summaryrefslogtreecommitdiff
path: root/include/linux/aio.h
blob: fd628f9d21652bfe147115217a0d658da56552bd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
#ifndef __LINUX__AIO_H
#define __LINUX__AIO_H

#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/aio_abi.h>
#include <linux/uio.h>
#include <linux/rcupdate.h>

#include <linux/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 */
/*
 * 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 */
#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)

/* 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.
 */
struct kiocb {
	struct list_head	ki_run_list;
	unsigned long		ki_flags;
	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;

	__u64			ki_user_data;	/* user's data for completion */
	loff_t			ki_pos;

	void			*private;
	/* 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 */
	struct iovec		ki_inline_vec;	/* inline vector */
 	struct iovec		*ki_iovec;
 	unsigned long		ki_nr_segs;
 	unsigned long		ki_cur_seg;

	struct list_head	ki_list;	/* the aio core uses this
						 * for cancellation */
	struct list_head	ki_batch;	/* batch allocation */

	struct iocb_attr_list	*ki_attrs;
	struct iocb_attr_ret_list *ki_attr_rets;

	/*
	 * If the aio_resfd field of the userspace iocb is not zero,
	 * this is the underlying eventfd context to deliver events to.
	 */
	struct eventfd_ctx	*ki_eventfd;
};

static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
	return kiocb->ki_key == KIOCB_SYNC_KEY;
}

static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
	*kiocb = (struct kiocb) {
			.ki_users = 1,
			.ki_key = KIOCB_SYNC_KEY,
			.ki_filp = filp,
			.ki_obj.tsk = current,
		};
}

#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_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];
};

static inline unsigned aio_ring_avail(struct aio_ring_info *info,
					struct aio_ring *ring)
{
	return (ring->head + info->nr - 1 - ring->tail) % info->nr;
}

struct kioctx {
	atomic_t		users;
	int			dead;
	struct mm_struct	*mm;

	/* This needs improving */
	unsigned long		user_id;
	struct hlist_node	list;

	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 */

	/* sys_io_setup currently limits this to an unsigned int */
	unsigned		max_reqs;

	struct aio_ring_info	ring_info;

	struct delayed_work	wq;

	struct rcu_head		rcu_head;
};

/* prototypes */
extern unsigned aio_max_size;

#ifdef CONFIG_AIO
extern ssize_t wait_on_sync_kiocb(struct kiocb *iocb);
extern void aio_put_req(struct kiocb *iocb);
extern void kick_iocb(struct kiocb *iocb);
extern void aio_complete(struct kiocb *iocb, long res, long res2);
struct mm_struct;
extern void exit_aio(struct mm_struct *mm);
extern long do_io_submit(aio_context_t ctx_id, long nr,
			 struct iocb __user *__user *iocbpp, bool compat);
#else
static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
static inline void aio_put_req(struct kiocb *iocb) { }
static inline void kick_iocb(struct kiocb *iocb) { }
static inline void aio_complete(struct kiocb *iocb, long res, long res2) { }
struct mm_struct;
static inline void exit_aio(struct mm_struct *mm) { }
static inline long do_io_submit(aio_context_t ctx_id, long nr,
				struct iocb __user * __user *iocbpp,
				bool compat) { return 0; }
#endif /* CONFIG_AIO */

#define for_each_iocb_attr(attr, attr_list)				\
	for (attr = (attr_list)->attrs;					\
	     attr != ((void *) (attr_list)) + (attr_list)->size;	\
	     attr = ((void *) attr) + (attr)->size)

static inline struct kiocb *list_kiocb(struct list_head *h)
{
	return list_entry(h, struct kiocb, ki_list);
}

static inline struct iocb_attr *iocb_attr_next(struct iocb_attr_list *attrs,
					       struct iocb_attr *attr)
{
	void *end = ((void *) attrs) + attrs->size;

	if (attr)
		attr = ((void *) attr) + attr->size;
	else
		attr = attrs->attrs;

	if (attr == end)
		return attr;

	return attr;
}

static inline void *__iocb_attr_lookup(struct iocb_attr_list *attrs, unsigned id)
{
	struct iocb_attr *attr = NULL;

	if (!attrs)
		return NULL;

	while (1) {
		attr = iocb_attr_next(attrs, attr);
		if (!attr)
			return NULL;

		if (attr->id == id)
			return attr;
	}

	return NULL;
}

#define iocb_attr_lookup(attrs, id)					\
({									\
	struct iocb_attr *_attr;					\
									\
	_attr = __iocb_attr_lookup((attrs), IOCB_ATTR_ ## id);		\
	if (_attr->size != sizeof(struct iocb_attr_ ## id))		\
		_attr = NULL;						\
									\
	(struct iocb_attr_ ## id *) _attr;				\
})

/* for sysctl: */
extern unsigned long aio_nr;
extern unsigned long aio_max_nr;

#endif /* __LINUX__AIO_H */