1 files changed, 153 insertions, 23 deletions

diff --git a/block/commit.c b/block/commit.c
index c284e8535d..22a0a4db98 100644
--- a/block/commit.c
+++ b/block/commit.c
@@ -36,6 +36,7 @@ typedef struct CommitBlockJob {
     BlockJob common;
     RateLimit limit;
     BlockDriverState *active;
+    BlockDriverState *commit_top_bs;
     BlockBackend *top;
     BlockBackend *base;
     BlockdevOnError on_error;
@@ -83,12 +84,23 @@ static void commit_complete(BlockJob *job, void *opaque)
     BlockDriverState *active = s->active;
     BlockDriverState *top = blk_bs(s->top);
     BlockDriverState *base = blk_bs(s->base);
-    BlockDriverState *overlay_bs = bdrv_find_overlay(active, top);
+    BlockDriverState *overlay_bs = bdrv_find_overlay(active, s->commit_top_bs);
     int ret = data->ret;
+    bool remove_commit_top_bs = false;
+
+    /* Remove base node parent that still uses BLK_PERM_WRITE/RESIZE before
+     * the normal backing chain can be restored. */
+    blk_unref(s->base);
 
     if (!block_job_is_cancelled(&s->common) && ret == 0) {
         /* success */
-        ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
+        ret = bdrv_drop_intermediate(active, s->commit_top_bs, base,
+                                     s->backing_file_str);
+    } else if (overlay_bs) {
+        /* XXX Can (or should) we somehow keep 'consistent read' blocked even
+         * after the failed/cancelled commit job is gone? If we already wrote
+         * something to base, the intermediate images aren't valid any more. */
+        remove_commit_top_bs = true;
     }
 
     /* restore base open flags here if appropriate (e.g., change the base back
@@ -102,9 +114,15 @@ static void commit_complete(BlockJob *job, void *opaque)
     }
     g_free(s->backing_file_str);
     blk_unref(s->top);
-    blk_unref(s->base);
     block_job_completed(&s->common, ret);
     g_free(data);
+
+    /* If bdrv_drop_intermediate() didn't already do that, remove the commit
+     * filter driver from the backing chain. Do this as the final step so that
+     * the 'consistent read' permission can be granted.  */
+    if (remove_commit_top_bs) {
+        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+    }
 }
 
 static void coroutine_fn commit_run(void *opaque)
@@ -208,10 +226,38 @@ static const BlockJobDriver commit_job_driver = {
     .start         = commit_run,
 };
 
+static int coroutine_fn bdrv_commit_top_preadv(BlockDriverState *bs,
+    uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags)
+{
+    return bdrv_co_preadv(bs->backing, offset, bytes, qiov, flags);
+}
+
+static void bdrv_commit_top_close(BlockDriverState *bs)
+{
+}
+
+static void bdrv_commit_top_child_perm(BlockDriverState *bs, BdrvChild *c,
+                                       const BdrvChildRole *role,
+                                       uint64_t perm, uint64_t shared,
+                                       uint64_t *nperm, uint64_t *nshared)
+{
+    *nperm = 0;
+    *nshared = BLK_PERM_ALL;
+}
+
+/* Dummy node that provides consistent read to its users without requiring it
+ * from its backing file and that allows writes on the backing file chain. */
+static BlockDriver bdrv_commit_top = {
+    .format_name        = "commit_top",
+    .bdrv_co_preadv     = bdrv_commit_top_preadv,
+    .bdrv_close         = bdrv_commit_top_close,
+    .bdrv_child_perm    = bdrv_commit_top_child_perm,
+};
+
 void commit_start(const char *job_id, BlockDriverState *bs,
                   BlockDriverState *base, BlockDriverState *top, int64_t speed,
                   BlockdevOnError on_error, const char *backing_file_str,
-                  Error **errp)
+                  const char *filter_node_name, Error **errp)
 {
     CommitBlockJob *s;
     BlockReopenQueue *reopen_queue = NULL;
@@ -219,7 +265,9 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     int orig_base_flags;
     BlockDriverState *iter;
     BlockDriverState *overlay_bs;
+    BlockDriverState *commit_top_bs = NULL;
     Error *local_err = NULL;
+    int ret;
 
     assert(top != bs);
     if (top == base) {
@@ -234,8 +282,8 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         return;
     }
 
-    s = block_job_create(job_id, &commit_job_driver, bs, speed,
-                         BLOCK_JOB_DEFAULT, NULL, NULL, errp);
+    s = block_job_create(job_id, &commit_job_driver, bs, 0, BLK_PERM_ALL,
+                         speed, BLOCK_JOB_DEFAULT, NULL, NULL, errp);
     if (!s) {
         return;
     }
@@ -256,30 +304,70 @@ void commit_start(const char *job_id, BlockDriverState *bs,
         bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err);
         if (local_err != NULL) {
             error_propagate(errp, local_err);
-            block_job_unref(&s->common);
-            return;
+            goto fail;
         }
     }
 
+    /* Insert commit_top block node above top, so we can block consistent read
+     * on the backing chain below it */
+    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, filter_node_name, 0,
+                                         errp);
+    if (commit_top_bs == NULL) {
+        goto fail;
+    }
+
+    bdrv_set_backing_hd(commit_top_bs, top, &error_abort);
+    bdrv_set_backing_hd(overlay_bs, commit_top_bs, &error_abort);
+
+    s->commit_top_bs = commit_top_bs;
+    bdrv_unref(commit_top_bs);
 
     /* Block all nodes between top and base, because they will
      * disappear from the chain after this operation. */
     assert(bdrv_chain_contains(top, base));
-    for (iter = top; iter != backing_bs(base); iter = backing_bs(iter)) {
-        block_job_add_bdrv(&s->common, iter);
+    for (iter = top; iter != base; iter = backing_bs(iter)) {
+        /* XXX BLK_PERM_WRITE needs to be allowed so we don't block ourselves
+         * at s->base (if writes are blocked for a node, they are also blocked
+         * for its backing file). The other options would be a second filter
+         * driver above s->base. */
+        ret = block_job_add_bdrv(&s->common, "intermediate node", iter, 0,
+                                 BLK_PERM_WRITE_UNCHANGED | BLK_PERM_WRITE,
+                                 errp);
+        if (ret < 0) {
+            goto fail;
+        }
+    }
+
+    ret = block_job_add_bdrv(&s->common, "base", base, 0, BLK_PERM_ALL, errp);
+    if (ret < 0) {
+        goto fail;
     }
+
     /* overlay_bs must be blocked because it needs to be modified to
-     * update the backing image string, but if it's the root node then
-     * don't block it again */
-    if (bs != overlay_bs) {
-        block_job_add_bdrv(&s->common, overlay_bs);
+     * update the backing image string. */
+    ret = block_job_add_bdrv(&s->common, "overlay of top", overlay_bs,
+                             BLK_PERM_GRAPH_MOD, BLK_PERM_ALL, errp);
+    if (ret < 0) {
+        goto fail;
     }
 
-    s->base = blk_new();
-    blk_insert_bs(s->base, base);
+    s->base = blk_new(BLK_PERM_CONSISTENT_READ
+                      | BLK_PERM_WRITE
+                      | BLK_PERM_RESIZE,
+                      BLK_PERM_CONSISTENT_READ
+                      | BLK_PERM_GRAPH_MOD
+                      | BLK_PERM_WRITE_UNCHANGED);
+    ret = blk_insert_bs(s->base, base, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
-    s->top = blk_new();
-    blk_insert_bs(s->top, top);
+    /* Required permissions are already taken with block_job_add_bdrv() */
+    s->top = blk_new(0, BLK_PERM_ALL);
+    blk_insert_bs(s->top, top, errp);
+    if (ret < 0) {
+        goto fail;
+    }
 
     s->active = bs;
 
@@ -292,6 +380,19 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 
     trace_commit_start(bs, base, top, s);
     block_job_start(&s->common);
+    return;
+
+fail:
+    if (s->base) {
+        blk_unref(s->base);
+    }
+    if (s->top) {
+        blk_unref(s->top);
+    }
+    if (commit_top_bs) {
+        bdrv_set_backing_hd(overlay_bs, top, &error_abort);
+    }
+    block_job_unref(&s->common);
 }
 
 
@@ -301,11 +402,14 @@ void commit_start(const char *job_id, BlockDriverState *bs,
 int bdrv_commit(BlockDriverState *bs)
 {
     BlockBackend *src, *backing;
+    BlockDriverState *backing_file_bs = NULL;
+    BlockDriverState *commit_top_bs = NULL;
     BlockDriver *drv = bs->drv;
     int64_t sector, total_sectors, length, backing_length;
     int n, ro, open_flags;
     int ret = 0;
     uint8_t *buf = NULL;
+    Error *local_err = NULL;
 
     if (!drv)
         return -ENOMEDIUM;
@@ -328,11 +432,33 @@ int bdrv_commit(BlockDriverState *bs)
         }
     }
 
-    src = blk_new();
-    blk_insert_bs(src, bs);
+    src = blk_new(BLK_PERM_CONSISTENT_READ, BLK_PERM_ALL);
+    backing = blk_new(BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL);
 
-    backing = blk_new();
-    blk_insert_bs(backing, bs->backing->bs);
+    ret = blk_insert_bs(src, bs, &local_err);
+    if (ret < 0) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
+
+    /* Insert commit_top block node above backing, so we can write to it */
+    backing_file_bs = backing_bs(bs);
+
+    commit_top_bs = bdrv_new_open_driver(&bdrv_commit_top, NULL, BDRV_O_RDWR,
+                                         &local_err);
+    if (commit_top_bs == NULL) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
+
+    bdrv_set_backing_hd(commit_top_bs, backing_file_bs, &error_abort);
+    bdrv_set_backing_hd(bs, commit_top_bs, &error_abort);
+
+    ret = blk_insert_bs(backing, backing_file_bs, &local_err);
+    if (ret < 0) {
+        error_report_err(local_err);
+        goto ro_cleanup;
+    }
 
     length = blk_getlength(src);
     if (length < 0) {
@@ -404,8 +530,12 @@ int bdrv_commit(BlockDriverState *bs)
 ro_cleanup:
     qemu_vfree(buf);
 
-    blk_unref(src);
     blk_unref(backing);
+    if (backing_file_bs) {
+        bdrv_set_backing_hd(bs, backing_file_bs, &error_abort);
+    }
+    bdrv_unref(commit_top_bs);
+    blk_unref(src);
 
     if (ro) {
         /* ignoring error return here */