On 5/2/24 22:45, Hernan Vargas wrote:
Moving memory barrier so that dequeue thread can be in sync with enqueue
thread.
Fixes: 32e8b7ea35dd ("baseband/acc100: refactor to segregate common code")
Cc: sta...@dpdk.org
Signed-off-by: Hernan Vargas <hernan.var...@intel.com>
---
drivers/baseband/acc/acc_common.h | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/baseband/acc/acc_common.h
b/drivers/baseband/acc/acc_common.h
index fddeb0737b8b..e249f37e38fe 100644
--- a/drivers/baseband/acc/acc_common.h
+++ b/drivers/baseband/acc/acc_common.h
@@ -1112,6 +1112,9 @@ acc_dma_enqueue(struct acc_queue *q, uint16_t n,
req_elem_addr,
(void *)q->mmio_reg_enqueue);
+ q->aq_enqueued++;
+ q->sw_ring_head += enq_batch_size;
+
rte_wmb();
/* Start time measurement for enqueue function offload. */
@@ -1122,8 +1125,6 @@ acc_dma_enqueue(struct acc_queue *q, uint16_t n,
queue_stats->acc_offload_cycles += rte_rdtsc_precise() - start_time;
- q->aq_enqueued++;
- q->sw_ring_head += enq_batch_size;
n -= enq_batch_size;
} while (n);
Reviewed-by: Maxime Coquelin <maxime.coque...@redhat.com>
Thanks,
Maxime
