From 11848b964777af9c68d9160582628c2eb11f46d5 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Mon, 19 Jul 2010 14:15:04 +0000 Subject: [PATCH] bnx2: Remove some unnecessary smp_mb() in tx fast path. smp_mb() inside bnx2_tx_avail() is used twice in the normal bnx2_start_xmit() path (see illustration below). The full memory barrier is only necessary during race conditions with tx completion. We can speed up the tx path by replacing smp_mb() in bnx2_tx_avail() with a compiler barrier. The compiler barrier is to force the compiler to fetch the tx_prod and tx_cons from memory. In the race condition between bnx2_start_xmit() and bnx2_tx_int(), we have the following situation: bnx2_start_xmit() bnx2_tx_int() if (!bnx2_tx_avail()) BUG(); ... if (!bnx2_tx_avail()) netif_tx_stop_queue(); update_tx_index(); smp_mb(); smp_mb(); if (bnx2_tx_avail()) if (netif_tx_queue_stopped() && netif_tx_wake_queue(); bnx2_tx_avail()) With smp_mb() removed from bnx2_tx_avail(), we need to add smp_mb() to bnx2_start_xmit() as shown above to properly order netif_tx_stop_queue() and bnx2_tx_avail() to check the ring index. If it is not strictly ordered, the tx queue can be stopped forever. This improves performance by about 5% with 2 ports running bi-directional 64-byte packets. Reviewed-by: Benjamin Li Reviewed-by: Matt Carlson Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/bnx2.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index d44ecc30865f..2af570d7a2fb 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -253,7 +253,8 @@ static inline u32 bnx2_tx_avail(struct bnx2 *bp, struct bnx2_tx_ring_info *txr) { u32 diff; - smp_mb(); + /* Tell compiler to fetch tx_prod and tx_cons from memory. */ + barrier(); /* The ring uses 256 indices for 255 entries, one of them * needs to be skipped. @@ -6534,6 +6535,13 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) if (unlikely(bnx2_tx_avail(bp, txr) <= MAX_SKB_FRAGS)) { netif_tx_stop_queue(txq); + + /* netif_tx_stop_queue() must be done before checking + * tx index in bnx2_tx_avail() below, because in + * bnx2_tx_int(), we update tx index before checking for + * netif_tx_queue_stopped(). + */ + smp_mb(); if (bnx2_tx_avail(bp, txr) > bp->tx_wake_thresh) netif_tx_wake_queue(txq); }