From 5b9e12dbf92b441b37136ea71dac59f05f2673a9 Mon Sep 17 00:00:00 2001 From: "Denis V. Lunev" Date: Wed, 13 Mar 2013 00:24:15 +0000 Subject: ipv4: fix definition of FIB_TABLE_HASHSZ a long time ago by the commit commit 93456b6d7753def8760b423ac6b986eb9d5a4a95 Author: Denis V. Lunev Date: Thu Jan 10 03:23:38 2008 -0800 [IPV4]: Unify access to the routing tables. the defenition of FIB_HASH_TABLE size has obtained wrong dependency: it should depend upon CONFIG_IP_MULTIPLE_TABLES (as was in the original code) but it was depended from CONFIG_IP_ROUTE_MULTIPATH This patch returns the situation to the original state. The problem was spotted by Tingwei Liu. Signed-off-by: Denis V. Lunev CC: Tingwei Liu CC: Alexey Kuznetsov Signed-off-by: David S. Miller --- include/net/ip_fib.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/net') diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 9497be1ad4c0..e49db91593a9 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -152,18 +152,16 @@ struct fib_result_nl { }; #ifdef CONFIG_IP_ROUTE_MULTIPATH - #define FIB_RES_NH(res) ((res).fi->fib_nh[(res).nh_sel]) - -#define FIB_TABLE_HASHSZ 2 - #else /* CONFIG_IP_ROUTE_MULTIPATH */ - #define FIB_RES_NH(res) ((res).fi->fib_nh[0]) +#endif /* CONFIG_IP_ROUTE_MULTIPATH */ +#ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 - -#endif /* CONFIG_IP_ROUTE_MULTIPATH */ +#else +#define FIB_TABLE_HASHSZ 2 +#endif extern __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh); -- cgit v1.2.3 From aaa0c23cb90141309f5076ba5e3bfbd39544b985 Mon Sep 17 00:00:00 2001 From: Zhouyi Zhou Date: Thu, 14 Mar 2013 17:21:50 +0000 Subject: Fix dst_neigh_lookup/dst_neigh_lookup_skb return value handling bug When neighbour table is full, dst_neigh_lookup/dst_neigh_lookup_skb will return -ENOBUFS which is absolutely non zero, while all the code in kernel which use above functions assume failure only on zero return which will cause panic. (for example: : https://bugzilla.kernel.org/show_bug.cgi?id=54731). This patch corrects above error with smallest changes to kernel source code and also correct two return value check missing bugs in drivers/infiniband/hw/cxgb4/cm.c Tested on my x86_64 SMP machine Reported-by: Zhouyi Zhou Tested-by: Zhouyi Zhou Signed-off-by: Zhouyi Zhou Signed-off-by: David S. Miller --- drivers/infiniband/hw/cxgb4/cm.c | 12 ++++++++++++ include/net/dst.h | 6 ++++-- 2 files changed, 16 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 565bfb161c1a..a3fde52840ca 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -1575,6 +1575,12 @@ static int c4iw_reconnect(struct c4iw_ep *ep) neigh = dst_neigh_lookup(ep->dst, &ep->com.cm_id->remote_addr.sin_addr.s_addr); + if (!neigh) { + pr_err("%s - cannot alloc neigh.\n", __func__); + err = -ENOMEM; + goto fail4; + } + /* get a l2t entry */ if (neigh->dev->flags & IFF_LOOPBACK) { PDBG("%s LOOPBACK\n", __func__); @@ -3053,6 +3059,12 @@ static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb) dst = &rt->dst; neigh = dst_neigh_lookup_skb(dst, skb); + if (!neigh) { + pr_err("%s - failed to allocate neigh!\n", + __func__); + goto free_dst; + } + if (neigh->dev->flags & IFF_LOOPBACK) { pdev = ip_dev_find(&init_net, iph->daddr); e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, diff --git a/include/net/dst.h b/include/net/dst.h index 853cda11e518..1f8fd109e225 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -413,13 +413,15 @@ static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n, static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) { - return dst->ops->neigh_lookup(dst, NULL, daddr); + struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr); + return IS_ERR(n) ? NULL : n; } static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { - return dst->ops->neigh_lookup(dst, skb, NULL); + struct neighbour *n = dst->ops->neigh_lookup(dst, skb, NULL); + return IS_ERR(n) ? NULL : n; } static inline void dst_link_failure(struct sk_buff *skb) -- cgit v1.2.3 From 0c12582fbcdea0cbb0dfd224e1c5f9a8428ffa18 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 9 Mar 2013 23:25:04 +0200 Subject: ipvs: add backup_only flag to avoid loops Dmitry Akindinov is reporting for a problem where SYNs are looping between the master and backup server when the backup server is used as real server in DR mode and has IPVS rules to function as director. Even when the backup function is enabled we continue to forward traffic and schedule new connections when the current master is using the backup server as real server. While this is not a problem for NAT, for DR and TUN method the backup server can not determine if a request comes from client or from director. To avoid such loops add new sysctl flag backup_only. It can be needed for DR/TUN setups that do not need backup and director function at the same time. When the backup function is enabled we stop any forwarding and pass the traffic to the local stack (real server mode). The flag disables the director function when the backup function is enabled. For setups that enable backup function for some virtual services and director function for other virtual services there should be another more complex solution to support DR/TUN mode, may be to assign per-virtual service syncid value, so that we can differentiate the requests. Reported-by: Dmitry Akindinov Tested-by: German Myzovsky Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 7 +++++++ include/net/ip_vs.h | 12 ++++++++++++ net/netfilter/ipvs/ip_vs_core.c | 12 ++++++++---- net/netfilter/ipvs/ip_vs_ctl.c | 7 +++++++ 4 files changed, 34 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index f2a2488f1bf3..9573d0c48c6e 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -15,6 +15,13 @@ amemthresh - INTEGER enabled and the variable is automatically set to 2, otherwise the strategy is disabled and the variable is set to 1. +backup_only - BOOLEAN + 0 - disabled (default) + not 0 - enabled + + If set, disable the director function while the server is + in backup mode to avoid packet loops for DR/TUN methods. + conntrack - BOOLEAN 0 - disabled (default) not 0 - enabled diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 68c69d54d392..fce8e6b66d55 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -976,6 +976,7 @@ struct netns_ipvs { int sysctl_sync_retries; int sysctl_nat_icmp_send; int sysctl_pmtu_disc; + int sysctl_backup_only; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1067,6 +1068,12 @@ static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs) return ipvs->sysctl_pmtu_disc; } +static inline int sysctl_backup_only(struct netns_ipvs *ipvs) +{ + return ipvs->sync_state & IP_VS_STATE_BACKUP && + ipvs->sysctl_backup_only; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1114,6 +1121,11 @@ static inline int sysctl_pmtu_disc(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_backup_only(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 47edf5a40a59..18b4bc55fa3d 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1577,7 +1577,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; ip_vs_fill_iph_skb(af, skb, &iph); @@ -1654,7 +1655,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ @@ -1815,13 +1815,15 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct netns_ipvs *ipvs; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp(skb, &r, hooknum); @@ -1835,6 +1837,7 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, { int r; struct net *net; + struct netns_ipvs *ipvs; struct ip_vs_iphdr iphdr; ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr); @@ -1843,7 +1846,8 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, /* ipvs enabled in this netns ? */ net = skb_net(skb); - if (!net_ipvs(net)->enable) + ipvs = net_ipvs(net); + if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; return ip_vs_in_icmp_v6(skb, &r, hooknum, &iphdr); diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index c68198bf9128..9e2d1cccd1eb 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1808,6 +1808,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "backup_only", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -3741,6 +3747,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; ipvs->sysctl_pmtu_disc = 1; tbl[idx++].data = &ipvs->sysctl_pmtu_disc; + tbl[idx++].data = &ipvs->sysctl_backup_only; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); -- cgit v1.2.3 From 5a3da1fe9561828d0ca7eca664b16ec2b9bf0055 Mon Sep 17 00:00:00 2001 From: Hannes Frederic Sowa Date: Fri, 15 Mar 2013 11:32:30 +0000 Subject: inet: limit length of fragment queue hash table bucket lists This patch introduces a constant limit of the fragment queue hash table bucket list lengths. Currently the limit 128 is choosen somewhat arbitrary and just ensures that we can fill up the fragment cache with empty packets up to the default ip_frag_high_thresh limits. It should just protect from list iteration eating considerable amounts of cpu. If we reach the maximum length in one hash bucket a warning is printed. This is implemented on the caller side of inet_frag_find to distinguish between the different users of inet_fragment.c. I dropped the out of memory warning in the ipv4 fragment lookup path, because we already get a warning by the slab allocator. Cc: Eric Dumazet Cc: Jesper Dangaard Brouer Signed-off-by: Hannes Frederic Sowa Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_frag.h | 9 +++++++++ net/ipv4/inet_fragment.c | 20 +++++++++++++++++++- net/ipv4/ip_fragment.c | 11 ++++------- net/ipv6/netfilter/nf_conntrack_reasm.c | 12 ++++++------ net/ipv6/reassembly.c | 8 ++++++-- 5 files changed, 44 insertions(+), 16 deletions(-) (limited to 'include/net') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 76c3fe5ecc2e..0a1dcc2fa2f5 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -43,6 +43,13 @@ struct inet_frag_queue { #define INETFRAGS_HASHSZ 64 +/* averaged: + * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ / + * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or + * struct frag_queue)) + */ +#define INETFRAGS_MAXDEPTH 128 + struct inet_frags { struct hlist_head hash[INETFRAGS_HASHSZ]; /* This rwlock is a global lock (seperate per IPv4, IPv6 and @@ -76,6 +83,8 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force); struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, struct inet_frags *f, void *key, unsigned int hash) __releases(&f->lock); +void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, + const char *prefix); static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f) { diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 245ae078a07f..f4fd23de9b13 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -21,6 +21,7 @@ #include #include +#include #include static void inet_frag_secret_rebuild(unsigned long dummy) @@ -277,6 +278,7 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, __releases(&f->lock) { struct inet_frag_queue *q; + int depth = 0; hlist_for_each_entry(q, &f->hash[hash], list) { if (q->net == nf && f->match(q, key)) { @@ -284,9 +286,25 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, read_unlock(&f->lock); return q; } + depth++; } read_unlock(&f->lock); - return inet_frag_create(nf, f, key); + if (depth <= INETFRAGS_MAXDEPTH) + return inet_frag_create(nf, f, key); + else + return ERR_PTR(-ENOBUFS); } EXPORT_SYMBOL(inet_frag_find); + +void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, + const char *prefix) +{ + static const char msg[] = "inet_frag_find: Fragment hash bucket" + " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH) + ". Dropping fragment.\n"; + + if (PTR_ERR(q) == -ENOBUFS) + LIMIT_NETDEBUG(KERN_WARNING "%s%s", prefix, msg); +} +EXPORT_SYMBOL(inet_frag_maybe_warn_overflow); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b6d30acb600c..a6445b843ef4 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -292,14 +292,11 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); - if (q == NULL) - goto out_nomem; - + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct ipq, q); - -out_nomem: - LIMIT_NETDEBUG(KERN_ERR pr_fmt("ip_frag_create: no memory left !\n")); - return NULL; } /* Is the fragment too far ahead to be part of ipq? */ diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 54087e96d7b8..6700069949dd 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -14,6 +14,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) "IPv6-nf: " fmt + #include #include #include @@ -180,13 +182,11 @@ static inline struct frag_queue *fq_find(struct net *net, __be32 id, q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); local_bh_enable(); - if (q == NULL) - goto oom; - + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); + return NULL; + } return container_of(q, struct frag_queue, q); - -oom: - return NULL; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 3c6a77290c6e..196ab9347ad1 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -26,6 +26,9 @@ * YOSHIFUJI,H. @USAGI Always remove fragment header to * calculate ICV correctly. */ + +#define pr_fmt(fmt) "IPv6: " fmt + #include #include #include @@ -185,9 +188,10 @@ fq_find(struct net *net, __be32 id, const struct in6_addr *src, const struct in6 hash = inet6_hash_frag(id, src, dst, ip6_frags.rnd); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); - if (q == NULL) + if (IS_ERR_OR_NULL(q)) { + inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; - + } return container_of(q, struct frag_queue, q); } -- cgit v1.2.3 From 8ed781668dd49b608f1e67a22e3b445fd0c2cd6f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 19 Mar 2013 06:39:29 +0000 Subject: flow_keys: include thoff into flow_keys for later usage In skb_flow_dissect(), we perform a dissection of a skbuff. Since we're doing the work here anyway, also store thoff for a later usage, e.g. in the BPF filter. Suggested-by: Eric Dumazet Signed-off-by: Daniel Borkmann Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/flow_keys.h | 1 + net/core/flow_dissector.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'include/net') diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h index 80461c1ae9ef..bb8271d487b7 100644 --- a/include/net/flow_keys.h +++ b/include/net/flow_keys.h @@ -9,6 +9,7 @@ struct flow_keys { __be32 ports; __be16 port16[2]; }; + u16 thoff; u8 ip_proto; }; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 9d4c7201400d..e187bf06d673 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -140,6 +140,8 @@ ipv6: flow->ports = *ports; } + flow->thoff = (u16) nhoff; + return true; } EXPORT_SYMBOL(skb_flow_dissect); -- cgit v1.2.3