commit.c 7.5 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * Live block commit
 *
 * Copyright Red Hat, Inc. 2012
 *
 * Authors:
 *  Jeff Cody   <jcody@redhat.com>
 *  Based on stream.c by Stefan Hajnoczi
 *
 * 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_int.h"
17
#include "blockjob.h"
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
#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.
     */
    COMMIT_BUFFER_SIZE = 512 * 1024, /* in bytes */
};

#define SLICE_TIME 100000000ULL /* ns */

typedef struct CommitBlockJob {
    BlockJob common;
    RateLimit limit;
    BlockDriverState *active;
    BlockDriverState *top;
    BlockDriverState *base;
    BlockErrorAction on_error;
    int base_flags;
    int orig_overlay_flags;
} CommitBlockJob;

static int coroutine_fn commit_populate(BlockDriverState *bs,
                                        BlockDriverState *base,
                                        int64_t sector_num, int nb_sectors,
                                        void *buf)
{
    int ret = 0;

    ret = bdrv_read(bs, sector_num, buf, nb_sectors);
    if (ret) {
        return ret;
    }

    ret = bdrv_write(base, sector_num, buf, nb_sectors);
    if (ret) {
        return ret;
    }

    return 0;
}

static void coroutine_fn commit_run(void *opaque)
{
    CommitBlockJob *s = opaque;
    BlockDriverState *active = s->active;
    BlockDriverState *top = s->top;
    BlockDriverState *base = s->base;
    BlockDriverState *overlay_bs = NULL;
    int64_t sector_num, end;
    int ret = 0;
    int n = 0;
    void *buf;
    int bytes_written = 0;
    int64_t base_len;

    ret = s->common.len = bdrv_getlength(top);


    if (s->common.len < 0) {
        goto exit_restore_reopen;
    }

    ret = base_len = bdrv_getlength(base);
    if (base_len < 0) {
        goto exit_restore_reopen;
    }

    if (base_len < s->common.len) {
        ret = bdrv_truncate(base, s->common.len);
        if (ret) {
            goto exit_restore_reopen;
        }
    }

    overlay_bs = bdrv_find_overlay(active, top);

    end = s->common.len >> BDRV_SECTOR_BITS;
    buf = qemu_blockalign(top, COMMIT_BUFFER_SIZE);

    for (sector_num = 0; sector_num < end; sector_num += n) {
        uint64_t delay_ns = 0;
        bool copy;

wait:
        /* Note that even when no rate limit is applied we need to yield
         * with no pending I/O here so that qemu_aio_flush() returns.
         */
        block_job_sleep_ns(&s->common, rt_clock, delay_ns);
        if (block_job_is_cancelled(&s->common)) {
            break;
        }
        /* Copy if allocated above the base */
        ret = bdrv_co_is_allocated_above(top, base, sector_num,
                                         COMMIT_BUFFER_SIZE / BDRV_SECTOR_SIZE,
                                         &n);
        copy = (ret == 1);
        trace_commit_one_iteration(s, sector_num, n, ret);
        if (copy) {
            if (s->common.speed) {
                delay_ns = ratelimit_calculate_delay(&s->limit, n);
                if (delay_ns > 0) {
                    goto wait;
                }
            }
            ret = commit_populate(top, base, sector_num, n, buf);
            bytes_written += n * BDRV_SECTOR_SIZE;
        }
        if (ret < 0) {
            if (s->on_error == BLOCK_ERR_STOP_ANY    ||
                s->on_error == BLOCK_ERR_REPORT      ||
                (s->on_error == BLOCK_ERR_STOP_ENOSPC && ret == -ENOSPC)) {
                goto exit_free_buf;
            } else {
                n = 0;
                continue;
            }
        }
        /* Publish progress */
        s->common.offset += n * BDRV_SECTOR_SIZE;
    }

    ret = 0;

    if (!block_job_is_cancelled(&s->common) && sector_num == end) {
        /* success */
        ret = bdrv_drop_intermediate(active, top, base);
    }

exit_free_buf:
    qemu_vfree(buf);

exit_restore_reopen:
    /* restore base open flags here if appropriate (e.g., change the base back
     * to r/o). These reopens do not need to be atomic, since we won't abort
     * even on failure here */
    if (s->base_flags != bdrv_get_flags(base)) {
        bdrv_reopen(base, s->base_flags, NULL);
    }
    if (s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
        bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
    }

    block_job_complete(&s->common, ret);
}

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

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

static BlockJobType commit_job_type = {
    .instance_size = sizeof(CommitBlockJob),
    .job_type      = "commit",
    .set_speed     = commit_set_speed,
};

void commit_start(BlockDriverState *bs, BlockDriverState *base,
                  BlockDriverState *top, int64_t speed,
                  BlockErrorAction on_error, BlockDriverCompletionFunc *cb,
                  void *opaque, Error **errp)
{
    CommitBlockJob *s;
    BlockReopenQueue *reopen_queue = NULL;
    int orig_overlay_flags;
    int orig_base_flags;
    BlockDriverState *overlay_bs;
    Error *local_err = NULL;

    if ((on_error == BLOCK_ERR_STOP_ANY ||
         on_error == BLOCK_ERR_STOP_ENOSPC) &&
        !bdrv_iostatus_is_enabled(bs)) {
        error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
        return;
    }

    /* Once we support top == active layer, remove this check */
    if (top == bs) {
        error_setg(errp,
                   "Top image as the active layer is currently unsupported");
        return;
    }

    if (top == base) {
        error_setg(errp, "Invalid files for merge: top and base are the same");
        return;
    }

    /* top and base may be valid, but let's make sure that base is reachable
     * from top */
    if (bdrv_find_backing_image(top, base->filename) != base) {
        error_setg(errp,
                   "Base (%s) is not reachable from top (%s)",
                   base->filename, top->filename);
        return;
    }

    overlay_bs = bdrv_find_overlay(bs, top);

    if (overlay_bs == NULL) {
        error_setg(errp, "Could not find overlay image for %s:", top->filename);
        return;
    }

    orig_base_flags    = bdrv_get_flags(base);
    orig_overlay_flags = bdrv_get_flags(overlay_bs);

    /* convert base & overlay_bs to r/w, if necessary */
    if (!(orig_base_flags & BDRV_O_RDWR)) {
        reopen_queue = bdrv_reopen_queue(reopen_queue, base,
                                         orig_base_flags | BDRV_O_RDWR);
    }
    if (!(orig_overlay_flags & BDRV_O_RDWR)) {
        reopen_queue = bdrv_reopen_queue(reopen_queue, overlay_bs,
                                         orig_overlay_flags | BDRV_O_RDWR);
    }
    if (reopen_queue) {
        bdrv_reopen_multiple(reopen_queue, &local_err);
        if (local_err != NULL) {
            error_propagate(errp, local_err);
            return;
        }
    }


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

    s->base   = base;
    s->top    = top;
    s->active = bs;

    s->base_flags          = orig_base_flags;
    s->orig_overlay_flags  = orig_overlay_flags;

    s->on_error = on_error;
    s->common.co = qemu_coroutine_create(commit_run);

    trace_commit_start(bs, base, top, s, s->common.co, opaque);
    qemu_coroutine_enter(s->common.co, s);
}