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

Block layer patches

# gpg: Signature made Fri 22 Dec 2017 14:09:01 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: (35 commits)
  block: Keep nodes drained between reopen_queue/multiple
  commit: Simplify reopen of base
  test-bdrv-drain: Test graph changes in drained section
  block: Allow graph changes in subtree drained section
  test-bdrv-drain: Recursive draining with multiple parents
  test-bdrv-drain: Test behaviour in coroutine context
  test-bdrv-drain: Tests for bdrv_subtree_drain
  block: Add bdrv_subtree_drained_begin/end()
  block: Don't notify parents in drain call chain
  test-bdrv-drain: Test nested drain sections
  block: Nested drain_end must still call callbacks
  block: Don't block_job_pause_all() in bdrv_drain_all()
  test-bdrv-drain: Test drain vs. block jobs
  blockjob: Pause job on draining any job BDS
  test-bdrv-drain: Test bs->quiesce_counter
  test-bdrv-drain: Test callback for bdrv_drain
  block: Make bdrv_drain() driver callbacks non-recursive
  block: Assert drain_all is only called from main AioContext
  block: Remove unused bdrv_requests_pending
  block: Mention -drive cyls/heads/secs/trans/serial/addr in deprecation chapter
  ...

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

block.c

@@ -822,6 +822,18 @@ static void bdrv_child_cb_drained_end(BdrvChild *child)
     bdrv_drained_end(bs);
 }
 
+static void bdrv_child_cb_attach(BdrvChild *child)
+{
+    BlockDriverState *bs = child->opaque;
+    bdrv_apply_subtree_drain(child, bs);
+}
+
+static void bdrv_child_cb_detach(BdrvChild *child)
+{
+    BlockDriverState *bs = child->opaque;
+    bdrv_unapply_subtree_drain(child, bs);
+}
+
 static int bdrv_child_cb_inactivate(BdrvChild *child)
 {
     BlockDriverState *bs = child->opaque;
@@ -889,6 +901,8 @@ const BdrvChildRole child_file = {
     .inherit_options = bdrv_inherited_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
+    .attach          = bdrv_child_cb_attach,
+    .detach          = bdrv_child_cb_detach,
     .inactivate      = bdrv_child_cb_inactivate,
 };
 
@@ -911,6 +925,8 @@ const BdrvChildRole child_format = {
     .inherit_options = bdrv_inherited_fmt_options,
     .drained_begin   = bdrv_child_cb_drained_begin,
     .drained_end     = bdrv_child_cb_drained_end,
+    .attach          = bdrv_child_cb_attach,
+    .detach          = bdrv_child_cb_detach,
     .inactivate      = bdrv_child_cb_inactivate,
 };
 
@@ -953,6 +969,8 @@ static void bdrv_backing_attach(BdrvChild *c)
                     parent->backing_blocker);
     bdrv_op_unblock(backing_hd, BLOCK_OP_TYPE_BACKUP_TARGET,
                     parent->backing_blocker);
+
+    bdrv_child_cb_attach(c);
 }
 
 static void bdrv_backing_detach(BdrvChild *c)
@@ -963,6 +981,8 @@ static void bdrv_backing_detach(BdrvChild *c)
     bdrv_op_unblock_all(c->bs, parent->backing_blocker);
     error_free(parent->backing_blocker);
     parent->backing_blocker = NULL;
+
+    bdrv_child_cb_detach(c);
 }
 
 /*
@@ -1924,6 +1944,8 @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
     assert(role == &child_backing || role == &child_file);
 
     if (!backing) {
+        int flags = bdrv_reopen_get_flags(reopen_queue, bs);
+
         /* Apart from the modifications below, the same permissions are
          * forwarded and left alone as for filters */
         bdrv_filter_default_perms(bs, c, role, reopen_queue, perm, shared,
@@ -1936,7 +1958,9 @@ void bdrv_format_default_perms(BlockDriverState *bs, BdrvChild *c,
 
         /* bs->file always needs to be consistent because of the metadata. We
          * can never allow other users to resize or write to it. */
-        perm |= BLK_PERM_CONSISTENT_READ;
+        if (!(flags & BDRV_O_NO_IO)) {
+            perm |= BLK_PERM_CONSISTENT_READ;
+        }
         shared &= ~(BLK_PERM_WRITE | BLK_PERM_RESIZE);
     } else {
         /* We want consistent read from backing files if the parent needs it.
@@ -1968,17 +1992,23 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
                                       BlockDriverState *new_bs)
 {
     BlockDriverState *old_bs = child->bs;
+    int i;
 
     if (old_bs && new_bs) {
         assert(bdrv_get_aio_context(old_bs) == bdrv_get_aio_context(new_bs));
     }
     if (old_bs) {
-        if (old_bs->quiesce_counter && child->role->drained_end) {
-            child->role->drained_end(child);
-        }
+        /* Detach first so that the recursive drain sections coming from @child
+         * are already gone and we only end the drain sections that came from
+         * elsewhere. */
         if (child->role->detach) {
             child->role->detach(child);
         }
+        if (old_bs->quiesce_counter && child->role->drained_end) {
+            for (i = 0; i < old_bs->quiesce_counter; i++) {
+                child->role->drained_end(child);
+            }
+        }
         QLIST_REMOVE(child, next_parent);
     }
 
@@ -1987,9 +2017,14 @@ static void bdrv_replace_child_noperm(BdrvChild *child,
     if (new_bs) {
         QLIST_INSERT_HEAD(&new_bs->parents, child, next_parent);
         if (new_bs->quiesce_counter && child->role->drained_begin) {
-            child->role->drained_begin(child);
+            for (i = 0; i < new_bs->quiesce_counter; i++) {
+                child->role->drained_begin(child);
+            }
         }
 
+        /* Attach only after starting new drained sections, so that recursive
+         * drain sections coming from @child don't get an extra .drained_begin
+         * callback. */
         if (child->role->attach) {
             child->role->attach(child);
         }
@@ -2731,6 +2766,7 @@ BlockDriverState *bdrv_open(const char *filename, const char *reference,
  * returns a pointer to bs_queue, which is either the newly allocated
  * bs_queue, or the existing bs_queue being used.
  *
+ * bs must be drained between bdrv_reopen_queue() and bdrv_reopen_multiple().
  */
 static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
                                                  BlockDriverState *bs,
@@ -2746,6 +2782,11 @@ static BlockReopenQueue *bdrv_reopen_queue_child(BlockReopenQueue *bs_queue,
     BdrvChild *child;
     QDict *old_options, *explicit_options;
 
+    /* Make sure that the caller remembered to use a drained section. This is
+     * important to avoid graph changes between the recursive queuing here and
+     * bdrv_reopen_multiple(). */
+    assert(bs->quiesce_counter > 0);
+
     if (bs_queue == NULL) {
         bs_queue = g_new0(BlockReopenQueue, 1);
         QSIMPLEQ_INIT(bs_queue);
@@ -2870,6 +2911,8 @@ BlockReopenQueue *bdrv_reopen_queue(BlockReopenQueue *bs_queue,
  * If all devices prepare successfully, then the changes are committed
  * to all devices.
  *
+ * All affected nodes must be drained between bdrv_reopen_queue() and
+ * bdrv_reopen_multiple().
  */
 int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **errp)
 {
@@ -2879,11 +2922,8 @@ int bdrv_reopen_multiple(AioContext *ctx, BlockReopenQueue *bs_queue, Error **er
 
     assert(bs_queue != NULL);
 
-    aio_context_release(ctx);
-    bdrv_drain_all_begin();
-    aio_context_acquire(ctx);
-
     QSIMPLEQ_FOREACH(bs_entry, bs_queue, entry) {
+        assert(bs_entry->state.bs->quiesce_counter > 0);
         if (bdrv_reopen_prepare(&bs_entry->state, bs_queue, &local_err)) {
             error_propagate(errp, local_err);
             goto cleanup;
@@ -2912,8 +2952,6 @@ cleanup:
     }
     g_free(bs_queue);
 
-    bdrv_drain_all_end();
-
     return ret;
 }
 
@@ -2923,12 +2961,18 @@ int bdrv_reopen(BlockDriverState *bs, int bdrv_flags, Error **errp)
 {
     int ret = -1;
     Error *local_err = NULL;
-    BlockReopenQueue *queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags);
+    BlockReopenQueue *queue;
 
+    bdrv_subtree_drained_begin(bs);
+
+    queue = bdrv_reopen_queue(NULL, bs, NULL, bdrv_flags);
     ret = bdrv_reopen_multiple(bdrv_get_aio_context(bs), queue, &local_err);
     if (local_err != NULL) {
         error_propagate(errp, local_err);
     }
+
+    bdrv_subtree_drained_end(bs);
+
     return ret;
 }
 
@@ -4601,10 +4645,11 @@ void bdrv_img_create(const char *filename, const char *fmt,
         back_flags = flags;
         back_flags &= ~(BDRV_O_RDWR | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING);
 
+        backing_options = qdict_new();
         if (backing_fmt) {
-            backing_options = qdict_new();
             qdict_put_str(backing_options, "driver", backing_fmt);
         }
+        qdict_put_bool(backing_options, BDRV_OPT_FORCE_SHARE, true);
 
         bs = bdrv_open(full_backing, NULL, backing_options, back_flags,
                        &local_err);
@@ -4754,7 +4799,7 @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
     AioContext *ctx = bdrv_get_aio_context(bs);
 
     aio_disable_external(ctx);
-    bdrv_parent_drained_begin(bs);
+    bdrv_parent_drained_begin(bs, NULL);
     bdrv_drain(bs); /* ensure there are no in-flight requests */
 
     while (aio_poll(ctx, false)) {
@@ -4768,7 +4813,7 @@ void bdrv_set_aio_context(BlockDriverState *bs, AioContext *new_context)
      */
     aio_context_acquire(new_context);
     bdrv_attach_aio_context(bs, new_context);
-    bdrv_parent_drained_end(bs);
+    bdrv_parent_drained_end(bs, NULL);
     aio_enable_external(ctx);
     aio_context_release(new_context);
 }

block/commit.c

@@ -277,7 +277,6 @@ void commit_start(const char *job_id, BlockDriverState *bs,
                   const char *filter_node_name, Error **errp)
 {
     CommitBlockJob *s;
-    BlockReopenQueue *reopen_queue = NULL;
     int orig_base_flags;
     BlockDriverState *iter;
     BlockDriverState *commit_top_bs = NULL;
@@ -299,12 +298,7 @@ void commit_start(const char *job_id, BlockDriverState *bs,
     /* convert base to r/w, if necessary */
     orig_base_flags = bdrv_get_flags(base);
     if (!(orig_base_flags & BDRV_O_RDWR)) {
-        reopen_queue = bdrv_reopen_queue(reopen_queue, base, NULL,
-                                         orig_base_flags | BDRV_O_RDWR);
-    }
-
-    if (reopen_queue) {
-        bdrv_reopen_multiple(bdrv_get_aio_context(bs), reopen_queue, &local_err);
+        bdrv_reopen(base, orig_base_flags | BDRV_O_RDWR, &local_err);
         if (local_err != NULL) {
             error_propagate(errp, local_err);
             goto fail;

block/io.c

@@ -40,22 +40,28 @@
 static int coroutine_fn bdrv_co_do_pwrite_zeroes(BlockDriverState *bs,
     int64_t offset, int bytes, BdrvRequestFlags flags);
 
-void bdrv_parent_drained_begin(BlockDriverState *bs)
+void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore)
 {
     BdrvChild *c, *next;
 
     QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
+        if (c == ignore) {
+            continue;
+        }
         if (c->role->drained_begin) {
             c->role->drained_begin(c);
         }
     }
 }
 
-void bdrv_parent_drained_end(BlockDriverState *bs)
+void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore)
 {
     BdrvChild *c, *next;
 
     QLIST_FOREACH_SAFE(c, &bs->parents, next_parent, next) {
+        if (c == ignore) {
+            continue;
+        }
         if (c->role->drained_end) {
             c->role->drained_end(c);
         }
@@ -134,29 +140,13 @@ void bdrv_disable_copy_on_read(BlockDriverState *bs)
     assert(old >= 1);
 }
 
-/* Check if any requests are in-flight (including throttled requests) */
-bool bdrv_requests_pending(BlockDriverState *bs)
-{
-    BdrvChild *child;
-
-    if (atomic_read(&bs->in_flight)) {
-        return true;
-    }
-
-    QLIST_FOREACH(child, &bs->children, next) {
-        if (bdrv_requests_pending(child->bs)) {
-            return true;
-        }
-    }
-
-    return false;
-}
-
 typedef struct {
     Coroutine *co;
     BlockDriverState *bs;
     bool done;
     bool begin;
+    bool recursive;
+    BdrvChild *parent;
 } BdrvCoDrainData;
 
 static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
@@ -175,8 +165,10 @@ static void coroutine_fn bdrv_drain_invoke_entry(void *opaque)
     bdrv_wakeup(bs);
 }
 
-static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
+/* Recursively call BlockDriver.bdrv_co_drain_begin/end callbacks */
+static void bdrv_drain_invoke(BlockDriverState *bs, bool begin, bool recursive)
 {
+    BdrvChild *child, *tmp;
     BdrvCoDrainData data = { .bs = bs, .done = false, .begin = begin};
 
     if (!bs->drv || (begin && !bs->drv->bdrv_co_drain_begin) ||
@@ -187,16 +179,19 @@ static void bdrv_drain_invoke(BlockDriverState *bs, bool begin)
     data.co = qemu_coroutine_create(bdrv_drain_invoke_entry, &data);
     bdrv_coroutine_enter(bs, data.co);
     BDRV_POLL_WHILE(bs, !data.done);
+
+    if (recursive) {
+        QLIST_FOREACH_SAFE(child, &bs->children, next, tmp) {
+            bdrv_drain_invoke(child->bs, begin, true);
+        }
+    }
 }
 
-static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin)
+static bool bdrv_drain_recurse(BlockDriverState *bs)
 {
     BdrvChild *child, *tmp;
     bool waited;
 
-    /* Ensure any pending metadata writes are submitted to bs->file.  */
-    bdrv_drain_invoke(bs, begin);
-
     /* Wait for drained requests to finish */
     waited = BDRV_POLL_WHILE(bs, atomic_read(&bs->in_flight) > 0);
 
@@ -215,7 +210,7 @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin)
              */
             bdrv_ref(bs);
         }
-        waited |= bdrv_drain_recurse(bs, begin);
+        waited |= bdrv_drain_recurse(bs);
         if (in_main_loop) {
             bdrv_unref(bs);
         }
@@ -224,6 +219,11 @@ static bool bdrv_drain_recurse(BlockDriverState *bs, bool begin)
     return waited;
 }
 
+static void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
+                                  BdrvChild *parent);
+static void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
+                                BdrvChild *parent);
+
 static void bdrv_co_drain_bh_cb(void *opaque)
 {
     BdrvCoDrainData *data = opaque;
@@ -232,9 +232,9 @@ static void bdrv_co_drain_bh_cb(void *opaque)
 
     bdrv_dec_in_flight(bs);
     if (data->begin) {
-        bdrv_drained_begin(bs);
+        bdrv_do_drained_begin(bs, data->recursive, data->parent);
     } else {
-        bdrv_drained_end(bs);
+        bdrv_do_drained_end(bs, data->recursive, data->parent);
     }
 
     data->done = true;
@@ -242,7 +242,8 @@ static void bdrv_co_drain_bh_cb(void *opaque)
 }
 
 static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
-                                                bool begin)
+                                                bool begin, bool recursive,
+                                                BdrvChild *parent)
 {
     BdrvCoDrainData data;
 
@@ -256,6 +257,8 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
         .bs = bs,
         .done = false,
         .begin = begin,
+        .recursive = recursive,
+        .parent = parent,
     };
     bdrv_inc_in_flight(bs);
     aio_bh_schedule_oneshot(bdrv_get_aio_context(bs),
@@ -267,35 +270,97 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs,
     assert(data.done);
 }
 
-void bdrv_drained_begin(BlockDriverState *bs)
+void bdrv_do_drained_begin(BlockDriverState *bs, bool recursive,
+                           BdrvChild *parent)
 {
+    BdrvChild *child, *next;
+
     if (qemu_in_coroutine()) {
-        bdrv_co_yield_to_drain(bs, true);
+        bdrv_co_yield_to_drain(bs, true, recursive, parent);
         return;
     }
 
+    /* Stop things in parent-to-child order */
     if (atomic_fetch_inc(&bs->quiesce_counter) == 0) {
         aio_disable_external(bdrv_get_aio_context(bs));
-        bdrv_parent_drained_begin(bs);
     }
 
-    bdrv_drain_recurse(bs, true);
+    bdrv_parent_drained_begin(bs, parent);
+    bdrv_drain_invoke(bs, true, false);
+    bdrv_drain_recurse(bs);
+
+    if (recursive) {
+        bs->recursive_quiesce_counter++;
+        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
+            bdrv_do_drained_begin(child->bs, true, child);
+        }
+    }
+}
+
+void bdrv_drained_begin(BlockDriverState *bs)
+{
+    bdrv_do_drained_begin(bs, false, NULL);
+}
+
+void bdrv_subtree_drained_begin(BlockDriverState *bs)
+{
+    bdrv_do_drained_begin(bs, true, NULL);
+}
+
+void bdrv_do_drained_end(BlockDriverState *bs, bool recursive,
+                         BdrvChild *parent)
+{
+    BdrvChild *child, *next;
+    int old_quiesce_counter;
+
+    if (qemu_in_coroutine()) {
+        bdrv_co_yield_to_drain(bs, false, recursive, parent);
+        return;
+    }
+    assert(bs->quiesce_counter > 0);
+    old_quiesce_counter = atomic_fetch_dec(&bs->quiesce_counter);
+
+    /* Re-enable things in child-to-parent order */
+    bdrv_drain_invoke(bs, false, false);
+    bdrv_parent_drained_end(bs, parent);
+    if (old_quiesce_counter == 1) {
+        aio_enable_external(bdrv_get_aio_context(bs));
+    }
+
+    if (recursive) {
+        bs->recursive_quiesce_counter--;
+        QLIST_FOREACH_SAFE(child, &bs->children, next, next) {
+            bdrv_do_drained_end(child->bs, true, child);
+        }
+    }
 }
 
 void bdrv_drained_end(BlockDriverState *bs)
 {
-    if (qemu_in_coroutine()) {
-        bdrv_co_yield_to_drain(bs, false);
-        return;
-    }
-    assert(bs->quiesce_counter > 0);
-    if (atomic_fetch_dec(&bs->quiesce_counter) > 1) {
-        return;
-    }
+    bdrv_do_drained_end(bs, false, NULL);
+}
 
-    bdrv_parent_drained_end(bs);
-    bdrv_drain_recurse(bs, false);
-    aio_enable_external(bdrv_get_aio_context(bs));
+void bdrv_subtree_drained_end(BlockDriverState *bs)
+{
+    bdrv_do_drained_end(bs, true, NULL);
+}
+
+void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent)
+{
+    int i;
+
+    for (i = 0; i < new_parent->recursive_quiesce_counter; i++) {
+        bdrv_do_drained_begin(child->bs, true, child);
+    }
+}
+
+void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent)
+{
+    int i;
+
+    for (i = 0; i < old_parent->recursive_quiesce_counter; i++) {
+        bdrv_do_drained_end(child->bs, true, child);
+    }
 }
 
 /*
@@ -342,14 +407,20 @@ void bdrv_drain_all_begin(void)
     BdrvNextIterator it;
     GSList *aio_ctxs = NULL, *ctx;
 
-    block_job_pause_all();
+    /* BDRV_POLL_WHILE() for a node can only be called from its own I/O thread
+     * or the main loop AioContext. We potentially use BDRV_POLL_WHILE() on
+     * nodes in several different AioContexts, so make sure we're in the main
+     * context. */
+    assert(qemu_get_current_aio_context() == qemu_get_aio_context());
 
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
+        /* Stop things in parent-to-child order */
         aio_context_acquire(aio_context);
-        bdrv_parent_drained_begin(bs);
         aio_disable_external(aio_context);
+        bdrv_parent_drained_begin(bs, NULL);
+        bdrv_drain_invoke(bs, true, true);
         aio_context_release(aio_context);
 
         if (!g_slist_find(aio_ctxs, aio_context)) {
@@ -372,7 +443,7 @@ void bdrv_drain_all_begin(void)
             aio_context_acquire(aio_context);
             for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
                 if (aio_context == bdrv_get_aio_context(bs)) {
-                    waited |= bdrv_drain_recurse(bs, true);
+                    waited |= bdrv_drain_recurse(bs);
                 }
             }
             aio_context_release(aio_context);
@@ -390,14 +461,13 @@ void bdrv_drain_all_end(void)
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
+        /* Re-enable things in child-to-parent order */
         aio_context_acquire(aio_context);
+        bdrv_drain_invoke(bs, false, true);
+        bdrv_parent_drained_end(bs, NULL);
         aio_enable_external(aio_context);
-        bdrv_parent_drained_end(bs);
-        bdrv_drain_recurse(bs, false);
         aio_context_release(aio_context);
     }
-
-    block_job_resume_all();
 }
 
 void bdrv_drain_all(void)

block/qcow2.c

@@ -1672,34 +1672,12 @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
     return status;
 }
 
-/* handle reading after the end of the backing file */
-int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
-                        int64_t offset, int bytes)
-{
-    uint64_t bs_size = bs->total_sectors * BDRV_SECTOR_SIZE;
-    int n1;
-
-    if ((offset + bytes) <= bs_size) {
-        return bytes;
-    }
-
-    if (offset >= bs_size) {
-        n1 = 0;
-    } else {
-        n1 = bs_size - offset;
-    }
-
-    qemu_iovec_memset(qiov, n1, 0, bytes - n1);
-
-    return n1;
-}
-
 static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
                                         uint64_t bytes, QEMUIOVector *qiov,
                                         int flags)
 {
     BDRVQcow2State *s = bs->opaque;
-    int offset_in_cluster, n1;
+    int offset_in_cluster;
     int ret;
     unsigned int cur_bytes; /* number of bytes in current iteration */
     uint64_t cluster_offset = 0;
@@ -1734,26 +1712,13 @@ static coroutine_fn int qcow2_co_preadv(BlockDriverState *bs, uint64_t offset,
         case QCOW2_CLUSTER_UNALLOCATED:
 
             if (bs->backing) {
-                /* read from the base image */
-                n1 = qcow2_backing_read1(bs->backing->bs, &hd_qiov,
-                                         offset, cur_bytes);
-                if (n1 > 0) {
-                    QEMUIOVector local_qiov;
-
-                    qemu_iovec_init(&local_qiov, hd_qiov.niov);
-                    qemu_iovec_concat(&local_qiov, &hd_qiov, 0, n1);
-
-                    BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
-                    qemu_co_mutex_unlock(&s->lock);
-                    ret = bdrv_co_preadv(bs->backing, offset, n1,
-                                         &local_qiov, 0);
-                    qemu_co_mutex_lock(&s->lock);
-
-                    qemu_iovec_destroy(&local_qiov);
-
-                    if (ret < 0) {
-                        goto fail;
-                    }
+                BLKDBG_EVENT(bs->file, BLKDBG_READ_BACKING_AIO);
+                qemu_co_mutex_unlock(&s->lock);
+                ret = bdrv_co_preadv(bs->backing, offset, cur_bytes,
+                                     &hd_qiov, 0);
+                qemu_co_mutex_lock(&s->lock);
+                if (ret < 0) {
+                    goto fail;
                 }
             } else {
                 /* Note: in this case, no need to wait */

block/qcow2.h

@@ -528,9 +528,6 @@ uint32_t offset_to_reftable_index(BDRVQcow2State *s, uint64_t offset)
 }
 
 /* qcow2.c functions */
-int qcow2_backing_read1(BlockDriverState *bs, QEMUIOVector *qiov,
-                  int64_t sector_num, int nb_sectors);
-
 int64_t qcow2_refcount_metadata_size(int64_t clusters, size_t cluster_size,
                                      int refcount_order, bool generous_increase,
                                      uint64_t *refblock_count);

block/replication.c

@@ -394,6 +394,9 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable,
         new_secondary_flags = s->orig_secondary_flags;
     }
 
+    bdrv_subtree_drained_begin(s->hidden_disk->bs);
+    bdrv_subtree_drained_begin(s->secondary_disk->bs);
+
     if (orig_hidden_flags != new_hidden_flags) {
         reopen_queue = bdrv_reopen_queue(reopen_queue, s->hidden_disk->bs, NULL,
                                          new_hidden_flags);
@@ -409,6 +412,9 @@ static void reopen_backing_file(BlockDriverState *bs, bool writable,
                              reopen_queue, &local_err);
         error_propagate(errp, local_err);
     }
+
+    bdrv_subtree_drained_end(s->hidden_disk->bs);
+    bdrv_subtree_drained_end(s->secondary_disk->bs);
 }
 
 static void backup_job_cleanup(BlockDriverState *bs)

blockdev.c

@@ -734,10 +734,6 @@ QemuOptsList qemu_legacy_drive_opts = {
             .name = "trans",
             .type = QEMU_OPT_STRING,
             .help = "chs translation (auto, lba, none)",
-        },{
-            .name = "boot",
-            .type = QEMU_OPT_BOOL,
-            .help = "(deprecated, ignored)",
         },{
             .name = "addr",
             .type = QEMU_OPT_STRING,
@@ -873,13 +869,6 @@ DriveInfo *drive_new(QemuOpts *all_opts, BlockInterfaceType block_default_type)
         goto fail;
     }
 
-    /* Deprecated option boot=[on|off] */
-    if (qemu_opt_get(legacy_opts, "boot") != NULL) {
-        fprintf(stderr, "qemu-kvm: boot=on|off is deprecated and will be "
-                "ignored. Future versions will reject this parameter. Please "
-                "update your scripts.\n");
-    }
-
     /* Other deprecated options */
     if (!qtest_enabled()) {
         for (i = 0; i < ARRAY_SIZE(deprecated); i++) {

blockjob.c

@@ -234,26 +234,23 @@ static char *child_job_get_parent_desc(BdrvChild *c)
                            job->id);
 }
 
-static const BdrvChildRole child_job = {
-    .get_parent_desc    = child_job_get_parent_desc,
-    .stay_at_node       = true,
-};
-
-static void block_job_drained_begin(void *opaque)
+static void child_job_drained_begin(BdrvChild *c)
 {
-    BlockJob *job = opaque;
+    BlockJob *job = c->opaque;
     block_job_pause(job);
 }
 
-static void block_job_drained_end(void *opaque)
+static void child_job_drained_end(BdrvChild *c)
 {
-    BlockJob *job = opaque;
+    BlockJob *job = c->opaque;
     block_job_resume(job);
 }
 
-static const BlockDevOps block_job_dev_ops = {
-    .drained_begin = block_job_drained_begin,
-    .drained_end = block_job_drained_end,
+static const BdrvChildRole child_job = {
+    .get_parent_desc    = child_job_get_parent_desc,
+    .drained_begin      = child_job_drained_begin,
+    .drained_end        = child_job_drained_end,
+    .stay_at_node       = true,
 };
 
 void block_job_remove_all_bdrv(BlockJob *job)
@@ -715,7 +712,6 @@ void *block_job_create(const char *job_id, const BlockJobDriver *driver,
     block_job_add_bdrv(job, "main node", bs, 0, BLK_PERM_ALL, &error_abort);
     bs->job = job;
 
-    blk_set_dev_ops(blk, &block_job_dev_ops, job);
     bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
 
     QLIST_INSERT_HEAD(&block_jobs, job, job_list);

hmp.c

@@ -2318,7 +2318,6 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
 {
     BlockBackend *blk;
     BlockBackend *local_blk = NULL;
-    AioContext *aio_context;
     const char* device = qdict_get_str(qdict, "device");
     const char* command = qdict_get_str(qdict, "command");
     Error *err = NULL;
@@ -2338,9 +2337,6 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
         }
     }
 
-    aio_context = blk_get_aio_context(blk);
-    aio_context_acquire(aio_context);
-
     /*
      * Notably absent: Proper permission management. This is sad, but it seems
      * almost impossible to achieve without changing the semantics and thereby
@@ -2368,8 +2364,6 @@ void hmp_qemu_io(Monitor *mon, const QDict *qdict)
      */
     qemuio_command(blk, command);
 
-    aio_context_release(aio_context);
-
 fail:
     blk_unref(local_blk);
     hmp_handle_error(mon, &err);

hw/block/trace-events

@@ -11,6 +11,99 @@ virtio_blk_submit_multireq(void *vdev, void *mrb, int start, int num_reqs, uint6
 hd_geometry_lchs_guess(void *blk, int cyls, int heads, int secs) "blk %p LCHS %d %d %d"
 hd_geometry_guess(void *blk, uint32_t cyls, uint32_t heads, uint32_t secs, int trans) "blk %p CHS %u %u %u trans %d"
 
+# hw/block/nvme.c
+# nvme traces for successful events
+nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u"
+nvme_irq_pin(void) "pulsing IRQ pin"
+nvme_irq_masked(void) "IRQ is masked"
+nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64""
+nvme_rw(char const *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
+nvme_create_sq(uint64_t addr, uint16_t sqid, uint16_t cqid, uint16_t qsize, uint16_t qflags) "create submission queue, addr=0x%"PRIx64", sqid=%"PRIu16", cqid=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16""
+nvme_create_cq(uint64_t addr, uint16_t cqid, uint16_t vector, uint16_t size, uint16_t qflags, int ien) "create completion queue, addr=0x%"PRIx64", cqid=%"PRIu16", vector=%"PRIu16", qsize=%"PRIu16", qflags=%"PRIu16", ien=%d"
+nvme_del_sq(uint16_t qid) "deleting submission queue sqid=%"PRIu16""
+nvme_del_cq(uint16_t cqid) "deleted completion queue, sqid=%"PRIu16""
+nvme_identify_ctrl(void) "identify controller"
+nvme_identify_ns(uint16_t ns) "identify namespace, nsid=%"PRIu16""
+nvme_identify_nslist(uint16_t ns) "identify namespace list, nsid=%"PRIu16""
+nvme_getfeat_vwcache(char const* result) "get feature volatile write cache, result=%s"
+nvme_getfeat_numq(int result) "get feature number of queues, result=%d"
+nvme_setfeat_numq(int reqcq, int reqsq, int gotcq, int gotsq) "requested cq_count=%d sq_count=%d, responding with cq_count=%d sq_count=%d"
+nvme_mmio_intm_set(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask set, data=0x%"PRIx64", new_mask=0x%"PRIx64""
+nvme_mmio_intm_clr(uint64_t data, uint64_t new_mask) "wrote MMIO, interrupt mask clr, data=0x%"PRIx64", new_mask=0x%"PRIx64""
+nvme_mmio_cfg(uint64_t data) "wrote MMIO, config controller config=0x%"PRIx64""
+nvme_mmio_aqattr(uint64_t data) "wrote MMIO, admin queue attributes=0x%"PRIx64""
+nvme_mmio_asqaddr(uint64_t data) "wrote MMIO, admin submission queue address=0x%"PRIx64""
+nvme_mmio_acqaddr(uint64_t data) "wrote MMIO, admin completion queue address=0x%"PRIx64""
+nvme_mmio_asqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin submission queue high half=0x%"PRIx64", new_address=0x%"PRIx64""
+nvme_mmio_acqaddr_hi(uint64_t data, uint64_t new_addr) "wrote MMIO, admin completion queue high half=0x%"PRIx64", new_address=0x%"PRIx64""
+nvme_mmio_start_success(void) "setting controller enable bit succeeded"
+nvme_mmio_stopped(void) "cleared controller enable bit"
+nvme_mmio_shutdown_set(void) "shutdown bit set"
+nvme_mmio_shutdown_cleared(void) "shutdown bit cleared"
+
+# nvme traces for error conditions
+nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size"
+nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64""
+nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
+nvme_err_invalid_prp2_missing(void) "PRP2 is null and more data to be transferred"
+nvme_err_invalid_field(void) "invalid field"
+nvme_err_invalid_prp(void) "invalid PRP"
+nvme_err_invalid_sgl(void) "invalid SGL"
+nvme_err_invalid_ns(uint32_t ns, uint32_t limit) "invalid namespace %u not within 1-%u"
+nvme_err_invalid_opc(uint8_t opc) "invalid opcode 0x%"PRIx8""
+nvme_err_invalid_admin_opc(uint8_t opc) "invalid admin opcode 0x%"PRIx8""
+nvme_err_invalid_lba_range(uint64_t start, uint64_t len, uint64_t limit) "Invalid LBA start=%"PRIu64" len=%"PRIu64" limit=%"PRIu64""
+nvme_err_invalid_del_sq(uint16_t qid) "invalid submission queue deletion, sid=%"PRIu16""
+nvme_err_invalid_create_sq_cqid(uint16_t cqid) "failed creating submission queue, invalid cqid=%"PRIu16""
+nvme_err_invalid_create_sq_sqid(uint16_t sqid) "failed creating submission queue, invalid sqid=%"PRIu16""
+nvme_err_invalid_create_sq_size(uint16_t qsize) "failed creating submission queue, invalid qsize=%"PRIu16""
+nvme_err_invalid_create_sq_addr(uint64_t addr) "failed creating submission queue, addr=0x%"PRIx64""
+nvme_err_invalid_create_sq_qflags(uint16_t qflags) "failed creating submission queue, qflags=%"PRIu16""
+nvme_err_invalid_del_cq_cqid(uint16_t cqid) "failed deleting completion queue, cqid=%"PRIu16""
+nvme_err_invalid_del_cq_notempty(uint16_t cqid) "failed deleting completion queue, it is not empty, cqid=%"PRIu16""
+nvme_err_invalid_create_cq_cqid(uint16_t cqid) "failed creating completion queue, cqid=%"PRIu16""
+nvme_err_invalid_create_cq_size(uint16_t size) "failed creating completion queue, size=%"PRIu16""
+nvme_err_invalid_create_cq_addr(uint64_t addr) "failed creating completion queue, addr=0x%"PRIx64""
+nvme_err_invalid_create_cq_vector(uint16_t vector) "failed creating completion queue, vector=%"PRIu16""
+nvme_err_invalid_create_cq_qflags(uint16_t qflags) "failed creating completion queue, qflags=%"PRIu16""
+nvme_err_invalid_identify_cns(uint16_t cns) "identify, invalid cns=0x%"PRIx16""
+nvme_err_invalid_getfeat(int dw10) "invalid get features, dw10=0x%"PRIx32""
+nvme_err_invalid_setfeat(uint32_t dw10) "invalid set features, dw10=0x%"PRIx32""
+nvme_err_startfail_cq(void) "nvme_start_ctrl failed because there are non-admin completion queues"
+nvme_err_startfail_sq(void) "nvme_start_ctrl failed because there are non-admin submission queues"
+nvme_err_startfail_nbarasq(void) "nvme_start_ctrl failed because the admin submission queue address is null"
+nvme_err_startfail_nbaracq(void) "nvme_start_ctrl failed because the admin completion queue address is null"
+nvme_err_startfail_asq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin submission queue address is misaligned: 0x%"PRIx64""
+nvme_err_startfail_acq_misaligned(uint64_t addr) "nvme_start_ctrl failed because the admin completion queue address is misaligned: 0x%"PRIx64""
+nvme_err_startfail_page_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too small: log2size=%u, min=%u"
+nvme_err_startfail_page_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the page size is too large: log2size=%u, max=%u"
+nvme_err_startfail_cqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too small: log2size=%u, min=%u"
+nvme_err_startfail_cqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the completion queue entry size is too large: log2size=%u, max=%u"
+nvme_err_startfail_sqent_too_small(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too small: log2size=%u, min=%u"
+nvme_err_startfail_sqent_too_large(uint8_t log2ps, uint8_t maxlog2ps) "nvme_start_ctrl failed because the submission queue entry size is too large: log2size=%u, max=%u"
+nvme_err_startfail_asqent_sz_zero(void) "nvme_start_ctrl failed because the admin submission queue size is zero"
+nvme_err_startfail_acqent_sz_zero(void) "nvme_start_ctrl failed because the admin completion queue size is zero"
+nvme_err_startfail(void) "setting controller enable bit failed"
+
+# Traces for undefined behavior
+nvme_ub_mmiowr_misaligned32(uint64_t offset) "MMIO write not 32-bit aligned, offset=0x%"PRIx64""
+nvme_ub_mmiowr_toosmall(uint64_t offset, unsigned size) "MMIO write smaller than 32 bits, offset=0x%"PRIx64", size=%u"
+nvme_ub_mmiowr_intmask_with_msix(void) "undefined access to interrupt mask set when MSI-X is enabled"
+nvme_ub_mmiowr_ro_csts(void) "attempted to set a read only bit of controller status"
+nvme_ub_mmiowr_ssreset_w1c_unsupported(void) "attempted to W1C CSTS.NSSRO but CAP.NSSRS is zero (not supported)"
+nvme_ub_mmiowr_ssreset_unsupported(void) "attempted NVM subsystem reset but CAP.NSSRS is zero (not supported)"
+nvme_ub_mmiowr_cmbloc_reserved(void) "invalid write to reserved CMBLOC when CMBSZ is zero, ignored"
+nvme_ub_mmiowr_cmbsz_readonly(void) "invalid write to read only CMBSZ, ignored"
+nvme_ub_mmiowr_invalid(uint64_t offset, uint64_t data) "invalid MMIO write, offset=0x%"PRIx64", data=0x%"PRIx64""
+nvme_ub_mmiord_misaligned32(uint64_t offset) "MMIO read not 32-bit aligned, offset=0x%"PRIx64""
+nvme_ub_mmiord_toosmall(uint64_t offset) "MMIO read smaller than 32-bits, offset=0x%"PRIx64""
+nvme_ub_mmiord_invalid_ofs(uint64_t offset) "MMIO read beyond last register, offset=0x%"PRIx64", returning 0"
+nvme_ub_db_wr_misaligned(uint64_t offset) "doorbell write not 32-bit aligned, offset=0x%"PRIx64", ignoring"
+nvme_ub_db_wr_invalid_cq(uint32_t qid) "completion queue doorbell write for nonexistent queue, cqid=%"PRIu32", ignoring"
+nvme_ub_db_wr_invalid_cqhead(uint32_t qid, uint16_t new_head) "completion queue doorbell write value beyond queue size, cqid=%"PRIu32", new_head=%"PRIu16", ignoring"
+nvme_ub_db_wr_invalid_sq(uint32_t qid) "submission queue doorbell write for nonexistent queue, sqid=%"PRIu32", ignoring"
+nvme_ub_db_wr_invalid_sqtail(uint32_t qid, uint16_t new_tail) "submission queue doorbell write value beyond queue size, sqid=%"PRIu32", new_head=%"PRIu16", ignoring"
+
 # hw/block/xen_disk.c
 xen_disk_alloc(char *name) "%s"
 xen_disk_init(char *name) "%s"

include/block/block.h

@@ -585,7 +585,7 @@ void bdrv_io_unplug(BlockDriverState *bs);
  * Begin a quiesced section of all users of @bs. This is part of
  * bdrv_drained_begin.
  */
-void bdrv_parent_drained_begin(BlockDriverState *bs);
+void bdrv_parent_drained_begin(BlockDriverState *bs, BdrvChild *ignore);
 
 /**
  * bdrv_parent_drained_end:
@@ -593,7 +593,7 @@ void bdrv_parent_drained_begin(BlockDriverState *bs);
  * End a quiesced section of all users of @bs. This is part of
  * bdrv_drained_end.
  */
-void bdrv_parent_drained_end(BlockDriverState *bs);
+void bdrv_parent_drained_end(BlockDriverState *bs, BdrvChild *ignore);
 
 /**
  * bdrv_drained_begin:
@@ -607,6 +607,12 @@ void bdrv_parent_drained_end(BlockDriverState *bs);
  */
 void bdrv_drained_begin(BlockDriverState *bs);
 
+/**
+ * Like bdrv_drained_begin, but recursively begins a quiesced section for
+ * exclusive access to all child nodes as well.
+ */
+void bdrv_subtree_drained_begin(BlockDriverState *bs);
+
 /**
  * bdrv_drained_end:
  *
@@ -614,6 +620,11 @@ void bdrv_drained_begin(BlockDriverState *bs);
  */
 void bdrv_drained_end(BlockDriverState *bs);
 
+/**
+ * End a quiescent section started by bdrv_subtree_drained_begin().
+ */
+void bdrv_subtree_drained_end(BlockDriverState *bs);
+
 void bdrv_add_child(BlockDriverState *parent, BlockDriverState *child,
                     Error **errp);
 void bdrv_del_child(BlockDriverState *parent, BdrvChild *child, Error **errp);

include/block/block_int.h

@@ -717,6 +717,8 @@ struct BlockDriverState {
 
     /* Accessed with atomic ops.  */
     int quiesce_counter;
+    int recursive_quiesce_counter;
+
     unsigned int write_gen;               /* Current data generation */
 
     /* Protected by reqs_lock.  */
@@ -768,6 +770,9 @@ int coroutine_fn bdrv_co_pwritev(BdrvChild *child,
     int64_t offset, unsigned int bytes, QEMUIOVector *qiov,
     BdrvRequestFlags flags);
 
+void bdrv_apply_subtree_drain(BdrvChild *child, BlockDriverState *new_parent);
+void bdrv_unapply_subtree_drain(BdrvChild *child, BlockDriverState *old_parent);
+
 int get_tmp_filename(char *filename, int size);
 BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
                             const char *filename);
@@ -1045,7 +1050,6 @@ bool blk_dev_is_tray_open(BlockBackend *blk);
 bool blk_dev_is_medium_locked(BlockBackend *blk);
 
 void bdrv_set_dirty(BlockDriverState *bs, int64_t offset, int64_t bytes);
-bool bdrv_requests_pending(BlockDriverState *bs);
 
 void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out);
 void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in);

qapi/block-core.json

@@ -3918,6 +3918,10 @@
 # does not support all kinds of operations, all kinds of children, nor
 # all block drivers.
 #
+# FIXME Removing children from a quorum node means introducing gaps in the
+# child indices. This cannot be represented in the 'children' list of
+# BlockdevOptionsQuorum, as returned by .bdrv_refresh_filename().
+#
 # Warning: The data in a new quorum child MUST be consistent with that of
 # the rest of the array.
 #

qemu-doc.texi

@@ -2589,12 +2589,6 @@ deprecated.
 
 @section System emulator command line arguments
 
-@subsection -drive boot=on|off (since 1.3.0)
-
-The ``boot=on|off'' option to the ``-drive'' argument is
-ignored. Applications should use the ``bootindex=N'' parameter
-to set an absolute ordering between devices instead.
-
 @subsection -tdf (since 1.3.0)
 
 The ``-tdf'' argument is ignored. The behaviour implemented
@@ -2690,20 +2684,27 @@ longer be directly supported in QEMU.
 The ``-drive if=scsi'' argument is replaced by the the
 ``-device BUS-TYPE'' argument combined with ``-drive if=none''.
 
+@subsection -drive cyls=...,heads=...,secs=...,trans=... (since 2.10.0)
+
+The drive geometry arguments are replaced by the the geometry arguments
+that can be specified with the ``-device'' parameter.
+
+@subsection -drive serial=... (since 2.10.0)
+
+The drive serial argument is replaced by the the serial argument
+that can be specified with the ``-device'' parameter.
+
+@subsection -drive addr=... (since 2.10.0)
+
+The drive addr argument is replaced by the the addr argument
+that can be specified with the ``-device'' parameter.
+
 @subsection -net dump (since 2.10.0)
 
 The ``--net dump'' argument is now replaced with the
 ``-object filter-dump'' argument which works in combination
 with the modern ``-netdev`` backends instead.
 
-@subsection -hdachs (since 2.10.0)
-
-The ``-hdachs'' argument is now a synonym for setting
-the ``cyls'', ``heads'', ``secs'', and ``trans'' properties
-on the ``ide-hd'' device using the ``-device'' argument.
-The new syntax allows different settings to be provided
-per disk.
-
 @subsection -usbdevice (since 2.10.0)
 
 The ``-usbdevice DEV'' argument is now a synonym for setting

qemu-io-cmds.c

@@ -2013,8 +2013,11 @@ static int reopen_f(BlockBackend *blk, int argc, char **argv)
     opts = qopts ? qemu_opts_to_qdict(qopts, NULL) : NULL;
     qemu_opts_reset(&reopen_opts);
 
+    bdrv_subtree_drained_begin(bs);
     brq = bdrv_reopen_queue(NULL, bs, opts, flags);
     bdrv_reopen_multiple(bdrv_get_aio_context(bs), brq, &local_err);
+    bdrv_subtree_drained_end(bs);
+
     if (local_err) {
         error_report_err(local_err);
     } else {

qemu-options.hx

@@ -846,8 +846,8 @@ of available connectors of a given interface type.
 @item media=@var{media}
 This option defines the type of the media: disk or cdrom.
 @item cyls=@var{c},heads=@var{h},secs=@var{s}[,trans=@var{t}]
-These options have the same definition as they have in @option{-hdachs}.
-These parameters are deprecated, use the corresponding parameters
+Force disk physical geometry and the optional BIOS translation (trans=none or
+lba). These parameters are deprecated, use the corresponding parameters
 of @code{-device} instead.
 @item snapshot=@var{snapshot}
 @var{snapshot} is "on" or "off" and controls snapshot mode for the given drive
@@ -1027,21 +1027,6 @@ the raw disk image you use is not written back. You can however force
 the write back by pressing @key{C-a s} (@pxref{disk_images}).
 ETEXI
 
-DEF("hdachs", HAS_ARG, QEMU_OPTION_hdachs, \
-    "-hdachs c,h,s[,t]\n" \
-    "                force hard disk 0 physical geometry and the optional BIOS\n" \
-    "                translation (t=none or lba) (usually QEMU can guess them)\n",
-    QEMU_ARCH_ALL)
-STEXI
-@item -hdachs @var{c},@var{h},@var{s},[,@var{t}]
-@findex -hdachs
-Force hard disk 0 physical geometry (1 <= @var{c} <= 16383, 1 <=
-@var{h} <= 16, 1 <= @var{s} <= 63) and optionally force the BIOS
-translation mode (@var{t}=none, lba or auto). Usually QEMU can guess
-all those parameters. This option is deprecated, please use
-@code{-device ide-hd,cyls=c,heads=h,secs=s,...} instead.
-ETEXI
-
 DEF("fsdev", HAS_ARG, QEMU_OPTION_fsdev,
     "-fsdev fsdriver,id=id[,path=path,][security_model={mapped-xattr|mapped-file|passthrough|none}]\n"
     " [,writeout=immediate][,readonly][,socket=socket|sock_fd=sock_fd][,fmode=fmode][,dmode=dmode]\n"

tests/Makefile.include

@@ -80,6 +80,7 @@ gcov-files-test-thread-pool-y = thread-pool.c
 gcov-files-test-hbitmap-y = util/hbitmap.c
 check-unit-y += tests/test-hbitmap$(EXESUF)
 gcov-files-test-hbitmap-y = blockjob.c
+check-unit-y += tests/test-bdrv-drain$(EXESUF)
 check-unit-y += tests/test-blockjob$(EXESUF)
 check-unit-y += tests/test-blockjob-txn$(EXESUF)
 check-unit-y += tests/test-x86-cpuid$(EXESUF)
@@ -595,6 +596,7 @@ tests/test-coroutine$(EXESUF): tests/test-coroutine.o $(test-block-obj-y)
 tests/test-aio$(EXESUF): tests/test-aio.o $(test-block-obj-y)
 tests/test-aio-multithread$(EXESUF): tests/test-aio-multithread.o $(test-block-obj-y)
 tests/test-throttle$(EXESUF): tests/test-throttle.o $(test-block-obj-y)
+tests/test-bdrv-drain$(EXESUF): tests/test-bdrv-drain.o $(test-block-obj-y) $(test-util-obj-y)
 tests/test-blockjob$(EXESUF): tests/test-blockjob.o $(test-block-obj-y) $(test-util-obj-y)
 tests/test-blockjob-txn$(EXESUF): tests/test-blockjob-txn.o $(test-block-obj-y) $(test-util-obj-y)
 tests/test-thread-pool$(EXESUF): tests/test-thread-pool.o $(test-block-obj-y)

tests/qemu-iotests/197

@@ -60,6 +60,10 @@ echo '=== Copy-on-read ==='
 echo
 
 # Prep the images
+# VPC rounds image sizes to a specific geometry, force a specific size.
+if [ "$IMGFMT" = "vpc" ]; then
+    IMGOPTS=$(_optstr_add "$IMGOPTS" "force_size")
+fi
 _make_test_img 4G
 $QEMU_IO -c "write -P 55 3G 1k" "$TEST_IMG" | _filter_qemu_io
 IMGPROTO=file IMGFMT=qcow2 IMGOPTS= TEST_IMG_FILE="$TEST_WRAP" \

tests/qemu-iotests/common.filter

@@ -134,7 +134,8 @@ _filter_img_create()
         -e "s# log_size=[0-9]\\+##g" \
         -e "s# refcount_bits=[0-9]\\+##g" \
         -e "s# key-secret=[a-zA-Z0-9]\\+##g" \
-        -e "s# iter-time=[0-9]\\+##g"
+        -e "s# iter-time=[0-9]\\+##g" \
+        -e "s# force_size=\\(on\\|off\\)##g"
 }
 
 _filter_img_info()