#include "trace.h"
#include "block/blockjob.h"
#include "block/block_int.h"
+#include "sysemu/block-backend.h"
+#include "qapi/qmp/qerror.h"
#include "qemu/ratelimit.h"
#include "qemu/bitmap.h"
+#include "qemu/error-report.h"
#define SLICE_TIME 100000000ULL /* ns */
#define MAX_IN_FLIGHT 16
+#define DEFAULT_MIRROR_BUF_SIZE (10 << 20)
/* The mirroring buffer is a list of granularity-sized chunks.
* Free chunks are organized in a list.
int in_flight;
int sectors_in_flight;
int ret;
+ bool unmap;
+ bool waiting_for_io;
} MirrorBlockJob;
typedef struct MirrorOp {
}
qemu_iovec_destroy(&op->qiov);
- g_slice_free(MirrorOp, op);
+ g_free(op);
- /* Enter coroutine when it is not sleeping. The coroutine sleeps to
- * rate-limit itself. The coroutine will eventually resume since there is
- * a sleep timeout so don't wake it early.
- */
- if (s->common.busy) {
+ if (s->waiting_for_io) {
qemu_coroutine_enter(s->common.co, NULL);
}
}
int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
uint64_t delay_ns = 0;
MirrorOp *op;
+ int pnum;
+ int64_t ret;
s->sector_num = hbitmap_iter_next(&s->hbi);
if (s->sector_num < 0) {
/* Wait for I/O to this cluster (from a previous iteration) to be done. */
while (test_bit(next_chunk, s->in_flight_bitmap)) {
trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
+ s->waiting_for_io = true;
qemu_coroutine_yield();
+ s->waiting_for_io = false;
}
do {
*/
while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
+ s->waiting_for_io = true;
qemu_coroutine_yield();
+ s->waiting_for_io = false;
}
if (s->buf_free_count < nb_chunks + added_chunks) {
trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
break;
}
+ if (IOV_MAX < nb_chunks + added_chunks) {
+ trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
+ break;
+ }
/* We have enough free space to copy these sectors. */
bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
} while (delay_ns == 0 && next_sector < end);
/* Allocate a MirrorOp that is used as an AIO callback. */
- op = g_slice_new(MirrorOp);
+ op = g_new(MirrorOp, 1);
op->s = s;
op->sector_num = sector_num;
op->nb_sectors = nb_sectors;
s->in_flight++;
s->sectors_in_flight += nb_sectors;
trace_mirror_one_iteration(s, sector_num, nb_sectors);
- bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
- mirror_read_complete, op);
+
+ ret = bdrv_get_block_status_above(source, NULL, sector_num,
+ nb_sectors, &pnum);
+ if (ret < 0 || pnum < nb_sectors ||
+ (ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) {
+ bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
+ mirror_read_complete, op);
+ } else if (ret & BDRV_BLOCK_ZERO) {
+ bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors,
+ s->unmap ? BDRV_REQ_MAY_UNMAP : 0,
+ mirror_write_complete, op);
+ } else {
+ assert(!(ret & BDRV_BLOCK_DATA));
+ bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
+ mirror_write_complete, op);
+ }
return delay_ns;
}
static void mirror_drain(MirrorBlockJob *s)
{
while (s->in_flight > 0) {
+ s->waiting_for_io = true;
qemu_coroutine_yield();
+ s->waiting_for_io = false;
}
}
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
+ BlockDriverState *src = s->common.bs;
+
+ /* Make sure that the source BDS doesn't go away before we called
+ * block_job_completed(). */
+ bdrv_ref(src);
if (s->to_replace) {
replace_aio_context = bdrv_get_aio_context(s->to_replace);
if (s->to_replace) {
to_replace = s->to_replace;
}
+
+ /* This was checked in mirror_start_job(), but meanwhile one of the
+ * nodes could have been newly attached to a BlockBackend. */
+ if (to_replace->blk && s->target->blk) {
+ error_report("block job: Can't create node with two BlockBackends");
+ data->ret = -EINVAL;
+ goto out;
+ }
+
if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
}
- bdrv_swap(s->target, to_replace);
- if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
- /* drop the bs loop chain formed by the swap: break the loop then
- * trigger the unref from the top one */
- BlockDriverState *p = s->base->backing_hd;
- bdrv_set_backing_hd(s->base, NULL);
- bdrv_unref(p);
- }
+ bdrv_replace_in_backing_chain(to_replace, s->target);
}
+
+out:
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
aio_context_release(replace_aio_context);
}
g_free(s->replaces);
+ bdrv_op_unblock_all(s->target, s->common.blocker);
bdrv_unref(s->target);
block_job_completed(&s->common, data->ret);
g_free(data);
+ bdrv_drained_end(src);
+ bdrv_unref(src);
}
static void coroutine_fn mirror_run(void *opaque)
MirrorBlockJob *s = opaque;
MirrorExitData *data;
BlockDriverState *bs = s->common.bs;
- int64_t sector_num, end, sectors_per_chunk, length;
+ int64_t sector_num, end, length;
uint64_t last_pause_ns;
BlockDriverInfo bdi;
char backing_filename[2]; /* we only need 2 characters because we are only
*/
bdrv_get_backing_filename(s->target, backing_filename,
sizeof(backing_filename));
- if (backing_filename[0] && !s->target->backing_hd) {
+ if (backing_filename[0] && !s->target->backing) {
ret = bdrv_get_info(s->target, &bdi);
if (ret < 0) {
goto immediate_exit;
goto immediate_exit;
}
- sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
mirror_free_init(s);
+ last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
if (!s->is_none_mode) {
/* First part, loop on the sectors and initialize the dirty bitmap. */
BlockDriverState *base = s->base;
+ bool mark_all_dirty = s->base == NULL && !bdrv_has_zero_init(s->target);
+
for (sector_num = 0; sector_num < end; ) {
- int64_t next = (sector_num | (sectors_per_chunk - 1)) + 1;
- ret = bdrv_is_allocated_above(bs, base,
- sector_num, next - sector_num, &n);
+ /* Just to make sure we are not exceeding int limit. */
+ int nb_sectors = MIN(INT_MAX >> BDRV_SECTOR_BITS,
+ end - sector_num);
+ int64_t now = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
+
+ if (now - last_pause_ns > SLICE_TIME) {
+ last_pause_ns = now;
+ block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, 0);
+ }
+
+ if (block_job_is_cancelled(&s->common)) {
+ goto immediate_exit;
+ }
+
+ ret = bdrv_is_allocated_above(bs, base, sector_num, nb_sectors, &n);
if (ret < 0) {
goto immediate_exit;
}
assert(n > 0);
- if (ret == 1) {
+ if (ret == 1 || mark_all_dirty) {
bdrv_set_dirty_bitmap(s->dirty_bitmap, sector_num, n);
- sector_num = next;
- } else {
- sector_num += n;
}
+ sector_num += n;
}
}
bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
- last_pause_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
for (;;) {
uint64_t delay_ns = 0;
int64_t cnt;
if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
(cnt == 0 && s->in_flight > 0)) {
trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
+ s->waiting_for_io = true;
qemu_coroutine_yield();
+ s->waiting_for_io = false;
continue;
} else if (cnt != 0) {
delay_ns = mirror_iteration(s);
g_free(s->cow_bitmap);
g_free(s->in_flight_bitmap);
bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
- bdrv_iostatus_disable(s->target);
+ if (s->target->blk) {
+ blk_iostatus_disable(s->target->blk);
+ }
data = g_malloc(sizeof(*data));
data->ret = ret;
+ /* Before we switch to target in mirror_exit, make sure data doesn't
+ * change. */
+ bdrv_drained_begin(s->common.bs);
block_job_defer_to_main_loop(&s->common, mirror_exit, data);
}
MirrorBlockJob *s = container_of(job, MirrorBlockJob, 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);
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
- bdrv_iostatus_reset(s->target);
+ if (s->target->blk) {
+ blk_iostatus_reset(s->target->blk);
+ }
}
static void mirror_complete(BlockJob *job, Error **errp)
Error *local_err = NULL;
int ret;
- ret = bdrv_open_backing_file(s->target, NULL, &local_err);
+ ret = bdrv_open_backing_file(s->target, NULL, "backing", &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return;
}
if (!s->synced) {
- error_set(errp, QERR_BLOCK_JOB_NOT_READY,
- bdrv_get_device_name(job->bs));
+ error_setg(errp, QERR_BLOCK_JOB_NOT_READY, job->id);
return;
}
if (s->replaces) {
AioContext *replace_aio_context;
- s->to_replace = check_to_replace_node(s->replaces, &local_err);
+ s->to_replace = bdrv_find_node(s->replaces);
if (!s->to_replace) {
- error_propagate(errp, local_err);
+ error_setg(errp, "Node name '%s' not found", s->replaces);
return;
}
int64_t buf_size,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
+ bool unmap,
BlockCompletionFunc *cb,
void *opaque, Error **errp,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base)
{
MirrorBlockJob *s;
+ BlockDriverState *replaced_bs;
if (granularity == 0) {
granularity = bdrv_get_default_bitmap_granularity(target);
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");
+ (!bs->blk || !blk_iostatus_is_enabled(bs->blk))) {
+ error_setg(errp, QERR_INVALID_PARAMETER, "on-source-error");
return;
}
+ if (buf_size < 0) {
+ error_setg(errp, "Invalid parameter 'buf-size'");
+ return;
+ }
+
+ if (buf_size == 0) {
+ buf_size = DEFAULT_MIRROR_BUF_SIZE;
+ }
+
+ /* We can't support this case as long as the block layer can't handle
+ * multiple BlockBackends per BlockDriverState. */
+ if (replaces) {
+ replaced_bs = bdrv_lookup_bs(replaces, replaces, errp);
+ if (replaced_bs == NULL) {
+ return;
+ }
+ } else {
+ replaced_bs = bs;
+ }
+ if (replaced_bs->blk && target->blk) {
+ error_setg(errp, "Can't create node with two BlockBackends");
+ return;
+ }
s = block_job_create(driver, bs, speed, cb, opaque, errp);
if (!s) {
s->is_none_mode = is_none_mode;
s->base = base;
s->granularity = granularity;
- s->buf_size = MAX(buf_size, granularity);
+ s->buf_size = ROUND_UP(buf_size, granularity);
+ s->unmap = unmap;
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
if (!s->dirty_bitmap) {
+ g_free(s->replaces);
+ block_job_unref(&s->common);
return;
}
+
+ bdrv_op_block_all(s->target, s->common.blocker);
+
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);
+ if (s->target->blk) {
+ blk_set_on_error(s->target->blk, on_target_error, on_target_error);
+ blk_iostatus_enable(s->target->blk);
+ }
s->common.co = qemu_coroutine_create(mirror_run);
trace_mirror_start(bs, s, s->common.co, opaque);
qemu_coroutine_enter(s->common.co, s);
int64_t speed, uint32_t granularity, int64_t buf_size,
MirrorSyncMode mode, BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
+ bool unmap,
BlockCompletionFunc *cb,
void *opaque, Error **errp)
{
bool is_none_mode;
BlockDriverState *base;
- if (mode == MIRROR_SYNC_MODE_DIRTY_BITMAP) {
- error_setg(errp, "Sync mode 'dirty-bitmap' not supported");
+ if (mode == MIRROR_SYNC_MODE_INCREMENTAL) {
+ error_setg(errp, "Sync mode 'incremental' not supported");
return;
}
is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
- base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
+ base = mode == MIRROR_SYNC_MODE_TOP ? backing_bs(bs) : NULL;
mirror_start_job(bs, target, replaces,
speed, granularity, buf_size,
- on_source_error, on_target_error, cb, opaque, errp,
+ on_source_error, on_target_error, unmap, cb, opaque, errp,
&mirror_job_driver, is_none_mode, base);
}
bdrv_ref(base);
mirror_start_job(bs, base, NULL, speed, 0, 0,
- on_error, on_error, cb, opaque, &local_err,
+ on_error, on_error, false, cb, opaque, &local_err,
&commit_active_job_driver, false, base);
if (local_err) {
error_propagate(errp, local_err);
projects / qemu.git / blobdiff