2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __LINUX__AIO_H
|
|
|
|
#define __LINUX__AIO_H
|
|
|
|
|
|
|
|
#include <linux/list.h>
|
|
|
|
#include <linux/workqueue.h>
|
|
|
|
#include <linux/aio_abi.h>
|
2006-10-01 14:28:46 +08:00
|
|
|
#include <linux/uio.h>
|
2008-12-09 15:11:22 +08:00
|
|
|
#include <linux/rcupdate.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/atomic.h>
|
|
|
|
|
|
|
|
#define AIO_MAXSEGS 4
|
|
|
|
#define AIO_KIOGRP_NR_ATOMIC 8
|
|
|
|
|
|
|
|
struct kioctx;
|
|
|
|
|
|
|
|
/* Notes on cancelling a kiocb:
|
|
|
|
* If a kiocb is cancelled, aio_complete may return 0 to indicate
|
|
|
|
* that cancel has not yet disposed of the kiocb. All cancel
|
|
|
|
* operations *must* call aio_put_req to dispose of the kiocb
|
|
|
|
* to guard against races with the completion code.
|
|
|
|
*/
|
|
|
|
#define KIOCB_C_CANCELLED 0x01
|
|
|
|
#define KIOCB_C_COMPLETE 0x02
|
|
|
|
|
|
|
|
#define KIOCB_SYNC_KEY (~0U)
|
|
|
|
|
|
|
|
/* ki_flags bits */
|
2005-10-18 07:43:33 +08:00
|
|
|
/*
|
|
|
|
* This may be used for cancel/retry serialization in the future, but
|
|
|
|
* for now it's unused and we probably don't want modules to even
|
|
|
|
* think they can use it.
|
|
|
|
*/
|
|
|
|
/* #define KIF_LOCKED 0 */
|
2005-04-17 06:20:36 +08:00
|
|
|
#define KIF_KICKED 1
|
|
|
|
#define KIF_CANCELLED 2
|
|
|
|
|
|
|
|
#define kiocbTryLock(iocb) test_and_set_bit(KIF_LOCKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbTryKick(iocb) test_and_set_bit(KIF_KICKED, &(iocb)->ki_flags)
|
|
|
|
|
|
|
|
#define kiocbSetLocked(iocb) set_bit(KIF_LOCKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbSetKicked(iocb) set_bit(KIF_KICKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbSetCancelled(iocb) set_bit(KIF_CANCELLED, &(iocb)->ki_flags)
|
|
|
|
|
|
|
|
#define kiocbClearLocked(iocb) clear_bit(KIF_LOCKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbClearKicked(iocb) clear_bit(KIF_KICKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbClearCancelled(iocb) clear_bit(KIF_CANCELLED, &(iocb)->ki_flags)
|
|
|
|
|
|
|
|
#define kiocbIsLocked(iocb) test_bit(KIF_LOCKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbIsKicked(iocb) test_bit(KIF_KICKED, &(iocb)->ki_flags)
|
|
|
|
#define kiocbIsCancelled(iocb) test_bit(KIF_CANCELLED, &(iocb)->ki_flags)
|
|
|
|
|
2005-10-01 02:58:55 +08:00
|
|
|
/* is there a better place to document function pointer methods? */
|
|
|
|
/**
|
|
|
|
* ki_retry - iocb forward progress callback
|
|
|
|
* @kiocb: The kiocb struct to advance by performing an operation.
|
|
|
|
*
|
|
|
|
* This callback is called when the AIO core wants a given AIO operation
|
|
|
|
* to make forward progress. The kiocb argument describes the operation
|
|
|
|
* that is to be performed. As the operation proceeds, perhaps partially,
|
|
|
|
* ki_retry is expected to update the kiocb with progress made. Typically
|
|
|
|
* ki_retry is set in the AIO core and it itself calls file_operations
|
|
|
|
* helpers.
|
|
|
|
*
|
|
|
|
* ki_retry's return value determines when the AIO operation is completed
|
|
|
|
* and an event is generated in the AIO event ring. Except the special
|
|
|
|
* return values described below, the value that is returned from ki_retry
|
|
|
|
* is transferred directly into the completion ring as the operation's
|
|
|
|
* resulting status. Once this has happened ki_retry *MUST NOT* reference
|
|
|
|
* the kiocb pointer again.
|
|
|
|
*
|
|
|
|
* If ki_retry returns -EIOCBQUEUED it has made a promise that aio_complete()
|
|
|
|
* will be called on the kiocb pointer in the future. The AIO core will
|
|
|
|
* not ask the method again -- ki_retry must ensure forward progress.
|
|
|
|
* aio_complete() must be called once and only once in the future, multiple
|
|
|
|
* calls may result in undefined behaviour.
|
|
|
|
*
|
|
|
|
* If ki_retry returns -EIOCBRETRY it has made a promise that kick_iocb()
|
|
|
|
* will be called on the kiocb pointer in the future. This may happen
|
|
|
|
* through generic helpers that associate kiocb->ki_wait with a wait
|
|
|
|
* queue head that ki_retry uses via current->io_wait. It can also happen
|
|
|
|
* with custom tracking and manual calls to kick_iocb(), though that is
|
|
|
|
* discouraged. In either case, kick_iocb() must be called once and only
|
|
|
|
* once. ki_retry must ensure forward progress, the AIO core will wait
|
|
|
|
* indefinitely for kick_iocb() to be called.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
struct kiocb {
|
|
|
|
struct list_head ki_run_list;
|
2007-07-19 16:47:55 +08:00
|
|
|
unsigned long ki_flags;
|
2005-04-17 06:20:36 +08:00
|
|
|
int ki_users;
|
|
|
|
unsigned ki_key; /* id of this request */
|
|
|
|
|
|
|
|
struct file *ki_filp;
|
|
|
|
struct kioctx *ki_ctx; /* may be NULL for sync ops */
|
|
|
|
int (*ki_cancel)(struct kiocb *, struct io_event *);
|
|
|
|
ssize_t (*ki_retry)(struct kiocb *);
|
|
|
|
void (*ki_dtor)(struct kiocb *);
|
|
|
|
|
|
|
|
union {
|
|
|
|
void __user *user;
|
|
|
|
struct task_struct *tsk;
|
|
|
|
} ki_obj;
|
2006-01-08 17:04:34 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
__u64 ki_user_data; /* user's data for completion */
|
2006-01-08 17:04:34 +08:00
|
|
|
wait_queue_t ki_wait;
|
2005-04-17 06:20:36 +08:00
|
|
|
loff_t ki_pos;
|
2006-01-08 17:04:34 +08:00
|
|
|
|
|
|
|
void *private;
|
2005-04-17 06:20:36 +08:00
|
|
|
/* State that we remember to be able to restart/retry */
|
|
|
|
unsigned short ki_opcode;
|
|
|
|
size_t ki_nbytes; /* copy of iocb->aio_nbytes */
|
|
|
|
char __user *ki_buf; /* remaining iocb->aio_buf */
|
|
|
|
size_t ki_left; /* remaining bytes */
|
2006-10-01 14:28:46 +08:00
|
|
|
struct iovec ki_inline_vec; /* inline vector */
|
2006-10-01 14:28:49 +08:00
|
|
|
struct iovec *ki_iovec;
|
|
|
|
unsigned long ki_nr_segs;
|
|
|
|
unsigned long ki_cur_seg;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2006-01-08 17:04:34 +08:00
|
|
|
struct list_head ki_list; /* the aio core uses this
|
|
|
|
* for cancellation */
|
signal/timer/event: KAIO eventfd support example
This is an example about how to add eventfd support to the current KAIO code,
in order to enable KAIO to post readiness events to a pollable fd (hence
compatible with POSIX select/poll). The KAIO code simply signals the eventfd
fd when events are ready, and this triggers a POLLIN in the fd. This patch
uses a reserved for future use member of the struct iocb to pass an eventfd
file descriptor, that KAIO will use to post events every time a request
completes. At that point, an aio_getevents() will return the completed result
to a struct io_event. I made a quick test program to verify the patch, and it
runs fine here:
http://www.xmailserver.org/eventfd-aio-test.c
The test program uses poll(2), but it'd, of course, work with select and epoll
too.
This can allow to schedule both block I/O and other poll-able devices
requests, and wait for results using select/poll/epoll. In a typical
scenario, an application would submit KAIO request using aio_submit(), and
will also use epoll_ctl() on the whole other class of devices (that with the
addition of signals, timers and user events, now it's pretty much complete),
and then would:
epoll_wait(...);
for_each_event {
if (curr_event_is_kaiofd) {
aio_getevents();
dispatch_aio_events();
} else {
dispatch_epoll_event();
}
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-11 13:23:21 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If the aio_resfd field of the userspace iocb is not zero,
|
2009-07-01 02:41:11 +08:00
|
|
|
* this is the underlying eventfd context to deliver events to.
|
signal/timer/event: KAIO eventfd support example
This is an example about how to add eventfd support to the current KAIO code,
in order to enable KAIO to post readiness events to a pollable fd (hence
compatible with POSIX select/poll). The KAIO code simply signals the eventfd
fd when events are ready, and this triggers a POLLIN in the fd. This patch
uses a reserved for future use member of the struct iocb to pass an eventfd
file descriptor, that KAIO will use to post events every time a request
completes. At that point, an aio_getevents() will return the completed result
to a struct io_event. I made a quick test program to verify the patch, and it
runs fine here:
http://www.xmailserver.org/eventfd-aio-test.c
The test program uses poll(2), but it'd, of course, work with select and epoll
too.
This can allow to schedule both block I/O and other poll-able devices
requests, and wait for results using select/poll/epoll. In a typical
scenario, an application would submit KAIO request using aio_submit(), and
will also use epoll_ctl() on the whole other class of devices (that with the
addition of signals, timers and user events, now it's pretty much complete),
and then would:
epoll_wait(...);
for_each_event {
if (curr_event_is_kaiofd) {
aio_getevents();
dispatch_aio_events();
} else {
dispatch_epoll_event();
}
}
Signed-off-by: Davide Libenzi <davidel@xmailserver.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-11 13:23:21 +08:00
|
|
|
*/
|
2009-07-01 02:41:11 +08:00
|
|
|
struct eventfd_ctx *ki_eventfd;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
#define is_sync_kiocb(iocb) ((iocb)->ki_key == KIOCB_SYNC_KEY)
|
|
|
|
#define init_sync_kiocb(x, filp) \
|
|
|
|
do { \
|
|
|
|
struct task_struct *tsk = current; \
|
|
|
|
(x)->ki_flags = 0; \
|
|
|
|
(x)->ki_users = 1; \
|
|
|
|
(x)->ki_key = KIOCB_SYNC_KEY; \
|
|
|
|
(x)->ki_filp = (filp); \
|
2005-11-14 08:07:33 +08:00
|
|
|
(x)->ki_ctx = NULL; \
|
2005-04-17 06:20:36 +08:00
|
|
|
(x)->ki_cancel = NULL; \
|
2006-01-08 17:04:34 +08:00
|
|
|
(x)->ki_retry = NULL; \
|
2005-04-17 06:20:36 +08:00
|
|
|
(x)->ki_dtor = NULL; \
|
|
|
|
(x)->ki_obj.tsk = tsk; \
|
|
|
|
(x)->ki_user_data = 0; \
|
|
|
|
init_wait((&(x)->ki_wait)); \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define AIO_RING_MAGIC 0xa10a10a1
|
|
|
|
#define AIO_RING_COMPAT_FEATURES 1
|
|
|
|
#define AIO_RING_INCOMPAT_FEATURES 0
|
|
|
|
struct aio_ring {
|
|
|
|
unsigned id; /* kernel internal index number */
|
|
|
|
unsigned nr; /* number of io_events */
|
|
|
|
unsigned head;
|
|
|
|
unsigned tail;
|
|
|
|
|
|
|
|
unsigned magic;
|
|
|
|
unsigned compat_features;
|
|
|
|
unsigned incompat_features;
|
|
|
|
unsigned header_length; /* size of aio_ring */
|
|
|
|
|
|
|
|
|
|
|
|
struct io_event io_events[0];
|
|
|
|
}; /* 128 bytes + ring size */
|
|
|
|
|
|
|
|
#define aio_ring_avail(info, ring) (((ring)->head + (info)->nr - 1 - (ring)->tail) % (info)->nr)
|
|
|
|
|
|
|
|
#define AIO_RING_PAGES 8
|
|
|
|
struct aio_ring_info {
|
|
|
|
unsigned long mmap_base;
|
|
|
|
unsigned long mmap_size;
|
|
|
|
|
|
|
|
struct page **ring_pages;
|
|
|
|
spinlock_t ring_lock;
|
|
|
|
long nr_pages;
|
|
|
|
|
|
|
|
unsigned nr, tail;
|
|
|
|
|
|
|
|
struct page *internal_pages[AIO_RING_PAGES];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct kioctx {
|
|
|
|
atomic_t users;
|
|
|
|
int dead;
|
|
|
|
struct mm_struct *mm;
|
|
|
|
|
|
|
|
/* This needs improving */
|
|
|
|
unsigned long user_id;
|
2008-12-09 15:11:22 +08:00
|
|
|
struct hlist_node list;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
wait_queue_head_t wait;
|
|
|
|
|
|
|
|
spinlock_t ctx_lock;
|
|
|
|
|
|
|
|
int reqs_active;
|
|
|
|
struct list_head active_reqs; /* used for cancellation */
|
|
|
|
struct list_head run_list; /* used for kicked reqs */
|
|
|
|
|
2005-11-07 16:59:31 +08:00
|
|
|
/* sys_io_setup currently limits this to an unsigned int */
|
2005-04-17 06:20:36 +08:00
|
|
|
unsigned max_reqs;
|
|
|
|
|
|
|
|
struct aio_ring_info ring_info;
|
|
|
|
|
2006-11-22 22:54:01 +08:00
|
|
|
struct delayed_work wq;
|
2008-12-09 15:11:22 +08:00
|
|
|
|
|
|
|
struct rcu_head rcu_head;
|
2005-04-17 06:20:36 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
/* prototypes */
|
|
|
|
extern unsigned aio_max_size;
|
|
|
|
|
2008-10-16 13:05:12 +08:00
|
|
|
#ifdef CONFIG_AIO
|
2008-02-14 07:03:15 +08:00
|
|
|
extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
|
|
|
|
extern int aio_put_req(struct kiocb *iocb);
|
|
|
|
extern void kick_iocb(struct kiocb *iocb);
|
|
|
|
extern int aio_complete(struct kiocb *iocb, long res, long res2);
|
2005-04-17 06:20:36 +08:00
|
|
|
struct mm_struct;
|
2008-02-14 07:03:15 +08:00
|
|
|
extern void exit_aio(struct mm_struct *mm);
|
2008-10-16 13:05:12 +08:00
|
|
|
#else
|
|
|
|
static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
|
|
|
|
static inline int aio_put_req(struct kiocb *iocb) { return 0; }
|
|
|
|
static inline void kick_iocb(struct kiocb *iocb) { }
|
|
|
|
static inline int aio_complete(struct kiocb *iocb, long res, long res2) { return 0; }
|
|
|
|
struct mm_struct;
|
|
|
|
static inline void exit_aio(struct mm_struct *mm) { }
|
|
|
|
#endif /* CONFIG_AIO */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define io_wait_to_kiocb(wait) container_of(wait, struct kiocb, ki_wait)
|
|
|
|
|
|
|
|
static inline struct kiocb *list_kiocb(struct list_head *h)
|
|
|
|
{
|
|
|
|
return list_entry(h, struct kiocb, ki_list);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* for sysctl: */
|
2005-11-07 16:59:31 +08:00
|
|
|
extern unsigned long aio_nr;
|
|
|
|
extern unsigned long aio_max_nr;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#endif /* __LINUX__AIO_H */
|