xref: /kernel/linux/linux-5.10/drivers/acpi/apei/erst.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-only
2/*
3 * APEI Error Record Serialization Table support
4 *
5 * ERST is a way provided by APEI to save and retrieve hardware error
6 * information to and from a persistent store.
7 *
8 * For more information about ERST, please refer to ACPI Specification
9 * version 4.0, section 17.4.
10 *
11 * Copyright 2010 Intel Corp.
12 *   Author: Huang Ying <ying.huang@intel.com>
13 */
14
15#include <linux/kernel.h>
16#include <linux/module.h>
17#include <linux/init.h>
18#include <linux/delay.h>
19#include <linux/io.h>
20#include <linux/acpi.h>
21#include <linux/uaccess.h>
22#include <linux/cper.h>
23#include <linux/nmi.h>
24#include <linux/hardirq.h>
25#include <linux/pstore.h>
26#include <linux/vmalloc.h>
27#include <linux/mm.h> /* kvfree() */
28#include <acpi/apei.h>
29
30#include "apei-internal.h"
31
32#undef pr_fmt
33#define pr_fmt(fmt) "ERST: " fmt
34
35/* ERST command status */
36#define ERST_STATUS_SUCCESS			0x0
37#define ERST_STATUS_NOT_ENOUGH_SPACE		0x1
38#define ERST_STATUS_HARDWARE_NOT_AVAILABLE	0x2
39#define ERST_STATUS_FAILED			0x3
40#define ERST_STATUS_RECORD_STORE_EMPTY		0x4
41#define ERST_STATUS_RECORD_NOT_FOUND		0x5
42
43#define ERST_TAB_ENTRY(tab)						\
44	((struct acpi_whea_header *)((char *)(tab) +			\
45				     sizeof(struct acpi_table_erst)))
46
47#define SPIN_UNIT		100			/* 100ns */
48/* Firmware should respond within 1 milliseconds */
49#define FIRMWARE_TIMEOUT	(1 * NSEC_PER_MSEC)
50#define FIRMWARE_MAX_STALL	50			/* 50us */
51
52int erst_disable;
53EXPORT_SYMBOL_GPL(erst_disable);
54
55static struct acpi_table_erst *erst_tab;
56
57/* ERST Error Log Address Range atrributes */
58#define ERST_RANGE_RESERVED	0x0001
59#define ERST_RANGE_NVRAM	0x0002
60#define ERST_RANGE_SLOW		0x0004
61
62/*
63 * ERST Error Log Address Range, used as buffer for reading/writing
64 * error records.
65 */
66static struct erst_erange {
67	u64 base;
68	u64 size;
69	void __iomem *vaddr;
70	u32 attr;
71} erst_erange;
72
73/*
74 * Prevent ERST interpreter to run simultaneously, because the
75 * corresponding firmware implementation may not work properly when
76 * invoked simultaneously.
77 *
78 * It is used to provide exclusive accessing for ERST Error Log
79 * Address Range too.
80 */
81static DEFINE_RAW_SPINLOCK(erst_lock);
82
83static inline int erst_errno(int command_status)
84{
85	switch (command_status) {
86	case ERST_STATUS_SUCCESS:
87		return 0;
88	case ERST_STATUS_HARDWARE_NOT_AVAILABLE:
89		return -ENODEV;
90	case ERST_STATUS_NOT_ENOUGH_SPACE:
91		return -ENOSPC;
92	case ERST_STATUS_RECORD_STORE_EMPTY:
93	case ERST_STATUS_RECORD_NOT_FOUND:
94		return -ENOENT;
95	default:
96		return -EINVAL;
97	}
98}
99
100static int erst_timedout(u64 *t, u64 spin_unit)
101{
102	if ((s64)*t < spin_unit) {
103		pr_warn(FW_WARN "Firmware does not respond in time.\n");
104		return 1;
105	}
106	*t -= spin_unit;
107	ndelay(spin_unit);
108	touch_nmi_watchdog();
109	return 0;
110}
111
112static int erst_exec_load_var1(struct apei_exec_context *ctx,
113			       struct acpi_whea_header *entry)
114{
115	return __apei_exec_read_register(entry, &ctx->var1);
116}
117
118static int erst_exec_load_var2(struct apei_exec_context *ctx,
119			       struct acpi_whea_header *entry)
120{
121	return __apei_exec_read_register(entry, &ctx->var2);
122}
123
124static int erst_exec_store_var1(struct apei_exec_context *ctx,
125				struct acpi_whea_header *entry)
126{
127	return __apei_exec_write_register(entry, ctx->var1);
128}
129
130static int erst_exec_add(struct apei_exec_context *ctx,
131			 struct acpi_whea_header *entry)
132{
133	ctx->var1 += ctx->var2;
134	return 0;
135}
136
137static int erst_exec_subtract(struct apei_exec_context *ctx,
138			      struct acpi_whea_header *entry)
139{
140	ctx->var1 -= ctx->var2;
141	return 0;
142}
143
144static int erst_exec_add_value(struct apei_exec_context *ctx,
145			       struct acpi_whea_header *entry)
146{
147	int rc;
148	u64 val;
149
150	rc = __apei_exec_read_register(entry, &val);
151	if (rc)
152		return rc;
153	val += ctx->value;
154	rc = __apei_exec_write_register(entry, val);
155	return rc;
156}
157
158static int erst_exec_subtract_value(struct apei_exec_context *ctx,
159				    struct acpi_whea_header *entry)
160{
161	int rc;
162	u64 val;
163
164	rc = __apei_exec_read_register(entry, &val);
165	if (rc)
166		return rc;
167	val -= ctx->value;
168	rc = __apei_exec_write_register(entry, val);
169	return rc;
170}
171
172static int erst_exec_stall(struct apei_exec_context *ctx,
173			   struct acpi_whea_header *entry)
174{
175	u64 stall_time;
176
177	if (ctx->value > FIRMWARE_MAX_STALL) {
178		if (!in_nmi())
179			pr_warn(FW_WARN
180			"Too long stall time for stall instruction: 0x%llx.\n",
181				   ctx->value);
182		stall_time = FIRMWARE_MAX_STALL;
183	} else
184		stall_time = ctx->value;
185	udelay(stall_time);
186	return 0;
187}
188
189static int erst_exec_stall_while_true(struct apei_exec_context *ctx,
190				      struct acpi_whea_header *entry)
191{
192	int rc;
193	u64 val;
194	u64 timeout = FIRMWARE_TIMEOUT;
195	u64 stall_time;
196
197	if (ctx->var1 > FIRMWARE_MAX_STALL) {
198		if (!in_nmi())
199			pr_warn(FW_WARN
200		"Too long stall time for stall while true instruction: 0x%llx.\n",
201				   ctx->var1);
202		stall_time = FIRMWARE_MAX_STALL;
203	} else
204		stall_time = ctx->var1;
205
206	for (;;) {
207		rc = __apei_exec_read_register(entry, &val);
208		if (rc)
209			return rc;
210		if (val != ctx->value)
211			break;
212		if (erst_timedout(&timeout, stall_time * NSEC_PER_USEC))
213			return -EIO;
214	}
215	return 0;
216}
217
218static int erst_exec_skip_next_instruction_if_true(
219	struct apei_exec_context *ctx,
220	struct acpi_whea_header *entry)
221{
222	int rc;
223	u64 val;
224
225	rc = __apei_exec_read_register(entry, &val);
226	if (rc)
227		return rc;
228	if (val == ctx->value) {
229		ctx->ip += 2;
230		return APEI_EXEC_SET_IP;
231	}
232
233	return 0;
234}
235
236static int erst_exec_goto(struct apei_exec_context *ctx,
237			  struct acpi_whea_header *entry)
238{
239	ctx->ip = ctx->value;
240	return APEI_EXEC_SET_IP;
241}
242
243static int erst_exec_set_src_address_base(struct apei_exec_context *ctx,
244					  struct acpi_whea_header *entry)
245{
246	return __apei_exec_read_register(entry, &ctx->src_base);
247}
248
249static int erst_exec_set_dst_address_base(struct apei_exec_context *ctx,
250					  struct acpi_whea_header *entry)
251{
252	return __apei_exec_read_register(entry, &ctx->dst_base);
253}
254
255static int erst_exec_move_data(struct apei_exec_context *ctx,
256			       struct acpi_whea_header *entry)
257{
258	int rc;
259	u64 offset;
260	void *src, *dst;
261
262	/* ioremap does not work in interrupt context */
263	if (in_interrupt()) {
264		pr_warn("MOVE_DATA can not be used in interrupt context.\n");
265		return -EBUSY;
266	}
267
268	rc = __apei_exec_read_register(entry, &offset);
269	if (rc)
270		return rc;
271
272	src = ioremap(ctx->src_base + offset, ctx->var2);
273	if (!src)
274		return -ENOMEM;
275	dst = ioremap(ctx->dst_base + offset, ctx->var2);
276	if (!dst) {
277		iounmap(src);
278		return -ENOMEM;
279	}
280
281	memmove(dst, src, ctx->var2);
282
283	iounmap(src);
284	iounmap(dst);
285
286	return 0;
287}
288
289static struct apei_exec_ins_type erst_ins_type[] = {
290	[ACPI_ERST_READ_REGISTER] = {
291		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
292		.run = apei_exec_read_register,
293	},
294	[ACPI_ERST_READ_REGISTER_VALUE] = {
295		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
296		.run = apei_exec_read_register_value,
297	},
298	[ACPI_ERST_WRITE_REGISTER] = {
299		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
300		.run = apei_exec_write_register,
301	},
302	[ACPI_ERST_WRITE_REGISTER_VALUE] = {
303		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
304		.run = apei_exec_write_register_value,
305	},
306	[ACPI_ERST_NOOP] = {
307		.flags = 0,
308		.run = apei_exec_noop,
309	},
310	[ACPI_ERST_LOAD_VAR1] = {
311		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
312		.run = erst_exec_load_var1,
313	},
314	[ACPI_ERST_LOAD_VAR2] = {
315		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
316		.run = erst_exec_load_var2,
317	},
318	[ACPI_ERST_STORE_VAR1] = {
319		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
320		.run = erst_exec_store_var1,
321	},
322	[ACPI_ERST_ADD] = {
323		.flags = 0,
324		.run = erst_exec_add,
325	},
326	[ACPI_ERST_SUBTRACT] = {
327		.flags = 0,
328		.run = erst_exec_subtract,
329	},
330	[ACPI_ERST_ADD_VALUE] = {
331		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
332		.run = erst_exec_add_value,
333	},
334	[ACPI_ERST_SUBTRACT_VALUE] = {
335		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
336		.run = erst_exec_subtract_value,
337	},
338	[ACPI_ERST_STALL] = {
339		.flags = 0,
340		.run = erst_exec_stall,
341	},
342	[ACPI_ERST_STALL_WHILE_TRUE] = {
343		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
344		.run = erst_exec_stall_while_true,
345	},
346	[ACPI_ERST_SKIP_NEXT_IF_TRUE] = {
347		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
348		.run = erst_exec_skip_next_instruction_if_true,
349	},
350	[ACPI_ERST_GOTO] = {
351		.flags = 0,
352		.run = erst_exec_goto,
353	},
354	[ACPI_ERST_SET_SRC_ADDRESS_BASE] = {
355		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
356		.run = erst_exec_set_src_address_base,
357	},
358	[ACPI_ERST_SET_DST_ADDRESS_BASE] = {
359		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
360		.run = erst_exec_set_dst_address_base,
361	},
362	[ACPI_ERST_MOVE_DATA] = {
363		.flags = APEI_EXEC_INS_ACCESS_REGISTER,
364		.run = erst_exec_move_data,
365	},
366};
367
368static inline void erst_exec_ctx_init(struct apei_exec_context *ctx)
369{
370	apei_exec_ctx_init(ctx, erst_ins_type, ARRAY_SIZE(erst_ins_type),
371			   ERST_TAB_ENTRY(erst_tab), erst_tab->entries);
372}
373
374static int erst_get_erange(struct erst_erange *range)
375{
376	struct apei_exec_context ctx;
377	int rc;
378
379	erst_exec_ctx_init(&ctx);
380	rc = apei_exec_run(&ctx, ACPI_ERST_GET_ERROR_RANGE);
381	if (rc)
382		return rc;
383	range->base = apei_exec_ctx_get_output(&ctx);
384	rc = apei_exec_run(&ctx, ACPI_ERST_GET_ERROR_LENGTH);
385	if (rc)
386		return rc;
387	range->size = apei_exec_ctx_get_output(&ctx);
388	rc = apei_exec_run(&ctx, ACPI_ERST_GET_ERROR_ATTRIBUTES);
389	if (rc)
390		return rc;
391	range->attr = apei_exec_ctx_get_output(&ctx);
392
393	return 0;
394}
395
396static ssize_t __erst_get_record_count(void)
397{
398	struct apei_exec_context ctx;
399	int rc;
400
401	erst_exec_ctx_init(&ctx);
402	rc = apei_exec_run(&ctx, ACPI_ERST_GET_RECORD_COUNT);
403	if (rc)
404		return rc;
405	return apei_exec_ctx_get_output(&ctx);
406}
407
408ssize_t erst_get_record_count(void)
409{
410	ssize_t count;
411	unsigned long flags;
412
413	if (erst_disable)
414		return -ENODEV;
415
416	raw_spin_lock_irqsave(&erst_lock, flags);
417	count = __erst_get_record_count();
418	raw_spin_unlock_irqrestore(&erst_lock, flags);
419
420	return count;
421}
422EXPORT_SYMBOL_GPL(erst_get_record_count);
423
424#define ERST_RECORD_ID_CACHE_SIZE_MIN	16
425#define ERST_RECORD_ID_CACHE_SIZE_MAX	1024
426
427struct erst_record_id_cache {
428	struct mutex lock;
429	u64 *entries;
430	int len;
431	int size;
432	int refcount;
433};
434
435static struct erst_record_id_cache erst_record_id_cache = {
436	.lock = __MUTEX_INITIALIZER(erst_record_id_cache.lock),
437	.refcount = 0,
438};
439
440static int __erst_get_next_record_id(u64 *record_id)
441{
442	struct apei_exec_context ctx;
443	int rc;
444
445	erst_exec_ctx_init(&ctx);
446	rc = apei_exec_run(&ctx, ACPI_ERST_GET_RECORD_ID);
447	if (rc)
448		return rc;
449	*record_id = apei_exec_ctx_get_output(&ctx);
450
451	return 0;
452}
453
454int erst_get_record_id_begin(int *pos)
455{
456	int rc;
457
458	if (erst_disable)
459		return -ENODEV;
460
461	rc = mutex_lock_interruptible(&erst_record_id_cache.lock);
462	if (rc)
463		return rc;
464	erst_record_id_cache.refcount++;
465	mutex_unlock(&erst_record_id_cache.lock);
466
467	*pos = 0;
468
469	return 0;
470}
471EXPORT_SYMBOL_GPL(erst_get_record_id_begin);
472
473/* erst_record_id_cache.lock must be held by caller */
474static int __erst_record_id_cache_add_one(void)
475{
476	u64 id, prev_id, first_id;
477	int i, rc;
478	u64 *entries;
479	unsigned long flags;
480
481	id = prev_id = first_id = APEI_ERST_INVALID_RECORD_ID;
482retry:
483	raw_spin_lock_irqsave(&erst_lock, flags);
484	rc = __erst_get_next_record_id(&id);
485	raw_spin_unlock_irqrestore(&erst_lock, flags);
486	if (rc == -ENOENT)
487		return 0;
488	if (rc)
489		return rc;
490	if (id == APEI_ERST_INVALID_RECORD_ID)
491		return 0;
492	/* can not skip current ID, or loop back to first ID */
493	if (id == prev_id || id == first_id)
494		return 0;
495	if (first_id == APEI_ERST_INVALID_RECORD_ID)
496		first_id = id;
497	prev_id = id;
498
499	entries = erst_record_id_cache.entries;
500	for (i = 0; i < erst_record_id_cache.len; i++) {
501		if (entries[i] == id)
502			break;
503	}
504	/* record id already in cache, try next */
505	if (i < erst_record_id_cache.len)
506		goto retry;
507	if (erst_record_id_cache.len >= erst_record_id_cache.size) {
508		int new_size;
509		u64 *new_entries;
510
511		new_size = erst_record_id_cache.size * 2;
512		new_size = clamp_val(new_size, ERST_RECORD_ID_CACHE_SIZE_MIN,
513				     ERST_RECORD_ID_CACHE_SIZE_MAX);
514		if (new_size <= erst_record_id_cache.size) {
515			if (printk_ratelimit())
516				pr_warn(FW_WARN "too many record IDs!\n");
517			return 0;
518		}
519		new_entries = kvmalloc_array(new_size, sizeof(entries[0]),
520					     GFP_KERNEL);
521		if (!new_entries)
522			return -ENOMEM;
523		memcpy(new_entries, entries,
524		       erst_record_id_cache.len * sizeof(entries[0]));
525		kvfree(entries);
526		erst_record_id_cache.entries = entries = new_entries;
527		erst_record_id_cache.size = new_size;
528	}
529	entries[i] = id;
530	erst_record_id_cache.len++;
531
532	return 1;
533}
534
535/*
536 * Get the record ID of an existing error record on the persistent
537 * storage. If there is no error record on the persistent storage, the
538 * returned record_id is APEI_ERST_INVALID_RECORD_ID.
539 */
540int erst_get_record_id_next(int *pos, u64 *record_id)
541{
542	int rc = 0;
543	u64 *entries;
544
545	if (erst_disable)
546		return -ENODEV;
547
548	/* must be enclosed by erst_get_record_id_begin/end */
549	BUG_ON(!erst_record_id_cache.refcount);
550	BUG_ON(*pos < 0 || *pos > erst_record_id_cache.len);
551
552	mutex_lock(&erst_record_id_cache.lock);
553	entries = erst_record_id_cache.entries;
554	for (; *pos < erst_record_id_cache.len; (*pos)++)
555		if (entries[*pos] != APEI_ERST_INVALID_RECORD_ID)
556			break;
557	/* found next record id in cache */
558	if (*pos < erst_record_id_cache.len) {
559		*record_id = entries[*pos];
560		(*pos)++;
561		goto out_unlock;
562	}
563
564	/* Try to add one more record ID to cache */
565	rc = __erst_record_id_cache_add_one();
566	if (rc < 0)
567		goto out_unlock;
568	/* successfully add one new ID */
569	if (rc == 1) {
570		*record_id = erst_record_id_cache.entries[*pos];
571		(*pos)++;
572		rc = 0;
573	} else {
574		*pos = -1;
575		*record_id = APEI_ERST_INVALID_RECORD_ID;
576	}
577out_unlock:
578	mutex_unlock(&erst_record_id_cache.lock);
579
580	return rc;
581}
582EXPORT_SYMBOL_GPL(erst_get_record_id_next);
583
584/* erst_record_id_cache.lock must be held by caller */
585static void __erst_record_id_cache_compact(void)
586{
587	int i, wpos = 0;
588	u64 *entries;
589
590	if (erst_record_id_cache.refcount)
591		return;
592
593	entries = erst_record_id_cache.entries;
594	for (i = 0; i < erst_record_id_cache.len; i++) {
595		if (entries[i] == APEI_ERST_INVALID_RECORD_ID)
596			continue;
597		if (wpos != i)
598			entries[wpos] = entries[i];
599		wpos++;
600	}
601	erst_record_id_cache.len = wpos;
602}
603
604void erst_get_record_id_end(void)
605{
606	/*
607	 * erst_disable != 0 should be detected by invoker via the
608	 * return value of erst_get_record_id_begin/next, so this
609	 * function should not be called for erst_disable != 0.
610	 */
611	BUG_ON(erst_disable);
612
613	mutex_lock(&erst_record_id_cache.lock);
614	erst_record_id_cache.refcount--;
615	BUG_ON(erst_record_id_cache.refcount < 0);
616	__erst_record_id_cache_compact();
617	mutex_unlock(&erst_record_id_cache.lock);
618}
619EXPORT_SYMBOL_GPL(erst_get_record_id_end);
620
621static int __erst_write_to_storage(u64 offset)
622{
623	struct apei_exec_context ctx;
624	u64 timeout = FIRMWARE_TIMEOUT;
625	u64 val;
626	int rc;
627
628	erst_exec_ctx_init(&ctx);
629	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_WRITE);
630	if (rc)
631		return rc;
632	apei_exec_ctx_set_input(&ctx, offset);
633	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_OFFSET);
634	if (rc)
635		return rc;
636	rc = apei_exec_run(&ctx, ACPI_ERST_EXECUTE_OPERATION);
637	if (rc)
638		return rc;
639	for (;;) {
640		rc = apei_exec_run(&ctx, ACPI_ERST_CHECK_BUSY_STATUS);
641		if (rc)
642			return rc;
643		val = apei_exec_ctx_get_output(&ctx);
644		if (!val)
645			break;
646		if (erst_timedout(&timeout, SPIN_UNIT))
647			return -EIO;
648	}
649	rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS);
650	if (rc)
651		return rc;
652	val = apei_exec_ctx_get_output(&ctx);
653	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
654	if (rc)
655		return rc;
656
657	return erst_errno(val);
658}
659
660static int __erst_read_from_storage(u64 record_id, u64 offset)
661{
662	struct apei_exec_context ctx;
663	u64 timeout = FIRMWARE_TIMEOUT;
664	u64 val;
665	int rc;
666
667	erst_exec_ctx_init(&ctx);
668	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_READ);
669	if (rc)
670		return rc;
671	apei_exec_ctx_set_input(&ctx, offset);
672	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_OFFSET);
673	if (rc)
674		return rc;
675	apei_exec_ctx_set_input(&ctx, record_id);
676	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_ID);
677	if (rc)
678		return rc;
679	rc = apei_exec_run(&ctx, ACPI_ERST_EXECUTE_OPERATION);
680	if (rc)
681		return rc;
682	for (;;) {
683		rc = apei_exec_run(&ctx, ACPI_ERST_CHECK_BUSY_STATUS);
684		if (rc)
685			return rc;
686		val = apei_exec_ctx_get_output(&ctx);
687		if (!val)
688			break;
689		if (erst_timedout(&timeout, SPIN_UNIT))
690			return -EIO;
691	};
692	rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS);
693	if (rc)
694		return rc;
695	val = apei_exec_ctx_get_output(&ctx);
696	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
697	if (rc)
698		return rc;
699
700	return erst_errno(val);
701}
702
703static int __erst_clear_from_storage(u64 record_id)
704{
705	struct apei_exec_context ctx;
706	u64 timeout = FIRMWARE_TIMEOUT;
707	u64 val;
708	int rc;
709
710	erst_exec_ctx_init(&ctx);
711	rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_CLEAR);
712	if (rc)
713		return rc;
714	apei_exec_ctx_set_input(&ctx, record_id);
715	rc = apei_exec_run(&ctx, ACPI_ERST_SET_RECORD_ID);
716	if (rc)
717		return rc;
718	rc = apei_exec_run(&ctx, ACPI_ERST_EXECUTE_OPERATION);
719	if (rc)
720		return rc;
721	for (;;) {
722		rc = apei_exec_run(&ctx, ACPI_ERST_CHECK_BUSY_STATUS);
723		if (rc)
724			return rc;
725		val = apei_exec_ctx_get_output(&ctx);
726		if (!val)
727			break;
728		if (erst_timedout(&timeout, SPIN_UNIT))
729			return -EIO;
730	}
731	rc = apei_exec_run(&ctx, ACPI_ERST_GET_COMMAND_STATUS);
732	if (rc)
733		return rc;
734	val = apei_exec_ctx_get_output(&ctx);
735	rc = apei_exec_run_optional(&ctx, ACPI_ERST_END);
736	if (rc)
737		return rc;
738
739	return erst_errno(val);
740}
741
742/* NVRAM ERST Error Log Address Range is not supported yet */
743static void pr_unimpl_nvram(void)
744{
745	if (printk_ratelimit())
746		pr_warn("NVRAM ERST Log Address Range not implemented yet.\n");
747}
748
749static int __erst_write_to_nvram(const struct cper_record_header *record)
750{
751	/* do not print message, because printk is not safe for NMI */
752	return -ENOSYS;
753}
754
755static int __erst_read_to_erange_from_nvram(u64 record_id, u64 *offset)
756{
757	pr_unimpl_nvram();
758	return -ENOSYS;
759}
760
761static int __erst_clear_from_nvram(u64 record_id)
762{
763	pr_unimpl_nvram();
764	return -ENOSYS;
765}
766
767int erst_write(const struct cper_record_header *record)
768{
769	int rc;
770	unsigned long flags;
771	struct cper_record_header *rcd_erange;
772
773	if (erst_disable)
774		return -ENODEV;
775
776	if (memcmp(record->signature, CPER_SIG_RECORD, CPER_SIG_SIZE))
777		return -EINVAL;
778
779	if (erst_erange.attr & ERST_RANGE_NVRAM) {
780		if (!raw_spin_trylock_irqsave(&erst_lock, flags))
781			return -EBUSY;
782		rc = __erst_write_to_nvram(record);
783		raw_spin_unlock_irqrestore(&erst_lock, flags);
784		return rc;
785	}
786
787	if (record->record_length > erst_erange.size)
788		return -EINVAL;
789
790	if (!raw_spin_trylock_irqsave(&erst_lock, flags))
791		return -EBUSY;
792	memcpy(erst_erange.vaddr, record, record->record_length);
793	rcd_erange = erst_erange.vaddr;
794	/* signature for serialization system */
795	memcpy(&rcd_erange->persistence_information, "ER", 2);
796
797	rc = __erst_write_to_storage(0);
798	raw_spin_unlock_irqrestore(&erst_lock, flags);
799
800	return rc;
801}
802EXPORT_SYMBOL_GPL(erst_write);
803
804static int __erst_read_to_erange(u64 record_id, u64 *offset)
805{
806	int rc;
807
808	if (erst_erange.attr & ERST_RANGE_NVRAM)
809		return __erst_read_to_erange_from_nvram(
810			record_id, offset);
811
812	rc = __erst_read_from_storage(record_id, 0);
813	if (rc)
814		return rc;
815	*offset = 0;
816
817	return 0;
818}
819
820static ssize_t __erst_read(u64 record_id, struct cper_record_header *record,
821			   size_t buflen)
822{
823	int rc;
824	u64 offset, len = 0;
825	struct cper_record_header *rcd_tmp;
826
827	rc = __erst_read_to_erange(record_id, &offset);
828	if (rc)
829		return rc;
830	rcd_tmp = erst_erange.vaddr + offset;
831	len = rcd_tmp->record_length;
832	if (len <= buflen)
833		memcpy(record, rcd_tmp, len);
834
835	return len;
836}
837
838/*
839 * If return value > buflen, the buffer size is not big enough,
840 * else if return value < 0, something goes wrong,
841 * else everything is OK, and return value is record length
842 */
843ssize_t erst_read(u64 record_id, struct cper_record_header *record,
844		  size_t buflen)
845{
846	ssize_t len;
847	unsigned long flags;
848
849	if (erst_disable)
850		return -ENODEV;
851
852	raw_spin_lock_irqsave(&erst_lock, flags);
853	len = __erst_read(record_id, record, buflen);
854	raw_spin_unlock_irqrestore(&erst_lock, flags);
855	return len;
856}
857EXPORT_SYMBOL_GPL(erst_read);
858
859int erst_clear(u64 record_id)
860{
861	int rc, i;
862	unsigned long flags;
863	u64 *entries;
864
865	if (erst_disable)
866		return -ENODEV;
867
868	rc = mutex_lock_interruptible(&erst_record_id_cache.lock);
869	if (rc)
870		return rc;
871	raw_spin_lock_irqsave(&erst_lock, flags);
872	if (erst_erange.attr & ERST_RANGE_NVRAM)
873		rc = __erst_clear_from_nvram(record_id);
874	else
875		rc = __erst_clear_from_storage(record_id);
876	raw_spin_unlock_irqrestore(&erst_lock, flags);
877	if (rc)
878		goto out;
879	entries = erst_record_id_cache.entries;
880	for (i = 0; i < erst_record_id_cache.len; i++) {
881		if (entries[i] == record_id)
882			entries[i] = APEI_ERST_INVALID_RECORD_ID;
883	}
884	__erst_record_id_cache_compact();
885out:
886	mutex_unlock(&erst_record_id_cache.lock);
887	return rc;
888}
889EXPORT_SYMBOL_GPL(erst_clear);
890
891static int __init setup_erst_disable(char *str)
892{
893	erst_disable = 1;
894	return 1;
895}
896
897__setup("erst_disable", setup_erst_disable);
898
899static int erst_check_table(struct acpi_table_erst *erst_tab)
900{
901	if ((erst_tab->header_length !=
902	     (sizeof(struct acpi_table_erst) - sizeof(erst_tab->header)))
903	    && (erst_tab->header_length != sizeof(struct acpi_table_erst)))
904		return -EINVAL;
905	if (erst_tab->header.length < sizeof(struct acpi_table_erst))
906		return -EINVAL;
907	if (erst_tab->entries !=
908	    (erst_tab->header.length - sizeof(struct acpi_table_erst)) /
909	    sizeof(struct acpi_erst_entry))
910		return -EINVAL;
911
912	return 0;
913}
914
915static int erst_open_pstore(struct pstore_info *psi);
916static int erst_close_pstore(struct pstore_info *psi);
917static ssize_t erst_reader(struct pstore_record *record);
918static int erst_writer(struct pstore_record *record);
919static int erst_clearer(struct pstore_record *record);
920
921static struct pstore_info erst_info = {
922	.owner		= THIS_MODULE,
923	.name		= "erst",
924	.flags		= PSTORE_FLAGS_DMESG,
925	.open		= erst_open_pstore,
926	.close		= erst_close_pstore,
927	.read		= erst_reader,
928	.write		= erst_writer,
929	.erase		= erst_clearer
930};
931
932#define CPER_CREATOR_PSTORE						\
933	GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c,	\
934		  0x64, 0x90, 0xb8, 0x9d)
935#define CPER_SECTION_TYPE_DMESG						\
936	GUID_INIT(0xc197e04e, 0xd545, 0x4a70, 0x9c, 0x17, 0xa5, 0x54,	\
937		  0x94, 0x19, 0xeb, 0x12)
938#define CPER_SECTION_TYPE_DMESG_Z					\
939	GUID_INIT(0x4f118707, 0x04dd, 0x4055, 0xb5, 0xdd, 0x95, 0x6d,	\
940		  0x34, 0xdd, 0xfa, 0xc6)
941#define CPER_SECTION_TYPE_MCE						\
942	GUID_INIT(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96,	\
943		  0x04, 0x4a, 0x38, 0xfc)
944
945struct cper_pstore_record {
946	struct cper_record_header hdr;
947	struct cper_section_descriptor sec_hdr;
948	char data[];
949} __packed;
950
951static int reader_pos;
952
953static int erst_open_pstore(struct pstore_info *psi)
954{
955	int rc;
956
957	if (erst_disable)
958		return -ENODEV;
959
960	rc = erst_get_record_id_begin(&reader_pos);
961
962	return rc;
963}
964
965static int erst_close_pstore(struct pstore_info *psi)
966{
967	erst_get_record_id_end();
968
969	return 0;
970}
971
972static ssize_t erst_reader(struct pstore_record *record)
973{
974	int rc;
975	ssize_t len = 0;
976	u64 record_id;
977	struct cper_pstore_record *rcd;
978	size_t rcd_len = sizeof(*rcd) + erst_info.bufsize;
979
980	if (erst_disable)
981		return -ENODEV;
982
983	rcd = kmalloc(rcd_len, GFP_KERNEL);
984	if (!rcd) {
985		rc = -ENOMEM;
986		goto out;
987	}
988skip:
989	rc = erst_get_record_id_next(&reader_pos, &record_id);
990	if (rc)
991		goto out;
992
993	/* no more record */
994	if (record_id == APEI_ERST_INVALID_RECORD_ID) {
995		rc = -EINVAL;
996		goto out;
997	}
998
999	len = erst_read(record_id, &rcd->hdr, rcd_len);
1000	/* The record may be cleared by others, try read next record */
1001	if (len == -ENOENT)
1002		goto skip;
1003	else if (len < 0 || len < sizeof(*rcd)) {
1004		rc = -EIO;
1005		goto out;
1006	}
1007	if (!guid_equal(&rcd->hdr.creator_id, &CPER_CREATOR_PSTORE))
1008		goto skip;
1009
1010	record->buf = kmalloc(len, GFP_KERNEL);
1011	if (record->buf == NULL) {
1012		rc = -ENOMEM;
1013		goto out;
1014	}
1015	memcpy(record->buf, rcd->data, len - sizeof(*rcd));
1016	record->id = record_id;
1017	record->compressed = false;
1018	record->ecc_notice_size = 0;
1019	if (guid_equal(&rcd->sec_hdr.section_type, &CPER_SECTION_TYPE_DMESG_Z)) {
1020		record->type = PSTORE_TYPE_DMESG;
1021		record->compressed = true;
1022	} else if (guid_equal(&rcd->sec_hdr.section_type, &CPER_SECTION_TYPE_DMESG))
1023		record->type = PSTORE_TYPE_DMESG;
1024	else if (guid_equal(&rcd->sec_hdr.section_type, &CPER_SECTION_TYPE_MCE))
1025		record->type = PSTORE_TYPE_MCE;
1026	else
1027		record->type = PSTORE_TYPE_MAX;
1028
1029	if (rcd->hdr.validation_bits & CPER_VALID_TIMESTAMP)
1030		record->time.tv_sec = rcd->hdr.timestamp;
1031	else
1032		record->time.tv_sec = 0;
1033	record->time.tv_nsec = 0;
1034
1035out:
1036	kfree(rcd);
1037	return (rc < 0) ? rc : (len - sizeof(*rcd));
1038}
1039
1040static int erst_writer(struct pstore_record *record)
1041{
1042	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
1043					(erst_info.buf - sizeof(*rcd));
1044	int ret;
1045
1046	memset(rcd, 0, sizeof(*rcd));
1047	memcpy(rcd->hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE);
1048	rcd->hdr.revision = CPER_RECORD_REV;
1049	rcd->hdr.signature_end = CPER_SIG_END;
1050	rcd->hdr.section_count = 1;
1051	rcd->hdr.error_severity = CPER_SEV_FATAL;
1052	/* timestamp valid. platform_id, partition_id are invalid */
1053	rcd->hdr.validation_bits = CPER_VALID_TIMESTAMP;
1054	rcd->hdr.timestamp = ktime_get_real_seconds();
1055	rcd->hdr.record_length = sizeof(*rcd) + record->size;
1056	rcd->hdr.creator_id = CPER_CREATOR_PSTORE;
1057	rcd->hdr.notification_type = CPER_NOTIFY_MCE;
1058	rcd->hdr.record_id = cper_next_record_id();
1059	rcd->hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR;
1060
1061	rcd->sec_hdr.section_offset = sizeof(*rcd);
1062	rcd->sec_hdr.section_length = record->size;
1063	rcd->sec_hdr.revision = CPER_SEC_REV;
1064	/* fru_id and fru_text is invalid */
1065	rcd->sec_hdr.validation_bits = 0;
1066	rcd->sec_hdr.flags = CPER_SEC_PRIMARY;
1067	switch (record->type) {
1068	case PSTORE_TYPE_DMESG:
1069		if (record->compressed)
1070			rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG_Z;
1071		else
1072			rcd->sec_hdr.section_type = CPER_SECTION_TYPE_DMESG;
1073		break;
1074	case PSTORE_TYPE_MCE:
1075		rcd->sec_hdr.section_type = CPER_SECTION_TYPE_MCE;
1076		break;
1077	default:
1078		return -EINVAL;
1079	}
1080	rcd->sec_hdr.section_severity = CPER_SEV_FATAL;
1081
1082	ret = erst_write(&rcd->hdr);
1083	record->id = rcd->hdr.record_id;
1084
1085	return ret;
1086}
1087
1088static int erst_clearer(struct pstore_record *record)
1089{
1090	return erst_clear(record->id);
1091}
1092
1093static int __init erst_init(void)
1094{
1095	int rc = 0;
1096	acpi_status status;
1097	struct apei_exec_context ctx;
1098	struct apei_resources erst_resources;
1099	struct resource *r;
1100	char *buf;
1101
1102	if (acpi_disabled)
1103		goto err;
1104
1105	if (erst_disable) {
1106		pr_info(
1107	"Error Record Serialization Table (ERST) support is disabled.\n");
1108		goto err;
1109	}
1110
1111	status = acpi_get_table(ACPI_SIG_ERST, 0,
1112				(struct acpi_table_header **)&erst_tab);
1113	if (status == AE_NOT_FOUND)
1114		goto err;
1115	else if (ACPI_FAILURE(status)) {
1116		const char *msg = acpi_format_exception(status);
1117		pr_err("Failed to get table, %s\n", msg);
1118		rc = -EINVAL;
1119		goto err;
1120	}
1121
1122	rc = erst_check_table(erst_tab);
1123	if (rc) {
1124		pr_err(FW_BUG "ERST table is invalid.\n");
1125		goto err_put_erst_tab;
1126	}
1127
1128	apei_resources_init(&erst_resources);
1129	erst_exec_ctx_init(&ctx);
1130	rc = apei_exec_collect_resources(&ctx, &erst_resources);
1131	if (rc)
1132		goto err_fini;
1133	rc = apei_resources_request(&erst_resources, "APEI ERST");
1134	if (rc)
1135		goto err_fini;
1136	rc = apei_exec_pre_map_gars(&ctx);
1137	if (rc)
1138		goto err_release;
1139	rc = erst_get_erange(&erst_erange);
1140	if (rc) {
1141		if (rc == -ENODEV)
1142			pr_info(
1143	"The corresponding hardware device or firmware implementation "
1144	"is not available.\n");
1145		else
1146			pr_err("Failed to get Error Log Address Range.\n");
1147		goto err_unmap_reg;
1148	}
1149
1150	r = request_mem_region(erst_erange.base, erst_erange.size, "APEI ERST");
1151	if (!r) {
1152		pr_err("Can not request [mem %#010llx-%#010llx] for ERST.\n",
1153		       (unsigned long long)erst_erange.base,
1154		       (unsigned long long)erst_erange.base + erst_erange.size - 1);
1155		rc = -EIO;
1156		goto err_unmap_reg;
1157	}
1158	rc = -ENOMEM;
1159	erst_erange.vaddr = ioremap_cache(erst_erange.base,
1160					  erst_erange.size);
1161	if (!erst_erange.vaddr)
1162		goto err_release_erange;
1163
1164	pr_info(
1165	"Error Record Serialization Table (ERST) support is initialized.\n");
1166
1167	buf = kmalloc(erst_erange.size, GFP_KERNEL);
1168	if (buf) {
1169		erst_info.buf = buf + sizeof(struct cper_pstore_record);
1170		erst_info.bufsize = erst_erange.size -
1171				    sizeof(struct cper_pstore_record);
1172		rc = pstore_register(&erst_info);
1173		if (rc) {
1174			if (rc != -EPERM)
1175				pr_info(
1176				"Could not register with persistent store.\n");
1177			erst_info.buf = NULL;
1178			erst_info.bufsize = 0;
1179			kfree(buf);
1180		}
1181	} else
1182		pr_err(
1183		"Failed to allocate %lld bytes for persistent store error log.\n",
1184		erst_erange.size);
1185
1186	/* Cleanup ERST Resources */
1187	apei_resources_fini(&erst_resources);
1188
1189	return 0;
1190
1191err_release_erange:
1192	release_mem_region(erst_erange.base, erst_erange.size);
1193err_unmap_reg:
1194	apei_exec_post_unmap_gars(&ctx);
1195err_release:
1196	apei_resources_release(&erst_resources);
1197err_fini:
1198	apei_resources_fini(&erst_resources);
1199err_put_erst_tab:
1200	acpi_put_table((struct acpi_table_header *)erst_tab);
1201err:
1202	erst_disable = 1;
1203	return rc;
1204}
1205
1206device_initcall(erst_init);
1207