diff options
Diffstat (limited to 'drivers/gpu/drm')
108 files changed, 989 insertions, 339 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index ffe149aafc39..dfef5a7e0f5a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -207,11 +207,11 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s }) /* GPUVM API */ -int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid, +int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid, void **vm, void **process_info, struct dma_fence **ef); int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd, - struct file *filp, unsigned int pasid, + struct file *filp, u32 pasid, void **vm, void **process_info, struct dma_fence **ef); void amdgpu_amdkfd_gpuvm_destroy_cb(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c index bf927f432506..ee531c3988d1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c @@ -105,7 +105,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c index 744366c7ee85..4d41317b9292 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c @@ -139,7 +139,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c index feab4cc6e836..35917d4b50f6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c @@ -96,7 +96,7 @@ static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c index 1102de76d876..1abfe63c80fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c @@ -110,7 +110,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, unlock_srbm(kgd); } -int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid) { struct amdgpu_device *adev = get_amdgpu_device(kgd); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h index aedf67d57449..ff2bc72e6646 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h @@ -26,7 +26,7 @@ void kgd_gfx_v9_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid, uint32_t sh_mem_config, uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases); -int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid, +int kgd_gfx_v9_set_pasid_vmid_mapping(struct kgd_dev *kgd, u32 pasid, unsigned int vmid); int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id); int kgd_gfx_v9_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index a58af513c952..d02c5c177a98 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -992,7 +992,7 @@ create_evict_fence_fail: return ret; } -int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, unsigned int pasid, +int amdgpu_amdkfd_gpuvm_create_process_vm(struct kgd_dev *kgd, u32 pasid, void **vm, void **process_info, struct dma_fence **ef) { @@ -1028,7 +1028,7 @@ amdgpu_vm_init_fail: } int amdgpu_amdkfd_gpuvm_acquire_process_vm(struct kgd_dev *kgd, - struct file *filp, unsigned int pasid, + struct file *filp, u32 pasid, void **vm, void **process_info, struct dma_fence **ef) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index eb7cfe87042e..d0b8d0d341af 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,8 +80,6 @@ MODULE_FIRMWARE("amdgpu/renoir_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi10_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi14_gpu_info.bin"); MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/sienna_cichlid_gpu_info.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 @@ -1600,6 +1598,8 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_CARRIZO: case CHIP_STONEY: case CHIP_VEGA20: + case CHIP_SIENNA_CICHLID: + case CHIP_NAVY_FLOUNDER: default: return 0; case CHIP_VEGA10: @@ -1631,12 +1631,6 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) case CHIP_NAVI12: chip_name = "navi12"; break; - case CHIP_SIENNA_CICHLID: - chip_name = "sienna_cichlid"; - break; - case CHIP_NAVY_FLOUNDER: - chip_name = "navy_flounder"; - break; } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_gpu_info.bin", chip_name); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index d76172965199..44c1f6e00635 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -297,7 +297,7 @@ int amdgpu_display_crtc_set_config(struct drm_mode_set *set, take the current one */ if (active && !adev->have_disp_power_ref) { adev->have_disp_power_ref = true; - goto out; + return ret; } /* if we have no active crtcs, then drop the power ref we got before */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 26127c7d2f32..321032d3a51a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1044,8 +1044,16 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU}, /* Navi12 */ - {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12}, + {0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12}, + + /* Sienna_Cichlid */ + {0x1002, 0x73A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, + {0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID}, {0, 0, 0} }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c index 7521f4ab55de..6e9a9e5dbea0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c @@ -43,7 +43,7 @@ static DEFINE_IDA(amdgpu_pasid_ida); /* Helper to free pasid from a fence callback */ struct amdgpu_pasid_cb { struct dma_fence_cb cb; - unsigned int pasid; + u32 pasid; }; /** @@ -79,7 +79,7 @@ int amdgpu_pasid_alloc(unsigned int bits) * amdgpu_pasid_free - Free a PASID * @pasid: PASID to free */ -void amdgpu_pasid_free(unsigned int pasid) +void amdgpu_pasid_free(u32 pasid) { trace_amdgpu_pasid_freed(pasid); ida_simple_remove(&amdgpu_pasid_ida, pasid); @@ -105,7 +105,7 @@ static void amdgpu_pasid_free_cb(struct dma_fence *fence, * Free the pasid only after all the fences in resv are signaled. */ void amdgpu_pasid_free_delayed(struct dma_resv *resv, - unsigned int pasid) + u32 pasid) { struct dma_fence *fence, **fences; struct amdgpu_pasid_cb *cb; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h index 8e58325bbca2..0c3b4fa1f936 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h @@ -71,9 +71,9 @@ struct amdgpu_vmid_mgr { }; int amdgpu_pasid_alloc(unsigned int bits); -void amdgpu_pasid_free(unsigned int pasid); +void amdgpu_pasid_free(u32 pasid); void amdgpu_pasid_free_delayed(struct dma_resv *resv, - unsigned int pasid); + u32 pasid); bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev, struct amdgpu_vmid *id); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c index 414548064648..b403b2a88ee5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c @@ -1084,7 +1084,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev, struct amdgpu_fpriv *fpriv = file_priv->driver_priv; struct amdgpu_bo_list *list; struct amdgpu_bo *pd; - unsigned int pasid; + u32 pasid; int handle; if (!fpriv) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index d8c6520ff74a..06757681b2ce 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -178,7 +178,7 @@ static int psp_sw_init(void *handle) return ret; } - if (adev->asic_type == CHIP_NAVI10) { + if (adev->asic_type == CHIP_NAVI10 || adev->asic_type == CHIP_SIENNA_CICHLID) { ret= psp_sysfs_init(adev); if (ret) { return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index e11c5d69843d..978bae731398 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -1076,6 +1076,7 @@ static int amdgpu_ttm_tt_pin_userptr(struct ttm_tt *ttm) release_sg: kfree(ttm->sg); + ttm->sg = NULL; return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 71e005cf2952..cb1d7cddebc3 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -2785,7 +2785,7 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) * 0 for success, error for failure. */ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, - int vm_context, unsigned int pasid) + int vm_context, u32 pasid) { struct amdgpu_bo_param bp; struct amdgpu_bo *root; @@ -2956,7 +2956,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev, * 0 for success, -errno for errors. */ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, - unsigned int pasid) + u32 pasid) { bool pte_support_ats = (adev->asic_type == CHIP_RAVEN); int r; @@ -3254,7 +3254,7 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) * @pasid: PASID identifier for VM * @task_info: task_info to fill. */ -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, +void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, struct amdgpu_task_info *task_info) { struct amdgpu_vm *vm; @@ -3298,7 +3298,7 @@ void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) * Try to gracefully handle a VM fault. Return true if the fault was handled and * shouldn't be reported any more. */ -bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid, +bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t addr) { struct amdgpu_bo *root; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 770025a5e500..ffbc0cc87ccf 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -372,8 +372,8 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev); long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout); int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, - int vm_context, unsigned int pasid); -int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid); + int vm_context, u32 pasid); +int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, u32 pasid); void amdgpu_vm_release_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm); void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm, @@ -430,9 +430,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, struct amdgpu_job *job); void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev); -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, +void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, struct amdgpu_task_info *task_info); -bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid, +bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t addr); void amdgpu_vm_set_task_info(struct amdgpu_vm *vm); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 037a187aa42f..f73ce9721233 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -3595,6 +3595,9 @@ static void gfx_v10_0_check_gfxoff_flag(struct amdgpu_device *adev) if (!gfx_v10_0_navi10_gfxoff_should_enable(adev)) adev->pm.pp_feature &= ~PP_GFXOFF_MASK; break; + case CHIP_NAVY_FLOUNDER: + adev->pm.pp_feature &= ~PP_GFXOFF_MASK; + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index e16874f30d5d..6c5d9612abcb 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -58,7 +58,7 @@ MODULE_FIRMWARE("amdgpu/arcturus_ta.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_sos.bin"); MODULE_FIRMWARE("amdgpu/sienna_cichlid_ta.bin"); MODULE_FIRMWARE("amdgpu/navy_flounder_sos.bin"); -MODULE_FIRMWARE("amdgpu/navy_flounder_asd.bin"); +MODULE_FIRMWARE("amdgpu/navy_flounder_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 84d811b6e48b..c28ebf41530a 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -694,12 +694,12 @@ static void soc15_reg_base_init(struct amdgpu_device *adev) * it doesn't support SRIOV. */ if (amdgpu_discovery) { r = amdgpu_discovery_reg_base_init(adev); - if (r) { - DRM_WARN("failed to init reg base from ip discovery table, " - "fallback to legacy init method\n"); - vega10_reg_base_init(adev); - } + if (r == 0) + break; + DRM_WARN("failed to init reg base from ip discovery table, " + "fallback to legacy init method\n"); } + vega10_reg_base_init(adev); break; case CHIP_VEGA20: vega20_reg_base_init(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index 63e5547cfb16..3a805eaf6f11 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -746,18 +746,18 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_GATE__IME_HEVC_MASK | UVD_SUVD_CGC_GATE__EFC_MASK | UVD_SUVD_CGC_GATE__SAOE_MASK - | 0x08000000 + | UVD_SUVD_CGC_GATE__SRE_AV1_MASK | UVD_SUVD_CGC_GATE__FBC_PCLK_MASK | UVD_SUVD_CGC_GATE__FBC_CCLK_MASK - | 0x40000000 + | UVD_SUVD_CGC_GATE__SCM_AV1_MASK | UVD_SUVD_CGC_GATE__SMPA_MASK); WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE, data); data = RREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2); data |= (UVD_SUVD_CGC_GATE2__MPBE0_MASK | UVD_SUVD_CGC_GATE2__MPBE1_MASK - | 0x00000004 - | 0x00000008 + | UVD_SUVD_CGC_GATE2__SIT_AV1_MASK + | UVD_SUVD_CGC_GATE2__SDB_AV1_MASK | UVD_SUVD_CGC_GATE2__MPC1_MASK); WREG32_SOC15(VCN, inst, mmUVD_SUVD_CGC_GATE2, data); @@ -776,8 +776,8 @@ static void vcn_v3_0_disable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK - | 0x00008000 - | 0x00010000 + | UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK + | UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK | UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK | UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK | UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK); @@ -892,8 +892,8 @@ static void vcn_v3_0_enable_clock_gating(struct amdgpu_device *adev, int inst) | UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK | UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK - | 0x00008000 - | 0x00010000 + | UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK + | UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK | UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK | UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK | UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK); diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c index 24b471734117..dcb1d89d776e 100644 --- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c +++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c @@ -91,7 +91,7 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev, (const struct cik_ih_ring_entry *)ih_ring_entry; uint32_t context_id = ihre->data & 0xfffffff; unsigned int vmid = (ihre->ring_id & 0x0000ff00) >> 8; - unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16; + u32 pasid = (ihre->ring_id & 0xffff0000) >> 16; if (pasid == 0) return; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c index 27bcc5b472f6..b258a3dae767 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c @@ -45,7 +45,7 @@ static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev) } static int dbgdev_diq_submit_ib(struct kfd_dbgdev *dbgdev, - unsigned int pasid, uint64_t vmid0_address, + u32 pasid, uint64_t vmid0_address, uint32_t *packet_buff, size_t size_in_bytes) { struct pm4__release_mem *rm_packet; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h index a04a1fe1d0d9..f9c6df1fdc5c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.h @@ -275,7 +275,7 @@ struct kfd_dbgdev { }; struct kfd_dbgmgr { - unsigned int pasid; + u32 pasid; struct kfd_dev *dev; struct kfd_dbgdev *dbgdev; }; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index e0e60b0d0669..a8d316711625 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -40,7 +40,7 @@ #define CIK_HPD_EOP_BYTES (1U << CIK_HPD_EOP_BYTES_LOG2) static int set_pasid_vmid_mapping(struct device_queue_manager *dqm, - unsigned int pasid, unsigned int vmid); + u32 pasid, unsigned int vmid); static int execute_queues_cpsch(struct device_queue_manager *dqm, enum kfd_unmap_queues_filter filter, @@ -948,7 +948,7 @@ out: } static int -set_pasid_vmid_mapping(struct device_queue_manager *dqm, unsigned int pasid, +set_pasid_vmid_mapping(struct device_queue_manager *dqm, u32 pasid, unsigned int vmid) { return dqm->dev->kfd2kgd->set_pasid_vmid_mapping( @@ -1216,6 +1216,8 @@ static int stop_cpsch(struct device_queue_manager *dqm) dqm->sched_running = false; dqm_unlock(dqm); + pm_release_ib(&dqm->packets); + kfd_gtt_sa_free(dqm->dev, dqm->fence_mem); pm_uninit(&dqm->packets, hanging); @@ -1326,7 +1328,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q, if (q->properties.is_active) { increment_queue_count(dqm, q->properties.type); - retval = execute_queues_cpsch(dqm, + execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); } @@ -1979,8 +1981,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm) kfree(dqm); } -int kfd_process_vm_fault(struct device_queue_manager *dqm, - unsigned int pasid) +int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid) { struct kfd_process_device *pdd; struct kfd_process *p = kfd_lookup_process_by_pasid(pasid); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c index a9583b95fcc1..ba2c2ce0c55a 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c @@ -460,7 +460,7 @@ static void set_event_from_interrupt(struct kfd_process *p, } } -void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, +void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, uint32_t valid_id_bits) { struct kfd_event *ev = NULL; @@ -872,7 +872,7 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p, } #ifdef KFD_SUPPORT_IOMMU_V2 -void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid, +void kfd_signal_iommu_event(struct kfd_dev *dev, u32 pasid, unsigned long address, bool is_write_requested, bool is_execute_requested) { @@ -950,7 +950,7 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid, } #endif /* KFD_SUPPORT_IOMMU_V2 */ -void kfd_signal_hw_exception_event(unsigned int pasid) +void kfd_signal_hw_exception_event(u32 pasid) { /* * Because we are called from arbitrary context (workqueue) as opposed @@ -971,7 +971,7 @@ void kfd_signal_hw_exception_event(unsigned int pasid) kfd_unref_process(p); } -void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, +void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid, struct kfd_vm_fault_info *info) { struct kfd_event *ev; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h index c7ac6c73af86..c8fe5dbdad55 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h @@ -79,7 +79,7 @@ struct kfd_event { #define KFD_EVENT_TYPE_DEBUG 5 #define KFD_EVENT_TYPE_MEMORY 8 -extern void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, - uint32_t valid_id_bits); +extern void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, + uint32_t valid_id_bits); #endif diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c index 7c8786b9eb0a..e8ef3886688b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c @@ -139,7 +139,7 @@ void kfd_iommu_unbind_process(struct kfd_process *p) } /* Callback for process shutdown invoked by the IOMMU driver */ -static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid) +static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, u32 pasid) { struct kfd_dev *dev = kfd_device_by_pci_dev(pdev); struct kfd_process *p; @@ -185,8 +185,8 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid) } /* This function called by IOMMU driver on PPR failure */ -static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid, - unsigned long address, u16 flags) +static int iommu_invalid_ppr_cb(struct pci_dev *pdev, u32 pasid, + unsigned long address, u16 flags) { struct kfd_dev *dev; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c index 2a07c4f2cd0d..af5816f51e55 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pasid.c @@ -51,7 +51,7 @@ unsigned int kfd_get_pasid_limit(void) return 1U << pasid_bits; } -unsigned int kfd_pasid_alloc(void) +u32 kfd_pasid_alloc(void) { int r = amdgpu_pasid_alloc(pasid_bits); @@ -63,7 +63,7 @@ unsigned int kfd_pasid_alloc(void) return 0; } -void kfd_pasid_free(unsigned int pasid) +void kfd_pasid_free(u32 pasid) { amdgpu_pasid_free(pasid); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index 6727e9de5b8b..922ae138ab85 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -723,7 +723,7 @@ struct kfd_process { /* We want to receive a notification when the mm_struct is destroyed */ struct mmu_notifier mmu_notifier; - uint16_t pasid; + u32 pasid; unsigned int doorbell_index; /* @@ -800,7 +800,7 @@ int kfd_process_create_wq(void); void kfd_process_destroy_wq(void); struct kfd_process *kfd_create_process(struct file *filep); struct kfd_process *kfd_get_process(const struct task_struct *); -struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid); +struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid); struct kfd_process *kfd_lookup_process_by_mm(const struct mm_struct *mm); void kfd_unref_process(struct kfd_process *p); int kfd_process_evict_queues(struct kfd_process *p); @@ -841,8 +841,8 @@ int kfd_pasid_init(void); void kfd_pasid_exit(void); bool kfd_set_pasid_limit(unsigned int new_limit); unsigned int kfd_get_pasid_limit(void); -unsigned int kfd_pasid_alloc(void); -void kfd_pasid_free(unsigned int pasid); +u32 kfd_pasid_alloc(void); +void kfd_pasid_free(u32 pasid); /* Doorbells */ size_t kfd_doorbell_process_slice(struct kfd_dev *kfd); @@ -927,7 +927,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm); struct kernel_queue *kernel_queue_init(struct kfd_dev *dev, enum kfd_queue_type type); void kernel_queue_uninit(struct kernel_queue *kq, bool hanging); -int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid); +int kfd_process_vm_fault(struct device_queue_manager *dqm, u32 pasid); /* Process Queue Manager */ struct process_queue_node { @@ -1049,12 +1049,12 @@ int kfd_wait_on_events(struct kfd_process *p, uint32_t num_events, void __user *data, bool all, uint32_t user_timeout_ms, uint32_t *wait_result); -void kfd_signal_event_interrupt(unsigned int pasid, uint32_t partial_id, +void kfd_signal_event_interrupt(u32 pasid, uint32_t partial_id, uint32_t valid_id_bits); void kfd_signal_iommu_event(struct kfd_dev *dev, - unsigned int pasid, unsigned long address, - bool is_write_requested, bool is_execute_requested); -void kfd_signal_hw_exception_event(unsigned int pasid); + u32 pasid, unsigned long address, + bool is_write_requested, bool is_execute_requested); +void kfd_signal_hw_exception_event(u32 pasid); int kfd_set_event(struct kfd_process *p, uint32_t event_id); int kfd_reset_event(struct kfd_process *p, uint32_t event_id); int kfd_event_page_set(struct kfd_process *p, void *kernel_address, @@ -1065,7 +1065,7 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p, uint64_t *event_page_offset, uint32_t *event_slot_index); int kfd_event_destroy(struct kfd_process *p, uint32_t event_id); -void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid, +void kfd_signal_vm_fault_event(struct kfd_dev *dev, u32 pasid, struct kfd_vm_fault_info *info); void kfd_signal_reset_event(struct kfd_dev *dev); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c index 40695d52e9a8..627793029033 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c @@ -1306,7 +1306,7 @@ void kfd_process_device_remove_obj_handle(struct kfd_process_device *pdd, } /* This increments the process->ref counter. */ -struct kfd_process *kfd_lookup_process_by_pasid(unsigned int pasid) +struct kfd_process *kfd_lookup_process_by_pasid(u32 pasid) { struct kfd_process *p, *ret_p = NULL; unsigned int temp; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index b51c527a3f0d..a717a4904268 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -1409,7 +1409,7 @@ static int dm_late_init(void *handle) if (dmcu) ret = dmcu_load_iram(dmcu, params); else if (adev->dm.dc->ctx->dmub_srv) - ret = dmub_init_abm_config(adev->dm.dc->res_pool->abm, params); + ret = dmub_init_abm_config(adev->dm.dc->res_pool, params); if (!ret) return -EINVAL; @@ -5278,19 +5278,6 @@ static void dm_crtc_helper_disable(struct drm_crtc *crtc) { } -static bool does_crtc_have_active_cursor(struct drm_crtc_state *new_crtc_state) -{ - struct drm_device *dev = new_crtc_state->crtc->dev; - struct drm_plane *plane; - - drm_for_each_plane_mask(plane, dev, new_crtc_state->plane_mask) { - if (plane->type == DRM_PLANE_TYPE_CURSOR) - return true; - } - - return false; -} - static int count_crtc_active_planes(struct drm_crtc_state *new_crtc_state) { struct drm_atomic_state *state = new_crtc_state->state; @@ -5354,19 +5341,20 @@ static int dm_crtc_helper_atomic_check(struct drm_crtc *crtc, return ret; } - /* In some use cases, like reset, no stream is attached */ - if (!dm_crtc_state->stream) - return 0; - /* - * We want at least one hardware plane enabled to use - * the stream with a cursor enabled. + * We require the primary plane to be enabled whenever the CRTC is, otherwise + * drm_mode_cursor_universal may end up trying to enable the cursor plane while all other + * planes are disabled, which is not supported by the hardware. And there is legacy + * userspace which stops using the HW cursor altogether in response to the resulting EINVAL. */ - if (state->enable && state->active && - does_crtc_have_active_cursor(state) && - dm_crtc_state->active_planes == 0) + if (state->enable && + !(state->plane_mask & drm_plane_mask(crtc->primary))) return -EINVAL; + /* In some use cases, like reset, no stream is attached */ + if (!dm_crtc_state->stream) + return 0; + if (dc_validate_stream(dc, dm_crtc_state->stream) == DC_OK) return 0; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c index 694c5bc93665..c2cd184f0bbd 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c @@ -604,7 +604,7 @@ struct hdcp_workqueue *hdcp_create_workqueue(struct amdgpu_device *adev, struct int i = 0; hdcp_work = kcalloc(max_caps, sizeof(*hdcp_work), GFP_KERNEL); - if (hdcp_work == NULL) + if (ZERO_OR_NULL_PTR(hdcp_work)) return NULL; hdcp_work->srm = kcalloc(PSP_HDCP_SRM_FIRST_GEN_MAX_SIZE, sizeof(*hdcp_work->srm), GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index 543afa34d87a..21a3073c8929 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -783,7 +783,6 @@ void rn_clk_mgr_construct( } else { struct clk_log_info log_info = {0}; - clk_mgr->smu_ver = rn_vbios_smu_get_smu_version(clk_mgr); clk_mgr->periodic_retraining_disabled = rn_vbios_smu_is_periodic_retraining_disabled(clk_mgr); /* SMU Version 55.51.0 and up no longer have an issue diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c index 9140b3fc767a..f31f48dd0da2 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c @@ -409,8 +409,8 @@ static struct _vcs_dpi_soc_bounding_box_st dcn2_0_nv14_soc = { }, }, .num_states = 5, - .sr_exit_time_us = 8.6, - .sr_enter_plus_exit_time_us = 10.9, + .sr_exit_time_us = 11.6, + .sr_enter_plus_exit_time_us = 13.9, .urgent_latency_us = 4.0, .urgent_latency_pixel_data_only_us = 4.0, .urgent_latency_pixel_mixed_with_vm_data_us = 4.0, diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile index 025637a83c3b..bd2a068f9863 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/Makefile +++ b/drivers/gpu/drm/amd/display/dc/dcn30/Makefile @@ -31,9 +31,21 @@ DCN30 = dcn30_init.o dcn30_hubbub.o dcn30_hubp.o dcn30_dpp.o dcn30_optc.o \ dcn30_dio_link_encoder.o dcn30_resource.o -CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse -mpreferred-stack-boundary=4 - +ifdef CONFIG_X86 CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -msse +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -msse +endif + +ifdef CONFIG_PPC64 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mhard-float -maltivec +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mhard-float -maltivec +endif + +ifdef CONFIG_ARM64 +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o := -mgeneral-regs-only +CFLAGS_REMOVE_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o := -mgeneral-regs-only +endif + ifdef CONFIG_CC_IS_GCC ifeq ($(call cc-ifversion, -lt, 0701, y), y) IS_OLD_GCC = 1 @@ -45,8 +57,10 @@ ifdef IS_OLD_GCC # GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3 # (8B stack alignment). CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -mpreferred-stack-boundary=4 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -mpreferred-stack-boundary=4 else CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_resource.o += -msse2 +CFLAGS_$(AMDDALPATH)/dc/dcn30/dcn30_optc.o += -msse2 endif AMD_DAL_DCN30 = $(addprefix $(AMDDALPATH)/dc/dcn30/,$(DCN30)) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h index d3192b9d0c3d..47f8ee2832ff 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h @@ -27,7 +27,7 @@ #define MOD_HDCP_LOG_H_ #ifdef CONFIG_DRM_AMD_DC_HDCP -#define HDCP_LOG_ERR(hdcp, ...) DRM_WARN(__VA_ARGS__) +#define HDCP_LOG_ERR(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__) #define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__) diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c index fb1161dd7ea8..3a367a5968ae 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c @@ -88,7 +88,7 @@ enum mod_hdcp_status mod_hdcp_add_display_to_topology(struct mod_hdcp *hdcp, enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS; if (!psp->dtm_context.dtm_initialized) { - DRM_ERROR("Failed to add display topology, DTM TA is not initialized."); + DRM_INFO("Failed to add display topology, DTM TA is not initialized."); display->state = MOD_HDCP_DISPLAY_INACTIVE; return MOD_HDCP_STATUS_FAILURE; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 859724771a75..61497954e67e 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -657,7 +657,7 @@ void fill_iram_v_2_3(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame params, ram_table, big_endian); } -bool dmub_init_abm_config(struct abm *abm, +bool dmub_init_abm_config(struct resource_pool *res_pool, struct dmcu_iram_parameters params) { struct iram_table_v_2_2 ram_table; @@ -665,8 +665,13 @@ bool dmub_init_abm_config(struct abm *abm, bool result = false; uint32_t i, j = 0; - if (abm == NULL) +#if defined(CONFIG_DRM_AMD_DC_DCN3_0) + if (res_pool->abm == NULL && res_pool->multiple_abms[0] == NULL) return false; +#else + if (res_pool->abm == NULL) + return false; +#endif memset(&ram_table, 0, sizeof(ram_table)); memset(&config, 0, sizeof(config)); @@ -707,8 +712,14 @@ bool dmub_init_abm_config(struct abm *abm, config.min_abm_backlight = ram_table.min_abm_backlight; - result = abm->funcs->init_abm_config( - abm, (char *)(&config), sizeof(struct abm_config_table)); +#if defined(CONFIG_DRM_AMD_DC_DCN3_0) + if (res_pool->multiple_abms[0]) { + result = res_pool->multiple_abms[0]->funcs->init_abm_config( + res_pool->multiple_abms[0], (char *)(&config), sizeof(struct abm_config_table)); + } else +#endif + result = res_pool->abm->funcs->init_abm_config( + res_pool->abm, (char *)(&config), sizeof(struct abm_config_table)); return result; } diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h index 46fbca2e2cd1..fa4728d88092 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h @@ -28,6 +28,8 @@ #include "dc/inc/hw/dmcu.h" #include "dc/inc/hw/abm.h" +struct resource_pool; + enum abm_defines { abm_defines_max_level = 4, @@ -45,7 +47,7 @@ struct dmcu_iram_parameters { bool dmcu_load_iram(struct dmcu *dmcu, struct dmcu_iram_parameters params); -bool dmub_init_abm_config(struct abm *abm, +bool dmub_init_abm_config(struct resource_pool *res_pool, struct dmcu_iram_parameters params); #endif /* MODULES_POWER_POWER_HELPERS_H_ */ diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h index 1116779252e6..e245e912535e 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_default.h @@ -2727,6 +2727,7 @@ #define mmDB_STENCIL_WRITE_BASE_DEFAULT 0x00000000 #define mmDB_RESERVED_REG_1_DEFAULT 0x00000000 #define mmDB_RESERVED_REG_3_DEFAULT 0x00000000 +#define mmDB_VRS_OVERRIDE_CNTL_DEFAULT 0x00000000 #define mmDB_Z_READ_BASE_HI_DEFAULT 0x00000000 #define mmDB_STENCIL_READ_BASE_HI_DEFAULT 0x00000000 #define mmDB_Z_WRITE_BASE_HI_DEFAULT 0x00000000 @@ -3062,6 +3063,7 @@ #define mmPA_SU_OVER_RASTERIZATION_CNTL_DEFAULT 0x00000000 #define mmPA_STEREO_CNTL_DEFAULT 0x00000000 #define mmPA_STATE_STEREO_X_DEFAULT 0x00000000 +#define mmPA_CL_VRS_CNTL_DEFAULT 0x00000000 #define mmPA_SU_POINT_SIZE_DEFAULT 0x00000000 #define mmPA_SU_POINT_MINMAX_DEFAULT 0x00000000 #define mmPA_SU_LINE_CNTL_DEFAULT 0x00000000 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h index 05d1b0a5f6d2..644a9fa71bb2 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_offset.h @@ -5379,6 +5379,8 @@ #define mmDB_RESERVED_REG_1_BASE_IDX 1 #define mmDB_RESERVED_REG_3 0x0017 #define mmDB_RESERVED_REG_3_BASE_IDX 1 +#define mmDB_VRS_OVERRIDE_CNTL 0x0019 +#define mmDB_VRS_OVERRIDE_CNTL_BASE_IDX 1 #define mmDB_Z_READ_BASE_HI 0x001a #define mmDB_Z_READ_BASE_HI_BASE_IDX 1 #define mmDB_STENCIL_READ_BASE_HI 0x001b @@ -6049,6 +6051,8 @@ #define mmPA_STEREO_CNTL_BASE_IDX 1 #define mmPA_STATE_STEREO_X 0x0211 #define mmPA_STATE_STEREO_X_BASE_IDX 1 +#define mmPA_CL_VRS_CNTL 0x0212 +#define mmPA_CL_VRS_CNTL_BASE_IDX 1 #define mmPA_SU_POINT_SIZE 0x0280 #define mmPA_SU_POINT_SIZE_BASE_IDX 1 #define mmPA_SU_POINT_MINMAX 0x0281 diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h index aac57f714cf1..2e449fcff893 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_10_3_0_sh_mask.h @@ -9777,6 +9777,7 @@ #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE__SHIFT 0x3 #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD__SHIFT 0x4 #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE__SHIFT 0x8 +#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE__SHIFT 0x10 #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK__SHIFT 0x18 #define DB_EXCEPTION_CONTROL__EARLY_Z_PANIC_DISABLE_MASK 0x00000001L #define DB_EXCEPTION_CONTROL__LATE_Z_PANIC_DISABLE_MASK 0x00000002L @@ -9784,6 +9785,7 @@ #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_HTILE_MASK 0x00000008L #define DB_EXCEPTION_CONTROL__AUTO_FLUSH_QUAD_MASK 0x00000010L #define DB_EXCEPTION_CONTROL__FORCE_SUMMARIZE_MASK 0x00000F00L +#define DB_EXCEPTION_CONTROL__FORCE_VRS_RATE_FINE_MASK 0x00FF0000L #define DB_EXCEPTION_CONTROL__DTAG_WATERMARK_MASK 0x7F000000L //DB_DFSM_CONFIG #define DB_DFSM_CONFIG__BYPASS_DFSM__SHIFT 0x0 @@ -10076,6 +10078,7 @@ #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM__SHIFT 0x18 #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT__SHIFT 0x19 #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING__SHIFT 0x1a +#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT__SHIFT 0x1c #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT__SHIFT 0x1e #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC__SHIFT 0x1f #define CB_HW_CONTROL_3__DISABLE_SLOW_MODE_EMPTY_HALF_QUAD_KILL_MASK 0x00000001L @@ -10103,12 +10106,15 @@ #define CB_HW_CONTROL_3__DISABLE_NACK_PROCESSING_CM_MASK 0x01000000L #define CB_HW_CONTROL_3__DISABLE_NACK_COLOR_RD_WR_OPT_MASK 0x02000000L #define CB_HW_CONTROL_3__DISABLE_BLENDER_CLOCK_GATING_MASK 0x04000000L +#define CB_HW_CONTROL_3__DISABLE_DCC_VRS_OPT_MASK 0x10000000L #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_MASK 0x40000000L #define CB_HW_CONTROL_3__DISABLE_FMASK_NOFETCH_OPT_BC_MASK 0x80000000L //CB_HW_CONTROL #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE__SHIFT 0x0 +#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION__SHIFT 0x1 #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC__SHIFT 0x3 #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX__SHIFT 0x4 +#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN__SHIFT 0x5 #define CB_HW_CONTROL__RMI_CREDITS__SHIFT 0x6 #define CB_HW_CONTROL__CHICKEN_BITS__SHIFT 0xc #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS__SHIFT 0xf @@ -10129,8 +10135,10 @@ #define CB_HW_CONTROL__DISABLE_CC_IB_SERIALIZER_STATE_OPT__SHIFT 0x1e #define CB_HW_CONTROL__DISABLE_PIXEL_IN_QUAD_FIX_FOR_LINEAR_SURFACE__SHIFT 0x1f #define CB_HW_CONTROL__ALLOW_MRT_WITH_DUAL_SOURCE_MASK 0x00000001L +#define CB_HW_CONTROL__DISABLE_VRS_FILLRATE_OPTIMIZATION_MASK 0x00000002L #define CB_HW_CONTROL__DISABLE_FILLRATE_OPT_FIX_WITH_CFC_MASK 0x00000008L #define CB_HW_CONTROL__DISABLE_POST_DCC_WITH_CFC_FIX_MASK 0x00000010L +#define CB_HW_CONTROL__DISABLE_COMPRESS_1FRAG_WHEN_VRS_RATE_HINT_EN_MASK 0x00000020L #define CB_HW_CONTROL__RMI_CREDITS_MASK 0x00000FC0L #define CB_HW_CONTROL__CHICKEN_BITS_MASK 0x00007000L #define CB_HW_CONTROL__DISABLE_FMASK_MULTI_MGCG_DOMAINS_MASK 0x00008000L @@ -19881,6 +19889,7 @@ #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS__SHIFT 0x16 #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS__SHIFT 0x17 #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL__SHIFT 0x19 +#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE__SHIFT 0x1a #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE__SHIFT 0x1b #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_CONTROL_MASK 0x00000003L #define DB_RENDER_OVERRIDE2__PARTIAL_SQUAD_LAUNCH_COUNTDOWN_MASK 0x0000001CL @@ -19898,6 +19907,7 @@ #define DB_RENDER_OVERRIDE2__PRESERVE_SRESULTS_MASK 0x00400000L #define DB_RENDER_OVERRIDE2__DISABLE_FAST_PASS_MASK 0x00800000L #define DB_RENDER_OVERRIDE2__ALLOW_PARTIAL_RES_HIER_KILL_MASK 0x02000000L +#define DB_RENDER_OVERRIDE2__FORCE_VRS_RATE_FINE_MASK 0x04000000L #define DB_RENDER_OVERRIDE2__CENTROID_COMPUTATION_MODE_MASK 0x18000000L //DB_HTILE_DATA_BASE #define DB_HTILE_DATA_BASE__BASE_256B__SHIFT 0x0 @@ -20021,6 +20031,13 @@ //DB_RESERVED_REG_3 #define DB_RESERVED_REG_3__FIELD_1__SHIFT 0x0 #define DB_RESERVED_REG_3__FIELD_1_MASK 0x003FFFFFL +//DB_VRS_OVERRIDE_CNTL +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE__SHIFT 0x0 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X__SHIFT 0x4 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y__SHIFT 0x6 +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_COMBINER_MODE_MASK 0x00000007L +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_X_MASK 0x00000030L +#define DB_VRS_OVERRIDE_CNTL__VRS_OVERRIDE_RATE_Y_MASK 0x000000C0L //DB_Z_READ_BASE_HI #define DB_Z_READ_BASE_HI__BASE_HI__SHIFT 0x0 #define DB_Z_READ_BASE_HI__BASE_HI_MASK 0x000000FFL @@ -22598,6 +22615,7 @@ #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA__SHIFT 0x18 #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG__SHIFT 0x19 #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH__SHIFT 0x1b +#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE__SHIFT 0x1c #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER__SHIFT 0x1d #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER__SHIFT 0x1e #define PA_CL_VS_OUT_CNTL__CLIP_DIST_ENA_0_MASK 0x00000001L @@ -22627,6 +22645,7 @@ #define PA_CL_VS_OUT_CNTL__VS_OUT_MISC_SIDE_BUS_ENA_MASK 0x01000000L #define PA_CL_VS_OUT_CNTL__USE_VTX_GS_CUT_FLAG_MASK 0x02000000L #define PA_CL_VS_OUT_CNTL__USE_VTX_LINE_WIDTH_MASK 0x08000000L +#define PA_CL_VS_OUT_CNTL__USE_VTX_VRS_RATE_MASK 0x10000000L #define PA_CL_VS_OUT_CNTL__BYPASS_VTX_RATE_COMBINER_MASK 0x20000000L #define PA_CL_VS_OUT_CNTL__BYPASS_PRIM_RATE_COMBINER_MASK 0x40000000L //PA_CL_NANINF_CNTL @@ -22740,6 +22759,19 @@ //PA_STATE_STEREO_X #define PA_STATE_STEREO_X__STEREO_X_OFFSET__SHIFT 0x0 #define PA_STATE_STEREO_X__STEREO_X_OFFSET_MASK 0xFFFFFFFFL +//PA_CL_VRS_CNTL +#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE__SHIFT 0x0 +#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE__SHIFT 0x3 +#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE__SHIFT 0x6 +#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE__SHIFT 0x9 +#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK__SHIFT 0xd +#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO__SHIFT 0xe +#define PA_CL_VRS_CNTL__VERTEX_RATE_COMBINER_MODE_MASK 0x00000007L +#define PA_CL_VRS_CNTL__PRIMITIVE_RATE_COMBINER_MODE_MASK 0x00000038L +#define PA_CL_VRS_CNTL__HTILE_RATE_COMBINER_MODE_MASK 0x000001C0L +#define PA_CL_VRS_CNTL__SAMPLE_ITER_COMBINER_MODE_MASK 0x00000E00L +#define PA_CL_VRS_CNTL__EXPOSE_VRS_PIXELS_MASK_MASK 0x00002000L +#define PA_CL_VRS_CNTL__CMASK_RATE_HINT_FORCE_ZERO_MASK 0x00004000L //PA_SU_POINT_SIZE #define PA_SU_POINT_SIZE__HEIGHT__SHIFT 0x0 #define PA_SU_POINT_SIZE__WIDTH__SHIFT 0x10 @@ -23088,6 +23120,7 @@ #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE__SHIFT 0x10 #define DB_HTILE_SURFACE__RESERVED_FIELD_6__SHIFT 0x11 #define DB_HTILE_SURFACE__PIPE_ALIGNED__SHIFT 0x12 +#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING__SHIFT 0x13 #define DB_HTILE_SURFACE__RESERVED_FIELD_1_MASK 0x00000001L #define DB_HTILE_SURFACE__FULL_CACHE_MASK 0x00000002L #define DB_HTILE_SURFACE__RESERVED_FIELD_2_MASK 0x00000004L @@ -23097,6 +23130,7 @@ #define DB_HTILE_SURFACE__DST_OUTSIDE_ZERO_TO_ONE_MASK 0x00010000L #define DB_HTILE_SURFACE__RESERVED_FIELD_6_MASK 0x00020000L #define DB_HTILE_SURFACE__PIPE_ALIGNED_MASK 0x00040000L +#define DB_HTILE_SURFACE__VRS_HTILE_ENCODING_MASK 0x00180000L //DB_SRESULTS_COMPARE_STATE0 #define DB_SRESULTS_COMPARE_STATE0__COMPAREFUNC0__SHIFT 0x0 #define DB_SRESULTS_COMPARE_STATE0__COMPAREVALUE0__SHIFT 0x4 @@ -24954,6 +24988,7 @@ #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR0_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR0_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR0_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24962,6 +24997,7 @@ #define CB_COLOR0_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR0_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR0_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR0_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR1_ATTRIB3 #define CB_COLOR1_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR1_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -24971,6 +25007,7 @@ #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR1_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR1_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR1_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24979,6 +25016,7 @@ #define CB_COLOR1_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR1_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR1_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR1_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR2_ATTRIB3 #define CB_COLOR2_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR2_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -24988,6 +25026,7 @@ #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR2_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR2_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR2_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -24996,6 +25035,7 @@ #define CB_COLOR2_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR2_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR2_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR2_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR3_ATTRIB3 #define CB_COLOR3_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR3_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25005,6 +25045,7 @@ #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR3_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR3_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR3_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25013,6 +25054,7 @@ #define CB_COLOR3_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR3_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR3_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR3_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR4_ATTRIB3 #define CB_COLOR4_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR4_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25022,6 +25064,7 @@ #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR4_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR4_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR4_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25030,6 +25073,7 @@ #define CB_COLOR4_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR4_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR4_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR4_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR5_ATTRIB3 #define CB_COLOR5_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR5_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25039,6 +25083,7 @@ #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR5_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR5_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR5_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25047,6 +25092,7 @@ #define CB_COLOR5_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR5_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR5_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR5_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR6_ATTRIB3 #define CB_COLOR6_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR6_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25056,6 +25102,7 @@ #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR6_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR6_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR6_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25064,6 +25111,7 @@ #define CB_COLOR6_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR6_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR6_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR6_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L //CB_COLOR7_ATTRIB3 #define CB_COLOR7_ATTRIB3__MIP0_DEPTH__SHIFT 0x0 #define CB_COLOR7_ATTRIB3__META_LINEAR__SHIFT 0xd @@ -25073,6 +25121,7 @@ #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED__SHIFT 0x1a #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL__SHIFT 0x1b #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED__SHIFT 0x1e +#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE__SHIFT 0x1f #define CB_COLOR7_ATTRIB3__MIP0_DEPTH_MASK 0x00001FFFL #define CB_COLOR7_ATTRIB3__META_LINEAR_MASK 0x00002000L #define CB_COLOR7_ATTRIB3__COLOR_SW_MODE_MASK 0x0007C000L @@ -25081,6 +25130,7 @@ #define CB_COLOR7_ATTRIB3__CMASK_PIPE_ALIGNED_MASK 0x04000000L #define CB_COLOR7_ATTRIB3__RESOURCE_LEVEL_MASK 0x38000000L #define CB_COLOR7_ATTRIB3__DCC_PIPE_ALIGNED_MASK 0x40000000L +#define CB_COLOR7_ATTRIB3__VRS_RATE_HINT_ENABLE_MASK 0x80000000L // addressBlock: gc_gfxudec diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h index c0efd90808f2..58cf7adb9d54 100644 --- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h +++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_3_0_0_sh_mask.h @@ -2393,6 +2393,7 @@ #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC__SHIFT 0x7 #define VCN_FEATURES__HAS_SCLR_DEC__SHIFT 0x8 #define VCN_FEATURES__HAS_VP9_DEC__SHIFT 0x9 +#define VCN_FEATURES__HAS_AV1_DEC__SHIFT 0xa #define VCN_FEATURES__HAS_EFC_ENC__SHIFT 0xb #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC__SHIFT 0xc #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC__SHIFT 0xd @@ -2407,6 +2408,7 @@ #define VCN_FEATURES__HAS_MJPEG2_IDCT_DEC_MASK 0x00000080L #define VCN_FEATURES__HAS_SCLR_DEC_MASK 0x00000100L #define VCN_FEATURES__HAS_VP9_DEC_MASK 0x00000200L +#define VCN_FEATURES__HAS_AV1_DEC_MASK 0x00000400L #define VCN_FEATURES__HAS_EFC_ENC_MASK 0x00000800L #define VCN_FEATURES__HAS_EFC_HDR2SDR_ENC_MASK 0x00001000L #define VCN_FEATURES__HAS_DUAL_MJPEG_DEC_MASK 0x00002000L @@ -2809,8 +2811,10 @@ #define UVD_SUVD_CGC_GATE__IME_HEVC__SHIFT 0x18 #define UVD_SUVD_CGC_GATE__EFC__SHIFT 0x19 #define UVD_SUVD_CGC_GATE__SAOE__SHIFT 0x1a +#define UVD_SUVD_CGC_GATE__SRE_AV1__SHIFT 0x1b #define UVD_SUVD_CGC_GATE__FBC_PCLK__SHIFT 0x1c #define UVD_SUVD_CGC_GATE__FBC_CCLK__SHIFT 0x1d +#define UVD_SUVD_CGC_GATE__SCM_AV1__SHIFT 0x1e #define UVD_SUVD_CGC_GATE__SMPA__SHIFT 0x1f #define UVD_SUVD_CGC_GATE__SRE_MASK 0x00000001L #define UVD_SUVD_CGC_GATE__SIT_MASK 0x00000002L @@ -2839,8 +2843,10 @@ #define UVD_SUVD_CGC_GATE__IME_HEVC_MASK 0x01000000L #define UVD_SUVD_CGC_GATE__EFC_MASK 0x02000000L #define UVD_SUVD_CGC_GATE__SAOE_MASK 0x04000000L +#define UVD_SUVD_CGC_GATE__SRE_AV1_MASK 0x08000000L #define UVD_SUVD_CGC_GATE__FBC_PCLK_MASK 0x10000000L #define UVD_SUVD_CGC_GATE__FBC_CCLK_MASK 0x20000000L +#define UVD_SUVD_CGC_GATE__SCM_AV1_MASK 0x40000000L #define UVD_SUVD_CGC_GATE__SMPA_MASK 0x80000000L //UVD_SUVD_CGC_STATUS #define UVD_SUVD_CGC_STATUS__SRE_VCLK__SHIFT 0x0 @@ -2873,6 +2879,8 @@ #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK__SHIFT 0x1b #define UVD_SUVD_CGC_STATUS__EFC_DCLK__SHIFT 0x1c #define UVD_SUVD_CGC_STATUS__SAOE_DCLK__SHIFT 0x1d +#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK__SHIFT 0x1e +#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK__SHIFT 0x1f #define UVD_SUVD_CGC_STATUS__SRE_VCLK_MASK 0x00000001L #define UVD_SUVD_CGC_STATUS__SRE_DCLK_MASK 0x00000002L #define UVD_SUVD_CGC_STATUS__SIT_DCLK_MASK 0x00000004L @@ -2903,6 +2911,8 @@ #define UVD_SUVD_CGC_STATUS__IME_HEVC_DCLK_MASK 0x08000000L #define UVD_SUVD_CGC_STATUS__EFC_DCLK_MASK 0x10000000L #define UVD_SUVD_CGC_STATUS__SAOE_DCLK_MASK 0x20000000L +#define UVD_SUVD_CGC_STATUS__SRE_AV1_VCLK_MASK 0x40000000L +#define UVD_SUVD_CGC_STATUS__SCM_AV1_DCLK_MASK 0x80000000L //UVD_SUVD_CGC_CTRL #define UVD_SUVD_CGC_CTRL__SRE_MODE__SHIFT 0x0 #define UVD_SUVD_CGC_CTRL__SIT_MODE__SHIFT 0x1 @@ -2919,6 +2929,8 @@ #define UVD_SUVD_CGC_CTRL__SMPA_MODE__SHIFT 0xc #define UVD_SUVD_CGC_CTRL__MPBE0_MODE__SHIFT 0xd #define UVD_SUVD_CGC_CTRL__MPBE1_MODE__SHIFT 0xe +#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE__SHIFT 0xf +#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE__SHIFT 0x10 #define UVD_SUVD_CGC_CTRL__MPC1_MODE__SHIFT 0x11 #define UVD_SUVD_CGC_CTRL__FBC_PCLK__SHIFT 0x1c #define UVD_SUVD_CGC_CTRL__FBC_CCLK__SHIFT 0x1d @@ -2937,6 +2949,8 @@ #define UVD_SUVD_CGC_CTRL__SMPA_MODE_MASK 0x00001000L #define UVD_SUVD_CGC_CTRL__MPBE0_MODE_MASK 0x00002000L #define UVD_SUVD_CGC_CTRL__MPBE1_MODE_MASK 0x00004000L +#define UVD_SUVD_CGC_CTRL__SIT_AV1_MODE_MASK 0x00008000L +#define UVD_SUVD_CGC_CTRL__SDB_AV1_MODE_MASK 0x00010000L #define UVD_SUVD_CGC_CTRL__MPC1_MODE_MASK 0x00020000L #define UVD_SUVD_CGC_CTRL__FBC_PCLK_MASK 0x10000000L #define UVD_SUVD_CGC_CTRL__FBC_CCLK_MASK 0x20000000L @@ -3658,6 +3672,8 @@ #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK__SHIFT 0x0 #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK__SHIFT 0x1 #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK__SHIFT 0x3 +#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK__SHIFT 0x4 +#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK__SHIFT 0x5 #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK__SHIFT 0x6 #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK__SHIFT 0x7 #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK__SHIFT 0x8 @@ -3666,6 +3682,8 @@ #define UVD_SUVD_CGC_STATUS2__SMPA_VCLK_MASK 0x00000001L #define UVD_SUVD_CGC_STATUS2__SMPA_DCLK_MASK 0x00000002L #define UVD_SUVD_CGC_STATUS2__MPBE1_DCLK_MASK 0x00000008L +#define UVD_SUVD_CGC_STATUS2__SIT_AV1_DCLK_MASK 0x00000010L +#define UVD_SUVD_CGC_STATUS2__SDB_AV1_DCLK_MASK 0x00000020L #define UVD_SUVD_CGC_STATUS2__MPC1_DCLK_MASK 0x00000040L #define UVD_SUVD_CGC_STATUS2__MPC1_SCLK_MASK 0x00000080L #define UVD_SUVD_CGC_STATUS2__MPC1_VCLK_MASK 0x00000100L @@ -3674,25 +3692,41 @@ //UVD_SUVD_CGC_GATE2 #define UVD_SUVD_CGC_GATE2__MPBE0__SHIFT 0x0 #define UVD_SUVD_CGC_GATE2__MPBE1__SHIFT 0x1 +#define UVD_SUVD_CGC_GATE2__SIT_AV1__SHIFT 0x2 +#define UVD_SUVD_CGC_GATE2__SDB_AV1__SHIFT 0x3 #define UVD_SUVD_CGC_GATE2__MPC1__SHIFT 0x4 #define UVD_SUVD_CGC_GATE2__MPBE0_MASK 0x00000001L #define UVD_SUVD_CGC_GATE2__MPBE1_MASK 0x00000002L +#define UVD_SUVD_CGC_GATE2__SIT_AV1_MASK 0x00000004L +#define UVD_SUVD_CGC_GATE2__SDB_AV1_MASK 0x00000008L #define UVD_SUVD_CGC_GATE2__MPC1_MASK 0x00000010L //UVD_SUVD_INT_STATUS2 #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT__SHIFT 0x0 #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT__SHIFT 0x5 +#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT__SHIFT 0x6 +#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT__SHIFT 0xb #define UVD_SUVD_INT_STATUS2__SMPA_FUNC_INT_MASK 0x0000001FL #define UVD_SUVD_INT_STATUS2__SMPA_ERR_INT_MASK 0x00000020L +#define UVD_SUVD_INT_STATUS2__SDB_AV1_FUNC_INT_MASK 0x000007C0L +#define UVD_SUVD_INT_STATUS2__SDB_AV1_ERR_INT_MASK 0x00000800L //UVD_SUVD_INT_EN2 #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN__SHIFT 0x0 #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN__SHIFT 0x5 +#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN__SHIFT 0x6 +#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN__SHIFT 0xb #define UVD_SUVD_INT_EN2__SMPA_FUNC_INT_EN_MASK 0x0000001FL #define UVD_SUVD_INT_EN2__SMPA_ERR_INT_EN_MASK 0x00000020L +#define UVD_SUVD_INT_EN2__SDB_AV1_FUNC_INT_EN_MASK 0x000007C0L +#define UVD_SUVD_INT_EN2__SDB_AV1_ERR_INT_EN_MASK 0x00000800L //UVD_SUVD_INT_ACK2 #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK__SHIFT 0x0 #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK__SHIFT 0x5 +#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK__SHIFT 0x6 +#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK__SHIFT 0xb #define UVD_SUVD_INT_ACK2__SMPA_FUNC_INT_ACK_MASK 0x0000001FL #define UVD_SUVD_INT_ACK2__SMPA_ERR_INT_ACK_MASK 0x00000020L +#define UVD_SUVD_INT_ACK2__SDB_AV1_FUNC_INT_ACK_MASK 0x000007C0L +#define UVD_SUVD_INT_ACK2__SDB_AV1_ERR_INT_ACK_MASK 0x00000800L // addressBlock: uvd0_ecpudec diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h index a3c238c39ef5..301de493377a 100644 --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h @@ -226,7 +226,7 @@ struct kfd2kgd_calls { uint32_t sh_mem_config, uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases); - int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, unsigned int pasid, + int (*set_pasid_vmid_mapping)(struct kgd_dev *kgd, u32 pasid, unsigned int vmid); int (*init_interrupts)(struct kgd_dev *kgd, uint32_t pipe_id); diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c index 0826625573dc..8dc5abb6931e 100644 --- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c @@ -479,17 +479,6 @@ static int smu_late_init(void *handle) return ret; } - /* - * Set initialized values (get from vbios) to dpm tables context such as - * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each - * type of clks. - */ - ret = smu_set_default_dpm_table(smu); - if (ret) { - dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); - return ret; - } - ret = smu_populate_umd_state_clk(smu); if (ret) { dev_err(adev->dev, "Failed to populate UMD state clocks!\n"); @@ -984,6 +973,17 @@ static int smu_smc_hw_setup(struct smu_context *smu) return ret; } + /* + * Set initialized values (get from vbios) to dpm tables context such as + * gfxclk, memclk, dcefclk, and etc. And enable the DPM feature for each + * type of clks. + */ + ret = smu_set_default_dpm_table(smu); + if (ret) { + dev_err(adev->dev, "Failed to setup default dpm clock tables!\n"); + return ret; + } + ret = smu_notify_display_change(smu); if (ret) return ret; @@ -1126,7 +1126,7 @@ static int smu_disable_dpms(struct smu_context *smu) */ if (smu->uploading_custom_pp_table && (adev->asic_type >= CHIP_NAVI10) && - (adev->asic_type <= CHIP_NAVI12)) + (adev->asic_type <= CHIP_NAVY_FLOUNDER)) return 0; /* @@ -1211,7 +1211,9 @@ static int smu_hw_fini(void *handle) int smu_reset(struct smu_context *smu) { struct amdgpu_device *adev = smu->adev; - int ret = 0; + int ret; + + amdgpu_gfx_off_ctrl(smu->adev, false); ret = smu_hw_fini(adev); if (ret) @@ -1222,8 +1224,12 @@ int smu_reset(struct smu_context *smu) return ret; ret = smu_late_init(adev); + if (ret) + return ret; - return ret; + amdgpu_gfx_off_ctrl(smu->adev, true); + + return 0; } static int smu_suspend(void *handle) diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c index fb962b9ceffb..9582b38162f0 100644 --- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c @@ -1840,10 +1840,14 @@ static bool arcturus_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index 9ee8cf8267c8..43f7adff6cb7 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -563,6 +563,8 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, struct smu10_hwmgr *data = hwmgr->backend; uint32_t min_sclk = hwmgr->display_config->min_core_set_clock; uint32_t min_mclk = hwmgr->display_config->min_mem_set_clock/100; + uint32_t index_fclk = data->clock_vol_info.vdd_dep_on_fclk->count - 1; + uint32_t index_socclk = data->clock_vol_info.vdd_dep_on_socclk->count - 1; if (hwmgr->smu_version < 0x1E3700) { pr_info("smu firmware version too old, can not set dpm level\n"); @@ -676,13 +678,13 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinFclkByFreq, hwmgr->display_config->num_display > 3 ? - SMU10_UMD_PSTATE_PEAK_FCLK : + data->clock_vol_info.vdd_dep_on_fclk->entries[0].clk : min_mclk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinSocclkByFreq, - SMU10_UMD_PSTATE_MIN_SOCCLK, + data->clock_vol_info.vdd_dep_on_socclk->entries[0].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinVcn, @@ -695,11 +697,11 @@ static int smu10_dpm_force_dpm_level(struct pp_hwmgr *hwmgr, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxFclkByFreq, - SMU10_UMD_PSTATE_PEAK_FCLK, + data->clock_vol_info.vdd_dep_on_fclk->entries[index_fclk].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxSocclkByFreq, - SMU10_UMD_PSTATE_PEAK_SOCCLK, + data->clock_vol_info.vdd_dep_on_socclk->entries[index_socclk].clk, NULL); smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetSoftMaxVcn, diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c index ffe05b7cc1f0..4a3b64aa21ce 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c @@ -3581,7 +3581,8 @@ static int smu7_read_sensor(struct pp_hwmgr *hwmgr, int idx, case AMDGPU_PP_SENSOR_GPU_POWER: return smu7_get_gpu_power(hwmgr, (uint32_t *)value); case AMDGPU_PP_SENSOR_VDDGFX: - if ((data->vr_config & 0xff) == 0x2) + if ((data->vr_config & VRCONF_VDDGFX_MASK) == + (VR_SVI2_PLANE_2 << VRCONF_VDDGFX_SHIFT)) val_vid = PHM_READ_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, PWR_SVI2_STATUS, PLANE2_VID); else diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c index d572ba4ec9b1..952cd3d7240e 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_thermal.c @@ -374,8 +374,18 @@ static int vega10_thermal_set_temperature_range(struct pp_hwmgr *hwmgr, /* compare them in unit celsius degree */ if (low < range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES) low = range->min / PP_TEMPERATURE_UNITS_PER_CENTIGRADES; - if (high > tdp_table->usSoftwareShutdownTemp) - high = tdp_table->usSoftwareShutdownTemp; + + /* + * As a common sense, usSoftwareShutdownTemp should be bigger + * than ThotspotLimit. For any invalid usSoftwareShutdownTemp, + * we will just use the max possible setting VEGA10_THERMAL_MAXIMUM_ALERT_TEMP + * to avoid false alarms. + */ + if ((tdp_table->usSoftwareShutdownTemp > + range->hotspot_crit_max / PP_TEMPERATURE_UNITS_PER_CENTIGRADES)) { + if (high > tdp_table->usSoftwareShutdownTemp) + high = tdp_table->usSoftwareShutdownTemp; + } if (low > high) return -EINVAL; diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c index 9f62af9abd23..b1547a83e721 100644 --- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c @@ -1331,10 +1331,14 @@ static bool navi10_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } @@ -2261,8 +2265,6 @@ static void navi10_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2300,6 +2302,12 @@ static int navi10_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, false, address, numbytes, data); @@ -2336,6 +2344,12 @@ static int navi10_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); navi10_fill_i2c_req(&req, true, address, numbytes, data); diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c index dbb676c482fd..15263cf210d5 100644 --- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c @@ -232,14 +232,16 @@ static int renoir_get_profiling_clk_mask(struct smu_context *smu, *sclk_mask = 0; } else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) { if (mclk_mask) - *mclk_mask = 0; + /* mclk levels are in reverse order */ + *mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1; } else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) { if(sclk_mask) /* The sclk as gfxclk and has three level about max/min/current */ *sclk_mask = 3 - 1; if(mclk_mask) - *mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1; + /* mclk levels are in reverse order */ + *mclk_mask = 0; if(soc_mask) *soc_mask = NUM_SOCCLK_DPM_LEVELS - 1; @@ -333,7 +335,7 @@ static int renoir_get_dpm_ultimate_freq(struct smu_context *smu, case SMU_UCLK: case SMU_FCLK: case SMU_MCLK: - ret = renoir_get_dpm_clk_limited(smu, clk_type, 0, min); + ret = renoir_get_dpm_clk_limited(smu, clk_type, NUM_MEMCLK_DPM_LEVELS - 1, min); if (ret) goto failed; break; diff --git a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c index 638760839c15..ace682fde22f 100644 --- a/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/powerplay/sienna_cichlid_ppt.c @@ -68,7 +68,8 @@ FEATURE_MASK(FEATURE_DPM_LINK_BIT) | \ FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT) | \ FEATURE_MASK(FEATURE_DPM_FCLK_BIT) | \ - FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT)) + FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT) | \ + FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT)) #define SMU_11_0_7_GFX_BUSY_THRESHOLD 15 @@ -229,6 +230,7 @@ sienna_cichlid_get_allowed_feature_mask(struct smu_context *smu, *(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_PREFETCHER_BIT) | FEATURE_MASK(FEATURE_DPM_FCLK_BIT) + | FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT) | FEATURE_MASK(FEATURE_DS_SOCCLK_BIT) | FEATURE_MASK(FEATURE_DS_DCEFCLK_BIT) | FEATURE_MASK(FEATURE_DS_FCLK_BIT) @@ -1147,10 +1149,14 @@ static bool sienna_cichlid_is_dpm_running(struct smu_context *smu) { int ret = 0; uint32_t feature_mask[2]; - unsigned long feature_enabled; + uint64_t feature_enabled; + ret = smu_cmn_get_enabled_mask(smu, feature_mask, 2); - feature_enabled = (unsigned long)((uint64_t)feature_mask[0] | - ((uint64_t)feature_mask[1] << 32)); + if (ret) + return false; + + feature_enabled = (uint64_t)feature_mask[1] << 32 | feature_mask[0]; + return !!(feature_enabled & SMC_DPM_FEATURE); } @@ -2439,8 +2445,6 @@ static void sienna_cichlid_fill_i2c_req(SwI2cRequest_t *req, bool write, { int i; - BUG_ON(numbytes > MAX_SW_I2C_COMMANDS); - req->I2CcontrollerPort = 0; req->I2CSpeed = 2; req->SlaveAddress = address; @@ -2478,6 +2482,12 @@ static int sienna_cichlid_i2c_read_data(struct i2c_adapter *control, struct smu_table_context *smu_table = &adev->smu.smu_table; struct smu_table *table = &smu_table->driver_table; + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, false, address, numbytes, data); @@ -2514,6 +2524,12 @@ static int sienna_cichlid_i2c_write_data(struct i2c_adapter *control, SwI2cRequest_t req; struct amdgpu_device *adev = to_amdgpu_device(control); + if (numbytes > MAX_SW_I2C_COMMANDS) { + dev_err(adev->dev, "numbytes requested %d is over max allowed %d\n", + numbytes, MAX_SW_I2C_COMMANDS); + return -EINVAL; + } + memset(&req, 0, sizeof(req)); sienna_cichlid_fill_i2c_req(&req, true, address, numbytes, data); diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c index c18169aa59ce..e4d1f3d66ef4 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c @@ -37,6 +37,7 @@ #include "cgs_common.h" #include "atombios.h" #include "pppcielanes.h" +#include "smu7_smumgr.h" #include "smu/smu_7_0_1_d.h" #include "smu/smu_7_0_1_sh_mask.h" @@ -2948,6 +2949,7 @@ const struct pp_smumgr_func ci_smu_funcs = { .request_smu_load_specific_fw = NULL, .send_msg_to_smc = ci_send_msg_to_smc, .send_msg_to_smc_with_parameter = ci_send_msg_to_smc_with_parameter, + .get_argument = smu7_get_argument, .download_pptable_settings = NULL, .upload_pptable_settings = NULL, .get_offsetof = ci_get_offsetof, diff --git a/drivers/gpu/drm/i915/display/intel_combo_phy.c b/drivers/gpu/drm/i915/display/intel_combo_phy.c index 6968de4f3477..157d8c8c605a 100644 --- a/drivers/gpu/drm/i915/display/intel_combo_phy.c +++ b/drivers/gpu/drm/i915/display/intel_combo_phy.c @@ -258,7 +258,7 @@ static bool phy_is_master(struct drm_i915_private *dev_priv, enum phy phy) static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, enum phy phy) { - bool ret; + bool ret = true; u32 expected_val = 0; if (!icl_combo_phy_enabled(dev_priv, phy)) @@ -276,7 +276,7 @@ static bool icl_combo_phy_verify_state(struct drm_i915_private *dev_priv, DCC_MODE_SELECT_CONTINUOSLY); } - ret = cnl_verify_procmon_ref_values(dev_priv, phy); + ret &= cnl_verify_procmon_ref_values(dev_priv, phy); if (phy_is_master(dev_priv, phy)) { ret &= check_phy_reg(dev_priv, phy, ICL_PORT_COMP_DW8(phy), diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 68325678f5ef..b18c5ac2934d 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -14956,12 +14956,6 @@ static int intel_atomic_check(struct drm_device *dev, if (dev_priv->wm.distrust_bios_wm) any_ms = true; - if (any_ms) { - ret = intel_modeset_checks(state); - if (ret) - goto fail; - } - intel_fbc_choose_crtc(dev_priv, state); ret = calc_watermark_data(state); if (ret) @@ -14976,6 +14970,10 @@ static int intel_atomic_check(struct drm_device *dev, goto fail; if (any_ms) { + ret = intel_modeset_checks(state); + if (ret) + goto fail; + ret = intel_modeset_calc_cdclk(state); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c index 89a4d294822d..1a0d49af2a08 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp.c +++ b/drivers/gpu/drm/i915/display/intel_hdcp.c @@ -336,8 +336,10 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, /* Fill up the empty slots in sha_text and write it out */ sha_empty = sizeof(sha_text) - sha_leftovers; - for (j = 0; j < sha_empty; j++) - sha_text |= ksv[j] << ((sizeof(sha_text) - j - 1) * 8); + for (j = 0; j < sha_empty; j++) { + u8 off = ((sizeof(sha_text) - j - 1 - sha_leftovers) * 8); + sha_text |= ksv[j] << off; + } ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) @@ -435,7 +437,7 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, /* Write 32 bits of text */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32); - sha_text |= bstatus[0] << 24 | bstatus[1] << 16; + sha_text |= bstatus[0] << 8 | bstatus[1]; ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) return ret; @@ -450,17 +452,29 @@ int intel_hdcp_validate_v_prime(struct intel_connector *connector, return ret; sha_idx += sizeof(sha_text); } + + /* + * Terminate the SHA-1 stream by hand. For the other leftover + * cases this is appended by the hardware. + */ + intel_de_write(dev_priv, HDCP_REP_CTL, + rep_ctl | HDCP_SHA1_TEXT_32); + sha_text = DRM_HDCP_SHA1_TERMINATOR << 24; + ret = intel_write_sha_text(dev_priv, sha_text); + if (ret < 0) + return ret; + sha_idx += sizeof(sha_text); } else if (sha_leftovers == 3) { - /* Write 32 bits of text */ + /* Write 32 bits of text (filled from LSB) */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_32); - sha_text |= bstatus[0] << 24; + sha_text |= bstatus[0]; ret = intel_write_sha_text(dev_priv, sha_text); if (ret < 0) return ret; sha_idx += sizeof(sha_text); - /* Write 8 bits of text, 24 bits of M0 */ + /* Write 8 bits of text (filled from LSB), 24 bits of M0 */ intel_de_write(dev_priv, HDCP_REP_CTL, rep_ctl | HDCP_SHA1_TEXT_8); ret = intel_write_sha_text(dev_priv, bstatus[1]); @@ -781,6 +795,7 @@ static int _intel_hdcp_disable(struct intel_connector *connector) struct intel_hdcp *hdcp = &connector->hdcp; enum port port = dig_port->base.port; enum transcoder cpu_transcoder = hdcp->cpu_transcoder; + u32 repeater_ctl; int ret; drm_dbg_kms(&dev_priv->drm, "[%s:%d] HDCP is being disabled...\n", @@ -796,6 +811,11 @@ static int _intel_hdcp_disable(struct intel_connector *connector) return -ETIMEDOUT; } + repeater_ctl = intel_hdcp_get_repeater_ctl(dev_priv, cpu_transcoder, + port); + intel_de_write(dev_priv, HDCP_REP_CTL, + intel_de_read(dev_priv, HDCP_REP_CTL) & ~repeater_ctl); + ret = hdcp->shim->toggle_signalling(dig_port, false); if (ret) { drm_err(&dev_priv->drm, "Failed to disable HDCP signalling\n"); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c index d0bdb6d447ed..ef755dd5e68f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_context.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c @@ -439,29 +439,36 @@ static bool __cancel_engine(struct intel_engine_cs *engine) return __reset_engine(engine); } -static struct intel_engine_cs *__active_engine(struct i915_request *rq) +static bool +__active_engine(struct i915_request *rq, struct intel_engine_cs **active) { struct intel_engine_cs *engine, *locked; + bool ret = false; /* * Serialise with __i915_request_submit() so that it sees * is-banned?, or we know the request is already inflight. + * + * Note that rq->engine is unstable, and so we double + * check that we have acquired the lock on the final engine. */ locked = READ_ONCE(rq->engine); spin_lock_irq(&locked->active.lock); while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) { spin_unlock(&locked->active.lock); - spin_lock(&engine->active.lock); locked = engine; + spin_lock(&locked->active.lock); } - engine = NULL; - if (i915_request_is_active(rq) && rq->fence.error != -EIO) - engine = rq->engine; + if (!i915_request_completed(rq)) { + if (i915_request_is_active(rq) && rq->fence.error != -EIO) + *active = locked; + ret = true; + } spin_unlock_irq(&locked->active.lock); - return engine; + return ret; } static struct intel_engine_cs *active_engine(struct intel_context *ce) @@ -472,17 +479,16 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce) if (!ce->timeline) return NULL; - mutex_lock(&ce->timeline->mutex); - list_for_each_entry_reverse(rq, &ce->timeline->requests, link) { - if (i915_request_completed(rq)) - break; + rcu_read_lock(); + list_for_each_entry_rcu(rq, &ce->timeline->requests, link) { + if (i915_request_is_active(rq) && i915_request_completed(rq)) + continue; /* Check with the backend if the request is inflight */ - engine = __active_engine(rq); - if (engine) + if (__active_engine(rq, &engine)) break; } - mutex_unlock(&ce->timeline->mutex); + rcu_read_unlock(); return engine; } @@ -713,6 +719,7 @@ __create_context(struct drm_i915_private *i915) ctx->i915 = i915; ctx->sched.priority = I915_USER_PRIORITY(I915_PRIORITY_NORMAL); mutex_init(&ctx->mutex); + INIT_LIST_HEAD(&ctx->link); spin_lock_init(&ctx->stale.lock); INIT_LIST_HEAD(&ctx->stale.engines); @@ -740,10 +747,6 @@ __create_context(struct drm_i915_private *i915) for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++) ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES; - spin_lock(&i915->gem.contexts.lock); - list_add_tail(&ctx->link, &i915->gem.contexts.list); - spin_unlock(&i915->gem.contexts.lock); - return ctx; err_free: @@ -931,6 +934,7 @@ static int gem_context_register(struct i915_gem_context *ctx, struct drm_i915_file_private *fpriv, u32 *id) { + struct drm_i915_private *i915 = ctx->i915; struct i915_address_space *vm; int ret; @@ -949,8 +953,16 @@ static int gem_context_register(struct i915_gem_context *ctx, /* And finally expose ourselves to userspace via the idr */ ret = xa_alloc(&fpriv->context_xa, id, ctx, xa_limit_32b, GFP_KERNEL); if (ret) - put_pid(fetch_and_zero(&ctx->pid)); + goto err_pid; + + spin_lock(&i915->gem.contexts.lock); + list_add_tail(&ctx->link, &i915->gem.contexts.list); + spin_unlock(&i915->gem.contexts.lock); + + return 0; +err_pid: + put_pid(fetch_and_zero(&ctx->pid)); return ret; } diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 6b4ec66cb558..446e76e95c38 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -45,6 +45,13 @@ struct eb_vma_array { struct eb_vma vma[]; }; +enum { + FORCE_CPU_RELOC = 1, + FORCE_GTT_RELOC, + FORCE_GPU_RELOC, +#define DBG_FORCE_RELOC 0 /* choose one of the above! */ +}; + #define __EXEC_OBJECT_HAS_PIN BIT(31) #define __EXEC_OBJECT_HAS_FENCE BIT(30) #define __EXEC_OBJECT_NEEDS_MAP BIT(29) @@ -253,6 +260,8 @@ struct i915_execbuffer { */ struct reloc_cache { struct drm_mm_node node; /** temporary GTT binding */ + unsigned long vaddr; /** Current kmap address */ + unsigned long page; /** Currently mapped page index */ unsigned int gen; /** Cached value of INTEL_GEN */ bool use_64bit_reloc : 1; bool has_llc : 1; @@ -596,6 +605,23 @@ eb_add_vma(struct i915_execbuffer *eb, } } +static inline int use_cpu_reloc(const struct reloc_cache *cache, + const struct drm_i915_gem_object *obj) +{ + if (!i915_gem_object_has_struct_page(obj)) + return false; + + if (DBG_FORCE_RELOC == FORCE_CPU_RELOC) + return true; + + if (DBG_FORCE_RELOC == FORCE_GTT_RELOC) + return false; + + return (cache->has_llc || + obj->cache_dirty || + obj->cache_level != I915_CACHE_NONE); +} + static int eb_reserve_vma(const struct i915_execbuffer *eb, struct eb_vma *ev, u64 pin_flags) @@ -926,6 +952,8 @@ relocation_target(const struct drm_i915_gem_relocation_entry *reloc, static void reloc_cache_init(struct reloc_cache *cache, struct drm_i915_private *i915) { + cache->page = -1; + cache->vaddr = 0; /* Must be a variable in the struct to allow GCC to unroll. */ cache->gen = INTEL_GEN(i915); cache->has_llc = HAS_LLC(i915); @@ -937,6 +965,25 @@ static void reloc_cache_init(struct reloc_cache *cache, cache->target = NULL; } +static inline void *unmask_page(unsigned long p) +{ + return (void *)(uintptr_t)(p & PAGE_MASK); +} + +static inline unsigned int unmask_flags(unsigned long p) +{ + return p & ~PAGE_MASK; +} + +#define KMAP 0x4 /* after CLFLUSH_FLAGS */ + +static inline struct i915_ggtt *cache_to_ggtt(struct reloc_cache *cache) +{ + struct drm_i915_private *i915 = + container_of(cache, struct i915_execbuffer, reloc_cache)->i915; + return &i915->ggtt; +} + #define RELOC_TAIL 4 static int reloc_gpu_chain(struct reloc_cache *cache) @@ -1049,6 +1096,181 @@ static int reloc_gpu_flush(struct reloc_cache *cache) return err; } +static void reloc_cache_reset(struct reloc_cache *cache) +{ + void *vaddr; + + if (!cache->vaddr) + return; + + vaddr = unmask_page(cache->vaddr); + if (cache->vaddr & KMAP) { + if (cache->vaddr & CLFLUSH_AFTER) + mb(); + + kunmap_atomic(vaddr); + i915_gem_object_finish_access((struct drm_i915_gem_object *)cache->node.mm); + } else { + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + + intel_gt_flush_ggtt_writes(ggtt->vm.gt); + io_mapping_unmap_atomic((void __iomem *)vaddr); + + if (drm_mm_node_allocated(&cache->node)) { + ggtt->vm.clear_range(&ggtt->vm, + cache->node.start, + cache->node.size); + mutex_lock(&ggtt->vm.mutex); + drm_mm_remove_node(&cache->node); + mutex_unlock(&ggtt->vm.mutex); + } else { + i915_vma_unpin((struct i915_vma *)cache->node.mm); + } + } + + cache->vaddr = 0; + cache->page = -1; +} + +static void *reloc_kmap(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + + if (cache->vaddr) { + kunmap_atomic(unmask_page(cache->vaddr)); + } else { + unsigned int flushes; + int err; + + err = i915_gem_object_prepare_write(obj, &flushes); + if (err) + return ERR_PTR(err); + + BUILD_BUG_ON(KMAP & CLFLUSH_FLAGS); + BUILD_BUG_ON((KMAP | CLFLUSH_FLAGS) & PAGE_MASK); + + cache->vaddr = flushes | KMAP; + cache->node.mm = (void *)obj; + if (flushes) + mb(); + } + + vaddr = kmap_atomic(i915_gem_object_get_dirty_page(obj, page)); + cache->vaddr = unmask_flags(cache->vaddr) | (unsigned long)vaddr; + cache->page = page; + + return vaddr; +} + +static void *reloc_iomap(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + struct i915_ggtt *ggtt = cache_to_ggtt(cache); + unsigned long offset; + void *vaddr; + + if (cache->vaddr) { + intel_gt_flush_ggtt_writes(ggtt->vm.gt); + io_mapping_unmap_atomic((void __force __iomem *) unmask_page(cache->vaddr)); + } else { + struct i915_vma *vma; + int err; + + if (i915_gem_object_is_tiled(obj)) + return ERR_PTR(-EINVAL); + + if (use_cpu_reloc(cache, obj)) + return NULL; + + i915_gem_object_lock(obj); + err = i915_gem_object_set_to_gtt_domain(obj, true); + i915_gem_object_unlock(obj); + if (err) + return ERR_PTR(err); + + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, + PIN_MAPPABLE | + PIN_NONBLOCK /* NOWARN */ | + PIN_NOEVICT); + if (IS_ERR(vma)) { + memset(&cache->node, 0, sizeof(cache->node)); + mutex_lock(&ggtt->vm.mutex); + err = drm_mm_insert_node_in_range + (&ggtt->vm.mm, &cache->node, + PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE, + 0, ggtt->mappable_end, + DRM_MM_INSERT_LOW); + mutex_unlock(&ggtt->vm.mutex); + if (err) /* no inactive aperture space, use cpu reloc */ + return NULL; + } else { + cache->node.start = vma->node.start; + cache->node.mm = (void *)vma; + } + } + + offset = cache->node.start; + if (drm_mm_node_allocated(&cache->node)) { + ggtt->vm.insert_page(&ggtt->vm, + i915_gem_object_get_dma_address(obj, page), + offset, I915_CACHE_NONE, 0); + } else { + offset += page << PAGE_SHIFT; + } + + vaddr = (void __force *)io_mapping_map_atomic_wc(&ggtt->iomap, + offset); + cache->page = page; + cache->vaddr = (unsigned long)vaddr; + + return vaddr; +} + +static void *reloc_vaddr(struct drm_i915_gem_object *obj, + struct reloc_cache *cache, + unsigned long page) +{ + void *vaddr; + + if (cache->page == page) { + vaddr = unmask_page(cache->vaddr); + } else { + vaddr = NULL; + if ((cache->vaddr & KMAP) == 0) + vaddr = reloc_iomap(obj, cache, page); + if (!vaddr) + vaddr = reloc_kmap(obj, cache, page); + } + + return vaddr; +} + +static void clflush_write32(u32 *addr, u32 value, unsigned int flushes) +{ + if (unlikely(flushes & (CLFLUSH_BEFORE | CLFLUSH_AFTER))) { + if (flushes & CLFLUSH_BEFORE) { + clflushopt(addr); + mb(); + } + + *addr = value; + + /* + * Writes to the same cacheline are serialised by the CPU + * (including clflush). On the write path, we only require + * that it hits memory in an orderly fashion and place + * mb barriers at the start and end of the relocation phase + * to ensure ordering of clflush wrt to the system. + */ + if (flushes & CLFLUSH_AFTER) + clflushopt(addr); + } else + *addr = value; +} + static int reloc_move_to_gpu(struct i915_request *rq, struct i915_vma *vma) { struct drm_i915_gem_object *obj = vma->obj; @@ -1214,6 +1436,17 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb, return cmd; } +static inline bool use_reloc_gpu(struct i915_vma *vma) +{ + if (DBG_FORCE_RELOC == FORCE_GPU_RELOC) + return true; + + if (DBG_FORCE_RELOC) + return false; + + return !dma_resv_test_signaled_rcu(vma->resv, true); +} + static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) { struct page *page; @@ -1228,10 +1461,10 @@ static unsigned long vma_phys_addr(struct i915_vma *vma, u32 offset) return addr + offset_in_page(offset); } -static int __reloc_entry_gpu(struct i915_execbuffer *eb, - struct i915_vma *vma, - u64 offset, - u64 target_addr) +static bool __reloc_entry_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + u64 offset, + u64 target_addr) { const unsigned int gen = eb->reloc_cache.gen; unsigned int len; @@ -1247,7 +1480,7 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb, batch = reloc_gpu(eb, vma, len); if (IS_ERR(batch)) - return PTR_ERR(batch); + return false; addr = gen8_canonical_addr(vma->node.start + offset); if (gen >= 8) { @@ -1296,21 +1529,55 @@ static int __reloc_entry_gpu(struct i915_execbuffer *eb, *batch++ = target_addr; } - return 0; + return true; +} + +static bool reloc_entry_gpu(struct i915_execbuffer *eb, + struct i915_vma *vma, + u64 offset, + u64 target_addr) +{ + if (eb->reloc_cache.vaddr) + return false; + + if (!use_reloc_gpu(vma)) + return false; + + return __reloc_entry_gpu(eb, vma, offset, target_addr); } static u64 -relocate_entry(struct i915_execbuffer *eb, - struct i915_vma *vma, +relocate_entry(struct i915_vma *vma, const struct drm_i915_gem_relocation_entry *reloc, + struct i915_execbuffer *eb, const struct i915_vma *target) { u64 target_addr = relocation_target(reloc, target); - int err; - - err = __reloc_entry_gpu(eb, vma, reloc->offset, target_addr); - if (err) - return err; + u64 offset = reloc->offset; + + if (!reloc_entry_gpu(eb, vma, offset, target_addr)) { + bool wide = eb->reloc_cache.use_64bit_reloc; + void *vaddr; + +repeat: + vaddr = reloc_vaddr(vma->obj, + &eb->reloc_cache, + offset >> PAGE_SHIFT); + if (IS_ERR(vaddr)) + return PTR_ERR(vaddr); + + GEM_BUG_ON(!IS_ALIGNED(offset, sizeof(u32))); + clflush_write32(vaddr + offset_in_page(offset), + lower_32_bits(target_addr), + eb->reloc_cache.vaddr); + + if (wide) { + offset += sizeof(u32); + target_addr >>= 32; + wide = false; + goto repeat; + } + } return target->node.start | UPDATE; } @@ -1375,7 +1642,8 @@ eb_relocate_entry(struct i915_execbuffer *eb, * If the relocation already has the right value in it, no * more work needs to be done. */ - if (gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) + if (!DBG_FORCE_RELOC && + gen8_canonical_addr(target->vma->node.start) == reloc->presumed_offset) return 0; /* Check that the relocation address is valid... */ @@ -1407,7 +1675,7 @@ eb_relocate_entry(struct i915_execbuffer *eb, ev->flags &= ~EXEC_OBJECT_ASYNC; /* and update the user's relocation entry */ - return relocate_entry(eb, ev->vma, reloc, target->vma); + return relocate_entry(ev->vma, reloc, eb, target->vma); } static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) @@ -1445,8 +1713,10 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) * this is bad and so lockdep complains vehemently. */ copied = __copy_from_user(r, urelocs, count * sizeof(r[0])); - if (unlikely(copied)) - return -EFAULT; + if (unlikely(copied)) { + remain = -EFAULT; + goto out; + } remain -= count; do { @@ -1454,7 +1724,8 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) if (likely(offset == 0)) { } else if ((s64)offset < 0) { - return (int)offset; + remain = (int)offset; + goto out; } else { /* * Note that reporting an error now @@ -1484,8 +1755,9 @@ static int eb_relocate_vma(struct i915_execbuffer *eb, struct eb_vma *ev) } while (r++, --count); urelocs += ARRAY_SIZE(stack); } while (remain); - - return 0; +out: + reloc_cache_reset(&eb->reloc_cache); + return remain; } static int eb_relocate(struct i915_execbuffer *eb) @@ -2392,7 +2664,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, eb.i915 = i915; eb.file = file; eb.args = args; - if (!(args->flags & I915_EXEC_NO_RELOC)) + if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC)) args->flags |= __EXEC_HAS_RELOC; eb.exec = exec; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h index e5b9276d254c..9cf4ad78ece6 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h @@ -258,6 +258,10 @@ struct page * i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n); +struct page * +i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, + unsigned int n); + dma_addr_t i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index d15ff6748a50..e8a083743e09 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -548,6 +548,20 @@ i915_gem_object_get_page(struct drm_i915_gem_object *obj, unsigned int n) return nth_page(sg_page(sg), offset); } +/* Like i915_gem_object_get_page(), but mark the returned page dirty */ +struct page * +i915_gem_object_get_dirty_page(struct drm_i915_gem_object *obj, + unsigned int n) +{ + struct page *page; + + page = i915_gem_object_get_page(obj, n); + if (!obj->mm.dirty) + set_page_dirty(page); + + return page; +} + dma_addr_t i915_gem_object_get_dma_address_len(struct drm_i915_gem_object *obj, unsigned long n, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 2c2bf24140c9..12b30075134a 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -596,14 +596,6 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj) GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN); - /* - * Using __get_user_pages_fast() with a read-only - * access is questionable. A read-only page may be - * COW-broken, and then this might end up giving - * the wrong side of the COW.. - * - * We may or may not care. - */ if (pvec) { /* defer to worker if malloc fails */ if (!i915_gem_object_is_readonly(obj)) diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c index 57c14d3340cd..a49016f8ee0d 100644 --- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c @@ -37,14 +37,20 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb, return err; /* 8-Byte aligned */ - err = __reloc_entry_gpu(eb, vma, offsets[0] * sizeof(u32), 0); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[0] * sizeof(u32), + 0)) { + err = -EIO; goto unpin_vma; + } /* !8-Byte aligned */ - err = __reloc_entry_gpu(eb, vma, offsets[1] * sizeof(u32), 1); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[1] * sizeof(u32), + 1)) { + err = -EIO; goto unpin_vma; + } /* Skip to the end of the cmd page */ i = PAGE_SIZE / sizeof(u32) - RELOC_TAIL - 1; @@ -54,9 +60,12 @@ static int __igt_gpu_reloc(struct i915_execbuffer *eb, eb->reloc_cache.rq_size += i; /* Force batch chaining */ - err = __reloc_entry_gpu(eb, vma, offsets[2] * sizeof(u32), 2); - if (err) + if (!__reloc_entry_gpu(eb, vma, + offsets[2] * sizeof(u32), + 2)) { + err = -EIO; goto unpin_vma; + } GEM_BUG_ON(!eb->reloc_cache.rq); rq = i915_request_get(eb->reloc_cache.rq); diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 24322ef08aa4..9eeaca957a7e 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -2060,6 +2060,14 @@ static inline void clear_ports(struct i915_request **ports, int count) memset_p((void **)ports, NULL, count); } +static inline void +copy_ports(struct i915_request **dst, struct i915_request **src, int count) +{ + /* A memcpy_p() would be very useful here! */ + while (count--) + WRITE_ONCE(*dst++, *src++); /* avoid write tearing */ +} + static void execlists_dequeue(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; @@ -2648,10 +2656,9 @@ static void process_csb(struct intel_engine_cs *engine) /* switch pending to inflight */ GEM_BUG_ON(!assert_pending_valid(execlists, "promote")); - memcpy(execlists->inflight, - execlists->pending, - execlists_num_ports(execlists) * - sizeof(*execlists->pending)); + copy_ports(execlists->inflight, + execlists->pending, + execlists_num_ports(execlists)); smp_wmb(); /* complete the seqlock */ WRITE_ONCE(execlists->active, execlists->inflight); diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index 8fa9b31a2484..f6d7e33c7099 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -368,6 +368,7 @@ void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu) static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, struct intel_vgpu_creation_params *param) { + struct drm_i915_private *dev_priv = gvt->gt->i915; struct intel_vgpu *vgpu; int ret; @@ -436,7 +437,10 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (ret) goto out_clean_sched_policy; - ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); + if (IS_BROADWELL(dev_priv)) + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); + else + ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c index d960d0be5bd2..839bd53df6e9 100644 --- a/drivers/gpu/drm/i915/i915_active.c +++ b/drivers/gpu/drm/i915/i915_active.c @@ -81,7 +81,7 @@ static void *active_debug_hint(void *addr) return (void *)ref->active ?: (void *)ref->retire ?: (void *)ref; } -static struct debug_obj_descr active_debug_desc = { +static const struct debug_obj_descr active_debug_desc = { .name = "i915_active", .debug_hint = active_debug_hint, }; diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 0b2fe55e6194..781a6783affe 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -388,17 +388,38 @@ static bool __request_in_flight(const struct i915_request *signal) * As we know that there are always preemption points between * requests, we know that only the currently executing request * may be still active even though we have cleared the flag. - * However, we can't rely on our tracking of ELSP[0] to known + * However, we can't rely on our tracking of ELSP[0] to know * which request is currently active and so maybe stuck, as * the tracking maybe an event behind. Instead assume that * if the context is still inflight, then it is still active * even if the active flag has been cleared. + * + * To further complicate matters, if there a pending promotion, the HW + * may either perform a context switch to the second inflight execlists, + * or it may switch to the pending set of execlists. In the case of the + * latter, it may send the ACK and we process the event copying the + * pending[] over top of inflight[], _overwriting_ our *active. Since + * this implies the HW is arbitrating and not struck in *active, we do + * not worry about complete accuracy, but we do require no read/write + * tearing of the pointer [the read of the pointer must be valid, even + * as the array is being overwritten, for which we require the writes + * to avoid tearing.] + * + * Note that the read of *execlists->active may race with the promotion + * of execlists->pending[] to execlists->inflight[], overwritting + * the value at *execlists->active. This is fine. The promotion implies + * that we received an ACK from the HW, and so the context is not + * stuck -- if we do not see ourselves in *active, the inflight status + * is valid. If instead we see ourselves being copied into *active, + * we are inflight and may signal the callback. */ if (!intel_context_inflight(signal->context)) return false; rcu_read_lock(); - for (port = __engine_active(signal->engine); (rq = *port); port++) { + for (port = __engine_active(signal->engine); + (rq = READ_ONCE(*port)); /* may race with promotion of pending[] */ + port++) { if (rq->context == signal->context) { inflight = i915_seqno_passed(rq->fence.seqno, signal->fence.seqno); diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 295b9829e2da..038d4c6884c5 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -34,7 +34,7 @@ static void *i915_sw_fence_debug_hint(void *addr) #ifdef CONFIG_DRM_I915_SW_FENCE_DEBUG_OBJECTS -static struct debug_obj_descr i915_sw_fence_debug_descr = { +static const struct debug_obj_descr i915_sw_fence_debug_descr = { .name = "i915_sw_fence", .debug_hint = i915_sw_fence_debug_hint, }; @@ -164,9 +164,13 @@ static void __i915_sw_fence_wake_up_all(struct i915_sw_fence *fence, do { list_for_each_entry_safe(pos, next, &x->head, entry) { - pos->func(pos, - TASK_NORMAL, fence->error, - &extra); + int wake_flags; + + wake_flags = fence->error; + if (pos->func == autoremove_wake_function) + wake_flags = 0; + + pos->func(pos, TASK_NORMAL, wake_flags, &extra); } if (list_empty(&extra)) diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c index f127e633f7ca..397c313a8b69 100644 --- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c +++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c @@ -118,11 +118,11 @@ static struct dev_pm_domain pm_domain = { struct drm_i915_private *mock_gem_device(void) { - struct drm_i915_private *i915; - struct pci_dev *pdev; #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - struct dev_iommu iommu; + static struct dev_iommu fake_iommu = { .priv = (void *)-1 }; #endif + struct drm_i915_private *i915; + struct pci_dev *pdev; int err; pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); @@ -141,10 +141,8 @@ struct drm_i915_private *mock_gem_device(void) dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); #if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU) - /* HACK HACK HACK to disable iommu for the fake device; force identity mapping */ - memset(&iommu, 0, sizeof(iommu)); - iommu.priv = (void *)-1; - pdev->dev.iommu = &iommu; + /* HACK to disable iommu for the fake device; force identity mapping */ + pdev->dev.iommu = &fake_iommu; #endif pci_set_drvdata(pdev, i915); diff --git a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c index ada990a7f911..b7074161ccf0 100644 --- a/drivers/gpu/drm/ingenic/ingenic-drm-drv.c +++ b/drivers/gpu/drm/ingenic/ingenic-drm-drv.c @@ -673,7 +673,7 @@ static void ingenic_drm_unbind_all(void *d) component_unbind_all(priv->dev, &priv->drm); } -static int ingenic_drm_bind(struct device *dev) +static int ingenic_drm_bind(struct device *dev, bool has_components) { struct platform_device *pdev = to_platform_device(dev); const struct jz_soc_info *soc_info; @@ -808,7 +808,7 @@ static int ingenic_drm_bind(struct device *dev) return ret; } - if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU)) { + if (IS_ENABLED(CONFIG_DRM_INGENIC_IPU) && has_components) { ret = component_bind_all(dev, drm); if (ret) { if (ret != -EPROBE_DEFER) @@ -939,6 +939,11 @@ err_pixclk_disable: return ret; } +static int ingenic_drm_bind_with_components(struct device *dev) +{ + return ingenic_drm_bind(dev, true); +} + static int compare_of(struct device *dev, void *data) { return dev->of_node == data; @@ -957,7 +962,7 @@ static void ingenic_drm_unbind(struct device *dev) } static const struct component_master_ops ingenic_master_ops = { - .bind = ingenic_drm_bind, + .bind = ingenic_drm_bind_with_components, .unbind = ingenic_drm_unbind, }; @@ -968,16 +973,15 @@ static int ingenic_drm_probe(struct platform_device *pdev) struct device_node *np; if (!IS_ENABLED(CONFIG_DRM_INGENIC_IPU)) - return ingenic_drm_bind(dev); + return ingenic_drm_bind(dev, false); /* IPU is at port address 8 */ np = of_graph_get_remote_node(dev->of_node, 8, 0); - if (!np) { - dev_err(dev, "Unable to get IPU node\n"); - return -EINVAL; - } + if (!np) + return ingenic_drm_bind(dev, false); drm_of_component_match_add(dev, &match, compare_of, np); + of_node_put(np); return component_master_add_with_match(dev, &ingenic_master_ops, match); } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 3fc5511330b9..4d29568be3f5 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -831,13 +831,19 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_crtc_index(&mtk_crtc->base)); mtk_crtc->cmdq_client = NULL; } - ret = of_property_read_u32_index(priv->mutex_node, - "mediatek,gce-events", - drm_crtc_index(&mtk_crtc->base), - &mtk_crtc->cmdq_event); - if (ret) - dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", - drm_crtc_index(&mtk_crtc->base)); + + if (mtk_crtc->cmdq_client) { + ret = of_property_read_u32_index(priv->mutex_node, + "mediatek,gce-events", + drm_crtc_index(&mtk_crtc->base), + &mtk_crtc->cmdq_event); + if (ret) { + dev_dbg(dev, "mtk_crtc %d failed to get mediatek,gce-events property\n", + drm_crtc_index(&mtk_crtc->base)); + cmdq_mbox_destroy(mtk_crtc->cmdq_client); + mtk_crtc->cmdq_client = NULL; + } + } #endif return 0; } diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c index 57c88de9a329..526648885b97 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c @@ -496,6 +496,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node, #if IS_REACHABLE(CONFIG_MTK_CMDQ) if (of_address_to_resource(node, 0, &res) != 0) { dev_err(dev, "Missing reg in %s node\n", node->full_name); + put_device(&larb_pdev->dev); return -EINVAL; } comp->regs_pa = res.start; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 040a8f393fe2..2d982740b1a4 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -27,7 +27,6 @@ #include "mtk_drm_crtc.h" #include "mtk_drm_ddp.h" -#include "mtk_drm_ddp.h" #include "mtk_drm_ddp_comp.h" #include "mtk_drm_drv.h" #include "mtk_drm_gem.h" @@ -165,7 +164,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = drmm_mode_config_init(drm); if (ret) - return ret; + goto put_mutex_dev; drm->mode_config.min_width = 64; drm->mode_config.min_height = 64; @@ -182,7 +181,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) ret = component_bind_all(drm->dev, drm); if (ret) - return ret; + goto put_mutex_dev; /* * We currently support two fixed data streams, each optional, @@ -229,7 +228,7 @@ static int mtk_drm_kms_init(struct drm_device *drm) } if (!dma_dev->dma_parms) { ret = -ENOMEM; - goto err_component_unbind; + goto put_dma_dev; } ret = dma_set_max_seg_size(dma_dev, (unsigned int)DMA_BIT_MASK(32)); @@ -256,9 +255,12 @@ static int mtk_drm_kms_init(struct drm_device *drm) err_unset_dma_parms: if (private->dma_parms_allocated) dma_dev->dma_parms = NULL; +put_dma_dev: + put_device(private->dma_dev); err_component_unbind: component_unbind_all(drm->dev, drm); - +put_mutex_dev: + put_device(private->mutex_dev); return ret; } @@ -544,8 +546,13 @@ err_pm: pm_runtime_disable(dev); err_node: of_node_put(private->mutex_node); - for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) + for (i = 0; i < DDP_COMPONENT_ID_MAX; i++) { of_node_put(private->comp_node[i]); + if (private->ddp_comp[i]) { + put_device(private->ddp_comp[i]->larb_dev); + private->ddp_comp[i] = NULL; + } + } return ret; } diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 16fd99dcdacf..80b7a082e874 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -466,14 +466,13 @@ static void mtk_dsi_config_vdo_timing(struct mtk_dsi *dsi) horizontal_sync_active_byte = (vm->hsync_len * dsi_tmp_buf_bpp - 10); if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) - horizontal_backporch_byte = - (vm->hback_porch * dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = vm->hback_porch * dsi_tmp_buf_bpp; else - horizontal_backporch_byte = ((vm->hback_porch + vm->hsync_len) * - dsi_tmp_buf_bpp - 10); + horizontal_backporch_byte = (vm->hback_porch + vm->hsync_len) * + dsi_tmp_buf_bpp; data_phy_cycles = timing->lpx + timing->da_hs_prepare + - timing->da_hs_zero + timing->da_hs_exit + 3; + timing->da_hs_zero + timing->da_hs_exit; if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO_BURST) { if ((vm->hfront_porch + vm->hback_porch) * dsi_tmp_buf_bpp > diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c index f2e9b429960b..a97725680d4e 100644 --- a/drivers/gpu/drm/mediatek/mtk_hdmi.c +++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c @@ -1507,25 +1507,30 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to get system configuration registers: %d\n", ret); - return ret; + goto put_device; } hdmi->sys_regmap = regmap; mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); hdmi->regs = devm_ioremap_resource(dev, mem); - if (IS_ERR(hdmi->regs)) - return PTR_ERR(hdmi->regs); + if (IS_ERR(hdmi->regs)) { + ret = PTR_ERR(hdmi->regs); + goto put_device; + } remote = of_graph_get_remote_node(np, 1, 0); - if (!remote) - return -EINVAL; + if (!remote) { + ret = -EINVAL; + goto put_device; + } if (!of_device_is_compatible(remote, "hdmi-connector")) { hdmi->next_bridge = of_drm_find_bridge(remote); if (!hdmi->next_bridge) { dev_err(dev, "Waiting for external bridge\n"); of_node_put(remote); - return -EPROBE_DEFER; + ret = -EPROBE_DEFER; + goto put_device; } } @@ -1534,7 +1539,8 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, dev_err(dev, "Failed to find ddc-i2c-bus node in %pOF\n", remote); of_node_put(remote); - return -EINVAL; + ret = -EINVAL; + goto put_device; } of_node_put(remote); @@ -1542,10 +1548,14 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi, of_node_put(i2c_np); if (!hdmi->ddc_adpt) { dev_err(dev, "Failed to get ddc i2c adapter by node\n"); - return -EINVAL; + ret = -EINVAL; + goto put_device; } return 0; +put_device: + put_device(hdmi->cec_dev); + return ret; } /* diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c index 6021f8d9efd1..48fa49f69d6d 100644 --- a/drivers/gpu/drm/msm/adreno/a2xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a2xx_gpu.c @@ -164,6 +164,11 @@ static int a2xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + gpu_write(gpu, REG_AXXX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* NOTE: PM4/micro-engine firmware registers look to be the same * for a2xx and a3xx.. we could possibly push that part down to * adreno_gpu base class. Or push both PM4 and PFP but diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c index 0a5ea9f56cb8..f6471145a7a6 100644 --- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c @@ -211,6 +211,16 @@ static int a3xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* + * Use the default ringbuffer size and block size but disable the RPTR + * shadow + */ + gpu_write(gpu, REG_AXXX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* Set the ringbuffer address */ + gpu_write(gpu, REG_AXXX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* setup access protection: */ gpu_write(gpu, REG_A3XX_CP_PROTECT_CTRL, 0x00000007); diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index b9b26b2bf9c5..954753600625 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -267,6 +267,16 @@ static int a4xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* + * Use the default ringbuffer size and block size but disable the RPTR + * shadow + */ + gpu_write(gpu, REG_A4XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + /* Set the ringbuffer address */ + gpu_write(gpu, REG_A4XX_CP_RB_BASE, lower_32_bits(gpu->rb[0]->iova)); + /* Load PM4: */ ptr = (uint32_t *)(adreno_gpu->fw[ADRENO_FW_PM4]->data); len = adreno_gpu->fw[ADRENO_FW_PM4]->size / 4; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 84a5d9c1f2a2..91726da82ed6 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -703,8 +703,6 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; - a5xx_preempt_hw_init(gpu); - if (!adreno_is_a510(adreno_gpu)) a5xx_gpmu_ucode_init(gpu); @@ -712,6 +710,15 @@ static int a5xx_hw_init(struct msm_gpu *gpu) if (ret) return ret; + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, + gpu->rb[0]->iova); + + gpu_write(gpu, REG_A5XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + + a5xx_preempt_hw_init(gpu); + /* Disable the interrupts through the initial bringup stage */ gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK, A5XX_INT_MASK); @@ -1511,7 +1518,8 @@ struct msm_gpu *a5xx_gpu_init(struct drm_device *dev) check_speed_bin(&pdev->dev); - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 4); + /* Restricting nr_rings to 1 to temporarily disable preemption */ + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a5xx_destroy(&(a5xx_gpu->base.base)); return ERR_PTR(ret); diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index 54868d4e3958..1e5b1a15a70f 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -31,6 +31,7 @@ struct a5xx_gpu { struct msm_ringbuffer *next_ring; struct drm_gem_object *preempt_bo[MSM_GPU_MAX_RINGS]; + struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS]; struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS]; uint64_t preempt_iova[MSM_GPU_MAX_RINGS]; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 9cf9353a7ff1..9f3fe177b00e 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -226,19 +226,31 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, struct adreno_gpu *adreno_gpu = &a5xx_gpu->base; struct msm_gpu *gpu = &adreno_gpu->base; struct a5xx_preempt_record *ptr; - struct drm_gem_object *bo = NULL; - u64 iova = 0; + void *counters; + struct drm_gem_object *bo = NULL, *counters_bo = NULL; + u64 iova = 0, counters_iova = 0; ptr = msm_gem_kernel_new(gpu->dev, A5XX_PREEMPT_RECORD_SIZE + A5XX_PREEMPT_COUNTER_SIZE, - MSM_BO_UNCACHED, gpu->aspace, &bo, &iova); + MSM_BO_UNCACHED | MSM_BO_MAP_PRIV, gpu->aspace, &bo, &iova); if (IS_ERR(ptr)) return PTR_ERR(ptr); + /* The buffer to store counters needs to be unprivileged */ + counters = msm_gem_kernel_new(gpu->dev, + A5XX_PREEMPT_COUNTER_SIZE, + MSM_BO_UNCACHED, gpu->aspace, &counters_bo, &counters_iova); + if (IS_ERR(counters)) { + msm_gem_kernel_put(bo, gpu->aspace, true); + return PTR_ERR(counters); + } + msm_gem_object_set_name(bo, "preempt"); + msm_gem_object_set_name(counters_bo, "preempt_counters"); a5xx_gpu->preempt_bo[ring->id] = bo; + a5xx_gpu->preempt_counters_bo[ring->id] = counters_bo; a5xx_gpu->preempt_iova[ring->id] = iova; a5xx_gpu->preempt[ring->id] = ptr; @@ -249,7 +261,7 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu, ptr->data = 0; ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT; ptr->rptr_addr = rbmemptr(ring, rptr); - ptr->counter = iova + A5XX_PREEMPT_RECORD_SIZE; + ptr->counter = counters_iova; return 0; } @@ -260,8 +272,11 @@ void a5xx_preempt_fini(struct msm_gpu *gpu) struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); int i; - for (i = 0; i < gpu->nr_rings; i++) + for (i = 0; i < gpu->nr_rings; i++) { msm_gem_kernel_put(a5xx_gpu->preempt_bo[i], gpu->aspace, true); + msm_gem_kernel_put(a5xx_gpu->preempt_counters_bo[i], + gpu->aspace, true); + } } void a5xx_preempt_init(struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 3966abd523cc..66a95e22b7b3 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -678,7 +678,8 @@ static int a6xx_hw_init(struct msm_gpu *gpu) A6XX_PROTECT_RDONLY(0x980, 0x4)); gpu_write(gpu, REG_A6XX_CP_PROTECT(25), A6XX_PROTECT_RW(0xa630, 0x0)); - if (adreno_is_a650(adreno_gpu)) { + /* Enable expanded apriv for targets that support it */ + if (gpu->hw_apriv) { gpu_write(gpu, REG_A6XX_CP_APRIV_CNTL, (1 << 6) | (1 << 5) | (1 << 3) | (1 << 2) | (1 << 1)); } @@ -694,6 +695,13 @@ static int a6xx_hw_init(struct msm_gpu *gpu) if (ret) goto out; + /* Set the ringbuffer address */ + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, + gpu->rb[0]->iova); + + gpu_write(gpu, REG_A6XX_CP_RB_CNTL, + MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE); + /* Always come up on rb 0 */ a6xx_gpu->cur_ring = gpu->rb[0]; @@ -1056,6 +1064,9 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = NULL; adreno_gpu->reg_offsets = a6xx_register_offsets; + if (adreno_is_a650(adreno_gpu)) + adreno_gpu->base.hw_apriv = true; + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 288141fe4c58..862dd35b27d3 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -400,26 +400,6 @@ int adreno_hw_init(struct msm_gpu *gpu) ring->memptrs->rptr = 0; } - /* - * Setup REG_CP_RB_CNTL. The same value is used across targets (with - * the excpetion of A430 that disables the RPTR shadow) - the cacluation - * for the ringbuffer size and block size is moved to msm_gpu.h for the - * pre-processor to deal with and the A430 variant is ORed in here - */ - adreno_gpu_write(adreno_gpu, REG_ADRENO_CP_RB_CNTL, - MSM_GPU_RB_CNTL_DEFAULT | - (adreno_is_a430(adreno_gpu) ? AXXX_CP_RB_CNTL_NO_UPDATE : 0)); - - /* Setup ringbuffer address - use ringbuffer[0] for GPU init */ - adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_BASE, - REG_ADRENO_CP_RB_BASE_HI, gpu->rb[0]->iova); - - if (!adreno_is_a430(adreno_gpu)) { - adreno_gpu_write64(adreno_gpu, REG_ADRENO_CP_RB_RPTR_ADDR, - REG_ADRENO_CP_RB_RPTR_ADDR_HI, - rbmemptr(gpu->rb[0], rptr)); - } - return 0; } @@ -427,11 +407,8 @@ int adreno_hw_init(struct msm_gpu *gpu) static uint32_t get_rptr(struct adreno_gpu *adreno_gpu, struct msm_ringbuffer *ring) { - if (adreno_is_a430(adreno_gpu)) - return ring->memptrs->rptr = adreno_gpu_read( - adreno_gpu, REG_ADRENO_CP_RB_RPTR); - else - return ring->memptrs->rptr; + return ring->memptrs->rptr = adreno_gpu_read( + adreno_gpu, REG_ADRENO_CP_RB_RPTR); } struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index d5645472b25d..57ddc9438351 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -908,7 +908,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, memptrs = msm_gem_kernel_new(drm, sizeof(struct msm_rbmemptrs) * nr_rings, - MSM_BO_UNCACHED, gpu->aspace, &gpu->memptrs_bo, + check_apriv(gpu, MSM_BO_UNCACHED), gpu->aspace, &gpu->memptrs_bo, &memptrs_iova); if (IS_ERR(memptrs)) { diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 0db117a7339b..37cffac4cbe3 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -15,6 +15,7 @@ #include "msm_drv.h" #include "msm_fence.h" #include "msm_ringbuffer.h" +#include "msm_gem.h" struct msm_gem_submit; struct msm_gpu_perfcntr; @@ -139,6 +140,8 @@ struct msm_gpu { } devfreq; struct msm_gpu_state *crashstate; + /* True if the hardware supports expanded apriv (a650 and newer) */ + bool hw_apriv; }; /* It turns out that all targets use the same ringbuffer size */ @@ -327,4 +330,12 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu) mutex_unlock(&gpu->dev->struct_mutex); } +/* + * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can + * support expanded privileges + */ +#define check_apriv(gpu, flags) \ + (((gpu)->hw_apriv ? MSM_BO_MAP_PRIV : 0) | (flags)) + + #endif /* __MSM_GPU_H__ */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c index 39ecb5a18431..935bf9b1d941 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.c +++ b/drivers/gpu/drm/msm/msm_ringbuffer.c @@ -27,8 +27,8 @@ struct msm_ringbuffer *msm_ringbuffer_new(struct msm_gpu *gpu, int id, ring->id = id; ring->start = msm_gem_kernel_new(gpu->dev, MSM_GPU_RINGBUFFER_SZ, - MSM_BO_WC | MSM_BO_GPU_READONLY, gpu->aspace, &ring->bo, - &ring->iova); + check_apriv(gpu, MSM_BO_WC | MSM_BO_GPU_READONLY), + gpu->aspace, &ring->bo, &ring->iova); if (IS_ERR(ring->start)) { ret = PTR_ERR(ring->start); diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index ad1f09a143aa..248edf69e168 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -50,7 +50,10 @@ core507d_update(struct nv50_core *core, u32 *interlock, bool ntfy) interlock[NV50_DISP_INTERLOCK_OVLY] | NVDEF(NV507D, UPDATE, NOT_DRIVER_FRIENDLY, FALSE) | NVDEF(NV507D, UPDATE, NOT_DRIVER_UNFRIENDLY, FALSE) | - NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE)); + NVDEF(NV507D, UPDATE, INHIBIT_INTERRUPTS, FALSE), + + SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE)); return PUSH_KICK(push); } diff --git a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c index 9afe9a87bde0..814e5bd97446 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/crcc37d.c @@ -6,7 +6,7 @@ #include "disp.h" #include "head.h" -#include <nvif/push507c.h> +#include <nvif/pushc37b.h> #include <nvhw/class/clc37d.h> diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index e7874877da85..1ed242070001 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -257,6 +257,12 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, dmac->push->end = dmac->push->bgn; dmac->max = 0x1000/4 - 1; + /* EVO channels are affected by a HW bug where the last 12 DWORDs + * of the push buffer aren't able to be used safely. + */ + if (disp->oclass < GV100_DISP) + dmac->max -= 12; + args->pushbuf = nvif_handle(&dmac->_push.mem.object); ret = nv50_chan_create(device, disp, oclass, head, data, size, diff --git a/drivers/gpu/drm/nouveau/include/nvif/push507c.h b/drivers/gpu/drm/nouveau/include/nvif/push507c.h index 889467f13fd9..7917bead4845 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/push507c.h +++ b/drivers/gpu/drm/nouveau/include/nvif/push507c.h @@ -20,6 +20,6 @@ PUSH_ASSERT(!((o) & ~DRF_SMASK(NV507C_DMA_JUMP_OFFSET)), "offset"); \ PUSH_DATA__((p), NVDEF(NV507C, DMA, OPCODE, JUMP) | \ NVVAL(NV507C, DMA, JUMP_OFFSET, (o) >> 2), \ - "jump 0x%08x - %s", (u32)(o), __func__); \ + " jump 0x%08x - %s", (u32)(o), __func__); \ } while(0) #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c index b1bb542d3115..e5fae57fffbd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.c +++ b/drivers/gpu/drm/nouveau/nouveau_mem.c @@ -176,6 +176,8 @@ void nouveau_mem_del(struct ttm_mem_reg *reg) { struct nouveau_mem *mem = nouveau_mem(reg); + if (!mem) + return; nouveau_mem_fini(mem); kfree(reg->mm_node); reg->mm_node = NULL; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index 9f4ac2672cf2..dcb70677d0ac 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -3149,6 +3149,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func, case 0x168: device->chip = &nv168_chipset; break; default: nvdev_error(device, "unknown chipset (%08x)\n", boot0); + ret = -ENODEV; goto done; } diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 072ea113e6be..ed5d86617802 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -589,8 +589,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine, /* We can't have an alpha plane at the lowest position */ if (!backend->quirks->supports_lowest_plane_alpha && - (plane_states[0]->fb->format->has_alpha || - (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE))) + (plane_states[0]->alpha != DRM_BLEND_ALPHA_OPAQUE)) return -EINVAL; for (i = 1; i < num_planes; i++) { @@ -995,7 +994,6 @@ static const struct sun4i_backend_quirks sun6i_backend_quirks = { static const struct sun4i_backend_quirks sun7i_backend_quirks = { .needs_output_muxing = true, - .supports_lowest_plane_alpha = true, }; static const struct sun4i_backend_quirks sun8i_a33_backend_quirks = { diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index ced9a8287dd8..e40c542254f6 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -1433,14 +1433,18 @@ static int sun8i_r40_tcon_tv_set_mux(struct sun4i_tcon *tcon, if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) && encoder->encoder_type == DRM_MODE_ENCODER_TMDS) { ret = sun8i_tcon_top_set_hdmi_src(&pdev->dev, id); - if (ret) + if (ret) { + put_device(&pdev->dev); return ret; + } } if (IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP)) { ret = sun8i_tcon_top_de_config(&pdev->dev, tcon->id, id); - if (ret) + if (ret) { + put_device(&pdev->dev); return ret; + } } return 0; diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c index 7f13f4d715bf..de8a11abd66a 100644 --- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c +++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c @@ -889,7 +889,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi, regmap_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(0), sun6i_dsi_dcs_build_pkt_hdr(dsi, msg)); - bounce = kzalloc(msg->tx_len + sizeof(crc), GFP_KERNEL); + bounce = kzalloc(ALIGN(msg->tx_len + sizeof(crc), 4), GFP_KERNEL); if (!bounce) return -ENOMEM; @@ -900,7 +900,7 @@ static int sun6i_dsi_dcs_write_long(struct sun6i_dsi *dsi, memcpy((u8 *)bounce + msg->tx_len, &crc, sizeof(crc)); len += sizeof(crc); - regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, len); + regmap_bulk_write(dsi->regs, SUN6I_DSI_CMD_TX_REG(1), bounce, DIV_ROUND_UP(len, 4)); regmap_write(dsi->regs, SUN6I_DSI_CMD_CTL_REG, len + 4 - 1); kfree(bounce); diff --git a/drivers/gpu/drm/sun4i/sun8i_csc.h b/drivers/gpu/drm/sun4i/sun8i_csc.h index f42441b1b14d..a55a38ad849c 100644 --- a/drivers/gpu/drm/sun4i/sun8i_csc.h +++ b/drivers/gpu/drm/sun4i/sun8i_csc.h @@ -12,7 +12,7 @@ struct sun8i_mixer; /* VI channel CSC units offsets */ #define CCSC00_OFFSET 0xAA050 -#define CCSC01_OFFSET 0xFA000 +#define CCSC01_OFFSET 0xFA050 #define CCSC10_OFFSET 0xA0000 #define CCSC11_OFFSET 0xF0000 diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c index cc4fb916318f..c3304028e3dc 100644 --- a/drivers/gpu/drm/sun4i/sun8i_mixer.c +++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c @@ -307,7 +307,7 @@ static struct regmap_config sun8i_mixer_regmap_config = { .reg_bits = 32, .val_bits = 32, .reg_stride = 4, - .max_register = 0xbfffc, /* guessed */ + .max_register = 0xffffc, /* guessed */ }; static int sun8i_mixer_of_get_id(struct device_node *node) diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c index 22c8c5375d0d..c0147af6a840 100644 --- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c +++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c @@ -211,7 +211,7 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel, return 0; } -static bool sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format) +static u32 sun8i_vi_layer_get_csc_mode(const struct drm_format_info *format) { if (!format->is_yuv) return SUN8I_CSC_MODE_OFF; diff --git a/drivers/gpu/drm/tve200/tve200_display.c b/drivers/gpu/drm/tve200/tve200_display.c index d733bbc4ac0e..17ff24d999d1 100644 --- a/drivers/gpu/drm/tve200/tve200_display.c +++ b/drivers/gpu/drm/tve200/tve200_display.c @@ -14,6 +14,7 @@ #include <linux/version.h> #include <linux/dma-buf.h> #include <linux/of_graph.h> +#include <linux/delay.h> #include <drm/drm_fb_cma_helper.h> #include <drm/drm_fourcc.h> @@ -130,9 +131,25 @@ static void tve200_display_enable(struct drm_simple_display_pipe *pipe, struct drm_connector *connector = priv->connector; u32 format = fb->format->format; u32 ctrl1 = 0; + int retries; clk_prepare_enable(priv->clk); + /* Reset the TVE200 and wait for it to come back online */ + writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4); + for (retries = 0; retries < 5; retries++) { + usleep_range(30000, 50000); + if (readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) + continue; + else + break; + } + if (retries == 5 && + readl(priv->regs + TVE200_CTRL_4) & TVE200_CTRL_4_RESET) { + dev_err(drm->dev, "can't get hardware out of reset\n"); + return; + } + /* Function 1 */ ctrl1 |= TVE200_CTRL_CSMODE; /* Interlace mode for CCIR656: parameterize? */ @@ -230,8 +247,9 @@ static void tve200_display_disable(struct drm_simple_display_pipe *pipe) drm_crtc_vblank_off(crtc); - /* Disable and Power Down */ + /* Disable put into reset and Power Down */ writel(0, priv->regs + TVE200_CTRL); + writel(TVE200_CTRL_4_RESET, priv->regs + TVE200_CTRL_4); clk_disable_unprepare(priv->clk); } @@ -279,6 +297,8 @@ static int tve200_display_enable_vblank(struct drm_simple_display_pipe *pipe) struct drm_device *drm = crtc->dev; struct tve200_drm_dev_private *priv = drm->dev_private; + /* Clear any IRQs and enable */ + writel(0xFF, priv->regs + TVE200_INT_CLR); writel(TVE200_INT_V_STATUS, priv->regs + TVE200_INT_EN); return 0; } diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index 15a11cd4de25..6339c6f0f571 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -1117,6 +1117,7 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *hdmi) card->num_links = 1; card->name = "vc4-hdmi"; card->dev = dev; + card->owner = THIS_MODULE; /* * Be careful, snd_soc_register_card() calls dev_set_drvdata() and diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c index af55b334be2f..afd0f9200f90 100644 --- a/drivers/gpu/drm/virtio/virtgpu_display.c +++ b/drivers/gpu/drm/virtio/virtgpu_display.c @@ -97,9 +97,6 @@ static void virtio_gpu_crtc_mode_set_nofb(struct drm_crtc *crtc) static void virtio_gpu_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { - struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc); - - output->enabled = true; } static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc, @@ -111,7 +108,6 @@ static void virtio_gpu_crtc_atomic_disable(struct drm_crtc *crtc, virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, 0, 0, 0, 0); virtio_gpu_notify(vgdev); - output->enabled = false; } static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc, @@ -123,6 +119,17 @@ static int virtio_gpu_crtc_atomic_check(struct drm_crtc *crtc, static void virtio_gpu_crtc_atomic_flush(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { + struct virtio_gpu_output *output = drm_crtc_to_virtio_gpu_output(crtc); + + /* + * virtio-gpu can't do modeset and plane update operations + * independent from each other. So the actual modeset happens + * in the plane update callback, and here we just check + * whenever we must force the modeset. + */ + if (drm_atomic_crtc_needs_modeset(crtc->state)) { + output->needs_modeset = true; + } } static const struct drm_crtc_helper_funcs virtio_gpu_crtc_helper_funcs = { diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 9ff9f4ac0522..fbc04272db4f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -137,7 +137,7 @@ struct virtio_gpu_output { struct edid *edid; int cur_x; int cur_y; - bool enabled; + bool needs_modeset; }; #define drm_crtc_to_virtio_gpu_output(x) \ container_of(x, struct virtio_gpu_output, crtc) diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c index e83651b7747d..842f8b61aa89 100644 --- a/drivers/gpu/drm/virtio/virtgpu_object.c +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -151,7 +151,13 @@ static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, if (ret < 0) return -EINVAL; - shmem->pages = drm_gem_shmem_get_pages_sgt(&bo->base.base); + /* + * virtio_gpu uses drm_gem_shmem_get_sg_table instead of + * drm_gem_shmem_get_pages_sgt because virtio has it's own set of + * dma-ops. This is discouraged for other drivers, but should be fine + * since virtio_gpu doesn't support dma-buf import from other devices. + */ + shmem->pages = drm_gem_shmem_get_sg_table(&bo->base.base); if (!shmem->pages) { drm_gem_shmem_unpin(&bo->base.base); return -EINVAL; diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c index 52d24179bcec..6a311cd93440 100644 --- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -142,7 +142,7 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane, if (WARN_ON(!output)) return; - if (!plane->state->fb || !output->enabled) { + if (!plane->state->fb || !output->crtc.state->active) { DRM_DEBUG("nofb\n"); virtio_gpu_cmd_set_scanout(vgdev, output->index, 0, plane->state->src_w >> 16, @@ -163,7 +163,9 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane, plane->state->src_w != old_state->src_w || plane->state->src_h != old_state->src_h || plane->state->src_x != old_state->src_x || - plane->state->src_y != old_state->src_y) { + plane->state->src_y != old_state->src_y || + output->needs_modeset) { + output->needs_modeset = false; DRM_DEBUG("handle 0x%x, crtc %dx%d+%d+%d, src %dx%d+%d+%d\n", bo->hw_res_handle, plane->state->crtc_w, plane->state->crtc_h, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c index 4a76fc7114ad..f8bdd4ea294a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c @@ -55,7 +55,7 @@ static int vmw_gmrid_man_get_node(struct ttm_mem_type_manager *man, id = ida_alloc_max(&gman->gmr_ida, gman->max_gmr_ids - 1, GFP_KERNEL); if (id < 0) - return (id != -ENOMEM ? 0 : id); + return id; spin_lock(&gman->lock); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c index b7c816ba7166..c8b9335bccd8 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_thp.c @@ -95,7 +95,7 @@ found_unlock: mem->start = node->start; } - return 0; + return ret; } diff --git a/drivers/gpu/drm/xen/xen_drm_front_gem.c b/drivers/gpu/drm/xen/xen_drm_front_gem.c index 39ff95b75357..534daf37c97e 100644 --- a/drivers/gpu/drm/xen/xen_drm_front_gem.c +++ b/drivers/gpu/drm/xen/xen_drm_front_gem.c @@ -18,6 +18,7 @@ #include <drm/drm_probe_helper.h> #include <xen/balloon.h> +#include <xen/xen.h> #include "xen_drm_front.h" #include "xen_drm_front_gem.h" @@ -99,8 +100,8 @@ static struct xen_gem_object *gem_create(struct drm_device *dev, size_t size) * allocate ballooned pages which will be used to map * grant references provided by the backend */ - ret = alloc_xenballooned_pages(xen_obj->num_pages, - xen_obj->pages); + ret = xen_alloc_unpopulated_pages(xen_obj->num_pages, + xen_obj->pages); if (ret < 0) { DRM_ERROR("Cannot allocate %zu ballooned pages: %d\n", xen_obj->num_pages, ret); @@ -152,8 +153,8 @@ void xen_drm_front_gem_free_object_unlocked(struct drm_gem_object *gem_obj) } else { if (xen_obj->pages) { if (xen_obj->be_alloc) { - free_xenballooned_pages(xen_obj->num_pages, - xen_obj->pages); + xen_free_unpopulated_pages(xen_obj->num_pages, + xen_obj->pages); gem_free_pages_array(xen_obj); } else { drm_gem_put_pages(&xen_obj->base, diff --git a/drivers/gpu/drm/xlnx/Kconfig b/drivers/gpu/drm/xlnx/Kconfig index aa6cd889bd11..b52c6cdfc0b8 100644 --- a/drivers/gpu/drm/xlnx/Kconfig +++ b/drivers/gpu/drm/xlnx/Kconfig @@ -2,6 +2,7 @@ config DRM_ZYNQMP_DPSUB tristate "ZynqMP DisplayPort Controller Driver" depends on ARCH_ZYNQMP || COMPILE_TEST depends on COMMON_CLK && DRM && OF + depends on DMADEVICES select DMA_ENGINE select DRM_GEM_CMA_HELPER select DRM_KMS_CMA_HELPER |