78 lines
3.3 KiB
Diff
78 lines
3.3 KiB
Diff
From 2c14a6831954a59256cc8d1980da0ad705a3a3fa Mon Sep 17 00:00:00 2001
|
|
From: Juan Quintela <quintela@redhat.com>
|
|
Date: Tue, 3 Mar 2020 14:51:37 +0000
|
|
Subject: [PATCH 05/18] migration/multifd: fix destroyed mutex access in
|
|
terminating multifd threads
|
|
|
|
RH-Author: Juan Quintela <quintela@redhat.com>
|
|
Message-id: <20200303145143.149290-5-quintela@redhat.com>
|
|
Patchwork-id: 94119
|
|
O-Subject: [RHEL-AV-8.2.0 qemu-kvm PATCH v2 04/10] migration/multifd: fix destroyed mutex access in terminating multifd threads
|
|
Bugzilla: 1738451
|
|
RH-Acked-by: Laurent Vivier <lvivier@redhat.com>
|
|
RH-Acked-by: Peter Xu <peterx@redhat.com>
|
|
RH-Acked-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
|
|
|
|
From: Jiahui Cen <cenjiahui@huawei.com>
|
|
|
|
One multifd will lock all the other multifds' IOChannel mutex to inform them
|
|
to quit by setting p->quit or shutting down p->c. In this senario, if some
|
|
multifds had already been terminated and multifd_load_cleanup/multifd_save_cleanup
|
|
had destroyed their mutex, it could cause destroyed mutex access when trying
|
|
lock their mutex.
|
|
|
|
Here is the coredump stack:
|
|
#0 0x00007f81a2794437 in raise () from /usr/lib64/libc.so.6
|
|
#1 0x00007f81a2795b28 in abort () from /usr/lib64/libc.so.6
|
|
#2 0x00007f81a278d1b6 in __assert_fail_base () from /usr/lib64/libc.so.6
|
|
#3 0x00007f81a278d262 in __assert_fail () from /usr/lib64/libc.so.6
|
|
#4 0x000055eb1bfadbd3 in qemu_mutex_lock_impl (mutex=0x55eb1e2d1988, file=<optimized out>, line=<optimized out>) at util/qemu-thread-posix.c:64
|
|
#5 0x000055eb1bb4564a in multifd_send_terminate_threads (err=<optimized out>) at migration/ram.c:1015
|
|
#6 0x000055eb1bb4bb7f in multifd_send_thread (opaque=0x55eb1e2d19f8) at migration/ram.c:1171
|
|
#7 0x000055eb1bfad628 in qemu_thread_start (args=0x55eb1e170450) at util/qemu-thread-posix.c:502
|
|
#8 0x00007f81a2b36df5 in start_thread () from /usr/lib64/libpthread.so.0
|
|
#9 0x00007f81a286048d in clone () from /usr/lib64/libc.so.6
|
|
|
|
To fix it up, let's destroy the mutex after all the other multifd threads had
|
|
been terminated.
|
|
|
|
Signed-off-by: Jiahui Cen <cenjiahui@huawei.com>
|
|
Signed-off-by: Ying Fang <fangying1@huawei.com>
|
|
Reviewed-by: Juan Quintela <quintela@redhat.com>
|
|
Signed-off-by: Juan Quintela <quintela@redhat.com>
|
|
(cherry picked from commit 9560a48ecc0c20d87bc458a6db77fba651605819)
|
|
Signed-off-by: Danilo C. L. de Paula <ddepaula@redhat.com>
|
|
---
|
|
migration/ram.c | 8 ++++++++
|
|
1 file changed, 8 insertions(+)
|
|
|
|
diff --git a/migration/ram.c b/migration/ram.c
|
|
index 860f781..6c55c5d 100644
|
|
--- a/migration/ram.c
|
|
+++ b/migration/ram.c
|
|
@@ -1052,6 +1052,10 @@ void multifd_save_cleanup(void)
|
|
if (p->running) {
|
|
qemu_thread_join(&p->thread);
|
|
}
|
|
+ }
|
|
+ for (i = 0; i < migrate_multifd_channels(); i++) {
|
|
+ MultiFDSendParams *p = &multifd_send_state->params[i];
|
|
+
|
|
socket_send_channel_destroy(p->c);
|
|
p->c = NULL;
|
|
qemu_mutex_destroy(&p->mutex);
|
|
@@ -1335,6 +1339,10 @@ int multifd_load_cleanup(Error **errp)
|
|
qemu_sem_post(&p->sem_sync);
|
|
qemu_thread_join(&p->thread);
|
|
}
|
|
+ }
|
|
+ for (i = 0; i < migrate_multifd_channels(); i++) {
|
|
+ MultiFDRecvParams *p = &multifd_recv_state->params[i];
|
|
+
|
|
object_unref(OBJECT(p->c));
|
|
p->c = NULL;
|
|
qemu_mutex_destroy(&p->mutex);
|
|
--
|
|
1.8.3.1
|
|
|