forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
io_uring.c
4619 lines (3981 loc) · 120 KB
/
io_uring.c
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
// SPDX-License-Identifier: GPL-2.0
/*
* Shared application/kernel submission and completion ring pairs, for
* supporting fast/efficient IO.
*
* A note on the read/write ordering memory barriers that are matched between
* the application and kernel side.
*
* After the application reads the CQ ring tail, it must use an
* appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
* before writing the tail (using smp_load_acquire to read the tail will
* do). It also needs a smp_mb() before updating CQ head (ordering the
* entry load(s) with the head store), pairing with an implicit barrier
* through a control-dependency in io_get_cqe (smp_store_release to
* store head will do). Failure to do so could lead to reading invalid
* CQ entries.
*
* Likewise, the application must use an appropriate smp_wmb() before
* writing the SQ tail (ordering SQ entry stores with the tail store),
* which pairs with smp_load_acquire in io_get_sqring (smp_store_release
* to store the tail will do). And it needs a barrier ordering the SQ
* head load before writing new SQ entries (smp_load_acquire to read
* head will do).
*
* When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
* needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
* updating the SQ tail; a full memory barrier smp_mb() is needed
* between.
*
* Also see the examples in the liburing library:
*
* git://git.kernel.dk/liburing
*
* io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
* from data shared between the kernel and application. This is done both
* for ordering purposes, but also to ensure that once a value is loaded from
* data that the application could potentially modify, it remains stable.
*
* Copyright (C) 2018-2019 Jens Axboe
* Copyright (c) 2018-2019 Christoph Hellwig
*/
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/syscalls.h>
#include <net/compat.h>
#include <linux/refcount.h>
#include <linux/uio.h>
#include <linux/bits.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/bvec.h>
#include <linux/net.h>
#include <net/sock.h>
#include <net/af_unix.h>
#include <net/scm.h>
#include <linux/anon_inodes.h>
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
#include <linux/highmem.h>
#include <linux/fsnotify.h>
#include <linux/fadvise.h>
#include <linux/task_work.h>
#include <linux/io_uring.h>
#include <linux/audit.h>
#include <linux/security.h>
#include <asm/shmparam.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
#include <uapi/linux/io_uring.h>
#include "io-wq.h"
#include "io_uring.h"
#include "opdef.h"
#include "refs.h"
#include "tctx.h"
#include "sqpoll.h"
#include "fdinfo.h"
#include "kbuf.h"
#include "rsrc.h"
#include "cancel.h"
#include "net.h"
#include "notif.h"
#include "timeout.h"
#include "poll.h"
#include "rw.h"
#include "alloc_cache.h"
#define IORING_MAX_ENTRIES 32768
#define IORING_MAX_CQ_ENTRIES (2 * IORING_MAX_ENTRIES)
#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \
IORING_REGISTER_LAST + IORING_OP_LAST)
#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
IOSQE_IO_HARDLINK | IOSQE_ASYNC)
#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS | IOSQE_BUFFER_SELECT | \
IOSQE_IO_DRAIN | IOSQE_CQE_SKIP_SUCCESS)
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
REQ_F_ASYNC_DATA)
#define IO_REQ_CLEAN_SLOW_FLAGS (REQ_F_REFCOUNT | REQ_F_LINK | REQ_F_HARDLINK |\
IO_REQ_CLEAN_FLAGS)
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
#define IO_COMPL_BATCH 32
#define IO_REQ_ALLOC_BATCH 8
enum {
IO_CHECK_CQ_OVERFLOW_BIT,
IO_CHECK_CQ_DROPPED_BIT,
};
enum {
IO_EVENTFD_OP_SIGNAL_BIT,
IO_EVENTFD_OP_FREE_BIT,
};
struct io_defer_entry {
struct list_head list;
struct io_kiocb *req;
u32 seq;
};
/* requests with any of those set should undergo io_disarm_next() */
#define IO_DISARM_MASK (REQ_F_ARM_LTIMEOUT | REQ_F_LINK_TIMEOUT | REQ_F_FAIL)
#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
struct task_struct *task,
bool cancel_all);
static void io_queue_sqe(struct io_kiocb *req);
static void io_move_task_work_from_local(struct io_ring_ctx *ctx);
static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
struct kmem_cache *req_cachep;
struct sock *io_uring_get_socket(struct file *file)
{
#if defined(CONFIG_UNIX)
if (io_is_uring_fops(file)) {
struct io_ring_ctx *ctx = file->private_data;
return ctx->ring_sock->sk;
}
#endif
return NULL;
}
EXPORT_SYMBOL(io_uring_get_socket);
static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
{
if (!wq_list_empty(&ctx->submit_state.compl_reqs) ||
ctx->submit_state.cqes_count)
__io_submit_flush_completions(ctx);
}
static inline unsigned int __io_cqring_events(struct io_ring_ctx *ctx)
{
return ctx->cached_cq_tail - READ_ONCE(ctx->rings->cq.head);
}
static inline unsigned int __io_cqring_events_user(struct io_ring_ctx *ctx)
{
return READ_ONCE(ctx->rings->cq.tail) - READ_ONCE(ctx->rings->cq.head);
}
static bool io_match_linked(struct io_kiocb *head)
{
struct io_kiocb *req;
io_for_each_link(req, head) {
if (req->flags & REQ_F_INFLIGHT)
return true;
}
return false;
}
/*
* As io_match_task() but protected against racing with linked timeouts.
* User must not hold timeout_lock.
*/
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all)
{
bool matched;
if (task && head->task != task)
return false;
if (cancel_all)
return true;
if (head->flags & REQ_F_LINK_TIMEOUT) {
struct io_ring_ctx *ctx = head->ctx;
/* protect against races with linked timeouts */
spin_lock_irq(&ctx->timeout_lock);
matched = io_match_linked(head);
spin_unlock_irq(&ctx->timeout_lock);
} else {
matched = io_match_linked(head);
}
return matched;
}
static inline void req_fail_link_node(struct io_kiocb *req, int res)
{
req_set_fail(req);
io_req_set_res(req, res, 0);
}
static inline void io_req_add_to_cache(struct io_kiocb *req, struct io_ring_ctx *ctx)
{
wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
kasan_poison_object_data(req_cachep, req);
}
static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
complete(&ctx->ref_comp);
}
static __cold void io_fallback_req_func(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
fallback_work.work);
struct llist_node *node = llist_del_all(&ctx->fallback_llist);
struct io_kiocb *req, *tmp;
struct io_tw_state ts = { .locked = true, };
mutex_lock(&ctx->uring_lock);
llist_for_each_entry_safe(req, tmp, node, io_task_work.node)
req->io_task_work.func(req, &ts);
if (WARN_ON_ONCE(!ts.locked))
return;
io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
}
static int io_alloc_hash_table(struct io_hash_table *table, unsigned bits)
{
unsigned hash_buckets = 1U << bits;
size_t hash_size = hash_buckets * sizeof(table->hbs[0]);
table->hbs = kmalloc(hash_size, GFP_KERNEL);
if (!table->hbs)
return -ENOMEM;
table->hash_bits = bits;
init_hash_table(table, hash_buckets);
return 0;
}
static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
int hash_bits;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return NULL;
xa_init(&ctx->io_bl_xa);
/*
* Use 5 bits less than the max cq entries, that should give us around
* 32 entries per hash list if totally full and uniformly spread, but
* don't keep too many buckets to not overconsume memory.
*/
hash_bits = ilog2(p->cq_entries) - 5;
hash_bits = clamp(hash_bits, 1, 8);
if (io_alloc_hash_table(&ctx->cancel_table, hash_bits))
goto err;
if (io_alloc_hash_table(&ctx->cancel_table_locked, hash_bits))
goto err;
ctx->dummy_ubuf = kzalloc(sizeof(*ctx->dummy_ubuf), GFP_KERNEL);
if (!ctx->dummy_ubuf)
goto err;
/* set invalid range, so io_import_fixed() fails meeting it */
ctx->dummy_ubuf->ubuf = -1UL;
if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free,
0, GFP_KERNEL))
goto err;
ctx->flags = p->flags;
init_waitqueue_head(&ctx->sqo_sq_wait);
INIT_LIST_HEAD(&ctx->sqd_list);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
INIT_LIST_HEAD(&ctx->io_buffers_cache);
io_alloc_cache_init(&ctx->rsrc_node_cache, IO_NODE_ALLOC_CACHE_MAX,
sizeof(struct io_rsrc_node));
io_alloc_cache_init(&ctx->apoll_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct async_poll));
io_alloc_cache_init(&ctx->netmsg_cache, IO_ALLOC_CACHE_MAX,
sizeof(struct io_async_msghdr));
init_completion(&ctx->ref_comp);
xa_init_flags(&ctx->personalities, XA_FLAGS_ALLOC1);
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->cq_wait);
init_waitqueue_head(&ctx->poll_wq);
init_waitqueue_head(&ctx->rsrc_quiesce_wq);
spin_lock_init(&ctx->completion_lock);
spin_lock_init(&ctx->timeout_lock);
INIT_WQ_LIST(&ctx->iopoll_list);
INIT_LIST_HEAD(&ctx->io_buffers_pages);
INIT_LIST_HEAD(&ctx->io_buffers_comp);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
INIT_LIST_HEAD(&ctx->ltimeout_list);
INIT_LIST_HEAD(&ctx->rsrc_ref_list);
init_llist_head(&ctx->work_llist);
INIT_LIST_HEAD(&ctx->tctx_list);
ctx->submit_state.free_list.next = NULL;
INIT_WQ_LIST(&ctx->locked_free_list);
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
return ctx;
err:
kfree(ctx->dummy_ubuf);
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
kfree(ctx->io_bl);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
return NULL;
}
static void io_account_cq_overflow(struct io_ring_ctx *ctx)
{
struct io_rings *r = ctx->rings;
WRITE_ONCE(r->cq_overflow, READ_ONCE(r->cq_overflow) + 1);
ctx->cq_extra--;
}
static bool req_need_defer(struct io_kiocb *req, u32 seq)
{
if (unlikely(req->flags & REQ_F_IO_DRAIN)) {
struct io_ring_ctx *ctx = req->ctx;
return seq + READ_ONCE(ctx->cq_extra) != ctx->cached_cq_tail;
}
return false;
}
static void io_clean_op(struct io_kiocb *req)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
spin_lock(&req->ctx->completion_lock);
io_put_kbuf_comp(req);
spin_unlock(&req->ctx->completion_lock);
}
if (req->flags & REQ_F_NEED_CLEANUP) {
const struct io_cold_def *def = &io_cold_defs[req->opcode];
if (def->cleanup)
def->cleanup(req);
}
if ((req->flags & REQ_F_POLLED) && req->apoll) {
kfree(req->apoll->double_poll);
kfree(req->apoll);
req->apoll = NULL;
}
if (req->flags & REQ_F_INFLIGHT) {
struct io_uring_task *tctx = req->task->io_uring;
atomic_dec(&tctx->inflight_tracked);
}
if (req->flags & REQ_F_CREDS)
put_cred(req->creds);
if (req->flags & REQ_F_ASYNC_DATA) {
kfree(req->async_data);
req->async_data = NULL;
}
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
static inline void io_req_track_inflight(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_INFLIGHT)) {
req->flags |= REQ_F_INFLIGHT;
atomic_inc(&req->task->io_uring->inflight_tracked);
}
}
static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
if (WARN_ON_ONCE(!req->link))
return NULL;
req->flags &= ~REQ_F_ARM_LTIMEOUT;
req->flags |= REQ_F_LINK_TIMEOUT;
/* linked timeouts should have two refs once prep'ed */
io_req_set_refcount(req);
__io_req_set_refcount(req->link, 2);
return req->link;
}
static inline struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req)
{
if (likely(!(req->flags & REQ_F_ARM_LTIMEOUT)))
return NULL;
return __io_prep_linked_timeout(req);
}
static noinline void __io_arm_ltimeout(struct io_kiocb *req)
{
io_queue_linked_timeout(__io_prep_linked_timeout(req));
}
static inline void io_arm_ltimeout(struct io_kiocb *req)
{
if (unlikely(req->flags & REQ_F_ARM_LTIMEOUT))
__io_arm_ltimeout(req);
}
static void io_prep_async_work(struct io_kiocb *req)
{
const struct io_issue_def *def = &io_issue_defs[req->opcode];
struct io_ring_ctx *ctx = req->ctx;
if (!(req->flags & REQ_F_CREDS)) {
req->flags |= REQ_F_CREDS;
req->creds = get_current_cred();
}
req->work.list.next = NULL;
req->work.flags = 0;
req->work.cancel_seq = atomic_read(&ctx->cancel_seq);
if (req->flags & REQ_F_FORCE_ASYNC)
req->work.flags |= IO_WQ_WORK_CONCURRENT;
if (req->file && !(req->flags & REQ_F_FIXED_FILE))
req->flags |= io_file_get_flags(req->file);
if (req->file && (req->flags & REQ_F_ISREG)) {
bool should_hash = def->hash_reg_file;
/* don't serialize this request if the fs doesn't need it */
if (should_hash && (req->file->f_flags & O_DIRECT) &&
(req->file->f_mode & FMODE_DIO_PARALLEL_WRITE))
should_hash = false;
if (should_hash || (ctx->flags & IORING_SETUP_IOPOLL))
io_wq_hash_work(&req->work, file_inode(req->file));
} else if (!req->file || !S_ISBLK(file_inode(req->file)->i_mode)) {
if (def->unbound_nonreg_file)
req->work.flags |= IO_WQ_WORK_UNBOUND;
}
}
static void io_prep_async_link(struct io_kiocb *req)
{
struct io_kiocb *cur;
if (req->flags & REQ_F_LINK_TIMEOUT) {
struct io_ring_ctx *ctx = req->ctx;
spin_lock_irq(&ctx->timeout_lock);
io_for_each_link(cur, req)
io_prep_async_work(cur);
spin_unlock_irq(&ctx->timeout_lock);
} else {
io_for_each_link(cur, req)
io_prep_async_work(cur);
}
}
void io_queue_iowq(struct io_kiocb *req, struct io_tw_state *ts_dont_use)
{
struct io_kiocb *link = io_prep_linked_timeout(req);
struct io_uring_task *tctx = req->task->io_uring;
BUG_ON(!tctx);
BUG_ON(!tctx->io_wq);
/* init ->work of the whole link before punting */
io_prep_async_link(req);
/*
* Not expected to happen, but if we do have a bug where this _can_
* happen, catch it here and ensure the request is marked as
* canceled. That will make io-wq go through the usual work cancel
* procedure rather than attempt to run this request (or create a new
* worker for it).
*/
if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
req->work.flags |= IO_WQ_WORK_CANCEL;
trace_io_uring_queue_async_work(req, io_wq_is_hashed(&req->work));
io_wq_enqueue(tctx->io_wq, &req->work);
if (link)
io_queue_linked_timeout(link);
}
static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
{
while (!list_empty(&ctx->defer_list)) {
struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
struct io_defer_entry, list);
if (req_need_defer(de->req, de->seq))
break;
list_del_init(&de->list);
io_req_task_queue(de->req);
kfree(de);
}
}
static void io_eventfd_ops(struct rcu_head *rcu)
{
struct io_ev_fd *ev_fd = container_of(rcu, struct io_ev_fd, rcu);
int ops = atomic_xchg(&ev_fd->ops, 0);
if (ops & BIT(IO_EVENTFD_OP_SIGNAL_BIT))
eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
/* IO_EVENTFD_OP_FREE_BIT may not be set here depending on callback
* ordering in a race but if references are 0 we know we have to free
* it regardless.
*/
if (atomic_dec_and_test(&ev_fd->refs)) {
eventfd_ctx_put(ev_fd->cq_ev_fd);
kfree(ev_fd);
}
}
static void io_eventfd_signal(struct io_ring_ctx *ctx)
{
struct io_ev_fd *ev_fd = NULL;
rcu_read_lock();
/*
* rcu_dereference ctx->io_ev_fd once and use it for both for checking
* and eventfd_signal
*/
ev_fd = rcu_dereference(ctx->io_ev_fd);
/*
* Check again if ev_fd exists incase an io_eventfd_unregister call
* completed between the NULL check of ctx->io_ev_fd at the start of
* the function and rcu_read_lock.
*/
if (unlikely(!ev_fd))
goto out;
if (READ_ONCE(ctx->rings->cq_flags) & IORING_CQ_EVENTFD_DISABLED)
goto out;
if (ev_fd->eventfd_async && !io_wq_current_is_worker())
goto out;
if (likely(eventfd_signal_allowed())) {
eventfd_signal_mask(ev_fd->cq_ev_fd, 1, EPOLL_URING_WAKE);
} else {
atomic_inc(&ev_fd->refs);
if (!atomic_fetch_or(BIT(IO_EVENTFD_OP_SIGNAL_BIT), &ev_fd->ops))
call_rcu_hurry(&ev_fd->rcu, io_eventfd_ops);
else
atomic_dec(&ev_fd->refs);
}
out:
rcu_read_unlock();
}
static void io_eventfd_flush_signal(struct io_ring_ctx *ctx)
{
bool skip;
spin_lock(&ctx->completion_lock);
/*
* Eventfd should only get triggered when at least one event has been
* posted. Some applications rely on the eventfd notification count
* only changing IFF a new CQE has been added to the CQ ring. There's
* no depedency on 1:1 relationship between how many times this
* function is called (and hence the eventfd count) and number of CQEs
* posted to the CQ ring.
*/
skip = ctx->cached_cq_tail == ctx->evfd_last_cq_tail;
ctx->evfd_last_cq_tail = ctx->cached_cq_tail;
spin_unlock(&ctx->completion_lock);
if (skip)
return;
io_eventfd_signal(ctx);
}
void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
if (ctx->poll_activated)
io_poll_wq_wake(ctx);
if (ctx->off_timeout_used)
io_flush_timeouts(ctx);
if (ctx->drain_active) {
spin_lock(&ctx->completion_lock);
io_queue_deferred(ctx);
spin_unlock(&ctx->completion_lock);
}
if (ctx->has_evfd)
io_eventfd_flush_signal(ctx);
}
static inline void __io_cq_lock(struct io_ring_ctx *ctx)
{
if (!ctx->task_complete)
spin_lock(&ctx->completion_lock);
}
static inline void io_cq_lock(struct io_ring_ctx *ctx)
__acquires(ctx->completion_lock)
{
spin_lock(&ctx->completion_lock);
}
static inline void __io_cq_unlock_post(struct io_ring_ctx *ctx)
{
io_commit_cqring(ctx);
if (ctx->task_complete) {
/*
* ->task_complete implies that only current might be waiting
* for CQEs, and obviously, we currently don't. No one is
* waiting, wakeups are futile, skip them.
*/
io_commit_cqring_flush(ctx);
} else {
spin_unlock(&ctx->completion_lock);
io_commit_cqring_flush(ctx);
io_cqring_wake(ctx);
}
}
static void io_cq_unlock_post(struct io_ring_ctx *ctx)
__releases(ctx->completion_lock)
{
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_commit_cqring_flush(ctx);
io_cqring_wake(ctx);
}
/* Returns true if there are no backlogged entries after the flush */
static void io_cqring_overflow_kill(struct io_ring_ctx *ctx)
{
struct io_overflow_cqe *ocqe;
LIST_HEAD(list);
spin_lock(&ctx->completion_lock);
list_splice_init(&ctx->cq_overflow_list, &list);
clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
spin_unlock(&ctx->completion_lock);
while (!list_empty(&list)) {
ocqe = list_first_entry(&list, struct io_overflow_cqe, list);
list_del(&ocqe->list);
kfree(ocqe);
}
}
static void __io_cqring_overflow_flush(struct io_ring_ctx *ctx)
{
size_t cqe_size = sizeof(struct io_uring_cqe);
if (__io_cqring_events(ctx) == ctx->cq_entries)
return;
if (ctx->flags & IORING_SETUP_CQE32)
cqe_size <<= 1;
io_cq_lock(ctx);
while (!list_empty(&ctx->cq_overflow_list)) {
struct io_uring_cqe *cqe = io_get_cqe_overflow(ctx, true);
struct io_overflow_cqe *ocqe;
if (!cqe)
break;
ocqe = list_first_entry(&ctx->cq_overflow_list,
struct io_overflow_cqe, list);
memcpy(cqe, &ocqe->cqe, cqe_size);
list_del(&ocqe->list);
kfree(ocqe);
}
if (list_empty(&ctx->cq_overflow_list)) {
clear_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
atomic_andnot(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
}
io_cq_unlock_post(ctx);
}
static void io_cqring_do_overflow_flush(struct io_ring_ctx *ctx)
{
/* iopoll syncs against uring_lock, not completion_lock */
if (ctx->flags & IORING_SETUP_IOPOLL)
mutex_lock(&ctx->uring_lock);
__io_cqring_overflow_flush(ctx);
if (ctx->flags & IORING_SETUP_IOPOLL)
mutex_unlock(&ctx->uring_lock);
}
static void io_cqring_overflow_flush(struct io_ring_ctx *ctx)
{
if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
io_cqring_do_overflow_flush(ctx);
}
/* can be called by any task */
static void io_put_task_remote(struct task_struct *task)
{
struct io_uring_task *tctx = task->io_uring;
percpu_counter_sub(&tctx->inflight, 1);
if (unlikely(atomic_read(&tctx->in_cancel)))
wake_up(&tctx->wait);
put_task_struct(task);
}
/* used by a task to put its own references */
static void io_put_task_local(struct task_struct *task)
{
task->io_uring->cached_refs++;
}
/* must to be called somewhat shortly after putting a request */
static inline void io_put_task(struct task_struct *task)
{
if (likely(task == current))
io_put_task_local(task);
else
io_put_task_remote(task);
}
void io_task_refs_refill(struct io_uring_task *tctx)
{
unsigned int refill = -tctx->cached_refs + IO_TCTX_REFS_CACHE_NR;
percpu_counter_add(&tctx->inflight, refill);
refcount_add(refill, ¤t->usage);
tctx->cached_refs += refill;
}
static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
{
struct io_uring_task *tctx = task->io_uring;
unsigned int refs = tctx->cached_refs;
if (refs) {
tctx->cached_refs = 0;
percpu_counter_sub(&tctx->inflight, refs);
put_task_struct_many(task, refs);
}
}
static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
s32 res, u32 cflags, u64 extra1, u64 extra2)
{
struct io_overflow_cqe *ocqe;
size_t ocq_size = sizeof(struct io_overflow_cqe);
bool is_cqe32 = (ctx->flags & IORING_SETUP_CQE32);
lockdep_assert_held(&ctx->completion_lock);
if (is_cqe32)
ocq_size += sizeof(struct io_uring_cqe);
ocqe = kmalloc(ocq_size, GFP_ATOMIC | __GFP_ACCOUNT);
trace_io_uring_cqe_overflow(ctx, user_data, res, cflags, ocqe);
if (!ocqe) {
/*
* If we're in ring overflow flush mode, or in task cancel mode,
* or cannot allocate an overflow entry, then we need to drop it
* on the floor.
*/
io_account_cq_overflow(ctx);
set_bit(IO_CHECK_CQ_DROPPED_BIT, &ctx->check_cq);
return false;
}
if (list_empty(&ctx->cq_overflow_list)) {
set_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq);
atomic_or(IORING_SQ_CQ_OVERFLOW, &ctx->rings->sq_flags);
}
ocqe->cqe.user_data = user_data;
ocqe->cqe.res = res;
ocqe->cqe.flags = cflags;
if (is_cqe32) {
ocqe->cqe.big_cqe[0] = extra1;
ocqe->cqe.big_cqe[1] = extra2;
}
list_add_tail(&ocqe->list, &ctx->cq_overflow_list);
return true;
}
bool io_req_cqe_overflow(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_CQE32_INIT)) {
req->extra1 = 0;
req->extra2 = 0;
}
return io_cqring_event_overflow(req->ctx, req->cqe.user_data,
req->cqe.res, req->cqe.flags,
req->extra1, req->extra2);
}
/*
* writes to the cq entry need to come after reading head; the
* control dependency is enough as we're using WRITE_ONCE to
* fill the cq entry
*/
struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow)
{
struct io_rings *rings = ctx->rings;
unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
unsigned int free, queued, len;
/*
* Posting into the CQ when there are pending overflowed CQEs may break
* ordering guarantees, which will affect links, F_MORE users and more.
* Force overflow the completion.
*/
if (!overflow && (ctx->check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)))
return NULL;
/* userspace may cheat modifying the tail, be safe and do min */
queued = min(__io_cqring_events(ctx), ctx->cq_entries);
free = ctx->cq_entries - queued;
/* we need a contiguous range, limit based on the current array offset */
len = min(free, ctx->cq_entries - off);
if (!len)
return NULL;
if (ctx->flags & IORING_SETUP_CQE32) {
off <<= 1;
len <<= 1;
}
ctx->cqe_cached = &rings->cqes[off];
ctx->cqe_sentinel = ctx->cqe_cached + len;
ctx->cached_cq_tail++;
ctx->cqe_cached++;
if (ctx->flags & IORING_SETUP_CQE32)
ctx->cqe_cached++;
return &rings->cqes[off];
}
static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,
u32 cflags)
{
struct io_uring_cqe *cqe;
ctx->cq_extra++;
/*
* If we can't get a cq entry, userspace overflowed the
* submission (by quite a lot). Increment the overflow count in
* the ring.
*/
cqe = io_get_cqe(ctx);
if (likely(cqe)) {
trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
WRITE_ONCE(cqe->user_data, user_data);
WRITE_ONCE(cqe->res, res);
WRITE_ONCE(cqe->flags, cflags);
if (ctx->flags & IORING_SETUP_CQE32) {
WRITE_ONCE(cqe->big_cqe[0], 0);
WRITE_ONCE(cqe->big_cqe[1], 0);
}
return true;
}
return false;
}
static void __io_flush_post_cqes(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
struct io_submit_state *state = &ctx->submit_state;
unsigned int i;
lockdep_assert_held(&ctx->uring_lock);
for (i = 0; i < state->cqes_count; i++) {
struct io_uring_cqe *cqe = &state->cqes[i];
if (!io_fill_cqe_aux(ctx, cqe->user_data, cqe->res, cqe->flags)) {
if (ctx->task_complete) {
spin_lock(&ctx->completion_lock);
io_cqring_event_overflow(ctx, cqe->user_data,
cqe->res, cqe->flags, 0, 0);
spin_unlock(&ctx->completion_lock);
} else {
io_cqring_event_overflow(ctx, cqe->user_data,
cqe->res, cqe->flags, 0, 0);
}
}
}
state->cqes_count = 0;
}
static bool __io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags,
bool allow_overflow)
{
bool filled;
io_cq_lock(ctx);
filled = io_fill_cqe_aux(ctx, user_data, res, cflags);
if (!filled && allow_overflow)
filled = io_cqring_event_overflow(ctx, user_data, res, cflags, 0, 0);
io_cq_unlock_post(ctx);
return filled;
}
bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags)
{
return __io_post_aux_cqe(ctx, user_data, res, cflags, true);
}
bool io_aux_cqe(const struct io_kiocb *req, bool defer, s32 res, u32 cflags,
bool allow_overflow)
{
struct io_ring_ctx *ctx = req->ctx;
u64 user_data = req->cqe.user_data;
struct io_uring_cqe *cqe;
if (!defer)
return __io_post_aux_cqe(ctx, user_data, res, cflags, allow_overflow);
lockdep_assert_held(&ctx->uring_lock);
if (ctx->submit_state.cqes_count == ARRAY_SIZE(ctx->submit_state.cqes)) {
__io_cq_lock(ctx);
__io_flush_post_cqes(ctx);
/* no need to flush - flush is deferred */
__io_cq_unlock_post(ctx);
}
/* For defered completions this is not as strict as it is otherwise,
* however it's main job is to prevent unbounded posted completions,
* and in that it works just as well.
*/
if (!allow_overflow && test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
return false;
cqe = &ctx->submit_state.cqes[ctx->submit_state.cqes_count++];
cqe->user_data = user_data;
cqe->res = res;
cqe->flags = cflags;
return true;
}
static void __io_req_complete_post(struct io_kiocb *req, unsigned issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_rsrc_node *rsrc_node = NULL;
io_cq_lock(ctx);
if (!(req->flags & REQ_F_CQE_SKIP))
io_fill_cqe_req(ctx, req);
/*
* If we're the last reference to this request, add to our locked
* free_list cache.
*/
if (req_ref_put_and_test(req)) {
if (req->flags & IO_REQ_LINK_FLAGS) {
if (req->flags & IO_DISARM_MASK)
io_disarm_next(req);
if (req->link) {
io_req_task_queue(req->link);
req->link = NULL;
}
}
io_put_kbuf_comp(req);
if (unlikely(req->flags & IO_REQ_CLEAN_FLAGS))