diff options
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 91 |
1 files changed, 84 insertions, 7 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 5381b8d596e6..01d5bca2dee1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -54,6 +54,12 @@ #define AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT 2 +/* Signature used to validate the SR-IOV dynamic critical region init data header ("INDA") */ +#define AMDGPU_SRIOV_CRIT_DATA_SIGNATURE "INDA" +#define AMDGPU_SRIOV_CRIT_DATA_SIG_LEN 4 + +#define IS_SRIOV_CRIT_REGN_ENTRY_VALID(hdr, id) ((hdr)->valid_tables & (1 << (id))) + enum amdgpu_sriov_vf_mode { SRIOV_VF_MODE_BARE_METAL = 0, SRIOV_VF_MODE_ONE_VF, @@ -96,6 +102,9 @@ struct amdgpu_virt_ops { enum amdgpu_ras_block block); bool (*rcvd_ras_intr)(struct amdgpu_device *adev); int (*req_ras_err_count)(struct amdgpu_device *adev); + int (*req_ras_cper_dump)(struct amdgpu_device *adev, u64 vf_rptr); + int (*req_bad_pages)(struct amdgpu_device *adev); + int (*req_ras_chk_criti)(struct amdgpu_device *adev, u64 addr); }; /* @@ -140,15 +149,21 @@ enum AMDGIM_FEATURE_FLAG { AMDGIM_FEATURE_MES_INFO_ENABLE = (1 << 8), AMDGIM_FEATURE_RAS_CAPS = (1 << 9), AMDGIM_FEATURE_RAS_TELEMETRY = (1 << 10), + AMDGIM_FEATURE_RAS_CPER = (1 << 11), + AMDGIM_FEATURE_XGMI_TA_EXT_PEER_LINK = (1 << 12), }; enum AMDGIM_REG_ACCESS_FLAG { /* Use PSP to program IH_RB_CNTL */ - AMDGIM_FEATURE_IH_REG_PSP_EN = (1 << 0), + AMDGIM_FEATURE_IH_REG_PSP_EN = (1 << 0), /* Use RLC to program MMHUB regs */ - AMDGIM_FEATURE_MMHUB_REG_RLC_EN = (1 << 1), + AMDGIM_FEATURE_MMHUB_REG_RLC_EN = (1 << 1), /* Use RLC to program GC regs */ - AMDGIM_FEATURE_GC_REG_RLC_EN = (1 << 2), + AMDGIM_FEATURE_GC_REG_RLC_EN = (1 << 2), + /* Use PSP to program L1_TLB_CNTL */ + AMDGIM_FEATURE_L1_TLB_CNTL_PSP_EN = (1 << 3), + /* Use RLCG to program SQ_CONFIG1 */ + AMDGIM_FEATURE_REG_ACCESS_SQ_CONFIG = (1 << 4), }; struct amdgim_pf2vf_info_v1 { @@ -242,6 +257,23 @@ struct amdgpu_virt_ras_err_handler_data { int last_reserved; }; +struct amdgpu_virt_ras { + struct ratelimit_state ras_error_cnt_rs; + struct ratelimit_state ras_cper_dump_rs; + struct ratelimit_state ras_chk_criti_rs; + struct mutex ras_telemetry_mutex; + uint64_t cper_rptr; +}; + +#define AMDGPU_VIRT_CAPS_LIST(X) X(AMDGPU_VIRT_CAP_POWER_LIMIT) + +DECLARE_ATTR_CAP_CLASS(amdgpu_virt, AMDGPU_VIRT_CAPS_LIST); + +struct amdgpu_virt_region { + uint32_t offset; + uint32_t size_kb; +}; + /* GPU virtualization */ struct amdgpu_virt { uint32_t caps; @@ -251,11 +283,16 @@ struct amdgpu_virt { uint32_t reg_val_offs; struct amdgpu_irq_src ack_irq; struct amdgpu_irq_src rcv_irq; + struct work_struct flr_work; + struct work_struct req_bad_pages_work; + struct work_struct handle_bad_pages_work; + struct amdgpu_mm_table mm_table; const struct amdgpu_virt_ops *ops; struct amdgpu_vf_error_buffer vf_errors; struct amdgpu_virt_fw_reserve fw_reserve; + struct amdgpu_virt_caps virt_caps; uint32_t gim_feature; uint32_t reg_access_mode; int req_init_data_ver; @@ -264,6 +301,12 @@ struct amdgpu_virt { bool ras_init_done; uint32_t reg_access; + /* dynamic(v2) critical regions */ + struct amdgpu_virt_region init_data_header; + struct amdgpu_virt_region crit_regn; + struct amdgpu_virt_region crit_regn_tbl[AMD_SRIOV_MSG_MAX_TABLE_ID]; + bool is_dynamic_crit_regn_enabled; + /* vf2pf message */ struct delayed_work vf2pf_work; uint32_t vf2pf_update_interval_ms; @@ -279,13 +322,18 @@ struct amdgpu_virt { /* the ucode id to signal the autoload */ uint32_t autoload_ucode_id; - struct mutex rlcg_reg_lock; + /* Spinlock to protect access to the RLCG register interface */ + spinlock_t rlcg_reg_lock; + + struct mutex access_req_mutex; union amd_sriov_ras_caps ras_en_caps; union amd_sriov_ras_caps ras_telemetry_en_caps; - - struct ratelimit_state ras_telemetry_rs; + struct amdgpu_virt_ras ras; struct amd_sriov_ras_telemetry_error_count count_cache; + + /* hibernate and resume with different VF feature for xgmi enabled system */ + bool is_xgmi_node_migrate_enabled; }; struct amdgpu_video_codec_info; @@ -321,9 +369,17 @@ struct amdgpu_video_codec_info; (amdgpu_sriov_vf((adev)) && \ ((adev)->virt.reg_access & (AMDGIM_FEATURE_GC_REG_RLC_EN))) +#define amdgpu_sriov_reg_indirect_l1_tlb_cntl(adev) \ +(amdgpu_sriov_vf((adev)) && \ + ((adev)->virt.reg_access & (AMDGIM_FEATURE_L1_TLB_CNTL_PSP_EN))) + #define amdgpu_sriov_rlcg_error_report_enabled(adev) \ (amdgpu_sriov_reg_indirect_mmhub(adev) || amdgpu_sriov_reg_indirect_gc(adev)) +#define amdgpu_sriov_reg_access_sq_config(adev) \ +(amdgpu_sriov_vf((adev)) && \ + ((adev)->virt.reg_access & (AMDGIM_FEATURE_REG_ACCESS_SQ_CONFIG))) + #define amdgpu_passthrough(adev) \ ((adev)->virt.caps & AMDGPU_PASSTHROUGH_MODE) @@ -339,6 +395,12 @@ struct amdgpu_video_codec_info; #define amdgpu_sriov_ras_telemetry_block_en(adev, sriov_blk) \ (amdgpu_sriov_ras_telemetry_en((adev)) && (adev)->virt.ras_telemetry_en_caps.all & BIT(sriov_blk)) +#define amdgpu_sriov_ras_cper_en(adev) \ +((adev)->virt.gim_feature & AMDGIM_FEATURE_RAS_CPER) + +#define amdgpu_sriov_xgmi_ta_ext_peer_link_en(adev) \ +((adev)->virt.gim_feature & AMDGIM_FEATURE_XGMI_TA_EXT_PEER_LINK) + static inline bool is_virtual_machine(void) { #if defined(CONFIG_X86) @@ -352,6 +414,8 @@ static inline bool is_virtual_machine(void) #define amdgpu_sriov_is_pp_one_vf(adev) \ ((adev)->virt.gim_feature & AMDGIM_FEATURE_PP_ONE_VF) +#define amdgpu_sriov_multi_vf_mode(adev) \ + (amdgpu_sriov_vf(adev) && !amdgpu_sriov_is_pp_one_vf(adev)) #define amdgpu_sriov_is_debug(adev) \ ((!amdgpu_in_reset(adev)) && adev->virt.tdr_debug) #define amdgpu_sriov_is_normal(adev) \ @@ -362,6 +426,10 @@ static inline bool is_virtual_machine(void) ((adev)->virt.gim_feature & AMDGIM_FEATURE_VCN_RB_DECOUPLE) #define amdgpu_sriov_is_mes_info_enable(adev) \ ((adev)->virt.gim_feature & AMDGIM_FEATURE_MES_INFO_ENABLE) + +#define amdgpu_virt_xgmi_migrate_enabled(adev) \ + ((adev)->virt.is_xgmi_node_migrate_enabled && (adev)->gmc.xgmi.node_segment_size != 0) + bool amdgpu_virt_mmio_blocked(struct amdgpu_device *adev); void amdgpu_virt_init_setting(struct amdgpu_device *adev); int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init); @@ -377,7 +445,11 @@ void amdgpu_virt_release_ras_err_handler_data(struct amdgpu_device *adev); void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev); void amdgpu_virt_exchange_data(struct amdgpu_device *adev); void amdgpu_virt_fini_data_exchange(struct amdgpu_device *adev); -void amdgpu_detect_virtualization(struct amdgpu_device *adev); +void amdgpu_virt_init(struct amdgpu_device *adev); + +int amdgpu_virt_init_critical_region(struct amdgpu_device *adev); +int amdgpu_virt_get_dynamic_data_info(struct amdgpu_device *adev, + int data_id, uint8_t *binary, u32 *size); bool amdgpu_virt_can_access_debugfs(struct amdgpu_device *adev); int amdgpu_virt_enable_access_debugfs(struct amdgpu_device *adev); @@ -405,5 +477,10 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f bool amdgpu_virt_get_ras_capability(struct amdgpu_device *adev); int amdgpu_virt_req_ras_err_count(struct amdgpu_device *adev, enum amdgpu_ras_block block, struct ras_err_data *err_data); +int amdgpu_virt_req_ras_cper_dump(struct amdgpu_device *adev, bool force_update); int amdgpu_virt_ras_telemetry_post_reset(struct amdgpu_device *adev); +bool amdgpu_virt_ras_telemetry_block_en(struct amdgpu_device *adev, + enum amdgpu_ras_block block); +void amdgpu_virt_request_bad_pages(struct amdgpu_device *adev); +int amdgpu_virt_check_vf_critical_region(struct amdgpu_device *adev, u64 addr, bool *hit); #endif |