*
*/
-#include <stdio.h>
-#include <errno.h>
-#include <unistd.h>
+#include "qemu/osdep.h"
#include "trace.h"
#include "block/block.h"
#include "block/block_int.h"
#include "block/blockjob.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qerror.h"
#include "qemu/ratelimit.h"
+#include "qemu/cutils.h"
+#include "sysemu/block-backend.h"
+#include "qemu/bitmap.h"
-#define BACKUP_CLUSTER_BITS 16
-#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
-#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
-
+#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
#define SLICE_TIME 100000000ULL /* ns */
typedef struct CowRequest {
typedef struct BackupBlockJob {
BlockJob common;
- BlockDriverState *target;
+ BlockBackend *target;
+ /* bitmap for sync=incremental */
+ BdrvDirtyBitmap *sync_bitmap;
MirrorSyncMode sync_mode;
RateLimit limit;
BlockdevOnError on_source_error;
BlockdevOnError on_target_error;
CoRwlock flush_rwlock;
uint64_t sectors_read;
- HBitmap *bitmap;
+ unsigned long *done_bitmap;
+ int64_t cluster_size;
+ NotifierWithReturn before_write;
QLIST_HEAD(, CowRequest) inflight_reqs;
} BackupBlockJob;
+/* Size of a cluster in sectors, instead of bytes. */
+static inline int64_t cluster_size_sectors(BackupBlockJob *job)
+{
+ return job->cluster_size / BDRV_SECTOR_SIZE;
+}
+
/* See if in-flight requests overlap and wait for them to complete */
static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
int64_t start,
qemu_co_queue_restart_all(&req->wait_queue);
}
-static int coroutine_fn backup_do_cow(BlockDriverState *bs,
+static int coroutine_fn backup_do_cow(BackupBlockJob *job,
int64_t sector_num, int nb_sectors,
- bool *error_is_read)
+ bool *error_is_read,
+ bool is_write_notifier)
{
- BackupBlockJob *job = (BackupBlockJob *)bs->job;
+ BlockBackend *blk = job->common.blk;
CowRequest cow_request;
struct iovec iov;
QEMUIOVector bounce_qiov;
void *bounce_buffer = NULL;
int ret = 0;
+ int64_t sectors_per_cluster = cluster_size_sectors(job);
int64_t start, end;
int n;
qemu_co_rwlock_rdlock(&job->flush_rwlock);
- start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
- end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
+ start = sector_num / sectors_per_cluster;
+ end = DIV_ROUND_UP(sector_num + nb_sectors, sectors_per_cluster);
trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
cow_request_begin(&cow_request, job, start, end);
for (; start < end; start++) {
- if (hbitmap_get(job->bitmap, start)) {
+ if (test_bit(start, job->done_bitmap)) {
trace_backup_do_cow_skip(job, start);
continue; /* already copied */
}
trace_backup_do_cow_process(job, start);
- n = MIN(BACKUP_SECTORS_PER_CLUSTER,
+ n = MIN(sectors_per_cluster,
job->common.len / BDRV_SECTOR_SIZE -
- start * BACKUP_SECTORS_PER_CLUSTER);
+ start * sectors_per_cluster);
if (!bounce_buffer) {
- bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
+ bounce_buffer = blk_blockalign(blk, job->cluster_size);
}
iov.iov_base = bounce_buffer;
iov.iov_len = n * BDRV_SECTOR_SIZE;
qemu_iovec_init_external(&bounce_qiov, &iov, 1);
- ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
- &bounce_qiov);
+ ret = blk_co_preadv(blk, start * job->cluster_size,
+ bounce_qiov.size, &bounce_qiov,
+ is_write_notifier ? BDRV_REQ_NO_SERIALISING : 0);
if (ret < 0) {
trace_backup_do_cow_read_fail(job, start, ret);
if (error_is_read) {
}
if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
- ret = bdrv_co_write_zeroes(job->target,
- start * BACKUP_SECTORS_PER_CLUSTER,
- n, BDRV_REQ_MAY_UNMAP);
+ ret = blk_co_pwrite_zeroes(job->target, start * job->cluster_size,
+ bounce_qiov.size, BDRV_REQ_MAY_UNMAP);
} else {
- ret = bdrv_co_writev(job->target,
- start * BACKUP_SECTORS_PER_CLUSTER, n,
- &bounce_qiov);
+ ret = blk_co_pwritev(job->target, start * job->cluster_size,
+ bounce_qiov.size, &bounce_qiov, 0);
}
if (ret < 0) {
trace_backup_do_cow_write_fail(job, start, ret);
goto out;
}
- hbitmap_set(job->bitmap, start, 1);
+ set_bit(start, job->done_bitmap);
/* Publish progress, guest I/O counts as progress too. Note that the
* offset field is an opaque progress value, it is not a disk offset.
NotifierWithReturn *notifier,
void *opaque)
{
+ BackupBlockJob *job = container_of(notifier, BackupBlockJob, before_write);
BdrvTrackedRequest *req = opaque;
int64_t sector_num = req->offset >> BDRV_SECTOR_BITS;
int nb_sectors = req->bytes >> BDRV_SECTOR_BITS;
+ assert(req->bs == blk_bs(job->common.blk));
assert((req->offset & (BDRV_SECTOR_SIZE - 1)) == 0);
assert((req->bytes & (BDRV_SECTOR_SIZE - 1)) == 0);
- return backup_do_cow(req->bs, sector_num, nb_sectors, NULL);
+ return backup_do_cow(job, sector_num, nb_sectors, NULL, true);
}
static void backup_set_speed(BlockJob *job, int64_t speed, Error **errp)
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
if (speed < 0) {
- error_set(errp, QERR_INVALID_PARAMETER, "speed");
+ error_setg(errp, QERR_INVALID_PARAMETER, "speed");
return;
}
ratelimit_set_speed(&s->limit, speed / BDRV_SECTOR_SIZE, SLICE_TIME);
}
-static void backup_iostatus_reset(BlockJob *job)
+static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
+{
+ BdrvDirtyBitmap *bm;
+ BlockDriverState *bs = blk_bs(job->common.blk);
+
+ if (ret < 0 || block_job_is_cancelled(&job->common)) {
+ /* Merge the successor back into the parent, delete nothing. */
+ bm = bdrv_reclaim_dirty_bitmap(bs, job->sync_bitmap, NULL);
+ assert(bm);
+ } else {
+ /* Everything is fine, delete this bitmap and install the backup. */
+ bm = bdrv_dirty_bitmap_abdicate(bs, job->sync_bitmap, NULL);
+ assert(bm);
+ }
+}
+
+static void backup_commit(BlockJob *job)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+ if (s->sync_bitmap) {
+ backup_cleanup_sync_bitmap(s, 0);
+ }
+}
- bdrv_iostatus_reset(s->target);
+static void backup_abort(BlockJob *job)
+{
+ BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+ if (s->sync_bitmap) {
+ backup_cleanup_sync_bitmap(s, -1);
+ }
}
static const BlockJobDriver backup_job_driver = {
.instance_size = sizeof(BackupBlockJob),
.job_type = BLOCK_JOB_TYPE_BACKUP,
.set_speed = backup_set_speed,
- .iostatus_reset = backup_iostatus_reset,
+ .commit = backup_commit,
+ .abort = backup_abort,
};
static BlockErrorAction backup_error_action(BackupBlockJob *job,
bool read, int error)
{
if (read) {
- return block_job_error_action(&job->common, job->common.bs,
- job->on_source_error, true, error);
+ return block_job_error_action(&job->common, job->on_source_error,
+ true, error);
} else {
- return block_job_error_action(&job->common, job->target,
- job->on_target_error, false, error);
+ return block_job_error_action(&job->common, job->on_target_error,
+ false, error);
}
}
+typedef struct {
+ int ret;
+} BackupCompleteData;
+
+static void backup_complete(BlockJob *job, void *opaque)
+{
+ BackupBlockJob *s = container_of(job, BackupBlockJob, common);
+ BackupCompleteData *data = opaque;
+
+ blk_unref(s->target);
+
+ block_job_completed(job, data->ret);
+ g_free(data);
+}
+
+static bool coroutine_fn yield_and_check(BackupBlockJob *job)
+{
+ if (block_job_is_cancelled(&job->common)) {
+ return true;
+ }
+
+ /* we need to yield so that bdrv_drain_all() returns.
+ * (without, VM does not reboot)
+ */
+ if (job->common.speed) {
+ uint64_t delay_ns = ratelimit_calculate_delay(&job->limit,
+ job->sectors_read);
+ job->sectors_read = 0;
+ block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
+ } else {
+ block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
+ }
+
+ if (block_job_is_cancelled(&job->common)) {
+ return true;
+ }
+
+ return false;
+}
+
+static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
+{
+ bool error_is_read;
+ int ret = 0;
+ int clusters_per_iter;
+ uint32_t granularity;
+ int64_t sector;
+ int64_t cluster;
+ int64_t end;
+ int64_t last_cluster = -1;
+ int64_t sectors_per_cluster = cluster_size_sectors(job);
+ HBitmapIter hbi;
+
+ granularity = bdrv_dirty_bitmap_granularity(job->sync_bitmap);
+ clusters_per_iter = MAX((granularity / job->cluster_size), 1);
+ bdrv_dirty_iter_init(job->sync_bitmap, &hbi);
+
+ /* Find the next dirty sector(s) */
+ while ((sector = hbitmap_iter_next(&hbi)) != -1) {
+ cluster = sector / sectors_per_cluster;
+
+ /* Fake progress updates for any clusters we skipped */
+ if (cluster != last_cluster + 1) {
+ job->common.offset += ((cluster - last_cluster - 1) *
+ job->cluster_size);
+ }
+
+ for (end = cluster + clusters_per_iter; cluster < end; cluster++) {
+ do {
+ if (yield_and_check(job)) {
+ return ret;
+ }
+ ret = backup_do_cow(job, cluster * sectors_per_cluster,
+ sectors_per_cluster, &error_is_read,
+ false);
+ if ((ret < 0) &&
+ backup_error_action(job, error_is_read, -ret) ==
+ BLOCK_ERROR_ACTION_REPORT) {
+ return ret;
+ }
+ } while (ret < 0);
+ }
+
+ /* If the bitmap granularity is smaller than the backup granularity,
+ * we need to advance the iterator pointer to the next cluster. */
+ if (granularity < job->cluster_size) {
+ bdrv_set_dirty_iter(&hbi, cluster * sectors_per_cluster);
+ }
+
+ last_cluster = cluster - 1;
+ }
+
+ /* Play some final catchup with the progress meter */
+ end = DIV_ROUND_UP(job->common.len, job->cluster_size);
+ if (last_cluster + 1 < end) {
+ job->common.offset += ((end - last_cluster - 1) * job->cluster_size);
+ }
+
+ return ret;
+}
+
static void coroutine_fn backup_run(void *opaque)
{
BackupBlockJob *job = opaque;
- BlockDriverState *bs = job->common.bs;
- BlockDriverState *target = job->target;
- BlockdevOnError on_target_error = job->on_target_error;
- NotifierWithReturn before_write = {
- .notify = backup_before_write_notify,
- };
+ BackupCompleteData *data;
+ BlockDriverState *bs = blk_bs(job->common.blk);
+ BlockBackend *target = job->target;
int64_t start, end;
+ int64_t sectors_per_cluster = cluster_size_sectors(job);
int ret = 0;
QLIST_INIT(&job->inflight_reqs);
qemu_co_rwlock_init(&job->flush_rwlock);
start = 0;
- end = DIV_ROUND_UP(job->common.len / BDRV_SECTOR_SIZE,
- BACKUP_SECTORS_PER_CLUSTER);
-
- job->bitmap = hbitmap_alloc(end, 0);
+ end = DIV_ROUND_UP(job->common.len, job->cluster_size);
- bdrv_set_enable_write_cache(target, true);
- bdrv_set_on_error(target, on_target_error, on_target_error);
- bdrv_iostatus_enable(target);
+ job->done_bitmap = bitmap_new(end);
- bdrv_add_before_write_notifier(bs, &before_write);
+ job->before_write.notify = backup_before_write_notify;
+ bdrv_add_before_write_notifier(bs, &job->before_write);
if (job->sync_mode == MIRROR_SYNC_MODE_NONE) {
while (!block_job_is_cancelled(&job->common)) {
qemu_coroutine_yield();
job->common.busy = true;
}
+ } else if (job->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
+ ret = backup_run_incremental(job);
} else {
/* Both FULL and TOP SYNC_MODE's require copying.. */
for (; start < end; start++) {
bool error_is_read;
-
- if (block_job_is_cancelled(&job->common)) {
- break;
- }
-
- /* we need to yield so that qemu_aio_flush() returns.
- * (without, VM does not reboot)
- */
- if (job->common.speed) {
- uint64_t delay_ns = ratelimit_calculate_delay(
- &job->limit, job->sectors_read);
- job->sectors_read = 0;
- block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, delay_ns);
- } else {
- block_job_sleep_ns(&job->common, QEMU_CLOCK_REALTIME, 0);
- }
-
- if (block_job_is_cancelled(&job->common)) {
+ if (yield_and_check(job)) {
break;
}
/* Check to see if these blocks are already in the
* backing file. */
- for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
+ for (i = 0; i < sectors_per_cluster;) {
/* bdrv_is_allocated() only returns true/false based
* on the first set of sectors it comes across that
* are are all in the same state.
* needed but at some point that is always the case. */
alloced =
bdrv_is_allocated(bs,
- start * BACKUP_SECTORS_PER_CLUSTER + i,
- BACKUP_SECTORS_PER_CLUSTER - i, &n);
+ start * sectors_per_cluster + i,
+ sectors_per_cluster - i, &n);
i += n;
- if (alloced == 1) {
+ if (alloced == 1 || n == 0) {
break;
}
}
}
}
/* FULL sync mode we copy the whole drive. */
- ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
- BACKUP_SECTORS_PER_CLUSTER, &error_is_read);
+ ret = backup_do_cow(job, start * sectors_per_cluster,
+ sectors_per_cluster, &error_is_read, false);
if (ret < 0) {
/* Depending on error action, fail now or retry cluster */
BlockErrorAction action =
}
}
- notifier_with_return_remove(&before_write);
+ notifier_with_return_remove(&job->before_write);
/* wait until pending backup_do_cow() calls have completed */
qemu_co_rwlock_wrlock(&job->flush_rwlock);
qemu_co_rwlock_unlock(&job->flush_rwlock);
+ g_free(job->done_bitmap);
- hbitmap_free(job->bitmap);
+ bdrv_op_unblock_all(blk_bs(target), job->common.blocker);
- bdrv_iostatus_disable(target);
- bdrv_unref(target);
-
- block_job_completed(&job->common, ret);
+ data = g_malloc(sizeof(*data));
+ data->ret = ret;
+ block_job_defer_to_main_loop(&job->common, backup_complete, data);
}
void backup_start(BlockDriverState *bs, BlockDriverState *target,
int64_t speed, MirrorSyncMode sync_mode,
+ BdrvDirtyBitmap *sync_bitmap,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
- BlockDriverCompletionFunc *cb, void *opaque,
- Error **errp)
+ BlockCompletionFunc *cb, void *opaque,
+ BlockJobTxn *txn, Error **errp)
{
int64_t len;
+ BlockDriverInfo bdi;
+ BackupBlockJob *job = NULL;
+ int ret;
assert(bs);
assert(target);
assert(cb);
- 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");
+ if (bs == target) {
+ error_setg(errp, "Source and target cannot be the same");
+ return;
+ }
+
+ if (!bdrv_is_inserted(bs)) {
+ error_setg(errp, "Device is not inserted: %s",
+ bdrv_get_device_name(bs));
+ return;
+ }
+
+ if (!bdrv_is_inserted(target)) {
+ error_setg(errp, "Device is not inserted: %s",
+ bdrv_get_device_name(target));
+ return;
+ }
+
+ if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
+ return;
+ }
+
+ if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_BACKUP_TARGET, errp)) {
+ return;
+ }
+
+ if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
+ if (!sync_bitmap) {
+ error_setg(errp, "must provide a valid bitmap name for "
+ "\"incremental\" sync mode");
+ return;
+ }
+
+ /* Create a new bitmap, and freeze/disable this one. */
+ if (bdrv_dirty_bitmap_create_successor(bs, sync_bitmap, errp) < 0) {
+ return;
+ }
+ } else if (sync_bitmap) {
+ error_setg(errp,
+ "a sync_bitmap was provided to backup_run, "
+ "but received an incompatible sync_mode (%s)",
+ MirrorSyncMode_lookup[sync_mode]);
return;
}
if (len < 0) {
error_setg_errno(errp, -len, "unable to get length for '%s'",
bdrv_get_device_name(bs));
- return;
+ goto error;
}
- BackupBlockJob *job = block_job_create(&backup_job_driver, bs, speed,
- cb, opaque, errp);
+ job = block_job_create(&backup_job_driver, bs, speed, cb, opaque, errp);
if (!job) {
- return;
+ goto error;
}
+ job->target = blk_new();
+ blk_insert_bs(job->target, target);
+
job->on_source_error = on_source_error;
job->on_target_error = on_target_error;
- job->target = target;
job->sync_mode = sync_mode;
+ job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
+ sync_bitmap : NULL;
+
+ /* If there is no backing file on the target, we cannot rely on COW if our
+ * backup cluster size is smaller than the target cluster size. Even for
+ * targets with a backing file, try to avoid COW if possible. */
+ ret = bdrv_get_info(target, &bdi);
+ if (ret < 0 && !target->backing) {
+ error_setg_errno(errp, -ret,
+ "Couldn't determine the cluster size of the target image, "
+ "which has no backing file");
+ error_append_hint(errp,
+ "Aborting, since this may create an unusable destination image\n");
+ goto error;
+ } else if (ret < 0 && target->backing) {
+ /* Not fatal; just trudge on ahead. */
+ job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT;
+ } else {
+ job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
+ }
+
+ bdrv_op_block_all(target, job->common.blocker);
job->common.len = len;
job->common.co = qemu_coroutine_create(backup_run);
+ block_job_txn_add_job(txn, &job->common);
qemu_coroutine_enter(job->common.co, job);
+ return;
+
+ error:
+ if (sync_bitmap) {
+ bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
+ }
+ if (job) {
+ blk_unref(job->target);
+ block_job_unref(&job->common);
+ }
}
projects / qemu.git / blobdiff