Re: [dpdk-dev] [PATCH 2/3] eventdev: use c11 atomics for lcore timer armed flag

["Carrillo, Erik G" <erik.g.carrillo@intel.com>]

Hi Phil,

Comment in-line:

> -----Original Message-----
> From: Phil Yang <phil.yang@arm.com>
> Sent: Friday, June 12, 2020 6:20 AM
> To: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>
> Cc: drc@linux.vnet.ibm.com; honnappa.nagarahalli@arm.com;
> ruifeng.wang@arm.com; dharmik.thakkar@arm.com; nd@arm.com
> Subject: [PATCH 2/3] eventdev: use c11 atomics for lcore timer armed flag
> 
> The in_use flag is a per core variable which is not shared between lcores in
> the normal case and the access of this variable should be ordered on the
> same core. However, if non-EAL thread pick the highest lcore to insert timers
> into, there is the possibility of conflicts on this flag between threads. Then
> the atomic CAS operation is needed.
> 
> Use the c11 atomic CAS instead of the generic rte_atomic operations to avoid
> the unnecessary barrier on aarch64.
> 
> Signed-off-by: Phil Yang <phil.yang@arm.com>
> Reviewed-by: Dharmik Thakkar <dharmik.thakkar@arm.com>
> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
> ---
>  lib/librte_eventdev/rte_event_timer_adapter.c | 15 +++++++++++----
>  1 file changed, 11 insertions(+), 4 deletions(-)
> 
> diff --git a/lib/librte_eventdev/rte_event_timer_adapter.c
> b/lib/librte_eventdev/rte_event_timer_adapter.c
> index 6a0e283..6947efb 100644
> --- a/lib/librte_eventdev/rte_event_timer_adapter.c
> +++ b/lib/librte_eventdev/rte_event_timer_adapter.c
> @@ -554,7 +554,7 @@ struct swtim {
>  	uint32_t timer_data_id;
>  	/* Track which cores have actually armed a timer */
>  	struct {
> -		rte_atomic16_t v;
> +		int16_t v;
>  	} __rte_cache_aligned in_use[RTE_MAX_LCORE];
>  	/* Track which cores' timer lists should be polled */
>  	unsigned int poll_lcores[RTE_MAX_LCORE]; @@ -606,7 +606,8 @@
> swtim_callback(struct rte_timer *tim)
>  				      "with immediate expiry value");
>  		}
> 
> -		if (unlikely(rte_atomic16_test_and_set(&sw-
> >in_use[lcore].v))) {
> +		if (unlikely(sw->in_use[lcore].v == 0)) {
> +			sw->in_use[lcore].v = 1;
>  			n_lcores = __atomic_fetch_add(&sw->n_poll_lcores,
> 1,
>  						__ATOMIC_RELAXED);
>  			__atomic_store_n(&sw->poll_lcores[n_lcores],
> lcore, @@ -834,7 +835,7 @@ swtim_init(struct rte_event_timer_adapter
> *adapter)
> 
>  	/* Initialize the variables that track in-use timer lists */
>  	for (i = 0; i < RTE_MAX_LCORE; i++)
> -		rte_atomic16_init(&sw->in_use[i].v);
> +		sw->in_use[i].v = 0;
> 
>  	/* Initialize the timer subsystem and allocate timer data instance */
>  	ret = rte_timer_subsystem_init();
> @@ -1017,6 +1018,8 @@ __swtim_arm_burst(const struct
> rte_event_timer_adapter *adapter,
>  	struct rte_timer *tim, *tims[nb_evtims];
>  	uint64_t cycles;
>  	int n_lcores;
> +	/* Timer is not armed state */

A more accurate comment would be something like "Timer list for this lcore is not in use".

With that change, it looks good to me:
Acked-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>

> +	int16_t exp_state = 0;
> 
>  #ifdef RTE_LIBRTE_EVENTDEV_DEBUG
>  	/* Check that the service is running. */ @@ -1035,8 +1038,12 @@
> __swtim_arm_burst(const struct rte_event_timer_adapter *adapter,
>  	/* If this is the first time we're arming an event timer on this lcore,
>  	 * mark this lcore as "in use"; this will cause the service
>  	 * function to process the timer list that corresponds to this lcore.
> +	 * The atomic CAS operation can prevent the race condition on
> in_use
> +	 * flag between multiple non-EAL threads.
>  	 */
> -	if (unlikely(rte_atomic16_test_and_set(&sw->in_use[lcore_id].v))) {
> +	if (unlikely(__atomic_compare_exchange_n(&sw-
> >in_use[lcore_id].v,
> +			&exp_state, 1, 0,
> +			__ATOMIC_RELAXED, __ATOMIC_RELAXED))) {
>  		EVTIM_LOG_DBG("Adding lcore id = %u to list of lcores to
> poll",
>  			      lcore_id);
>  		n_lcores = __atomic_fetch_add(&sw->n_poll_lcores, 1,
> --
> 2.7.4