Documentation/ABI/testing/sysfs-bus-platform-devices-ampere-smpro

   1 What:           /sys/bus/platform/devices/smpro-errmon.*/error_[core|mem|pcie|other]_[ce|ue]
   2 KernelVersion:  6.1
   3 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
   4 Description:
   5                 (RO) Contains the 48-byte Ampere (Vendor-Specific) Error Record printed
   6                 in hex format according to the table below:
   7
   8                 +--------+---------------+-------------+------------------------------------------------------------+
   9                 | Offset |     Field     | Size (byte) |                     Description                            |
  10                 +--------+---------------+-------------+------------------------------------------------------------+
  11                 | 00     | Error Type    | 1           | See :ref:`the table below <smpro-error-types>` for details |
  12                 +--------+---------------+-------------+------------------------------------------------------------+
  13                 | 01     | Subtype       | 1           | See :ref:`the table below <smpro-error-types>` for details |
  14                 +--------+---------------+-------------+------------------------------------------------------------+
  15                 | 02     | Instance      | 2           | See :ref:`the table below <smpro-error-types>` for details |
  16                 +--------+---------------+-------------+------------------------------------------------------------+
  17                 | 04     | Error status  | 4           | See ARM RAS specification for details                      |
  18                 +--------+---------------+-------------+------------------------------------------------------------+
  19                 | 08     | Error Address | 8           | See ARM RAS specification for details                      |
  20                 +--------+---------------+-------------+------------------------------------------------------------+
  21                 | 16     | Error Misc 0  | 8           | See ARM RAS specification for details                      |
  22                 +--------+---------------+-------------+------------------------------------------------------------+
  23                 | 24     | Error Misc 1  | 8           | See ARM RAS specification for details                      |
  24                 +--------+---------------+-------------+------------------------------------------------------------+
  25                 | 32     | Error Misc 2  | 8           | See ARM RAS specification for details                      |
  26                 +--------+---------------+-------------+------------------------------------------------------------+
  27                 | 40     | Error Misc 3  | 8           | See ARM RAS specification for details                      |
  28                 +--------+---------------+-------------+------------------------------------------------------------+
  29
  30                 The table below defines the value of error types, their subtype, subcomponent and instance:
  31
  32                 .. _smpro-error-types:
  33
  34                 +-----------------+------------+----------+----------------+----------------------------------------+
  35                 |   Error Group   | Error Type | Sub type | Sub component  |               Instance                 |
  36                 +-----------------+------------+----------+----------------+----------------------------------------+
  37                 | CPM (core)      | 0          | 0        | Snoop-Logic    | CPM #                                  |
  38                 +-----------------+------------+----------+----------------+----------------------------------------+
  39                 | CPM (core)      | 0          | 2        | Armv8 Core 1   | CPM #                                  |
  40                 +-----------------+------------+----------+----------------+----------------------------------------+
  41                 | MCU (mem)       | 1          | 1        | ERR1           | MCU # \| SLOT << 11                    |
  42                 +-----------------+------------+----------+----------------+----------------------------------------+
  43                 | MCU (mem)       | 1          | 2        | ERR2           | MCU # \| SLOT << 11                    |
  44                 +-----------------+------------+----------+----------------+----------------------------------------+
  45                 | MCU (mem)       | 1          | 3        | ERR3           | MCU #                                  |
  46                 +-----------------+------------+----------+----------------+----------------------------------------+
  47                 | MCU (mem)       | 1          | 4        | ERR4           | MCU #                                  |
  48                 +-----------------+------------+----------+----------------+----------------------------------------+
  49                 | MCU (mem)       | 1          | 5        | ERR5           | MCU #                                  |
  50                 +-----------------+------------+----------+----------------+----------------------------------------+
  51                 | MCU (mem)       | 1          | 6        | ERR6           | MCU #                                  |
  52                 +-----------------+------------+----------+----------------+----------------------------------------+
  53                 | MCU (mem)       | 1          | 7        | Link Error     | MCU #                                  |
  54                 +-----------------+------------+----------+----------------+----------------------------------------+
  55                 | Mesh (other)    | 2          | 0        | Cross Point    | X \| (Y << 5) \| NS <<11               |
  56                 +-----------------+------------+----------+----------------+----------------------------------------+
  57                 | Mesh (other)    | 2          | 1        | Home Node(IO)  | X \| (Y << 5) \| NS <<11               |
  58                 +-----------------+------------+----------+----------------+----------------------------------------+
  59                 | Mesh (other)    | 2          | 2        | Home Node(Mem) | X \| (Y << 5) \| NS <<11 \| device<<12 |
  60                 +-----------------+------------+----------+----------------+----------------------------------------+
  61                 | Mesh (other)    | 2          | 4        | CCIX Node      | X \| (Y << 5) \| NS <<11               |
  62                 +-----------------+------------+----------+----------------+----------------------------------------+
  63                 | 2P Link (other) | 3          | 0        | N/A            | Altra 2P Link #                        |
  64                 +-----------------+------------+----------+----------------+----------------------------------------+
  65                 | GIC (other)     | 5          | 0        | ERR0           | 0                                      |
  66                 +-----------------+------------+----------+----------------+----------------------------------------+
  67                 | GIC (other)     | 5          | 1        | ERR1           | 0                                      |
  68                 +-----------------+------------+----------+----------------+----------------------------------------+
  69                 | GIC (other)     | 5          | 2        | ERR2           | 0                                      |
  70                 +-----------------+------------+----------+----------------+----------------------------------------+
  71                 | GIC (other)     | 5          | 3        | ERR3           | 0                                      |
  72                 +-----------------+------------+----------+----------------+----------------------------------------+
  73                 | GIC (other)     | 5          | 4        | ERR4           | 0                                      |
  74                 +-----------------+------------+----------+----------------+----------------------------------------+
  75                 | GIC (other)     | 5          | 5        | ERR5           | 0                                      |
  76                 +-----------------+------------+----------+----------------+----------------------------------------+
  77                 | GIC (other)     | 5          | 6        | ERR6           | 0                                      |
  78                 +-----------------+------------+----------+----------------+----------------------------------------+
  79                 | GIC (other)     | 5          | 7        | ERR7           | 0                                      |
  80                 +-----------------+------------+----------+----------------+----------------------------------------+
  81                 | GIC (other)     | 5          | 8        | ERR8           | 0                                      |
  82                 +-----------------+------------+----------+----------------+----------------------------------------+
  83                 | GIC (other)     | 5          | 9        | ERR9           | 0                                      |
  84                 +-----------------+------------+----------+----------------+----------------------------------------+
  85                 | GIC (other)     | 5          | 10       | ERR10          | 0                                      |
  86                 +-----------------+------------+----------+----------------+----------------------------------------+
  87                 | GIC (other)     | 5          | 11       | ERR11          | 0                                      |
  88                 +-----------------+------------+----------+----------------+----------------------------------------+
  89                 | GIC (other)     | 5          | 12       | ERR12          | 0                                      |
  90                 +-----------------+------------+----------+----------------+----------------------------------------+
  91                 | GIC (other)     | 5          | 13-21    | ERR13          | RC # + 1                               |
  92                 +-----------------+------------+----------+----------------+----------------------------------------+
  93                 | SMMU (other)    | 6          | TCU      | 100            | RC #                                   |
  94                 +-----------------+------------+----------+----------------+----------------------------------------+
  95                 | SMMU (other)    | 6          | TBU0     | 0              | RC #                                   |
  96                 +-----------------+------------+----------+----------------+----------------------------------------+
  97                 | SMMU (other)    | 6          | TBU1     | 1              | RC #                                   |
  98                 +-----------------+------------+----------+----------------+----------------------------------------+
  99                 | SMMU (other)    | 6          | TBU2     | 2              | RC #                                   |
 100                 +-----------------+------------+----------+----------------+----------------------------------------+
 101                 | SMMU (other)    | 6          | TBU3     | 3              | RC #                                   |
 102                 +-----------------+------------+----------+----------------+----------------------------------------+
 103                 | SMMU (other)    | 6          | TBU4     | 4              | RC #                                   |
 104                 +-----------------+------------+----------+----------------+----------------------------------------+
 105                 | SMMU (other)    | 6          | TBU5     | 5              | RC #                                   |
 106                 +-----------------+------------+----------+----------------+----------------------------------------+
 107                 | SMMU (other)    | 6          | TBU6     | 6              | RC #                                   |
 108                 +-----------------+------------+----------+----------------+----------------------------------------+
 109                 | SMMU (other)    | 6          | TBU7     | 7              | RC #                                   |
 110                 +-----------------+------------+----------+----------------+----------------------------------------+
 111                 | SMMU (other)    | 6          | TBU8     | 8              | RC #                                   |
 112                 +-----------------+------------+----------+----------------+----------------------------------------+
 113                 | SMMU (other)    | 6          | TBU9     | 9              | RC #                                   |
 114                 +-----------------+------------+----------+----------------+----------------------------------------+
 115                 | PCIe AER (pcie) | 7          | Root     | 0              | RC #                                   |
 116                 +-----------------+------------+----------+----------------+----------------------------------------+
 117                 | PCIe AER (pcie) | 7          | Device   | 1              | RC #                                   |
 118                 +-----------------+------------+----------+----------------+----------------------------------------+
 119                 | PCIe RC (pcie)  | 8          | RCA HB   | 0              | RC #                                   |
 120                 +-----------------+------------+----------+----------------+----------------------------------------+
 121                 | PCIe RC (pcie)  | 8          | RCB HB   | 1              | RC #                                   |
 122                 +-----------------+------------+----------+----------------+----------------------------------------+
 123                 | PCIe RC (pcie)  | 8          | RASDP    | 8              | RC #                                   |
 124                 +-----------------+------------+----------+----------------+----------------------------------------+
 125                 | OCM (other)     | 9          | ERR0     | 0              | 0                                      |
 126                 +-----------------+------------+----------+----------------+----------------------------------------+
 127                 | OCM (other)     | 9          | ERR1     | 1              | 0                                      |
 128                 +-----------------+------------+----------+----------------+----------------------------------------+
 129                 | OCM (other)     | 9          | ERR2     | 2              | 0                                      |
 130                 +-----------------+------------+----------+----------------+----------------------------------------+
 131                 | SMpro (other)   | 10         | ERR0     | 0              | 0                                      |
 132                 +-----------------+------------+----------+----------------+----------------------------------------+
 133                 | SMpro (other)   | 10         | ERR1     | 1              | 0                                      |
 134                 +-----------------+------------+----------+----------------+----------------------------------------+
 135                 | SMpro (other)   | 10         | MPA_ERR  | 2              | 0                                      |
 136                 +-----------------+------------+----------+----------------+----------------------------------------+
 137                 | PMpro (other)   | 11         | ERR0     | 0              | 0                                      |
 138                 +-----------------+------------+----------+----------------+----------------------------------------+
 139                 | PMpro (other)   | 11         | ERR1     | 1              | 0                                      |
 140                 +-----------------+------------+----------+----------------+----------------------------------------+
 141                 | PMpro (other)   | 11         | MPA_ERR  | 2              | 0                                      |
 142                 +-----------------+------------+----------+----------------+----------------------------------------+
 143
 144                 Example::
 145
 146                  # cat error_other_ue
 147                  880807001e004010401040101500000001004010401040100c0000000000000000000000000000000000000000000000
 148
 149                 The detail of each sysfs entries is as below:
 150
 151                 +-------------+---------------------------------------------------------+----------------------------------+
 152                 |   Error     |                   Sysfs entry                           |   Description (when triggered)   |
 153                 +-------------+---------------------------------------------------------+----------------------------------+
 154                 | Core's CE   | /sys/bus/platform/devices/smpro-errmon.*/error_core_ce  | Core has CE error                |
 155                 +-------------+---------------------------------------------------------+----------------------------------+
 156                 | Core's UE   | /sys/bus/platform/devices/smpro-errmon.*/error_core_ue  | Core has UE error                |
 157                 +-------------+---------------------------------------------------------+----------------------------------+
 158                 | Memory's CE | /sys/bus/platform/devices/smpro-errmon.*/error_mem_ce   | Memory has CE error              |
 159                 +-------------+---------------------------------------------------------+----------------------------------+
 160                 | Memory's UE | /sys/bus/platform/devices/smpro-errmon.*/error_mem_ue   | Memory has UE error              |
 161                 +-------------+---------------------------------------------------------+----------------------------------+
 162                 | PCIe's CE   | /sys/bus/platform/devices/smpro-errmon.*/error_pcie_ce  | any PCIe controller has CE error |
 163                 +-------------+---------------------------------------------------------+----------------------------------+
 164                 | PCIe's UE   | /sys/bus/platform/devices/smpro-errmon.*/error_pcie_ue  | any PCIe controller has UE error |
 165                 +-------------+---------------------------------------------------------+----------------------------------+
 166                 | Other's CE  | /sys/bus/platform/devices/smpro-errmon.*/error_other_ce | any other CE error               |
 167                 +-------------+---------------------------------------------------------+----------------------------------+
 168                 | Other's UE  | /sys/bus/platform/devices/smpro-errmon.*/error_other_ue | any other UE error               |
 169                 +-------------+---------------------------------------------------------+----------------------------------+
 170
 171                 UE: Uncorrect-able Error
 172                 CE: Correct-able Error
 173
 174                 For details, see section `3.3 Ampere (Vendor-Specific) Error Record Formats,
 175                 Altra Family RAS Supplement`.
 176
 177
 178 What:           /sys/bus/platform/devices/smpro-errmon.*/overflow_[core|mem|pcie|other]_[ce|ue]
 179 KernelVersion:  6.1
 180 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
 181 Description:
 182                 (RO) Return the overflow status of each type HW error reported:
 183
 184                   - 0      : No overflow
 185                   - 1      : There is an overflow and the oldest HW errors are dropped
 186
 187                 The detail of each sysfs entries is as below:
 188
 189                 +-------------+-----------------------------------------------------------+---------------------------------------+
 190                 |   Overflow  |                   Sysfs entry                             |             Description               |
 191                 +-------------+-----------------------------------------------------------+---------------------------------------+
 192                 | Core's CE   | /sys/bus/platform/devices/smpro-errmon.*/overflow_core_ce | Core CE error overflow                |
 193                 +-------------+-----------------------------------------------------------+---------------------------------------+
 194                 | Core's UE   | /sys/bus/platform/devices/smpro-errmon.*/overflow_core_ue | Core UE error overflow                |
 195                 +-------------+-----------------------------------------------------------+---------------------------------------+
 196                 | Memory's CE | /sys/bus/platform/devices/smpro-errmon.*/overflow_mem_ce  | Memory CE error overflow              |
 197                 +-------------+-----------------------------------------------------------+---------------------------------------+
 198                 | Memory's UE | /sys/bus/platform/devices/smpro-errmon.*/overflow_mem_ue  | Memory UE error overflow              |
 199                 +-------------+-----------------------------------------------------------+---------------------------------------+
 200                 | PCIe's CE   | /sys/bus/platform/devices/smpro-errmon.*/overflow_pcie_ce | any PCIe controller CE error overflow |
 201                 +-------------+-----------------------------------------------------------+---------------------------------------+
 202                 | PCIe's UE   | /sys/bus/platform/devices/smpro-errmon.*/overflow_pcie_ue | any PCIe controller UE error overflow |
 203                 +-------------+-----------------------------------------------------------+---------------------------------------+
 204                 | Other's CE  | /sys/bus/platform/devices/smpro-errmon.*/overflow_other_ce| any other CE error overflow           |
 205                 +-------------+-----------------------------------------------------------+---------------------------------------+
 206                 | Other's UE  | /sys/bus/platform/devices/smpro-errmon.*/overflow_other_ue| other UE error overflow               |
 207                 +-------------+-----------------------------------------------------------+---------------------------------------+
 208
 209                 where:
 210
 211                   - UE: Uncorrect-able Error
 212                   - CE: Correct-able Error
 213
 214 What:           /sys/bus/platform/devices/smpro-errmon.*/[error|warn]_[smpro|pmpro]
 215 KernelVersion:  6.1
 216 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
 217 Description:
 218                 (RO) Contains the internal firmware error/warning printed as hex format.
 219
 220                 The detail of each sysfs entries is as below:
 221
 222                 +---------------+------------------------------------------------------+--------------------------+
 223                 |   Error       |                   Sysfs entry                        |        Description       |
 224                 +---------------+------------------------------------------------------+--------------------------+
 225                 | SMpro error   | /sys/bus/platform/devices/smpro-errmon.*/error_smpro | system has SMpro error   |
 226                 +---------------+------------------------------------------------------+--------------------------+
 227                 | SMpro warning | /sys/bus/platform/devices/smpro-errmon.*/warn_smpro  | system has SMpro warning |
 228                 +---------------+------------------------------------------------------+--------------------------+
 229                 | PMpro error   | /sys/bus/platform/devices/smpro-errmon.*/error_pmpro | system has PMpro error   |
 230                 +---------------+------------------------------------------------------+--------------------------+
 231                 | PMpro warning | /sys/bus/platform/devices/smpro-errmon.*/warn_pmpro  | system has PMpro warning |
 232                 +---------------+------------------------------------------------------+--------------------------+
 233
 234                 For details, see section `5.10 RAS Internal Error Register Definitions,
 235                 Altra Family Soc BMC Interface Specification`.
 236
 237 What:           /sys/bus/platform/devices/smpro-errmon.*/event_[vrd_warn_fault|vrd_hot|dimm_hot|dimm_2x_refresh]
 238 KernelVersion:  6.1 (event_[vrd_warn_fault|vrd_hot|dimm_hot]), 6.4 (event_dimm_2x_refresh)
 239 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
 240 Description:
 241                 (RO) Contains the detail information in case of VRD/DIMM warning/hot events
 242                 in hex format as below::
 243
 244                     AAAA
 245
 246                 where:
 247
 248                   - ``AAAA``: The event detail information data
 249
 250                 The detail of each sysfs entries is as below:
 251
 252                 +---------------+---------------------------------------------------------------+---------------------+
 253                 |   Event       |                        Sysfs entry                            |     Description     |
 254                 +---------------+---------------------------------------------------------------+---------------------+
 255                 | VRD HOT       | /sys/bus/platform/devices/smpro-errmon.*/event_vrd_hot        | VRD Hot             |
 256                 +---------------+---------------------------------------------------------------+---------------------+
 257                 | VR Warn/Fault | /sys/bus/platform/devices/smpro-errmon.*/event_vrd_warn_fault | VR Warning or Fault |
 258                 +---------------+---------------------------------------------------------------+---------------------+
 259                 | DIMM HOT      | /sys/bus/platform/devices/smpro-errmon.*/event_dimm_hot       | DIMM Hot            |
 260                 +---------------+---------------------------------------------------------------+---------------------+
 261                 | DIMM 2X       | /sys/bus/platform/devices/smpro-errmon.*/event_dimm_2x_refresh| DIMM 2x refresh rate|
 262                 | REFRESH RATE  |                                                               | event in high temp  |
 263                 +---------------+---------------------------------------------------------------+---------------------+
 264
 265                 For more details, see section `5.7 GPI Status Registers and 5.9 Memory Error Register Definitions,
 266                 Altra Family Soc BMC Interface Specification`.
 267
 268 What:           /sys/bus/platform/devices/smpro-errmon.*/event_dimm[0-15]_syndrome
 269 KernelVersion:  6.4
 270 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
 271 Description:
 272                 (RO) The sysfs returns the 2-byte DIMM failure syndrome data for slot
 273                 0-15 if it failed to initialize.
 274
 275                 For more details, see section `5.11 Boot Stage Register Definitions,
 276                 Altra Family Soc BMC Interface Specification`.
 277
 278 What:           /sys/bus/platform/devices/smpro-misc.*/boot_progress
 279 KernelVersion:  6.1
 280 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
 281 Description:
 282                 (RO) Contains the boot stages information in hex as format below::
 283
 284                     AABBCCCCCCCC
 285
 286                 where:
 287
 288                   - ``AA``      : The boot stages
 289
 290                     - 00: SMpro firmware booting
 291                     - 01: PMpro firmware booting
 292                     - 02: ATF BL1 firmware booting
 293                     - 03: DDR initialization
 294                     - 04: DDR training report status
 295                     - 05: ATF BL2 firmware booting
 296                     - 06: ATF BL31 firmware booting
 297                     - 07: ATF BL32 firmware booting
 298                     - 08: UEFI firmware booting
 299                     - 09: OS booting
 300
 301                   - ``BB``      : Boot status
 302
 303                     - 00: Not started
 304                     - 01: Started
 305                     - 02: Completed without error
 306                     - 03: Failed.
 307
 308                   - ``CCCCCCCC``: Boot status information defined for each boot stages
 309
 310                 For details, see section `5.11 Boot Stage Register Definitions`
 311                 and section `6. Processor Boot Progress Codes, Altra Family Soc BMC
 312                 Interface Specification`.
 313
 314
 315 What:           /sys/bus/platform/devices/smpro-misc*/soc_power_limit
 316 KernelVersion:  6.1
 317 Contact:        Quan Nguyen <quan@os.amperecomputing.com>
 318 Description:
 319                 (RW) Contains the desired SoC power limit in Watt.
 320                 Writes to this sysfs set the desired SoC power limit (W).
 321                 Reads from this register return the current SoC power limit (W).
 322                 The value ranges:
 323
 324                   - Minimum: 120 W
 325                   - Maximum: Socket TDP power