The virtio devices require proper memory ordering between
the vcpus and the iothreads.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/tcg-op.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index c07de5d9f8..7aadb37756 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -102,7 +102,19 @@ void tcg_gen_br(TCGLabel *l)
 
 void tcg_gen_mb(TCGBar mb_type)
 {
-    if (tcg_ctx->gen_tb->cflags & CF_PARALLEL) {
+#ifdef CONFIG_USER_ONLY
+    bool parallel = tcg_ctx->gen_tb->cflags & CF_PARALLEL;
+#else
+    /*
+     * It is tempting to elide the barrier in a uniprocessor context.
+     * However, even with a single cpu we have i/o threads running in
+     * parallel, and lack of memory order can result in e.g. virtio
+     * queue entries being read incorrectly.
+     */
+    bool parallel = true;
+#endif
+
+    if (parallel) {
         tcg_gen_op1(INDEX_op_mb, mb_type);
     }
 }
-- 
2.34.1