aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2009-05-12 20:48:02 +0000
committerDavid S. Miller <davem@davemloft.net>2009-05-17 20:47:44 -0700
commitd62fda082c48b417b47a553860abf75d9cf8b591 (patch)
tree1b2679e4fcce72eb6ac584ecf9cc039fe9ea2c4a
parenttcp: tcp_prequeue() can use keyed wakeups (diff)
downloadlinux-dev-d62fda082c48b417b47a553860abf75d9cf8b591.tar.xz
linux-dev-d62fda082c48b417b47a553860abf75d9cf8b591.zip
bnx2: bnx2_tx_int() optimizations
When using bnx2 in a high transmit load, bnx2_tx_int() cost is pretty high. There are two reasons. One is an expensive call to bnx2_get_hw_tx_cons(bnapi) for each freed skb One is cpu stalls when accessing skb_is_gso(skb) / skb_shinfo(skb)->nr_frags because of two cache line misses. (One to get skb->end/head to compute skb_shinfo(skb), one to get is_gso/nr_frags) This patch : 1) avoids calling bnx2_get_hw_tx_cons(bnapi) too many times. 2) makes bnx2_start_xmit() cache is_gso & nr_frags into sw_tx_bd descriptor. This uses a litle bit more ram (256 longs per device on x86), but helps a lot. 3) uses a prefetch(&skb->end) to speedup dev_kfree_skb(), bringing cache line that will be needed in skb_release_data() result is 5 % bandwidth increase in benchmarks, involving UDP or TCP receive & transmits, when a cpu is dedicated to ksoftirqd for bnx2. bnx2_tx_int going from 3.33 % cpu to 0.5 % cpu in oprofile Note : skb_dma_unmap() still very expensive but this is for another patch, not related to bnx2 (2.9 % of cpu, while it does nothing on x86_32) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--drivers/net/bnx2.c18
-rw-r--r--drivers/net/bnx2.h2
2 files changed, 13 insertions, 7 deletions
diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index b0cb29d4cc01..c37acc1d10ac 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -2630,14 +2630,15 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
tx_buf = &txr->tx_buf_ring[sw_ring_cons];
skb = tx_buf->skb;
+ /* prefetch skb_end_pointer() to speedup skb_shinfo(skb) */
+ prefetch(&skb->end);
+
/* partial BD completions possible with TSO packets */
- if (skb_is_gso(skb)) {
+ if (tx_buf->is_gso) {
u16 last_idx, last_ring_idx;
- last_idx = sw_cons +
- skb_shinfo(skb)->nr_frags + 1;
- last_ring_idx = sw_ring_cons +
- skb_shinfo(skb)->nr_frags + 1;
+ last_idx = sw_cons + tx_buf->nr_frags + 1;
+ last_ring_idx = sw_ring_cons + tx_buf->nr_frags + 1;
if (unlikely(last_ring_idx >= MAX_TX_DESC_CNT)) {
last_idx++;
}
@@ -2649,7 +2650,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
skb_dma_unmap(&bp->pdev->dev, skb, DMA_TO_DEVICE);
tx_buf->skb = NULL;
- last = skb_shinfo(skb)->nr_frags;
+ last = tx_buf->nr_frags;
for (i = 0; i < last; i++) {
sw_cons = NEXT_TX_BD(sw_cons);
@@ -2662,7 +2663,8 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
if (tx_pkt == budget)
break;
- hw_cons = bnx2_get_hw_tx_cons(bnapi);
+ if (hw_cons == sw_cons)
+ hw_cons = bnx2_get_hw_tx_cons(bnapi);
}
txr->hw_tx_cons = hw_cons;
@@ -6179,6 +6181,8 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
txbd->tx_bd_vlan_tag_flags = vlan_tag_flags | TX_BD_FLAGS_START;
last_frag = skb_shinfo(skb)->nr_frags;
+ tx_buf->nr_frags = last_frag;
+ tx_buf->is_gso = skb_is_gso(skb);
for (i = 0; i < last_frag; i++) {
skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h
index 5b570e17c839..026ed1c84698 100644
--- a/drivers/net/bnx2.h
+++ b/drivers/net/bnx2.h
@@ -6552,6 +6552,8 @@ struct sw_pg {
struct sw_tx_bd {
struct sk_buff *skb;
+ unsigned short is_gso;
+ unsigned short nr_frags;
};
#define SW_RXBD_RING_SIZE (sizeof(struct sw_bd) * RX_DESC_CNT)