aboutsummaryrefslogtreecommitdiff
path: root/block
diff options
context:
space:
mode:
Diffstat (limited to 'block')
-rw-r--r--block/backup.c22
-rw-r--r--block/blkdebug.c4
-rwxr-xr-xblock/blkreplay.c1
-rw-r--r--block/blkverify.c1
-rw-r--r--block/block-backend.c118
-rw-r--r--block/bochs.c7
-rw-r--r--block/cloop.c7
-rw-r--r--block/commit.c176
-rw-r--r--block/crypto.c9
-rw-r--r--block/curl.c24
-rw-r--r--block/dmg.c7
-rw-r--r--block/file-posix.c28
-rw-r--r--block/io.c41
-rw-r--r--block/iscsi.c436
-rw-r--r--block/mirror.c298
-rw-r--r--block/nbd.c2
-rw-r--r--block/nfs.c75
-rw-r--r--block/parallels.c18
-rw-r--r--block/qapi.c1
-rw-r--r--block/qcow.c14
-rw-r--r--block/qcow2-refcount.c2
-rw-r--r--block/qcow2.c41
-rw-r--r--block/qed.c22
-rw-r--r--block/quorum.c11
-rw-r--r--block/raw-format.c9
-rw-r--r--block/rbd.c633
-rw-r--r--block/replication.c9
-rw-r--r--block/sheepdog.c2
-rw-r--r--block/stream.c47
-rw-r--r--block/vdi.c10
-rw-r--r--block/vhdx-log.c2
-rw-r--r--block/vhdx.c12
-rw-r--r--block/vmdk.c13
-rw-r--r--block/vpc.c10
-rw-r--r--block/vvfat.c34
35 files changed, 1572 insertions, 574 deletions
diff --git a/block/backup.c b/block/backup.c
index fe010e78e3..d1ab617c7e 100644
--- a/block/backup.c
+++ b/block/backup.c
@@ -618,14 +618,24 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
goto error;
}
- job = block_job_create(job_id, &backup_job_driver, bs, speed,
- creation_flags, cb, opaque, errp);
+ /* job->common.len is fixed, so we can't allow resize */
+ job = block_job_create(job_id, &backup_job_driver, 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;
}
- job->target = blk_new();
- blk_insert_bs(job->target, target);
+ /* 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;
@@ -652,7 +662,9 @@ BlockJob *backup_job_create(const char *job_id, BlockDriverState *bs,
job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
}
- block_job_add_bdrv(&job->common, target);
+ /* 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;
block_job_txn_add_job(txn, &job->common);
diff --git a/block/blkdebug.c b/block/blkdebug.c
index d8eee1b9b4..67e8024e36 100644
--- a/block/blkdebug.c
+++ b/block/blkdebug.c
@@ -663,7 +663,7 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
{
- return bdrv_truncate(bs->file->bs, offset);
+ return bdrv_truncate(bs->file, offset);
}
static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
@@ -734,6 +734,8 @@ static BlockDriver bdrv_blkdebug = {
.bdrv_file_open = blkdebug_open,
.bdrv_close = blkdebug_close,
.bdrv_reopen_prepare = blkdebug_reopen_prepare,
+ .bdrv_child_perm = bdrv_filter_default_perms,
+
.bdrv_getlength = blkdebug_getlength,
.bdrv_truncate = blkdebug_truncate,
.bdrv_refresh_filename = blkdebug_refresh_filename,
diff --git a/block/blkreplay.c b/block/blkreplay.c
index cfc8c5be02..e1102119fb 100755
--- a/block/blkreplay.c
+++ b/block/blkreplay.c
@@ -137,6 +137,7 @@ static BlockDriver bdrv_blkreplay = {
.bdrv_file_open = blkreplay_open,
.bdrv_close = blkreplay_close,
+ .bdrv_child_perm = bdrv_filter_default_perms,
.bdrv_getlength = blkreplay_getlength,
.bdrv_co_preadv = blkreplay_co_preadv,
diff --git a/block/blkverify.c b/block/blkverify.c
index 43a940c2f5..9a1e21c6ad 100644
--- a/block/blkverify.c
+++ b/block/blkverify.c
@@ -320,6 +320,7 @@ static BlockDriver bdrv_blkverify = {
.bdrv_parse_filename = blkverify_parse_filename,
.bdrv_file_open = blkverify_open,
.bdrv_close = blkverify_close,
+ .bdrv_child_perm = bdrv_filter_default_perms,
.bdrv_getlength = blkverify_getlength,
.bdrv_refresh_filename = blkverify_refresh_filename,
diff --git a/block/block-backend.c b/block/block-backend.c
index 819f27213a..daa7908d01 100644
--- a/block/block-backend.c
+++ b/block/block-backend.c
@@ -59,6 +59,9 @@ struct BlockBackend {
bool iostatus_enabled;
BlockDeviceIoStatus iostatus;
+ uint64_t perm;
+ uint64_t shared_perm;
+
bool allow_write_beyond_eof;
NotifierList remove_bs_notifiers, insert_bs_notifiers;
@@ -77,6 +80,7 @@ static const AIOCBInfo block_backend_aiocb_info = {
static void drive_info_del(DriveInfo *dinfo);
static BlockBackend *bdrv_first_blk(BlockDriverState *bs);
+static char *blk_get_attached_dev_id(BlockBackend *blk);
/* All BlockBackends */
static QTAILQ_HEAD(, BlockBackend) block_backends =
@@ -99,6 +103,25 @@ static void blk_root_drained_end(BdrvChild *child);
static void blk_root_change_media(BdrvChild *child, bool load);
static void blk_root_resize(BdrvChild *child);
+static char *blk_root_get_parent_desc(BdrvChild *child)
+{
+ BlockBackend *blk = child->opaque;
+ char *dev_id;
+
+ if (blk->name) {
+ return g_strdup(blk->name);
+ }
+
+ dev_id = blk_get_attached_dev_id(blk);
+ if (*dev_id) {
+ return dev_id;
+ } else {
+ /* TODO Callback into the BB owner for something more detailed */
+ g_free(dev_id);
+ return g_strdup("a block device");
+ }
+}
+
static const char *blk_root_get_name(BdrvChild *child)
{
return blk_name(child->opaque);
@@ -110,6 +133,7 @@ static const BdrvChildRole child_root = {
.change_media = blk_root_change_media,
.resize = blk_root_resize,
.get_name = blk_root_get_name,
+ .get_parent_desc = blk_root_get_parent_desc,
.drained_begin = blk_root_drained_begin,
.drained_end = blk_root_drained_end,
@@ -117,15 +141,23 @@ static const BdrvChildRole child_root = {
/*
* Create a new BlockBackend with a reference count of one.
- * Store an error through @errp on failure, unless it's null.
+ *
+ * @perm is a bitmasks of BLK_PERM_* constants which describes the permissions
+ * to request for a block driver node that is attached to this BlockBackend.
+ * @shared_perm is a bitmask which describes which permissions may be granted
+ * to other users of the attached node.
+ * Both sets of permissions can be changed later using blk_set_perm().
+ *
* Return the new BlockBackend on success, null on failure.
*/
-BlockBackend *blk_new(void)
+BlockBackend *blk_new(uint64_t perm, uint64_t shared_perm)
{
BlockBackend *blk;
blk = g_new0(BlockBackend, 1);
blk->refcnt = 1;
+ blk->perm = perm;
+ blk->shared_perm = shared_perm;
blk_set_enable_write_cache(blk, true);
qemu_co_queue_init(&blk->public.throttled_reqs[0]);
@@ -155,15 +187,33 @@ BlockBackend *blk_new_open(const char *filename, const char *reference,
{
BlockBackend *blk;
BlockDriverState *bs;
+ uint64_t perm;
+
+ /* blk_new_open() is mainly used in .bdrv_create implementations and the
+ * tools where sharing isn't a concern because the BDS stays private, so we
+ * just request permission according to the flags.
+ *
+ * The exceptions are xen_disk and blockdev_init(); in these cases, the
+ * caller of blk_new_open() doesn't make use of the permissions, but they
+ * shouldn't hurt either. We can still share everything here because the
+ * guest devices will add their own blockers if they can't share. */
+ perm = BLK_PERM_CONSISTENT_READ;
+ if (flags & BDRV_O_RDWR) {
+ perm |= BLK_PERM_WRITE;
+ }
+ if (flags & BDRV_O_RESIZE) {
+ perm |= BLK_PERM_RESIZE;
+ }
- blk = blk_new();
+ blk = blk_new(perm, BLK_PERM_ALL);
bs = bdrv_open(filename, reference, options, flags, errp);
if (!bs) {
blk_unref(blk);
return NULL;
}
- blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk);
+ blk->root = bdrv_root_attach_child(bs, "root", &child_root,
+ perm, BLK_PERM_ALL, blk, &error_abort);
return blk;
}
@@ -495,16 +545,49 @@ void blk_remove_bs(BlockBackend *blk)
/*
* Associates a new BlockDriverState with @blk.
*/
-void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs)
+int blk_insert_bs(BlockBackend *blk, BlockDriverState *bs, Error **errp)
{
+ blk->root = bdrv_root_attach_child(bs, "root", &child_root,
+ blk->perm, blk->shared_perm, blk, errp);
+ if (blk->root == NULL) {
+ return -EPERM;
+ }
bdrv_ref(bs);
- blk->root = bdrv_root_attach_child(bs, "root", &child_root, blk);
notifier_list_notify(&blk->insert_bs_notifiers, blk);
if (blk->public.throttle_state) {
throttle_timers_attach_aio_context(
&blk->public.throttle_timers, bdrv_get_aio_context(bs));
}
+
+ return 0;
+}
+
+/*
+ * Sets the permission bitmasks that the user of the BlockBackend needs.
+ */
+int blk_set_perm(BlockBackend *blk, uint64_t perm, uint64_t shared_perm,
+ Error **errp)
+{
+ int ret;
+
+ if (blk->root) {
+ ret = bdrv_child_try_set_perm(blk->root, perm, shared_perm, errp);
+ if (ret < 0) {
+ return ret;
+ }
+ }
+
+ blk->perm = perm;
+ blk->shared_perm = shared_perm;
+
+ return 0;
+}
+
+void blk_get_perm(BlockBackend *blk, uint64_t *perm, uint64_t *shared_perm)
+{
+ *perm = blk->perm;
+ *shared_perm = blk->shared_perm;
}
static int blk_do_attach_dev(BlockBackend *blk, void *dev)
@@ -553,6 +636,7 @@ void blk_detach_dev(BlockBackend *blk, void *dev)
blk->dev_ops = NULL;
blk->dev_opaque = NULL;
blk->guest_block_size = 512;
+ blk_set_perm(blk, 0, BLK_PERM_ALL, &error_abort);
blk_unref(blk);
}
@@ -620,19 +704,29 @@ void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
/*
* Notify @blk's attached device model of media change.
- * If @load is true, notify of media load.
- * Else, notify of media eject.
+ *
+ * If @load is true, notify of media load. This action can fail, meaning that
+ * the medium cannot be loaded. @errp is set then.
+ *
+ * If @load is false, notify of media eject. This can never fail.
+ *
* Also send DEVICE_TRAY_MOVED events as appropriate.
*/
-void blk_dev_change_media_cb(BlockBackend *blk, bool load)
+void blk_dev_change_media_cb(BlockBackend *blk, bool load, Error **errp)
{
if (blk->dev_ops && blk->dev_ops->change_media_cb) {
bool tray_was_open, tray_is_open;
+ Error *local_err = NULL;
assert(!blk->legacy_dev);
tray_was_open = blk_dev_is_tray_open(blk);
- blk->dev_ops->change_media_cb(blk->dev_opaque, load);
+ blk->dev_ops->change_media_cb(blk->dev_opaque, load, &local_err);
+ if (local_err) {
+ assert(load == true);
+ error_propagate(errp, local_err);
+ return;
+ }
tray_is_open = blk_dev_is_tray_open(blk);
if (tray_was_open != tray_is_open) {
@@ -646,7 +740,7 @@ void blk_dev_change_media_cb(BlockBackend *blk, bool load)
static void blk_root_change_media(BdrvChild *child, bool load)
{
- blk_dev_change_media_cb(child->opaque, load);
+ blk_dev_change_media_cb(child->opaque, load, NULL);
}
/*
@@ -1605,7 +1699,7 @@ int blk_truncate(BlockBackend *blk, int64_t offset)
return -ENOMEDIUM;
}
- return bdrv_truncate(blk_bs(blk), offset);
+ return bdrv_truncate(blk->root, offset);
}
static void blk_pdiscard_entry(void *opaque)
diff --git a/block/bochs.c b/block/bochs.c
index 8c9652ebeb..516da56c3b 100644
--- a/block/bochs.c
+++ b/block/bochs.c
@@ -104,6 +104,12 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
struct bochs_header bochs;
int ret;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
bs->read_only = true; /* no write support yet */
ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
@@ -287,6 +293,7 @@ static BlockDriver bdrv_bochs = {
.instance_size = sizeof(BDRVBochsState),
.bdrv_probe = bochs_probe,
.bdrv_open = bochs_open,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_refresh_limits = bochs_refresh_limits,
.bdrv_co_preadv = bochs_co_preadv,
.bdrv_close = bochs_close,
diff --git a/block/cloop.c b/block/cloop.c
index 7b75f7ef7b..a6c7b9dbe6 100644
--- a/block/cloop.c
+++ b/block/cloop.c
@@ -66,6 +66,12 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
uint32_t offsets_size, max_compressed_block_size = 1, i;
int ret;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
bs->read_only = true;
/* read header */
@@ -284,6 +290,7 @@ static BlockDriver bdrv_cloop = {
.instance_size = sizeof(BDRVCloopState),
.bdrv_probe = cloop_probe,
.bdrv_open = cloop_open,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_refresh_limits = cloop_refresh_limits,
.bdrv_co_preadv = cloop_co_preadv,
.bdrv_close = cloop_close,
diff --git a/block/commit.c b/block/commit.c
index c284e8535d..22a0a4db98 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -36,6 +36,7 @@ typedef struct CommitBlockJob {
BlockJob common;
RateLimit limit;
BlockDriverState *active;
+ BlockDriverState *commit_top_bs;
BlockBackend *top;
BlockBackend *base;
BlockdevOnError on_error;
@@ -83,12 +84,23 @@ static void commit_complete(BlockJob *job, void *opaque)
BlockDriverState *active = s->active;
BlockDriverState *top = blk_bs(s->top);
BlockDriverState *base = blk_bs(s->base);
- BlockDriverState *overlay_bs = bdrv_find_overlay(active, top);
+ BlockDriverState *overlay_bs = bdrv_find_overlay(active, s->commit_top_bs);
int ret = data->ret;
+ bool remove_commit_top_bs = false;
+
+ /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
+ * the normal backing chain can be restored. */
+ blk_unref(s->base);
if (!block_job_is_cancelled(&s->common) && ret == 0) {
/* success */
- ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
+ ret = bdrv_drop_intermediate(active, s->commit_top_bs, base,
+ s->backing_file_str);
+ } else if (overlay_bs) {
+ /* 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. */
+ remove_commit_top_bs = true;
}
/* restore base open flags here if appropriate (e.g., change the base back
@@ -102,9 +114,15 @@ static void commit_complete(BlockJob *job, void *opaque)
}
g_free(s->backing_file_str);
blk_unref(s->top);
- blk_unref(s->base);
block_job_completed(&s->common, ret);
g_free(data);
+
+ /* If bdrv_drop_intermediate() didn't already do that, remove the commit
+ * filter driver from the backing chain. Do this as the final step so that
+ * the 'consistent read' permission can be granted. */
+ if (remove_commit_top_bs) {
+ bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+ }
}
static void coroutine_fn commit_run(void *opaque)
@@ -208,10 +226,38 @@ static const BlockJobDriver commit_job_driver = {
.start = commit_run,
};
+static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+ return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static void bdrv_commit_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+ const BdrvChildRole *role,
+ uint64_t perm, uint64_t shared,
+ uint64_t *nperm, uint64_t *nshared)
+{
+ *nperm = 0;
+ *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_commit_top = {
+ .format_name = "commit_top",
+ .bdrv_co_preadv = bdrv_commit_top_preadv,
+ .bdrv_close = bdrv_commit_top_close,
+ .bdrv_child_perm = bdrv_commit_top_child_perm,
+};
+
void commit_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, BlockDriverState *top, int64_t speed,
BlockdevOnError on_error, const char *backing_file_str,
- Error **errp)
+ const char *filter_node_name, Error **errp)
{
CommitBlockJob *s;
BlockReopenQueue *reopen_queue = NULL;
@@ -219,7 +265,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
int orig_base_flags;
BlockDriverState *iter;
BlockDriverState *overlay_bs;
+ BlockDriverState *commit_top_bs = NULL;
Error *local_err = NULL;
+ int ret;
assert(top != bs);
if (top == base) {
@@ -234,8 +282,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
return;
}
- s = block_job_create(job_id, &commit_job_driver, bs, speed,
- BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+ s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL,
+ speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
if (!s) {
return;
}
@@ -256,30 +304,70 @@ void commit_start(const char *job_id, BlockDriverState *bs,
bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
- block_job_unref(&s->common);
- return;
+ goto fail;
}
}
+ /* Insert commit_top block node above top, so we can block consistent read
+ * on the backing chain below it */
+ commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
+ errp);
+ if (commit_top_bs == NULL) {
+ goto fail;
+ }
+
+ bdrv_set_backing_hd(commit_top_bs, top, &error_abort);
+ bdrv_set_backing_hd(overlay_bs, commit_top_bs, &error_abort);
+
+ s->commit_top_bs = commit_top_bs;
+ bdrv_unref(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 != backing_bs(base); iter = backing_bs(iter)) {
- block_job_add_bdrv(&s->common, iter);
+ 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. */
+ ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+ BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+ errp);
+ if (ret < 0) {
+ goto fail;
+ }
+ }
+
+ ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ goto fail;
}
+
/* overlay_bs must be blocked because it needs to be modified to
- * update the backing image string, but if it's the root node then
- * don't block it again */
- if (bs != overlay_bs) {
- block_job_add_bdrv(&s->common, overlay_bs);
+ * update the backing image string. */
+ ret = block_job_add_bdrv(&s->common, "overlay of top", overlay_bs,
+ BLK_PERM_GRAPH_MOD, BLK_PERM_ALL, errp);
+ if (ret < 0) {
+ goto fail;
}
- s->base = blk_new();
- blk_insert_bs(s->base, base);
+ s->base = blk_new(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;
+ }
- s->top = blk_new();
- blk_insert_bs(s->top, top);
+ /* Required permissions are already taken with block_job_add_bdrv() */
+ s->top = blk_new(0, BLK_PERM_ALL);
+ blk_insert_bs(s->top, top, errp);
+ if (ret < 0) {
+ goto fail;
+ }
s->active = bs;
@@ -292,6 +380,19 @@ void commit_start(const char *job_id, BlockDriverState *bs,
trace_commit_start(bs, base, top, s);
block_job_start(&s->common);
+ return;
+
+fail:
+ if (s->base) {
+ blk_unref(s->base);
+ }
+ if (s->top) {
+ blk_unref(s->top);
+ }
+ if (commit_top_bs) {
+ bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+ }
+ block_job_unref(&s->common);
}
@@ -301,11 +402,14 @@ void commit_start(const char *job_id, BlockDriverState *bs,
int bdrv_commit(BlockDriverState *bs)
{
BlockBackend *src, *backing;
+ BlockDriverState *backing_file_bs = NULL;
+ BlockDriverState *commit_top_bs = NULL;
BlockDriver *drv = bs->drv;
int64_t sector, total_sectors, length, backing_length;
int n, ro, open_flags;
int ret = 0;
uint8_t *buf = NULL;
+ Error *local_err = NULL;
if (!drv)
return -ENOMEDIUM;
@@ -328,11 +432,33 @@ int bdrv_commit(BlockDriverState *bs)
}
}
- src = blk_new();
- blk_insert_bs(src, bs);
+ src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
+ backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
- backing = blk_new();
- blk_insert_bs(backing, bs->backing->bs);
+ ret = blk_insert_bs(src, bs, &local_err);
+ if (ret < 0) {
+ error_report_err(local_err);
+ goto ro_cleanup;
+ }
+
+ /* 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) {
+ error_report_err(local_err);
+ goto ro_cleanup;
+ }
+
+ bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
+ bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
+
+ ret = blk_insert_bs(backing, backing_file_bs, &local_err);
+ if (ret < 0) {
+ error_report_err(local_err);
+ goto ro_cleanup;
+ }
length = blk_getlength(src);
if (length < 0) {
@@ -404,8 +530,12 @@ int bdrv_commit(BlockDriverState *bs)
ro_cleanup:
qemu_vfree(buf);
- blk_unref(src);
blk_unref(backing);
+ if (backing_file_bs) {
+ bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
+ }
+ bdrv_unref(commit_top_bs);
+ blk_unref(src);
if (ro) {
/* ignoring error return here */
diff --git a/block/crypto.c b/block/crypto.c
index 7aa7eb553e..4a2038888d 100644
--- a/block/crypto.c
+++ b/block/crypto.c
@@ -300,6 +300,12 @@ static int block_crypto_open_generic(QCryptoBlockFormat format,
QCryptoBlockOpenOptions *open_opts = NULL;
unsigned int cflags = 0;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
@@ -383,7 +389,7 @@ static int block_crypto_truncate(BlockDriverState *bs, int64_t offset)
offset += payload_offset;
- return bdrv_truncate(bs->file->bs, offset);
+ return bdrv_truncate(bs->file, offset);
}
static void block_crypto_close(BlockDriverState *bs)
@@ -622,6 +628,7 @@ BlockDriver bdrv_crypto_luks = {
.bdrv_probe = block_crypto_probe_luks,
.bdrv_open = block_crypto_open_luks,
.bdrv_close = block_crypto_close,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_create = block_crypto_create_luks,
.bdrv_truncate = block_crypto_truncate,
.create_opts = &block_crypto_create_opts_luks,
diff --git a/block/curl.c b/block/curl.c
index 2939cc77e9..e83dcd8f50 100644
--- a/block/curl.c
+++ b/block/curl.c
@@ -135,6 +135,7 @@ typedef struct BDRVCURLState {
char *cookie;
bool accept_range;
AioContext *aio_context;
+ QemuMutex mutex;
char *username;
char *password;
char *proxyusername;
@@ -333,6 +334,7 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
return FIND_RET_NONE;
}
+/* Called with s->mutex held. */
static void curl_multi_check_completion(BDRVCURLState *s)
{
int msgs_in_queue;
@@ -374,7 +376,9 @@ static void curl_multi_check_completion(BDRVCURLState *s)
continue;
}
+ qemu_mutex_unlock(&s->mutex);
acb->common.cb(acb->common.opaque, -EPROTO);
+ qemu_mutex_lock(&s->mutex);
qemu_aio_unref(acb);
state->acb[i] = NULL;
}
@@ -386,6 +390,7 @@ static void curl_multi_check_completion(BDRVCURLState *s)
}
}
+/* Called with s->mutex held. */
static void curl_multi_do_locked(CURLState *s)
{
CURLSocket *socket, *next_socket;
@@ -409,19 +414,19 @@ static void curl_multi_do(void *arg)
{
CURLState *s = (CURLState *)arg;
- aio_context_acquire(s->s->aio_context);
+ qemu_mutex_lock(&s->s->mutex);
curl_multi_do_locked(s);
- aio_context_release(s->s->aio_context);
+ qemu_mutex_unlock(&s->s->mutex);
}
static void curl_multi_read(void *arg)
{
CURLState *s = (CURLState *)arg;
- aio_context_acquire(s->s->aio_context);
+ qemu_mutex_lock(&s->s->mutex);
curl_multi_do_locked(s);
curl_multi_check_completion(s->s);
- aio_context_release(s->s->aio_context);
+ qemu_mutex_unlock(&s->s->mutex);
}
static void curl_multi_timeout_do(void *arg)
@@ -434,11 +439,11 @@ static void curl_multi_timeout_do(void *arg)
return;
}
- aio_context_acquire(s->aio_context);
+ qemu_mutex_lock(&s->mutex);
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
curl_multi_check_completion(s);
- aio_context_release(s->aio_context);
+ qemu_mutex_unlock(&s->mutex);
#else
abort();
#endif
@@ -771,6 +776,7 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
curl_easy_cleanup(state->curl);
state->curl = NULL;
+ qemu_mutex_init(&s->mutex);
curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
qemu_opts_del(opts);
@@ -801,12 +807,11 @@ static void curl_readv_bh_cb(void *p)
CURLAIOCB *acb = p;
BlockDriverState *bs = acb->common.bs;
BDRVCURLState *s = bs->opaque;
- AioContext *ctx = bdrv_get_aio_context(bs);
size_t start = acb->sector_num * BDRV_SECTOR_SIZE;
size_t end;
- aio_context_acquire(ctx);
+ qemu_mutex_lock(&s->mutex);
// In case we have the requested data already (e.g. read-ahead),
// we can just call the callback and be done.
@@ -854,7 +859,7 @@ static void curl_readv_bh_cb(void *p)
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
out:
- aio_context_release(ctx);
+ qemu_mutex_unlock(&s->mutex);
if (ret != -EINPROGRESS) {
acb->common.cb(acb->common.opaque, ret);
qemu_aio_unref(acb);
@@ -883,6 +888,7 @@ static void curl_close(BlockDriverState *bs)
DPRINTF("CURL: Close\n");
curl_detach_aio_context(bs);
+ qemu_mutex_destroy(&s->mutex);
g_free(s->cookie);
g_free(s->url);
diff --git a/block/dmg.c b/block/dmg.c
index 58a3ae86c1..a7d25fc47b 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -413,6 +413,12 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
int64_t offset;
int ret;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
block_module_load_one("dmg-bz2");
bs->read_only = true;
@@ -691,6 +697,7 @@ static BlockDriver bdrv_dmg = {
.bdrv_probe = dmg_probe,
.bdrv_open = dmg_open,
.bdrv_refresh_limits = dmg_refresh_limits,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_co_preadv = dmg_co_preadv,
.bdrv_close = dmg_close,
};
diff --git a/block/file-posix.c b/block/file-posix.c
index 2134e0ef96..4de1abd023 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1591,18 +1591,17 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
#endif
}
- if (ftruncate(fd, total_size) != 0) {
- result = -errno;
- error_setg_errno(errp, -result, "Could not resize file");
- goto out_close;
- }
-
switch (prealloc) {
#ifdef CONFIG_POSIX_FALLOCATE
case PREALLOC_MODE_FALLOC:
- /* posix_fallocate() doesn't set errno. */
+ /*
+ * Truncating before posix_fallocate() makes it about twice slower on
+ * file systems that do not support fallocate(), trying to check if a
+ * block is allocated before allocating it, so don't do that here.
+ */
result = -posix_fallocate(fd, 0, total_size);
if (result != 0) {
+ /* posix_fallocate() doesn't set errno. */
error_setg_errno(errp, -result,
"Could not preallocate data for the new file");
}
@@ -1610,6 +1609,17 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
#endif
case PREALLOC_MODE_FULL:
{
+ /*
+ * Knowing the final size from the beginning could allow the file
+ * system driver to do less allocations and possibly avoid
+ * fragmentation of the file.
+ */
+ if (ftruncate(fd, total_size) != 0) {
+ result = -errno;
+ error_setg_errno(errp, -result, "Could not resize file");
+ goto out_close;
+ }
+
int64_t num = 0, left = total_size;
buf = g_malloc0(65536);
@@ -1636,6 +1646,10 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
break;
}
case PREALLOC_MODE_OFF:
+ if (ftruncate(fd, total_size) != 0) {
+ result = -errno;
+ error_setg_errno(errp, -result, "Could not resize file");
+ }
break;
default:
result = -EINVAL;
diff --git a/block/io.c b/block/io.c
index d5c45447fd..8f38d46de0 100644
--- a/block/io.c
+++ b/block/io.c
@@ -925,9 +925,11 @@ bdrv_driver_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
return drv->bdrv_co_pwritev_compressed(bs, offset, bytes, qiov);
}
-static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
+static int coroutine_fn bdrv_co_do_copy_on_readv(BdrvChild *child,
int64_t offset, unsigned int bytes, QEMUIOVector *qiov)
{
+ BlockDriverState *bs = child->bs;
+
/* Perform I/O through a temporary buffer so that users who scribble over
* their read buffer while the operation is in progress do not end up
* modifying the image file. This is critical for zero-copy guest I/O
@@ -943,6 +945,8 @@ static int coroutine_fn bdrv_co_do_copy_on_readv(BlockDriverState *bs,
size_t skip_bytes;
int ret;
+ assert(child->perm & (BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE));
+
/* Cover entire cluster so no additional backing file I/O is required when
* allocating cluster in the image file.
*/
@@ -1001,10 +1005,11 @@ err:
* handles copy on read, zeroing after EOF, and fragmentation of large
* reads; any other features must be implemented by the caller.
*/
-static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
+static int coroutine_fn bdrv_aligned_preadv(BdrvChild *child,
BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
int64_t align, QEMUIOVector *qiov, int flags)
{
+ BlockDriverState *bs = child->bs;
int64_t total_bytes, max_bytes;
int ret = 0;
uint64_t bytes_remaining = bytes;
@@ -1050,7 +1055,7 @@ static int coroutine_fn bdrv_aligned_preadv(BlockDriverState *bs,
}
if (!ret || pnum != nb_sectors) {
- ret = bdrv_co_do_copy_on_readv(bs, offset, bytes, qiov);
+ ret = bdrv_co_do_copy_on_readv(child, offset, bytes, qiov);
goto out;
}
}
@@ -1158,7 +1163,7 @@ int coroutine_fn bdrv_co_preadv(BdrvChild *child,
}
tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_READ);
- ret = bdrv_aligned_preadv(bs, &req, offset, bytes, align,
+ ret = bdrv_aligned_preadv(child, &req, offset, bytes, align,
use_local_qiov ? &local_qiov : qiov,
flags);
tracked_request_end(&req);
@@ -1306,10 +1311,11 @@ fail:
* Forwards an already correctly aligned write request to the BlockDriver,
* after possibly fragmenting it.
*/
-static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
+static int coroutine_fn bdrv_aligned_pwritev(BdrvChild *child,
BdrvTrackedRequest *req, int64_t offset, unsigned int bytes,
int64_t align, QEMUIOVector *qiov, int flags)
{
+ BlockDriverState *bs = child->bs;
BlockDriver *drv = bs->drv;
bool waited;
int ret;
@@ -1332,6 +1338,8 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
assert(!waited || !req->serialising);
assert(req->overlap_offset <= offset);
assert(offset + bytes <= req->overlap_offset + req->overlap_bytes);
+ assert(child->perm & BLK_PERM_WRITE);
+ assert(end_sector <= bs->total_sectors || child->perm & BLK_PERM_RESIZE);
ret = notifier_with_return_list_notify(&bs->before_write_notifiers, req);
@@ -1397,12 +1405,13 @@ static int coroutine_fn bdrv_aligned_pwritev(BlockDriverState *bs,
return ret;
}
-static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
+static int coroutine_fn bdrv_co_do_zero_pwritev(BdrvChild *child,
int64_t offset,
unsigned int bytes,
BdrvRequestFlags flags,
BdrvTrackedRequest *req)
{
+ BlockDriverState *bs = child->bs;
uint8_t *buf = NULL;
QEMUIOVector local_qiov;
struct iovec iov;
@@ -1430,7 +1439,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
mark_request_serialising(req, align);
wait_serialising_requests(req);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
- ret = bdrv_aligned_preadv(bs, req, offset & ~(align - 1), align,
+ ret = bdrv_aligned_preadv(child, req, offset & ~(align - 1), align,
align, &local_qiov, 0);
if (ret < 0) {
goto fail;
@@ -1438,7 +1447,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_HEAD);
memset(buf + head_padding_bytes, 0, zero_bytes);
- ret = bdrv_aligned_pwritev(bs, req, offset & ~(align - 1), align,
+ ret = bdrv_aligned_pwritev(child, req, offset & ~(align - 1), align,
align, &local_qiov,
flags & ~BDRV_REQ_ZERO_WRITE);
if (ret < 0) {
@@ -1452,7 +1461,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
if (bytes >= align) {
/* Write the aligned part in the middle. */
uint64_t aligned_bytes = bytes & ~(align - 1);
- ret = bdrv_aligned_pwritev(bs, req, offset, aligned_bytes, align,
+ ret = bdrv_aligned_pwritev(child, req, offset, aligned_bytes, align,
NULL, flags);
if (ret < 0) {
goto fail;
@@ -1468,7 +1477,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
mark_request_serialising(req, align);
wait_serialising_requests(req);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
- ret = bdrv_aligned_preadv(bs, req, offset, align,
+ ret = bdrv_aligned_preadv(child, req, offset, align,
align, &local_qiov, 0);
if (ret < 0) {
goto fail;
@@ -1476,7 +1485,7 @@ static int coroutine_fn bdrv_co_do_zero_pwritev(BlockDriverState *bs,
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_AFTER_TAIL);
memset(buf, 0, bytes);
- ret = bdrv_aligned_pwritev(bs, req, offset, align, align,
+ ret = bdrv_aligned_pwritev(child, req, offset, align, align,
&local_qiov, flags & ~BDRV_REQ_ZERO_WRITE);
}
fail:
@@ -1523,7 +1532,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
tracked_request_begin(&req, bs, offset, bytes, BDRV_TRACKED_WRITE);
if (!qiov) {
- ret = bdrv_co_do_zero_pwritev(bs, offset, bytes, flags, &req);
+ ret = bdrv_co_do_zero_pwritev(child, offset, bytes, flags, &req);
goto out;
}
@@ -1542,7 +1551,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
qemu_iovec_init_external(&head_qiov, &head_iov, 1);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_HEAD);
- ret = bdrv_aligned_preadv(bs, &req, offset & ~(align - 1), align,
+ ret = bdrv_aligned_preadv(child, &req, offset & ~(align - 1), align,
align, &head_qiov, 0);
if (ret < 0) {
goto fail;
@@ -1584,8 +1593,8 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
qemu_iovec_init_external(&tail_qiov, &tail_iov, 1);
bdrv_debug_event(bs, BLKDBG_PWRITEV_RMW_TAIL);
- ret = bdrv_aligned_preadv(bs, &req, (offset + bytes) & ~(align - 1), align,
- align, &tail_qiov, 0);
+ ret = bdrv_aligned_preadv(child, &req, (offset + bytes) & ~(align - 1),
+ align, align, &tail_qiov, 0);
if (ret < 0) {
goto fail;
}
@@ -1603,7 +1612,7 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
bytes = ROUND_UP(bytes, align);
}
- ret = bdrv_aligned_pwritev(bs, &req, offset, bytes, align,
+ ret = bdrv_aligned_pwritev(child, &req, offset, bytes, align,
use_local_qiov ? &local_qiov : qiov,
flags);
diff --git a/block/iscsi.c b/block/iscsi.c
index 2561be90de..76319a1a6e 100644
--- a/block/iscsi.c
+++ b/block/iscsi.c
@@ -58,6 +58,7 @@ typedef struct IscsiLun {
int events;
QEMUTimer *nop_timer;
QEMUTimer *event_timer;
+ QemuMutex mutex;
struct scsi_inquiry_logical_block_provisioning lbp;
struct scsi_inquiry_block_limits bl;
unsigned char *zeroblock;
@@ -252,6 +253,7 @@ static int iscsi_translate_sense(struct scsi_sense *sense)
return ret;
}
+/* Called (via iscsi_service) with QemuMutex held. */
static void
iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
void *command_data, void *opaque)
@@ -352,6 +354,7 @@ static const AIOCBInfo iscsi_aiocb_info = {
static void iscsi_process_read(void *arg);
static void iscsi_process_write(void *arg);
+/* Called with QemuMutex held. */
static void
iscsi_set_events(IscsiLun *iscsilun)
{
@@ -395,10 +398,10 @@ iscsi_process_read(void *arg)
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
- aio_context_acquire(iscsilun->aio_context);
+ qemu_mutex_lock(&iscsilun->mutex);
iscsi_service(iscsi, POLLIN);
iscsi_set_events(iscsilun);
- aio_context_release(iscsilun->aio_context);
+ qemu_mutex_unlock(&iscsilun->mutex);
}
static void
@@ -407,10 +410,10 @@ iscsi_process_write(void *arg)
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
- aio_context_acquire(iscsilun->aio_context);
+ qemu_mutex_lock(&iscsilun->mutex);
iscsi_service(iscsi, POLLOUT);
iscsi_set_events(iscsilun);
- aio_context_release(iscsilun->aio_context);
+ qemu_mutex_unlock(&iscsilun->mutex);
}
static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun)
@@ -589,6 +592,7 @@ iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
uint64_t lba;
uint32_t num_sectors;
bool fua = flags & BDRV_REQ_FUA;
+ int r = 0;
if (fua) {
assert(iscsilun->dpofua);
@@ -604,6 +608,7 @@ iscsi_co_writev_flags(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
lba = sector_qemu2lun(sector_num, iscsilun);
num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
+ qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsilun->use_16_for_rw) {
#if LIBISCSI_API_VERSION >= (20160603)
@@ -640,7 +645,9 @@ retry:
#endif
while (!iTask.complete) {
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
+ qemu_mutex_lock(&iscsilun->mutex);
}
if (iTask.task != NULL) {
@@ -655,12 +662,15 @@ retry:
if (iTask.status != SCSI_STATUS_GOOD) {
iscsi_allocmap_set_invalid(iscsilun, sector_num, nb_sectors);
- return iTask.err_code;
+ r = iTask.err_code;
+ goto out_unlock;
}
iscsi_allocmap_set_allocated(iscsilun, sector_num, nb_sectors);
- return 0;
+out_unlock:
+ qemu_mutex_unlock(&iscsilun->mutex);
+ return r;
}
@@ -693,18 +703,21 @@ static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
goto out;
}
+ qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsi_get_lba_status_task(iscsilun->iscsi, iscsilun->lun,
sector_qemu2lun(sector_num, iscsilun),
8 + 16, iscsi_co_generic_cb,
&iTask) == NULL) {
ret = -ENOMEM;
- goto out;
+ goto out_unlock;
}
while (!iTask.complete) {
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
+ qemu_mutex_lock(&iscsilun->mutex);
}
if (iTask.do_retry) {
@@ -721,20 +734,20 @@ retry:
* because the device is busy or the cmd is not
* supported) we pretend all blocks are allocated
* for backwards compatibility */
- goto out;
+ goto out_unlock;
}
lbas = scsi_datain_unmarshall(iTask.task);
if (lbas == NULL) {
ret = -EIO;
- goto out;
+ goto out_unlock;
}
lbasd = &lbas->descriptors[0];
if (sector_qemu2lun(sector_num, iscsilun) != lbasd->lba) {
ret = -EIO;
- goto out;
+ goto out_unlock;
}
*pnum = sector_lun2qemu(lbasd->num_blocks, iscsilun);
@@ -756,6 +769,8 @@ retry:
if (*pnum > nb_sectors) {
*pnum = nb_sectors;
}
+out_unlock:
+ qemu_mutex_unlock(&iscsilun->mutex);
out:
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
@@ -818,6 +833,7 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
+ qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsilun->use_16_for_rw) {
#if LIBISCSI_API_VERSION >= (20160603)
@@ -855,7 +871,9 @@ retry:
#endif
while (!iTask.complete) {
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
+ qemu_mutex_lock(&iscsilun->mutex);
}
if (iTask.task != NULL) {
@@ -867,6 +885,7 @@ retry:
iTask.complete = 0;
goto retry;
}
+ qemu_mutex_unlock(&iscsilun->mutex);
if (iTask.status != SCSI_STATUS_GOOD) {
return iTask.err_code;
@@ -881,6 +900,7 @@ static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
struct IscsiTask iTask;
iscsi_co_init_iscsitask(iscsilun, &iTask);
+ qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
0, iscsi_co_generic_cb, &iTask) == NULL) {
@@ -889,7 +909,9 @@ retry:
while (!iTask.complete) {
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
+ qemu_mutex_lock(&iscsilun->mutex);
}
if (iTask.task != NULL) {
@@ -901,6 +923,7 @@ retry:
iTask.complete = 0;
goto retry;
}
+ qemu_mutex_unlock(&iscsilun->mutex);
if (iTask.status != SCSI_STATUS_GOOD) {
return iTask.err_code;
@@ -910,6 +933,7 @@ retry:
}
#ifdef __linux__
+/* Called (via iscsi_service) with QemuMutex held. */
static void
iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
void *command_data, void *opaque)
@@ -1034,6 +1058,7 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
acb->task->expxferlen = acb->ioh->dxfer_len;
data.size = 0;
+ qemu_mutex_lock(&iscsilun->mutex);
if (acb->task->xfer_dir == SCSI_XFER_WRITE) {
if (acb->ioh->iovec_count == 0) {
data.data = acb->ioh->dxferp;
@@ -1049,6 +1074,7 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
iscsi_aio_ioctl_cb,
(data.size > 0) ? &data : NULL,
acb) != 0) {
+ qemu_mutex_unlock(&iscsilun->mutex);
scsi_free_scsi_task(acb->task);
qemu_aio_unref(acb);
return NULL;
@@ -1068,6 +1094,7 @@ static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
}
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
return &acb->common;
}
@@ -1092,6 +1119,7 @@ coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
struct unmap_list list;
+ int r = 0;
if (!is_byte_request_lun_aligned(offset, count, iscsilun)) {
return -ENOTSUP;
@@ -1106,15 +1134,19 @@ coroutine_fn iscsi_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
list.num = count / iscsilun->block_size;
iscsi_co_init_iscsitask(iscsilun, &iTask);
+ qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsi_unmap_task(iscsilun->iscsi, iscsilun->lun, 0, 0, &list, 1,
iscsi_co_generic_cb, &iTask) == NULL) {
- return -ENOMEM;
+ r = -ENOMEM;
+ goto out_unlock;
}
while (!iTask.complete) {
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
+ qemu_mutex_lock(&iscsilun->mutex);
}
if (iTask.task != NULL) {
@@ -1131,17 +1163,20 @@ retry:
/* the target might fail with a check condition if it
is not happy with the alignment of the UNMAP request
we silently fail in this case */
- return 0;
+ goto out_unlock;
}
if (iTask.status != SCSI_STATUS_GOOD) {
- return iTask.err_code;
+ r = iTask.err_code;
+ goto out_unlock;
}
iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
count >> BDRV_SECTOR_BITS);
- return 0;
+out_unlock:
+ qemu_mutex_unlock(&iscsilun->mutex);
+ return r;
}
static int
@@ -1153,6 +1188,7 @@ coroutine_fn iscsi_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
uint64_t lba;
uint32_t nb_blocks;
bool use_16_for_ws = iscsilun->use_16_for_rw;
+ int r = 0;
if (!is_byte_request_lun_aligned(offset, count, iscsilun)) {
return -ENOTSUP;
@@ -1186,6 +1222,7 @@ coroutine_fn iscsi_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
}
}
+ qemu_mutex_lock(&iscsilun->mutex);
iscsi_co_init_iscsitask(iscsilun, &iTask);
retry:
if (use_16_for_ws) {
@@ -1205,7 +1242,9 @@ retry:
while (!iTask.complete) {
iscsi_set_events(iscsilun);
+ qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
+ qemu_mutex_lock(&iscsilun->mutex);
}
if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
@@ -1215,7 +1254,8 @@ retry:
/* WRITE SAME is not supported by the target */
iscsilun->has_write_same = false;
scsi_free_scsi_task(iTask.task);
- return -ENOTSUP;
+ r = -ENOTSUP;
+ goto out_unlock;
}
if (iTask.task != NULL) {
@@ -1231,7 +1271,8 @@ retry:
if (iTask.status != SCSI_STATUS_GOOD) {
iscsi_allocmap_set_invalid(iscsilun, offset >> BDRV_SECTOR_BITS,
count >> BDRV_SECTOR_BITS);
- return iTask.err_code;
+ r = iTask.err_code;
+ goto out_unlock;
}
if (flags & BDRV_REQ_MAY_UNMAP) {
@@ -1242,32 +1283,19 @@ retry:
count >> BDRV_SECTOR_BITS);
}
- return 0;
+out_unlock:
+ qemu_mutex_unlock(&iscsilun->mutex);
+ return r;
}
-static void parse_chap(struct iscsi_context *iscsi, const char *target,
+static void apply_chap(struct iscsi_context *iscsi, QemuOpts *opts,
Error **errp)
{
- QemuOptsList *list;
- QemuOpts *opts;
const char *user = NULL;
const char *password = NULL;
const char *secretid;
char *secret = NULL;
- list = qemu_find_opts("iscsi");
- if (!list) {
- return;
- }
-
- opts = qemu_opts_find(list, target);
- if (opts == NULL) {
- opts = QTAILQ_FIRST(&list->head);
- if (!opts) {
- return;
- }
- }
-
user = qemu_opt_get(opts, "user");
if (!user) {
return;
@@ -1298,64 +1326,36 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
g_free(secret);
}
-static void parse_header_digest(struct iscsi_context *iscsi, const char *target,
+static void apply_header_digest(struct iscsi_context *iscsi, QemuOpts *opts,
Error **errp)
{
- QemuOptsList *list;
- QemuOpts *opts;
const char *digest = NULL;
- list = qemu_find_opts("iscsi");
- if (!list) {
- return;
- }
-
- opts = qemu_opts_find(list, target);
- if (opts == NULL) {
- opts = QTAILQ_FIRST(&list->head);
- if (!opts) {
- return;
- }
- }
-
digest = qemu_opt_get(opts, "header-digest");
if (!digest) {
- return;
- }
-
- if (!strcmp(digest, "CRC32C")) {
+ iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
+ } else if (!strcmp(digest, "crc32c")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_CRC32C);
- } else if (!strcmp(digest, "NONE")) {
+ } else if (!strcmp(digest, "none")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE);
- } else if (!strcmp(digest, "CRC32C-NONE")) {
+ } else if (!strcmp(digest, "crc32c-none")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_CRC32C_NONE);
- } else if (!strcmp(digest, "NONE-CRC32C")) {
+ } else if (!strcmp(digest, "none-crc32c")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
} else {
error_setg(errp, "Invalid header-digest setting : %s", digest);
}
}
-static char *parse_initiator_name(const char *target)
+static char *get_initiator_name(QemuOpts *opts)
{
- QemuOptsList *list;
- QemuOpts *opts;
const char *name;
char *iscsi_name;
UuidInfo *uuid_info;
- list = qemu_find_opts("iscsi");
- if (list) {
- opts = qemu_opts_find(list, target);
- if (!opts) {
- opts = QTAILQ_FIRST(&list->head);
- }
- if (opts) {
- name = qemu_opt_get(opts, "initiator-name");
- if (name) {
- return g_strdup(name);
- }
- }
+ name = qemu_opt_get(opts, "initiator-name");
+ if (name) {
+ return g_strdup(name);
}
uuid_info = qmp_query_uuid(NULL);
@@ -1370,34 +1370,11 @@ static char *parse_initiator_name(const char *target)
return iscsi_name;
}
-static int parse_timeout(const char *target)
-{
- QemuOptsList *list;
- QemuOpts *opts;
- const char *timeout;
-
- list = qemu_find_opts("iscsi");
- if (list) {
- opts = qemu_opts_find(list, target);
- if (!opts) {
- opts = QTAILQ_FIRST(&list->head);
- }
- if (opts) {
- timeout = qemu_opt_get(opts, "timeout");
- if (timeout) {
- return atoi(timeout);
- }
- }
- }
-
- return 0;
-}
-
static void iscsi_nop_timed_event(void *opaque)
{
IscsiLun *iscsilun = opaque;
- aio_context_acquire(iscsilun->aio_context);
+ qemu_mutex_lock(&iscsilun->mutex);
if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) {
error_report("iSCSI: NOP timeout. Reconnecting...");
iscsilun->request_timed_out = true;
@@ -1410,7 +1387,7 @@ static void iscsi_nop_timed_event(void *opaque)
iscsi_set_events(iscsilun);
out:
- aio_context_release(iscsilun->aio_context);
+ qemu_mutex_unlock(&iscsilun->mutex);
}
static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
@@ -1483,20 +1460,6 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
}
}
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
- .name = "iscsi",
- .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
- .desc = {
- {
- .name = "filename",
- .type = QEMU_OPT_STRING,
- .help = "URL to the iscsi image",
- },
- { /* end of list */ }
- },
-};
-
static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi, int lun,
int evpd, int pc, void **inq, Error **errp)
{
@@ -1614,24 +1577,178 @@ out:
}
}
+static void iscsi_parse_iscsi_option(const char *target, QDict *options)
+{
+ QemuOptsList *list;
+ QemuOpts *opts;
+ const char *user, *password, *password_secret, *initiator_name,
+ *header_digest, *timeout;
+
+ list = qemu_find_opts("iscsi");
+ if (!list) {
+ return;
+ }
+
+ opts = qemu_opts_find(list, target);
+ if (opts == NULL) {
+ opts = QTAILQ_FIRST(&list->head);
+ if (!opts) {
+ return;
+ }
+ }
+
+ user = qemu_opt_get(opts, "user");
+ if (user) {
+ qdict_set_default_str(options, "user", user);
+ }
+
+ password = qemu_opt_get(opts, "password");
+ if (password) {
+ qdict_set_default_str(options, "password", password);
+ }
+
+ password_secret = qemu_opt_get(opts, "password-secret");
+ if (password_secret) {
+ qdict_set_default_str(options, "password-secret", password_secret);
+ }
+
+ initiator_name = qemu_opt_get(opts, "initiator-name");
+ if (initiator_name) {
+ qdict_set_default_str(options, "initiator-name", initiator_name);
+ }
+
+ header_digest = qemu_opt_get(opts, "header-digest");
+ if (header_digest) {
+ /* -iscsi takes upper case values, but QAPI only supports lower case
+ * enum constant names, so we have to convert here. */
+ char *qapi_value = g_ascii_strdown(header_digest, -1);
+ qdict_set_default_str(options, "header-digest", qapi_value);
+ g_free(qapi_value);
+ }
+
+ timeout = qemu_opt_get(opts, "timeout");
+ if (timeout) {
+ qdict_set_default_str(options, "timeout", timeout);
+ }
+}
+
/*
* We support iscsi url's on the form
* iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
*/
+static void iscsi_parse_filename(const char *filename, QDict *options,
+ Error **errp)
+{
+ struct iscsi_url *iscsi_url;
+ const char *transport_name;
+ char *lun_str;
+
+ iscsi_url = iscsi_parse_full_url(NULL, filename);
+ if (iscsi_url == NULL) {
+ error_setg(errp, "Failed to parse URL : %s", filename);
+ return;
+ }
+
+#if LIBISCSI_API_VERSION >= (20160603)
+ switch (iscsi_url->transport) {
+ case TCP_TRANSPORT:
+ transport_name = "tcp";
+ break;
+ case ISER_TRANSPORT:
+ transport_name = "iser";
+ break;
+ default:
+ error_setg(errp, "Unknown transport type (%d)",
+ iscsi_url->transport);
+ return;
+ }
+#else
+ transport_name = "tcp";
+#endif
+
+ qdict_set_default_str(options, "transport", transport_name);
+ qdict_set_default_str(options, "portal", iscsi_url->portal);
+ qdict_set_default_str(options, "target", iscsi_url->target);
+
+ lun_str = g_strdup_printf("%d", iscsi_url->lun);
+ qdict_set_default_str(options, "lun", lun_str);
+ g_free(lun_str);
+
+ /* User/password from -iscsi take precedence over those from the URL */
+ iscsi_parse_iscsi_option(iscsi_url->target, options);
+
+ if (iscsi_url->user[0] != '\0') {
+ qdict_set_default_str(options, "user", iscsi_url->user);
+ qdict_set_default_str(options, "password", iscsi_url->passwd);
+ }
+
+ iscsi_destroy_url(iscsi_url);
+}
+
+static QemuOptsList runtime_opts = {
+ .name = "iscsi",
+ .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+ .desc = {
+ {
+ .name = "transport",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "portal",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "target",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "user",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "password",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "password-secret",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "lun",
+ .type = QEMU_OPT_NUMBER,
+ },
+ {
+ .name = "initiator-name",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "header-digest",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "timeout",
+ .type = QEMU_OPT_NUMBER,
+ },
+ { /* end of list */ }
+ },
+};
+
static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
IscsiLun *iscsilun = bs->opaque;
struct iscsi_context *iscsi = NULL;
- struct iscsi_url *iscsi_url = NULL;
struct scsi_task *task = NULL;
struct scsi_inquiry_standard *inq = NULL;
struct scsi_inquiry_supported_pages *inq_vpd;
char *initiator_name = NULL;
QemuOpts *opts;
Error *local_err = NULL;
- const char *filename;
- int i, ret = 0, timeout = 0;
+ const char *transport_name, *portal, *target;
+#if LIBISCSI_API_VERSION >= (20160603)
+ enum iscsi_transport_type transport;
+#endif
+ int i, ret = 0, timeout = 0, lun;
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -1641,18 +1758,34 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
goto out;
}
- filename = qemu_opt_get(opts, "filename");
+ transport_name = qemu_opt_get(opts, "transport");
+ portal = qemu_opt_get(opts, "portal");
+ target = qemu_opt_get(opts, "target");
+ lun = qemu_opt_get_number(opts, "lun", 0);
- iscsi_url = iscsi_parse_full_url(iscsi, filename);
- if (iscsi_url == NULL) {
- error_setg(errp, "Failed to parse URL : %s", filename);
+ if (!transport_name || !portal || !target) {
+ error_setg(errp, "Need all of transport, portal and target options");
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (!strcmp(transport_name, "tcp")) {
+#if LIBISCSI_API_VERSION >= (20160603)
+ transport = TCP_TRANSPORT;
+ } else if (!strcmp(transport_name, "iser")) {
+ transport = ISER_TRANSPORT;
+#else
+ /* TCP is what older libiscsi versions always use */
+#endif
+ } else {
+ error_setg(errp, "Unknown transport: %s", transport_name);
ret = -EINVAL;
goto out;
}
memset(iscsilun, 0, sizeof(IscsiLun));
- initiator_name = parse_initiator_name(iscsi_url->target);
+ initiator_name = get_initiator_name(opts);
iscsi = iscsi_create_context(initiator_name);
if (iscsi == NULL) {
@@ -1661,30 +1794,20 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
goto out;
}
#if LIBISCSI_API_VERSION >= (20160603)
- if (iscsi_init_transport(iscsi, iscsi_url->transport)) {
+ if (iscsi_init_transport(iscsi, transport)) {
error_setg(errp, ("Error initializing transport."));
ret = -EINVAL;
goto out;
}
#endif
- if (iscsi_set_targetname(iscsi, iscsi_url->target)) {
+ if (iscsi_set_targetname(iscsi, target)) {
error_setg(errp, "iSCSI: Failed to set target name.");
ret = -EINVAL;
goto out;
}
- if (iscsi_url->user[0] != '\0') {
- ret = iscsi_set_initiator_username_pwd(iscsi, iscsi_url->user,
- iscsi_url->passwd);
- if (ret != 0) {
- error_setg(errp, "Failed to set initiator username and password");
- ret = -EINVAL;
- goto out;
- }
- }
-
/* check if we got CHAP username/password via the options */
- parse_chap(iscsi, iscsi_url->target, &local_err);
+ apply_chap(iscsi, opts, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
ret = -EINVAL;
@@ -1697,10 +1820,8 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
goto out;
}
- iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
-
/* check if we got HEADER_DIGEST via the options */
- parse_header_digest(iscsi, iscsi_url->target, &local_err);
+ apply_header_digest(iscsi, opts, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
ret = -EINVAL;
@@ -1708,7 +1829,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
}
/* timeout handling is broken in libiscsi before 1.15.0 */
- timeout = parse_timeout(iscsi_url->target);
+ timeout = qemu_opt_get_number(opts, "timeout", 0);
#if LIBISCSI_API_VERSION >= 20150621
iscsi_set_timeout(iscsi, timeout);
#else
@@ -1717,7 +1838,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
}
#endif
- if (iscsi_full_connect_sync(iscsi, iscsi_url->portal, iscsi_url->lun) != 0) {
+ if (iscsi_full_connect_sync(iscsi, portal, lun) != 0) {
error_setg(errp, "iSCSI: Failed to connect to LUN : %s",
iscsi_get_error(iscsi));
ret = -EINVAL;
@@ -1726,7 +1847,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
iscsilun->iscsi = iscsi;
iscsilun->aio_context = bdrv_get_aio_context(bs);
- iscsilun->lun = iscsi_url->lun;
+ iscsilun->lun = lun;
iscsilun->has_write_same = true;
task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 0, 0,
@@ -1812,6 +1933,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
scsi_free_scsi_task(task);
task = NULL;
+ qemu_mutex_init(&iscsilun->mutex);
iscsi_attach_aio_context(bs, iscsilun->aio_context);
/* Guess the internal cluster (page) size of the iscsi target by the means
@@ -1829,9 +1951,6 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
out:
qemu_opts_del(opts);
g_free(initiator_name);
- if (iscsi_url != NULL) {
- iscsi_destroy_url(iscsi_url);
- }
if (task != NULL) {
scsi_free_scsi_task(task);
}
@@ -1860,6 +1979,7 @@ static void iscsi_close(BlockDriverState *bs)
iscsi_destroy_context(iscsi);
g_free(iscsilun->zeroblock);
iscsi_allocmap_free(iscsilun);
+ qemu_mutex_destroy(&iscsilun->mutex);
memset(iscsilun, 0, sizeof(IscsiLun));
}
@@ -2040,15 +2160,15 @@ static BlockDriver bdrv_iscsi = {
.format_name = "iscsi",
.protocol_name = "iscsi",
- .instance_size = sizeof(IscsiLun),
- .bdrv_needs_filename = true,
- .bdrv_file_open = iscsi_open,
- .bdrv_close = iscsi_close,
- .bdrv_create = iscsi_create,
- .create_opts = &iscsi_create_opts,
- .bdrv_reopen_prepare = iscsi_reopen_prepare,
- .bdrv_reopen_commit = iscsi_reopen_commit,
- .bdrv_invalidate_cache = iscsi_invalidate_cache,
+ .instance_size = sizeof(IscsiLun),
+ .bdrv_parse_filename = iscsi_parse_filename,
+ .bdrv_file_open = iscsi_open,
+ .bdrv_close = iscsi_close,
+ .bdrv_create = iscsi_create,
+ .create_opts = &iscsi_create_opts,
+ .bdrv_reopen_prepare = iscsi_reopen_prepare,
+ .bdrv_reopen_commit = iscsi_reopen_commit,
+ .bdrv_invalidate_cache = iscsi_invalidate_cache,
.bdrv_getlength = iscsi_getlength,
.bdrv_get_info = iscsi_get_info,
@@ -2075,15 +2195,15 @@ static BlockDriver bdrv_iser = {
.format_name = "iser",
.protocol_name = "iser",
- .instance_size = sizeof(IscsiLun),
- .bdrv_needs_filename = true,
- .bdrv_file_open = iscsi_open,
- .bdrv_close = iscsi_close,
- .bdrv_create = iscsi_create,
- .create_opts = &iscsi_create_opts,
- .bdrv_reopen_prepare = iscsi_reopen_prepare,
- .bdrv_reopen_commit = iscsi_reopen_commit,
- .bdrv_invalidate_cache = iscsi_invalidate_cache,
+ .instance_size = sizeof(IscsiLun),
+ .bdrv_parse_filename = iscsi_parse_filename,
+ .bdrv_file_open = iscsi_open,
+ .bdrv_close = iscsi_close,
+ .bdrv_create = iscsi_create,
+ .create_opts = &iscsi_create_opts,
+ .bdrv_reopen_prepare = iscsi_reopen_prepare,
+ .bdrv_reopen_commit = iscsi_reopen_commit,
+ .bdrv_invalidate_cache = iscsi_invalidate_cache,
.bdrv_getlength = iscsi_getlength,
.bdrv_get_info = iscsi_get_info,
diff --git a/block/mirror.c b/block/mirror.c
index 698a54e50f..57f26c33a4 100644
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -38,7 +38,10 @@ typedef struct MirrorBlockJob {
BlockJob common;
RateLimit limit;
BlockBackend *target;
+ BlockDriverState *mirror_top_bs;
+ BlockDriverState *source;
BlockDriverState *base;
+
/* The name of the graph node to replace */
char *replaces;
/* The BDS to replace */
@@ -69,6 +72,7 @@ typedef struct MirrorBlockJob {
bool waiting_for_io;
int target_cluster_sectors;
int max_iov;
+ bool initial_zeroing_ongoing;
} MirrorBlockJob;
typedef struct MirrorOp {
@@ -117,9 +121,10 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
if (s->cow_bitmap) {
bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
}
- s->common.offset += (uint64_t)op->nb_sectors * BDRV_SECTOR_SIZE;
+ if (!s->initial_zeroing_ongoing) {
+ s->common.offset += (uint64_t)op->nb_sectors * BDRV_SECTOR_SIZE;
+ }
}
-
qemu_iovec_destroy(&op->qiov);
g_free(op);
@@ -325,7 +330,7 @@ static void mirror_do_zero_or_discard(MirrorBlockJob *s,
static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
{
- BlockDriverState *source = blk_bs(s->common.blk);
+ BlockDriverState *source = s->source;
int64_t sector_num, first_chunk;
uint64_t delay_ns = 0;
/* At least the first dirty chunk is mirrored in one iteration. */
@@ -384,7 +389,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
nb_chunks * sectors_per_chunk);
bitmap_set(s->in_flight_bitmap, sector_num / sectors_per_chunk, nb_chunks);
while (nb_chunks > 0 && sector_num < end) {
- int ret;
+ int64_t ret;
int io_sectors, io_sectors_acct;
BlockDriverState *file;
enum MirrorMethod {
@@ -495,12 +500,30 @@ static void mirror_exit(BlockJob *job, void *opaque)
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
- BlockDriverState *src = blk_bs(s->common.blk);
+ BlockDriverState *src = s->source;
BlockDriverState *target_bs = blk_bs(s->target);
+ BlockDriverState *mirror_top_bs = s->mirror_top_bs;
+ Error *local_err = NULL;
/* Make sure that the source BDS doesn't go away before we called
* block_job_completed(). */
bdrv_ref(src);
+ bdrv_ref(mirror_top_bs);
+
+ /* We don't access the source any more. Dropping any WRITE/RESIZE is
+ * required before it could become a backing file of target_bs. */
+ bdrv_child_try_set_perm(mirror_top_bs->backing, 0, BLK_PERM_ALL,
+ &error_abort);
+ if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
+ BlockDriverState *backing = s->is_none_mode ? src : s->base;
+ if (backing_bs(target_bs) != backing) {
+ bdrv_set_backing_hd(target_bs, backing, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ data->ret = -EPERM;
+ }
+ }
+ }
if (s->to_replace) {
replace_aio_context = bdrv_get_aio_context(s->to_replace);
@@ -522,10 +545,6 @@ static void mirror_exit(BlockJob *job, void *opaque)
bdrv_drained_begin(target_bs);
bdrv_replace_in_backing_chain(to_replace, target_bs);
bdrv_drained_end(target_bs);
-
- /* We just changed the BDS the job BB refers to */
- blk_remove_bs(job->blk);
- blk_insert_bs(job->blk, src);
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
@@ -538,9 +557,26 @@ static void mirror_exit(BlockJob *job, void *opaque)
g_free(s->replaces);
blk_unref(s->target);
s->target = NULL;
+
+ /* Remove the mirror filter driver from the graph. Before this, get rid of
+ * the blockers on the intermediate nodes so that the resulting state is
+ * valid. */
+ block_job_remove_all_bdrv(job);
+ bdrv_replace_in_backing_chain(mirror_top_bs, backing_bs(mirror_top_bs));
+
+ /* We just changed the BDS the job BB refers to (with either or both of the
+ * bdrv_replace_in_backing_chain() calls), so switch the BB back so the
+ * cleanup does the right thing. We don't need any permissions any more
+ * now. */
+ blk_remove_bs(job->blk);
+ blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
+ blk_insert_bs(job->blk, mirror_top_bs, &error_abort);
+
block_job_completed(&s->common, data->ret);
+
g_free(data);
bdrv_drained_end(src);
+ bdrv_unref(mirror_top_bs);
bdrv_unref(src);
}
@@ -560,7 +596,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
{
int64_t sector_num, end;
BlockDriverState *base = s->base;
- BlockDriverState *bs = blk_bs(s->common.blk);
+ BlockDriverState *bs = s->source;
BlockDriverState *target_bs = blk_bs(s->target);
int ret, n;
@@ -572,6 +608,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
return 0;
}
+ s->initial_zeroing_ongoing = true;
for (sector_num = 0; sector_num < end; ) {
int nb_sectors = MIN(end - sector_num,
QEMU_ALIGN_DOWN(INT_MAX, s->granularity) >> BDRV_SECTOR_BITS);
@@ -579,6 +616,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
mirror_throttle(s);
if (block_job_is_cancelled(&s->common)) {
+ s->initial_zeroing_ongoing = false;
return 0;
}
@@ -593,6 +631,7 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
}
mirror_wait_for_all_io(s);
+ s->initial_zeroing_ongoing = false;
}
/* First part, loop on the sectors and initialize the dirty bitmap. */
@@ -639,7 +678,7 @@ static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
MirrorExitData *data;
- BlockDriverState *bs = blk_bs(s->common.blk);
+ BlockDriverState *bs = s->source;
BlockDriverState *target_bs = blk_bs(s->target);
bool need_drain = true;
int64_t length;
@@ -657,7 +696,28 @@ static void coroutine_fn mirror_run(void *opaque)
if (s->bdev_length < 0) {
ret = s->bdev_length;
goto immediate_exit;
- } else if (s->bdev_length == 0) {
+ }
+
+ /* Active commit must resize the base image if its size differs from the
+ * active layer. */
+ if (s->base == blk_bs(s->target)) {
+ int64_t base_length;
+
+ base_length = blk_getlength(s->target);
+ if (base_length < 0) {
+ ret = base_length;
+ goto immediate_exit;
+ }
+
+ if (s->bdev_length > base_length) {
+ ret = blk_truncate(s->target, s->bdev_length);
+ if (ret < 0) {
+ goto immediate_exit;
+ }
+ }
+ }
+
+ if (s->bdev_length == 0) {
/* Report BLOCK_JOB_READY and wait for complete. */
block_job_event_ready(&s->common);
s->synced = true;
@@ -850,9 +910,8 @@ static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
static void mirror_complete(BlockJob *job, Error **errp)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
- BlockDriverState *src, *target;
+ BlockDriverState *target;
- src = blk_bs(job->blk);
target = blk_bs(s->target);
if (!s->synced) {
@@ -884,6 +943,10 @@ static void mirror_complete(BlockJob *job, Error **errp)
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
+ /* TODO Translate this into permission system. Current definition of
+ * GRAPH_MOD would require to request it for the parents; they might
+ * not even be BlockDriverStates, however, so a BdrvChild can't address
+ * them. May need redefinition of GRAPH_MOD. */
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
@@ -892,13 +955,6 @@ static void mirror_complete(BlockJob *job, Error **errp)
aio_context_release(replace_aio_context);
}
- if (s->backing_mode == MIRROR_SOURCE_BACKING_CHAIN) {
- BlockDriverState *backing = s->is_none_mode ? src : s->base;
- if (backing_bs(target) != backing) {
- bdrv_set_backing_hd(target, backing);
- }
- }
-
s->should_complete = true;
block_job_enter(&s->common);
}
@@ -954,6 +1010,77 @@ static const BlockJobDriver commit_active_job_driver = {
.drain = mirror_drain,
};
+static int coroutine_fn bdrv_mirror_top_preadv(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+ return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_pwritev(BlockDriverState *bs,
+ uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+ return bdrv_co_pwritev(bs->backing, offset, bytes, qiov, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_flush(BlockDriverState *bs)
+{
+ return bdrv_co_flush(bs->backing->bs);
+}
+
+static int64_t coroutine_fn bdrv_mirror_top_get_block_status(
+ BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,
+ BlockDriverState **file)
+{
+ *pnum = nb_sectors;
+ *file = bs->backing->bs;
+ return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
+ (sector_num << BDRV_SECTOR_BITS);
+}
+
+static int coroutine_fn bdrv_mirror_top_pwrite_zeroes(BlockDriverState *bs,
+ int64_t offset, int count, BdrvRequestFlags flags)
+{
+ return bdrv_co_pwrite_zeroes(bs->backing, offset, count, flags);
+}
+
+static int coroutine_fn bdrv_mirror_top_pdiscard(BlockDriverState *bs,
+ int64_t offset, int count)
+{
+ return bdrv_co_pdiscard(bs->backing->bs, offset, count);
+}
+
+static void bdrv_mirror_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_mirror_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+ const BdrvChildRole *role,
+ uint64_t perm, uint64_t shared,
+ uint64_t *nperm, uint64_t *nshared)
+{
+ /* Must be able to forward guest writes to the real image */
+ *nperm = 0;
+ if (perm & BLK_PERM_WRITE) {
+ *nperm |= BLK_PERM_WRITE;
+ }
+
+ *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_mirror_top = {
+ .format_name = "mirror_top",
+ .bdrv_co_preadv = bdrv_mirror_top_preadv,
+ .bdrv_co_pwritev = bdrv_mirror_top_pwritev,
+ .bdrv_co_pwrite_zeroes = bdrv_mirror_top_pwrite_zeroes,
+ .bdrv_co_pdiscard = bdrv_mirror_top_pdiscard,
+ .bdrv_co_flush = bdrv_mirror_top_flush,
+ .bdrv_co_get_block_status = bdrv_mirror_top_get_block_status,
+ .bdrv_close = bdrv_mirror_top_close,
+ .bdrv_child_perm = bdrv_mirror_top_child_perm,
+};
+
static void mirror_start_job(const char *job_id, BlockDriverState *bs,
int creation_flags, BlockDriverState *target,
const char *replaces, int64_t speed,
@@ -966,9 +1093,14 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
void *opaque, Error **errp,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base,
- bool auto_complete)
+ bool auto_complete, const char *filter_node_name)
{
MirrorBlockJob *s;
+ BlockDriverState *mirror_top_bs;
+ bool target_graph_mod;
+ bool target_is_backing;
+ Error *local_err = NULL;
+ int ret;
if (granularity == 0) {
granularity = bdrv_get_default_bitmap_granularity(target);
@@ -985,14 +1117,62 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
buf_size = DEFAULT_MIRROR_BUF_SIZE;
}
- s = block_job_create(job_id, driver, bs, speed, creation_flags,
- cb, opaque, errp);
- if (!s) {
+ /* In the case of active commit, add dummy driver to provide consistent
+ * reads on the top, while disabling it in the intermediate nodes, and make
+ * the backing chain writable. */
+ mirror_top_bs = bdrv_new_open_driver(&bdrv_mirror_top, filter_node_name,
+ BDRV_O_RDWR, errp);
+ if (mirror_top_bs == NULL) {
return;
}
+ mirror_top_bs->total_sectors = bs->total_sectors;
+
+ /* bdrv_append takes ownership of the mirror_top_bs reference, need to keep
+ * it alive until block_job_create() even if bs has no parent. */
+ bdrv_ref(mirror_top_bs);
+ bdrv_drained_begin(bs);
+ bdrv_append(mirror_top_bs, bs, &local_err);
+ bdrv_drained_end(bs);
- s->target = blk_new();
- blk_insert_bs(s->target, target);
+ if (local_err) {
+ bdrv_unref(mirror_top_bs);
+ error_propagate(errp, local_err);
+ return;
+ }
+
+ /* Make sure that the source is not resized while the job is running */
+ s = block_job_create(job_id, driver, mirror_top_bs,
+ BLK_PERM_CONSISTENT_READ,
+ BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+ BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD, speed,
+ creation_flags, cb, opaque, errp);
+ bdrv_unref(mirror_top_bs);
+ if (!s) {
+ goto fail;
+ }
+ s->source = bs;
+ s->mirror_top_bs = mirror_top_bs;
+
+ /* No resize for the target either; while the mirror is still running, a
+ * consistent read isn't necessarily possible. We could possibly allow
+ * writes and graph modifications, though it would likely defeat the
+ * purpose of a mirror, so leave them blocked for now.
+ *
+ * In the case of active commit, things look a bit different, though,
+ * because the target is an already populated backing file in active use.
+ * We can allow anything except resize there.*/
+ target_is_backing = bdrv_chain_contains(bs, target);
+ target_graph_mod = (backing_mode != MIRROR_LEAVE_BACKING_CHAIN);
+ s->target = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE |
+ (target_graph_mod ? BLK_PERM_GRAPH_MOD : 0),
+ BLK_PERM_WRITE_UNCHANGED |
+ (target_is_backing ? BLK_PERM_CONSISTENT_READ |
+ BLK_PERM_WRITE |
+ BLK_PERM_GRAPH_MOD : 0));
+ ret = blk_insert_bs(s->target, target, errp);
+ if (ret < 0) {
+ goto fail;
+ }
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
@@ -1015,18 +1195,40 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
return;
}
- block_job_add_bdrv(&s->common, target);
+ /* Required permissions are already taken with blk_new() */
+ block_job_add_bdrv(&s->common, "target", target, 0, BLK_PERM_ALL,
+ &error_abort);
+
/* In commit_active_start() all intermediate nodes disappear, so
* any jobs in them must be blocked */
- if (bdrv_chain_contains(bs, target)) {
+ if (target_is_backing) {
BlockDriverState *iter;
for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
- block_job_add_bdrv(&s->common, 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 (== target). */
+ ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+ BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+ errp);
+ if (ret < 0) {
+ goto fail;
+ }
}
}
trace_mirror_start(bs, s, opaque);
block_job_start(&s->common);
+ return;
+
+fail:
+ if (s) {
+ g_free(s->replaces);
+ blk_unref(s->target);
+ block_job_unref(&s->common);
+ }
+
+ bdrv_replace_in_backing_chain(mirror_top_bs, backing_bs(mirror_top_bs));
}
void mirror_start(const char *job_id, BlockDriverState *bs,
@@ -1035,7 +1237,7 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
MirrorSyncMode mode, BlockMirrorBackingMode backing_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
- bool unmap, Error **errp)
+ bool unmap, const char *filter_node_name, Error **errp)
{
bool is_none_mode;
BlockDriverState *base;
@@ -1049,18 +1251,18 @@ void mirror_start(const char *job_id, BlockDriverState *bs,
mirror_start_job(job_id, bs, BLOCK_JOB_DEFAULT, target, replaces,
speed, granularity, buf_size, backing_mode,
on_source_error, on_target_error, unmap, NULL, NULL, errp,
- &mirror_job_driver, is_none_mode, base, false);
+ &mirror_job_driver, is_none_mode, base, false,
+ filter_node_name);
}
void commit_active_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *base, int creation_flags,
int64_t speed, BlockdevOnError on_error,
+ const char *filter_node_name,
BlockCompletionFunc *cb, void *opaque, Error **errp,
bool auto_complete)
{
- int64_t length, base_length;
int orig_base_flags;
- int ret;
Error *local_err = NULL;
orig_base_flags = bdrv_get_flags(base);
@@ -1069,35 +1271,11 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
return;
}
- length = bdrv_getlength(bs);
- if (length < 0) {
- error_setg_errno(errp, -length,
- "Unable to determine length of %s", bs->filename);
- goto error_restore_flags;
- }
-
- base_length = bdrv_getlength(base);
- if (base_length < 0) {
- error_setg_errno(errp, -base_length,
- "Unable to determine length of %s", base->filename);
- goto error_restore_flags;
- }
-
- if (length > base_length) {
- ret = bdrv_truncate(base, length);
- if (ret < 0) {
- error_setg_errno(errp, -ret,
- "Top image %s is larger than base image %s, and "
- "resize of base image failed",
- bs->filename, base->filename);
- goto error_restore_flags;
- }
- }
-
mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0,
MIRROR_LEAVE_BACKING_CHAIN,
on_error, on_error, true, cb, opaque, &local_err,
- &commit_active_job_driver, false, base, auto_complete);
+ &commit_active_job_driver, false, base, auto_complete,
+ filter_node_name);
if (local_err) {
error_propagate(errp, local_err);
goto error_restore_flags;
diff --git a/block/nbd.c b/block/nbd.c
index 35f24be069..a7f9108fe5 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -537,8 +537,6 @@ static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
visit_type_SocketAddress(ov, NULL, &s->saddr, &error_abort);
visit_complete(ov, &saddr_qdict);
visit_free(ov);
- assert(qobject_type(saddr_qdict) == QTYPE_QDICT);
-
qdict_put_obj(opts, "server", saddr_qdict);
if (s->export) {
diff --git a/block/nfs.c b/block/nfs.c
index 08b43dd189..890d5d4aff 100644
--- a/block/nfs.c
+++ b/block/nfs.c
@@ -54,6 +54,7 @@ typedef struct NFSClient {
int events;
bool has_zero_init;
AioContext *aio_context;
+ QemuMutex mutex;
blkcnt_t st_blocks;
bool cache_used;
NFSServer *server;
@@ -191,6 +192,7 @@ static void nfs_parse_filename(const char *filename, QDict *options,
static void nfs_process_read(void *arg);
static void nfs_process_write(void *arg);
+/* Called with QemuMutex held. */
static void nfs_set_events(NFSClient *client)
{
int ev = nfs_which_events(client->context);
@@ -209,20 +211,20 @@ static void nfs_process_read(void *arg)
{
NFSClient *client = arg;
- aio_context_acquire(client->aio_context);
+ qemu_mutex_lock(&client->mutex);
nfs_service(client->context, POLLIN);
nfs_set_events(client);
- aio_context_release(client->aio_context);
+ qemu_mutex_unlock(&client->mutex);
}
static void nfs_process_write(void *arg)
{
NFSClient *client = arg;
- aio_context_acquire(client->aio_context);
+ qemu_mutex_lock(&client->mutex);
nfs_service(client->context, POLLOUT);
nfs_set_events(client);
- aio_context_release(client->aio_context);
+ qemu_mutex_unlock(&client->mutex);
}
static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
@@ -242,6 +244,7 @@ static void nfs_co_generic_bh_cb(void *opaque)
aio_co_wake(task->co);
}
+/* Called (via nfs_service) with QemuMutex held. */
static void
nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
void *private_data)
@@ -263,9 +266,9 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
nfs_co_generic_bh_cb, task);
}
-static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov)
+static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *iov,
+ int flags)
{
NFSClient *client = bs->opaque;
NFSRPC task;
@@ -273,14 +276,15 @@ static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
nfs_co_init_task(bs, &task);
task.iov = iov;
+ qemu_mutex_lock(&client->mutex);
if (nfs_pread_async(client->context, client->fh,
- sector_num * BDRV_SECTOR_SIZE,
- nb_sectors * BDRV_SECTOR_SIZE,
- nfs_co_generic_cb, &task) != 0) {
+ offset, bytes, nfs_co_generic_cb, &task) != 0) {
+ qemu_mutex_unlock(&client->mutex);
return -ENOMEM;
}
nfs_set_events(client);
+ qemu_mutex_unlock(&client->mutex);
while (!task.complete) {
qemu_coroutine_yield();
}
@@ -297,39 +301,50 @@ static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
return 0;
}
-static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
- int64_t sector_num, int nb_sectors,
- QEMUIOVector *iov)
+static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
+ uint64_t bytes, QEMUIOVector *iov,
+ int flags)
{
NFSClient *client = bs->opaque;
NFSRPC task;
char *buf = NULL;
+ bool my_buffer = false;
nfs_co_init_task(bs, &task);
- buf = g_try_malloc(nb_sectors * BDRV_SECTOR_SIZE);
- if (nb_sectors && buf == NULL) {
- return -ENOMEM;
+ if (iov->niov != 1) {
+ buf = g_try_malloc(bytes);
+ if (bytes && buf == NULL) {
+ return -ENOMEM;
+ }
+ qemu_iovec_to_buf(iov, 0, buf, bytes);
+ my_buffer = true;
+ } else {
+ buf = iov->iov[0].iov_base;
}
- qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
-
+ qemu_mutex_lock(&client->mutex);
if (nfs_pwrite_async(client->context, client->fh,
- sector_num * BDRV_SECTOR_SIZE,
- nb_sectors * BDRV_SECTOR_SIZE,
- buf, nfs_co_generic_cb, &task) != 0) {
- g_free(buf);
+ offset, bytes, buf,
+ nfs_co_generic_cb, &task) != 0) {
+ qemu_mutex_unlock(&client->mutex);
+ if (my_buffer) {
+ g_free(buf);
+ }
return -ENOMEM;
}
nfs_set_events(client);
+ qemu_mutex_unlock(&client->mutex);
while (!task.complete) {
qemu_coroutine_yield();
}
- g_free(buf);
+ if (my_buffer) {
+ g_free(buf);
+ }
- if (task.ret != nb_sectors * BDRV_SECTOR_SIZE) {
+ if (task.ret != bytes) {
return task.ret < 0 ? task.ret : -EIO;
}
@@ -343,12 +358,15 @@ static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
nfs_co_init_task(bs, &task);
+ qemu_mutex_lock(&client->mutex);
if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
&task) != 0) {
+ qemu_mutex_unlock(&client->mutex);
return -ENOMEM;
}
nfs_set_events(client);
+ qemu_mutex_unlock(&client->mutex);
while (!task.complete) {
qemu_coroutine_yield();
}
@@ -434,6 +452,7 @@ static void nfs_file_close(BlockDriverState *bs)
{
NFSClient *client = bs->opaque;
nfs_client_close(client);
+ qemu_mutex_destroy(&client->mutex);
}
static NFSServer *nfs_config(QDict *options, Error **errp)
@@ -641,6 +660,7 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
if (ret < 0) {
return ret;
}
+ qemu_mutex_init(&client->mutex);
bs->total_sectors = ret;
ret = 0;
return ret;
@@ -696,6 +716,7 @@ static int nfs_has_zero_init(BlockDriverState *bs)
return client->has_zero_init;
}
+/* Called (via nfs_service) with QemuMutex held. */
static void
nfs_get_allocated_file_size_cb(int ret, struct nfs_context *nfs, void *data,
void *private_data)
@@ -805,8 +826,6 @@ static void nfs_refresh_filename(BlockDriverState *bs, QDict *options)
ov = qobject_output_visitor_new(&server_qdict);
visit_type_NFSServer(ov, NULL, &client->server, &error_abort);
visit_complete(ov, &server_qdict);
- assert(qobject_type(server_qdict) == QTYPE_QDICT);
-
qdict_put_obj(opts, "server", server_qdict);
qdict_put(opts, "path", qstring_from_str(client->path));
@@ -863,8 +882,8 @@ static BlockDriver bdrv_nfs = {
.bdrv_create = nfs_file_create,
.bdrv_reopen_prepare = nfs_reopen_prepare,
- .bdrv_co_readv = nfs_co_readv,
- .bdrv_co_writev = nfs_co_writev,
+ .bdrv_co_preadv = nfs_co_preadv,
+ .bdrv_co_pwritev = nfs_co_pwritev,
.bdrv_co_flush_to_disk = nfs_co_flush,
.bdrv_detach_aio_context = nfs_detach_aio_context,
diff --git a/block/parallels.c b/block/parallels.c
index 2ccefa7d85..19935e29a9 100644
--- a/block/parallels.c
+++ b/block/parallels.c
@@ -215,7 +215,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
s->data_end << BDRV_SECTOR_BITS,
space << BDRV_SECTOR_BITS, 0);
} else {
- ret = bdrv_truncate(bs->file->bs,
+ ret = bdrv_truncate(bs->file,
(s->data_end + space) << BDRV_SECTOR_BITS);
}
if (ret < 0) {
@@ -449,7 +449,7 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
size - res->image_end_offset);
res->leaks += count;
if (fix & BDRV_FIX_LEAKS) {
- ret = bdrv_truncate(bs->file->bs, res->image_end_offset);
+ ret = bdrv_truncate(bs->file, res->image_end_offset);
if (ret < 0) {
res->check_errors++;
return ret;
@@ -488,7 +488,8 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
}
file = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (file == NULL) {
error_propagate(errp, local_err);
return -EIO;
@@ -581,6 +582,12 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
Error *local_err = NULL;
char *buf;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
if (ret < 0) {
goto fail;
@@ -681,7 +688,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
goto fail_options;
}
if (!bdrv_has_zero_init(bs->file->bs) ||
- bdrv_truncate(bs->file->bs, bdrv_getlength(bs->file->bs)) != 0) {
+ bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs)) != 0) {
s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
}
@@ -724,7 +731,7 @@ static void parallels_close(BlockDriverState *bs)
}
if (bs->open_flags & BDRV_O_RDWR) {
- bdrv_truncate(bs->file->bs, s->data_end << BDRV_SECTOR_BITS);
+ bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS);
}
g_free(s->bat_dirty_bmap);
@@ -756,6 +763,7 @@ static BlockDriver bdrv_parallels = {
.bdrv_probe = parallels_probe,
.bdrv_open = parallels_open,
.bdrv_close = parallels_close,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_co_get_block_status = parallels_co_get_block_status,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_flush_to_os = parallels_co_flush_to_os,
diff --git a/block/qapi.c b/block/qapi.c
index ac480aa93c..a40922ea26 100644
--- a/block/qapi.c
+++ b/block/qapi.c
@@ -682,7 +682,6 @@ void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
visit_type_ImageInfoSpecific(v, NULL, &info_spec, &error_abort);
visit_complete(v, &obj);
- assert(qobject_type(obj) == QTYPE_QDICT);
data = qdict_get(qobject_to_qdict(obj), "data");
dump_qobject(func_fprintf, f, 1, data);
qobject_decref(obj);
diff --git a/block/qcow.c b/block/qcow.c
index fb738fc507..9d6ac83959 100644
--- a/block/qcow.c
+++ b/block/qcow.c
@@ -106,6 +106,12 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
QCowHeader header;
Error *local_err = NULL;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
if (ret < 0) {
goto fail;
@@ -467,7 +473,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
/* round to cluster size */
cluster_offset = (cluster_offset + s->cluster_size - 1) &
~(s->cluster_size - 1);
- bdrv_truncate(bs->file->bs, cluster_offset + s->cluster_size);
+ bdrv_truncate(bs->file, cluster_offset + s->cluster_size);
/* if encrypted, we must initialize the cluster
content which won't be written */
if (bs->encrypted &&
@@ -817,7 +823,8 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
}
qcow_blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (qcow_blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -909,7 +916,7 @@ static int qcow_make_empty(BlockDriverState *bs)
if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
l1_length) < 0)
return -1;
- ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length);
+ ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
if (ret < 0)
return ret;
@@ -1046,6 +1053,7 @@ static BlockDriver bdrv_qcow = {
.bdrv_probe = qcow_probe,
.bdrv_open = qcow_open,
.bdrv_close = qcow_close,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_reopen_prepare = qcow_reopen_prepare,
.bdrv_create = qcow_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
diff --git a/block/qcow2-refcount.c b/block/qcow2-refcount.c
index 3dbde18612..9e96f64c8b 100644
--- a/block/qcow2-refcount.c
+++ b/block/qcow2-refcount.c
@@ -1734,7 +1734,7 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res,
goto resize_fail;
}
- ret = bdrv_truncate(bs->file->bs, offset + s->cluster_size);
+ ret = bdrv_truncate(bs->file, offset + s->cluster_size);
if (ret < 0) {
goto resize_fail;
}
diff --git a/block/qcow2.c b/block/qcow2.c
index 3e274bd1ba..6a92d2ef3f 100644
--- a/block/qcow2.c
+++ b/block/qcow2.c
@@ -814,8 +814,8 @@ static int qcow2_update_options(BlockDriverState *bs, QDict *options,
return ret;
}
-static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
- Error **errp)
+static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
+ Error **errp)
{
BDRVQcow2State *s = bs->opaque;
unsigned int len, i;
@@ -1205,6 +1205,18 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
return ret;
}
+static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
+ Error **errp)
+{
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
+ return qcow2_do_open(bs, options, flags, errp);
+}
+
static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
{
BDRVQcow2State *s = bs->opaque;
@@ -1785,7 +1797,7 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
options = qdict_clone_shallow(bs->options);
flags &= ~BDRV_O_INACTIVE;
- ret = qcow2_open(bs, options, flags, &local_err);
+ ret = qcow2_do_open(bs, options, flags, &local_err);
QDECREF(options);
if (local_err) {
error_propagate(errp, local_err);
@@ -2190,7 +2202,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
}
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
return -EIO;
@@ -2254,7 +2267,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
options = qdict_new();
qdict_put(options, "driver", qstring_from_str("qcow2"));
blk = blk_new_open(filename, NULL, options,
- BDRV_O_RDWR | BDRV_O_NO_FLUSH, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_NO_FLUSH,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -2570,7 +2584,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
/* align end of file to a sector boundary to ease reading with
sector based I/Os */
cluster_offset = bdrv_getlength(bs->file->bs);
- return bdrv_truncate(bs->file->bs, cluster_offset);
+ return bdrv_truncate(bs->file, cluster_offset);
}
buf = qemu_blockalign(bs, s->cluster_size);
@@ -2784,7 +2798,7 @@ static int make_completely_empty(BlockDriverState *bs)
goto fail;
}
- ret = bdrv_truncate(bs->file->bs, (3 + l1_clusters) * s->cluster_size);
+ ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size);
if (ret < 0) {
goto fail;
}
@@ -3101,6 +3115,7 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
uint64_t cluster_size = s->cluster_size;
bool encrypt;
int refcount_bits = s->refcount_bits;
+ Error *local_err = NULL;
int ret;
QemuOptDesc *desc = opts->list->desc;
Qcow2AmendHelperCBInfo helper_cb_info;
@@ -3250,7 +3265,16 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
}
if (new_size) {
- ret = bdrv_truncate(bs, new_size);
+ BlockBackend *blk = blk_new(BLK_PERM_RESIZE, BLK_PERM_ALL);
+ ret = blk_insert_bs(blk, bs, &local_err);
+ if (ret < 0) {
+ error_report_err(local_err);
+ blk_unref(blk);
+ return ret;
+ }
+
+ ret = blk_truncate(blk, new_size);
+ blk_unref(blk);
if (ret < 0) {
return ret;
}
@@ -3387,6 +3411,7 @@ BlockDriver bdrv_qcow2 = {
.bdrv_reopen_commit = qcow2_reopen_commit,
.bdrv_reopen_abort = qcow2_reopen_abort,
.bdrv_join_options = qcow2_join_options,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_create = qcow2_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_get_block_status = qcow2_co_get_block_status,
diff --git a/block/qed.c b/block/qed.c
index 0b62c7799e..5ec7fd83f2 100644
--- a/block/qed.c
+++ b/block/qed.c
@@ -415,8 +415,8 @@ static void bdrv_qed_drain(BlockDriverState *bs)
}
}
-static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
- Error **errp)
+static int bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int flags,
+ Error **errp)
{
BDRVQEDState *s = bs->opaque;
QEDHeader le_header;
@@ -550,6 +550,18 @@ out:
return ret;
}
+static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
+ Error **errp)
+{
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
+ return bdrv_qed_do_open(bs, options, flags, errp);
+}
+
static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp)
{
BDRVQEDState *s = bs->opaque;
@@ -613,7 +625,8 @@ static int qed_create(const char *filename, uint32_t cluster_size,
}
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
return -EIO;
@@ -1629,7 +1642,7 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp)
bdrv_qed_close(bs);
memset(s, 0, sizeof(BDRVQEDState));
- ret = bdrv_qed_open(bs, NULL, bs->open_flags, &local_err);
+ ret = bdrv_qed_do_open(bs, NULL, bs->open_flags, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_prepend(errp, "Could not reopen qed layer: ");
@@ -1692,6 +1705,7 @@ static BlockDriver bdrv_qed = {
.bdrv_open = bdrv_qed_open,
.bdrv_close = bdrv_qed_close,
.bdrv_reopen_prepare = bdrv_qed_reopen_prepare,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_create = bdrv_qed_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_get_block_status = bdrv_qed_co_get_block_status,
diff --git a/block/quorum.c b/block/quorum.c
index 86e2072dce..40205fb1b3 100644
--- a/block/quorum.c
+++ b/block/quorum.c
@@ -1032,10 +1032,17 @@ static void quorum_add_child(BlockDriverState *bs, BlockDriverState *child_bs,
/* We can safely add the child now */
bdrv_ref(child_bs);
- child = bdrv_attach_child(bs, child_bs, indexstr, &child_format);
+
+ child = bdrv_attach_child(bs, child_bs, indexstr, &child_format, errp);
+ if (child == NULL) {
+ s->next_child_index--;
+ bdrv_unref(child_bs);
+ goto out;
+ }
s->children = g_renew(BdrvChild *, s->children, s->num_children + 1);
s->children[s->num_children++] = child;
+out:
bdrv_drained_end(bs);
}
@@ -1126,6 +1133,8 @@ static BlockDriver bdrv_quorum = {
.bdrv_add_child = quorum_add_child,
.bdrv_del_child = quorum_del_child,
+ .bdrv_child_perm = bdrv_filter_default_perms,
+
.is_filter = true,
.bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter,
};
diff --git a/block/raw-format.c b/block/raw-format.c
index 8404a82e0c..86fbc657eb 100644
--- a/block/raw-format.c
+++ b/block/raw-format.c
@@ -341,7 +341,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
s->size = offset;
offset += s->offset;
- return bdrv_truncate(bs->file->bs, offset);
+ return bdrv_truncate(bs->file, offset);
}
static int raw_media_changed(BlockDriverState *bs)
@@ -384,6 +384,12 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
BDRVRawState *s = bs->opaque;
int ret;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
bs->sg = bs->file->bs->sg;
bs->supported_write_flags = BDRV_REQ_FUA &
bs->file->bs->supported_write_flags;
@@ -461,6 +467,7 @@ BlockDriver bdrv_raw = {
.bdrv_reopen_abort = &raw_reopen_abort,
.bdrv_open = &raw_open,
.bdrv_close = &raw_close,
+ .bdrv_child_perm = bdrv_filter_default_perms,
.bdrv_create = &raw_create,
.bdrv_co_preadv = &raw_co_preadv,
.bdrv_co_pwritev = &raw_co_pwritev,
diff --git a/block/rbd.c b/block/rbd.c
index a57b3e3c5d..ee13f3d9d3 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -18,6 +18,7 @@
#include "block/block_int.h"
#include "crypto/secret.h"
#include "qemu/cutils.h"
+#include "qapi/qmp/qstring.h"
#include <rbd/librbd.h>
@@ -62,6 +63,13 @@
#define RBD_MAX_SNAP_NAME_SIZE 128
#define RBD_MAX_SNAPS 100
+/* The LIBRBD_SUPPORTS_IOVEC is defined in librbd.h */
+#ifdef LIBRBD_SUPPORTS_IOVEC
+#define LIBRBD_USE_IOVEC 1
+#else
+#define LIBRBD_USE_IOVEC 0
+#endif
+
typedef enum {
RBD_AIO_READ,
RBD_AIO_WRITE,
@@ -95,10 +103,10 @@ typedef struct BDRVRBDState {
char *snap;
} BDRVRBDState;
-static int qemu_rbd_next_tok(char *dst, int dst_len,
- char *src, char delim,
- const char *name,
- char **p, Error **errp)
+static char *qemu_rbd_next_tok(int max_len,
+ char *src, char delim,
+ const char *name,
+ char **p, Error **errp)
{
int l;
char *end;
@@ -120,17 +128,15 @@ static int qemu_rbd_next_tok(char *dst, int dst_len,
}
}
l = strlen(src);
- if (l >= dst_len) {
+ if (l >= max_len) {
error_setg(errp, "%s too long", name);
- return -EINVAL;
+ return NULL;
} else if (l == 0) {
error_setg(errp, "%s too short", name);
- return -EINVAL;
+ return NULL;
}
- pstrcpy(dst, dst_len, src);
-
- return 0;
+ return src;
}
static void qemu_rbd_unescape(char *src)
@@ -146,87 +152,134 @@ static void qemu_rbd_unescape(char *src)
*p = '\0';
}
-static int qemu_rbd_parsename(const char *filename,
- char *pool, int pool_len,
- char *snap, int snap_len,
- char *name, int name_len,
- char *conf, int conf_len,
- Error **errp)
+static void qemu_rbd_parse_filename(const char *filename, QDict *options,
+ Error **errp)
{
const char *start;
- char *p, *buf;
- int ret;
+ char *p, *buf, *keypairs;
+ char *found_str;
+ size_t max_keypair_size;
+ Error *local_err = NULL;
if (!strstart(filename, "rbd:", &start)) {
error_setg(errp, "File name must start with 'rbd:'");
- return -EINVAL;
+ return;
}
+ max_keypair_size = strlen(start) + 1;
buf = g_strdup(start);
+ keypairs = g_malloc0(max_keypair_size);
p = buf;
- *snap = '\0';
- *conf = '\0';
- ret = qemu_rbd_next_tok(pool, pool_len, p,
- '/', "pool name", &p, errp);
- if (ret < 0 || !p) {
- ret = -EINVAL;
+ found_str = qemu_rbd_next_tok(RBD_MAX_POOL_NAME_SIZE, p,
+ '/', "pool name", &p, &local_err);
+ if (local_err) {
goto done;
}
- qemu_rbd_unescape(pool);
+ if (!p) {
+ error_setg(errp, "Pool name is required");
+ goto done;
+ }
+ qemu_rbd_unescape(found_str);
+ qdict_put(options, "pool", qstring_from_str(found_str));
if (strchr(p, '@')) {
- ret = qemu_rbd_next_tok(name, name_len, p,
- '@', "object name", &p, errp);
- if (ret < 0) {
+ found_str = qemu_rbd_next_tok(RBD_MAX_IMAGE_NAME_SIZE, p,
+ '@', "object name", &p, &local_err);
+ if (local_err) {
goto done;
}
- ret = qemu_rbd_next_tok(snap, snap_len, p,
- ':', "snap name", &p, errp);
- qemu_rbd_unescape(snap);
+ qemu_rbd_unescape(found_str);
+ qdict_put(options, "image", qstring_from_str(found_str));
+
+ found_str = qemu_rbd_next_tok(RBD_MAX_SNAP_NAME_SIZE, p,
+ ':', "snap name", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
+ qemu_rbd_unescape(found_str);
+ qdict_put(options, "snapshot", qstring_from_str(found_str));
} else {
- ret = qemu_rbd_next_tok(name, name_len, p,
- ':', "object name", &p, errp);
+ found_str = qemu_rbd_next_tok(RBD_MAX_IMAGE_NAME_SIZE, p,
+ ':', "object name", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
+ qemu_rbd_unescape(found_str);
+ qdict_put(options, "image", qstring_from_str(found_str));
}
- qemu_rbd_unescape(name);
- if (ret < 0 || !p) {
+ if (!p) {
goto done;
}
- ret = qemu_rbd_next_tok(conf, conf_len, p,
- '\0', "configuration", &p, errp);
-
-done:
- g_free(buf);
- return ret;
-}
-
-static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
-{
- const char *p = conf;
+ found_str = qemu_rbd_next_tok(RBD_MAX_CONF_NAME_SIZE, p,
+ '\0', "configuration", &p, &local_err);
+ if (local_err) {
+ goto done;
+ }
- while (*p) {
- int len;
- const char *end = strchr(p, ':');
+ p = found_str;
- if (end) {
- len = end - p;
- } else {
- len = strlen(p);
+ /* The following are essentially all key/value pairs, and we treat
+ * 'id' and 'conf' a bit special. Key/value pairs may be in any order. */
+ while (p) {
+ char *name, *value;
+ name = qemu_rbd_next_tok(RBD_MAX_CONF_NAME_SIZE, p,
+ '=', "conf option name", &p, &local_err);
+ if (local_err) {
+ break;
}
- if (strncmp(p, "id=", 3) == 0) {
- len -= 3;
- strncpy(clientname, p + 3, len);
- clientname[len] = '\0';
- return clientname;
+ if (!p) {
+ error_setg(errp, "conf option %s has no value", name);
+ break;
}
- if (end == NULL) {
+
+ qemu_rbd_unescape(name);
+
+ value = qemu_rbd_next_tok(RBD_MAX_CONF_VAL_SIZE, p,
+ ':', "conf option value", &p, &local_err);
+ if (local_err) {
break;
}
- p = end + 1;
+ qemu_rbd_unescape(value);
+
+ if (!strcmp(name, "conf")) {
+ qdict_put(options, "conf", qstring_from_str(value));
+ } else if (!strcmp(name, "id")) {
+ qdict_put(options, "user" , qstring_from_str(value));
+ } else {
+ /* FIXME: This is pretty ugly, and not the right way to do this.
+ * These should be contained in a structure, and then
+ * passed explicitly as individual key/value pairs to
+ * rados. Consider this legacy code that needs to be
+ * updated. */
+ char *tmp = g_malloc0(max_keypair_size);
+ /* only use a delimiter if it is not the first keypair found */
+ /* These are sets of unknown key/value pairs we'll pass along
+ * to ceph */
+ if (keypairs[0]) {
+ snprintf(tmp, max_keypair_size, ":%s=%s", name, value);
+ pstrcat(keypairs, max_keypair_size, tmp);
+ } else {
+ snprintf(keypairs, max_keypair_size, "%s=%s", name, value);
+ }
+ g_free(tmp);
+ }
}
- return NULL;
+
+ if (keypairs[0]) {
+ qdict_put(options, "keyvalue-pairs", qstring_from_str(keypairs));
+ }
+
+
+done:
+ if (local_err) {
+ error_propagate(errp, local_err);
+ }
+ g_free(buf);
+ g_free(keypairs);
+ return;
}
@@ -249,26 +302,24 @@ static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
return 0;
}
-
-static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
- bool only_read_conf_file,
- Error **errp)
+static int qemu_rbd_set_keypairs(rados_t cluster, const char *keypairs,
+ Error **errp)
{
char *p, *buf;
- char name[RBD_MAX_CONF_NAME_SIZE];
- char value[RBD_MAX_CONF_VAL_SIZE];
+ char *name;
+ char *value;
+ Error *local_err = NULL;
int ret = 0;
- buf = g_strdup(conf);
+ buf = g_strdup(keypairs);
p = buf;
while (p) {
- ret = qemu_rbd_next_tok(name, sizeof(name), p,
- '=', "conf option name", &p, errp);
- if (ret < 0) {
+ name = qemu_rbd_next_tok(RBD_MAX_CONF_NAME_SIZE, p,
+ '=', "conf option name", &p, &local_err);
+ if (local_err) {
break;
}
- qemu_rbd_unescape(name);
if (!p) {
error_setg(errp, "conf option %s has no value", name);
@@ -276,67 +327,117 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
break;
}
- ret = qemu_rbd_next_tok(value, sizeof(value), p,
- ':', "conf option value", &p, errp);
- if (ret < 0) {
+ value = qemu_rbd_next_tok(RBD_MAX_CONF_VAL_SIZE, p,
+ ':', "conf option value", &p, &local_err);
+ if (local_err) {
break;
}
- qemu_rbd_unescape(value);
- if (strcmp(name, "conf") == 0) {
- /* read the conf file alone, so it doesn't override more
- specific settings for a particular device */
- if (only_read_conf_file) {
- ret = rados_conf_read_file(cluster, value);
- if (ret < 0) {
- error_setg_errno(errp, -ret, "error reading conf file %s",
- value);
- break;
- }
- }
- } else if (strcmp(name, "id") == 0) {
- /* ignore, this is parsed by qemu_rbd_parse_clientname() */
- } else if (!only_read_conf_file) {
- ret = rados_conf_set(cluster, name, value);
- if (ret < 0) {
- error_setg_errno(errp, -ret, "invalid conf option %s", name);
- ret = -EINVAL;
- break;
- }
+ ret = rados_conf_set(cluster, name, value);
+ if (ret < 0) {
+ error_setg_errno(errp, -ret, "invalid conf option %s", name);
+ ret = -EINVAL;
+ break;
}
}
+ if (local_err) {
+ error_propagate(errp, local_err);
+ ret = -EINVAL;
+ }
g_free(buf);
return ret;
}
+static void qemu_rbd_memset(RADOSCB *rcb, int64_t offs)
+{
+ if (LIBRBD_USE_IOVEC) {
+ RBDAIOCB *acb = rcb->acb;
+ iov_memset(acb->qiov->iov, acb->qiov->niov, offs, 0,
+ acb->qiov->size - offs);
+ } else {
+ memset(rcb->buf + offs, 0, rcb->size - offs);
+ }
+}
+
+static QemuOptsList runtime_opts = {
+ .name = "rbd",
+ .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+ .desc = {
+ {
+ .name = "filename",
+ .type = QEMU_OPT_STRING,
+ .help = "Specification of the rbd image",
+ },
+ {
+ .name = "password-secret",
+ .type = QEMU_OPT_STRING,
+ .help = "ID of secret providing the password",
+ },
+ {
+ .name = "conf",
+ .type = QEMU_OPT_STRING,
+ .help = "Rados config file location",
+ },
+ {
+ .name = "pool",
+ .type = QEMU_OPT_STRING,
+ .help = "Rados pool name",
+ },
+ {
+ .name = "image",
+ .type = QEMU_OPT_STRING,
+ .help = "Image name in the pool",
+ },
+ {
+ .name = "snapshot",
+ .type = QEMU_OPT_STRING,
+ .help = "Ceph snapshot name",
+ },
+ {
+ /* maps to 'id' in rados_create() */
+ .name = "user",
+ .type = QEMU_OPT_STRING,
+ .help = "Rados id name",
+ },
+ {
+ .name = "keyvalue-pairs",
+ .type = QEMU_OPT_STRING,
+ .help = "Legacy rados key/value option parameters",
+ },
+ {
+ .name = "host",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "port",
+ .type = QEMU_OPT_STRING,
+ },
+ {
+ .name = "auth",
+ .type = QEMU_OPT_STRING,
+ .help = "Supported authentication method, either cephx or none",
+ },
+ { /* end of list */ }
+ },
+};
+
static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
{
Error *local_err = NULL;
int64_t bytes = 0;
int64_t objsize;
int obj_order = 0;
- char pool[RBD_MAX_POOL_NAME_SIZE];
- char name[RBD_MAX_IMAGE_NAME_SIZE];
- char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
- char conf[RBD_MAX_CONF_SIZE];
- char clientname_buf[RBD_MAX_CONF_SIZE];
- char *clientname;
+ const char *pool, *name, *conf, *clientname, *keypairs;
const char *secretid;
rados_t cluster;
rados_ioctx_t io_ctx;
- int ret;
+ QDict *options = NULL;
+ QemuOpts *rbd_opts = NULL;
+ int ret = 0;
secretid = qemu_opt_get(opts, "password-secret");
- if (qemu_rbd_parsename(filename, pool, sizeof(pool),
- snap_buf, sizeof(snap_buf),
- name, sizeof(name),
- conf, sizeof(conf), &local_err) < 0) {
- error_propagate(errp, local_err);
- return -EINVAL;
- }
-
/* Read out options */
bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
@@ -344,35 +445,55 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
if (objsize) {
if ((objsize - 1) & objsize) { /* not a power of 2? */
error_setg(errp, "obj size needs to be power of 2");
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit;
}
if (objsize < 4096) {
error_setg(errp, "obj size too small");
- return -EINVAL;
+ ret = -EINVAL;
+ goto exit;
}
obj_order = ctz32(objsize);
}
- clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
+ options = qdict_new();
+ qemu_rbd_parse_filename(filename, options, &local_err);
+ if (local_err) {
+ ret = -EINVAL;
+ error_propagate(errp, local_err);
+ goto exit;
+ }
+
+ rbd_opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+ qemu_opts_absorb_qdict(rbd_opts, options, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ ret = -EINVAL;
+ goto exit;
+ }
+
+ pool = qemu_opt_get(rbd_opts, "pool");
+ conf = qemu_opt_get(rbd_opts, "conf");
+ clientname = qemu_opt_get(rbd_opts, "user");
+ name = qemu_opt_get(rbd_opts, "image");
+ keypairs = qemu_opt_get(rbd_opts, "keyvalue-pairs");
+
ret = rados_create(&cluster, clientname);
if (ret < 0) {
error_setg_errno(errp, -ret, "error initializing");
- return ret;
+ goto exit;
}
- if (strstr(conf, "conf=") == NULL) {
- /* try default location, but ignore failure */
- rados_conf_read_file(cluster, NULL);
- } else if (conf[0] != '\0' &&
- qemu_rbd_set_conf(cluster, conf, true, &local_err) < 0) {
- error_propagate(errp, local_err);
+ /* try default location when conf=NULL, but ignore failure */
+ ret = rados_conf_read_file(cluster, conf);
+ if (conf && ret < 0) {
+ error_setg_errno(errp, -ret, "error reading conf file %s", conf);
ret = -EIO;
goto shutdown;
}
- if (conf[0] != '\0' &&
- qemu_rbd_set_conf(cluster, conf, false, &local_err) < 0) {
- error_propagate(errp, local_err);
+ ret = qemu_rbd_set_keypairs(cluster, keypairs, errp);
+ if (ret < 0) {
ret = -EIO;
goto shutdown;
}
@@ -403,6 +524,10 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
shutdown:
rados_shutdown(cluster);
+
+exit:
+ QDECREF(options);
+ qemu_opts_del(rbd_opts);
return ret;
}
@@ -426,11 +551,11 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
}
} else {
if (r < 0) {
- memset(rcb->buf, 0, rcb->size);
+ qemu_rbd_memset(rcb, 0);
acb->ret = r;
acb->error = 1;
} else if (r < rcb->size) {
- memset(rcb->buf + r, 0, rcb->size - r);
+ qemu_rbd_memset(rcb, r);
if (!acb->error) {
acb->ret = rcb->size;
}
@@ -441,47 +566,116 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
g_free(rcb);
- if (acb->cmd == RBD_AIO_READ) {
- qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
+ if (!LIBRBD_USE_IOVEC) {
+ if (acb->cmd == RBD_AIO_READ) {
+ qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
+ }
+ qemu_vfree(acb->bounce);
}
- qemu_vfree(acb->bounce);
+
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
qemu_aio_unref(acb);
}
-/* TODO Convert to fine grained options */
-static QemuOptsList runtime_opts = {
- .name = "rbd",
- .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
- .desc = {
- {
- .name = "filename",
- .type = QEMU_OPT_STRING,
- .help = "Specification of the rbd image",
- },
- {
- .name = "password-secret",
- .type = QEMU_OPT_STRING,
- .help = "ID of secret providing the password",
- },
- { /* end of list */ }
- },
-};
+#define RBD_MON_HOST 0
+#define RBD_AUTH_SUPPORTED 1
+
+static char *qemu_rbd_array_opts(QDict *options, const char *prefix, int type,
+ Error **errp)
+{
+ int num_entries;
+ QemuOpts *opts = NULL;
+ QDict *sub_options;
+ const char *host;
+ const char *port;
+ char *str;
+ char *rados_str = NULL;
+ Error *local_err = NULL;
+ int i;
+
+ assert(type == RBD_MON_HOST || type == RBD_AUTH_SUPPORTED);
+
+ num_entries = qdict_array_entries(options, prefix);
+
+ if (num_entries < 0) {
+ error_setg(errp, "Parse error on RBD QDict array");
+ return NULL;
+ }
+
+ for (i = 0; i < num_entries; i++) {
+ char *strbuf = NULL;
+ const char *value;
+ char *rados_str_tmp;
+
+ str = g_strdup_printf("%s%d.", prefix, i);
+ qdict_extract_subqdict(options, &sub_options, str);
+ g_free(str);
+
+ opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+ qemu_opts_absorb_qdict(opts, sub_options, &local_err);
+ QDECREF(sub_options);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ g_free(rados_str);
+ rados_str = NULL;
+ goto exit;
+ }
+
+ if (type == RBD_MON_HOST) {
+ host = qemu_opt_get(opts, "host");
+ port = qemu_opt_get(opts, "port");
+
+ value = host;
+ if (port) {
+ /* check for ipv6 */
+ if (strchr(host, ':')) {
+ strbuf = g_strdup_printf("[%s]:%s", host, port);
+ } else {
+ strbuf = g_strdup_printf("%s:%s", host, port);
+ }
+ value = strbuf;
+ } else if (strchr(host, ':')) {
+ strbuf = g_strdup_printf("[%s]", host);
+ value = strbuf;
+ }
+ } else {
+ value = qemu_opt_get(opts, "auth");
+ }
+
+
+ /* each iteration in the for loop will build upon the string, and if
+ * rados_str is NULL then it is our first pass */
+ if (rados_str) {
+ /* separate options with ';', as that is what rados_conf_set()
+ * requires */
+ rados_str_tmp = rados_str;
+ rados_str = g_strdup_printf("%s;%s", rados_str_tmp, value);
+ g_free(rados_str_tmp);
+ } else {
+ rados_str = g_strdup(value);
+ }
+
+ g_free(strbuf);
+ qemu_opts_del(opts);
+ opts = NULL;
+ }
+
+exit:
+ qemu_opts_del(opts);
+ return rados_str;
+}
static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVRBDState *s = bs->opaque;
- char pool[RBD_MAX_POOL_NAME_SIZE];
- char snap_buf[RBD_MAX_SNAP_NAME_SIZE];
- char conf[RBD_MAX_CONF_SIZE];
- char clientname_buf[RBD_MAX_CONF_SIZE];
- char *clientname;
+ const char *pool, *snap, *conf, *clientname, *name, *keypairs;
const char *secretid;
QemuOpts *opts;
Error *local_err = NULL;
- const char *filename;
+ char *mon_host = NULL;
+ char *auth_supported = NULL;
int r;
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
@@ -492,41 +686,63 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
return -EINVAL;
}
- filename = qemu_opt_get(opts, "filename");
- secretid = qemu_opt_get(opts, "password-secret");
+ auth_supported = qemu_rbd_array_opts(options, "auth-supported.",
+ RBD_AUTH_SUPPORTED, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
+ r = -EINVAL;
+ goto failed_opts;
+ }
- if (qemu_rbd_parsename(filename, pool, sizeof(pool),
- snap_buf, sizeof(snap_buf),
- s->name, sizeof(s->name),
- conf, sizeof(conf), errp) < 0) {
+ mon_host = qemu_rbd_array_opts(options, "server.",
+ RBD_MON_HOST, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
r = -EINVAL;
goto failed_opts;
}
- clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
+ secretid = qemu_opt_get(opts, "password-secret");
+
+ pool = qemu_opt_get(opts, "pool");
+ conf = qemu_opt_get(opts, "conf");
+ snap = qemu_opt_get(opts, "snapshot");
+ clientname = qemu_opt_get(opts, "user");
+ name = qemu_opt_get(opts, "image");
+ keypairs = qemu_opt_get(opts, "keyvalue-pairs");
+
r = rados_create(&s->cluster, clientname);
if (r < 0) {
error_setg_errno(errp, -r, "error initializing");
goto failed_opts;
}
- s->snap = NULL;
- if (snap_buf[0] != '\0') {
- s->snap = g_strdup(snap_buf);
+ s->snap = g_strdup(snap);
+ if (name) {
+ pstrcpy(s->name, RBD_MAX_IMAGE_NAME_SIZE, name);
+ }
+
+ /* try default location when conf=NULL, but ignore failure */
+ r = rados_conf_read_file(s->cluster, conf);
+ if (conf && r < 0) {
+ error_setg_errno(errp, -r, "error reading conf file %s", conf);
+ goto failed_shutdown;
+ }
+
+ r = qemu_rbd_set_keypairs(s->cluster, keypairs, errp);
+ if (r < 0) {
+ goto failed_shutdown;
}
- if (strstr(conf, "conf=") == NULL) {
- /* try default location, but ignore failure */
- rados_conf_read_file(s->cluster, NULL);
- } else if (conf[0] != '\0') {
- r = qemu_rbd_set_conf(s->cluster, conf, true, errp);
+ if (mon_host) {
+ r = rados_conf_set(s->cluster, "mon_host", mon_host);
if (r < 0) {
goto failed_shutdown;
}
}
- if (conf[0] != '\0') {
- r = qemu_rbd_set_conf(s->cluster, conf, false, errp);
+ if (auth_supported) {
+ r = rados_conf_set(s->cluster, "auth_supported", auth_supported);
if (r < 0) {
goto failed_shutdown;
}
@@ -580,6 +796,8 @@ failed_shutdown:
g_free(s->snap);
failed_opts:
qemu_opts_del(opts);
+ g_free(mon_host);
+ g_free(auth_supported);
return r;
}
@@ -655,7 +873,6 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
RBDAIOCB *acb;
RADOSCB *rcb = NULL;
rbd_completion_t c;
- char *buf;
int r;
BDRVRBDState *s = bs->opaque;
@@ -664,27 +881,29 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
acb->cmd = cmd;
acb->qiov = qiov;
assert(!qiov || qiov->size == size);
- if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
- acb->bounce = NULL;
- } else {
- acb->bounce = qemu_try_blockalign(bs, qiov->size);
- if (acb->bounce == NULL) {
- goto failed;
+
+ rcb = g_new(RADOSCB, 1);
+
+ if (!LIBRBD_USE_IOVEC) {
+ if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
+ acb->bounce = NULL;
+ } else {
+ acb->bounce = qemu_try_blockalign(bs, qiov->size);
+ if (acb->bounce == NULL) {
+ goto failed;
+ }
+ }
+ if (cmd == RBD_AIO_WRITE) {
+ qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
+ rcb->buf = acb->bounce;
}
+
acb->ret = 0;
acb->error = 0;
acb->s = s;
- if (cmd == RBD_AIO_WRITE) {
- qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
- }
-
- buf = acb->bounce;
-
- rcb = g_new(RADOSCB, 1);
rcb->acb = acb;
- rcb->buf = buf;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
@@ -694,10 +913,18 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
switch (cmd) {
case RBD_AIO_WRITE:
- r = rbd_aio_write(s->image, off, size, buf, c);
+#ifdef LIBRBD_SUPPORTS_IOVEC
+ r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, off, c);
+#else
+ r = rbd_aio_write(s->image, off, size, rcb->buf, c);
+#endif
break;
case RBD_AIO_READ:
- r = rbd_aio_read(s->image, off, size, buf, c);
+#ifdef LIBRBD_SUPPORTS_IOVEC
+ r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, off, c);
+#else
+ r = rbd_aio_read(s->image, off, size, rcb->buf, c);
+#endif
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
@@ -712,14 +939,16 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
if (r < 0) {
goto failed_completion;
}
-
return &acb->common;
failed_completion:
rbd_aio_release(c);
failed:
g_free(rcb);
- qemu_vfree(acb->bounce);
+ if (!LIBRBD_USE_IOVEC) {
+ qemu_vfree(acb->bounce);
+ }
+
qemu_aio_unref(acb);
return NULL;
}
@@ -972,18 +1201,18 @@ static QemuOptsList qemu_rbd_create_opts = {
};
static BlockDriver bdrv_rbd = {
- .format_name = "rbd",
- .instance_size = sizeof(BDRVRBDState),
- .bdrv_needs_filename = true,
- .bdrv_file_open = qemu_rbd_open,
- .bdrv_close = qemu_rbd_close,
- .bdrv_create = qemu_rbd_create,
- .bdrv_has_zero_init = bdrv_has_zero_init_1,
- .bdrv_get_info = qemu_rbd_getinfo,
- .create_opts = &qemu_rbd_create_opts,
- .bdrv_getlength = qemu_rbd_getlength,
- .bdrv_truncate = qemu_rbd_truncate,
- .protocol_name = "rbd",
+ .format_name = "rbd",
+ .instance_size = sizeof(BDRVRBDState),
+ .bdrv_parse_filename = qemu_rbd_parse_filename,
+ .bdrv_file_open = qemu_rbd_open,
+ .bdrv_close = qemu_rbd_close,
+ .bdrv_create = qemu_rbd_create,
+ .bdrv_has_zero_init = bdrv_has_zero_init_1,
+ .bdrv_get_info = qemu_rbd_getinfo,
+ .create_opts = &qemu_rbd_create_opts,
+ .bdrv_getlength = qemu_rbd_getlength,
+ .bdrv_truncate = qemu_rbd_truncate,
+ .protocol_name = "rbd",
.bdrv_aio_readv = qemu_rbd_aio_readv,
.bdrv_aio_writev = qemu_rbd_aio_writev,
diff --git a/block/replication.c b/block/replication.c
index 729dd12499..22f170fd33 100644
--- a/block/replication.c
+++ b/block/replication.c
@@ -86,6 +86,12 @@ static int replication_open(BlockDriverState *bs, QDict *options,
const char *mode;
const char *top_id;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
ret = -EINVAL;
opts = qemu_opts_create(&replication_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -638,7 +644,7 @@ static void replication_stop(ReplicationState *rs, bool failover, Error **errp)
s->replication_state = BLOCK_REPLICATION_FAILOVER;
commit_active_start(NULL, s->active_disk->bs, s->secondary_disk->bs,
BLOCK_JOB_INTERNAL, 0, BLOCKDEV_ON_ERROR_REPORT,
- replication_done, bs, errp, true);
+ NULL, replication_done, bs, errp, true);
break;
default:
aio_context_release(aio_context);
@@ -654,6 +660,7 @@ BlockDriver bdrv_replication = {
.bdrv_open = replication_open,
.bdrv_close = replication_close,
+ .bdrv_child_perm = bdrv_filter_default_perms,
.bdrv_getlength = replication_getlength,
.bdrv_co_readv = replication_co_readv,
diff --git a/block/sheepdog.c b/block/sheepdog.c
index 860ba61502..743471043e 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -1609,7 +1609,7 @@ static int sd_prealloc(const char *filename, Error **errp)
int ret;
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, errp);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
if (blk == NULL) {
ret = -EIO;
goto out_with_err_set;
diff --git a/block/stream.c b/block/stream.c
index 1523ba7dfb..0113710845 100644
--- a/block/stream.c
+++ b/block/stream.c
@@ -68,6 +68,7 @@ static void stream_complete(BlockJob *job, void *opaque)
StreamCompleteData *data = opaque;
BlockDriverState *bs = blk_bs(job->blk);
BlockDriverState *base = s->base;
+ Error *local_err = NULL;
if (!block_job_is_cancelled(&s->common) && data->reached_end &&
data->ret == 0) {
@@ -79,11 +80,19 @@ static void stream_complete(BlockJob *job, void *opaque)
}
}
data->ret = bdrv_change_backing_file(bs, base_id, base_fmt);
- bdrv_set_backing_hd(bs, base);
+ bdrv_set_backing_hd(bs, base, &local_err);
+ if (local_err) {
+ error_report_err(local_err);
+ data->ret = -EPERM;
+ goto out;
+ }
}
+out:
/* Reopen the image back in read-only mode if necessary */
if (s->bs_flags != bdrv_get_flags(bs)) {
+ /* Give up write permissions before making it read-only */
+ blk_set_perm(job->blk, 0, BLK_PERM_ALL, &error_abort);
bdrv_reopen(bs, s->bs_flags, NULL);
}
@@ -229,25 +238,35 @@ void stream_start(const char *job_id, BlockDriverState *bs,
BlockDriverState *iter;
int orig_bs_flags;
- s = block_job_create(job_id, &stream_job_driver, bs, speed,
- BLOCK_JOB_DEFAULT, NULL, NULL, errp);
- if (!s) {
- return;
- }
-
/* Make sure that the image is opened in read-write mode */
orig_bs_flags = bdrv_get_flags(bs);
if (!(orig_bs_flags & BDRV_O_RDWR)) {
if (bdrv_reopen(bs, orig_bs_flags | BDRV_O_RDWR, errp) != 0) {
- block_job_unref(&s->common);
return;
}
}
- /* Block all intermediate nodes between bs and base, because they
- * will disappear from the chain after this operation */
+ /* 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. */
+ s = block_job_create(job_id, &stream_job_driver, bs,
+ BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+ BLK_PERM_GRAPH_MOD,
+ BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+ BLK_PERM_WRITE,
+ speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+ if (!s) {
+ goto fail;
+ }
+
+ /* Block all intermediate nodes between bs and base, because they will
+ * disappear from the chain after this operation. The streaming job reads
+ * every block only once, assuming that it doesn't change, so block writes
+ * and resizes. */
for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
- block_job_add_bdrv(&s->common, iter);
+ block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+ BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED,
+ &error_abort);
}
s->base = base;
@@ -257,4 +276,10 @@ void stream_start(const char *job_id, BlockDriverState *bs,
s->on_error = on_error;
trace_stream_start(bs, base, s);
block_job_start(&s->common);
+ return;
+
+fail:
+ if (orig_bs_flags != bdrv_get_flags(bs)) {
+ bdrv_reopen(bs, s->bs_flags, NULL);
+ }
}
diff --git a/block/vdi.c b/block/vdi.c
index 0aeb940aa8..9b4f70e977 100644
--- a/block/vdi.c
+++ b/block/vdi.c
@@ -363,6 +363,12 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
int ret;
Error *local_err = NULL;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
logout("\n");
ret = bdrv_read(bs->file, 0, (uint8_t *)&header, 1);
@@ -757,7 +763,8 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
}
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -885,6 +892,7 @@ static BlockDriver bdrv_vdi = {
.bdrv_open = vdi_open,
.bdrv_close = vdi_close,
.bdrv_reopen_prepare = vdi_reopen_prepare,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_create = vdi_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_get_block_status = vdi_co_get_block_status,
diff --git a/block/vhdx-log.c b/block/vhdx-log.c
index 02eb104310..67a91c0de5 100644
--- a/block/vhdx-log.c
+++ b/block/vhdx-log.c
@@ -548,7 +548,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
if (new_file_size % (1024*1024)) {
/* round up to nearest 1MB boundary */
new_file_size = ((new_file_size >> 20) + 1) << 20;
- bdrv_truncate(bs->file->bs, new_file_size);
+ bdrv_truncate(bs->file, new_file_size);
}
}
qemu_vfree(desc_entries);
diff --git a/block/vhdx.c b/block/vhdx.c
index 68db9e074e..052a753159 100644
--- a/block/vhdx.c
+++ b/block/vhdx.c
@@ -898,6 +898,12 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
uint64_t signature;
Error *local_err = NULL;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
s->bat = NULL;
s->first_visible_write = true;
@@ -1165,7 +1171,7 @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
/* per the spec, the address for a block is in units of 1MB */
*new_offset = ROUND_UP(*new_offset, 1024 * 1024);
- return bdrv_truncate(bs->file->bs, *new_offset + s->block_size);
+ return bdrv_truncate(bs->file, *new_offset + s->block_size);
}
/*
@@ -1853,7 +1859,8 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
}
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -1977,6 +1984,7 @@ static BlockDriver bdrv_vhdx = {
.bdrv_open = vhdx_open,
.bdrv_close = vhdx_close,
.bdrv_reopen_prepare = vhdx_reopen_prepare,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_co_readv = vhdx_co_readv,
.bdrv_co_writev = vhdx_co_writev,
.bdrv_create = vhdx_create,
diff --git a/block/vmdk.c b/block/vmdk.c
index 393c84d8b1..a9bd22bf93 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -943,6 +943,12 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
uint32_t magic;
Error *local_err = NULL;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
buf = vmdk_read_desc(bs->file, 0, errp);
if (!buf) {
return -EINVAL;
@@ -1697,7 +1703,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
}
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -2065,7 +2072,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
}
new_blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (new_blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -2353,6 +2361,7 @@ static BlockDriver bdrv_vmdk = {
.bdrv_open = vmdk_open,
.bdrv_check = vmdk_check,
.bdrv_reopen_prepare = vmdk_reopen_prepare,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_co_preadv = vmdk_co_preadv,
.bdrv_co_pwritev = vmdk_co_pwritev,
.bdrv_co_pwritev_compressed = vmdk_co_pwritev_compressed,
diff --git a/block/vpc.c b/block/vpc.c
index ed6353dbd4..f591d4be38 100644
--- a/block/vpc.c
+++ b/block/vpc.c
@@ -220,6 +220,12 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
int disk_type = VHD_DYNAMIC;
int ret;
+ bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
+ false, errp);
+ if (!bs->file) {
+ return -EINVAL;
+ }
+
opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
@@ -909,7 +915,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
}
blk = blk_new_open(filename, NULL, NULL,
- BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
+ BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL,
+ &local_err);
if (blk == NULL) {
error_propagate(errp, local_err);
ret = -EIO;
@@ -1061,6 +1068,7 @@ static BlockDriver bdrv_vpc = {
.bdrv_open = vpc_open,
.bdrv_close = vpc_close,
.bdrv_reopen_prepare = vpc_reopen_prepare,
+ .bdrv_child_perm = bdrv_format_default_perms,
.bdrv_create = vpc_create,
.bdrv_co_preadv = vpc_co_preadv,
diff --git a/block/vvfat.c b/block/vvfat.c
index c6bf67e8f3..aa61c329e7 100644
--- a/block/vvfat.c
+++ b/block/vvfat.c
@@ -2968,6 +2968,7 @@ static void write_target_close(BlockDriverState *bs) {
static BlockDriver vvfat_write_target = {
.format_name = "vvfat_write_target",
+ .instance_size = sizeof(void*),
.bdrv_co_pwritev = write_target_commit,
.bdrv_close = write_target_close,
};
@@ -3036,13 +3037,12 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
unlink(s->qcow_filename);
#endif
- backing = bdrv_new();
- bdrv_set_backing_hd(s->bs, backing);
- bdrv_unref(backing);
+ backing = bdrv_new_open_driver(&vvfat_write_target, NULL, BDRV_O_ALLOW_RDWR,
+ &error_abort);
+ *(void**) backing->opaque = s;
- s->bs->backing->bs->drv = &vvfat_write_target;
- s->bs->backing->bs->opaque = g_new(void *, 1);
- *(void**)s->bs->backing->bs->opaque = s;
+ bdrv_set_backing_hd(s->bs, backing, &error_abort);
+ bdrv_unref(backing);
return 0;
@@ -3052,6 +3052,27 @@ err:
return ret;
}
+static void vvfat_child_perm(BlockDriverState *bs, BdrvChild *c,
+ const BdrvChildRole *role,
+ uint64_t perm, uint64_t shared,
+ uint64_t *nperm, uint64_t *nshared)
+{
+ BDRVVVFATState *s = bs->opaque;
+
+ assert(c == s->qcow || role == &child_backing);
+
+ if (c == s->qcow) {
+ /* This is a private node, nobody should try to attach to it */
+ *nperm = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE;
+ *nshared = BLK_PERM_WRITE_UNCHANGED;
+ } else {
+ /* The backing file is there so 'commit' can use it. vvfat doesn't
+ * access it in any way. */
+ *nperm = 0;
+ *nshared = BLK_PERM_ALL;
+ }
+}
+
static void vvfat_close(BlockDriverState *bs)
{
BDRVVVFATState *s = bs->opaque;
@@ -3077,6 +3098,7 @@ static BlockDriver bdrv_vvfat = {
.bdrv_file_open = vvfat_open,
.bdrv_refresh_limits = vvfat_refresh_limits,
.bdrv_close = vvfat_close,
+ .bdrv_child_perm = vvfat_child_perm,
.bdrv_co_preadv = vvfat_co_preadv,
.bdrv_co_pwritev = vvfat_co_pwritev,
generated by cgit v1.2.3 (git 2.26.2) at 2025-01-21 00:20:06 +0000