summaryrefslogtreecommitdiff
path: root/drivers/cxl/pci.c
blob: 33083a522fd1cc121b7b1a117364e19c88c04f53 (plain)
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
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2020 Intel Corporation. All rights reserved. */
#include <linux/io-64-nonatomic-lo-hi.h>
#include <linux/moduleparam.h>
#include <linux/module.h>
#include <linux/delay.h>
#include <linux/sizes.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/pci.h>
#include <linux/pci-doe.h>
#include <linux/aer.h>
#include <linux/io.h>
#include "cxlmem.h"
#include "cxlpci.h"
#include "cxl.h"
#define CREATE_TRACE_POINTS
#include <trace/events/cxl.h>

/**
 * DOC: cxl pci
 *
 * This implements the PCI exclusive functionality for a CXL device as it is
 * defined by the Compute Express Link specification. CXL devices may surface
 * certain functionality even if it isn't CXL enabled. While this driver is
 * focused around the PCI specific aspects of a CXL device, it binds to the
 * specific CXL memory device class code, and therefore the implementation of
 * cxl_pci is focused around CXL memory devices.
 *
 * The driver has several responsibilities, mainly:
 *  - Create the memX device and register on the CXL bus.
 *  - Enumerate device's register interface and map them.
 *  - Registers nvdimm bridge device with cxl_core.
 *  - Registers a CXL mailbox with cxl_core.
 */

#define cxl_doorbell_busy(cxlds)                                                \
	(readl((cxlds)->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET) &                  \
	 CXLDEV_MBOX_CTRL_DOORBELL)

/* CXL 2.0 - 8.2.8.4 */
#define CXL_MAILBOX_TIMEOUT_MS (2 * HZ)

/*
 * CXL 2.0 ECN "Add Mailbox Ready Time" defines a capability field to
 * dictate how long to wait for the mailbox to become ready. The new
 * field allows the device to tell software the amount of time to wait
 * before mailbox ready. This field per the spec theoretically allows
 * for up to 255 seconds. 255 seconds is unreasonably long, its longer
 * than the maximum SATA port link recovery wait. Default to 60 seconds
 * until someone builds a CXL device that needs more time in practice.
 */
static unsigned short mbox_ready_timeout = 60;
module_param(mbox_ready_timeout, ushort, 0644);
MODULE_PARM_DESC(mbox_ready_timeout, "seconds to wait for mailbox ready");

static int cxl_pci_mbox_wait_for_doorbell(struct cxl_dev_state *cxlds)
{
	const unsigned long start = jiffies;
	unsigned long end = start;

	while (cxl_doorbell_busy(cxlds)) {
		end = jiffies;

		if (time_after(end, start + CXL_MAILBOX_TIMEOUT_MS)) {
			/* Check again in case preempted before timeout test */
			if (!cxl_doorbell_busy(cxlds))
				break;
			return -ETIMEDOUT;
		}
		cpu_relax();
	}

	dev_dbg(cxlds->dev, "Doorbell wait took %dms",
		jiffies_to_msecs(end) - jiffies_to_msecs(start));
	return 0;
}

#define cxl_err(dev, status, msg)                                        \
	dev_err_ratelimited(dev, msg ", device state %s%s\n",                  \
			    status & CXLMDEV_DEV_FATAL ? " fatal" : "",        \
			    status & CXLMDEV_FW_HALT ? " firmware-halt" : "")

#define cxl_cmd_err(dev, cmd, status, msg)                               \
	dev_err_ratelimited(dev, msg " (opcode: %#x), device state %s%s\n",    \
			    (cmd)->opcode,                                     \
			    status & CXLMDEV_DEV_FATAL ? " fatal" : "",        \
			    status & CXLMDEV_FW_HALT ? " firmware-halt" : "")

/**
 * __cxl_pci_mbox_send_cmd() - Execute a mailbox command
 * @cxlds: The device state to communicate with.
 * @mbox_cmd: Command to send to the memory device.
 *
 * Context: Any context. Expects mbox_mutex to be held.
 * Return: -ETIMEDOUT if timeout occurred waiting for completion. 0 on success.
 *         Caller should check the return code in @mbox_cmd to make sure it
 *         succeeded.
 *
 * This is a generic form of the CXL mailbox send command thus only using the
 * registers defined by the mailbox capability ID - CXL 2.0 8.2.8.4. Memory
 * devices, and perhaps other types of CXL devices may have further information
 * available upon error conditions. Driver facilities wishing to send mailbox
 * commands should use the wrapper command.
 *
 * The CXL spec allows for up to two mailboxes. The intention is for the primary
 * mailbox to be OS controlled and the secondary mailbox to be used by system
 * firmware. This allows the OS and firmware to communicate with the device and
 * not need to coordinate with each other. The driver only uses the primary
 * mailbox.
 */
static int __cxl_pci_mbox_send_cmd(struct cxl_dev_state *cxlds,
				   struct cxl_mbox_cmd *mbox_cmd)
{
	void __iomem *payload = cxlds->regs.mbox + CXLDEV_MBOX_PAYLOAD_OFFSET;
	struct device *dev = cxlds->dev;
	u64 cmd_reg, status_reg;
	size_t out_len;
	int rc;

	lockdep_assert_held(&cxlds->mbox_mutex);

	/*
	 * Here are the steps from 8.2.8.4 of the CXL 2.0 spec.
	 *   1. Caller reads MB Control Register to verify doorbell is clear
	 *   2. Caller writes Command Register
	 *   3. Caller writes Command Payload Registers if input payload is non-empty
	 *   4. Caller writes MB Control Register to set doorbell
	 *   5. Caller either polls for doorbell to be clear or waits for interrupt if configured
	 *   6. Caller reads MB Status Register to fetch Return code
	 *   7. If command successful, Caller reads Command Register to get Payload Length
	 *   8. If output payload is non-empty, host reads Command Payload Registers
	 *
	 * Hardware is free to do whatever it wants before the doorbell is rung,
	 * and isn't allowed to change anything after it clears the doorbell. As
	 * such, steps 2 and 3 can happen in any order, and steps 6, 7, 8 can
	 * also happen in any order (though some orders might not make sense).
	 */

	/* #1 */
	if (cxl_doorbell_busy(cxlds)) {
		u64 md_status =
			readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET);

		cxl_cmd_err(cxlds->dev, mbox_cmd, md_status,
			    "mailbox queue busy");
		return -EBUSY;
	}

	cmd_reg = FIELD_PREP(CXLDEV_MBOX_CMD_COMMAND_OPCODE_MASK,
			     mbox_cmd->opcode);
	if (mbox_cmd->size_in) {
		if (WARN_ON(!mbox_cmd->payload_in))
			return -EINVAL;

		cmd_reg |= FIELD_PREP(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK,
				      mbox_cmd->size_in);
		memcpy_toio(payload, mbox_cmd->payload_in, mbox_cmd->size_in);
	}

	/* #2, #3 */
	writeq(cmd_reg, cxlds->regs.mbox + CXLDEV_MBOX_CMD_OFFSET);

	/* #4 */
	dev_dbg(dev, "Sending command\n");
	writel(CXLDEV_MBOX_CTRL_DOORBELL,
	       cxlds->regs.mbox + CXLDEV_MBOX_CTRL_OFFSET);

	/* #5 */
	rc = cxl_pci_mbox_wait_for_doorbell(cxlds);
	if (rc == -ETIMEDOUT) {
		u64 md_status = readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET);

		cxl_cmd_err(cxlds->dev, mbox_cmd, md_status, "mailbox timeout");
		return rc;
	}

	/* #6 */
	status_reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_STATUS_OFFSET);
	mbox_cmd->return_code =
		FIELD_GET(CXLDEV_MBOX_STATUS_RET_CODE_MASK, status_reg);

	if (mbox_cmd->return_code != CXL_MBOX_CMD_RC_SUCCESS) {
		dev_dbg(dev, "Mailbox operation had an error: %s\n",
			cxl_mbox_cmd_rc2str(mbox_cmd));
		return 0; /* completed but caller must check return_code */
	}

	/* #7 */
	cmd_reg = readq(cxlds->regs.mbox + CXLDEV_MBOX_CMD_OFFSET);
	out_len = FIELD_GET(CXLDEV_MBOX_CMD_PAYLOAD_LENGTH_MASK, cmd_reg);

	/* #8 */
	if (out_len && mbox_cmd->payload_out) {
		/*
		 * Sanitize the copy. If hardware misbehaves, out_len per the
		 * spec can actually be greater than the max allowed size (21
		 * bits available but spec defined 1M max). The caller also may
		 * have requested less data than the hardware supplied even
		 * within spec.
		 */
		size_t n = min3(mbox_cmd->size_out, cxlds->payload_size, out_len);

		memcpy_fromio(mbox_cmd->payload_out, payload, n);
		mbox_cmd->size_out = n;
	} else {
		mbox_cmd->size_out = 0;
	}

	return 0;
}

static int cxl_pci_mbox_send(struct cxl_dev_state *cxlds, struct cxl_mbox_cmd *cmd)
{
	int rc;

	mutex_lock_io(&cxlds->mbox_mutex);
	rc = __cxl_pci_mbox_send_cmd(cxlds, cmd);
	mutex_unlock(&cxlds->mbox_mutex);

	return rc;
}

static int cxl_pci_setup_mailbox(struct cxl_dev_state *cxlds)
{
	const int cap = readl(cxlds->regs.mbox + CXLDEV_MBOX_CAPS_OFFSET);
	unsigned long timeout;
	u64 md_status;

	timeout = jiffies + mbox_ready_timeout * HZ;
	do {
		md_status = readq(cxlds->regs.memdev + CXLMDEV_STATUS_OFFSET);
		if (md_status & CXLMDEV_MBOX_IF_READY)
			break;
		if (msleep_interruptible(100))
			break;
	} while (!time_after(jiffies, timeout));

	if (!(md_status & CXLMDEV_MBOX_IF_READY)) {
		cxl_err(cxlds->dev, md_status,
			"timeout awaiting mailbox ready");
		return -ETIMEDOUT;
	}

	/*
	 * A command may be in flight from a previous driver instance,
	 * think kexec, do one doorbell wait so that
	 * __cxl_pci_mbox_send_cmd() can assume that it is the only
	 * source for future doorbell busy events.
	 */
	if (cxl_pci_mbox_wait_for_doorbell(cxlds) != 0) {
		cxl_err(cxlds->dev, md_status, "timeout awaiting mailbox idle");
		return -ETIMEDOUT;
	}

	cxlds->mbox_send = cxl_pci_mbox_send;
	cxlds->payload_size =
		1 << FIELD_GET(CXLDEV_MBOX_CAP_PAYLOAD_SIZE_MASK, cap);

	/*
	 * CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register
	 *
	 * If the size is too small, mandatory commands will not work and so
	 * there's no point in going forward. If the size is too large, there's
	 * no harm is soft limiting it.
	 */
	cxlds->payload_size = min_t(size_t, cxlds->payload_size, SZ_1M);
	if (cxlds->payload_size < 256) {
		dev_err(cxlds->dev, "Mailbox is too small (%zub)",
			cxlds->payload_size);
		return -ENXIO;
	}

	dev_dbg(cxlds->dev, "Mailbox payload sized %zu",
		cxlds->payload_size);

	return 0;
}

static int cxl_map_regblock(struct pci_dev *pdev, struct cxl_register_map *map)
{
	struct device *dev = &pdev->dev;

	map->base = ioremap(map->resource, map->max_size);
	if (!map->base) {
		dev_err(dev, "failed to map registers\n");
		return -ENOMEM;
	}

	dev_dbg(dev, "Mapped CXL Memory Device resource %pa\n", &map->resource);
	return 0;
}

static void cxl_unmap_regblock(struct pci_dev *pdev,
			       struct cxl_register_map *map)
{
	iounmap(map->base);
	map->base = NULL;
}

static int cxl_probe_regs(struct pci_dev *pdev, struct cxl_register_map *map)
{
	struct cxl_component_reg_map *comp_map;
	struct cxl_device_reg_map *dev_map;
	struct device *dev = &pdev->dev;
	void __iomem *base = map->base;

	switch (map->reg_type) {
	case CXL_REGLOC_RBI_COMPONENT:
		comp_map = &map->component_map;
		cxl_probe_component_regs(dev, base, comp_map);
		if (!comp_map->hdm_decoder.valid) {
			dev_err(dev, "HDM decoder registers not found\n");
			return -ENXIO;
		}

		if (!comp_map->ras.valid)
			dev_dbg(dev, "RAS registers not found\n");

		dev_dbg(dev, "Set up component registers\n");
		break;
	case CXL_REGLOC_RBI_MEMDEV:
		dev_map = &map->device_map;
		cxl_probe_device_regs(dev, base, dev_map);
		if (!dev_map->status.valid || !dev_map->mbox.valid ||
		    !dev_map->memdev.valid) {
			dev_err(dev, "registers not found: %s%s%s\n",
				!dev_map->status.valid ? "status " : "",
				!dev_map->mbox.valid ? "mbox " : "",
				!dev_map->memdev.valid ? "memdev " : "");
			return -ENXIO;
		}

		dev_dbg(dev, "Probing device registers...\n");
		break;
	default:
		break;
	}

	return 0;
}

static int cxl_setup_regs(struct pci_dev *pdev, enum cxl_regloc_type type,
			  struct cxl_register_map *map)
{
	int rc;

	rc = cxl_find_regblock(pdev, type, map);
	if (rc)
		return rc;

	rc = cxl_map_regblock(pdev, map);
	if (rc)
		return rc;

	rc = cxl_probe_regs(pdev, map);
	cxl_unmap_regblock(pdev, map);

	return rc;
}

static void cxl_pci_destroy_doe(void *mbs)
{
	xa_destroy(mbs);
}

static void devm_cxl_pci_create_doe(struct cxl_dev_state *cxlds)
{
	struct device *dev = cxlds->dev;
	struct pci_dev *pdev = to_pci_dev(dev);
	u16 off = 0;

	xa_init(&cxlds->doe_mbs);
	if (devm_add_action(&pdev->dev, cxl_pci_destroy_doe, &cxlds->doe_mbs)) {
		dev_err(dev, "Failed to create XArray for DOE's\n");
		return;
	}

	/*
	 * Mailbox creation is best effort.  Higher layers must determine if
	 * the lack of a mailbox for their protocol is a device failure or not.
	 */
	pci_doe_for_each_off(pdev, off) {
		struct pci_doe_mb *doe_mb;

		doe_mb = pcim_doe_create_mb(pdev, off);
		if (IS_ERR(doe_mb)) {
			dev_err(dev, "Failed to create MB object for MB @ %x\n",
				off);
			continue;
		}

		if (!pci_request_config_region_exclusive(pdev, off,
							 PCI_DOE_CAP_SIZEOF,
							 dev_name(dev)))
			pci_err(pdev, "Failed to exclude DOE registers\n");

		if (xa_insert(&cxlds->doe_mbs, off, doe_mb, GFP_KERNEL)) {
			dev_err(dev, "xa_insert failed to insert MB @ %x\n",
				off);
			continue;
		}

		dev_dbg(dev, "Created DOE mailbox @%x\n", off);
	}
}

/*
 * Assume that any RCIEP that emits the CXL memory expander class code
 * is an RCD
 */
static bool is_cxl_restricted(struct pci_dev *pdev)
{
	return pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END;
}

static void disable_aer(void *pdev)
{
	pci_disable_pcie_error_reporting(pdev);
}

static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
	struct cxl_register_map map;
	struct cxl_memdev *cxlmd;
	struct cxl_dev_state *cxlds;
	int rc;

	/*
	 * Double check the anonymous union trickery in struct cxl_regs
	 * FIXME switch to struct_group()
	 */
	BUILD_BUG_ON(offsetof(struct cxl_regs, memdev) !=
		     offsetof(struct cxl_regs, device_regs.memdev));

	rc = pcim_enable_device(pdev);
	if (rc)
		return rc;

	cxlds = cxl_dev_state_create(&pdev->dev);
	if (IS_ERR(cxlds))
		return PTR_ERR(cxlds);
	pci_set_drvdata(pdev, cxlds);

	cxlds->rcd = is_cxl_restricted(pdev);
	cxlds->serial = pci_get_dsn(pdev);
	cxlds->cxl_dvsec = pci_find_dvsec_capability(
		pdev, PCI_DVSEC_VENDOR_ID_CXL, CXL_DVSEC_PCIE_DEVICE);
	if (!cxlds->cxl_dvsec)
		dev_warn(&pdev->dev,
			 "Device DVSEC not present, skip CXL.mem init\n");

	rc = cxl_setup_regs(pdev, CXL_REGLOC_RBI_MEMDEV, &map);
	if (rc)
		return rc;

	rc = cxl_map_device_regs(&pdev->dev, &cxlds->regs.device_regs, &map);
	if (rc)
		return rc;

	/*
	 * If the component registers can't be found, the cxl_pci driver may
	 * still be useful for management functions so don't return an error.
	 */
	cxlds->component_reg_phys = CXL_RESOURCE_NONE;
	rc = cxl_setup_regs(pdev, CXL_REGLOC_RBI_COMPONENT, &map);
	if (rc)
		dev_warn(&pdev->dev, "No component registers (%d)\n", rc);

	cxlds->component_reg_phys = map.resource;

	devm_cxl_pci_create_doe(cxlds);

	rc = cxl_map_component_regs(&pdev->dev, &cxlds->regs.component,
				    &map, BIT(CXL_CM_CAP_CAP_ID_RAS));
	if (rc)
		dev_dbg(&pdev->dev, "Failed to map RAS capability.\n");

	rc = cxl_pci_setup_mailbox(cxlds);
	if (rc)
		return rc;

	rc = cxl_enumerate_cmds(cxlds);
	if (rc)
		return rc;

	rc = cxl_dev_state_identify(cxlds);
	if (rc)
		return rc;

	rc = cxl_mem_create_range_info(cxlds);
	if (rc)
		return rc;

	cxlmd = devm_cxl_add_memdev(cxlds);
	if (IS_ERR(cxlmd))
		return PTR_ERR(cxlmd);

	if (cxlds->regs.ras) {
		pci_enable_pcie_error_reporting(pdev);
		rc = devm_add_action_or_reset(&pdev->dev, disable_aer, pdev);
		if (rc)
			return rc;
	}
	pci_save_state(pdev);

	return rc;
}

static const struct pci_device_id cxl_mem_pci_tbl[] = {
	/* PCI class code for CXL.mem Type-3 Devices */
	{ PCI_DEVICE_CLASS((PCI_CLASS_MEMORY_CXL << 8 | CXL_MEMORY_PROGIF), ~0)},
	{ /* terminate list */ },
};
MODULE_DEVICE_TABLE(pci, cxl_mem_pci_tbl);

/* CXL spec rev3.0 8.2.4.16.1 */
static void header_log_copy(struct cxl_dev_state *cxlds, u32 *log)
{
	void __iomem *addr;
	u32 *log_addr;
	int i, log_u32_size = CXL_HEADERLOG_SIZE / sizeof(u32);

	addr = cxlds->regs.ras + CXL_RAS_HEADER_LOG_OFFSET;
	log_addr = log;

	for (i = 0; i < log_u32_size; i++) {
		*log_addr = readl(addr);
		log_addr++;
		addr += sizeof(u32);
	}
}

/*
 * Log the state of the RAS status registers and prepare them to log the
 * next error status. Return 1 if reset needed.
 */
static bool cxl_report_and_clear(struct cxl_dev_state *cxlds)
{
	struct cxl_memdev *cxlmd = cxlds->cxlmd;
	struct device *dev = &cxlmd->dev;
	u32 hl[CXL_HEADERLOG_SIZE_U32];
	void __iomem *addr;
	u32 status;
	u32 fe;

	if (!cxlds->regs.ras)
		return false;

	addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_STATUS_OFFSET;
	status = readl(addr);
	if (!(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK))
		return false;

	/* If multiple errors, log header points to first error from ctrl reg */
	if (hweight32(status) > 1) {
		addr = cxlds->regs.ras + CXL_RAS_CAP_CONTROL_OFFSET;
		fe = BIT(FIELD_GET(CXL_RAS_CAP_CONTROL_FE_MASK, readl(addr)));
	} else {
		fe = status;
	}

	header_log_copy(cxlds, hl);
	trace_cxl_aer_uncorrectable_error(dev, status, fe, hl);
	writel(status & CXL_RAS_UNCORRECTABLE_STATUS_MASK, addr);

	return true;
}

static pci_ers_result_t cxl_error_detected(struct pci_dev *pdev,
					   pci_channel_state_t state)
{
	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
	struct cxl_memdev *cxlmd = cxlds->cxlmd;
	struct device *dev = &cxlmd->dev;
	bool ue;

	/*
	 * A frozen channel indicates an impending reset which is fatal to
	 * CXL.mem operation, and will likely crash the system. On the off
	 * chance the situation is recoverable dump the status of the RAS
	 * capability registers and bounce the active state of the memdev.
	 */
	ue = cxl_report_and_clear(cxlds);

	switch (state) {
	case pci_channel_io_normal:
		if (ue) {
			device_release_driver(dev);
			return PCI_ERS_RESULT_NEED_RESET;
		}
		return PCI_ERS_RESULT_CAN_RECOVER;
	case pci_channel_io_frozen:
		dev_warn(&pdev->dev,
			 "%s: frozen state error detected, disable CXL.mem\n",
			 dev_name(dev));
		device_release_driver(dev);
		return PCI_ERS_RESULT_NEED_RESET;
	case pci_channel_io_perm_failure:
		dev_warn(&pdev->dev,
			 "failure state error detected, request disconnect\n");
		return PCI_ERS_RESULT_DISCONNECT;
	}
	return PCI_ERS_RESULT_NEED_RESET;
}

static pci_ers_result_t cxl_slot_reset(struct pci_dev *pdev)
{
	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
	struct cxl_memdev *cxlmd = cxlds->cxlmd;
	struct device *dev = &cxlmd->dev;

	dev_info(&pdev->dev, "%s: restart CXL.mem after slot reset\n",
		 dev_name(dev));
	pci_restore_state(pdev);
	if (device_attach(dev) <= 0)
		return PCI_ERS_RESULT_DISCONNECT;
	return PCI_ERS_RESULT_RECOVERED;
}

static void cxl_error_resume(struct pci_dev *pdev)
{
	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
	struct cxl_memdev *cxlmd = cxlds->cxlmd;
	struct device *dev = &cxlmd->dev;

	dev_info(&pdev->dev, "%s: error resume %s\n", dev_name(dev),
		 dev->driver ? "successful" : "failed");
}

static void cxl_cor_error_detected(struct pci_dev *pdev)
{
	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
	struct cxl_memdev *cxlmd = cxlds->cxlmd;
	struct device *dev = &cxlmd->dev;
	void __iomem *addr;
	u32 status;

	if (!cxlds->regs.ras)
		return;

	addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_STATUS_OFFSET;
	status = readl(addr);
	if (status & CXL_RAS_CORRECTABLE_STATUS_MASK) {
		writel(status & CXL_RAS_CORRECTABLE_STATUS_MASK, addr);
		trace_cxl_aer_correctable_error(dev, status);
	}
}

static const struct pci_error_handlers cxl_error_handlers = {
	.error_detected	= cxl_error_detected,
	.slot_reset	= cxl_slot_reset,
	.resume		= cxl_error_resume,
	.cor_error_detected	= cxl_cor_error_detected,
};

static struct pci_driver cxl_pci_driver = {
	.name			= KBUILD_MODNAME,
	.id_table		= cxl_mem_pci_tbl,
	.probe			= cxl_pci_probe,
	.err_handler		= &cxl_error_handlers,
	.driver	= {
		.probe_type	= PROBE_PREFER_ASYNCHRONOUS,
	},
};

MODULE_LICENSE("GPL v2");
module_pci_driver(cxl_pci_driver);
MODULE_IMPORT_NS(CXL);