net: mvneta: prefetch next rx descriptor instead of current one

Currently, the mvneta driver tries to prefetch the current Rx
descriptor during read. Tests have shown that prefetching the
next one instead increases general performance by about 1% on
HTTP traffic.

Cc: Thomas Petazzoni <[email protected]>
Cc: Gregory CLEMENT <[email protected]>
Tested-by: Arnaud Ebalard <[email protected]>
Signed-off-by: Willy Tarreau <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index aa3a4f7c3f7c121062c5a8c253830bf92ae38000..c7b37e07f870ed105cd54458370db3572eeb4923 100644 (file)
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -611,6 +611,7 @@ mvneta_rxq_next_desc_get(struct mvneta_rx_queue *rxq)
        int rx_desc = rxq->next_desc_to_proc;
 
        rxq->next_desc_to_proc = MVNETA_QUEUE_NEXT_DESC(rxq, rx_desc);
+       prefetch(rxq->descs + rxq->next_desc_to_proc);
        return rxq->descs + rx_desc;
 }
 
@@ -1442,7 +1443,6 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo,
                u32 rx_status;
                int rx_bytes, err;
 
-               prefetch(rx_desc);
                rx_done++;
                rx_filled++;
                rx_status = rx_desc->status;