[dpdk-dev] [memnic PATCH v2] pmd: fix race condition

[Olivier MATZ]

On Thursday, April 03, 2014 06:35:06 AM Hiroshi Shimamoto wrote:
> From: Hiroshi Shimamoto 
> 
> There is a race condition, on transmit to host.
> 
> Guest PMD Host
> Thread-A Thread-B vSwitch
> 
>|idx=0   |idx=0   |p[0] st!=2
>|cmpxchg ||
>|p[0] st->1  ||
>|idx=1   ||
>|fill data   ||
>|p[0] st->2  ||p[0] st==2
>|
>|||receive data
>|||p[0] st->0
>||
>||cmpxchg |
>||success |p[1] st!=2
>||p[0] st->1  |
> 
>   This is BAD
> 
> That causes traffic stop.
> 
> We have to take care about that race condition with checking
> whether current index is correct.
> 
> Signed-off-by: Hiroshi Shimamoto 
> Reviewed-by: Hayato Momma 
> ---
>  pmd/pmd_memnic.c | 9 +
>  1 file changed, 9 insertions(+)

Reviewed-by: Olivier Matz 

[dpdk-dev] [memnic PATCH v2] pmd: fix race condition

[Hiroshi Shimamoto]

From: Hiroshi Shimamoto 

There is a race condition, on transmit to host.

Guest PMD Host
Thread-A Thread-B vSwitch
   |idx=0   |idx=0   |p[0] st!=2
   |cmpxchg ||
   |p[0] st->1  ||
   |idx=1   ||
   |fill data   ||
   |p[0] st->2  ||p[0] st==2
   |||receive data
   |||p[0] st->0
   ||cmpxchg |
   ||success |p[1] st!=2
   ||p[0] st->1  |
  This is BAD

That causes traffic stop.

We have to take care about that race condition with checking
whether current index is correct.

Signed-off-by: Hiroshi Shimamoto 
Reviewed-by: Hayato Momma 
---
 pmd/pmd_memnic.c | 9 +
 1 file changed, 9 insertions(+)

diff --git a/pmd/pmd_memnic.c b/pmd/pmd_memnic.c
index d833130..4a1c1e4 100644
--- a/pmd/pmd_memnic.c
+++ b/pmd/pmd_memnic.c
@@ -345,6 +345,15 @@ retry:
goto retry;
}

+   if (idx != ACCESS_ONCE(adapter->down_idx)) {
+   /*
+* host freed this and got false positive,
+* need to recover the status and retry.
+*/
+   p->status = MEMNIC_PKT_ST_FREE;
+   goto retry;
+   }
+
if (++idx >= MEMNIC_NR_PACKET)
idx = 0;
adapter->down_idx = idx;
-- 
1.8.4