1 /* 2 * Copyright 2023 Advanced Micro Devices, Inc. 3 * 4 * Permission is hereby granted, free of charge, to any person obtaining a 5 * copy of this software and associated documentation files (the "Software"), 6 * to deal in the Software without restriction, including without limitation 7 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 8 * and/or sell copies of the Software, and to permit persons to whom the 9 * Software is furnished to do so, subject to the following conditions: 10 * 11 * The above copyright notice and this permission notice shall be included in 12 * all copies or substantial portions of the Software. 13 * 14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 17 * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR 18 * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, 19 * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR 20 * OTHER DEALINGS IN THE SOFTWARE. 21 * 22 */ 23 24 #ifndef __AMDGPU_ACA_H__ 25 #define __AMDGPU_ACA_H__ 26 27 #include <linux/list.h> 28 29 struct ras_err_data; 30 struct ras_query_context; 31 32 #define ACA_MAX_REGS_COUNT (16) 33 34 #define ACA_REG_FIELD(x, h, l) (((x) & GENMASK_ULL(h, l)) >> l) 35 #define ACA_REG__STATUS__VAL(x) ACA_REG_FIELD(x, 63, 63) 36 #define ACA_REG__STATUS__OVERFLOW(x) ACA_REG_FIELD(x, 62, 62) 37 #define ACA_REG__STATUS__UC(x) ACA_REG_FIELD(x, 61, 61) 38 #define ACA_REG__STATUS__EN(x) ACA_REG_FIELD(x, 60, 60) 39 #define ACA_REG__STATUS__MISCV(x) ACA_REG_FIELD(x, 59, 59) 40 #define ACA_REG__STATUS__ADDRV(x) ACA_REG_FIELD(x, 58, 58) 41 #define ACA_REG__STATUS__PCC(x) ACA_REG_FIELD(x, 57, 57) 42 #define ACA_REG__STATUS__ERRCOREIDVAL(x) ACA_REG_FIELD(x, 56, 56) 43 #define ACA_REG__STATUS__TCC(x) ACA_REG_FIELD(x, 55, 55) 44 #define ACA_REG__STATUS__SYNDV(x) ACA_REG_FIELD(x, 53, 53) 45 #define ACA_REG__STATUS__CECC(x) ACA_REG_FIELD(x, 46, 46) 46 #define ACA_REG__STATUS__UECC(x) ACA_REG_FIELD(x, 45, 45) 47 #define ACA_REG__STATUS__DEFERRED(x) ACA_REG_FIELD(x, 44, 44) 48 #define ACA_REG__STATUS__POISON(x) ACA_REG_FIELD(x, 43, 43) 49 #define ACA_REG__STATUS__SCRUB(x) ACA_REG_FIELD(x, 40, 40) 50 #define ACA_REG__STATUS__ERRCOREID(x) ACA_REG_FIELD(x, 37, 32) 51 #define ACA_REG__STATUS__ADDRLSB(x) ACA_REG_FIELD(x, 29, 24) 52 #define ACA_REG__STATUS__ERRORCODEEXT(x) ACA_REG_FIELD(x, 21, 16) 53 #define ACA_REG__STATUS__ERRORCODE(x) ACA_REG_FIELD(x, 15, 0) 54 55 #define ACA_REG__IPID__MCATYPE(x) ACA_REG_FIELD(x, 63, 48) 56 #define ACA_REG__IPID__INSTANCEIDHI(x) ACA_REG_FIELD(x, 47, 44) 57 #define ACA_REG__IPID__HARDWAREID(x) ACA_REG_FIELD(x, 43, 32) 58 #define ACA_REG__IPID__INSTANCEIDLO(x) ACA_REG_FIELD(x, 31, 0) 59 60 #define ACA_REG__MISC0__VALID(x) ACA_REG_FIELD(x, 63, 63) 61 #define ACA_REG__MISC0__OVRFLW(x) ACA_REG_FIELD(x, 48, 48) 62 #define ACA_REG__MISC0__ERRCNT(x) ACA_REG_FIELD(x, 43, 32) 63 64 #define ACA_REG__SYND__ERRORINFORMATION(x) ACA_REG_FIELD(x, 17, 0) 65 66 /* NOTE: The following codes refers to the smu header file */ 67 #define ACA_EXTERROR_CODE_CE 0x3a 68 #define ACA_EXTERROR_CODE_FAULT 0x3b 69 70 #define ACA_ERROR_UE_MASK BIT_MASK(ACA_ERROR_TYPE_UE) 71 #define ACA_ERROR_CE_MASK BIT_MASK(ACA_ERROR_TYPE_CE) 72 #define ACA_ERROR_DEFERRED_MASK BIT_MASK(ACA_ERROR_TYPE_DEFERRED) 73 74 #define mmSMNAID_AID0_MCA_SMU 0x03b30400 /* SMN AID AID0 */ 75 #define mmSMNAID_XCD0_MCA_SMU 0x36430400 /* SMN AID XCD0 */ 76 #define mmSMNAID_XCD1_MCA_SMU 0x38430400 /* SMN AID XCD1 */ 77 #define mmSMNXCD_XCD0_MCA_SMU 0x40430400 /* SMN XCD XCD0 */ 78 79 #define ACA_BANK_ERR_IS_DEFFERED(bank) \ 80 (ACA_REG__STATUS__POISON((bank)->regs[ACA_REG_IDX_STATUS]) || \ 81 ACA_REG__STATUS__DEFERRED((bank)->regs[ACA_REG_IDX_STATUS])) 82 83 #define ACA_BANK_ERR_CE_DE_DECODE(bank) \ 84 (ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \ 85 ACA_ERROR_TYPE_CE) 86 87 #define ACA_BANK_ERR_UE_DE_DECODE(bank) \ 88 (ACA_BANK_ERR_IS_DEFFERED(bank) ? ACA_ERROR_TYPE_DEFERRED : \ 89 ACA_ERROR_TYPE_UE) 90 91 enum aca_reg_idx { 92 ACA_REG_IDX_CTL = 0, 93 ACA_REG_IDX_STATUS = 1, 94 ACA_REG_IDX_ADDR = 2, 95 ACA_REG_IDX_MISC0 = 3, 96 ACA_REG_IDX_CONFIG = 4, 97 ACA_REG_IDX_IPID = 5, 98 ACA_REG_IDX_SYND = 6, 99 ACA_REG_IDX_DESTAT = 8, 100 ACA_REG_IDX_DEADDR = 9, 101 ACA_REG_IDX_CTL_MASK = 10, 102 ACA_REG_IDX_COUNT = 16, 103 }; 104 105 enum aca_hwip_type { 106 ACA_HWIP_TYPE_UNKNOW = -1, 107 ACA_HWIP_TYPE_PSP = 0, 108 ACA_HWIP_TYPE_UMC, 109 ACA_HWIP_TYPE_SMU, 110 ACA_HWIP_TYPE_PCS_XGMI, 111 ACA_HWIP_TYPE_COUNT, 112 }; 113 114 enum aca_error_type { 115 ACA_ERROR_TYPE_INVALID = -1, 116 ACA_ERROR_TYPE_UE = 0, 117 ACA_ERROR_TYPE_CE, 118 ACA_ERROR_TYPE_DEFERRED, 119 ACA_ERROR_TYPE_COUNT 120 }; 121 122 enum aca_smu_type { 123 ACA_SMU_TYPE_INVALID = -1, 124 ACA_SMU_TYPE_UE = 0, 125 ACA_SMU_TYPE_CE, 126 ACA_SMU_TYPE_COUNT, 127 }; 128 129 struct aca_hwip { 130 int hwid; 131 int mcatype; 132 }; 133 134 struct aca_bank { 135 enum aca_error_type aca_err_type; 136 enum aca_smu_type smu_err_type; 137 u64 regs[ACA_MAX_REGS_COUNT]; 138 }; 139 140 struct aca_bank_node { 141 struct aca_bank bank; 142 struct list_head node; 143 }; 144 145 struct aca_banks { 146 int nr_banks; 147 struct list_head list; 148 }; 149 150 struct aca_bank_info { 151 int die_id; 152 int socket_id; 153 int hwid; 154 int mcatype; 155 }; 156 157 struct aca_bank_error { 158 struct list_head node; 159 struct aca_bank_info info; 160 u64 count; 161 }; 162 163 struct aca_error { 164 struct list_head list; 165 struct mutex lock; 166 enum aca_error_type type; 167 int nr_errors; 168 }; 169 170 struct aca_handle_manager { 171 struct list_head list; 172 int nr_handles; 173 }; 174 175 struct aca_error_cache { 176 struct aca_error errors[ACA_ERROR_TYPE_COUNT]; 177 }; 178 179 struct aca_handle { 180 struct list_head node; 181 enum aca_hwip_type hwip; 182 struct amdgpu_device *adev; 183 struct aca_handle_manager *mgr; 184 struct aca_error_cache error_cache; 185 const struct aca_bank_ops *bank_ops; 186 struct device_attribute aca_attr; 187 char attr_name[64]; 188 const char *name; 189 u32 mask; 190 void *data; 191 }; 192 193 struct aca_bank_ops { 194 int (*aca_bank_parser)(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type, void *data); 195 bool (*aca_bank_is_valid)(struct aca_handle *handle, struct aca_bank *bank, enum aca_smu_type type, 196 void *data); 197 }; 198 199 struct aca_smu_funcs { 200 int max_ue_bank_count; 201 int max_ce_bank_count; 202 int (*set_debug_mode)(struct amdgpu_device *adev, bool enable); 203 int (*get_valid_aca_count)(struct amdgpu_device *adev, enum aca_smu_type type, u32 *count); 204 int (*get_valid_aca_bank)(struct amdgpu_device *adev, enum aca_smu_type type, int idx, struct aca_bank *bank); 205 int (*parse_error_code)(struct amdgpu_device *adev, struct aca_bank *bank); 206 }; 207 208 struct amdgpu_aca { 209 struct aca_handle_manager mgr; 210 const struct aca_smu_funcs *smu_funcs; 211 atomic_t ue_update_flag; 212 bool is_enabled; 213 }; 214 215 struct aca_info { 216 enum aca_hwip_type hwip; 217 const struct aca_bank_ops *bank_ops; 218 u32 mask; 219 }; 220 221 int amdgpu_aca_init(struct amdgpu_device *adev); 222 void amdgpu_aca_fini(struct amdgpu_device *adev); 223 int amdgpu_aca_reset(struct amdgpu_device *adev); 224 void amdgpu_aca_set_smu_funcs(struct amdgpu_device *adev, const struct aca_smu_funcs *smu_funcs); 225 bool amdgpu_aca_is_enabled(struct amdgpu_device *adev); 226 227 int aca_bank_info_decode(struct aca_bank *bank, struct aca_bank_info *info); 228 int aca_bank_check_error_codes(struct amdgpu_device *adev, struct aca_bank *bank, int *err_codes, int size); 229 230 int amdgpu_aca_add_handle(struct amdgpu_device *adev, struct aca_handle *handle, 231 const char *name, const struct aca_info *aca_info, void *data); 232 void amdgpu_aca_remove_handle(struct aca_handle *handle); 233 int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *handle, 234 enum aca_error_type type, struct ras_err_data *err_data, 235 struct ras_query_context *qctx); 236 int amdgpu_aca_smu_set_debug_mode(struct amdgpu_device *adev, bool en); 237 void amdgpu_aca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root); 238 int aca_error_cache_log_bank_error(struct aca_handle *handle, struct aca_bank_info *info, 239 enum aca_error_type type, u64 count); 240 #endif 241