aboutsummaryrefslogtreecommitdiff
path: root/posix-aio-compat.c
blob: cccb673d2ef9a4e41dfb6f515e04e486f634b7e1 (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
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
/*
 * QEMU posix-aio emulation
 *
 * 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.
 *
 */

#include <sys/ioctl.h>
#include <sys/types.h>
#include <pthread.h>
#include <unistd.h>
#include <errno.h>
#include <time.h>
#include <string.h>
#include <stdlib.h>
#include <stdio.h>

#include "qemu-queue.h"
#include "osdep.h"
#include "sysemu.h"
#include "qemu-common.h"
#include "trace.h"
#include "block_int.h"

#include "block/raw-posix-aio.h"

static void do_spawn_thread(void);

struct qemu_paiocb {
    BlockDriverAIOCB common;
    int aio_fildes;
    union {
        struct iovec *aio_iov;
        void *aio_ioctl_buf;
    };
    int aio_niov;
    size_t aio_nbytes;
#define aio_ioctl_cmd   aio_nbytes /* for QEMU_AIO_IOCTL */
    off_t aio_offset;

    QTAILQ_ENTRY(qemu_paiocb) node;
    int aio_type;
    ssize_t ret;
    int active;
    struct qemu_paiocb *next;
};

typedef struct PosixAioState {
    int rfd, wfd;
    struct qemu_paiocb *first_aio;
} PosixAioState;


static pthread_mutex_t lock = PTHREAD_MUTEX_INITIALIZER;
static pthread_cond_t cond = PTHREAD_COND_INITIALIZER;
static pthread_t thread_id;
static pthread_attr_t attr;
static int max_threads = 64;
static int cur_threads = 0;
static int idle_threads = 0;
static int new_threads = 0;     /* backlog of threads we need to create */
static int pending_threads = 0; /* threads created but not running yet */
static QEMUBH *new_thread_bh;
static QTAILQ_HEAD(, qemu_paiocb) request_list;

#ifdef CONFIG_PREADV
static int preadv_present = 1;
#else
static int preadv_present = 0;
#endif

static void die2(int err, const char *what)
{
    fprintf(stderr, "%s failed: %s\n", what, strerror(err));
    abort();
}

static void die(const char *what)
{
    die2(errno, what);
}

static void mutex_lock(pthread_mutex_t *mutex)
{
    int ret = pthread_mutex_lock(mutex);
    if (ret) die2(ret, "pthread_mutex_lock");
}

static void mutex_unlock(pthread_mutex_t *mutex)
{
    int ret = pthread_mutex_unlock(mutex);
    if (ret) die2(ret, "pthread_mutex_unlock");
}

static int cond_timedwait(pthread_cond_t *cond, pthread_mutex_t *mutex,
                           struct timespec *ts)
{
    int ret = pthread_cond_timedwait(cond, mutex, ts);
    if (ret && ret != ETIMEDOUT) die2(ret, "pthread_cond_timedwait");
    return ret;
}

static void cond_signal(pthread_cond_t *cond)
{
    int ret = pthread_cond_signal(cond);
    if (ret) die2(ret, "pthread_cond_signal");
}

static void thread_create(pthread_t *thread, pthread_attr_t *attr,
                          void *(*start_routine)(void*), void *arg)
{
    int ret = pthread_create(thread, attr, start_routine, arg);
    if (ret) die2(ret, "pthread_create");
}

static ssize_t handle_aiocb_ioctl(struct qemu_paiocb *aiocb)
{
    int ret;

    ret = ioctl(aiocb->aio_fildes, aiocb->aio_ioctl_cmd, aiocb->aio_ioctl_buf);
    if (ret == -1)
        return -errno;

    /*
     * This looks weird, but the aio code only considers a request
     * successful if it has written the full number of bytes.
     *
     * Now we overload aio_nbytes as aio_ioctl_cmd for the ioctl command,
     * so in fact we return the ioctl command here to make posix_aio_read()
     * happy..
     */
    return aiocb->aio_nbytes;
}

static ssize_t handle_aiocb_flush(struct qemu_paiocb *aiocb)
{
    int ret;

    ret = qemu_fdatasync(aiocb->aio_fildes);
    if (ret == -1)
        return -errno;
    return 0;
}

#ifdef CONFIG_PREADV

static ssize_t
qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return preadv(fd, iov, nr_iov, offset);
}

static ssize_t
qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return pwritev(fd, iov, nr_iov, offset);
}

#else

static ssize_t
qemu_preadv(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return -ENOSYS;
}

static ssize_t
qemu_pwritev(int fd, const struct iovec *iov, int nr_iov, off_t offset)
{
    return -ENOSYS;
}

#endif

static ssize_t handle_aiocb_rw_vector(struct qemu_paiocb *aiocb)
{
    ssize_t len;

    do {
        if (aiocb->aio_type & QEMU_AIO_WRITE)
            len = qemu_pwritev(aiocb->aio_fildes,
                               aiocb->aio_iov,
                               aiocb->aio_niov,
                               aiocb->aio_offset);
         else
            len = qemu_preadv(aiocb->aio_fildes,
                              aiocb->aio_iov,
                              aiocb->aio_niov,
                              aiocb->aio_offset);
    } while (len == -1 && errno == EINTR);

    if (len == -1)
        return -errno;
    return len;
}

/*
 * Read/writes the data to/from a given linear buffer.
 *
 * Returns the number of bytes handles or -errno in case of an error. Short
 * reads are only returned if the end of the file is reached.
 */
static ssize_t handle_aiocb_rw_linear(struct qemu_paiocb *aiocb, char *buf)
{
    ssize_t offset = 0;
    ssize_t len;

    while (offset < aiocb->aio_nbytes) {
         if (aiocb->aio_type & QEMU_AIO_WRITE)
             len = pwrite(aiocb->aio_fildes,
                          (const char *)buf + offset,
                          aiocb->aio_nbytes - offset,
                          aiocb->aio_offset + offset);
         else
             len = pread(aiocb->aio_fildes,
                         buf + offset,
                         aiocb->aio_nbytes - offset,
                         aiocb->aio_offset + offset);

         if (len == -1 && errno == EINTR)
             continue;
         else if (len == -1) {
             offset = -errno;
             break;
         } else if (len == 0)
             break;

         offset += len;
    }

    return offset;
}

static ssize_t handle_aiocb_rw(struct qemu_paiocb *aiocb)
{
    ssize_t nbytes;
    char *buf;

    if (!(aiocb->aio_type & QEMU_AIO_MISALIGNED)) {
        /*
         * If there is just a single buffer, and it is properly aligned
         * we can just use plain pread/pwrite without any problems.
         */
        if (aiocb->aio_niov == 1)
             return handle_aiocb_rw_linear(aiocb, aiocb->aio_iov->iov_base);

        /*
         * We have more than one iovec, and all are properly aligned.
         *
         * Try preadv/pwritev first and fall back to linearizing the
         * buffer if it's not supported.
         */
        if (preadv_present) {
            nbytes = handle_aiocb_rw_vector(aiocb);
            if (nbytes == aiocb->aio_nbytes)
                return nbytes;
            if (nbytes < 0 && nbytes != -ENOSYS)
                return nbytes;
            preadv_present = 0;
        }

        /*
         * XXX(hch): short read/write.  no easy way to handle the reminder
         * using these interfaces.  For now retry using plain
         * pread/pwrite?
         */
    }

    /*
     * Ok, we have to do it the hard way, copy all segments into
     * a single aligned buffer.
     */
    buf = qemu_blockalign(aiocb->common.bs, aiocb->aio_nbytes);
    if (aiocb->aio_type & QEMU_AIO_WRITE) {
        char *p = buf;
        int i;

        for (i = 0; i < aiocb->aio_niov; ++i) {
            memcpy(p, aiocb->aio_iov[i].iov_base, aiocb->aio_iov[i].iov_len);
            p += aiocb->aio_iov[i].iov_len;
        }
    }

    nbytes = handle_aiocb_rw_linear(aiocb, buf);
    if (!(aiocb->aio_type & QEMU_AIO_WRITE)) {
        char *p = buf;
        size_t count = aiocb->aio_nbytes, copy;
        int i;

        for (i = 0; i < aiocb->aio_niov && count; ++i) {
            copy = count;
            if (copy > aiocb->aio_iov[i].iov_len)
                copy = aiocb->aio_iov[i].iov_len;
            memcpy(aiocb->aio_iov[i].iov_base, p, copy);
            p     += copy;
            count -= copy;
        }
    }
    qemu_vfree(buf);

    return nbytes;
}

static void posix_aio_notify_event(void);

static void *aio_thread(void *unused)
{
    mutex_lock(&lock);
    pending_threads--;
    mutex_unlock(&lock);
    do_spawn_thread();

    while (1) {
        struct qemu_paiocb *aiocb;
        ssize_t ret = 0;
        qemu_timeval tv;
        struct timespec ts;

        qemu_gettimeofday(&tv);
        ts.tv_sec = tv.tv_sec + 10;
        ts.tv_nsec = 0;

        mutex_lock(&lock);

        while (QTAILQ_EMPTY(&request_list) &&
               !(ret == ETIMEDOUT)) {
            idle_threads++;
            ret = cond_timedwait(&cond, &lock, &ts);
            idle_threads--;
        }

        if (QTAILQ_EMPTY(&request_list))
            break;

        aiocb = QTAILQ_FIRST(&request_list);
        QTAILQ_REMOVE(&request_list, aiocb, node);
        aiocb->active = 1;
        mutex_unlock(&lock);

        switch (aiocb->aio_type & QEMU_AIO_TYPE_MASK) {
        case QEMU_AIO_READ:
            ret = handle_aiocb_rw(aiocb);
            if (ret >= 0 && ret < aiocb->aio_nbytes && aiocb->common.bs->growable) {
                /* A short read means that we have reached EOF. Pad the buffer
                 * with zeros for bytes after EOF. */
                QEMUIOVector qiov;

                qemu_iovec_init_external(&qiov, aiocb->aio_iov,
                                         aiocb->aio_niov);
                qemu_iovec_memset_skip(&qiov, 0, aiocb->aio_nbytes - ret, ret);

                ret = aiocb->aio_nbytes;
            }
            break;
        case QEMU_AIO_WRITE:
            ret = handle_aiocb_rw(aiocb);
            break;
        case QEMU_AIO_FLUSH:
            ret = handle_aiocb_flush(aiocb);
            break;
        case QEMU_AIO_IOCTL:
            ret = handle_aiocb_ioctl(aiocb);
            break;
        default:
            fprintf(stderr, "invalid aio request (0x%x)\n", aiocb->aio_type);
            ret = -EINVAL;
            break;
        }

        mutex_lock(&lock);
        aiocb->ret = ret;
        mutex_unlock(&lock);

        posix_aio_notify_event();
    }

    cur_threads--;
    mutex_unlock(&lock);

    return NULL;
}

static void do_spawn_thread(void)
{
    sigset_t set, oldset;

    mutex_lock(&lock);
    if (!new_threads) {
        mutex_unlock(&lock);
        return;
    }

    new_threads--;
    pending_threads++;

    mutex_unlock(&lock);

    /* block all signals */
    if (sigfillset(&set)) die("sigfillset");
    if (sigprocmask(SIG_SETMASK, &set, &oldset)) die("sigprocmask");

    thread_create(&thread_id, &attr, aio_thread, NULL);

    if (sigprocmask(SIG_SETMASK, &oldset, NULL)) die("sigprocmask restore");
}

static void spawn_thread_bh_fn(void *opaque)
{
    do_spawn_thread();
}

static void spawn_thread(void)
{
    cur_threads++;
    new_threads++;
    /* If there are threads being created, they will spawn new workers, so
     * we don't spend time creating many threads in a loop holding a mutex or
     * starving the current vcpu.
     *
     * If there are no idle threads, ask the main thread to create one, so we
     * inherit the correct affinity instead of the vcpu affinity.
     */
    if (!pending_threads) {
        qemu_bh_schedule(new_thread_bh);
    }
}

static void qemu_paio_submit(struct qemu_paiocb *aiocb)
{
    aiocb->ret = -EINPROGRESS;
    aiocb->active = 0;
    mutex_lock(&lock);
    if (idle_threads == 0 && cur_threads < max_threads)
        spawn_thread();
    QTAILQ_INSERT_TAIL(&request_list, aiocb, node);
    mutex_unlock(&lock);
    cond_signal(&cond);
}

static ssize_t qemu_paio_return(struct qemu_paiocb *aiocb)
{
    ssize_t ret;

    mutex_lock(&lock);
    ret = aiocb->ret;
    mutex_unlock(&lock);

    return ret;
}

static int qemu_paio_error(struct qemu_paiocb *aiocb)
{
    ssize_t ret = qemu_paio_return(aiocb);

    if (ret < 0)
        ret = -ret;
    else
        ret = 0;

    return ret;
}

static int posix_aio_process_queue(void *opaque)
{
    PosixAioState *s = opaque;
    struct qemu_paiocb *acb, **pacb;
    int ret;
    int result = 0;

    for(;;) {
        pacb = &s->first_aio;
        for(;;) {
            acb = *pacb;
            if (!acb)
                return result;

            ret = qemu_paio_error(acb);
            if (ret == ECANCELED) {
                /* remove the request */
                *pacb = acb->next;
                qemu_aio_release(acb);
                result = 1;
            } else if (ret != EINPROGRESS) {
                /* end of aio */
                if (ret == 0) {
                    ret = qemu_paio_return(acb);
                    if (ret == acb->aio_nbytes)
                        ret = 0;
                    else
                        ret = -EINVAL;
                } else {
                    ret = -ret;
                }

                trace_paio_complete(acb, acb->common.opaque, ret);

                /* remove the request */
                *pacb = acb->next;
                /* call the callback */
                acb->common.cb(acb->common.opaque, ret);
                qemu_aio_release(acb);
                result = 1;
                break;
            } else {
                pacb = &acb->next;
            }
        }
    }

    return result;
}

static void posix_aio_read(void *opaque)
{
    PosixAioState *s = opaque;
    ssize_t len;

    /* read all bytes from signal pipe */
    for (;;) {
        char bytes[16];

        len = read(s->rfd, bytes, sizeof(bytes));
        if (len == -1 && errno == EINTR)
            continue; /* try again */
        if (len == sizeof(bytes))
            continue; /* more to read */
        break;
    }

    posix_aio_process_queue(s);
}

static int posix_aio_flush(void *opaque)
{
    PosixAioState *s = opaque;
    return !!s->first_aio;
}

static PosixAioState *posix_aio_state;

static void posix_aio_notify_event(void)
{
    char byte = 0;
    ssize_t ret;

    ret = write(posix_aio_state->wfd, &byte, sizeof(byte));
    if (ret < 0 && errno != EAGAIN)
        die("write()");
}

static void paio_remove(struct qemu_paiocb *acb)
{
    struct qemu_paiocb **pacb;

    /* remove the callback from the queue */
    pacb = &posix_aio_state->first_aio;
    for(;;) {
        if (*pacb == NULL) {
            fprintf(stderr, "paio_remove: aio request not found!\n");
            break;
        } else if (*pacb == acb) {
            *pacb = acb->next;
            qemu_aio_release(acb);
            break;
        }
        pacb = &(*pacb)->next;
    }
}

static void paio_cancel(BlockDriverAIOCB *blockacb)
{
    struct qemu_paiocb *acb = (struct qemu_paiocb *)blockacb;
    int active = 0;

    trace_paio_cancel(acb, acb->common.opaque);

    mutex_lock(&lock);
    if (!acb->active) {
        QTAILQ_REMOVE(&request_list, acb, node);
        acb->ret = -ECANCELED;
    } else if (acb->ret == -EINPROGRESS) {
        active = 1;
    }
    mutex_unlock(&lock);

    if (active) {
        /* fail safe: if the aio could not be canceled, we wait for
           it */
        while (qemu_paio_error(acb) == EINPROGRESS)
            ;
    }

    paio_remove(acb);
}

static AIOPool raw_aio_pool = {
    .aiocb_size         = sizeof(struct qemu_paiocb),
    .cancel             = paio_cancel,
};

BlockDriverAIOCB *paio_submit(BlockDriverState *bs, int fd,
        int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
        BlockDriverCompletionFunc *cb, void *opaque, int type)
{
    struct qemu_paiocb *acb;

    acb = qemu_aio_get(&raw_aio_pool, bs, cb, opaque);
    acb->aio_type = type;
    acb->aio_fildes = fd;

    if (qiov) {
        acb->aio_iov = qiov->iov;
        acb->aio_niov = qiov->niov;
    }
    acb->aio_nbytes = nb_sectors * 512;
    acb->aio_offset = sector_num * 512;

    acb->next = posix_aio_state->first_aio;
    posix_aio_state->first_aio = acb;

    trace_paio_submit(acb, opaque, sector_num, nb_sectors, type);
    qemu_paio_submit(acb);
    return &acb->common;
}

BlockDriverAIOCB *paio_ioctl(BlockDriverState *bs, int fd,
        unsigned long int req, void *buf,
        BlockDriverCompletionFunc *cb, void *opaque)
{
    struct qemu_paiocb *acb;

    acb = qemu_aio_get(&raw_aio_pool, bs, cb, opaque);
    acb->aio_type = QEMU_AIO_IOCTL;
    acb->aio_fildes = fd;
    acb->aio_offset = 0;
    acb->aio_ioctl_buf = buf;
    acb->aio_ioctl_cmd = req;

    acb->next = posix_aio_state->first_aio;
    posix_aio_state->first_aio = acb;

    qemu_paio_submit(acb);
    return &acb->common;
}

int paio_init(void)
{
    PosixAioState *s;
    int fds[2];
    int ret;

    if (posix_aio_state)
        return 0;

    s = g_malloc(sizeof(PosixAioState));

    s->first_aio = NULL;
    if (qemu_pipe(fds) == -1) {
        fprintf(stderr, "failed to create pipe\n");
        g_free(s);
        return -1;
    }

    s->rfd = fds[0];
    s->wfd = fds[1];

    fcntl(s->rfd, F_SETFL, O_NONBLOCK);
    fcntl(s->wfd, F_SETFL, O_NONBLOCK);

    qemu_aio_set_fd_handler(s->rfd, posix_aio_read, NULL, posix_aio_flush,
        posix_aio_process_queue, s);

    ret = pthread_attr_init(&attr);
    if (ret)
        die2(ret, "pthread_attr_init");

    ret = pthread_attr_setdetachstate(&attr, PTHREAD_CREATE_DETACHED);
    if (ret)
        die2(ret, "pthread_attr_setdetachstate");

    QTAILQ_INIT(&request_list);
    new_thread_bh = qemu_bh_new(spawn_thread_bh_fn, NULL);

    posix_aio_state = s;
    return 0;
}