aboutsummaryrefslogtreecommitdiff
path: root/aio.c
blob: eb3bf42574fd07c480cea8ed0f2674293fbe3217 (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
/*
 * QEMU aio implementation
 *
 * Copyright IBM, Corp. 2008
 *
 * Authors:
 *  Anthony Liguori   <aliguori@us.ibm.com>
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 *
 * Contributions after 2012-01-13 are licensed under the terms of the
 * GNU GPL, version 2 or (at your option) any later version.
 */

#include "qemu-common.h"
#include "block.h"
#include "qemu-queue.h"
#include "qemu_socket.h"

typedef struct AioHandler AioHandler;

/* The list of registered AIO handlers */
static QLIST_HEAD(, AioHandler) aio_handlers;

/* This is a simple lock used to protect the aio_handlers list.  Specifically,
 * it's used to ensure that no callbacks are removed while we're walking and
 * dispatching callbacks.
 */
static int walking_handlers;

struct AioHandler
{
    int fd;
    IOHandler *io_read;
    IOHandler *io_write;
    AioFlushHandler *io_flush;
    AioProcessQueue *io_process_queue;
    int deleted;
    void *opaque;
    QLIST_ENTRY(AioHandler) node;
};

static AioHandler *find_aio_handler(int fd)
{
    AioHandler *node;

    QLIST_FOREACH(node, &aio_handlers, node) {
        if (node->fd == fd)
            if (!node->deleted)
                return node;
    }

    return NULL;
}

int qemu_aio_set_fd_handler(int fd,
                            IOHandler *io_read,
                            IOHandler *io_write,
                            AioFlushHandler *io_flush,
                            AioProcessQueue *io_process_queue,
                            void *opaque)
{
    AioHandler *node;

    node = find_aio_handler(fd);

    /* Are we deleting the fd handler? */
    if (!io_read && !io_write) {
        if (node) {
            /* If the lock is held, just mark the node as deleted */
            if (walking_handlers)
                node->deleted = 1;
            else {
                /* Otherwise, delete it for real.  We can't just mark it as
                 * deleted because deleted nodes are only cleaned up after
                 * releasing the walking_handlers lock.
                 */
                QLIST_REMOVE(node, node);
                g_free(node);
            }
        }
    } else {
        if (node == NULL) {
            /* Alloc and insert if it's not already there */
            node = g_malloc0(sizeof(AioHandler));
            node->fd = fd;
            QLIST_INSERT_HEAD(&aio_handlers, node, node);
        }
        /* Update handler with latest information */
        node->io_read = io_read;
        node->io_write = io_write;
        node->io_flush = io_flush;
        node->io_process_queue = io_process_queue;
        node->opaque = opaque;
    }

    qemu_set_fd_handler2(fd, NULL, io_read, io_write, opaque);

    return 0;
}

void qemu_aio_flush(void)
{
    AioHandler *node;
    int ret;

    do {
        ret = 0;

	/*
	 * If there are pending emulated aio start them now so flush
	 * will be able to return 1.
	 */
        qemu_aio_wait();

        QLIST_FOREACH(node, &aio_handlers, node) {
            if (node->io_flush) {
                ret |= node->io_flush(node->opaque);
            }
        }
    } while (qemu_bh_poll() || ret > 0);
}

int qemu_aio_process_queue(void)
{
    AioHandler *node;
    int ret = 0;

    walking_handlers = 1;

    QLIST_FOREACH(node, &aio_handlers, node) {
        if (node->io_process_queue) {
            if (node->io_process_queue(node->opaque)) {
                ret = 1;
            }
        }
    }

    walking_handlers = 0;

    return ret;
}

void qemu_aio_wait(void)
{
    int ret;

    if (qemu_bh_poll())
        return;

    /*
     * If there are callbacks left that have been queued, we need to call then.
     * Return afterwards to avoid waiting needlessly in select().
     */
    if (qemu_aio_process_queue())
        return;

    do {
        AioHandler *node;
        fd_set rdfds, wrfds;
        int max_fd = -1;

        walking_handlers = 1;

        FD_ZERO(&rdfds);
        FD_ZERO(&wrfds);

        /* fill fd sets */
        QLIST_FOREACH(node, &aio_handlers, node) {
            /* If there aren't pending AIO operations, don't invoke callbacks.
             * Otherwise, if there are no AIO requests, qemu_aio_wait() would
             * wait indefinitely.
             */
            if (node->io_flush && node->io_flush(node->opaque) == 0)
                continue;

            if (!node->deleted && node->io_read) {
                FD_SET(node->fd, &rdfds);
                max_fd = MAX(max_fd, node->fd + 1);
            }
            if (!node->deleted && node->io_write) {
                FD_SET(node->fd, &wrfds);
                max_fd = MAX(max_fd, node->fd + 1);
            }
        }

        walking_handlers = 0;

        /* No AIO operations?  Get us out of here */
        if (max_fd == -1)
            break;

        /* wait until next event */
        ret = select(max_fd, &rdfds, &wrfds, NULL, NULL);
        if (ret == -1 && errno == EINTR)
            continue;

        /* if we have any readable fds, dispatch event */
        if (ret > 0) {
            walking_handlers = 1;

            /* we have to walk very carefully in case
             * qemu_aio_set_fd_handler is called while we're walking */
            node = QLIST_FIRST(&aio_handlers);
            while (node) {
                AioHandler *tmp;

                if (!node->deleted &&
                    FD_ISSET(node->fd, &rdfds) &&
                    node->io_read) {
                    node->io_read(node->opaque);
                }
                if (!node->deleted &&
                    FD_ISSET(node->fd, &wrfds) &&
                    node->io_write) {
                    node->io_write(node->opaque);
                }

                tmp = node;
                node = QLIST_NEXT(node, node);

                if (tmp->deleted) {
                    QLIST_REMOVE(tmp, node);
                    g_free(tmp);
                }
            }

            walking_handlers = 0;
        }
    } while (ret == 0);
}