bnx2: Add prefetches to rx path.

Add prefetches of the skb and the next rx descriptor to speed up rx path.

Use prefetchw() for the skb [suggested by Eric Dumazet].

The rx descriptor is in skb->data which is mapped for streaming mode DMA.
Eric Dumazet pointed out that we should not prefetch the data before
dma_sync.  So we prefetch only if dma_sync is no_op on the system.

Signed-off-by: Michael Chan <mchan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 13 insertions, 3 deletions

diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index 320526b9b467..667f4196dc29 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -2719,6 +2719,7 @@ bnx2_alloc_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index)
         }
 
         rx_buf->skb = skb;
+        rx_buf->desc = (struct l2_fhdr *) skb->data;
         dma_unmap_addr_set(rx_buf, mapping, mapping);
 
         rxbd->rx_bd_haddr_hi = (u64) mapping >> 32;
@@ -2941,6 +2942,7 @@ bnx2_reuse_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
         rxr->rx_prod_bseq += bp->rx_buf_use_size;
 
         prod_rx_buf->skb = skb;
+        prod_rx_buf->desc = (struct l2_fhdr *) skb->data;
 
         if (cons == prod)
                 return;
@@ -3074,6 +3076,7 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
         u16 hw_cons, sw_cons, sw_ring_cons, sw_prod, sw_ring_prod;
         struct l2_fhdr *rx_hdr;
         int rx_pkt = 0, pg_ring_used = 0;
+        struct pci_dev *pdev = bp->pdev;
 
         hw_cons = bnx2_get_hw_rx_cons(bnapi);
         sw_cons = rxr->rx_cons;
@@ -3086,7 +3089,7 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
         while (sw_cons != hw_cons) {
                 unsigned int len, hdr_len;
                 u32 status;
-                struct sw_bd *rx_buf;
+                struct sw_bd *rx_buf, *next_rx_buf;
                 struct sk_buff *skb;
                 dma_addr_t dma_addr;
                 u16 vtag = 0;
@@ -3097,7 +3100,14 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 
                 rx_buf = &rxr->rx_buf_ring[sw_ring_cons];
                 skb = rx_buf->skb;
+                prefetchw(skb);
 
+                if (!get_dma_ops(&pdev->dev)->sync_single_for_cpu) {
+                        next_rx_buf =
+                                &rxr->rx_buf_ring[
+                                        RX_RING_IDX(NEXT_RX_BD(sw_cons))];
+                        prefetch(next_rx_buf->desc);
+                }
                 rx_buf->skb = NULL;
 
                 dma_addr = dma_unmap_addr(rx_buf, mapping);
@@ -3106,7 +3116,7 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
                         BNX2_RX_OFFSET + BNX2_RX_COPY_THRESH,
                         PCI_DMA_FROMDEVICE);
 
-                rx_hdr = (struct l2_fhdr *) skb->data;
+                rx_hdr = rx_buf->desc;
                 len = rx_hdr->l2_fhdr_pkt_len;
                 status = rx_hdr->l2_fhdr_status;
 
@@ -5764,7 +5774,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
         rx_buf = &rxr->rx_buf_ring[rx_start_idx];
         rx_skb = rx_buf->skb;
 
-        rx_hdr = (struct l2_fhdr *) rx_skb->data;
+        rx_hdr = rx_buf->desc;
         skb_reserve(rx_skb, BNX2_RX_OFFSET);
 
         pci_dma_sync_single_for_cpu(bp->pdev,