[Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Bin Wu]

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:

(gdb) bt
qemu-coroutine-lock.c:66
to=0x7fa5a1798648) at qemu-coroutine.c:97
request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
block/nbd-client.c:165
sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
block/nbd-client.c:262
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
block/nbd-client.c:296
nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
flags=0) at block.c:3321
offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3447
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3471
nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
flags=0) at block.c:3321
offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3447
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3471
coroutine-ucontext.c:121

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>
---
 qemu-coroutine.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/qemu-coroutine.c b/qemu-coroutine.c
index 525247b..cc0bdfa 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 +134,9 @@ 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)
-- 
1.7.12.4

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Paolo Bonzini]

On 09/02/2015 07:50, Bin Wu wrote:
> 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:
> 
> (gdb) bt
> qemu-coroutine-lock.c:66
> to=0x7fa5a1798648) at qemu-coroutine.c:97
> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
> block/nbd-client.c:165
> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
> block/nbd-client.c:262
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
> block/nbd-client.c:296
> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> flags=0) at block.c:3321
> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3447
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3471
> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> flags=0) at block.c:3321
> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3447
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3471
> coroutine-ucontext.c:121
> 
> 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.

qemu_coroutine_yield can be executed for other reasons than locks.  In
those cases, it is correct to call qemu_co_queue_run_restart.  I think
it's an NBD bug.

Paolo

> 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>
> ---
>  qemu-coroutine.c | 16 ++++++++++------
>  1 file changed, 10 insertions(+), 6 deletions(-)
> 
> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
> index 525247b..cc0bdfa 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 +134,9 @@ 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)
> 

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Bin Wu]

On 2015/2/9 17:09, Paolo Bonzini wrote:
> 
> 
> On 09/02/2015 07:50, Bin Wu wrote:
>> 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:
>>
>> (gdb) bt
>> qemu-coroutine-lock.c:66
>> to=0x7fa5a1798648) at qemu-coroutine.c:97
>> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
>> block/nbd-client.c:165
>> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
>> block/nbd-client.c:262
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
>> block/nbd-client.c:296
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
>> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>> flags=0) at block.c:3321
>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3447
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3471
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
>> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>> flags=0) at block.c:3321
>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3447
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3471
>> coroutine-ucontext.c:121
>>
>> 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.
> 
> qemu_coroutine_yield can be executed for other reasons than locks.  In
> those cases, it is correct to call qemu_co_queue_run_restart.  I think
> it's an NBD bug.
> 
> Paolo
> 

Maybe I didn't describe the error scenario clearly, but it's a normal coroutine
using case, not a NBD bug. Please reference stefan's reply, thanks.

>> 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>
>> ---
>>  qemu-coroutine.c | 16 ++++++++++------
>>  1 file changed, 10 insertions(+), 6 deletions(-)
>>
>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>> index 525247b..cc0bdfa 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 +134,9 @@ 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)
>>
> 
> 
> .
> 

-- 
Bin Wu

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Kevin Wolf]

Am 09.02.2015 um 07:50 hat Bin Wu geschrieben:
> 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:
> 
> (gdb) bt
> qemu-coroutine-lock.c:66
> to=0x7fa5a1798648) at qemu-coroutine.c:97
> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
> block/nbd-client.c:165
> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
> block/nbd-client.c:262
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
> block/nbd-client.c:296
> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> flags=0) at block.c:3321
> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3447
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3471
> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> flags=0) at block.c:3321
> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3447
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3471
> coroutine-ucontext.c:121
> 
> 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.

Why would C1 be used for the qemu_co_queue_run_restart() call? There is
only one caller, coroutine_swap(). It calls the function for the
coroutine that has just yielded or terminated. In the case of
termination, the coroutine is deleted only afterwards, in the switch
block in coroutine_swap().

> 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.

It shouldn't make a difference. Any coroutine waiting in a CoQueue
should be ready to be restarted at either point.

Kevin

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Stefan Hajnoczi]

[-- Attachment #1: Type: text/plain, Size: 7835 bytes --]

On Mon, Feb 09, 2015 at 02:50:39PM +0800, Bin Wu wrote:
> 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:
> 
> (gdb) bt
> qemu-coroutine-lock.c:66
> to=0x7fa5a1798648) at qemu-coroutine.c:97
> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
> block/nbd-client.c:165
> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
> block/nbd-client.c:262
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
> block/nbd-client.c:296
> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> flags=0) at block.c:3321
> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3447
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3471
> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> flags=0) at block.c:3321
> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3447
> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> block.c:3471
> coroutine-ucontext.c:121

This backtrace is incomplete.  Where are the function names?  The
parameter lists appear incomplete too.

> 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.

This example captures the scenario you describe:

diff --git a/qemu-coroutine.c b/qemu-coroutine.c
index 525247b..883cbf5 100644
--- a/qemu-coroutine.c
+++ b/qemu-coroutine.c
@@ -103,7 +103,10 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
 {
     CoroutineAction ret;
 
+    fprintf(stderr, "> %s from %p to %p\n", __func__, from, to);
     ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
+    fprintf(stderr, "< %s from %p to %p switch %s\n", __func__, from, to,
+            ret == COROUTINE_YIELD ? "yield" : "terminate");
 
     qemu_co_queue_run_restart(to);
 
@@ -111,6 +114,7 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
     case COROUTINE_YIELD:
         return;
     case COROUTINE_TERMINATE:
+        fprintf(stderr, "coroutine_delete %p\n", to);
         trace_qemu_coroutine_terminate(to);
         coroutine_delete(to);
         return;
diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
index 27d1b6f..d44c428 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
@@ -122,6 +123,35 @@ static void test_yield(void)
     g_assert_cmpint(i, ==, 5); /* coroutine must yield 5 times */
 }
 
+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);
+}
+
 /*
  * Check that creation, enter, and return work
  */
@@ -343,6 +373,7 @@ static void perf_cost(void)
 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);

Here is the output (with printfs in coroutine_swap):

-> coroutine_swap from MAIN to C1
c1 Part 1
-> coroutine_swap from C1 to C2
c2 Part 1
-> coroutine_swap from C2 to C1
<- coroutine_swap from C1 to C2 switch yield
c1 Part 2
<- coroutine_swap from MAIN to C1 switch terminate
coroutine_delete C1
-> coroutine_swap from MAIN to C2
<- coroutine_swap from C2 to C1 switch yield  !!!
c2 Part 2
<- coroutine_swap from MAIN to C2 switch terminate
coroutine_delete C2

I have marked the problematic line with "!!!".  The to=C1 variable is
used after C1 has been deleted.

The test crashes since it writes 0xff to C1 after it has terminated.

> Signed-off-by: Bin Wu <wu.wubin@huawei.com>
> ---
>  qemu-coroutine.c | 16 ++++++++++------
>  1 file changed, 10 insertions(+), 6 deletions(-)
> 
> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
> index 525247b..cc0bdfa 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 +134,9 @@ 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);
>  }

Your fix looks correct although QEMU coding style requires {}.

I tried to think of a simpler solution that keeps a single
qemu_co_queue_run_restart() call but was unable to find one.

Please send another revision with a test-coroutine.c test case so we can
protect against regressions.

Thanks,
Stefan

[-- Attachment #2: Type: application/pgp-signature, Size: 473 bytes --]

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Bin Wu]

On 2015/2/9 22:48, Stefan Hajnoczi wrote:
> On Mon, Feb 09, 2015 at 02:50:39PM +0800, Bin Wu wrote:
>> 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:
>>
>> (gdb) bt
>> qemu-coroutine-lock.c:66
>> to=0x7fa5a1798648) at qemu-coroutine.c:97
>> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
>> block/nbd-client.c:165
>> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
>> block/nbd-client.c:262
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
>> block/nbd-client.c:296
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
>> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>> flags=0) at block.c:3321
>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3447
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3471
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
>> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>> flags=0) at block.c:3321
>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3447
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3471
>> coroutine-ucontext.c:121
> 
> This backtrace is incomplete.  Where are the function names?  The
> parameter lists appear incomplete too.
> 

I put the stack in the git log, so some lines are missed:
(gdb) bt
#0  0x00007fa5a0c63fc5 in qemu_co_queue_run_restart (co=0x7fa5a1798648) at
qemu-coroutine-lock.c:66
#1  0x00007fa5a0c63bed in coroutine_swap (from=0x7fa5a178f160,
to=0x7fa5a1798648) at qemu-coroutine.c:97
#2  0x00007fa5a0c63dbf in qemu_coroutine_yield () at qemu-coroutine.c:140
#3  0x00007fa5a0c9e474 in nbd_co_receive_reply (s=0x7fa5a1a3cfd0,
request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
block/nbd-client.c:165
#4  0x00007fa5a0c9e8b5 in nbd_co_writev_1 (client=0x7fa5a1a3cfd0,
sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
block/nbd-client.c:262
#5  0x00007fa5a0c9e9dd in nbd_client_session_co_writev (client=0x7fa5a1a3cfd0,
sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
block/nbd-client.c:296
#6  0x00007fa5a0c9dda1 in nbd_co_writev (bs=0x7fa5a198fcb0, sector_num=8552704,
nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
#7  0x00007fa5a0c509a4 in bdrv_aligned_pwritev (bs=0x7fa5a198fcb0,
req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
flags=0) at block.c:3321
#8  0x00007fa5a0c50f3f in bdrv_co_do_pwritev (bs=0x7fa5a198fcb0,
offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
block.c:3447
#9  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.
> 
> This example captures the scenario you describe:
> 
> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
> index 525247b..883cbf5 100644
> --- a/qemu-coroutine.c
> +++ b/qemu-coroutine.c
> @@ -103,7 +103,10 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>  {
>      CoroutineAction ret;
>  
> +    fprintf(stderr, "> %s from %p to %p\n", __func__, from, to);
>      ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
> +    fprintf(stderr, "< %s from %p to %p switch %s\n", __func__, from, to,
> +            ret == COROUTINE_YIELD ? "yield" : "terminate");
>  
>      qemu_co_queue_run_restart(to);
>  
> @@ -111,6 +114,7 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>      case COROUTINE_YIELD:
>          return;
>      case COROUTINE_TERMINATE:
> +        fprintf(stderr, "coroutine_delete %p\n", to);
>          trace_qemu_coroutine_terminate(to);
>          coroutine_delete(to);
>          return;
> diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
> index 27d1b6f..d44c428 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
> @@ -122,6 +123,35 @@ static void test_yield(void)
>      g_assert_cmpint(i, ==, 5); /* coroutine must yield 5 times */
>  }
>  
> +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);
> +}
> +
>  /*
>   * Check that creation, enter, and return work
>   */
> @@ -343,6 +373,7 @@ static void perf_cost(void)
>  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);
> 
> Here is the output (with printfs in coroutine_swap):
> 
> -> coroutine_swap from MAIN to C1
> c1 Part 1
> -> coroutine_swap from C1 to C2
> c2 Part 1
> -> coroutine_swap from C2 to C1
> <- coroutine_swap from C1 to C2 switch yield
> c1 Part 2
> <- coroutine_swap from MAIN to C1 switch terminate
> coroutine_delete C1
> -> coroutine_swap from MAIN to C2
> <- coroutine_swap from C2 to C1 switch yield  !!!
> c2 Part 2
> <- coroutine_swap from MAIN to C2 switch terminate
> coroutine_delete C2
> 
> I have marked the problematic line with "!!!".  The to=C1 variable is
> used after C1 has been deleted.
> 
> The test crashes since it writes 0xff to C1 after it has terminated.

yes, this is exactly the error scenario I described. Thanks, stefan.

> 
>> Signed-off-by: Bin Wu <wu.wubin@huawei.com>
>> ---
>>  qemu-coroutine.c | 16 ++++++++++------
>>  1 file changed, 10 insertions(+), 6 deletions(-)
>>
>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>> index 525247b..cc0bdfa 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 +134,9 @@ 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);
>>  }
> 
> Your fix looks correct although QEMU coding style requires {}.
> 
> I tried to think of a simpler solution that keeps a single
> qemu_co_queue_run_restart() call but was unable to find one.
> 
> Please send another revision with a test-coroutine.c test case so we can
> protect against regressions.

OK, I will send another version latter.

> 
> Thanks,
> Stefan
> 

-- 
Bin Wu

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Wen Congyang]

On 02/09/2015 10:48 PM, Stefan Hajnoczi wrote:
> On Mon, Feb 09, 2015 at 02:50:39PM +0800, Bin Wu wrote:
>> 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:
>>
>> (gdb) bt
>> qemu-coroutine-lock.c:66
>> to=0x7fa5a1798648) at qemu-coroutine.c:97
>> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
>> block/nbd-client.c:165
>> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
>> block/nbd-client.c:262
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
>> block/nbd-client.c:296
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
>> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>> flags=0) at block.c:3321
>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3447
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3471
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
>> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>> flags=0) at block.c:3321
>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3447
>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>> block.c:3471
>> coroutine-ucontext.c:121
> 
> This backtrace is incomplete.  Where are the function names?  The
> parameter lists appear incomplete too.
> 
>> 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.
> 
> This example captures the scenario you describe:
> 
> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
> index 525247b..883cbf5 100644
> --- a/qemu-coroutine.c
> +++ b/qemu-coroutine.c
> @@ -103,7 +103,10 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>  {
>      CoroutineAction ret;
>  
> +    fprintf(stderr, "> %s from %p to %p\n", __func__, from, to);
>      ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
> +    fprintf(stderr, "< %s from %p to %p switch %s\n", __func__, from, to,
> +            ret == COROUTINE_YIELD ? "yield" : "terminate");
>  
>      qemu_co_queue_run_restart(to);
>  
> @@ -111,6 +114,7 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>      case COROUTINE_YIELD:
>          return;
>      case COROUTINE_TERMINATE:
> +        fprintf(stderr, "coroutine_delete %p\n", to);
>          trace_qemu_coroutine_terminate(to);
>          coroutine_delete(to);
>          return;
> diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
> index 27d1b6f..d44c428 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
> @@ -122,6 +123,35 @@ static void test_yield(void)
>      g_assert_cmpint(i, ==, 5); /* coroutine must yield 5 times */
>  }
>  
> +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);
> +}
> +
>  /*
>   * Check that creation, enter, and return work
>   */
> @@ -343,6 +373,7 @@ static void perf_cost(void)
>  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);
> 
> Here is the output (with printfs in coroutine_swap):
> 
> -> coroutine_swap from MAIN to C1
> c1 Part 1
> -> coroutine_swap from C1 to C2
> c2 Part 1
> -> coroutine_swap from C2 to C1
> <- coroutine_swap from C1 to C2 switch yield
> c1 Part 2
> <- coroutine_swap from MAIN to C1 switch terminate
> coroutine_delete C1
> -> coroutine_swap from MAIN to C2
> <- coroutine_swap from C2 to C1 switch yield  !!!
> c2 Part 2
> <- coroutine_swap from MAIN to C2 switch terminate
> coroutine_delete C2
> 
> I have marked the problematic line with "!!!".  The to=C1 variable is
> used after C1 has been deleted.

How to build the test program? make test? I meet the following errors:
make test
make -C tests/tcg test
make[1]: Entering directory '/work/src/qemu/tests/tcg'
  CC    test_path.o
In file included from /work/src/qemu/include/qemu-common.h:43:0,
                 from /work/src/qemu/util/cutils.c:24,
                 from test_path.c:3:
/work/src/qemu/include/glib-compat.h:19:18: fatal error: glib.h: No such file or directory
 #include <glib.h>
                  ^
compilation terminated.
/work/src/qemu/rules.mak:57: recipe for target 'test_path.o' failed
make[1]: *** [test_path.o] Error 1
make[1]: Leaving directory '/work/src/qemu/tests/tcg'
Makefile:428: recipe for target 'test' failed
make: *** [test] Error 2

Do I miss something?

Thanks
Wen Congyang

> 
> The test crashes since it writes 0xff to C1 after it has terminated.
> 
>> Signed-off-by: Bin Wu <wu.wubin@huawei.com>
>> ---
>>  qemu-coroutine.c | 16 ++++++++++------
>>  1 file changed, 10 insertions(+), 6 deletions(-)
>>
>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>> index 525247b..cc0bdfa 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 +134,9 @@ 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);
>>  }
> 
> Your fix looks correct although QEMU coding style requires {}.
> 
> I tried to think of a simpler solution that keeps a single
> qemu_co_queue_run_restart() call but was unable to find one.
> 
> Please send another revision with a test-coroutine.c test case so we can
> protect against regressions.
> 
> Thanks,
> Stefan
> 

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Bin Wu]

On 2015/2/10 11:16, Wen Congyang wrote:
> On 02/09/2015 10:48 PM, Stefan Hajnoczi wrote:
>> On Mon, Feb 09, 2015 at 02:50:39PM +0800, Bin Wu wrote:
>>> 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:
>>>
>>> (gdb) bt
>>> qemu-coroutine-lock.c:66
>>> to=0x7fa5a1798648) at qemu-coroutine.c:97
>>> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
>>> block/nbd-client.c:165
>>> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
>>> block/nbd-client.c:262
>>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
>>> block/nbd-client.c:296
>>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
>>> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>>> flags=0) at block.c:3321
>>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>> block.c:3447
>>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>> block.c:3471
>>> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
>>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
>>> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>>> flags=0) at block.c:3321
>>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>> block.c:3447
>>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>> block.c:3471
>>> coroutine-ucontext.c:121
>>
>> This backtrace is incomplete.  Where are the function names?  The
>> parameter lists appear incomplete too.
>>
>>> 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.
>>
>> This example captures the scenario you describe:
>>
>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>> index 525247b..883cbf5 100644
>> --- a/qemu-coroutine.c
>> +++ b/qemu-coroutine.c
>> @@ -103,7 +103,10 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>>  {
>>      CoroutineAction ret;
>>  
>> +    fprintf(stderr, "> %s from %p to %p\n", __func__, from, to);
>>      ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
>> +    fprintf(stderr, "< %s from %p to %p switch %s\n", __func__, from, to,
>> +            ret == COROUTINE_YIELD ? "yield" : "terminate");
>>  
>>      qemu_co_queue_run_restart(to);
>>  
>> @@ -111,6 +114,7 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>>      case COROUTINE_YIELD:
>>          return;
>>      case COROUTINE_TERMINATE:
>> +        fprintf(stderr, "coroutine_delete %p\n", to);
>>          trace_qemu_coroutine_terminate(to);
>>          coroutine_delete(to);
>>          return;
>> diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
>> index 27d1b6f..d44c428 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
>> @@ -122,6 +123,35 @@ static void test_yield(void)
>>      g_assert_cmpint(i, ==, 5); /* coroutine must yield 5 times */
>>  }
>>  
>> +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);
>> +}
>> +
>>  /*
>>   * Check that creation, enter, and return work
>>   */
>> @@ -343,6 +373,7 @@ static void perf_cost(void)
>>  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);
>>
>> Here is the output (with printfs in coroutine_swap):
>>
>> -> coroutine_swap from MAIN to C1
>> c1 Part 1
>> -> coroutine_swap from C1 to C2
>> c2 Part 1
>> -> coroutine_swap from C2 to C1
>> <- coroutine_swap from C1 to C2 switch yield
>> c1 Part 2
>> <- coroutine_swap from MAIN to C1 switch terminate
>> coroutine_delete C1
>> -> coroutine_swap from MAIN to C2
>> <- coroutine_swap from C2 to C1 switch yield  !!!
>> c2 Part 2
>> <- coroutine_swap from MAIN to C2 switch terminate
>> coroutine_delete C2
>>
>> I have marked the problematic line with "!!!".  The to=C1 variable is
>> used after C1 has been deleted.
> 
> How to build the test program? make test? I meet the following errors:
> make test
> make -C tests/tcg test
> make[1]: Entering directory '/work/src/qemu/tests/tcg'
>   CC    test_path.o
> In file included from /work/src/qemu/include/qemu-common.h:43:0,
>                  from /work/src/qemu/util/cutils.c:24,
>                  from test_path.c:3:
> /work/src/qemu/include/glib-compat.h:19:18: fatal error: glib.h: No such file or directory
>  #include <glib.h>
>                   ^
> compilation terminated.
> /work/src/qemu/rules.mak:57: recipe for target 'test_path.o' failed
> make[1]: *** [test_path.o] Error 1
> make[1]: Leaving directory '/work/src/qemu/tests/tcg'
> Makefile:428: recipe for target 'test' failed
> make: *** [test] Error 2
> 
> Do I miss something?
> 
> Thanks
> Wen Congyang
> 

First, you need to install glib2-devel package which includes the glib.h. Then
you can use "make check" in the source tree to compile and run all tests (or use
"make check-help" to get some helps).

>>
>> The test crashes since it writes 0xff to C1 after it has terminated.
>>
>>> Signed-off-by: Bin Wu <wu.wubin@huawei.com>
>>> ---
>>>  qemu-coroutine.c | 16 ++++++++++------
>>>  1 file changed, 10 insertions(+), 6 deletions(-)
>>>
>>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>>> index 525247b..cc0bdfa 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 +134,9 @@ 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);
>>>  }
>>
>> Your fix looks correct although QEMU coding style requires {}.
>>
>> I tried to think of a simpler solution that keeps a single
>> qemu_co_queue_run_restart() call but was unable to find one.
>>
>> Please send another revision with a test-coroutine.c test case so we can
>> protect against regressions.
>>
>> Thanks,
>> Stefan
>>
> 
> 
> .
> 

-- 
Bin Wu

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Wen Congyang]

On 02/10/2015 11:48 AM, Bin Wu wrote:
> On 2015/2/10 11:16, Wen Congyang wrote:
>> On 02/09/2015 10:48 PM, Stefan Hajnoczi wrote:
>>> On Mon, Feb 09, 2015 at 02:50:39PM +0800, Bin Wu wrote:
>>>> 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:
>>>>
>>>> (gdb) bt
>>>> qemu-coroutine-lock.c:66
>>>> to=0x7fa5a1798648) at qemu-coroutine.c:97
>>>> request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
>>>> block/nbd-client.c:165
>>>> sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
>>>> block/nbd-client.c:262
>>>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
>>>> block/nbd-client.c:296
>>>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
>>>> req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>>>> flags=0) at block.c:3321
>>>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>>> block.c:3447
>>>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>>> block.c:3471
>>>> nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
>>>> nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
>>>> req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
>>>> flags=0) at block.c:3321
>>>> offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>>> block.c:3447
>>>> sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
>>>> block.c:3471
>>>> coroutine-ucontext.c:121
>>>
>>> This backtrace is incomplete.  Where are the function names?  The
>>> parameter lists appear incomplete too.
>>>
>>>> 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.
>>>
>>> This example captures the scenario you describe:
>>>
>>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>>> index 525247b..883cbf5 100644
>>> --- a/qemu-coroutine.c
>>> +++ b/qemu-coroutine.c
>>> @@ -103,7 +103,10 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>>>  {
>>>      CoroutineAction ret;
>>>  
>>> +    fprintf(stderr, "> %s from %p to %p\n", __func__, from, to);
>>>      ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
>>> +    fprintf(stderr, "< %s from %p to %p switch %s\n", __func__, from, to,
>>> +            ret == COROUTINE_YIELD ? "yield" : "terminate");
>>>  
>>>      qemu_co_queue_run_restart(to);
>>>  
>>> @@ -111,6 +114,7 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>>>      case COROUTINE_YIELD:
>>>          return;
>>>      case COROUTINE_TERMINATE:
>>> +        fprintf(stderr, "coroutine_delete %p\n", to);
>>>          trace_qemu_coroutine_terminate(to);
>>>          coroutine_delete(to);
>>>          return;
>>> diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
>>> index 27d1b6f..d44c428 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
>>> @@ -122,6 +123,35 @@ static void test_yield(void)
>>>      g_assert_cmpint(i, ==, 5); /* coroutine must yield 5 times */
>>>  }
>>>  
>>> +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);
>>> +}
>>> +
>>>  /*
>>>   * Check that creation, enter, and return work
>>>   */
>>> @@ -343,6 +373,7 @@ static void perf_cost(void)
>>>  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);
>>>
>>> Here is the output (with printfs in coroutine_swap):
>>>
>>> -> coroutine_swap from MAIN to C1
>>> c1 Part 1
>>> -> coroutine_swap from C1 to C2
>>> c2 Part 1
>>> -> coroutine_swap from C2 to C1
>>> <- coroutine_swap from C1 to C2 switch yield
>>> c1 Part 2
>>> <- coroutine_swap from MAIN to C1 switch terminate
>>> coroutine_delete C1
>>> -> coroutine_swap from MAIN to C2
>>> <- coroutine_swap from C2 to C1 switch yield  !!!
>>> c2 Part 2
>>> <- coroutine_swap from MAIN to C2 switch terminate
>>> coroutine_delete C2
>>>
>>> I have marked the problematic line with "!!!".  The to=C1 variable is
>>> used after C1 has been deleted.
>>
>> How to build the test program? make test? I meet the following errors:
>> make test
>> make -C tests/tcg test
>> make[1]: Entering directory '/work/src/qemu/tests/tcg'
>>   CC    test_path.o
>> In file included from /work/src/qemu/include/qemu-common.h:43:0,
>>                  from /work/src/qemu/util/cutils.c:24,
>>                  from test_path.c:3:
>> /work/src/qemu/include/glib-compat.h:19:18: fatal error: glib.h: No such file or directory
>>  #include <glib.h>
>>                   ^
>> compilation terminated.
>> /work/src/qemu/rules.mak:57: recipe for target 'test_path.o' failed
>> make[1]: *** [test_path.o] Error 1
>> make[1]: Leaving directory '/work/src/qemu/tests/tcg'
>> Makefile:428: recipe for target 'test' failed
>> make: *** [test] Error 2
>>
>> Do I miss something?
>>
>> Thanks
>> Wen Congyang
>>
> 
> First, you need to install glib2-devel package which includes the glib.h. Then
> you can use "make check" in the source tree to compile and run all tests (or use
> "make check-help" to get some helps).

I have installed glib2-devel, and "make check" can work, but "make test" cannot work...

Thanks
Wen Congyang

> 
>>>
>>> The test crashes since it writes 0xff to C1 after it has terminated.
>>>
>>>> Signed-off-by: Bin Wu <wu.wubin@huawei.com>
>>>> ---
>>>>  qemu-coroutine.c | 16 ++++++++++------
>>>>  1 file changed, 10 insertions(+), 6 deletions(-)
>>>>
>>>> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
>>>> index 525247b..cc0bdfa 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 +134,9 @@ 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);
>>>>  }
>>>
>>> Your fix looks correct although QEMU coding style requires {}.
>>>
>>> I tried to think of a simpler solution that keeps a single
>>> qemu_co_queue_run_restart() call but was unable to find one.
>>>
>>> Please send another revision with a test-coroutine.c test case so we can
>>> protect against regressions.
>>>
>>> Thanks,
>>> Stefan
>>>
>>
>>
>> .
>>
> 

Re: [Qemu-devel] [PATCH v2] qemu-coroutine: segfault when restarting co_queue

[Kevin Wolf]

[-- Attachment #1: Type: text/plain, Size: 8980 bytes --]

Am 09.02.2015 um 15:48 hat Stefan Hajnoczi geschrieben:
> On Mon, Feb 09, 2015 at 02:50:39PM +0800, Bin Wu wrote:
> > 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:
> > 
> > (gdb) bt
> > qemu-coroutine-lock.c:66
> > to=0x7fa5a1798648) at qemu-coroutine.c:97
> > request=0x7fa28c2ffa10, reply=0x7fa28c2ffa30, qiov=0x0, offset=0) at
> > block/nbd-client.c:165
> > sector_num=8552704, nb_sectors=2040, qiov=0x7fa5a1757468, offset=0) at
> > block/nbd-client.c:262
> > sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468) at
> > block/nbd-client.c:296
> > nb_sectors=2048, qiov=0x7fa5a1757468) at block/nbd.c:291
> > req=0x7fa28c2ffbb0, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> > flags=0) at block.c:3321
> > offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> > block.c:3447
> > sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> > block.c:3471
> > nb_sectors=2048, qiov=0x7fa5a1757468) at block.c:3480
> > nb_sectors=2048, qiov=0x7fa5a1757468) at block/raw_bsd.c:62
> > req=0x7fa28c2ffe30, offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468,
> > flags=0) at block.c:3321
> > offset=4378984448, bytes=1048576, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> > block.c:3447
> > sector_num=8552704, nb_sectors=2048, qiov=0x7fa5a1757468, flags=(unknown: 0)) at
> > block.c:3471
> > coroutine-ucontext.c:121
> 
> This backtrace is incomplete.  Where are the function names?  The
> parameter lists appear incomplete too.
> 
> > 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.
> 
> This example captures the scenario you describe:
> 
> diff --git a/qemu-coroutine.c b/qemu-coroutine.c
> index 525247b..883cbf5 100644
> --- a/qemu-coroutine.c
> +++ b/qemu-coroutine.c
> @@ -103,7 +103,10 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>  {
>      CoroutineAction ret;
>  
> +    fprintf(stderr, "> %s from %p to %p\n", __func__, from, to);
>      ret = qemu_coroutine_switch(from, to, COROUTINE_YIELD);
> +    fprintf(stderr, "< %s from %p to %p switch %s\n", __func__, from, to,
> +            ret == COROUTINE_YIELD ? "yield" : "terminate");
>  
>      qemu_co_queue_run_restart(to);
>  
> @@ -111,6 +114,7 @@ static void coroutine_swap(Coroutine *from, Coroutine *to)
>      case COROUTINE_YIELD:
>          return;
>      case COROUTINE_TERMINATE:
> +        fprintf(stderr, "coroutine_delete %p\n", to);
>          trace_qemu_coroutine_terminate(to);
>          coroutine_delete(to);
>          return;
> diff --git a/tests/test-coroutine.c b/tests/test-coroutine.c
> index 27d1b6f..d44c428 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
> @@ -122,6 +123,35 @@ static void test_yield(void)
>      g_assert_cmpint(i, ==, 5); /* coroutine must yield 5 times */
>  }
>  
> +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);
> +}
> +
>  /*
>   * Check that creation, enter, and return work
>   */
> @@ -343,6 +373,7 @@ static void perf_cost(void)
>  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);
> 
> Here is the output (with printfs in coroutine_swap):
> 
> -> coroutine_swap from MAIN to C1
> c1 Part 1
> -> coroutine_swap from C1 to C2
> c2 Part 1
> -> coroutine_swap from C2 to C1
> <- coroutine_swap from C1 to C2 switch yield
> c1 Part 2
> <- coroutine_swap from MAIN to C1 switch terminate
> coroutine_delete C1
> -> coroutine_swap from MAIN to C2
> <- coroutine_swap from C2 to C1 switch yield  !!!
> c2 Part 2
> <- coroutine_swap from MAIN to C2 switch terminate
> coroutine_delete C2
> 
> I have marked the problematic line with "!!!".  The to=C1 variable is
> used after C1 has been deleted.
> 
> The test crashes since it writes 0xff to C1 after it has terminated.
> 
> > Signed-off-by: Bin Wu <wu.wubin@huawei.com>
> > ---
> >  qemu-coroutine.c | 16 ++++++++++------
> >  1 file changed, 10 insertions(+), 6 deletions(-)
> > 
> > diff --git a/qemu-coroutine.c b/qemu-coroutine.c
> > index 525247b..cc0bdfa 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 +134,9 @@ 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);
> >  }
> 
> Your fix looks correct although QEMU coding style requires {}.
> 
> I tried to think of a simpler solution that keeps a single
> qemu_co_queue_run_restart() call but was unable to find one.

This one-liner is the core of the real fix:

--- a/qemu-coroutine.c
+++ b/qemu-coroutine.c
@@ -148,5 +148,5 @@ void coroutine_fn qemu_coroutine_yield(void)
     }
 
     self->caller = NULL;
-    coroutine_swap(self, to);
+    qemu_coroutine_switch(self, to, COROUTINE_YIELD);
 }

There is no reason at all for qemu_coroutine_yield() to go through
coroutine_swap(). The cleanups that can be made on top is to inline
coroutine_swap() in qemu_coroutine_enter(), and to change its use of
COROUTINE_YIELD into a new COROUTINE_ENTER (which is never looked at
anyway, but we're not yielding here).

All the other solutions take a unnecessarily complicated design as
granted and further complicate it to distinguish two unrelated code
paths.

Kevin

[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]