qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
* [Qemu-devel] [PATCH v3] qemu-coroutine: segfault when restarting co_queue
@ 2015-02-10  5:16 Bin Wu
  2015-02-10 10:32 ` Kevin Wolf
  0 siblings, 1 reply; 3+ messages in thread
From: Bin Wu @ 2015-02-10  5:16 UTC (permalink / raw)
  To: qemu-devel; +Cc: kwolf, pbonzini, famz, Bin Wu, stefanha

From: Bin Wu <wu.wubin@huawei.com>

We tested VMs migration with their disk images by drive_mirror. With
migration, two VMs copyed large files between each other. During the
test, a segfault occured. The stack was as follow:

00)  0x00007fa5a0c63fc5 in qemu_co_queue_run_restart (co=0x7fa5a1798648) at
qemu-coroutine-lock.c:66
01)  0x00007fa5a0c63bed in coroutine_swap (from=0x7fa5a178f160,
to=0x7fa5a1798648) at qemu-coroutine.c:97
02)  0x00007fa5a0c63dbf in qemu_coroutine_yield () at qemu-coroutine.c:140
03)  0x00007fa5a0c9e474 in nbd_co_receive_reply (s=0x7fa5a1a3cfd0,
request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
block/nbd-client.c:165
04)  0x00007fa5a0c9e8b5 in nbd_co_writev_1 (client=0x7fa5a1a3cfd0,
sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
block/nbd-client.c:262
05)  0x00007fa5a0c9e9dd in nbd_client_session_co_writev (client=0x7fa5a1a3cfd0,
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
block/nbd-client.c:296
06)  0x00007fa5a0c9dda1 in nbd_co_writev (bs=0x7fa5a198fcb0, sector_num=8552704,
nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
07)  0x00007fa5a0c509a4 in bdrv_aligned_pwritev (bs=0x7fa5a198fcb0,
req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
flags=0) at block.c:3321
08)  0x00007fa5a0c50f3f in bdrv_co_do_pwritev (bs=0x7fa5a198fcb0,
offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3447
09)  0x00007fa5a0c51007 in bdrv_co_do_writev (bs=0x7fa5a198fcb0,
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3471
10) 0x00007fa5a0c51074 in bdrv_co_writev (bs=0x7fa5a198fcb0, sector_num=8552704,
nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
11) 0x00007fa5a0c652ec in raw_co_writev (bs=0x7fa5a198c110, sector_num=8552704,
nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
12) 0x00007fa5a0c509a4 in bdrv_aligned_pwritev (bs=0x7fa5a198c110,
req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
flags=0) at block.c:3321
13) 0x00007fa5a0c50f3f in bdrv_co_do_pwritev (bs=0x7fa5a198c110,
offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3447
14) 0x00007fa5a0c51007 in bdrv_co_do_writev (bs=0x7fa5a198c110,
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3471
15) 0x00007fa5a0c542b3 in bdrv_co_do_rw (opaque=0x7fa5a17a0000) at block.c:4706
16) 0x00007fa5a0c64e6e in coroutine_trampoline (i0=-1585909408, i1=32677) at
coroutine-ucontext.c:121
17) 0x00007fa59dc5aa50 in __correctly_grouped_prefixwc () from /lib64/libc.so.6
18) 0x0000000000000000 in ?? ()

After analyzing the stack and reviewing the code, we find the
qemu_co_queue_run_restart should not be put in the coroutine_swap function which
can be invoked by qemu_coroutine_enter or qemu_coroutine_yield. Only
qemu_coroutine_enter needs to restart the co_queue.

The error scenario is as follow: coroutine C1 enters C2, C2 yields
back to C1, then C1 ternimates and the related coroutine memory
becomes invalid. After a while, the C2 coroutine is entered again.
At this point, C1 is used as a parameter passed to
qemu_co_queue_run_restart. Therefore, qemu_co_queue_run_restart
accesses an invalid memory and a segfault error ocurrs.

The qemu_co_queue_run_restart function re-enters coroutines waiting
in the co_queue. However, this function should be only used int the
qemu_coroutine_enter context. Only in this context, when the current
coroutine gets execution control again(after the execution of
qemu_coroutine_switch), we can restart the target coutine because the
target coutine has yielded back to the current coroutine or it has
terminated.

First we want to put qemu_co_queue_run_restart in qemu_coroutine_enter,
but we find we can not access the target coroutine if it terminates.

Signed-off-by: Bin Wu <wu.wubin@huawei.com>
---
v3: add a test case in coroutine test code provided by stefan.

v2: fix undefined variable.
---
 qemu-coroutine.c       | 17 +++++++++++------
 tests/test-coroutine.c | 31 +++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 6 deletions(-)

diff --git a/qemu-coroutine.c b/qemu-coroutine.c
index 525247b..c8e280d 100644
--- a/qemu-coroutine.c
+++ b/qemu-coroutine.c
@@ -99,29 +99,31 @@ static void coroutine_delete(Coroutine *co)
     qemu_coroutine_delete(co);
 }
 
-static void coroutine_swap(Coroutine *from, Coroutine *to)
+static CoroutineAction coroutine_swap(Coroutine *from, Coroutine *to)
 {
     CoroutineAction ret;
 
     ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
 
-    qemu_co_queue_run_restart(to);
-
     switch (ret) {
     case COROUTINE_YIELD:
-        return;
+        break;
     case COROUTINE_TERMINATE:
         trace_qemu_coroutine_terminate(to);
+        qemu_co_queue_run_restart(to);
         coroutine_delete(to);
-        return;
+        break;
     default:
         abort();
     }
+
+    return ret;
 }
 
 void qemu_coroutine_enter(Coroutine *co, void *opaque)
 {
     Coroutine *self = qemu_coroutine_self();
+    CoroutineAction ret;
 
     trace_qemu_coroutine_enter(self, co, opaque);
 
@@ -132,7 +134,10 @@ void qemu_coroutine_enter(Coroutine *co, void *opaque)
 
     co->caller = self;
     co->entry_arg = opaque;
-    coroutine_swap(self, co);
+    ret = coroutine_swap(self, co);
+    if (ret == COROUTINE_YIELD) {
+        qemu_co_queue_run_restart(co);
+    }
 }
 
 void coroutine_fn qemu_coroutine_yield(void)
diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
index 27d1b6f..015e666 100644
--- a/tests/test-coroutine.c
+++ b/tests/test-coroutine.c
@@ -13,6 +13,7 @@
 
 #include <glib.h>
 #include "block/coroutine.h"
+#include "block/coroutine_int.h"
 
 /*
  * Check that qemu_in_coroutine() works
@@ -340,9 +341,39 @@ static void perf_cost(void)
                    (unsigned long)(1000000000.0 * duration / maxcycles));
 }
 
+static void coroutine_fn c2_fn(void *opaque)
+{
+    //fprintf(stderr, "c2 Part 1\n");
+    qemu_coroutine_yield();
+    //fprintf(stderr, "c2 Part 2\n");
+}
+
+static void coroutine_fn c1_fn(void *opaque)
+{
+    Coroutine *c2 = opaque;
+
+    //fprintf(stderr, "c1 Part 1\n");
+    qemu_coroutine_enter(c2, NULL);
+    //fprintf(stderr, "c1 Part 2\n");
+}
+
+static void test_co_queue(void)
+{
+    Coroutine *c1;
+    Coroutine *c2;
+
+    c1 = qemu_coroutine_create(c1_fn);
+    c2 = qemu_coroutine_create(c2_fn);
+
+    qemu_coroutine_enter(c1, c2);
+    memset(c1, 0xff, sizeof(Coroutine));
+    qemu_coroutine_enter(c2, NULL);
+}
+
 int main(int argc, char **argv)
 {
     g_test_init(&argc, &argv, NULL);
+    g_test_add_func("/basic/co_queue", test_co_queue);
     g_test_add_func("/basic/lifecycle", test_lifecycle);
     g_test_add_func("/basic/yield", test_yield);
     g_test_add_func("/basic/nesting", test_nesting);
-- 
1.7.12.4

^ permalink raw reply related	[flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-02-10 11:14 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-02-10  5:16 [Qemu-devel] [PATCH v3] qemu-coroutine: segfault when restarting co_queue Bin Wu
2015-02-10 10:32 ` Kevin Wolf
2015-02-10 11:14   ` Bin Wu

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).