#include "block/block_int.h"
#include "block/blockjob_int.h"
#include "qapi/error.h"
-#include "qapi/qmp/qerror.h"
#include "qemu/ratelimit.h"
+#include "qemu/memalign.h"
#include "sysemu/block-backend.h"
enum {
BlockBackend *top;
BlockBackend *base;
BlockDriverState *base_bs;
+ BlockDriverState *base_overlay;
BlockdevOnError on_error;
bool base_read_only;
bool chain_frozen;
char *backing_file_str;
} CommitBlockJob;
-static int coroutine_fn commit_populate(BlockBackend *bs, BlockBackend *base,
- int64_t offset, uint64_t bytes,
- void *buf)
-{
- int ret = 0;
-
- assert(bytes < SIZE_MAX);
-
- ret = blk_co_pread(bs, offset, bytes, buf, 0);
- if (ret < 0) {
- return ret;
- }
-
- ret = blk_co_pwrite(base, offset, bytes, buf, 0);
- if (ret < 0) {
- return ret;
- }
-
- return 0;
-}
-
static int commit_prepare(Job *job)
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
+ bdrv_graph_rdlock_main_loop();
bdrv_unfreeze_backing_chain(s->commit_top_bs, s->base_bs);
s->chain_frozen = false;
+ bdrv_graph_rdunlock_main_loop();
/* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
* the normal backing chain can be restored. */
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
BlockDriverState *top_bs = blk_bs(s->top);
+ BlockDriverState *commit_top_backing_bs;
if (s->chain_frozen) {
+ bdrv_graph_rdlock_main_loop();
bdrv_unfreeze_backing_chain(s->commit_top_bs, s->base_bs);
+ bdrv_graph_rdunlock_main_loop();
}
/* Make sure commit_top_bs and top stay around until bdrv_replace_node() */
* XXX Can (or should) we somehow keep 'consistent read' blocked even
* after the failed/cancelled commit job is gone? If we already wrote
* something to base, the intermediate images aren't valid any more. */
- bdrv_replace_node(s->commit_top_bs, backing_bs(s->commit_top_bs),
- &error_abort);
+ commit_top_backing_bs = s->commit_top_bs->backing->bs;
+ bdrv_drained_begin(commit_top_backing_bs);
+ bdrv_graph_wrlock(commit_top_backing_bs);
+ bdrv_replace_node(s->commit_top_bs, commit_top_backing_bs, &error_abort);
+ bdrv_graph_wrunlock();
+ bdrv_drained_end(commit_top_backing_bs);
bdrv_unref(s->commit_top_bs);
bdrv_unref(top_bs);
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common.job);
int64_t offset;
- uint64_t delay_ns = 0;
int ret = 0;
int64_t n = 0; /* bytes */
- void *buf = NULL;
- int bytes_written = 0;
+ QEMU_AUTO_VFREE void *buf = NULL;
int64_t len, base_len;
- ret = len = blk_getlength(s->top);
+ len = blk_co_getlength(s->top);
if (len < 0) {
- goto out;
+ return len;
}
job_progress_set_remaining(&s->common.job, len);
- ret = base_len = blk_getlength(s->base);
+ base_len = blk_co_getlength(s->base);
if (base_len < 0) {
- goto out;
+ return base_len;
}
if (base_len < len) {
- ret = blk_truncate(s->base, len, PREALLOC_MODE_OFF, NULL);
+ ret = blk_co_truncate(s->base, len, false, PREALLOC_MODE_OFF, 0, NULL);
if (ret) {
- goto out;
+ return ret;
}
}
for (offset = 0; offset < len; offset += n) {
bool copy;
+ bool error_in_source = true;
/* 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 if allocated above the base */
- ret = bdrv_is_allocated_above(blk_bs(s->top), blk_bs(s->base), false,
- offset, COMMIT_BUFFER_SIZE, &n);
- copy = (ret == 1);
+ ret = blk_co_is_allocated_above(s->top, s->base_overlay, true,
+ offset, COMMIT_BUFFER_SIZE, &n);
+ copy = (ret > 0);
trace_commit_one_iteration(s, offset, n, ret);
if (copy) {
- ret = commit_populate(s->top, s->base, offset, n, buf);
- bytes_written += n;
+ assert(n < SIZE_MAX);
+
+ ret = blk_co_pread(s->top, offset, n, buf, 0);
+ if (ret >= 0) {
+ ret = blk_co_pwrite(s->base, offset, n, buf, 0);
+ if (ret < 0) {
+ error_in_source = false;
+ }
+ }
}
if (ret < 0) {
BlockErrorAction action =
- block_job_error_action(&s->common, false, s->on_error, -ret);
+ block_job_error_action(&s->common, s->on_error,
+ error_in_source, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT) {
- goto out;
+ return ret;
} else {
n = 0;
continue;
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);
}
}
- ret = 0;
-
-out:
- qemu_vfree(buf);
-
- return ret;
+ return 0;
}
static const BlockJobDriver commit_job_driver = {
.job_type = JOB_TYPE_COMMIT,
.free = block_job_free,
.user_resume = block_job_user_resume,
- .drain = block_job_drain,
.run = commit_run,
.prepare = commit_prepare,
.abort = commit_abort,
},
};
-static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
- uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+static int coroutine_fn GRAPH_RDLOCK
+bdrv_commit_top_preadv(BlockDriverState *bs, int64_t offset, int64_t bytes,
+ QEMUIOVector *qiov, BdrvRequestFlags flags)
{
return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
}
}
static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
- const BdrvChildRole *role,
+ BdrvChildRole role,
BlockReopenQueue *reopen_queue,
uint64_t perm, uint64_t shared,
uint64_t *nperm, uint64_t *nshared)
static BlockDriver bdrv_commit_top = {
.format_name = "commit_top",
.bdrv_co_preadv = bdrv_commit_top_preadv,
- .bdrv_co_block_status = bdrv_co_block_status_from_backing,
.bdrv_refresh_filename = bdrv_commit_top_refresh_filename,
.bdrv_child_perm = bdrv_commit_top_child_perm,
+
+ .is_filter = true,
+ .filtered_child_is_backing = true,
};
void commit_start(const char *job_id, BlockDriverState *bs,
CommitBlockJob *s;
BlockDriverState *iter;
BlockDriverState *commit_top_bs = NULL;
- Error *local_err = NULL;
+ BlockDriverState *filtered_base;
+ int64_t base_size, top_size;
+ uint64_t base_perms, iter_shared_perms;
int ret;
+ GLOBAL_STATE_CODE();
+
assert(top != bs);
- if (top == base) {
+ bdrv_graph_rdlock_main_loop();
+ if (bdrv_skip_filters(top) == bdrv_skip_filters(base)) {
error_setg(errp, "Invalid files for merge: top and base are the same");
+ bdrv_graph_rdunlock_main_loop();
+ return;
+ }
+ bdrv_graph_rdunlock_main_loop();
+
+ base_size = bdrv_getlength(base);
+ if (base_size < 0) {
+ error_setg_errno(errp, -base_size, "Could not inquire base image size");
+ return;
+ }
+
+ top_size = bdrv_getlength(top);
+ if (top_size < 0) {
+ error_setg_errno(errp, -top_size, "Could not inquire top image size");
return;
}
+ base_perms = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE;
+ if (base_size < top_size) {
+ base_perms |= BLK_PERM_RESIZE;
+ }
+
s = block_job_create(job_id, &commit_job_driver, NULL, bs, 0, BLK_PERM_ALL,
speed, creation_flags, NULL, NULL, errp);
if (!s) {
commit_top_bs->total_sectors = top->total_sectors;
- bdrv_append(commit_top_bs, top, &local_err);
- if (local_err) {
+ ret = bdrv_append(commit_top_bs, top, errp);
+ bdrv_unref(commit_top_bs); /* referenced by new parents or failed */
+ if (ret < 0) {
commit_top_bs = NULL;
- error_propagate(errp, local_err);
goto fail;
}
s->commit_top_bs = commit_top_bs;
- /* Block all nodes between top and base, because they will
- * disappear from the chain after this operation. */
- assert(bdrv_chain_contains(top, base));
- for (iter = top; iter != base; iter = backing_bs(iter)) {
- /* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
- * at s->base (if writes are blocked for a node, they are also blocked
- * for its backing file). The other options would be a second filter
- * driver above s->base. */
+ /*
+ * Block all nodes between top and base, because they will
+ * disappear from the chain after this operation.
+ * Note that this assumes that the user is fine with removing all
+ * nodes (including R/W filters) between top and base. Assuring
+ * this is the responsibility of the interface (i.e. whoever calls
+ * commit_start()).
+ */
+ bdrv_graph_wrlock(top);
+ s->base_overlay = bdrv_find_overlay(top, base);
+ assert(s->base_overlay);
+
+ /*
+ * The topmost node with
+ * bdrv_skip_filters(filtered_base) == bdrv_skip_filters(base)
+ */
+ filtered_base = bdrv_cow_bs(s->base_overlay);
+ assert(bdrv_skip_filters(filtered_base) == bdrv_skip_filters(base));
+
+ /*
+ * XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
+ * at s->base (if writes are blocked for a node, they are also blocked
+ * for its backing file). The other options would be a second filter
+ * driver above s->base.
+ */
+ iter_shared_perms = BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE;
+
+ for (iter = top; iter != base; iter = bdrv_filter_or_cow_bs(iter)) {
+ if (iter == filtered_base) {
+ /*
+ * From here on, all nodes are filters on the base. This
+ * allows us to share BLK_PERM_CONSISTENT_READ.
+ */
+ iter_shared_perms |= BLK_PERM_CONSISTENT_READ;
+ }
+
ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
- BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
- errp);
+ iter_shared_perms, errp);
if (ret < 0) {
+ bdrv_graph_wrunlock();
goto fail;
}
}
if (bdrv_freeze_backing_chain(commit_top_bs, base, errp) < 0) {
+ bdrv_graph_wrunlock();
goto fail;
}
s->chain_frozen = true;
ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
+ bdrv_graph_wrunlock();
+
if (ret < 0) {
goto fail;
}
s->base = blk_new(s->common.job.aio_context,
+ base_perms,
BLK_PERM_CONSISTENT_READ
- | BLK_PERM_WRITE
- | BLK_PERM_RESIZE,
- BLK_PERM_CONSISTENT_READ
- | BLK_PERM_GRAPH_MOD
| BLK_PERM_WRITE_UNCHANGED);
ret = blk_insert_bs(s->base, base, errp);
if (ret < 0) {
goto fail;
}
+ blk_set_disable_request_queuing(s->base, true);
s->base_bs = base;
/* Required permissions are already taken with block_job_add_bdrv() */
if (ret < 0) {
goto fail;
}
+ blk_set_disable_request_queuing(s->top, true);
s->backing_file_str = g_strdup(backing_file_str);
s->on_error = on_error;
fail:
if (s->chain_frozen) {
+ bdrv_graph_rdlock_main_loop();
bdrv_unfreeze_backing_chain(commit_top_bs, base);
+ bdrv_graph_rdunlock_main_loop();
}
if (s->base) {
blk_unref(s->base);
/* commit_top_bs has to be replaced after deleting the block job,
* otherwise this would fail because of lack of permissions. */
if (commit_top_bs) {
+ bdrv_drained_begin(top);
+ bdrv_graph_wrlock(top);
bdrv_replace_node(commit_top_bs, top, &error_abort);
+ bdrv_graph_wrunlock();
+ bdrv_drained_end(top);
}
}
int ro;
int64_t n;
int ret = 0;
- uint8_t *buf = NULL;
+ QEMU_AUTO_VFREE uint8_t *buf = NULL;
Error *local_err = NULL;
+ GLOBAL_STATE_CODE();
+ GRAPH_RDLOCK_GUARD_MAINLOOP();
+
if (!drv)
return -ENOMEDIUM;
- if (!bs->backing) {
+ backing_file_bs = bdrv_cow_bs(bs);
+
+ if (!backing_file_bs) {
return -ENOTSUP;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_COMMIT_SOURCE, NULL) ||
- bdrv_op_is_blocked(bs->backing->bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL)) {
+ bdrv_op_is_blocked(backing_file_bs, BLOCK_OP_TYPE_COMMIT_TARGET, NULL))
+ {
return -EBUSY;
}
- ro = bs->backing->bs->read_only;
+ ro = bdrv_is_read_only(backing_file_bs);
if (ro) {
- if (bdrv_reopen_set_read_only(bs->backing->bs, false, NULL)) {
+ if (bdrv_reopen_set_read_only(backing_file_bs, false, NULL)) {
return -EACCES;
}
}
ctx = bdrv_get_aio_context(bs);
- src = blk_new(ctx, BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
+ /* WRITE_UNCHANGED is required for bdrv_make_empty() */
+ src = blk_new(ctx, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
+ BLK_PERM_ALL);
backing = blk_new(ctx, BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
ret = blk_insert_bs(src, bs, &local_err);
}
/* Insert commit_top block node above backing, so we can write to it */
- backing_file_bs = backing_bs(bs);
-
commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
&local_err);
if (commit_top_bs == NULL) {
* grow the backing file image if possible. If not possible,
* we must return an error */
if (length > backing_length) {
- ret = blk_truncate(backing, length, PREALLOC_MODE_OFF, &local_err);
+ ret = blk_truncate(backing, length, false, PREALLOC_MODE_OFF, 0,
+ &local_err);
if (ret < 0) {
error_report_err(local_err);
goto ro_cleanup;
goto ro_cleanup;
}
if (ret) {
- ret = blk_pread(src, offset, buf, n);
+ ret = blk_pread(src, offset, n, buf, 0);
if (ret < 0) {
goto ro_cleanup;
}
- ret = blk_pwrite(backing, offset, buf, n, 0);
+ ret = blk_pwrite(backing, offset, n, buf, 0);
if (ret < 0) {
goto ro_cleanup;
}
}
}
- if (drv->bdrv_make_empty) {
- ret = drv->bdrv_make_empty(bs);
- if (ret < 0) {
- goto ro_cleanup;
- }
- blk_flush(src);
+ ret = blk_make_empty(src, NULL);
+ /* Ignore -ENOTSUP */
+ if (ret < 0 && ret != -ENOTSUP) {
+ goto ro_cleanup;
}
+ blk_flush(src);
+
/*
* Make sure all data we wrote to the backing device is actually
* stable on disk.
ret = 0;
ro_cleanup:
- qemu_vfree(buf);
-
blk_unref(backing);
- if (backing_file_bs) {
+ if (bdrv_cow_bs(bs) != backing_file_bs) {
bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
}
bdrv_unref(commit_top_bs);
if (ro) {
/* ignoring error return here */
- bdrv_reopen_set_read_only(bs->backing->bs, true, NULL);
+ bdrv_reopen_set_read_only(backing_file_bs, true, NULL);
}
return ret;