[v15,05/24] replay: don't drain/flush bdrv queue while RR is working

Commit Message

Pavel Dovgalyuk March 18, 2019, 9:27 a.m. UTC

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.

Stopping the machine when the IO requests are not finished is needed
for the debugging. E.g., breakpoint may be set at the specified step,
and forcing the IO requests to finish may break the determinism
of the execution.

Signed-off-by: Pavel Dovgalyuk <[e-mail]>
Acked-by: Kevin Wolf <[e-mail]>
---
 block/io.c |   28 ++++++++++++++++++++++++++++
 cpus.c     |    2 --
 2 files changed, 28 insertions(+), 2 deletions(-)

Patch

diff --git a/block/io.c b/block/io.c
index 2ba603c7bc..866fd70d96 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 */
 
@@ -538,6 +539,15 @@  void bdrv_drain_all_begin(void)
         return;
     }
 
+    /*
+     * bdrv queue is managed by record/replay,
+     * waiting for finishing the I/O requests may
+     * be infinite
+     */
+    if (replay_events_enabled()) {
+        return;
+    }
+
     /* AIO_WAIT_WHILE() with a NULL context can only be called from the main
      * loop AioContext, so make sure we're in the main context. */
     assert(qemu_get_current_aio_context() == qemu_get_aio_context());
@@ -566,6 +576,15 @@  void bdrv_drain_all_end(void)
 {
     BlockDriverState *bs = NULL;
 
+    /*
+     * bdrv queue is managed by record/replay,
+     * waiting for finishing the I/O requests may
+     * be endless
+     */
+    if (replay_events_enabled()) {
+        return;
+    }
+
     while ((bs = bdrv_next_all_states(bs))) {
         AioContext *aio_context = bdrv_get_aio_context(bs);
 
@@ -1960,6 +1979,15 @@  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 e83f72b48b..5ff61fbf53 100644
--- a/cpus.c
+++ b/cpus.c
@@ -1078,7 +1078,6 @@  static int do_vm_stop(RunState state, bool send_stop)
     }
 
     bdrv_drain_all();
-    replay_disable_events();
     ret = bdrv_flush_all();
 
     return ret;
@@ -2150,7 +2149,6 @@  int vm_prepare_start(void)
     /* We are sending this now, but the CPUs will be resumed shortly later */
     qapi_event_send_resume();
 
-    replay_enable_events();
     cpu_enable_ticks();
     runstate_set(RUN_STATE_RUNNING);
     vm_state_notify(1, RUN_STATE_RUNNING);