aboutsummaryrefslogtreecommitdiff
path: root/linux-aio.c
blob: fa0fbf34aaaddd57eba83b3d3a56436552175e3b (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
/*
 * Linux native AIO support.
 *
 * Copyright (C) 2009 IBM, Corp.
 * Copyright (C) 2009 Red Hat, Inc.
 *
 * This work is licensed under the terms of the GNU GPL, version 2 or later.
 * See the COPYING file in the top-level directory.
 */
#include "qemu-common.h"
#include "qemu-aio.h"
#include "block/raw-posix-aio.h"

#include <sys/eventfd.h>
#include <libaio.h>

/*
 * Queue size (per-device).
 *
 * XXX: eventually we need to communicate this to the guest and/or make it
 *      tunable by the guest.  If we get more outstanding requests at a time
 *      than this we will get EAGAIN from io_submit which is communicated to
 *      the guest as an I/O error.
 */
#define MAX_EVENTS 128

struct qemu_laiocb {
    BlockDriverAIOCB common;
    struct qemu_laio_state *ctx;
    struct iocb iocb;
    ssize_t ret;
    size_t nbytes;
    QEMUIOVector *qiov;
    bool is_read;
    QLIST_ENTRY(qemu_laiocb) node;
};

struct qemu_laio_state {
    io_context_t ctx;
    int efd;
    int count;
};

static inline ssize_t io_event_ret(struct io_event *ev)
{
    return (ssize_t)(((uint64_t)ev->res2 << 32) | ev->res);
}

/*
 * Completes an AIO request (calls the callback and frees the ACB).
 */
static void qemu_laio_process_completion(struct qemu_laio_state *s,
    struct qemu_laiocb *laiocb)
{
    int ret;

    s->count--;

    ret = laiocb->ret;
    if (ret != -ECANCELED) {
        if (ret == laiocb->nbytes) {
            ret = 0;
        } else if (ret >= 0) {
            /* Short reads mean EOF, pad with zeros. */
            if (laiocb->is_read) {
                qemu_iovec_memset_skip(laiocb->qiov, 0,
                    laiocb->qiov->size - ret, ret);
            } else {
                ret = -EINVAL;
            }
        }

        laiocb->common.cb(laiocb->common.opaque, ret);
    }

    qemu_aio_release(laiocb);
}

static void qemu_laio_completion_cb(void *opaque)
{
    struct qemu_laio_state *s = opaque;

    while (1) {
        struct io_event events[MAX_EVENTS];
        uint64_t val;
        ssize_t ret;
        struct timespec ts = { 0 };
        int nevents, i;

        do {
            ret = read(s->efd, &val, sizeof(val));
        } while (ret == -1 && errno == EINTR);

        if (ret == -1 && errno == EAGAIN)
            break;

        if (ret != 8)
            break;

        do {
            nevents = io_getevents(s->ctx, val, MAX_EVENTS, events, &ts);
        } while (nevents == -EINTR);

        for (i = 0; i < nevents; i++) {
            struct iocb *iocb = events[i].obj;
            struct qemu_laiocb *laiocb =
                    container_of(iocb, struct qemu_laiocb, iocb);

            laiocb->ret = io_event_ret(&events[i]);
            qemu_laio_process_completion(s, laiocb);
        }
    }
}

static int qemu_laio_flush_cb(void *opaque)
{
    struct qemu_laio_state *s = opaque;

    return (s->count > 0) ? 1 : 0;
}

static void laio_cancel(BlockDriverAIOCB *blockacb)
{
    struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
    struct io_event event;
    int ret;

    if (laiocb->ret != -EINPROGRESS)
        return;

    /*
     * Note that as of Linux 2.6.31 neither the block device code nor any
     * filesystem implements cancellation of AIO request.
     * Thus the polling loop below is the normal code path.
     */
    ret = io_cancel(laiocb->ctx->ctx, &laiocb->iocb, &event);
    if (ret == 0) {
        laiocb->ret = -ECANCELED;
        return;
    }

    /*
     * We have to wait for the iocb to finish.
     *
     * The only way to get the iocb status update is by polling the io context.
     * We might be able to do this slightly more optimal by removing the
     * O_NONBLOCK flag.
     */
    while (laiocb->ret == -EINPROGRESS)
        qemu_laio_completion_cb(laiocb->ctx);
}

static AIOPool laio_pool = {
    .aiocb_size         = sizeof(struct qemu_laiocb),
    .cancel             = laio_cancel,
};

BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type)
{
    struct qemu_laio_state *s = aio_ctx;
    struct qemu_laiocb *laiocb;
    struct iocb *iocbs;
    off_t offset = sector_num * 512;

    laiocb = qemu_aio_get(&laio_pool, bs, cb, opaque);
    laiocb->nbytes = nb_sectors * 512;
    laiocb->ctx = s;
    laiocb->ret = -EINPROGRESS;
    laiocb->is_read = (type == QEMU_AIO_READ);
    laiocb->qiov = qiov;

    iocbs = &laiocb->iocb;

    switch (type) {
    case QEMU_AIO_WRITE:
        io_prep_pwritev(iocbs, fd, qiov->iov, qiov->niov, offset);
	break;
    case QEMU_AIO_READ:
        io_prep_preadv(iocbs, fd, qiov->iov, qiov->niov, offset);
	break;
    /* Currently Linux kernel does not support other operations */
    default:
        fprintf(stderr, "%s: invalid AIO request type 0x%x.\n",
                        __func__, type);
        goto out_free_aiocb;
    }
    io_set_eventfd(&laiocb->iocb, s->efd);
    s->count++;

    if (io_submit(s->ctx, 1, &iocbs) < 0)
        goto out_dec_count;
    return &laiocb->common;

out_dec_count:
    s->count--;
out_free_aiocb:
    qemu_aio_release(laiocb);
    return NULL;
}

void *laio_init(void)
{
    struct qemu_laio_state *s;

    s = g_malloc0(sizeof(*s));
    s->efd = eventfd(0, 0);
    if (s->efd == -1)
        goto out_free_state;
    fcntl(s->efd, F_SETFL, O_NONBLOCK);

    if (io_setup(MAX_EVENTS, &s->ctx) != 0)
        goto out_close_efd;

    qemu_aio_set_fd_handler(s->efd, qemu_laio_completion_cb, NULL,
        qemu_laio_flush_cb, s);

    return s;

out_close_efd:
    close(s->efd);
out_free_state:
    g_free(s);
    return NULL;
}