aboutsummaryrefslogtreecommitdiff
path: root/block/stream.c
blob: e14579ff8091cf6e10701d459d39efd3807b3e2a (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
/*
 * Image streaming
 *
 * Copyright IBM, Corp. 2011
 *
 * Authors:
 *  Stefan Hajnoczi   <stefanha@linux.vnet.ibm.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 "qemu/osdep.h"
#include "trace.h"
#include "block/block_int.h"
#include "block/blockjob_int.h"
#include "qapi/error.h"
#include "qapi/qmp/qerror.h"
#include "qemu/ratelimit.h"
#include "sysemu/block-backend.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.
     */
    STREAM_BUFFER_SIZE = 512 * 1024, /* in bytes */
};

typedef struct StreamBlockJob {
    BlockJob common;
    BlockDriverState *base;
    BlockdevOnError on_error;
    char *backing_file_str;
    bool bs_read_only;
} StreamBlockJob;

static int coroutine_fn stream_populate(BlockBackend *blk,
                                        int64_t offset, uint64_t bytes,
                                        void *buf)
{
    QEMUIOVector qiov = QEMU_IOVEC_INIT_BUF(qiov, buf, bytes);

    assert(bytes < SIZE_MAX);

    /* Copy-on-read the unallocated clusters */
    return blk_co_preadv(blk, offset, qiov.size, &qiov, BDRV_REQ_COPY_ON_READ);
}

static int stream_prepare(Job *job)
{
    StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
    BlockJob *bjob = &s->common;
    BlockDriverState *bs = blk_bs(bjob->blk);
    BlockDriverState *base = s->base;
    Error *local_err = NULL;
    int ret = 0;

    if (bs->backing) {
        const char *base_id = NULL, *base_fmt = NULL;
        if (base) {
            base_id = s->backing_file_str;
            if (base->drv) {
                base_fmt = base->drv->format_name;
            }
        }
        ret = bdrv_change_backing_file(bs, base_id, base_fmt);
        bdrv_set_backing_hd(bs, base, &local_err);
        if (local_err) {
            error_report_err(local_err);
            return -EPERM;
        }
    }

    return ret;
}

static void stream_clean(Job *job)
{
    StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
    BlockJob *bjob = &s->common;
    BlockDriverState *bs = blk_bs(bjob->blk);

    /* Reopen the image back in read-only mode if necessary */
    if (s->bs_read_only) {
        /* Give up write permissions before making it read-only */
        blk_set_perm(bjob->blk, 0, BLK_PERM_ALL, &error_abort);
        bdrv_reopen_set_read_only(bs, true, NULL);
    }

    g_free(s->backing_file_str);
}

static int coroutine_fn stream_run(Job *job, Error **errp)
{
    StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
    BlockBackend *blk = s->common.blk;
    BlockDriverState *bs = blk_bs(blk);
    BlockDriverState *base = s->base;
    int64_t len;
    int64_t offset = 0;
    uint64_t delay_ns = 0;
    int error = 0;
    int ret = 0;
    int64_t n = 0; /* bytes */
    void *buf;

    if (!bs->backing) {
        goto out;
    }

    len = bdrv_getlength(bs);
    if (len < 0) {
        ret = len;
        goto out;
    }
    job_progress_set_remaining(&s->common.job, len);

    buf = qemu_blockalign(bs, STREAM_BUFFER_SIZE);

    /* Turn on copy-on-read for the whole block device so that guest read
     * requests help us make progress.  Only do this when copying the entire
     * backing chain since the copy-on-read operation does not take base into
     * account.
     */
    if (!base) {
        bdrv_enable_copy_on_read(bs);
    }

    for ( ; offset < len; offset += n) {
        bool copy;

        /* 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.
         */
        job_sleep_ns(&s->common.job, delay_ns);
        if (job_is_cancelled(&s->common.job)) {
            break;
        }

        copy = false;

        ret = bdrv_is_allocated(bs, offset, STREAM_BUFFER_SIZE, &n);
        if (ret == 1) {
            /* Allocated in the top, no need to copy.  */
        } else if (ret >= 0) {
            /* Copy if allocated in the intermediate images.  Limit to the
             * known-unallocated area [offset, offset+n*BDRV_SECTOR_SIZE).  */
            ret = bdrv_is_allocated_above(backing_bs(bs), base,
                                          offset, n, &n);

            /* Finish early if end of backing file has been reached */
            if (ret == 0 && n == 0) {
                n = len - offset;
            }

            copy = (ret == 1);
        }
        trace_stream_one_iteration(s, offset, n, ret);
        if (copy) {
            ret = stream_populate(blk, offset, n, buf);
        }
        if (ret < 0) {
            BlockErrorAction action =
                block_job_error_action(&s->common, s->on_error, true, -ret);
            if (action == BLOCK_ERROR_ACTION_STOP) {
                n = 0;
                continue;
            }
            if (error == 0) {
                error = ret;
            }
            if (action == BLOCK_ERROR_ACTION_REPORT) {
                break;
            }
        }
        ret = 0;

        /* Publish progress */
        job_progress_update(&s->common.job, n);
        if (copy) {
            delay_ns = block_job_ratelimit_get_delay(&s->common, n);
        } else {
            delay_ns = 0;
        }
    }

    if (!base) {
        bdrv_disable_copy_on_read(bs);
    }

    /* Do not remove the backing file if an error was there but ignored.  */
    ret = error;

    qemu_vfree(buf);

out:
    /* Modify backing chain and close BDSes in main loop */
    return ret;
}

static const BlockJobDriver stream_job_driver = {
    .job_driver = {
        .instance_size = sizeof(StreamBlockJob),
        .job_type      = JOB_TYPE_STREAM,
        .free          = block_job_free,
        .run           = stream_run,
        .prepare       = stream_prepare,
        .clean         = stream_clean,
        .user_resume   = block_job_user_resume,
        .drain         = block_job_drain,
    },
};

void stream_start(const char *job_id, BlockDriverState *bs,
                  BlockDriverState *base, const char *backing_file_str,
                  int creation_flags, int64_t speed,
                  BlockdevOnError on_error, Error **errp)
{
    StreamBlockJob *s;
    BlockDriverState *iter;
    bool bs_read_only;

    /* Make sure that the image is opened in read-write mode */
    bs_read_only = bdrv_is_read_only(bs);
    if (bs_read_only) {
        if (bdrv_reopen_set_read_only(bs, false, errp) != 0) {
            return;
        }
    }

    /* Prevent concurrent jobs trying to modify the graph structure here, we
     * already have our own plans. Also don't allow resize as the image size is
     * queried only at the job start and then cached. */
    s = block_job_create(job_id, &stream_job_driver, NULL, bs,
                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
                         BLK_PERM_GRAPH_MOD,
                         BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
                         BLK_PERM_WRITE,
                         speed, creation_flags, NULL, NULL, errp);
    if (!s) {
        goto fail;
    }

    /* Block all intermediate nodes between bs and base, because they will
     * disappear from the chain after this operation. The streaming job reads
     * every block only once, assuming that it doesn't change, so block writes
     * and resizes. */
    for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
        block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
                           BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
                           &error_abort);
    }

    s->base = base;
    s->backing_file_str = g_strdup(backing_file_str);
    s->bs_read_only = bs_read_only;

    s->on_error = on_error;
    trace_stream_start(bs, base, s);
    job_start(&s->common.job);
    return;

fail:
    if (bs_read_only) {
        bdrv_reopen_set_read_only(bs, true, NULL);
    }
}