summaryrefslogtreecommitdiffstats
path: root/io_uring/poll.c
blob: 6db1dcb2c7977662dc62127803d6bd1ef5d0b517 (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
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/hashtable.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 "napi.h"
#include "opdef.h"
#include "kbuf.h"
#include "poll.h"
#include "cancel.h"

struct io_poll_update {
	struct file			*file;
	u64				old_user_data;
	u64				new_user_data;
	__poll_t			events;
	bool				update_events;
	bool				update_user_data;
};

struct io_poll_table {
	struct poll_table_struct pt;
	struct io_kiocb *req;
	int nr_entries;
	int error;
	bool owning;
	/* output value, set only if arm poll returns >0 */
	__poll_t result_mask;
};

#define IO_POLL_CANCEL_FLAG	BIT(31)
#define IO_POLL_RETRY_FLAG	BIT(30)
#define IO_POLL_REF_MASK	GENMASK(29, 0)

/*
 * We usually have 1-2 refs taken, 128 is more than enough and we want to
 * maximise the margin between this amount and the moment when it overflows.
 */
#define IO_POLL_REF_BIAS	128

#define IO_WQE_F_DOUBLE		1

static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
			void *key);

static inline struct io_kiocb *wqe_to_req(struct wait_queue_entry *wqe)
{
	unsigned long priv = (unsigned long)wqe->private;

	return (struct io_kiocb *)(priv & ~IO_WQE_F_DOUBLE);
}

static inline bool wqe_is_double(struct wait_queue_entry *wqe)
{
	unsigned long priv = (unsigned long)wqe->private;

	return priv & IO_WQE_F_DOUBLE;
}

static bool io_poll_get_ownership_slowpath(struct io_kiocb *req)
{
	int v;

	/*
	 * poll_refs are already elevated and we don't have much hope for
	 * grabbing the ownership. Instead of incrementing set a retry flag
	 * to notify the loop that there might have been some change.
	 */
	v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs);
	if (v & IO_POLL_REF_MASK)
		return false;
	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
}

/*
 * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can
 * bump it and acquire ownership. It's disallowed to modify requests while not
 * owning it, that prevents from races for enqueueing task_work's and b/w
 * arming poll and wakeups.
 */
static inline bool io_poll_get_ownership(struct io_kiocb *req)
{
	if (unlikely(atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS))
		return io_poll_get_ownership_slowpath(req);
	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
}

static void io_poll_mark_cancelled(struct io_kiocb *req)
{
	atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs);
}

static struct io_poll *io_poll_get_double(struct io_kiocb *req)
{
	/* pure poll stashes this in ->async_data, poll driven retry elsewhere */
	if (req->opcode == IORING_OP_POLL_ADD)
		return req->async_data;
	return req->apoll->double_poll;
}

static struct io_poll *io_poll_get_single(struct io_kiocb *req)
{
	if (req->opcode == IORING_OP_POLL_ADD)
		return io_kiocb_to_cmd(req, struct io_poll);
	return &req->apoll->poll;
}

static void io_poll_req_insert(struct io_kiocb *req)
{
	struct io_hash_table *table = &req->ctx->cancel_table;
	u32 index = hash_long(req->cqe.user_data, table->hash_bits);
	struct io_hash_bucket *hb = &table->hbs[index];

	spin_lock(&hb->lock);
	hlist_add_head(&req->hash_node, &hb->list);
	spin_unlock(&hb->lock);
}

static void io_poll_req_delete(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
	struct io_hash_table *table = &req->ctx->cancel_table;
	u32 index = hash_long(req->cqe.user_data, table->hash_bits);
	spinlock_t *lock = &table->hbs[index].lock;

	spin_lock(lock);
	hash_del(&req->hash_node);
	spin_unlock(lock);
}

static void io_poll_req_insert_locked(struct io_kiocb *req)
{
	struct io_hash_table *table = &req->ctx->cancel_table_locked;
	u32 index = hash_long(req->cqe.user_data, table->hash_bits);

	lockdep_assert_held(&req->ctx->uring_lock);

	hlist_add_head(&req->hash_node, &table->hbs[index].list);
}

static void io_poll_tw_hash_eject(struct io_kiocb *req, struct io_tw_state *ts)
{
	struct io_ring_ctx *ctx = req->ctx;

	if (req->flags & REQ_F_HASH_LOCKED) {
		/*
		 * ->cancel_table_locked is protected by ->uring_lock in
		 * contrast to per bucket spinlocks. Likely, tctx_task_work()
		 * already grabbed the mutex for us, but there is a chance it
		 * failed.
		 */
		io_tw_lock(ctx, ts);
		hash_del(&req->hash_node);
		req->flags &= ~REQ_F_HASH_LOCKED;
	} else {
		io_poll_req_delete(req, ctx);
	}
}

static void io_init_poll_iocb(struct io_poll *poll, __poll_t events)
{
	poll->head = NULL;
#define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
	/* mask in events that we always want/need */
	poll->events = events | IO_POLL_UNMASK;
	INIT_LIST_HEAD(&poll->wait.entry);
	init_waitqueue_func_entry(&poll->wait, io_poll_wake);
}

static inline void io_poll_remove_entry(struct io_poll *poll)
{
	struct wait_queue_head *head = smp_load_acquire(&poll->head);

	if (head) {
		spin_lock_irq(&head->lock);
		list_del_init(&poll->wait.entry);
		poll->head = NULL;
		spin_unlock_irq(&head->lock);
	}
}

static void io_poll_remove_entries(struct io_kiocb *req)
{
	/*
	 * Nothing to do if neither of those flags are set. Avoid dipping
	 * into the poll/apoll/double cachelines if we can.
	 */
	if (!(req->flags & (REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL)))
		return;

	/*
	 * While we hold the waitqueue lock and the waitqueue is nonempty,
	 * wake_up_pollfree() will wait for us.  However, taking the waitqueue
	 * lock in the first place can race with the waitqueue being freed.
	 *
	 * We solve this as eventpoll does: by taking advantage of the fact that
	 * all users of wake_up_pollfree() will RCU-delay the actual free.  If
	 * we enter rcu_read_lock() and see that the pointer to the queue is
	 * non-NULL, we can then lock it without the memory being freed out from
	 * under us.
	 *
	 * Keep holding rcu_read_lock() as long as we hold the queue lock, in
	 * case the caller deletes the entry from the queue, leaving it empty.
	 * In that case, only RCU prevents the queue memory from being freed.
	 */
	rcu_read_lock();
	if (req->flags & REQ_F_SINGLE_POLL)
		io_poll_remove_entry(io_poll_get_single(req));
	if (req->flags & REQ_F_DOUBLE_POLL)
		io_poll_remove_entry(io_poll_get_double(req));
	rcu_read_unlock();
}

enum {
	IOU_POLL_DONE = 0,
	IOU_POLL_NO_ACTION = 1,
	IOU_POLL_REMOVE_POLL_USE_RES = 2,
	IOU_POLL_REISSUE = 3,
	IOU_POLL_REQUEUE = 4,
};

static void __io_poll_execute(struct io_kiocb *req, int mask)
{
	unsigned flags = 0;

	io_req_set_res(req, mask, 0);
	req->io_task_work.func = io_poll_task_func;

	trace_io_uring_task_add(req, mask);

	if (!(req->flags & REQ_F_POLL_NO_LAZY))
		flags = IOU_F_TWQ_LAZY_WAKE;
	__io_req_task_work_add(req, flags);
}

static inline void io_poll_execute(struct io_kiocb *req, int res)
{
	if (io_poll_get_ownership(req))
		__io_poll_execute(req, res);
}

/*
 * All poll tw should go through this. Checks for poll events, manages
 * references, does rewait, etc.
 *
 * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action
 * require, which is either spurious wakeup or multishot CQE is served.
 * IOU_POLL_DONE when it's done with the request, then the mask is stored in
 * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
 * poll and that the result is stored in req->cqe.
 */
static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
{
	int v;

	/* req->task == current here, checking PF_EXITING is safe */
	if (unlikely(req->task->flags & PF_EXITING))
		return -ECANCELED;

	do {
		v = atomic_read(&req->poll_refs);

		if (unlikely(v != 1)) {
			/* tw should be the owner and so have some refs */
			if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK)))
				return IOU_POLL_NO_ACTION;
			if (v & IO_POLL_CANCEL_FLAG)
				return -ECANCELED;
			/*
			 * cqe.res contains only events of the first wake up
			 * and all others are to be lost. Redo vfs_poll() to get
			 * up to date state.
			 */
			if ((v & IO_POLL_REF_MASK) != 1)
				req->cqe.res = 0;

			if (v & IO_POLL_RETRY_FLAG) {
				req->cqe.res = 0;
				/*
				 * We won't find new events that came in between
				 * vfs_poll and the ref put unless we clear the
				 * flag in advance.
				 */
				atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs);
				v &= ~IO_POLL_RETRY_FLAG;
			}
		}

		/* the mask was stashed in __io_poll_execute */
		if (!req->cqe.res) {
			struct poll_table_struct pt = { ._key = req->apoll_events };
			req->cqe.res = vfs_poll(req->file, &pt) & req->apoll_events;
			/*
			 * We got woken with a mask, but someone else got to
			 * it first. The above vfs_poll() doesn't add us back
			 * to the waitqueue, so if we get nothing back, we
			 * should be safe and attempt a reissue.
			 */
			if (unlikely(!req->cqe.res)) {
				/* Multishot armed need not reissue */
				if (!(req->apoll_events & EPOLLONESHOT))
					continue;
				return IOU_POLL_REISSUE;
			}
		}
		if (req->apoll_events & EPOLLONESHOT)
			return IOU_POLL_DONE;

		/* multishot, just fill a CQE and proceed */
		if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
			__poll_t mask = mangle_poll(req->cqe.res &
						    req->apoll_events);

			if (!io_fill_cqe_req_aux(req, ts->locked, mask,
						 IORING_CQE_F_MORE)) {
				io_req_set_res(req, mask, 0);
				return IOU_POLL_REMOVE_POLL_USE_RES;
			}
		} else {
			int ret = io_poll_issue(req, ts);
			if (ret == IOU_STOP_MULTISHOT)
				return IOU_POLL_REMOVE_POLL_USE_RES;
			else if (ret == IOU_REQUEUE)
				return IOU_POLL_REQUEUE;
			if (ret < 0)
				return ret;
		}

		/* force the next iteration to vfs_poll() */
		req->cqe.res = 0;

		/*
		 * Release all references, retry if someone tried to restart
		 * task_work while we were executing it.
		 */
		v &= IO_POLL_REF_MASK;
	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);

	return IOU_POLL_NO_ACTION;
}

void io_poll_task_func(struct io_kiocb *req, struct io_tw_state *ts)
{
	int ret;

	ret = io_poll_check_events(req, ts);
	if (ret == IOU_POLL_NO_ACTION) {
		return;
	} else if (ret == IOU_POLL_REQUEUE) {
		__io_poll_execute(req, 0);
		return;
	}
	io_poll_remove_entries(req);
	io_poll_tw_hash_eject(req, ts);

	if (req->opcode == IORING_OP_POLL_ADD) {
		if (ret == IOU_POLL_DONE) {
			struct io_poll *poll;

			poll = io_kiocb_to_cmd(req, struct io_poll);
			req->cqe.res = mangle_poll(req->cqe.res & poll->events);
		} else if (ret == IOU_POLL_REISSUE) {
			io_req_task_submit(req, ts);
			return;
		} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
			req->cqe.res = ret;
			req_set_fail(req);
		}

		io_req_set_res(req, req->cqe.res, 0);
		io_req_task_complete(req, ts);
	} else {
		io_tw_lock(req->ctx, ts);

		if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
			io_req_task_complete(req, ts);
		else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
			io_req_task_submit(req, ts);
		else
			io_req_defer_failed(req, ret);
	}
}

static void io_poll_cancel_req(struct io_kiocb *req)
{
	io_poll_mark_cancelled(req);
	/* kick tw, which should complete the request */
	io_poll_execute(req, 0);
}

#define IO_ASYNC_POLL_COMMON	(EPOLLONESHOT | EPOLLPRI)

static __cold int io_pollfree_wake(struct io_kiocb *req, struct io_poll *poll)
{
	io_poll_mark_cancelled(req);
	/* we have to kick tw in case it's not already */
	io_poll_execute(req, 0);

	/*
	 * If the waitqueue is being freed early but someone is already
	 * holds ownership over it, we have to tear down the request as
	 * best we can. That means immediately removing the request from
	 * its waitqueue and preventing all further accesses to the
	 * waitqueue via the request.
	 */
	list_del_init(&poll->wait.entry);

	/*
	 * Careful: this *must* be the last step, since as soon
	 * as req->head is NULL'ed out, the request can be
	 * completed and freed, since aio_poll_complete_work()
	 * will no longer need to take the waitqueue lock.
	 */
	smp_store_release(&poll->head, NULL);
	return 1;
}

static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
			void *key)
{
	struct io_kiocb *req = wqe_to_req(wait);
	struct io_poll *poll = container_of(wait, struct io_poll, wait);
	__poll_t mask = key_to_poll(key);

	if (unlikely(mask & POLLFREE))
		return io_pollfree_wake(req, poll);

	/* for instances that support it check for an event match first */
	if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON)))
		return 0;

	if (io_poll_get_ownership(req)) {
		/*
		 * If we trigger a multishot poll off our own wakeup path,
		 * disable multishot as there is a circular dependency between
		 * CQ posting and triggering the event.
		 */
		if (mask & EPOLL_URING_WAKE)
			poll->events |= EPOLLONESHOT;

		/* optional, saves extra locking for removal in tw handler */
		if (mask && poll->events & EPOLLONESHOT) {
			list_del_init(&poll->wait.entry);
			poll->head = NULL;
			if (wqe_is_double(wait))
				req->flags &= ~REQ_F_DOUBLE_POLL;
			else
				req->flags &= ~REQ_F_SINGLE_POLL;
		}
		__io_poll_execute(req, mask);
	}
	return 1;
}

/* fails only when polling is already completing by the first entry */
static bool io_poll_double_prepare(struct io_kiocb *req)
{
	struct wait_queue_head *head;
	struct io_poll *poll = io_poll_get_single(req);

	/* head is RCU protected, see io_poll_remove_entries() comments */
	rcu_read_lock();
	head = smp_load_acquire(&poll->head);
	/*
	 * poll arm might not hold ownership and so race for req->flags with
	 * io_poll_wake(). There is only one poll entry queued, serialise with
	 * it by taking its head lock. As we're still arming the tw hanlder
	 * is not going to be run, so there are no races with it.
	 */
	if (head) {
		spin_lock_irq(&head->lock);
		req->flags |= REQ_F_DOUBLE_POLL;
		if (req->opcode == IORING_OP_POLL_ADD)
			req->flags |= REQ_F_ASYNC_DATA;
		spin_unlock_irq(&head->lock);
	}
	rcu_read_unlock();
	return !!head;
}

static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
			    struct wait_queue_head *head,
			    struct io_poll **poll_ptr)
{
	struct io_kiocb *req = pt->req;
	unsigned long wqe_private = (unsigned long) req;

	/*
	 * The file being polled uses multiple waitqueues for poll handling
	 * (e.g. one for read, one for write). Setup a separate io_poll
	 * if this happens.
	 */
	if (unlikely(pt->nr_entries)) {
		struct io_poll *first = poll;

		/* double add on the same waitqueue head, ignore */
		if (first->head == head)
			return;
		/* already have a 2nd entry, fail a third attempt */
		if (*poll_ptr) {
			if ((*poll_ptr)->head == head)
				return;
			pt->error = -EINVAL;
			return;
		}

		poll = kmalloc(sizeof(*poll), GFP_ATOMIC);
		if (!poll) {
			pt->error = -ENOMEM;
			return;
		}

		/* mark as double wq entry */
		wqe_private |= IO_WQE_F_DOUBLE;
		io_init_poll_iocb(poll, first->events);
		if (!io_poll_double_prepare(req)) {
			/* the request is completing, just back off */
			kfree(poll);
			return;
		}
		*poll_ptr = poll;
	} else {
		/* fine to modify, there is no poll queued to race with us */
		req->flags |= REQ_F_SINGLE_POLL;
	}

	pt->nr_entries++;
	poll->head = head;
	poll->wait.private = (void *) wqe_private;

	if (poll->events & EPOLLEXCLUSIVE) {
		add_wait_queue_exclusive(head, &poll->wait);
	} else {
		add_wait_queue(head, &poll->wait);
	}
}

static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
			       struct poll_table_struct *p)
{
	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
	struct io_poll *poll = io_kiocb_to_cmd(pt->req, struct io_poll);

	__io_queue_proc(poll, pt, head,
			(struct io_poll **) &pt->req->async_data);
}

static bool io_poll_can_finish_inline(struct io_kiocb *req,
				      struct io_poll_table *pt)
{
	return pt->owning || io_poll_get_ownership(req);
}

static void io_poll_add_hash(struct io_kiocb *req)
{
	if (req->flags & REQ_F_HASH_LOCKED)
		io_poll_req_insert_locked(req);
	else
		io_poll_req_insert(req);
}

/*
 * Returns 0 when it's handed over for polling. The caller owns the requests if
 * it returns non-zero, but otherwise should not touch it. Negative values
 * contain an error code. When the result is >0, the polling has completed
 * inline and ipt.result_mask is set to the mask.
 */
static int __io_arm_poll_handler(struct io_kiocb *req,
				 struct io_poll *poll,
				 struct io_poll_table *ipt, __poll_t mask,
				 unsigned issue_flags)
{
	INIT_HLIST_NODE(&req->hash_node);
	io_init_poll_iocb(poll, mask);
	poll->file = req->file;
	req->apoll_events = poll->events;

	ipt->pt._key = mask;
	ipt->req = req;
	ipt->error = 0;
	ipt->nr_entries = 0;
	/*
	 * Polling is either completed here or via task_work, so if we're in the
	 * task context we're naturally serialised with tw by merit of running
	 * the same task. When it's io-wq, take the ownership to prevent tw
	 * from running. However, when we're in the task context, skip taking
	 * it as an optimisation.
	 *
	 * Note: even though the request won't be completed/freed, without
	 * ownership we still can race with io_poll_wake().
	 * io_poll_can_finish_inline() tries to deal with that.
	 */
	ipt->owning = issue_flags & IO_URING_F_UNLOCKED;
	atomic_set(&req->poll_refs, (int)ipt->owning);

	/* io-wq doesn't hold uring_lock */
	if (issue_flags & IO_URING_F_UNLOCKED)
		req->flags &= ~REQ_F_HASH_LOCKED;


	/*
	 * Exclusive waits may only wake a limited amount of entries
	 * rather than all of them, this may interfere with lazy
	 * wake if someone does wait(events > 1). Ensure we don't do
	 * lazy wake for those, as we need to process each one as they
	 * come in.
	 */
	if (poll->events & EPOLLEXCLUSIVE)
		req->flags |= REQ_F_POLL_NO_LAZY;

	mask = vfs_poll(req->file, &ipt->pt) & poll->events;

	if (unlikely(ipt->error || !ipt->nr_entries)) {
		io_poll_remove_entries(req);

		if (!io_poll_can_finish_inline(req, ipt)) {
			io_poll_mark_cancelled(req);
			return 0;
		} else if (mask && (poll->events & EPOLLET)) {
			ipt->result_mask = mask;
			return 1;
		}
		return ipt->error ?: -EINVAL;
	}

	if (mask &&
	   ((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) {
		if (!io_poll_can_finish_inline(req, ipt)) {
			io_poll_add_hash(req);
			return 0;
		}
		io_poll_remove_entries(req);
		ipt->result_mask = mask;
		/* no one else has access to the req, forget about the ref */
		return 1;
	}

	io_poll_add_hash(req);

	if (mask && (poll->events & EPOLLET) &&
	    io_poll_can_finish_inline(req, ipt)) {
		__io_poll_execute(req, mask);
		return 0;
	}
	io_napi_add(req);

	if (ipt->owning) {
		/*
		 * Try to release ownership. If we see a change of state, e.g.
		 * poll was waken up, queue up a tw, it'll deal with it.
		 */
		if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1)
			__io_poll_execute(req, 0);
	}
	return 0;
}

static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
			       struct poll_table_struct *p)
{
	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
	struct async_poll *apoll = pt->req->apoll;

	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
}

/*
 * We can't reliably detect loops in repeated poll triggers and issue
 * subsequently failing. But rather than fail these immediately, allow a
 * certain amount of retries before we give up. Given that this condition
 * should _rarely_ trigger even once, we should be fine with a larger value.
 */
#define APOLL_MAX_RETRY		128

static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
					     unsigned issue_flags)
{
	struct io_ring_ctx *ctx = req->ctx;
	struct io_cache_entry *entry;
	struct async_poll *apoll;

	if (req->flags & REQ_F_POLLED) {
		apoll = req->apoll;
		kfree(apoll->double_poll);
	} else if (!(issue_flags & IO_URING_F_UNLOCKED)) {
		entry = io_alloc_cache_get(&ctx->apoll_cache);
		if (entry == NULL)
			goto alloc_apoll;
		apoll = container_of(entry, struct async_poll, cache);
		apoll->poll.retries = APOLL_MAX_RETRY;
	} else {
alloc_apoll:
		apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
		if (unlikely(!apoll))
			return NULL;
		apoll->poll.retries = APOLL_MAX_RETRY;
	}
	apoll->double_poll = NULL;
	req->apoll = apoll;
	if (unlikely(!--apoll->poll.retries))
		return NULL;
	return apoll;
}

int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
{
	const struct io_issue_def *def = &io_issue_defs[req->opcode];
	struct async_poll *apoll;
	struct io_poll_table ipt;
	__poll_t mask = POLLPRI | POLLERR | EPOLLET;
	int ret;

	/*
	 * apoll requests already grab the mutex to complete in the tw handler,
	 * so removal from the mutex-backed hash is free, use it by default.
	 */
	req->flags |= REQ_F_HASH_LOCKED;

	if (!def->pollin && !def->pollout)
		return IO_APOLL_ABORTED;
	if (!io_file_can_poll(req))
		return IO_APOLL_ABORTED;
	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
		mask |= EPOLLONESHOT;

	if (def->pollin) {
		mask |= EPOLLIN | EPOLLRDNORM;

		/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
		if (req->flags & REQ_F_CLEAR_POLLIN)
			mask &= ~EPOLLIN;
	} else {
		mask |= EPOLLOUT | EPOLLWRNORM;
	}
	if (def->poll_exclusive)
		mask |= EPOLLEXCLUSIVE;

	apoll = io_req_alloc_apoll(req, issue_flags);
	if (!apoll)
		return IO_APOLL_ABORTED;
	req->flags &= ~(REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL);
	req->flags |= REQ_F_POLLED;
	ipt.pt._qproc = io_async_queue_proc;

	io_kbuf_recycle(req, issue_flags);

	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, issue_flags);
	if (ret)
		return ret > 0 ? IO_APOLL_READY : IO_APOLL_ABORTED;
	trace_io_uring_poll_arm(req, mask, apoll->poll.events);
	return IO_APOLL_OK;
}

static __cold bool io_poll_remove_all_table(struct task_struct *tsk,
					    struct io_hash_table *table,
					    bool cancel_all)
{
	unsigned nr_buckets = 1U << table->hash_bits;
	struct hlist_node *tmp;
	struct io_kiocb *req;
	bool found = false;
	int i;

	for (i = 0; i < nr_buckets; i++) {
		struct io_hash_bucket *hb = &table->hbs[i];

		spin_lock(&hb->lock);
		hlist_for_each_entry_safe(req, tmp, &hb->list, hash_node) {
			if (io_match_task_safe(req, tsk, cancel_all)) {
				hlist_del_init(&req->hash_node);
				io_poll_cancel_req(req);
				found = true;
			}
		}
		spin_unlock(&hb->lock);
	}
	return found;
}

/*
 * Returns true if we found and killed one or more poll requests
 */
__cold bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
			       bool cancel_all)
	__must_hold(&ctx->uring_lock)
{
	bool ret;

	ret = io_poll_remove_all_table(tsk, &ctx->cancel_table, cancel_all);
	ret |= io_poll_remove_all_table(tsk, &ctx->cancel_table_locked, cancel_all);
	return ret;
}

static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
				     struct io_cancel_data *cd,
				     struct io_hash_table *table,
				     struct io_hash_bucket **out_bucket)
{
	struct io_kiocb *req;
	u32 index = hash_long(cd->data, table->hash_bits);
	struct io_hash_bucket *hb = &table->hbs[index];

	*out_bucket = NULL;

	spin_lock(&hb->lock);
	hlist_for_each_entry(req, &hb->list, hash_node) {
		if (cd->data != req->cqe.user_data)
			continue;
		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
			continue;
		if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
			if (io_cancel_match_sequence(req, cd->seq))
				continue;
		}
		*out_bucket = hb;
		return req;
	}
	spin_unlock(&hb->lock);
	return NULL;
}

static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx,
					  struct io_cancel_data *cd,
					  struct io_hash_table *table,
					  struct io_hash_bucket **out_bucket)
{
	unsigned nr_buckets = 1U << table->hash_bits;
	struct io_kiocb *req;
	int i;

	*out_bucket = NULL;

	for (i = 0; i < nr_buckets; i++) {
		struct io_hash_bucket *hb = &table->hbs[i];

		spin_lock(&hb->lock);
		hlist_for_each_entry(req, &hb->list, hash_node) {
			if (io_cancel_req_match(req, cd)) {
				*out_bucket = hb;
				return req;
			}
		}
		spin_unlock(&hb->lock);
	}
	return NULL;
}

static int io_poll_disarm(struct io_kiocb *req)
{
	if (!req)
		return -ENOENT;
	if (!io_poll_get_ownership(req))
		return -EALREADY;
	io_poll_remove_entries(req);
	hash_del(&req->hash_node);
	return 0;
}

static int __io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
			    struct io_hash_table *table)
{
	struct io_hash_bucket *bucket;
	struct io_kiocb *req;

	if (cd->flags & (IORING_ASYNC_CANCEL_FD | IORING_ASYNC_CANCEL_OP |
			 IORING_ASYNC_CANCEL_ANY))
		req = io_poll_file_find(ctx, cd, table, &bucket);
	else
		req = io_poll_find(ctx, false, cd, table, &bucket);

	if (req)
		io_poll_cancel_req(req);
	if (bucket)
		spin_unlock(&bucket->lock);
	return req ? 0 : -ENOENT;
}

int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
		   unsigned issue_flags)
{
	int ret;

	ret = __io_poll_cancel(ctx, cd, &ctx->cancel_table);
	if (ret != -ENOENT)
		return ret;

	io_ring_submit_lock(ctx, issue_flags);
	ret = __io_poll_cancel(ctx, cd, &ctx->cancel_table_locked);
	io_ring_submit_unlock(ctx, issue_flags);
	return ret;
}

static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
				     unsigned int flags)
{
	u32 events;

	events = READ_ONCE(sqe->poll32_events);
#ifdef __BIG_ENDIAN
	events = swahw32(events);
#endif
	if (!(flags & IORING_POLL_ADD_MULTI))
		events |= EPOLLONESHOT;
	if (!(flags & IORING_POLL_ADD_LEVEL))
		events |= EPOLLET;
	return demangle_poll(events) |
		(events & (EPOLLEXCLUSIVE|EPOLLONESHOT|EPOLLET));
}

int io_poll_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_poll_update *upd = io_kiocb_to_cmd(req, struct io_poll_update);
	u32 flags;

	if (sqe->buf_index || sqe->splice_fd_in)
		return -EINVAL;
	flags = READ_ONCE(sqe->len);
	if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
		      IORING_POLL_ADD_MULTI))
		return -EINVAL;
	/* meaningless without update */
	if (flags == IORING_POLL_ADD_MULTI)
		return -EINVAL;

	upd->old_user_data = READ_ONCE(sqe->addr);
	upd->update_events = flags & IORING_POLL_UPDATE_EVENTS;
	upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA;

	upd->new_user_data = READ_ONCE(sqe->off);
	if (!upd->update_user_data && upd->new_user_data)
		return -EINVAL;
	if (upd->update_events)
		upd->events = io_poll_parse_events(sqe, flags);
	else if (sqe->poll32_events)
		return -EINVAL;

	return 0;
}

int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_poll *poll = io_kiocb_to_cmd(req, struct io_poll);
	u32 flags;

	if (sqe->buf_index || sqe->off || sqe->addr)
		return -EINVAL;
	flags = READ_ONCE(sqe->len);
	if (flags & ~IORING_POLL_ADD_MULTI)
		return -EINVAL;
	if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP))
		return -EINVAL;

	poll->events = io_poll_parse_events(sqe, flags);
	return 0;
}

int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_poll *poll = io_kiocb_to_cmd(req, struct io_poll);
	struct io_poll_table ipt;
	int ret;

	ipt.pt._qproc = io_poll_queue_proc;

	/*
	 * If sqpoll or single issuer, there is no contention for ->uring_lock
	 * and we'll end up holding it in tw handlers anyway.
	 */
	if (req->ctx->flags & (IORING_SETUP_SQPOLL|IORING_SETUP_SINGLE_ISSUER))
		req->flags |= REQ_F_HASH_LOCKED;

	ret = __io_arm_poll_handler(req, poll, &ipt, poll->events, issue_flags);
	if (ret > 0) {
		io_req_set_res(req, ipt.result_mask, 0);
		return IOU_OK;
	}
	return ret ?: IOU_ISSUE_SKIP_COMPLETE;
}

int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_poll_update *poll_update = io_kiocb_to_cmd(req, struct io_poll_update);
	struct io_ring_ctx *ctx = req->ctx;
	struct io_cancel_data cd = { .ctx = ctx, .data = poll_update->old_user_data, };
	struct io_hash_bucket *bucket;
	struct io_kiocb *preq;
	int ret2, ret = 0;

	io_ring_submit_lock(ctx, issue_flags);
	preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table, &bucket);
	ret2 = io_poll_disarm(preq);
	if (bucket)
		spin_unlock(&bucket->lock);
	if (!ret2)
		goto found;
	if (ret2 != -ENOENT) {
		ret = ret2;
		goto out;
	}

	preq = io_poll_find(ctx, true, &cd, &ctx->cancel_table_locked, &bucket);
	ret2 = io_poll_disarm(preq);
	if (bucket)
		spin_unlock(&bucket->lock);
	if (ret2) {
		ret = ret2;
		goto out;
	}

found:
	if (WARN_ON_ONCE(preq->opcode != IORING_OP_POLL_ADD)) {
		ret = -EFAULT;
		goto out;
	}

	if (poll_update->update_events || poll_update->update_user_data) {
		/* only mask one event flags, keep behavior flags */
		if (poll_update->update_events) {
			struct io_poll *poll = io_kiocb_to_cmd(preq, struct io_poll);

			poll->events &= ~0xffff;
			poll->events |= poll_update->events & 0xffff;
			poll->events |= IO_POLL_UNMASK;
		}
		if (poll_update->update_user_data)
			preq->cqe.user_data = poll_update->new_user_data;

		ret2 = io_poll_add(preq, issue_flags & ~IO_URING_F_UNLOCKED);
		/* successfully updated, don't complete poll request */
		if (!ret2 || ret2 == -EIOCBQUEUED)
			goto out;
	}

	req_set_fail(preq);
	io_req_set_res(preq, -ECANCELED, 0);
	preq->io_task_work.func = io_req_task_complete;
	io_req_task_work_add(preq);
out:
	io_ring_submit_unlock(ctx, issue_flags);
	if (ret < 0) {
		req_set_fail(req);
		return ret;
	}
	/* complete update request, we're done with it */
	io_req_set_res(req, ret, 0);
	return IOU_OK;
}

void io_apoll_cache_free(struct io_cache_entry *entry)
{
	kfree(container_of(entry, struct async_poll, cache));
}