linux-stable/include/uapi/linux/io_uring.h
Pavel Begunkov 04c76b41ca io_uring: add option to skip CQE posting
Emitting a CQE is expensive from the kernel perspective. Often, it's
also not convenient for the userspace, spends some cycles on processing
and just complicates the logic. A similar problems goes for linked
requests, where we post an CQE for each request in the link.

Introduce a new flags, IOSQE_CQE_SKIP_SUCCESS, trying to help with it.
When set and a request completed successfully, it won't generate a CQE.
When fails, it produces an CQE, but all following linked requests will
be CQE-less, regardless whether they have IOSQE_CQE_SKIP_SUCCESS or not.
The notion of "fail" is the same as for link failing-cancellation, where
it's opcode dependent, and _usually_ result >= 0 is a success, but not
always.

Linked timeouts are a bit special. When the requests it's linked to was
not attempted to be executed, e.g. failing linked requests, it follows
the description above. Otherwise, whether a linked timeout will post a
completion or not solely depends on IOSQE_CQE_SKIP_SUCCESS of that
linked timeout request. Linked timeout never "fail" during execution, so
for them it's unconditional. It's expected for users to not really care
about the result of it but rely solely on the result of the master
request. Another reason for such a treatment is that it's racy, and the
timeout callback may be running awhile the master request posts its
completion.

use case 1:
If one doesn't care about results of some requests, e.g. normal
timeouts, just set IOSQE_CQE_SKIP_SUCCESS. Error result will still be
posted and need to be handled.

use case 2:
Set IOSQE_CQE_SKIP_SUCCESS for all requests of a link but the last,
and it'll post a completion only for the last one if everything goes
right, otherwise there will be one only one CQE for the first failed
request.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/0220fbe06f7cf99e6fc71b4297bb1cb6c0e89c2c.1636559119.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-11-24 11:17:53 -07:00

425 lines
9.8 KiB
C

/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
/*
* 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;
};
union {
__u64 addr; /* pointer to buffer or iovecs */
__u64 splice_off_in;
};
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
__u32 fsync_flags;
__u16 poll_events; /* compatibility */
__u32 poll32_events; /* word-reversed for BE */
__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;
__u32 splice_flags;
__u32 rename_flags;
__u32 unlink_flags;
__u32 hardlink_flags;
};
__u64 user_data; /* data to be passed back at completion time */
/* pack this to avoid bogus arm OABI complaints */
union {
/* index into fixed buffers, if used */
__u16 buf_index;
/* for grouped buffer selection */
__u16 buf_group;
} __attribute__((packed));
/* personality to use, if used */
__u16 personality;
union {
__s32 splice_fd_in;
__u32 file_index;
};
__u64 __pad2[2];
};
enum {
IOSQE_FIXED_FILE_BIT,
IOSQE_IO_DRAIN_BIT,
IOSQE_IO_LINK_BIT,
IOSQE_IO_HARDLINK_BIT,
IOSQE_ASYNC_BIT,
IOSQE_BUFFER_SELECT_BIT,
IOSQE_CQE_SKIP_SUCCESS_BIT,
};
/*
* sqe->flags
*/
/* use fixed fileset */
#define IOSQE_FIXED_FILE (1U << IOSQE_FIXED_FILE_BIT)
/* issue after inflight IO */
#define IOSQE_IO_DRAIN (1U << IOSQE_IO_DRAIN_BIT)
/* links next sqe */
#define IOSQE_IO_LINK (1U << IOSQE_IO_LINK_BIT)
/* like LINK, but stronger */
#define IOSQE_IO_HARDLINK (1U << IOSQE_IO_HARDLINK_BIT)
/* always go async */
#define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT)
/* select buffer from sqe->buf_group */
#define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT)
/* don't post CQE if request succeeded */
#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT)
/*
* 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 */
#define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */
#define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */
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,
IORING_OP_OPENAT2,
IORING_OP_EPOLL_CTL,
IORING_OP_SPLICE,
IORING_OP_PROVIDE_BUFFERS,
IORING_OP_REMOVE_BUFFERS,
IORING_OP_TEE,
IORING_OP_SHUTDOWN,
IORING_OP_RENAMEAT,
IORING_OP_UNLINKAT,
IORING_OP_MKDIRAT,
IORING_OP_SYMLINKAT,
IORING_OP_LINKAT,
/* 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)
#define IORING_TIMEOUT_UPDATE (1U << 1)
#define IORING_TIMEOUT_BOOTTIME (1U << 2)
#define IORING_TIMEOUT_REALTIME (1U << 3)
#define IORING_LINK_TIMEOUT_UPDATE (1U << 4)
#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5)
#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
/*
* sqe->splice_flags
* extends splice(2) flags
*/
#define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */
/*
* POLL_ADD flags. Note that since sqe->poll_events is the flag space, the
* command flags for POLL_ADD are stored in sqe->len.
*
* IORING_POLL_ADD_MULTI Multishot poll. Sets IORING_CQE_F_MORE if
* the poll handler will continue to report
* CQEs on behalf of the same SQE.
*
* IORING_POLL_UPDATE Update existing poll request, matching
* sqe->addr as the old user_data field.
*/
#define IORING_POLL_ADD_MULTI (1U << 0)
#define IORING_POLL_UPDATE_EVENTS (1U << 1)
#define IORING_POLL_UPDATE_USER_DATA (1U << 2)
/*
* 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;
};
/*
* cqe->flags
*
* IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID
* IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries
*/
#define IORING_CQE_F_BUFFER (1U << 0)
#define IORING_CQE_F_MORE (1U << 1)
enum {
IORING_CQE_BUFFER_SHIFT = 16,
};
/*
* 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 */
#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */
struct io_cqring_offsets {
__u32 head;
__u32 tail;
__u32 ring_mask;
__u32 ring_entries;
__u32 overflow;
__u32 cqes;
__u32 flags;
__u32 resv1;
__u64 resv2;
};
/*
* cq_ring->flags
*/
/* disable eventfd notifications */
#define IORING_CQ_EVENTFD_DISABLED (1U << 0)
/*
* io_uring_enter(2) flags
*/
#define IORING_ENTER_GETEVENTS (1U << 0)
#define IORING_ENTER_SQ_WAKEUP (1U << 1)
#define IORING_ENTER_SQ_WAIT (1U << 2)
#define IORING_ENTER_EXT_ARG (1U << 3)
/*
* 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 wq_fd;
__u32 resv[3];
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)
#define IORING_FEAT_CUR_PERSONALITY (1U << 4)
#define IORING_FEAT_FAST_POLL (1U << 5)
#define IORING_FEAT_POLL_32BITS (1U << 6)
#define IORING_FEAT_SQPOLL_NONFIXED (1U << 7)
#define IORING_FEAT_EXT_ARG (1U << 8)
#define IORING_FEAT_NATIVE_WORKERS (1U << 9)
#define IORING_FEAT_RSRC_TAGS (1U << 10)
#define IORING_FEAT_CQE_SKIP (1U << 11)
/*
* io_uring_register(2) opcodes and arguments
*/
enum {
IORING_REGISTER_BUFFERS = 0,
IORING_UNREGISTER_BUFFERS = 1,
IORING_REGISTER_FILES = 2,
IORING_UNREGISTER_FILES = 3,
IORING_REGISTER_EVENTFD = 4,
IORING_UNREGISTER_EVENTFD = 5,
IORING_REGISTER_FILES_UPDATE = 6,
IORING_REGISTER_EVENTFD_ASYNC = 7,
IORING_REGISTER_PROBE = 8,
IORING_REGISTER_PERSONALITY = 9,
IORING_UNREGISTER_PERSONALITY = 10,
IORING_REGISTER_RESTRICTIONS = 11,
IORING_REGISTER_ENABLE_RINGS = 12,
/* extended with tagging */
IORING_REGISTER_FILES2 = 13,
IORING_REGISTER_FILES_UPDATE2 = 14,
IORING_REGISTER_BUFFERS2 = 15,
IORING_REGISTER_BUFFERS_UPDATE = 16,
/* set/clear io-wq thread affinities */
IORING_REGISTER_IOWQ_AFF = 17,
IORING_UNREGISTER_IOWQ_AFF = 18,
/* set/get max number of io-wq workers */
IORING_REGISTER_IOWQ_MAX_WORKERS = 19,
/* this goes last */
IORING_REGISTER_LAST
};
/* io-wq worker categories */
enum {
IO_WQ_BOUND,
IO_WQ_UNBOUND,
};
/* deprecated, see struct io_uring_rsrc_update */
struct io_uring_files_update {
__u32 offset;
__u32 resv;
__aligned_u64 /* __s32 * */ fds;
};
struct io_uring_rsrc_register {
__u32 nr;
__u32 resv;
__u64 resv2;
__aligned_u64 data;
__aligned_u64 tags;
};
struct io_uring_rsrc_update {
__u32 offset;
__u32 resv;
__aligned_u64 data;
};
struct io_uring_rsrc_update2 {
__u32 offset;
__u32 resv;
__aligned_u64 data;
__aligned_u64 tags;
__u32 nr;
__u32 resv2;
};
/* Skip updating fd indexes set to this value in the fd table */
#define IORING_REGISTER_FILES_SKIP (-2)
#define IO_URING_OP_SUPPORTED (1U << 0)
struct io_uring_probe_op {
__u8 op;
__u8 resv;
__u16 flags; /* IO_URING_OP_* flags */
__u32 resv2;
};
struct io_uring_probe {
__u8 last_op; /* last opcode supported */
__u8 ops_len; /* length of ops[] array below */
__u16 resv;
__u32 resv2[3];
struct io_uring_probe_op ops[0];
};
struct io_uring_restriction {
__u16 opcode;
union {
__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
__u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */
__u8 sqe_flags; /* IORING_RESTRICTION_SQE_FLAGS_* */
};
__u8 resv;
__u32 resv2[3];
};
/*
* io_uring_restriction->opcode values
*/
enum {
/* Allow an io_uring_register(2) opcode */
IORING_RESTRICTION_REGISTER_OP = 0,
/* Allow an sqe opcode */
IORING_RESTRICTION_SQE_OP = 1,
/* Allow sqe flags */
IORING_RESTRICTION_SQE_FLAGS_ALLOWED = 2,
/* Require sqe flags (these flags must be set on each submission) */
IORING_RESTRICTION_SQE_FLAGS_REQUIRED = 3,
IORING_RESTRICTION_LAST
};
struct io_uring_getevents_arg {
__u64 sigmask;
__u32 sigmask_sz;
__u32 pad;
__u64 ts;
};
#endif