>This patch fixes RTE SMP barrier bugs for the perf test of eventdev.
>
>For the "perf_process_last_stage" function, wmb after storing
>processed_pkts should be moved before it. This is because the worker
>lcore should ensure it has really finished data processing, e.g. event
>stored into buffers, before the shared variables "w-
>>processed_pkts"are
>stored.
>
>For the "perf_process_last_stage_latency", on the one hand, the wmb
>should be moved before storing into "w->processed_pkts". The reason
>is
>the same as above. But on the other hand, for "w->latency", wmb is
>unnecessary due to data dependency.
>
>Fixes: 2369f73329f8 ("app/testeventdev: add perf queue worker
>functions")
>Cc: jer...@marvell.com
>Cc: sta...@dpdk.org
>
>Signed-off-by: Feifei Wang <feifei.wa...@arm.com>
>Reviewed-by: Ruifeng Wang <ruifeng.w...@arm.com>
Acked-by: Pavan Nikhilesh <pbhagavat...@marvell.com>
>---
> app/test-eventdev/test_perf_common.h | 14 ++++++++++++--
> 1 file changed, 12 insertions(+), 2 deletions(-)
>
>diff --git a/app/test-eventdev/test_perf_common.h b/app/test-
>eventdev/test_perf_common.h
>index ff9705df8..e7233e5a5 100644
>--- a/app/test-eventdev/test_perf_common.h
>+++ b/app/test-eventdev/test_perf_common.h
>@@ -97,8 +97,13 @@ perf_process_last_stage(struct rte_mempool
>*const pool,
> void *bufs[], int const buf_sz, uint8_t count)
> {
> bufs[count++] = ev->event_ptr;
>- w->processed_pkts++;
>+
>+ /* wmb here ensures event_prt is stored before
>+ * updating the number of processed packets
>+ * for worker lcores
>+ */
> rte_smp_wmb();
>+ w->processed_pkts++;
>
> if (unlikely(count == buf_sz)) {
> count = 0;
>@@ -116,6 +121,12 @@ perf_process_last_stage_latency(struct
>rte_mempool *const pool,
> struct perf_elt *const m = ev->event_ptr;
>
> bufs[count++] = ev->event_ptr;
>+
>+ /* wmb here ensures event_prt is stored before
>+ * updating the number of processed packets
>+ * for worker lcores
>+ */
>+ rte_smp_wmb();
> w->processed_pkts++;
>
> if (unlikely(count == buf_sz)) {
>@@ -127,7 +138,6 @@ perf_process_last_stage_latency(struct
>rte_mempool *const pool,
> }
>
> w->latency += latency;
>- rte_smp_wmb();
> return count;
> }
>
>--
>2.25.1
