aer.c 38.6 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
2
/*
B
Bjorn Helgaas 已提交
3 4 5
 * Implement the AER root port service driver. The driver registers an IRQ
 * handler. When a root port triggers an AER interrupt, the IRQ handler
 * collects root port status and schedules work.
6 7 8 9
 *
 * Copyright (C) 2006 Intel Corp.
 *	Tom Long Nguyen (tom.l.nguyen@intel.com)
 *	Zhang Yanmin (yanmin.zhang@intel.com)
10 11 12
 *
 * (C) Copyright 2009 Hewlett-Packard Development Company, L.P.
 *    Andrew Patterson <andrew.patterson@hp.com>
13 14
 */

15 16 17
#define pr_fmt(fmt) "AER: " fmt
#define dev_fmt pr_fmt

18
#include <linux/cper.h>
19
#include <linux/pci.h>
20
#include <linux/pci-acpi.h>
21
#include <linux/sched.h>
22 23 24 25 26 27
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/pm.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
28
#include <linux/kfifo.h>
29
#include <linux/slab.h>
30
#include <acpi/apei.h>
31
#include <ras/ras_event.h>
32

33 34
#include "../pci.h"
#include "portdrv.h"
35

36
#define AER_ERROR_SOURCES_MAX		128
37

38 39 40
#define AER_MAX_TYPEOF_COR_ERRS		16	/* as per PCI_ERR_COR_STATUS */
#define AER_MAX_TYPEOF_UNCOR_ERRS	26	/* as per PCI_ERR_UNCOR_STATUS*/

41 42 43 44 45 46 47
struct aer_err_source {
	unsigned int status;
	unsigned int id;
};

struct aer_rpc {
	struct pci_dev *rpd;		/* Root Port device */
48
	DECLARE_KFIFO(aer_fifo, struct aer_err_source, AER_ERROR_SOURCES_MAX);
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
/* AER stats for the device */
struct aer_stats {

	/*
	 * Fields for all AER capable devices. They indicate the errors
	 * "as seen by this device". Note that this may mean that if an
	 * end point is causing problems, the AER counters may increment
	 * at its link partner (e.g. root port) because the errors will be
	 * "seen" by the link partner and not the the problematic end point
	 * itself (which may report all counters as 0 as it never saw any
	 * problems).
	 */
	/* Counters for different type of correctable errors */
	u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS];
	/* Counters for different type of fatal uncorrectable errors */
	u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS];
	/* Counters for different type of nonfatal uncorrectable errors */
	u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS];
	/* Total number of ERR_COR sent by this device */
	u64 dev_total_cor_errs;
	/* Total number of ERR_FATAL sent by this device */
	u64 dev_total_fatal_errs;
	/* Total number of ERR_NONFATAL sent by this device */
	u64 dev_total_nonfatal_errs;

	/*
	 * Fields for Root ports & root complex event collectors only, these
	 * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL
	 * messages received by the root port / event collector, INCLUDING the
	 * ones that are generated internally (by the rootport itself)
	 */
	u64 rootport_total_cor_errs;
	u64 rootport_total_fatal_errs;
	u64 rootport_total_nonfatal_errs;
};

87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
#define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
					PCI_ERR_UNC_ECRC|		\
					PCI_ERR_UNC_UNSUP|		\
					PCI_ERR_UNC_COMP_ABORT|		\
					PCI_ERR_UNC_UNX_COMP|		\
					PCI_ERR_UNC_MALF_TLP)

#define SYSTEM_ERROR_INTR_ON_MESG_MASK	(PCI_EXP_RTCTL_SECEE|	\
					PCI_EXP_RTCTL_SENFEE|	\
					PCI_EXP_RTCTL_SEFEE)
#define ROOT_PORT_INTR_ON_MESG_MASK	(PCI_ERR_ROOT_CMD_COR_EN|	\
					PCI_ERR_ROOT_CMD_NONFATAL_EN|	\
					PCI_ERR_ROOT_CMD_FATAL_EN)
#define ERR_COR_ID(d)			(d & 0xffff)
#define ERR_UNCOR_ID(d)			(d >> 16)
102

R
Randy Dunlap 已提交
103 104 105 106
static int pcie_aer_disable;

void pci_no_aer(void)
{
107
	pcie_aer_disable = 1;
R
Randy Dunlap 已提交
108 109
}

110 111 112 113 114
bool pci_aer_available(void)
{
	return !pcie_aer_disable && pci_msi_enabled();
}

115 116 117 118 119 120 121 122
#ifdef CONFIG_PCIE_ECRC

#define ECRC_POLICY_DEFAULT 0		/* ECRC set by BIOS */
#define ECRC_POLICY_OFF     1		/* ECRC off for performance */
#define ECRC_POLICY_ON      2		/* ECRC on for data integrity */

static int ecrc_policy = ECRC_POLICY_DEFAULT;

123
static const char * const ecrc_policy_str[] = {
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
	[ECRC_POLICY_DEFAULT] = "bios",
	[ECRC_POLICY_OFF] = "off",
	[ECRC_POLICY_ON] = "on"
};

/**
 * enable_ercr_checking - enable PCIe ECRC checking for a device
 * @dev: the PCI device
 *
 * Returns 0 on success, or negative on failure.
 */
static int enable_ecrc_checking(struct pci_dev *dev)
{
	int pos;
	u32 reg32;

	if (!pci_is_pcie(dev))
		return -ENODEV;

	pos = dev->aer_cap;
	if (!pos)
		return -ENODEV;

	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
	if (reg32 & PCI_ERR_CAP_ECRC_GENC)
		reg32 |= PCI_ERR_CAP_ECRC_GENE;
	if (reg32 & PCI_ERR_CAP_ECRC_CHKC)
		reg32 |= PCI_ERR_CAP_ECRC_CHKE;
	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);

	return 0;
}

/**
 * disable_ercr_checking - disables PCIe ECRC checking for a device
 * @dev: the PCI device
 *
 * Returns 0 on success, or negative on failure.
 */
static int disable_ecrc_checking(struct pci_dev *dev)
{
	int pos;
	u32 reg32;

	if (!pci_is_pcie(dev))
		return -ENODEV;

	pos = dev->aer_cap;
	if (!pos)
		return -ENODEV;

	pci_read_config_dword(dev, pos + PCI_ERR_CAP, &reg32);
	reg32 &= ~(PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
	pci_write_config_dword(dev, pos + PCI_ERR_CAP, reg32);

	return 0;
}

/**
 * pcie_set_ecrc_checking - set/unset PCIe ECRC checking for a device based on global policy
 * @dev: the PCI device
 */
void pcie_set_ecrc_checking(struct pci_dev *dev)
{
	switch (ecrc_policy) {
	case ECRC_POLICY_DEFAULT:
		return;
	case ECRC_POLICY_OFF:
		disable_ecrc_checking(dev);
		break;
	case ECRC_POLICY_ON:
		enable_ecrc_checking(dev);
		break;
	default:
		return;
	}
}

/**
 * pcie_ecrc_get_policy - parse kernel command-line ecrc option
 */
void pcie_ecrc_get_policy(char *str)
{
	int i;

209 210
	i = match_string(ecrc_policy_str, ARRAY_SIZE(ecrc_policy_str), str);
	if (i < 0)
211 212 213 214 215 216
		return;

	ecrc_policy = i;
}
#endif	/* CONFIG_PCIE_ECRC */

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
#ifdef CONFIG_ACPI_APEI
static inline int hest_match_pci(struct acpi_hest_aer_common *p,
				 struct pci_dev *pci)
{
	return   ACPI_HEST_SEGMENT(p->bus) == pci_domain_nr(pci->bus) &&
		 ACPI_HEST_BUS(p->bus)     == pci->bus->number &&
		 p->device                 == PCI_SLOT(pci->devfn) &&
		 p->function               == PCI_FUNC(pci->devfn);
}

static inline bool hest_match_type(struct acpi_hest_header *hest_hdr,
				struct pci_dev *dev)
{
	u16 hest_type = hest_hdr->type;
	u8 pcie_type = pci_pcie_type(dev);

	if ((hest_type == ACPI_HEST_TYPE_AER_ROOT_PORT &&
		pcie_type == PCI_EXP_TYPE_ROOT_PORT) ||
	    (hest_type == ACPI_HEST_TYPE_AER_ENDPOINT &&
		pcie_type == PCI_EXP_TYPE_ENDPOINT) ||
	    (hest_type == ACPI_HEST_TYPE_AER_BRIDGE &&
		(dev->class >> 16) == PCI_BASE_CLASS_BRIDGE))
		return true;
	return false;
}

struct aer_hest_parse_info {
	struct pci_dev *pci_dev;
	int firmware_first;
};

static int hest_source_is_pcie_aer(struct acpi_hest_header *hest_hdr)
{
	if (hest_hdr->type == ACPI_HEST_TYPE_AER_ROOT_PORT ||
	    hest_hdr->type == ACPI_HEST_TYPE_AER_ENDPOINT ||
	    hest_hdr->type == ACPI_HEST_TYPE_AER_BRIDGE)
		return 1;
	return 0;
}

static int aer_hest_parse(struct acpi_hest_header *hest_hdr, void *data)
{
	struct aer_hest_parse_info *info = data;
	struct acpi_hest_aer_common *p;
	int ff;

	if (!hest_source_is_pcie_aer(hest_hdr))
		return 0;

	p = (struct acpi_hest_aer_common *)(hest_hdr + 1);
	ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);

	/*
	 * If no specific device is supplied, determine whether
	 * FIRMWARE_FIRST is set for *any* PCIe device.
	 */
	if (!info->pci_dev) {
		info->firmware_first |= ff;
		return 0;
	}

	/* Otherwise, check the specific device */
	if (p->flags & ACPI_HEST_GLOBAL) {
		if (hest_match_type(hest_hdr, info->pci_dev))
			info->firmware_first = ff;
	} else
		if (hest_match_pci(p, info->pci_dev))
			info->firmware_first = ff;

	return 0;
}

static void aer_set_firmware_first(struct pci_dev *pci_dev)
{
	int rc;
	struct aer_hest_parse_info info = {
		.pci_dev	= pci_dev,
		.firmware_first	= 0,
	};

	rc = apei_hest_parse(aer_hest_parse, &info);

	if (rc)
		pci_dev->__aer_firmware_first = 0;
	else
		pci_dev->__aer_firmware_first = info.firmware_first;
	pci_dev->__aer_firmware_first_valid = 1;
}

int pcie_aer_get_firmware_first(struct pci_dev *dev)
{
	if (!pci_is_pcie(dev))
		return 0;

311 312 313
	if (pcie_ports_native)
		return 0;

314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
	if (!dev->__aer_firmware_first_valid)
		aer_set_firmware_first(dev);
	return dev->__aer_firmware_first;
}

static bool aer_firmware_first;

/**
 * aer_acpi_firmware_first - Check if APEI should control AER.
 */
bool aer_acpi_firmware_first(void)
{
	static bool parsed = false;
	struct aer_hest_parse_info info = {
		.pci_dev	= NULL,	/* Check all PCIe devices */
		.firmware_first	= 0,
	};

332 333 334
	if (pcie_ports_native)
		return false;

335 336 337 338 339 340 341 342 343
	if (!parsed) {
		apei_hest_parse(aer_hest_parse, &info);
		aer_firmware_first = info.firmware_first;
		parsed = true;
	}
	return aer_firmware_first;
}
#endif

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
#define	PCI_EXP_AER_FLAGS	(PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
				 PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)

int pci_enable_pcie_error_reporting(struct pci_dev *dev)
{
	if (pcie_aer_get_firmware_first(dev))
		return -EIO;

	if (!dev->aer_cap)
		return -EIO;

	return pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_AER_FLAGS);
}
EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting);

int pci_disable_pcie_error_reporting(struct pci_dev *dev)
{
	if (pcie_aer_get_firmware_first(dev))
		return -EIO;

	return pcie_capability_clear_word(dev, PCI_EXP_DEVCTL,
					  PCI_EXP_AER_FLAGS);
}
EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);

369 370 371 372 373 374 375 376
void pci_aer_clear_device_status(struct pci_dev *dev)
{
	u16 sta;

	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta);
	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta);
}

377 378 379
int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
{
	int pos;
380
	u32 status, sev;
381 382 383 384 385

	pos = dev->aer_cap;
	if (!pos)
		return -EIO;

386 387 388
	if (pcie_aer_get_firmware_first(dev))
		return -EIO;

389
	/* Clear status bits for ERR_NONFATAL errors only */
390
	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
391 392
	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
	status &= ~sev;
393 394 395 396 397 398 399
	if (status)
		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);

	return 0;
}
EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);

400 401 402 403 404 405 406 407 408
void pci_aer_clear_fatal_status(struct pci_dev *dev)
{
	int pos;
	u32 status, sev;

	pos = dev->aer_cap;
	if (!pos)
		return;

409 410 411
	if (pcie_aer_get_firmware_first(dev))
		return;

412 413 414 415 416 417 418 419
	/* Clear status bits for ERR_FATAL errors only */
	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
	status &= sev;
	if (status)
		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
}

420 421 422 423 424 425 426 427 428 429 430 431 432
int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
{
	int pos;
	u32 status;
	int port_type;

	if (!pci_is_pcie(dev))
		return -ENODEV;

	pos = dev->aer_cap;
	if (!pos)
		return -EIO;

433 434 435
	if (pcie_aer_get_firmware_first(dev))
		return -EIO;

436 437 438 439 440 441 442 443 444 445 446 447 448 449 450
	port_type = pci_pcie_type(dev);
	if (port_type == PCI_EXP_TYPE_ROOT_PORT) {
		pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status);
		pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, status);
	}

	pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
	pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS, status);

	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);

	return 0;
}

451
void pci_aer_init(struct pci_dev *dev)
452 453
{
	dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
454 455 456 457

	if (dev->aer_cap)
		dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL);

458
	pci_cleanup_aer_error_status_regs(dev);
459 460
}

461 462 463 464 465 466
void pci_aer_exit(struct pci_dev *dev)
{
	kfree(dev->aer_stats);
	dev->aer_stats = NULL;
}

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
#define AER_AGENT_RECEIVER		0
#define AER_AGENT_REQUESTER		1
#define AER_AGENT_COMPLETER		2
#define AER_AGENT_TRANSMITTER		3

#define AER_AGENT_REQUESTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
	0 : (PCI_ERR_UNC_COMP_TIME|PCI_ERR_UNC_UNSUP))
#define AER_AGENT_COMPLETER_MASK(t)	((t == AER_CORRECTABLE) ?	\
	0 : PCI_ERR_UNC_COMP_ABORT)
#define AER_AGENT_TRANSMITTER_MASK(t)	((t == AER_CORRECTABLE) ?	\
	(PCI_ERR_COR_REP_ROLL|PCI_ERR_COR_REP_TIMER) : 0)

#define AER_GET_AGENT(t, e)						\
	((e & AER_AGENT_COMPLETER_MASK(t)) ? AER_AGENT_COMPLETER :	\
	(e & AER_AGENT_REQUESTER_MASK(t)) ? AER_AGENT_REQUESTER :	\
	(e & AER_AGENT_TRANSMITTER_MASK(t)) ? AER_AGENT_TRANSMITTER :	\
	AER_AGENT_RECEIVER)

#define AER_PHYSICAL_LAYER_ERROR	0
#define AER_DATA_LINK_LAYER_ERROR	1
#define AER_TRANSACTION_LAYER_ERROR	2

#define AER_PHYSICAL_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
	PCI_ERR_COR_RCVR : 0)
#define AER_DATA_LINK_LAYER_ERROR_MASK(t) ((t == AER_CORRECTABLE) ?	\
	(PCI_ERR_COR_BAD_TLP|						\
	PCI_ERR_COR_BAD_DLLP|						\
	PCI_ERR_COR_REP_ROLL|						\
	PCI_ERR_COR_REP_TIMER) : PCI_ERR_UNC_DLP)

#define AER_GET_LAYER_ERROR(t, e)					\
	((e & AER_PHYSICAL_LAYER_ERROR_MASK(t)) ? AER_PHYSICAL_LAYER_ERROR : \
	(e & AER_DATA_LINK_LAYER_ERROR_MASK(t)) ? AER_DATA_LINK_LAYER_ERROR : \
	AER_TRANSACTION_LAYER_ERROR)

/*
 * AER error strings
 */
static const char *aer_error_severity_string[] = {
	"Uncorrected (Non-Fatal)",
	"Uncorrected (Fatal)",
	"Corrected"
};

static const char *aer_error_layer[] = {
	"Physical Layer",
	"Data Link Layer",
	"Transaction Layer"
};

517
static const char *aer_correctable_error_string[AER_MAX_TYPEOF_COR_ERRS] = {
518
	"RxErr",			/* Bit Position 0	*/
519 520 521 522 523
	NULL,
	NULL,
	NULL,
	NULL,
	NULL,
524 525 526
	"BadTLP",			/* Bit Position 6	*/
	"BadDLLP",			/* Bit Position 7	*/
	"Rollover",			/* Bit Position 8	*/
527 528 529
	NULL,
	NULL,
	NULL,
530 531 532 533
	"Timeout",			/* Bit Position 12	*/
	"NonFatalErr",			/* Bit Position 13	*/
	"CorrIntErr",			/* Bit Position 14	*/
	"HeaderOF",			/* Bit Position 15	*/
534 535
};

536
static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = {
537 538 539 540
	"Undefined",			/* Bit Position 0	*/
	NULL,
	NULL,
	NULL,
541 542
	"DLP",				/* Bit Position 4	*/
	"SDES",				/* Bit Position 5	*/
543 544 545 546 547 548
	NULL,
	NULL,
	NULL,
	NULL,
	NULL,
	NULL,
549 550 551 552 553 554 555
	"TLP",				/* Bit Position 12	*/
	"FCP",				/* Bit Position 13	*/
	"CmpltTO",			/* Bit Position 14	*/
	"CmpltAbrt",			/* Bit Position 15	*/
	"UnxCmplt",			/* Bit Position 16	*/
	"RxOF",				/* Bit Position 17	*/
	"MalfTLP",			/* Bit Position 18	*/
556
	"ECRC",				/* Bit Position 19	*/
557 558 559 560 561 562
	"UnsupReq",			/* Bit Position 20	*/
	"ACSViol",			/* Bit Position 21	*/
	"UncorrIntErr",			/* Bit Position 22	*/
	"BlockedTLP",			/* Bit Position 23	*/
	"AtomicOpBlocked",		/* Bit Position 24	*/
	"TLPBlockedErr",		/* Bit Position 25	*/
563 564 565 566 567 568 569 570 571
};

static const char *aer_agent_string[] = {
	"Receiver ID",
	"Requester ID",
	"Completer ID",
	"Transmitter ID"
};

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
#define aer_stats_dev_attr(name, stats_array, strings_array,		\
			   total_string, total_field)			\
	static ssize_t							\
	name##_show(struct device *dev, struct device_attribute *attr,	\
		     char *buf)						\
{									\
	unsigned int i;							\
	char *str = buf;						\
	struct pci_dev *pdev = to_pci_dev(dev);				\
	u64 *stats = pdev->aer_stats->stats_array;			\
									\
	for (i = 0; i < ARRAY_SIZE(strings_array); i++) {		\
		if (strings_array[i])					\
			str += sprintf(str, "%s %llu\n",		\
				       strings_array[i], stats[i]);	\
		else if (stats[i])					\
			str += sprintf(str, #stats_array "_bit[%d] %llu\n",\
				       i, stats[i]);			\
	}								\
	str += sprintf(str, "TOTAL_%s %llu\n", total_string,		\
		       pdev->aer_stats->total_field);			\
	return str-buf;							\
}									\
static DEVICE_ATTR_RO(name)

aer_stats_dev_attr(aer_dev_correctable, dev_cor_errs,
		   aer_correctable_error_string, "ERR_COR",
		   dev_total_cor_errs);
aer_stats_dev_attr(aer_dev_fatal, dev_fatal_errs,
		   aer_uncorrectable_error_string, "ERR_FATAL",
		   dev_total_fatal_errs);
aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs,
		   aer_uncorrectable_error_string, "ERR_NONFATAL",
		   dev_total_nonfatal_errs);

607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623
#define aer_stats_rootport_attr(name, field)				\
	static ssize_t							\
	name##_show(struct device *dev, struct device_attribute *attr,	\
		     char *buf)						\
{									\
	struct pci_dev *pdev = to_pci_dev(dev);				\
	return sprintf(buf, "%llu\n", pdev->aer_stats->field);		\
}									\
static DEVICE_ATTR_RO(name)

aer_stats_rootport_attr(aer_rootport_total_err_cor,
			 rootport_total_cor_errs);
aer_stats_rootport_attr(aer_rootport_total_err_fatal,
			 rootport_total_fatal_errs);
aer_stats_rootport_attr(aer_rootport_total_err_nonfatal,
			 rootport_total_nonfatal_errs);

624 625 626 627
static struct attribute *aer_stats_attrs[] __ro_after_init = {
	&dev_attr_aer_dev_correctable.attr,
	&dev_attr_aer_dev_fatal.attr,
	&dev_attr_aer_dev_nonfatal.attr,
628 629 630
	&dev_attr_aer_rootport_total_err_cor.attr,
	&dev_attr_aer_rootport_total_err_fatal.attr,
	&dev_attr_aer_rootport_total_err_nonfatal.attr,
631 632 633 634 635 636 637 638 639 640 641 642
	NULL
};

static umode_t aer_stats_attrs_are_visible(struct kobject *kobj,
					   struct attribute *a, int n)
{
	struct device *dev = kobj_to_dev(kobj);
	struct pci_dev *pdev = to_pci_dev(dev);

	if (!pdev->aer_stats)
		return 0;

643 644 645 646 647 648
	if ((a == &dev_attr_aer_rootport_total_err_cor.attr ||
	     a == &dev_attr_aer_rootport_total_err_fatal.attr ||
	     a == &dev_attr_aer_rootport_total_err_nonfatal.attr) &&
	    pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT)
		return 0;

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
	return a->mode;
}

const struct attribute_group aer_stats_attr_group = {
	.attrs  = aer_stats_attrs,
	.is_visible = aer_stats_attrs_are_visible,
};

static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
				   struct aer_err_info *info)
{
	int status, i, max = -1;
	u64 *counter = NULL;
	struct aer_stats *aer_stats = pdev->aer_stats;

	if (!aer_stats)
		return;

	switch (info->severity) {
	case AER_CORRECTABLE:
		aer_stats->dev_total_cor_errs++;
		counter = &aer_stats->dev_cor_errs[0];
		max = AER_MAX_TYPEOF_COR_ERRS;
		break;
	case AER_NONFATAL:
		aer_stats->dev_total_nonfatal_errs++;
		counter = &aer_stats->dev_nonfatal_errs[0];
		max = AER_MAX_TYPEOF_UNCOR_ERRS;
		break;
	case AER_FATAL:
		aer_stats->dev_total_fatal_errs++;
		counter = &aer_stats->dev_fatal_errs[0];
		max = AER_MAX_TYPEOF_UNCOR_ERRS;
		break;
	}

	status = (info->status & ~info->mask);
	for (i = 0; i < max; i++)
		if (status & (1 << i))
			counter[i]++;
}

691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
				 struct aer_err_source *e_src)
{
	struct aer_stats *aer_stats = pdev->aer_stats;

	if (!aer_stats)
		return;

	if (e_src->status & PCI_ERR_ROOT_COR_RCV)
		aer_stats->rootport_total_cor_errs++;

	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
			aer_stats->rootport_total_fatal_errs++;
		else
			aer_stats->rootport_total_nonfatal_errs++;
	}
}

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
static void __print_tlp_header(struct pci_dev *dev,
			       struct aer_header_log_regs *t)
{
	pci_err(dev, "  TLP Header: %08x %08x %08x %08x\n",
		t->dw0, t->dw1, t->dw2, t->dw3);
}

static void __aer_print_error(struct pci_dev *dev,
			      struct aer_err_info *info)
{
	int i, status;
	const char *errmsg = NULL;
	status = (info->status & ~info->mask);

	for (i = 0; i < 32; i++) {
		if (!(status & (1 << i)))
			continue;

		if (info->severity == AER_CORRECTABLE)
			errmsg = i < ARRAY_SIZE(aer_correctable_error_string) ?
				aer_correctable_error_string[i] : NULL;
		else
			errmsg = i < ARRAY_SIZE(aer_uncorrectable_error_string) ?
				aer_uncorrectable_error_string[i] : NULL;

		if (errmsg)
			pci_err(dev, "   [%2d] %-22s%s\n", i, errmsg,
				info->first_error == i ? " (First)" : "");
		else
			pci_err(dev, "   [%2d] Unknown Error Bit%s\n",
				i, info->first_error == i ? " (First)" : "");
	}
742
	pci_dev_aer_stats_incr(dev, info);
743 744
}

745
void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
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
{
	int layer, agent;
	int id = ((dev->bus->number << 8) | dev->devfn);

	if (!info->status) {
		pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n",
			aer_error_severity_string[info->severity]);
		goto out;
	}

	layer = AER_GET_LAYER_ERROR(info->severity, info->status);
	agent = AER_GET_AGENT(info->severity, info->status);

	pci_err(dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n",
		aer_error_severity_string[info->severity],
		aer_error_layer[layer], aer_agent_string[agent]);

	pci_err(dev, "  device [%04x:%04x] error status/mask=%08x/%08x\n",
		dev->vendor, dev->device,
		info->status, info->mask);

	__aer_print_error(dev, info);

	if (info->tlp_header_valid)
		__print_tlp_header(dev, &info->tlp);

out:
	if (info->id && info->error_dev_num > 1 && info->id == id)
		pci_err(dev, "  Error of this Agent is reported first\n");

	trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask),
			info->severity, info->tlp_header_valid, &info->tlp);
}

static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
{
	u8 bus = info->id >> 8;
	u8 devfn = info->id & 0xff;

785 786 787 788 789
	pci_info(dev, "%s%s error received: %04x:%02x:%02x.%d\n",
		 info->multi_error_valid ? "Multiple " : "",
		 aer_error_severity_string[info->severity],
		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
		 PCI_FUNC(devfn));
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
}

#ifdef CONFIG_ACPI_APEI_PCIEAER
int cper_severity_to_aer(int cper_severity)
{
	switch (cper_severity) {
	case CPER_SEV_RECOVERABLE:
		return AER_NONFATAL;
	case CPER_SEV_FATAL:
		return AER_FATAL;
	default:
		return AER_CORRECTABLE;
	}
}
EXPORT_SYMBOL_GPL(cper_severity_to_aer);

void cper_print_aer(struct pci_dev *dev, int aer_severity,
		    struct aer_capability_regs *aer)
{
	int layer, agent, tlp_header_valid = 0;
	u32 status, mask;
	struct aer_err_info info;

	if (aer_severity == AER_CORRECTABLE) {
		status = aer->cor_status;
		mask = aer->cor_mask;
	} else {
		status = aer->uncor_status;
		mask = aer->uncor_mask;
		tlp_header_valid = status & AER_LOG_TLP_MASKS;
	}

	layer = AER_GET_LAYER_ERROR(aer_severity, status);
	agent = AER_GET_AGENT(aer_severity, status);

	memset(&info, 0, sizeof(info));
	info.severity = aer_severity;
	info.status = status;
	info.mask = mask;
	info.first_error = PCI_ERR_CAP_FEP(aer->cap_control);

	pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask);
	__aer_print_error(dev, &info);
	pci_err(dev, "aer_layer=%s, aer_agent=%s\n",
		aer_error_layer[layer], aer_agent_string[agent]);

	if (aer_severity != AER_CORRECTABLE)
		pci_err(dev, "aer_uncor_severity: 0x%08x\n",
			aer->uncor_severity);

	if (tlp_header_valid)
		__print_tlp_header(dev, &aer->header_log);

	trace_aer_event(dev_name(&dev->dev), (status & ~mask),
			aer_severity, tlp_header_valid, &aer->header_log);
}
#endif

848 849 850 851 852 853 854 855
/**
 * add_error_device - list device to be handled
 * @e_info: pointer to error info
 * @dev: pointer to pci_dev to be added
 */
static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev)
{
	if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) {
856
		e_info->dev[e_info->error_dev_num] = pci_dev_get(dev);
857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997
		e_info->error_dev_num++;
		return 0;
	}
	return -ENOSPC;
}

/**
 * is_error_source - check whether the device is source of reported error
 * @dev: pointer to pci_dev to be checked
 * @e_info: pointer to reported error info
 */
static bool is_error_source(struct pci_dev *dev, struct aer_err_info *e_info)
{
	int pos;
	u32 status, mask;
	u16 reg16;

	/*
	 * When bus id is equal to 0, it might be a bad id
	 * reported by root port.
	 */
	if ((PCI_BUS_NUM(e_info->id) != 0) &&
	    !(dev->bus->bus_flags & PCI_BUS_FLAGS_NO_AERSID)) {
		/* Device ID match? */
		if (e_info->id == ((dev->bus->number << 8) | dev->devfn))
			return true;

		/* Continue id comparing if there is no multiple error */
		if (!e_info->multi_error_valid)
			return false;
	}

	/*
	 * When either
	 *      1) bus id is equal to 0. Some ports might lose the bus
	 *              id of error source id;
	 *      2) bus flag PCI_BUS_FLAGS_NO_AERSID is set
	 *      3) There are multiple errors and prior ID comparing fails;
	 * We check AER status registers to find possible reporter.
	 */
	if (atomic_read(&dev->enable_cnt) == 0)
		return false;

	/* Check if AER is enabled */
	pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &reg16);
	if (!(reg16 & PCI_EXP_AER_FLAGS))
		return false;

	pos = dev->aer_cap;
	if (!pos)
		return false;

	/* Check if error is recorded */
	if (e_info->severity == AER_CORRECTABLE) {
		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS, &status);
		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK, &mask);
	} else {
		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
	}
	if (status & ~mask)
		return true;

	return false;
}

static int find_device_iter(struct pci_dev *dev, void *data)
{
	struct aer_err_info *e_info = (struct aer_err_info *)data;

	if (is_error_source(dev, e_info)) {
		/* List this device */
		if (add_error_device(e_info, dev)) {
			/* We cannot handle more... Stop iteration */
			/* TODO: Should print error message here? */
			return 1;
		}

		/* If there is only a single error, stop iteration */
		if (!e_info->multi_error_valid)
			return 1;
	}
	return 0;
}

/**
 * find_source_device - search through device hierarchy for source device
 * @parent: pointer to Root Port pci_dev data structure
 * @e_info: including detailed error information such like id
 *
 * Return true if found.
 *
 * Invoked by DPC when error is detected at the Root Port.
 * Caller of this function must set id, severity, and multi_error_valid of
 * struct aer_err_info pointed by @e_info properly.  This function must fill
 * e_info->error_dev_num and e_info->dev[], based on the given information.
 */
static bool find_source_device(struct pci_dev *parent,
		struct aer_err_info *e_info)
{
	struct pci_dev *dev = parent;
	int result;

	/* Must reset in this function */
	e_info->error_dev_num = 0;

	/* Is Root Port an agent that sends error message? */
	result = find_device_iter(dev, e_info);
	if (result)
		return true;

	pci_walk_bus(parent->subordinate, find_device_iter, e_info);

	if (!e_info->error_dev_num) {
		pci_printk(KERN_DEBUG, parent, "can't find device of ID%04x\n",
			   e_info->id);
		return false;
	}
	return true;
}

/**
 * handle_error_source - handle logging error into an event log
 * @dev: pointer to pci_dev data structure of error source device
 * @info: comprehensive error information
 *
 * Invoked when an error being detected by Root Port.
 */
static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
{
	int pos;

	if (info->severity == AER_CORRECTABLE) {
		/*
		 * Correctable error does not need software intervention.
		 * No need to go through error recovery process.
		 */
		pos = dev->aer_cap;
		if (pos)
			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
					info->status);
998
		pci_aer_clear_device_status(dev);
999
	} else if (info->severity == AER_NONFATAL)
1000 1001
		pcie_do_recovery(dev, pci_channel_io_normal,
				 PCIE_PORT_SERVICE_AER);
1002
	else if (info->severity == AER_FATAL)
1003 1004
		pcie_do_recovery(dev, pci_channel_io_frozen,
				 PCIE_PORT_SERVICE_AER);
1005
	pci_dev_put(dev);
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039
}

#ifdef CONFIG_ACPI_APEI_PCIEAER

#define AER_RECOVER_RING_ORDER		4
#define AER_RECOVER_RING_SIZE		(1 << AER_RECOVER_RING_ORDER)

struct aer_recover_entry {
	u8	bus;
	u8	devfn;
	u16	domain;
	int	severity;
	struct aer_capability_regs *regs;
};

static DEFINE_KFIFO(aer_recover_ring, struct aer_recover_entry,
		    AER_RECOVER_RING_SIZE);

static void aer_recover_work_func(struct work_struct *work)
{
	struct aer_recover_entry entry;
	struct pci_dev *pdev;

	while (kfifo_get(&aer_recover_ring, &entry)) {
		pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus,
						   entry.devfn);
		if (!pdev) {
			pr_err("AER recover: Can not find pci_dev for %04x:%02x:%02x:%x\n",
			       entry.domain, entry.bus,
			       PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn));
			continue;
		}
		cper_print_aer(pdev, entry.severity, entry.regs);
		if (entry.severity == AER_NONFATAL)
1040 1041
			pcie_do_recovery(pdev, pci_channel_io_normal,
					 PCIE_PORT_SERVICE_AER);
1042
		else if (entry.severity == AER_FATAL)
1043 1044
			pcie_do_recovery(pdev, pci_channel_io_frozen,
					 PCIE_PORT_SERVICE_AER);
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067
		pci_dev_put(pdev);
	}
}

/*
 * Mutual exclusion for writers of aer_recover_ring, reader side don't
 * need lock, because there is only one reader and lock is not needed
 * between reader and writer.
 */
static DEFINE_SPINLOCK(aer_recover_ring_lock);
static DECLARE_WORK(aer_recover_work, aer_recover_work_func);

void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
		       int severity, struct aer_capability_regs *aer_regs)
{
	struct aer_recover_entry entry = {
		.bus		= bus,
		.devfn		= devfn,
		.domain		= domain,
		.severity	= severity,
		.regs		= aer_regs,
	};

1068
	if (kfifo_in_spinlocked(&aer_recover_ring, &entry, 1,
1069
				 &aer_recover_ring_lock))
1070 1071 1072 1073 1074 1075 1076 1077 1078
		schedule_work(&aer_recover_work);
	else
		pr_err("AER recover: Buffer overflow when recovering AER for %04x:%02x:%02x:%x\n",
		       domain, bus, PCI_SLOT(devfn), PCI_FUNC(devfn));
}
EXPORT_SYMBOL_GPL(aer_recover_queue);
#endif

/**
1079
 * aer_get_device_error_info - read error status from dev and store it to info
1080 1081 1082 1083 1084 1085 1086
 * @dev: pointer to the device expected to have a error record
 * @info: pointer to structure to store the error record
 *
 * Return 1 on success, 0 on error.
 *
 * Note that @info is reused among all error devices. Clear fields properly.
 */
1087
int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107
{
	int pos, temp;

	/* Must reset in this function */
	info->status = 0;
	info->tlp_header_valid = 0;

	pos = dev->aer_cap;

	/* The device might not support AER */
	if (!pos)
		return 0;

	if (info->severity == AER_CORRECTABLE) {
		pci_read_config_dword(dev, pos + PCI_ERR_COR_STATUS,
			&info->status);
		pci_read_config_dword(dev, pos + PCI_ERR_COR_MASK,
			&info->mask);
		if (!(info->status & ~info->mask))
			return 0;
1108 1109 1110
	} else if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
	           pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM ||
		   info->severity == AER_NONFATAL) {
1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145

		/* Link is still healthy for IO reads */
		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS,
			&info->status);
		pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK,
			&info->mask);
		if (!(info->status & ~info->mask))
			return 0;

		/* Get First Error Pointer */
		pci_read_config_dword(dev, pos + PCI_ERR_CAP, &temp);
		info->first_error = PCI_ERR_CAP_FEP(temp);

		if (info->status & AER_LOG_TLP_MASKS) {
			info->tlp_header_valid = 1;
			pci_read_config_dword(dev,
				pos + PCI_ERR_HEADER_LOG, &info->tlp.dw0);
			pci_read_config_dword(dev,
				pos + PCI_ERR_HEADER_LOG + 4, &info->tlp.dw1);
			pci_read_config_dword(dev,
				pos + PCI_ERR_HEADER_LOG + 8, &info->tlp.dw2);
			pci_read_config_dword(dev,
				pos + PCI_ERR_HEADER_LOG + 12, &info->tlp.dw3);
		}
	}

	return 1;
}

static inline void aer_process_err_devices(struct aer_err_info *e_info)
{
	int i;

	/* Report all before handle them, not to lost records by reset etc. */
	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
1146
		if (aer_get_device_error_info(e_info->dev[i], e_info))
1147 1148 1149
			aer_print_error(e_info->dev[i], e_info);
	}
	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
1150
		if (aer_get_device_error_info(e_info->dev[i], e_info))
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163
			handle_error_source(e_info->dev[i], e_info);
	}
}

/**
 * aer_isr_one_error - consume an error detected by root port
 * @rpc: pointer to the root port which holds an error
 * @e_src: pointer to an error source
 */
static void aer_isr_one_error(struct aer_rpc *rpc,
		struct aer_err_source *e_src)
{
	struct pci_dev *pdev = rpc->rpd;
1164
	struct aer_err_info e_info;
1165

1166 1167
	pci_rootport_aer_stats_incr(pdev, e_src);

1168 1169 1170 1171 1172
	/*
	 * There is a possibility that both correctable error and
	 * uncorrectable error being logged. Report correctable error first.
	 */
	if (e_src->status & PCI_ERR_ROOT_COR_RCV) {
1173 1174
		e_info.id = ERR_COR_ID(e_src->id);
		e_info.severity = AER_CORRECTABLE;
1175 1176

		if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV)
1177
			e_info.multi_error_valid = 1;
1178
		else
1179 1180
			e_info.multi_error_valid = 0;
		aer_print_port_info(pdev, &e_info);
1181

1182 1183
		if (find_source_device(pdev, &e_info))
			aer_process_err_devices(&e_info);
1184 1185 1186
	}

	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
1187
		e_info.id = ERR_UNCOR_ID(e_src->id);
1188 1189

		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
1190
			e_info.severity = AER_FATAL;
1191
		else
1192
			e_info.severity = AER_NONFATAL;
1193 1194

		if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV)
1195
			e_info.multi_error_valid = 1;
1196
		else
1197
			e_info.multi_error_valid = 0;
1198

1199
		aer_print_port_info(pdev, &e_info);
1200

1201 1202
		if (find_source_device(pdev, &e_info))
			aer_process_err_devices(&e_info);
1203 1204 1205 1206 1207 1208 1209 1210 1211
	}
}

/**
 * aer_isr - consume errors detected by root port
 * @work: definition of this work item
 *
 * Invoked, as DPC, when root port records new detected error
 */
1212
static irqreturn_t aer_isr(int irq, void *context)
1213
{
1214 1215
	struct pcie_device *dev = (struct pcie_device *)context;
	struct aer_rpc *rpc = get_service_data(dev);
1216 1217
	struct aer_err_source uninitialized_var(e_src);

1218 1219 1220
	if (kfifo_is_empty(&rpc->aer_fifo))
		return IRQ_NONE;

1221
	while (kfifo_get(&rpc->aer_fifo, &e_src))
1222
		aer_isr_one_error(rpc, &e_src);
1223
	return IRQ_HANDLED;
1224 1225
}

1226 1227 1228 1229 1230 1231 1232
/**
 * aer_irq - Root Port's ISR
 * @irq: IRQ assigned to Root Port
 * @context: pointer to Root Port data structure
 *
 * Invoked when Root Port detects AER messages.
 */
1233
static irqreturn_t aer_irq(int irq, void *context)
1234 1235 1236
{
	struct pcie_device *pdev = (struct pcie_device *)context;
	struct aer_rpc *rpc = get_service_data(pdev);
1237 1238 1239
	struct pci_dev *rp = rpc->rpd;
	struct aer_err_source e_src = {};
	int pos = rp->aer_cap;
1240

1241 1242
	pci_read_config_dword(rp, pos + PCI_ERR_ROOT_STATUS, &e_src.status);
	if (!(e_src.status & (PCI_ERR_ROOT_UNCOR_RCV|PCI_ERR_ROOT_COR_RCV)))
1243 1244
		return IRQ_NONE;

1245 1246
	pci_read_config_dword(rp, pos + PCI_ERR_ROOT_ERR_SRC, &e_src.id);
	pci_write_config_dword(rp, pos + PCI_ERR_ROOT_STATUS, e_src.status);
1247

1248
	if (!kfifo_put(&rpc->aer_fifo, e_src))
1249 1250
		return IRQ_HANDLED;

1251
	return IRQ_WAKE_THREAD;
1252 1253
}

1254 1255 1256
static int set_device_error_reporting(struct pci_dev *dev, void *data)
{
	bool enable = *((bool *)data);
1257
	int type = pci_pcie_type(dev);
1258

1259 1260 1261
	if ((type == PCI_EXP_TYPE_ROOT_PORT) ||
	    (type == PCI_EXP_TYPE_UPSTREAM) ||
	    (type == PCI_EXP_TYPE_DOWNSTREAM)) {
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
		if (enable)
			pci_enable_pcie_error_reporting(dev);
		else
			pci_disable_pcie_error_reporting(dev);
	}

	if (enable)
		pcie_set_ecrc_checking(dev);

	return 0;
}

/**
 * set_downstream_devices_error_reporting - enable/disable the error reporting  bits on the root port and its downstream ports.
 * @dev: pointer to root port's pci_dev data structure
 * @enable: true = enable error reporting, false = disable error reporting.
 */
static void set_downstream_devices_error_reporting(struct pci_dev *dev,
						   bool enable)
{
	set_device_error_reporting(dev, &enable);

	if (!dev->subordinate)
		return;
	pci_walk_bus(dev->subordinate, set_device_error_reporting, &enable);
}

/**
 * aer_enable_rootport - enable Root Port's interrupts when receiving messages
 * @rpc: pointer to a Root Port data structure
 *
 * Invoked when PCIe bus loads AER service driver.
 */
static void aer_enable_rootport(struct aer_rpc *rpc)
{
1297
	struct pci_dev *pdev = rpc->rpd;
1298
	int aer_pos;
1299 1300 1301 1302
	u16 reg16;
	u32 reg32;

	/* Clear PCIe Capability's Device Status */
1303 1304
	pcie_capability_read_word(pdev, PCI_EXP_DEVSTA, &reg16);
	pcie_capability_write_word(pdev, PCI_EXP_DEVSTA, reg16);
1305 1306

	/* Disable system error generation in response to error messages */
1307 1308
	pcie_capability_clear_word(pdev, PCI_EXP_RTCTL,
				   SYSTEM_ERROR_INTR_ON_MESG_MASK);
1309

K
Keith Busch 已提交
1310
	aer_pos = pdev->aer_cap;
1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338
	/* Clear error status */
	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);
	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);
	pci_read_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, &reg32);
	pci_write_config_dword(pdev, aer_pos + PCI_ERR_COR_STATUS, reg32);
	pci_read_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, &reg32);
	pci_write_config_dword(pdev, aer_pos + PCI_ERR_UNCOR_STATUS, reg32);

	/*
	 * Enable error reporting for the root port device and downstream port
	 * devices.
	 */
	set_downstream_devices_error_reporting(pdev, true);

	/* Enable Root Port's interrupt in response to error messages */
	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, &reg32);
	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_COMMAND, reg32);
}

/**
 * aer_disable_rootport - disable Root Port's interrupts when receiving messages
 * @rpc: pointer to a Root Port data structure
 *
 * Invoked when PCIe bus unloads AER service driver.
 */
static void aer_disable_rootport(struct aer_rpc *rpc)
{
1339
	struct pci_dev *pdev = rpc->rpd;
1340 1341 1342 1343 1344 1345 1346 1347 1348
	u32 reg32;
	int pos;

	/*
	 * Disable error reporting for the root port device and downstream port
	 * devices.
	 */
	set_downstream_devices_error_reporting(pdev, false);

K
Keith Busch 已提交
1349
	pos = pdev->aer_cap;
1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
	/* Disable Root's interrupt in response to error messages */
	pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, reg32);

	/* Clear Root's error status reg */
	pci_read_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, &reg32);
	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_STATUS, reg32);
}

1360 1361 1362 1363 1364
/**
 * aer_remove - clean up resources
 * @dev: pointer to the pcie_dev data structure
 *
 * Invoked when PCI Express bus unloads or AER probe fails.
1365
 */
1366 1367 1368 1369
static void aer_remove(struct pcie_device *dev)
{
	struct aer_rpc *rpc = get_service_data(dev);

1370
	aer_disable_rootport(rpc);
1371 1372 1373 1374 1375 1376 1377
}

/**
 * aer_probe - initialize resources
 * @dev: pointer to the pcie_dev data structure
 *
 * Invoked when PCI Express bus loads AER service driver.
1378
 */
B
Bill Pemberton 已提交
1379
static int aer_probe(struct pcie_device *dev)
1380 1381 1382
{
	int status;
	struct aer_rpc *rpc;
1383
	struct device *device = &dev->device;
1384
	struct pci_dev *port = dev->port;
1385

1386
	rpc = devm_kzalloc(device, sizeof(struct aer_rpc), GFP_KERNEL);
1387
	if (!rpc) {
1388
		dev_printk(KERN_DEBUG, device, "alloc AER rpc failed\n");
1389 1390
		return -ENOMEM;
	}
1391 1392

	rpc->rpd = port;
1393
	set_service_data(dev, rpc);
1394

1395 1396
	status = devm_request_threaded_irq(device, dev->irq, aer_irq, aer_isr,
					   IRQF_SHARED, "aerdrv", dev);
1397
	if (status) {
1398
		pci_err(port, "request AER IRQ %d failed\n", dev->irq);
1399 1400 1401 1402
		return status;
	}

	aer_enable_rootport(rpc);
1403
	pci_info(port, "enabled with IRQ %d\n", dev->irq);
1404
	return 0;
1405 1406 1407 1408 1409 1410 1411
}

/**
 * aer_root_reset - reset link on Root Port
 * @dev: pointer to Root Port's pci_dev data structure
 *
 * Invoked by Port Bus driver when performing link reset at Root Port.
1412
 */
1413 1414
static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
{
1415
	u32 reg32;
1416
	int pos;
1417
	int rc;
1418

K
Keith Busch 已提交
1419
	pos = dev->aer_cap;
1420 1421

	/* Disable Root's interrupt in response to error messages */
1422 1423 1424
	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
1425

K
Keith Busch 已提交
1426
	rc = pci_bus_error_reset(dev);
1427
	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
1428

1429 1430 1431 1432
	/* Clear Root Error Status */
	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &reg32);
	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, reg32);

1433
	/* Enable Root Port's interrupt in response to error messages */
1434 1435 1436
	pci_read_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, &reg32);
	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
1437

1438
	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
1439 1440
}

1441 1442 1443 1444 1445 1446 1447 1448 1449 1450
static struct pcie_port_service_driver aerdriver = {
	.name		= "aer",
	.port_type	= PCI_EXP_TYPE_ROOT_PORT,
	.service	= PCIE_PORT_SERVICE_AER,

	.probe		= aer_probe,
	.remove		= aer_remove,
	.reset_link	= aer_root_reset,
};

1451 1452 1453 1454
/**
 * aer_service_init - register AER root service driver
 *
 * Invoked when AER root service driver is loaded.
1455
 */
1456
int __init pcie_aer_init(void)
1457
{
1458
	if (!pci_aer_available() || aer_acpi_firmware_first())
A
Andi Kleen 已提交
1459
		return -ENXIO;
1460
	return pcie_port_service_register(&aerdriver);
1461
}