Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging

Block layer patches

# gpg: Signature made Mon 31 Oct 2016 16:10:07 GMT
# gpg:                using RSA key 0x7F09B272C88F2FD6
# gpg: Good signature from "Kevin Wolf <kwolf@redhat.com>"
# Primary key fingerprint: DC3D EB15 9A9A F95D 3D74  56FE 7F09 B272 C88F 2FD6

* remotes/kevin/tags/for-upstream: (29 commits)
  qapi: allow blockdev-add for NFS
  block/nfs: Introduce runtime_opts in NFS
  block: Mention replication in BlockdevDriver enum docs
  qemu-iotests: test 'offset' and 'size' options in raw driver
  raw_bsd: add offset and size options
  qemu-iotests: Test the 'base-node' parameter of 'block-stream'
  block: Add 'base-node' parameter to the 'block-stream' command
  qemu-iotests: Test streaming to a Quorum child
  qemu-iotests: Add iotests.supports_quorum()
  qemu-iotests: Test block-stream and block-commit in parallel
  qemu-iotests: Test overlapping stream and commit operations
  qemu-iotests: Test block-stream operations in parallel
  qemu-iotests: Test streaming to an intermediate layer
  docs: Document how to stream to an intermediate layer
  block: Add QMP support for streaming to an intermediate layer
  block: Support streaming to an intermediate layer
  block: Block all intermediate nodes in commit_active_start()
  block: Block all nodes involved in the block-commit operation
  block: Check blockers in all nodes involved in a block-commit job
  block: Use block_job_add_bdrv() in backup_start()
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

block.c

@@ -1428,9 +1428,11 @@ void bdrv_set_backing_hd(BlockDriverState *bs, BlockDriverState *backing_hd)
             backing_hd->drv ? backing_hd->drv->format_name : "");
 
     bdrv_op_block_all(backing_hd, bs->backing_blocker);
-    /* Otherwise we won't be able to commit due to check in bdrv_commit */
+    /* Otherwise we won't be able to commit or stream */
     bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_COMMIT_TARGET,
                     bs->backing_blocker);
+    bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_STREAM,
+                    bs->backing_blocker);
     /*
      * We do backup in 3 ways:
      * 1. drive backup
@@ -2091,7 +2093,7 @@ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **er
     assert(bs_queue != NULL);
 
     aio_context_release(ctx);
-    bdrv_drain_all();
+    bdrv_drain_all_begin();
     aio_context_acquire(ctx);
 
     QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
@@ -2122,6 +2124,9 @@ cleanup:
         g_free(bs_entry);
     }
     g_free(bs_queue);
+
+    bdrv_drain_all_end();
+
     return ret;
 }
 

block/backup.c

@@ -446,7 +446,6 @@ static void coroutine_fn backup_run(void *opaque)
     BackupBlockJob *job = opaque;
     BackupCompleteData *data;
     BlockDriverState *bs = blk_bs(job->common.blk);
-    BlockBackend *target = job->target;
     int64_t start, end;
     int64_t sectors_per_cluster = cluster_size_sectors(job);
     int ret = 0;
@@ -533,8 +532,6 @@ static void coroutine_fn backup_run(void *opaque)
     qemu_co_rwlock_unlock(&job->flush_rwlock);
     g_free(job->done_bitmap);
 
-    bdrv_op_unblock_all(blk_bs(target), job->common.blocker);
-
     data = g_malloc(sizeof(*data));
     data->ret = ret;
     block_job_defer_to_main_loop(&job->common, backup_complete, data);
@@ -648,7 +645,7 @@ void backup_start(const char *job_id, BlockDriverState *bs,
         job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
     }
 
-    bdrv_op_block_all(target, job->common.blocker);
+    block_job_add_bdrv(&job->common, target);
     job->common.len = len;
     job->common.co = qemu_coroutine_create(backup_run, job);
     block_job_txn_add_job(txn, &job->common);

block/commit.c

@@ -216,6 +216,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     BlockReopenQueue *reopen_queue = NULL;
     int orig_overlay_flags;
     int orig_base_flags;
+    BlockDriverState *iter;
     BlockDriverState *overlay_bs;
     Error *local_err = NULL;
 
@@ -260,6 +261,19 @@ void commit_start(const char *job_id, BlockDriverState *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);
+    }
+    /* 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);
+    }
+
     s->base = blk_new();
     blk_insert_bs(s->base, base);
 

block/io.c

@@ -273,8 +273,14 @@ void bdrv_drain(BlockDriverState *bs)
  *
  * This function does not flush data to disk, use bdrv_flush_all() for that
  * after calling this function.
+ *
+ * This pauses all block jobs and disables external clients. It must
+ * be paired with bdrv_drain_all_end().
+ *
+ * NOTE: no new block jobs or BlockDriverStates can be created between
+ * the bdrv_drain_all_begin() and bdrv_drain_all_end() calls.
  */
-void bdrv_drain_all(void)
+void bdrv_drain_all_begin(void)
 {
     /* Always run first iteration so any pending completion BHs run */
     bool waited = true;
@@ -297,6 +303,7 @@ void bdrv_drain_all(void)
         aio_context_acquire(aio_context);
         bdrv_parent_drained_begin(bs);
         bdrv_io_unplugged_begin(bs);
+        aio_disable_external(aio_context);
         aio_context_release(aio_context);
 
         if (!g_slist_find(aio_ctxs, aio_context)) {
@@ -326,17 +333,25 @@ void bdrv_drain_all(void)
         }
     }
 
+    g_slist_free(aio_ctxs);
+}
+
+void bdrv_drain_all_end(void)
+{
+    BlockDriverState *bs;
+    BdrvNextIterator it;
+    BlockJob *job = NULL;
+
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
         aio_context_acquire(aio_context);
+        aio_enable_external(aio_context);
         bdrv_io_unplugged_end(bs);
         bdrv_parent_drained_end(bs);
         aio_context_release(aio_context);
     }
-    g_slist_free(aio_ctxs);
 
-    job = NULL;
     while ((job = block_job_next(job))) {
         AioContext *aio_context = blk_get_aio_context(job->blk);
 
@@ -346,6 +361,12 @@ void bdrv_drain_all(void)
     }
 }
 
+void bdrv_drain_all(void)
+{
+    bdrv_drain_all_begin();
+    bdrv_drain_all_end();
+}
+
 /**
  * Remove an active request from the tracked requests list
  *

block/mirror.c

@@ -530,7 +530,6 @@ static void mirror_exit(BlockJob *job, void *opaque)
         aio_context_release(replace_aio_context);
     }
     g_free(s->replaces);
-    bdrv_op_unblock_all(target_bs, s->common.blocker);
     blk_unref(s->target);
     s->target = NULL;
     block_job_completed(&s->common, data->ret);
@@ -997,7 +996,15 @@ static void mirror_start_job(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    bdrv_op_block_all(target, s->common.blocker);
+    block_job_add_bdrv(&s->common, target);
+    /* In commit_active_start() all intermediate nodes disappear, so
+     * any jobs in them must be blocked */
+    if (bdrv_chain_contains(bs, target)) {
+        BlockDriverState *iter;
+        for (iter = backing_bs(bs); iter != target; iter = backing_bs(iter)) {
+            block_job_add_bdrv(&s->common, iter);
+        }
+    }
 
     s->common.co = qemu_coroutine_create(mirror_run, s);
     trace_mirror_start(bs, s, s->common.co, opaque);

block/raw_bsd.c

@@ -31,6 +31,30 @@
 #include "qapi/error.h"
 #include "qemu/option.h"
 
+typedef struct BDRVRawState {
+    uint64_t offset;
+    uint64_t size;
+    bool has_size;
+} BDRVRawState;
+
+static QemuOptsList raw_runtime_opts = {
+    .name = "raw",
+    .head = QTAILQ_HEAD_INITIALIZER(raw_runtime_opts.head),
+    .desc = {
+        {
+            .name = "offset",
+            .type = QEMU_OPT_SIZE,
+            .help = "offset in the disk where the image starts",
+        },
+        {
+            .name = "size",
+            .type = QEMU_OPT_SIZE,
+            .help = "virtual disk size",
+        },
+        { /* end of list */ }
+    },
+};
+
 static QemuOptsList raw_create_opts = {
     .name = "raw-create-opts",
     .head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
@@ -44,16 +68,108 @@ static QemuOptsList raw_create_opts = {
     }
 };
 
+static int raw_read_options(QDict *options, BlockDriverState *bs,
+    BDRVRawState *s, Error **errp)
+{
+    Error *local_err = NULL;
+    QemuOpts *opts = NULL;
+    int64_t real_size = 0;
+    int ret;
+
+    real_size = bdrv_getlength(bs->file->bs);
+    if (real_size < 0) {
+        error_setg_errno(errp, -real_size, "Could not get image size");
+        return real_size;
+    }
+
+    opts = qemu_opts_create(&raw_runtime_opts, NULL, 0, &error_abort);
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        ret = -EINVAL;
+        goto end;
+    }
+
+    s->offset = qemu_opt_get_size(opts, "offset", 0);
+    if (qemu_opt_find(opts, "size") != NULL) {
+        s->size = qemu_opt_get_size(opts, "size", 0);
+        s->has_size = true;
+    } else {
+        s->has_size = false;
+        s->size = real_size - s->offset;
+    }
+
+    /* Check size and offset */
+    if (real_size < s->offset || (real_size - s->offset) < s->size) {
+        error_setg(errp, "The sum of offset (%" PRIu64 ") and size "
+            "(%" PRIu64 ") has to be smaller or equal to the "
+            " actual size of the containing file (%" PRId64 ")",
+            s->offset, s->size, real_size);
+        ret = -EINVAL;
+        goto end;
+    }
+
+    /* Make sure size is multiple of BDRV_SECTOR_SIZE to prevent rounding
+     * up and leaking out of the specified area. */
+    if (!QEMU_IS_ALIGNED(s->size, BDRV_SECTOR_SIZE)) {
+        error_setg(errp, "Specified size is not multiple of %llu",
+            BDRV_SECTOR_SIZE);
+        ret = -EINVAL;
+        goto end;
+    }
+
+    ret = 0;
+
+end:
+
+    qemu_opts_del(opts);
+
+    return ret;
+}
+
 static int raw_reopen_prepare(BDRVReopenState *reopen_state,
                               BlockReopenQueue *queue, Error **errp)
 {
-    return 0;
+    assert(reopen_state != NULL);
+    assert(reopen_state->bs != NULL);
+
+    reopen_state->opaque = g_new0(BDRVRawState, 1);
+
+    return raw_read_options(
+        reopen_state->options,
+        reopen_state->bs,
+        reopen_state->opaque,
+        errp);
+}
+
+static void raw_reopen_commit(BDRVReopenState *state)
+{
+    BDRVRawState *new_s = state->opaque;
+    BDRVRawState *s = state->bs->opaque;
+
+    memcpy(s, new_s, sizeof(BDRVRawState));
+
+    g_free(state->opaque);
+    state->opaque = NULL;
+}
+
+static void raw_reopen_abort(BDRVReopenState *state)
+{
+    g_free(state->opaque);
+    state->opaque = NULL;
 }
 
 static int coroutine_fn raw_co_preadv(BlockDriverState *bs, uint64_t offset,
                                       uint64_t bytes, QEMUIOVector *qiov,
                                       int flags)
 {
+    BDRVRawState *s = bs->opaque;
+
+    if (offset > UINT64_MAX - s->offset) {
+        return -EINVAL;
+    }
+    offset += s->offset;
+
     BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
     return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
 }
@@ -62,11 +178,23 @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
                                        uint64_t bytes, QEMUIOVector *qiov,
                                        int flags)
 {
+    BDRVRawState *s = bs->opaque;
     void *buf = NULL;
     BlockDriver *drv;
     QEMUIOVector local_qiov;
     int ret;
 
+    if (s->has_size && (offset > s->size || bytes > (s->size - offset))) {
+        /* There's not enough space for the data. Don't write anything and just
+         * fail to prevent leaking out of the size specified in options. */
+        return -ENOSPC;
+    }
+
+    if (offset > UINT64_MAX - s->offset) {
+        ret = -EINVAL;
+        goto fail;
+    }
+
     if (bs->probed && offset < BLOCK_PROBE_BUF_SIZE && bytes) {
         /* Handling partial writes would be a pain - so we just
          * require that guests have 512-byte request alignment if
@@ -101,6 +229,8 @@ static int coroutine_fn raw_co_pwritev(BlockDriverState *bs, uint64_t offset,
         qiov = &local_qiov;
     }
 
+    offset += s->offset;
+
     BLKDBG_EVENT(bs->file, BLKDBG_WRITE_AIO);
     ret = bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
 
@@ -117,8 +247,10 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
                                             int nb_sectors, int *pnum,
                                             BlockDriverState **file)
 {
+    BDRVRawState *s = bs->opaque;
     *pnum = nb_sectors;
     *file = bs->file->bs;
+    sector_num += s->offset / BDRV_SECTOR_SIZE;
     return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
            (sector_num << BDRV_SECTOR_BITS);
 }
@@ -127,18 +259,49 @@ static int coroutine_fn raw_co_pwrite_zeroes(BlockDriverState *bs,
                                              int64_t offset, int count,
                                              BdrvRequestFlags flags)
 {
+    BDRVRawState *s = bs->opaque;
+    if (offset > UINT64_MAX - s->offset) {
+        return -EINVAL;
+    }
+    offset += s->offset;
     return bdrv_co_pwrite_zeroes(bs->file, offset, count, flags);
 }
 
 static int coroutine_fn raw_co_pdiscard(BlockDriverState *bs,
                                         int64_t offset, int count)
 {
+    BDRVRawState *s = bs->opaque;
+    if (offset > UINT64_MAX - s->offset) {
+        return -EINVAL;
+    }
+    offset += s->offset;
     return bdrv_co_pdiscard(bs->file->bs, offset, count);
 }
 
 static int64_t raw_getlength(BlockDriverState *bs)
 {
-    return bdrv_getlength(bs->file->bs);
+    int64_t len;
+    BDRVRawState *s = bs->opaque;
+
+    /* Update size. It should not change unless the file was externally
+     * modified. */
+    len = bdrv_getlength(bs->file->bs);
+    if (len < 0) {
+        return len;
+    }
+
+    if (len < s->offset) {
+        s->size = 0;
+    } else {
+        if (s->has_size) {
+            /* Try to honour the size */
+            s->size = MIN(s->size, len - s->offset);
+        } else {
+            s->size = len - s->offset;
+        }
+    }
+
+    return s->size;
 }
 
 static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
@@ -158,6 +321,18 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
 
 static int raw_truncate(BlockDriverState *bs, int64_t offset)
 {
+    BDRVRawState *s = bs->opaque;
+
+    if (s->has_size) {
+        return -ENOTSUP;
+    }
+
+    if (INT64_MAX - offset < s->offset) {
+        return -EINVAL;
+    }
+
+    s->size = offset;
+    offset += s->offset;
     return bdrv_truncate(bs->file->bs, offset);
 }
 
@@ -178,6 +353,10 @@ static void raw_lock_medium(BlockDriverState *bs, bool locked)
 
 static int raw_co_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
 {
+    BDRVRawState *s = bs->opaque;
+    if (s->offset || s->has_size) {
+        return -ENOTSUP;
+    }
     return bdrv_co_ioctl(bs->file->bs, req, buf);
 }
 
@@ -194,6 +373,9 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
 static int raw_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
+    BDRVRawState *s = bs->opaque;
+    int ret;
+
     bs->sg = bs->file->bs->sg;
     bs->supported_write_flags = BDRV_REQ_FUA &
         bs->file->bs->supported_write_flags;
@@ -211,6 +393,16 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
                 bs->file->bs->filename);
     }
 
+    ret = raw_read_options(options, bs, s, errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    if (bs->sg && (s->offset || s->has_size)) {
+        error_setg(errp, "Cannot use offset/size with SCSI generic devices");
+        return -EINVAL;
+    }
+
     return 0;
 }
 
@@ -228,18 +420,37 @@ static int raw_probe(const uint8_t *buf, int buf_size, const char *filename)
 
 static int raw_probe_blocksizes(BlockDriverState *bs, BlockSizes *bsz)
 {
-    return bdrv_probe_blocksizes(bs->file->bs, bsz);
+    BDRVRawState *s = bs->opaque;
+    int ret;
+
+    ret = bdrv_probe_blocksizes(bs->file->bs, bsz);
+    if (ret < 0) {
+        return ret;
+    }
+
+    if (!QEMU_IS_ALIGNED(s->offset, MAX(bsz->log, bsz->phys))) {
+        return -ENOTSUP;
+    }
+
+    return 0;
 }
 
 static int raw_probe_geometry(BlockDriverState *bs, HDGeometry *geo)
 {
+    BDRVRawState *s = bs->opaque;
+    if (s->offset || s->has_size) {
+        return -ENOTSUP;
+    }
     return bdrv_probe_geometry(bs->file->bs, geo);
 }
 
 BlockDriver bdrv_raw = {
     .format_name          = "raw",
+    .instance_size        = sizeof(BDRVRawState),
     .bdrv_probe           = &raw_probe,
     .bdrv_reopen_prepare  = &raw_reopen_prepare,
+    .bdrv_reopen_commit   = &raw_reopen_commit,
+    .bdrv_reopen_abort    = &raw_reopen_abort,
     .bdrv_open            = &raw_open,
     .bdrv_close           = &raw_close,
     .bdrv_create          = &raw_create,

block/ssh.c

@@ -30,10 +30,14 @@
 #include "block/block_int.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
+#include "qemu/cutils.h"
 #include "qemu/sockets.h"
 #include "qemu/uri.h"
+#include "qapi-visit.h"
 #include "qapi/qmp/qint.h"
 #include "qapi/qmp/qstring.h"
+#include "qapi/qobject-input-visitor.h"
+#include "qapi/qobject-output-visitor.h"
 
 /* DEBUG_SSH=1 enables the DPRINTF (debugging printf) statements in
  * this block driver code.
@@ -74,8 +78,9 @@ typedef struct BDRVSSHState {
      */
     LIBSSH2_SFTP_ATTRIBUTES attrs;
 
+    InetSocketAddress *inet;
+
     /* Used to warn if 'flush' is not supported. */
-    char *hostport;
     bool unsafe_flush_warning;
 } BDRVSSHState;
 
@@ -89,7 +94,6 @@ static void ssh_state_init(BDRVSSHState *s)
 
 static void ssh_state_free(BDRVSSHState *s)
 {
-    g_free(s->hostport);
     if (s->sftp_handle) {
         libssh2_sftp_close(s->sftp_handle);
     }
@@ -193,6 +197,7 @@ static int parse_uri(const char *filename, QDict *options, Error **errp)
 {
     URI *uri = NULL;
     QueryParams *qp;
+    char *port_str;
     int i;
 
     uri = uri_parse(filename);
@@ -225,11 +230,11 @@ static int parse_uri(const char *filename, QDict *options, Error **errp)
         qdict_put(options, "user", qstring_from_str(uri->user));
     }
 
-    qdict_put(options, "host", qstring_from_str(uri->server));
+    qdict_put(options, "server.host", qstring_from_str(uri->server));
 
-    if (uri->port) {
-        qdict_put(options, "port", qint_from_int(uri->port));
-    }
+    port_str = g_strdup_printf("%d", uri->port ?: 22);
+    qdict_put(options, "server.port", qstring_from_str(port_str));
+    g_free(port_str);
 
     qdict_put(options, "path", qstring_from_str(uri->path));
 
@@ -254,15 +259,31 @@ static int parse_uri(const char *filename, QDict *options, Error **errp)
     return -EINVAL;
 }
 
+static bool ssh_has_filename_options_conflict(QDict *options, Error **errp)
+{
+    const QDictEntry *qe;
+
+    for (qe = qdict_first(options); qe; qe = qdict_next(options, qe)) {
+        if (!strcmp(qe->key, "host") ||
+            !strcmp(qe->key, "port") ||
+            !strcmp(qe->key, "path") ||
+            !strcmp(qe->key, "user") ||
+            !strcmp(qe->key, "host_key_check") ||
+            strstart(qe->key, "server.", NULL))
+        {
+            error_setg(errp, "Option '%s' cannot be used with a file name",
+                       qe->key);
+            return true;
+        }
+    }
+
+    return false;
+}
+
 static void ssh_parse_filename(const char *filename, QDict *options,
                                Error **errp)
 {
-    if (qdict_haskey(options, "user") ||
-        qdict_haskey(options, "host") ||
-        qdict_haskey(options, "port") ||
-        qdict_haskey(options, "path") ||
-        qdict_haskey(options, "host_key_check")) {
-        error_setg(errp, "user, host, port, path, host_key_check cannot be used at the same time as a file option");
+    if (ssh_has_filename_options_conflict(options, errp)) {
         return;
     }
 
@@ -540,14 +561,69 @@ static QemuOptsList ssh_runtime_opts = {
     },
 };
 
+static bool ssh_process_legacy_socket_options(QDict *output_opts,
+                                              QemuOpts *legacy_opts,
+                                              Error **errp)
+{
+    const char *host = qemu_opt_get(legacy_opts, "host");
+    const char *port = qemu_opt_get(legacy_opts, "port");
+
+    if (!host && port) {
+        error_setg(errp, "port may not be used without host");
+        return false;
+    }
+
+    if (host) {
+        qdict_put(output_opts, "server.host", qstring_from_str(host));
+        qdict_put(output_opts, "server.port",
+                  qstring_from_str(port ?: stringify(22)));
+    }
+
+    return true;
+}
+
+static InetSocketAddress *ssh_config(BDRVSSHState *s, QDict *options,
+                                     Error **errp)
+{
+    InetSocketAddress *inet = NULL;
+    QDict *addr = NULL;
+    QObject *crumpled_addr = NULL;
+    Visitor *iv = NULL;
+    Error *local_error = NULL;
+
+    qdict_extract_subqdict(options, &addr, "server.");
+    if (!qdict_size(addr)) {
+        error_setg(errp, "SSH server address missing");
+        goto out;
+    }
+
+    crumpled_addr = qdict_crumple(addr, errp);
+    if (!crumpled_addr) {
+        goto out;
+    }
+
+    iv = qobject_input_visitor_new(crumpled_addr, true);
+    visit_type_InetSocketAddress(iv, NULL, &inet, &local_error);
+    if (local_error) {
+        error_propagate(errp, local_error);
+        goto out;
+    }
+
+out:
+    QDECREF(addr);
+    qobject_decref(crumpled_addr);
+    visit_free(iv);
+    return inet;
+}
+
 static int connect_to_ssh(BDRVSSHState *s, QDict *options,
                           int ssh_flags, int creat_mode, Error **errp)
 {
     int r, ret;
     QemuOpts *opts = NULL;
     Error *local_err = NULL;
-    const char *host, *user, *path, *host_key_check;
-    int port;
+    const char *user, *path, *host_key_check;
+    long port = 0;
 
     opts = qemu_opts_create(&ssh_runtime_opts, NULL, 0, &error_abort);
     qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -557,15 +633,11 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
         goto err;
     }
 
-    host = qemu_opt_get(opts, "host");
-    if (!host) {
+    if (!ssh_process_legacy_socket_options(options, opts, errp)) {
         ret = -EINVAL;
-        error_setg(errp, "No hostname was specified");
         goto err;
     }
 
-    port = qemu_opt_get_number(opts, "port", 22);
-
     path = qemu_opt_get(opts, "path");
     if (!path) {
         ret = -EINVAL;
@@ -588,12 +660,21 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
         host_key_check = "yes";
     }
 
-    /* Construct the host:port name for inet_connect. */
-    g_free(s->hostport);
-    s->hostport = g_strdup_printf("%s:%d", host, port);
+    /* Pop the config into our state object, Exit if invalid */
+    s->inet = ssh_config(s, options, errp);
+    if (!s->inet) {
+        ret = -EINVAL;
+        goto err;
+    }
+
+    if (qemu_strtol(s->inet->port, NULL, 10, &port) < 0) {
+        error_setg(errp, "Use only numeric port value");
+        ret = -EINVAL;
+        goto err;
+    }
 
     /* Open the socket and connect. */
-    s->sock = inet_connect(s->hostport, errp);
+    s->sock = inet_connect_saddr(s->inet, errp, NULL, NULL);
     if (s->sock < 0) {
         ret = -EIO;
         goto err;
@@ -619,7 +700,8 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
     }
 
     /* Check the remote host's key against known_hosts. */
-    ret = check_host_key(s, host, port, host_key_check, errp);
+    ret = check_host_key(s, s->inet->host, port, host_key_check,
+                         errp);
     if (ret < 0) {
         goto err;
     }
@@ -1040,7 +1122,7 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)
 {
     if (!s->unsafe_flush_warning) {
         error_report("warning: ssh server %s does not support fsync",
-                     s->hostport);
+                     s->inet->host);
         if (what) {
             error_report("to support fsync, you need %s", what);
         }

block/stream.c

@@ -37,6 +37,7 @@ typedef struct StreamBlockJob {
     BlockDriverState *base;
     BlockdevOnError on_error;
     char *backing_file_str;
+    int bs_flags;
 } StreamBlockJob;
 
 static int coroutine_fn stream_populate(BlockBackend *blk,
@@ -81,6 +82,11 @@ static void stream_complete(BlockJob *job, void *opaque)
         bdrv_set_backing_hd(bs, base);
     }
 
+    /* Reopen the image back in read-only mode if necessary */
+    if (s->bs_flags != bdrv_get_flags(bs)) {
+        bdrv_reopen(bs, s->bs_flags, NULL);
+    }
+
     g_free(s->backing_file_str);
     block_job_completed(&s->common, data->ret);
     g_free(data);
@@ -220,6 +226,8 @@ void stream_start(const char *job_id, BlockDriverState *bs,
                   BlockCompletionFunc *cb, void *opaque, Error **errp)
 {
     StreamBlockJob *s;
+    BlockDriverState *iter;
+    int orig_bs_flags;
 
     s = block_job_create(job_id, &stream_job_driver, bs, speed,
                          cb, opaque, errp);
@@ -227,8 +235,24 @@ void stream_start(const char *job_id, BlockDriverState *bs,
         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 */
+    for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
+        block_job_add_bdrv(&s->common, iter);
+    }
+
     s->base = base;
     s->backing_file_str = g_strdup(backing_file_str);
+    s->bs_flags = orig_bs_flags;
 
     s->on_error = on_error;
     s->common.co = qemu_coroutine_create(stream_run, s);

blockdev.c

@@ -2932,12 +2932,13 @@ static void block_job_cb(void *opaque, int ret)
 
 void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
                       bool has_base, const char *base,
+                      bool has_base_node, const char *base_node,
                       bool has_backing_file, const char *backing_file,
                       bool has_speed, int64_t speed,
                       bool has_on_error, BlockdevOnError on_error,
                       Error **errp)
 {
-    BlockDriverState *bs;
+    BlockDriverState *bs, *iter;
     BlockDriverState *base_bs = NULL;
     AioContext *aio_context;
     Error *local_err = NULL;
@@ -2947,7 +2948,7 @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
         on_error = BLOCKDEV_ON_ERROR_REPORT;
     }
 
-    bs = qmp_get_root_bs(device, errp);
+    bs = bdrv_lookup_bs(device, device, errp);
     if (!bs) {
         return;
     }
@@ -2955,7 +2956,9 @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
     aio_context = bdrv_get_aio_context(bs);
     aio_context_acquire(aio_context);
 
-    if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_STREAM, errp)) {
+    if (has_base && has_base_node) {
+        error_setg(errp, "'base' and 'base-node' cannot be specified "
+                   "at the same time");
         goto out;
     }
 
@@ -2969,6 +2972,27 @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
         base_name = base;
     }
 
+    if (has_base_node) {
+        base_bs = bdrv_lookup_bs(NULL, base_node, errp);
+        if (!base_bs) {
+            goto out;
+        }
+        if (bs == base_bs || !bdrv_chain_contains(bs, base_bs)) {
+            error_setg(errp, "Node '%s' is not a backing image of '%s'",
+                       base_node, device);
+            goto out;
+        }
+        assert(bdrv_get_aio_context(base_bs) == aio_context);
+        base_name = base_bs->filename;
+    }
+
+    /* Check for op blockers in the whole chain between bs and base */
+    for (iter = bs; iter && iter != base_bs; iter = backing_bs(iter)) {
+        if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_STREAM, errp)) {
+            goto out;
+        }
+    }
+
     /* if we are streaming the entire chain, the result will have no backing
      * file, and specifying one is therefore an error */
     if (base_bs == NULL && has_backing_file) {
@@ -3001,6 +3025,7 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
                       Error **errp)
 {
     BlockDriverState *bs;
+    BlockDriverState *iter;
     BlockDriverState *base_bs, *top_bs;
     AioContext *aio_context;
     Error *local_err = NULL;
@@ -3067,8 +3092,10 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
 
     assert(bdrv_get_aio_context(base_bs) == aio_context);
 
-    if (bdrv_op_is_blocked(base_bs, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
-        goto out;
+    for (iter = top_bs; iter != backing_bs(base_bs); iter = backing_bs(iter)) {
+        if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
+            goto out;
+        }
     }
 
     /* Do not allow attempts to commit an image into itself */
@@ -3086,6 +3113,10 @@ void qmp_block_commit(bool has_job_id, const char *job_id, const char *device,
         commit_active_start(has_job_id ? job_id : NULL, bs, base_bs, speed,
                             on_error, block_job_cb, bs, &local_err, false);
     } else {
+        BlockDriverState *overlay_bs = bdrv_find_overlay(bs, top_bs);
+        if (bdrv_op_is_blocked(overlay_bs, BLOCK_OP_TYPE_COMMIT_TARGET, errp)) {
+            goto out;
+        }
         commit_start(has_job_id ? job_id : NULL, bs, base_bs, top_bs, speed,
                      on_error, block_job_cb, bs,
                      has_backing_file ? backing_file : NULL, &local_err);

blockjob.c

@@ -113,6 +113,13 @@ static void block_job_detach_aio_context(void *opaque)
     block_job_unref(job);
 }
 
+void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs)
+{
+    job->nodes = g_slist_prepend(job->nodes, bs);
+    bdrv_ref(bs);
+    bdrv_op_block_all(bs, job->blocker);
+}
+
 void *block_job_create(const char *job_id, const BlockJobDriver *driver,
                        BlockDriverState *bs, int64_t speed,
                        BlockCompletionFunc *cb, void *opaque, Error **errp)
@@ -150,7 +157,7 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
     job = g_malloc0(driver->instance_size);
     error_setg(&job->blocker, "block device is in use by block job: %s",
                BlockJobType_lookup[driver->job_type]);
-    bdrv_op_block_all(bs, job->blocker);
+    block_job_add_bdrv(job, bs);
     bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
 
     job->driver        = driver;
@@ -189,9 +196,15 @@ void block_job_ref(BlockJob *job)
 void block_job_unref(BlockJob *job)
 {
     if (--job->refcnt == 0) {
+        GSList *l;
         BlockDriverState *bs = blk_bs(job->blk);
         bs->job = NULL;
-        bdrv_op_unblock_all(bs, job->blocker);
+        for (l = job->nodes; l; l = l->next) {
+            bs = l->data;
+            bdrv_op_unblock_all(bs, job->blocker);
+            bdrv_unref(bs);
+        }
+        g_slist_free(job->nodes);
         blk_remove_aio_context_notifier(job->blk,
                                         block_job_attached_aio_context,
                                         block_job_detach_aio_context, job);

docs/live-block-ops.txt

@@ -4,15 +4,20 @@ LIVE BLOCK OPERATIONS
 High level description of live block operations. Note these are not
 supported for use with the raw format at the moment.
 
+Note also that this document is incomplete and it currently only
+covers the 'stream' operation. Other operations supported by QEMU such
+as 'commit', 'mirror' and 'backup' are not described here yet. Please
+refer to the qapi/block-core.json file for an overview of those.
+
 Snapshot live merge
 ===================
 
 Given a snapshot chain, described in this document in the following
 format:
 
-[A] -> [B] -> [C] -> [D]
+[A] <- [B] <- [C] <- [D] <- [E]
 
-Where the rightmost object ([D] in the example) described is the current
+Where the rightmost object ([E] in the example) described is the current
 image which the guest OS has write access to. To the left of it is its base
 image, and so on accordingly until the leftmost image, which has no
 base.
@@ -21,11 +26,14 @@ The snapshot live merge operation transforms such a chain into a
 smaller one with fewer elements, such as this transformation relative
 to the first example:
 
-[A] -> [D]
+[A] <- [E]
 
-Currently only forward merge with target being the active image is
-supported, that is, data copy is performed in the right direction with
-destination being the rightmost image.
+Data is copied in the right direction with destination being the
+rightmost image, but any other intermediate image can be specified
+instead. In this example data is copied from [C] into [D], so [D] can
+be backed by [B]:
+
+[A] <- [B] <- [D] <- [E]
 
 The operation is implemented in QEMU through image streaming facilities.
 
@@ -35,14 +43,20 @@ streaming operation completes it raises a QMP event. 'block_stream'
 copies data from the backing file(s) into the active image. When finished,
 it adjusts the backing file pointer.
 
-The 'base' parameter specifies an image which data need not be streamed from.
-This image will be used as the backing file for the active image when the
-operation is finished.
+The 'base' parameter specifies an image which data need not be
+streamed from. This image will be used as the backing file for the
+destination image when the operation is finished.
 
-In the example above, the command would be:
+In the first example above, the command would be:
 
-(qemu) block_stream virtio0 A
+(qemu) block_stream virtio0 file-A.img
 
+In order to specify a destination image different from the active
+(rightmost) one we can use its node name instead.
+
+In the second example above, the command would be:
+
+(qemu) block_stream node-D file-B.img
 
 Live block copy
 ===============

docs/qmp-commands.txt

@@ -750,8 +750,11 @@ Arguments:
 - "job-id": Identifier for the newly-created block job. If omitted,
             the device name will be used. (json-string, optional)
 - "device": The device name or node-name of a root node (json-string)
-- "base": The file name of the backing image above which copying starts
-          (json-string, optional)
+- "base": The file name of the backing image above which copying starts.
+          It cannot be set if 'base-node' is also set (json-string, optional)
+- "base-node": the node name of the backing image above which copying starts.
+               It cannot be set if 'base' is also set.
+               (json-string, optional) (Since 2.8)
 - "backing-file": The backing file string to write into the active layer. This
                   filename is not validated.
 

hmp.c

@@ -1571,7 +1571,7 @@ void hmp_block_stream(Monitor *mon, const QDict *qdict)
     int64_t speed = qdict_get_try_int(qdict, "speed", 0);
 
     qmp_block_stream(false, NULL, device, base != NULL, base, false, NULL,
-                     qdict_haskey(qdict, "speed"), speed,
+                     false, NULL, qdict_haskey(qdict, "speed"), speed,
                      true, BLOCKDEV_ON_ERROR_REPORT, &error);
 
     hmp_handle_error(mon, &error);

include/block/block.h

@@ -332,6 +332,8 @@ int bdrv_flush_all(void);
 void bdrv_close_all(void);
 void bdrv_drain(BlockDriverState *bs);
 void coroutine_fn bdrv_co_drain(BlockDriverState *bs);
+void bdrv_drain_all_begin(void);
+void bdrv_drain_all_end(void);
 void bdrv_drain_all(void);
 
 #define BDRV_POLL_WHILE(bs, cond) ({                       \

include/block/blockjob.h

@@ -188,6 +188,9 @@ struct BlockJob {
     /** Block other operations when block job is running */
     Error *blocker;
 
+    /** BlockDriverStates that are involved in this block job */
+    GSList *nodes;
+
     /** The opaque value that is passed to the completion function.  */
     void *opaque;
 
@@ -252,6 +255,17 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
                        BlockDriverState *bs, int64_t speed,
                        BlockCompletionFunc *cb, void *opaque, Error **errp);
 
+/**
+ * block_job_add_bdrv:
+ * @job: A block job
+ * @bs: A BlockDriverState that is involved in @job
+ *
+ * Add @bs to the list of BlockDriverState that are involved in
+ * @job. This means that all operations will be blocked on @bs while
+ * @job exists.
+ */
+void block_job_add_bdrv(BlockJob *job, BlockDriverState *bs);
+
 /**
  * block_job_sleep_ns:
  * @job: The job that calls the function.

include/qemu/sockets.h

@@ -34,6 +34,8 @@ typedef void NonBlockingConnectHandler(int fd, Error *err, void *opaque);
 
 InetSocketAddress *inet_parse(const char *str, Error **errp);
 int inet_connect(const char *str, Error **errp);
+int inet_connect_saddr(InetSocketAddress *saddr, Error **errp,
+                       NonBlockingConnectHandler *callback, void *opaque);
 
 NetworkAddressFamily inet_netfamily(int family);
 

qapi/block-core.json

@@ -1464,6 +1464,13 @@
 # with query-block-jobs.  The operation can be stopped before it has completed
 # using the block-job-cancel command.
 #
+# The node that receives the data is called the top image, can be located in
+# any part of the chain (but always above the base image; see below) and can be
+# specified using its device or node name. Earlier qemu versions only allowed
+# 'device' to name the top level node; presence of the 'base-node' parameter
+# during introspection can be used as a witness of the enhanced semantics
+# of 'device'.
+#
 # If a base file is specified then sectors are not copied from that base file and
 # its backing chain.  When streaming completes the image file will have the base
 # file as its backing file.  This can be used to stream a subset of the backing
@@ -1475,12 +1482,16 @@
 # @job-id: #optional identifier for the newly-created block job. If
 #          omitted, the device name will be used. (Since 2.7)
 #
-# @device: the device name or node-name of a root node
+# @device: the device or node name of the top image
 #
-# @base:   #optional the common backing file name
+# @base:   #optional the common backing file name.
+#                    It cannot be set if @base-node is also set.
 #
-# @backing-file: #optional The backing file string to write into the active
-#                          layer. This filename is not validated.
+# @base-node: #optional the node name of the backing file.
+#                       It cannot be set if @base is also set. (Since 2.8)
+#
+# @backing-file: #optional The backing file string to write into the top
+#                          image. This filename is not validated.
 #
 #                          If a pathname string is such that it cannot be
 #                          resolved by QEMU, that means that subsequent QMP or
@@ -1504,7 +1515,7 @@
 ##
 { 'command': 'block-stream',
   'data': { '*job-id': 'str', 'device': 'str', '*base': 'str',
-            '*backing-file': 'str', '*speed': 'int',
+            '*base-node': 'str', '*backing-file': 'str', '*speed': 'int',
             '*on-error': 'BlockdevOnError' } }
 
 ##
@@ -1703,16 +1714,17 @@
 #
 # @host_device, @host_cdrom: Since 2.1
 # @gluster: Since 2.7
-# @nbd: Since 2.8
+# @nbd, @nfs, @replication, @ssh: Since 2.8
 #
 # Since: 2.0
 ##
 { 'enum': 'BlockdevDriver',
   'data': [ 'archipelago', 'blkdebug', 'blkverify', 'bochs', 'cloop',
             'dmg', 'file', 'ftp', 'ftps', 'gluster', 'host_cdrom',
-            'host_device', 'http', 'https', 'luks', 'nbd', 'null-aio',
+            'host_device', 'http', 'https', 'luks', 'nbd', 'nfs', 'null-aio',
             'null-co', 'parallels', 'qcow', 'qcow2', 'qed', 'quorum', 'raw',
-            'replication', 'tftp', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
+            'replication', 'ssh', 'tftp', 'vdi', 'vhdx', 'vmdk', 'vpc',
+            'vvfat' ] }
 
 ##
 # @BlockdevOptionsFile
@@ -1949,6 +1961,25 @@
             '*vport': 'int',
             '*segment': 'str' } }
 
+##
+# @BlockdevOptionsSsh
+#
+# @server:              host address
+#
+# @path:                path to the image on the host
+#
+# @user:                #optional user as which to connect, defaults to current
+#                       local user name
+#
+# TODO: Expose the host_key_check option in QMP
+#
+# Since 2.8
+##
+{ 'struct': 'BlockdevOptionsSsh',
+  'data': { 'server': 'InetSocketAddress',
+            'path': 'str',
+            '*user': 'str' } }
+
 
 ##
 # @BlkdebugEvent
@@ -2208,6 +2239,74 @@
   'data': { 'mode': 'ReplicationMode',
             '*top-id': 'str' } }
 
+##
+# @NFSTransport
+#
+# An enumeration of NFS transport types
+#
+# @inet:        TCP transport
+#
+# Since 2.8
+##
+{ 'enum': 'NFSTransport',
+  'data': [ 'inet' ] }
+
+##
+# @NFSServer
+#
+# Captures the address of the socket
+#
+# @type:        transport type used for NFS (only TCP supported)
+#
+# @host:        host address for NFS server
+#
+# Since 2.8
+##
+{ 'struct': 'NFSServer',
+  'data': { 'type': 'NFSTransport',
+            'host': 'str' } }
+
+##
+# @BlockdevOptionsNfs
+#
+# Driver specific block device option for NFS
+#
+# @server:                  host address
+#
+# @path:                    path of the image on the host
+#
+# @user:                    #optional UID value to use when talking to the
+#                           server (defaults to 65534 on Windows and getuid()
+#                           on unix)
+#
+# @group:                   #optional GID value to use when talking to the
+#                           server (defaults to 65534 on Windows and getgid()
+#                           in unix)
+#
+# @tcp-syn-count:           #optional number of SYNs during the session
+#                           establishment (defaults to libnfs default)
+#
+# @readahead-size:          #optional set the readahead size in bytes (defaults
+#                           to libnfs default)
+#
+# @page-cache-size:         #optional set the pagecache size in bytes (defaults
+#                           to libnfs default)
+#
+# @debug-level:             #optional set the NFS debug level (max 2) (defaults
+#                           to libnfs default)
+#
+# Since 2.8
+##
+{ 'struct': 'BlockdevOptionsNfs',
+  'data': { 'server': 'NFSServer',
+            'path': 'str',
+            '*user': 'int',
+            '*group': 'int',
+            '*tcp-syn-count': 'int',
+            '*readahead-size': 'int',
+            '*page-cache-size': 'int',
+            '*debug-level': 'int' } }
+
 ##
 # @BlockdevOptionsCurl
 #
@@ -2238,6 +2337,20 @@
             '*export': 'str',
             '*tls-creds': 'str' } }
 
+##
+# @BlockdevOptionsRaw
+#
+# Driver specific block device options for the raw driver.
+#
+# @offset:      #optional position where the block device starts
+# @size:        #optional the assumed size of the device
+#
+# Since: 2.8
+##
+{ 'struct': 'BlockdevOptionsRaw',
+  'base': 'BlockdevOptionsGenericFormat',
+  'data': { '*offset': 'int', '*size': 'int' } }
+
 ##
 # @BlockdevOptions
 #
@@ -2284,7 +2397,7 @@
 # TODO iscsi: Wait for structured options
       'luks':       'BlockdevOptionsLUKS',
       'nbd':        'BlockdevOptionsNbd',
-# TODO nfs: Wait for structured options
+      'nfs':        'BlockdevOptionsNfs',
       'null-aio':   'BlockdevOptionsNull',
       'null-co':    'BlockdevOptionsNull',
       'parallels':  'BlockdevOptionsGenericFormat',
@@ -2292,11 +2405,11 @@
       'qcow':       'BlockdevOptionsGenericCOWFormat',
       'qed':        'BlockdevOptionsGenericCOWFormat',
       'quorum':     'BlockdevOptionsQuorum',
-      'raw':        'BlockdevOptionsGenericFormat',
+      'raw':        'BlockdevOptionsRaw',
 # TODO rbd: Wait for structured options
       'replication':'BlockdevOptionsReplication',
 # TODO sheepdog: Wait for structured options
-# TODO ssh: Should take InetSocketAddress for 'host'?
+      'ssh':        'BlockdevOptionsSsh',
       'tftp':       'BlockdevOptionsCurl',
       'vdi':        'BlockdevOptionsGenericFormat',
       'vhdx':       'BlockdevOptionsGenericFormat',

tests/qemu-iotests/030

@@ -36,7 +36,7 @@ class TestSingleDrive(iotests.QMPTestCase):
         qemu_img('create', '-f', iotests.imgfmt, '-o', 'backing_file=%s' % mid_img, test_img)
         qemu_io('-f', 'raw', '-c', 'write -P 0x1 0 512', backing_img)
         qemu_io('-f', iotests.imgfmt, '-c', 'write -P 0x1 524288 512', mid_img)
-        self.vm = iotests.VM().add_drive("blkdebug::" + test_img)
+        self.vm = iotests.VM().add_drive("blkdebug::" + test_img, "backing.node-name=mid")
         self.vm.launch()
 
     def tearDown(self):
@@ -60,6 +60,25 @@ class TestSingleDrive(iotests.QMPTestCase):
                          qemu_io('-f', iotests.imgfmt, '-c', 'map', test_img),
                          'image file map does not match backing file after streaming')
 
+    def test_stream_intermediate(self):
+        self.assert_no_active_block_jobs()
+
+        self.assertNotEqual(qemu_io('-f', 'raw', '-c', 'map', backing_img),
+                            qemu_io('-f', iotests.imgfmt, '-c', 'map', mid_img),
+                            'image file map matches backing file before streaming')
+
+        result = self.vm.qmp('block-stream', device='mid', job_id='stream-mid')
+        self.assert_qmp(result, 'return', {})
+
+        self.wait_until_completed(drive='stream-mid')
+
+        self.assert_no_active_block_jobs()
+        self.vm.shutdown()
+
+        self.assertEqual(qemu_io('-f', 'raw', '-c', 'map', backing_img),
+                         qemu_io('-f', iotests.imgfmt, '-c', 'map', mid_img),
+                         'image file map does not match backing file after streaming')
+
     def test_stream_pause(self):
         self.assert_no_active_block_jobs()
 
@@ -129,6 +148,298 @@ class TestSingleDrive(iotests.QMPTestCase):
         self.assert_qmp(result, 'error/class', 'GenericError')
 
 
+class TestParallelOps(iotests.QMPTestCase):
+    num_ops = 4 # Number of parallel block-stream operations
+    num_imgs = num_ops * 2 + 1
+    image_len = num_ops * 1024 * 1024
+    imgs = []
+
+    def setUp(self):
+        opts = []
+        self.imgs = []
+
+        # Initialize file names and command-line options
+        for i in range(self.num_imgs):
+            img_depth = self.num_imgs - i - 1
+            opts.append("backing." * img_depth + "node-name=node%d" % i)
+            self.imgs.append(os.path.join(iotests.test_dir, 'img-%d.img' % i))
+
+        # Create all images
+        iotests.create_image(self.imgs[0], self.image_len)
+        for i in range(1, self.num_imgs):
+            qemu_img('create', '-f', iotests.imgfmt,
+                     '-o', 'backing_file=%s' % self.imgs[i-1], self.imgs[i])
+
+        # Put data into the images we are copying data from
+        for i in range(self.num_imgs / 2):
+            img_index = i * 2 + 1
+            # Alternate between 512k and 1M.
+            # This way jobs will not finish in the same order they were created
+            num_kb = 512 + 512 * (i % 2)
+            qemu_io('-f', iotests.imgfmt,
+                    '-c', 'write -P %d %d %d' % (i, i*1024*1024, num_kb * 1024),
+                    self.imgs[img_index])
+
+        # Attach the drive to the VM
+        self.vm = iotests.VM()
+        self.vm.add_drive(self.imgs[-1], ','.join(opts))
+        self.vm.launch()
+
+    def tearDown(self):
+        self.vm.shutdown()
+        for img in self.imgs:
+            os.remove(img)
+
+    # Test that it's possible to run several block-stream operations
+    # in parallel in the same snapshot chain
+    def test_stream_parallel(self):
+        self.assert_no_active_block_jobs()
+
+        # Check that the maps don't match before the streaming operations
+        for i in range(2, self.num_imgs, 2):
+            self.assertNotEqual(qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[i]),
+                                qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[i-1]),
+                                'image file map matches backing file before streaming')
+
+        # Create all streaming jobs
+        pending_jobs = []
+        for i in range(2, self.num_imgs, 2):
+            node_name = 'node%d' % i
+            job_id = 'stream-%s' % node_name
+            pending_jobs.append(job_id)
+            result = self.vm.qmp('block-stream', device=node_name, job_id=job_id, base=self.imgs[i-2], speed=512*1024)
+            self.assert_qmp(result, 'return', {})
+
+        # Wait for all jobs to be finished.
+        while len(pending_jobs) > 0:
+            for event in self.vm.get_qmp_events(wait=True):
+                if event['event'] == 'BLOCK_JOB_COMPLETED':
+                    job_id = self.dictpath(event, 'data/device')
+                    self.assertTrue(job_id in pending_jobs)
+                    self.assert_qmp_absent(event, 'data/error')
+                    pending_jobs.remove(job_id)
+
+        self.assert_no_active_block_jobs()
+        self.vm.shutdown()
+
+        # Check that all maps match now
+        for i in range(2, self.num_imgs, 2):
+            self.assertEqual(qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[i]),
+                             qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[i-1]),
+                             'image file map does not match backing file after streaming')
+
+    # Test that it's not possible to perform two block-stream
+    # operations if there are nodes involved in both.
+    def test_overlapping_1(self):
+        self.assert_no_active_block_jobs()
+
+        # Set a speed limit to make sure that this job blocks the rest
+        result = self.vm.qmp('block-stream', device='node4', job_id='stream-node4', base=self.imgs[1], speed=1024*1024)
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('block-stream', device='node5', job_id='stream-node5', base=self.imgs[2])
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        result = self.vm.qmp('block-stream', device='node3', job_id='stream-node3', base=self.imgs[2])
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        result = self.vm.qmp('block-stream', device='node4', job_id='stream-node4-v2')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # block-commit should also fail if it touches nodes used by the stream job
+        result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[4], job_id='commit-node4')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[1], top=self.imgs[3], job_id='commit-node1')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # This fails because it needs to modify the backing string in node2, which is blocked
+        result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[0], top=self.imgs[1], job_id='commit-node0')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        self.wait_until_completed(drive='stream-node4')
+        self.assert_no_active_block_jobs()
+
+    # Similar to test_overlapping_1, but with block-commit
+    # blocking the other jobs
+    def test_overlapping_2(self):
+        self.assertLessEqual(9, self.num_imgs)
+        self.assert_no_active_block_jobs()
+
+        # Set a speed limit to make sure that this job blocks the rest
+        result = self.vm.qmp('block-commit', device='drive0', top=self.imgs[5], base=self.imgs[3], job_id='commit-node3', speed=1024*1024)
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('block-stream', device='node3', job_id='stream-node3')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        result = self.vm.qmp('block-stream', device='node6', base=self.imgs[2], job_id='stream-node6')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        result = self.vm.qmp('block-stream', device='node4', base=self.imgs[2], job_id='stream-node4')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        result = self.vm.qmp('block-stream', device='node6', base=self.imgs[4], job_id='stream-node6-v2')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # This fails because block-commit needs to block node6, the overlay of the 'top' image
+        result = self.vm.qmp('block-stream', device='node7', base=self.imgs[5], job_id='stream-node6-v3')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # This fails because block-commit currently blocks the active layer even if it's not used
+        result = self.vm.qmp('block-stream', device='drive0', base=self.imgs[5], job_id='stream-drive0')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        self.wait_until_completed(drive='commit-node3')
+
+    # Similar to test_overlapping_2, but here block-commit doesn't use the 'top' parameter.
+    # Internally this uses a mirror block job, hence the separate test case.
+    def test_overlapping_3(self):
+        self.assertLessEqual(8, self.num_imgs)
+        self.assert_no_active_block_jobs()
+
+        # Set a speed limit to make sure that this job blocks the rest
+        result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[3], job_id='commit-drive0', speed=1024*1024)
+        self.assert_qmp(result, 'return', {})
+
+        result = self.vm.qmp('block-stream', device='node5', base=self.imgs[3], job_id='stream-node6')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        event = self.vm.get_qmp_event(wait=True)
+        self.assertEqual(event['event'], 'BLOCK_JOB_READY')
+        self.assert_qmp(event, 'data/device', 'commit-drive0')
+        self.assert_qmp(event, 'data/type', 'commit')
+        self.assert_qmp_absent(event, 'data/error')
+
+        result = self.vm.qmp('block-job-complete', device='commit-drive0')
+        self.assert_qmp(result, 'return', {})
+
+        self.wait_until_completed(drive='commit-drive0')
+
+    # Test a block-stream and a block-commit job in parallel
+    def test_stream_commit(self):
+        self.assertLessEqual(8, self.num_imgs)
+        self.assert_no_active_block_jobs()
+
+        # Stream from node0 into node2
+        result = self.vm.qmp('block-stream', device='node2', job_id='node2')
+        self.assert_qmp(result, 'return', {})
+
+        # Commit from the active layer into node3
+        result = self.vm.qmp('block-commit', device='drive0', base=self.imgs[3])
+        self.assert_qmp(result, 'return', {})
+
+        # Wait for all jobs to be finished.
+        pending_jobs = ['node2', 'drive0']
+        while len(pending_jobs) > 0:
+            for event in self.vm.get_qmp_events(wait=True):
+                if event['event'] == 'BLOCK_JOB_COMPLETED':
+                    node_name = self.dictpath(event, 'data/device')
+                    self.assertTrue(node_name in pending_jobs)
+                    self.assert_qmp_absent(event, 'data/error')
+                    pending_jobs.remove(node_name)
+                if event['event'] == 'BLOCK_JOB_READY':
+                    self.assert_qmp(event, 'data/device', 'drive0')
+                    self.assert_qmp(event, 'data/type', 'commit')
+                    self.assert_qmp_absent(event, 'data/error')
+                    self.assertTrue('drive0' in pending_jobs)
+                    self.vm.qmp('block-job-complete', device='drive0')
+
+        self.assert_no_active_block_jobs()
+
+    # Test the base_node parameter
+    def test_stream_base_node_name(self):
+        self.assert_no_active_block_jobs()
+
+        self.assertNotEqual(qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[4]),
+                            qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[3]),
+                            'image file map matches backing file before streaming')
+
+        # Error: the base node does not exist
+        result = self.vm.qmp('block-stream', device='node4', base_node='none', job_id='stream')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # Error: the base node is not a backing file of the top node
+        result = self.vm.qmp('block-stream', device='node4', base_node='node6', job_id='stream')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # Error: the base node is the same as the top node
+        result = self.vm.qmp('block-stream', device='node4', base_node='node4', job_id='stream')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # Error: cannot specify 'base' and 'base-node' at the same time
+        result = self.vm.qmp('block-stream', device='node4', base=self.imgs[2], base_node='node2', job_id='stream')
+        self.assert_qmp(result, 'error/class', 'GenericError')
+
+        # Success: the base node is a backing file of the top node
+        result = self.vm.qmp('block-stream', device='node4', base_node='node2', job_id='stream')
+        self.assert_qmp(result, 'return', {})
+
+        self.wait_until_completed(drive='stream')
+
+        self.assert_no_active_block_jobs()
+        self.vm.shutdown()
+
+        self.assertEqual(qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[4]),
+                         qemu_io('-f', iotests.imgfmt, '-c', 'map', self.imgs[3]),
+                         'image file map matches backing file after streaming')
+
+class TestQuorum(iotests.QMPTestCase):
+    num_children = 3
+    children = []
+    backing = []
+
+    def setUp(self):
+        opts = ['driver=quorum', 'vote-threshold=2']
+
+        # Initialize file names and command-line options
+        for i in range(self.num_children):
+            child_img = os.path.join(iotests.test_dir, 'img-%d.img' % i)
+            backing_img = os.path.join(iotests.test_dir, 'backing-%d.img' % i)
+            self.children.append(child_img)
+            self.backing.append(backing_img)
+            qemu_img('create', '-f', iotests.imgfmt, backing_img, '1M')
+            qemu_io('-f', iotests.imgfmt,
+                    '-c', 'write -P 0x55 0 1024', backing_img)
+            qemu_img('create', '-f', iotests.imgfmt,
+                     '-o', 'backing_file=%s' % backing_img, child_img)
+            opts.append("children.%d.file.filename=%s" % (i, child_img))
+            opts.append("children.%d.node-name=node%d" % (i, i))
+
+        # Attach the drive to the VM
+        self.vm = iotests.VM()
+        self.vm.add_drive(path = None, opts = ','.join(opts))
+        self.vm.launch()
+
+    def tearDown(self):
+        self.vm.shutdown()
+        for img in self.children:
+            os.remove(img)
+        for img in self.backing:
+            os.remove(img)
+
+    def test_stream_quorum(self):
+        if not iotests.supports_quorum():
+            return
+
+        self.assertNotEqual(qemu_io('-f', iotests.imgfmt, '-c', 'map', self.children[0]),
+                            qemu_io('-f', iotests.imgfmt, '-c', 'map', self.backing[0]),
+                            'image file map matches backing file before streaming')
+
+        self.assert_no_active_block_jobs()
+
+        result = self.vm.qmp('block-stream', device='node0', job_id='stream-node0')
+        self.assert_qmp(result, 'return', {})
+
+        self.wait_until_completed(drive='stream-node0')
+
+        self.assert_no_active_block_jobs()
+        self.vm.shutdown()
+
+        self.assertEqual(qemu_io('-f', iotests.imgfmt, '-c', 'map', self.children[0]),
+                         qemu_io('-f', iotests.imgfmt, '-c', 'map', self.backing[0]),
+                         'image file map does not match backing file after streaming')
+
 class TestSmallerBackingFile(iotests.QMPTestCase):
     backing_len = 1 * 1024 * 1024 # MB
     image_len = 2 * backing_len

tests/qemu-iotests/030.out

@@ -1,5 +1,5 @@
-..............
+......................
 ----------------------------------------------------------------------
-Ran 14 tests
+Ran 22 tests
 
 OK