[Qemu-devel] [PATCH v3 05/12] block: Introduce "drained begin/end" API

[Fam Zheng <famz@redhat.com>]

The semantics is that after bdrv_drained_begin(bs), bs will not get new external
requests until the matching bdrv_drained_end(bs).

Signed-off-by: Fam Zheng <famz@redhat.com>
---
 block.c                   |  2 ++
 block/io.c                | 17 +++++++++++++++++
 include/block/block.h     | 19 +++++++++++++++++++
 include/block/block_int.h |  2 ++
 4 files changed, 40 insertions(+)

diff --git a/block.c b/block.c
index 1f90b47..9b28a07 100644
--- a/block.c
+++ b/block.c
@@ -2058,6 +2058,8 @@ static void bdrv_move_feature_fields(BlockDriverState *bs_dest,
     bs_dest->device_list = bs_src->device_list;
     bs_dest->blk = bs_src->blk;
 
+    bs_dest->quiesce_counter = bs_src->quiesce_counter;
+
     memcpy(bs_dest->op_blockers, bs_src->op_blockers,
            sizeof(bs_dest->op_blockers));
 }
diff --git a/block/io.c b/block/io.c
index 17293c3..a331a19 100644
--- a/block/io.c
+++ b/block/io.c
@@ -2618,3 +2618,20 @@ void bdrv_flush_io_queue(BlockDriverState *bs)
     }
     bdrv_start_throttled_reqs(bs);
 }
+
+void bdrv_drained_begin(BlockDriverState *bs)
+{
+    if (!bs->quiesce_counter++) {
+        aio_disable_external(bdrv_get_aio_context(bs));
+    }
+    bdrv_drain(bs);
+}
+
+void bdrv_drained_end(BlockDriverState *bs)
+{
+    assert(bs->quiesce_counter > 0);
+    if (--bs->quiesce_counter > 0) {
+        return;
+    }
+    aio_enable_external(bdrv_get_aio_context(bs));
+}
diff --git a/include/block/block.h b/include/block/block.h
index 2dd6630..c4f6eef 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -619,4 +619,23 @@ void bdrv_flush_io_queue(BlockDriverState *bs);
 
 BlockAcctStats *bdrv_get_stats(BlockDriverState *bs);
 
+/**
+ * bdrv_drained_begin:
+ *
+ * Begin a quiesced section for exclusive access to the BDS, by disabling
+ * external request sources including NBD server and device model. Note that
+ * this doesn't block timers or coroutines from submitting more requests, which
+ * means block_job_pause is still necessary.
+ *
+ * This function can be recursive.
+ */
+void bdrv_drained_begin(BlockDriverState *bs);
+
+/**
+ * bdrv_drained_end:
+ *
+ * End a quiescent section started by bdrv_drained_begin().
+ */
+void bdrv_drained_end(BlockDriverState *bs);
+
 #endif
diff --git a/include/block/block_int.h b/include/block/block_int.h
index 14ad4c3..7c58221 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -456,6 +456,8 @@ struct BlockDriverState {
     /* threshold limit for writes, in bytes. "High water mark". */
     uint64_t write_threshold_offset;
     NotifierWithReturn write_threshold_notifier;
+
+    int quiesce_counter;
 };
 
 
-- 
2.4.3