linux-stable/include/uapi/linux/io_uring.h
Jens Axboe f2842ab5b7 io_uring: enable option to only trigger eventfd for async completions
If an application is using eventfd notifications with poll to know when
new SQEs can be issued, it's expecting the following read/writes to
complete inline. And with that, it knows that there are events available,
and don't want spurious wakeups on the eventfd for those requests.

This adds IORING_REGISTER_EVENTFD_ASYNC, which works just like
IORING_REGISTER_EVENTFD, except it only triggers notifications for events
that happen from async completions (IRQ, or io-wq worker completions).
Any completions inline from the submission itself will not trigger
notifications.

Suggested-by: Mark Papadakis <markuspapadakis@icloud.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-01-20 17:04:04 -07:00

203 lines
4.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
/*
* Header file for the io_uring interface.
*
* Copyright (C) 2019 Jens Axboe
* Copyright (C) 2019 Christoph Hellwig
*/
#ifndef LINUX_IO_URING_H
#define LINUX_IO_URING_H
#include <linux/fs.h>
#include <linux/types.h>
/*
* IO submission data structure (Submission Queue Entry)
*/
struct io_uring_sqe {
__u8 opcode; /* type of operation for this sqe */
__u8 flags; /* IOSQE_ flags */
__u16 ioprio; /* ioprio for the request */
__s32 fd; /* file descriptor to do IO on */
union {
__u64 off; /* offset into file */
__u64 addr2;
};
__u64 addr; /* pointer to buffer or iovecs */
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
__u32 fsync_flags;
__u16 poll_events;
__u32 sync_range_flags;
__u32 msg_flags;
__u32 timeout_flags;
__u32 accept_flags;
__u32 cancel_flags;
__u32 open_flags;
__u32 statx_flags;
__u32 fadvise_advice;
};
__u64 user_data; /* data to be passed back at completion time */
union {
__u16 buf_index; /* index into fixed buffers, if used */
__u64 __pad2[3];
};
};
/*
* sqe->flags
*/
#define IOSQE_FIXED_FILE (1U << 0) /* use fixed fileset */
#define IOSQE_IO_DRAIN (1U << 1) /* issue after inflight IO */
#define IOSQE_IO_LINK (1U << 2) /* links next sqe */
#define IOSQE_IO_HARDLINK (1U << 3) /* like LINK, but stronger */
#define IOSQE_ASYNC (1U << 4) /* always go async */
/*
* io_uring_setup() flags
*/
#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */
#define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */
#define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */
#define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */
#define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */
enum {
IORING_OP_NOP,
IORING_OP_READV,
IORING_OP_WRITEV,
IORING_OP_FSYNC,
IORING_OP_READ_FIXED,
IORING_OP_WRITE_FIXED,
IORING_OP_POLL_ADD,
IORING_OP_POLL_REMOVE,
IORING_OP_SYNC_FILE_RANGE,
IORING_OP_SENDMSG,
IORING_OP_RECVMSG,
IORING_OP_TIMEOUT,
IORING_OP_TIMEOUT_REMOVE,
IORING_OP_ACCEPT,
IORING_OP_ASYNC_CANCEL,
IORING_OP_LINK_TIMEOUT,
IORING_OP_CONNECT,
IORING_OP_FALLOCATE,
IORING_OP_OPENAT,
IORING_OP_CLOSE,
IORING_OP_FILES_UPDATE,
IORING_OP_STATX,
IORING_OP_READ,
IORING_OP_WRITE,
IORING_OP_FADVISE,
IORING_OP_MADVISE,
IORING_OP_SEND,
IORING_OP_RECV,
/* this goes last, obviously */
IORING_OP_LAST,
};
/*
* sqe->fsync_flags
*/
#define IORING_FSYNC_DATASYNC (1U << 0)
/*
* sqe->timeout_flags
*/
#define IORING_TIMEOUT_ABS (1U << 0)
/*
* IO completion data structure (Completion Queue Entry)
*/
struct io_uring_cqe {
__u64 user_data; /* sqe->data submission passed back */
__s32 res; /* result code for this event */
__u32 flags;
};
/*
* Magic offsets for the application to mmap the data it needs
*/
#define IORING_OFF_SQ_RING 0ULL
#define IORING_OFF_CQ_RING 0x8000000ULL
#define IORING_OFF_SQES 0x10000000ULL
/*
* Filled with the offset for mmap(2)
*/
struct io_sqring_offsets {
__u32 head;
__u32 tail;
__u32 ring_mask;
__u32 ring_entries;
__u32 flags;
__u32 dropped;
__u32 array;
__u32 resv1;
__u64 resv2;
};
/*
* sq_ring->flags
*/
#define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */
struct io_cqring_offsets {
__u32 head;
__u32 tail;
__u32 ring_mask;
__u32 ring_entries;
__u32 overflow;
__u32 cqes;
__u64 resv[2];
};
/*
* io_uring_enter(2) flags
*/
#define IORING_ENTER_GETEVENTS (1U << 0)
#define IORING_ENTER_SQ_WAKEUP (1U << 1)
/*
* Passed in for io_uring_setup(2). Copied back with updated info on success
*/
struct io_uring_params {
__u32 sq_entries;
__u32 cq_entries;
__u32 flags;
__u32 sq_thread_cpu;
__u32 sq_thread_idle;
__u32 features;
__u32 resv[4];
struct io_sqring_offsets sq_off;
struct io_cqring_offsets cq_off;
};
/*
* io_uring_params->features flags
*/
#define IORING_FEAT_SINGLE_MMAP (1U << 0)
#define IORING_FEAT_NODROP (1U << 1)
#define IORING_FEAT_SUBMIT_STABLE (1U << 2)
#define IORING_FEAT_RW_CUR_POS (1U << 3)
/*
* io_uring_register(2) opcodes and arguments
*/
#define IORING_REGISTER_BUFFERS 0
#define IORING_UNREGISTER_BUFFERS 1
#define IORING_REGISTER_FILES 2
#define IORING_UNREGISTER_FILES 3
#define IORING_REGISTER_EVENTFD 4
#define IORING_UNREGISTER_EVENTFD 5
#define IORING_REGISTER_FILES_UPDATE 6
#define IORING_REGISTER_EVENTFD_ASYNC 7
struct io_uring_files_update {
__u32 offset;
__u32 resv;
__aligned_u64 /* __s32 * */ fds;
};
#endif