[PATCH v4 5/6] net/colo-compare.c, softmmu/vl.c: Check that colo-compare is active

[Lukas Straub]

If the colo-compare object is removed before failover and a
checkpoint happens, qemu crashes because it tries to lock
the destroyed event_mtx in colo_notify_compares_event.

Fix this by checking if everything is initialized by
introducing a new variable colo_compare_active which
is protected by a new mutex colo_compare_mutex. The new mutex
also protects against concurrent access of the net_compares
list and makes sure that colo_notify_compares_event isn't
active while we destroy event_mtx and event_complete_cond.

With this it also is again possible to use colo without
colo-compare (periodic mode) and to use multiple colo-compare
for multiple network interfaces.

Signed-off-by: Lukas Straub <lukasstra...@web.de>
---
 net/colo-compare.c | 35 +++++++++++++++++++++++++++++------
 net/colo-compare.h |  1 +
 softmmu/vl.c       |  2 ++
 3 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/net/colo-compare.c b/net/colo-compare.c
index 56db3d3bfc..c7572d75e9 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -54,6 +54,8 @@ static NotifierList colo_compare_notifiers =
 #define REGULAR_PACKET_CHECK_MS 3000
 #define DEFAULT_TIME_OUT_MS 3000
 
+static QemuMutex colo_compare_mutex;
+static bool colo_compare_active;
 static QemuMutex event_mtx;
 static QemuCond event_complete_cond;
 static int event_unhandled_count;
@@ -906,6 +908,12 @@ static void check_old_packet_regular(void *opaque)
 void colo_notify_compares_event(void *opaque, int event, Error **errp)
 {
     CompareState *s;
+    qemu_mutex_lock(&colo_compare_mutex);
+
+    if (!colo_compare_active) {
+        qemu_mutex_unlock(&colo_compare_mutex);
+        return;
+    }
 
     qemu_mutex_lock(&event_mtx);
     QTAILQ_FOREACH(s, &net_compares, next) {
@@ -919,6 +927,7 @@ void colo_notify_compares_event(void *opaque, int event, 
Error **errp)
     }
 
     qemu_mutex_unlock(&event_mtx);
+    qemu_mutex_unlock(&colo_compare_mutex);
 }
 
 static void colo_compare_timer_init(CompareState *s)
@@ -1274,7 +1283,14 @@ static void colo_compare_complete(UserCreatable *uc, 
Error **errp)
                            s->vnet_hdr);
     }
 
+    qemu_mutex_lock(&colo_compare_mutex);
+    if (!colo_compare_active) {
+        qemu_mutex_init(&event_mtx);
+        qemu_cond_init(&event_complete_cond);
+        colo_compare_active = true;
+    }
     QTAILQ_INSERT_TAIL(&net_compares, s, next);
+    qemu_mutex_unlock(&colo_compare_mutex);
 
     s->out_sendco.s = s;
     s->out_sendco.chr = &s->chr_out;
@@ -1290,9 +1306,6 @@ static void colo_compare_complete(UserCreatable *uc, 
Error **errp)
 
     g_queue_init(&s->conn_list);
 
-    qemu_mutex_init(&event_mtx);
-    qemu_cond_init(&event_complete_cond);
-
     s->connection_track_table = g_hash_table_new_full(connection_key_hash,
                                                       connection_key_equal,
                                                       g_free,
@@ -1384,12 +1397,19 @@ static void colo_compare_finalize(Object *obj)
 
     qemu_bh_delete(s->event_bh);
 
+    qemu_mutex_lock(&colo_compare_mutex);
     QTAILQ_FOREACH(tmp, &net_compares, next) {
         if (tmp == s) {
             QTAILQ_REMOVE(&net_compares, s, next);
             break;
         }
     }
+    if (QTAILQ_EMPTY(&net_compares)) {
+        colo_compare_active = false;
+        qemu_mutex_destroy(&event_mtx);
+        qemu_cond_destroy(&event_complete_cond);
+    }
+    qemu_mutex_unlock(&colo_compare_mutex);
 
     AioContext *ctx = iothread_get_aio_context(s->iothread);
     aio_context_acquire(ctx);
@@ -1413,15 +1433,18 @@ static void colo_compare_finalize(Object *obj)
         object_unref(OBJECT(s->iothread));
     }
 
-    qemu_mutex_destroy(&event_mtx);
-    qemu_cond_destroy(&event_complete_cond);
-
     g_free(s->pri_indev);
     g_free(s->sec_indev);
     g_free(s->outdev);
     g_free(s->notify_dev);
 }
 
+void colo_compare_init_globals(void)
+{
+    colo_compare_active = false;
+    qemu_mutex_init(&colo_compare_mutex);
+}
+
 static const TypeInfo colo_compare_info = {
     .name = TYPE_COLO_COMPARE,
     .parent = TYPE_OBJECT,
diff --git a/net/colo-compare.h b/net/colo-compare.h
index 22ddd512e2..eb483ac586 100644
--- a/net/colo-compare.h
+++ b/net/colo-compare.h
@@ -17,6 +17,7 @@
 #ifndef QEMU_COLO_COMPARE_H
 #define QEMU_COLO_COMPARE_H
 
+void colo_compare_init_globals(void);
 void colo_notify_compares_event(void *opaque, int event, Error **errp);
 void colo_compare_register_notifier(Notifier *notify);
 void colo_compare_unregister_notifier(Notifier *notify);
diff --git a/softmmu/vl.c b/softmmu/vl.c
index 32c0047889..a913ed5469 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -112,6 +112,7 @@
 #include "qapi/qmp/qerror.h"
 #include "sysemu/iothread.h"
 #include "qemu/guest-random.h"
+#include "net/colo-compare.h"
 
 #define MAX_VIRTIO_CONSOLES 1
 
@@ -2906,6 +2907,7 @@ void qemu_init(int argc, char **argv, char **envp)
     precopy_infrastructure_init();
     postcopy_infrastructure_init();
     monitor_init_globals();
+    colo_compare_init_globals();
 
     if (qcrypto_init(&err) < 0) {
         error_reportf_err(err, "cannot initialize crypto: ");
-- 
2.20.1

pgpTI1w_fdPlR.pgp
Description: OpenPGP digital signature