summaryrefslogtreecommitdiff
path: root/kernel/printk/nmi.c
blob: 16bab471c7e23d8099eebca1c897ccb6a09f6bdf (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
/*
 * nmi.c - Safe printk in NMI context
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version 2
 * of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/preempt.h>
#include <linux/spinlock.h>
#include <linux/debug_locks.h>
#include <linux/smp.h>
#include <linux/cpumask.h>
#include <linux/irq_work.h>
#include <linux/printk.h>

#include "internal.h"

/*
 * printk() could not take logbuf_lock in NMI context. Instead,
 * it uses an alternative implementation that temporary stores
 * the strings into a per-CPU buffer. The content of the buffer
 * is later flushed into the main ring buffer via IRQ work.
 *
 * The alternative implementation is chosen transparently
 * via @printk_func per-CPU variable.
 *
 * The implementation allows to flush the strings also from another CPU.
 * There are situations when we want to make sure that all buffers
 * were handled or when IRQs are blocked.
 */
DEFINE_PER_CPU(printk_func_t, printk_func) = vprintk_default;
static int printk_nmi_irq_ready;
atomic_t nmi_message_lost;

#define NMI_LOG_BUF_LEN ((1 << CONFIG_NMI_LOG_BUF_SHIFT) -		\
			 sizeof(atomic_t) - sizeof(struct irq_work))

struct nmi_seq_buf {
	atomic_t		len;	/* length of written data */
	struct irq_work		work;	/* IRQ work that flushes the buffer */
	unsigned char		buffer[NMI_LOG_BUF_LEN];
};
static DEFINE_PER_CPU(struct nmi_seq_buf, nmi_print_seq);

/*
 * Safe printk() for NMI context. It uses a per-CPU buffer to
 * store the message. NMIs are not nested, so there is always only
 * one writer running. But the buffer might get flushed from another
 * CPU, so we need to be careful.
 */
static int vprintk_nmi(const char *fmt, va_list args)
{
	struct nmi_seq_buf *s = this_cpu_ptr(&nmi_print_seq);
	int add = 0;
	size_t len;

again:
	len = atomic_read(&s->len);

	if (len >= sizeof(s->buffer)) {
		atomic_inc(&nmi_message_lost);
		return 0;
	}

	/*
	 * Make sure that all old data have been read before the buffer was
	 * reseted. This is not needed when we just append data.
	 */
	if (!len)
		smp_rmb();

	add = vsnprintf(s->buffer + len, sizeof(s->buffer) - len, fmt, args);

	/*
	 * Do it once again if the buffer has been flushed in the meantime.
	 * Note that atomic_cmpxchg() is an implicit memory barrier that
	 * makes sure that the data were written before updating s->len.
	 */
	if (atomic_cmpxchg(&s->len, len, len + add) != len)
		goto again;

	/* Get flushed in a more safe context. */
	if (add && printk_nmi_irq_ready) {
		/* Make sure that IRQ work is really initialized. */
		smp_rmb();
		irq_work_queue(&s->work);
	}

	return add;
}

static void printk_nmi_flush_line(const char *text, int len)
{
	/*
	 * The buffers are flushed in NMI only on panic.  The messages must
	 * go only into the ring buffer at this stage.  Consoles will get
	 * explicitly called later when a crashdump is not generated.
	 */
	if (in_nmi())
		printk_deferred("%.*s", len, text);
	else
		printk("%.*s", len, text);

}

/*
 * printk one line from the temporary buffer from @start index until
 * and including the @end index.
 */
static void printk_nmi_flush_seq_line(struct nmi_seq_buf *s,
					int start, int end)
{
	const char *buf = s->buffer + start;

	printk_nmi_flush_line(buf, (end - start) + 1);
}

/*
 * Flush data from the associated per_CPU buffer. The function
 * can be called either via IRQ work or independently.
 */
static void __printk_nmi_flush(struct irq_work *work)
{
	static raw_spinlock_t read_lock =
		__RAW_SPIN_LOCK_INITIALIZER(read_lock);
	struct nmi_seq_buf *s = container_of(work, struct nmi_seq_buf, work);
	unsigned long flags;
	size_t len, size;
	int i, last_i;

	/*
	 * The lock has two functions. First, one reader has to flush all
	 * available message to make the lockless synchronization with
	 * writers easier. Second, we do not want to mix messages from
	 * different CPUs. This is especially important when printing
	 * a backtrace.
	 */
	raw_spin_lock_irqsave(&read_lock, flags);

	i = 0;
more:
	len = atomic_read(&s->len);

	/*
	 * This is just a paranoid check that nobody has manipulated
	 * the buffer an unexpected way. If we printed something then
	 * @len must only increase.
	 */
	if (i && i >= len) {
		const char *msg = "printk_nmi_flush: internal error\n";

		printk_nmi_flush_line(msg, strlen(msg));
	}

	if (!len)
		goto out; /* Someone else has already flushed the buffer. */

	/* Make sure that data has been written up to the @len */
	smp_rmb();

	size = min(len, sizeof(s->buffer));
	last_i = i;

	/* Print line by line. */
	for (; i < size; i++) {
		if (s->buffer[i] == '\n') {
			printk_nmi_flush_seq_line(s, last_i, i);
			last_i = i + 1;
		}
	}
	/* Check if there was a partial line. */
	if (last_i < size) {
		printk_nmi_flush_seq_line(s, last_i, size - 1);
		printk_nmi_flush_line("\n", strlen("\n"));
	}

	/*
	 * Check that nothing has got added in the meantime and truncate
	 * the buffer. Note that atomic_cmpxchg() is an implicit memory
	 * barrier that makes sure that the data were copied before
	 * updating s->len.
	 */
	if (atomic_cmpxchg(&s->len, len, 0) != len)
		goto more;

out:
	raw_spin_unlock_irqrestore(&read_lock, flags);
}

/**
 * printk_nmi_flush - flush all per-cpu nmi buffers.
 *
 * The buffers are flushed automatically via IRQ work. This function
 * is useful only when someone wants to be sure that all buffers have
 * been flushed at some point.
 */
void printk_nmi_flush(void)
{
	int cpu;

	for_each_possible_cpu(cpu)
		__printk_nmi_flush(&per_cpu(nmi_print_seq, cpu).work);
}

/**
 * printk_nmi_flush_on_panic - flush all per-cpu nmi buffers when the system
 *	goes down.
 *
 * Similar to printk_nmi_flush() but it can be called even in NMI context when
 * the system goes down. It does the best effort to get NMI messages into
 * the main ring buffer.
 *
 * Note that it could try harder when there is only one CPU online.
 */
void printk_nmi_flush_on_panic(void)
{
	/*
	 * Make sure that we could access the main ring buffer.
	 * Do not risk a double release when more CPUs are up.
	 */
	if (in_nmi() && raw_spin_is_locked(&logbuf_lock)) {
		if (num_online_cpus() > 1)
			return;

		debug_locks_off();
		raw_spin_lock_init(&logbuf_lock);
	}

	printk_nmi_flush();
}

void __init printk_nmi_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		struct nmi_seq_buf *s = &per_cpu(nmi_print_seq, cpu);

		init_irq_work(&s->work, __printk_nmi_flush);
	}

	/* Make sure that IRQ works are initialized before enabling. */
	smp_wmb();
	printk_nmi_irq_ready = 1;

	/* Flush pending messages that did not have scheduled IRQ works. */
	printk_nmi_flush();
}

void printk_nmi_enter(void)
{
	this_cpu_write(printk_func, vprintk_nmi);
}

void printk_nmi_exit(void)
{
	this_cpu_write(printk_func, vprintk_default);
}