OpenE2K/qemu-e2k
13
4
Fork 0
Code Issues 4 Pull Requests Projects 2 Releases Activity
6cf38cbf29
qemu-e2k/block/backup.c
John Snow 35d6b368f2 blockjobs: ensure abort is called for cancelled jobs 
Presently, even if a job is canceled post-completion as a result of
a failing peer in a transaction, it will still call .commit because
nothing has updated or changed its return code.

The reason why this does not cause problems currently is because
backup's implementation of .commit checks for cancellation itself.

I'd like to simplify this contract:

(1) Abort is called if the job/transaction fails
(2) Commit is called if the job/transaction succeeds

To this end: A job's return code, if 0, will be forcibly set as
-ECANCELED if that job has already concluded. Remove the now
redundant check in the backup job implementation.

We need to check for cancellation in both block_job_completed
AND block_job_completed_single, because jobs may be cancelled between
those two calls; for instance in transactions. This also necessitates
an ABORTING -> ABORTING transition to be allowed.

The check in block_job_completed could be removed, but there's no
point in starting to attempt to succeed a transaction that we know
in advance will fail.

This does NOT affect mirror jobs that are "canceled" during their
synchronous phase. The mirror job itself forcibly sets the canceled
property to false prior to ceding control, so such cases will invoke
the "commit" callback.

Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2018-03-19 12:01:24 +01:00

694 lines
22 KiB
C
Raw Blame History

/*
* QEMU backup
*
* Copyright (C) 2013 Proxmox Server Solutions
*
* Authors:
* Dietmar Maurer (dietmar@proxmox.com)
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "block/block.h"
#include "block/block_int.h"
#include "block/blockjob_int.h"
#include "block/block_backup.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"
#include "qemu/error-report.h"
#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
#define SLICE_TIME 100000000ULL /* ns */
typedef struct BackupBlockJob {
BlockJob common;
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 bytes_read;
int64_t cluster_size;
bool compress;
NotifierWithReturn before_write;
QLIST_HEAD(, CowRequest) inflight_reqs;
HBitmap *copy_bitmap;
} BackupBlockJob;
/* 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,
int64_t end)
{
CowRequest *req;
bool retry;
do {
retry = false;
QLIST_FOREACH(req, &job->inflight_reqs, list) {
if (end > req->start_byte && start < req->end_byte) {
qemu_co_queue_wait(&req->wait_queue, NULL);
retry = true;
break;
}
}
} while (retry);
}
/* Keep track of an in-flight request */
static void cow_request_begin(CowRequest *req, BackupBlockJob *job,
int64_t start, int64_t end)
{
req->start_byte = start;
req->end_byte = end;
qemu_co_queue_init(&req->wait_queue);
QLIST_INSERT_HEAD(&job->inflight_reqs, req, list);
}
/* Forget about a completed request */
static void cow_request_end(CowRequest *req)
{
QLIST_REMOVE(req, list);
qemu_co_queue_restart_all(&req->wait_queue);
}
static int coroutine_fn backup_do_cow(BackupBlockJob *job,
int64_t offset, uint64_t bytes,
bool *error_is_read,
bool is_write_notifier)
{
BlockBackend *blk = job->common.blk;
CowRequest cow_request;
struct iovec iov;
QEMUIOVector bounce_qiov;
void *bounce_buffer = NULL;
int ret = 0;
int64_t start, end; /* bytes */
int n; /* bytes */
qemu_co_rwlock_rdlock(&job->flush_rwlock);
start = QEMU_ALIGN_DOWN(offset, job->cluster_size);
end = QEMU_ALIGN_UP(bytes + offset, job->cluster_size);
trace_backup_do_cow_enter(job, start, offset, bytes);
wait_for_overlapping_requests(job, start, end);
cow_request_begin(&cow_request, job, start, end);
for (; start < end; start += job->cluster_size) {
if (!hbitmap_get(job->copy_bitmap, start / job->cluster_size)) {
trace_backup_do_cow_skip(job, start);
continue; /* already copied */
}
hbitmap_reset(job->copy_bitmap, start / job->cluster_size, 1);
trace_backup_do_cow_process(job, start);
n = MIN(job->cluster_size, job->common.len - start);
if (!bounce_buffer) {
bounce_buffer = blk_blockalign(blk, job->cluster_size);
}
iov.iov_base = bounce_buffer;
iov.iov_len = n;
qemu_iovec_init_external(&bounce_qiov, &iov, 1);
ret = blk_co_preadv(blk, start, 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) {
*error_is_read = true;
}
hbitmap_set(job->copy_bitmap, start / job->cluster_size, 1);
goto out;
}
if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
ret = blk_co_pwrite_zeroes(job->target, start,
bounce_qiov.size, BDRV_REQ_MAY_UNMAP);
} else {
ret = blk_co_pwritev(job->target, start,
bounce_qiov.size, &bounce_qiov,
job->compress ? BDRV_REQ_WRITE_COMPRESSED : 0);
}
if (ret < 0) {
trace_backup_do_cow_write_fail(job, start, ret);
if (error_is_read) {
*error_is_read = false;
}
hbitmap_set(job->copy_bitmap, start / job->cluster_size, 1);
goto out;
}
/* 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.
*/
job->bytes_read += n;
job->common.offset += n;
}
out:
if (bounce_buffer) {
qemu_vfree(bounce_buffer);
}
cow_request_end(&cow_request);
trace_backup_do_cow_return(job, offset, bytes, ret);
qemu_co_rwlock_unlock(&job->flush_rwlock);
return ret;
}
static int coroutine_fn backup_before_write_notify(
NotifierWithReturn *notifier,
void *opaque)
{
BackupBlockJob *job = container_of(notifier, BackupBlockJob, before_write);
BdrvTrackedRequest *req = opaque;
assert(req->bs == blk_bs(job->common.blk));
assert(QEMU_IS_ALIGNED(req->offset, BDRV_SECTOR_SIZE));
assert(QEMU_IS_ALIGNED(req->bytes, BDRV_SECTOR_SIZE));
return backup_do_cow(job, req->offset, req->bytes, 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_setg(errp, QERR_INVALID_PARAMETER, "speed");
return;
}
ratelimit_set_speed(&s->limit, speed, SLICE_TIME);
}
static void backup_cleanup_sync_bitmap(BackupBlockJob *job, int ret)
{
BdrvDirtyBitmap *bm;
BlockDriverState *bs = blk_bs(job->common.blk);
if (ret < 0) {
/* 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);
}
}
static void backup_abort(BlockJob *job)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
if (s->sync_bitmap) {
backup_cleanup_sync_bitmap(s, -1);
}
}
static void backup_clean(BlockJob *job)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
assert(s->target);
blk_unref(s->target);
s->target = NULL;
}
static void backup_attached_aio_context(BlockJob *job, AioContext *aio_context)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
blk_set_aio_context(s->target, aio_context);
}
void backup_do_checkpoint(BlockJob *job, Error **errp)
{
BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
int64_t len;
assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
if (backup_job->sync_mode != MIRROR_SYNC_MODE_NONE) {
error_setg(errp, "The backup job only supports block checkpoint in"
" sync=none mode");
return;
}
len = DIV_ROUND_UP(backup_job->common.len, backup_job->cluster_size);
hbitmap_set(backup_job->copy_bitmap, 0, len);
}
void backup_wait_for_overlapping_requests(BlockJob *job, int64_t offset,
uint64_t bytes)
{
BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
int64_t start, end;
assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
start = QEMU_ALIGN_DOWN(offset, backup_job->cluster_size);
end = QEMU_ALIGN_UP(offset + bytes, backup_job->cluster_size);
wait_for_overlapping_requests(backup_job, start, end);
}
void backup_cow_request_begin(CowRequest *req, BlockJob *job,
int64_t offset, uint64_t bytes)
{
BackupBlockJob *backup_job = container_of(job, BackupBlockJob, common);
int64_t start, end;
assert(job->driver->job_type == BLOCK_JOB_TYPE_BACKUP);
start = QEMU_ALIGN_DOWN(offset, backup_job->cluster_size);
end = QEMU_ALIGN_UP(offset + bytes, backup_job->cluster_size);
cow_request_begin(req, backup_job, start, end);
}
void backup_cow_request_end(CowRequest *req)
{
cow_request_end(req);
}
static void backup_drain(BlockJob *job)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
/* Need to keep a reference in case blk_drain triggers execution
* of backup_complete...
*/
if (s->target) {
BlockBackend *target = s->target;
blk_ref(target);
blk_drain(target);
blk_unref(target);
}
}
static BlockErrorAction backup_error_action(BackupBlockJob *job,
bool read, int error)
{
if (read) {
return block_job_error_action(&job->common, job->on_source_error,
true, error);
} else {
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)
{
BackupCompleteData *data = opaque;
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->bytes_read);
job->bytes_read = 0;
block_job_sleep_ns(&job->common, delay_ns);
} else {
block_job_sleep_ns(&job->common, 0);
}
if (block_job_is_cancelled(&job->common)) {
return true;
}
return false;
}
static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
{
int ret;
bool error_is_read;
int64_t cluster;
HBitmapIter hbi;
hbitmap_iter_init(&hbi, job->copy_bitmap, 0);
while ((cluster = hbitmap_iter_next(&hbi)) != -1) {
do {
if (yield_and_check(job)) {
return 0;
}
ret = backup_do_cow(job, cluster * job->cluster_size,
job->cluster_size, &error_is_read, false);
if (ret < 0 && backup_error_action(job, error_is_read, -ret) ==
BLOCK_ERROR_ACTION_REPORT)
{
return ret;
}
} while (ret < 0);
}
return 0;
}
/* init copy_bitmap from sync_bitmap */
static void backup_incremental_init_copy_bitmap(BackupBlockJob *job)
{
BdrvDirtyBitmapIter *dbi;
int64_t offset;
int64_t end = DIV_ROUND_UP(bdrv_dirty_bitmap_size(job->sync_bitmap),
job->cluster_size);
dbi = bdrv_dirty_iter_new(job->sync_bitmap);
while ((offset = bdrv_dirty_iter_next(dbi)) != -1) {
int64_t cluster = offset / job->cluster_size;
int64_t next_cluster;
offset += bdrv_dirty_bitmap_granularity(job->sync_bitmap);
if (offset >= bdrv_dirty_bitmap_size(job->sync_bitmap)) {
hbitmap_set(job->copy_bitmap, cluster, end - cluster);
break;
}
offset = bdrv_dirty_bitmap_next_zero(job->sync_bitmap, offset);
if (offset == -1) {
hbitmap_set(job->copy_bitmap, cluster, end - cluster);
break;
}
next_cluster = DIV_ROUND_UP(offset, job->cluster_size);
hbitmap_set(job->copy_bitmap, cluster, next_cluster - cluster);
if (next_cluster >= end) {
break;
}
bdrv_set_dirty_iter(dbi, next_cluster * job->cluster_size);
}
job->common.offset = job->common.len -
hbitmap_count(job->copy_bitmap) * job->cluster_size;
bdrv_dirty_iter_free(dbi);
}
static void coroutine_fn backup_run(void *opaque)
{
BackupBlockJob *job = opaque;
BackupCompleteData *data;
BlockDriverState *bs = blk_bs(job->common.blk);
int64_t offset, nb_clusters;
int ret = 0;
QLIST_INIT(&job->inflight_reqs);
qemu_co_rwlock_init(&job->flush_rwlock);
nb_clusters = DIV_ROUND_UP(job->common.len, job->cluster_size);
job->copy_bitmap = hbitmap_alloc(nb_clusters, 0);
if (job->sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
backup_incremental_init_copy_bitmap(job);
} else {
hbitmap_set(job->copy_bitmap, 0, nb_clusters);
}
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) {
/* All bits are set in copy_bitmap to allow any cluster to be copied.
* This does not actually require them to be copied. */
while (!block_job_is_cancelled(&job->common)) {
/* Yield until the job is cancelled. We just let our before_write
* notify callback service CoW requests. */
block_job_yield(&job->common);
}
} 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 (offset = 0; offset < job->common.len;
offset += job->cluster_size) {
bool error_is_read;
int alloced = 0;
if (yield_and_check(job)) {
break;
}
if (job->sync_mode == MIRROR_SYNC_MODE_TOP) {
int i;
int64_t n;
/* Check to see if these blocks are already in the
* backing file. */
for (i = 0; i < job->cluster_size;) {
/* 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.
* For that reason we must verify each sector in the
* backup cluster length. We end up copying more than
* needed but at some point that is always the case. */
alloced =
bdrv_is_allocated(bs, offset + i,
job->cluster_size - i, &n);
i += n;
if (alloced || n == 0) {
break;
}
}
/* If the above loop never found any sectors that are in
* the topmost image, skip this backup. */
if (alloced == 0) {
continue;
}
}
/* FULL sync mode we copy the whole drive. */
if (alloced < 0) {
ret = alloced;
} else {
ret = backup_do_cow(job, offset, job->cluster_size,
&error_is_read, false);
}
if (ret < 0) {
/* Depending on error action, fail now or retry cluster */
BlockErrorAction action =
backup_error_action(job, error_is_read, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT) {
break;
} else {
offset -= job->cluster_size;
continue;
}
}
}
}
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);
hbitmap_free(job->copy_bitmap);
data = g_malloc(sizeof(*data));
data->ret = ret;
block_job_defer_to_main_loop(&job->common, backup_complete, data);
}
static const BlockJobDriver backup_job_driver = {
.instance_size = sizeof(BackupBlockJob),
.job_type = BLOCK_JOB_TYPE_BACKUP,
.start = backup_run,
.set_speed = backup_set_speed,
.commit = backup_commit,
.abort = backup_abort,
.clean = backup_clean,
.attached_aio_context = backup_attached_aio_context,
.drain = backup_drain,
};
BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
BlockDriverState *target, int64_t speed,
MirrorSyncMode sync_mode, BdrvDirtyBitmap *sync_bitmap,
bool compress,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
int creation_flags,
BlockCompletionFunc *cb, void *opaque,
BlockJobTxn *txn, Error **errp)
{
int64_t len;
BlockDriverInfo bdi;
BackupBlockJob *job = NULL;
int ret;
assert(bs);
assert(target);
if (bs == target) {
error_setg(errp, "Source and target cannot be the same");
return NULL;
}
if (!bdrv_is_inserted(bs)) {
error_setg(errp, "Device is not inserted: %s",
bdrv_get_device_name(bs));
return NULL;
}
if (!bdrv_is_inserted(target)) {
error_setg(errp, "Device is not inserted: %s",
bdrv_get_device_name(target));
return NULL;
}
if (compress && target->drv->bdrv_co_pwritev_compressed == NULL) {
error_setg(errp, "Compression is not supported for this drive %s",
bdrv_get_device_name(target));
return NULL;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_BACKUP_SOURCE, errp)) {
return NULL;
}
if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_BACKUP_TARGET, errp)) {
return NULL;
}
if (sync_mode == MIRROR_SYNC_MODE_INCREMENTAL) {
if (!sync_bitmap) {
error_setg(errp, "must provide a valid bitmap name for "
"\"incremental\" sync mode");
return NULL;
}
/* Create a new bitmap, and freeze/disable this one. */
if (bdrv_dirty_bitmap_create_successor(bs, sync_bitmap, errp) < 0) {
return NULL;
}
} else if (sync_bitmap) {
error_setg(errp,
"a sync_bitmap was provided to backup_run, "
"but received an incompatible sync_mode (%s)",
MirrorSyncMode_str(sync_mode));
return NULL;
}
len = bdrv_getlength(bs);
if (len < 0) {
error_setg_errno(errp, -len, "unable to get length for '%s'",
bdrv_get_device_name(bs));
goto error;
}
/* job->common.len is fixed, so we can't allow resize */
job = block_job_create(job_id, &backup_job_driver, txn, bs,
BLK_PERM_CONSISTENT_READ,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD,
speed, creation_flags, cb, opaque, errp);
if (!job) {
goto error;
}
/* The target must match the source in size, so no resize here either */
job->target = blk_new(BLK_PERM_WRITE,
BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE |
BLK_PERM_WRITE_UNCHANGED | BLK_PERM_GRAPH_MOD);
ret = blk_insert_bs(job->target, target, errp);
if (ret < 0) {
goto error;
}
job->on_source_error = on_source_error;
job->on_target_error = on_target_error;
job->sync_mode = sync_mode;
job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
sync_bitmap : NULL;
job->compress = compress;
/* 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 == -ENOTSUP && !target->backing) {
/* Cluster size is not defined */
warn_report("The target block device doesn't provide "
"information about the block size and it doesn't have a "
"backing file. The default block size of %u bytes is "
"used. If the actual block size of the target exceeds "
"this default, the backup may be unusable",
BACKUP_CLUSTER_SIZE_DEFAULT);
job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT;
} else 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);
}
/* Required permissions are already taken with target's blk_new() */
block_job_add_bdrv(&job->common, "target", target, 0, BLK_PERM_ALL,
&error_abort);
job->common.len = len;
return &job->common;
error:
if (sync_bitmap) {
bdrv_reclaim_dirty_bitmap(bs, sync_bitmap, NULL);
}
if (job) {
backup_clean(&job->common);
block_job_early_fail(&job->common);
}
return NULL;
}
Reference in New Issue View Git Blame Copy Permalink