[fio.git] / os / linux / io_uring.h

/* 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;
		struct {
			__u32	cmd_op;
			__u32	__pad1;
		};
	};
	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;
		__u32		uring_cmd_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;
	};
	union {
		struct {
			__u64	addr3;
			__u64	__pad2[1];
		};
		/*
		 * If the ring is initialized with IORING_SETUP_SQE128, then
		 * this field is used for 80 bytes of arbitrary command data
		 */
		__u8	cmd[0];
	};
};

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 */
#define IORING_SETUP_SUBMIT_ALL	(1U << 7)	/* continue submit on error */
/*
 * Cooperative task running. When requests complete, they often require
 * forcing the submitter to transition to the kernel to complete. If this
 * flag is set, work will be done when the task transitions anyway, rather
 * than force an inter-processor interrupt reschedule. This avoids interrupting
 * a task running in userspace, and saves an IPI.
 */
#define IORING_SETUP_COOP_TASKRUN	(1U << 8)
/*
 * If COOP_TASKRUN is set, get notified if task work is available for
 * running and a kernel transition would be needed to run it. This sets
 * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
 */
#define IORING_SETUP_TASKRUN_FLAG	(1U << 9)

#define IORING_SETUP_SQE128		(1U << 10) /* SQEs are 128 byte */
#define IORING_SETUP_CQE32		(1U << 11) /* CQEs are 32 byte */

/*
 * Only one task is allowed to submit requests
 */
#define IORING_SETUP_SINGLE_ISSUER	(1U << 12)

/*
 * Defer running task work to get events.
 * Rather than running bits of task work whenever the task transitions
 * try to do it just before it is needed.
 */
#define IORING_SETUP_DEFER_TASKRUN	(1U << 13)

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,
	IORING_OP_MSG_RING,
	IORING_OP_FSETXATTR,
	IORING_OP_SETXATTR,
	IORING_OP_FGETXATTR,
	IORING_OP_GETXATTR,
	IORING_OP_SOCKET,
	IORING_OP_URING_CMD,


	/* this goes last, obviously */
	IORING_OP_LAST,
};

/*
 * sqe->uring_cmd_flags
 * IORING_URING_CMD_FIXED	use registered buffer; pass thig flag
 *				along with setting sqe->buf_index.
 */
#define IORING_URING_CMD_FIXED	(1U << 0)

/*
 * 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)

#define IORING_NOP_INJECT_RESULT	(1U << 0)
#define IORING_NOP_FILE			(1U << 1)
#define IORING_NOP_FIXED_FILE		(1U << 2)
#define IORING_NOP_FIXED_BUFFER		(1U << 3)

/*
 * 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;

	/*
	 * If the ring is initialized with IORING_SETUP_CQE32, then this field
	 * contains 16-bytes of padding, doubling the size of the CQE.
	 */
	__u64 big_cqe[];
};

/*
 * 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)
#define IORING_ENTER_REGISTERED_RING	(1U << 4)

/*
 * 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,

	/* register/unregister io_uring fd with the ring */
	IORING_REGISTER_RING_FDS		= 20,
	IORING_UNREGISTER_RING_FDS		= 21,

	/* 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
Commit	Line	Data
	1	/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
	2	/*
	3	* Header file for the io_uring interface.
	4	*
	5	* Copyright (C) 2019 Jens Axboe
	6	* Copyright (C) 2019 Christoph Hellwig
	7	*/
	8	#ifndef LINUX_IO_URING_H
	9	#define LINUX_IO_URING_H
	10
	11	#include <linux/fs.h>
	12	#include <linux/types.h>
	13
	14	/*
	15	* IO submission data structure (Submission Queue Entry)
	16	*/
	17	struct io_uring_sqe {
	18	__u8 opcode; /* type of operation for this sqe */
	19	__u8 flags; /* IOSQE_ flags */
	20	__u16 ioprio; /* ioprio for the request */
	21	__s32 fd; /* file descriptor to do IO on */
	22	union {
	23	__u64 off; /* offset into file */
	24	__u64 addr2;
	25	struct {
	26	__u32 cmd_op;
	27	__u32 __pad1;
	28	};
	29	};
	30	union {
	31	__u64 addr; /* pointer to buffer or iovecs */
	32	__u64 splice_off_in;
	33	};
	34	__u32 len; /* buffer size or number of iovecs */
	35	union {
	36	__kernel_rwf_t rw_flags;
	37	__u32 fsync_flags;
	38	__u16 poll_events; /* compatibility */
	39	__u32 poll32_events; /* word-reversed for BE */
	40	__u32 sync_range_flags;
	41	__u32 msg_flags;
	42	__u32 timeout_flags;
	43	__u32 accept_flags;
	44	__u32 cancel_flags;
	45	__u32 open_flags;
	46	__u32 statx_flags;
	47	__u32 fadvise_advice;
	48	__u32 splice_flags;
	49	__u32 rename_flags;
	50	__u32 unlink_flags;
	51	__u32 hardlink_flags;
	52	__u32 uring_cmd_flags;
	53	};
	54	__u64 user_data; /* data to be passed back at completion time */
	55	/* pack this to avoid bogus arm OABI complaints */
	56	union {
	57	/* index into fixed buffers, if used */
	58	__u16 buf_index;
	59	/* for grouped buffer selection */
	60	__u16 buf_group;
	61	} __attribute__((packed));
	62	/* personality to use, if used */
	63	__u16 personality;
	64	union {
	65	__s32 splice_fd_in;
	66	__u32 file_index;
	67	};
	68	union {
	69	struct {
	70	__u64 addr3;
	71	__u64 __pad2[1];
	72	};
	73	/*
	74	* If the ring is initialized with IORING_SETUP_SQE128, then
	75	* this field is used for 80 bytes of arbitrary command data
	76	*/
	77	__u8 cmd[0];
	78	};
	79	};
	80
	81	enum {
	82	IOSQE_FIXED_FILE_BIT,
	83	IOSQE_IO_DRAIN_BIT,
	84	IOSQE_IO_LINK_BIT,
	85	IOSQE_IO_HARDLINK_BIT,
	86	IOSQE_ASYNC_BIT,
	87	IOSQE_BUFFER_SELECT_BIT,
	88	IOSQE_CQE_SKIP_SUCCESS_BIT,
	89	};
	90
	91	/*
	92	* sqe->flags
	93	*/
	94	/* use fixed fileset */
	95	#define IOSQE_FIXED_FILE (1U << IOSQE_FIXED_FILE_BIT)
	96	/* issue after inflight IO */
	97	#define IOSQE_IO_DRAIN (1U << IOSQE_IO_DRAIN_BIT)
	98	/* links next sqe */
	99	#define IOSQE_IO_LINK (1U << IOSQE_IO_LINK_BIT)
	100	/* like LINK, but stronger */
	101	#define IOSQE_IO_HARDLINK (1U << IOSQE_IO_HARDLINK_BIT)
	102	/* always go async */
	103	#define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT)
	104	/* select buffer from sqe->buf_group */
	105	#define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT)
	106	/* don't post CQE if request succeeded */
	107	#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT)
	108
	109	/*
	110	* io_uring_setup() flags
	111	*/
	112	#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */
	113	#define IORING_SETUP_SQPOLL (1U << 1) /* SQ poll thread */
	114	#define IORING_SETUP_SQ_AFF (1U << 2) /* sq_thread_cpu is valid */
	115	#define IORING_SETUP_CQSIZE (1U << 3) /* app defines CQ size */
	116	#define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */
	117	#define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */
	118	#define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */
	119	#define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */
	120	/*
	121	* Cooperative task running. When requests complete, they often require
	122	* forcing the submitter to transition to the kernel to complete. If this
	123	* flag is set, work will be done when the task transitions anyway, rather
	124	* than force an inter-processor interrupt reschedule. This avoids interrupting
	125	* a task running in userspace, and saves an IPI.
	126	*/
	127	#define IORING_SETUP_COOP_TASKRUN (1U << 8)
	128	/*
	129	* If COOP_TASKRUN is set, get notified if task work is available for
	130	* running and a kernel transition would be needed to run it. This sets
	131	* IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN.
	132	*/
	133	#define IORING_SETUP_TASKRUN_FLAG (1U << 9)
	134
	135	#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */
	136	#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */
	137
	138	/*
	139	* Only one task is allowed to submit requests
	140	*/
	141	#define IORING_SETUP_SINGLE_ISSUER (1U << 12)
	142
	143	/*
	144	* Defer running task work to get events.
	145	* Rather than running bits of task work whenever the task transitions
	146	* try to do it just before it is needed.
	147	*/
	148	#define IORING_SETUP_DEFER_TASKRUN (1U << 13)
	149
	150	enum {
	151	IORING_OP_NOP,
	152	IORING_OP_READV,
	153	IORING_OP_WRITEV,
	154	IORING_OP_FSYNC,
	155	IORING_OP_READ_FIXED,
	156	IORING_OP_WRITE_FIXED,
	157	IORING_OP_POLL_ADD,
	158	IORING_OP_POLL_REMOVE,
	159	IORING_OP_SYNC_FILE_RANGE,
	160	IORING_OP_SENDMSG,
	161	IORING_OP_RECVMSG,
	162	IORING_OP_TIMEOUT,
	163	IORING_OP_TIMEOUT_REMOVE,
	164	IORING_OP_ACCEPT,
	165	IORING_OP_ASYNC_CANCEL,
	166	IORING_OP_LINK_TIMEOUT,
	167	IORING_OP_CONNECT,
	168	IORING_OP_FALLOCATE,
	169	IORING_OP_OPENAT,
	170	IORING_OP_CLOSE,
	171	IORING_OP_FILES_UPDATE,
	172	IORING_OP_STATX,
	173	IORING_OP_READ,
	174	IORING_OP_WRITE,
	175	IORING_OP_FADVISE,
	176	IORING_OP_MADVISE,
	177	IORING_OP_SEND,
	178	IORING_OP_RECV,
	179	IORING_OP_OPENAT2,
	180	IORING_OP_EPOLL_CTL,
	181	IORING_OP_SPLICE,
	182	IORING_OP_PROVIDE_BUFFERS,
	183	IORING_OP_REMOVE_BUFFERS,
	184	IORING_OP_TEE,
	185	IORING_OP_SHUTDOWN,
	186	IORING_OP_RENAMEAT,
	187	IORING_OP_UNLINKAT,
	188	IORING_OP_MKDIRAT,
	189	IORING_OP_SYMLINKAT,
	190	IORING_OP_LINKAT,
	191	IORING_OP_MSG_RING,
	192	IORING_OP_FSETXATTR,
	193	IORING_OP_SETXATTR,
	194	IORING_OP_FGETXATTR,
	195	IORING_OP_GETXATTR,
	196	IORING_OP_SOCKET,
	197	IORING_OP_URING_CMD,
	198
	199
	200	/* this goes last, obviously */
	201	IORING_OP_LAST,
	202	};
	203
	204	/*
	205	* sqe->uring_cmd_flags
	206	* IORING_URING_CMD_FIXED use registered buffer; pass thig flag
	207	* along with setting sqe->buf_index.
	208	*/
	209	#define IORING_URING_CMD_FIXED (1U << 0)
	210
	211	/*
	212	* sqe->fsync_flags
	213	*/
	214	#define IORING_FSYNC_DATASYNC (1U << 0)
	215
	216	/*
	217	* sqe->timeout_flags
	218	*/
	219	#define IORING_TIMEOUT_ABS (1U << 0)
	220	#define IORING_TIMEOUT_UPDATE (1U << 1)
	221	#define IORING_TIMEOUT_BOOTTIME (1U << 2)
	222	#define IORING_TIMEOUT_REALTIME (1U << 3)
	223	#define IORING_LINK_TIMEOUT_UPDATE (1U << 4)
	224	#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5)
	225	#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME \| IORING_TIMEOUT_REALTIME)
	226	#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE \| IORING_LINK_TIMEOUT_UPDATE)
	227	/*
	228	* sqe->splice_flags
	229	* extends splice(2) flags
	230	*/
	231	#define SPLICE_F_FD_IN_FIXED (1U << 31) /* the last bit of __u32 */
	232
	233	/*
	234	* POLL_ADD flags. Note that since sqe->poll_events is the flag space, the
	235	* command flags for POLL_ADD are stored in sqe->len.
	236	*
	237	* IORING_POLL_ADD_MULTI Multishot poll. Sets IORING_CQE_F_MORE if
	238	* the poll handler will continue to report
	239	* CQEs on behalf of the same SQE.
	240	*
	241	* IORING_POLL_UPDATE Update existing poll request, matching
	242	* sqe->addr as the old user_data field.
	243	*/
	244	#define IORING_POLL_ADD_MULTI (1U << 0)
	245	#define IORING_POLL_UPDATE_EVENTS (1U << 1)
	246	#define IORING_POLL_UPDATE_USER_DATA (1U << 2)
	247
	248	#define IORING_NOP_INJECT_RESULT (1U << 0)
	249	#define IORING_NOP_FILE (1U << 1)
	250	#define IORING_NOP_FIXED_FILE (1U << 2)
	251	#define IORING_NOP_FIXED_BUFFER (1U << 3)
	252
	253	/*
	254	* IO completion data structure (Completion Queue Entry)
	255	*/
	256	struct io_uring_cqe {
	257	__u64 user_data; /* sqe->data submission passed back */
	258	__s32 res; /* result code for this event */
	259	__u32 flags;
	260
	261	/*
	262	* If the ring is initialized with IORING_SETUP_CQE32, then this field
	263	* contains 16-bytes of padding, doubling the size of the CQE.
	264	*/
	265	__u64 big_cqe[];
	266	};
	267
	268	/*
	269	* cqe->flags
	270	*
	271	* IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID
	272	* IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries
	273	*/
	274	#define IORING_CQE_F_BUFFER (1U << 0)
	275	#define IORING_CQE_F_MORE (1U << 1)
	276
	277	enum {
	278	IORING_CQE_BUFFER_SHIFT = 16,
	279	};
	280
	281	/*
	282	* Magic offsets for the application to mmap the data it needs
	283	*/
	284	#define IORING_OFF_SQ_RING 0ULL
	285	#define IORING_OFF_CQ_RING 0x8000000ULL
	286	#define IORING_OFF_SQES 0x10000000ULL
	287
	288	/*
	289	* Filled with the offset for mmap(2)
	290	*/
	291	struct io_sqring_offsets {
	292	__u32 head;
	293	__u32 tail;
	294	__u32 ring_mask;
	295	__u32 ring_entries;
	296	__u32 flags;
	297	__u32 dropped;
	298	__u32 array;
	299	__u32 resv1;
	300	__u64 resv2;
	301	};
	302
	303	/*
	304	* sq_ring->flags
	305	*/
	306	#define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */
	307	#define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */
	308
	309	struct io_cqring_offsets {
	310	__u32 head;
	311	__u32 tail;
	312	__u32 ring_mask;
	313	__u32 ring_entries;
	314	__u32 overflow;
	315	__u32 cqes;
	316	__u32 flags;
	317	__u32 resv1;
	318	__u64 resv2;
	319	};
	320
	321	/*
	322	* cq_ring->flags
	323	*/
	324
	325	/* disable eventfd notifications */
	326	#define IORING_CQ_EVENTFD_DISABLED (1U << 0)
	327
	328	/*
	329	* io_uring_enter(2) flags
	330	*/
	331	#define IORING_ENTER_GETEVENTS (1U << 0)
	332	#define IORING_ENTER_SQ_WAKEUP (1U << 1)
	333	#define IORING_ENTER_SQ_WAIT (1U << 2)
	334	#define IORING_ENTER_EXT_ARG (1U << 3)
	335	#define IORING_ENTER_REGISTERED_RING (1U << 4)
	336
	337	/*
	338	* Passed in for io_uring_setup(2). Copied back with updated info on success
	339	*/
	340	struct io_uring_params {
	341	__u32 sq_entries;
	342	__u32 cq_entries;
	343	__u32 flags;
	344	__u32 sq_thread_cpu;
	345	__u32 sq_thread_idle;
	346	__u32 features;
	347	__u32 wq_fd;
	348	__u32 resv[3];
	349	struct io_sqring_offsets sq_off;
	350	struct io_cqring_offsets cq_off;
	351	};
	352
	353	/*
	354	* io_uring_params->features flags
	355	*/
	356	#define IORING_FEAT_SINGLE_MMAP (1U << 0)
	357	#define IORING_FEAT_NODROP (1U << 1)
	358	#define IORING_FEAT_SUBMIT_STABLE (1U << 2)
	359	#define IORING_FEAT_RW_CUR_POS (1U << 3)
	360	#define IORING_FEAT_CUR_PERSONALITY (1U << 4)
	361	#define IORING_FEAT_FAST_POLL (1U << 5)
	362	#define IORING_FEAT_POLL_32BITS (1U << 6)
	363	#define IORING_FEAT_SQPOLL_NONFIXED (1U << 7)
	364	#define IORING_FEAT_EXT_ARG (1U << 8)
	365	#define IORING_FEAT_NATIVE_WORKERS (1U << 9)
	366	#define IORING_FEAT_RSRC_TAGS (1U << 10)
	367	#define IORING_FEAT_CQE_SKIP (1U << 11)
	368
	369	/*
	370	* io_uring_register(2) opcodes and arguments
	371	*/
	372	enum {
	373	IORING_REGISTER_BUFFERS = 0,
	374	IORING_UNREGISTER_BUFFERS = 1,
	375	IORING_REGISTER_FILES = 2,
	376	IORING_UNREGISTER_FILES = 3,
	377	IORING_REGISTER_EVENTFD = 4,
	378	IORING_UNREGISTER_EVENTFD = 5,
	379	IORING_REGISTER_FILES_UPDATE = 6,
	380	IORING_REGISTER_EVENTFD_ASYNC = 7,
	381	IORING_REGISTER_PROBE = 8,
	382	IORING_REGISTER_PERSONALITY = 9,
	383	IORING_UNREGISTER_PERSONALITY = 10,
	384	IORING_REGISTER_RESTRICTIONS = 11,
	385	IORING_REGISTER_ENABLE_RINGS = 12,
	386
	387	/* extended with tagging */
	388	IORING_REGISTER_FILES2 = 13,
	389	IORING_REGISTER_FILES_UPDATE2 = 14,
	390	IORING_REGISTER_BUFFERS2 = 15,
	391	IORING_REGISTER_BUFFERS_UPDATE = 16,
	392
	393	/* set/clear io-wq thread affinities */
	394	IORING_REGISTER_IOWQ_AFF = 17,
	395	IORING_UNREGISTER_IOWQ_AFF = 18,
	396
	397	/* set/get max number of io-wq workers */
	398	IORING_REGISTER_IOWQ_MAX_WORKERS = 19,
	399
	400	/* register/unregister io_uring fd with the ring */
	401	IORING_REGISTER_RING_FDS = 20,
	402	IORING_UNREGISTER_RING_FDS = 21,
	403
	404	/* this goes last */
	405	IORING_REGISTER_LAST
	406	};
	407
	408	/* io-wq worker categories */
	409	enum {
	410	IO_WQ_BOUND,
	411	IO_WQ_UNBOUND,
	412	};
	413
	414	/* deprecated, see struct io_uring_rsrc_update */
	415	struct io_uring_files_update {
	416	__u32 offset;
	417	__u32 resv;
	418	__aligned_u64 /* __s32 * */ fds;
	419	};
	420
	421	struct io_uring_rsrc_register {
	422	__u32 nr;
	423	__u32 resv;
	424	__u64 resv2;
	425	__aligned_u64 data;
	426	__aligned_u64 tags;
	427	};
	428
	429	struct io_uring_rsrc_update {
	430	__u32 offset;
	431	__u32 resv;
	432	__aligned_u64 data;
	433	};
	434
	435	struct io_uring_rsrc_update2 {
	436	__u32 offset;
	437	__u32 resv;
	438	__aligned_u64 data;
	439	__aligned_u64 tags;
	440	__u32 nr;
	441	__u32 resv2;
	442	};
	443
	444	/* Skip updating fd indexes set to this value in the fd table */
	445	#define IORING_REGISTER_FILES_SKIP (-2)
	446
	447	#define IO_URING_OP_SUPPORTED (1U << 0)
	448
	449	struct io_uring_probe_op {
	450	__u8 op;
	451	__u8 resv;
	452	__u16 flags; /* IO_URING_OP_* flags */
	453	__u32 resv2;
	454	};
	455
	456	struct io_uring_probe {
	457	__u8 last_op; /* last opcode supported */
	458	__u8 ops_len; /* length of ops[] array below */
	459	__u16 resv;
	460	__u32 resv2[3];
	461	struct io_uring_probe_op ops[0];
	462	};
	463
	464	struct io_uring_restriction {
	465	__u16 opcode;
	466	union {
	467	__u8 register_op; /* IORING_RESTRICTION_REGISTER_OP */
	468	__u8 sqe_op; /* IORING_RESTRICTION_SQE_OP */
	469	__u8 sqe_flags; /* IORING_RESTRICTION_SQE_FLAGS_* */
	470	};
	471	__u8 resv;
	472	__u32 resv2[3];
	473	};
	474
	475	/*
	476	* io_uring_restriction->opcode values
	477	*/
	478	enum {
	479	/* Allow an io_uring_register(2) opcode */
	480	IORING_RESTRICTION_REGISTER_OP = 0,
	481
	482	/* Allow an sqe opcode */
	483	IORING_RESTRICTION_SQE_OP = 1,
	484
	485	/* Allow sqe flags */
	486	IORING_RESTRICTION_SQE_FLAGS_ALLOWED = 2,
	487
	488	/* Require sqe flags (these flags must be set on each submission) */
	489	IORING_RESTRICTION_SQE_FLAGS_REQUIRED = 3,
	490
	491	IORING_RESTRICTION_LAST
	492	};
	493
	494	struct io_uring_getevents_arg {
	495	__u64 sigmask;
	496	__u32 sigmask_sz;
	497	__u32 pad;
	498	__u64 ts;
	499	};
	500
	501	#endif