block: plug whole tree at once, introduce bdrv_io_unplugged_begin/end

Extract the handling of io_plug "depth" from linux-aio.c and let the
main bdrv_drain loop do nothing but wait on I/O.

Like the two newly introduced functions, bdrv_io_plug and bdrv_io_unplug
now operate on all children.  The visit order is now symmetrical between
plug and unplug, making it possible for formats to implement plug/unplug.

Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

6 files changed, 71 insertions, 44 deletions

diff --git a/block/io.c b/block/io.c
index b798040e52..b903270115 100644
--- a/block/io.c
+++ b/block/io.c
@@ -253,7 +253,6 @@ static void bdrv_drain_poll(BlockDriverState *bs)
 
     while (busy) {
         /* Keep iterating */
-        bdrv_flush_io_queue(bs);
         busy = bdrv_requests_pending(bs);
         busy |= aio_poll(bdrv_get_aio_context(bs), busy);
     }
@@ -307,20 +306,24 @@ static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
 void coroutine_fn bdrv_co_drain(BlockDriverState *bs)
 {
     bdrv_no_throttling_begin(bs);
+    bdrv_io_unplugged_begin(bs);
     bdrv_drain_recurse(bs);
     bdrv_co_yield_to_drain(bs);
+    bdrv_io_unplugged_end(bs);
     bdrv_no_throttling_end(bs);
 }
 
 void bdrv_drain(BlockDriverState *bs)
 {
     bdrv_no_throttling_begin(bs);
+    bdrv_io_unplugged_begin(bs);
     bdrv_drain_recurse(bs);
     if (qemu_in_coroutine()) {
         bdrv_co_yield_to_drain(bs);
     } else {
         bdrv_drain_poll(bs);
     }
+    bdrv_io_unplugged_end(bs);
     bdrv_no_throttling_end(bs);
 }
 
@@ -345,6 +348,7 @@ void bdrv_drain_all(void)
             block_job_pause(bs->job);
         }
         bdrv_no_throttling_begin(bs);
+        bdrv_io_unplugged_begin(bs);
         bdrv_drain_recurse(bs);
         aio_context_release(aio_context);
 
@@ -369,7 +373,6 @@ void bdrv_drain_all(void)
             aio_context_acquire(aio_context);
             while ((bs = bdrv_next(bs))) {
                 if (aio_context == bdrv_get_aio_context(bs)) {
-                    bdrv_flush_io_queue(bs);
                     if (bdrv_requests_pending(bs)) {
                         busy = true;
                         aio_poll(aio_context, busy);
@@ -386,6 +389,7 @@ void bdrv_drain_all(void)
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
         aio_context_acquire(aio_context);
+        bdrv_io_unplugged_end(bs);
         bdrv_no_throttling_end(bs);
         if (bs->job) {
             block_job_resume(bs->job);
@@ -2756,31 +2760,67 @@ void bdrv_add_before_write_notifier(BlockDriverState *bs,
 
 void bdrv_io_plug(BlockDriverState *bs)
 {
-    BlockDriver *drv = bs->drv;
-    if (drv && drv->bdrv_io_plug) {
-        drv->bdrv_io_plug(bs);
-    } else if (bs->file) {
-        bdrv_io_plug(bs->file->bs);
+    BdrvChild *child;
+
+    QLIST_FOREACH(child, &bs->children, next) {
+        bdrv_io_plug(child->bs);
+    }
+
+    if (bs->io_plugged++ == 0 && bs->io_plug_disabled == 0) {
+        BlockDriver *drv = bs->drv;
+        if (drv && drv->bdrv_io_plug) {
+            drv->bdrv_io_plug(bs);
+        }
     }
 }
 
 void bdrv_io_unplug(BlockDriverState *bs)
 {
-    BlockDriver *drv = bs->drv;
-    if (drv && drv->bdrv_io_unplug) {
-        drv->bdrv_io_unplug(bs);
-    } else if (bs->file) {
-        bdrv_io_unplug(bs->file->bs);
+    BdrvChild *child;
+
+    assert(bs->io_plugged);
+    if (--bs->io_plugged == 0 && bs->io_plug_disabled == 0) {
+        BlockDriver *drv = bs->drv;
+        if (drv && drv->bdrv_io_unplug) {
+            drv->bdrv_io_unplug(bs);
+        }
+    }
+
+    QLIST_FOREACH(child, &bs->children, next) {
+        bdrv_io_unplug(child->bs);
     }
 }
 
-void bdrv_flush_io_queue(BlockDriverState *bs)
+void bdrv_io_unplugged_begin(BlockDriverState *bs)
 {
-    BlockDriver *drv = bs->drv;
-    if (drv && drv->bdrv_flush_io_queue) {
-        drv->bdrv_flush_io_queue(bs);
-    } else if (bs->file) {
-        bdrv_flush_io_queue(bs->file->bs);
+    BdrvChild *child;
+
+    if (bs->io_plug_disabled++ == 0 && bs->io_plugged > 0) {
+        BlockDriver *drv = bs->drv;
+        if (drv && drv->bdrv_io_unplug) {
+            drv->bdrv_io_unplug(bs);
+        }
+    }
+
+    QLIST_FOREACH(child, &bs->children, next) {
+        bdrv_io_unplugged_begin(child->bs);
+    }
+}
+
+void bdrv_io_unplugged_end(BlockDriverState *bs)
+{
+    BdrvChild *child;
+
+    assert(bs->io_plug_disabled);
+    QLIST_FOREACH(child, &bs->children, next) {
+        bdrv_io_unplugged_end(child->bs);
+    }
+
+    if (--bs->io_plug_disabled == 0 && bs->io_plugged > 0) {
+        BlockDriver *drv = bs->drv;
+        if (drv && drv->bdrv_io_plug) {
+            drv->bdrv_io_plug(bs);
+        }
     }
 }
 
diff --git a/block/linux-aio.c b/block/linux-aio.c
index 805757e02e..102bf928af 100644
--- a/block/linux-aio.c
+++ b/block/linux-aio.c
@@ -220,19 +220,16 @@ void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
 {
     struct qemu_laio_state *s = aio_ctx;
 
-    s->io_q.plugged++;
+    assert(!s->io_q.plugged);
+    s->io_q.plugged = 1;
 }
 
-void laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
+void laio_io_unplug(BlockDriverState *bs, void *aio_ctx)
 {
     struct qemu_laio_state *s = aio_ctx;
 
-    assert(s->io_q.plugged > 0 || !unplug);
-
-    if (unplug && --s->io_q.plugged > 0) {
-        return;
-    }
-
+    assert(s->io_q.plugged);
+    s->io_q.plugged = 0;
     if (!s->io_q.blocked && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
         ioq_submit(s);
     }
diff --git a/block/raw-aio.h b/block/raw-aio.h
index 811e375018..0f5e35a7ec 100644
--- a/block/raw-aio.h
+++ b/block/raw-aio.h
@@ -43,7 +43,7 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
 void laio_detach_aio_context(void *s, AioContext *old_context);
 void laio_attach_aio_context(void *s, AioContext *new_context);
 void laio_io_plug(BlockDriverState *bs, void *aio_ctx);
-void laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug);
+void laio_io_unplug(BlockDriverState *bs, void *aio_ctx);
 #endif
 
 #ifdef _WIN32
diff --git a/block/raw-posix.c b/block/raw-posix.c
index 906d5c9411..50135ad383 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -1345,17 +1345,7 @@ static void raw_aio_unplug(BlockDriverState *bs)
 #ifdef CONFIG_LINUX_AIO
     BDRVRawState *s = bs->opaque;
     if (s->use_aio) {
-        laio_io_unplug(bs, s->aio_ctx, true);
-    }
-#endif
-}
-
-static void raw_aio_flush_io_queue(BlockDriverState *bs)
-{
-#ifdef CONFIG_LINUX_AIO
-    BDRVRawState *s = bs->opaque;
-    if (s->use_aio) {
-        laio_io_unplug(bs, s->aio_ctx, false);
+        laio_io_unplug(bs, s->aio_ctx);
     }
 #endif
 }
@@ -1949,7 +1939,6 @@ BlockDriver bdrv_file = {
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
-    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate = raw_truncate,
     .bdrv_getlength = raw_getlength,
@@ -2398,7 +2387,6 @@ static BlockDriver bdrv_host_device = {
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
-    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength	= raw_getlength,
@@ -2528,7 +2516,6 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
-    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,
@@ -2664,7 +2651,6 @@ static BlockDriver bdrv_host_cdrom = {
     .bdrv_refresh_limits = raw_refresh_limits,
     .bdrv_io_plug = raw_aio_plug,
     .bdrv_io_unplug = raw_aio_unplug,
-    .bdrv_flush_io_queue = raw_aio_flush_io_queue,
 
     .bdrv_truncate      = raw_truncate,
     .bdrv_getlength      = raw_getlength,
diff --git a/include/block/block.h b/include/block/block.h
index 3a731377db..0e8b4d1341 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -520,7 +520,8 @@ int bdrv_probe_geometry(BlockDriverState *bs, HDGeometry *geo);
 
 void bdrv_io_plug(BlockDriverState *bs);
 void bdrv_io_unplug(BlockDriverState *bs);
-void bdrv_flush_io_queue(BlockDriverState *bs);
+void bdrv_io_unplugged_begin(BlockDriverState *bs);
+void bdrv_io_unplugged_end(BlockDriverState *bs);
 
 /**
  * bdrv_drained_begin:
diff --git a/include/block/block_int.h b/include/block/block_int.h
index ed9314b615..f1aabb9103 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -294,7 +294,6 @@ struct BlockDriver {
     /* io queue for linux-aio */
     void (*bdrv_io_plug)(BlockDriverState *bs);
     void (*bdrv_io_unplug)(BlockDriverState *bs);
-    void (*bdrv_flush_io_queue)(BlockDriverState *bs);
 
     /**
      * Try to get @bs's logical and physical block size.
@@ -484,6 +483,10 @@ struct BlockDriverState {
     uint64_t write_threshold_offset;
     NotifierWithReturn write_threshold_notifier;
 
+    /* counters for nested bdrv_io_plug and bdrv_io_unplugged_begin */
+    unsigned io_plugged;
+    unsigned io_plug_disabled;
+
     int quiesce_counter;
 };