From bafa6d9d89072c1a18853afe9ee5de05c491c13a Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 7 Sep 2012 00:45:29 +0000 Subject: ipv4/route: arg delay is useless in rt_cache_flush() Since route cache deletion (89aef8921bfbac22f), delay is no more used. Remove it. Signed-off-by: Nicolas Dichtel Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/route.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 776a27f1ab78..da22243d2760 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -108,7 +108,7 @@ extern struct ip_rt_acct __percpu *ip_rt_acct; struct in_device; extern int ip_rt_init(void); -extern void rt_cache_flush(struct net *net, int how); +extern void rt_cache_flush(struct net *net); extern void rt_flush_dev(struct net_device *dev); extern struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); extern struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, -- cgit v1.2.3 From b42664f898c976247f7f609b8bb9c94d7475ca10 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 10 Sep 2012 22:09:44 +0000 Subject: netns: move net->ipv4.rt_genid to net->rt_genid This commit prepares the use of rt_genid by both IPv4 and IPv6. Initialization is left in IPv4 part. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/net_namespace.h | 10 ++++++++++ include/net/netns/ipv4.h | 1 - net/ipv4/route.c | 9 ++------- 3 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index ae1cd6c9ba52..fd87963a0ea5 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -102,6 +102,7 @@ struct net { #endif struct netns_ipvs *ipvs; struct sock *diag_nlsk; + atomic_t rt_genid; }; @@ -300,5 +301,14 @@ static inline void unregister_net_sysctl_table(struct ctl_table_header *header) } #endif +static inline int rt_genid(struct net *net) +{ + return atomic_read(&net->rt_genid); +} + +static inline void rt_genid_bump(struct net *net) +{ + atomic_inc(&net->rt_genid); +} #endif /* __NET_NET_NAMESPACE_H */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1474dd65c66f..eb24dbccd81e 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -65,7 +65,6 @@ struct netns_ipv4 { unsigned int sysctl_ping_group_range[2]; long sysctl_tcp_mem[3]; - atomic_t rt_genid; atomic_t dev_addr_genid; #ifdef CONFIG_IP_MROUTE diff --git a/net/ipv4/route.c b/net/ipv4/route.c index be27cfa96e88..fd9af60397b5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -202,11 +202,6 @@ EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field) -static inline int rt_genid(struct net *net) -{ - return atomic_read(&net->ipv4.rt_genid); -} - #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { @@ -449,7 +444,7 @@ static inline bool rt_is_expired(const struct rtable *rth) void rt_cache_flush(struct net *net) { - atomic_inc(&net->ipv4.rt_genid); + rt_genid_bump(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -2506,7 +2501,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->ipv4.rt_genid, 0); + atomic_set(&net->rt_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); return 0; -- cgit v1.2.3 From 6f3118b571b8a4c06c7985dc3172c3526cb86253 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Mon, 10 Sep 2012 22:09:46 +0000 Subject: ipv6: use net->rt_genid to check dst validity IPv6 dst should take care of rt_genid too. When a xfrm policy is inserted or deleted, all dst should be invalidated. To force the validation, dst entries should be created with ->obsolete set to DST_OBSOLETE_FORCE_CHK. This was already the case for all functions calling ip6_dst_alloc(), except for ip6_rt_copy(). As a consequence, we can remove the specific code in inet6_connection_sock. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 5 ++--- net/ipv6/inet6_connection_sock.c | 23 +---------------------- net/ipv6/route.c | 13 +++++++++---- 3 files changed, 12 insertions(+), 29 deletions(-) (limited to 'include') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 0fedbd8d747a..9fc7114159e8 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -111,9 +111,8 @@ struct rt6_info { struct inet6_dev *rt6i_idev; unsigned long _rt6i_peer; -#ifdef CONFIG_XFRM - u32 rt6i_flow_cache_genid; -#endif + u32 rt6i_genid; + /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 0251a6005be8..c4f934176cab 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -175,33 +175,12 @@ void __inet6_csk_dst_store(struct sock *sk, struct dst_entry *dst, const struct in6_addr *saddr) { __ip6_dst_store(sk, dst, daddr, saddr); - -#ifdef CONFIG_XFRM - { - struct rt6_info *rt = (struct rt6_info *)dst; - rt->rt6i_flow_cache_genid = atomic_read(&flow_cache_genid); - } -#endif } static inline struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) { - struct dst_entry *dst; - - dst = __sk_dst_check(sk, cookie); - -#ifdef CONFIG_XFRM - if (dst) { - struct rt6_info *rt = (struct rt6_info *)dst; - if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) { - __sk_dst_reset(sk); - dst = NULL; - } - } -#endif - - return dst; + return __sk_dst_check(sk, cookie); } static struct dst_entry *inet6_csk_route_socket(struct sock *sk, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8e80fd279100..fb29e2215a19 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -281,13 +281,14 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct fib6_table *table) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, - 0, DST_OBSOLETE_NONE, flags); + 0, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { struct dst_entry *dst = &rt->dst; memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); + rt->rt6i_genid = rt_genid(net); } return rt; } @@ -1031,6 +1032,13 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) rt = (struct rt6_info *) dst; + /* All IPV6 dsts are created with ->obsolete set to the value + * DST_OBSOLETE_FORCE_CHK which forces validation calls down + * into this function always. + */ + if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) + return NULL; + if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) { if (rt->rt6i_peer_genid != rt6_peer_genid()) { if (!rt6_has_peer(rt)) @@ -1397,8 +1405,6 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt->dst.obsolete = -1; - if (cfg->fc_flags & RTF_EXPIRES) rt6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); @@ -2080,7 +2086,6 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_idev = idev; - rt->dst.obsolete = -1; rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; if (anycast) -- cgit v1.2.3 From ecd7918745234e423dd87fcc0c077da557909720 Mon Sep 17 00:00:00 2001 From: Mathias Krause Date: Thu, 20 Sep 2012 10:01:49 +0000 Subject: xfrm_user: ensure user supplied esn replay window is valid The current code fails to ensure that the netlink message actually contains as many bytes as the header indicates. If a user creates a new state or updates an existing one but does not supply the bytes for the whole ESN replay window, the kernel copies random heap bytes into the replay bitmap, the ones happen to follow the XFRMA_REPLAY_ESN_VAL netlink attribute. This leads to following issues: 1. The replay window has random bits set confusing the replay handling code later on. 2. A malicious user could use this flaw to leak up to ~3.5kB of heap memory when she has access to the XFRM netlink interface (requires CAP_NET_ADMIN). Known users of the ESN replay window are strongSwan and Steffen's iproute2 patch (). The latter uses the interface with a bitmap supplied while the former does not. strongSwan is therefore prone to run into issue 1. To fix both issues without breaking existing userland allow using the XFRMA_REPLAY_ESN_VAL netlink attribute with either an empty bitmap or a fully specified one. For the former case we initialize the in-kernel bitmap with zero, for the latter we copy the user supplied bitmap. For state updates the full bitmap must be supplied. To prevent overflows in the bitmap length calculation the maximum size of bmp_len is limited to 128 by this patch -- resulting in a maximum replay window of 4096 packets. This should be sufficient for all real life scenarios (RFC 4303 recommends a default replay window size of 64). Cc: Steffen Klassert Cc: Martin Willi Cc: Ben Hutchings Signed-off-by: Mathias Krause Signed-off-by: David S. Miller --- include/linux/xfrm.h | 2 ++ net/xfrm/xfrm_user.c | 31 +++++++++++++++++++++++++------ 2 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 22e61fdf75a2..28e493b5b94c 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -84,6 +84,8 @@ struct xfrm_replay_state { __u32 bitmap; }; +#define XFRMA_REPLAY_ESN_MAX 4096 + struct xfrm_replay_state_esn { unsigned int bmp_len; __u32 oseq; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8024b3dea8c2..5927065e97cf 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -123,9 +123,21 @@ static inline int verify_replay(struct xfrm_usersa_info *p, struct nlattr **attrs) { struct nlattr *rt = attrs[XFRMA_REPLAY_ESN_VAL]; + struct xfrm_replay_state_esn *rs; - if ((p->flags & XFRM_STATE_ESN) && !rt) - return -EINVAL; + if (p->flags & XFRM_STATE_ESN) { + if (!rt) + return -EINVAL; + + rs = nla_data(rt); + + if (rs->bmp_len > XFRMA_REPLAY_ESN_MAX / sizeof(rs->bmp[0]) / 8) + return -EINVAL; + + if (nla_len(rt) < xfrm_replay_state_esn_len(rs) && + nla_len(rt) != sizeof(*rs)) + return -EINVAL; + } if (!rt) return 0; @@ -370,14 +382,15 @@ static inline int xfrm_replay_verify_len(struct xfrm_replay_state_esn *replay_es struct nlattr *rp) { struct xfrm_replay_state_esn *up; + int ulen; if (!replay_esn || !rp) return 0; up = nla_data(rp); + ulen = xfrm_replay_state_esn_len(up); - if (xfrm_replay_state_esn_len(replay_esn) != - xfrm_replay_state_esn_len(up)) + if (nla_len(rp) < ulen || xfrm_replay_state_esn_len(replay_esn) != ulen) return -EINVAL; return 0; @@ -388,22 +401,28 @@ static int xfrm_alloc_replay_state_esn(struct xfrm_replay_state_esn **replay_esn struct nlattr *rta) { struct xfrm_replay_state_esn *p, *pp, *up; + int klen, ulen; if (!rta) return 0; up = nla_data(rta); + klen = xfrm_replay_state_esn_len(up); + ulen = nla_len(rta) >= klen ? klen : sizeof(*up); - p = kmemdup(up, xfrm_replay_state_esn_len(up), GFP_KERNEL); + p = kzalloc(klen, GFP_KERNEL); if (!p) return -ENOMEM; - pp = kmemdup(up, xfrm_replay_state_esn_len(up), GFP_KERNEL); + pp = kzalloc(klen, GFP_KERNEL); if (!pp) { kfree(p); return -ENOMEM; } + memcpy(p, up, ulen); + memcpy(pp, up, ulen); + *replay_esn = p; *preplay_esn = pp; -- cgit v1.2.3