summaryrefslogtreecommitdiff
path: root/drivers/acpi/acpi_extlog.c
blob: a99d4a6156dcacaab5770fce845f88a2fa7a7766 (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
/*
 * Extended Error Log driver
 *
 * Copyright (C) 2013 Intel Corp.
 * Author: Chen, Gong <gong.chen@intel.com>
 *
 * This file is licensed under GPLv2.
 */

#include <linux/module.h>
#include <linux/acpi.h>
#include <linux/cper.h>
#include <linux/ratelimit.h>
#include <linux/edac.h>
#include <linux/ras.h>
#include <asm/cpu.h>
#include <asm/mce.h>

#include "apei/apei-internal.h"
#include <ras/ras_event.h>

#define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */

#define EXTLOG_DSM_REV		0x0
#define	EXTLOG_FN_ADDR		0x1

#define FLAG_OS_OPTIN		BIT(0)
#define ELOG_ENTRY_VALID	(1ULL<<63)
#define ELOG_ENTRY_LEN		0x1000

#define EMCA_BUG \
	"Can not request iomem region <0x%016llx-0x%016llx> - eMCA disabled\n"

struct extlog_l1_head {
	u32 ver;	/* Header Version */
	u32 hdr_len;	/* Header Length */
	u64 total_len;	/* entire L1 Directory length including this header */
	u64 elog_base;	/* MCA Error Log Directory base address */
	u64 elog_len;	/* MCA Error Log Directory length */
	u32 flags;	/* bit 0 - OS/VMM Opt-in */
	u8  rev0[12];
	u32 entries;	/* Valid L1 Directory entries per logical processor */
	u8  rev1[12];
};

static int old_edac_report_status;

static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";

/* L1 table related physical address */
static u64 elog_base;
static size_t elog_size;
static u64 l1_dirbase;
static size_t l1_size;

/* L1 table related virtual address */
static void __iomem *extlog_l1_addr;
static void __iomem *elog_addr;

static void *elog_buf;

static u64 *l1_entry_base;
static u32 l1_percpu_entry;

#define ELOG_IDX(cpu, bank) \
	(cpu_physical_id(cpu) * l1_percpu_entry + (bank))

#define ELOG_ENTRY_DATA(idx) \
	(*(l1_entry_base + (idx)))

#define ELOG_ENTRY_ADDR(phyaddr) \
	(phyaddr - elog_base + (u8 *)elog_addr)

static struct acpi_generic_status *extlog_elog_entry_check(int cpu, int bank)
{
	int idx;
	u64 data;
	struct acpi_generic_status *estatus;

	WARN_ON(cpu < 0);
	idx = ELOG_IDX(cpu, bank);
	data = ELOG_ENTRY_DATA(idx);
	if ((data & ELOG_ENTRY_VALID) == 0)
		return NULL;

	data &= EXT_ELOG_ENTRY_MASK;
	estatus = (struct acpi_generic_status *)ELOG_ENTRY_ADDR(data);

	/* if no valid data in elog entry, just return */
	if (estatus->block_status == 0)
		return NULL;

	return estatus;
}

static void __print_extlog_rcd(const char *pfx,
			       struct acpi_generic_status *estatus, int cpu)
{
	static atomic_t seqno;
	unsigned int curr_seqno;
	char pfx_seq[64];

	if (!pfx) {
		if (estatus->error_severity <= CPER_SEV_CORRECTED)
			pfx = KERN_INFO;
		else
			pfx = KERN_ERR;
	}
	curr_seqno = atomic_inc_return(&seqno);
	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}", pfx, curr_seqno);
	printk("%s""Hardware error detected on CPU%d\n", pfx_seq, cpu);
	cper_estatus_print(pfx_seq, estatus);
}

static int print_extlog_rcd(const char *pfx,
			    struct acpi_generic_status *estatus, int cpu)
{
	/* Not more than 2 messages every 5 seconds */
	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
	static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2);
	struct ratelimit_state *ratelimit;

	if (estatus->error_severity == CPER_SEV_CORRECTED ||
	    (estatus->error_severity == CPER_SEV_INFORMATIONAL))
		ratelimit = &ratelimit_corrected;
	else
		ratelimit = &ratelimit_uncorrected;
	if (__ratelimit(ratelimit)) {
		__print_extlog_rcd(pfx, estatus, cpu);
		return 0;
	}

	return 1;
}

static int extlog_print(struct notifier_block *nb, unsigned long val,
			void *data)
{
	struct mce *mce = (struct mce *)data;
	int	bank = mce->bank;
	int	cpu = mce->extcpu;
	struct acpi_generic_status *estatus, *tmp;
	struct acpi_generic_data *gdata;
	const uuid_le *fru_id = &NULL_UUID_LE;
	char *fru_text = "";
	uuid_le *sec_type;
	static u32 err_seq;

	estatus = extlog_elog_entry_check(cpu, bank);
	if (estatus == NULL)
		return NOTIFY_DONE;

	memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
	/* clear record status to enable BIOS to update it again */
	estatus->block_status = 0;

	tmp = (struct acpi_generic_status *)elog_buf;

	if (!ras_userspace_consumers()) {
		print_extlog_rcd(NULL, tmp, cpu);
		goto out;
	}

	/* log event via trace */
	err_seq++;
	gdata = (struct acpi_generic_data *)(tmp + 1);
	if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
		fru_id = (uuid_le *)gdata->fru_id;
	if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
		fru_text = gdata->fru_text;
	sec_type = (uuid_le *)gdata->section_type;
	if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
		struct cper_sec_mem_err *mem = (void *)(gdata + 1);
		if (gdata->error_data_length >= sizeof(*mem))
			trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
					       (u8)gdata->error_severity);
	}

out:
	return NOTIFY_STOP;
}

static bool __init extlog_get_l1addr(void)
{
	u8 uuid[16];
	acpi_handle handle;
	union acpi_object *obj;

	acpi_str_to_uuid(extlog_dsm_uuid, uuid);

	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
		return false;
	if (!acpi_check_dsm(handle, uuid, EXTLOG_DSM_REV, 1 << EXTLOG_FN_ADDR))
		return false;
	obj = acpi_evaluate_dsm_typed(handle, uuid, EXTLOG_DSM_REV,
				      EXTLOG_FN_ADDR, NULL, ACPI_TYPE_INTEGER);
	if (!obj) {
		return false;
	} else {
		l1_dirbase = obj->integer.value;
		ACPI_FREE(obj);
	}

	/* Spec says L1 directory must be 4K aligned, bail out if it isn't */
	if (l1_dirbase & ((1 << 12) - 1)) {
		pr_warn(FW_BUG "L1 Directory is invalid at physical %llx\n",
			l1_dirbase);
		return false;
	}

	return true;
}
static struct notifier_block extlog_mce_dec = {
	.notifier_call	= extlog_print,
};

static int __init extlog_init(void)
{
	struct extlog_l1_head *l1_head;
	void __iomem *extlog_l1_hdr;
	size_t l1_hdr_size;
	struct resource *r;
	u64 cap;
	int rc;

	if (get_edac_report_status() == EDAC_REPORTING_FORCE) {
		pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n");
		return -EPERM;
	}

	rc = -ENODEV;
	rdmsrl(MSR_IA32_MCG_CAP, cap);
	if (!(cap & MCG_ELOG_P))
		return rc;

	if (!extlog_get_l1addr())
		return rc;

	rc = -EINVAL;
	/* get L1 header to fetch necessary information */
	l1_hdr_size = sizeof(struct extlog_l1_head);
	r = request_mem_region(l1_dirbase, l1_hdr_size, "L1 DIR HDR");
	if (!r) {
		pr_warn(FW_BUG EMCA_BUG,
			(unsigned long long)l1_dirbase,
			(unsigned long long)l1_dirbase + l1_hdr_size);
		goto err;
	}

	extlog_l1_hdr = acpi_os_map_iomem(l1_dirbase, l1_hdr_size);
	l1_head = (struct extlog_l1_head *)extlog_l1_hdr;
	l1_size = l1_head->total_len;
	l1_percpu_entry = l1_head->entries;
	elog_base = l1_head->elog_base;
	elog_size = l1_head->elog_len;
	acpi_os_unmap_iomem(extlog_l1_hdr, l1_hdr_size);
	release_mem_region(l1_dirbase, l1_hdr_size);

	/* remap L1 header again based on completed information */
	r = request_mem_region(l1_dirbase, l1_size, "L1 Table");
	if (!r) {
		pr_warn(FW_BUG EMCA_BUG,
			(unsigned long long)l1_dirbase,
			(unsigned long long)l1_dirbase + l1_size);
		goto err;
	}
	extlog_l1_addr = acpi_os_map_iomem(l1_dirbase, l1_size);
	l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size);

	/* remap elog table */
	r = request_mem_region(elog_base, elog_size, "Elog Table");
	if (!r) {
		pr_warn(FW_BUG EMCA_BUG,
			(unsigned long long)elog_base,
			(unsigned long long)elog_base + elog_size);
		goto err_release_l1_dir;
	}
	elog_addr = acpi_os_map_iomem(elog_base, elog_size);

	rc = -ENOMEM;
	/* allocate buffer to save elog record */
	elog_buf = kmalloc(ELOG_ENTRY_LEN, GFP_KERNEL);
	if (elog_buf == NULL)
		goto err_release_elog;

	/*
	 * eMCA event report method has higher priority than EDAC method,
	 * unless EDAC event report method is mandatory.
	 */
	old_edac_report_status = get_edac_report_status();
	set_edac_report_status(EDAC_REPORTING_DISABLED);
	mce_register_decode_chain(&extlog_mce_dec);
	/* enable OS to be involved to take over management from BIOS */
	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;

	return 0;

err_release_elog:
	if (elog_addr)
		acpi_os_unmap_iomem(elog_addr, elog_size);
	release_mem_region(elog_base, elog_size);
err_release_l1_dir:
	if (extlog_l1_addr)
		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
	release_mem_region(l1_dirbase, l1_size);
err:
	pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n");
	return rc;
}

static void __exit extlog_exit(void)
{
	set_edac_report_status(old_edac_report_status);
	mce_unregister_decode_chain(&extlog_mce_dec);
	((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
	if (extlog_l1_addr)
		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
	if (elog_addr)
		acpi_os_unmap_iomem(elog_addr, elog_size);
	release_mem_region(elog_base, elog_size);
	release_mem_region(l1_dirbase, l1_size);
	kfree(elog_buf);
}

module_init(extlog_init);
module_exit(extlog_exit);

MODULE_AUTHOR("Chen, Gong <gong.chen@intel.com>");
MODULE_DESCRIPTION("Extended MCA Error Log Driver");
MODULE_LICENSE("GPL");