Blame view
drivers/edac/ghes_edac.c
13.6 KB
77c5f5d2f ghes_edac: Regist... |
1 2 3 4 5 6 |
/* * GHES/EDAC Linux driver * * This file may be distributed under the terms of the GNU General Public * License version 2. * |
37e59f876 [media, edac] Cha... |
7 |
* Copyright (c) 2013 by Mauro Carvalho Chehab |
77c5f5d2f ghes_edac: Regist... |
8 9 10 |
* * Red Hat Inc. http://www.redhat.com */ |
d2a685661 ghes_edac: Improv... |
11 |
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt |
77c5f5d2f ghes_edac: Regist... |
12 13 |
#include <acpi/ghes.h> #include <linux/edac.h> |
32fa1f53c ghes_edac: do a b... |
14 |
#include <linux/dmi.h> |
78d88e8a3 edac: rename edac... |
15 |
#include "edac_module.h" |
8ae8f50ad ghes_edac: Fix RA... |
16 |
#include <ras/ras_event.h> |
77c5f5d2f ghes_edac: Regist... |
17 |
|
77c5f5d2f ghes_edac: Regist... |
18 19 20 21 22 23 |
#define GHES_EDAC_REVISION " Ver: 1.0.0" struct ghes_edac_pvt { struct list_head list; struct ghes *ghes; struct mem_ctl_info *mci; |
689c9cd81 ghes_edac: Make i... |
24 25 |
/* Buffers for the error handling routine */ |
8ae8f50ad ghes_edac: Fix RA... |
26 |
char detail_location[240]; |
689c9cd81 ghes_edac: Make i... |
27 28 |
char other_detail[160]; char msg[80]; |
77c5f5d2f ghes_edac: Regist... |
29 30 31 32 33 |
}; static LIST_HEAD(ghes_reglist); static DEFINE_MUTEX(ghes_edac_lock); static int ghes_edac_mc_num; |
d2a685661 ghes_edac: Improv... |
34 |
|
32fa1f53c ghes_edac: do a b... |
35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
/* Memory Device - Type 17 of SMBIOS spec */ struct memdev_dmi_entry { u8 type; u8 length; u16 handle; u16 phys_mem_array_handle; u16 mem_err_info_handle; u16 total_width; u16 data_width; u16 size; u8 form_factor; u8 device_set; u8 device_locator; u8 bank_locator; u8 memory_type; u16 type_detail; u16 speed; u8 manufacturer; u8 serial_number; u8 asset_tag; u8 part_number; u8 attributes; u32 extended_size; u16 conf_mem_clk_speed; } __attribute__((__packed__)); struct ghes_edac_dimm_fill { struct mem_ctl_info *mci; unsigned count; }; |
32fa1f53c ghes_edac: do a b... |
65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
static void ghes_edac_count_dimms(const struct dmi_header *dh, void *arg) { int *num_dimm = arg; if (dh->type == DMI_ENTRY_MEM_DEVICE) (*num_dimm)++; } static void ghes_edac_dmidecode(const struct dmi_header *dh, void *arg) { struct ghes_edac_dimm_fill *dimm_fill = arg; struct mem_ctl_info *mci = dimm_fill->mci; if (dh->type == DMI_ENTRY_MEM_DEVICE) { struct memdev_dmi_entry *entry = (struct memdev_dmi_entry *)dh; struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, dimm_fill->count, 0, 0); if (entry->size == 0xffff) { |
d2a685661 ghes_edac: Improv... |
85 86 87 |
pr_info("Can't get DIMM%i size ", dimm_fill->count); |
32fa1f53c ghes_edac: do a b... |
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 |
dimm->nr_pages = MiB_TO_PAGES(32);/* Unknown */ } else if (entry->size == 0x7fff) { dimm->nr_pages = MiB_TO_PAGES(entry->extended_size); } else { if (entry->size & 1 << 15) dimm->nr_pages = MiB_TO_PAGES((entry->size & 0x7fff) << 10); else dimm->nr_pages = MiB_TO_PAGES(entry->size); } switch (entry->memory_type) { case 0x12: if (entry->type_detail & 1 << 13) dimm->mtype = MEM_RDDR; else dimm->mtype = MEM_DDR; break; case 0x13: if (entry->type_detail & 1 << 13) dimm->mtype = MEM_RDDR2; else dimm->mtype = MEM_DDR2; break; case 0x14: dimm->mtype = MEM_FB_DDR2; break; case 0x18: if (entry->type_detail & 1 << 13) dimm->mtype = MEM_RDDR3; else dimm->mtype = MEM_DDR3; break; default: if (entry->type_detail & 1 << 6) dimm->mtype = MEM_RMBS; else if ((entry->type_detail & ((1 << 7) | (1 << 13))) == ((1 << 7) | (1 << 13))) dimm->mtype = MEM_RDR; else if (entry->type_detail & 1 << 7) dimm->mtype = MEM_SDR; else if (entry->type_detail & 1 << 9) dimm->mtype = MEM_EDO; else dimm->mtype = MEM_UNKNOWN; } /* * Actually, we can only detect if the memory has bits for * checksum or not */ if (entry->total_width == entry->data_width) dimm->edac_mode = EDAC_NONE; else dimm->edac_mode = EDAC_SECDED; dimm->dtype = DEV_UNKNOWN; dimm->grain = 128; /* Likely, worse case */ /* * FIXME: It shouldn't be hard to also fill the DIMM labels */ if (dimm->nr_pages) { |
d2a685661 ghes_edac: Improv... |
152 153 |
edac_dbg(1, "DIMM%i: %s size = %d MB%s ", |
58a9c251c EDAC, ghes_edac: ... |
154 |
dimm_fill->count, edac_mem_types[dimm->mtype], |
32fa1f53c ghes_edac: do a b... |
155 156 |
PAGES_TO_MiB(dimm->nr_pages), (dimm->edac_mode != EDAC_NONE) ? "(ECC)" : ""); |
d2a685661 ghes_edac: Improv... |
157 158 |
edac_dbg(2, "\ttype %d, detail 0x%02x, width %d(total %d) ", |
32fa1f53c ghes_edac: do a b... |
159 160 161 162 163 164 165 |
entry->memory_type, entry->type_detail, entry->total_width, entry->data_width); } dimm_fill->count++; } } |
77c5f5d2f ghes_edac: Regist... |
166 |
void ghes_edac_report_mem_error(struct ghes *ghes, int sev, |
f04c62a70 ghes_edac: add su... |
167 |
struct cper_sec_mem_err *mem_err) |
77c5f5d2f ghes_edac: Regist... |
168 |
{ |
f04c62a70 ghes_edac: add su... |
169 170 171 172 |
enum hw_event_mc_err_type type; struct edac_raw_error_desc *e; struct mem_ctl_info *mci; struct ghes_edac_pvt *pvt = NULL; |
689c9cd81 ghes_edac: Make i... |
173 |
char *p; |
8ae8f50ad ghes_edac: Fix RA... |
174 |
u8 grain_bits; |
f04c62a70 ghes_edac: add su... |
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
list_for_each_entry(pvt, &ghes_reglist, list) { if (ghes == pvt->ghes) break; } if (!pvt) { pr_err("Internal error: Can't find EDAC structure "); return; } mci = pvt->mci; e = &mci->error_desc; /* Cleans the error report buffer */ memset(e, 0, sizeof (*e)); e->error_count = 1; |
689c9cd81 ghes_edac: Make i... |
191 192 193 194 195 196 197 198 |
strcpy(e->label, "unknown label"); e->msg = pvt->msg; e->other_detail = pvt->other_detail; e->top_layer = -1; e->mid_layer = -1; e->low_layer = -1; *pvt->other_detail = '\0'; *pvt->msg = '\0'; |
f04c62a70 ghes_edac: add su... |
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 |
switch (sev) { case GHES_SEV_CORRECTED: type = HW_EVENT_ERR_CORRECTED; break; case GHES_SEV_RECOVERABLE: type = HW_EVENT_ERR_UNCORRECTED; break; case GHES_SEV_PANIC: type = HW_EVENT_ERR_FATAL; break; default: case GHES_SEV_NO: type = HW_EVENT_ERR_INFO; } |
689c9cd81 ghes_edac: Make i... |
214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 |
edac_dbg(1, "error validation_bits: 0x%08llx ", (long long)mem_err->validation_bits); /* Error type, mapped on e->msg */ if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_TYPE) { p = pvt->msg; switch (mem_err->error_type) { case 0: p += sprintf(p, "Unknown"); break; case 1: p += sprintf(p, "No error"); break; case 2: p += sprintf(p, "Single-bit ECC"); break; case 3: p += sprintf(p, "Multi-bit ECC"); break; case 4: p += sprintf(p, "Single-symbol ChipKill ECC"); break; case 5: p += sprintf(p, "Multi-symbol ChipKill ECC"); break; case 6: p += sprintf(p, "Master abort"); break; case 7: p += sprintf(p, "Target abort"); break; case 8: p += sprintf(p, "Parity Error"); break; case 9: p += sprintf(p, "Watchdog timeout"); break; case 10: p += sprintf(p, "Invalid address"); break; case 11: p += sprintf(p, "Mirror Broken"); break; case 12: p += sprintf(p, "Memory Sparing"); break; case 13: p += sprintf(p, "Scrub corrected error"); break; case 14: p += sprintf(p, "Scrub uncorrected error"); break; case 15: p += sprintf(p, "Physical Memory Map-out event"); break; default: p += sprintf(p, "reserved error (%d)", mem_err->error_type); } } else { strcpy(pvt->msg, "unknown error"); } /* Error address */ |
147de1477 ACPI, APEI, CPER:... |
279 |
if (mem_err->validation_bits & CPER_MEM_VALID_PA) { |
689c9cd81 ghes_edac: Make i... |
280 281 282 283 284 |
e->page_frame_number = mem_err->physical_addr >> PAGE_SHIFT; e->offset_in_page = mem_err->physical_addr & ~PAGE_MASK; } /* Error grain */ |
147de1477 ACPI, APEI, CPER:... |
285 |
if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) |
689c9cd81 ghes_edac: Make i... |
286 |
e->grain = ~(mem_err->physical_addr_mask & ~PAGE_MASK); |
689c9cd81 ghes_edac: Make i... |
287 288 289 290 291 292 293 294 295 |
/* Memory error location, mapped on e->location */ p = e->location; if (mem_err->validation_bits & CPER_MEM_VALID_NODE) p += sprintf(p, "node:%d ", mem_err->node); if (mem_err->validation_bits & CPER_MEM_VALID_CARD) p += sprintf(p, "card:%d ", mem_err->card); if (mem_err->validation_bits & CPER_MEM_VALID_MODULE) p += sprintf(p, "module:%d ", mem_err->module); |
56507694d EDAC, GHES: Updat... |
296 297 |
if (mem_err->validation_bits & CPER_MEM_VALID_RANK_NUMBER) p += sprintf(p, "rank:%d ", mem_err->rank); |
689c9cd81 ghes_edac: Make i... |
298 299 300 301 302 303 304 305 |
if (mem_err->validation_bits & CPER_MEM_VALID_BANK) p += sprintf(p, "bank:%d ", mem_err->bank); if (mem_err->validation_bits & CPER_MEM_VALID_ROW) p += sprintf(p, "row:%d ", mem_err->row); if (mem_err->validation_bits & CPER_MEM_VALID_COLUMN) p += sprintf(p, "col:%d ", mem_err->column); if (mem_err->validation_bits & CPER_MEM_VALID_BIT_POSITION) p += sprintf(p, "bit_pos:%d ", mem_err->bit_pos); |
56507694d EDAC, GHES: Updat... |
306 307 308 309 310 311 312 313 314 |
if (mem_err->validation_bits & CPER_MEM_VALID_MODULE_HANDLE) { const char *bank = NULL, *device = NULL; dmi_memdev_name(mem_err->mem_dev_handle, &bank, &device); if (bank != NULL && device != NULL) p += sprintf(p, "DIMM location:%s %s ", bank, device); else p += sprintf(p, "DIMM DMI handle: 0x%.4x ", mem_err->mem_dev_handle); } |
689c9cd81 ghes_edac: Make i... |
315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 |
if (p > e->location) *(p - 1) = '\0'; /* All other fields are mapped on e->other_detail */ p = pvt->other_detail; if (mem_err->validation_bits & CPER_MEM_VALID_ERROR_STATUS) { u64 status = mem_err->error_status; p += sprintf(p, "status(0x%016llx): ", (long long)status); switch ((status >> 8) & 0xff) { case 1: p += sprintf(p, "Error detected internal to the component "); break; case 16: p += sprintf(p, "Error detected in the bus "); break; case 4: p += sprintf(p, "Storage error in DRAM memory "); break; case 5: p += sprintf(p, "Storage error in TLB "); break; case 6: p += sprintf(p, "Storage error in cache "); break; case 7: p += sprintf(p, "Error in one or more functional units "); break; case 8: p += sprintf(p, "component failed self test "); break; case 9: p += sprintf(p, "Overflow or undervalue of internal queue "); break; case 17: p += sprintf(p, "Virtual address not found on IO-TLB or IO-PDIR "); break; case 18: p += sprintf(p, "Improper access error "); break; case 19: p += sprintf(p, "Access to a memory address which is not mapped to any component "); break; case 20: p += sprintf(p, "Loss of Lockstep "); break; case 21: p += sprintf(p, "Response not associated with a request "); break; case 22: p += sprintf(p, "Bus parity error - must also set the A, C, or D Bits "); break; case 23: p += sprintf(p, "Detection of a PATH_ERROR "); break; case 25: p += sprintf(p, "Bus operation timeout "); break; case 26: p += sprintf(p, "A read was issued to data that has been poisoned "); break; default: p += sprintf(p, "reserved "); break; } } if (mem_err->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) p += sprintf(p, "requestorID: 0x%016llx ", (long long)mem_err->requestor_id); if (mem_err->validation_bits & CPER_MEM_VALID_RESPONDER_ID) p += sprintf(p, "responderID: 0x%016llx ", (long long)mem_err->responder_id); if (mem_err->validation_bits & CPER_MEM_VALID_TARGET_ID) p += sprintf(p, "targetID: 0x%016llx ", (long long)mem_err->responder_id); if (p > pvt->other_detail) *(p - 1) = '\0'; |
f04c62a70 ghes_edac: add su... |
392 |
|
8ae8f50ad ghes_edac: Fix RA... |
393 394 |
/* Generate the trace event */ grain_bits = fls_long(e->grain); |
665aa8cdc ghes_edac: Use sn... |
395 396 |
snprintf(pvt->detail_location, sizeof(pvt->detail_location), "APEI location: %s %s", e->location, e->other_detail); |
8ae8f50ad ghes_edac: Fix RA... |
397 398 |
trace_mc_event(type, e->msg, e->label, e->error_count, mci->mc_idx, e->top_layer, e->mid_layer, e->low_layer, |
990995bad EDAC: Fix PAGES_T... |
399 |
(e->page_frame_number << PAGE_SHIFT) | e->offset_in_page, |
8ae8f50ad ghes_edac: Fix RA... |
400 401 402 |
grain_bits, e->syndrome, pvt->detail_location); /* Report the error via EDAC API */ |
f04c62a70 ghes_edac: add su... |
403 |
edac_raw_mc_handle_error(type, mci, e); |
77c5f5d2f ghes_edac: Regist... |
404 405 406 407 408 |
} EXPORT_SYMBOL_GPL(ghes_edac_report_mem_error); int ghes_edac_register(struct ghes *ghes, struct device *dev) { |
32fa1f53c ghes_edac: do a b... |
409 410 |
bool fake = false; int rc, num_dimm = 0; |
77c5f5d2f ghes_edac: Regist... |
411 412 |
struct mem_ctl_info *mci; struct edac_mc_layer layers[1]; |
77c5f5d2f ghes_edac: Regist... |
413 |
struct ghes_edac_pvt *pvt; |
32fa1f53c ghes_edac: do a b... |
414 415 416 417 418 419 420 421 422 423 |
struct ghes_edac_dimm_fill dimm_fill; /* Get the number of DIMMs */ dmi_walk(ghes_edac_count_dimms, &num_dimm); /* Check if we've got a bogus BIOS */ if (num_dimm == 0) { fake = true; num_dimm = 1; } |
77c5f5d2f ghes_edac: Regist... |
424 425 |
layers[0].type = EDAC_MC_LAYER_ALL_MEM; |
32fa1f53c ghes_edac: do a b... |
426 |
layers[0].size = num_dimm; |
77c5f5d2f ghes_edac: Regist... |
427 428 429 430 431 432 433 434 435 436 |
layers[0].is_virt_csrow = true; /* * We need to serialize edac_mc_alloc() and edac_mc_add_mc(), * to avoid duplicated memory controller numbers */ mutex_lock(&ghes_edac_lock); mci = edac_mc_alloc(ghes_edac_mc_num, ARRAY_SIZE(layers), layers, sizeof(*pvt)); if (!mci) { |
d2a685661 ghes_edac: Improv... |
437 438 |
pr_info("Can't allocate memory for EDAC data "); |
77c5f5d2f ghes_edac: Regist... |
439 440 441 442 443 444 |
mutex_unlock(&ghes_edac_lock); return -ENOMEM; } pvt = mci->pvt_info; memset(pvt, 0, sizeof(*pvt)); |
f04c62a70 ghes_edac: add su... |
445 |
list_add_tail(&pvt->list, &ghes_reglist); |
77c5f5d2f ghes_edac: Regist... |
446 447 448 449 450 451 452 453 454 455 456 |
pvt->ghes = ghes; pvt->mci = mci; mci->pdev = dev; mci->mtype_cap = MEM_FLAG_EMPTY; mci->edac_ctl_cap = EDAC_FLAG_NONE; mci->edac_cap = EDAC_FLAG_NONE; mci->mod_name = "ghes_edac.c"; mci->mod_ver = GHES_EDAC_REVISION; mci->ctl_name = "ghes_edac"; mci->dev_name = "ghes"; |
d2a685661 ghes_edac: Improv... |
457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 |
if (!ghes_edac_mc_num) { if (!fake) { pr_info("This EDAC driver relies on BIOS to enumerate memory and get error reports. "); pr_info("Unfortunately, not all BIOSes reflect the memory layout correctly. "); pr_info("So, the end result of using this driver varies from vendor to vendor. "); pr_info("If you find incorrect reports, please contact your hardware vendor "); pr_info("to correct its BIOS. "); pr_info("This system has %d DIMM sockets. ", num_dimm); } else { pr_info("This system has a very crappy BIOS: It doesn't even list the DIMMS. "); pr_info("Its SMBIOS info is wrong. It is doubtful that the error report would "); pr_info("work on such system. Use this driver with caution "); } } |
32fa1f53c ghes_edac: do a b... |
481 |
if (!fake) { |
5ee726db5 ghes_edac: Don't ... |
482 483 484 485 486 487 488 489 490 491 492 493 494 |
/* * Fill DIMM info from DMI for the memory controller #0 * * Keep it in blank for the other memory controllers, as * there's no reliable way to properly credit each DIMM to * the memory controller, as different BIOSes fill the * DMI bank location fields on different ways */ if (!ghes_edac_mc_num) { dimm_fill.count = 0; dimm_fill.mci = mci; dmi_walk(ghes_edac_dmidecode, &dimm_fill); } |
32fa1f53c ghes_edac: do a b... |
495 496 497 |
} else { struct dimm_info *dimm = EDAC_DIMM_PTR(mci->layers, mci->dimms, mci->n_layers, 0, 0, 0); |
77c5f5d2f ghes_edac: Regist... |
498 |
|
d2a685661 ghes_edac: Improv... |
499 |
dimm->nr_pages = 1; |
32fa1f53c ghes_edac: do a b... |
500 501 502 503 504 |
dimm->grain = 128; dimm->mtype = MEM_UNKNOWN; dimm->dtype = DEV_UNKNOWN; dimm->edac_mode = EDAC_SECDED; } |
77c5f5d2f ghes_edac: Regist... |
505 506 507 |
rc = edac_mc_add_mc(mci); if (rc < 0) { |
d2a685661 ghes_edac: Improv... |
508 509 |
pr_info("Can't register at EDAC core "); |
77c5f5d2f ghes_edac: Regist... |
510 511 512 513 514 515 516 517 518 519 520 521 522 523 |
edac_mc_free(mci); mutex_unlock(&ghes_edac_lock); return -ENODEV; } ghes_edac_mc_num++; mutex_unlock(&ghes_edac_lock); return 0; } EXPORT_SYMBOL_GPL(ghes_edac_register); void ghes_edac_unregister(struct ghes *ghes) { struct mem_ctl_info *mci; |
5dae92a71 ghes_edac: fix to... |
524 |
struct ghes_edac_pvt *pvt, *tmp; |
77c5f5d2f ghes_edac: Regist... |
525 |
|
5dae92a71 ghes_edac: fix to... |
526 |
list_for_each_entry_safe(pvt, tmp, &ghes_reglist, list) { |
77c5f5d2f ghes_edac: Regist... |
527 528 529 530 531 532 533 534 535 |
if (ghes == pvt->ghes) { mci = pvt->mci; edac_mc_del_mc(mci->pdev); edac_mc_free(mci); list_del(&pvt->list); } } } EXPORT_SYMBOL_GPL(ghes_edac_unregister); |