stream: Deal with filters

Because of the (not so recent anymore) changes that make the stream job
independent of the base node and instead track the node above it, we
have to split that "bottom" node into two cases: The bottom COW node,
and the node directly above the base node (which may be an R/W filter
or the bottom COW node).

Signed-off-by: Max Reitz <mreitz@redhat.com>

block/stream.c

@@ -31,7 +31,8 @@ enum {
 
 typedef struct StreamBlockJob {
     BlockJob common;
-    BlockDriverState *bottom;
+    BlockDriverState *base_overlay; /* COW overlay (stream from this) */
+    BlockDriverState *above_base;   /* Node directly above the base */
     BlockdevOnError on_error;
     char *backing_file_str;
     bool bs_read_only;
@@ -53,7 +54,7 @@ static void stream_abort(Job *job)
 
     if (s->chain_frozen) {
         BlockJob *bjob = &s->common;
-        bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->bottom);
+        bdrv_unfreeze_backing_chain(blk_bs(bjob->blk), s->above_base);
     }
 }
 
@@ -62,14 +63,15 @@ static int stream_prepare(Job *job)
     StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
     BlockJob *bjob = &s->common;
     BlockDriverState *bs = blk_bs(bjob->blk);
-    BlockDriverState *base = backing_bs(s->bottom);
+    BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs);
+    BlockDriverState *base = bdrv_filter_or_cow_bs(s->above_base);
     Error *local_err = NULL;
     int ret = 0;
 
-    bdrv_unfreeze_backing_chain(bs, s->bottom);
+    bdrv_unfreeze_backing_chain(bs, s->above_base);
     s->chain_frozen = false;
 
-    if (bs->backing) {
+    if (bdrv_cow_child(unfiltered_bs)) {
         const char *base_id = NULL, *base_fmt = NULL;
         if (base) {
             base_id = s->backing_file_str;
@@ -77,8 +79,8 @@ static int stream_prepare(Job *job)
                 base_fmt = base->drv->format_name;
             }
         }
-        bdrv_set_backing_hd(bs, base, &local_err);
+        bdrv_set_backing_hd(unfiltered_bs, base, &local_err);
-        ret = bdrv_change_backing_file(bs, base_id, base_fmt, false);
+        ret = bdrv_change_backing_file(unfiltered_bs, base_id, base_fmt, false);
         if (local_err) {
             error_report_err(local_err);
             return -EPERM;
@@ -109,14 +111,15 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
     StreamBlockJob *s = container_of(job, StreamBlockJob, common.job);
     BlockBackend *blk = s->common.blk;
     BlockDriverState *bs = blk_bs(blk);
-    bool enable_cor = !backing_bs(s->bottom);
+    BlockDriverState *unfiltered_bs = bdrv_skip_filters(bs);
+    bool enable_cor = !bdrv_cow_child(s->base_overlay);
     int64_t len;
     int64_t offset = 0;
     uint64_t delay_ns = 0;
     int error = 0;
     int64_t n = 0; /* bytes */
 
-    if (bs == s->bottom) {
+    if (unfiltered_bs == s->base_overlay) {
         /* Nothing to stream */
         return 0;
     }
@@ -150,13 +153,14 @@ static int coroutine_fn stream_run(Job *job, Error **errp)
 
         copy = false;
 
-        ret = bdrv_is_allocated(bs, offset, STREAM_CHUNK, &n);
+        ret = bdrv_is_allocated(unfiltered_bs, offset, STREAM_CHUNK, &n);
         if (ret == 1) {
             /* Allocated in the top, no need to copy.  */
         } else if (ret >= 0) {
             /* Copy if allocated in the intermediate images.  Limit to the
              * known-unallocated area [offset, offset+n*BDRV_SECTOR_SIZE).  */
-            ret = bdrv_is_allocated_above(backing_bs(bs), s->bottom, true,
+            ret = bdrv_is_allocated_above(bdrv_cow_bs(unfiltered_bs),
+                                          s->base_overlay, true,
                                           offset, n, &n);
             /* Finish early if end of backing file has been reached */
             if (ret == 0 && n == 0) {
@@ -223,9 +227,29 @@ void stream_start(const char *job_id, BlockDriverState *bs,
     BlockDriverState *iter;
     bool bs_read_only;
     int basic_flags = BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED;
-    BlockDriverState *bottom = bdrv_find_overlay(bs, base);
+    BlockDriverState *base_overlay = bdrv_find_overlay(bs, base);
+    BlockDriverState *above_base;
 
-    if (bdrv_freeze_backing_chain(bs, bottom, errp) < 0) {
+    if (!base_overlay) {
+        error_setg(errp, "'%s' is not in the backing chain of '%s'",
+                   base->node_name, bs->node_name);
+        return;
+    }
+
+    /*
+     * Find the node directly above @base.  @base_overlay is a COW overlay, so
+     * it must have a bdrv_cow_child(), but it is the immediate overlay of
+     * @base, so between the two there can only be filters.
+     */
+    above_base = base_overlay;
+    if (bdrv_cow_bs(above_base) != base) {
+        above_base = bdrv_cow_bs(above_base);
+        while (bdrv_filter_bs(above_base) != base) {
+            above_base = bdrv_filter_bs(above_base);
+        }
+    }
+
+    if (bdrv_freeze_backing_chain(bs, above_base, errp) < 0) {
         return;
     }
 
@@ -255,14 +279,19 @@ void stream_start(const char *job_id, BlockDriverState *bs,
      * and resizes. Reassign the base node pointer because the backing BS of the
      * bottom node might change after the call to bdrv_reopen_set_read_only()
      * due to parallel block jobs running.
+     * above_base node might change after the call to
+     * bdrv_reopen_set_read_only() due to parallel block jobs running.
      */
-    base = backing_bs(bottom);
+    base = bdrv_filter_or_cow_bs(above_base);
-    for (iter = backing_bs(bs); iter && iter != base; iter = backing_bs(iter)) {
+    for (iter = bdrv_filter_or_cow_bs(bs); iter != base;
+         iter = bdrv_filter_or_cow_bs(iter))
+    {
         block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
                            basic_flags, &error_abort);
     }
 
-    s->bottom = bottom;
+    s->base_overlay = base_overlay;
+    s->above_base = above_base;
     s->backing_file_str = g_strdup(backing_file_str);
     s->bs_read_only = bs_read_only;
     s->chain_frozen = true;
@@ -276,5 +305,5 @@ fail:
     if (bs_read_only) {
         bdrv_reopen_set_read_only(bs, true, NULL);
     }
-    bdrv_unfreeze_backing_chain(bs, bottom);
+    bdrv_unfreeze_backing_chain(bs, above_base);
 }

blockdev.c

@@ -2528,7 +2528,9 @@ void qmp_block_stream(bool has_job_id, const char *job_id, const char *device,
     }
 
     /* Check for op blockers in the whole chain between bs and base */
-    for (iter = bs; iter && iter != base_bs; iter = backing_bs(iter)) {
+    for (iter = bs; iter && iter != base_bs;
+         iter = bdrv_filter_or_cow_bs(iter))
+    {
         if (bdrv_op_is_blocked(iter, BLOCK_OP_TYPE_STREAM, errp)) {
             goto out;
         }

qapi/block-core.json

@@ -2484,13 +2484,20 @@
 # 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
+# its backing chain.  This can be used to stream a subset of the backing file
-# file as its backing file.  This can be used to stream a subset of the backing
+# chain instead of flattening the entire image.
-# file chain instead of flattening the entire image.
+# When streaming completes the image file will have the base file as its backing
+# file, unless that node was changed while the job was running.  In that case,
+# base's parent's backing (or filtered, whichever exists) child (i.e., base at
+# the beginning of the job) will be the new backing file.
 #
 # On successful completion the image file is updated to drop the backing file
 # and the BLOCK_JOB_COMPLETED event is emitted.
 #
+# In case @device is a filter node, block-stream modifies the first non-filter
+# overlay node below it to point to the new backing node instead of modifying
+# @device itself.
+#
 # @job-id: identifier for the newly-created block job. If
 #          omitted, the device name will be used. (Since 2.7)
 #