summaryrefslogtreecommitdiffstats
path: root/io_uring/timeout.c
blob: fc950177e2e1d04d0f315e55accb3c8fa831e7d2 (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
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/io_uring.h>

#include <trace/events/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "io_uring.h"
#include "refs.h"
#include "cancel.h"
#include "timeout.h"

struct io_timeout {
	struct file			*file;
	u32				off;
	u32				target_seq;
	u32				repeats;
	struct list_head		list;
	/* head of the link, used by linked timeouts only */
	struct io_kiocb			*head;
	/* for linked completions */
	struct io_kiocb			*prev;
};

struct io_timeout_rem {
	struct file			*file;
	u64				addr;

	/* timeout update */
	struct timespec64		ts;
	u32				flags;
	bool				ltimeout;
};

static inline bool io_is_timeout_noseq(struct io_kiocb *req)
{
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_timeout_data *data = req->async_data;

	return !timeout->off || data->flags & IORING_TIMEOUT_MULTISHOT;
}

static inline void io_put_req(struct io_kiocb *req)
{
	if (req_ref_put_and_test(req)) {
		io_queue_next(req);
		io_free_req(req);
	}
}

static inline bool io_timeout_finish(struct io_timeout *timeout,
				     struct io_timeout_data *data)
{
	if (!(data->flags & IORING_TIMEOUT_MULTISHOT))
		return true;

	if (!timeout->off || (timeout->repeats && --timeout->repeats))
		return false;

	return true;
}

static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer);

static void io_timeout_complete(struct io_kiocb *req, struct io_tw_state *ts)
{
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_timeout_data *data = req->async_data;
	struct io_ring_ctx *ctx = req->ctx;

	if (!io_timeout_finish(timeout, data)) {
		bool filled;
		filled = io_aux_cqe(ctx, ts->locked, req->cqe.user_data, -ETIME,
				    IORING_CQE_F_MORE, false);
		if (filled) {
			/* re-arm timer */
			spin_lock_irq(&ctx->timeout_lock);
			list_add(&timeout->list, ctx->timeout_list.prev);
			data->timer.function = io_timeout_fn;
			hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
			spin_unlock_irq(&ctx->timeout_lock);
			return;
		}
	}

	io_req_task_complete(req, ts);
}

static bool io_kill_timeout(struct io_kiocb *req, int status)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_timeout_data *io = req->async_data;

	if (hrtimer_try_to_cancel(&io->timer) != -1) {
		struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);

		if (status)
			req_set_fail(req);
		atomic_set(&req->ctx->cq_timeouts,
			atomic_read(&req->ctx->cq_timeouts) + 1);
		list_del_init(&timeout->list);
		io_req_queue_tw_complete(req, status);
		return true;
	}
	return false;
}

__cold void io_flush_timeouts(struct io_ring_ctx *ctx)
{
	u32 seq;
	struct io_timeout *timeout, *tmp;

	spin_lock_irq(&ctx->timeout_lock);
	seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);

	list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) {
		struct io_kiocb *req = cmd_to_io_kiocb(timeout);
		u32 events_needed, events_got;

		if (io_is_timeout_noseq(req))
			break;

		/*
		 * Since seq can easily wrap around over time, subtract
		 * the last seq at which timeouts were flushed before comparing.
		 * Assuming not more than 2^31-1 events have happened since,
		 * these subtractions won't have wrapped, so we can check if
		 * target is in [last_seq, current_seq] by comparing the two.
		 */
		events_needed = timeout->target_seq - ctx->cq_last_tm_flush;
		events_got = seq - ctx->cq_last_tm_flush;
		if (events_got < events_needed)
			break;

		io_kill_timeout(req, 0);
	}
	ctx->cq_last_tm_flush = seq;
	spin_unlock_irq(&ctx->timeout_lock);
}

static void io_req_tw_fail_links(struct io_kiocb *link, struct io_tw_state *ts)
{
	io_tw_lock(link->ctx, ts);
	while (link) {
		struct io_kiocb *nxt = link->link;
		long res = -ECANCELED;

		if (link->flags & REQ_F_FAIL)
			res = link->cqe.res;
		link->link = NULL;
		io_req_set_res(link, res, 0);
		io_req_task_complete(link, ts);
		link = nxt;
	}
}

static void io_fail_links(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_kiocb *link = req->link;
	bool ignore_cqes = req->flags & REQ_F_SKIP_LINK_CQES;

	if (!link)
		return;

	while (link) {
		if (ignore_cqes)
			link->flags |= REQ_F_CQE_SKIP;
		else
			link->flags &= ~REQ_F_CQE_SKIP;
		trace_io_uring_fail_link(req, link);
		link = link->link;
	}

	link = req->link;
	link->io_task_work.func = io_req_tw_fail_links;
	io_req_task_work_add(link);
	req->link = NULL;
}

static inline void io_remove_next_linked(struct io_kiocb *req)
{
	struct io_kiocb *nxt = req->link;

	req->link = nxt->link;
	nxt->link = NULL;
}

void io_disarm_next(struct io_kiocb *req)
	__must_hold(&req->ctx->completion_lock)
{
	struct io_kiocb *link = NULL;

	if (req->flags & REQ_F_ARM_LTIMEOUT) {
		link = req->link;
		req->flags &= ~REQ_F_ARM_LTIMEOUT;
		if (link && link->opcode == IORING_OP_LINK_TIMEOUT) {
			io_remove_next_linked(req);
			io_req_queue_tw_complete(link, -ECANCELED);
		}
	} else if (req->flags & REQ_F_LINK_TIMEOUT) {
		struct io_ring_ctx *ctx = req->ctx;

		spin_lock_irq(&ctx->timeout_lock);
		link = io_disarm_linked_timeout(req);
		spin_unlock_irq(&ctx->timeout_lock);
		if (link)
			io_req_queue_tw_complete(link, -ECANCELED);
	}
	if (unlikely((req->flags & REQ_F_FAIL) &&
		     !(req->flags & REQ_F_HARDLINK)))
		io_fail_links(req);
}

struct io_kiocb *__io_disarm_linked_timeout(struct io_kiocb *req,
					    struct io_kiocb *link)
	__must_hold(&req->ctx->completion_lock)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_timeout_data *io = link->async_data;
	struct io_timeout *timeout = io_kiocb_to_cmd(link, struct io_timeout);

	io_remove_next_linked(req);
	timeout->head = NULL;
	if (hrtimer_try_to_cancel(&io->timer) != -1) {
		list_del(&timeout->list);
		return link;
	}

	return NULL;
}

static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
{
	struct io_timeout_data *data = container_of(timer,
						struct io_timeout_data, timer);
	struct io_kiocb *req = data->req;
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->timeout_lock, flags);
	list_del_init(&timeout->list);
	atomic_set(&req->ctx->cq_timeouts,
		atomic_read(&req->ctx->cq_timeouts) + 1);
	spin_unlock_irqrestore(&ctx->timeout_lock, flags);

	if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS))
		req_set_fail(req);

	io_req_set_res(req, -ETIME, 0);
	req->io_task_work.func = io_timeout_complete;
	io_req_task_work_add(req);
	return HRTIMER_NORESTART;
}

static struct io_kiocb *io_timeout_extract(struct io_ring_ctx *ctx,
					   struct io_cancel_data *cd)
	__must_hold(&ctx->timeout_lock)
{
	struct io_timeout *timeout;
	struct io_timeout_data *io;
	struct io_kiocb *req = NULL;

	list_for_each_entry(timeout, &ctx->timeout_list, list) {
		struct io_kiocb *tmp = cmd_to_io_kiocb(timeout);

		if (!(cd->flags & IORING_ASYNC_CANCEL_ANY) &&
		    cd->data != tmp->cqe.user_data)
			continue;
		if (cd->flags & (IORING_ASYNC_CANCEL_ALL|IORING_ASYNC_CANCEL_ANY)) {
			if (cd->seq == tmp->work.cancel_seq)
				continue;
			tmp->work.cancel_seq = cd->seq;
		}
		req = tmp;
		break;
	}
	if (!req)
		return ERR_PTR(-ENOENT);

	io = req->async_data;
	if (hrtimer_try_to_cancel(&io->timer) == -1)
		return ERR_PTR(-EALREADY);
	timeout = io_kiocb_to_cmd(req, struct io_timeout);
	list_del_init(&timeout->list);
	return req;
}

int io_timeout_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd)
	__must_hold(&ctx->completion_lock)
{
	struct io_kiocb *req;

	spin_lock_irq(&ctx->timeout_lock);
	req = io_timeout_extract(ctx, cd);
	spin_unlock_irq(&ctx->timeout_lock);

	if (IS_ERR(req))
		return PTR_ERR(req);
	io_req_task_queue_fail(req, -ECANCELED);
	return 0;
}

static void io_req_task_link_timeout(struct io_kiocb *req, struct io_tw_state *ts)
{
	unsigned issue_flags = ts->locked ? 0 : IO_URING_F_UNLOCKED;
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_kiocb *prev = timeout->prev;
	int ret = -ENOENT;

	if (prev) {
		if (!(req->task->flags & PF_EXITING)) {
			struct io_cancel_data cd = {
				.ctx		= req->ctx,
				.data		= prev->cqe.user_data,
			};

			ret = io_try_cancel(req->task->io_uring, &cd, issue_flags);
		}
		io_req_set_res(req, ret ?: -ETIME, 0);
		io_req_task_complete(req, ts);
		io_put_req(prev);
	} else {
		io_req_set_res(req, -ETIME, 0);
		io_req_task_complete(req, ts);
	}
}

static enum hrtimer_restart io_link_timeout_fn(struct hrtimer *timer)
{
	struct io_timeout_data *data = container_of(timer,
						struct io_timeout_data, timer);
	struct io_kiocb *prev, *req = data->req;
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_ring_ctx *ctx = req->ctx;
	unsigned long flags;

	spin_lock_irqsave(&ctx->timeout_lock, flags);
	prev = timeout->head;
	timeout->head = NULL;

	/*
	 * We don't expect the list to be empty, that will only happen if we
	 * race with the completion of the linked work.
	 */
	if (prev) {
		io_remove_next_linked(prev);
		if (!req_ref_inc_not_zero(prev))
			prev = NULL;
	}
	list_del(&timeout->list);
	timeout->prev = prev;
	spin_unlock_irqrestore(&ctx->timeout_lock, flags);

	req->io_task_work.func = io_req_task_link_timeout;
	io_req_task_work_add(req);
	return HRTIMER_NORESTART;
}

static clockid_t io_timeout_get_clock(struct io_timeout_data *data)
{
	switch (data->flags & IORING_TIMEOUT_CLOCK_MASK) {
	case IORING_TIMEOUT_BOOTTIME:
		return CLOCK_BOOTTIME;
	case IORING_TIMEOUT_REALTIME:
		return CLOCK_REALTIME;
	default:
		/* can't happen, vetted at prep time */
		WARN_ON_ONCE(1);
		fallthrough;
	case 0:
		return CLOCK_MONOTONIC;
	}
}

static int io_linked_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
				    struct timespec64 *ts, enum hrtimer_mode mode)
	__must_hold(&ctx->timeout_lock)
{
	struct io_timeout_data *io;
	struct io_timeout *timeout;
	struct io_kiocb *req = NULL;

	list_for_each_entry(timeout, &ctx->ltimeout_list, list) {
		struct io_kiocb *tmp = cmd_to_io_kiocb(timeout);

		if (user_data == tmp->cqe.user_data) {
			req = tmp;
			break;
		}
	}
	if (!req)
		return -ENOENT;

	io = req->async_data;
	if (hrtimer_try_to_cancel(&io->timer) == -1)
		return -EALREADY;
	hrtimer_init(&io->timer, io_timeout_get_clock(io), mode);
	io->timer.function = io_link_timeout_fn;
	hrtimer_start(&io->timer, timespec64_to_ktime(*ts), mode);
	return 0;
}

static int io_timeout_update(struct io_ring_ctx *ctx, __u64 user_data,
			     struct timespec64 *ts, enum hrtimer_mode mode)
	__must_hold(&ctx->timeout_lock)
{
	struct io_cancel_data cd = { .data = user_data, };
	struct io_kiocb *req = io_timeout_extract(ctx, &cd);
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_timeout_data *data;

	if (IS_ERR(req))
		return PTR_ERR(req);

	timeout->off = 0; /* noseq */
	data = req->async_data;
	list_add_tail(&timeout->list, &ctx->timeout_list);
	hrtimer_init(&data->timer, io_timeout_get_clock(data), mode);
	data->timer.function = io_timeout_fn;
	hrtimer_start(&data->timer, timespec64_to_ktime(*ts), mode);
	return 0;
}

int io_timeout_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_timeout_rem *tr = io_kiocb_to_cmd(req, struct io_timeout_rem);

	if (unlikely(req->flags & (REQ_F_FIXED_FILE | REQ_F_BUFFER_SELECT)))
		return -EINVAL;
	if (sqe->buf_index || sqe->len || sqe->splice_fd_in)
		return -EINVAL;

	tr->ltimeout = false;
	tr->addr = READ_ONCE(sqe->addr);
	tr->flags = READ_ONCE(sqe->timeout_flags);
	if (tr->flags & IORING_TIMEOUT_UPDATE_MASK) {
		if (hweight32(tr->flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
			return -EINVAL;
		if (tr->flags & IORING_LINK_TIMEOUT_UPDATE)
			tr->ltimeout = true;
		if (tr->flags & ~(IORING_TIMEOUT_UPDATE_MASK|IORING_TIMEOUT_ABS))
			return -EINVAL;
		if (get_timespec64(&tr->ts, u64_to_user_ptr(sqe->addr2)))
			return -EFAULT;
		if (tr->ts.tv_sec < 0 || tr->ts.tv_nsec < 0)
			return -EINVAL;
	} else if (tr->flags) {
		/* timeout removal doesn't support flags */
		return -EINVAL;
	}

	return 0;
}

static inline enum hrtimer_mode io_translate_timeout_mode(unsigned int flags)
{
	return (flags & IORING_TIMEOUT_ABS) ? HRTIMER_MODE_ABS
					    : HRTIMER_MODE_REL;
}

/*
 * Remove or update an existing timeout command
 */
int io_timeout_remove(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_timeout_rem *tr = io_kiocb_to_cmd(req, struct io_timeout_rem);
	struct io_ring_ctx *ctx = req->ctx;
	int ret;

	if (!(tr->flags & IORING_TIMEOUT_UPDATE)) {
		struct io_cancel_data cd = { .data = tr->addr, };

		spin_lock(&ctx->completion_lock);
		ret = io_timeout_cancel(ctx, &cd);
		spin_unlock(&ctx->completion_lock);
	} else {
		enum hrtimer_mode mode = io_translate_timeout_mode(tr->flags);

		spin_lock_irq(&ctx->timeout_lock);
		if (tr->ltimeout)
			ret = io_linked_timeout_update(ctx, tr->addr, &tr->ts, mode);
		else
			ret = io_timeout_update(ctx, tr->addr, &tr->ts, mode);
		spin_unlock_irq(&ctx->timeout_lock);
	}

	if (ret < 0)
		req_set_fail(req);
	io_req_set_res(req, ret, 0);
	return IOU_OK;
}

static int __io_timeout_prep(struct io_kiocb *req,
			     const struct io_uring_sqe *sqe,
			     bool is_timeout_link)
{
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_timeout_data *data;
	unsigned flags;
	u32 off = READ_ONCE(sqe->off);

	if (sqe->buf_index || sqe->len != 1 || sqe->splice_fd_in)
		return -EINVAL;
	if (off && is_timeout_link)
		return -EINVAL;
	flags = READ_ONCE(sqe->timeout_flags);
	if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK |
		      IORING_TIMEOUT_ETIME_SUCCESS |
		      IORING_TIMEOUT_MULTISHOT))
		return -EINVAL;
	/* more than one clock specified is invalid, obviously */
	if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
		return -EINVAL;
	/* multishot requests only make sense with rel values */
	if (!(~flags & (IORING_TIMEOUT_MULTISHOT | IORING_TIMEOUT_ABS)))
		return -EINVAL;

	INIT_LIST_HEAD(&timeout->list);
	timeout->off = off;
	if (unlikely(off && !req->ctx->off_timeout_used))
		req->ctx->off_timeout_used = true;
	/*
	 * for multishot reqs w/ fixed nr of repeats, repeats tracks the
	 * remaining nr
	 */
	timeout->repeats = 0;
	if ((flags & IORING_TIMEOUT_MULTISHOT) && off > 0)
		timeout->repeats = off;

	if (WARN_ON_ONCE(req_has_async_data(req)))
		return -EFAULT;
	if (io_alloc_async_data(req))
		return -ENOMEM;

	data = req->async_data;
	data->req = req;
	data->flags = flags;

	if (get_timespec64(&data->ts, u64_to_user_ptr(sqe->addr)))
		return -EFAULT;

	if (data->ts.tv_sec < 0 || data->ts.tv_nsec < 0)
		return -EINVAL;

	INIT_LIST_HEAD(&timeout->list);
	data->mode = io_translate_timeout_mode(flags);
	hrtimer_init(&data->timer, io_timeout_get_clock(data), data->mode);

	if (is_timeout_link) {
		struct io_submit_link *link = &req->ctx->submit_state.link;

		if (!link->head)
			return -EINVAL;
		if (link->last->opcode == IORING_OP_LINK_TIMEOUT)
			return -EINVAL;
		timeout->head = link->last;
		link->last->flags |= REQ_F_ARM_LTIMEOUT;
	}
	return 0;
}

int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	return __io_timeout_prep(req, sqe, false);
}

int io_link_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	return __io_timeout_prep(req, sqe, true);
}

int io_timeout(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_ring_ctx *ctx = req->ctx;
	struct io_timeout_data *data = req->async_data;
	struct list_head *entry;
	u32 tail, off = timeout->off;

	spin_lock_irq(&ctx->timeout_lock);

	/*
	 * sqe->off holds how many events that need to occur for this
	 * timeout event to be satisfied. If it isn't set, then this is
	 * a pure timeout request, sequence isn't used.
	 */
	if (io_is_timeout_noseq(req)) {
		entry = ctx->timeout_list.prev;
		goto add;
	}

	tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
	timeout->target_seq = tail + off;

	/* Update the last seq here in case io_flush_timeouts() hasn't.
	 * This is safe because ->completion_lock is held, and submissions
	 * and completions are never mixed in the same ->completion_lock section.
	 */
	ctx->cq_last_tm_flush = tail;

	/*
	 * Insertion sort, ensuring the first entry in the list is always
	 * the one we need first.
	 */
	list_for_each_prev(entry, &ctx->timeout_list) {
		struct io_timeout *nextt = list_entry(entry, struct io_timeout, list);
		struct io_kiocb *nxt = cmd_to_io_kiocb(nextt);

		if (io_is_timeout_noseq(nxt))
			continue;
		/* nxt.seq is behind @tail, otherwise would've been completed */
		if (off >= nextt->target_seq - tail)
			break;
	}
add:
	list_add(&timeout->list, entry);
	data->timer.function = io_timeout_fn;
	hrtimer_start(&data->timer, timespec64_to_ktime(data->ts), data->mode);
	spin_unlock_irq(&ctx->timeout_lock);
	return IOU_ISSUE_SKIP_COMPLETE;
}

void io_queue_linked_timeout(struct io_kiocb *req)
{
	struct io_timeout *timeout = io_kiocb_to_cmd(req, struct io_timeout);
	struct io_ring_ctx *ctx = req->ctx;

	spin_lock_irq(&ctx->timeout_lock);
	/*
	 * If the back reference is NULL, then our linked request finished
	 * before we got a chance to setup the timer
	 */
	if (timeout->head) {
		struct io_timeout_data *data = req->async_data;

		data->timer.function = io_link_timeout_fn;
		hrtimer_start(&data->timer, timespec64_to_ktime(data->ts),
				data->mode);
		list_add_tail(&timeout->list, &ctx->ltimeout_list);
	}
	spin_unlock_irq(&ctx->timeout_lock);
	/* drop submission reference */
	io_put_req(req);
}

static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
			  bool cancel_all)
	__must_hold(&req->ctx->timeout_lock)
{
	struct io_kiocb *req;

	if (task && head->task != task)
		return false;
	if (cancel_all)
		return true;

	io_for_each_link(req, head) {
		if (req->flags & REQ_F_INFLIGHT)
			return true;
	}
	return false;
}

/* Returns true if we found and killed one or more timeouts */
__cold bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
			     bool cancel_all)
{
	struct io_timeout *timeout, *tmp;
	int canceled = 0;

	/*
	 * completion_lock is needed for io_match_task(). Take it before
	 * timeout_lockfirst to keep locking ordering.
	 */
	spin_lock(&ctx->completion_lock);
	spin_lock_irq(&ctx->timeout_lock);
	list_for_each_entry_safe(timeout, tmp, &ctx->timeout_list, list) {
		struct io_kiocb *req = cmd_to_io_kiocb(timeout);

		if (io_match_task(req, tsk, cancel_all) &&
		    io_kill_timeout(req, -ECANCELED))
			canceled++;
	}
	spin_unlock_irq(&ctx->timeout_lock);
	spin_unlock(&ctx->completion_lock);
	return canceled != 0;
}