Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 | /* * The file intends to implement the functions needed by EEH, which is * built on IODA compliant chip. Actually, lots of functions related * to EEH would be built based on the OPAL APIs. * * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. */ #include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/init.h> #include <linux/io.h> #include <linux/irq.h> #include <linux/kernel.h> #include <linux/msi.h> #include <linux/notifier.h> #include <linux/pci.h> #include <linux/string.h> #include <asm/eeh.h> #include <asm/eeh_event.h> #include <asm/io.h> #include <asm/iommu.h> #include <asm/msi_bitmap.h> #include <asm/opal.h> #include <asm/pci-bridge.h> #include <asm/ppc-pci.h> #include <asm/tce.h> #include "powernv.h" #include "pci.h" /* Debugging option */ #ifdef IODA_EEH_DBG_ON #define IODA_EEH_DBG(args...) pr_info(args) #else #define IODA_EEH_DBG(args...) #endif static char *hub_diag = NULL; static int ioda_eeh_nb_init = 0; static int ioda_eeh_event(struct notifier_block *nb, unsigned long events, void *change) { uint64_t changed_evts = (uint64_t)change; /* We simply send special EEH event */ if ((changed_evts & OPAL_EVENT_PCI_ERROR) && (events & OPAL_EVENT_PCI_ERROR)) eeh_send_failure_event(NULL); return 0; } static struct notifier_block ioda_eeh_nb = { .notifier_call = ioda_eeh_event, .next = NULL, .priority = 0 }; #ifdef CONFIG_DEBUG_FS static int ioda_eeh_dbgfs_set(void *data, u64 val) { struct pci_controller *hose = data; struct pnv_phb *phb = hose->private_data; out_be64(phb->regs + 0xD10, val); return 0; } static int ioda_eeh_dbgfs_get(void *data, u64 *val) { struct pci_controller *hose = data; struct pnv_phb *phb = hose->private_data; *val = in_be64(phb->regs + 0xD10); return 0; } DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_dbgfs_ops, ioda_eeh_dbgfs_get, ioda_eeh_dbgfs_set, "0x%llx\n"); #endif /* CONFIG_DEBUG_FS */ /** * ioda_eeh_post_init - Chip dependent post initialization * @hose: PCI controller * * The function will be called after eeh PEs and devices * have been built. That means the EEH is ready to supply * service with I/O cache. */ static int ioda_eeh_post_init(struct pci_controller *hose) { struct pnv_phb *phb = hose->private_data; int ret; /* Register OPAL event notifier */ if (!ioda_eeh_nb_init) { ret = opal_notifier_register(&ioda_eeh_nb); if (ret) { pr_err("%s: Can't register OPAL event notifier (%d)\n", __func__, ret); return ret; } ioda_eeh_nb_init = 1; } /* FIXME: Enable it for PHB3 later */ if (phb->type == PNV_PHB_IODA1) { if (!hub_diag) { hub_diag = (char *)__get_free_page(GFP_KERNEL | __GFP_ZERO); if (!hub_diag) { pr_err("%s: Out of memory !\n", __func__); return -ENOMEM; } } #ifdef CONFIG_DEBUG_FS if (phb->dbgfs) debugfs_create_file("err_injct", 0600, phb->dbgfs, hose, &ioda_eeh_dbgfs_ops); #endif phb->eeh_state |= PNV_EEH_STATE_ENABLED; } return 0; } /** * ioda_eeh_set_option - Set EEH operation or I/O setting * @pe: EEH PE * @option: options * * Enable or disable EEH option for the indicated PE. The * function also can be used to enable I/O or DMA for the * PE. */ static int ioda_eeh_set_option(struct eeh_pe *pe, int option) { s64 ret; u32 pe_no; struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; /* Check on PE number */ if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) { pr_err("%s: PE address %x out of range [0, %x] " "on PHB#%x\n", __func__, pe->addr, phb->ioda.total_pe, hose->global_number); return -EINVAL; } pe_no = pe->addr; switch (option) { case EEH_OPT_DISABLE: ret = -EEXIST; break; case EEH_OPT_ENABLE: ret = 0; break; case EEH_OPT_THAW_MMIO: ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_MMIO); if (ret) { pr_warning("%s: Failed to enable MMIO for " "PHB#%x-PE#%x, err=%lld\n", __func__, hose->global_number, pe_no, ret); return -EIO; } break; case EEH_OPT_THAW_DMA: ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_DMA); if (ret) { pr_warning("%s: Failed to enable DMA for " "PHB#%x-PE#%x, err=%lld\n", __func__, hose->global_number, pe_no, ret); return -EIO; } break; default: pr_warning("%s: Invalid option %d\n", __func__, option); return -EINVAL; } return ret; } /** * ioda_eeh_get_state - Retrieve the state of PE * @pe: EEH PE * * The PE's state should be retrieved from the PEEV, PEST * IODA tables. Since the OPAL has exported the function * to do it, it'd better to use that. */ static int ioda_eeh_get_state(struct eeh_pe *pe) { s64 ret = 0; u8 fstate; u16 pcierr; u32 pe_no; int result; struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; /* * Sanity check on PE address. The PHB PE address should * be zero. */ if (pe->addr < 0 || pe->addr >= phb->ioda.total_pe) { pr_err("%s: PE address %x out of range [0, %x] " "on PHB#%x\n", __func__, pe->addr, phb->ioda.total_pe, hose->global_number); return EEH_STATE_NOT_SUPPORT; } /* Retrieve PE status through OPAL */ pe_no = pe->addr; ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr, NULL); if (ret) { pr_err("%s: Failed to get EEH status on " "PHB#%x-PE#%x\n, err=%lld\n", __func__, hose->global_number, pe_no, ret); return EEH_STATE_NOT_SUPPORT; } /* Check PHB status */ if (pe->type & EEH_PE_PHB) { result = 0; result &= ~EEH_STATE_RESET_ACTIVE; if (pcierr != OPAL_EEH_PHB_ERROR) { result |= EEH_STATE_MMIO_ACTIVE; result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; result |= EEH_STATE_DMA_ENABLED; } return result; } /* Parse result out */ result = 0; switch (fstate) { case OPAL_EEH_STOPPED_NOT_FROZEN: result &= ~EEH_STATE_RESET_ACTIVE; result |= EEH_STATE_MMIO_ACTIVE; result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; result |= EEH_STATE_DMA_ENABLED; break; case OPAL_EEH_STOPPED_MMIO_FREEZE: result &= ~EEH_STATE_RESET_ACTIVE; result |= EEH_STATE_DMA_ACTIVE; result |= EEH_STATE_DMA_ENABLED; break; case OPAL_EEH_STOPPED_DMA_FREEZE: result &= ~EEH_STATE_RESET_ACTIVE; result |= EEH_STATE_MMIO_ACTIVE; result |= EEH_STATE_MMIO_ENABLED; break; case OPAL_EEH_STOPPED_MMIO_DMA_FREEZE: result &= ~EEH_STATE_RESET_ACTIVE; break; case OPAL_EEH_STOPPED_RESET: result |= EEH_STATE_RESET_ACTIVE; break; case OPAL_EEH_STOPPED_TEMP_UNAVAIL: result |= EEH_STATE_UNAVAILABLE; break; case OPAL_EEH_STOPPED_PERM_UNAVAIL: result |= EEH_STATE_NOT_SUPPORT; break; default: pr_warning("%s: Unexpected EEH status 0x%x " "on PHB#%x-PE#%x\n", __func__, fstate, hose->global_number, pe_no); } return result; } static int ioda_eeh_pe_clear(struct eeh_pe *pe) { struct pci_controller *hose; struct pnv_phb *phb; u32 pe_no; u8 fstate; u16 pcierr; s64 ret; pe_no = pe->addr; hose = pe->phb; phb = pe->phb->private_data; /* Clear the EEH error on the PE */ ret = opal_pci_eeh_freeze_clear(phb->opal_id, pe_no, OPAL_EEH_ACTION_CLEAR_FREEZE_ALL); if (ret) { pr_err("%s: Failed to clear EEH error for " "PHB#%x-PE#%x, err=%lld\n", __func__, hose->global_number, pe_no, ret); return -EIO; } /* * Read the PE state back and verify that the frozen * state has been removed. */ ret = opal_pci_eeh_freeze_status(phb->opal_id, pe_no, &fstate, &pcierr, NULL); if (ret) { pr_err("%s: Failed to get EEH status on " "PHB#%x-PE#%x\n, err=%lld\n", __func__, hose->global_number, pe_no, ret); return -EIO; } if (fstate != OPAL_EEH_STOPPED_NOT_FROZEN) { pr_err("%s: Frozen state not cleared on " "PHB#%x-PE#%x, sts=%x\n", __func__, hose->global_number, pe_no, fstate); return -EIO; } return 0; } static s64 ioda_eeh_phb_poll(struct pnv_phb *phb) { s64 rc = OPAL_HARDWARE; while (1) { rc = opal_pci_poll(phb->opal_id); if (rc <= 0) break; msleep(rc); } return rc; } static int ioda_eeh_phb_reset(struct pci_controller *hose, int option) { struct pnv_phb *phb = hose->private_data; s64 rc = OPAL_HARDWARE; pr_debug("%s: Reset PHB#%x, option=%d\n", __func__, hose->global_number, option); /* Issue PHB complete reset request */ if (option == EEH_RESET_FUNDAMENTAL || option == EEH_RESET_HOT) rc = opal_pci_reset(phb->opal_id, OPAL_PHB_COMPLETE, OPAL_ASSERT_RESET); else if (option == EEH_RESET_DEACTIVATE) rc = opal_pci_reset(phb->opal_id, OPAL_PHB_COMPLETE, OPAL_DEASSERT_RESET); if (rc < 0) goto out; /* * Poll state of the PHB until the request is done * successfully. */ rc = ioda_eeh_phb_poll(phb); out: if (rc != OPAL_SUCCESS) return -EIO; return 0; } static int ioda_eeh_root_reset(struct pci_controller *hose, int option) { struct pnv_phb *phb = hose->private_data; s64 rc = OPAL_SUCCESS; pr_debug("%s: Reset PHB#%x, option=%d\n", __func__, hose->global_number, option); /* * During the reset deassert time, we needn't care * the reset scope because the firmware does nothing * for fundamental or hot reset during deassert phase. */ if (option == EEH_RESET_FUNDAMENTAL) rc = opal_pci_reset(phb->opal_id, OPAL_PCI_FUNDAMENTAL_RESET, OPAL_ASSERT_RESET); else if (option == EEH_RESET_HOT) rc = opal_pci_reset(phb->opal_id, OPAL_PCI_HOT_RESET, OPAL_ASSERT_RESET); else if (option == EEH_RESET_DEACTIVATE) rc = opal_pci_reset(phb->opal_id, OPAL_PCI_HOT_RESET, OPAL_DEASSERT_RESET); if (rc < 0) goto out; /* Poll state of the PHB until the request is done */ rc = ioda_eeh_phb_poll(phb); out: if (rc != OPAL_SUCCESS) return -EIO; return 0; } static int ioda_eeh_bridge_reset(struct pci_controller *hose, struct pci_dev *dev, int option) { u16 ctrl; pr_debug("%s: Reset device %04x:%02x:%02x.%01x with option %d\n", __func__, hose->global_number, dev->bus->number, PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn), option); switch (option) { case EEH_RESET_FUNDAMENTAL: case EEH_RESET_HOT: pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); ctrl |= PCI_BRIDGE_CTL_BUS_RESET; pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); break; case EEH_RESET_DEACTIVATE: pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &ctrl); ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; pci_write_config_word(dev, PCI_BRIDGE_CONTROL, ctrl); break; } return 0; } /** * ioda_eeh_reset - Reset the indicated PE * @pe: EEH PE * @option: reset option * * Do reset on the indicated PE. For PCI bus sensitive PE, * we need to reset the parent p2p bridge. The PHB has to * be reinitialized if the p2p bridge is root bridge. For * PCI device sensitive PE, we will try to reset the device * through FLR. For now, we don't have OPAL APIs to do HARD * reset yet, so all reset would be SOFT (HOT) reset. */ static int ioda_eeh_reset(struct eeh_pe *pe, int option) { struct pci_controller *hose = pe->phb; struct eeh_dev *edev; struct pci_dev *dev; int ret; /* * Anyway, we have to clear the problematic state for the * corresponding PE. However, we needn't do it if the PE * is PHB associated. That means the PHB is having fatal * errors and it needs reset. Further more, the AIB interface * isn't reliable any more. */ if (!(pe->type & EEH_PE_PHB) && (option == EEH_RESET_HOT || option == EEH_RESET_FUNDAMENTAL)) { ret = ioda_eeh_pe_clear(pe); if (ret) return -EIO; } /* * The rules applied to reset, either fundamental or hot reset: * * We always reset the direct upstream bridge of the PE. If the * direct upstream bridge isn't root bridge, we always take hot * reset no matter what option (fundamental or hot) is. Otherwise, * we should do the reset according to the required option. */ if (pe->type & EEH_PE_PHB) { ret = ioda_eeh_phb_reset(hose, option); } else { if (pe->type & EEH_PE_DEVICE) { /* * If it's device PE, we didn't refer to the parent * PCI bus yet. So we have to figure it out indirectly. */ edev = list_first_entry(&pe->edevs, struct eeh_dev, list); dev = eeh_dev_to_pci_dev(edev); dev = dev->bus->self; } else { /* * If it's bus PE, the parent PCI bus is already there * and just pick it up. */ dev = pe->bus->self; } /* * Do reset based on the fact that the direct upstream bridge * is root bridge (port) or not. */ if (dev->bus->number == 0) ret = ioda_eeh_root_reset(hose, option); else ret = ioda_eeh_bridge_reset(hose, dev, option); } return ret; } /** * ioda_eeh_get_log - Retrieve error log * @pe: EEH PE * @severity: Severity level of the log * @drv_log: buffer to store the log * @len: space of the log buffer * * The function is used to retrieve error log from P7IOC. */ static int ioda_eeh_get_log(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len) { s64 ret; unsigned long flags; struct pci_controller *hose = pe->phb; struct pnv_phb *phb = hose->private_data; spin_lock_irqsave(&phb->lock, flags); ret = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE); if (ret) { spin_unlock_irqrestore(&phb->lock, flags); pr_warning("%s: Failed to get log for PHB#%x-PE#%x\n", __func__, hose->global_number, pe->addr); return -EIO; } /* * FIXME: We probably need log the error in somewhere. * Lets make it up in future. */ /* pr_info("%s", phb->diag.blob); */ spin_unlock_irqrestore(&phb->lock, flags); return 0; } /** * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE * @pe: EEH PE * * For particular PE, it might have included PCI bridges. In order * to make the PE work properly, those PCI bridges should be configured * correctly. However, we need do nothing on P7IOC since the reset * function will do everything that should be covered by the function. */ static int ioda_eeh_configure_bridge(struct eeh_pe *pe) { return 0; } static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data) { /* GEM */ pr_info(" GEM XFIR: %016llx\n", data->gemXfir); pr_info(" GEM RFIR: %016llx\n", data->gemRfir); pr_info(" GEM RIRQFIR: %016llx\n", data->gemRirqfir); pr_info(" GEM Mask: %016llx\n", data->gemMask); pr_info(" GEM RWOF: %016llx\n", data->gemRwof); /* LEM */ pr_info(" LEM FIR: %016llx\n", data->lemFir); pr_info(" LEM Error Mask: %016llx\n", data->lemErrMask); pr_info(" LEM Action 0: %016llx\n", data->lemAction0); pr_info(" LEM Action 1: %016llx\n", data->lemAction1); pr_info(" LEM WOF: %016llx\n", data->lemWof); } static void ioda_eeh_hub_diag(struct pci_controller *hose) { struct pnv_phb *phb = hose->private_data; struct OpalIoP7IOCErrorData *data; long rc; data = (struct OpalIoP7IOCErrorData *)ioda_eeh_hub_diag; rc = opal_pci_get_hub_diag_data(phb->hub_id, data, PAGE_SIZE); if (rc != OPAL_SUCCESS) { pr_warning("%s: Failed to get HUB#%llx diag-data (%ld)\n", __func__, phb->hub_id, rc); return; } switch (data->type) { case OPAL_P7IOC_DIAG_TYPE_RGC: pr_info("P7IOC diag-data for RGC\n\n"); ioda_eeh_hub_diag_common(data); pr_info(" RGC Status: %016llx\n", data->rgc.rgcStatus); pr_info(" RGC LDCP: %016llx\n", data->rgc.rgcLdcp); break; case OPAL_P7IOC_DIAG_TYPE_BI: pr_info("P7IOC diag-data for BI %s\n\n", data->bi.biDownbound ? "Downbound" : "Upbound"); ioda_eeh_hub_diag_common(data); pr_info(" BI LDCP 0: %016llx\n", data->bi.biLdcp0); pr_info(" BI LDCP 1: %016llx\n", data->bi.biLdcp1); pr_info(" BI LDCP 2: %016llx\n", data->bi.biLdcp2); pr_info(" BI Fence Status: %016llx\n", data->bi.biFenceStatus); break; case OPAL_P7IOC_DIAG_TYPE_CI: pr_info("P7IOC diag-data for CI Port %d\\nn", data->ci.ciPort); ioda_eeh_hub_diag_common(data); pr_info(" CI Port Status: %016llx\n", data->ci.ciPortStatus); pr_info(" CI Port LDCP: %016llx\n", data->ci.ciPortLdcp); break; case OPAL_P7IOC_DIAG_TYPE_MISC: pr_info("P7IOC diag-data for MISC\n\n"); ioda_eeh_hub_diag_common(data); break; case OPAL_P7IOC_DIAG_TYPE_I2C: pr_info("P7IOC diag-data for I2C\n\n"); ioda_eeh_hub_diag_common(data); break; default: pr_warning("%s: Invalid type of HUB#%llx diag-data (%d)\n", __func__, phb->hub_id, data->type); } } static void ioda_eeh_p7ioc_phb_diag(struct pci_controller *hose, struct OpalIoPhbErrorCommon *common) { struct OpalIoP7IOCPhbErrorData *data; int i; data = (struct OpalIoP7IOCPhbErrorData *)common; pr_info("P7IOC PHB#%x Diag-data (Version: %d)\n\n", hose->global_number, common->version); pr_info(" brdgCtl: %08x\n", data->brdgCtl); pr_info(" portStatusReg: %08x\n", data->portStatusReg); pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus); pr_info(" busAgentStatus: %08x\n", data->busAgentStatus); pr_info(" deviceStatus: %08x\n", data->deviceStatus); pr_info(" slotStatus: %08x\n", data->slotStatus); pr_info(" linkStatus: %08x\n", data->linkStatus); pr_info(" devCmdStatus: %08x\n", data->devCmdStatus); pr_info(" devSecStatus: %08x\n", data->devSecStatus); pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus); pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus); pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus); pr_info(" tlpHdr1: %08x\n", data->tlpHdr1); pr_info(" tlpHdr2: %08x\n", data->tlpHdr2); pr_info(" tlpHdr3: %08x\n", data->tlpHdr3); pr_info(" tlpHdr4: %08x\n", data->tlpHdr4); pr_info(" sourceId: %08x\n", data->sourceId); pr_info(" errorClass: %016llx\n", data->errorClass); pr_info(" correlator: %016llx\n", data->correlator); pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr); pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr); pr_info(" lemFir: %016llx\n", data->lemFir); pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask); pr_info(" lemWOF: %016llx\n", data->lemWOF); pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus); pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus); pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0); pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1); pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus); pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus); pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0); pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1); pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus); pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus); pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0); pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1); pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus); pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus); pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0); pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1); for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) { if ((data->pestA[i] >> 63) == 0 && (data->pestB[i] >> 63) == 0) continue; pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]); pr_info(" PESTB: %016llx\n", data->pestB[i]); } } static void ioda_eeh_phb_diag(struct pci_controller *hose) { struct pnv_phb *phb = hose->private_data; struct OpalIoPhbErrorCommon *common; long rc; common = (struct OpalIoPhbErrorCommon *)phb->diag.blob; rc = opal_pci_get_phb_diag_data2(phb->opal_id, common, PAGE_SIZE); if (rc != OPAL_SUCCESS) { pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n", __func__, hose->global_number, rc); return; } switch (common->ioType) { case OPAL_PHB_ERROR_DATA_TYPE_P7IOC: ioda_eeh_p7ioc_phb_diag(hose, common); break; default: pr_warning("%s: Unrecognized I/O chip %d\n", __func__, common->ioType); } } static int ioda_eeh_get_phb_pe(struct pci_controller *hose, struct eeh_pe **pe) { struct eeh_pe *phb_pe; phb_pe = eeh_phb_pe_get(hose); if (!phb_pe) { pr_warning("%s Can't find PE for PHB#%d\n", __func__, hose->global_number); return -EEXIST; } *pe = phb_pe; return 0; } static int ioda_eeh_get_pe(struct pci_controller *hose, u16 pe_no, struct eeh_pe **pe) { struct eeh_pe *phb_pe, *dev_pe; struct eeh_dev dev; /* Find the PHB PE */ if (ioda_eeh_get_phb_pe(hose, &phb_pe)) return -EEXIST; /* Find the PE according to PE# */ memset(&dev, 0, sizeof(struct eeh_dev)); dev.phb = hose; dev.pe_config_addr = pe_no; dev_pe = eeh_pe_get(&dev); if (!dev_pe) { pr_warning("%s: Can't find PE for PHB#%x - PE#%x\n", __func__, hose->global_number, pe_no); return -EEXIST; } *pe = dev_pe; return 0; } /** * ioda_eeh_next_error - Retrieve next error for EEH core to handle * @pe: The affected PE * * The function is expected to be called by EEH core while it gets * special EEH event (without binding PE). The function calls to * OPAL APIs for next error to handle. The informational error is * handled internally by platform. However, the dead IOC, dead PHB, * fenced PHB and frozen PE should be handled by EEH core eventually. */ static int ioda_eeh_next_error(struct eeh_pe **pe) { struct pci_controller *hose, *tmp; struct pnv_phb *phb; u64 frozen_pe_no; u16 err_type, severity; long rc; int ret = 1; /* * While running here, it's safe to purge the event queue. * And we should keep the cached OPAL notifier event sychronized * between the kernel and firmware. */ eeh_remove_event(NULL); opal_notifier_update_evt(OPAL_EVENT_PCI_ERROR, 0x0ul); list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { /* * If the subordinate PCI buses of the PHB has been * removed, we needn't take care of it any more. */ phb = hose->private_data; if (phb->eeh_state & PNV_EEH_STATE_REMOVED) continue; rc = opal_pci_next_error(phb->opal_id, &frozen_pe_no, &err_type, &severity); /* If OPAL API returns error, we needn't proceed */ if (rc != OPAL_SUCCESS) { IODA_EEH_DBG("%s: Invalid return value on " "PHB#%x (0x%lx) from opal_pci_next_error", __func__, hose->global_number, rc); continue; } /* If the PHB doesn't have error, stop processing */ if (err_type == OPAL_EEH_NO_ERROR || severity == OPAL_EEH_SEV_NO_ERROR) { IODA_EEH_DBG("%s: No error found on PHB#%x\n", __func__, hose->global_number); continue; } /* * Processing the error. We're expecting the error with * highest priority reported upon multiple errors on the * specific PHB. */ IODA_EEH_DBG("%s: Error (%d, %d, %d) on PHB#%x\n", err_type, severity, pe_no, hose->global_number); switch (err_type) { case OPAL_EEH_IOC_ERROR: if (severity == OPAL_EEH_SEV_IOC_DEAD) { list_for_each_entry_safe(hose, tmp, &hose_list, list_node) { phb = hose->private_data; phb->eeh_state |= PNV_EEH_STATE_REMOVED; } pr_err("EEH: dead IOC detected\n"); ret = 4; goto out; } else if (severity == OPAL_EEH_SEV_INF) { pr_info("EEH: IOC informative error " "detected\n"); ioda_eeh_hub_diag(hose); } break; case OPAL_EEH_PHB_ERROR: if (severity == OPAL_EEH_SEV_PHB_DEAD) { if (ioda_eeh_get_phb_pe(hose, pe)) break; pr_err("EEH: dead PHB#%x detected\n", hose->global_number); phb->eeh_state |= PNV_EEH_STATE_REMOVED; ret = 3; goto out; } else if (severity == OPAL_EEH_SEV_PHB_FENCED) { if (ioda_eeh_get_phb_pe(hose, pe)) break; pr_err("EEH: fenced PHB#%x detected\n", hose->global_number); ret = 2; goto out; } else if (severity == OPAL_EEH_SEV_INF) { pr_info("EEH: PHB#%x informative error " "detected\n", hose->global_number); ioda_eeh_phb_diag(hose); } break; case OPAL_EEH_PE_ERROR: if (ioda_eeh_get_pe(hose, frozen_pe_no, pe)) break; pr_err("EEH: Frozen PE#%x on PHB#%x detected\n", (*pe)->addr, (*pe)->phb->global_number); ret = 1; goto out; } } ret = 0; out: return ret; } struct pnv_eeh_ops ioda_eeh_ops = { .post_init = ioda_eeh_post_init, .set_option = ioda_eeh_set_option, .get_state = ioda_eeh_get_state, .reset = ioda_eeh_reset, .get_log = ioda_eeh_get_log, .configure_bridge = ioda_eeh_configure_bridge, .next_error = ioda_eeh_next_error }; |