diff mbox series

[PULL,6/9] migration/rdma.c: Swap synchronize_rcu for call_rcu

Message ID 20190925150130.12303-7-dgilbert@redhat.com
State New
Headers show
Series [PULL,1/9] migration: fix vmdesc leak on vmstate_save() error | expand

Commit Message

Dr. David Alan Gilbert Sept. 25, 2019, 3:01 p.m. UTC 
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>

This fixes a deadlock that can occur on the migration source after
a failed RDMA migration;  as the source tries to cleanup it
clears a pair of pointers and uses synchronize_rcu to wait; this
is happening on the main thread.  With the CPUs running
a CPU thread can be an rcu reader and attempt to grab the main lock
(kvm_handle_io->address_space_write->flatview_write->flatview_write_continue->
prepare_mmio_access->qemu_mutex_lock_iothread_impl)

Replace the synchronize_rcu with a call_rcu to postpone the freeing.

Fixes: 74637e6f08fceda98806 ("migration: implement bi-directional RDMA QIOChannel")

( https://bugzilla.redhat.com/show_bug.cgi?id=1746787 )

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20190913163507.1403-3-dgilbert@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 migration/rdma.c | 39 +++++++++++++++++++++++++++------------
 1 file changed, 27 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/migration/rdma.c b/migration/rdma.c
index 0fcf02f48e..4c74e88a37 100644
--- a/migration/rdma.c
+++ b/migration/rdma.c
@@ -3017,11 +3017,35 @@  static void qio_channel_rdma_set_aio_fd_handler(QIOChannel *ioc,
     }
 }
 
+struct rdma_close_rcu {
+    struct rcu_head rcu;
+    RDMAContext *rdmain;
+    RDMAContext *rdmaout;
+};
+
+/* callback from qio_channel_rdma_close via call_rcu */
+static void qio_channel_rdma_close_rcu(struct rdma_close_rcu *rcu)
+{
+    if (rcu->rdmain) {
+        qemu_rdma_cleanup(rcu->rdmain);
+    }
+
+    if (rcu->rdmaout) {
+        qemu_rdma_cleanup(rcu->rdmaout);
+    }
+
+    g_free(rcu->rdmain);
+    g_free(rcu->rdmaout);
+    g_free(rcu);
+}
+
 static int qio_channel_rdma_close(QIOChannel *ioc,
                                   Error **errp)
 {
     QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc);
     RDMAContext *rdmain, *rdmaout;
+    struct rdma_close_rcu *rcu = g_new(struct rdma_close_rcu, 1);
+
     trace_qemu_rdma_close();
 
     rdmain = rioc->rdmain;
@@ -3034,18 +3058,9 @@  static int qio_channel_rdma_close(QIOChannel *ioc,
         atomic_rcu_set(&rioc->rdmaout, NULL);
     }
 
-    synchronize_rcu();
-
-    if (rdmain) {
-        qemu_rdma_cleanup(rdmain);
-    }
-
-    if (rdmaout) {
-        qemu_rdma_cleanup(rdmaout);
-    }
-
-    g_free(rdmain);
-    g_free(rdmaout);
+    rcu->rdmain = rdmain;
+    rcu->rdmaout = rdmaout;
+    call_rcu(rcu, qio_channel_rdma_close_rcu, rcu);
 
     return 0;
 }