summaryrefslogtreecommitdiff
path: root/io_uring/rw.c
blob: 7f8363f77bd5788325b671a420d47b60681db894 (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
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/blk-mq.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/fsnotify.h>
#include <linux/poll.h>
#include <linux/nospec.h>
#include <linux/compat.h>
#include <linux/io_uring.h>

#include <uapi/linux/io_uring.h>

#include "io_uring.h"
#include "opdef.h"
#include "kbuf.h"
#include "rsrc.h"
#include "rw.h"

struct io_rw {
	/* NOTE: kiocb has the file as the first member, so don't do it here */
	struct kiocb			kiocb;
	u64				addr;
	u32				len;
	rwf_t				flags;
};

static inline bool io_file_supports_nowait(struct io_kiocb *req)
{
	return req->flags & REQ_F_SUPPORT_NOWAIT;
}

int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	unsigned ioprio;
	int ret;

	rw->kiocb.ki_pos = READ_ONCE(sqe->off);
	/* used for fixed read/write too - just read unconditionally */
	req->buf_index = READ_ONCE(sqe->buf_index);

	if (req->opcode == IORING_OP_READ_FIXED ||
	    req->opcode == IORING_OP_WRITE_FIXED) {
		struct io_ring_ctx *ctx = req->ctx;
		u16 index;

		if (unlikely(req->buf_index >= ctx->nr_user_bufs))
			return -EFAULT;
		index = array_index_nospec(req->buf_index, ctx->nr_user_bufs);
		req->imu = ctx->user_bufs[index];
		io_req_set_rsrc_node(req, ctx, 0);
	}

	ioprio = READ_ONCE(sqe->ioprio);
	if (ioprio) {
		ret = ioprio_check_cap(ioprio);
		if (ret)
			return ret;

		rw->kiocb.ki_ioprio = ioprio;
	} else {
		rw->kiocb.ki_ioprio = get_current_ioprio();
	}

	rw->addr = READ_ONCE(sqe->addr);
	rw->len = READ_ONCE(sqe->len);
	rw->flags = READ_ONCE(sqe->rw_flags);
	return 0;
}

void io_readv_writev_cleanup(struct io_kiocb *req)
{
	struct io_async_rw *io = req->async_data;

	kfree(io->free_iovec);
}

static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
{
	switch (ret) {
	case -EIOCBQUEUED:
		break;
	case -ERESTARTSYS:
	case -ERESTARTNOINTR:
	case -ERESTARTNOHAND:
	case -ERESTART_RESTARTBLOCK:
		/*
		 * We can't just restart the syscall, since previously
		 * submitted sqes may already be in progress. Just fail this
		 * IO with EINTR.
		 */
		ret = -EINTR;
		fallthrough;
	default:
		kiocb->ki_complete(kiocb, ret);
	}
}

static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);

	if (rw->kiocb.ki_pos != -1)
		return &rw->kiocb.ki_pos;

	if (!(req->file->f_mode & FMODE_STREAM)) {
		req->flags |= REQ_F_CUR_POS;
		rw->kiocb.ki_pos = req->file->f_pos;
		return &rw->kiocb.ki_pos;
	}

	rw->kiocb.ki_pos = 0;
	return NULL;
}

static void io_req_task_queue_reissue(struct io_kiocb *req)
{
	req->io_task_work.func = io_queue_iowq;
	io_req_task_work_add(req);
}

#ifdef CONFIG_BLOCK
static bool io_resubmit_prep(struct io_kiocb *req)
{
	struct io_async_rw *io = req->async_data;

	if (!req_has_async_data(req))
		return !io_req_prep_async(req);
	iov_iter_restore(&io->s.iter, &io->s.iter_state);
	return true;
}

static bool io_rw_should_reissue(struct io_kiocb *req)
{
	umode_t mode = file_inode(req->file)->i_mode;
	struct io_ring_ctx *ctx = req->ctx;

	if (!S_ISBLK(mode) && !S_ISREG(mode))
		return false;
	if ((req->flags & REQ_F_NOWAIT) || (io_wq_current_is_worker() &&
	    !(ctx->flags & IORING_SETUP_IOPOLL)))
		return false;
	/*
	 * If ref is dying, we might be running poll reap from the exit work.
	 * Don't attempt to reissue from that path, just let it fail with
	 * -EAGAIN.
	 */
	if (percpu_ref_is_dying(&ctx->refs))
		return false;
	/*
	 * Play it safe and assume not safe to re-import and reissue if we're
	 * not in the original thread group (or in task context).
	 */
	if (!same_thread_group(req->task, current) || !in_task())
		return false;
	return true;
}
#else
static bool io_resubmit_prep(struct io_kiocb *req)
{
	return false;
}
static bool io_rw_should_reissue(struct io_kiocb *req)
{
	return false;
}
#endif

static void kiocb_end_write(struct io_kiocb *req)
{
	/*
	 * Tell lockdep we inherited freeze protection from submission
	 * thread.
	 */
	if (req->flags & REQ_F_ISREG) {
		struct super_block *sb = file_inode(req->file)->i_sb;

		__sb_writers_acquired(sb, SB_FREEZE_WRITE);
		sb_end_write(sb);
	}
}

static bool __io_complete_rw_common(struct io_kiocb *req, long res)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);

	if (rw->kiocb.ki_flags & IOCB_WRITE) {
		kiocb_end_write(req);
		fsnotify_modify(req->file);
	} else {
		fsnotify_access(req->file);
	}
	if (unlikely(res != req->cqe.res)) {
		if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
		    io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
			return true;
		}
		req_set_fail(req);
		req->cqe.res = res;
	}
	return false;
}

static void io_complete_rw(struct kiocb *kiocb, long res)
{
	struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
	struct io_kiocb *req = cmd_to_io_kiocb(rw);

	if (__io_complete_rw_common(req, res))
		return;
	io_req_set_res(req, res, 0);
	req->io_task_work.func = io_req_task_complete;
	io_req_task_prio_work_add(req);
}

static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
{
	struct io_rw *rw = container_of(kiocb, struct io_rw, kiocb);
	struct io_kiocb *req = cmd_to_io_kiocb(rw);

	if (kiocb->ki_flags & IOCB_WRITE)
		kiocb_end_write(req);
	if (unlikely(res != req->cqe.res)) {
		if (res == -EAGAIN && io_rw_should_reissue(req)) {
			req->flags |= REQ_F_REISSUE | REQ_F_PARTIAL_IO;
			return;
		}
		req->cqe.res = res;
	}

	/* order with io_iopoll_complete() checking ->iopoll_completed */
	smp_store_release(&req->iopoll_completed, 1);
}

static int kiocb_done(struct io_kiocb *req, ssize_t ret,
		       unsigned int issue_flags)
{
	struct io_async_rw *io = req->async_data;
	struct io_rw *rw = io_kiocb_to_cmd(req);

	/* add previously done IO, if any */
	if (req_has_async_data(req) && io->bytes_done > 0) {
		if (ret < 0)
			ret = io->bytes_done;
		else
			ret += io->bytes_done;
	}

	if (req->flags & REQ_F_CUR_POS)
		req->file->f_pos = rw->kiocb.ki_pos;
	if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) {
		if (!__io_complete_rw_common(req, ret)) {
			io_req_set_res(req, req->cqe.res,
				       io_put_kbuf(req, issue_flags));
			return IOU_OK;
		}
	} else {
		io_rw_done(&rw->kiocb, ret);
	}

	if (req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		if (io_resubmit_prep(req))
			io_req_task_queue_reissue(req);
		else
			io_req_task_queue_fail(req, ret);
	}
	return IOU_ISSUE_SKIP_COMPLETE;
}

static int __io_import_fixed(struct io_kiocb *req, int ddir,
			     struct iov_iter *iter, struct io_mapped_ubuf *imu)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	size_t len = rw->len;
	u64 buf_end, buf_addr = rw->addr;
	size_t offset;

	if (unlikely(check_add_overflow(buf_addr, (u64)len, &buf_end)))
		return -EFAULT;
	/* not inside the mapped region */
	if (unlikely(buf_addr < imu->ubuf || buf_end > imu->ubuf_end))
		return -EFAULT;

	/*
	 * May not be a start of buffer, set size appropriately
	 * and advance us to the beginning.
	 */
	offset = buf_addr - imu->ubuf;
	iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len);

	if (offset) {
		/*
		 * Don't use iov_iter_advance() here, as it's really slow for
		 * using the latter parts of a big fixed buffer - it iterates
		 * over each segment manually. We can cheat a bit here, because
		 * we know that:
		 *
		 * 1) it's a BVEC iter, we set it up
		 * 2) all bvecs are PAGE_SIZE in size, except potentially the
		 *    first and last bvec
		 *
		 * So just find our index, and adjust the iterator afterwards.
		 * If the offset is within the first bvec (or the whole first
		 * bvec, just use iov_iter_advance(). This makes it easier
		 * since we can just skip the first segment, which may not
		 * be PAGE_SIZE aligned.
		 */
		const struct bio_vec *bvec = imu->bvec;

		if (offset <= bvec->bv_len) {
			iov_iter_advance(iter, offset);
		} else {
			unsigned long seg_skip;

			/* skip first vec */
			offset -= bvec->bv_len;
			seg_skip = 1 + (offset >> PAGE_SHIFT);

			iter->bvec = bvec + seg_skip;
			iter->nr_segs -= seg_skip;
			iter->count -= bvec->bv_len + offset;
			iter->iov_offset = offset & ~PAGE_MASK;
		}
	}

	return 0;
}

static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter,
			   unsigned int issue_flags)
{
	if (WARN_ON_ONCE(!req->imu))
		return -EFAULT;
	return __io_import_fixed(req, rw, iter, req->imu);
}

#ifdef CONFIG_COMPAT
static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
				unsigned int issue_flags)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct compat_iovec __user *uiov;
	compat_ssize_t clen;
	void __user *buf;
	size_t len;

	uiov = u64_to_user_ptr(rw->addr);
	if (!access_ok(uiov, sizeof(*uiov)))
		return -EFAULT;
	if (__get_user(clen, &uiov->iov_len))
		return -EFAULT;
	if (clen < 0)
		return -EINVAL;

	len = clen;
	buf = io_buffer_select(req, &len, issue_flags);
	if (!buf)
		return -ENOBUFS;
	rw->addr = (unsigned long) buf;
	iov[0].iov_base = buf;
	rw->len = iov[0].iov_len = (compat_size_t) len;
	return 0;
}
#endif

static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				      unsigned int issue_flags)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct iovec __user *uiov = u64_to_user_ptr(rw->addr);
	void __user *buf;
	ssize_t len;

	if (copy_from_user(iov, uiov, sizeof(*uiov)))
		return -EFAULT;

	len = iov[0].iov_len;
	if (len < 0)
		return -EINVAL;
	buf = io_buffer_select(req, &len, issue_flags);
	if (!buf)
		return -ENOBUFS;
	rw->addr = (unsigned long) buf;
	iov[0].iov_base = buf;
	rw->len = iov[0].iov_len = len;
	return 0;
}

static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
				    unsigned int issue_flags)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);

	if (req->flags & (REQ_F_BUFFER_SELECTED|REQ_F_BUFFER_RING)) {
		iov[0].iov_base = u64_to_user_ptr(rw->addr);
		iov[0].iov_len = rw->len;
		return 0;
	}
	if (rw->len != 1)
		return -EINVAL;

#ifdef CONFIG_COMPAT
	if (req->ctx->compat)
		return io_compat_import(req, iov, issue_flags);
#endif

	return __io_iov_buffer_select(req, iov, issue_flags);
}

static struct iovec *__io_import_iovec(int ddir, struct io_kiocb *req,
				       struct io_rw_state *s,
				       unsigned int issue_flags)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct iov_iter *iter = &s->iter;
	u8 opcode = req->opcode;
	struct iovec *iovec;
	void __user *buf;
	size_t sqe_len;
	ssize_t ret;

	if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
		ret = io_import_fixed(req, ddir, iter, issue_flags);
		if (ret)
			return ERR_PTR(ret);
		return NULL;
	}

	buf = u64_to_user_ptr(rw->addr);
	sqe_len = rw->len;

	if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
		if (io_do_buffer_select(req)) {
			buf = io_buffer_select(req, &sqe_len, issue_flags);
			if (!buf)
				return ERR_PTR(-ENOBUFS);
			rw->addr = (unsigned long) buf;
			rw->len = sqe_len;
		}

		ret = import_single_range(ddir, buf, sqe_len, s->fast_iov, iter);
		if (ret)
			return ERR_PTR(ret);
		return NULL;
	}

	iovec = s->fast_iov;
	if (req->flags & REQ_F_BUFFER_SELECT) {
		ret = io_iov_buffer_select(req, iovec, issue_flags);
		if (ret)
			return ERR_PTR(ret);
		iov_iter_init(iter, ddir, iovec, 1, iovec->iov_len);
		return NULL;
	}

	ret = __import_iovec(ddir, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
			      req->ctx->compat);
	if (unlikely(ret < 0))
		return ERR_PTR(ret);
	return iovec;
}

static inline int io_import_iovec(int rw, struct io_kiocb *req,
				  struct iovec **iovec, struct io_rw_state *s,
				  unsigned int issue_flags)
{
	*iovec = __io_import_iovec(rw, req, s, issue_flags);
	if (unlikely(IS_ERR(*iovec)))
		return PTR_ERR(*iovec);

	iov_iter_save_state(&s->iter, &s->iter_state);
	return 0;
}

static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
{
	return (kiocb->ki_filp->f_mode & FMODE_STREAM) ? NULL : &kiocb->ki_pos;
}

/*
 * For files that don't have ->read_iter() and ->write_iter(), handle them
 * by looping over ->read() or ->write() manually.
 */
static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
{
	struct kiocb *kiocb = &rw->kiocb;
	struct file *file = kiocb->ki_filp;
	ssize_t ret = 0;
	loff_t *ppos;

	/*
	 * Don't support polled IO through this interface, and we can't
	 * support non-blocking either. For the latter, this just causes
	 * the kiocb to be handled from an async context.
	 */
	if (kiocb->ki_flags & IOCB_HIPRI)
		return -EOPNOTSUPP;
	if ((kiocb->ki_flags & IOCB_NOWAIT) &&
	    !(kiocb->ki_filp->f_flags & O_NONBLOCK))
		return -EAGAIN;

	ppos = io_kiocb_ppos(kiocb);

	while (iov_iter_count(iter)) {
		struct iovec iovec;
		ssize_t nr;

		if (!iov_iter_is_bvec(iter)) {
			iovec = iov_iter_iovec(iter);
		} else {
			iovec.iov_base = u64_to_user_ptr(rw->addr);
			iovec.iov_len = rw->len;
		}

		if (ddir == READ) {
			nr = file->f_op->read(file, iovec.iov_base,
					      iovec.iov_len, ppos);
		} else {
			nr = file->f_op->write(file, iovec.iov_base,
					       iovec.iov_len, ppos);
		}

		if (nr < 0) {
			if (!ret)
				ret = nr;
			break;
		}
		ret += nr;
		if (!iov_iter_is_bvec(iter)) {
			iov_iter_advance(iter, nr);
		} else {
			rw->addr += nr;
			rw->len -= nr;
			if (!rw->len)
				break;
		}
		if (nr != iovec.iov_len)
			break;
	}

	return ret;
}

static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
			  const struct iovec *fast_iov, struct iov_iter *iter)
{
	struct io_async_rw *io = req->async_data;

	memcpy(&io->s.iter, iter, sizeof(*iter));
	io->free_iovec = iovec;
	io->bytes_done = 0;
	/* can only be fixed buffers, no need to do anything */
	if (iov_iter_is_bvec(iter))
		return;
	if (!iovec) {
		unsigned iov_off = 0;

		io->s.iter.iov = io->s.fast_iov;
		if (iter->iov != fast_iov) {
			iov_off = iter->iov - fast_iov;
			io->s.iter.iov += iov_off;
		}
		if (io->s.fast_iov != fast_iov)
			memcpy(io->s.fast_iov + iov_off, fast_iov + iov_off,
			       sizeof(struct iovec) * iter->nr_segs);
	} else {
		req->flags |= REQ_F_NEED_CLEANUP;
	}
}

static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
			     struct io_rw_state *s, bool force)
{
	if (!force && !io_op_defs[req->opcode].prep_async)
		return 0;
	if (!req_has_async_data(req)) {
		struct io_async_rw *iorw;

		if (io_alloc_async_data(req)) {
			kfree(iovec);
			return -ENOMEM;
		}

		io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
		iorw = req->async_data;
		/* we've copied and mapped the iter, ensure state is saved */
		iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
	}
	return 0;
}

static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
{
	struct io_async_rw *iorw = req->async_data;
	struct iovec *iov;
	int ret;

	/* submission path, ->uring_lock should already be taken */
	ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
	if (unlikely(ret < 0))
		return ret;

	iorw->bytes_done = 0;
	iorw->free_iovec = iov;
	if (iov)
		req->flags |= REQ_F_NEED_CLEANUP;
	return 0;
}

int io_readv_prep_async(struct io_kiocb *req)
{
	return io_rw_prep_async(req, READ);
}

int io_writev_prep_async(struct io_kiocb *req)
{
	return io_rw_prep_async(req, WRITE);
}

/*
 * This is our waitqueue callback handler, registered through __folio_lock_async()
 * when we initially tried to do the IO with the iocb armed our waitqueue.
 * This gets called when the page is unlocked, and we generally expect that to
 * happen when the page IO is completed and the page is now uptodate. This will
 * queue a task_work based retry of the operation, attempting to copy the data
 * again. If the latter fails because the page was NOT uptodate, then we will
 * do a thread based blocking retry of the operation. That's the unexpected
 * slow path.
 */
static int io_async_buf_func(struct wait_queue_entry *wait, unsigned mode,
			     int sync, void *arg)
{
	struct wait_page_queue *wpq;
	struct io_kiocb *req = wait->private;
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct wait_page_key *key = arg;

	wpq = container_of(wait, struct wait_page_queue, wait);

	if (!wake_page_match(wpq, key))
		return 0;

	rw->kiocb.ki_flags &= ~IOCB_WAITQ;
	list_del_init(&wait->entry);
	io_req_task_queue(req);
	return 1;
}

/*
 * This controls whether a given IO request should be armed for async page
 * based retry. If we return false here, the request is handed to the async
 * worker threads for retry. If we're doing buffered reads on a regular file,
 * we prepare a private wait_page_queue entry and retry the operation. This
 * will either succeed because the page is now uptodate and unlocked, or it
 * will register a callback when the page is unlocked at IO completion. Through
 * that callback, io_uring uses task_work to setup a retry of the operation.
 * That retry will attempt the buffered read again. The retry will generally
 * succeed, or in rare cases where it fails, we then fall back to using the
 * async worker threads for a blocking retry.
 */
static bool io_rw_should_retry(struct io_kiocb *req)
{
	struct io_async_rw *io = req->async_data;
	struct wait_page_queue *wait = &io->wpq;
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct kiocb *kiocb = &rw->kiocb;

	/* never retry for NOWAIT, we just complete with -EAGAIN */
	if (req->flags & REQ_F_NOWAIT)
		return false;

	/* Only for buffered IO */
	if (kiocb->ki_flags & (IOCB_DIRECT | IOCB_HIPRI))
		return false;

	/*
	 * just use poll if we can, and don't attempt if the fs doesn't
	 * support callback based unlocks
	 */
	if (file_can_poll(req->file) || !(req->file->f_mode & FMODE_BUF_RASYNC))
		return false;

	wait->wait.func = io_async_buf_func;
	wait->wait.private = req;
	wait->wait.flags = 0;
	INIT_LIST_HEAD(&wait->wait.entry);
	kiocb->ki_flags |= IOCB_WAITQ;
	kiocb->ki_flags &= ~IOCB_NOWAIT;
	kiocb->ki_waitq = wait;
	return true;
}

static inline int io_iter_do_read(struct io_rw *rw, struct iov_iter *iter)
{
	struct file *file = rw->kiocb.ki_filp;

	if (likely(file->f_op->read_iter))
		return call_read_iter(file, &rw->kiocb, iter);
	else if (file->f_op->read)
		return loop_rw_iter(READ, rw, iter);
	else
		return -EINVAL;
}

static bool need_read_all(struct io_kiocb *req)
{
	return req->flags & REQ_F_ISREG ||
		S_ISBLK(file_inode(req->file)->i_mode);
}

static inline bool io_req_ffs_set(struct io_kiocb *req)
{
	return req->flags & REQ_F_FIXED_FILE;
}

static int io_rw_init_file(struct io_kiocb *req, fmode_t mode)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct kiocb *kiocb = &rw->kiocb;
	struct io_ring_ctx *ctx = req->ctx;
	struct file *file = req->file;
	int ret;

	if (unlikely(!file || !(file->f_mode & mode)))
		return -EBADF;

	if (!io_req_ffs_set(req))
		req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;

	kiocb->ki_flags = iocb_flags(file);
	ret = kiocb_set_rw_flags(kiocb, rw->flags);
	if (unlikely(ret))
		return ret;

	/*
	 * If the file is marked O_NONBLOCK, still allow retry for it if it
	 * supports async. Otherwise it's impossible to use O_NONBLOCK files
	 * reliably. If not, or it IOCB_NOWAIT is set, don't retry.
	 */
	if ((kiocb->ki_flags & IOCB_NOWAIT) ||
	    ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
		req->flags |= REQ_F_NOWAIT;

	if (ctx->flags & IORING_SETUP_IOPOLL) {
		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
			return -EOPNOTSUPP;

		kiocb->private = NULL;
		kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
		kiocb->ki_complete = io_complete_rw_iopoll;
		req->iopoll_completed = 0;
	} else {
		if (kiocb->ki_flags & IOCB_HIPRI)
			return -EINVAL;
		kiocb->ki_complete = io_complete_rw;
	}

	return 0;
}

int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct io_rw_state __s, *s = &__s;
	struct iovec *iovec;
	struct kiocb *kiocb = &rw->kiocb;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	struct io_async_rw *io;
	ssize_t ret, ret2;
	loff_t *ppos;

	if (!req_has_async_data(req)) {
		ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
		if (unlikely(ret < 0))
			return ret;
	} else {
		/*
		 * Safe and required to re-import if we're using provided
		 * buffers, as we dropped the selected one before retry.
		 */
		if (req->flags & REQ_F_BUFFER_SELECT) {
			ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
			if (unlikely(ret < 0))
				return ret;
		}

		io = req->async_data;
		s = &io->s;
		/*
		 * We come here from an earlier attempt, restore our state to
		 * match in case it doesn't. It's cheap enough that we don't
		 * need to make this conditional.
		 */
		iov_iter_restore(&s->iter, &s->iter_state);
		iovec = NULL;
	}
	ret = io_rw_init_file(req, FMODE_READ);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}
	req->cqe.res = iov_iter_count(&s->iter);

	if (force_nonblock) {
		/* If the file doesn't support async, just async punt */
		if (unlikely(!io_file_supports_nowait(req))) {
			ret = io_setup_async_rw(req, iovec, s, true);
			return ret ?: -EAGAIN;
		}
		kiocb->ki_flags |= IOCB_NOWAIT;
	} else {
		/* Ensure we clear previously set non-block flag */
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	}

	ppos = io_kiocb_update_pos(req);

	ret = rw_verify_area(READ, req->file, ppos, req->cqe.res);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}

	ret = io_iter_do_read(rw, &s->iter);

	if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
		req->flags &= ~REQ_F_REISSUE;
		/* if we can poll, just do that */
		if (req->opcode == IORING_OP_READ && file_can_poll(req->file))
			return -EAGAIN;
		/* IOPOLL retry should happen for io-wq threads */
		if (!force_nonblock && !(req->ctx->flags & IORING_SETUP_IOPOLL))
			goto done;
		/* no retry on NONBLOCK nor RWF_NOWAIT */
		if (req->flags & REQ_F_NOWAIT)
			goto done;
		ret = 0;
	} else if (ret == -EIOCBQUEUED) {
		if (iovec)
			kfree(iovec);
		return IOU_ISSUE_SKIP_COMPLETE;
	} else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
		   (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
		/* read all, failed, already did sync or don't want to retry */
		goto done;
	}

	/*
	 * Don't depend on the iter state matching what was consumed, or being
	 * untouched in case of error. Restore it and we'll advance it
	 * manually if we need to.
	 */
	iov_iter_restore(&s->iter, &s->iter_state);

	ret2 = io_setup_async_rw(req, iovec, s, true);
	if (ret2)
		return ret2;

	iovec = NULL;
	io = req->async_data;
	s = &io->s;
	/*
	 * Now use our persistent iterator and state, if we aren't already.
	 * We've restored and mapped the iter to match.
	 */

	do {
		/*
		 * We end up here because of a partial read, either from
		 * above or inside this loop. Advance the iter by the bytes
		 * that were consumed.
		 */
		iov_iter_advance(&s->iter, ret);
		if (!iov_iter_count(&s->iter))
			break;
		io->bytes_done += ret;
		iov_iter_save_state(&s->iter, &s->iter_state);

		/* if we can retry, do so with the callbacks armed */
		if (!io_rw_should_retry(req)) {
			kiocb->ki_flags &= ~IOCB_WAITQ;
			return -EAGAIN;
		}

		/*
		 * Now retry read with the IOCB_WAITQ parts set in the iocb. If
		 * we get -EIOCBQUEUED, then we'll get a notification when the
		 * desired page gets unlocked. We can also get a partial read
		 * here, and if we do, then just retry at the new offset.
		 */
		ret = io_iter_do_read(rw, &s->iter);
		if (ret == -EIOCBQUEUED)
			return IOU_ISSUE_SKIP_COMPLETE;
		/* we got some bytes, but not all. retry. */
		kiocb->ki_flags &= ~IOCB_WAITQ;
		iov_iter_restore(&s->iter, &s->iter_state);
	} while (ret > 0);
done:
	/* it's faster to check here then delegate to kfree */
	if (iovec)
		kfree(iovec);
	return kiocb_done(req, ret, issue_flags);
}

int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
	struct io_rw *rw = io_kiocb_to_cmd(req);
	struct io_rw_state __s, *s = &__s;
	struct iovec *iovec;
	struct kiocb *kiocb = &rw->kiocb;
	bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
	ssize_t ret, ret2;
	loff_t *ppos;

	if (!req_has_async_data(req)) {
		ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
		if (unlikely(ret < 0))
			return ret;
	} else {
		struct io_async_rw *io = req->async_data;

		s = &io->s;
		iov_iter_restore(&s->iter, &s->iter_state);
		iovec = NULL;
	}
	ret = io_rw_init_file(req, FMODE_WRITE);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}
	req->cqe.res = iov_iter_count(&s->iter);

	if (force_nonblock) {
		/* If the file doesn't support async, just async punt */
		if (unlikely(!io_file_supports_nowait(req)))
			goto copy_iov;

		/* file path doesn't support NOWAIT for non-direct_IO */
		if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
		    (req->flags & REQ_F_ISREG))
			goto copy_iov;

		kiocb->ki_flags |= IOCB_NOWAIT;
	} else {
		/* Ensure we clear previously set non-block flag */
		kiocb->ki_flags &= ~IOCB_NOWAIT;
	}

	ppos = io_kiocb_update_pos(req);

	ret = rw_verify_area(WRITE, req->file, ppos, req->cqe.res);
	if (unlikely(ret)) {
		kfree(iovec);
		return ret;
	}

	/*
	 * Open-code file_start_write here to grab freeze protection,
	 * which will be released by another thread in
	 * io_complete_rw().  Fool lockdep by telling it the lock got
	 * released so that it doesn't complain about the held lock when
	 * we return to userspace.
	 */
	if (req->flags & REQ_F_ISREG) {
		sb_start_write(file_inode(req->file)->i_sb);
		__sb_writers_release(file_inode(req->file)->i_sb,
					SB_FREEZE_WRITE);
	}
	kiocb->ki_flags |= IOCB_WRITE;

	if (likely(req->file->f_op->write_iter))
		ret2 = call_write_iter(req->file, kiocb, &s->iter);
	else if (req->file->f_op->write)
		ret2 = loop_rw_iter(WRITE, rw, &s->iter);
	else
		ret2 = -EINVAL;

	if (req->flags & REQ_F_REISSUE) {
		req->flags &= ~REQ_F_REISSUE;
		ret2 = -EAGAIN;
	}

	/*
	 * Raw bdev writes will return -EOPNOTSUPP for IOCB_NOWAIT. Just
	 * retry them without IOCB_NOWAIT.
	 */
	if (ret2 == -EOPNOTSUPP && (kiocb->ki_flags & IOCB_NOWAIT))
		ret2 = -EAGAIN;
	/* no retry on NONBLOCK nor RWF_NOWAIT */
	if (ret2 == -EAGAIN && (req->flags & REQ_F_NOWAIT))
		goto done;
	if (!force_nonblock || ret2 != -EAGAIN) {
		/* IOPOLL retry should happen for io-wq threads */
		if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
			goto copy_iov;
done:
		ret = kiocb_done(req, ret2, issue_flags);
	} else {
copy_iov:
		iov_iter_restore(&s->iter, &s->iter_state);
		ret = io_setup_async_rw(req, iovec, s, false);
		return ret ?: -EAGAIN;
	}
	/* it's reportedly faster than delegating the null check to kfree() */
	if (iovec)
		kfree(iovec);
	return ret;
}

static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
{
	if (unlikely(ctx->off_timeout_used || ctx->drain_active ||
		     ctx->has_evfd))
		__io_commit_cqring_flush(ctx);

	if (ctx->flags & IORING_SETUP_SQPOLL)
		io_cqring_wake(ctx);
}

int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
{
	struct io_wq_work_node *pos, *start, *prev;
	unsigned int poll_flags = BLK_POLL_NOSLEEP;
	DEFINE_IO_COMP_BATCH(iob);
	int nr_events = 0;

	/*
	 * Only spin for completions if we don't have multiple devices hanging
	 * off our complete list.
	 */
	if (ctx->poll_multi_queue || force_nonspin)
		poll_flags |= BLK_POLL_ONESHOT;

	wq_list_for_each(pos, start, &ctx->iopoll_list) {
		struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
		struct io_rw *rw = io_kiocb_to_cmd(req);
		int ret;

		/*
		 * Move completed and retryable entries to our local lists.
		 * If we find a request that requires polling, break out
		 * and complete those lists first, if we have entries there.
		 */
		if (READ_ONCE(req->iopoll_completed))
			break;

		ret = rw->kiocb.ki_filp->f_op->iopoll(&rw->kiocb, &iob, poll_flags);
		if (unlikely(ret < 0))
			return ret;
		else if (ret)
			poll_flags |= BLK_POLL_ONESHOT;

		/* iopoll may have completed current req */
		if (!rq_list_empty(iob.req_list) ||
		    READ_ONCE(req->iopoll_completed))
			break;
	}

	if (!rq_list_empty(iob.req_list))
		iob.complete(&iob);
	else if (!pos)
		return 0;

	prev = start;
	wq_list_for_each_resume(pos, prev) {
		struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);

		/* order with io_complete_rw_iopoll(), e.g. ->result updates */
		if (!smp_load_acquire(&req->iopoll_completed))
			break;
		nr_events++;
		if (unlikely(req->flags & REQ_F_CQE_SKIP))
			continue;

		req->cqe.flags = io_put_kbuf(req, 0);
		__io_fill_cqe_req(req->ctx, req);
	}

	if (unlikely(!nr_events))
		return 0;

	io_commit_cqring(ctx);
	io_cqring_ev_posted_iopoll(ctx);
	pos = start ? start->next : ctx->iopoll_list.first;
	wq_list_cut(&ctx->iopoll_list, prev, start);
	io_free_batch_list(ctx, pos);
	return nr_events;
}