block: Fix hangs in synchronous APIs with iothreads

In the block layer, synchronous APIs are often implemented by creating a
coroutine that calls the asynchronous coroutine-based implementation and
then waiting for completion with BDRV_POLL_WHILE().

For this to work with iothreads (more specifically, when the synchronous
API is called in a thread that is not the home thread of the block
device, so that the coroutine will run in a different thread), we must
make sure to call aio_wait_kick() at the end of the operation. Many
places are missing this, so that BDRV_POLL_WHILE() keeps hanging even if
the condition has long become false.

Note that bdrv_dec_in_flight() involves an aio_wait_kick() call. This
corresponds to the BDRV_POLL_WHILE() in the drain functions, but it is
generally not enough for most other operations because they haven't set
the return value in the coroutine entry stub yet. To avoid race
conditions there, we need to kick after setting the return value.

The race window is small enough that the problem doesn't usually surface
in the common path. However, it does surface and causes easily
reproducible hangs if the operation can return early before even calling
bdrv_inc/dec_in_flight, which many of them do (trivial error or no-op
success paths).

The bug in bdrv_truncate(), bdrv_check() and bdrv_invalidate_cache() is
slightly different: These functions even neglected to schedule the
coroutine in the home thread of the node. This avoids the hang, but is
obviously wrong, too. Fix those to schedule the coroutine in the right
AioContext in addition to adding aio_wait_kick() calls.

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>

1 files changed, 7 insertions, 1 deletions

diff --git a/block/io.c b/block/io.c
index bd9d688f8b..213ca03d8d 100644
--- a/block/io.c
+++ b/block/io.c
@@ -806,6 +806,7 @@ static void coroutine_fn bdrv_rw_co_entry(void *opaque)
                                     rwco->qiov->size, rwco->qiov,
                                     rwco->flags);
     }
+    aio_wait_kick();
 }
 
 /*
@@ -2279,6 +2280,7 @@ static void coroutine_fn bdrv_block_status_above_co_entry(void *opaque)
                                            data->offset, data->bytes,
                                            data->pnum, data->map, data->file);
     data->done = true;
+    aio_wait_kick();
 }
 
 /*
@@ -2438,6 +2440,7 @@ static void coroutine_fn bdrv_co_rw_vmstate_entry(void *opaque)
 {
     BdrvVmstateCo *co = opaque;
     co->ret = bdrv_co_rw_vmstate(co->bs, co->qiov, co->pos, co->is_read);
+    aio_wait_kick();
 }
 
 static inline int
@@ -2559,6 +2562,7 @@ static void coroutine_fn bdrv_flush_co_entry(void *opaque)
     FlushCo *rwco = opaque;
 
     rwco->ret = bdrv_co_flush(rwco->bs);
+    aio_wait_kick();
 }
 
 int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
@@ -2704,6 +2708,7 @@ static void coroutine_fn bdrv_pdiscard_co_entry(void *opaque)
     DiscardCo *rwco = opaque;
 
     rwco->ret = bdrv_co_pdiscard(rwco->child, rwco->offset, rwco->bytes);
+    aio_wait_kick();
 }
 
 int coroutine_fn bdrv_co_pdiscard(BdrvChild *child, int64_t offset, int bytes)
@@ -3217,6 +3222,7 @@ static void coroutine_fn bdrv_truncate_co_entry(void *opaque)
     TruncateCo *tco = opaque;
     tco->ret = bdrv_co_truncate(tco->child, tco->offset, tco->prealloc,
                                 tco->errp);
+    aio_wait_kick();
 }
 
 int bdrv_truncate(BdrvChild *child, int64_t offset, PreallocMode prealloc,
@@ -3236,7 +3242,7 @@ int bdrv_truncate(BdrvChild *child, int64_t offset, PreallocMode prealloc,
         bdrv_truncate_co_entry(&tco);
     } else {
         co = qemu_coroutine_create(bdrv_truncate_co_entry, &tco);
-        qemu_coroutine_enter(co);
+        bdrv_coroutine_enter(child->bs, co);
         BDRV_POLL_WHILE(child->bs, tco.ret == NOT_DONE);
     }