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 #define ACA_MAX_REGS_COUNT (16) 30 31 #define ACA_REG_FIELD(x, h, l) (((x) & GENMASK_ULL(h, l)) >> l) 32 #define ACA_REG__STATUS__VAL(x) ACA_REG_FIELD(x, 63, 63) 33 #define ACA_REG__STATUS__OVERFLOW(x) ACA_REG_FIELD(x, 62, 62) 34 #define ACA_REG__STATUS__UC(x) ACA_REG_FIELD(x, 61, 61) 35 #define ACA_REG__STATUS__EN(x) ACA_REG_FIELD(x, 60, 60) 36 #define ACA_REG__STATUS__MISCV(x) ACA_REG_FIELD(x, 59, 59) 37 #define ACA_REG__STATUS__ADDRV(x) ACA_REG_FIELD(x, 58, 58) 38 #define ACA_REG__STATUS__PCC(x) ACA_REG_FIELD(x, 57, 57) 39 #define ACA_REG__STATUS__ERRCOREIDVAL(x) ACA_REG_FIELD(x, 56, 56) 40 #define ACA_REG__STATUS__TCC(x) ACA_REG_FIELD(x, 55, 55) 41 #define ACA_REG__STATUS__SYNDV(x) ACA_REG_FIELD(x, 53, 53) 42 #define ACA_REG__STATUS__CECC(x) ACA_REG_FIELD(x, 46, 46) 43 #define ACA_REG__STATUS__UECC(x) ACA_REG_FIELD(x, 45, 45) 44 #define ACA_REG__STATUS__DEFERRED(x) ACA_REG_FIELD(x, 44, 44) 45 #define ACA_REG__STATUS__POISON(x) ACA_REG_FIELD(x, 43, 43) 46 #define ACA_REG__STATUS__SCRUB(x) ACA_REG_FIELD(x, 40, 40) 47 #define ACA_REG__STATUS__ERRCOREID(x) ACA_REG_FIELD(x, 37, 32) 48 #define ACA_REG__STATUS__ADDRLSB(x) ACA_REG_FIELD(x, 29, 24) 49 #define ACA_REG__STATUS__ERRORCODEEXT(x) ACA_REG_FIELD(x, 21, 16) 50 #define ACA_REG__STATUS__ERRORCODE(x) ACA_REG_FIELD(x, 15, 0) 51 52 #define ACA_REG__IPID__MCATYPE(x) ACA_REG_FIELD(x, 63, 48) 53 #define ACA_REG__IPID__INSTANCEIDHI(x) ACA_REG_FIELD(x, 47, 44) 54 #define ACA_REG__IPID__HARDWAREID(x) ACA_REG_FIELD(x, 43, 32) 55 #define ACA_REG__IPID__INSTANCEIDLO(x) ACA_REG_FIELD(x, 31, 0) 56 57 #define ACA_REG__MISC0__VALID(x) ACA_REG_FIELD(x, 63, 63) 58 #define ACA_REG__MISC0__OVRFLW(x) ACA_REG_FIELD(x, 48, 48) 59 #define ACA_REG__MISC0__ERRCNT(x) ACA_REG_FIELD(x, 43, 32) 60 61 #define ACA_REG__SYND__ERRORINFORMATION(x) ACA_REG_FIELD(x, 17, 0) 62 63 /* NOTE: The following codes refers to the smu header file */ 64 #define ACA_EXTERROR_CODE_CE 0x3a 65 #define ACA_EXTERROR_CODE_FAULT 0x3b 66 67 #define ACA_ERROR_UE_MASK BIT_MASK(ACA_ERROR_TYPE_UE) 68 #define ACA_ERROR_CE_MASK BIT_MASK(ACA_ERROR_TYPE_CE) 69 #define ACA_ERROR_DEFERRED_MASK BIT_MASK(ACA_ERROR_TYPE_DEFERRED) 70 71 enum aca_reg_idx { 72 ACA_REG_IDX_CTL = 0, 73 ACA_REG_IDX_STATUS = 1, 74 ACA_REG_IDX_ADDR = 2, 75 ACA_REG_IDX_MISC0 = 3, 76 ACA_REG_IDX_CONFG = 4, 77 ACA_REG_IDX_IPID = 5, 78 ACA_REG_IDX_SYND = 6, 79 ACA_REG_IDX_DESTAT = 8, 80 ACA_REG_IDX_DEADDR = 9, 81 ACA_REG_IDX_CTL_MASK = 10, 82 ACA_REG_IDX_COUNT = 16, 83 }; 84 85 enum aca_hwip_type { 86 ACA_HWIP_TYPE_UNKNOW = -1, 87 ACA_HWIP_TYPE_PSP = 0, 88 ACA_HWIP_TYPE_UMC, 89 ACA_HWIP_TYPE_SMU, 90 ACA_HWIP_TYPE_PCS_XGMI, 91 ACA_HWIP_TYPE_COUNT, 92 }; 93 94 enum aca_error_type { 95 ACA_ERROR_TYPE_INVALID = -1, 96 ACA_ERROR_TYPE_UE = 0, 97 ACA_ERROR_TYPE_CE, 98 ACA_ERROR_TYPE_DEFERRED, 99 ACA_ERROR_TYPE_COUNT 100 }; 101 102 struct aca_bank { 103 u64 regs[ACA_MAX_REGS_COUNT]; 104 }; 105 106 struct aca_bank_node { 107 struct aca_bank bank; 108 struct list_head node; 109 }; 110 111 struct aca_bank_info { 112 int die_id; 113 int socket_id; 114 int hwid; 115 int mcatype; 116 }; 117 118 struct aca_bank_report { 119 struct aca_bank_info info; 120 u64 count[ACA_ERROR_TYPE_COUNT]; 121 }; 122 123 struct aca_bank_error { 124 struct list_head node; 125 struct aca_bank_info info; 126 u64 count[ACA_ERROR_TYPE_COUNT]; 127 }; 128 129 struct aca_error { 130 struct list_head list; 131 struct mutex lock; 132 enum aca_error_type type; 133 int nr_errors; 134 }; 135 136 struct aca_handle_manager { 137 struct list_head list; 138 int nr_handles; 139 }; 140 141 struct aca_error_cache { 142 struct aca_error errors[ACA_ERROR_TYPE_COUNT]; 143 }; 144 145 struct aca_handle { 146 struct list_head node; 147 enum aca_hwip_type hwip; 148 struct amdgpu_device *adev; 149 struct aca_handle_manager *mgr; 150 struct aca_error_cache error_cache; 151 const struct aca_bank_ops *bank_ops; 152 struct device_attribute aca_attr; 153 char attr_name[64]; 154 const char *name; 155 u32 mask; 156 void *data; 157 }; 158 159 struct aca_bank_ops { 160 int (*aca_bank_generate_report)(struct aca_handle *handle, struct aca_bank *bank, enum aca_error_type type, 161 struct aca_bank_report *report, void *data); 162 bool (*aca_bank_is_valid)(struct aca_handle *handle, struct aca_bank *bank, enum aca_error_type type, 163 void *data); 164 }; 165 166 struct aca_smu_funcs { 167 int max_ue_bank_count; 168 int max_ce_bank_count; 169 int (*set_debug_mode)(struct amdgpu_device *adev, bool enable); 170 int (*get_valid_aca_count)(struct amdgpu_device *adev, enum aca_error_type type, u32 *count); 171 int (*get_valid_aca_bank)(struct amdgpu_device *adev, enum aca_error_type type, int idx, struct aca_bank *bank); 172 }; 173 174 struct amdgpu_aca { 175 struct aca_handle_manager mgr; 176 const struct aca_smu_funcs *smu_funcs; 177 bool is_enabled; 178 }; 179 180 struct aca_info { 181 enum aca_hwip_type hwip; 182 const struct aca_bank_ops *bank_ops; 183 u32 mask; 184 }; 185 186 int amdgpu_aca_init(struct amdgpu_device *adev); 187 void amdgpu_aca_fini(struct amdgpu_device *adev); 188 int amdgpu_aca_reset(struct amdgpu_device *adev); 189 void amdgpu_aca_set_smu_funcs(struct amdgpu_device *adev, const struct aca_smu_funcs *smu_funcs); 190 bool amdgpu_aca_is_enabled(struct amdgpu_device *adev); 191 192 int aca_bank_info_decode(struct aca_bank *bank, struct aca_bank_info *info); 193 int aca_bank_check_error_codes(struct amdgpu_device *adev, struct aca_bank *bank, int *err_codes, int size); 194 195 int amdgpu_aca_add_handle(struct amdgpu_device *adev, struct aca_handle *handle, 196 const char *name, const struct aca_info *aca_info, void *data); 197 void amdgpu_aca_remove_handle(struct aca_handle *handle); 198 int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *handle, 199 enum aca_error_type type, void *data); 200 int amdgpu_aca_smu_set_debug_mode(struct amdgpu_device *adev, bool en); 201 void amdgpu_aca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root); 202 #endif 203