[Qemu-devel] [RFC PATCH v2 04/19] replay: don't drain/flush bdrv queue while RR is working

[Pavel Dovgalyuk]

In record/replay mode bdrv queue is controlled by replay mechanism.
It does not allow saving or loading the snapshots
when bdrv queue is not empty. Stopping the VM is not blocked by nonempty
queue, but flushing the queue is still impossible there,
because it may cause deadlocks in replay mode.
This patch disables bdrv_drain_all and bdrv_flush_all in
record/replay mode.

Signed-off-by: Pavel Dovgalyuk <address@hidden>
---
 block/io.c |   22 ++++++++++++++++++++++
 cpus.c     |    2 --
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/block/io.c b/block/io.c
index bd9a19a..1ceefbc 100644
--- a/block/io.c
+++ b/block/io.c
@@ -32,6 +32,7 @@
 #include "qemu/cutils.h"
 #include "qapi/error.h"
 #include "qemu/error-report.h"
+#include "sysemu/replay.h"
 
 #define NOT_DONE 0x7fffffff /* used while emulated sync operation in progress 
*/
 
@@ -407,6 +408,13 @@ void bdrv_drain_all_begin(void)
     BdrvNextIterator it;
     GSList *aio_ctxs = NULL, *ctx;
 
+    /* bdrv queue is managed by record/replay,
+       waiting for finishing the I/O requests may
+       be infinite */
+    if (replay_events_enabled()) {
+        return;
+    }
+
     /* BDRV_POLL_WHILE() for a node can only be called from its own I/O thread
      * or the main loop AioContext. We potentially use BDRV_POLL_WHILE() on
      * nodes in several different AioContexts, so make sure we're in the main
@@ -458,6 +466,13 @@ void bdrv_drain_all_end(void)
     BlockDriverState *bs;
     BdrvNextIterator it;
 
+    /* bdrv queue is managed by record/replay,
+       waiting for finishing the I/O requests may
+       be endless */
+    if (replay_events_enabled()) {
+        return;
+    }
+
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
@@ -1832,6 +1847,13 @@ int bdrv_flush_all(void)
     BlockDriverState *bs = NULL;
     int result = 0;
 
+    /* bdrv queue is managed by record/replay,
+       creating new flush request for stopping
+       the VM may break the determinism */
+    if (replay_events_enabled()) {
+        return result;
+    }
+
     for (bs = bdrv_first(&it); bs; bs = bdrv_next(&it)) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
         int ret;
diff --git a/cpus.c b/cpus.c
index 38eba8b..140cc4f 100644
--- a/cpus.c
+++ b/cpus.c
@@ -1016,7 +1016,6 @@ static int do_vm_stop(RunState state, bool send_stop)
     }
 
     bdrv_drain_all();
-    replay_disable_events();
     ret = bdrv_flush_all();
 
     return ret;
@@ -2059,7 +2058,6 @@ int vm_prepare_start(void)
         qapi_event_send_stop(&error_abort);
         res = -1;
     } else {
-        replay_enable_events();
         cpu_enable_ticks();
         runstate_set(RUN_STATE_RUNNING);
         vm_state_notify(1, RUN_STATE_RUNNING);