mirror: Wait only for in-flight operations

mirror_wait_for_free_in_flight_slot() just picks a random operation to
wait for. However, a MirrorOp is already in s->ops_in_flight when
mirror_co_read() waits for free slots, so if not enough slots are
immediately available, an operation can end up waiting for itself, or
two or more operations can wait for each other to complete, which
results in a hang.

Fix this by adding a flag to MirrorOp that tells us if the request is
already in flight (and therefore occupies slots that it will later
free), and picking only such operations for waiting.

Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1794692
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20200326153628.4869-3-kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

diff --git a/block/mirror.c b/block/mirror.c
index 5879e634733f9875e86561d0111d0194714602f9..c26fd9260d892eaa4273abb81789fd039d1076a6 100644 (file)
--- a/block/mirror.c
+++ b/block/mirror.c
@@ -102,6 +102,7 @@ struct MirrorOp {
 
     bool is_pseudo_op;
     bool is_active_write;
+    bool is_in_flight;
     CoQueue waiting_requests;
     Coroutine *co;
 
@@ -293,7 +294,9 @@ mirror_wait_for_any_operation(MirrorBlockJob *s, bool active)
          * caller of this function.  Since there is only one pseudo op
          * at any given time, we will always find some real operation
          * to wait on. */
-        if (!op->is_pseudo_op && op->is_active_write == active) {
+        if (!op->is_pseudo_op && op->is_in_flight &&
+            op->is_active_write == active)
+        {
             qemu_co_queue_wait(&op->waiting_requests, NULL);
             return;
         }
@@ -367,6 +370,7 @@ static void coroutine_fn mirror_co_read(void *opaque)
     /* Copy the dirty cluster.  */
     s->in_flight++;
     s->bytes_in_flight += op->bytes;
+    op->is_in_flight = true;
     trace_mirror_one_iteration(s, op->offset, op->bytes);
 
     ret = bdrv_co_preadv(s->mirror_top_bs->backing, op->offset, op->bytes,
@@ -382,6 +386,7 @@ static void coroutine_fn mirror_co_zero(void *opaque)
     op->s->in_flight++;
     op->s->bytes_in_flight += op->bytes;
     *op->bytes_handled = op->bytes;
+    op->is_in_flight = true;
 
     ret = blk_co_pwrite_zeroes(op->s->target, op->offset, op->bytes,
                                op->s->unmap ? BDRV_REQ_MAY_UNMAP : 0);
@@ -396,6 +401,7 @@ static void coroutine_fn mirror_co_discard(void *opaque)
     op->s->in_flight++;
     op->s->bytes_in_flight += op->bytes;
     *op->bytes_handled = op->bytes;
+    op->is_in_flight = true;
 
     ret = blk_co_pdiscard(op->s->target, op->offset, op->bytes);
     mirror_write_complete(op, ret);
@@ -1319,6 +1325,7 @@ static MirrorOp *coroutine_fn active_write_prepare(MirrorBlockJob *s,
         .offset             = offset,
         .bytes              = bytes,
         .is_active_write    = true,
+        .is_in_flight       = true,
     };
     qemu_co_queue_init(&op->waiting_requests);
     QTAILQ_INSERT_TAIL(&s->ops_in_flight, op, next);