Files
linux-cryptodev-2.6/include/uapi/linux/io_uring.h
Jens Axboe edafccee56 io_uring: add support for pre-mapped user IO buffers
If we have fixed user buffers, we can map them into the kernel when we
setup the io_uring. That avoids the need to do get_user_pages() for
each and every IO.

To utilize this feature, the application must call io_uring_register()
after having setup an io_uring instance, passing in
IORING_REGISTER_BUFFERS as the opcode. The argument must be a pointer to
an iovec array, and the nr_args should contain how many iovecs the
application wishes to map.

If successful, these buffers are now mapped into the kernel, eligible
for IO. To use these fixed buffers, the application must use the
IORING_OP_READ_FIXED and IORING_OP_WRITE_FIXED opcodes, and then
set sqe->index to the desired buffer index. sqe->addr..sqe->addr+seq->len
must point to somewhere inside the indexed buffer.

The application may register buffers throughout the lifetime of the
io_uring instance. It can call io_uring_register() with
IORING_UNREGISTER_BUFFERS as the opcode to unregister the current set of
buffers, and then register a new set. The application need not
unregister buffers explicitly before shutting down the io_uring
instance.

It's perfectly valid to setup a larger buffer, and then sometimes only
use parts of it for an IO. As long as the range is within the originally
mapped region, it will work just fine.

For now, buffers must not be file backed. If file backed buffers are
passed in, the registration will fail with -1/EOPNOTSUPP. This
restriction may be relaxed in the future.

RLIMIT_MEMLOCK is used to check how much memory we can pin. A somewhat
arbitrary 1G per buffer size is also imposed.

Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-02-28 08:24:23 -07:00

118 lines
2.4 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; /* as of now unused */
__u16 ioprio; /* ioprio for the request */
__s32 fd; /* file descriptor to do IO on */
__u64 off; /* offset into file */
__u64 addr; /* pointer to buffer or iovecs */
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
__u32 fsync_flags;
};
__u64 user_data; /* data to be passed back at completion time */
union {
__u16 buf_index; /* index into fixed buffers, if used */
__u64 __pad2[3];
};
};
/*
* io_uring_setup() flags
*/
#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */
#define IORING_OP_NOP 0
#define IORING_OP_READV 1
#define IORING_OP_WRITEV 2
#define IORING_OP_FSYNC 3
#define IORING_OP_READ_FIXED 4
#define IORING_OP_WRITE_FIXED 5
/*
* sqe->fsync_flags
*/
#define IORING_FSYNC_DATASYNC (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;
};
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)
/*
* 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 resv[7];
struct io_sqring_offsets sq_off;
struct io_cqring_offsets cq_off;
};
/*
* io_uring_register(2) opcodes and arguments
*/
#define IORING_REGISTER_BUFFERS 0
#define IORING_UNREGISTER_BUFFERS 1
#endif