summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorPranith Kumar K <pkarampu@redhat.com>2013-05-22 15:18:19 +0530
committerAnand Avati <avati@redhat.com>2013-06-10 13:04:21 -0700
commit2fda7a9de2edd624a03558d9a9a580e5639fef1f (patch)
treef1d13045cabeee7bd07be0110f1a58ed6a9838c4
parentbb0bbfecd609fff1a3890775b3119a552aba0e18 (diff)
cluster/afr: Perform delayed changelog wakeups for anon fdv3.4.0beta3
Problem: Nfs xlator never does open on a file for performing writes, afr does not perform changelog wakeup for this fd so operations which do metadata operations as soon as the data operations are completed perceive a delay od 'post-op-delay-secs'. Fix: Perform changelog wakeup on anon-fd if the fd with same pid is not present in inode-list. Note: This approach is a short-term fix. A proper fix needs a new domain for taking metadata locks so that data/metadata locks don't compete with each other. BUG: 966018 Change-Id: Ia9188a253e7943801b665e1b9205e2f551952d87 Signed-off-by: Pranith Kumar K <pkarampu@redhat.com> Reviewed-on: http://review.gluster.org/5067 Tested-by: Gluster Build System <jenkins@build.gluster.com> Reviewed-by: Anand Avati <avati@redhat.com>
Diffstat
-rw-r--r--libglusterfs/src/fd.c17
-rw-r--r--libglusterfs/src/fd.h3
-rw-r--r--tests/bugs/bug-966018.t33
-rw-r--r--xlators/cluster/afr/src/afr-transaction.c3
4 files changed, 56 insertions, 0 deletions
diff --git a/libglusterfs/src/fd.c b/libglusterfs/src/fd.c
index 2f4afc5e8..36cc4d056 100644
--- a/libglusterfs/src/fd.c
+++ b/libglusterfs/src/fd.c
@@ -780,6 +780,23 @@ fd_anonymous (inode_t *inode)
return fd;
}
+fd_t*
+fd_lookup_anonymous (inode_t *inode)
+{
+ fd_t *fd = NULL;
+
+ if (!inode) {
+ gf_log_callingfn ("fd", GF_LOG_WARNING, "!inode");
+ return NULL;
+ }
+
+ LOCK (&inode->lock);
+ {
+ fd = __fd_lookup_anonymous (inode);
+ }
+ UNLOCK (&inode->lock);
+ return fd;
+}
gf_boolean_t
fd_is_anonymous (fd_t *fd)
diff --git a/libglusterfs/src/fd.h b/libglusterfs/src/fd.h
index 54290b198..c1b9157d8 100644
--- a/libglusterfs/src/fd.h
+++ b/libglusterfs/src/fd.h
@@ -134,6 +134,9 @@ fd_lookup (struct _inode *inode, pid_t pid);
fd_t *
fd_lookup_uint64 (struct _inode *inode, uint64_t pid);
+fd_t*
+fd_lookup_anonymous (inode_t *inode);
+
fd_t *
fd_anonymous (inode_t *inode);
diff --git a/tests/bugs/bug-966018.t b/tests/bugs/bug-966018.t
new file mode 100644
index 000000000..f29690a1a
--- /dev/null
+++ b/tests/bugs/bug-966018.t
@@ -0,0 +1,33 @@
+#!/bin/bash
+
+. $(dirname $0)/../include.rc
+. $(dirname $0)/../volume.rc
+
+#This tests if eager-lock blocks metadata operations on nfs/fuse mounts.
+#If it is not woken up, INODELK from the next command waits
+#for post-op-delay secs.
+
+cleanup;
+TEST glusterd
+TEST pidof glusterd
+
+TEST $CLI volume create $V0 replica 2 $H0:$B0/r2_0 $H0:$B0/r2_1
+TEST $CLI volume set $V0 cluster.eager-lock on
+TEST $CLI volume set $V0 cluster.post-op-delay-secs 3
+
+TEST $CLI volume start $V0
+TEST $CLI volume profile $V0 start
+sleep 5
+TEST mount -t nfs -o vers=3,nolock $H0:/$V0 $N0;
+TEST glusterfs --entry-timeout=0 --attribute-timeout=0 -s $H0 --volfile-id=$V0 $M0
+echo 1 > $N0/1 && chmod +x $N0/1
+echo 1 > $M0/1 && chmod +x $M0/1
+
+#Check that INODELK MAX latency is not in the order of seconds
+#Test if the MAX INODELK fop latency is of the order of seconds.
+inodelk_max_latency=$($CLI volume profile $V0 info | grep INODELK | awk 'BEGIN {max = 0} {if ($6 > max) max=$6;} END {print max}' | cut -d. -f 1 | egrep "[0-9]{7,}")
+
+TEST [ -z $inodelk_max_latency ]
+TEST umount $N0
+
+cleanup;
diff --git a/xlators/cluster/afr/src/afr-transaction.c b/xlators/cluster/afr/src/afr-transaction.c
index d20928d15..a39eac9a2 100644
--- a/xlators/cluster/afr/src/afr-transaction.c
+++ b/xlators/cluster/afr/src/afr-transaction.c
@@ -1471,6 +1471,9 @@ afr_transaction (call_frame_t *frame, xlator_t *this, afr_transaction_type type)
if (!local->transaction.eager_lock_on && local->loc.inode) {
fd = fd_lookup (local->loc.inode, frame->root->pid);
+ if (fd == NULL)
+ fd = fd_lookup_anonymous (local->loc.inode);
+
if (fd) {
afr_delayed_changelog_wake_up (this, fd);
fd_unref (fd);
generated by cgit (git 2.34.1) at 2026-02-17 00:04:30 +0000
ass='add'>+{
+ qemu_co_queue_init(&bs->throttled_reqs);
+ bs->block_timer = qemu_new_timer_ns(vm_clock, bdrv_block_timer, bs);
+ bs->io_limits_enabled = true;
+}
+
+bool bdrv_io_limits_enabled(BlockDriverState *bs)
+{
+ BlockIOLimit *io_limits = &bs->io_limits;
+ return io_limits->bps[BLOCK_IO_LIMIT_READ]
+ || io_limits->bps[BLOCK_IO_LIMIT_WRITE]
+ || io_limits->bps[BLOCK_IO_LIMIT_TOTAL]
+ || io_limits->iops[BLOCK_IO_LIMIT_READ]
+ || io_limits->iops[BLOCK_IO_LIMIT_WRITE]
+ || io_limits->iops[BLOCK_IO_LIMIT_TOTAL];
+}
+
+static void bdrv_io_limits_intercept(BlockDriverState *bs,
+ bool is_write, int nb_sectors)
+{
+ int64_t wait_time = -1;
+
+ if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
+ qemu_co_queue_wait(&bs->throttled_reqs);
+ }
+
+ /* In fact, we hope to keep each request's timing, in FIFO mode. The next
+ * throttled requests will not be dequeued until the current request is
+ * allowed to be serviced. So if the current request still exceeds the
+ * limits, it will be inserted to the head. All requests followed it will
+ * be still in throttled_reqs queue.
+ */
+
+ while (bdrv_exceed_io_limits(bs, nb_sectors, is_write, &wait_time)) {
+ qemu_mod_timer(bs->block_timer,
+ wait_time + qemu_get_clock_ns(vm_clock));
+ qemu_co_queue_wait_insert_head(&bs->throttled_reqs);
+ }
+
+ qemu_co_queue_next(&bs->throttled_reqs);
+}
+
+/* check if the path starts with "<protocol>:" */
+static int path_has_protocol(const char *path)
+{
+ const char *p;
+
+#ifdef _WIN32
+ if (is_windows_drive(path) ||
+ is_windows_drive_prefix(path)) {
+ return 0;
+ }
+ p = path + strcspn(path, ":/\\");
+#else
+ p = path + strcspn(path, ":/");
+#endif
+
+ return *p == ':';
+}
+
+int path_is_absolute(const char *path)
+{
+#ifdef _WIN32
+ /* specific case for names like: "\\.\d:" */
+ if (is_windows_drive(path) || is_windows_drive_prefix(path)) {
+ return 1;
+ }
+ return (*path == '/' || *path == '\\');
+#else
+ return (*path == '/');
+#endif
+}
+
+/* if filename is absolute, just copy it to dest. Otherwise, build a
+ path to it by considering it is relative to base_path. URL are
+ supported. */
+void path_combine(char *dest, int dest_size,
+ const char *base_path,
+ const char *filename)
+{
+ const char *p, *p1;
+ int len;
+
+ if (dest_size <= 0)
+ return;
+ if (path_is_absolute(filename)) {
+ pstrcpy(dest, dest_size, filename);
+ } else {
+ p = strchr(base_path, ':');
+ if (p)
+ p++;
+ else
+ p = base_path;
+ p1 = strrchr(base_path, '/');
+#ifdef _WIN32
+ {
+ const char *p2;
+ p2 = strrchr(base_path, '\\');
+ if (!p1 || p2 > p1)
+ p1 = p2;
+ }
+#endif
+ if (p1)
+ p1++;
+ else
+ p1 = base_path;
+ if (p1 > p)
+ p = p1;
+ len = p - base_path;
+ if (len > dest_size - 1)
+ len = dest_size - 1;
+ memcpy(dest, base_path, len);
+ dest[len] = '\0';
+ pstrcat(dest, dest_size, filename);
+ }
+}
+
+void bdrv_get_full_backing_filename(BlockDriverState *bs, char *dest, size_t sz)
+{
+ if (bs->backing_file[0] == '\0' || path_has_protocol(bs->backing_file)) {
+ pstrcpy(dest, sz, bs->backing_file);
+ } else {
+ path_combine(dest, sz, bs->filename, bs->backing_file);
+ }
+}
+
+void bdrv_register(BlockDriver *bdrv)
+{
+ /* Block drivers without coroutine functions need emulation */
+ if (!bdrv->bdrv_co_readv) {
+ bdrv->bdrv_co_readv = bdrv_co_readv_em;
+ bdrv->bdrv_co_writev = bdrv_co_writev_em;
+
+ /* bdrv_co_readv_em()/brdv_co_writev_em() work in terms of aio, so if
+ * the block driver lacks aio we need to emulate that too.
+ */
+ if (!bdrv->bdrv_aio_readv) {
+ /* add AIO emulation layer */
+ bdrv->bdrv_aio_readv = bdrv_aio_readv_em;
+ bdrv->bdrv_aio_writev = bdrv_aio_writev_em;
+ }
+ }
+
+ QLIST_INSERT_HEAD(&bdrv_drivers, bdrv, list);
+}
+
+/* create a new block device (by default it is empty) */
+BlockDriverState *bdrv_new(const char *device_name)
+{
+ BlockDriverState *bs;
+
+ bs = g_malloc0(sizeof(BlockDriverState));
+ pstrcpy(bs->device_name, sizeof(bs->device_name), device_name);
+ if (device_name[0] != '\0') {
+ QTAILQ_INSERT_TAIL(&bdrv_states, bs, list);
+ }
+ bdrv_iostatus_disable(bs);
+ notifier_list_init(&bs->close_notifiers);
+ notifier_with_return_list_init(&bs->before_write_notifiers);
+
+ return bs;
+}
+
+void bdrv_add_close_notifier(BlockDriverState *bs, Notifier *notify)
+{
+ notifier_list_add(&bs->close_notifiers, notify);
+}
+
+BlockDriver *bdrv_find_format(const char *format_name)
+{
+ BlockDriver *drv1;
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (!strcmp(drv1->format_name, format_name)) {
+ return drv1;
+ }
+ }
+ return NULL;
+}
+
+static int bdrv_is_whitelisted(BlockDriver *drv, bool read_only)
+{
+ static const char *whitelist_rw[] = {
+ CONFIG_BDRV_RW_WHITELIST
+ };
+ static const char *whitelist_ro[] = {
+ CONFIG_BDRV_RO_WHITELIST
+ };
+ const char **p;
+
+ if (!whitelist_rw[0] && !whitelist_ro[0]) {
+ return 1; /* no whitelist, anything goes */
+ }
+
+ for (p = whitelist_rw; *p; p++) {
+ if (!strcmp(drv->format_name, *p)) {
+ return 1;
+ }
+ }
+ if (read_only) {
+ for (p = whitelist_ro; *p; p++) {
+ if (!strcmp(drv->format_name, *p)) {
+ return 1;
+ }
+ }
+ }
+ return 0;
+}
+
+BlockDriver *bdrv_find_whitelisted_format(const char *format_name,
+ bool read_only)
+{
+ BlockDriver *drv = bdrv_find_format(format_name);
+ return drv && bdrv_is_whitelisted(drv, read_only) ? drv : NULL;
+}
+
+typedef struct CreateCo {
+ BlockDriver *drv;
+ char *filename;
+ QEMUOptionParameter *options;
+ int ret;
+} CreateCo;
+
+static void coroutine_fn bdrv_create_co_entry(void *opaque)
+{
+ CreateCo *cco = opaque;
+ assert(cco->drv);
+
+ cco->ret = cco->drv->bdrv_create(cco->filename, cco->options);
+}
+
+int bdrv_create(BlockDriver *drv, const char* filename,
+ QEMUOptionParameter *options)
+{
+ int ret;
+
+ Coroutine *co;
+ CreateCo cco = {
+ .drv = drv,
+ .filename = g_strdup(filename),
+ .options = options,
+ .ret = NOT_DONE,
+ };
+
+ if (!drv->bdrv_create) {
+ ret = -ENOTSUP;
+ goto out;
+ }
+
+ if (qemu_in_coroutine()) {
+ /* Fast-path if already in coroutine context */
+ bdrv_create_co_entry(&cco);
+ } else {
+ co = qemu_coroutine_create(bdrv_create_co_entry);
+ qemu_coroutine_enter(co, &cco);
+ while (cco.ret == NOT_DONE) {
+ qemu_aio_wait();
+ }
+ }
+
+ ret = cco.ret;
+
+out:
+ g_free(cco.filename);
+ return ret;
+}
+
+int bdrv_create_file(const char* filename, QEMUOptionParameter *options)
+{
+ BlockDriver *drv;
+
+ drv = bdrv_find_protocol(filename, true);
+ if (drv == NULL) {
+ return -ENOENT;
+ }
+
+ return bdrv_create(drv, filename, options);
+}
+
+/*
+ * Create a uniquely-named empty temporary file.
+ * Return 0 upon success, otherwise a negative errno value.
+ */
+int get_tmp_filename(char *filename, int size)
+{
+#ifdef _WIN32
+ char temp_dir[MAX_PATH];
+ /* GetTempFileName requires that its output buffer (4th param)
+ have length MAX_PATH or greater. */
+ assert(size >= MAX_PATH);
+ return (GetTempPath(MAX_PATH, temp_dir)
+ && GetTempFileName(temp_dir, "qem", 0, filename)
+ ? 0 : -GetLastError());
+#else
+ int fd;
+ const char *tmpdir;
+ tmpdir = getenv("TMPDIR");
+ if (!tmpdir)
+ tmpdir = "/tmp";
+ if (snprintf(filename, size, "%s/vl.XXXXXX", tmpdir) >= size) {
+ return -EOVERFLOW;
+ }
+ fd = mkstemp(filename);
+ if (fd < 0) {
+ return -errno;
+ }
+ if (close(fd) != 0) {
+ unlink(filename);
+ return -errno;
+ }
+ return 0;
+#endif
+}
+
+/*
+ * Detect host devices. By convention, /dev/cdrom[N] is always
+ * recognized as a host CDROM.
+ */
+static BlockDriver *find_hdev_driver(const char *filename)
+{
+ int score_max = 0, score;
+ BlockDriver *drv = NULL, *d;
+
+ QLIST_FOREACH(d, &bdrv_drivers, list) {
+ if (d->bdrv_probe_device) {
+ score = d->bdrv_probe_device(filename);
+ if (score > score_max) {
+ score_max = score;
+ drv = d;
+ }
+ }
+ }
+
+ return drv;
+}
+
+BlockDriver *bdrv_find_protocol(const char *filename,
+ bool allow_protocol_prefix)
+{
+ BlockDriver *drv1;
+ char protocol[128];
+ int len;
+ const char *p;
+
+ /* TODO Drivers without bdrv_file_open must be specified explicitly */
+
+ /*
+ * XXX(hch): we really should not let host device detection
+ * override an explicit protocol specification, but moving this
+ * later breaks access to device names with colons in them.
+ * Thanks to the brain-dead persistent naming schemes on udev-
+ * based Linux systems those actually are quite common.
+ */
+ drv1 = find_hdev_driver(filename);
+ if (drv1) {
+ return drv1;
+ }
+
+ if (!path_has_protocol(filename) || !allow_protocol_prefix) {
+ return bdrv_find_format("file");
+ }
+
+ p = strchr(filename, ':');
+ assert(p != NULL);
+ len = p - filename;
+ if (len > sizeof(protocol) - 1)
+ len = sizeof(protocol) - 1;
+ memcpy(protocol, filename, len);
+ protocol[len] = '\0';
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (drv1->protocol_name &&
+ !strcmp(drv1->protocol_name, protocol)) {
+ return drv1;
+ }
+ }
+ return NULL;
+}
+
+static int find_image_format(BlockDriverState *bs, const char *filename,
+ BlockDriver **pdrv)
+{
+ int score, score_max;
+ BlockDriver *drv1, *drv;
+ uint8_t buf[2048];
+ int ret = 0;
+
+ /* Return the raw BlockDriver * to scsi-generic devices or empty drives */
+ if (bs->sg || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
+ drv = bdrv_find_format("raw");
+ if (!drv) {
+ ret = -ENOENT;
+ }
+ *pdrv = drv;
+ return ret;
+ }
+
+ ret = bdrv_pread(bs, 0, buf, sizeof(buf));
+ if (ret < 0) {
+ *pdrv = NULL;
+ return ret;
+ }
+
+ score_max = 0;
+ drv = NULL;
+ QLIST_FOREACH(drv1, &bdrv_drivers, list) {
+ if (drv1->bdrv_probe) {
+ score = drv1->bdrv_probe(buf, ret, filename);
+ if (score > score_max) {
+ score_max = score;
+ drv = drv1;
+ }
+ }
+ }
+ if (!drv) {
+ ret = -ENOENT;
+ }
+ *pdrv = drv;
+ return ret;
+}
+
+/**
+ * Set the current 'total_sectors' value
+ */
+static int refresh_total_sectors(BlockDriverState *bs, int64_t hint)
+{
+ BlockDriver *drv = bs->drv;
+
+ /* Do not attempt drv->bdrv_getlength() on scsi-generic devices */
+ if (bs->sg)
+ return 0;
+
+ /* query actual device if possible, otherwise just trust the hint */
+ if (drv->bdrv_getlength) {
+ int64_t length = drv->bdrv_getlength(bs);
+ if (length < 0) {
+ return length;
+ }
+ hint = length >> BDRV_SECTOR_BITS;
+ }
+
+ bs->total_sectors = hint;
+ return 0;
+}
+
+/**
+ * Set open flags for a given discard mode
+ *
+ * Return 0 on success, -1 if the discard mode was invalid.
+ */
+int bdrv_parse_discard_flags(const char *mode, int *flags)
+{
+ *flags &= ~BDRV_O_UNMAP;
+
+ if (!strcmp(mode, "off") || !strcmp(mode, "ignore")) {
+ /* do nothing */
+ } else if (!strcmp(mode, "on") || !strcmp(mode, "unmap")) {
+ *flags |= BDRV_O_UNMAP;
+ } else {
+ return -1;
+ }
+
+ return 0;
+}
+
+/**
+ * Set open flags for a given cache mode
+ *
+ * Return 0 on success, -1 if the cache mode was invalid.
+ */
+int bdrv_parse_cache_flags(const char *mode, int *flags)
+{
+ *flags &= ~BDRV_O_CACHE_MASK;
+
+ if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
+ *flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
+ } else if (!strcmp(mode, "directsync")) {
+ *flags |= BDRV_O_NOCACHE;
+ } else if (!strcmp(mode, "writeback")) {
+ *flags |= BDRV_O_CACHE_WB;
+ } else if (!strcmp(mode, "unsafe")) {
+ *flags |= BDRV_O_CACHE_WB;
+ *flags |= BDRV_O_NO_FLUSH;
+ } else if (!strcmp(mode, "writethrough")) {
+ /* this is the default */
+ } else {
+ return -1;
+ }
+
+ return 0;
+}
+
+/**
+ * The copy-on-read flag is actually a reference count so multiple users may
+ * use the feature without worrying about clobbering its previous state.
+ * Copy-on-read stays enabled until all users have called to disable it.
+ */
+void bdrv_enable_copy_on_read(BlockDriverState *bs)
+{
+ bs->copy_on_read++;
+}
+
+void bdrv_disable_copy_on_read(BlockDriverState *bs)
+{
+ assert(bs->copy_on_read > 0);
+ bs->copy_on_read--;
+}
+
+static int bdrv_open_flags(BlockDriverState *bs, int flags)
+{
+ int open_flags = flags | BDRV_O_CACHE_WB;
+
+ /*
+ * Clear flags that are internal to the block layer before opening the
+ * image.
+ */
+ open_flags &= ~(BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
+
+ /*
+ * Snapshots should be writable.
+ */
+ if (bs->is_temporary) {
+ open_flags |= BDRV_O_RDWR;
+ }
+
+ return open_flags;
+}
+
+/*
+ * Common part for opening disk images and files
+ *
+ * Removes all processed options from *options.
+ */
+static int bdrv_open_common(BlockDriverState *bs, BlockDriverState *file,
+ QDict *options, int flags, BlockDriver *drv)
+{
+ int ret, open_flags;
+ const char *filename;
+
+ assert(drv != NULL);
+ assert(bs->file == NULL);
+ assert(options != NULL && bs->options != options);
+
+ if (file != NULL) {
+ filename = file->filename;
+ } else {
+ filename = qdict_get_try_str(options, "filename");
+ }
+
+ trace_bdrv_open_common(bs, filename ?: "", flags, drv->format_name);
+
+ /* bdrv_open() with directly using a protocol as drv. This layer is already
+ * opened, so assign it to bs (while file becomes a closed BlockDriverState)
+ * and return immediately. */
+ if (file != NULL && drv->bdrv_file_open) {
+ bdrv_swap(file, bs);
+ return 0;
+ }
+
+ bs->open_flags = flags;
+ bs->buffer_alignment = 512;
+ open_flags = bdrv_open_flags(bs, flags);
+ bs->read_only = !(open_flags & BDRV_O_RDWR);
+
+ if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
+ return -ENOTSUP;
+ }
+
+ assert(bs->copy_on_read == 0); /* bdrv_new() and bdrv_close() make it so */
+ if (!bs->read_only && (flags & BDRV_O_COPY_ON_READ)) {
+ bdrv_enable_copy_on_read(bs);
+ }
+
+ if (filename != NULL) {
+ pstrcpy(bs->filename, sizeof(bs->filename), filename);
+ } else {
+ bs->filename[0] = '\0';
+ }
+
+ bs->drv = drv;
+ bs->opaque = g_malloc0(drv->instance_size);
+
+ bs->enable_write_cache = !!(flags & BDRV_O_CACHE_WB);
+
+ /* Open the image, either directly or using a protocol */
+ if (drv->bdrv_file_open) {
+ assert(file == NULL);
+ assert(drv->bdrv_parse_filename || filename != NULL);
+ ret = drv->bdrv_file_open(bs, options, open_flags);
+ } else {
+ if (file == NULL) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Can't use '%s' as a "
+ "block driver for the protocol level",
+ drv->format_name);
+ ret = -EINVAL;
+ goto free_and_fail;
+ }
+ assert(file != NULL);
+ bs->file = file;
+ ret = drv->bdrv_open(bs, options, open_flags);
+ }
+
+ if (ret < 0) {
+ goto free_and_fail;
+ }
+
+ ret = refresh_total_sectors(bs, bs->total_sectors);
+ if (ret < 0) {
+ goto free_and_fail;
+ }
+
+#ifndef _WIN32
+ if (bs->is_temporary) {
+ assert(filename != NULL);
+ unlink(filename);
+ }
+#endif
+ return 0;
+
+free_and_fail:
+ bs->file = NULL;
+ g_free(bs->opaque);
+ bs->opaque = NULL;
+ bs->drv = NULL;
+ return ret;
+}
+
+/*
+ * Opens a file using a protocol (file, host_device, nbd, ...)
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict belongs to the block layer
+ * after the call (even on failure), so if the caller intends to reuse the
+ * dictionary, it needs to use QINCREF() before calling bdrv_file_open.
+ */
+int bdrv_file_open(BlockDriverState **pbs, const char *filename,
+ QDict *options, int flags)
+{
+ BlockDriverState *bs;
+ BlockDriver *drv;
+ const char *drvname;
+ bool allow_protocol_prefix = false;
+ int ret;
+
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
+ bs = bdrv_new("");
+ bs->options = options;
+ options = qdict_clone_shallow(options);
+
+ /* Fetch the file name from the options QDict if necessary */
+ if (!filename) {
+ filename = qdict_get_try_str(options, "filename");
+ } else if (filename && !qdict_haskey(options, "filename")) {
+ qdict_put(options, "filename", qstring_from_str(filename));
+ allow_protocol_prefix = true;
+ } else {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Can't specify 'file' and "
+ "'filename' options at the same time");
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ /* Find the right block driver */
+ drvname = qdict_get_try_str(options, "driver");
+ if (drvname) {
+ drv = bdrv_find_whitelisted_format(drvname, !(flags & BDRV_O_RDWR));
+ qdict_del(options, "driver");
+ } else if (filename) {
+ drv = bdrv_find_protocol(filename, allow_protocol_prefix);
+ if (!drv) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Unknown protocol");
+ }
+ } else {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR,
+ "Must specify either driver or file");
+ drv = NULL;
+ }
+
+ if (!drv) {
+ ret = -ENOENT;
+ goto fail;
+ }
+
+ /* Parse the filename and open it */
+ if (drv->bdrv_parse_filename && filename) {
+ Error *local_err = NULL;
+ drv->bdrv_parse_filename(filename, options, &local_err);
+ if (error_is_set(&local_err)) {
+ qerror_report_err(local_err);
+ error_free(local_err);
+ ret = -EINVAL;
+ goto fail;
+ }
+ qdict_del(options, "filename");
+ } else if (!drv->bdrv_parse_filename && !filename) {
+ qerror_report(ERROR_CLASS_GENERIC_ERROR,
+ "The '%s' block driver requires a file name",
+ drv->format_name);
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ ret = bdrv_open_common(bs, NULL, options, flags, drv);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Check if any unknown options were used */
+ if (qdict_size(options) != 0) {
+ const QDictEntry *entry = qdict_first(options);
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Block protocol '%s' doesn't "
+ "support the option '%s'",
+ drv->format_name, entry->key);
+ ret = -EINVAL;
+ goto fail;
+ }
+ QDECREF(options);
+
+ bs->growable = 1;
+ *pbs = bs;
+ return 0;
+
+fail:
+ QDECREF(options);
+ if (!bs->drv) {
+ QDECREF(bs->options);
+ }
+ bdrv_delete(bs);
+ return ret;
+}
+
+/*
+ * Opens the backing file for a BlockDriverState if not yet open
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict is transferred to this
+ * function (even on failure), so if the caller intends to reuse the dictionary,
+ * it needs to use QINCREF() before calling bdrv_file_open.
+ */
+int bdrv_open_backing_file(BlockDriverState *bs, QDict *options)
+{
+ char backing_filename[PATH_MAX];
+ int back_flags, ret;
+ BlockDriver *back_drv = NULL;
+
+ if (bs->backing_hd != NULL) {
+ QDECREF(options);
+ return 0;
+ }
+
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
+ bs->open_flags &= ~BDRV_O_NO_BACKING;
+ if (qdict_haskey(options, "file.filename")) {
+ backing_filename[0] = '\0';
+ } else if (bs->backing_file[0] == '\0' && qdict_size(options) == 0) {
+ QDECREF(options);
+ return 0;
+ }
+
+ bs->backing_hd = bdrv_new("");
+ bdrv_get_full_backing_filename(bs, backing_filename,
+ sizeof(backing_filename));
+
+ if (bs->backing_format[0] != '\0') {
+ back_drv = bdrv_find_format(bs->backing_format);
+ }
+
+ /* backing files always opened read-only */
+ back_flags = bs->open_flags & ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT);
+
+ ret = bdrv_open(bs->backing_hd,
+ *backing_filename ? backing_filename : NULL, options,
+ back_flags, back_drv);
+ if (ret < 0) {
+ bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ bs->open_flags |= BDRV_O_NO_BACKING;
+ return ret;
+ }
+ return 0;
+}
+
+static void extract_subqdict(QDict *src, QDict **dst, const char *start)
+{
+ const QDictEntry *entry, *next;
+ const char *p;
+
+ *dst = qdict_new();
+ entry = qdict_first(src);
+
+ while (entry != NULL) {
+ next = qdict_next(src, entry);
+ if (strstart(entry->key, start, &p)) {
+ qobject_incref(entry->value);
+ qdict_put_obj(*dst, p, entry->value);
+ qdict_del(src, entry->key);
+ }
+ entry = next;
+ }
+}
+
+/*
+ * Opens a disk image (raw, qcow2, vmdk, ...)
+ *
+ * options is a QDict of options to pass to the block drivers, or NULL for an
+ * empty set of options. The reference to the QDict belongs to the block layer
+ * after the call (even on failure), so if the caller intends to reuse the
+ * dictionary, it needs to use QINCREF() before calling bdrv_open.
+ */
+int bdrv_open(BlockDriverState *bs, const char *filename, QDict *options,
+ int flags, BlockDriver *drv)
+{
+ int ret;
+ /* TODO: extra byte is a hack to ensure MAX_PATH space on Windows. */
+ char tmp_filename[PATH_MAX + 1];
+ BlockDriverState *file = NULL;
+ QDict *file_options = NULL;
+
+ /* NULL means an empty set of options */
+ if (options == NULL) {
+ options = qdict_new();
+ }
+
+ bs->options = options;
+ options = qdict_clone_shallow(options);
+
+ /* For snapshot=on, create a temporary qcow2 overlay */
+ if (flags & BDRV_O_SNAPSHOT) {
+ BlockDriverState *bs1;
+ int64_t total_size;
+ BlockDriver *bdrv_qcow2;
+ QEMUOptionParameter *create_options;
+ char backing_filename[PATH_MAX];
+
+ if (qdict_size(options) != 0) {
+ error_report("Can't use snapshot=on with driver-specific options");
+ ret = -EINVAL;
+ goto fail;
+ }
+ assert(filename != NULL);
+
+ /* if snapshot, we create a temporary backing file and open it
+ instead of opening 'filename' directly */
+
+ /* if there is a backing file, use it */
+ bs1 = bdrv_new("");
+ ret = bdrv_open(bs1, filename, NULL, 0, drv);
+ if (ret < 0) {
+ bdrv_delete(bs1);
+ goto fail;
+ }
+ total_size = bdrv_getlength(bs1) & BDRV_SECTOR_MASK;
+
+ bdrv_delete(bs1);
+
+ ret = get_tmp_filename(tmp_filename, sizeof(tmp_filename));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Real path is meaningless for protocols */
+ if (path_has_protocol(filename)) {
+ snprintf(backing_filename, sizeof(backing_filename),
+ "%s", filename);
+ } else if (!realpath(filename, backing_filename)) {
+ ret = -errno;
+ goto fail;
+ }
+
+ bdrv_qcow2 = bdrv_find_format("qcow2");
+ create_options = parse_option_parameters("", bdrv_qcow2->create_options,
+ NULL);
+
+ set_option_parameter_int(create_options, BLOCK_OPT_SIZE, total_size);
+ set_option_parameter(create_options, BLOCK_OPT_BACKING_FILE,
+ backing_filename);
+ if (drv) {
+ set_option_parameter(create_options, BLOCK_OPT_BACKING_FMT,
+ drv->format_name);
+ }
+
+ ret = bdrv_create(bdrv_qcow2, tmp_filename, create_options);
+ free_option_parameters(create_options);
+ if (ret < 0) {
+ goto fail;
+ }
+
+ filename = tmp_filename;
+ drv = bdrv_qcow2;
+ bs->is_temporary = 1;
+ }
+
+ /* Open image file without format layer */
+ if (flags & BDRV_O_RDWR) {
+ flags |= BDRV_O_ALLOW_RDWR;
+ }
+
+ extract_subqdict(options, &file_options, "file.");
+
+ ret = bdrv_file_open(&file, filename, file_options,
+ bdrv_open_flags(bs, flags | BDRV_O_UNMAP));
+ if (ret < 0) {
+ goto fail;
+ }
+
+ /* Find the right image format driver */
+ if (!drv) {
+ ret = find_image_format(file, filename, &drv);
+ }
+
+ if (!drv) {
+ goto unlink_and_fail;
+ }
+
+ /* Open the image */
+ ret = bdrv_open_common(bs, file, options, flags, drv);
+ if (ret < 0) {
+ goto unlink_and_fail;
+ }
+
+ if (bs->file != file) {
+ bdrv_delete(file);
+ file = NULL;
+ }
+
+ /* If there is a backing file, use it */
+ if ((flags & BDRV_O_NO_BACKING) == 0) {
+ QDict *backing_options;
+
+ extract_subqdict(options, &backing_options, "backing.");
+ ret = bdrv_open_backing_file(bs, backing_options);
+ if (ret < 0) {
+ goto close_and_fail;
+ }
+ }
+
+ /* Check if any unknown options were used */
+ if (qdict_size(options) != 0) {
+ const QDictEntry *entry = qdict_first(options);
+ qerror_report(ERROR_CLASS_GENERIC_ERROR, "Block format '%s' used by "
+ "device '%s' doesn't support the option '%s'",
+ drv->format_name, bs->device_name, entry->key);
+
+ ret = -EINVAL;
+ goto close_and_fail;
+ }
+ QDECREF(options);
+
+ if (!bdrv_key_required(bs)) {
+ bdrv_dev_change_media_cb(bs, true);
+ }
+
+ /* throttling disk I/O limits */
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_enable(bs);
+ }
+
+ return 0;
+
+unlink_and_fail:
+ if (file != NULL) {
+ bdrv_delete(file);
+ }
+ if (bs->is_temporary) {
+ unlink(filename);
+ }
+fail:
+ QDECREF(bs->options);
+ QDECREF(options);
+ bs->options = NULL;
+ return ret;
+
+close_and_fail:
+ bdrv_close(bs);
+ QDECREF(options);
+ return ret;
+}
+
+typedef struct BlockReopenQueueEntry {
+ bool prepared;
+ BDRVReopenState state;
+ QSIMPLEQ_ENTRY(BlockReopenQueueEntry) entry;
+} BlockReopenQueueEntry;
+
+/*
+ * Adds a BlockDriverState to a simple queue for an atomic, transactional
+ * reopen of multiple devices.
+ *
+ * bs_queue can either be an existing BlockReopenQueue that has had QSIMPLE_INIT
+ * already performed, or alternatively may be NULL a new BlockReopenQueue will
+ * be created and initialized. This newly created BlockReopenQueue should be
+ * passed back in for subsequent calls that are intended to be of the same
+ * atomic 'set'.
+ *
+ * bs is the BlockDriverState to add to the reopen queue.
+ *
+ * flags contains the open flags for the associated bs
+ *
+ * returns a pointer to bs_queue, which is either the newly allocated
+ * bs_queue, or the existing bs_queue being used.
+ *
+ */
+BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
+ BlockDriverState *bs, int flags)
+{
+ assert(bs != NULL);
+
+ BlockReopenQueueEntry *bs_entry;
+ if (bs_queue == NULL) {
+ bs_queue = g_new0(BlockReopenQueue, 1);
+ QSIMPLEQ_INIT(bs_queue);
+ }
+
+ if (bs->file) {
+ bdrv_reopen_queue(bs_queue, bs->file, flags);
+ }
+
+ bs_entry = g_new0(BlockReopenQueueEntry, 1);
+ QSIMPLEQ_INSERT_TAIL(bs_queue, bs_entry, entry);
+
+ bs_entry->state.bs = bs;
+ bs_entry->state.flags = flags;
+
+ return bs_queue;
+}
+
+/*
+ * Reopen multiple BlockDriverStates atomically & transactionally.
+ *
+ * The queue passed in (bs_queue) must have been built up previous
+ * via bdrv_reopen_queue().
+ *
+ * Reopens all BDS specified in the queue, with the appropriate
+ * flags. All devices are prepared for reopen, and failure of any
+ * device will cause all device changes to be abandonded, and intermediate
+ * data cleaned up.
+ *
+ * If all devices prepare successfully, then the changes are committed
+ * to all devices.
+ *
+ */
+int bdrv_reopen_multiple(BlockReopenQueue *bs_queue, Error **errp)
+{
+ int ret = -1;
+ BlockReopenQueueEntry *bs_entry, *next;
+ Error *local_err = NULL;
+
+ assert(bs_queue != NULL);
+
+ bdrv_drain_all();
+
+ QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
+ if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) {
+ error_propagate(errp, local_err);
+ goto cleanup;
+ }
+ bs_entry->prepared = true;
+ }
+
+ /* If we reach this point, we have success and just need to apply the
+ * changes
+ */
+ QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
+ bdrv_reopen_commit(&bs_entry->state);
+ }
+
+ ret = 0;
+
+cleanup:
+ QSIMPLEQ_FOREACH_SAFE(bs_entry, bs_queue, entry, next) {
+ if (ret && bs_entry->prepared) {
+ bdrv_reopen_abort(&bs_entry->state);
+ }
+ g_free(bs_entry);
+ }
+ g_free(bs_queue);
+ return ret;
+}
+
+
+/* Reopen a single BlockDriverState with the specified flags. */
+int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp)
+{
+ int ret = -1;
+ Error *local_err = NULL;
+ BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, bdrv_flags);
+
+ ret = bdrv_reopen_multiple(queue, &local_err);
+ if (local_err != NULL) {
+ error_propagate(errp, local_err);
+ }
+ return ret;
+}
+
+
+/*
+ * Prepares a BlockDriverState for reopen. All changes are staged in the
+ * 'opaque' field of the BDRVReopenState, which is used and allocated by
+ * the block driver layer .bdrv_reopen_prepare()
+ *
+ * bs is the BlockDriverState to reopen
+ * flags are the new open flags
+ * queue is the reopen queue
+ *
+ * Returns 0 on success, non-zero on error. On error errp will be set
+ * as well.
+ *
+ * On failure, bdrv_reopen_abort() will be called to clean up any data.
+ * It is the responsibility of the caller to then call the abort() or
+ * commit() for any other BDS that have been left in a prepare() state
+ *
+ */
+int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
+ Error **errp)
+{
+ int ret = -1;
+ Error *local_err = NULL;
+ BlockDriver *drv;
+
+ assert(reopen_state != NULL);
+ assert(reopen_state->bs->drv != NULL);
+ drv = reopen_state->bs->drv;
+
+ /* if we are to stay read-only, do not allow permission change
+ * to r/w */
+ if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
+ reopen_state->flags & BDRV_O_RDWR) {
+ error_set(errp, QERR_DEVICE_IS_READ_ONLY,
+ reopen_state->bs->device_name);
+ goto error;
+ }
+
+
+ ret = bdrv_flush(reopen_state->bs);
+ if (ret) {
+ error_set(errp, ERROR_CLASS_GENERIC_ERROR, "Error (%s) flushing drive",
+ strerror(-ret));
+ goto error;
+ }
+
+ if (drv->bdrv_reopen_prepare) {
+ ret = drv->bdrv_reopen_prepare(reopen_state, queue, &local_err);
+ if (ret) {
+ if (local_err != NULL) {
+ error_propagate(errp, local_err);
+ } else {
+ error_setg(errp, "failed while preparing to reopen image '%s'",
+ reopen_state->bs->filename);
+ }
+ goto error;
+ }
+ } else {
+ /* It is currently mandatory to have a bdrv_reopen_prepare()
+ * handler for each supported drv. */
+ error_set(errp, QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
+ drv->format_name, reopen_state->bs->device_name,
+ "reopening of file");
+ ret = -1;
+ goto error;
+ }
+
+ ret = 0;
+
+error:
+ return ret;
+}
+
+/*
+ * Takes the staged changes for the reopen from bdrv_reopen_prepare(), and
+ * makes them final by swapping the staging BlockDriverState contents into
+ * the active BlockDriverState contents.
+ */
+void bdrv_reopen_commit(BDRVReopenState *reopen_state)
+{
+ BlockDriver *drv;
+
+ assert(reopen_state != NULL);
+ drv = reopen_state->bs->drv;
+ assert(drv != NULL);
+
+ /* If there are any driver level actions to take */
+ if (drv->bdrv_reopen_commit) {
+ drv->bdrv_reopen_commit(reopen_state);
+ }
+
+ /* set BDS specific flags now */
+ reopen_state->bs->open_flags = reopen_state->flags;
+ reopen_state->bs->enable_write_cache = !!(reopen_state->flags &
+ BDRV_O_CACHE_WB);
+ reopen_state->bs->read_only = !(reopen_state->flags & BDRV_O_RDWR);
+}
+
+/*
+ * Abort the reopen, and delete and free the staged changes in
+ * reopen_state
+ */
+void bdrv_reopen_abort(BDRVReopenState *reopen_state)
+{
+ BlockDriver *drv;
+
+ assert(reopen_state != NULL);
+ drv = reopen_state->bs->drv;
+ assert(drv != NULL);
+
+ if (drv->bdrv_reopen_abort) {
+ drv->bdrv_reopen_abort(reopen_state);
+ }
+}
+
+
+void bdrv_close(BlockDriverState *bs)
+{
+ if (bs->job) {
+ block_job_cancel_sync(bs->job);
+ }
+ bdrv_drain_all(); /* complete I/O */
+ bdrv_flush(bs);
+ bdrv_drain_all(); /* in case flush left pending I/O */
+ notifier_list_notify(&bs->close_notifiers, bs);
+
+ if (bs->drv) {
+ if (bs->backing_hd) {
+ bdrv_delete(bs->backing_hd);
+ bs->backing_hd = NULL;
+ }
+ bs->drv->bdrv_close(bs);
+ g_free(bs->opaque);
+#ifdef _WIN32
+ if (bs->is_temporary) {
+ unlink(bs->filename);
+ }
+#endif
+ bs->opaque = NULL;
+ bs->drv = NULL;
+ bs->copy_on_read = 0;
+ bs->backing_file[0] = '\0';
+ bs->backing_format[0] = '\0';
+ bs->total_sectors = 0;
+ bs->encrypted = 0;
+ bs->valid_key = 0;
+ bs->sg = 0;
+ bs->growable = 0;
+ QDECREF(bs->options);
+ bs->options = NULL;
+
+ if (bs->file != NULL) {
+ bdrv_delete(bs->file);
+ bs->file = NULL;
+ }
+ }
+
+ bdrv_dev_change_media_cb(bs, false);
+
+ /*throttling disk I/O limits*/
+ if (bs->io_limits_enabled) {
+ bdrv_io_limits_disable(bs);
+ }
+}
+
+void bdrv_close_all(void)
+{
+ BlockDriverState *bs;
+
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ bdrv_close(bs);
+ }
+}
+
+/*
+ * Wait for pending requests to complete across all BlockDriverStates
+ *
+ * This function does not flush data to disk, use bdrv_flush_all() for that
+ * after calling this function.
+ *
+ * Note that completion of an asynchronous I/O operation can trigger any
+ * number of other I/O operations on other devices---for example a coroutine
+ * can be arbitrarily complex and a constant flow of I/O can come until the
+ * coroutine is complete. Because of this, it is not possible to have a
+ * function to drain a single device's I/O queue.
+ */
+void bdrv_drain_all(void)
+{
+ BlockDriverState *bs;
+ bool busy;
+
+ do {
+ busy = qemu_aio_wait();
+
+ /* FIXME: We do not have timer support here, so this is effectively
+ * a busy wait.
+ */
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ if (!qemu_co_queue_empty(&bs->throttled_reqs)) {
+ qemu_co_queue_restart_all(&bs->throttled_reqs);
+ busy = true;
+ }
+ }
+ } while (busy);
+
+ /* If requests are still pending there is a bug somewhere */
+ QTAILQ_FOREACH(bs, &bdrv_states, list) {
+ assert(QLIST_EMPTY(&bs->tracked_requests));
+ assert(qemu_co_queue_empty(&bs->throttled_reqs));
+ }
+}
+
+/* make a BlockDriverState anonymous by removing from bdrv_state list.
+ Also, NULL terminate the device_name to prevent double remove */
+void bdrv_make_anon(BlockDriverState *bs)
+{
+ if (bs->device_name[0] != '\0') {
+ QTAILQ_REMOVE(&bdrv_states, bs, list);
+ }
+ bs->device_name[0] = '\0';
+}
+
+static void bdrv_rebind(BlockDriverState *bs)
+{
+ if (bs->drv && bs->drv->bdrv_rebind) {
+ bs->drv->bdrv_rebind(bs);
+ }
+}
+
+static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
+ BlockDriverState *bs_src)
+{
+ /* move some fields that need to stay attached to the device */
+ bs_dest->open_flags = bs_src->open_flags;
+
+ /* dev info */
+ bs_dest->dev_ops = bs_src->dev_ops;
+ bs_dest->dev_opaque = bs_src->dev_opaque;
+ bs_dest->dev = bs_src->dev;
+ bs_dest->buffer_alignment = bs_src->buffer_alignment;
+ bs_dest->copy_on_read = bs_src->copy_on_read;
+
+ bs_dest->enable_write_cache = bs_src->enable_write_cache;
+
+ /* i/o timing parameters */
+ bs_dest->slice_start = bs_src->slice_start;
+ bs_dest->slice_end = bs_src->slice_end;
+ bs_dest->slice_submitted = bs_src->slice_submitted;
+ bs_dest->io_limits = bs_src->io_limits;
+ bs_dest->throttled_reqs = bs_src->throttled_reqs;
+ bs_dest->block_timer = bs_src->block_timer;
+ bs_dest->io_limits_enabled = bs_src->io_limits_enabled;
+
+ /* r/w error */
+ bs_dest->on_read_error = bs_src->on_read_error;
+ bs_dest->on_write_error = bs_src->on_write_error;
+
+ /* i/o status */
+ bs_dest->iostatus_enabled = bs_src->iostatus_enabled;
+ bs_dest->iostatus = bs_src->iostatus;
+
+ /* dirty bitmap */
+ bs_dest->dirty_bitmap = bs_src->dirty_bitmap;
+
+ /* job */
+ bs_dest->in_use = bs_src->in_use;
+ bs_dest->job = bs_src->job;
+
+ /* keep the same entry in bdrv_states */
+ pstrcpy(bs_dest->device_name, sizeof(bs_dest->device_name),
+ bs_src->device_name);
+ bs_dest->list = bs_src->list;
+}
+
+/*
+ * Swap bs contents for two image chains while they are live,
+ * while keeping required fields on the BlockDriverState that is
+ * actually attached to a device.
+ *
+ * This will modify the BlockDriverState fields, and swap contents
+ * between bs_new and bs_old. Both bs_new and bs_old are modified.
+ *
+ * bs_new is required to be anonymous.
+ *
+ * This function does not create any image files.
+ */
+void bdrv_swap(BlockDriverState *bs_new, BlockDriverState *bs_old)
+{
+ BlockDriverState tmp;
+
+ /* bs_new must be anonymous and shouldn't have anything fancy enabled */
+ assert(bs_new->device_name[0] == '\0');
+ assert(bs_new->dirty_bitmap == NULL);
+ assert(bs_new->job == NULL);
+ assert(bs_new->dev == NULL);
+ assert(bs_new->in_use == 0);
+ assert(bs_new->io_limits_enabled == false);
+ assert(bs_new->block_timer == NULL);
+
+ tmp = *bs_new;
+ *bs_new = *bs_old;
+ *bs_old = tmp;
+
+ /* there are some fields that should not be swapped, move them back */
+ bdrv_move_feature_fields(&tmp, bs_old);
+ bdrv_move_feature_fields(bs_old, bs_new);
+ bdrv_move_feature_fields(bs_new, &tmp);
+
+ /* bs_new shouldn't be in bdrv_states even after the swap! */
+ assert(bs_new->device_name[0] == '\0');
+
+ /* Check a few fields that should remain attached to the device */
+ assert(bs_new->dev == NULL);
+ assert(bs_new->job == NULL);
+ assert(bs_new->in_use == 0);
+ assert(bs_new->io_limits_enabled == false);
+ assert(bs_new->block_timer == NULL);
+
+ bdrv_rebind(bs_new);
+ bdrv_rebind(bs_old);
+}
+
+/*
+ * Add new bs contents at the top of an image chain while the chain is
+ * live, while keeping required fields on the top layer.
+ *
+ * This will modify the BlockDriverState fields, and swap contents
+ * between bs_new and bs_top. Both bs_new and bs_top are modified.
+ *
+ * bs_new is required to be anonymous.
+ *
+ * This function does not create any image files.
+ */
+void bdrv_append(BlockDriverState *bs_new, BlockDriverState *bs_top)
+{
+ bdrv_swap(bs_new, bs_top);
+
+ /* The contents of 'tmp' will become bs_top, as we are
+ * swapping bs_new and bs_top contents. */
+ bs_top->backing_hd = bs_new;
+ bs_top->open_flags &= ~BDRV_O_NO_BACKING;
+ pstrcpy(bs_top->backing_file, sizeof(bs_top->backing_file),
+ bs_new->filename);
+ pstrcpy(bs_top->backing_format, sizeof(bs_top->backing_format),
+ bs_new->drv ? bs_new->drv->format_name : "");
+}
+
+void bdrv_delete(BlockDriverState *bs)
+{
+ assert(!bs->dev);
+ assert(!bs->job);
+ assert(!bs->in_use);
+
+ /* remove from list, if necessary */
+ bdrv_make_anon(bs);
+
+ bdrv_close(bs);
+