Re: [dpdk-dev] [PATCH v6] eal: fix race in ctrl thread creation

[Olivier Matz]

Hi Luc,

On Wed, Apr 07, 2021 at 10:42:37AM -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>
> ---
> 
> Hi Olivier,
> 
> I've made the changes as you requested. However, I'm using the atomic
> built-ins for reading and writing start_routine; I think they're
> required to prevent any re-reordering.
> 
> Please let me know what you think.

>From [1], it seems that pthread_barrier_wait() is a full memory barrier.
So while not wrong, I think using atomic built-ins it is not needed.

[1] 
https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap04.html#tag_04_11



> 
>  lib/librte_eal/common/eal_common_thread.c | 63 +++++++++++++----------
>  1 file changed, 35 insertions(+), 28 deletions(-)
> 
> diff --git a/lib/librte_eal/common/eal_common_thread.c 
> b/lib/librte_eal/common/eal_common_thread.c
> index 73a055902..fcb386f77 100644
> --- a/lib/librte_eal/common/eal_common_thread.c
> +++ b/lib/librte_eal/common/eal_common_thread.c
> @@ -170,25 +170,34 @@ 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;
>       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);
>  
> -     ret = pthread_barrier_wait(&params->configured);
> -     if (ret == PTHREAD_BARRIER_SERIAL_THREAD) {
> -             pthread_barrier_destroy(&params->configured);
> -             free(params);
> -     }
> +     pthread_barrier_wait(&params->configured);
> +     start_routine = __atomic_load_n(&params->start_routine, 
> __ATOMIC_ACQUIRE);
> +     ctrl_params_free(params);
> +
> +     if (start_routine == NULL)
> +             return NULL;
>  
>       return start_routine(routine_arg);
>  }
> @@ -210,14 +219,15 @@ 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 +237,22 @@ rte_ctrl_thread_create(pthread_t *thread, const char 
> *name,
>       }
>  
>       ret = pthread_setaffinity_np(*thread, sizeof(*cpuset), cpuset);
> -     if (ret)
> -             goto fail;
> +     if (ret != 0)
> +             __atomic_store_n(&params->start_routine, NULL, 
> __ATOMIC_RELEASE);
> +     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);
> -     }
> +     if (ret != 0)
> +             pthread_join(*thread, NULL);
>  
> -     return 0;
> +     return -ret;
> +
> +fail_with_barrier:
> +     pthread_barrier_destroy(&params->configured);
> +
> +fail_no_barrier:
> +     free(params);
>  
> -fail:
> -     if (PTHREAD_BARRIER_SERIAL_THREAD ==
> -         pthread_barrier_wait(&params->configured)) {
> -             pthread_barrier_destroy(&params->configured);
> -             free(params);
> -     }
> -     pthread_cancel(*thread);
> -     pthread_join(*thread, NULL);
>       return -ret;
>  }
>  
> -- 
> 2.25.1
>