From 0287587884b15041203b3a362d485e1ab1f24445 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Oct 2014 18:38:35 -0700 Subject: net: better IFF_XMIT_DST_RELEASE support Testing xmit_more support with netperf and connected UDP sockets, I found strange dst refcount false sharing. Current handling of IFF_XMIT_DST_RELEASE is not optimal. Dropping dst in validate_xmit_skb() is certainly too late in case packet was queued by cpu X but dequeued by cpu Y The logical point to take care of drop/force is in __dev_queue_xmit() before even taking qdisc lock. As Julian Anastasov pointed out, need for skb_dst() might come from some packet schedulers or classifiers. This patch adds new helper to cleanly express needs of various drivers or qdiscs/classifiers. Drivers that need skb_dst() in their ndo_start_xmit() should call following helper in their setup instead of the prior : dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; -> netif_keep_dst(dev); Instead of using a single bit, we use two bits, one being eventually rebuilt in bonding/team drivers. The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being rebuilt in bonding/team. Eventually, we could add something smarter later. Signed-off-by: Eric Dumazet Cc: Julian Anastasov Signed-off-by: David S. Miller --- drivers/net/eql.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/eql.c') diff --git a/drivers/net/eql.c b/drivers/net/eql.c index 957e5c0cede3..a10ad74cc8d2 100644 --- a/drivers/net/eql.c +++ b/drivers/net/eql.c @@ -199,7 +199,7 @@ static void __init eql_setup(struct net_device *dev) dev->type = ARPHRD_SLIP; dev->tx_queue_len = 5; /* Hands them off fast */ - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + netif_keep_dst(dev); } static int eql_open(struct net_device *dev) -- cgit v1.2.3