketPower - uint16_t AverageCorePower[2]; //Filtered of [sum of CorePower[8] per ccx]) - uint16_t AverageCoreC0Residency[16]; //Filtered of [average C0 residency % per core] - uint16_t spare1; - uint32_t MetricsCounter; //Counts the # of metrics table parameter reads per update to the metrics table, i.e. if the metrics table update happens every 1 second, this value could be up to 1000 if the smu collected metrics data every cycle, or as low as 0 if the smu was asleep the whole time. Reset to 0 after writing. -} SmuMetrics_legacy_t; - //ISP tile definitions typedef enum { TILE_XTILE = 0, //ONO0 diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index cc02f979e9e9..95cb919718ae 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -299,5 +299,7 @@ int smu_v13_0_update_pcie_parameters(struct smu_context *smu, uint8_t pcie_gen_cap, uint8_t pcie_width_cap); +int smu_v13_0_disable_pmfw_state(struct smu_context *smu); + #endif #endif 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 3efc6aed28f1..762b31455a0b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -234,24 +234,15 @@ static int vangogh_tables_init(struct smu_context *smu) PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_ACTIVITY_MONITOR_COEFF, sizeof(DpmActivityMonitorCoeffExt_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, max(sizeof(SmuMetrics_t), sizeof(SmuMetrics_legacy_t)), + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - if (smu->smc_fw_if_version < 0x3) { - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_legacy_t), - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_legacy_t), GFP_KERNEL); - } else { - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL); - } + smu_table->metrics_table = kzalloc(max(sizeof(SmuMetrics_t), sizeof(SmuMetrics_legacy_t)), GFP_KERNEL); if (!smu_table->metrics_table) goto err0_out; smu_table->metrics_time = 0; - if (smu->smc_fw_version >= 0x043F3E00) - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_3); - else - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_2); + smu_table->gpu_metrics_table_size = max(sizeof(struct gpu_metrics_v2_3), 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; 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 a49e5adf7cc3..cf1b84060bc3 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 @@ -2477,3 +2477,16 @@ int smu_v13_0_update_pcie_parameters(struct smu_context *smu, return 0; } + +int smu_v13_0_disable_pmfw_state(struct smu_context *smu) +{ + int ret; + struct amdgpu_device *adev = smu->adev; + + WREG32_PCIE(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff), 0); + + ret = RREG32_PCIE(MP1_Public | + (smnMP1_FIRMWARE_FLAGS & 0xffffffff)); + + return ret == 0 ? 0 : -EINVAL; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 34bd99b0e137..82c4e1f1c6f0 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -354,12 +354,12 @@ static int smu_v13_0_0_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) + if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_BACO) { smu_baco->platform_support = true; - if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) - smu_baco->maco_support = true; + if (powerplay_table->platform_caps & SMU_13_0_0_PP_PLATFORM_CAP_MACO) + smu_baco->maco_support = true; + } if (!overdrive_lowerlimits->FeatureCtrlMask || !overdrive_upperlimits->FeatureCtrlMask) @@ -2530,38 +2530,10 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu, } } - if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_COMPUTE && - (((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xC8)) || - ((smu->adev->pdev->device == 0x744C) && (smu->adev->pdev->revision == 0xCC)))) { - ret = smu_cmn_update_table(smu, - SMU_TABLE_ACTIVITY_MONITOR_COEFF, - WORKLOAD_PPLIB_COMPUTE_BIT, - (void *)(&activity_monitor_external), - false); - if (ret) { - dev_err(smu->adev->dev, "[%s] Failed to get activity monitor!", __func__); - return ret; - } - - ret = smu_cmn_update_table(smu, - SMU_TABLE_ACTIVITY_MONITOR_COEFF, - WORKLOAD_PPLIB_CUSTOM_BIT, - (void *)(&activity_monitor_external), - true); - if (ret) { - dev_err(smu->adev->dev, "[%s] Failed to set activity monitor!", __func__); - return ret; - } - - workload_type = smu_cmn_to_asic_specific_index(smu, - CMN2ASIC_MAPPING_WORKLOAD, - PP_SMC_POWER_PROFILE_CUSTOM); - } else { - /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ - workload_type = smu_cmn_to_asic_specific_index(smu, + /* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */ + workload_type = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_WORKLOAD, smu->power_profile_mode); - } if (workload_type < 0) return -EINVAL; @@ -2602,14 +2574,20 @@ static int smu_v13_0_0_baco_enter(struct smu_context *smu) static int smu_v13_0_0_baco_exit(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; + int ret; if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) { /* Wait for PMFW handling for the Dstate change */ usleep_range(10000, 11000); - return smu_v13_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); + ret = smu_v13_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); } else { - return smu_v13_0_baco_exit(smu); + ret = smu_v13_0_baco_exit(smu); } + + if (!ret) + adev->gfx.is_poweron = false; + + return ret; } static bool smu_v13_0_0_is_mode1_reset_supported(struct smu_context *smu) @@ -2794,7 +2772,13 @@ static int smu_v13_0_0_set_mp1_state(struct smu_context *smu, switch (mp1_state) { case PP_MP1_STATE_UNLOAD: - ret = smu_cmn_set_mp1_state(smu, mp1_state); + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_PrepareMp1ForUnload, + 0x55, NULL); + + if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT) + ret = smu_v13_0_disable_pmfw_state(smu); + break; default: /* Ignore others */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index f42b48b31927..20f66e696f87 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -270,7 +270,7 @@ static int smu_v13_0_6_init_microcode(struct smu_context *smu) struct amdgpu_device *adev = smu->adev; uint32_t p2s_table_id = P2S_TABLE_ID_A; int ret = 0, i, p2stable_count; - char ucode_prefix[30]; + char ucode_prefix[15]; char fw_name[30]; /* No need to load P2S tables in IOV mode */ diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index ac0e1cc812bd..81eafed76045 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -346,12 +346,13 @@ static int smu_v13_0_7_check_powerplay_table(struct smu_context *smu) if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_HARDWAREDC) smu->dc_controlled_by_gpio = true; - if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_BACO || - powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_MACO) + if (powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_BACO) { smu_baco->platform_support = true; - if (smu_baco->platform_support && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) - smu_baco->maco_support = true; + if ((powerplay_table->platform_caps & SMU_13_0_7_PP_PLATFORM_CAP_MACO) + && (BoardTable->HsrEnabled || BoardTable->VddqOffEnabled)) + smu_baco->maco_support = true; + } if (!overdrive_lowerlimits->FeatureCtrlMask || !overdrive_upperlimits->FeatureCtrlMask) @@ -2498,7 +2499,13 @@ static int smu_v13_0_7_set_mp1_state(struct smu_context *smu, switch (mp1_state) { case PP_MP1_STATE_UNLOAD: - ret = smu_cmn_set_mp1_state(smu, mp1_state); + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_PrepareMp1ForUnload, + 0x55, NULL); + + if (!ret && smu->smu_baco.state == SMU_BACO_STATE_EXIT) + ret = smu_v13_0_disable_pmfw_state(smu); + break; default: /* Ignore others */ @@ -2524,14 +2531,20 @@ static int smu_v13_0_7_baco_enter(struct smu_context *smu) static int smu_v13_0_7_baco_exit(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; + int ret; if (adev->in_runpm && smu_cmn_is_audio_func_enabled(adev)) { /* Wait for PMFW handling for the Dstate change */ usleep_range(10000, 11000); - return smu_v13_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); + ret = smu_v13_0_baco_set_armd3_sequence(smu, BACO_SEQ_ULPS); } else { - return smu_v13_0_baco_exit(smu); + ret = smu_v13_0_baco_exit(smu); } + + if (!ret) + adev->gfx.is_poweron = false; + + return ret; } static bool smu_v13_0_7_is_mode1_reset_supported(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c index 4ac22f44d160..d8f8ad0e7137 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c @@ -57,7 +57,7 @@ int smu_v14_0_init_microcode(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; char fw_name[30]; - char ucode_prefix[30]; + char ucode_prefix[15]; int err = 0; const struct smc_firmware_header_v1_0 *hdr; const struct common_firmware_header *header; @@ -229,6 +229,8 @@ int smu_v14_0_check_fw_version(struct smu_context *smu) smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_2; break; case IP_VERSION(14, 0, 0): + if ((smu->smc_fw_version < 0x5d3a00)) + dev_warn(smu->adev->dev, "The PMFW version(%x) is behind in this BIOS!\n", smu->smc_fw_version); smu->smc_driver_if_version = SMU14_DRIVER_IF_VERSION_SMU_V14_0_0; break; default: diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c index c36fc10b63c8..03b38c3a9968 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_0_ppt.c @@ -156,15 +156,10 @@ static int smu_v14_0_0_init_smc_tables(struct smu_context *smu) PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); SMU_TABLE_INIT(tables, SMU_TABLE_DPMCLOCKS, sizeof(DpmClocks_t), PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - if (smu->smc_fw_version > 0x5d3500) { - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL); - } else { - SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_legacy_t), - PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); - smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_legacy_t), GFP_KERNEL); - } + SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t), + PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM); + + smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL); if (!smu_table->metrics_table) goto err0_out; smu_table->metrics_time = 0; @@ -177,10 +172,7 @@ static int smu_v14_0_0_init_smc_tables(struct smu_context *smu) if (!smu_table->watermarks_table) goto err2_out; - if (smu->smc_fw_version > 0x5d3500) - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v3_0); - else - smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v2_1); + smu_table->gpu_metrics_table_size = sizeof(struct gpu_metrics_v3_0); smu_table->gpu_metrics_table = kzalloc(smu_table->gpu_metrics_table_size, GFP_KERNEL); if (!smu_table->gpu_metrics_table) goto err3_out; @@ -242,13 +234,13 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu, switch (member) { case METRICS_AVERAGE_GFXCLK: - *value = metrics->AverageGfxclkFrequency; + *value = metrics->GfxclkFrequency; break; case METRICS_AVERAGE_SOCCLK: - *value = metrics->AverageSocclkFrequency; + *value = metrics->SocclkFrequency; break; case METRICS_AVERAGE_VCLK: - *value = metrics->AverageVclkFrequency; + *value = metrics->VclkFrequency; break; case METRICS_AVERAGE_DCLK: *value = 0; @@ -257,25 +249,25 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu, *value = 0; break; case METRICS_AVERAGE_FCLK: - *value = metrics->AverageFclkFrequency; + *value = metrics->FclkFrequency; break; case METRICS_AVERAGE_GFXACTIVITY: - *value = metrics->AverageGfxActivity >> 8; + *value = metrics->GfxActivity / 100; break; case METRICS_AVERAGE_VCNACTIVITY: - *value = metrics->AverageVcnActivity >> 8; + *value = metrics->VcnActivity / 100; break; case METRICS_AVERAGE_SOCKETPOWER: case METRICS_CURR_SOCKETPOWER: - *value = (metrics->AverageSocketPower & 0xff00) + - ((metrics->AverageSocketPower & 0xff) * 100 >> 8); + *value = (metrics->SocketPower / 1000 << 8) + + (metrics->SocketPower % 1000 / 10); break; case METRICS_TEMPERATURE_EDGE: - *value = (metrics->GfxTemperature >> 8) * + *value = metrics->GfxTemperature / 100 * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_TEMPERATURE_HOTSPOT: - *value = (metrics->SocTemperature >> 8) * + *value = metrics->SocTemperature / 100 * SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; break; case METRICS_THROTTLER_STATUS: @@ -317,107 +309,6 @@ static int smu_v14_0_0_get_smu_metrics_data(struct smu_context *smu, return ret; } -static int smu_v14_0_0_legacy_get_smu_metrics_data(struct smu_context *smu, - MetricsMember_t member, - uint32_t *value) -{ - struct smu_table_context *smu_table = &smu->smu_table; - - SmuMetrics_legacy_t *metrics = (SmuMetrics_legacy_t *)smu_table->metrics_table; - int ret = 0; - - ret = smu_cmn_get_metrics_table(smu, NULL, false); - if (ret) - return ret; - - switch (member) { - case METRICS_AVERAGE_GFXCLK: - *value = metrics->GfxclkFrequency; - break; - case METRICS_AVERAGE_SOCCLK: - *value = metrics->SocclkFrequency; - break; - case METRICS_AVERAGE_VCLK: - *value = metrics->VclkFrequency; - break; - case METRICS_AVERAGE_DCLK: - *value = metrics->DclkFrequency; - break; - case METRICS_AVERAGE_UCLK: - *value = metrics->MemclkFrequency; - break; - case METRICS_AVERAGE_GFXACTIVITY: - *value = metrics->GfxActivity / 100; - break; - case METRICS_AVERAGE_FCLK: - *value = metrics->AverageFclkFrequency; - break; - case METRICS_AVERAGE_VCNACTIVITY: - *value = metrics->UvdActivity; - break; - case METRICS_AVERAGE_SOCKETPOWER: - *value = (metrics->AverageSocketPower << 8) / 1000; - break; - case METRICS_CURR_SOCKETPOWER: - *value = (metrics->CurrentSocketPower << 8) / 1000; - break; - case METRICS_TEMPERATURE_EDGE: - *value = metrics->GfxTemperature / 100 * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - break; - case METRICS_TEMPERATURE_HOTSPOT: - *value = metrics->SocTemperature / 100 * - SMU_TEMPERATURE_UNITS_PER_CENTIGRADES; - break; - case METRICS_THROTTLER_STATUS: - *value = metrics->ThrottlerStatus; - break; - case METRICS_VOLTAGE_VDDGFX: - *value = metrics->Voltage[0]; - break; - 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; - } - - return ret; -} - -static int smu_v14_0_0_common_get_smu_metrics_data(struct smu_context *smu, - MetricsMember_t member, - uint32_t *value) -{ - if (smu->smc_fw_version > 0x5d3500) - return smu_v14_0_0_get_smu_metrics_data(smu, member, value); - else - return smu_v14_0_0_legacy_get_smu_metrics_data(smu, member, value); -} - static int smu_v14_0_0_read_sensor(struct smu_context *smu, enum amd_pp_sensors sensor, void *data, uint32_t *size) @@ -429,69 +320,69 @@ static int smu_v14_0_0_read_sensor(struct smu_context *smu, switch (sensor) { case AMDGPU_PP_SENSOR_GPU_LOAD: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_AVERAGE_GFXACTIVITY, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_GPU_AVG_POWER: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_AVERAGE_SOCKETPOWER, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_GPU_INPUT_POWER: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_CURR_SOCKETPOWER, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_EDGE_TEMP: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_TEMPERATURE_EDGE, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_HOTSPOT_TEMP: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_TEMPERATURE_HOTSPOT, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_GFX_MCLK: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_AVERAGE_UCLK, (uint32_t *)data); *(uint32_t *)data *= 100; *size = 4; break; case AMDGPU_PP_SENSOR_GFX_SCLK: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_AVERAGE_GFXCLK, (uint32_t *)data); *(uint32_t *)data *= 100; *size = 4; break; case AMDGPU_PP_SENSOR_VDDGFX: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDGFX, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_VDDNB: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_VOLTAGE_VDDSOC, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_SS_APU_SHARE: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_SS_APU_SHARE, (uint32_t *)data); *size = 4; break; case AMDGPU_PP_SENSOR_SS_DGPU_SHARE: - ret = smu_v14_0_0_common_get_smu_metrics_data(smu, + ret = smu_v14_0_0_get_smu_metrics_data(smu, METRICS_SS_DGPU_SHARE, (uint32_t *)data); *size = 4; @@ -588,7 +479,7 @@ static ssize_t smu_v14_0_0_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, 3, 0); gpu_metrics->temperature_gfx = metrics.GfxTemperature; gpu_metrics->temperature_soc = metrics.SocTemperature; @@ -597,32 +488,33 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu, sizeof(uint16_t) * 16); gpu_metrics->temperature_skin = metrics.SkinTemp; - gpu_metrics->average_gfx_activity = metrics.AverageGfxActivity; - gpu_metrics->average_vcn_activity = metrics.AverageVcnActivity; + gpu_metrics->average_gfx_activity = metrics.GfxActivity; + gpu_metrics->average_vcn_activity = metrics.VcnActivity; memcpy(&gpu_metrics->average_ipu_activity[0], - &metrics.AverageIpuBusy[0], + &metrics.IpuBusy[0], sizeof(uint16_t) * 8); memcpy(&gpu_metrics->average_core_c0_activity[0], - &metrics.AverageCoreC0Residency[0], + &metrics.CoreC0Residency[0], sizeof(uint16_t) * 16); - gpu_metrics->average_dram_reads = metrics.AverageDRAMReads; - gpu_metrics->average_dram_writes = metrics.AverageDRAMWrites; + gpu_metrics->average_dram_reads = metrics.DRAMReads; + gpu_metrics->average_dram_writes = metrics.DRAMWrites; - gpu_metrics->average_socket_power = metrics.AverageSocketPower; + gpu_metrics->average_socket_power = metrics.SocketPower; gpu_metrics->average_ipu_power = metrics.IpuPower; gpu_metrics->average_apu_power = metrics.ApuPower; + gpu_metrics->average_gfx_power = metrics.GfxPower; gpu_metrics->average_dgpu_power = metrics.dGpuPower; - gpu_metrics->average_core_power = metrics.AverageCorePower; - memcpy(&gpu_metrics->core_power[0], + gpu_metrics->average_all_core_power = metrics.AllCorePower; + memcpy(&gpu_metrics->average_core_power[0], &metrics.CorePower[0], sizeof(uint16_t) * 16); - gpu_metrics->average_gfxclk_frequency = metrics.AverageGfxclkFrequency; - gpu_metrics->average_socclk_frequency = metrics.AverageSocclkFrequency; - gpu_metrics->average_vpeclk_frequency = metrics.AverageVpeclkFrequency; - gpu_metrics->average_fclk_frequency = metrics.AverageFclkFrequency; - gpu_metrics->average_vclk_frequency = metrics.AverageVclkFrequency; - gpu_metrics->average_ipuclk_frequency = metrics.AverageIpuclkFrequency; + gpu_metrics->average_gfxclk_frequency = metrics.GfxclkFrequency; + gpu_metrics->average_socclk_frequency = metrics.SocclkFrequency; + gpu_metrics->average_vpeclk_frequency = metrics.VpeclkFrequency; + gpu_metrics->average_fclk_frequency = metrics.FclkFrequency; + gpu_metrics->average_vclk_frequency = metrics.VclkFrequency; + gpu_metrics->average_ipuclk_frequency = metrics.IpuclkFrequency; memcpy(&gpu_metrics->current_coreclk[0], &metrics.CoreFrequency[0], @@ -638,68 +530,6 @@ static ssize_t smu_v14_0_0_get_gpu_metrics(struct smu_context *smu, return sizeof(struct gpu_metrics_v3_0); } -static ssize_t smu_v14_0_0_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; - SmuMetrics_legacy_t metrics; - int ret = 0; - - ret = smu_cmn_get_metrics_table(smu, &metrics, true); - if (ret) - return ret; - - smu_cmn_init_soft_gpu_metrics(gpu_metrics, 2, 1); - - gpu_metrics->temperature_gfx = metrics.GfxTemperature; - gpu_metrics->temperature_soc = metrics.SocTemperature; - memcpy(&gpu_metrics->temperature_core[0], - &metrics.CoreTemperature[0], - sizeof(uint16_t) * 8); - gpu_metrics->temperature_l3[0] = metrics.L3Temperature[0]; - gpu_metrics->temperature_l3[1] = metrics.L3Temperature[1]; - - gpu_metrics->average_gfx_activity = metrics.GfxActivity; - gpu_metrics->average_mm_activity = metrics.UvdActivity; - - gpu_metrics->average_socket_power = metrics.CurrentSocketPower; - gpu_metrics->average_gfx_power = metrics.Power[0]; - gpu_metrics->average_soc_power = metrics.Power[1]; - memcpy(&gpu_metrics->average_core_power[0], - &metrics.CorePower[0], - sizeof(uint16_t) * 8); - - gpu_metrics->average_gfxclk_frequency = metrics.GfxclkFrequency; - gpu_metrics->average_socclk_frequency = metrics.SocclkFrequency; - gpu_metrics->average_uclk_frequency = metrics.MemclkFrequency; - gpu_metrics->average_fclk_frequency = metrics.MemclkFrequency; - gpu_metrics->average_vclk_frequency = metrics.VclkFrequency; - gpu_metrics->average_dclk_frequency = metrics.DclkFrequency; - - memcpy(&gpu_metrics->current_coreclk[0], - &metrics.CoreFrequency[0], - sizeof(uint16_t) * 8); - - gpu_metrics->throttle_status = metrics.ThrottlerStatus; - gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); - - *table = (void *)gpu_metrics; - - return sizeof(struct gpu_metrics_v2_1); -} - -static ssize_t smu_v14_0_0_common_get_gpu_metrics(struct smu_context *smu, - void **table) -{ - - if (smu->smc_fw_version > 0x5d3500) - return smu_v14_0_0_get_gpu_metrics(smu, table); - else - return smu_v14_0_0_get_legacy_gpu_metrics(smu, table); -} - static int smu_v14_0_0_mode2_reset(struct smu_context *smu) { int ret; @@ -928,7 +758,7 @@ static int smu_v14_0_0_get_current_clk_freq(struct smu_context *smu, return -EINVAL; } - return smu_v14_0_0_common_get_smu_metrics_data(smu, member_type, value); + return smu_v14_0_0_get_smu_metrics_data(smu, member_type, value); } static int smu_v14_0_0_get_dpm_level_count(struct smu_context *smu, @@ -1230,7 +1060,7 @@ static const struct pptable_funcs smu_v14_0_0_ppt_funcs = { .read_sensor = smu_v14_0_0_read_sensor, .is_dpm_running = smu_v14_0_0_is_dpm_running, .set_watermarks_table = smu_v14_0_0_set_watermarks_table, - .get_gpu_metrics = smu_v14_0_0_common_get_gpu_metrics, + .get_gpu_metrics = smu_v14_0_0_get_gpu_metrics, .get_enabled_mask = smu_cmn_get_enabled_mask, .get_pp_feature_mask = smu_cmn_get_pp_feature_mask, .set_driver_table_location = smu_v14_0_set_driver_table_location, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index 6e57c94379a9..001a5cf09657 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -1004,6 +1004,9 @@ void smu_cmn_init_soft_gpu_metrics(void *table, uint8_t frev, uint8_t crev) case METRICS_VERSION(2, 4): structure_size = sizeof(struct gpu_metrics_v2_4); break; + case METRICS_VERSION(3, 0): + structure_size = sizeof(struct gpu_metrics_v3_0); + break; default: return; } diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h index 8a6621f1e82c..2db40789235c 100644 --- a/drivers/gpu/drm/radeon/atombios.h +++ b/drivers/gpu/drm/radeon/atombios.h @@ -3893,7 +3893,7 @@ typedef struct _ATOM_GPIO_PIN_ASSIGNMENT typedef struct _ATOM_GPIO_PIN_LUT { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_GPIO_PIN_ASSIGNMENT asGPIO_Pin[1]; + ATOM_GPIO_PIN_ASSIGNMENT asGPIO_Pin[]; }ATOM_GPIO_PIN_LUT; /****************************************************************************/ @@ -4061,7 +4061,7 @@ typedef struct _ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT //usSrcDstTableOffset UCHAR ucNumberOfSrc; USHORT usSrcObjectID[1]; UCHAR ucNumberOfDst; - USHORT usDstObjectID[1]; + USHORT usDstObjectID[]; }ATOM_SRC_DST_TABLE_FOR_ONE_OBJECT; @@ -4233,7 +4233,7 @@ typedef struct _ATOM_CONNECTOR_DEVICE_TAG_RECORD ATOM_COMMON_RECORD_HEADER sheader; UCHAR ucNumberOfDevice; UCHAR ucReserved; - ATOM_CONNECTOR_DEVICE_TAG asDeviceTag[1]; //This Id is same as "ATOM_DEVICE_XXX_SUPPORT", 1 is only for allocation + ATOM_CONNECTOR_DEVICE_TAG asDeviceTag[]; //This Id is same as "ATOM_DEVICE_XXX_SUPPORT", 1 is only for allocation }ATOM_CONNECTOR_DEVICE_TAG_RECORD; @@ -4293,7 +4293,7 @@ typedef struct _ATOM_OBJECT_GPIO_CNTL_RECORD ATOM_COMMON_RECORD_HEADER sheader; UCHAR ucFlags; // Future expnadibility UCHAR ucNumberOfPins; // Number of GPIO pins used to control the object - ATOM_GPIO_PIN_CONTROL_PAIR asGpio[1]; // the real gpio pin pair determined by number of pins ucNumberOfPins + ATOM_GPIO_PIN_CONTROL_PAIR asGpio[]; // the real gpio pin pair determined by number of pins ucNumberOfPins }ATOM_OBJECT_GPIO_CNTL_RECORD; //Definitions for GPIO pin state @@ -4444,7 +4444,7 @@ typedef struct _ATOM_BRACKET_LAYOUT_RECORD UCHAR ucWidth; UCHAR ucConnNum; UCHAR ucReserved; - ATOM_CONNECTOR_LAYOUT_INFO asConnInfo[1]; + ATOM_CONNECTOR_LAYOUT_INFO asConnInfo[]; }ATOM_BRACKET_LAYOUT_RECORD; /****************************************************************************/ @@ -4600,7 +4600,7 @@ typedef struct _ATOM_I2C_VOLTAGE_OBJECT_V3 UCHAR ucVoltageControlAddress; UCHAR ucVoltageControlOffset; ULONG ulReserved; - VOLTAGE_LUT_ENTRY asVolI2cLut[1]; // end with 0xff + VOLTAGE_LUT_ENTRY asVolI2cLut[]; // end with 0xff }ATOM_I2C_VOLTAGE_OBJECT_V3; // ATOM_I2C_VOLTAGE_OBJECT_V3.ucVoltageControlFlag @@ -4625,7 +4625,7 @@ typedef struct _ATOM_LEAKAGE_VOLTAGE_OBJECT_V3 UCHAR ucLeakageEntryNum; // indicate the entry number of LeakageId/Voltage Lut table UCHAR ucReserved[2]; ULONG ulMaxVoltageLevel; - LEAKAGE_VOLTAGE_LUT_ENTRY_V2 asLeakageIdLut[1]; + LEAKAGE_VOLTAGE_LUT_ENTRY_V2 asLeakageIdLut[]; }ATOM_LEAKAGE_VOLTAGE_OBJECT_V3; @@ -4753,7 +4753,7 @@ typedef struct _ATOM_POWER_SOURCE_INFO { ATOM_COMMON_TABLE_HEADER asHeader; UCHAR asPwrbehave[16]; - ATOM_POWER_SOURCE_OBJECT asPwrObj[1]; + ATOM_POWER_SOURCE_OBJECT asPwrObj[]; }ATOM_POWER_SOURCE_INFO; @@ -5440,7 +5440,7 @@ typedef struct _ATOM_FUSION_SYSTEM_INFO_V2 typedef struct _ATOM_I2C_DATA_RECORD { UCHAR ucNunberOfBytes; //Indicates how many bytes SW needs to write to the external ASIC for one block, besides to "Start" and "Stop" - UCHAR ucI2CData[1]; //I2C data in bytes, should be less than 16 bytes usually + UCHAR ucI2CData[]; //I2C data in bytes, should be less than 16 bytes usually }ATOM_I2C_DATA_RECORD; @@ -5451,14 +5451,14 @@ typedef struct _ATOM_I2C_DEVICE_SETUP_INFO UCHAR ucSSChipID; //SS chip being used UCHAR ucSSChipSlaveAddr; //Slave Address to set up this SS chip UCHAR ucNumOfI2CDataRecords; //number of data block - ATOM_I2C_DATA_RECORD asI2CData[1]; + ATOM_I2C_DATA_RECORD asI2CData[]; }ATOM_I2C_DEVICE_SETUP_INFO; //========================================================================================== typedef struct _ATOM_ASIC_MVDD_INFO { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_I2C_DEVICE_SETUP_INFO asI2CSetup[1]; + ATOM_I2C_DEVICE_SETUP_INFO asI2CSetup[]; }ATOM_ASIC_MVDD_INFO; //========================================================================================== @@ -5520,7 +5520,7 @@ typedef struct _ATOM_ASIC_INTERNAL_SS_INFO typedef struct _ATOM_ASIC_INTERNAL_SS_INFO_V2 { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_ASIC_SS_ASSIGNMENT_V2 asSpreadSpectrum[1]; //this is point only. + ATOM_ASIC_SS_ASSIGNMENT_V2 asSpreadSpectrum[]; //this is point only. }ATOM_ASIC_INTERNAL_SS_INFO_V2; typedef struct _ATOM_ASIC_SS_ASSIGNMENT_V3 @@ -5542,7 +5542,7 @@ typedef struct _ATOM_ASIC_SS_ASSIGNMENT_V3 typedef struct _ATOM_ASIC_INTERNAL_SS_INFO_V3 { ATOM_COMMON_TABLE_HEADER sHeader; - ATOM_ASIC_SS_ASSIGNMENT_V3 asSpreadSpectrum[1]; //this is pointer only. + ATOM_ASIC_SS_ASSIGNMENT_V3 asSpreadSpectrum[]; //this is pointer only. }ATOM_ASIC_INTERNAL_SS_INFO_V3; @@ -6282,7 +6282,7 @@ typedef union _ATOM_MEMORY_SETTING_ID_CONFIG_ACCESS typedef struct _ATOM_MEMORY_SETTING_DATA_BLOCK{ ATOM_MEMORY_SETTING_ID_CONFIG_ACCESS ulMemoryID; - ULONG aulMemData[1]; + ULONG aulMemData[]; }ATOM_MEMORY_SETTING_DATA_BLOCK; @@ -7092,7 +7092,7 @@ typedef struct _ATOM_DISP_OUT_INFO_V3 UCHAR ucCoreRefClkSource; // value of CORE_REF_CLK_SOURCE UCHAR ucDispCaps; UCHAR ucReserved[2]; - ASIC_TRANSMITTER_INFO_V2 asTransmitterInfo[1]; // for alligment only + ASIC_TRANSMITTER_INFO_V2 asTransmitterInfo[]; // for alligment only }ATOM_DISP_OUT_INFO_V3; //ucDispCaps @@ -7324,12 +7324,12 @@ typedef struct _CLOCK_CONDITION_SETTING_ENTRY{ USHORT usMaxClockFreq; UCHAR ucEncodeMode; UCHAR ucPhySel; - ULONG ulAnalogSetting[1]; + ULONG ulAnalogSetting[]; }CLOCK_CONDITION_SETTING_ENTRY; typedef struct _CLOCK_CONDITION_SETTING_INFO{ USHORT usEntrySize; - CLOCK_CONDITION_SETTING_ENTRY asClkCondSettingEntry[1]; + CLOCK_CONDITION_SETTING_ENTRY asClkCondSettingEntry[]; }CLOCK_CONDITION_SETTING_INFO; typedef struct _PHY_CONDITION_REG_VAL{ @@ -7346,27 +7346,27 @@ typedef struct _PHY_CONDITION_REG_VAL_V2{ typedef struct _PHY_CONDITION_REG_INFO{ USHORT usRegIndex; USHORT usSize; - PHY_CONDITION_REG_VAL asRegVal[1]; + PHY_CONDITION_REG_VAL asRegVal[]; }PHY_CONDITION_REG_INFO; typedef struct _PHY_CONDITION_REG_INFO_V2{ USHORT usRegIndex; USHORT usSize; - PHY_CONDITION_REG_VAL_V2 asRegVal[1]; + PHY_CONDITION_REG_VAL_V2 asRegVal[]; }PHY_CONDITION_REG_INFO_V2; typedef struct _PHY_ANALOG_SETTING_INFO{ UCHAR ucEncodeMode; UCHAR ucPhySel; USHORT usSize; - PHY_CONDITION_REG_INFO asAnalogSetting[1]; + PHY_CONDITION_REG_INFO asAnalogSetting[]; }PHY_ANALOG_SETTING_INFO; typedef struct _PHY_ANALOG_SETTING_INFO_V2{ UCHAR ucEncodeMode; UCHAR ucPhySel; USHORT usSize; - PHY_CONDITION_REG_INFO_V2 asAnalogSetting[1]; + PHY_CONDITION_REG_INFO_V2 asAnalogSetting[]; }PHY_ANALOG_SETTING_INFO_V2; typedef struct _GFX_HAVESTING_PARAMETERS { |