aboutsummaryrefslogtreecommitdiff
path: root/block/linux-aio.c
blob: f4baba2be0bcff9325fe732f3499c4a6717574d0 (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
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
/*
 * 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 "block/aio.h"
#include "qemu/queue.h"
#include "block/raw-aio.h"
#include "qemu/event_notifier.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

#define MAX_QUEUED_IO  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;
};

typedef struct {
    struct iocb *iocbs[MAX_QUEUED_IO];
    int plugged;
    unsigned int size;
    unsigned int idx;
} LaioQueue;

struct qemu_laio_state {
    io_context_t ctx;
    EventNotifier e;

    /* io queue for submit at batch */
    LaioQueue io_q;

    /* I/O completion processing */
    QEMUBH *completion_bh;
    struct io_event events[MAX_EVENTS];
    int event_idx;
    int event_max;
};

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;

    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(laiocb->qiov, ret, 0,
                    laiocb->qiov->size - ret);
            } else {
                ret = -EINVAL;
            }
        }
    }
    laiocb->common.cb(laiocb->common.opaque, ret);

    qemu_aio_unref(laiocb);
}

/* The completion BH fetches completed I/O requests and invokes their
 * callbacks.
 *
 * The function is somewhat tricky because it supports nested event loops, for
 * example when a request callback invokes aio_poll().  In order to do this,
 * the completion events array and index are kept in qemu_laio_state.  The BH
 * reschedules itself as long as there are completions pending so it will
 * either be called again in a nested event loop or will be called after all
 * events have been completed.  When there are no events left to complete, the
 * BH returns without rescheduling.
 */
static void qemu_laio_completion_bh(void *opaque)
{
    struct qemu_laio_state *s = opaque;

    /* Fetch more completion events when empty */
    if (s->event_idx == s->event_max) {
        do {
            struct timespec ts = { 0 };
            s->event_max = io_getevents(s->ctx, MAX_EVENTS, MAX_EVENTS,
                                        s->events, &ts);
        } while (s->event_max == -EINTR);

        s->event_idx = 0;
        if (s->event_max <= 0) {
            s->event_max = 0;
            return; /* no more events */
        }
    }

    /* Reschedule so nested event loops see currently pending completions */
    qemu_bh_schedule(s->completion_bh);

    /* Process completion events */
    while (s->event_idx < s->event_max) {
        struct iocb *iocb = s->events[s->event_idx].obj;
        struct qemu_laiocb *laiocb =
                container_of(iocb, struct qemu_laiocb, iocb);

        laiocb->ret = io_event_ret(&s->events[s->event_idx]);
        s->event_idx++;

        qemu_laio_process_completion(s, laiocb);
    }
}

static void qemu_laio_completion_cb(EventNotifier *e)
{
    struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);

    if (event_notifier_test_and_clear(&s->e)) {
        qemu_bh_schedule(s->completion_bh);
    }
}

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;
    }
    ret = io_cancel(laiocb->ctx->ctx, &laiocb->iocb, &event);
    laiocb->ret = -ECANCELED;
    if (ret != 0) {
        /* iocb is not cancelled, cb will be called by the event loop later */
        return;
    }

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

static const AIOCBInfo laio_aiocb_info = {
    .aiocb_size         = sizeof(struct qemu_laiocb),
    .cancel_async       = laio_cancel,
};

static void ioq_init(LaioQueue *io_q)
{
    io_q->size = MAX_QUEUED_IO;
    io_q->idx = 0;
    io_q->plugged = 0;
}

static int ioq_submit(struct qemu_laio_state *s)
{
    int ret, i = 0;
    int len = s->io_q.idx;

    do {
        ret = io_submit(s->ctx, len, s->io_q.iocbs);
    } while (i++ < 3 && ret == -EAGAIN);

    /* empty io queue */
    s->io_q.idx = 0;

    if (ret < 0) {
        i = 0;
    } else {
        i = ret;
    }

    for (; i < len; i++) {
        struct qemu_laiocb *laiocb =
            container_of(s->io_q.iocbs[i], struct qemu_laiocb, iocb);

        laiocb->ret = (ret < 0) ? ret : -EIO;
        qemu_laio_process_completion(s, laiocb);
    }
    return ret;
}

static void ioq_enqueue(struct qemu_laio_state *s, struct iocb *iocb)
{
    unsigned int idx = s->io_q.idx;

    s->io_q.iocbs[idx++] = iocb;
    s->io_q.idx = idx;

    /* submit immediately if queue is full */
    if (idx == s->io_q.size) {
        ioq_submit(s);
    }
}

void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
{
    struct qemu_laio_state *s = aio_ctx;

    s->io_q.plugged++;
}

int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
{
    struct qemu_laio_state *s = aio_ctx;
    int ret = 0;

    assert(s->io_q.plugged > 0 || !unplug);

    if (unplug && --s->io_q.plugged > 0) {
        return 0;
    }

    if (s->io_q.idx > 0) {
        ret = ioq_submit(s);
    }

    return ret;
}

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_aiocb_info, 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, event_notifier_get_fd(&s->e));

    if (!s->io_q.plugged) {
        if (io_submit(s->ctx, 1, &iocbs) < 0) {
            goto out_free_aiocb;
        }
    } else {
        ioq_enqueue(s, iocbs);
    }
    return &laiocb->common;

out_free_aiocb:
    qemu_aio_unref(laiocb);
    return NULL;
}

void laio_detach_aio_context(void *s_, AioContext *old_context)
{
    struct qemu_laio_state *s = s_;

    aio_set_event_notifier(old_context, &s->e, NULL);
    qemu_bh_delete(s->completion_bh);
}

void laio_attach_aio_context(void *s_, AioContext *new_context)
{
    struct qemu_laio_state *s = s_;

    s->completion_bh = aio_bh_new(new_context, qemu_laio_completion_bh, s);
    aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
}

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

    s = g_malloc0(sizeof(*s));
    if (event_notifier_init(&s->e, false) < 0) {
        goto out_free_state;
    }

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

    ioq_init(&s->io_q);

    return s;

out_close_efd:
    event_notifier_cleanup(&s->e);
out_free_state:
    g_free(s);
    return NULL;
}

void laio_cleanup(void *s_)
{
    struct qemu_laio_state *s = s_;

    event_notifier_cleanup(&s->e);

    if (io_destroy(s->ctx) != 0) {
        fprintf(stderr, "%s: destroy AIO context %p failed\n",
                        __func__, &s->ctx);
    }
    g_free(s);
}