Re: [dpdk-dev] [PATCH v5] eal: fix race in ctrl thread creation

[Honnappa Nagarahalli]

<snip>

> 
> Hi Luc,
> 
> On Wed, Apr 07, 2021 at 08:53:23AM -0400, Luc Pelletier wrote:
> > The creation of control threads uses a pthread barrier for
> > synchronization. This patch fixes a race condition where the pthread
> > barrier could get destroyed while one of the threads has not yet
> > returned from the pthread_barrier_wait function, which could result in
> > undefined behaviour.
> >
> > Fixes: 3a0d465d4c53 ("eal: fix use-after-free on control thread
> > creation")
> > Cc: jianfeng....@intel.com
> > Cc: sta...@dpdk.org
> >
> > Signed-off-by: Luc Pelletier <lucp.at.w...@gmail.com>
> > ---
> >
> > Same as v4 except that I fixed 2 minor style issues flagged by patchwork.
> >
> >  lib/librte_eal/common/eal_common_thread.c | 52
> > +++++++++++------------
> >  1 file changed, 25 insertions(+), 27 deletions(-)
> >
> > diff --git a/lib/librte_eal/common/eal_common_thread.c
> > b/lib/librte_eal/common/eal_common_thread.c
> > index 73a055902..c1044e795 100644
> > --- a/lib/librte_eal/common/eal_common_thread.c
> > +++ b/lib/librte_eal/common/eal_common_thread.c
> > @@ -170,11 +170,19 @@ struct rte_thread_ctrl_params {
> >     void *(*start_routine)(void *);
> >     void *arg;
> >     pthread_barrier_t configured;
> > +   unsigned int refcnt;
> >  };
> >
> > +static void ctrl_params_free(struct rte_thread_ctrl_params *params) {
> > +   if (__atomic_sub_fetch(&params->refcnt, 1, __ATOMIC_ACQ_REL) ==
> 0) {
> > +           pthread_barrier_destroy(&params->configured);
> > +           free(params);
> > +   }
> > +}
> > +
> >  static void *ctrl_thread_init(void *arg)  {
> > -   int ret;
> >     struct internal_config *internal_conf =
> >             eal_get_internal_configuration();
> >     rte_cpuset_t *cpuset = &internal_conf->ctrl_cpuset; @@ -184,11
> > +192,8 @@ static void *ctrl_thread_init(void *arg)
> >
> >     __rte_thread_init(rte_lcore_id(), cpuset);
> >
> > -   ret = pthread_barrier_wait(&params->configured);
> > -   if (ret == PTHREAD_BARRIER_SERIAL_THREAD) {
> > -           pthread_barrier_destroy(&params->configured);
> > -           free(params);
> > -   }
> > +   pthread_barrier_wait(&params->configured);
> > +   ctrl_params_free(params);
> >
> >     return start_routine(routine_arg);
> >  }
> > @@ -210,14 +215,15 @@ rte_ctrl_thread_create(pthread_t *thread, const
> > char *name,
> >
> >     params->start_routine = start_routine;
> >     params->arg = arg;
> > +   params->refcnt = 2;
> >
> > -   pthread_barrier_init(&params->configured, NULL, 2);
> > +   ret = pthread_barrier_init(&params->configured, NULL, 2);
> > +   if (ret != 0)
> > +           goto fail_no_barrier;
> >
> >     ret = pthread_create(thread, attr, ctrl_thread_init, (void *)params);
> > -   if (ret != 0) {
> > -           free(params);
> > -           return -ret;
> > -   }
> > +   if (ret != 0)
> > +           goto fail_with_barrier;
> >
> >     if (name != NULL) {
> >             ret = rte_thread_setname(*thread, name); @@ -227,25
> +233,17 @@
> > rte_ctrl_thread_create(pthread_t *thread, const char *name,
> >     }
> >
> >     ret = pthread_setaffinity_np(*thread, sizeof(*cpuset), cpuset);
> > -   if (ret)
> > -           goto fail;
> > +   pthread_barrier_wait(&params->configured);
> > +   ctrl_params_free(params);
> >
> > -   ret = pthread_barrier_wait(&params->configured);
> > -   if (ret == PTHREAD_BARRIER_SERIAL_THREAD) {
> > -           pthread_barrier_destroy(&params->configured);
> > -           free(params);
> > -   }
> > +   return -ret;
> 
> I think not killing the thread when pthread_setaffinity_np() returns an error 
> is
> not very understandable from the API user point of view.
Agree.

> 
> What about doing this on top of your patch? The idea is to set start_routine
> to NULL before the barrier if pthread_setaffinity_np() failed. So there is no
> need to cancel the thread, it will exit by itself.
How about using the pthread_attr_setaffinity_np API?
It is deviating from the documentation of the 'rte_ctrl_thread_create'. But, 
from the user perspective, the behavior should not change.
This way we do not have to handle the error after the thread is launched.

> 
>   @@ -187,14 +187,18 @@ static void *ctrl_thread_init(void *arg)
>                   eal_get_internal_configuration();
>           rte_cpuset_t *cpuset = &internal_conf->ctrl_cpuset;
>           struct rte_thread_ctrl_params *params = arg;
>   -       void *(*start_routine)(void *) = params->start_routine;
>   +       void *(*start_routine)(void *);
>           void *routine_arg = params->arg;
> 
>           __rte_thread_init(rte_lcore_id(), cpuset);
> 
>           pthread_barrier_wait(&params->configured);
>   +       start_routine = params->start_routine;
>           ctrl_params_free(params);
> 
>   +       if (start_routine == NULL)
>   +               return NULL;
>   +
>           return start_routine(routine_arg);
>    }
> 
>   @@ -233,10 +237,18 @@ rte_ctrl_thread_create(pthread_t *thread, const
> char *name,
>           }
> 
>           ret = pthread_setaffinity_np(*thread, sizeof(*cpuset), cpuset);
>   +       if (ret != 0)
>   +               params->start_routine = NULL;
>   +
>           pthread_barrier_wait(&params->configured);
>           ctrl_params_free(params);
> 
>   -       return -ret;
>   +       if (ret != 0) {
>   +               pthread_join(*thread, NULL);
>   +               return -ret;
>   +       }
>   +
>   +       return 0;
> 
>    fail_with_barrier:
>           pthread_barrier_destroy(&params->configured);
> 
> 
> Regards,
> Olivier