From 8b5c171bb3dc0686b2647a84e990199c5faa9ef8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Nov 2011 12:07:14 +0000 Subject: neigh: new unresolved queue limits MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Le mercredi 09 novembre 2011 à 16:21 -0500, David Miller a écrit : > From: David Miller > Date: Wed, 09 Nov 2011 16:16:44 -0500 (EST) > > > From: Eric Dumazet > > Date: Wed, 09 Nov 2011 12:14:09 +0100 > > > >> unres_qlen is the number of frames we are able to queue per unresolved > >> neighbour. Its default value (3) was never changed and is responsible > >> for strange drops, especially if IP fragments are used, or multiple > >> sessions start in parallel. Even a single tcp flow can hit this limit. > > ... > > > > Ok, I've applied this, let's see what happens :-) > > Early answer, build fails. > > Please test build this patch with DECNET enabled and resubmit. The > decnet neigh layer still refers to the removed ->queue_len member. > > Thanks. Ouch, this was fixed on one machine yesterday, but not the other one I used this morning, sorry. [PATCH V5 net-next] neigh: new unresolved queue limits unres_qlen is the number of frames we are able to queue per unresolved neighbour. Its default value (3) was never changed and is responsible for strange drops, especially if IP fragments are used, or multiple sessions start in parallel. Even a single tcp flow can hit this limit. $ arp -d 192.168.20.108 ; ping -c 2 -s 8000 192.168.20.108 PING 192.168.20.108 (192.168.20.108) 8000(8028) bytes of data. 8008 bytes from 192.168.20.108: icmp_seq=2 ttl=64 time=0.322 ms Signed-off-by: David S. Miller --- net/decnet/dn_neigh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/decnet/dn_neigh.c') diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 7f0eb087dc11..3532ac64c82d 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -107,7 +107,7 @@ struct neigh_table dn_neigh_table = { .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 0, .app_probes = 0, .mcast_probes = 0, -- cgit v1.2.3 From 2721745501a26d0dc3b88c0d2f3aa11471891388 Mon Sep 17 00:00:00 2001 From: David Miller Date: Fri, 2 Dec 2011 16:52:08 +0000 Subject: net: Rename dst_get_neighbour{, _raw} to dst_get_neighbour_noref{, _raw}. To reflect the fact that a refrence is not obtained to the resulting neighbour entry. Signed-off-by: David S. Miller Acked-by: Roland Dreier --- drivers/infiniband/core/addr.c | 4 ++-- drivers/infiniband/hw/cxgb3/iwch_cm.c | 4 ++-- drivers/infiniband/hw/cxgb4/cm.c | 6 +++--- drivers/infiniband/hw/nes/nes_cm.c | 2 +- drivers/infiniband/ulp/ipoib/ipoib_main.c | 8 ++++---- drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 4 ++-- drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c | 8 ++++---- drivers/s390/net/qeth_l3_main.c | 4 ++-- drivers/scsi/cxgbi/cxgb3i/cxgb3i.c | 2 +- drivers/scsi/cxgbi/cxgb4i/cxgb4i.c | 2 +- drivers/scsi/cxgbi/libcxgbi.c | 4 ++-- include/net/dst.h | 6 +++--- net/atm/clip.c | 2 +- net/bridge/br_netfilter.c | 2 +- net/core/dst.c | 2 +- net/core/neighbour.c | 2 +- net/decnet/dn_neigh.c | 2 +- net/decnet/dn_route.c | 8 ++++---- net/ipv4/ip_gre.c | 2 +- net/ipv4/ip_output.c | 2 +- net/ipv4/route.c | 2 +- net/ipv6/addrconf.c | 2 +- net/ipv6/ip6_fib.c | 2 +- net/ipv6/ip6_output.c | 6 +++--- net/ipv6/ndisc.c | 4 ++-- net/ipv6/route.c | 16 ++++++++-------- net/ipv6/sit.c | 4 ++-- net/sched/sch_teql.c | 2 +- net/xfrm/xfrm_policy.c | 2 +- 29 files changed, 58 insertions(+), 58 deletions(-) (limited to 'net/decnet/dn_neigh.c') diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index a20c3c8224ea..70154f7e0415 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -217,7 +217,7 @@ static int addr4_resolve(struct sockaddr_in *src_in, neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev); if (!neigh || !(neigh->nud_state & NUD_VALID)) { rcu_read_lock(); - neigh_event_send(dst_get_neighbour(&rt->dst), NULL); + neigh_event_send(dst_get_neighbour_noref(&rt->dst), NULL); rcu_read_unlock(); ret = -ENODATA; if (neigh) @@ -277,7 +277,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in, } rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (!neigh || !(neigh->nud_state & NUD_VALID)) { if (neigh) neigh_event_send(neigh, NULL); diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c index c88b12beef25..23686df0517c 100644 --- a/drivers/infiniband/hw/cxgb3/iwch_cm.c +++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c @@ -1376,7 +1376,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx) } dst = &rt->dst; rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); l2t = t3_l2t_get(tdev, neigh, neigh->dev); rcu_read_unlock(); if (!l2t) { @@ -1949,7 +1949,7 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) ep->dst = &rt->dst; rcu_read_lock(); - neigh = dst_get_neighbour(ep->dst); + neigh = dst_get_neighbour_noref(ep->dst); /* get a l2t entry */ ep->l2t = t3_l2t_get(ep->com.tdev, neigh, neigh->dev); diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 0747004313ad..e61c80271f99 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1597,7 +1597,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb) } dst = &rt->dst; rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh->dev->flags & IFF_LOOPBACK) { pdev = ip_dev_find(&init_net, peer_ip); BUG_ON(!pdev); @@ -1825,7 +1825,7 @@ static int c4iw_reconnect(struct c4iw_ep *ep) ep->dst = &rt->dst; rcu_read_lock(); - neigh = dst_get_neighbour(ep->dst); + neigh = dst_get_neighbour_noref(ep->dst); /* get a l2t entry */ if (neigh->dev->flags & IFF_LOOPBACK) { @@ -2308,7 +2308,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) ep->dst = &rt->dst; rcu_read_lock(); - neigh = dst_get_neighbour(ep->dst); + neigh = dst_get_neighbour_noref(ep->dst); /* get a l2t entry */ if (neigh->dev->flags & IFF_LOOPBACK) { diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index 0a52d72371ee..686667a362cf 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -1379,7 +1379,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID))) { rcu_read_lock(); - neigh_event_send(dst_get_neighbour(&rt->dst), NULL); + neigh_event_send(dst_get_neighbour_noref(&rt->dst), NULL); rcu_read_unlock(); } ip_rt_put(rt); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index d3ed89ca4852..eef6786c8de6 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -564,7 +564,7 @@ static void neigh_add_path(struct sk_buff *skb, struct net_device *dev) struct neighbour *n; unsigned long flags; - n = dst_get_neighbour(skb_dst(skb)); + n = dst_get_neighbour_noref(skb_dst(skb)); neigh = ipoib_neigh_alloc(n, skb->dev); if (!neigh) { ++dev->stats.tx_dropped; @@ -645,7 +645,7 @@ static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev) struct neighbour *n; /* Look up path record for unicasts */ - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (n->ha[4] != 0xff) { neigh_add_path(skb, dev); return; @@ -724,7 +724,7 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); if (likely(skb_dst(skb))) - n = dst_get_neighbour(skb_dst(skb)); + n = dst_get_neighbour_noref(skb_dst(skb)); if (likely(n)) { if (unlikely(!*to_ipoib_neigh(n))) { @@ -841,7 +841,7 @@ static int ipoib_hard_header(struct sk_buff *skb, dst = skb_dst(skb); n = NULL; if (dst) - n = dst_get_neighbour_raw(dst); + n = dst_get_neighbour_noref_raw(dst); if ((!dst || !n) && daddr) { struct ipoib_pseudoheader *phdr = (struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 873bff97e69e..f7ff9dd66cda 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -269,7 +269,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast, skb->dev = dev; if (dst) - n = dst_get_neighbour_raw(dst); + n = dst_get_neighbour_noref_raw(dst); if (!dst || !n) { /* put pseudoheader back on for next time */ skb_push(skb, sizeof (struct ipoib_pseudoheader)); @@ -728,7 +728,7 @@ out: rcu_read_lock(); if (dst) - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (n && !*to_ipoib_neigh(n)) { struct ipoib_neigh *neigh = ipoib_neigh_alloc(n, skb->dev); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c index 7f7882d24bc6..6ed9f87db8ea 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c @@ -969,7 +969,7 @@ static int nb_callback(struct notifier_block *self, unsigned long event, case (NETEVENT_REDIRECT):{ struct netevent_redirect *nr = ctx; cxgb_redirect(nr->old, nr->new); - cxgb_neigh_update(dst_get_neighbour(nr->new)); + cxgb_neigh_update(dst_get_neighbour_noref(nr->new)); break; } default: @@ -1114,8 +1114,8 @@ static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new) struct l2t_entry *e; struct t3c_tid_entry *te; - olddev = dst_get_neighbour(old)->dev; - newdev = dst_get_neighbour(new)->dev; + olddev = dst_get_neighbour_noref(old)->dev; + newdev = dst_get_neighbour_noref(new)->dev; if (!is_offloading(olddev)) return; if (!is_offloading(newdev)) { @@ -1132,7 +1132,7 @@ static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new) } /* Add new L2T entry */ - e = t3_l2t_get(tdev, dst_get_neighbour(new), newdev); + e = t3_l2t_get(tdev, dst_get_neighbour_noref(new), newdev); if (!e) { printk(KERN_ERR "%s: couldn't allocate new l2t entry!\n", __func__); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 63578925bc59..b2a55e3fde0b 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -2759,7 +2759,7 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb) rcu_read_lock(); dst = skb_dst(skb); if (dst) - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (n) { cast_type = n->type; rcu_read_unlock(); @@ -2855,7 +2855,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, rcu_read_lock(); dst = skb_dst(skb); if (dst) - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (ipv == 4) { /* IPv4 */ hdr->hdr.l3.flags = qeth_l3_get_qeth_hdr_flags4(cast_type); diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c index 000294a9df80..88902d380f88 100644 --- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c +++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c @@ -966,7 +966,7 @@ static int init_act_open(struct cxgbi_sock *csk) csk->saddr.sin_addr.s_addr = chba->ipv4addr; csk->rss_qid = 0; - csk->l2t = t3_l2t_get(t3dev, dst_get_neighbour(dst), ndev); + csk->l2t = t3_l2t_get(t3dev, dst_get_neighbour_noref(dst), ndev); if (!csk->l2t) { pr_err("NO l2t available.\n"); return -EINVAL; diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c index ac7a9b1e3e23..c8fd13aadf9c 100644 --- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c +++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c @@ -1141,7 +1141,7 @@ static int init_act_open(struct cxgbi_sock *csk) cxgbi_sock_set_flag(csk, CTPF_HAS_ATID); cxgbi_sock_get(csk); - csk->l2t = cxgb4_l2t_get(lldi->l2t, dst_get_neighbour(csk->dst), ndev, 0); + csk->l2t = cxgb4_l2t_get(lldi->l2t, dst_get_neighbour_noref(csk->dst), ndev, 0); if (!csk->l2t) { pr_err("%s, cannot alloc l2t.\n", ndev->name); goto rel_resource; diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index c10f74a566f2..a026a2f12621 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -493,7 +493,7 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr) goto err_out; } dst = &rt->dst; - ndev = dst_get_neighbour(dst)->dev; + ndev = dst_get_neighbour_noref(dst)->dev; if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { pr_info("multi-cast route %pI4, port %u, dev %s.\n", @@ -507,7 +507,7 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr) ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr); mtu = ndev->mtu; pr_info("rt dev %s, loopback -> %s, mtu %u.\n", - dst_get_neighbour(dst)->dev->name, ndev->name, mtu); + dst_get_neighbour_noref(dst)->dev->name, ndev->name, mtu); } cdev = cxgbi_device_find_by_netdev(ndev, &port); diff --git a/include/net/dst.h b/include/net/dst.h index 6faec1a60216..01343b043517 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -86,12 +86,12 @@ struct dst_entry { }; }; -static inline struct neighbour *dst_get_neighbour(struct dst_entry *dst) +static inline struct neighbour *dst_get_neighbour_noref(struct dst_entry *dst) { return rcu_dereference(dst->_neighbour); } -static inline struct neighbour *dst_get_neighbour_raw(struct dst_entry *dst) +static inline struct neighbour *dst_get_neighbour_noref_raw(struct dst_entry *dst) { return rcu_dereference_raw(dst->_neighbour); } @@ -392,7 +392,7 @@ static inline void dst_confirm(struct dst_entry *dst) struct neighbour *n; rcu_read_lock(); - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); neigh_confirm(n); rcu_read_unlock(); } diff --git a/net/atm/clip.c b/net/atm/clip.c index c84ce7fe3f9b..c12c2582457c 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -338,7 +338,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, dev->stats.tx_dropped++; return NETDEV_TX_OK; } - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (!n) { pr_err("NO NEIGHBOUR !\n"); dev_kfree_skb(skb); diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index d6ec3720c77e..834dfabb30f9 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -356,7 +356,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) if (!skb->dev) goto free_skb; dst = skb_dst(skb); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; diff --git a/net/core/dst.c b/net/core/dst.c index d5e2c4c09107..43d94cedbf7c 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -366,7 +366,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, dev_hold(dst->dev); dev_put(dev); rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh && neigh->dev == dev) { neigh->dev = dst->dev; dev_hold(dst->dev); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index cdf8dc34f0ba..4af151e1bf5d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1190,7 +1190,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, rcu_read_lock(); /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (dst && (n2 = dst_get_neighbour(dst)) != NULL) + if (dst && (n2 = dst_get_neighbour_noref(dst)) != NULL) n1 = n2; n1->output(n1, skb); rcu_read_unlock(); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 3532ac64c82d..7d2fff29380f 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -202,7 +202,7 @@ static int dn_neigh_output_packet(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; - struct neighbour *neigh = dst_get_neighbour(dst); + struct neighbour *neigh = dst_get_neighbour_noref(dst); struct net_device *dev = neigh->dev; char mac_addr[ETH_ALEN]; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 94f4ec036669..f31ce72dca65 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -244,7 +244,7 @@ static int dn_dst_gc(struct dst_ops *ops) */ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) { - struct neighbour *n = dst_get_neighbour(dst); + struct neighbour *n = dst_get_neighbour_noref(dst); u32 min_mtu = 230; struct dn_dev *dn; @@ -713,7 +713,7 @@ out: static int dn_to_neigh_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct neighbour *n = dst_get_neighbour(dst); + struct neighbour *n = dst_get_neighbour_noref(dst); return n->output(n, skb); } @@ -728,7 +728,7 @@ static int dn_output(struct sk_buff *skb) int err = -EINVAL; - if ((neigh = dst_get_neighbour(dst)) == NULL) + if ((neigh = dst_get_neighbour_noref(dst)) == NULL) goto error; skb->dev = dev; @@ -852,7 +852,7 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) } rt->rt_type = res->type; - if (dev != NULL && dst_get_neighbour(&rt->dst) == NULL) { + if (dev != NULL && dst_get_neighbour_noref(&rt->dst) == NULL) { n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev); if (IS_ERR(n)) return PTR_ERR(n); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 2b32296b7958..fe070c1593ab 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -731,7 +731,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct neighbour *neigh = dst_get_neighbour(skb_dst(skb)); + struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb)); const struct in6_addr *addr6; int addr_type; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0d5e5672f3d1..ff302bde8890 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -206,7 +206,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) } rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh) { int res = neigh_output(neigh, skb); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7047069cf967..90402a2a26a9 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -419,7 +419,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) int len, HHUptod; rcu_read_lock(); - n = dst_get_neighbour(&r->dst); + n = dst_get_neighbour_noref(&r->dst); HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; rcu_read_unlock(); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 586051726341..058cc222b3f1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -657,7 +657,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, * layer address of our nexhop router */ - if (dst_get_neighbour_raw(&rt->dst) == NULL) + if (dst_get_neighbour_noref_raw(&rt->dst) == NULL) ifa->flags &= ~IFA_F_OPTIMISTIC; ifa->idev = idev; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 7b4730315d09..278363123657 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1533,7 +1533,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) RT6_TRACE("aging clone %p\n", rt); return -1; } else if ((rt->rt6i_flags & RTF_GATEWAY) && - (!(dst_get_neighbour_raw(&rt->dst)->flags & NTF_ROUTER))) { + (!(dst_get_neighbour_noref_raw(&rt->dst)->flags & NTF_ROUTER))) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); return -1; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3221bc675654..71d26999c955 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -136,7 +136,7 @@ static int ip6_finish_output2(struct sk_buff *skb) } rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh) { int res = neigh_output(neigh, skb); @@ -463,7 +463,7 @@ int ip6_forward(struct sk_buff *skb) send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ - n = dst_get_neighbour(dst); + n = dst_get_neighbour_noref(dst); if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct rt6_info *rt; @@ -983,7 +983,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry of the nexthop router */ rcu_read_lock(); - n = dst_get_neighbour(*dst); + n = dst_get_neighbour_noref(*dst); if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index cfb9709ac7c9..e72c8af85781 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1238,7 +1238,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); if (rt) - neigh = dst_get_neighbour(&rt->dst); + neigh = dst_get_neighbour_noref(&rt->dst); if (rt && lifetime == 0) { neigh_clone(neigh); @@ -1258,7 +1258,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - neigh = dst_get_neighbour(&rt->dst); + neigh = dst_get_neighbour_noref(&rt->dst); if (neigh == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() got default router without neighbour.\n", diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1138b0a5566d..09412baf1ca6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -385,7 +385,7 @@ static void rt6_probe(struct rt6_info *rt) * to no more than one per minute. */ rcu_read_lock(); - neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; + neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) goto out; read_lock_bh(&neigh->lock); @@ -432,7 +432,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt) int m; rcu_read_lock(); - neigh = dst_get_neighbour(&rt->dst); + neigh = dst_get_neighbour_noref(&rt->dst); if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) m = 1; @@ -786,7 +786,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, if (rt) { rt->rt6i_flags |= RTF_CACHE; - dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst))); + dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst))); } return rt; } @@ -820,7 +820,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -1629,7 +1629,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, dst_confirm(&rt->dst); /* Duplicate redirect: silently ignore. */ - if (neigh == dst_get_neighbour_raw(&rt->dst)) + if (neigh == dst_get_neighbour_noref_raw(&rt->dst)) goto out; nrt = ip6_rt_copy(rt, dest); @@ -1721,7 +1721,7 @@ again: 1. It is connected route. Action: COW 2. It is gatewayed route or NONEXTHOP route. Action: clone it. */ - if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, daddr, saddr); else nrt = rt6_alloc_clone(rt, daddr); @@ -2456,7 +2456,7 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; rcu_read_lock(); - n = dst_get_neighbour(&rt->dst); + n = dst_get_neighbour_noref(&rt->dst); if (n) NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key); rcu_read_unlock(); @@ -2653,7 +2653,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) seq_puts(m, "00000000000000000000000000000000 00 "); #endif rcu_read_lock(); - n = dst_get_neighbour(&rt->dst); + n = dst_get_neighbour_noref(&rt->dst); if (n) { seq_printf(m, "%pi6", n->primary_key); } else { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 50968f226e75..b7d14cc12ee8 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -680,7 +680,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct neighbour *neigh = NULL; if (skb_dst(skb)) - neigh = dst_get_neighbour(skb_dst(skb)); + neigh = dst_get_neighbour_noref(skb_dst(skb)); if (neigh == NULL) { if (net_ratelimit()) @@ -705,7 +705,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct neighbour *neigh = NULL; if (skb_dst(skb)) - neigh = dst_get_neighbour(skb_dst(skb)); + neigh = dst_get_neighbour_noref(skb_dst(skb)); if (neigh == NULL) { if (net_ratelimit()) diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index ed1336e15920..45326599fda3 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -277,7 +277,7 @@ static inline int teql_resolve(struct sk_buff *skb, return 0; rcu_read_lock(); - mn = dst_get_neighbour(dst); + mn = dst_get_neighbour_noref(dst); res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0; rcu_read_unlock(); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4fce1cec193e..82e803b56952 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1499,7 +1499,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto free_dst; /* Copy neighbour for reachability confirmation */ - dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour(dst))); + dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour_noref(dst))); xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len); xfrm_init_pmtu(dst_prev); -- cgit v1.2.3 From 2c2aba6c561ac425602f4a0be61422224cb87151 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Wed, 28 Dec 2011 15:06:58 -0500 Subject: ipv6: Use universal hash for NDISC. In order to perform a proper universal hash on a vector of integers, we have to use different universal hashes on each vector element. Which means we need 4 different hash randoms for ipv6. Signed-off-by: David S. Miller --- include/net/arp.h | 2 +- include/net/ndisc.h | 9 +++++++++ include/net/neighbour.h | 6 ++++-- net/core/neighbour.c | 13 ++++++++++--- net/decnet/dn_neigh.c | 4 ++-- net/ipv4/arp.c | 6 +++--- net/ipv6/ndisc.c | 13 +++---------- 7 files changed, 32 insertions(+), 21 deletions(-) (limited to 'net/decnet/dn_neigh.c') diff --git a/include/net/arp.h b/include/net/arp.h index 4979af8b1559..0013dc87940b 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -23,7 +23,7 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct neigh_table *tbl, str rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - hash_val = arp_hashfn(key, dev, nht->hash_rnd) >> (32 - nht->hash_shift); + hash_val = arp_hashfn(key, dev, nht->hash_rnd[0]) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; n = rcu_dereference_bh(n->next)) { diff --git a/include/net/ndisc.h b/include/net/ndisc.h index c977c377c015..e9c30023b784 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -79,6 +79,15 @@ struct nd_opt_hdr { __u8 nd_opt_len; } __packed; +static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) +{ + const u32 *p32 = pkey; + + return (((p32[0] ^ dev->ifindex) * hash_rnd[0]) + + (p32[1] * hash_rnd[1]) + + (p32[2] * hash_rnd[2]) + + (p32[3] * hash_rnd[3])); +} extern int ndisc_init(void); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e31f0a86f9b7..34c996f46181 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -139,10 +139,12 @@ struct pneigh_entry { * neighbour table manipulation */ +#define NEIGH_NUM_HASH_RND 4 + struct neigh_hash_table { struct neighbour __rcu **hash_buckets; unsigned int hash_shift; - __u32 hash_rnd; + __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; }; @@ -154,7 +156,7 @@ struct neigh_table { int key_len; __u32 (*hash)(const void *pkey, const struct net_device *dev, - __u32 hash_rnd); + __u32 *hash_rnd); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 4af151e1bf5d..e287346e0934 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -322,11 +322,18 @@ out_entries: goto out; } +static void neigh_get_hash_rnd(u32 *x) +{ + get_random_bytes(x, sizeof(*x)); + *x |= 1; +} + static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) { size_t size = (1 << shift) * sizeof(struct neighbour *); struct neigh_hash_table *ret; struct neighbour __rcu **buckets; + int i; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) @@ -343,8 +350,8 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) } ret->hash_buckets = buckets; ret->hash_shift = shift; - get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); - ret->hash_rnd |= 1; + for (i = 0; i < NEIGH_NUM_HASH_RND; i++) + neigh_get_hash_rnd(&ret->hash_rnd[i]); return ret; } @@ -1828,7 +1835,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - ndc.ndtc_hash_rnd = nht->hash_rnd; + ndc.ndtc_hash_rnd = nht->hash_rnd[0]; ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); rcu_read_unlock_bh(); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 7d2fff29380f..befe426491ba 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -88,9 +88,9 @@ static const struct neigh_ops dn_phase3_ops = { static u32 dn_neigh_hash(const void *pkey, const struct net_device *dev, - __u32 hash_rnd) + __u32 *hash_rnd) { - return jhash_2words(*(__u16 *)pkey, 0, hash_rnd); + return jhash_2words(*(__u16 *)pkey, 0, hash_rnd[0]); } struct neigh_table dn_neigh_table = { diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 381a0876c363..59402be133f0 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -121,7 +121,7 @@ /* * Interface to generic neighbour cache. */ -static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 rnd); +static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -215,9 +215,9 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) static u32 arp_hash(const void *pkey, const struct net_device *dev, - __u32 hash_rnd) + __u32 *hash_rnd) { - return arp_hashfn(*(u32 *)pkey, dev, hash_rnd); + return arp_hashfn(*(u32 *)pkey, dev, *hash_rnd); } static int arp_constructor(struct neighbour *neigh) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f3e50c29add4..538a61960a24 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -93,7 +93,7 @@ static u32 ndisc_hash(const void *pkey, const struct net_device *dev, - __u32 rnd); + __u32 *hash_rnd); static int ndisc_constructor(struct neighbour *neigh); static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb); static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -349,16 +349,9 @@ EXPORT_SYMBOL(ndisc_mc_map); static u32 ndisc_hash(const void *pkey, const struct net_device *dev, - __u32 hash_rnd) + __u32 *hash_rnd) { - const u32 *p32 = pkey; - u32 addr_hash, i; - - addr_hash = 0; - for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++) - addr_hash ^= *p32++; - - return jhash_2words(addr_hash, dev->ifindex, hash_rnd); + return ndisc_hashfn(pkey, dev, hash_rnd); } static int ndisc_constructor(struct neighbour *neigh) -- cgit v1.2.3