summaryrefslogtreecommitdiff
path: root/block/mirror.c
blob: 8aeacbf12c768e1654ad512a2e2c1be4d81bd588 (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
/*
 * Image mirroring
 *
 * Copyright Red Hat, Inc. 2012
 *
 * Authors:
 *  Paolo Bonzini  <pbonzini@redhat.com>
 *
 * This work is licensed under the terms of the GNU LGPL, version 2 or later.
 * See the COPYING.LIB file in the top-level directory.
 *
 */

#include "trace.h"
#include "block/blockjob.h"
#include "block/block_int.h"
#include "qemu/ratelimit.h"

enum {
    /*
     * Size of data buffer for populating the image file.  This should be large
     * enough to process multiple clusters in a single call, so that populating
     * contiguous regions of the image is efficient.
     */
    BLOCK_SIZE = 512 * BDRV_SECTORS_PER_DIRTY_CHUNK, /* in bytes */
};

#define SLICE_TIME 100000000ULL /* ns */

typedef struct MirrorBlockJob {
    BlockJob common;
    RateLimit limit;
    BlockDriverState *target;
    MirrorSyncMode mode;
    BlockdevOnError on_source_error, on_target_error;
    bool synced;
    bool should_complete;
    int64_t sector_num;
    uint8_t *buf;
} MirrorBlockJob;

static BlockErrorAction mirror_error_action(MirrorBlockJob *s, bool read,
                                            int error)
{
    s->synced = false;
    if (read) {
        return block_job_error_action(&s->common, s->common.bs,
                                      s->on_source_error, true, error);
    } else {
        return block_job_error_action(&s->common, s->target,
                                      s->on_target_error, false, error);
    }
}

static int coroutine_fn mirror_iteration(MirrorBlockJob *s,
                                         BlockErrorAction *p_action)
{
    BlockDriverState *source = s->common.bs;
    BlockDriverState *target = s->target;
    QEMUIOVector qiov;
    int ret, nb_sectors;
    int64_t end;
    struct iovec iov;

    end = s->common.len >> BDRV_SECTOR_BITS;
    s->sector_num = bdrv_get_next_dirty(source, s->sector_num);
    nb_sectors = MIN(BDRV_SECTORS_PER_DIRTY_CHUNK, end - s->sector_num);
    bdrv_reset_dirty(source, s->sector_num, nb_sectors);

    /* Copy the dirty cluster.  */
    iov.iov_base = s->buf;
    iov.iov_len  = nb_sectors * 512;
    qemu_iovec_init_external(&qiov, &iov, 1);

    trace_mirror_one_iteration(s, s->sector_num, nb_sectors);
    ret = bdrv_co_readv(source, s->sector_num, nb_sectors, &qiov);
    if (ret < 0) {
        *p_action = mirror_error_action(s, true, -ret);
        goto fail;
    }
    ret = bdrv_co_writev(target, s->sector_num, nb_sectors, &qiov);
    if (ret < 0) {
        *p_action = mirror_error_action(s, false, -ret);
        s->synced = false;
        goto fail;
    }
    return 0;

fail:
    /* Try again later.  */
    bdrv_set_dirty(source, s->sector_num, nb_sectors);
    return ret;
}

static void coroutine_fn mirror_run(void *opaque)
{
    MirrorBlockJob *s = opaque;
    BlockDriverState *bs = s->common.bs;
    int64_t sector_num, end;
    int ret = 0;
    int n;

    if (block_job_is_cancelled(&s->common)) {
        goto immediate_exit;
    }

    s->common.len = bdrv_getlength(bs);
    if (s->common.len < 0) {
        block_job_completed(&s->common, s->common.len);
        return;
    }

    end = s->common.len >> BDRV_SECTOR_BITS;
    s->buf = qemu_blockalign(bs, BLOCK_SIZE);

    if (s->mode != MIRROR_SYNC_MODE_NONE) {
        /* First part, loop on the sectors and initialize the dirty bitmap.  */
        BlockDriverState *base;
        base = s->mode == MIRROR_SYNC_MODE_FULL ? NULL : bs->backing_hd;
        for (sector_num = 0; sector_num < end; ) {
            int64_t next = (sector_num | (BDRV_SECTORS_PER_DIRTY_CHUNK - 1)) + 1;
            ret = bdrv_co_is_allocated_above(bs, base,
                                             sector_num, next - sector_num, &n);

            if (ret < 0) {
                goto immediate_exit;
            }

            assert(n > 0);
            if (ret == 1) {
                bdrv_set_dirty(bs, sector_num, n);
                sector_num = next;
            } else {
                sector_num += n;
            }
        }
    }

    s->sector_num = -1;
    for (;;) {
        uint64_t delay_ns;
        int64_t cnt;
        bool should_complete;

        cnt = bdrv_get_dirty_count(bs);
        if (cnt != 0) {
            BlockErrorAction action = BDRV_ACTION_REPORT;
            ret = mirror_iteration(s, &action);
            if (ret < 0 && action == BDRV_ACTION_REPORT) {
                goto immediate_exit;
            }
            cnt = bdrv_get_dirty_count(bs);
        }

        should_complete = false;
        if (cnt == 0) {
            trace_mirror_before_flush(s);
            ret = bdrv_flush(s->target);
            if (ret < 0) {
                if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
                    goto immediate_exit;
                }
            } else {
                /* We're out of the streaming phase.  From now on, if the job
                 * is cancelled we will actually complete all pending I/O and
                 * report completion.  This way, block-job-cancel will leave
                 * the target in a consistent state.
                 */
                s->common.offset = end * BDRV_SECTOR_SIZE;
                if (!s->synced) {
                    block_job_ready(&s->common);
                    s->synced = true;
                }

                should_complete = s->should_complete ||
                    block_job_is_cancelled(&s->common);
                cnt = bdrv_get_dirty_count(bs);
            }
        }

        if (cnt == 0 && should_complete) {
            /* The dirty bitmap is not updated while operations are pending.
             * If we're about to exit, wait for pending operations before
             * calling bdrv_get_dirty_count(bs), or we may exit while the
             * source has dirty data to copy!
             *
             * Note that I/O can be submitted by the guest while
             * mirror_populate runs.
             */
            trace_mirror_before_drain(s, cnt);
            bdrv_drain_all();
            cnt = bdrv_get_dirty_count(bs);
        }

        ret = 0;
        trace_mirror_before_sleep(s, cnt, s->synced);
        if (!s->synced) {
            /* Publish progress */
            s->common.offset = end * BDRV_SECTOR_SIZE - cnt * BLOCK_SIZE;

            if (s->common.speed) {
                delay_ns = ratelimit_calculate_delay(&s->limit, BDRV_SECTORS_PER_DIRTY_CHUNK);
            } else {
                delay_ns = 0;
            }

            /* Note that even when no rate limit is applied we need to yield
             * with no pending I/O here so that bdrv_drain_all() returns.
             */
            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
            if (block_job_is_cancelled(&s->common)) {
                break;
            }
        } else if (!should_complete) {
            delay_ns = (cnt == 0 ? SLICE_TIME : 0);
            block_job_sleep_ns(&s->common, rt_clock, delay_ns);
        } else if (cnt == 0) {
            /* The two disks are in sync.  Exit and report successful
             * completion.
             */
            assert(QLIST_EMPTY(&bs->tracked_requests));
            s->common.cancelled = false;
            break;
        }
    }

immediate_exit:
    g_free(s->buf);
    bdrv_set_dirty_tracking(bs, false);
    bdrv_iostatus_disable(s->target);
    if (s->should_complete && ret == 0) {
        if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
            bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
        }
        bdrv_swap(s->target, s->common.bs);
    }
    bdrv_close(s->target);
    bdrv_delete(s->target);
    block_job_completed(&s->common, ret);
}

static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
{
    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);

    if (speed < 0) {
        error_set(errp, QERR_INVALID_PARAMETER, "speed");
        return;
    }
    ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
}

static void mirror_iostatus_reset(BlockJob *job)
{
    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);

    bdrv_iostatus_reset(s->target);
}

static void mirror_complete(BlockJob *job, Error **errp)
{
    MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
    int ret;

    ret = bdrv_open_backing_file(s->target);
    if (ret < 0) {
        char backing_filename[PATH_MAX];
        bdrv_get_full_backing_filename(s->target, backing_filename,
                                       sizeof(backing_filename));
        error_set(errp, QERR_OPEN_FILE_FAILED, backing_filename);
        return;
    }
    if (!s->synced) {
        error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
        return;
    }

    s->should_complete = true;
    block_job_resume(job);
}

static BlockJobType mirror_job_type = {
    .instance_size = sizeof(MirrorBlockJob),
    .job_type      = "mirror",
    .set_speed     = mirror_set_speed,
    .iostatus_reset= mirror_iostatus_reset,
    .complete      = mirror_complete,
};

void mirror_start(BlockDriverState *bs, BlockDriverState *target,
                  int64_t speed, MirrorSyncMode mode,
                  BlockdevOnError on_source_error,
                  BlockdevOnError on_target_error,
                  BlockDriverCompletionFunc *cb,
                  void *opaque, Error **errp)
{
    MirrorBlockJob *s;

    if ((on_source_error == BLOCKDEV_ON_ERROR_STOP ||
         on_source_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
        !bdrv_iostatus_is_enabled(bs)) {
        error_set(errp, QERR_INVALID_PARAMETER, "on-source-error");
        return;
    }

    s = block_job_create(&mirror_job_type, bs, speed, cb, opaque, errp);
    if (!s) {
        return;
    }

    s->on_source_error = on_source_error;
    s->on_target_error = on_target_error;
    s->target = target;
    s->mode = mode;
    bdrv_set_dirty_tracking(bs, true);
    bdrv_set_enable_write_cache(s->target, true);
    bdrv_set_on_error(s->target, on_target_error, on_target_error);
    bdrv_iostatus_enable(s->target);
    s->common.co = qemu_coroutine_create(mirror_run);
    trace_mirror_start(bs, s, s->common.co, opaque);
    qemu_coroutine_enter(s->common.co, s);
}