183bd5a34b
Implement the linux_io_* syscalls (AIO). They are only enabled if the native
AIO code is available (either compiled in to the kernel or as a module) at
the time the functions are used. If the AIO stuff is not available there
will be a ENOSYS.
From the submitter:
---snip---
DESIGN NOTES:
1. Linux permits a process to own multiple AIO queues (distinguished by
"context"), but FreeBSD creates only one single AIO queue per process.
My code maintains a request queue (STAILQ of queue(3)) per "context",
and throws all AIO requests of all contexts owned by a process into
the single FreeBSD per-process AIO queue.
When the process calls io_destroy(2), io_getevents(2), io_submit(2) and
io_cancel(2), my code can pick out requests owned by the specified context
from the single FreeBSD per-process AIO queue according to the per-context
request queues maintained by my code.
2. The request queue maintained by my code stores contrast information between
Linux IO control blocks (struct linux_iocb) and FreeBSD IO control blocks
(struct aiocb). FreeBSD IO control block actually exists in userland memory
space, required by FreeBSD native aio_XXXXXX(2).
3. It is quite troubling that the function io_getevents() of libaio-0.3.105
needs to use Linux-specific "struct aio_ring", which is a partial mirror
of context in user space. I would rather take the address of context in
kernel as the context ID, but the io_getevents() of libaio forces me to
take the address of the "ring" in user space as the context ID.
To my surprise, one comment line in the file "io_getevents.c" of
libaio-0.3.105 reads:
Ben will hate me for this
REFERENCE:
1. Linux kernel source code: http://www.kernel.org/pub/linux/kernel/v2.6/
(include/linux/aio_abi.h, fs/aio.c)
2. Linux manual pages: http://www.kernel.org/pub/linux/docs/manpages/
(io_setup(2), io_destroy(2), io_getevents(2), io_submit(2), io_cancel(2))
3. Linux Scalability Effort: http://lse.sourceforge.net/io/aio.html
The design notes: http://lse.sourceforge.net/io/aionotes.txt
4. The package libaio, both source and binary:
http://rpmfind.net/linux/rpm2html/search.php?query=libaio
Simple transparent interface to Linux AIO system calls.
5. Libaio-oracle: http://oss.oracle.com/projects/libaio-oracle/
POSIX AIO implementation based on Linux AIO system calls (depending on
libaio).
---snip---
Submitted by: Li, Xiao <intron@intron.ac>
99 lines
2.8 KiB
C
99 lines
2.8 KiB
C
/*-
|
|
* Copyright (c) 2006 Li, Xiao <intron@intron.ac>. All rights reserved.
|
|
*
|
|
* Redistribution and use in source and binary forms, with or without
|
|
* modification, are permitted provided that the following conditions
|
|
* are met:
|
|
* 1. Redistributions of source code must retain the above copyright
|
|
* notice, this list of conditions and the following disclaimer.
|
|
* 2. Redistributions in binary form must reproduce the above copyright
|
|
* notice, this list of conditions and the following disclaimer in the
|
|
* documentation and/or other materials provided with the distribution.
|
|
*
|
|
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
|
|
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
|
|
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
|
|
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
|
|
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
|
|
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
|
|
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
|
|
* SUCH DAMAGE.
|
|
*
|
|
* $FreeBSD$
|
|
*/
|
|
|
|
/*
|
|
* Linux Kernel Implementation of Asynchronous I/O
|
|
*/
|
|
|
|
#ifndef _LINUX_AIO_H_
|
|
#define _LINUX_AIO_H_
|
|
|
|
typedef unsigned long linux_aio_context_t;
|
|
|
|
enum {
|
|
LINUX_IOCB_CMD_PREAD = 0,
|
|
LINUX_IOCB_CMD_PWRITE = 1,
|
|
LINUX_IOCB_CMD_FSYNC = 2,
|
|
LINUX_IOCB_CMD_FDSYNC = 3,
|
|
#if 0
|
|
LINUX_IOCB_CMD_PREADX = 4,
|
|
LINUX_IOCB_CMD_POLL = 5,
|
|
#endif
|
|
LINUX_IOCB_CMD_NOOP = 6,
|
|
};
|
|
|
|
struct linux_io_event {
|
|
uint64_t data;
|
|
uint64_t obj;
|
|
int64_t res;
|
|
int64_t res2;
|
|
};
|
|
|
|
#if _BYTE_ORDER == _LITTLE_ENDIAN
|
|
#define LINUX_AIO_PADDED(x,y) x,y
|
|
#elif _BYTE_ORDER == _BIG_ENDIAN
|
|
#define LINUX_AIO_PADDED(x,y) y,x
|
|
#else
|
|
#error Unidentified byte order !!!
|
|
#endif
|
|
|
|
struct linux_iocb {
|
|
uint64_t aio_data;
|
|
uint32_t LINUX_AIO_PADDED(aio_key, aio_reserved1);
|
|
|
|
uint16_t aio_lio_opcode;
|
|
int16_t aio_reqprio;
|
|
uint32_t aio_fildes;
|
|
|
|
uint64_t aio_buf;
|
|
uint64_t aio_nbytes;
|
|
int64_t aio_offset;
|
|
|
|
uint64_t aio_reserved2; /* TODO: use this for a (struct sigevent *) */
|
|
uint64_t aio_reserved3;
|
|
|
|
};
|
|
|
|
/* User space context information structure */
|
|
struct linux_aio_ring {
|
|
l_uint ring_id;
|
|
l_uint ring_nr;
|
|
l_uint ring_head;
|
|
l_uint ring_tail;
|
|
#define LINUX_AIO_RING_MAGIC 0xa10a10a1
|
|
l_uint ring_magic;
|
|
#define LINUX_AIO_RING_COMPAT_FEATURES 1
|
|
l_uint ring_compat_features;
|
|
#define LINUX_AIO_RING_INCOMPAT_FEATURES 0
|
|
l_uint ring_incompat_features;
|
|
l_uint ring_header_length; /* Size of this structure */
|
|
|
|
struct linux_io_event ring_io_events[0];
|
|
};
|
|
|
|
#endif /* !_LINUX_AIO_H_ */
|