diff options
Diffstat (limited to 'drivers/gpu')
148 files changed, 1672 insertions, 969 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index e8b41756c9f9..e3783f5a459d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -80,6 +80,7 @@ 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/green_sardine_gpu_info.bin"); #define AMDGPU_RESUME_MS 2000 @@ -239,9 +240,11 @@ bool amdgpu_device_supports_baco(struct drm_device *dev) return amdgpu_asic_supports_baco(adev); } +/* + * VRAM access helper functions + */ + /** - * VRAM access helper functions. - * * amdgpu_device_vram_access - read/write a buffer in vram * * @adev: amdgpu_device pointer @@ -705,7 +708,7 @@ void amdgpu_device_indirect_wreg64(struct amdgpu_device *adev, /** * amdgpu_invalid_rreg - dummy reg read function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * * Dummy register read function. Used for register blocks @@ -722,7 +725,7 @@ static uint32_t amdgpu_invalid_rreg(struct amdgpu_device *adev, uint32_t reg) /** * amdgpu_invalid_wreg - dummy reg write function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * @v: value to write to the register * @@ -739,7 +742,7 @@ static void amdgpu_invalid_wreg(struct amdgpu_device *adev, uint32_t reg, uint32 /** * amdgpu_invalid_rreg64 - dummy 64 bit reg read function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * * Dummy register read function. Used for register blocks @@ -756,7 +759,7 @@ static uint64_t amdgpu_invalid_rreg64(struct amdgpu_device *adev, uint32_t reg) /** * amdgpu_invalid_wreg64 - dummy reg write function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @reg: offset of register * @v: value to write to the register * @@ -773,7 +776,7 @@ static void amdgpu_invalid_wreg64(struct amdgpu_device *adev, uint32_t reg, uint /** * amdgpu_block_invalid_rreg - dummy reg read function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @block: offset of instance * @reg: offset of register * @@ -793,7 +796,7 @@ static uint32_t amdgpu_block_invalid_rreg(struct amdgpu_device *adev, /** * amdgpu_block_invalid_wreg - dummy reg write function * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @block: offset of instance * @reg: offset of register * @v: value to write to the register @@ -813,7 +816,7 @@ static void amdgpu_block_invalid_wreg(struct amdgpu_device *adev, /** * amdgpu_device_asic_init - Wrapper for atom asic_init * - * @dev: drm_device pointer + * @adev: amdgpu_device pointer * * Does any asic specific work and then calls atom asic init. */ @@ -827,7 +830,7 @@ static int amdgpu_device_asic_init(struct amdgpu_device *adev) /** * amdgpu_device_vram_scratch_init - allocate the VRAM scratch page * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * Allocates a scratch page of VRAM for use by various things in the * driver. @@ -844,7 +847,7 @@ static int amdgpu_device_vram_scratch_init(struct amdgpu_device *adev) /** * amdgpu_device_vram_scratch_fini - Free the VRAM scratch page * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * Frees the VRAM scratch page. */ @@ -1803,7 +1806,10 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; case CHIP_NAVI10: chip_name = "navi10"; @@ -3011,7 +3017,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type) /** * amdgpu_device_has_dc_support - check if dc is supported * - * @adev: amdgpu_device_pointer + * @adev: amdgpu_device pointer * * Returns true for supported, false for not supported */ @@ -4045,7 +4051,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) /** * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @from_hypervisor: request from hypervisor * * do VF FLR and reinitialize Asic @@ -4100,7 +4106,7 @@ error: /** * amdgpu_device_has_job_running - check if there is any job in mirror list * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * check if there is any job in mirror list */ @@ -4128,7 +4134,7 @@ bool amdgpu_device_has_job_running(struct amdgpu_device *adev) /** * amdgpu_device_should_recover_gpu - check if we should try GPU recovery * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * * Check amdgpu_gpu_recovery and SRIOV status to see if we should try to recover * a hung GPU. @@ -4477,7 +4483,7 @@ static int amdgpu_device_suspend_display_audio(struct amdgpu_device *adev) /** * amdgpu_device_gpu_recover - reset the asic and recover scheduler * - * @adev: amdgpu device pointer + * @adev: amdgpu_device pointer * @job: which job trigger hang * * Attempt to reset the GPU if it has hung (all asics). @@ -4497,7 +4503,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, bool need_emergency_restart = false; bool audio_suspended = false; - /** + /* * Special case: RAS triggered and full reset isn't supported */ need_emergency_restart = amdgpu_ras_need_emergency_restart(adev); @@ -4625,7 +4631,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, retry: /* Rest of adevs pre asic reset from XGMI hive. */ list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) { r = amdgpu_device_pre_asic_reset(tmp_adev, - NULL, + (tmp_adev == adev) ? job : NULL, &need_full_reset); /*TODO Should we stop ?*/ if (r) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index c241317edee7..8e988f07f085 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -1055,10 +1055,10 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x15dd, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, {0x1002, 0x15d8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RAVEN|AMD_IS_APU}, /* Arcturus */ - {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, - {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS|AMD_EXP_HW_SUPPORT}, + {0x1002, 0x738C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7388, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x738E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, + {0x1002, 0x7390, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_ARCTURUS}, /* Navi10 */ {0x1002, 0x7310, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x7312, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, @@ -1066,6 +1066,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x7319, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, + {0x1002, 0x731E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, {0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10}, /* Navi14 */ {0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14}, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index aa7f230c71bf..7e8265da9f25 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -596,6 +596,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, struct ww_acquire_ctx ticket; struct list_head list, duplicates; uint64_t va_flags; + uint64_t vm_size; int r = 0; if (args->va_address < AMDGPU_VA_RESERVED_SIZE) { @@ -616,6 +617,15 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, args->va_address &= AMDGPU_GMC_HOLE_MASK; + vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE; + vm_size -= AMDGPU_VA_RESERVED_SIZE; + if (args->va_address + args->map_size > vm_size) { + dev_dbg(&dev->pdev->dev, + "va_address 0x%llx is in top reserved area 0x%llx\n", + args->va_address + args->map_size, vm_size); + return -EINVAL; + } + if ((args->flags & ~valid_flags) && (args->flags & ~prt_flags)) { dev_dbg(&dev->pdev->dev, "invalid flags combination 0x%08X\n", args->flags); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c index f203e4a6a3f2..731f3aa2e6ba 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c @@ -81,8 +81,8 @@ static const struct ttm_resource_manager_func amdgpu_gtt_mgr_func; /** * amdgpu_gtt_mgr_init - init GTT manager and DRM MM * - * @man: TTM memory type manager - * @p_size: maximum size of GTT + * @adev: amdgpu_device pointer + * @gtt_size: maximum size of GTT * * Allocate and initialize the GTT manager. */ @@ -123,7 +123,7 @@ int amdgpu_gtt_mgr_init(struct amdgpu_device *adev, uint64_t gtt_size) /** * amdgpu_gtt_mgr_fini - free and destroy GTT manager * - * @man: TTM memory type manager + * @adev: amdgpu_device pointer * * Destroy and free the GTT manager, returns -EBUSY if ranges are still * allocated inside it. diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 18be544d8c1e..a6dbe4b83533 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -208,7 +208,8 @@ static int psp_sw_fini(void *handle) adev->psp.ta_fw = NULL; } - if (adev->asic_type == CHIP_NAVI10) + if (adev->asic_type == CHIP_NAVI10 || + adev->asic_type == CHIP_SIENNA_CICHLID) psp_sysfs_fini(adev); return 0; @@ -1750,6 +1751,12 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode, case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM: *type = GFX_FW_TYPE_RLC_RESTORE_LIST_SRM_MEM; break; + case AMDGPU_UCODE_ID_RLC_IRAM: + *type = GFX_FW_TYPE_RLC_IRAM; + break; + case AMDGPU_UCODE_ID_RLC_DRAM: + *type = GFX_FW_TYPE_RLC_DRAM_BOOT; + break; case AMDGPU_UCODE_ID_SMC: *type = GFX_FW_TYPE_SMU; break; @@ -2517,6 +2524,7 @@ int parse_ta_bin_descriptor(struct psp_context *psp, psp->asd_feature_version = le32_to_cpu(desc->fw_version); psp->asd_ucode_size = le32_to_cpu(desc->size_bytes); psp->asd_start_addr = ucode_start_addr; + psp->asd_fw = psp->ta_fw; break; case TA_FW_TYPE_PSP_XGMI: psp->ta_xgmi_ucode_version = le32_to_cpu(desc->fw_version); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 8bf6a7c056bc..4e36551ab50b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1986,7 +1986,8 @@ static int amdgpu_ras_check_asic_type(struct amdgpu_device *adev) { if (adev->asic_type != CHIP_VEGA10 && adev->asic_type != CHIP_VEGA20 && - adev->asic_type != CHIP_ARCTURUS) + adev->asic_type != CHIP_ARCTURUS && + adev->asic_type != CHIP_SIENNA_CICHLID) return 1; else return 0; @@ -2030,7 +2031,6 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev, *supported = amdgpu_ras_enable == 0 ? 0 : *hw_supported & amdgpu_ras_mask; - adev->ras_features = *supported; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h index 60bb3e8b3118..aeaaae713c59 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h @@ -168,12 +168,16 @@ struct amdgpu_rlc { u32 save_restore_list_cntl_size_bytes; u32 save_restore_list_gpm_size_bytes; u32 save_restore_list_srm_size_bytes; + u32 rlc_iram_ucode_size_bytes; + u32 rlc_dram_ucode_size_bytes; u32 *register_list_format; u32 *register_restore; u8 *save_restore_list_cntl; u8 *save_restore_list_gpm; u8 *save_restore_list_srm; + u8 *rlc_iram_ucode; + u8 *rlc_dram_ucode; bool is_rlc_v2_1; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c index 55fe19a2f332..b313ce4c3e97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c @@ -500,6 +500,8 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev, ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL && ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM && ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM && + ucode->ucode_id != AMDGPU_UCODE_ID_RLC_IRAM && + ucode->ucode_id != AMDGPU_UCODE_ID_RLC_DRAM && ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_ERAM && ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV && ucode->ucode_id != AMDGPU_UCODE_ID_DMCUB)) { @@ -556,6 +558,14 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev, ucode->ucode_size = adev->gfx.rlc.save_restore_list_srm_size_bytes; memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_srm, ucode->ucode_size); + } else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_IRAM) { + ucode->ucode_size = adev->gfx.rlc.rlc_iram_ucode_size_bytes; + memcpy(ucode->kaddr, adev->gfx.rlc.rlc_iram_ucode, + ucode->ucode_size); + } else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_DRAM) { + ucode->ucode_size = adev->gfx.rlc.rlc_dram_ucode_size_bytes; + memcpy(ucode->kaddr, adev->gfx.rlc.rlc_dram_ucode, + ucode->ucode_size); } else if (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MES) { ucode->ucode_size = le32_to_cpu(mes_hdr->mes_ucode_size_bytes); memcpy(ucode->kaddr, (void *)((uint8_t *)adev->mes.fw->data + diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h index 3c23c6293ff9..0e43b46d3ab5 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h @@ -222,6 +222,15 @@ struct rlc_firmware_header_v2_1 { uint32_t save_restore_list_srm_offset_bytes; }; +/* version_major=2, version_minor=1 */ +struct rlc_firmware_header_v2_2 { + struct rlc_firmware_header_v2_1 v2_1; + uint32_t rlc_iram_ucode_size_bytes; + uint32_t rlc_iram_ucode_offset_bytes; + uint32_t rlc_dram_ucode_size_bytes; + uint32_t rlc_dram_ucode_offset_bytes; +}; + /* version_major=1, version_minor=0 */ struct sdma_firmware_header_v1_0 { struct common_firmware_header header; @@ -339,6 +348,8 @@ enum AMDGPU_UCODE_ID { AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM, AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM, + AMDGPU_UCODE_ID_RLC_IRAM, + AMDGPU_UCODE_ID_RLC_DRAM, AMDGPU_UCODE_ID_RLC_G, AMDGPU_UCODE_ID_STORAGE, AMDGPU_UCODE_ID_SMC, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 495c3d7bb2b2..a563328e3dae 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -39,6 +39,7 @@ #define FIRMWARE_RAVEN2 "amdgpu/raven2_vcn.bin" #define FIRMWARE_ARCTURUS "amdgpu/arcturus_vcn.bin" #define FIRMWARE_RENOIR "amdgpu/renoir_vcn.bin" +#define FIRMWARE_GREEN_SARDINE "amdgpu/green_sardine_vcn.bin" #define FIRMWARE_NAVI10 "amdgpu/navi10_vcn.bin" #define FIRMWARE_NAVI14 "amdgpu/navi14_vcn.bin" #define FIRMWARE_NAVI12 "amdgpu/navi12_vcn.bin" @@ -50,6 +51,7 @@ MODULE_FIRMWARE(FIRMWARE_PICASSO); MODULE_FIRMWARE(FIRMWARE_RAVEN2); MODULE_FIRMWARE(FIRMWARE_ARCTURUS); MODULE_FIRMWARE(FIRMWARE_RENOIR); +MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE); MODULE_FIRMWARE(FIRMWARE_NAVI10); MODULE_FIRMWARE(FIRMWARE_NAVI14); MODULE_FIRMWARE(FIRMWARE_NAVI12); @@ -68,6 +70,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler); mutex_init(&adev->vcn.vcn_pg_lock); + mutex_init(&adev->vcn.vcn1_jpeg1_workaround); atomic_set(&adev->vcn.total_submission_cnt, 0); for (i = 0; i < adev->vcn.num_vcn_inst; i++) atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0); @@ -88,7 +91,11 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) adev->vcn.indirect_sram = true; break; case CHIP_RENOIR: - fw_name = FIRMWARE_RENOIR; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + fw_name = FIRMWARE_RENOIR; + else + fw_name = FIRMWARE_GREEN_SARDINE; + if ((adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) && (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG)) adev->vcn.indirect_sram = true; @@ -237,6 +244,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) } release_firmware(adev->vcn.fw); + mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround); mutex_destroy(&adev->vcn.vcn_pg_lock); return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 7a9b804bc988..17691158f783 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -220,6 +220,7 @@ struct amdgpu_vcn { struct amdgpu_vcn_inst inst[AMDGPU_MAX_VCN_INSTANCES]; struct amdgpu_vcn_reg internal; struct mutex vcn_pg_lock; + struct mutex vcn1_jpeg1_workaround; atomic_t total_submission_cnt; unsigned harvest_config; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index c6abb16e8018..58c83a7ad0fd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -112,8 +112,8 @@ struct amdgpu_bo_list_entry; #define AMDGPU_MMHUB_0 1 #define AMDGPU_MMHUB_1 2 -/* hardcode that limit for now */ -#define AMDGPU_VA_RESERVED_SIZE (1ULL << 20) +/* Reserve 2MB at top/bottom of address space for kernel use */ +#define AMDGPU_VA_RESERVED_SIZE (2ULL << 20) /* max vmids dedicated for process */ #define AMDGPU_VM_MAX_RESERVED_VMID 1 diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c index 01c1171afbe0..0c6b7c5ecfec 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c @@ -168,8 +168,7 @@ static const struct ttm_resource_manager_func amdgpu_vram_mgr_func; /** * amdgpu_vram_mgr_init - init VRAM manager and DRM MM * - * @man: TTM memory type manager - * @p_size: maximum size of VRAM + * @adev: amdgpu_device pointer * * Allocate and initialize the VRAM manager. */ @@ -199,7 +198,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev) /** * amdgpu_vram_mgr_fini - free and destroy VRAM manager * - * @man: TTM memory type manager + * @adev: amdgpu_device pointer * * Destroy and free the VRAM manager, returns -EBUSY if ranges are still * allocated inside it. @@ -229,7 +228,7 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev) /** * amdgpu_vram_mgr_vis_size - Calculate visible node size * - * @adev: amdgpu device structure + * @adev: amdgpu_device pointer * @node: MM node structure * * Calculate how many bytes of the MM node are inside visible VRAM diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c index 03ff8bd1fee8..5442df094102 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik.c +++ b/drivers/gpu/drm/amd/amdgpu/cik.c @@ -1336,11 +1336,13 @@ cik_asic_reset_method(struct amdgpu_device *adev) switch (adev->asic_type) { case CHIP_BONAIRE: - case CHIP_HAWAII: /* disable baco reset until it works */ /* smu7_asic_get_baco_capability(adev, &baco_reset); */ baco_reset = false; break; + case CHIP_HAWAII: + baco_reset = cik_asic_supports_baco(adev); + break; default: baco_reset = false; break; diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c index 20f108818b2b..a3c3fe96515f 100644 --- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c +++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c @@ -1071,22 +1071,19 @@ static int cik_sdma_soft_reset(void *handle) { u32 srbm_soft_reset = 0; struct amdgpu_device *adev = (struct amdgpu_device *)handle; - u32 tmp = RREG32(mmSRBM_STATUS2); + u32 tmp; - if (tmp & SRBM_STATUS2__SDMA_BUSY_MASK) { - /* sdma0 */ - tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET); - tmp |= SDMA0_F32_CNTL__HALT_MASK; - WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp); - srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK; - } - if (tmp & SRBM_STATUS2__SDMA1_BUSY_MASK) { - /* sdma1 */ - tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET); - tmp |= SDMA0_F32_CNTL__HALT_MASK; - WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp); - srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK; - } + /* sdma0 */ + tmp = RREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET); + tmp |= SDMA0_F32_CNTL__HALT_MASK; + WREG32(mmSDMA0_F32_CNTL + SDMA0_REGISTER_OFFSET, tmp); + srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA_MASK; + + /* sdma1 */ + tmp = RREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET); + tmp |= SDMA0_F32_CNTL__HALT_MASK; + WREG32(mmSDMA0_F32_CNTL + SDMA1_REGISTER_OFFSET, tmp); + srbm_soft_reset |= SRBM_SOFT_RESET__SOFT_RESET_SDMA1_MASK; if (srbm_soft_reset) { tmp = RREG32(mmSRBM_SOFT_RESET); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 9792ec737029..3579565e0eab 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -112,6 +112,25 @@ #define mmCP_HYP_ME_UCODE_DATA 0x5817 #define mmCP_HYP_ME_UCODE_DATA_BASE_IDX 1 +//CC_GC_SA_UNIT_DISABLE +#define mmCC_GC_SA_UNIT_DISABLE 0x0fe9 +#define mmCC_GC_SA_UNIT_DISABLE_BASE_IDX 0 +#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT 0x8 +#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK 0x0000FF00L +//GC_USER_SA_UNIT_DISABLE +#define mmGC_USER_SA_UNIT_DISABLE 0x0fea +#define mmGC_USER_SA_UNIT_DISABLE_BASE_IDX 0 +#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT 0x8 +#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK 0x0000FF00L +//PA_SC_ENHANCE_3 +#define mmPA_SC_ENHANCE_3 0x1085 +#define mmPA_SC_ENHANCE_3_BASE_IDX 0 +#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3 +#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK 0x00000008L + +#define mmCGTT_SPI_CS_CLK_CTRL 0x507c +#define mmCGTT_SPI_CS_CLK_CTRL_BASE_IDX 1 + MODULE_FIRMWARE("amdgpu/navi10_ce.bin"); MODULE_FIRMWARE("amdgpu/navi10_pfp.bin"); MODULE_FIRMWARE("amdgpu/navi10_me.bin"); @@ -3078,6 +3097,7 @@ static const struct soc15_reg_golden golden_settings_gc_rlc_spm_10_1_2_nv12[] = static const struct soc15_reg_golden golden_settings_gc_10_3[] = { + SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CS_CLK_CTRL, 0x78000000, 0x78000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_PS_CLK_CTRL, 0xff7f0fff, 0x78000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA0_CLK_CTRL, 0xff7f0fff, 0x30000100), SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_RA1_CLK_CTRL, 0xff7f0fff, 0x7e000100), @@ -3091,6 +3111,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] = SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CM_CTRL1, 0xff8fff0f, 0x580f1008), SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xf7ffffff, 0x10f80988), + SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG, 0x00000020, 0x00000020), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_CL_ENHANCE, 0xf17fffff, 0x01200007), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800), SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000820), @@ -3188,6 +3209,8 @@ static int gfx_v10_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev); static void gfx_v10_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume); static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume); static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure); +static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev); +static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev); static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask) { @@ -3586,6 +3609,17 @@ static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev) le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length); } +static void gfx_v10_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev) +{ + const struct rlc_firmware_header_v2_2 *rlc_hdr; + + rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data; + adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes); + adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes); + adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes); + adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes); +} + static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev) { bool ret = false; @@ -3701,8 +3735,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data; version_major = le16_to_cpu(rlc_hdr->header.header_version_major); version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor); - if (version_major == 2 && version_minor == 1) - adev->gfx.rlc.is_rlc_v2_1 = true; adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version); adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version); @@ -3744,8 +3776,12 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++) adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]); - if (adev->gfx.rlc.is_rlc_v2_1) - gfx_v10_0_init_rlc_ext_microcode(adev); + if (version_major == 2) { + if (version_minor >= 1) + gfx_v10_0_init_rlc_ext_microcode(adev); + if (version_minor == 2) + gfx_v10_0_init_rlc_iram_dram_microcode(adev); + } } snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks); @@ -3806,8 +3842,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) adev->firmware.fw_size += ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE); } - if (adev->gfx.rlc.is_rlc_v2_1 && - adev->gfx.rlc.save_restore_list_cntl_size_bytes && + if (adev->gfx.rlc.save_restore_list_cntl_size_bytes && adev->gfx.rlc.save_restore_list_gpm_size_bytes && adev->gfx.rlc.save_restore_list_srm_size_bytes) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL]; @@ -3827,6 +3862,21 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev) info->fw = adev->gfx.rlc_fw; adev->firmware.fw_size += ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE); + + if (adev->gfx.rlc.rlc_iram_ucode_size_bytes && + adev->gfx.rlc.rlc_dram_ucode_size_bytes) { + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE); + + info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM]; + info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM; + info->fw = adev->gfx.rlc_fw; + adev->firmware.fw_size += + ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE); + } } info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1]; @@ -4536,12 +4586,17 @@ static void gfx_v10_0_setup_rb(struct amdgpu_device *adev) int i, j; u32 data; u32 active_rbs = 0; + u32 bitmap; u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se / adev->gfx.config.max_sh_per_se; mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + bitmap = i * adev->gfx.config.max_sh_per_se + j; + if ((adev->asic_type == CHIP_SIENNA_CICHLID) && + ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1)) + continue; gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff); data = gfx_v10_0_get_rb_active_bitmap(adev); active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) * @@ -6950,6 +7005,9 @@ static int gfx_v10_0_hw_init(void *handle) if (r) return r; + if (adev->asic_type == CHIP_SIENNA_CICHLID) + gfx_v10_3_program_pbb_mode(adev); + return r; } @@ -8763,6 +8821,10 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev, mutex_lock(&adev->grbm_idx_mutex); for (i = 0; i < adev->gfx.config.max_shader_engines; i++) { for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) { + bitmap = i * adev->gfx.config.max_sh_per_se + j; + if ((adev->asic_type == CHIP_SIENNA_CICHLID) && + ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1)) + continue; mask = 1; ao_bitmap = 0; counter = 0; @@ -8797,6 +8859,47 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev, return 0; } +static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev) +{ + uint32_t efuse_setting, vbios_setting, disabled_sa, max_sa_mask; + + efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SA_UNIT_DISABLE); + efuse_setting &= CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK; + efuse_setting >>= CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT; + + vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SA_UNIT_DISABLE); + vbios_setting &= GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK; + vbios_setting >>= GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT; + + max_sa_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_sh_per_se * + adev->gfx.config.max_shader_engines); + disabled_sa = efuse_setting | vbios_setting; + disabled_sa &= max_sa_mask; + + return disabled_sa; +} + +static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev) +{ + uint32_t max_sa_per_se, max_sa_per_se_mask, max_shader_engines; + uint32_t disabled_sa_mask, se_index, disabled_sa_per_se; + + disabled_sa_mask = gfx_v10_3_get_disabled_sa(adev); + + max_sa_per_se = adev->gfx.config.max_sh_per_se; + max_sa_per_se_mask = (1 << max_sa_per_se) - 1; + max_shader_engines = adev->gfx.config.max_shader_engines; + + for (se_index = 0; max_shader_engines > se_index; se_index++) { + disabled_sa_per_se = disabled_sa_mask >> (se_index * max_sa_per_se); + disabled_sa_per_se &= max_sa_per_se_mask; + if (disabled_sa_per_se == max_sa_per_se_mask) { + WREG32_FIELD15(GC, 0, PA_SC_ENHANCE_3, FORCE_PBB_WORKLOAD_MODE_TO_ZERO, 1); + break; + } + } +} + const struct amdgpu_ip_block_version gfx_v10_0_ip_block = { .type = AMD_IP_BLOCK_TYPE_GFX, diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6959aebae6d4..0d8e203b10ef 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -117,6 +117,13 @@ MODULE_FIRMWARE("amdgpu/renoir_mec.bin"); MODULE_FIRMWARE("amdgpu/renoir_mec2.bin"); MODULE_FIRMWARE("amdgpu/renoir_rlc.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_ce.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_pfp.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_me.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_mec.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_mec2.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_rlc.bin"); + #define mmTCP_CHAN_STEER_0_ARCT 0x0b03 #define mmTCP_CHAN_STEER_0_ARCT_BASE_IDX 0 #define mmTCP_CHAN_STEER_1_ARCT 0x0b04 @@ -1630,7 +1637,10 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c index bc300283b6ab..c600b61b5f45 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c @@ -33,6 +33,7 @@ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev); static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev); +static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring); static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val) { @@ -564,8 +565,8 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = { .insert_start = jpeg_v1_0_decode_ring_insert_start, .insert_end = jpeg_v1_0_decode_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, - .begin_use = vcn_v1_0_ring_begin_use, - .end_use = amdgpu_vcn_ring_end_use, + .begin_use = jpeg_v1_0_ring_begin_use, + .end_use = vcn_v1_0_ring_end_use, .emit_wreg = jpeg_v1_0_decode_ring_emit_wreg, .emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, @@ -586,3 +587,22 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev) { adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs; } + +static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring) +{ + struct amdgpu_device *adev = ring->adev; + bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + int cnt = 0; + + mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + + if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec)) + DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n"); + + for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) { + if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt])) + DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt); + } + + vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); +} diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c index 1ce741a0c6a7..8eeba8096493 100644 --- a/drivers/gpu/drm/amd/amdgpu/nv.c +++ b/drivers/gpu/drm/amd/amdgpu/nv.c @@ -455,6 +455,15 @@ void nv_set_virt_ops(struct amdgpu_device *adev) adev->virt.ops = &xgpu_nv_virt_ops; } +static bool nv_is_headless_sku(struct pci_dev *pdev) +{ + if ((pdev->device == 0x731E && + (pdev->revision == 0xC6 || pdev->revision == 0xC7)) || + (pdev->device == 0x7340 && pdev->revision == 0xC9)) + return true; + return false; +} + int nv_set_ip_blocks(struct amdgpu_device *adev) { int r; @@ -491,7 +500,8 @@ int nv_set_ip_blocks(struct amdgpu_device *adev) if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT && !amdgpu_sriov_vf(adev)) amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block); - amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); + if (!nv_is_headless_sku(adev->pdev)) + amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block); amdgpu_device_ip_block_add(adev, &jpeg_v2_0_ip_block); if (adev->enable_mes) amdgpu_device_ip_block_add(adev, &mes_v10_1_ip_block); diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h index 1ef2f5b1d828..4137dc710aaf 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h +++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h @@ -201,7 +201,7 @@ enum psp_gfx_fw_type { GFX_FW_TYPE_UVD1 = 23, /* UVD1 VG-20 */ GFX_FW_TYPE_TOC = 24, /* TOC NV-10 */ GFX_FW_TYPE_RLC_P = 25, /* RLC P NV */ - GFX_FW_TYPE_RLX6 = 26, /* RLX6 NV */ + GFX_FW_TYPE_RLC_IRAM = 26, /* RLC_IRAM NV */ GFX_FW_TYPE_GLOBAL_TAP_DELAYS = 27, /* GLOBAL TAP DELAYS NV */ GFX_FW_TYPE_SE0_TAP_DELAYS = 28, /* SE0 TAP DELAYS NV */ GFX_FW_TYPE_SE1_TAP_DELAYS = 29, /* SE1 TAP DELAYS NV */ @@ -223,7 +223,7 @@ enum psp_gfx_fw_type { GFX_FW_TYPE_ACCUM_CTRL_RAM = 45, /* ACCUM CTRL RAM NV */ GFX_FW_TYPE_RLCP_CAM = 46, /* RLCP CAM NV */ GFX_FW_TYPE_RLC_SPP_CAM_EXT = 47, /* RLC SPP CAM EXT NV */ - GFX_FW_TYPE_RLX6_DRAM_BOOT = 48, /* RLX6 DRAM BOOT NV */ + GFX_FW_TYPE_RLC_DRAM_BOOT = 48, /* RLC DRAM BOOT NV */ GFX_FW_TYPE_VCN0_RAM = 49, /* VCN_RAM NV + RN */ GFX_FW_TYPE_VCN1_RAM = 50, /* VCN_RAM NV + RN */ GFX_FW_TYPE_DMUB = 51, /* DMUB RN */ diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c index 75489313dbad..c4828bd3264b 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c @@ -39,6 +39,8 @@ MODULE_FIRMWARE("amdgpu/renoir_asd.bin"); MODULE_FIRMWARE("amdgpu/renoir_ta.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_asd.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_ta.bin"); /* address block */ #define smnMP1_FIRMWARE_FLAGS 0x3010024 @@ -54,7 +56,10 @@ static int psp_v12_0_init_microcode(struct psp_context *psp) switch (adev->asic_type) { case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 86fb1eddf5a6..e82f49f62f6e 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -69,6 +69,7 @@ MODULE_FIRMWARE("amdgpu/picasso_sdma.bin"); MODULE_FIRMWARE("amdgpu/raven2_sdma.bin"); MODULE_FIRMWARE("amdgpu/arcturus_sdma.bin"); MODULE_FIRMWARE("amdgpu/renoir_sdma.bin"); +MODULE_FIRMWARE("amdgpu/green_sardine_sdma.bin"); #define SDMA0_POWER_CNTL__ON_OFF_CONDITION_HOLD_TIME_MASK 0x000000F8L #define SDMA0_POWER_CNTL__ON_OFF_STATUS_DURATION_TIME_MASK 0xFC000000L @@ -619,7 +620,10 @@ static int sdma_v4_0_init_microcode(struct amdgpu_device *adev) chip_name = "arcturus"; break; case CHIP_RENOIR: - chip_name = "renoir"; + if (adev->apu_flags & AMD_APU_IS_RENOIR) + chip_name = "renoir"; + else + chip_name = "green_sardine"; break; default: BUG(); diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index afcccc6c0fc6..f57c5f57efa8 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -1195,8 +1195,7 @@ static int soc15_common_early_init(void *handle) adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_MMHUB | - AMD_PG_SUPPORT_VCN | - AMD_PG_SUPPORT_VCN_DPG; + AMD_PG_SUPPORT_VCN; } else { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | @@ -1243,7 +1242,15 @@ static int soc15_common_early_init(void *handle) break; case CHIP_RENOIR: adev->asic_funcs = &soc15_asic_funcs; - adev->apu_flags |= AMD_APU_IS_RENOIR; + if (adev->pdev->device == 0x1636) + adev->apu_flags |= AMD_APU_IS_RENOIR; + else + adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE; + + if (adev->apu_flags & AMD_APU_IS_RENOIR) + adev->external_rev_id = adev->rev_id + 0x91; + else + adev->external_rev_id = adev->rev_id + 0xa1; adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | AMD_CG_SUPPORT_GFX_MGLS | AMD_CG_SUPPORT_GFX_3D_CGCG | @@ -1268,7 +1275,6 @@ static int soc15_common_early_init(void *handle) AMD_PG_SUPPORT_VCN | AMD_PG_SUPPORT_JPEG | AMD_PG_SUPPORT_VCN_DPG; - adev->external_rev_id = adev->rev_id + 0x91; break; default: /* FIXME: not supported yet */ diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c index 73699eafb51e..86e1ef732ebe 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c @@ -54,6 +54,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev, int inst_idx, struct dpg_pause_state *new_state); static void vcn_v1_0_idle_work_handler(struct work_struct *work); +static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); /** * vcn_v1_0_early_init - set function pointers @@ -1804,11 +1805,24 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work) } } -void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) +static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) { - struct amdgpu_device *adev = ring->adev; + struct amdgpu_device *adev = ring->adev; bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work); + mutex_lock(&adev->vcn.vcn1_jpeg1_workaround); + + if (amdgpu_fence_wait_empty(&ring->adev->jpeg.inst->ring_dec)) + DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n"); + + vcn_v1_0_set_pg_for_begin_use(ring, set_clocks); + +} + +void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks) +{ + struct amdgpu_device *adev = ring->adev; + if (set_clocks) { amdgpu_gfx_off_ctrl(adev, false); if (adev->pm.dpm_enabled) @@ -1844,6 +1858,12 @@ void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring) } } +void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring) +{ + schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT); + mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround); +} + static const struct amd_ip_funcs vcn_v1_0_ip_funcs = { .name = "vcn_v1_0", .early_init = vcn_v1_0_early_init, @@ -1891,7 +1911,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = { .insert_end = vcn_v1_0_dec_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = vcn_v1_0_ring_begin_use, - .end_use = amdgpu_vcn_ring_end_use, + .end_use = vcn_v1_0_ring_end_use, .emit_wreg = vcn_v1_0_dec_ring_emit_wreg, .emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, @@ -1923,7 +1943,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = { .insert_end = vcn_v1_0_enc_ring_insert_end, .pad_ib = amdgpu_ring_generic_pad_ib, .begin_use = vcn_v1_0_ring_begin_use, - .end_use = amdgpu_vcn_ring_end_use, + .end_use = vcn_v1_0_ring_end_use, .emit_wreg = vcn_v1_0_enc_ring_emit_wreg, .emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait, .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper, diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h index f67d7391fc21..1f1cc7f0ece7 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h @@ -24,7 +24,8 @@ #ifndef __VCN_V1_0_H__ #define __VCN_V1_0_H__ -void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring); +void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring); +void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks); extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index d2981524dba0..3de5e14c5ae3 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -798,10 +798,10 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size) } pcrat_image = kvmalloc(crat_table->length, GFP_KERNEL); - memcpy(pcrat_image, crat_table, crat_table->length); if (!pcrat_image) return -ENOMEM; + memcpy(pcrat_image, crat_table, crat_table->length); *crat_image = pcrat_image; *size = crat_table->length; @@ -1426,5 +1426,5 @@ int kfd_create_crat_image_virtual(void **crat_image, size_t *size, */ void kfd_destroy_crat_image(void *crat_image) { - kfree(crat_image); + kvfree(crat_image); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c index 72e4d61ac752..ad0593342333 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v10.c @@ -58,8 +58,9 @@ static int update_qpd_v10(struct device_queue_manager *dqm, /* check if sh_mem_config register already configured */ if (qpd->sh_mem_config == 0) { qpd->sh_mem_config = - SH_MEM_ALIGNMENT_MODE_UNALIGNED << - SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT; + (SH_MEM_ALIGNMENT_MODE_UNALIGNED << + SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT) | + (3 << SH_MEM_CONFIG__INITIAL_INST_PREFETCH__SHIFT); #if 0 /* TODO: * This shouldn't be an issue with Navi10. Verify. diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig index f24abf428534..60dfdd432aba 100644 --- a/drivers/gpu/drm/amd/display/Kconfig +++ b/drivers/gpu/drm/amd/display/Kconfig @@ -42,6 +42,7 @@ config DRM_AMD_DC_SI config DEBUG_KERNEL_DC bool "Enable kgdb break in DC" depends on DRM_AMD_DC + depends on KGDB help Choose this option if you want to hit kdgb_break in assert. 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 bb1bc7f5d149..0e7118000919 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -100,6 +100,8 @@ MODULE_FIRMWARE(FIRMWARE_SIENNA_CICHLID_DMUB); #define FIRMWARE_NAVY_FLOUNDER_DMUB "amdgpu/navy_flounder_dmcub.bin" MODULE_FIRMWARE(FIRMWARE_NAVY_FLOUNDER_DMUB); #endif +#define FIRMWARE_GREEN_SARDINE_DMUB "amdgpu/green_sardine_dmcub.bin" +MODULE_FIRMWARE(FIRMWARE_GREEN_SARDINE_DMUB); #define FIRMWARE_RAVEN_DMCU "amdgpu/raven_dmcu.bin" MODULE_FIRMWARE(FIRMWARE_RAVEN_DMCU); @@ -583,7 +585,7 @@ static void amdgpu_dm_fbc_init(struct drm_connector *connector) { struct drm_device *dev = connector->dev; struct amdgpu_device *adev = drm_to_adev(dev); - struct dm_comressor_info *compressor = &adev->dm.compressor; + struct dm_compressor_info *compressor = &adev->dm.compressor; struct amdgpu_dm_connector *aconn = to_amdgpu_dm_connector(connector); struct drm_display_mode *mode; unsigned long max_size = 0; @@ -973,6 +975,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev) case CHIP_RAVEN: case CHIP_RENOIR: init_data.flags.gpu_vm_support = true; + if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id)) + init_data.flags.disable_dmcu = true; break; default: break; @@ -1267,6 +1271,8 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) case CHIP_RENOIR: dmub_asic = DMUB_ASIC_DCN21; fw_name_dmub = FIRMWARE_RENOIR_DMUB; + if (ASICREV_IS_GREEN_SARDINE(adev->external_rev_id)) + fw_name_dmub = FIRMWARE_GREEN_SARDINE_DMUB; break; #if defined(CONFIG_DRM_AMD_DC_DCN3_0) case CHIP_SIENNA_CICHLID: @@ -5063,7 +5069,13 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector) struct amdgpu_device *adev = drm_to_adev(connector->dev); struct amdgpu_display_manager *dm = &adev->dm; - drm_atomic_private_obj_fini(&aconnector->mst_mgr.base); + /* + * Call only if mst_mgr was iniitalized before since it's not done + * for all connector types. + */ + if (aconnector->mst_mgr.dev) + drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr); + #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) ||\ defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE) @@ -7494,7 +7506,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) bool mode_set_reset_required = false; drm_atomic_helper_update_legacy_modeset_state(dev, state); - drm_atomic_helper_calc_timestamping_constants(state); dm_state = dm_atomic_get_new_state(state); if (dm_state && dm_state->context) { @@ -7521,6 +7532,8 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) } } + drm_atomic_helper_calc_timestamping_constants(state); + /* update changed items */ for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 9c1e003d9c29..a8a0e8cb1a11 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -86,7 +86,7 @@ struct irq_list_head { * @bo_ptr: Pointer to the buffer object * @gpu_addr: MMIO gpu addr */ -struct dm_comressor_info { +struct dm_compressor_info { void *cpu_addr; struct amdgpu_bo *bo_ptr; uint64_t gpu_addr; @@ -148,7 +148,9 @@ struct amdgpu_dm_backlight_caps { * @soc_bounding_box: SOC bounding box values provided by gpu_info FW * @cached_state: Caches device atomic state for suspend/resume * @cached_dc_state: Cached state of content streams - * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info + * @compressor: Frame buffer compression buffer. See &struct dm_compressor_info + * @force_timing_sync: set via debugfs. When set, indicates that all connected + * displays will be forced to synchronize. */ struct amdgpu_display_manager { @@ -322,7 +324,7 @@ struct amdgpu_display_manager { struct drm_atomic_state *cached_state; struct dc_state *cached_dc_state; - struct dm_comressor_info compressor; + struct dm_compressor_info compressor; const struct firmware *fw_dmcu; uint32_t dmcu_fw_version; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index db741e47d194..eee19edeeee5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -647,7 +647,7 @@ static void try_disable_dsc(struct drm_atomic_state *state, for (i = 0; i < count; i++) { if (vars[i].dsc_enabled && vars[i].bpp_x16 == params[i].bw_range.max_target_bpp_x16 - && !params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) { + && params[i].clock_force_enable == DSC_CLK_FORCE_DEFAULT) { kbps_increase[i] = params[i].bw_range.stream_kbps - params[i].bw_range.max_kbps; tried[i] = false; remaining_to_try += 1; diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c index efb909ef7a0f..857f156e4985 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c @@ -166,6 +166,11 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); break; } + + if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) { + rn_clk_mgr_construct(ctx, clk_mgr, pp_smu, dccg); + break; + } if (ASICREV_IS_RAVEN2(asic_id.hw_internal_rev)) { rv2_clk_mgr_construct(ctx, clk_mgr, pp_smu); break; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 2a725a5fba40..45ad05f6e03b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -848,7 +848,7 @@ static void disable_vbios_mode_if_required( struct dc *dc, struct dc_state *context) { - unsigned int i; + unsigned int i, j; /* check if timing_changed, disable stream*/ for (i = 0; i < dc->res_pool->pipe_count; i++) { @@ -872,10 +872,10 @@ static void disable_vbios_mode_if_required( enc_inst = link->link_enc->funcs->get_dig_frontend(link->link_enc); if (enc_inst != ENGINE_ID_UNKNOWN) { - for (i = 0; i < dc->res_pool->stream_enc_count; i++) { - if (dc->res_pool->stream_enc[i]->id == enc_inst) { - tg_inst = dc->res_pool->stream_enc[i]->funcs->dig_source_otg( - dc->res_pool->stream_enc[i]); + for (j = 0; j < dc->res_pool->stream_enc_count; j++) { + if (dc->res_pool->stream_enc[j]->id == enc_inst) { + tg_inst = dc->res_pool->stream_enc[j]->funcs->dig_source_otg( + dc->res_pool->stream_enc[j]); break; } } @@ -1571,8 +1571,8 @@ static void init_state(struct dc *dc, struct dc_state *context) struct dc_state *dc_create_state(struct dc *dc) { - struct dc_state *context = kzalloc(sizeof(struct dc_state), - GFP_KERNEL); + struct dc_state *context = kvzalloc(sizeof(struct dc_state), + GFP_KERNEL); if (!context) return NULL; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index e430148e47cf..59d48cf819ea 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -120,6 +120,8 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id) dc_version = DCN_VERSION_1_01; if (ASICREV_IS_RENOIR(asic_id.hw_internal_rev)) dc_version = DCN_VERSION_2_1; + if (ASICREV_IS_GREEN_SARDINE(asic_id.hw_internal_rev)) + dc_version = DCN_VERSION_2_1; break; #endif diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c index 9cc65dc1970f..49ae5ff12da6 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c @@ -1149,7 +1149,8 @@ static uint32_t dcn3_get_pix_clk_dividers( static const struct clock_source_funcs dcn3_clk_src_funcs = { .cs_power_down = dce110_clock_source_power_down, .program_pix_clk = dcn3_program_pix_clk, - .get_pix_clk_dividers = dcn3_get_pix_clk_dividers + .get_pix_clk_dividers = dcn3_get_pix_clk_dividers, + .get_pixel_clk_frequency_100hz = get_pixel_clk_frequency_100hz }; #endif /*****************************************/ diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c index 24fb39a11e5d..2455d210ccf6 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_resource.c @@ -2105,12 +2105,12 @@ static bool dcn30_internal_validate_bw( if (split[i]) { if (odm) { - if (split[i] == 4 && old_pipe->next_odm_pipe->next_odm_pipe) + if (split[i] == 4 && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe) old_index = old_pipe->next_odm_pipe->next_odm_pipe->pipe_idx; else if (old_pipe->next_odm_pipe) old_index = old_pipe->next_odm_pipe->pipe_idx; } else { - if (split[i] == 4 && old_pipe->bottom_pipe->bottom_pipe && + if (split[i] == 4 && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state) old_index = old_pipe->bottom_pipe->bottom_pipe->pipe_idx; else if (old_pipe->bottom_pipe && @@ -2150,10 +2150,12 @@ static bool dcn30_internal_validate_bw( goto validate_fail; newly_split[pipe_4to1->pipe_idx] = true; - if (odm && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe) + if (odm && old_pipe->next_odm_pipe && old_pipe->next_odm_pipe->next_odm_pipe + && old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe) old_index = old_pipe->next_odm_pipe->next_odm_pipe->next_odm_pipe->pipe_idx; - else if (!odm && old_pipe->bottom_pipe->bottom_pipe->bottom_pipe && - old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state) + else if (!odm && old_pipe->bottom_pipe && old_pipe->bottom_pipe->bottom_pipe && + old_pipe->bottom_pipe->bottom_pipe->bottom_pipe && + old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->plane_state == old_pipe->plane_state) old_index = old_pipe->bottom_pipe->bottom_pipe->bottom_pipe->pipe_idx; else old_index = -1; diff --git a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c index 3be2c90b0c61..21583699f992 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/dcn30/hw_factory_dcn30.c @@ -117,6 +117,12 @@ static const struct ddc_registers ddc_data_regs_dcn[] = { ddc_data_regs_dcn2(4), ddc_data_regs_dcn2(5), ddc_data_regs_dcn2(6), + { + DDC_GPIO_VGA_REG_LIST(DATA), + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + } }; static const struct ddc_registers ddc_clk_regs_dcn[] = { @@ -126,6 +132,12 @@ static const struct ddc_registers ddc_clk_regs_dcn[] = { ddc_clk_regs_dcn2(4), ddc_clk_regs_dcn2(5), ddc_clk_regs_dcn2(6), + { + DDC_GPIO_VGA_REG_LIST(CLK), + .ddc_setup = 0, + .phy_aux_cntl = 0, + .dc_gpio_aux_ctrl_5 = 0 + } }; static const struct ddc_sh_mask ddc_shift[] = { diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c index f67c18375bfd..dac427b68fd7 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c @@ -63,13 +63,13 @@ enum gpio_result dal_gpio_open_ex( enum gpio_mode mode) { if (gpio->pin) { - ASSERT_CRITICAL(false); + BREAK_TO_DEBUGGER(); return GPIO_RESULT_ALREADY_OPENED; } // No action if allocation failed during gpio construct if (!gpio->hw_container.ddc) { - ASSERT_CRITICAL(false); + BREAK_TO_DEBUGGER(); return GPIO_RESULT_NON_SPECIFIC_ERROR; } gpio->mode = mode; diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c index 2a1fea501f8c..3f1e7a196a23 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn20/irq_service_dcn20.c @@ -299,8 +299,8 @@ irq_source_info_dcn20[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c index 49689f71f4f1..0effbb2bd74a 100644 --- a/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c +++ b/drivers/gpu/drm/amd/display/dc/irq/dcn30/irq_service_dcn30.c @@ -306,8 +306,8 @@ irq_source_info_dcn30[DAL_IRQ_SOURCES_NUMBER] = { pflip_int_entry(1), pflip_int_entry(2), pflip_int_entry(3), - [DC_IRQ_SOURCE_PFLIP5] = dummy_irq_entry(), - [DC_IRQ_SOURCE_PFLIP6] = dummy_irq_entry(), + pflip_int_entry(4), + pflip_int_entry(5), [DC_IRQ_SOURCE_PFLIP_UNDERLAY0] = dummy_irq_entry(), gpio_pad_int_entry(0), gpio_pad_int_entry(1), diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h index 330acaaed79a..95cb56929e79 100644 --- a/drivers/gpu/drm/amd/display/dc/os_types.h +++ b/drivers/gpu/drm/amd/display/dc/os_types.h @@ -94,36 +94,27 @@ * general debug capabilities * */ -#if defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB) -#define ASSERT_CRITICAL(expr) do { \ - if (WARN_ON(!(expr))) { \ - kgdb_breakpoint(); \ - } \ -} while (0) +#ifdef CONFIG_DEBUG_KERNEL_DC +#define dc_breakpoint() kgdb_breakpoint() #else -#define ASSERT_CRITICAL(expr) do { \ - if (WARN_ON(!(expr))) { \ - ; \ - } \ -} while (0) +#define dc_breakpoint() do {} while (0) #endif -#if defined(CONFIG_DEBUG_KERNEL_DC) -#define ASSERT(expr) ASSERT_CRITICAL(expr) +#define ASSERT_CRITICAL(expr) do { \ + if (WARN_ON(!(expr))) \ + dc_breakpoint(); \ + } while (0) -#else -#define ASSERT(expr) WARN_ON_ONCE(!(expr)) -#endif +#define ASSERT(expr) do { \ + if (WARN_ON_ONCE(!(expr))) \ + dc_breakpoint(); \ + } while (0) -#if defined(CONFIG_DEBUG_KERNEL_DC) && (defined(CONFIG_HAVE_KGDB) || defined(CONFIG_KGDB)) #define BREAK_TO_DEBUGGER() \ do { \ DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__); \ - kgdb_breakpoint(); \ + dc_breakpoint(); \ } while (0) -#else -#define BREAK_TO_DEBUGGER() DRM_DEBUG_DRIVER("%s():%d\n", __func__, __LINE__) -#endif #define DC_ERR(...) do { \ dm_error(__VA_ARGS__); \ diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h index b267987aed06..ffcb059297d3 100644 --- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h +++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h @@ -205,6 +205,10 @@ enum { #if defined(CONFIG_DRM_AMD_DC_DCN3_0) #define ASICREV_IS_SIENNA_CICHLID_P(eChipRev) ((eChipRev >= NV_SIENNA_CICHLID_P_A0)) #endif +#define GREEN_SARDINE_A0 0xA1 +#ifndef ASICREV_IS_GREEN_SARDINE +#define ASICREV_IS_GREEN_SARDINE(eChipRev) ((eChipRev >= GREEN_SARDINE_A0) && (eChipRev < 0xFF)) +#endif /* * ASIC chip ID diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h index 10dc481ecbc4..06c1aabf10ce 100644 --- a/drivers/gpu/drm/amd/include/amd_shared.h +++ b/drivers/gpu/drm/amd/include/amd_shared.h @@ -45,6 +45,7 @@ enum amd_apu_flags { AMD_APU_IS_RAVEN2 = 0x00000002UL, AMD_APU_IS_PICASSO = 0x00000004UL, AMD_APU_IS_RENOIR = 0x00000008UL, + AMD_APU_IS_GREEN_SARDINE = 0x00000010UL, }; /** diff --git a/drivers/gpu/drm/amd/pm/inc/hwmgr.h b/drivers/gpu/drm/amd/pm/inc/hwmgr.h index 3898a95ec28b..518796a26eda 100644 --- a/drivers/gpu/drm/amd/pm/inc/hwmgr.h +++ b/drivers/gpu/drm/amd/pm/inc/hwmgr.h @@ -229,6 +229,7 @@ struct pp_smumgr_func { bool (*is_hw_avfs_present)(struct pp_hwmgr *hwmgr); int (*update_dpm_settings)(struct pp_hwmgr *hwmgr, void *profile_setting); int (*smc_table_manager)(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); /*rw: true for read, false for write */ + int (*stop_smc)(struct pp_hwmgr *hwmgr); }; struct pp_hwmgr_func { diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h index 35fc46d3c9c0..cbf4a58b77d9 100644 --- a/drivers/gpu/drm/amd/pm/inc/smu_types.h +++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h @@ -220,6 +220,7 @@ enum smu_clk_type { __SMU_DUMMY_MAP(DPM_MP0CLK), \ __SMU_DUMMY_MAP(DPM_LINK), \ __SMU_DUMMY_MAP(DPM_DCEFCLK), \ + __SMU_DUMMY_MAP(DPM_XGMI), \ __SMU_DUMMY_MAP(DS_GFXCLK), \ __SMU_DUMMY_MAP(DS_SOCCLK), \ __SMU_DUMMY_MAP(DS_LCLK), \ diff --git a/drivers/gpu/drm/amd/pm/inc/smumgr.h b/drivers/gpu/drm/amd/pm/inc/smumgr.h index ad100b533d04..5f46f1a4f38e 100644 --- a/drivers/gpu/drm/amd/pm/inc/smumgr.h +++ b/drivers/gpu/drm/amd/pm/inc/smumgr.h @@ -113,4 +113,6 @@ extern int smum_update_dpm_settings(struct pp_hwmgr *hwmgr, void *profile_settin extern int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw); +extern int smum_stop_smc(struct pp_hwmgr *hwmgr); + #endif diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c index 3be40114e63d..45f608838f6e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ci_baco.c @@ -142,12 +142,12 @@ static const struct baco_cmd_entry exit_baco_tbl[] = { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 }, { CMD_DELAY_MS, 0, 0, 0, 20, 0 }, - { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 }, + { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 }, - { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c }, + { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 }, - { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 }, + { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 }, { CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 }, { CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 } }; @@ -155,6 +155,7 @@ static const struct baco_cmd_entry exit_baco_tbl[] = static const struct baco_cmd_entry clean_baco_tbl[] = { { CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 }, + { CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 }, { CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 } }; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 3bf8be4d107b..35629140fc7a 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -1541,6 +1541,10 @@ static int smu7_disable_dpm_tasks(struct pp_hwmgr *hwmgr) PP_ASSERT_WITH_CODE((tmp_result == 0), "Failed to reset to default!", result = tmp_result); + tmp_result = smum_stop_smc(hwmgr); + PP_ASSERT_WITH_CODE((tmp_result == 0), + "Failed to stop smc!", result = tmp_result); + tmp_result = smu7_force_switch_to_arbf0(hwmgr); PP_ASSERT_WITH_CODE((tmp_result == 0), "Failed to force to switch arbf0!", result = tmp_result); @@ -1585,18 +1589,24 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->current_profile_setting.sclk_down_hyst = 100; data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT; data->current_profile_setting.bupdate_mclk = 1; - if (adev->gmc.vram_width == 256) { - data->current_profile_setting.mclk_up_hyst = 10; - data->current_profile_setting.mclk_down_hyst = 60; - data->current_profile_setting.mclk_activity = 25; - } else if (adev->gmc.vram_width == 128) { - data->current_profile_setting.mclk_up_hyst = 5; - data->current_profile_setting.mclk_down_hyst = 16; - data->current_profile_setting.mclk_activity = 20; - } else if (adev->gmc.vram_width == 64) { - data->current_profile_setting.mclk_up_hyst = 3; - data->current_profile_setting.mclk_down_hyst = 16; - data->current_profile_setting.mclk_activity = 20; + if (hwmgr->chip_id >= CHIP_POLARIS10) { + if (adev->gmc.vram_width == 256) { + data->current_profile_setting.mclk_up_hyst = 10; + data->current_profile_setting.mclk_down_hyst = 60; + data->current_profile_setting.mclk_activity = 25; + } else if (adev->gmc.vram_width == 128) { + data->current_profile_setting.mclk_up_hyst = 5; + data->current_profile_setting.mclk_down_hyst = 16; + data->current_profile_setting.mclk_activity = 20; + } else if (adev->gmc.vram_width == 64) { + data->current_profile_setting.mclk_up_hyst = 3; + data->current_profile_setting.mclk_down_hyst = 16; + data->current_profile_setting.mclk_activity = 20; + } + } else { + data->current_profile_setting.mclk_up_hyst = 0; + data->current_profile_setting.mclk_down_hyst = 100; + data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT; } hwmgr->workload_mask = 1 << hwmgr->workload_prority[PP_SMC_POWER_PROFILE_FULLSCREEN3D]; hwmgr->power_profile_mode = PP_SMC_POWER_PROFILE_FULLSCREEN3D; @@ -2883,7 +2893,7 @@ static int smu7_vblank_too_short(struct pp_hwmgr *hwmgr, if (hwmgr->is_kicker) switch_limit_us = data->is_memory_gddr5 ? 450 : 150; else - switch_limit_us = data->is_memory_gddr5 ? 190 : 150; + switch_limit_us = data->is_memory_gddr5 ? 200 : 150; break; case CHIP_VEGAM: switch_limit_us = 30; diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c index e4d1f3d66ef4..329bf4d44bbc 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/ci_smumgr.c @@ -2726,10 +2726,7 @@ static int ci_initialize_mc_reg_table(struct pp_hwmgr *hwmgr) static bool ci_is_dpm_running(struct pp_hwmgr *hwmgr) { - return (1 == PHM_READ_INDIRECT_FIELD(hwmgr->device, - CGS_IND_REG__SMC, FEATURE_STATUS, - VOLTAGE_CONTROLLER_ON)) - ? true : false; + return ci_is_smc_ram_running(hwmgr); } static int ci_smu_init(struct pp_hwmgr *hwmgr) @@ -2939,6 +2936,29 @@ static int ci_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type) return 0; } +static void ci_reset_smc(struct pp_hwmgr *hwmgr) +{ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SMC_SYSCON_RESET_CNTL, + rst_reg, 1); +} + + +static void ci_stop_smc_clock(struct pp_hwmgr *hwmgr) +{ + PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, + SMC_SYSCON_CLOCK_CNTL_0, + ck_disable, 1); +} + +static int ci_stop_smc(struct pp_hwmgr *hwmgr) +{ + ci_reset_smc(hwmgr); + ci_stop_smc_clock(hwmgr); + + return 0; +} + const struct pp_smumgr_func ci_smu_funcs = { .name = "ci_smu", .smu_init = ci_smu_init, @@ -2964,4 +2984,5 @@ const struct pp_smumgr_func ci_smu_funcs = { .is_dpm_running = ci_is_dpm_running, .update_dpm_settings = ci_update_dpm_settings, .update_smc_table = ci_update_smc_table, + .stop_smc = ci_stop_smc, }; diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c index b6fb48066841..b6921db3c130 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/smumgr.c @@ -245,3 +245,11 @@ int smum_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t tabl return -EINVAL; } + +int smum_stop_smc(struct pp_hwmgr *hwmgr) +{ + if (hwmgr->smumgr_funcs->stop_smc) + return hwmgr->smumgr_funcs->stop_smc(hwmgr); + + return 0; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 942793947b4b..b1e5ec01527b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -417,6 +417,9 @@ static int smu_early_init(void *handle) smu->pm_enabled = !!amdgpu_dpm; smu->is_apu = false; mutex_init(&smu->mutex); + mutex_init(&smu->smu_baco.mutex); + smu->smu_baco.state = SMU_BACO_STATE_EXIT; + smu->smu_baco.platform_support = false; return smu_set_funcs(adev); } @@ -795,10 +798,6 @@ static int smu_sw_init(void *handle) bitmap_zero(smu->smu_feature.enabled, SMU_FEATURE_MAX); bitmap_zero(smu->smu_feature.allowed, SMU_FEATURE_MAX); - mutex_init(&smu->smu_baco.mutex); - smu->smu_baco.state = SMU_BACO_STATE_EXIT; - smu->smu_baco.platform_support = false; - mutex_init(&smu->sensor_lock); mutex_init(&smu->metrics_lock); mutex_init(&smu->message_lock); @@ -1030,17 +1029,6 @@ 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; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index 8d8081c6bd38..ef1a62e86a0e 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -1361,14 +1361,9 @@ static int navi10_get_fan_speed_rpm(struct smu_context *smu, if (!speed) return -EINVAL; - switch (smu_v11_0_get_fan_control_mode(smu)) { - case AMD_FAN_CTRL_AUTO: - return navi10_get_smu_metrics_data(smu, - METRICS_CURR_FANSPEED, - speed); - default: - return smu_v11_0_get_fan_speed_rpm(smu, speed); - } + return navi10_get_smu_metrics_data(smu, + METRICS_CURR_FANSPEED, + speed); } static int navi10_get_fan_parameters(struct smu_context *smu) @@ -2534,29 +2529,6 @@ static const struct i2c_algorithm navi10_i2c_algo = { .functionality = navi10_i2c_func, }; -static int navi10_i2c_control_init(struct smu_context *smu, struct i2c_adapter *control) -{ - struct amdgpu_device *adev = to_amdgpu_device(control); - int res; - - control->owner = THIS_MODULE; - control->class = I2C_CLASS_SPD; - control->dev.parent = &adev->pdev->dev; - control->algo = &navi10_i2c_algo; - snprintf(control->name, sizeof(control->name), "AMDGPU SMU"); - - res = i2c_add_adapter(control); - if (res) - DRM_ERROR("Failed to register hw i2c, err: %d\n", res); - - return res; -} - -static void navi10_i2c_control_fini(struct smu_context *smu, struct i2c_adapter *control) -{ - i2c_del_adapter(control); -} - static ssize_t navi10_get_gpu_metrics(struct smu_context *smu, void **table) { @@ -2687,8 +2659,6 @@ static const struct pptable_funcs navi10_ppt_funcs = { .set_default_dpm_table = navi10_set_default_dpm_table, .dpm_set_vcn_enable = navi10_dpm_set_vcn_enable, .dpm_set_jpeg_enable = navi10_dpm_set_jpeg_enable, - .i2c_init = navi10_i2c_control_init, - .i2c_fini = navi10_i2c_control_fini, .print_clk_levels = navi10_print_clk_levels, .force_clk_levels = navi10_force_clk_levels, .populate_umd_state_clk = navi10_populate_umd_state_clk, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index c27806fd07e0..895d89bea7fa 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -151,14 +151,17 @@ static struct cmn2asic_mapping sienna_cichlid_feature_mask_map[SMU_FEATURE_COUNT FEA_MAP(DPM_GFXCLK), FEA_MAP(DPM_GFX_GPO), FEA_MAP(DPM_UCLK), + FEA_MAP(DPM_FCLK), FEA_MAP(DPM_SOCCLK), FEA_MAP(DPM_MP0CLK), FEA_MAP(DPM_LINK), FEA_MAP(DPM_DCEFCLK), + FEA_MAP(DPM_XGMI), FEA_MAP(MEM_VDDCI_SCALING), FEA_MAP(MEM_MVDD_SCALING), FEA_MAP(DS_GFXCLK), FEA_MAP(DS_SOCCLK), + FEA_MAP(DS_FCLK), FEA_MAP(DS_LCLK), FEA_MAP(DS_DCEFCLK), FEA_MAP(DS_UCLK), @@ -452,6 +455,9 @@ static int sienna_cichlid_get_smu_metrics_data(struct smu_context *smu, case METRICS_CURR_DCEFCLK: *value = metrics->CurrClock[PPCLK_DCEFCLK]; break; + case METRICS_CURR_FCLK: + *value = metrics->CurrClock[PPCLK_FCLK]; + break; case METRICS_AVERAGE_GFXCLK: if (metrics->AverageGfxActivity <= SMU_11_0_7_GFX_BUSY_THRESHOLD) *value = metrics->AverageGfxclkFrequencyPostDs; @@ -948,19 +954,23 @@ static int sienna_cichlid_print_clk_levels(struct smu_context *smu, freq_values[1] = cur_value; mark_index = cur_value == freq_values[0] ? 0 : cur_value == freq_values[2] ? 2 : 1; - if (mark_index != 1) - freq_values[1] = (freq_values[0] + freq_values[2]) / 2; - for (i = 0; i < 3; i++) { + count = 3; + if (mark_index != 1) { + count = 2; + freq_values[1] = freq_values[2]; + } + + for (i = 0; i < count; i++) { size += sprintf(buf + size, "%d: %uMhz %s\n", i, freq_values[i], - i == mark_index ? "*" : ""); + cur_value == freq_values[i] ? "*" : ""); } } break; case SMU_PCIE: - gen_speed = smu_v11_0_get_current_pcie_link_speed(smu); - lane_width = smu_v11_0_get_current_pcie_link_width(smu); + gen_speed = smu_v11_0_get_current_pcie_link_speed_level(smu); + lane_width = smu_v11_0_get_current_pcie_link_width_level(smu); for (i = 0; i < NUM_LINK_LEVELS; i++) size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i, (dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," : @@ -1167,14 +1177,9 @@ static int sienna_cichlid_get_fan_speed_rpm(struct smu_context *smu, if (!speed) return -EINVAL; - switch (smu_v11_0_get_fan_control_mode(smu)) { - case AMD_FAN_CTRL_AUTO: - return sienna_cichlid_get_smu_metrics_data(smu, - METRICS_CURR_FANSPEED, - speed); - default: - return smu_v11_0_get_fan_speed_rpm(smu, speed); - } + return sienna_cichlid_get_smu_metrics_data(smu, + METRICS_CURR_FANSPEED, + speed); } static int sienna_cichlid_get_fan_parameters(struct smu_context *smu) diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c index c30d3338825f..92b2ea4c197b 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu_cmn.c @@ -431,10 +431,9 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu, char *buf) { uint32_t feature_mask[2] = { 0 }; - int32_t feature_index = 0; + int feature_index = 0; uint32_t count = 0; - uint32_t sort_feature[SMU_FEATURE_COUNT]; - uint64_t hw_feature_count = 0; + int8_t sort_feature[SMU_FEATURE_COUNT]; size_t size = 0; int ret = 0, i; @@ -447,23 +446,31 @@ size_t smu_cmn_get_pp_feature_mask(struct smu_context *smu, size = sprintf(buf + size, "features high: 0x%08x low: 0x%08x\n", feature_mask[1], feature_mask[0]); + memset(sort_feature, -1, sizeof(sort_feature)); + for (i = 0; i < SMU_FEATURE_COUNT; i++) { feature_index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_FEATURE, i); if (feature_index < 0) continue; + sort_feature[feature_index] = i; - hw_feature_count++; } - for (i = 0; i < hw_feature_count; i++) { + size += sprintf(buf + size, "%-2s. %-20s %-3s : %-s\n", + "No", "Feature", "Bit", "State"); + + for (i = 0; i < SMU_FEATURE_COUNT; i++) { + if (sort_feature[i] < 0) + continue; + size += sprintf(buf + size, "%02d. %-20s (%2d) : %s\n", - count++, - smu_get_feature_name(smu, sort_feature[i]), - i, - !!smu_cmn_feature_is_enabled(smu, sort_feature[i]) ? - "enabled" : "disabled"); + count++, + smu_get_feature_name(smu, sort_feature[i]), + i, + !!smu_cmn_feature_is_enabled(smu, sort_feature[i]) ? + "enabled" : "disabled"); } return size; diff --git a/drivers/gpu/drm/bridge/cadence/Kconfig b/drivers/gpu/drm/bridge/cadence/Kconfig index 511d67b16d14..ef8c230e0f62 100644 --- a/drivers/gpu/drm/bridge/cadence/Kconfig +++ b/drivers/gpu/drm/bridge/cadence/Kconfig @@ -13,7 +13,7 @@ config DRM_CDNS_MHDP8546 if DRM_CDNS_MHDP8546 config DRM_CDNS_MHDP8546_J721E - depends on ARCH_K3_J721E_SOC || COMPILE_TEST + depends on ARCH_K3 || COMPILE_TEST bool "J721E Cadence DPI/DP wrapper support" default y help diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 748df1cacd2b..0c79a9ba48bb 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -2327,12 +2327,6 @@ static enum drm_connector_status dw_hdmi_detect(struct dw_hdmi *hdmi) { enum drm_connector_status result; - mutex_lock(&hdmi->mutex); - hdmi->force = DRM_FORCE_UNSPECIFIED; - dw_hdmi_update_power(hdmi); - dw_hdmi_update_phy_mask(hdmi); - mutex_unlock(&hdmi->mutex); - result = hdmi->phy.ops->read_hpd(hdmi, hdmi->phy.data); mutex_lock(&hdmi->mutex); diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c index 90807a6b415c..deeed73f4ed6 100644 --- a/drivers/gpu/drm/drm_dp_helper.c +++ b/drivers/gpu/drm/drm_dp_helper.c @@ -374,6 +374,10 @@ static bool is_edid_digital_input_dp(const struct edid *edid) * drm_dp_downstream_is_type() - is the downstream facing port of certain type? * @dpcd: DisplayPort configuration data * @port_cap: port capabilities + * @type: port type to be checked. Can be: + * %DP_DS_PORT_TYPE_DP, %DP_DS_PORT_TYPE_VGA, %DP_DS_PORT_TYPE_DVI, + * %DP_DS_PORT_TYPE_HDMI, %DP_DS_PORT_TYPE_NON_EDID, + * %DP_DS_PORT_TYPE_DP_DUALMODE or %DP_DS_PORT_TYPE_WIRELESS. * * Caveat: Only works with DPCD 1.1+ port caps. * @@ -870,6 +874,7 @@ EXPORT_SYMBOL(drm_dp_downstream_444_to_420_conversion); /** * drm_dp_downstream_mode() - return a mode for downstream facing port + * @dev: DRM device * @dpcd: DisplayPort configuration data * @port_cap: port capabilities * @@ -1028,7 +1033,8 @@ EXPORT_SYMBOL(drm_dp_downstream_debug); /** * drm_dp_subconnector_type() - get DP branch device type - * + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities */ enum drm_mode_subconnector drm_dp_subconnector_type(const u8 dpcd[DP_RECEIVER_CAP_SIZE], @@ -1079,6 +1085,10 @@ EXPORT_SYMBOL(drm_dp_subconnector_type); /** * drm_mode_set_dp_subconnector_property - set subconnector for DP connector + * @connector: connector to set property on + * @status: connector status + * @dpcd: DisplayPort configuration data + * @port_cap: port capabilities * * Called by a driver on every detect event. */ diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index a82f37d44258..631125b46e04 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -3741,7 +3741,7 @@ drm_add_cmdb_modes(struct drm_connector *connector, u8 svd) /** * drm_display_mode_from_cea_vic() - return a mode for CEA VIC * @dev: DRM device - * @vic: CEA VIC of the mode + * @video_code: CEA VIC of the mode * * Creates a new mode matching the specified CEA VIC. * diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 19d73868490e..69c2c079d803 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -1085,6 +1085,8 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size, */ drm_gem_object_get(obj); + vma->vm_private_data = obj; + if (obj->funcs && obj->funcs->mmap) { ret = obj->funcs->mmap(obj, vma); if (ret) { @@ -1107,8 +1109,6 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size, vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot); } - vma->vm_private_data = obj; - return 0; } EXPORT_SYMBOL(drm_gem_mmap_obj); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index d77c9f8ff26c..e00616d94f26 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -593,8 +593,13 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma) /* Remove the fake offset */ vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node); - if (obj->import_attach) + if (obj->import_attach) { + /* Drop the reference drm_gem_mmap_obj() acquired.*/ + drm_gem_object_put(obj); + vma->vm_private_data = NULL; + return dma_buf_mmap(obj->dma_buf, vma, 0); + } shmem = to_drm_gem_shmem_obj(obj); diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c index 50cad0e4a92e..375c79e23ca5 100644 --- a/drivers/gpu/drm/drm_gem_vram_helper.c +++ b/drivers/gpu/drm/drm_gem_vram_helper.c @@ -140,7 +140,7 @@ static void drm_gem_vram_placement(struct drm_gem_vram_object *gbo, unsigned int c = 0; if (pl_flag & DRM_GEM_VRAM_PL_FLAG_TOPDOWN) - pl_flag = TTM_PL_FLAG_TOPDOWN; + invariant_flags = TTM_PL_FLAG_TOPDOWN; gbo->placement.placement = gbo->placements; gbo->placement.busy_placement = gbo->placements; diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c index 11fe9ff76fd5..9f955f2010c2 100644 --- a/drivers/gpu/drm/drm_prime.c +++ b/drivers/gpu/drm/drm_prime.c @@ -794,6 +794,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { /** * drm_prime_pages_to_sg - converts a page array into an sg list + * @dev: DRM device * @pages: pointer to the array of page pointers to convert * @nr_pages: length of the page vector * @@ -806,30 +807,27 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops = { struct sg_table *drm_prime_pages_to_sg(struct drm_device *dev, struct page **pages, unsigned int nr_pages) { - struct sg_table *sg = NULL; + struct sg_table *sg; + struct scatterlist *sge; size_t max_segment = 0; - int ret; sg = kmalloc(sizeof(struct sg_table), GFP_KERNEL); - if (!sg) { - ret = -ENOMEM; - goto out; - } + if (!sg) + return ERR_PTR(-ENOMEM); if (dev) max_segment = dma_max_mapping_size(dev->dev); if (max_segment == 0 || max_segment > SCATTERLIST_MAX_SEGMENT) max_segment = SCATTERLIST_MAX_SEGMENT; - ret = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0, + sge = __sg_alloc_table_from_pages(sg, pages, nr_pages, 0, nr_pages << PAGE_SHIFT, - max_segment, GFP_KERNEL); - if (ret) - goto out; - + max_segment, + NULL, 0, GFP_KERNEL); + if (IS_ERR(sge)) { + kfree(sg); + sg = ERR_CAST(sge); + } return sg; -out: - kfree(sg); - return ERR_PTR(ret); } EXPORT_SYMBOL(drm_prime_pages_to_sg); diff --git a/drivers/gpu/drm/gma500/psb_irq.c b/drivers/gpu/drm/gma500/psb_irq.c index 15eb3770d817..361e3a0c5ab6 100644 --- a/drivers/gpu/drm/gma500/psb_irq.c +++ b/drivers/gpu/drm/gma500/psb_irq.c @@ -347,6 +347,7 @@ int psb_irq_postinstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; unsigned long irqflags; + unsigned int i; spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); @@ -359,20 +360,12 @@ int psb_irq_postinstall(struct drm_device *dev) PSB_WVDC32(dev_priv->vdc_irq_mask, PSB_INT_ENABLE_R); PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM); - if (dev->vblank[0].enabled) - psb_enable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[1].enabled) - psb_enable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[2].enabled) - psb_enable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); - else - psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); + for (i = 0; i < dev->num_crtcs; ++i) { + if (dev->vblank[i].enabled) + psb_enable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + else + psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + } if (dev_priv->ops->hotplug_enable) dev_priv->ops->hotplug_enable(dev, true); @@ -385,6 +378,7 @@ void psb_irq_uninstall(struct drm_device *dev) { struct drm_psb_private *dev_priv = dev->dev_private; unsigned long irqflags; + unsigned int i; spin_lock_irqsave(&dev_priv->irqmask_lock, irqflags); @@ -393,14 +387,10 @@ void psb_irq_uninstall(struct drm_device *dev) PSB_WVDC32(0xFFFFFFFF, PSB_HWSTAM); - if (dev->vblank[0].enabled) - psb_disable_pipestat(dev_priv, 0, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[1].enabled) - psb_disable_pipestat(dev_priv, 1, PIPE_VBLANK_INTERRUPT_ENABLE); - - if (dev->vblank[2].enabled) - psb_disable_pipestat(dev_priv, 2, PIPE_VBLANK_INTERRUPT_ENABLE); + for (i = 0; i < dev->num_crtcs; ++i) { + if (dev->vblank[i].enabled) + psb_disable_pipestat(dev_priv, i, PIPE_VBLANK_INTERRUPT_ENABLE); + } dev_priv->vdc_irq_mask &= _PSB_IRQ_SGX_FLAG | _PSB_IRQ_MSVDX_FLAG | diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig index 9afa5c4a6bf0..1e1cb245fca7 100644 --- a/drivers/gpu/drm/i915/Kconfig +++ b/drivers/gpu/drm/i915/Kconfig @@ -25,6 +25,7 @@ config DRM_I915 select CRC32 select SND_HDA_I915 if SND_HDA_CORE select CEC_CORE if CEC_NOTIFIER + select VMAP_PFN help Choose this option if you have a system that has "Intel Graphics Media Accelerator" or "HD Graphics" integrated graphics, diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug index 1cb28c20807c..25cd9788a4d5 100644 --- a/drivers/gpu/drm/i915/Kconfig.debug +++ b/drivers/gpu/drm/i915/Kconfig.debug @@ -153,6 +153,7 @@ config DRM_I915_SELFTEST select DRM_EXPORT_FOR_TESTS if m select FAULT_INJECTION select PRIME_NUMBERS + select CRC32 help Choose this option to allow the driver to perform selftests upon loading; also requires the i915.selftest=1 module parameter. To diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c index 4d06178cd76c..cdcb7b1034ae 100644 --- a/drivers/gpu/drm/i915/display/intel_ddi.c +++ b/drivers/gpu/drm/i915/display/intel_ddi.c @@ -2742,7 +2742,7 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock, u32 n_entries, val, ln, dpcnt_mask, dpcnt_val; int rate = 0; - if (type == INTEL_OUTPUT_HDMI) { + if (type != INTEL_OUTPUT_HDMI) { struct intel_dp *intel_dp = enc_to_intel_dp(encoder); rate = intel_dp->link_rate; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 631b4338224e..99e682563d47 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -3434,6 +3434,14 @@ initial_plane_vma(struct drm_i915_private *i915, if (IS_ERR(obj)) return NULL; + /* + * Mark it WT ahead of time to avoid changing the + * cache_level during fbdev initialization. The + * unbind there would get stuck waiting for rcu. + */ + i915_gem_object_set_cache_coherency(obj, HAS_WT(i915) ? + I915_CACHE_WT : I915_CACHE_NONE); + switch (plane_config->tiling) { case I915_TILING_NONE: break; @@ -4093,8 +4101,7 @@ static int skl_check_ccs_aux_surface(struct intel_plane_state *plane_state) int skl_check_plane_surface(struct intel_plane_state *plane_state) { const struct drm_framebuffer *fb = plane_state->hw.fb; - int ret; - bool needs_aux = false; + int ret, i; ret = intel_plane_compute_gtt(plane_state); if (ret) @@ -4108,7 +4115,6 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state) * it. */ if (is_ccs_modifier(fb->modifier)) { - needs_aux = true; ret = skl_check_ccs_aux_surface(plane_state); if (ret) return ret; @@ -4116,20 +4122,15 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state) if (intel_format_info_is_yuv_semiplanar(fb->format, fb->modifier)) { - needs_aux = true; ret = skl_check_nv12_aux_surface(plane_state); if (ret) return ret; } - if (!needs_aux) { - int i; - - for (i = 1; i < fb->format->num_planes; i++) { - plane_state->color_plane[i].offset = ~0xfff; - plane_state->color_plane[i].x = 0; - plane_state->color_plane[i].y = 0; - } + for (i = fb->format->num_planes; i < ARRAY_SIZE(plane_state->color_plane); i++) { + plane_state->color_plane[i].offset = ~0xfff; + plane_state->color_plane[i].x = 0; + plane_state->color_plane[i].y = 0; } ret = skl_check_main_surface(plane_state); @@ -10635,6 +10636,10 @@ skl_get_initial_plane_config(struct intel_crtc *crtc, val & PLANE_CTL_FLIP_HORIZONTAL) plane_config->rotation |= DRM_MODE_REFLECT_X; + /* 90/270 degree rotation would require extra work */ + if (drm_rotation_90_or_270(plane_config->rotation)) + goto error; + base = intel_de_read(dev_priv, PLANE_SURF(pipe, plane_id)) & 0xfffff000; plane_config->base = base; @@ -12873,10 +12878,11 @@ compute_sink_pipe_bpp(const struct drm_connector_state *conn_state, case 10 ... 11: bpp = 10 * 3; break; - case 12: + case 12 ... 16: bpp = 12 * 3; break; default: + MISSING_CASE(conn_state->max_bpc); return -EINVAL; } diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c index acbd7eb66cbe..036f504ac7db 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c +++ b/drivers/gpu/drm/i915/display/intel_dp_aux_backlight.c @@ -52,17 +52,11 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable) } } -/* - * Read the current backlight value from DPCD register(s) based - * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported - */ -static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) +static bool intel_dp_aux_backlight_dpcd_mode(struct intel_connector *connector) { struct intel_dp *intel_dp = intel_attached_dp(connector); struct drm_i915_private *i915 = dp_to_i915(intel_dp); - u8 read_val[2] = { 0x0 }; u8 mode_reg; - u16 level = 0; if (drm_dp_dpcd_readb(&intel_dp->aux, DP_EDP_BACKLIGHT_MODE_SET_REGISTER, @@ -70,15 +64,29 @@ static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) drm_dbg_kms(&i915->drm, "Failed to read the DPCD register 0x%x\n", DP_EDP_BACKLIGHT_MODE_SET_REGISTER); - return 0; + return false; } + return (mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) == + DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD; +} + +/* + * Read the current backlight value from DPCD register(s) based + * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported + */ +static u32 intel_dp_aux_get_backlight(struct intel_connector *connector) +{ + struct intel_dp *intel_dp = intel_attached_dp(connector); + struct drm_i915_private *i915 = dp_to_i915(intel_dp); + u8 read_val[2] = { 0x0 }; + u16 level = 0; + /* * If we're not in DPCD control mode yet, the programmed brightness * value is meaningless and we should assume max brightness */ - if ((mode_reg & DP_EDP_BACKLIGHT_CONTROL_MODE_MASK) != - DP_EDP_BACKLIGHT_CONTROL_MODE_DPCD) + if (!intel_dp_aux_backlight_dpcd_mode(connector)) return connector->panel.backlight.max; if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB, @@ -319,7 +327,8 @@ static int intel_dp_aux_setup_backlight(struct intel_connector *connector, panel->backlight.min = 0; panel->backlight.level = intel_dp_aux_get_backlight(connector); - panel->backlight.enabled = panel->backlight.level != 0; + panel->backlight.enabled = intel_dp_aux_backlight_dpcd_mode(connector) && + panel->backlight.level != 0; return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c index 8a9d0bdde1bf..40e9cb29233d 100644 --- a/drivers/gpu/drm/i915/display/intel_psr.c +++ b/drivers/gpu/drm/i915/display/intel_psr.c @@ -1754,7 +1754,7 @@ void intel_psr_atomic_check(struct drm_connector *connector, return; intel_connector = to_intel_connector(connector); - dig_port = enc_to_dig_port(intel_attached_encoder(intel_connector)); + dig_port = enc_to_dig_port(to_intel_encoder(new_state->best_encoder)); if (dev_priv->psr.dp != &dig_port->dp) return; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_domain.c b/drivers/gpu/drm/i915/gem/i915_gem_domain.c index 7c90a63c273d..fcce6909f201 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_domain.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_domain.c @@ -509,21 +509,6 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, return -ENOENT; /* - * Already in the desired write domain? Nothing for us to do! - * - * We apply a little bit of cunning here to catch a broader set of - * no-ops. If obj->write_domain is set, we must be in the same - * obj->read_domains, and only that domain. Therefore, if that - * obj->write_domain matches the request read_domains, we are - * already in the same read/write domain and can skip the operation, - * without having to further check the requested write_domain. - */ - if (READ_ONCE(obj->write_domain) == read_domains) { - err = 0; - goto out; - } - - /* * Try to flush the object off the GPU without holding the lock. * We will repeat the flush holding the lock in the normal manner * to catch cases where we are gazumped. @@ -560,6 +545,19 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data, if (err) goto out; + /* + * Already in the desired write domain? Nothing for us to do! + * + * We apply a little bit of cunning here to catch a broader set of + * no-ops. If obj->write_domain is set, we must be in the same + * obj->read_domains, and only that domain. Therefore, if that + * obj->write_domain matches the request read_domains, we are + * already in the same read/write domain and can skip the operation, + * without having to further check the requested write_domain. + */ + if (READ_ONCE(obj->write_domain) == read_domains) + goto out_unpin; + err = i915_gem_object_lock_interruptible(obj, NULL); if (err) goto out_unpin; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c index 4b09bcd70cf4..1904e6e5ea64 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c @@ -287,8 +287,8 @@ struct i915_execbuffer { u64 invalid_flags; /** Set of execobj.flags that are invalid */ u32 context_flags; /** Set of execobj.flags to insert from the ctx */ + u64 batch_len; /** Length of batch within object */ u32 batch_start_offset; /** Location within object of batch */ - u32 batch_len; /** Length of batch within object */ u32 batch_flags; /** Flags composed for emit_bb_start() */ struct intel_gt_buffer_pool_node *batch_pool; /** pool node for batch buffer */ @@ -871,6 +871,10 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb) if (eb->batch_len == 0) eb->batch_len = eb->batch->vma->size - eb->batch_start_offset; + if (unlikely(eb->batch_len == 0)) { /* impossible! */ + drm_dbg(&i915->drm, "Invalid batch length\n"); + return -EINVAL; + } return 0; @@ -2424,7 +2428,7 @@ static int eb_parse(struct i915_execbuffer *eb) struct drm_i915_private *i915 = eb->i915; struct intel_gt_buffer_pool_node *pool = eb->batch_pool; struct i915_vma *shadow, *trampoline, *batch; - unsigned int len; + unsigned long len; int err; if (!eb_use_cmdparser(eb)) { @@ -2449,6 +2453,8 @@ static int eb_parse(struct i915_execbuffer *eb) } else { len += I915_CMD_PARSER_TRAMPOLINE_SIZE; } + if (unlikely(len < eb->batch_len)) /* last paranoid check of overflow */ + return -EINVAL; if (!pool) { pool = intel_gt_get_buffer_pool(eb->engine->gt, len); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h index b5c15557cc87..d6711caa7f39 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h @@ -56,6 +56,8 @@ struct drm_i915_gem_object_ops { void (*truncate)(struct drm_i915_gem_object *obj); void (*writeback)(struct drm_i915_gem_object *obj); + int (*pread)(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *arg); int (*pwrite)(struct drm_i915_gem_object *obj, const struct drm_i915_gem_pwrite *arg); diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c index d6eeefab3d01..f60ca6dc911f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c @@ -162,8 +162,6 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr) { if (is_vmalloc_addr(ptr)) vunmap(ptr); - else - kunmap(kmap_to_page(ptr)); } struct sg_table * @@ -234,34 +232,21 @@ unlock: return err; } -static inline pte_t iomap_pte(resource_size_t base, - dma_addr_t offset, - pgprot_t prot) -{ - return pte_mkspecial(pfn_pte((base + offset) >> PAGE_SHIFT, prot)); -} - /* The 'mapping' part of i915_gem_object_pin_map() below */ -static void *i915_gem_object_map(struct drm_i915_gem_object *obj, - enum i915_map_type type) +static void *i915_gem_object_map_page(struct drm_i915_gem_object *obj, + enum i915_map_type type) { - unsigned long n_pte = obj->base.size >> PAGE_SHIFT; - struct sg_table *sgt = obj->mm.pages; - pte_t *stack[32], **mem; - struct vm_struct *area; + unsigned long n_pages = obj->base.size >> PAGE_SHIFT, i; + struct page *stack[32], **pages = stack, *page; + struct sgt_iter iter; pgprot_t pgprot; + void *vaddr; - if (!i915_gem_object_has_struct_page(obj) && type != I915_MAP_WC) - return NULL; - - if (GEM_WARN_ON(type == I915_MAP_WC && - !static_cpu_has(X86_FEATURE_PAT))) - return NULL; - - /* A single page can always be kmapped */ - if (n_pte == 1 && type == I915_MAP_WB) { - struct page *page = sg_page(sgt->sgl); - + switch (type) { + default: + MISSING_CASE(type); + fallthrough; /* to use PAGE_KERNEL anyway */ + case I915_MAP_WB: /* * On 32b, highmem using a finite set of indirect PTE (i.e. * vmap) to provide virtual mappings of the high pages. @@ -277,33 +262,10 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, * forever. * * So if the page is beyond the 32b boundary, make an explicit - * vmap. On 64b, this check will be optimised away as we can - * directly kmap any page on the system. + * vmap. */ - if (!PageHighMem(page)) - return kmap(page); - } - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - /* Too big for stack -- allocate temporary array instead */ - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } - - area = alloc_vm_area(obj->base.size, mem); - if (!area) { - if (mem != stack) - kvfree(mem); - return NULL; - } - - switch (type) { - default: - MISSING_CASE(type); - fallthrough; /* to use PAGE_KERNEL anyway */ - case I915_MAP_WB: + if (n_pages == 1 && !PageHighMem(sg_page(obj->mm.pages->sgl))) + return page_address(sg_page(obj->mm.pages->sgl)); pgprot = PAGE_KERNEL; break; case I915_MAP_WC: @@ -311,30 +273,50 @@ static void *i915_gem_object_map(struct drm_i915_gem_object *obj, break; } - if (i915_gem_object_has_struct_page(obj)) { - struct sgt_iter iter; - struct page *page; - pte_t **ptes = mem; + if (n_pages > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) + return NULL; + } - for_each_sgt_page(page, iter, sgt) - **ptes++ = mk_pte(page, pgprot); - } else { - resource_size_t iomap; - struct sgt_iter iter; - pte_t **ptes = mem; - dma_addr_t addr; + i = 0; + for_each_sgt_page(page, iter, obj->mm.pages) + pages[i++] = page; + vaddr = vmap(pages, n_pages, 0, pgprot); + if (pages != stack) + kvfree(pages); + return vaddr; +} - iomap = obj->mm.region->iomap.base; - iomap -= obj->mm.region->region.start; +static void *i915_gem_object_map_pfn(struct drm_i915_gem_object *obj, + enum i915_map_type type) +{ + resource_size_t iomap = obj->mm.region->iomap.base - + obj->mm.region->region.start; + unsigned long n_pfn = obj->base.size >> PAGE_SHIFT; + unsigned long stack[32], *pfns = stack, i; + struct sgt_iter iter; + dma_addr_t addr; + void *vaddr; + + if (type != I915_MAP_WC) + return NULL; - for_each_sgt_daddr(addr, iter, sgt) - **ptes++ = iomap_pte(iomap, addr, pgprot); + if (n_pfn > ARRAY_SIZE(stack)) { + /* Too big for stack -- allocate temporary array instead */ + pfns = kvmalloc_array(n_pfn, sizeof(*pfns), GFP_KERNEL); + if (!pfns) + return NULL; } - if (mem != stack) - kvfree(mem); - - return area->addr; + i = 0; + for_each_sgt_daddr(addr, iter, obj->mm.pages) + pfns[i++] = (iomap + addr) >> PAGE_SHIFT; + vaddr = vmap_pfn(pfns, n_pfn, pgprot_writecombine(PAGE_KERNEL_IO)); + if (pfns != stack) + kvfree(pfns); + return vaddr; } /* get, pin, and map the pages of the object into kernel space */ @@ -386,7 +368,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj, } if (!ptr) { - ptr = i915_gem_object_map(obj, type); + if (GEM_WARN_ON(type == I915_MAP_WC && + !static_cpu_has(X86_FEATURE_PAT))) + ptr = NULL; + else if (i915_gem_object_has_struct_page(obj)) + ptr = i915_gem_object_map_page(obj, type); + else + ptr = i915_gem_object_map_pfn(obj, type); if (!ptr) { err = -ENOMEM; goto err_unpin; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_phys.c b/drivers/gpu/drm/i915/gem/i915_gem_phys.c index 28147aab47b9..3a4dfe2ef1da 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_phys.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_phys.c @@ -134,6 +134,58 @@ i915_gem_object_put_pages_phys(struct drm_i915_gem_object *obj, vaddr, dma); } +static int +phys_pwrite(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pwrite *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE | + I915_WAIT_ALL, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + /* + * We manually control the domain here and pretend that it + * remains coherent i.e. in the GTT domain, like shmem_pwrite. + */ + i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); + + if (copy_from_user(vaddr, user_data, args->size)) + return -EFAULT; + + drm_clflush_virt_range(vaddr, args->size); + intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); + + i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); + return 0; +} + +static int +phys_pread(struct drm_i915_gem_object *obj, + const struct drm_i915_gem_pread *args) +{ + void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; + char __user *user_data = u64_to_user_ptr(args->data_ptr); + int err; + + err = i915_gem_object_wait(obj, + I915_WAIT_INTERRUPTIBLE, + MAX_SCHEDULE_TIMEOUT); + if (err) + return err; + + drm_clflush_virt_range(vaddr, args->size); + if (copy_to_user(user_data, vaddr, args->size)) + return -EFAULT; + + return 0; +} + static void phys_release(struct drm_i915_gem_object *obj) { fput(obj->base.filp); @@ -144,6 +196,9 @@ static const struct drm_i915_gem_object_ops i915_gem_phys_ops = { .get_pages = i915_gem_object_get_pages_phys, .put_pages = i915_gem_object_put_pages_phys, + .pread = phys_pread, + .pwrite = phys_pwrite, + .release = phys_release, }; diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c index 0be5e8683337..84b2707d8b17 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c @@ -53,8 +53,10 @@ int i915_gem_stolen_insert_node(struct drm_i915_private *i915, struct drm_mm_node *node, u64 size, unsigned alignment) { - return i915_gem_stolen_insert_node_in_range(i915, node, size, - alignment, 0, U64_MAX); + return i915_gem_stolen_insert_node_in_range(i915, node, + size, alignment, + I915_GEM_STOLEN_BIAS, + U64_MAX); } void i915_gem_stolen_remove_node(struct drm_i915_private *i915, diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h index e15c0adad8af..61e028063f9f 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.h @@ -30,4 +30,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv resource_size_t stolen_offset, resource_size_t size); +#define I915_GEM_STOLEN_BIAS SZ_128K + #endif /* __I915_GEM_STOLEN_H__ */ diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c index 12b30075134a..f2eaed6aca3d 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c @@ -403,6 +403,7 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, unsigned int max_segment = i915_sg_segment_size(); struct sg_table *st; unsigned int sg_page_sizes; + struct scatterlist *sg; int ret; st = kmalloc(sizeof(*st), GFP_KERNEL); @@ -410,13 +411,12 @@ __i915_gem_userptr_alloc_pages(struct drm_i915_gem_object *obj, return ERR_PTR(-ENOMEM); alloc_table: - ret = __sg_alloc_table_from_pages(st, pvec, num_pages, - 0, num_pages << PAGE_SHIFT, - max_segment, - GFP_KERNEL); - if (ret) { + sg = __sg_alloc_table_from_pages(st, pvec, num_pages, 0, + num_pages << PAGE_SHIFT, max_segment, + NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { kfree(st); - return ERR_PTR(ret); + return ERR_CAST(sg); } ret = i915_gem_gtt_prepare_pages(obj, st); diff --git a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c index fd0d24d28763..c30adc05fa98 100644 --- a/drivers/gpu/drm/i915/gt/gen6_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen6_ppgtt.c @@ -239,18 +239,24 @@ static int gen6_ppgtt_init_scratch(struct gen6_ppgtt *ppgtt) I915_CACHE_NONE, PTE_READ_ONLY); vm->scratch[1] = vm->alloc_pt_dma(vm, I915_GTT_PAGE_SIZE_4K); - if (IS_ERR(vm->scratch[1])) - return PTR_ERR(vm->scratch[1]); + if (IS_ERR(vm->scratch[1])) { + ret = PTR_ERR(vm->scratch[1]); + goto err_scratch0; + } ret = pin_pt_dma(vm, vm->scratch[1]); - if (ret) { - i915_gem_object_put(vm->scratch[1]); - return ret; - } + if (ret) + goto err_scratch1; fill32_px(vm->scratch[1], vm->scratch[0]->encode); return 0; + +err_scratch1: + i915_gem_object_put(vm->scratch[1]); +err_scratch0: + i915_gem_object_put(vm->scratch[0]); + return ret; } static void gen6_ppgtt_free_pd(struct gen6_ppgtt *ppgtt) diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index eb64f474a78c..38c7069b7749 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -604,7 +604,8 @@ static int gen8_init_scratch(struct i915_address_space *vm) return 0; free_scratch: - free_scratch(vm); + while (i--) + i915_gem_object_put(vm->scratch[i]); return -ENOMEM; } diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h index 7c3a1012e702..760fefdfe392 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine.h +++ b/drivers/gpu/drm/i915/gt/intel_engine.h @@ -245,22 +245,14 @@ static inline u32 *gen12_emit_pipe_control(u32 *batch, u32 flags0, u32 flags1, u } static inline u32 * -__gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1) +__gen8_emit_write_rcs(u32 *cs, u32 value, u32 offset, u32 flags0, u32 flags1) { - /* We're using qword write, offset should be aligned to 8 bytes. */ - GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); - - /* w/a for post sync ops following a GPGPU operation we - * need a prior CS_STALL, which is emitted by the flush - * following the batch. - */ *cs++ = GFX_OP_PIPE_CONTROL(6) | flags0; - *cs++ = flags1 | PIPE_CONTROL_QW_WRITE | PIPE_CONTROL_GLOBAL_GTT_IVB; - *cs++ = gtt_offset; + *cs++ = flags1 | PIPE_CONTROL_QW_WRITE; + *cs++ = offset; *cs++ = 0; *cs++ = value; - /* We're thrashing one dword of HWS. */ - *cs++ = 0; + *cs++ = 0; /* We're thrashing one extra dword. */ return cs; } @@ -268,13 +260,38 @@ __gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 f static inline u32* gen8_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags) { - return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, 0, flags); + /* We're using qword write, offset should be aligned to 8 bytes. */ + GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); + + return __gen8_emit_write_rcs(cs, + value, + gtt_offset, + 0, + flags | PIPE_CONTROL_GLOBAL_GTT_IVB); } static inline u32* gen12_emit_ggtt_write_rcs(u32 *cs, u32 value, u32 gtt_offset, u32 flags0, u32 flags1) { - return __gen8_emit_ggtt_write_rcs(cs, value, gtt_offset, flags0, flags1); + /* We're using qword write, offset should be aligned to 8 bytes. */ + GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); + + return __gen8_emit_write_rcs(cs, + value, + gtt_offset, + flags0, + flags1 | PIPE_CONTROL_GLOBAL_GTT_IVB); +} + +static inline u32 * +__gen8_emit_flush_dw(u32 *cs, u32 value, u32 gtt_offset, u32 flags) +{ + *cs++ = (MI_FLUSH_DW + 1) | flags; + *cs++ = gtt_offset; + *cs++ = 0; + *cs++ = value; + + return cs; } static inline u32 * @@ -285,12 +302,10 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset, u32 flags) /* Offset should be aligned to 8 bytes for both (QW/DW) write types */ GEM_BUG_ON(!IS_ALIGNED(gtt_offset, 8)); - *cs++ = (MI_FLUSH_DW + 1) | MI_FLUSH_DW_OP_STOREDW | flags; - *cs++ = gtt_offset | MI_FLUSH_DW_USE_GTT; - *cs++ = 0; - *cs++ = value; - - return cs; + return __gen8_emit_flush_dw(cs, + value, + gtt_offset | MI_FLUSH_DW_USE_GTT, + flags | MI_FLUSH_DW_OP_STOREDW); } static inline void __intel_engine_reset(struct intel_engine_cs *engine, diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c index 5bfb5f7ed02c..efdeb7b7b2a0 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c @@ -371,7 +371,8 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine) * instances. */ if ((INTEL_GEN(i915) >= 11 && - engine->gt->info.vdbox_sfc_access & engine->mask) || + (engine->gt->info.vdbox_sfc_access & + BIT(engine->instance))) || (INTEL_GEN(i915) >= 9 && engine->instance == 0)) engine->uabi_capabilities |= I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC; diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h index c400aaa2287b..ee6312601c56 100644 --- a/drivers/gpu/drm/i915/gt/intel_engine_types.h +++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h @@ -278,7 +278,7 @@ struct intel_engine_execlists { * * Note these register may be either mmio or HWSP shadow. */ - u32 *csb_status; + u64 *csb_status; /** * @csb_size: context status buffer FIFO size diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c index 0412a44f25f2..9bb16bdf93cf 100644 --- a/drivers/gpu/drm/i915/gt/intel_lrc.c +++ b/drivers/gpu/drm/i915/gt/intel_lrc.c @@ -1140,9 +1140,8 @@ __unwind_incomplete_requests(struct intel_engine_cs *engine) /* Check in case we rollback so far we wrap [size/2] */ if (intel_ring_direction(rq->ring, - intel_ring_wrap(rq->ring, - rq->tail), - rq->ring->tail) > 0) + rq->tail, + rq->ring->tail + 8) > 0) rq->context->lrc.desc |= CTX_DESC_FORCE_RESTORE; active = rq; @@ -2464,7 +2463,7 @@ cancel_port_requests(struct intel_engine_execlists * const execlists) } static inline void -invalidate_csb_entries(const u32 *first, const u32 *last) +invalidate_csb_entries(const u64 *first, const u64 *last) { clflush((void *)first); clflush((void *)last); @@ -2496,14 +2495,25 @@ invalidate_csb_entries(const u32 *first, const u32 *last) * bits 47-57: sw context id of the lrc the GT switched away from * bits 58-63: sw counter of the lrc the GT switched away from */ -static inline bool -gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) -{ - u32 lower_dw = csb[0]; - u32 upper_dw = csb[1]; - bool ctx_to_valid = GEN12_CSB_CTX_VALID(lower_dw); - bool ctx_away_valid = GEN12_CSB_CTX_VALID(upper_dw); - bool new_queue = lower_dw & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE; +static inline bool gen12_csb_parse(const u64 *csb) +{ + bool ctx_away_valid; + bool new_queue; + u64 entry; + + /* HSD#22011248461 */ + entry = READ_ONCE(*csb); + if (unlikely(entry == -1)) { + preempt_disable(); + if (wait_for_atomic_us((entry = READ_ONCE(*csb)) != -1, 50)) + GEM_WARN_ON("50us CSB timeout"); + preempt_enable(); + } + WRITE_ONCE(*(u64 *)csb, -1); + + ctx_away_valid = GEN12_CSB_CTX_VALID(upper_32_bits(entry)); + new_queue = + lower_32_bits(entry) & GEN12_CTX_STATUS_SWITCHED_TO_NEW_QUEUE; /* * The context switch detail is not guaranteed to be 5 when a preemption @@ -2513,7 +2523,7 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) * would require some extra handling, but we don't support that. */ if (!ctx_away_valid || new_queue) { - GEM_BUG_ON(!ctx_to_valid); + GEM_BUG_ON(!GEN12_CSB_CTX_VALID(lower_32_bits(entry))); return true; } @@ -2522,12 +2532,11 @@ gen12_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) * context switch on an unsuccessful wait instruction since we always * use polling mode. */ - GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_dw)); + GEM_BUG_ON(GEN12_CTX_SWITCH_DETAIL(upper_32_bits(entry))); return false; } -static inline bool -gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) +static inline bool gen8_csb_parse(const u64 *csb) { return *csb & (GEN8_CTX_STATUS_IDLE_ACTIVE | GEN8_CTX_STATUS_PREEMPTED); } @@ -2535,7 +2544,7 @@ gen8_csb_parse(const struct intel_engine_execlists *execlists, const u32 *csb) static void process_csb(struct intel_engine_cs *engine) { struct intel_engine_execlists * const execlists = &engine->execlists; - const u32 * const buf = execlists->csb_status; + const u64 * const buf = execlists->csb_status; const u8 num_entries = execlists->csb_size; u8 head, tail; @@ -2616,12 +2625,14 @@ static void process_csb(struct intel_engine_cs *engine) */ ENGINE_TRACE(engine, "csb[%d]: status=0x%08x:0x%08x\n", - head, buf[2 * head + 0], buf[2 * head + 1]); + head, + upper_32_bits(buf[head]), + lower_32_bits(buf[head])); if (INTEL_GEN(engine->i915) >= 12) - promote = gen12_csb_parse(execlists, buf + 2 * head); + promote = gen12_csb_parse(buf + head); else - promote = gen8_csb_parse(execlists, buf + 2 * head); + promote = gen8_csb_parse(buf + head); if (promote) { struct i915_request * const *old = execlists->active; @@ -2649,6 +2660,9 @@ static void process_csb(struct intel_engine_cs *engine) smp_wmb(); /* complete the seqlock */ WRITE_ONCE(execlists->active, execlists->inflight); + /* XXX Magic delay for tgl */ + ENGINE_POSTING_READ(engine, RING_CONTEXT_STATUS_PTR); + WRITE_ONCE(execlists->pending[0], NULL); } else { if (GEM_WARN_ON(!*execlists->active)) { @@ -3533,6 +3547,19 @@ static const struct intel_context_ops execlists_context_ops = { .destroy = execlists_context_destroy, }; +static u32 hwsp_offset(const struct i915_request *rq) +{ + const struct intel_timeline_cacheline *cl; + + /* Before the request is executed, the timeline/cachline is fixed */ + + cl = rcu_dereference_protected(rq->hwsp_cacheline, 1); + if (cl) + return cl->ggtt_offset; + + return rcu_dereference_protected(rq->timeline, 1)->hwsp_offset; +} + static int gen8_emit_init_breadcrumb(struct i915_request *rq) { u32 *cs; @@ -3555,7 +3582,7 @@ static int gen8_emit_init_breadcrumb(struct i915_request *rq) *cs++ = MI_NOOP; *cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT; - *cs++ = i915_request_timeline(rq)->hwsp_offset; + *cs++ = hwsp_offset(rq); *cs++ = 0; *cs++ = rq->fence.seqno - 1; @@ -4005,6 +4032,8 @@ static void reset_csb_pointers(struct intel_engine_cs *engine) WRITE_ONCE(*execlists->csb_write, reset_value); wmb(); /* Make sure this is visible to HW (paranoia?) */ + /* Check that the GPU does indeed update the CSB entries! */ + memset(execlists->csb_status, -1, (reset_value + 1) * sizeof(u64)); invalidate_csb_entries(&execlists->csb_status[0], &execlists->csb_status[reset_value]); @@ -4870,11 +4899,9 @@ gen8_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs) return gen8_emit_wa_tail(request, cs); } -static u32 *emit_xcs_breadcrumb(struct i915_request *request, u32 *cs) +static u32 *emit_xcs_breadcrumb(struct i915_request *rq, u32 *cs) { - u32 addr = i915_request_active_timeline(request)->hwsp_offset; - - return gen8_emit_ggtt_write(cs, request->fence.seqno, addr, 0); + return gen8_emit_ggtt_write(cs, rq->fence.seqno, hwsp_offset(rq), 0); } static u32 *gen8_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs) @@ -4893,7 +4920,7 @@ static u32 *gen8_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) /* XXX flush+write+CS_STALL all in one upsets gem_concurrent_blt:kbl */ cs = gen8_emit_ggtt_write_rcs(cs, request->fence.seqno, - i915_request_active_timeline(request)->hwsp_offset, + hwsp_offset(request), PIPE_CONTROL_FLUSH_ENABLE | PIPE_CONTROL_CS_STALL); @@ -4905,7 +4932,7 @@ gen11_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) { cs = gen8_emit_ggtt_write_rcs(cs, request->fence.seqno, - i915_request_active_timeline(request)->hwsp_offset, + hwsp_offset(request), PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TILE_CACHE_FLUSH | PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH | @@ -4967,7 +4994,9 @@ gen12_emit_fini_breadcrumb_tail(struct i915_request *request, u32 *cs) static u32 *gen12_emit_fini_breadcrumb(struct i915_request *rq, u32 *cs) { - return gen12_emit_fini_breadcrumb_tail(rq, emit_xcs_breadcrumb(rq, cs)); + /* XXX Stalling flush before seqno write; post-sync not */ + cs = emit_xcs_breadcrumb(rq, __gen8_emit_flush_dw(cs, 0, 0, 0)); + return gen12_emit_fini_breadcrumb_tail(rq, cs); } static u32 * @@ -4975,7 +5004,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs) { cs = gen12_emit_ggtt_write_rcs(cs, request->fence.seqno, - i915_request_active_timeline(request)->hwsp_offset, + hwsp_offset(request), PIPE_CONTROL0_HDC_PIPELINE_FLUSH, PIPE_CONTROL_CS_STALL | PIPE_CONTROL_TILE_CACHE_FLUSH | @@ -5157,7 +5186,7 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine) } execlists->csb_status = - &engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX]; + (u64 *)&engine->status_page.addr[I915_HWS_CSB_BUF0_INDEX]; execlists->csb_write = &engine->status_page.addr[intel_hws_csb_write_index(i915)]; @@ -5428,6 +5457,7 @@ static void virtual_context_destroy(struct kref *kref) __execlists_context_fini(&ve->context); intel_context_fini(&ve->context); + intel_breadcrumbs_free(ve->base.breadcrumbs); intel_engine_free_request_pool(&ve->base); kfree(ve->bonds); diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c index 632e08a4592b..313e51e7d4f7 100644 --- a/drivers/gpu/drm/i915/gt/intel_mocs.c +++ b/drivers/gpu/drm/i915/gt/intel_mocs.c @@ -234,11 +234,18 @@ static const struct drm_i915_mocs_entry broxton_mocs_table[] = { L3_1_UC) static const struct drm_i915_mocs_entry tgl_mocs_table[] = { - /* Base - Error (Reserved for Non-Use) */ - MOCS_ENTRY(0, 0x0, 0x0), - /* Base - Reserved */ - MOCS_ENTRY(1, 0x0, 0x0), - + /* + * NOTE: + * Reserved and unspecified MOCS indices have been set to (L3 + LCC). + * These reserved entries should never be used, they may be changed + * to low performant variants with better coherency in the future if + * more entries are needed. We are programming index I915_MOCS_PTE(1) + * only, __init_mocs_table() take care to program unused index with + * this entry. + */ + MOCS_ENTRY(I915_MOCS_PTE, + LE_0_PAGETABLE | LE_TC_0_PAGETABLE, + L3_1_UC), GEN11_MOCS_ENTRIES, /* Implicitly enable L1 - HDC:L1 + L3 + LLC */ diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c index ab675d35030d..d7b8e4457fc2 100644 --- a/drivers/gpu/drm/i915/gt/intel_rc6.c +++ b/drivers/gpu/drm/i915/gt/intel_rc6.c @@ -56,9 +56,12 @@ static inline void set(struct intel_uncore *uncore, i915_reg_t reg, u32 val) static void gen11_rc6_enable(struct intel_rc6 *rc6) { - struct intel_uncore *uncore = rc6_to_uncore(rc6); + struct intel_gt *gt = rc6_to_gt(rc6); + struct intel_uncore *uncore = gt->uncore; struct intel_engine_cs *engine; enum intel_engine_id id; + u32 pg_enable; + int i; /* 2b: Program RC6 thresholds.*/ set(uncore, GEN6_RC6_WAKE_RATE_LIMIT, 54 << 16 | 85); @@ -102,10 +105,19 @@ static void gen11_rc6_enable(struct intel_rc6 *rc6) GEN6_RC_CTL_RC6_ENABLE | GEN6_RC_CTL_EI_MODE(1); - set(uncore, GEN9_PG_ENABLE, - GEN9_RENDER_PG_ENABLE | - GEN9_MEDIA_PG_ENABLE | - GEN11_MEDIA_SAMPLER_PG_ENABLE); + pg_enable = + GEN9_RENDER_PG_ENABLE | + GEN9_MEDIA_PG_ENABLE | + GEN11_MEDIA_SAMPLER_PG_ENABLE; + + if (INTEL_GEN(gt->i915) >= 12) { + for (i = 0; i < I915_MAX_VCS; i++) + if (HAS_ENGINE(gt, _VCS(i))) + pg_enable |= (VDN_HCP_POWERGATE_ENABLE(i) | + VDN_MFX_POWERGATE_ENABLE(i)); + } + + set(uncore, GEN9_PG_ENABLE, pg_enable); } static void gen9_rc6_enable(struct intel_rc6 *rc6) diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c index a2f74cefe4c3..7ea94d201fe6 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline.c +++ b/drivers/gpu/drm/i915/gt/intel_timeline.c @@ -188,10 +188,14 @@ cacheline_alloc(struct intel_timeline_hwsp *hwsp, unsigned int cacheline) return cl; } -static void cacheline_acquire(struct intel_timeline_cacheline *cl) +static void cacheline_acquire(struct intel_timeline_cacheline *cl, + u32 ggtt_offset) { - if (cl) - i915_active_acquire(&cl->active); + if (!cl) + return; + + cl->ggtt_offset = ggtt_offset; + i915_active_acquire(&cl->active); } static void cacheline_release(struct intel_timeline_cacheline *cl) @@ -340,7 +344,7 @@ int intel_timeline_pin(struct intel_timeline *tl, struct i915_gem_ww_ctx *ww) GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n", tl->fence_context, tl->hwsp_offset); - cacheline_acquire(tl->hwsp_cacheline); + cacheline_acquire(tl->hwsp_cacheline, tl->hwsp_offset); if (atomic_fetch_inc(&tl->pin_count)) { cacheline_release(tl->hwsp_cacheline); __i915_vma_unpin(tl->hwsp_ggtt); @@ -515,7 +519,7 @@ __intel_timeline_get_seqno(struct intel_timeline *tl, GT_TRACE(tl->gt, "timeline:%llx using HWSP offset:%x\n", tl->fence_context, tl->hwsp_offset); - cacheline_acquire(cl); + cacheline_acquire(cl, tl->hwsp_offset); tl->hwsp_cacheline = cl; *seqno = timeline_advance(tl); @@ -573,9 +577,7 @@ int intel_timeline_read_hwsp(struct i915_request *from, if (err) goto out; - *hwsp = i915_ggtt_offset(cl->hwsp->vma) + - ptr_unmask_bits(cl->vaddr, CACHELINE_BITS) * CACHELINE_BYTES; - + *hwsp = cl->ggtt_offset; out: i915_active_release(&cl->active); return err; diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h index 02181c5020db..4474f487f589 100644 --- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h +++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h @@ -94,6 +94,8 @@ struct intel_timeline_cacheline { struct intel_timeline_hwsp *hwsp; void *vaddr; + u32 ggtt_offset; + struct rcu_head rcu; }; diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c index 6c580d0d9ea8..4a3bde7c9f21 100644 --- a/drivers/gpu/drm/i915/gt/intel_workarounds.c +++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c @@ -131,8 +131,10 @@ static void _wa_add(struct i915_wa_list *wal, const struct i915_wa *wa) return; } - if (wal->list) + if (wal->list) { memcpy(list, wal->list, sizeof(*wa) * wal->count); + kfree(wal->list); + } wal->list = list; } diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c index 35406ecdf0b2..ef5aeebbeeb0 100644 --- a/drivers/gpu/drm/i915/gt/selftest_reset.c +++ b/drivers/gpu/drm/i915/gt/selftest_reset.c @@ -3,9 +3,203 @@ * Copyright © 2018 Intel Corporation */ +#include <linux/crc32.h> + +#include "gem/i915_gem_stolen.h" + +#include "i915_memcpy.h" #include "i915_selftest.h" #include "selftests/igt_reset.h" #include "selftests/igt_atomic.h" +#include "selftests/igt_spinner.h" + +static int +__igt_reset_stolen(struct intel_gt *gt, + intel_engine_mask_t mask, + const char *msg) +{ + struct i915_ggtt *ggtt = >->i915->ggtt; + const struct resource *dsm = >->i915->dsm; + resource_size_t num_pages, page; + struct intel_engine_cs *engine; + intel_wakeref_t wakeref; + enum intel_engine_id id; + struct igt_spinner spin; + long max, count; + void *tmp; + u32 *crc; + int err; + + if (!drm_mm_node_allocated(&ggtt->error_capture)) + return 0; + + num_pages = resource_size(dsm) >> PAGE_SHIFT; + if (!num_pages) + return 0; + + crc = kmalloc_array(num_pages, sizeof(u32), GFP_KERNEL); + if (!crc) + return -ENOMEM; + + tmp = kmalloc(PAGE_SIZE, GFP_KERNEL); + if (!tmp) { + err = -ENOMEM; + goto err_crc; + } + + igt_global_reset_lock(gt); + wakeref = intel_runtime_pm_get(gt->uncore->rpm); + + err = igt_spinner_init(&spin, gt); + if (err) + goto err_lock; + + for_each_engine(engine, gt, id) { + struct intel_context *ce; + struct i915_request *rq; + + if (!(mask & engine->mask)) + continue; + + if (!intel_engine_can_store_dword(engine)) + continue; + + ce = intel_context_create(engine); + if (IS_ERR(ce)) { + err = PTR_ERR(ce); + goto err_spin; + } + rq = igt_spinner_create_request(&spin, ce, MI_ARB_CHECK); + intel_context_put(ce); + if (IS_ERR(rq)) { + err = PTR_ERR(rq); + goto err_spin; + } + i915_request_add(rq); + } + + for (page = 0; page < num_pages; page++) { + dma_addr_t dma = (dma_addr_t)dsm->start + (page << PAGE_SHIFT); + void __iomem *s; + void *in; + + ggtt->vm.insert_page(&ggtt->vm, dma, + ggtt->error_capture.start, + I915_CACHE_NONE, 0); + mb(); + + s = io_mapping_map_wc(&ggtt->iomap, + ggtt->error_capture.start, + PAGE_SIZE); + + if (!__drm_mm_interval_first(>->i915->mm.stolen, + page << PAGE_SHIFT, + ((page + 1) << PAGE_SHIFT) - 1)) + memset32(s, STACK_MAGIC, PAGE_SIZE / sizeof(u32)); + + in = s; + if (i915_memcpy_from_wc(tmp, s, PAGE_SIZE)) + in = tmp; + crc[page] = crc32_le(0, in, PAGE_SIZE); + + io_mapping_unmap(s); + } + mb(); + ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE); + + if (mask == ALL_ENGINES) { + intel_gt_reset(gt, mask, NULL); + } else { + for_each_engine(engine, gt, id) { + if (mask & engine->mask) + intel_engine_reset(engine, NULL); + } + } + + max = -1; + count = 0; + for (page = 0; page < num_pages; page++) { + dma_addr_t dma = (dma_addr_t)dsm->start + (page << PAGE_SHIFT); + void __iomem *s; + void *in; + u32 x; + + ggtt->vm.insert_page(&ggtt->vm, dma, + ggtt->error_capture.start, + I915_CACHE_NONE, 0); + mb(); + + s = io_mapping_map_wc(&ggtt->iomap, + ggtt->error_capture.start, + PAGE_SIZE); + + in = s; + if (i915_memcpy_from_wc(tmp, s, PAGE_SIZE)) + in = tmp; + x = crc32_le(0, in, PAGE_SIZE); + + if (x != crc[page] && + !__drm_mm_interval_first(>->i915->mm.stolen, + page << PAGE_SHIFT, + ((page + 1) << PAGE_SHIFT) - 1)) { + pr_debug("unused stolen page %pa modified by GPU reset\n", + &page); + if (count++ == 0) + igt_hexdump(in, PAGE_SIZE); + max = page; + } + + io_mapping_unmap(s); + } + mb(); + ggtt->vm.clear_range(&ggtt->vm, ggtt->error_capture.start, PAGE_SIZE); + + if (count > 0) { + pr_info("%s reset clobbered %ld pages of stolen, last clobber at page %ld\n", + msg, count, max); + } + if (max >= I915_GEM_STOLEN_BIAS >> PAGE_SHIFT) { + pr_err("%s reset clobbered unreserved area [above %x] of stolen; may cause severe faults\n", + msg, I915_GEM_STOLEN_BIAS); + err = -EINVAL; + } + +err_spin: + igt_spinner_fini(&spin); + +err_lock: + intel_runtime_pm_put(gt->uncore->rpm, wakeref); + igt_global_reset_unlock(gt); + + kfree(tmp); +err_crc: + kfree(crc); + return err; +} + +static int igt_reset_device_stolen(void *arg) +{ + return __igt_reset_stolen(arg, ALL_ENGINES, "device"); +} + +static int igt_reset_engines_stolen(void *arg) +{ + struct intel_gt *gt = arg; + struct intel_engine_cs *engine; + enum intel_engine_id id; + int err; + + if (!intel_has_reset_engine(gt)) + return 0; + + for_each_engine(engine, gt, id) { + err = __igt_reset_stolen(gt, engine->mask, engine->name); + if (err) + return err; + } + + return 0; +} static int igt_global_reset(void *arg) { @@ -164,6 +358,8 @@ int intel_reset_live_selftests(struct drm_i915_private *i915) { static const struct i915_subtest tests[] = { SUBTEST(igt_global_reset), /* attempt to recover GPU first */ + SUBTEST(igt_reset_device_stolen), + SUBTEST(igt_reset_engines_stolen), SUBTEST(igt_wedged_reset), SUBTEST(igt_atomic_reset), SUBTEST(igt_atomic_engine_reset), diff --git a/drivers/gpu/drm/i915/gt/shmem_utils.c b/drivers/gpu/drm/i915/gt/shmem_utils.c index 43c7acbdc79d..f011ea42487e 100644 --- a/drivers/gpu/drm/i915/gt/shmem_utils.c +++ b/drivers/gpu/drm/i915/gt/shmem_utils.c @@ -49,80 +49,40 @@ struct file *shmem_create_from_object(struct drm_i915_gem_object *obj) return file; } -static size_t shmem_npte(struct file *file) -{ - return file->f_mapping->host->i_size >> PAGE_SHIFT; -} - -static void __shmem_unpin_map(struct file *file, void *ptr, size_t n_pte) -{ - unsigned long pfn; - - vunmap(ptr); - - for (pfn = 0; pfn < n_pte; pfn++) { - struct page *page; - - page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, - GFP_KERNEL); - if (!WARN_ON(IS_ERR(page))) { - put_page(page); - put_page(page); - } - } -} - void *shmem_pin_map(struct file *file) { - const size_t n_pte = shmem_npte(file); - pte_t *stack[32], **ptes, **mem; - struct vm_struct *area; - unsigned long pfn; - - mem = stack; - if (n_pte > ARRAY_SIZE(stack)) { - mem = kvmalloc_array(n_pte, sizeof(*mem), GFP_KERNEL); - if (!mem) - return NULL; - } + struct page **pages; + size_t n_pages, i; + void *vaddr; - area = alloc_vm_area(n_pte << PAGE_SHIFT, mem); - if (!area) { - if (mem != stack) - kvfree(mem); + n_pages = file->f_mapping->host->i_size >> PAGE_SHIFT; + pages = kvmalloc_array(n_pages, sizeof(*pages), GFP_KERNEL); + if (!pages) return NULL; - } - ptes = mem; - for (pfn = 0; pfn < n_pte; pfn++) { - struct page *page; - - page = shmem_read_mapping_page_gfp(file->f_mapping, pfn, - GFP_KERNEL); - if (IS_ERR(page)) + for (i = 0; i < n_pages; i++) { + pages[i] = shmem_read_mapping_page_gfp(file->f_mapping, i, + GFP_KERNEL); + if (IS_ERR(pages[i])) goto err_page; - - **ptes++ = mk_pte(page, PAGE_KERNEL); } - if (mem != stack) - kvfree(mem); - + vaddr = vmap(pages, n_pages, VM_MAP_PUT_PAGES, PAGE_KERNEL); + if (!vaddr) + goto err_page; mapping_set_unevictable(file->f_mapping); - return area->addr; - + return vaddr; err_page: - if (mem != stack) - kvfree(mem); - - __shmem_unpin_map(file, area->addr, pfn); + while (--i >= 0) + put_page(pages[i]); + kvfree(pages); return NULL; } void shmem_unpin_map(struct file *file, void *ptr) { mapping_clear_unevictable(file->f_mapping); - __shmem_unpin_map(file, ptr, shmem_npte(file)); + vfree(ptr); } static int __shmem_rw(struct file *file, loff_t off, diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c index 7ba16ddfe75f..d7898e87791f 100644 --- a/drivers/gpu/drm/i915/gvt/display.c +++ b/drivers/gpu/drm/i915/gvt/display.c @@ -164,7 +164,7 @@ static unsigned char virtual_dp_monitor_edid[GVT_EDID_NUM][EDID_SIZE] = { /* let the virtual display supports DP1.2 */ static u8 dpcd_fix_data[DPCD_HEADER_SIZE] = { - 0x12, 0x014, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 + 0x12, 0x014, 0x84, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; static void emulate_monitor_status_change(struct intel_vgpu *vgpu) diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 3be37e6fe33d..eb342a759943 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1489,7 +1489,8 @@ static int hws_pga_write(struct intel_vgpu *vgpu, unsigned int offset, const struct intel_engine_cs *engine = intel_gvt_render_mmio_to_engine(vgpu->gvt, offset); - if (!intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) { + if (value != 0 && + !intel_gvt_ggtt_validate_range(vgpu, value, I915_GTT_PAGE_SIZE)) { gvt_vgpu_err("write invalid HWSP address, reg:0x%x, value:0x%x\n", offset, value); return -EINVAL; @@ -1650,6 +1651,34 @@ static int edp_psr_imr_iir_write(struct intel_vgpu *vgpu, return 0; } +/** + * FixMe: + * If guest fills non-priv batch buffer on ApolloLake/Broxton as Mesa i965 did: + * 717e7539124d (i965: Use a WC map and memcpy for the batch instead of pwrite.) + * Due to the missing flush of bb filled by VM vCPU, host GPU hangs on executing + * these MI_BATCH_BUFFER. + * Temporarily workaround this by setting SNOOP bit for PAT3 used by PPGTT + * PML4 PTE: PAT(0) PCD(1) PWT(1). + * The performance is still expected to be low, will need further improvement. + */ +static int bxt_ppat_low_write(struct intel_vgpu *vgpu, unsigned int offset, + void *p_data, unsigned int bytes) +{ + u64 pat = + GEN8_PPAT(0, CHV_PPAT_SNOOP) | + GEN8_PPAT(1, 0) | + GEN8_PPAT(2, 0) | + GEN8_PPAT(3, CHV_PPAT_SNOOP) | + GEN8_PPAT(4, CHV_PPAT_SNOOP) | + GEN8_PPAT(5, CHV_PPAT_SNOOP) | + GEN8_PPAT(6, CHV_PPAT_SNOOP) | + GEN8_PPAT(7, CHV_PPAT_SNOOP); + + vgpu_vreg(vgpu, offset) = lower_32_bits(pat); + + return 0; +} + static int guc_status_read(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) @@ -2812,7 +2841,7 @@ static int init_bdw_mmio_info(struct intel_gvt *gvt) MMIO_DH(GEN6_PCODE_MAILBOX, D_BDW_PLUS, NULL, mailbox_write); - MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS); + MMIO_D(GEN8_PRIVATE_PAT_LO, D_BDW_PLUS & ~D_BXT); MMIO_D(GEN8_PRIVATE_PAT_HI, D_BDW_PLUS); MMIO_D(GAMTARBMODE, D_BDW_PLUS); @@ -3139,7 +3168,7 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) NULL, NULL); MMIO_DFH(GAMT_CHKN_BIT_REG, D_KBL | D_CFL, F_CMD_ACCESS, NULL, NULL); - MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS); + MMIO_D(GEN9_CTX_PREEMPT_REG, D_SKL_PLUS & ~D_BXT); return 0; } @@ -3313,9 +3342,21 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt) MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT); MMIO_D(GEN6_GFXPAUSE, D_BXT); MMIO_DFH(GEN8_L3SQCREG1, D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(GEN8_L3CNTLREG, D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_DFH(_MMIO(0x20D8), D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(RENDER_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(GEN6_BSD_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(BLT_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); + MMIO_F(GEN8_RING_CS_GPR(VEBOX_RING_BASE, 0), 0x40, F_CMD_ACCESS, + 0, 0, D_BXT, NULL, NULL); MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL); + MMIO_DH(GEN8_PRIVATE_PAT_LO, D_BXT, NULL, bxt_ppat_low_write); + return 0; } diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index ad8a9df49f29..778eb8cab610 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -829,8 +829,10 @@ static int intel_vgpu_open(struct mdev_device *mdev) /* Take a module reference as mdev core doesn't take * a reference for vendor driver. */ - if (!try_module_get(THIS_MODULE)) + if (!try_module_get(THIS_MODULE)) { + ret = -ENODEV; goto undo_group; + } ret = kvmgt_guest_init(mdev); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c index 1570eb8aa978..aed2ef6466a2 100644 --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@ -1277,7 +1277,7 @@ void intel_vgpu_clean_submission(struct intel_vgpu *vgpu) i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(s->shadow[0]->vm)); for_each_engine(engine, vgpu->gvt->gt, id) - intel_context_unpin(s->shadow[id]); + intel_context_put(s->shadow[id]); kmem_cache_destroy(s->workloads); } @@ -1369,11 +1369,6 @@ int intel_vgpu_setup_submission(struct intel_vgpu *vgpu) ce->ring = __intel_context_ring_size(ring_size); } - ret = intel_context_pin(ce); - intel_context_put(ce); - if (ret) - goto out_shadow_ctx; - s->shadow[i] = ce; } @@ -1405,7 +1400,6 @@ out_shadow_ctx: if (IS_ERR(s->shadow[i])) break; - intel_context_unpin(s->shadow[i]); intel_context_put(s->shadow[i]); } i915_vm_put(&ppgtt->vm); @@ -1479,6 +1473,7 @@ void intel_vgpu_destroy_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu_submission *s = &workload->vgpu->submission; + intel_context_unpin(s->shadow[workload->engine->id]); release_shadow_batch_buffer(workload); release_shadow_wa_ctx(&workload->wa_ctx); @@ -1724,6 +1719,12 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, return ERR_PTR(ret); } + ret = intel_context_pin(s->shadow[engine->id]); + if (ret) { + intel_vgpu_destroy_workload(workload); + return ERR_PTR(ret); + } + return workload; } diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c index f6d7e33c7099..399582aeeefb 100644 --- a/drivers/gpu/drm/i915/gvt/vgpu.c +++ b/drivers/gpu/drm/i915/gvt/vgpu.c @@ -439,7 +439,8 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt, if (IS_BROADWELL(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B); - else + /* FixMe: Re-enable APL/BXT once vfio_edid enabled */ + else if (!IS_BROXTON(dev_priv)) ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D); if (ret) goto out_clean_sched_policy; diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index eef9a821c49c..8426d5974669 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -33,6 +33,8 @@ #include <uapi/drm/i915_drm.h> #include <uapi/drm/drm_fourcc.h> +#include <asm/hypervisor.h> + #include <linux/io-mapping.h> #include <linux/i2c.h> #include <linux/i2c-algo-bit.h> @@ -1760,7 +1762,9 @@ static inline bool intel_vtd_active(void) if (intel_iommu_gfx_mapped) return true; #endif - return false; + + /* Running as a guest, we assume the host is enforcing VT'd */ + return !hypervisor_is_type(X86_HYPER_NATIVE); } static inline bool intel_scanout_needs_vtd_wa(struct drm_i915_private *dev_priv) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index bb0c12975f38..58276694c848 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -180,30 +180,6 @@ try_again: } static int -i915_gem_phys_pwrite(struct drm_i915_gem_object *obj, - struct drm_i915_gem_pwrite *args, - struct drm_file *file) -{ - void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset; - char __user *user_data = u64_to_user_ptr(args->data_ptr); - - /* - * We manually control the domain here and pretend that it - * remains coherent i.e. in the GTT domain, like shmem_pwrite. - */ - i915_gem_object_invalidate_frontbuffer(obj, ORIGIN_CPU); - - if (copy_from_user(vaddr, user_data, args->size)) - return -EFAULT; - - drm_clflush_virt_range(vaddr, args->size); - intel_gt_chipset_flush(&to_i915(obj->base.dev)->gt); - - i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU); - return 0; -} - -static int i915_gem_create(struct drm_file *file, struct intel_memory_region *mr, u64 *size_p, @@ -527,6 +503,12 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data, trace_i915_gem_object_pread(obj, args->offset, args->size); + ret = -ENODEV; + if (obj->ops->pread) + ret = obj->ops->pread(obj, args); + if (ret != -ENODEV) + goto out; + ret = i915_gem_object_wait(obj, I915_WAIT_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); @@ -866,8 +848,6 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data, if (ret == -EFAULT || ret == -ENOSPC) { if (i915_gem_object_has_struct_page(obj)) ret = i915_gem_shmem_pwrite(obj, args); - else - ret = i915_gem_phys_pwrite(obj, args, file); } i915_gem_object_unpin_pages(obj); diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index a635ec8d0b94..cf6e47adfde6 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1312,7 +1312,7 @@ capture_vma(struct intel_engine_capture_vma *next, } strcpy(c->name, name); - c->vma = i915_vma_get(vma); + c->vma = vma; /* reference held while active */ c->next = next; return c; @@ -1402,7 +1402,6 @@ intel_engine_coredump_add_vma(struct intel_engine_coredump *ee, compress)); i915_active_release(&vma->active); - i915_vma_put(vma); capture = this->next; kfree(this); diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c index 366ddfc8df6b..fb5e30de78c2 100644 --- a/drivers/gpu/drm/i915/i915_pci.c +++ b/drivers/gpu/drm/i915/i915_pci.c @@ -389,6 +389,7 @@ static const struct intel_device_info ilk_m_info = { GEN5_FEATURES, PLATFORM(INTEL_IRONLAKE), .is_mobile = 1, + .has_rps = true, .display.has_fbc = 1, }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index d805d4da6181..664f3bf9af03 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -8971,10 +8971,6 @@ enum { #define GEN9_PWRGT_MEDIA_STATUS_MASK (1 << 0) #define GEN9_PWRGT_RENDER_STATUS_MASK (1 << 1) -#define POWERGATE_ENABLE _MMIO(0xa210) -#define VDN_HCP_POWERGATE_ENABLE(n) BIT(((n) * 2) + 3) -#define VDN_MFX_POWERGATE_ENABLE(n) BIT(((n) * 2) + 4) - #define GTFIFODBG _MMIO(0x120000) #define GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV (0x1f << 20) #define GT_FIFO_FREE_ENTRIES_CHV (0x7f << 13) @@ -9114,9 +9110,11 @@ enum { #define GEN9_MEDIA_PG_IDLE_HYSTERESIS _MMIO(0xA0C4) #define GEN9_RENDER_PG_IDLE_HYSTERESIS _MMIO(0xA0C8) #define GEN9_PG_ENABLE _MMIO(0xA210) -#define GEN9_RENDER_PG_ENABLE REG_BIT(0) -#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) -#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define GEN9_RENDER_PG_ENABLE REG_BIT(0) +#define GEN9_MEDIA_PG_ENABLE REG_BIT(1) +#define GEN11_MEDIA_SAMPLER_PG_ENABLE REG_BIT(2) +#define VDN_HCP_POWERGATE_ENABLE(n) REG_BIT(3 + 2 * (n)) +#define VDN_MFX_POWERGATE_ENABLE(n) REG_BIT(4 + 2 * (n)) #define GEN8_PUSHBUS_CONTROL _MMIO(0xA248) #define GEN8_PUSHBUS_ENABLE _MMIO(0xA250) #define GEN8_PUSHBUS_SHIFT _MMIO(0xA25C) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index ffb5287e055a..caa9b041616b 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -314,8 +314,10 @@ static void __vma_release(struct dma_fence_work *work) { struct i915_vma_work *vw = container_of(work, typeof(*vw), base); - if (vw->pinned) + if (vw->pinned) { __i915_gem_object_unpin_pages(vw->pinned); + i915_gem_object_put(vw->pinned); + } i915_vm_free_pt_stash(vw->vm, &vw->stash); i915_vm_put(vw->vm); @@ -431,7 +433,7 @@ int i915_vma_bind(struct i915_vma *vma, if (vma->obj) { __i915_gem_object_pin_pages(vma->obj); - work->pinned = vma->obj; + work->pinned = i915_gem_object_get(vma->obj); } } else { vma->ops->bind_vma(vma->vm, NULL, vma, cache_level, bind_flags); diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c index 6b5e9d88646d..180e1078ef7c 100644 --- a/drivers/gpu/drm/i915/intel_memory_region.c +++ b/drivers/gpu/drm/i915/intel_memory_region.c @@ -87,7 +87,7 @@ __intel_memory_region_get_pages_buddy(struct intel_memory_region *mem, min_order = ilog2(size) - ilog2(mem->mm.chunk_size); } - if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size) + if (size > mem->mm.size) return -E2BIG; n_pages = size >> ilog2(mem->mm.chunk_size); diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 34e0d22d456b..cfb806767fc5 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -7118,23 +7118,10 @@ static void icl_init_clock_gating(struct drm_i915_private *dev_priv) static void tgl_init_clock_gating(struct drm_i915_private *dev_priv) { - u32 vd_pg_enable = 0; - unsigned int i; - /* Wa_1409120013:tgl */ I915_WRITE(ILK_DPFC_CHICKEN, ILK_DPFC_CHICKEN_COMP_DUMMY_PIXEL); - /* This is not a WA. Enable VD HCP & MFX_ENC powergate */ - for (i = 0; i < I915_MAX_VCS; i++) { - if (HAS_ENGINE(&dev_priv->gt, _VCS(i))) - vd_pg_enable |= VDN_HCP_POWERGATE_ENABLE(i) | - VDN_MFX_POWERGATE_ENABLE(i); - } - - I915_WRITE(POWERGATE_ENABLE, - I915_READ(POWERGATE_ENABLE) | vd_pg_enable); - /* Wa_1409825376:tgl (pre-prod)*/ if (IS_TGL_DISP_REVID(dev_priv, TGL_REVID_A0, TGL_REVID_B1)) I915_WRITE(GEN9_CLKGATE_DIS_3, I915_READ(GEN9_CLKGATE_DIS_3) | diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c index 263ffcb832b7..97ded2a59cf4 100644 --- a/drivers/gpu/drm/i915/intel_uncore.c +++ b/drivers/gpu/drm/i915/intel_uncore.c @@ -1209,6 +1209,18 @@ unclaimed_reg_debug(struct intel_uncore *uncore, spin_unlock(&uncore->debug->lock); } +#define __vgpu_read(x) \ +static u##x \ +vgpu_read##x(struct intel_uncore *uncore, i915_reg_t reg, bool trace) { \ + u##x val = __raw_uncore_read##x(uncore, reg); \ + trace_i915_reg_rw(false, reg, val, sizeof(val), trace); \ + return val; \ +} +__vgpu_read(8) +__vgpu_read(16) +__vgpu_read(32) +__vgpu_read(64) + #define GEN2_READ_HEADER(x) \ u##x val = 0; \ assert_rpm_wakelock_held(uncore->rpm); @@ -1414,6 +1426,16 @@ __gen_reg_write_funcs(gen8); #undef GEN6_WRITE_FOOTER #undef GEN6_WRITE_HEADER +#define __vgpu_write(x) \ +static void \ +vgpu_write##x(struct intel_uncore *uncore, i915_reg_t reg, u##x val, bool trace) { \ + trace_i915_reg_rw(true, reg, val, sizeof(val), trace); \ + __raw_uncore_write##x(uncore, reg, val); \ +} +__vgpu_write(8) +__vgpu_write(16) +__vgpu_write(32) + #define ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, x) \ do { \ (uncore)->funcs.mmio_writeb = x##_write8; \ @@ -1735,7 +1757,10 @@ static void uncore_raw_init(struct intel_uncore *uncore) { GEM_BUG_ON(intel_uncore_has_forcewake(uncore)); - if (IS_GEN(uncore->i915, 5)) { + if (intel_vgpu_active(uncore->i915)) { + ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, vgpu); + ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, vgpu); + } else if (IS_GEN(uncore->i915, 5)) { ASSIGN_RAW_WRITE_MMIO_VFUNCS(uncore, gen5); ASSIGN_RAW_READ_MMIO_VFUNCS(uncore, gen5); } else { diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c index 64bbb8288249..e424a6d1a68c 100644 --- a/drivers/gpu/drm/i915/selftests/i915_request.c +++ b/drivers/gpu/drm/i915/selftests/i915_request.c @@ -2293,8 +2293,10 @@ static int perf_request_latency(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { @@ -2467,8 +2469,10 @@ static int perf_series_engines(void *arg) struct intel_context *ce; ce = intel_context_create(engine); - if (IS_ERR(ce)) + if (IS_ERR(ce)) { + err = PTR_ERR(ce); goto out; + } err = intel_context_pin(ce); if (err) { diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c index 334b0648e253..0aeba8e3af28 100644 --- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c +++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c @@ -261,6 +261,82 @@ err_close_objects: return err; } +static int igt_mock_splintered_region(void *arg) +{ + struct intel_memory_region *mem = arg; + struct drm_i915_private *i915 = mem->i915; + struct drm_i915_gem_object *obj; + unsigned int expected_order; + LIST_HEAD(objects); + u64 size; + int err = 0; + + /* + * Sanity check we can still allocate everything even if the + * mm.max_order != mm.size. i.e our starting address space size is not a + * power-of-two. + */ + + size = (SZ_4G - 1) & PAGE_MASK; + mem = mock_region_create(i915, 0, size, PAGE_SIZE, 0); + if (IS_ERR(mem)) + return PTR_ERR(mem); + + if (mem->mm.size != size) { + pr_err("%s size mismatch(%llu != %llu)\n", + __func__, mem->mm.size, size); + err = -EINVAL; + goto out_put; + } + + expected_order = get_order(rounddown_pow_of_two(size)); + if (mem->mm.max_order != expected_order) { + pr_err("%s order mismatch(%u != %u)\n", + __func__, mem->mm.max_order, expected_order); + err = -EINVAL; + goto out_put; + } + + obj = igt_object_create(mem, &objects, size, 0); + if (IS_ERR(obj)) { + err = PTR_ERR(obj); + goto out_close; + } + + close_objects(mem, &objects); + + /* + * While we should be able allocate everything without any flag + * restrictions, if we consider I915_BO_ALLOC_CONTIGUOUS then we are + * actually limited to the largest power-of-two for the region size i.e + * max_order, due to the inner workings of the buddy allocator. So make + * sure that does indeed hold true. + */ + + obj = igt_object_create(mem, &objects, size, I915_BO_ALLOC_CONTIGUOUS); + if (!IS_ERR(obj)) { + pr_err("%s too large contiguous allocation was not rejected\n", + __func__); + err = -EINVAL; + goto out_close; + } + + obj = igt_object_create(mem, &objects, rounddown_pow_of_two(size), + I915_BO_ALLOC_CONTIGUOUS); + if (IS_ERR(obj)) { + pr_err("%s largest possible contiguous allocation failed\n", + __func__); + err = PTR_ERR(obj); + goto out_close; + } + +out_close: + close_objects(mem, &objects); +out_put: + intel_memory_region_put(mem); + return err; +} + static int igt_gpu_write_dw(struct intel_context *ce, struct i915_vma *vma, u32 dword, @@ -771,6 +847,7 @@ int intel_memory_region_mock_selftests(void) static const struct i915_subtest tests[] = { SUBTEST(igt_mock_fill), SUBTEST(igt_mock_contiguous), + SUBTEST(igt_mock_splintered_region), }; struct intel_memory_region *mem; struct drm_i915_private *i915; diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c index 09660f5a0a4c..979d96f27c43 100644 --- a/drivers/gpu/drm/i915/selftests/mock_region.c +++ b/drivers/gpu/drm/i915/selftests/mock_region.c @@ -24,7 +24,7 @@ mock_object_create(struct intel_memory_region *mem, struct drm_i915_private *i915 = mem->i915; struct drm_i915_gem_object *obj; - if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size) + if (size > mem->mm.size) return ERR_PTR(-E2BIG); obj = i915_gem_object_alloc(); diff --git a/drivers/gpu/drm/imx/dw_hdmi-imx.c b/drivers/gpu/drm/imx/dw_hdmi-imx.c index 71d84c7a5378..d07b39b8afd2 100644 --- a/drivers/gpu/drm/imx/dw_hdmi-imx.c +++ b/drivers/gpu/drm/imx/dw_hdmi-imx.c @@ -111,10 +111,6 @@ static int dw_hdmi_imx_parse_dt(struct imx_hdmi *hdmi) return 0; } -static void dw_hdmi_imx_encoder_disable(struct drm_encoder *encoder) -{ -} - static void dw_hdmi_imx_encoder_enable(struct drm_encoder *encoder) { struct imx_hdmi *hdmi = enc_to_imx_hdmi(encoder); @@ -140,7 +136,6 @@ static int dw_hdmi_imx_atomic_check(struct drm_encoder *encoder, static const struct drm_encoder_helper_funcs dw_hdmi_imx_encoder_helper_funcs = { .enable = dw_hdmi_imx_encoder_enable, - .disable = dw_hdmi_imx_encoder_disable, .atomic_check = dw_hdmi_imx_atomic_check, }; @@ -219,15 +214,9 @@ static int dw_hdmi_imx_bind(struct device *dev, struct device *master, hdmi->dev = &pdev->dev; encoder = &hdmi->encoder; - encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node); - /* - * If we failed to find the CRTC(s) which this encoder is - * supposed to be connected to, it's because the CRTC has - * not been registered yet. Defer probing, and hope that - * the required CRTC is added later. - */ - if (encoder->possible_crtcs == 0) - return -EPROBE_DEFER; + ret = imx_drm_encoder_parse_of(drm, encoder, dev->of_node); + if (ret) + return ret; ret = dw_hdmi_imx_parse_dt(hdmi); if (ret < 0) diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c index 7d00c49fd5a5..9bf5ad6d18a2 100644 --- a/drivers/gpu/drm/imx/imx-drm-core.c +++ b/drivers/gpu/drm/imx/imx-drm-core.c @@ -20,6 +20,7 @@ #include <drm/drm_fb_helper.h> #include <drm/drm_gem_cma_helper.h> #include <drm/drm_gem_framebuffer_helper.h> +#include <drm/drm_managed.h> #include <drm/drm_of.h> #include <drm/drm_plane_helper.h> #include <drm/drm_probe_helper.h> @@ -212,7 +213,9 @@ static int imx_drm_bind(struct device *dev) drm->mode_config.allow_fb_modifiers = true; drm->mode_config.normalize_zpos = true; - drm_mode_config_init(drm); + ret = drmm_mode_config_init(drm); + if (ret) + return ret; ret = drm_vblank_init(drm, MAX_CRTC); if (ret) @@ -251,7 +254,6 @@ err_poll_fini: drm_kms_helper_poll_fini(drm); component_unbind_all(drm->dev, drm); err_kms: - drm_mode_config_cleanup(drm); drm_dev_put(drm); return ret; @@ -267,11 +269,9 @@ static void imx_drm_unbind(struct device *dev) component_unbind_all(drm->dev, drm); - drm_mode_config_cleanup(drm); + drm_dev_put(drm); dev_set_drvdata(dev, NULL); - - drm_dev_put(drm); } static const struct component_master_ops imx_drm_ops = { diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index af757d1e21fe..41e2978cb1eb 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -62,7 +62,6 @@ struct imx_ldb_channel { struct i2c_adapter *ddc; int chno; void *edid; - int edid_len; struct drm_display_mode mode; int mode_valid; u32 bus_format; @@ -536,15 +535,14 @@ static int imx_ldb_panel_ddc(struct device *dev, } if (!channel->ddc) { + int edid_len; + /* if no DDC available, fallback to hardcoded EDID */ dev_dbg(dev, "no ddc available\n"); - edidp = of_get_property(child, "edid", - &channel->edid_len); + edidp = of_get_property(child, "edid", &edid_len); if (edidp) { - channel->edid = kmemdup(edidp, - channel->edid_len, - GFP_KERNEL); + channel->edid = kmemdup(edidp, edid_len, GFP_KERNEL); } else if (!channel->panel) { /* fallback to display-timings node */ ret = of_get_drm_display_mode(child, diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c index 813bb6156a68..2a8d2e32e7b4 100644 --- a/drivers/gpu/drm/imx/imx-tve.c +++ b/drivers/gpu/drm/imx/imx-tve.c @@ -13,7 +13,6 @@ #include <linux/platform_device.h> #include <linux/regmap.h> #include <linux/regulator/consumer.h> -#include <linux/spinlock.h> #include <linux/videodev2.h> #include <video/imx-ipu-v3.h> @@ -104,8 +103,6 @@ struct imx_tve { struct drm_connector connector; struct drm_encoder encoder; struct device *dev; - spinlock_t lock; /* register lock */ - bool enabled; int mode; int di_hsync_pin; int di_vsync_pin; @@ -129,30 +126,10 @@ static inline struct imx_tve *enc_to_tve(struct drm_encoder *e) return container_of(e, struct imx_tve, encoder); } -static void tve_lock(void *__tve) -__acquires(&tve->lock) -{ - struct imx_tve *tve = __tve; - - spin_lock(&tve->lock); -} - -static void tve_unlock(void *__tve) -__releases(&tve->lock) -{ - struct imx_tve *tve = __tve; - - spin_unlock(&tve->lock); -} - static void tve_enable(struct imx_tve *tve) { - if (!tve->enabled) { - tve->enabled = true; - clk_prepare_enable(tve->clk); - regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, - TVE_EN, TVE_EN); - } + clk_prepare_enable(tve->clk); + regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, TVE_EN); /* clear interrupt status register */ regmap_write(tve->regmap, TVE_STAT_REG, 0xffffffff); @@ -169,11 +146,8 @@ static void tve_enable(struct imx_tve *tve) static void tve_disable(struct imx_tve *tve) { - if (tve->enabled) { - tve->enabled = false; - regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0); - clk_disable_unprepare(tve->clk); - } + regmap_update_bits(tve->regmap, TVE_COM_CONF_REG, TVE_EN, 0); + clk_disable_unprepare(tve->clk); } static int tve_setup_tvout(struct imx_tve *tve) @@ -500,8 +474,7 @@ static struct regmap_config tve_regmap_config = { .readable_reg = imx_tve_readable_reg, - .lock = tve_lock, - .unlock = tve_unlock, + .fast_io = true, .max_register = 0xdc, }; @@ -511,7 +484,7 @@ static const char * const imx_tve_modes[] = { [TVE_MODE_VGA] = "vga", }; -static const int of_get_tve_mode(struct device_node *np) +static int of_get_tve_mode(struct device_node *np) { const char *bm; int ret, i; @@ -544,7 +517,6 @@ static int imx_tve_bind(struct device *dev, struct device *master, void *data) memset(tve, 0, sizeof(*tve)); tve->dev = dev; - spin_lock_init(&tve->lock); ddc_node = of_parse_phandle(np, "ddc-i2c-bus", 0); if (ddc_node) { diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c index 8232f512b9ed..2eb8df4697df 100644 --- a/drivers/gpu/drm/imx/parallel-display.c +++ b/drivers/gpu/drm/imx/parallel-display.c @@ -28,7 +28,6 @@ struct imx_parallel_display { struct drm_bridge bridge; struct device *dev; void *edid; - int edid_len; u32 bus_format; u32 bus_flags; struct drm_display_mode mode; @@ -41,11 +40,6 @@ static inline struct imx_parallel_display *con_to_imxpd(struct drm_connector *c) return container_of(c, struct imx_parallel_display, connector); } -static inline struct imx_parallel_display *enc_to_imxpd(struct drm_encoder *e) -{ - return container_of(e, struct imx_parallel_display, encoder); -} - static inline struct imx_parallel_display *bridge_to_imxpd(struct drm_bridge *b) { return container_of(b, struct imx_parallel_display, bridge); @@ -310,6 +304,7 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) struct device_node *np = dev->of_node; const u8 *edidp; struct imx_parallel_display *imxpd; + int edid_len; int ret; u32 bus_format = 0; const char *fmt; @@ -323,9 +318,9 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) if (ret && ret != -ENODEV) return ret; - edidp = of_get_property(np, "edid", &imxpd->edid_len); + edidp = of_get_property(np, "edid", &edid_len); if (edidp) - imxpd->edid = kmemdup(edidp, imxpd->edid_len, GFP_KERNEL); + imxpd->edid = devm_kmemdup(dev, edidp, edid_len, GFP_KERNEL); ret = of_property_read_string(np, "interface-pix-fmt", &fmt); if (!ret) { @@ -349,17 +344,8 @@ static int imx_pd_bind(struct device *dev, struct device *master, void *data) return 0; } -static void imx_pd_unbind(struct device *dev, struct device *master, - void *data) -{ - struct imx_parallel_display *imxpd = dev_get_drvdata(dev); - - kfree(imxpd->edid); -} - static const struct component_ops imx_pd_ops = { .bind = imx_pd_bind, - .unbind = imx_pd_unbind, }; static int imx_pd_probe(struct platform_device *pdev) diff --git a/drivers/gpu/drm/mcde/mcde_drv.c b/drivers/gpu/drm/mcde/mcde_drv.c index c592957ed07f..92f8bd907193 100644 --- a/drivers/gpu/drm/mcde/mcde_drv.c +++ b/drivers/gpu/drm/mcde/mcde_drv.c @@ -413,7 +413,13 @@ static int mcde_probe(struct platform_device *pdev) match); if (ret) { dev_err(dev, "failed to add component master\n"); - goto clk_disable; + /* + * The EPOD regulator is already disabled at this point so some + * special errorpath code is needed + */ + clk_disable_unprepare(mcde->mcde_clk); + regulator_disable(mcde->vana); + return ret; } return 0; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 4d29568be3f5..ac038572164d 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -481,7 +481,7 @@ static void mtk_drm_crtc_hw_config(struct mtk_drm_crtc *mtk_crtc) mbox_flush(mtk_crtc->cmdq_client->chan, 2000); cmdq_handle = cmdq_pkt_create(mtk_crtc->cmdq_client, PAGE_SIZE); cmdq_pkt_clear_event(cmdq_handle, mtk_crtc->cmdq_event); - cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event); + cmdq_pkt_wfe(cmdq_handle, mtk_crtc->cmdq_event, false); mtk_crtc_ddp_config(crtc, cmdq_handle); cmdq_pkt_finalize(cmdq_handle); cmdq_pkt_flush_async(cmdq_handle, ddp_cmdq_cb, cmdq_handle); diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.h b/drivers/gpu/drm/nouveau/dispnv50/core.h index 498622c0c670..f75088186fba 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core.h +++ b/drivers/gpu/drm/nouveau/dispnv50/core.h @@ -44,6 +44,7 @@ int core507d_new_(const struct nv50_core_func *, struct nouveau_drm *, s32, struct nv50_core **); int core507d_init(struct nv50_core *); void core507d_ntfy_init(struct nouveau_bo *, u32); +int core507d_read_caps(struct nv50_disp *disp); int core507d_caps_init(struct nouveau_drm *, struct nv50_disp *); int core507d_ntfy_wait_done(struct nouveau_bo *, u32, struct nvif_device *); int core507d_update(struct nv50_core *, u32 *, bool); @@ -55,6 +56,7 @@ extern const struct nv50_outp_func pior507d; int core827d_new(struct nouveau_drm *, s32, struct nv50_core **); int core907d_new(struct nouveau_drm *, s32, struct nv50_core **); +int core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp); extern const struct nv50_outp_func dac907d; extern const struct nv50_outp_func sor907d; diff --git a/drivers/gpu/drm/nouveau/dispnv50/core507d.c b/drivers/gpu/drm/nouveau/dispnv50/core507d.c index 248edf69e168..e6f16a7750f0 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core507d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core507d.c @@ -78,19 +78,56 @@ core507d_ntfy_init(struct nouveau_bo *bo, u32 offset) } int -core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp) +core507d_read_caps(struct nv50_disp *disp) { struct nvif_push *push = disp->core->chan.push; int ret; - if ((ret = PUSH_WAIT(push, 2))) + ret = PUSH_WAIT(push, 6); + if (ret) return ret; + PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, MODE, WRITE) | + NVVAL(NV507D, SET_NOTIFIER_CONTROL, OFFSET, NV50_DISP_CORE_NTFY >> 2) | + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, ENABLE)); + PUSH_MTHD(push, NV507D, GET_CAPABILITIES, 0x00000000); + + PUSH_MTHD(push, NV507D, SET_NOTIFIER_CONTROL, + NVDEF(NV507D, SET_NOTIFIER_CONTROL, NOTIFY, DISABLE)); + return PUSH_KICK(push); } int +core507d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp) +{ + struct nv50_core *core = disp->core; + struct nouveau_bo *bo = disp->sync; + s64 time; + int ret; + + NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, + NVDEF(NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, FALSE)); + + ret = core507d_read_caps(disp); + if (ret < 0) + return ret; + + time = nvif_msec(core->chan.base.device, 2000ULL, + if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY, + NV_DISP_CORE_NOTIFIER_1, CAPABILITIES_1, DONE, ==, TRUE)) + break; + usleep_range(1, 2); + ); + if (time < 0) + NV_ERROR(drm, "core caps notifier timeout\n"); + + return 0; +} + +int core507d_init(struct nv50_core *core) { struct nvif_push *push = core->chan.push; diff --git a/drivers/gpu/drm/nouveau/dispnv50/core907d.c b/drivers/gpu/drm/nouveau/dispnv50/core907d.c index b17c03529c78..8564d4dffaff 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core907d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core907d.c @@ -22,11 +22,45 @@ #include "core.h" #include "head.h" +#include <nvif/push507c.h> +#include <nvif/timer.h> + +#include <nvhw/class/cl907d.h> + +#include "nouveau_bo.h" + +int +core907d_caps_init(struct nouveau_drm *drm, struct nv50_disp *disp) +{ + struct nv50_core *core = disp->core; + struct nouveau_bo *bo = disp->sync; + s64 time; + int ret; + + NVBO_WR32(bo, NV50_DISP_CORE_NTFY, NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, + NVDEF(NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, FALSE)); + + ret = core507d_read_caps(disp); + if (ret < 0) + return ret; + + time = nvif_msec(core->chan.base.device, 2000ULL, + if (NVBO_TD32(bo, NV50_DISP_CORE_NTFY, + NV907D_CORE_NOTIFIER_3, CAPABILITIES_4, DONE, ==, TRUE)) + break; + usleep_range(1, 2); + ); + if (time < 0) + NV_ERROR(drm, "core caps notifier timeout\n"); + + return 0; +} + static const struct nv50_core_func core907d = { .init = core507d_init, .ntfy_init = core507d_ntfy_init, - .caps_init = core507d_caps_init, + .caps_init = core907d_caps_init, .ntfy_wait_done = core507d_ntfy_wait_done, .update = core507d_update, .head = &head907d, diff --git a/drivers/gpu/drm/nouveau/dispnv50/core917d.c b/drivers/gpu/drm/nouveau/dispnv50/core917d.c index 66846f372080..1cd3a2a35dfb 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/core917d.c +++ b/drivers/gpu/drm/nouveau/dispnv50/core917d.c @@ -26,7 +26,7 @@ static const struct nv50_core_func core917d = { .init = core507d_init, .ntfy_init = core507d_ntfy_init, - .caps_init = core507d_caps_init, + .caps_init = core907d_caps_init, .ntfy_wait_done = core507d_ntfy_wait_done, .update = core507d_update, .head = &head917d, diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index b111fe24a06b..36d6b6093d16 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -455,7 +455,7 @@ nv50_outp_get_old_connector(struct nouveau_encoder *outp, * DAC *****************************************************************************/ static void -nv50_dac_disable(struct drm_encoder *encoder) +nv50_dac_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -467,7 +467,7 @@ nv50_dac_disable(struct drm_encoder *encoder) } static void -nv50_dac_enable(struct drm_encoder *encoder) +nv50_dac_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -525,8 +525,8 @@ nv50_dac_detect(struct drm_encoder *encoder, struct drm_connector *connector) static const struct drm_encoder_helper_funcs nv50_dac_help = { .atomic_check = nv50_outp_atomic_check, - .enable = nv50_dac_enable, - .disable = nv50_dac_disable, + .atomic_enable = nv50_dac_enable, + .atomic_disable = nv50_dac_disable, .detect = nv50_dac_detect }; @@ -1055,7 +1055,7 @@ nv50_dp_bpc_to_depth(unsigned int bpc) } static void -nv50_msto_enable(struct drm_encoder *encoder) +nv50_msto_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_head *head = nv50_head(encoder->crtc); struct nv50_head_atom *armh = nv50_head_atom(head->base.base.state); @@ -1101,7 +1101,7 @@ nv50_msto_enable(struct drm_encoder *encoder) } static void -nv50_msto_disable(struct drm_encoder *encoder) +nv50_msto_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nv50_msto *msto = nv50_msto(encoder); struct nv50_mstc *mstc = msto->mstc; @@ -1118,8 +1118,8 @@ nv50_msto_disable(struct drm_encoder *encoder) static const struct drm_encoder_helper_funcs nv50_msto_help = { - .disable = nv50_msto_disable, - .enable = nv50_msto_enable, + .atomic_disable = nv50_msto_disable, + .atomic_enable = nv50_msto_enable, .atomic_check = nv50_msto_atomic_check, }; @@ -1645,8 +1645,7 @@ nv50_sor_disable(struct drm_encoder *encoder, } static void -nv50_sor_enable(struct drm_encoder *encoder, - struct drm_atomic_state *state) +nv50_sor_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1873,7 +1872,7 @@ nv50_pior_atomic_check(struct drm_encoder *encoder, } static void -nv50_pior_disable(struct drm_encoder *encoder) +nv50_pior_disable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nv50_core *core = nv50_disp(encoder->dev)->core; @@ -1885,7 +1884,7 @@ nv50_pior_disable(struct drm_encoder *encoder) } static void -nv50_pior_enable(struct drm_encoder *encoder) +nv50_pior_enable(struct drm_encoder *encoder, struct drm_atomic_state *state) { struct nouveau_encoder *nv_encoder = nouveau_encoder(encoder); struct nouveau_crtc *nv_crtc = nouveau_crtc(encoder->crtc); @@ -1921,14 +1920,14 @@ nv50_pior_enable(struct drm_encoder *encoder) } core->func->pior->ctrl(core, nv_encoder->or, ctrl, asyh); - nv_encoder->crtc = encoder->crtc; + nv_encoder->crtc = &nv_crtc->base; } static const struct drm_encoder_helper_funcs nv50_pior_help = { .atomic_check = nv50_pior_atomic_check, - .enable = nv50_pior_enable, - .disable = nv50_pior_disable, + .atomic_enable = nv50_pior_enable, + .atomic_disable = nv50_pior_disable, }; static void diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h index 2e444bac701d..6a463f308b64 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl507d.h @@ -32,7 +32,10 @@ #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_DONE_TRUE 0x00000001 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_R0 15:1 #define NV_DISP_CORE_NOTIFIER_1_COMPLETION_0_TIMESTAMP 29:16 - +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1 0x00000001 +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE 0:0 +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_FALSE 0x00000000 +#define NV_DISP_CORE_NOTIFIER_1_CAPABILITIES_1_DONE_TRUE 0x00000001 // class methods #define NV507D_UPDATE (0x00000080) diff --git a/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h b/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h index 34bc3eafac7d..79aff6ff3138 100644 --- a/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h +++ b/drivers/gpu/drm/nouveau/include/nvhw/class/cl907d.h @@ -24,6 +24,10 @@ #ifndef _cl907d_h_ #define _cl907d_h_ +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4 0x00000004 +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE 0:0 +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_FALSE 0x00000000 +#define NV907D_CORE_NOTIFIER_3_CAPABILITIES_4_DONE_TRUE 0x00000001 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20 0x00000014 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18 0:0 #define NV907D_CORE_NOTIFIER_3_CAPABILITIES_CAP_SOR0_20_SINGLE_LVDS18_FALSE 0x00000000 diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 2ee75646ad6f..56b335a55966 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -350,14 +350,13 @@ set_placement_list(struct nouveau_drm *drm, struct ttm_place *pl, unsigned *n, if (domain & NOUVEAU_GEM_DOMAIN_VRAM) { struct nvif_mmu *mmu = &drm->client.mmu; - const u8 type = mmu->type[drm->ttm.type_vram].type; pl[*n].mem_type = TTM_PL_VRAM; pl[*n].flags = flags & ~TTM_PL_FLAG_CACHED; /* Some BARs do not support being ioremapped WC */ if (drm->client.device.info.family >= NV_DEVICE_INFO_V0_TESLA && - type & NVIF_MEM_UNCACHED) + mmu->type[drm->ttm.type_vram].type & NVIF_MEM_UNCACHED) pl[*n].flags &= ~TTM_PL_FLAG_WC; (*n)++; diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 49dd0cbc332f..8b4b3688c7ae 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -532,11 +532,13 @@ static void nouveau_connector_set_edid(struct nouveau_connector *nv_connector, struct edid *edid) { - struct edid *old_edid = nv_connector->edid; + if (nv_connector->edid != edid) { + struct edid *old_edid = nv_connector->edid; - drm_connector_update_edid_property(&nv_connector->base, edid); - kfree(old_edid); - nv_connector->edid = edid; + drm_connector_update_edid_property(&nv_connector->base, edid); + kfree(old_edid); + nv_connector->edid = edid; + } } static enum drm_connector_status @@ -669,8 +671,10 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force) /* Try retrieving EDID via DDC */ if (!drm->vbios.fp_no_ddc) { status = nouveau_connector_detect(connector, force); - if (status == connector_status_connected) + if (status == connector_status_connected) { + edid = nv_connector->edid; goto out; + } } /* On some laptops (Sony, i'm looking at you) there appears to @@ -1023,29 +1027,6 @@ get_tmds_link_bandwidth(struct drm_connector *connector) return 112000 * duallink_scale; } -enum drm_mode_status -nouveau_conn_mode_clock_valid(const struct drm_display_mode *mode, - const unsigned min_clock, - const unsigned max_clock, - unsigned int *clock_out) -{ - unsigned int clock = mode->clock; - - if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == - DRM_MODE_FLAG_3D_FRAME_PACKING) - clock *= 2; - - if (clock < min_clock) - return MODE_CLOCK_LOW; - if (clock > max_clock) - return MODE_CLOCK_HIGH; - - if (clock_out) - *clock_out = clock; - - return MODE_OK; -} - static enum drm_mode_status nouveau_connector_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) @@ -1053,7 +1034,7 @@ nouveau_connector_mode_valid(struct drm_connector *connector, struct nouveau_connector *nv_connector = nouveau_connector(connector); struct nouveau_encoder *nv_encoder = nv_connector->detected_encoder; struct drm_encoder *encoder = to_drm_encoder(nv_encoder); - unsigned min_clock = 25000, max_clock = min_clock; + unsigned int min_clock = 25000, max_clock = min_clock, clock = mode->clock; switch (nv_encoder->dcb->type) { case DCB_OUTPUT_LVDS: @@ -1082,8 +1063,15 @@ nouveau_connector_mode_valid(struct drm_connector *connector, return MODE_BAD; } - return nouveau_conn_mode_clock_valid(mode, min_clock, max_clock, - NULL); + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) + clock *= 2; + + if (clock < min_clock) + return MODE_CLOCK_LOW; + if (clock > max_clock) + return MODE_CLOCK_HIGH; + + return MODE_OK; } static struct drm_encoder * diff --git a/drivers/gpu/drm/nouveau/nouveau_dp.c b/drivers/gpu/drm/nouveau/nouveau_dp.c index 7b640e05bd4c..040ed88d362d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dp.c +++ b/drivers/gpu/drm/nouveau/nouveau_dp.c @@ -231,23 +231,30 @@ nv50_dp_mode_valid(struct drm_connector *connector, const struct drm_display_mode *mode, unsigned *out_clock) { - const unsigned min_clock = 25000; - unsigned max_clock, ds_clock, clock; - enum drm_mode_status ret; + const unsigned int min_clock = 25000; + unsigned int max_rate, mode_rate, ds_max_dotclock, clock = mode->clock; + const u8 bpp = connector->display_info.bpc * 3; if (mode->flags & DRM_MODE_FLAG_INTERLACE && !outp->caps.dp_interlace) return MODE_NO_INTERLACE; - max_clock = outp->dp.link_nr * outp->dp.link_bw; - ds_clock = drm_dp_downstream_max_dotclock(outp->dp.dpcd, - outp->dp.downstream_ports); - if (ds_clock) - max_clock = min(max_clock, ds_clock); + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) + clock *= 2; + + max_rate = outp->dp.link_nr * outp->dp.link_bw; + mode_rate = DIV_ROUND_UP(clock * bpp, 8); + if (mode_rate > max_rate) + return MODE_CLOCK_HIGH; + + ds_max_dotclock = drm_dp_downstream_max_dotclock(outp->dp.dpcd, outp->dp.downstream_ports); + if (ds_max_dotclock && clock > ds_max_dotclock) + return MODE_CLOCK_HIGH; + + if (clock < min_clock) + return MODE_CLOCK_LOW; - clock = mode->clock * (connector->display_info.bpc * 3) / 10; - ret = nouveau_conn_mode_clock_valid(mode, min_clock, max_clock, - &clock); if (out_clock) *out_clock = clock; - return ret; + + return MODE_OK; } diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 89adadf4706b..549bc67feabb 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -190,7 +190,8 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain, * to the caller, instead of a normal nouveau_bo ttm reference. */ ret = drm_gem_object_init(drm->dev, &nvbo->bo.base, size); if (ret) { - nouveau_bo_ref(NULL, &nvbo); + drm_gem_object_release(&nvbo->bo.base); + kfree(nvbo); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 2df1c0460559..4f69e4c3dafd 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -105,11 +105,11 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, struct nouveau_cli *cli = nouveau_cli(file_priv); struct drm_nouveau_svm_bind *args = data; unsigned target, cmd, priority; - unsigned long addr, end, size; + unsigned long addr, end; struct mm_struct *mm; args->va_start &= PAGE_MASK; - args->va_end &= PAGE_MASK; + args->va_end = ALIGN(args->va_end, PAGE_SIZE); /* Sanity check arguments */ if (args->reserved0 || args->reserved1) @@ -118,8 +118,6 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, return -EINVAL; if (args->va_start >= args->va_end) return -EINVAL; - if (!args->npages) - return -EINVAL; cmd = args->header >> NOUVEAU_SVM_BIND_COMMAND_SHIFT; cmd &= NOUVEAU_SVM_BIND_COMMAND_MASK; @@ -151,12 +149,6 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, if (args->stride) return -EINVAL; - size = ((unsigned long)args->npages) << PAGE_SHIFT; - if ((args->va_start + size) <= args->va_start) - return -EINVAL; - if ((args->va_start + size) > args->va_end) - return -EINVAL; - /* * Ok we are ask to do something sane, for now we only support migrate * commands but we will add things like memory policy (what to do on @@ -171,7 +163,7 @@ nouveau_svmm_bind(struct drm_device *dev, void *data, return -EINVAL; } - for (addr = args->va_start, end = args->va_start + size; addr < end;) { + for (addr = args->va_start, end = args->va_end; addr < end;) { struct vm_area_struct *vma; unsigned long next; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c index dcb70677d0ac..7851bec5f0e5 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c @@ -2924,17 +2924,34 @@ nvkm_device_del(struct nvkm_device **pdevice) } } +/* returns true if the GPU is in the CPU native byte order */ static inline bool nvkm_device_endianness(struct nvkm_device *device) { - u32 boot1 = nvkm_rd32(device, 0x000004) & 0x01000001; #ifdef __BIG_ENDIAN - if (!boot1) - return false; + const bool big_endian = true; #else - if (boot1) - return false; + const bool big_endian = false; #endif + + /* Read NV_PMC_BOOT_1, and assume non-functional endian switch if it + * doesn't contain the expected values. + */ + u32 pmc_boot_1 = nvkm_rd32(device, 0x000004); + if (pmc_boot_1 && pmc_boot_1 != 0x01000001) + return !big_endian; /* Assume GPU is LE in this case. */ + + /* 0 means LE and 0x01000001 means BE GPU. Condition is true when + * GPU/CPU endianness don't match. + */ + if (big_endian == !pmc_boot_1) { + nvkm_wr32(device, 0x000004, 0x01000001); + nvkm_rd32(device, 0x000000); + if (nvkm_rd32(device, 0x000004) != (big_endian ? 0x01000001 : 0x00000000)) + return !big_endian; /* Assume GPU is LE on any unexpected read-back. */ + } + + /* CPU/GPU endianness should (hopefully) match. */ return true; } @@ -2987,14 +3004,10 @@ nvkm_device_ctor(const struct nvkm_device_func *func, if (detect) { /* switch mmio to cpu's native endianness */ if (!nvkm_device_endianness(device)) { - nvkm_wr32(device, 0x000004, 0x01000001); - nvkm_rd32(device, 0x000000); - if (!nvkm_device_endianness(device)) { - nvdev_error(device, - "GPU not supported on big-endian\n"); - ret = -ENOSYS; - goto done; - } + nvdev_error(device, + "Couldn't switch GPU to CPUs endianess\n"); + ret = -ENOSYS; + goto done; } boot0 = nvkm_rd32(device, 0x000000); diff --git a/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c b/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c index 3482e28e30fc..0c5f22e95c2d 100644 --- a/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c +++ b/drivers/gpu/drm/panel/panel-mantix-mlaf057we51.c @@ -26,7 +26,9 @@ struct mantix { struct device *dev; struct drm_panel panel; + struct gpio_desc *reset_gpio; + struct gpio_desc *tp_rstn_gpio; struct regulator *avdd; struct regulator *avee; @@ -124,6 +126,10 @@ static int mantix_unprepare(struct drm_panel *panel) { struct mantix *ctx = panel_to_mantix(panel); + gpiod_set_value_cansleep(ctx->tp_rstn_gpio, 1); + usleep_range(5000, 6000); + gpiod_set_value_cansleep(ctx->reset_gpio, 1); + regulator_disable(ctx->avee); regulator_disable(ctx->avdd); /* T11 */ @@ -165,13 +171,10 @@ static int mantix_prepare(struct drm_panel *panel) return ret; } - /* T3+T5 */ - usleep_range(10000, 12000); - - gpiod_set_value_cansleep(ctx->reset_gpio, 1); - usleep_range(5150, 7000); - + /* T3 + T4 + time for voltage to become stable: */ + usleep_range(6000, 7000); gpiod_set_value_cansleep(ctx->reset_gpio, 0); + gpiod_set_value_cansleep(ctx->tp_rstn_gpio, 0); /* T6 */ msleep(50); @@ -204,7 +207,7 @@ static int mantix_get_modes(struct drm_panel *panel, if (!mode) { dev_err(ctx->dev, "Failed to add mode %ux%u@%u\n", default_mode.hdisplay, default_mode.vdisplay, - drm_mode_vrefresh(mode)); + drm_mode_vrefresh(&default_mode)); return -ENOMEM; } @@ -236,12 +239,18 @@ static int mantix_probe(struct mipi_dsi_device *dsi) if (!ctx) return -ENOMEM; - ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + ctx->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(ctx->reset_gpio)) { dev_err(dev, "cannot get reset gpio\n"); return PTR_ERR(ctx->reset_gpio); } + ctx->tp_rstn_gpio = devm_gpiod_get(dev, "mantix,tp-rstn", GPIOD_OUT_HIGH); + if (IS_ERR(ctx->tp_rstn_gpio)) { + dev_err(dev, "cannot get tp-rstn gpio\n"); + return PTR_ERR(ctx->tp_rstn_gpio); + } + mipi_dsi_set_drvdata(dsi, ctx); ctx->dev = dev; diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 37d4cb7a5491..0fc084110e5b 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -626,6 +626,7 @@ static int panfrost_probe(struct platform_device *pdev) err_out1: pm_runtime_disable(pfdev->dev); panfrost_device_fini(pfdev); + pm_runtime_set_suspended(pfdev->dev); err_out0: drm_dev_put(ddev); return err; @@ -640,9 +641,9 @@ static int panfrost_remove(struct platform_device *pdev) panfrost_gem_shrinker_cleanup(ddev); pm_runtime_get_sync(pfdev->dev); - panfrost_device_fini(pfdev); - pm_runtime_put_sync_suspend(pfdev->dev); pm_runtime_disable(pfdev->dev); + panfrost_device_fini(pfdev); + pm_runtime_set_suspended(pfdev->dev); drm_dev_put(ddev); return 0; diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.c b/drivers/gpu/drm/panfrost/panfrost_gem.c index 1a6cea0e0bd7..62d4d710a571 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem.c @@ -105,14 +105,12 @@ void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping) kref_put(&mapping->refcount, panfrost_gem_mapping_release); } -void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo) +void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo) { struct panfrost_gem_mapping *mapping; - mutex_lock(&bo->mappings.lock); list_for_each_entry(mapping, &bo->mappings.list, node) panfrost_gem_teardown_mapping(mapping); - mutex_unlock(&bo->mappings.lock); } int panfrost_gem_open(struct drm_gem_object *obj, struct drm_file *file_priv) diff --git a/drivers/gpu/drm/panfrost/panfrost_gem.h b/drivers/gpu/drm/panfrost/panfrost_gem.h index b3517ff9630c..8088d5fd8480 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem.h +++ b/drivers/gpu/drm/panfrost/panfrost_gem.h @@ -82,7 +82,7 @@ struct panfrost_gem_mapping * panfrost_gem_mapping_get(struct panfrost_gem_object *bo, struct panfrost_file_priv *priv); void panfrost_gem_mapping_put(struct panfrost_gem_mapping *mapping); -void panfrost_gem_teardown_mappings(struct panfrost_gem_object *bo); +void panfrost_gem_teardown_mappings_locked(struct panfrost_gem_object *bo); void panfrost_gem_shrinker_init(struct drm_device *dev); void panfrost_gem_shrinker_cleanup(struct drm_device *dev); diff --git a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c index 288e46c40673..1b9f68d8e9aa 100644 --- a/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c +++ b/drivers/gpu/drm/panfrost/panfrost_gem_shrinker.c @@ -40,18 +40,26 @@ static bool panfrost_gem_purge(struct drm_gem_object *obj) { struct drm_gem_shmem_object *shmem = to_drm_gem_shmem_obj(obj); struct panfrost_gem_object *bo = to_panfrost_bo(obj); + bool ret = false; if (atomic_read(&bo->gpu_usecount)) return false; - if (!mutex_trylock(&shmem->pages_lock)) + if (!mutex_trylock(&bo->mappings.lock)) return false; - panfrost_gem_teardown_mappings(bo); + if (!mutex_trylock(&shmem->pages_lock)) + goto unlock_mappings; + + panfrost_gem_teardown_mappings_locked(bo); drm_gem_shmem_purge_locked(obj); + ret = true; mutex_unlock(&shmem->pages_lock); - return true; + +unlock_mappings: + mutex_unlock(&bo->mappings.lock); + return ret; } static unsigned long diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c index 77497b45f9a2..55960cbb1019 100644 --- a/drivers/gpu/drm/sun4i/sun4i_backend.c +++ b/drivers/gpu/drm/sun4i/sun4i_backend.c @@ -814,9 +814,15 @@ static int sun4i_backend_bind(struct device *dev, struct device *master, * * XXX(hch): this has no business in a driver and needs to move * to the device tree. + * + * If we have two subsequent calls to dma_direct_set_offset + * returns -EINVAL. Unfortunately, this happens when we have two + * backends in the system, and will result in the driver + * reporting an error while it has been setup properly before. + * Ignore EINVAL, but it should really be removed eventually. */ ret = dma_direct_set_offset(drm->dev, PHYS_OFFSET, 0, SZ_4G); - if (ret) + if (ret && ret != -EINVAL) return ret; } diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.c b/drivers/gpu/drm/sun4i/sun4i_frontend.c index b51cc685c13a..edb60ae0a9b7 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.c +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.c @@ -407,6 +407,7 @@ int sun4i_frontend_update_formats(struct sun4i_frontend *frontend, struct drm_framebuffer *fb = state->fb; const struct drm_format_info *format = fb->format; uint64_t modifier = fb->modifier; + unsigned int ch1_phase_idx; u32 out_fmt_val; u32 in_fmt_val, in_mod_val, in_ps_val; unsigned int i; @@ -442,18 +443,19 @@ int sun4i_frontend_update_formats(struct sun4i_frontend *frontend, * I have no idea what this does exactly, but it seems to be * related to the scaler FIR filter phase parameters. */ + ch1_phase_idx = (format->num_planes > 1) ? 1 : 0; regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_HORZPHASE_REG, - frontend->data->ch_phase[0].horzphase); + frontend->data->ch_phase[0]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_HORZPHASE_REG, - frontend->data->ch_phase[1].horzphase); + frontend->data->ch_phase[ch1_phase_idx]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE0_REG, - frontend->data->ch_phase[0].vertphase[0]); + frontend->data->ch_phase[0]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE0_REG, - frontend->data->ch_phase[1].vertphase[0]); + frontend->data->ch_phase[ch1_phase_idx]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH0_VERTPHASE1_REG, - frontend->data->ch_phase[0].vertphase[1]); + frontend->data->ch_phase[0]); regmap_write(frontend->regs, SUN4I_FRONTEND_CH1_VERTPHASE1_REG, - frontend->data->ch_phase[1].vertphase[1]); + frontend->data->ch_phase[ch1_phase_idx]); /* * Checking the input format is sufficient since we currently only @@ -687,30 +689,12 @@ static const struct dev_pm_ops sun4i_frontend_pm_ops = { }; static const struct sun4i_frontend_data sun4i_a10_frontend = { - .ch_phase = { - { - .horzphase = 0, - .vertphase = { 0, 0 }, - }, - { - .horzphase = 0xfc000, - .vertphase = { 0xfc000, 0xfc000 }, - }, - }, + .ch_phase = { 0x000, 0xfc000 }, .has_coef_rdy = true, }; static const struct sun4i_frontend_data sun8i_a33_frontend = { - .ch_phase = { - { - .horzphase = 0x400, - .vertphase = { 0x400, 0x400 }, - }, - { - .horzphase = 0x400, - .vertphase = { 0x400, 0x400 }, - }, - }, + .ch_phase = { 0x400, 0xfc400 }, .has_coef_access_ctrl = true, }; diff --git a/drivers/gpu/drm/sun4i/sun4i_frontend.h b/drivers/gpu/drm/sun4i/sun4i_frontend.h index 0c382c1ddb0f..2e7b76e50c2b 100644 --- a/drivers/gpu/drm/sun4i/sun4i_frontend.h +++ b/drivers/gpu/drm/sun4i/sun4i_frontend.h @@ -115,11 +115,7 @@ struct reset_control; struct sun4i_frontend_data { bool has_coef_access_ctrl; bool has_coef_rdy; - - struct { - u32 horzphase; - u32 vertphase[2]; - } ch_phase[2]; + u32 ch_phase[2]; }; struct sun4i_frontend { diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c index d4c08043dd81..92add2cef2e7 100644 --- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c +++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c @@ -208,6 +208,7 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master, phy_node = of_parse_phandle(dev->of_node, "phys", 0); if (!phy_node) { dev_err(dev, "Can't found PHY phandle\n"); + ret = -EINVAL; goto err_disable_clk_tmds; } diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index 70b3bee27850..eb4b7df02ca0 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -647,7 +647,7 @@ bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, /* Don't evict this BO if it's outside of the * requested placement range */ - if (place->fpfn >= (bo->mem.start + bo->mem.size) || + if (place->fpfn >= (bo->mem.start + bo->mem.num_pages) || (place->lpfn && place->lpfn <= bo->mem.start)) return false; diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c index 915f8bfdb58c..182c586525eb 100644 --- a/drivers/gpu/drm/v3d/v3d_gem.c +++ b/drivers/gpu/drm/v3d/v3d_gem.c @@ -568,7 +568,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data, ret = v3d_job_init(v3d, file_priv, &bin->base, v3d_job_free, args->in_sync_bcl); if (ret) { - kfree(bin); v3d_job_put(&render->base); kfree(bin); return ret; diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 74ceebd62fbc..cc74a3f3a07a 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -449,7 +449,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size, } if (IS_ERR(cma_obj)) { - struct drm_printer p = drm_info_printer(vc4->dev->dev); + struct drm_printer p = drm_info_printer(vc4->base.dev); DRM_ERROR("Failed to allocate from CMA:\n"); vc4_bo_stats_print(&p, vc4); return ERR_PTR(-ENOMEM); @@ -590,7 +590,7 @@ static void vc4_bo_cache_time_work(struct work_struct *work) { struct vc4_dev *vc4 = container_of(work, struct vc4_dev, bo_cache.time_work); - struct drm_device *dev = vc4->dev; + struct drm_device *dev = &vc4->base; mutex_lock(&vc4->bo_lock); vc4_bo_cache_free_old(dev); @@ -1005,6 +1005,7 @@ int vc4_get_tiling_ioctl(struct drm_device *dev, void *data, return 0; } +static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused); int vc4_bo_cache_init(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); @@ -1033,10 +1034,10 @@ int vc4_bo_cache_init(struct drm_device *dev) INIT_WORK(&vc4->bo_cache.time_work, vc4_bo_cache_time_work); timer_setup(&vc4->bo_cache.time_timer, vc4_bo_cache_time_timer, 0); - return 0; + return drmm_add_action_or_reset(dev, vc4_bo_cache_destroy, NULL); } -void vc4_bo_cache_destroy(struct drm_device *dev) +static void vc4_bo_cache_destroy(struct drm_device *dev, void *unused) { struct vc4_dev *vc4 = to_vc4_dev(dev); int i; diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c index f1a5fd5dab6f..839610f8092a 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.c +++ b/drivers/gpu/drm/vc4/vc4_drv.c @@ -257,37 +257,37 @@ static int vc4_drm_bind(struct device *dev) dev->coherent_dma_mask = DMA_BIT_MASK(32); - vc4 = devm_kzalloc(dev, sizeof(*vc4), GFP_KERNEL); - if (!vc4) - return -ENOMEM; - /* If VC4 V3D is missing, don't advertise render nodes. */ node = of_find_matching_node_and_match(NULL, vc4_v3d_dt_match, NULL); if (!node || !of_device_is_available(node)) vc4_drm_driver.driver_features &= ~DRIVER_RENDER; of_node_put(node); - drm = drm_dev_alloc(&vc4_drm_driver, dev); - if (IS_ERR(drm)) - return PTR_ERR(drm); + vc4 = devm_drm_dev_alloc(dev, &vc4_drm_driver, struct vc4_dev, base); + if (IS_ERR(vc4)) + return PTR_ERR(vc4); + + drm = &vc4->base; platform_set_drvdata(pdev, drm); - vc4->dev = drm; - drm->dev_private = vc4; INIT_LIST_HEAD(&vc4->debugfs_list); mutex_init(&vc4->bin_bo_lock); ret = vc4_bo_cache_init(drm); if (ret) - goto dev_put; + return ret; - drm_mode_config_init(drm); + ret = drmm_mode_config_init(drm); + if (ret) + return ret; - vc4_gem_init(drm); + ret = vc4_gem_init(drm); + if (ret) + return ret; ret = component_bind_all(dev, drm); if (ret) - goto gem_destroy; + return ret; ret = vc4_plane_create_additional_planes(drm); if (ret) @@ -312,29 +312,17 @@ static int vc4_drm_bind(struct device *dev) unbind_all: component_unbind_all(dev, drm); -gem_destroy: - vc4_gem_destroy(drm); - vc4_bo_cache_destroy(drm); -dev_put: - drm_dev_put(drm); + return ret; } static void vc4_drm_unbind(struct device *dev) { struct drm_device *drm = dev_get_drvdata(dev); - struct vc4_dev *vc4 = to_vc4_dev(drm); drm_dev_unregister(drm); drm_atomic_helper_shutdown(drm); - - drm_mode_config_cleanup(drm); - - drm_atomic_private_obj_fini(&vc4->load_tracker); - drm_atomic_private_obj_fini(&vc4->ctm_manager); - - drm_dev_put(drm); } static const struct component_master_ops vc4_drm_ops = { diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 90b911fd2a7f..19b75bebd35f 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -14,6 +14,7 @@ #include <drm/drm_device.h> #include <drm/drm_encoder.h> #include <drm/drm_gem_cma_helper.h> +#include <drm/drm_managed.h> #include <drm/drm_mm.h> #include <drm/drm_modeset_lock.h> @@ -71,7 +72,7 @@ struct vc4_perfmon { }; struct vc4_dev { - struct drm_device *dev; + struct drm_device base; struct vc4_hvs *hvs; struct vc4_v3d *v3d; @@ -234,7 +235,7 @@ struct vc4_dev { static inline struct vc4_dev * to_vc4_dev(struct drm_device *dev) { - return (struct vc4_dev *)dev->dev_private; + return container_of(dev, struct vc4_dev, base); } struct vc4_bo { @@ -287,7 +288,7 @@ struct vc4_bo { static inline struct vc4_bo * to_vc4_bo(struct drm_gem_object *bo) { - return (struct vc4_bo *)bo; + return container_of(to_drm_gem_cma_obj(bo), struct vc4_bo, base); } struct vc4_fence { @@ -300,7 +301,7 @@ struct vc4_fence { static inline struct vc4_fence * to_vc4_fence(struct dma_fence *fence) { - return (struct vc4_fence *)fence; + return container_of(fence, struct vc4_fence, base); } struct vc4_seqno_cb { @@ -347,7 +348,7 @@ struct vc4_plane { static inline struct vc4_plane * to_vc4_plane(struct drm_plane *plane) { - return (struct vc4_plane *)plane; + return container_of(plane, struct vc4_plane, base); } enum vc4_scaling_mode { @@ -423,7 +424,7 @@ struct vc4_plane_state { static inline struct vc4_plane_state * to_vc4_plane_state(struct drm_plane_state *state) { - return (struct vc4_plane_state *)state; + return container_of(state, struct vc4_plane_state, base); } enum vc4_encoder_type { @@ -499,7 +500,7 @@ struct vc4_crtc { static inline struct vc4_crtc * to_vc4_crtc(struct drm_crtc *crtc) { - return (struct vc4_crtc *)crtc; + return container_of(crtc, struct vc4_crtc, base); } static inline const struct vc4_crtc_data * @@ -537,7 +538,7 @@ struct vc4_crtc_state { static inline struct vc4_crtc_state * to_vc4_crtc_state(struct drm_crtc_state *crtc_state) { - return (struct vc4_crtc_state *)crtc_state; + return container_of(crtc_state, struct vc4_crtc_state, base); } #define V3D_READ(offset) readl(vc4->v3d->regs + offset) @@ -809,7 +810,6 @@ struct drm_gem_object *vc4_prime_import_sg_table(struct drm_device *dev, struct sg_table *sgt); void *vc4_prime_vmap(struct drm_gem_object *obj); int vc4_bo_cache_init(struct drm_device *dev); -void vc4_bo_cache_destroy(struct drm_device *dev); int vc4_bo_inc_usecnt(struct vc4_bo *bo); void vc4_bo_dec_usecnt(struct vc4_bo *bo); void vc4_bo_add_to_purgeable_pool(struct vc4_bo *bo); @@ -874,8 +874,7 @@ extern struct platform_driver vc4_dsi_driver; extern const struct dma_fence_ops vc4_fence_ops; /* vc4_gem.c */ -void vc4_gem_init(struct drm_device *dev); -void vc4_gem_destroy(struct drm_device *dev); +int vc4_gem_init(struct drm_device *dev); int vc4_submit_cl_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv); int vc4_wait_seqno_ioctl(struct drm_device *dev, void *data, diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 9f01ddd5b932..b641252939d8 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -314,16 +314,16 @@ vc4_reset_work(struct work_struct *work) struct vc4_dev *vc4 = container_of(work, struct vc4_dev, hangcheck.reset_work); - vc4_save_hang_state(vc4->dev); + vc4_save_hang_state(&vc4->base); - vc4_reset(vc4->dev); + vc4_reset(&vc4->base); } static void vc4_hangcheck_elapsed(struct timer_list *t) { struct vc4_dev *vc4 = from_timer(vc4, t, hangcheck.timer); - struct drm_device *dev = vc4->dev; + struct drm_device *dev = &vc4->base; uint32_t ct0ca, ct1ca; unsigned long irqflags; struct vc4_exec_info *bin_exec, *render_exec; @@ -1000,7 +1000,7 @@ vc4_job_handle_completed(struct vc4_dev *vc4) list_del(&exec->head); spin_unlock_irqrestore(&vc4->job_lock, irqflags); - vc4_complete_exec(vc4->dev, exec); + vc4_complete_exec(&vc4->base, exec); spin_lock_irqsave(&vc4->job_lock, irqflags); } @@ -1258,13 +1258,13 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, return 0; fail: - vc4_complete_exec(vc4->dev, exec); + vc4_complete_exec(&vc4->base, exec); return ret; } -void -vc4_gem_init(struct drm_device *dev) +static void vc4_gem_destroy(struct drm_device *dev, void *unused); +int vc4_gem_init(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); @@ -1285,10 +1285,11 @@ vc4_gem_init(struct drm_device *dev) INIT_LIST_HEAD(&vc4->purgeable.list); mutex_init(&vc4->purgeable.lock); + + return drmm_add_action_or_reset(dev, vc4_gem_destroy, NULL); } -void -vc4_gem_destroy(struct drm_device *dev) +static void vc4_gem_destroy(struct drm_device *dev, void *unused) { struct vc4_dev *vc4 = to_vc4_dev(dev); diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c index e8f99e290655..95779d50cca0 100644 --- a/drivers/gpu/drm/vc4/vc4_hdmi.c +++ b/drivers/gpu/drm/vc4/vc4_hdmi.c @@ -922,6 +922,7 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) { struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); + struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; struct device *dev = &vc4_hdmi->pdev->dev; u32 audio_packet_config, channel_mask; u32 channel_map; @@ -981,6 +982,8 @@ static int vc4_hdmi_audio_hw_params(struct snd_pcm_substream *substream, HDMI_WRITE(HDMI_AUDIO_PACKET_CONFIG, audio_packet_config); vc4_hdmi_set_n_cts(vc4_hdmi); + vc4_hdmi_set_audio_infoframe(encoder); + return 0; } @@ -988,11 +991,9 @@ static int vc4_hdmi_audio_trigger(struct snd_pcm_substream *substream, int cmd, struct snd_soc_dai *dai) { struct vc4_hdmi *vc4_hdmi = dai_to_hdmi(dai); - struct drm_encoder *encoder = &vc4_hdmi->encoder.base.base; switch (cmd) { case SNDRV_PCM_TRIGGER_START: - vc4_hdmi_set_audio_infoframe(encoder); vc4_hdmi->audio.streaming = true; if (vc4_hdmi->variant->phy_rng_enable) @@ -1076,6 +1077,7 @@ static const struct snd_soc_dapm_route vc4_hdmi_audio_routes[] = { }; static const struct snd_soc_component_driver vc4_hdmi_audio_component_drv = { + .name = "vc4-hdmi-codec-dai-component", .controls = vc4_hdmi_audio_controls, .num_controls = ARRAY_SIZE(vc4_hdmi_audio_controls), .dapm_widgets = vc4_hdmi_audio_widgets, diff --git a/drivers/gpu/drm/vc4/vc4_hvs.c b/drivers/gpu/drm/vc4/vc4_hvs.c index 4d0a833366ce..b72b2bd05a81 100644 --- a/drivers/gpu/drm/vc4/vc4_hvs.c +++ b/drivers/gpu/drm/vc4/vc4_hvs.c @@ -560,7 +560,7 @@ static int vc4_hvs_bind(struct device *dev, struct device *master, void *data) { struct platform_device *pdev = to_platform_device(dev); struct drm_device *drm = dev_get_drvdata(master); - struct vc4_dev *vc4 = drm->dev_private; + struct vc4_dev *vc4 = to_vc4_dev(drm); struct vc4_hvs *hvs = NULL; int ret; u32 dispctrl; @@ -679,7 +679,7 @@ static void vc4_hvs_unbind(struct device *dev, struct device *master, void *data) { struct drm_device *drm = dev_get_drvdata(master); - struct vc4_dev *vc4 = drm->dev_private; + struct vc4_dev *vc4 = to_vc4_dev(drm); struct vc4_hvs *hvs = vc4->hvs; if (drm_mm_node_allocated(&vc4->hvs->mitchell_netravali_filter)) diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c index 149825ff5df8..2b951cae04ad 100644 --- a/drivers/gpu/drm/vc4/vc4_kms.c +++ b/drivers/gpu/drm/vc4/vc4_kms.c @@ -51,7 +51,7 @@ static struct vc4_ctm_state *vc4_get_ctm_state(struct drm_atomic_state *state, struct drm_private_obj *manager) { struct drm_device *dev = state->dev; - struct vc4_dev *vc4 = dev->dev_private; + struct vc4_dev *vc4 = to_vc4_dev(dev); struct drm_private_state *priv_state; int ret; @@ -93,6 +93,29 @@ static const struct drm_private_state_funcs vc4_ctm_state_funcs = { .atomic_destroy_state = vc4_ctm_destroy_state, }; +static void vc4_ctm_obj_fini(struct drm_device *dev, void *unused) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + drm_atomic_private_obj_fini(&vc4->ctm_manager); +} + +static int vc4_ctm_obj_init(struct vc4_dev *vc4) +{ + struct vc4_ctm_state *ctm_state; + + drm_modeset_lock_init(&vc4->ctm_state_lock); + + ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL); + if (!ctm_state) + return -ENOMEM; + + drm_atomic_private_obj_init(&vc4->base, &vc4->ctm_manager, &ctm_state->base, + &vc4_ctm_state_funcs); + + return drmm_add_action(&vc4->base, vc4_ctm_obj_fini, NULL); +} + /* Converts a DRM S31.32 value to the HW S0.9 format. */ static u16 vc4_ctm_s31_32_to_s0_9(u64 in) { @@ -609,6 +632,34 @@ static const struct drm_private_state_funcs vc4_load_tracker_state_funcs = { .atomic_destroy_state = vc4_load_tracker_destroy_state, }; +static void vc4_load_tracker_obj_fini(struct drm_device *dev, void *unused) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + if (!vc4->load_tracker_available) + return; + + drm_atomic_private_obj_fini(&vc4->load_tracker); +} + +static int vc4_load_tracker_obj_init(struct vc4_dev *vc4) +{ + struct vc4_load_tracker_state *load_state; + + if (!vc4->load_tracker_available) + return 0; + + load_state = kzalloc(sizeof(*load_state), GFP_KERNEL); + if (!load_state) + return -ENOMEM; + + drm_atomic_private_obj_init(&vc4->base, &vc4->load_tracker, + &load_state->base, + &vc4_load_tracker_state_funcs); + + return drmm_add_action(&vc4->base, vc4_load_tracker_obj_fini, NULL); +} + #define NUM_OUTPUTS 6 #define NUM_CHANNELS 3 @@ -711,8 +762,6 @@ static const struct drm_mode_config_funcs vc4_mode_funcs = { int vc4_kms_load(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); - struct vc4_ctm_state *ctm_state; - struct vc4_load_tracker_state *load_state; bool is_vc5 = of_device_is_compatible(dev->dev->of_node, "brcm,bcm2711-vc5"); int ret; @@ -751,26 +800,13 @@ int vc4_kms_load(struct drm_device *dev) dev->mode_config.async_page_flip = true; dev->mode_config.allow_fb_modifiers = true; - drm_modeset_lock_init(&vc4->ctm_state_lock); - - ctm_state = kzalloc(sizeof(*ctm_state), GFP_KERNEL); - if (!ctm_state) - return -ENOMEM; - - drm_atomic_private_obj_init(dev, &vc4->ctm_manager, &ctm_state->base, - &vc4_ctm_state_funcs); - - if (vc4->load_tracker_available) { - load_state = kzalloc(sizeof(*load_state), GFP_KERNEL); - if (!load_state) { - drm_atomic_private_obj_fini(&vc4->ctm_manager); - return -ENOMEM; - } + ret = vc4_ctm_obj_init(vc4); + if (ret) + return ret; - drm_atomic_private_obj_init(dev, &vc4->load_tracker, - &load_state->base, - &vc4_load_tracker_state_funcs); - } + ret = vc4_load_tracker_obj_init(vc4); + if (ret) + return ret; drm_mode_config_reset(dev); diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index f7ab979721b3..65d0dac69b0b 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -168,7 +168,7 @@ static void vc4_v3d_init_hw(struct drm_device *dev) int vc4_v3d_get_bin_slot(struct vc4_dev *vc4) { - struct drm_device *dev = vc4->dev; + struct drm_device *dev = &vc4->base; unsigned long irqflags; int slot; uint64_t seqno = 0; @@ -246,7 +246,7 @@ static int bin_bo_alloc(struct vc4_dev *vc4) INIT_LIST_HEAD(&list); while (true) { - struct vc4_bo *bo = vc4_bo_create(vc4->dev, size, true, + struct vc4_bo *bo = vc4_bo_create(&vc4->base, size, true, VC4_BO_TYPE_BIN); if (IS_ERR(bo)) { @@ -361,7 +361,7 @@ static int vc4_v3d_runtime_suspend(struct device *dev) struct vc4_v3d *v3d = dev_get_drvdata(dev); struct vc4_dev *vc4 = v3d->vc4; - vc4_irq_uninstall(vc4->dev); + vc4_irq_uninstall(&vc4->base); clk_disable_unprepare(v3d->clk); @@ -378,11 +378,11 @@ static int vc4_v3d_runtime_resume(struct device *dev) if (ret != 0) return ret; - vc4_v3d_init_hw(vc4->dev); + vc4_v3d_init_hw(&vc4->base); /* We disabled the IRQ as part of vc4_irq_uninstall in suspend. */ - enable_irq(vc4->dev->irq); - vc4_irq_postinstall(vc4->dev); + enable_irq(vc4->base.irq); + vc4_irq_postinstall(&vc4->base); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c index 7f0310441da1..73116ec70ba5 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c @@ -432,6 +432,7 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) int ret = 0; static size_t sgl_size; static size_t sgt_size; + struct scatterlist *sg; if (vmw_tt->mapped) return 0; @@ -454,13 +455,15 @@ static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt) if (unlikely(ret != 0)) return ret; - ret = __sg_alloc_table_from_pages - (&vmw_tt->sgt, vsgt->pages, vsgt->num_pages, 0, - (unsigned long) vsgt->num_pages << PAGE_SHIFT, - dma_get_max_seg_size(dev_priv->dev->dev), - GFP_KERNEL); - if (unlikely(ret != 0)) + sg = __sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages, + vsgt->num_pages, 0, + (unsigned long) vsgt->num_pages << PAGE_SHIFT, + dma_get_max_seg_size(dev_priv->dev->dev), + NULL, 0, GFP_KERNEL); + if (IS_ERR(sg)) { + ret = PTR_ERR(sg); goto out_sg_alloc_fail; + } if (vsgt->num_pages > vmw_tt->sgt.orig_nents) { uint64_t over_alloc = diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index b3dae9ec1a38..d166ee262ce4 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -133,73 +133,6 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat) } EXPORT_SYMBOL_GPL(ipu_pixelformat_to_colorspace); -bool ipu_pixelformat_is_planar(u32 pixelformat) -{ - switch (pixelformat) { - case V4L2_PIX_FMT_YUV420: - case V4L2_PIX_FMT_YVU420: - case V4L2_PIX_FMT_YUV422P: - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - return true; - } - - return false; -} -EXPORT_SYMBOL_GPL(ipu_pixelformat_is_planar); - -enum ipu_color_space ipu_mbus_code_to_colorspace(u32 mbus_code) -{ - switch (mbus_code & 0xf000) { - case 0x1000: - return IPUV3_COLORSPACE_RGB; - case 0x2000: - return IPUV3_COLORSPACE_YUV; - default: - return IPUV3_COLORSPACE_UNKNOWN; - } -} -EXPORT_SYMBOL_GPL(ipu_mbus_code_to_colorspace); - -int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat) -{ - switch (pixelformat) { - case V4L2_PIX_FMT_YUV420: - case V4L2_PIX_FMT_YVU420: - case V4L2_PIX_FMT_YUV422P: - case V4L2_PIX_FMT_NV12: - case V4L2_PIX_FMT_NV21: - case V4L2_PIX_FMT_NV16: - case V4L2_PIX_FMT_NV61: - /* - * for the planar YUV formats, the stride passed to - * cpmem must be the stride in bytes of the Y plane. - * And all the planar YUV formats have an 8-bit - * Y component. - */ - return (8 * pixel_stride) >> 3; - case V4L2_PIX_FMT_RGB565: - case V4L2_PIX_FMT_YUYV: - case V4L2_PIX_FMT_UYVY: - return (16 * pixel_stride) >> 3; - case V4L2_PIX_FMT_BGR24: - case V4L2_PIX_FMT_RGB24: - return (24 * pixel_stride) >> 3; - case V4L2_PIX_FMT_BGR32: - case V4L2_PIX_FMT_RGB32: - case V4L2_PIX_FMT_XBGR32: - case V4L2_PIX_FMT_XRGB32: - return (32 * pixel_stride) >> 3; - default: - break; - } - - return -EINVAL; -} -EXPORT_SYMBOL_GPL(ipu_stride_to_bytes); - int ipu_degrees_to_rot_mode(enum ipu_rotate_mode *mode, int degrees, bool hflip, bool vflip) { |