aboutsummaryrefslogtreecommitdiff
path: root/src/include/liburing.h
blob: 51dc60251d88df101f16091e3cb6d4c55fc59632 (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
/* SPDX-License-Identifier: MIT */
#ifndef LIB_URING_H
#define LIB_URING_H

#ifndef _XOPEN_SOURCE
#define _XOPEN_SOURCE 500 /* Required for glibc to expose sigset_t */
#endif

#include <sys/socket.h>
#include <sys/uio.h>
#include <sys/stat.h>
#include <errno.h>
#include <signal.h>
#include <stdbool.h>
#include <inttypes.h>
#include <time.h>
#include <linux/swab.h>
#include "liburing/compat.h"
#include "liburing/io_uring.h"
#include "liburing/barrier.h"

#ifndef uring_unlikely
#  define uring_unlikely(cond)      __builtin_expect(!!(cond), 0)
#endif

#ifndef uring_likely
#  define uring_likely(cond)        __builtin_expect(!!(cond), 1)
#endif

#ifdef __cplusplus
extern "C" {
#endif

/*
 * Library interface to io_uring
 */
struct io_uring_sq {
	unsigned *khead;
	unsigned *ktail;
	unsigned *kring_mask;
	unsigned *kring_entries;
	unsigned *kflags;
	unsigned *kdropped;
	unsigned *array;
	struct io_uring_sqe *sqes;

	unsigned sqe_head;
	unsigned sqe_tail;

	size_t ring_sz;
	void *ring_ptr;

	unsigned pad[4];
};

struct io_uring_cq {
	unsigned *khead;
	unsigned *ktail;
	unsigned *kring_mask;
	unsigned *kring_entries;
	unsigned *kflags;
	unsigned *koverflow;
	struct io_uring_cqe *cqes;

	size_t ring_sz;
	void *ring_ptr;

	unsigned pad[4];
};

struct io_uring {
	struct io_uring_sq sq;
	struct io_uring_cq cq;
	unsigned flags;
	int ring_fd;

	unsigned features;
	unsigned pad[3];
};

/*
 * Library interface
 */

/*
 * return an allocated io_uring_probe structure, or NULL if probe fails (for
 * example, if it is not available). The caller is responsible for freeing it
 */
extern struct io_uring_probe *io_uring_get_probe_ring(struct io_uring *ring);
/* same as io_uring_get_probe_ring, but takes care of ring init and teardown */
extern struct io_uring_probe *io_uring_get_probe(void);

/*
 * frees a probe allocated through io_uring_get_probe() or
 * io_uring_get_probe_ring()
 */
extern void io_uring_free_probe(struct io_uring_probe *probe);

static inline int io_uring_opcode_supported(const struct io_uring_probe *p, int op)
{
	if (op > p->last_op)
		return 0;
	return (p->ops[op].flags & IO_URING_OP_SUPPORTED) != 0;
}

extern int io_uring_queue_init_params(unsigned entries, struct io_uring *ring,
	struct io_uring_params *p);
extern int io_uring_queue_init(unsigned entries, struct io_uring *ring,
	unsigned flags);
extern int io_uring_queue_mmap(int fd, struct io_uring_params *p,
	struct io_uring *ring);
extern int io_uring_ring_dontfork(struct io_uring *ring);
extern void io_uring_queue_exit(struct io_uring *ring);
unsigned io_uring_peek_batch_cqe(struct io_uring *ring,
	struct io_uring_cqe **cqes, unsigned count);
extern int io_uring_wait_cqes(struct io_uring *ring,
	struct io_uring_cqe **cqe_ptr, unsigned wait_nr,
	struct __kernel_timespec *ts, sigset_t *sigmask);
extern int io_uring_wait_cqe_timeout(struct io_uring *ring,
	struct io_uring_cqe **cqe_ptr, struct __kernel_timespec *ts);
extern int io_uring_submit(struct io_uring *ring);
extern int io_uring_submit_and_wait(struct io_uring *ring, unsigned wait_nr);
extern struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring);

extern int io_uring_register_buffers(struct io_uring *ring,
					const struct iovec *iovecs,
					unsigned nr_iovecs);
extern int io_uring_unregister_buffers(struct io_uring *ring);
extern int io_uring_register_files(struct io_uring *ring, const int *files,
					unsigned nr_files);
extern int io_uring_unregister_files(struct io_uring *ring);
extern int io_uring_register_files_update(struct io_uring *ring, unsigned off,
					int *files, unsigned nr_files);
extern int io_uring_register_eventfd(struct io_uring *ring, int fd);
extern int io_uring_register_eventfd_async(struct io_uring *ring, int fd);
extern int io_uring_unregister_eventfd(struct io_uring *ring);
extern int io_uring_register_probe(struct io_uring *ring,
					struct io_uring_probe *p, unsigned nr);
extern int io_uring_register_personality(struct io_uring *ring);
extern int io_uring_unregister_personality(struct io_uring *ring, int id);
extern int io_uring_register_restrictions(struct io_uring *ring,
					  struct io_uring_restriction *res,
					  unsigned int nr_res);
extern int io_uring_enable_rings(struct io_uring *ring);
extern int __io_uring_sqring_wait(struct io_uring *ring);

/*
 * Helper for the peek/wait single cqe functions. Exported because of that,
 * but probably shouldn't be used directly in an application.
 */
extern int __io_uring_get_cqe(struct io_uring *ring,
			      struct io_uring_cqe **cqe_ptr, unsigned submit,
			      unsigned wait_nr, sigset_t *sigmask);

#define LIBURING_UDATA_TIMEOUT	((__u64) -1)

#define io_uring_for_each_cqe(ring, head, cqe)				\
	/*								\
	 * io_uring_smp_load_acquire() enforces the order of tail	\
	 * and CQE reads.						\
	 */								\
	for (head = *(ring)->cq.khead;					\
	     (cqe = (head != io_uring_smp_load_acquire((ring)->cq.ktail) ? \
		&(ring)->cq.cqes[head & (*(ring)->cq.kring_mask)] : NULL)); \
	     head++)							\

/*
 * Must be called after io_uring_for_each_cqe()
 */
static inline void io_uring_cq_advance(struct io_uring *ring,
				       unsigned nr)
{
	if (nr) {
		struct io_uring_cq *cq = &ring->cq;

		/*
		 * Ensure that the kernel only sees the new value of the head
		 * index after the CQEs have been read.
		 */
		io_uring_smp_store_release(cq->khead, *cq->khead + nr);
	}
}

/*
 * Must be called after io_uring_{peek,wait}_cqe() after the cqe has
 * been processed by the application.
 */
static inline void io_uring_cqe_seen(struct io_uring *ring,
				     struct io_uring_cqe *cqe)
{
	if (cqe)
		io_uring_cq_advance(ring, 1);
}

/*
 * Command prep helpers
 */
static inline void io_uring_sqe_set_data(struct io_uring_sqe *sqe, void *data)
{
	sqe->user_data = (unsigned long) data;
}

static inline void *io_uring_cqe_get_data(const struct io_uring_cqe *cqe)
{
	return (void *) (uintptr_t) cqe->user_data;
}

static inline void io_uring_sqe_set_flags(struct io_uring_sqe *sqe,
					  unsigned flags)
{
	sqe->flags = flags;
}

static inline void io_uring_prep_rw(int op, struct io_uring_sqe *sqe, int fd,
				    const void *addr, unsigned len,
				    __u64 offset)
{
	sqe->opcode = op;
	sqe->flags = 0;
	sqe->ioprio = 0;
	sqe->fd = fd;
	sqe->off = offset;
	sqe->addr = (unsigned long) addr;
	sqe->len = len;
	sqe->rw_flags = 0;
	sqe->user_data = 0;
	sqe->__pad2[0] = sqe->__pad2[1] = sqe->__pad2[2] = 0;
}

/**
 * @pre Either fd_in or fd_out must be a pipe.
 * @param off_in If fd_in refers to a pipe, off_in must be (int64_t) -1;
 *               If fd_in does not refer to a pipe and off_in is (int64_t) -1, then bytes are read
 *               from fd_in starting from the file offset and it is adjust appropriately;
 *               If fd_in does not refer to a pipe and off_in is not (int64_t) -1, then the
 *               starting offset of fd_in will be off_in.
 * @param off_out The description of off_in also applied to off_out.
 * @param splice_flags see man splice(2) for description of flags.
 *
 * This splice operation can be used to implement sendfile by splicing to an intermediate pipe
 * first, then splice to the final destination.
 * In fact, the implementation of sendfile in kernel uses splice internally.
 *
 * NOTE that even if fd_in or fd_out refers to a pipe, the splice operation can still failed with
 * EINVAL if one of the fd doesn't explicitly support splice operation, e.g. reading from terminal
 * is unsupported from kernel 5.7 to 5.11.
 * Check issue #291 for more information.
 */
static inline void io_uring_prep_splice(struct io_uring_sqe *sqe,
					int fd_in, int64_t off_in,
					int fd_out, int64_t off_out,
					unsigned int nbytes,
					unsigned int splice_flags)
{
	io_uring_prep_rw(IORING_OP_SPLICE, sqe, fd_out, NULL, nbytes, off_out);
	sqe->splice_off_in = off_in;
	sqe->splice_fd_in = fd_in;
	sqe->splice_flags = splice_flags;
}

static inline void io_uring_prep_tee(struct io_uring_sqe *sqe,
				     int fd_in, int fd_out,
				     unsigned int nbytes,
				     unsigned int splice_flags)
{
	io_uring_prep_rw(IORING_OP_TEE, sqe, fd_out, NULL, nbytes, 0);
	sqe->splice_off_in = 0;
	sqe->splice_fd_in = fd_in;
	sqe->splice_flags = splice_flags;
}

static inline void io_uring_prep_readv(struct io_uring_sqe *sqe, int fd,
				       const struct iovec *iovecs,
				       unsigned nr_vecs, off_t offset)
{
	io_uring_prep_rw(IORING_OP_READV, sqe, fd, iovecs, nr_vecs, offset);
}

static inline void io_uring_prep_read_fixed(struct io_uring_sqe *sqe, int fd,
					    void *buf, unsigned nbytes,
					    off_t offset, int buf_index)
{
	io_uring_prep_rw(IORING_OP_READ_FIXED, sqe, fd, buf, nbytes, offset);
	sqe->buf_index = buf_index;
}

static inline void io_uring_prep_writev(struct io_uring_sqe *sqe, int fd,
					const struct iovec *iovecs,
					unsigned nr_vecs, off_t offset)
{
	io_uring_prep_rw(IORING_OP_WRITEV, sqe, fd, iovecs, nr_vecs, offset);
}

static inline void io_uring_prep_write_fixed(struct io_uring_sqe *sqe, int fd,
					     const void *buf, unsigned nbytes,
					     off_t offset, int buf_index)
{
	io_uring_prep_rw(IORING_OP_WRITE_FIXED, sqe, fd, buf, nbytes, offset);
	sqe->buf_index = buf_index;
}

static inline void io_uring_prep_recvmsg(struct io_uring_sqe *sqe, int fd,
					 struct msghdr *msg, unsigned flags)
{
	io_uring_prep_rw(IORING_OP_RECVMSG, sqe, fd, msg, 1, 0);
	sqe->msg_flags = flags;
}

static inline void io_uring_prep_sendmsg(struct io_uring_sqe *sqe, int fd,
					 const struct msghdr *msg, unsigned flags)
{
	io_uring_prep_rw(IORING_OP_SENDMSG, sqe, fd, msg, 1, 0);
	sqe->msg_flags = flags;
}

static inline void io_uring_prep_poll_add(struct io_uring_sqe *sqe, int fd,
					  unsigned poll_mask)
{
	io_uring_prep_rw(IORING_OP_POLL_ADD, sqe, fd, NULL, 0, 0);
#if __BYTE_ORDER == __BIG_ENDIAN
	poll_mask = __swahw32(poll_mask);
#endif
	sqe->poll32_events = poll_mask;
}

static inline void io_uring_prep_poll_remove(struct io_uring_sqe *sqe,
					     void *user_data)
{
	io_uring_prep_rw(IORING_OP_POLL_REMOVE, sqe, -1, user_data, 0, 0);
}

static inline void io_uring_prep_poll_update(struct io_uring_sqe *sqe,
					     void *old_user_data,
					     void *new_user_data,
					     unsigned poll_mask, unsigned flags)
{
	io_uring_prep_rw(IORING_OP_POLL_REMOVE, sqe, -1, old_user_data, flags,
			 (__u64)new_user_data);
#if __BYTE_ORDER == __BIG_ENDIAN
	poll_mask = __swahw32(poll_mask);
#endif
	sqe->poll32_events = poll_mask;
}

static inline void io_uring_prep_fsync(struct io_uring_sqe *sqe, int fd,
				       unsigned fsync_flags)
{
	io_uring_prep_rw(IORING_OP_FSYNC, sqe, fd, NULL, 0, 0);
	sqe->fsync_flags = fsync_flags;
}

static inline void io_uring_prep_nop(struct io_uring_sqe *sqe)
{
	io_uring_prep_rw(IORING_OP_NOP, sqe, -1, NULL, 0, 0);
}

static inline void io_uring_prep_timeout(struct io_uring_sqe *sqe,
					 struct __kernel_timespec *ts,
					 unsigned count, unsigned flags)
{
	io_uring_prep_rw(IORING_OP_TIMEOUT, sqe, -1, ts, 1, count);
	sqe->timeout_flags = flags;
}

static inline void io_uring_prep_timeout_remove(struct io_uring_sqe *sqe,
						__u64 user_data, unsigned flags)
{
	io_uring_prep_rw(IORING_OP_TIMEOUT_REMOVE, sqe, -1,
				(void *)(unsigned long)user_data, 0, 0);
	sqe->timeout_flags = flags;
}

static inline void io_uring_prep_timeout_update(struct io_uring_sqe *sqe,
						struct __kernel_timespec *ts,
						__u64 user_data, unsigned flags)
{
	io_uring_prep_rw(IORING_OP_TIMEOUT_REMOVE, sqe, -1,
				(void *)(unsigned long)user_data, 0,
				(uintptr_t)ts);
	sqe->timeout_flags = flags | IORING_TIMEOUT_UPDATE;
}

static inline void io_uring_prep_accept(struct io_uring_sqe *sqe, int fd,
					struct sockaddr *addr,
					socklen_t *addrlen, int flags)
{
	io_uring_prep_rw(IORING_OP_ACCEPT, sqe, fd, addr, 0,
				(__u64) (unsigned long) addrlen);
	sqe->accept_flags = flags;
}

static inline void io_uring_prep_cancel(struct io_uring_sqe *sqe, void *user_data,
					int flags)
{
	io_uring_prep_rw(IORING_OP_ASYNC_CANCEL, sqe, -1, user_data, 0, 0);
	sqe->cancel_flags = flags;
}

static inline void io_uring_prep_link_timeout(struct io_uring_sqe *sqe,
					      struct __kernel_timespec *ts,
					      unsigned flags)
{
	io_uring_prep_rw(IORING_OP_LINK_TIMEOUT, sqe, -1, ts, 1, 0);
	sqe->timeout_flags = flags;
}

static inline void io_uring_prep_connect(struct io_uring_sqe *sqe, int fd,
					 const struct sockaddr *addr,
					 socklen_t addrlen)
{
	io_uring_prep_rw(IORING_OP_CONNECT, sqe, fd, addr, 0, addrlen);
}

static inline void io_uring_prep_files_update(struct io_uring_sqe *sqe,
					      int *fds, unsigned nr_fds,
					      int offset)
{
	io_uring_prep_rw(IORING_OP_FILES_UPDATE, sqe, -1, fds, nr_fds, offset);
}

static inline void io_uring_prep_fallocate(struct io_uring_sqe *sqe, int fd,
					   int mode, off_t offset, off_t len)
{

	io_uring_prep_rw(IORING_OP_FALLOCATE, sqe, fd,
			(const uintptr_t *) (unsigned long) len, mode, offset);
}

static inline void io_uring_prep_openat(struct io_uring_sqe *sqe, int dfd,
					const char *path, int flags, mode_t mode)
{
	io_uring_prep_rw(IORING_OP_OPENAT, sqe, dfd, path, mode, 0);
	sqe->open_flags = flags;
}

static inline void io_uring_prep_close(struct io_uring_sqe *sqe, int fd)
{
	io_uring_prep_rw(IORING_OP_CLOSE, sqe, fd, NULL, 0, 0);
}

static inline void io_uring_prep_read(struct io_uring_sqe *sqe, int fd,
				      void *buf, unsigned nbytes, off_t offset)
{
	io_uring_prep_rw(IORING_OP_READ, sqe, fd, buf, nbytes, offset);
}

static inline void io_uring_prep_write(struct io_uring_sqe *sqe, int fd,
				       const void *buf, unsigned nbytes, off_t offset)
{
	io_uring_prep_rw(IORING_OP_WRITE, sqe, fd, buf, nbytes, offset);
}

struct statx;
static inline void io_uring_prep_statx(struct io_uring_sqe *sqe, int dfd,
				const char *path, int flags, unsigned mask,
				struct statx *statxbuf)
{
	io_uring_prep_rw(IORING_OP_STATX, sqe, dfd, path, mask,
				(__u64) (unsigned long) statxbuf);
	sqe->statx_flags = flags;
}

static inline void io_uring_prep_fadvise(struct io_uring_sqe *sqe, int fd,
					 off_t offset, off_t len, int advice)
{
	io_uring_prep_rw(IORING_OP_FADVISE, sqe, fd, NULL, len, offset);
	sqe->fadvise_advice = advice;
}

static inline void io_uring_prep_madvise(struct io_uring_sqe *sqe, void *addr,
					 off_t length, int advice)
{
	io_uring_prep_rw(IORING_OP_MADVISE, sqe, -1, addr, length, 0);
	sqe->fadvise_advice = advice;
}

static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd,
				      const void *buf, size_t len, int flags)
{
	io_uring_prep_rw(IORING_OP_SEND, sqe, sockfd, buf, len, 0);
	sqe->msg_flags = flags;
}

static inline void io_uring_prep_recv(struct io_uring_sqe *sqe, int sockfd,
				      void *buf, size_t len, int flags)
{
	io_uring_prep_rw(IORING_OP_RECV, sqe, sockfd, buf, len, 0);
	sqe->msg_flags = flags;
}

static inline void io_uring_prep_openat2(struct io_uring_sqe *sqe, int dfd,
					const char *path, struct open_how *how)
{
	io_uring_prep_rw(IORING_OP_OPENAT2, sqe, dfd, path, sizeof(*how),
				(uint64_t) (uintptr_t) how);
}

struct epoll_event;
static inline void io_uring_prep_epoll_ctl(struct io_uring_sqe *sqe, int epfd,
					   int fd, int op,
					   struct epoll_event *ev)
{
	io_uring_prep_rw(IORING_OP_EPOLL_CTL, sqe, epfd, ev, op, fd);
}

static inline void io_uring_prep_provide_buffers(struct io_uring_sqe *sqe,
						 void *addr, int len, int nr,
						 int bgid, int bid)
{
	io_uring_prep_rw(IORING_OP_PROVIDE_BUFFERS, sqe, nr, addr, len, bid);
	sqe->buf_group = bgid;
}

static inline void io_uring_prep_remove_buffers(struct io_uring_sqe *sqe,
						int nr, int bgid)
{
	io_uring_prep_rw(IORING_OP_REMOVE_BUFFERS, sqe, nr, NULL, 0, 0);
	sqe->buf_group = bgid;
}

static inline void io_uring_prep_shutdown(struct io_uring_sqe *sqe, int fd,
					  int how)
{
	io_uring_prep_rw(IORING_OP_SHUTDOWN, sqe, fd, NULL, how, 0);
}

static inline void io_uring_prep_unlinkat(struct io_uring_sqe *sqe, int dfd,
					  const char *path, int flags)
{
	io_uring_prep_rw(IORING_OP_UNLINKAT, sqe, dfd, path, 0, 0);
	sqe->unlink_flags = flags;
}

static inline void io_uring_prep_renameat(struct io_uring_sqe *sqe, int olddfd,
					  const char *oldpath, int newdfd,
					  const char *newpath, int flags)
{
	io_uring_prep_rw(IORING_OP_RENAMEAT, sqe, olddfd, oldpath, newdfd,
				(uint64_t) (uintptr_t) newpath);
	sqe->rename_flags = flags;
}

static inline void io_uring_prep_sync_file_range(struct io_uring_sqe *sqe,
						 int fd, unsigned len,
						 off_t offset, int flags)
{
	io_uring_prep_rw(IORING_OP_SYNC_FILE_RANGE, sqe, fd, NULL, len, offset);
	sqe->sync_range_flags = flags;
}

static inline void io_uring_prep_mkdirat(struct io_uring_sqe *sqe, int dfd,
					const char *path, mode_t mode)
{
	io_uring_prep_rw(IORING_OP_MKDIRAT, sqe, dfd, path, mode, 0);
}

static inline void io_uring_prep_symlinkat(struct io_uring_sqe *sqe,
					const char *target, int newdirfd, const char *linkpath)
{
	io_uring_prep_rw(IORING_OP_SYMLINKAT, sqe, newdirfd, target, 0,
				(uint64_t) (uintptr_t) linkpath);
}

static inline void io_uring_prep_linkat(struct io_uring_sqe *sqe, int olddfd,
					const char *oldpath, int newdfd,
					const char *newpath, int flags)
{
	io_uring_prep_rw(IORING_OP_LINKAT, sqe, olddfd, oldpath, newdfd,
				(uint64_t) (uintptr_t) newpath);
	sqe->hardlink_flags = flags;
}

/*
 * Returns number of unconsumed (if SQPOLL) or unsubmitted entries exist in
 * the SQ ring
 */
static inline unsigned io_uring_sq_ready(const struct io_uring *ring)
{
	/*
	 * Without a barrier, we could miss an update and think the SQ wasn't ready.
	 * We don't need the load acquire for non-SQPOLL since then we drive updates.
	 */
	if (ring->flags & IORING_SETUP_SQPOLL)
		return ring->sq.sqe_tail - io_uring_smp_load_acquire(ring->sq.khead);

	/* always use real head, to avoid losing sync for short submit */
	return ring->sq.sqe_tail - *ring->sq.khead;
}

/*
 * Returns how much space is left in the SQ ring.
 */
static inline unsigned io_uring_sq_space_left(const struct io_uring *ring)
{
	return *ring->sq.kring_entries - io_uring_sq_ready(ring);
}

/*
 * Only applicable when using SQPOLL - allows the caller to wait for space
 * to free up in the SQ ring, which happens when the kernel side thread has
 * consumed one or more entries. If the SQ ring is currently non-full, no
 * action is taken. Note: may return -EINVAL if the kernel doesn't support
 * this feature.
 */
static inline int io_uring_sqring_wait(struct io_uring *ring)
{
	if (!(ring->flags & IORING_SETUP_SQPOLL))
		return 0;
	if (io_uring_sq_space_left(ring))
		return 0;

	return __io_uring_sqring_wait(ring);
}

/*
 * Returns how many unconsumed entries are ready in the CQ ring
 */
static inline unsigned io_uring_cq_ready(const struct io_uring *ring)
{
	return io_uring_smp_load_acquire(ring->cq.ktail) - *ring->cq.khead;
}

/*
 * Returns true if the eventfd notification is currently enabled
 */
static inline bool io_uring_cq_eventfd_enabled(const struct io_uring *ring)
{
	if (!ring->cq.kflags)
		return true;

	return !(*ring->cq.kflags & IORING_CQ_EVENTFD_DISABLED);
}

/*
 * Toggle eventfd notification on or off, if an eventfd is registered with
 * the ring.
 */
static inline int io_uring_cq_eventfd_toggle(struct io_uring *ring,
					     bool enabled)
{
	uint32_t flags;

	if (!!enabled == io_uring_cq_eventfd_enabled(ring))
		return 0;

	if (!ring->cq.kflags)
		return -EOPNOTSUPP;

	flags = *ring->cq.kflags;

	if (enabled)
		flags &= ~IORING_CQ_EVENTFD_DISABLED;
	else
		flags |= IORING_CQ_EVENTFD_DISABLED;

	IO_URING_WRITE_ONCE(*ring->cq.kflags, flags);

	return 0;
}

/*
 * Return an IO completion, waiting for 'wait_nr' completions if one isn't
 * readily available. Returns 0 with cqe_ptr filled in on success, -errno on
 * failure.
 */
static inline int io_uring_wait_cqe_nr(struct io_uring *ring,
				      struct io_uring_cqe **cqe_ptr,
				      unsigned wait_nr)
{
	return __io_uring_get_cqe(ring, cqe_ptr, 0, wait_nr, NULL);
}

/*
 * Return an IO completion, if one is readily available. Returns 0 with
 * cqe_ptr filled in on success, -errno on failure.
 */
static inline int io_uring_peek_cqe(struct io_uring *ring,
				    struct io_uring_cqe **cqe_ptr)
{
	return io_uring_wait_cqe_nr(ring, cqe_ptr, 0);
}

/*
 * Return an IO completion, waiting for it if necessary. Returns 0 with
 * cqe_ptr filled in on success, -errno on failure.
 */
static inline int io_uring_wait_cqe(struct io_uring *ring,
				    struct io_uring_cqe **cqe_ptr)
{
	return io_uring_wait_cqe_nr(ring, cqe_ptr, 1);
}

ssize_t io_uring_mlock_size(unsigned entries, unsigned flags);
ssize_t io_uring_mlock_size_params(unsigned entries, struct io_uring_params *p);

#ifdef __cplusplus
}
#endif

#endif