aboutsummaryrefslogtreecommitdiff
path: root/block/blk-timeout.c
blob: 652d4d4d3e9726855bfb73d185ed9c44cad0a63f (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
/*
 * Functions related to generic timeout handling of requests.
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/fault-inject.h>

#include "blk.h"
#include "blk-mq.h"

#ifdef CONFIG_FAIL_IO_TIMEOUT

static DECLARE_FAULT_ATTR(fail_io_timeout);

static int __init setup_fail_io_timeout(char *str)
{
	return setup_fault_attr(&fail_io_timeout, str);
}
__setup("fail_io_timeout=", setup_fail_io_timeout);

int blk_should_fake_timeout(struct request_queue *q)
{
	if (!test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags))
		return 0;

	return should_fail(&fail_io_timeout, 1);
}

static int __init fail_io_timeout_debugfs(void)
{
	struct dentry *dir = fault_create_debugfs_attr("fail_io_timeout",
						NULL, &fail_io_timeout);

	return PTR_ERR_OR_ZERO(dir);
}

late_initcall(fail_io_timeout_debugfs);

ssize_t part_timeout_show(struct device *dev, struct device_attribute *attr,
			  char *buf)
{
	struct gendisk *disk = dev_to_disk(dev);
	int set = test_bit(QUEUE_FLAG_FAIL_IO, &disk->queue->queue_flags);

	return sprintf(buf, "%d\n", set != 0);
}

ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr,
			   const char *buf, size_t count)
{
	struct gendisk *disk = dev_to_disk(dev);
	int val;

	if (count) {
		struct request_queue *q = disk->queue;
		char *p = (char *) buf;

		val = simple_strtoul(p, &p, 10);
		if (val)
			blk_queue_flag_set(QUEUE_FLAG_FAIL_IO, q);
		else
			blk_queue_flag_clear(QUEUE_FLAG_FAIL_IO, q);
	}

	return count;
}

#endif /* CONFIG_FAIL_IO_TIMEOUT */

/*
 * blk_delete_timer - Delete/cancel timer for a given function.
 * @req:	request that we are canceling timer for
 *
 */
void blk_delete_timer(struct request *req)
{
	list_del_init(&req->timeout_list);
}

static void blk_rq_timed_out(struct request *req)
{
	struct request_queue *q = req->q;
	enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER;

	if (q->rq_timed_out_fn)
		ret = q->rq_timed_out_fn(req);
	switch (ret) {
	case BLK_EH_HANDLED:
		__blk_complete_request(req);
		break;
	case BLK_EH_RESET_TIMER:
		blk_add_timer(req);
		blk_clear_rq_complete(req);
		break;
	case BLK_EH_NOT_HANDLED:
		/*
		 * LLD handles this for now but in the future
		 * we can send a request msg to abort the command
		 * and we can move more of the generic scsi eh code to
		 * the blk layer.
		 */
		break;
	default:
		printk(KERN_ERR "block: bad eh return: %d\n", ret);
		break;
	}
}

static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout,
			  unsigned int *next_set)
{
	const unsigned long deadline = blk_rq_deadline(rq);

	if (time_after_eq(jiffies, deadline)) {
		list_del_init(&rq->timeout_list);

		/*
		 * Check if we raced with end io completion
		 */
		if (!blk_mark_rq_complete(rq))
			blk_rq_timed_out(rq);
	} else if (!*next_set || time_after(*next_timeout, deadline)) {
		*next_timeout = deadline;
		*next_set = 1;
	}
}

void blk_timeout_work(struct work_struct *work)
{
	struct request_queue *q =
		container_of(work, struct request_queue, timeout_work);
	unsigned long flags, next = 0;
	struct request *rq, *tmp;
	int next_set = 0;

	spin_lock_irqsave(q->queue_lock, flags);

	list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list)
		blk_rq_check_expired(rq, &next, &next_set);

	if (next_set)
		mod_timer(&q->timeout, round_jiffies_up(next));

	spin_unlock_irqrestore(q->queue_lock, flags);
}

/**
 * blk_abort_request -- Request request recovery for the specified command
 * @req:	pointer to the request of interest
 *
 * This function requests that the block layer start recovery for the
 * request by deleting the timer and calling the q's timeout function.
 * LLDDs who implement their own error recovery MAY ignore the timeout
 * event if they generated blk_abort_req. Must hold queue lock.
 */
void blk_abort_request(struct request *req)
{
	if (req->q->mq_ops) {
		/*
		 * All we need to ensure is that timeout scan takes place
		 * immediately and that scan sees the new timeout value.
		 * No need for fancy synchronizations.
		 */
		blk_rq_set_deadline(req, jiffies);
		kblockd_schedule_work(&req->q->timeout_work);
	} else {
		if (blk_mark_rq_complete(req))
			return;
		blk_delete_timer(req);
		blk_rq_timed_out(req);
	}
}
EXPORT_SYMBOL_GPL(blk_abort_request);

unsigned long blk_rq_timeout(unsigned long timeout)
{
	unsigned long maxt;

	maxt = round_jiffies_up(jiffies + BLK_MAX_TIMEOUT);
	if (time_after(timeout, maxt))
		timeout = maxt;

	return timeout;
}

/**
 * blk_add_timer - Start timeout timer for a single request
 * @req:	request that is about to start running.
 *
 * Notes:
 *    Each request has its own timer, and as it is added to the queue, we
 *    set up the timer. When the request completes, we cancel the timer.
 */
void blk_add_timer(struct request *req)
{
	struct request_queue *q = req->q;
	unsigned long expiry;

	if (!q->mq_ops)
		lockdep_assert_held(q->queue_lock);

	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
	if (!q->mq_ops && !q->rq_timed_out_fn)
		return;

	BUG_ON(!list_empty(&req->timeout_list));

	/*
	 * Some LLDs, like scsi, peek at the timeout to prevent a
	 * command from being retried forever.
	 */
	if (!req->timeout)
		req->timeout = q->rq_timeout;

	blk_rq_set_deadline(req, jiffies + req->timeout);
	req->rq_flags &= ~RQF_MQ_TIMEOUT_EXPIRED;

	/*
	 * Only the non-mq case needs to add the request to a protected list.
	 * For the mq case we simply scan the tag map.
	 */
	if (!q->mq_ops)
		list_add_tail(&req->timeout_list, &req->q->timeout_list);

	/*
	 * If the timer isn't already pending or this timeout is earlier
	 * than an existing one, modify the timer. Round up to next nearest
	 * second.
	 */
	expiry = blk_rq_timeout(round_jiffies_up(blk_rq_deadline(req)));

	if (!timer_pending(&q->timeout) ||
	    time_before(expiry, q->timeout.expires)) {
		unsigned long diff = q->timeout.expires - expiry;

		/*
		 * Due to added timer slack to group timers, the timer
		 * will often be a little in front of what we asked for.
		 * So apply some tolerance here too, otherwise we keep
		 * modifying the timer because expires for value X
		 * will be X + something.
		 */
		if (!timer_pending(&q->timeout) || (diff >= HZ / 2))
			mod_timer(&q->timeout, expiry);
	}

}