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 From 330305cc4a6b0cb75c22fc01b8826f0ad755550f Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Sun, 24 Mar 2013 17:36:29 +0000 Subject: ipv4: Fix ip-header identification for gso packets. ip-header id needs to be incremented even if IP_DF flag is set. This behaviour was changed in commit 490ab08127cebc25e3a26 (IP_GRE: Fix IP-Identification). Following patch fixes it so that identification is always incremented. Reported-by: Cong Wang Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/net/ipip.h | 16 ++++++---------- net/ipv4/af_inet.c | 3 +-- 2 files changed, 7 insertions(+), 12 deletions(-) (limited to 'include/net') diff --git a/include/net/ipip.h b/include/net/ipip.h index fd19625ff99d..982141c15200 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -77,15 +77,11 @@ static inline void tunnel_ip_select_ident(struct sk_buff *skb, { struct iphdr *iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_DF)) - iph->id = 0; - else { - /* Use inner packet iph-id if possible. */ - if (skb->protocol == htons(ETH_P_IP) && old_iph->id) - iph->id = old_iph->id; - else - __ip_select_ident(iph, dst, - (skb_shinfo(skb)->gso_segs ?: 1) - 1); - } + /* Use inner packet iph-id if possible. */ + if (skb->protocol == htons(ETH_P_IP) && old_iph->id) + iph->id = old_iph->id; + else + __ip_select_ident(iph, dst, + (skb_shinfo(skb)->gso_segs ?: 1) - 1); } #endif diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 68f6a94f7661..c929d9c1c4b6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1333,8 +1333,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, iph->frag_off |= htons(IP_MF); offset += (skb->len - skb->mac_len - iph->ihl * 4); } else { - if (!(iph->frag_off & htons(IP_DF))) - iph->id = htons(id++); + iph->id = htons(id++); } iph->tot_len = htons(skb->len - skb->mac_len); iph->check = 0; -- cgit v1.2.3 From f9c41a62bba3f3f7ef3541b2a025e3371bcbba97 Mon Sep 17 00:00:00 2001 From: Ursula Braun Date: Sun, 7 Apr 2013 22:19:26 +0000 Subject: af_iucv: fix recvmsg by replacing skb_pull() function When receiving data messages, the "BUG_ON(skb->len < skb->data_len)" in the skb_pull() function triggers a kernel panic. Replace the skb_pull logic by a per skb offset as advised by Eric Dumazet. Signed-off-by: Ursula Braun Signed-off-by: Frank Blaschka Reviewed-by: Hendrik Brueckner Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/iucv/af_iucv.h | 8 ++++++++ net/iucv/af_iucv.c | 34 ++++++++++++++++------------------ 2 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include/net') diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index cc7c19732389..714cc9a54a4c 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -130,6 +130,14 @@ struct iucv_sock { enum iucv_tx_notify n); }; +struct iucv_skb_cb { + u32 class; /* target class of message */ + u32 tag; /* tag associated with message */ + u32 offset; /* offset for skb receival */ +}; + +#define IUCV_SKB_CB(__skb) ((struct iucv_skb_cb *)&((__skb)->cb[0])) + /* iucv socket options (SOL_IUCV) */ #define SO_IPRMDATA_MSG 0x0080 /* send/recv IPRM_DATA msgs */ #define SO_MSGLIMIT 0x1000 /* get/set IUCV MSGLIMIT */ diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index bf6935820001..206ce6db2c36 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -49,12 +49,6 @@ static const u8 iprm_shutdown[8] = #define TRGCLS_SIZE (sizeof(((struct iucv_message *)0)->class)) -/* macros to set/get socket control buffer at correct offset */ -#define CB_TAG(skb) ((skb)->cb) /* iucv message tag */ -#define CB_TAG_LEN (sizeof(((struct iucv_message *) 0)->tag)) -#define CB_TRGCLS(skb) ((skb)->cb + CB_TAG_LEN) /* iucv msg target class */ -#define CB_TRGCLS_LEN (TRGCLS_SIZE) - #define __iucv_sock_wait(sk, condition, timeo, ret) \ do { \ DEFINE_WAIT(__wait); \ @@ -1141,7 +1135,7 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock, /* increment and save iucv message tag for msg_completion cbk */ txmsg.tag = iucv->send_tag++; - memcpy(CB_TAG(skb), &txmsg.tag, CB_TAG_LEN); + IUCV_SKB_CB(skb)->tag = txmsg.tag; if (iucv->transport == AF_IUCV_TRANS_HIPER) { atomic_inc(&iucv->msg_sent); @@ -1224,7 +1218,7 @@ static int iucv_fragment_skb(struct sock *sk, struct sk_buff *skb, int len) return -ENOMEM; /* copy target class to control buffer of new skb */ - memcpy(CB_TRGCLS(nskb), CB_TRGCLS(skb), CB_TRGCLS_LEN); + IUCV_SKB_CB(nskb)->class = IUCV_SKB_CB(skb)->class; /* copy data fragment */ memcpy(nskb->data, skb->data + copied, size); @@ -1256,7 +1250,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, /* store msg target class in the second 4 bytes of skb ctrl buffer */ /* Note: the first 4 bytes are reserved for msg tag */ - memcpy(CB_TRGCLS(skb), &msg->class, CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = msg->class; /* check for special IPRM messages (e.g. iucv_sock_shutdown) */ if ((msg->flags & IUCV_IPRMDATA) && len > 7) { @@ -1292,6 +1286,7 @@ static void iucv_process_message(struct sock *sk, struct sk_buff *skb, } } + IUCV_SKB_CB(skb)->offset = 0; if (sock_queue_rcv_skb(sk, skb)) skb_queue_head(&iucv_sk(sk)->backlog_skb_q, skb); } @@ -1327,6 +1322,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, unsigned int copied, rlen; struct sk_buff *skb, *rskb, *cskb; int err = 0; + u32 offset; msg->msg_namelen = 0; @@ -1348,13 +1344,14 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, return err; } - rlen = skb->len; /* real length of skb */ + offset = IUCV_SKB_CB(skb)->offset; + rlen = skb->len - offset; /* real length of skb */ copied = min_t(unsigned int, rlen, len); if (!rlen) sk->sk_shutdown = sk->sk_shutdown | RCV_SHUTDOWN; cskb = skb; - if (skb_copy_datagram_iovec(cskb, 0, msg->msg_iov, copied)) { + if (skb_copy_datagram_iovec(cskb, offset, msg->msg_iov, copied)) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); return -EFAULT; @@ -1372,7 +1369,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, * get the trgcls from the control buffer of the skb due to * fragmentation of original iucv message. */ err = put_cmsg(msg, SOL_IUCV, SCM_IUCV_TRGCLS, - CB_TRGCLS_LEN, CB_TRGCLS(skb)); + sizeof(IUCV_SKB_CB(skb)->class), + (void *)&IUCV_SKB_CB(skb)->class); if (err) { if (!(flags & MSG_PEEK)) skb_queue_head(&sk->sk_receive_queue, skb); @@ -1384,9 +1382,8 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, /* SOCK_STREAM: re-queue skb if it contains unreceived data */ if (sk->sk_type == SOCK_STREAM) { - skb_pull(skb, copied); - if (skb->len) { - skb_queue_head(&sk->sk_receive_queue, skb); + if (copied < rlen) { + IUCV_SKB_CB(skb)->offset = offset + copied; goto done; } } @@ -1405,6 +1402,7 @@ static int iucv_sock_recvmsg(struct kiocb *iocb, struct socket *sock, spin_lock_bh(&iucv->message_q.lock); rskb = skb_dequeue(&iucv->backlog_skb_q); while (rskb) { + IUCV_SKB_CB(rskb)->offset = 0; if (sock_queue_rcv_skb(sk, rskb)) { skb_queue_head(&iucv->backlog_skb_q, rskb); @@ -1832,7 +1830,7 @@ static void iucv_callback_txdone(struct iucv_path *path, spin_lock_irqsave(&list->lock, flags); while (list_skb != (struct sk_buff *)list) { - if (!memcmp(&msg->tag, CB_TAG(list_skb), CB_TAG_LEN)) { + if (msg->tag != IUCV_SKB_CB(list_skb)->tag) { this = list_skb; break; } @@ -2093,6 +2091,7 @@ static int afiucv_hs_callback_rx(struct sock *sk, struct sk_buff *skb) skb_pull(skb, sizeof(struct af_iucv_trans_hdr)); skb_reset_transport_header(skb); skb_reset_network_header(skb); + IUCV_SKB_CB(skb)->offset = 0; spin_lock(&iucv->message_q.lock); if (skb_queue_empty(&iucv->backlog_skb_q)) { if (sock_queue_rcv_skb(sk, skb)) { @@ -2197,8 +2196,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, /* fall through and receive zero length data */ case 0: /* plain data frame */ - memcpy(CB_TRGCLS(skb), &trans_hdr->iucv_hdr.class, - CB_TRGCLS_LEN); + IUCV_SKB_CB(skb)->class = trans_hdr->iucv_hdr.class; err = afiucv_hs_callback_rx(sk, skb); break; default: -- cgit v1.2.3 From f88c91ddba958e9a5dd4a5ee8c52a0faa790f586 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sun, 14 Apr 2013 23:18:43 +0800 Subject: ipv6: statically link register_inet6addr_notifier() Tomas reported the following build error: net/built-in.o: In function `ieee80211_unregister_hw': (.text+0x10f0e1): undefined reference to `unregister_inet6addr_notifier' net/built-in.o: In function `ieee80211_register_hw': (.text+0x10f610): undefined reference to `register_inet6addr_notifier' make: *** [vmlinux] Error 1 when built IPv6 as a module. So we have to statically link these symbols. Reported-by: Tomas Melin Cc: Tomas Melin Cc: "David S. Miller" Cc: YOSHIFUJI Hidaki Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/addrconf.h | 1 + net/ipv6/addrconf.c | 24 +++--------------------- net/ipv6/addrconf_core.c | 19 +++++++++++++++++++ 3 files changed, 23 insertions(+), 21 deletions(-) (limited to 'include/net') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 40be2a0d8ae1..84a6440f1f19 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -199,6 +199,7 @@ extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, /* Device notifier */ extern int register_inet6addr_notifier(struct notifier_block *nb); extern int unregister_inet6addr_notifier(struct notifier_block *nb); +extern int inet6addr_notifier_call_chain(unsigned long val, void *v); extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, struct ipv6_devconf *devconf); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index a459c4f5b769..dae802c0af7c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -168,8 +168,6 @@ static void inet6_prefix_notify(int event, struct inet6_dev *idev, static bool ipv6_chk_same_addr(struct net *net, const struct in6_addr *addr, struct net_device *dev); -static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); - static struct ipv6_devconf ipv6_devconf __read_mostly = { .forwarding = 0, .hop_limit = IPV6_DEFAULT_HOPLIMIT, @@ -837,7 +835,7 @@ out2: rcu_read_unlock_bh(); if (likely(err == 0)) - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_UP, ifa); + inet6addr_notifier_call_chain(NETDEV_UP, ifa); else { kfree(ifa); ifa = ERR_PTR(err); @@ -927,7 +925,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) ipv6_ifa_notify(RTM_DELADDR, ifp); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifp); /* * Purge or update corresponding prefix @@ -2988,7 +2986,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); - atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); + inet6addr_notifier_call_chain(NETDEV_DOWN, ifa); } in6_ifa_put(ifa); @@ -4869,22 +4867,6 @@ static struct pernet_operations addrconf_ops = { .exit = addrconf_exit_net, }; -/* - * Device notifier - */ - -int register_inet6addr_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_register(&inet6addr_chain, nb); -} -EXPORT_SYMBOL(register_inet6addr_notifier); - -int unregister_inet6addr_notifier(struct notifier_block *nb) -{ - return atomic_notifier_chain_unregister(&inet6addr_chain, nb); -} -EXPORT_SYMBOL(unregister_inet6addr_notifier); - static struct rtnl_af_ops inet6_ops = { .family = AF_INET6, .fill_link_af = inet6_fill_link_af, diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index d051e5f4bf34..72104562c864 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -78,3 +78,22 @@ int __ipv6_addr_type(const struct in6_addr *addr) } EXPORT_SYMBOL(__ipv6_addr_type); +static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); + +int register_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(register_inet6addr_notifier); + +int unregister_inet6addr_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&inet6addr_chain, nb); +} +EXPORT_SYMBOL(unregister_inet6addr_notifier); + +int inet6addr_notifier_call_chain(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&inet6addr_chain, val, v); +} +EXPORT_SYMBOL(inet6addr_notifier_call_chain); -- cgit v1.2.3 From e15465e1808542743627f13d1c0cbb7eacc82b83 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 16 Apr 2013 21:10:38 +0000 Subject: irda: small read past the end of array in debug code The "reason" can come from skb->data[] and it hasn't been capped so it can be from 0-255 instead of just 0-6. For example in irlmp_state_dtr() the code does: reason = skb->data[3]; ... irlmp_disconnect_indication(self, reason, skb); Also LMREASON has a couple other values which don't have entries in the irlmp_reasons[] array. And 0xff is a valid reason as well which means "unknown". So far as I can see we don't actually care about "reason" except for in the debug code. Signed-off-by: Dan Carpenter Signed-off-by: David S. Miller --- include/net/irda/irlmp.h | 3 ++- net/irda/iriap.c | 3 ++- net/irda/irlmp.c | 10 +++++++++- 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/include/net/irda/irlmp.h b/include/net/irda/irlmp.h index f74109144d3f..f132924cc9da 100644 --- a/include/net/irda/irlmp.h +++ b/include/net/irda/irlmp.h @@ -256,7 +256,8 @@ static inline __u32 irlmp_get_daddr(const struct lsap_cb *self) return (self && self->lap) ? self->lap->daddr : 0; } -extern const char *irlmp_reasons[]; +const char *irlmp_reason_str(LM_REASON reason); + extern int sysctl_discovery_timeout; extern int sysctl_discovery_slots; extern int sysctl_discovery; diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 29340a9a6fb9..e1b37f5a2691 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -303,7 +303,8 @@ static void iriap_disconnect_indication(void *instance, void *sap, { struct iriap_cb *self; - IRDA_DEBUG(4, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); + IRDA_DEBUG(4, "%s(), reason=%s [%d]\n", __func__, + irlmp_reason_str(reason), reason); self = instance; diff --git a/net/irda/irlmp.c b/net/irda/irlmp.c index 6115a44c0a24..1064621da6f6 100644 --- a/net/irda/irlmp.c +++ b/net/irda/irlmp.c @@ -66,8 +66,15 @@ const char *irlmp_reasons[] = { "LM_LAP_RESET", "LM_INIT_DISCONNECT", "ERROR, NOT USED", + "UNKNOWN", }; +const char *irlmp_reason_str(LM_REASON reason) +{ + reason = min_t(size_t, reason, ARRAY_SIZE(irlmp_reasons) - 1); + return irlmp_reasons[reason]; +} + /* * Function irlmp_init (void) * @@ -747,7 +754,8 @@ void irlmp_disconnect_indication(struct lsap_cb *self, LM_REASON reason, { struct lsap_cb *lsap; - IRDA_DEBUG(1, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); + IRDA_DEBUG(1, "%s(), reason=%s [%d]\n", __func__, + irlmp_reason_str(reason), reason); IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;); -- cgit v1.2.3 From 83f1b4ba917db5dc5a061a44b3403ddb6e783494 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 19 Apr 2013 15:32:32 +0000 Subject: net: fix incorrect credentials passing Commit 257b5358b32f ("scm: Capture the full credentials of the scm sender") changed the credentials passing code to pass in the effective uid/gid instead of the real uid/gid. Obviously this doesn't matter most of the time (since normally they are the same), but it results in differences for suid binaries when the wrong uid/gid ends up being used. This just undoes that (presumably unintentional) part of the commit. Reported-by: Andy Lutomirski Cc: Eric W. Biederman Cc: Serge E. Hallyn Cc: David S. Miller Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/net/scm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/scm.h b/include/net/scm.h index 975cca01048b..b11708105681 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -56,8 +56,8 @@ static __inline__ void scm_set_cred(struct scm_cookie *scm, scm->pid = get_pid(pid); scm->cred = cred ? get_cred(cred) : NULL; scm->creds.pid = pid_vnr(pid); - scm->creds.uid = cred ? cred->euid : INVALID_UID; - scm->creds.gid = cred ? cred->egid : INVALID_GID; + scm->creds.uid = cred ? cred->uid : INVALID_UID; + scm->creds.gid = cred ? cred->gid : INVALID_GID; } static __inline__ void scm_destroy_cred(struct scm_cookie *scm) -- cgit v1.2.3