summaryrefslogtreecommitdiffstats
path: root/aio-posix.c
blob: bd06f33c7824184d56ccd7e6149cc1fa1e56448d (plain) (blame)
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
/*
 * 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/block.h"
#include "qemu/queue.h"
#include "qemu/sockets.h"

struct AioHandler
{
    GPollFD pfd;
    IOHandler *io_read;
    IOHandler *io_write;
    int deleted;
    int pollfds_idx;
    void *opaque;
    QLIST_ENTRY(AioHandler) node;
};

static AioHandler *find_aio_handler(AioContext *ctx, int fd)
{
    AioHandler *node;

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

    return NULL;
}

void aio_set_fd_handler(AioContext *ctx,
                        int fd,
                        IOHandler *io_read,
                        IOHandler *io_write,
                        void *opaque)
{
    AioHandler *node;

    node = find_aio_handler(ctx, fd);

    /* Are we deleting the fd handler? */
    if (!io_read && !io_write) {
        if (node) {
            g_source_remove_poll(&ctx->source, &node->pfd);

            /* If the lock is held, just mark the node as deleted */
            if (ctx->walking_handlers) {
                node->deleted = 1;
                node->pfd.revents = 0;
            } 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->pfd.fd = fd;
            QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);

            g_source_add_poll(&ctx->source, &node->pfd);
        }
        /* Update handler with latest information */
        node->io_read = io_read;
        node->io_write = io_write;
        node->opaque = opaque;
        node->pollfds_idx = -1;

        node->pfd.events = (io_read ? G_IO_IN | G_IO_HUP | G_IO_ERR : 0);
        node->pfd.events |= (io_write ? G_IO_OUT | G_IO_ERR : 0);
    }

    aio_notify(ctx);
}

void aio_set_event_notifier(AioContext *ctx,
                            EventNotifier *notifier,
                            EventNotifierHandler *io_read)
{
    aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
                       (IOHandler *)io_read, NULL, notifier);
}

bool aio_pending(AioContext *ctx)
{
    AioHandler *node;

    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
        int revents;

        revents = node->pfd.revents & node->pfd.events;
        if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read) {
            return true;
        }
        if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write) {
            return true;
        }
    }

    return false;
}

static bool aio_dispatch(AioContext *ctx)
{
    AioHandler *node;
    bool progress = false;

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

        ctx->walking_handlers++;

        revents = node->pfd.revents & node->pfd.events;
        node->pfd.revents = 0;

        if (!node->deleted &&
            (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) &&
            node->io_read) {
            node->io_read(node->opaque);

            /* aio_notify() does not count as progress */
            if (node->opaque != &ctx->notifier) {
                progress = true;
            }
        }
        if (!node->deleted &&
            (revents & (G_IO_OUT | G_IO_ERR)) &&
            node->io_write) {
            node->io_write(node->opaque);
            progress = true;
        }

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

        ctx->walking_handlers--;

        if (!ctx->walking_handlers && tmp->deleted) {
            QLIST_REMOVE(tmp, node);
            g_free(tmp);
        }
    }

    /* Run our timers */
    progress |= timerlistgroup_run_timers(&ctx->tlg);

    return progress;
}

bool aio_poll(AioContext *ctx, bool blocking)
{
    AioHandler *node;
    int ret;
    bool progress;

    progress = false;

    /*
     * If there are callbacks left that have been queued, we need to call them.
     * Do not call select in this case, because it is possible that the caller
     * does not need a complete flush (as is the case for qemu_aio_wait loops).
     */
    if (aio_bh_poll(ctx)) {
        blocking = false;
        progress = true;
    }

    if (aio_dispatch(ctx)) {
        progress = true;
    }

    if (progress && !blocking) {
        return true;
    }

    ctx->walking_handlers++;

    g_array_set_size(ctx->pollfds, 0);

    /* fill pollfds */
    QLIST_FOREACH(node, &ctx->aio_handlers, node) {
        node->pollfds_idx = -1;
        if (!node->deleted && node->pfd.events) {
            GPollFD pfd = {
                .fd = node->pfd.fd,
                .events = node->pfd.events,
            };
            node->pollfds_idx = ctx->pollfds->len;
            g_array_append_val(ctx->pollfds, pfd);
        }
    }

    ctx->walking_handlers--;

    /* early return if we only have the aio_notify() fd */
    if (ctx->pollfds->len == 1) {
        return progress;
    }

    /* wait until next event */
    ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
                         ctx->pollfds->len,
                         blocking ? timerlistgroup_deadline_ns(&ctx->tlg) : 0);

    /* if we have any readable fds, dispatch event */
    if (ret > 0) {
        QLIST_FOREACH(node, &ctx->aio_handlers, node) {
            if (node->pollfds_idx != -1) {
                GPollFD *pfd = &g_array_index(ctx->pollfds, GPollFD,
                                              node->pollfds_idx);
                node->pfd.revents = pfd->revents;
            }
        }
    }

    /* Run dispatch even if there were no readable fds to run timers */
    if (aio_dispatch(ctx)) {
        progress = true;
    }

    return progress;
}