[memnic PATCH v2] pmd: fix race condition

[memnic PATCH v2] pmd: fix race condition

[Hiroshi Shimamoto]

From: Hiroshi Shimamoto <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>

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 <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>
Reviewed-by: Hayato Momma <h-momma-JhyGz2TFV9J8UrSeD/g0lQ@public.gmane.org>
---
 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

Re: [memnic PATCH v2] pmd: fix race condition

[Olivier MATZ]

On Thursday, April 03, 2014 06:35:06 AM Hiroshi Shimamoto wrote:
> From: Hiroshi Shimamoto <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>
> 
> 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 <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>
> Reviewed-by: Hayato Momma <h-momma-JhyGz2TFV9J8UrSeD/g0lQ@public.gmane.org>
> ---
>  pmd/pmd_memnic.c | 9 +++++++++
>  1 file changed, 9 insertions(+)

Reviewed-by: Olivier Matz <olivier.matz-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>

Re: [memnic PATCH v2] pmd: fix race condition

[Thomas Monjalon]

2014-04-11 16:41, Olivier MATZ:
> On Thursday, April 03, 2014 06:35:06 AM Hiroshi Shimamoto wrote:
> > From: Hiroshi Shimamoto <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>
> > 
> > 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 <h-shimamoto-ehU+Cx/zZe18UrSeD/g0lQ@public.gmane.org>
> > Reviewed-by: Hayato Momma <h-momma-JhyGz2TFV9J8UrSeD/g0lQ@public.gmane.org>
> 
> Reviewed-by: Olivier Matz <olivier.matz-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>

Applied

Thanks
-- 
Thomas