#include "block/block_int.h"
#include "block/blockjob_int.h"
#include "qapi/error.h"
-#include "qapi/qmp/qerror.h"
#include "qapi/qmp/qdict.h"
#include "qemu/ratelimit.h"
#include "sysemu/block-backend.h"
typedef struct StreamBlockJob {
BlockJob common;
+ BlockBackend *blk;
BlockDriverState *base_overlay; /* COW overlay (stream from this) */
BlockDriverState *above_base; /* Node directly above the base */
BlockDriverState *cor_filter_bs;
BlockDriverState *target_bs;
BlockdevOnError on_error;
char *backing_file_str;
+ bool backing_mask_protocol;
bool bs_read_only;
} StreamBlockJob;
static int stream_prepare(Job *job)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
- BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs);
- BlockDriverState *base = bdrv_filter_or_cow_bs(s->above_base);
- BlockDriverState *unfiltered_base = bdrv_skip_filters(base);
+ BlockDriverState *unfiltered_bs;
+ BlockDriverState *unfiltered_bs_cow;
+ BlockDriverState *base;
+ BlockDriverState *unfiltered_base;
Error *local_err = NULL;
int ret = 0;
+ GLOBAL_STATE_CODE();
+
+ bdrv_graph_rdlock_main_loop();
+ unfiltered_bs = bdrv_skip_filters(s->target_bs);
+ unfiltered_bs_cow = bdrv_cow_bs(unfiltered_bs);
+ bdrv_graph_rdunlock_main_loop();
+
/* We should drop filter at this point, as filter hold the backing chain */
bdrv_cor_filter_drop(s->cor_filter_bs);
s->cor_filter_bs = NULL;
- if (bdrv_cow_child(unfiltered_bs)) {
+ /*
+ * bdrv_set_backing_hd() requires that the unfiltered_bs and the COW child
+ * of unfiltered_bs is drained. Drain already here and use
+ * bdrv_set_backing_hd_drained() instead because the polling during
+ * drained_begin() might change the graph, and if we do this only later, we
+ * may end up working with the wrong base node (or it might even have gone
+ * away by the time we want to use it).
+ */
+ bdrv_drained_begin(unfiltered_bs);
+ if (unfiltered_bs_cow) {
+ bdrv_ref(unfiltered_bs_cow);
+ bdrv_drained_begin(unfiltered_bs_cow);
+ }
+
+ bdrv_graph_rdlock_main_loop();
+ base = bdrv_filter_or_cow_bs(s->above_base);
+ unfiltered_base = bdrv_skip_filters(base);
+ bdrv_graph_rdunlock_main_loop();
+
+ if (unfiltered_bs_cow) {
const char *base_id = NULL, *base_fmt = NULL;
if (unfiltered_base) {
base_id = s->backing_file_str ?: unfiltered_base->filename;
if (unfiltered_base->drv) {
- base_fmt = unfiltered_base->drv->format_name;
+ if (s->backing_mask_protocol &&
+ unfiltered_base->drv->protocol_name) {
+ base_fmt = "raw";
+ } else {
+ base_fmt = unfiltered_base->drv->format_name;
+ }
}
}
- bdrv_set_backing_hd(unfiltered_bs, base, &local_err);
+
+ bdrv_graph_wrlock();
+ bdrv_set_backing_hd_drained(unfiltered_bs, base, &local_err);
+ bdrv_graph_wrunlock();
+
+ /*
+ * This call will do I/O, so the graph can change again from here on.
+ * We have already completed the graph change, so we are not in danger
+ * of operating on the wrong node any more if this happens.
+ */
ret = bdrv_change_backing_file(unfiltered_bs, base_id, base_fmt, false);
if (local_err) {
error_report_err(local_err);
- return -EPERM;
+ ret = -EPERM;
+ goto out;
}
}
+out:
+ if (unfiltered_bs_cow) {
+ bdrv_drained_end(unfiltered_bs_cow);
+ bdrv_unref(unfiltered_bs_cow);
+ }
+ bdrv_drained_end(unfiltered_bs);
return ret;
}
static void stream_clean(Job *job)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
- BlockJob *bjob = &s->common;
if (s->cor_filter_bs) {
bdrv_cor_filter_drop(s->cor_filter_bs);
s->cor_filter_bs = NULL;
}
+ blk_unref(s->blk);
+ s->blk = NULL;
+
/* 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(s->target_bs, true, NULL);
}
static int coroutine_fn stream_run(Job *job, Error **errp)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
- BlockBackend *blk = s->common.blk;
- BlockDriverState *unfiltered_bs = bdrv_skip_filters(s->target_bs);
+ BlockDriverState *unfiltered_bs;
int64_t len;
int64_t offset = 0;
- uint64_t delay_ns = 0;
int error = 0;
int64_t n = 0; /* bytes */
- if (unfiltered_bs == s->base_overlay) {
- /* Nothing to stream */
- return 0;
- }
+ WITH_GRAPH_RDLOCK_GUARD() {
+ unfiltered_bs = bdrv_skip_filters(s->target_bs);
+ if (unfiltered_bs == s->base_overlay) {
+ /* Nothing to stream */
+ return 0;
+ }
- len = bdrv_getlength(s->target_bs);
- if (len < 0) {
- return len;
+ len = bdrv_co_getlength(s->target_bs);
+ if (len < 0) {
+ return len;
+ }
}
job_progress_set_remaining(&s->common.job, len);
/* 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);
+ block_job_ratelimit_sleep(&s->common);
if (job_is_cancelled(&s->common.job)) {
break;
}
copy = false;
- ret = bdrv_is_allocated(unfiltered_bs, offset, STREAM_CHUNK, &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(bdrv_cow_bs(unfiltered_bs),
- s->base_overlay, true,
- offset, n, &n);
- /* Finish early if end of backing file has been reached */
- if (ret == 0 && n == 0) {
- n = len - offset;
+ WITH_GRAPH_RDLOCK_GUARD() {
+ ret = bdrv_co_is_allocated(unfiltered_bs, offset, STREAM_CHUNK, &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_co_is_allocated_above(bdrv_cow_bs(unfiltered_bs),
+ s->base_overlay, true,
+ offset, n, &n);
+ /* Finish early if end of backing file has been reached */
+ if (ret == 0 && n == 0) {
+ n = len - offset;
+ }
+
+ copy = (ret > 0);
}
-
- copy = (ret > 0);
}
trace_stream_one_iteration(s, offset, n, ret);
if (copy) {
- ret = stream_populate(blk, offset, n);
+ ret = stream_populate(s->blk, offset, n);
}
if (ret < 0) {
BlockErrorAction action =
/* 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;
+ block_job_ratelimit_processed_bytes(&s->common, n);
}
}
void stream_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, const char *backing_file_str,
+ bool backing_mask_protocol,
BlockDriverState *bottom,
int creation_flags, int64_t speed,
BlockdevOnError on_error,
const char *filter_node_name,
Error **errp)
{
- StreamBlockJob *s;
+ StreamBlockJob *s = NULL;
BlockDriverState *iter;
bool bs_read_only;
int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
BlockDriverState *cor_filter_bs = NULL;
BlockDriverState *above_base;
QDict *opts;
+ int ret;
+
+ GLOBAL_STATE_CODE();
assert(!(base && bottom));
assert(!(backing_file_str && bottom));
+ bdrv_graph_rdlock_main_loop();
+
if (bottom) {
/*
* New simple interface. The code is written in terms of old interface
if (!base_overlay) {
error_setg(errp, "'%s' is not in the backing chain of '%s'",
base->node_name, bs->node_name);
- return;
+ goto out_rdlock;
}
/*
/* Make sure that the image is opened in read-write mode */
bs_read_only = bdrv_is_read_only(bs);
if (bs_read_only) {
- int ret;
/* Hold the chain during reopen */
if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) {
- return;
+ goto out_rdlock;
}
ret = bdrv_reopen_set_read_only(bs, false, errp);
bdrv_unfreeze_backing_chain(bs, above_base);
if (ret < 0) {
- return;
+ goto out_rdlock;
}
}
+ bdrv_graph_rdunlock_main_loop();
+
opts = qdict_new();
qdict_put_str(opts, "driver", "copy-on-read");
}
s = block_job_create(job_id, &stream_job_driver, NULL, cor_filter_bs,
- BLK_PERM_CONSISTENT_READ,
- basic_flags | BLK_PERM_WRITE,
+ 0, BLK_PERM_ALL,
speed, creation_flags, NULL, NULL, errp);
if (!s) {
goto fail;
}
+ s->blk = blk_new_with_bs(cor_filter_bs, BLK_PERM_CONSISTENT_READ,
+ basic_flags | BLK_PERM_WRITE, errp);
+ if (!s->blk) {
+ goto fail;
+ }
+ /*
+ * Disable request queuing in the BlockBackend to avoid deadlocks on drain:
+ * The job reports that it's busy until it reaches a pause point.
+ */
+ blk_set_disable_request_queuing(s->blk, true);
+ blk_set_allow_aio_context_change(s->blk, true);
+
/*
* 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.
*/
+ bdrv_graph_wrlock();
if (block_job_add_bdrv(&s->common, "active node", bs, 0,
- basic_flags | BLK_PERM_WRITE, &error_abort)) {
+ basic_flags | BLK_PERM_WRITE, errp)) {
+ bdrv_graph_wrunlock();
goto fail;
}
for (iter = bdrv_filter_or_cow_bs(bs); iter != base;
iter = bdrv_filter_or_cow_bs(iter))
{
- block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
- basic_flags, &error_abort);
+ ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+ basic_flags, errp);
+ if (ret < 0) {
+ bdrv_graph_wrunlock();
+ goto fail;
+ }
}
+ bdrv_graph_wrunlock();
s->base_overlay = base_overlay;
s->above_base = above_base;
s->backing_file_str = g_strdup(backing_file_str);
+ s->backing_mask_protocol = backing_mask_protocol;
s->cor_filter_bs = cor_filter_bs;
s->target_bs = bs;
s->bs_read_only = bs_read_only;
return;
fail:
+ if (s) {
+ job_early_fail(&s->common.job);
+ }
if (cor_filter_bs) {
bdrv_cor_filter_drop(cor_filter_bs);
}
if (bs_read_only) {
bdrv_reopen_set_read_only(bs, true, NULL);
}
+ return;
+
+out_rdlock:
+ bdrv_graph_rdunlock_main_loop();
}
projects / mirror_qemu.git / blobdiff