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 --- net/sched/cls_flow.c | 2 ++ net/sched/cls_route.c | 1 + net/sched/sch_generic.c | 3 --- net/sched/sch_teql.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'net/sched') diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index a5d2b20db560..4ac515f2a6ce 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -493,6 +493,8 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, tcf_exts_change(tp, &fnew->exts, &e); tcf_em_tree_change(tp, &fnew->ematches, &t); + netif_keep_dst(qdisc_dev(tp->q)); + if (tb[TCA_FLOW_KEYS]) { fnew->keymask = keymask; fnew->nkeys = nkeys; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 6f22baae0afa..109a329b7198 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -524,6 +524,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, if (f->handle < f1->handle) break; + netif_keep_dst(qdisc_dev(tp->q)); rcu_assign_pointer(f->next, f1); rcu_assign_pointer(*fp, f); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 2b349a4de3c8..38d58e6cef07 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -47,7 +47,6 @@ EXPORT_SYMBOL(default_qdisc_ops); static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { - skb_dst_force(skb); q->gso_skb = skb; q->qstats.requeues++; q->q.qlen++; /* it's still part of the queue */ @@ -218,8 +217,6 @@ static inline int qdisc_restart(struct Qdisc *q) if (unlikely(!skb)) return 0; - WARN_ON_ONCE(skb_dst_is_noref(skb)); - root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 5cd291bd00e4..6ada42396a24 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -470,7 +470,7 @@ static __init void teql_master_setup(struct net_device *dev) dev->tx_queue_len = 100; dev->flags = IFF_NOARP; dev->hard_header_len = LL_MAX_HEADER; - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + netif_keep_dst(dev); } static LIST_HEAD(master_dev_list); -- cgit v1.2.3-59-g8ed1b