block: Add replaces argument to drive-mirror

drive-mirror will bdrv_swap the new BDS named node-name with the one
pointed by replaces when the mirroring is finished.

Signed-off-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

block.c

@@ -5766,3 +5766,28 @@ bool bdrv_is_first_non_filter(BlockDriverState *candidate)
 
     return false;
 }
+
+BlockDriverState *check_to_replace_node(const char *node_name, Error **errp)
+{
+    BlockDriverState *to_replace_bs = bdrv_find_node(node_name);
+    if (!to_replace_bs) {
+        error_setg(errp, "Node name '%s' not found", node_name);
+        return NULL;
+    }
+
+    if (bdrv_op_is_blocked(to_replace_bs, BLOCK_OP_TYPE_REPLACE, errp)) {
+        return NULL;
+    }
+
+    /* We don't want arbitrary node of the BDS chain to be replaced only the top
+     * most non filter in order to prevent data corruption.
+     * Another benefit is that this tests exclude backing files which are
+     * blocked by the backing blockers.
+     */
+    if (!bdrv_is_first_non_filter(to_replace_bs)) {
+        error_setg(errp, "Only top most non filter can be replaced");
+        return NULL;
+    }
+
+    return to_replace_bs;
+}

block/mirror.c

@@ -32,6 +32,12 @@ typedef struct MirrorBlockJob {
     RateLimit limit;
     BlockDriverState *target;
     BlockDriverState *base;
+    /* The name of the graph node to replace */
+    char *replaces;
+    /* The BDS to replace */
+    BlockDriverState *to_replace;
+    /* Used to block operations on the drive-mirror-replace target */
+    Error *replace_blocker;
     bool is_none_mode;
     BlockdevOnError on_source_error, on_target_error;
     bool synced;
@@ -500,10 +506,14 @@ immediate_exit:
     bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
     bdrv_iostatus_disable(s->target);
     if (s->should_complete && ret == 0) {
-        if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
-            bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
+        BlockDriverState *to_replace = s->common.bs;
+        if (s->to_replace) {
+            to_replace = s->to_replace;
         }
-        bdrv_swap(s->target, s->common.bs);
+        if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
+            bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
+        }
+        bdrv_swap(s->target, to_replace);
         if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
             /* drop the bs loop chain formed by the swap: break the loop then
              * trigger the unref from the top one */
@@ -512,6 +522,12 @@ immediate_exit:
             bdrv_unref(p);
         }
     }
+    if (s->to_replace) {
+        bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
+        error_free(s->replace_blocker);
+        bdrv_unref(s->to_replace);
+    }
+    g_free(s->replaces);
     bdrv_unref(s->target);
     block_job_completed(&s->common, ret);
 }
@@ -550,6 +566,20 @@ static void mirror_complete(BlockJob *job, Error **errp)
         return;
     }
 
+    /* check the target bs is not blocked and block all operations on it */
+    if (s->replaces) {
+        s->to_replace = check_to_replace_node(s->replaces, &local_err);
+        if (!s->to_replace) {
+            error_propagate(errp, local_err);
+            return;
+        }
+
+        error_setg(&s->replace_blocker,
+                   "block device is in use by block-job-complete");
+        bdrv_op_block_all(s->to_replace, s->replace_blocker);
+        bdrv_ref(s->to_replace);
+    }
+
     s->should_complete = true;
     block_job_resume(job);
 }
@@ -572,14 +602,15 @@ static const BlockJobDriver commit_active_job_driver = {
 };
 
 static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
-                            int64_t speed, int64_t granularity,
-                            int64_t buf_size,
-                            BlockdevOnError on_source_error,
-                            BlockdevOnError on_target_error,
-                            BlockDriverCompletionFunc *cb,
-                            void *opaque, Error **errp,
-                            const BlockJobDriver *driver,
-                            bool is_none_mode, BlockDriverState *base)
+                             const char *replaces,
+                             int64_t speed, int64_t granularity,
+                             int64_t buf_size,
+                             BlockdevOnError on_source_error,
+                             BlockdevOnError on_target_error,
+                             BlockDriverCompletionFunc *cb,
+                             void *opaque, Error **errp,
+                             const BlockJobDriver *driver,
+                             bool is_none_mode, BlockDriverState *base)
 {
     MirrorBlockJob *s;
 
@@ -610,6 +641,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
         return;
     }
 
+    s->replaces = g_strdup(replaces);
     s->on_source_error = on_source_error;
     s->on_target_error = on_target_error;
     s->target = target;
@@ -631,6 +663,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
 }
 
 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+                  const char *replaces,
                   int64_t speed, int64_t granularity, int64_t buf_size,
                   MirrorSyncMode mode, BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,
@@ -642,7 +675,8 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
 
     is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
     base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
-    mirror_start_job(bs, target, speed, granularity, buf_size,
+    mirror_start_job(bs, target, replaces,
+                     speed, granularity, buf_size,
                      on_source_error, on_target_error, cb, opaque, errp,
                      &mirror_job_driver, is_none_mode, base);
 }
@@ -690,7 +724,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
     }
 
     bdrv_ref(base);
-    mirror_start_job(bs, base, speed, 0, 0,
+    mirror_start_job(bs, base, NULL, speed, 0, 0,
                      on_error, on_error, cb, opaque, &local_err,
                      &commit_active_job_driver, false, base);
     if (local_err) {

blockdev.c

@@ -2100,6 +2100,7 @@ BlockDeviceInfoList *qmp_query_named_block_nodes(Error **errp)
 void qmp_drive_mirror(const char *device, const char *target,
                       bool has_format, const char *format,
                       bool has_node_name, const char *node_name,
+                      bool has_replaces, const char *replaces,
                       enum MirrorSyncMode sync,
                       bool has_mode, enum NewImageMode mode,
                       bool has_speed, int64_t speed,
@@ -2187,6 +2188,29 @@ void qmp_drive_mirror(const char *device, const char *target,
         return;
     }
 
+    if (has_replaces) {
+        BlockDriverState *to_replace_bs;
+
+        if (!has_node_name) {
+            error_setg(errp, "a node-name must be provided when replacing a"
+                             " named node of the graph");
+            return;
+        }
+
+        to_replace_bs = check_to_replace_node(replaces, &local_err);
+
+        if (!to_replace_bs) {
+            error_propagate(errp, local_err);
+            return;
+        }
+
+        if (size != bdrv_getlength(to_replace_bs)) {
+            error_setg(errp, "cannot replace image with a mirror image of "
+                             "different size");
+            return;
+        }
+    }
+
     if ((sync == MIRROR_SYNC_MODE_FULL || !source)
         && mode != NEW_IMAGE_MODE_EXISTING)
     {
@@ -2231,7 +2255,12 @@ void qmp_drive_mirror(const char *device, const char *target,
         return;
     }
 
-    mirror_start(bs, target_bs, speed, granularity, buf_size, sync,
+    /* pass the node name to replace to mirror start since it's loose coupling
+     * and will allow to check whether the node still exist at mirror completion
+     */
+    mirror_start(bs, target_bs,
+                 has_replaces ? replaces : NULL,
+                 speed, granularity, buf_size, sync,
                  on_source_error, on_target_error,
                  block_job_cb, bs, &local_err);
     if (local_err != NULL) {

hmp.c

@@ -933,7 +933,7 @@ void hmp_drive_mirror(Monitor *mon, const QDict *qdict)
     }
 
     qmp_drive_mirror(device, filename, !!format, format,
-                     false, NULL,
+                     false, NULL, false, NULL,
                      full ? MIRROR_SYNC_MODE_FULL : MIRROR_SYNC_MODE_TOP,
                      true, mode, false, 0, false, 0, false, 0,
                      false, 0, false, 0, &err);

include/block/block.h

@@ -175,6 +175,7 @@ typedef enum BlockOpType {
     BLOCK_OP_TYPE_MIRROR,
     BLOCK_OP_TYPE_RESIZE,
     BLOCK_OP_TYPE_STREAM,
+    BLOCK_OP_TYPE_REPLACE,
     BLOCK_OP_TYPE_MAX,
 } BlockOpType;
 
@@ -314,6 +315,9 @@ bool bdrv_recurse_is_first_non_filter(BlockDriverState *bs,
                                       BlockDriverState *candidate);
 bool bdrv_is_first_non_filter(BlockDriverState *candidate);
 
+/* check if a named node can be replaced when doing drive-mirror */
+BlockDriverState *check_to_replace_node(const char *node_name, Error **errp);
+
 /* async block I/O */
 typedef void BlockDriverDirtyHandler(BlockDriverState *bs, int64_t sector,
                                      int sector_num);

include/block/block_int.h

@@ -489,6 +489,8 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
  * mirror_start:
  * @bs: Block device to operate on.
  * @target: Block device to write to.
+ * @replaces: Block graph node name to replace once the mirror is done. Can
+ *            only be used when full mirroring is selected.
  * @speed: The maximum speed, in bytes per second, or 0 for unlimited.
  * @granularity: The chosen granularity for the dirty bitmap.
  * @buf_size: The amount of data that can be in flight at one time.
@@ -505,6 +507,7 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
  * @bs will be switched to read from @target.
  */
 void mirror_start(BlockDriverState *bs, BlockDriverState *target,
+                  const char *replaces,
                   int64_t speed, int64_t granularity, int64_t buf_size,
                   MirrorSyncMode mode, BlockdevOnError on_source_error,
                   BlockdevOnError on_target_error,

qapi/block-core.json

@@ -768,6 +768,10 @@
 # @node-name: #optional the new block driver state node name in the graph
 #             (Since 2.1)
 #
+# @replaces: #optional with sync=full graph node name to be replaced by the new
+#            image when a whole image copy is done. This can be used to repair
+#            broken Quorum files. (Since 2.1)
+#
 # @mode: #optional whether and how QEMU should create a new image, default is
 #        'absolute-paths'.
 #
@@ -800,7 +804,7 @@
 ##
 { 'command': 'drive-mirror',
   'data': { 'device': 'str', 'target': 'str', '*format': 'str',
-            '*node-name': 'str',
+            '*node-name': 'str', '*replaces': 'str',
             'sync': 'MirrorSyncMode', '*mode': 'NewImageMode',
             '*speed': 'int', '*granularity': 'uint32',
             '*buf-size': 'int', '*on-source-error': 'BlockdevOnError',

qmp-commands.hx

@@ -1293,7 +1293,7 @@ EQMP
     {
         .name       = "drive-mirror",
         .args_type  = "sync:s,device:B,target:s,speed:i?,mode:s?,format:s?,"
-                      "node-name:s?,"
+                      "node-name:s?,replaces:s?,"
                       "on-source-error:s?,on-target-error:s?,"
                       "granularity:i?,buf-size:i?",
         .mhandler.cmd_new = qmp_marshal_input_drive_mirror,
@@ -1317,6 +1317,8 @@ Arguments:
 - "format": format of new image (json-string, optional)
 - "node-name": the name of the new block driver state in the node graph
                (json-string, optional)
+- "replaces": the block driver node name to replace when finished
+              (json-string, optional)
 - "mode": how an image file should be created into the target
   file/device (NewImageMode, optional, default 'absolute-paths')
 - "speed": maximum speed of the streaming job, in bytes per second