diff options
author | David S. Miller <davem@davemloft.net> | 2011-08-07 23:20:26 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2011-08-07 23:20:26 -0700 |
commit | 19fd61785a580c60cba900c5171bfadb57dd5056 (patch) | |
tree | 1e491fb014be0dc03f4b6755bb94e73afd38c455 /net | |
parent | 57569d0e12eaf31717e295960cd2a26f626c8e5b (diff) | |
parent | 8028837d71ba9904b17281b40f94b93e947fbe38 (diff) | |
download | op-kernel-dev-19fd61785a580c60cba900c5171bfadb57dd5056.zip op-kernel-dev-19fd61785a580c60cba900c5171bfadb57dd5056.tar.gz |
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net
Diffstat (limited to 'net')
41 files changed, 353 insertions, 103 deletions
diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 2252c20..52cfd0c 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -242,8 +242,6 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev, if (brdev->payload == p_bridged) { skb_push(skb, 2); memset(skb->data, 0, 2); - } else { /* p_routed */ - skb_pull(skb, ETH_HLEN); } } skb_debug(skb); diff --git a/net/core/Makefile b/net/core/Makefile index 8a04dd2..0d357b1 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -3,7 +3,7 @@ # obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ - gen_stats.o gen_estimator.o net_namespace.o + gen_stats.o gen_estimator.o net_namespace.o secure_seq.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c new file mode 100644 index 0000000..45329d7 --- /dev/null +++ b/net/core/secure_seq.c @@ -0,0 +1,184 @@ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/cryptohash.h> +#include <linux/module.h> +#include <linux/cache.h> +#include <linux/random.h> +#include <linux/hrtimer.h> +#include <linux/ktime.h> +#include <linux/string.h> + +#include <net/secure_seq.h> + +static u32 net_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned; + +static int __init net_secret_init(void) +{ + get_random_bytes(net_secret, sizeof(net_secret)); + return 0; +} +late_initcall(net_secret_init); + +static u32 seq_scale(u32 seq) +{ + /* + * As close as possible to RFC 793, which + * suggests using a 250 kHz clock. + * Further reading shows this assumes 2 Mb/s networks. + * For 10 Mb/s Ethernet, a 1 MHz clock is appropriate. + * For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but + * we also need to limit the resolution so that the u32 seq + * overlaps less than one time per MSL (2 minutes). + * Choosing a clock of 64 ns period is OK. (period of 274 s) + */ + return seq + (ktime_to_ns(ktime_get_real()) >> 6); +} + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +__u32 secure_tcpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return seq_scale(hash[0]); +} +EXPORT_SYMBOL(secure_tcpv6_sequence_number); + +u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + (__force u32) daddr[i]; + secret[4] = net_secret[4] + (__force u32)dport; + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + return hash[0]; +} +#endif + +#ifdef CONFIG_INET +__u32 secure_ip_id(__be32 daddr) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force __u32) daddr; + hash[1] = net_secret[13]; + hash[2] = net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} + +__u32 secure_ipv6_id(const __be32 daddr[4]) +{ + __u32 hash[4]; + + memcpy(hash, daddr, 16); + md5_transform(hash, net_secret); + + return hash[0]; +} + +__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return seq_scale(hash[0]); +} + +u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = (__force u32)dport ^ net_secret[14]; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + return hash[0]; +} +EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral); +#endif + +#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE) +u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +{ + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + + hash[0] = (__force u32)saddr; + hash[1] = (__force u32)daddr; + hash[2] = ((__force u16)sport << 16) + (__force u16)dport; + hash[3] = net_secret[15]; + + md5_transform(hash, net_secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccp_sequence_number); + +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, + __be16 sport, __be16 dport) +{ + u32 secret[MD5_MESSAGE_BYTES / 4]; + u32 hash[MD5_DIGEST_WORDS]; + u64 seq; + u32 i; + + memcpy(hash, saddr, 16); + for (i = 0; i < 4; i++) + secret[i] = net_secret[i] + daddr[i]; + secret[4] = net_secret[4] + + (((__force u16)sport << 16) + (__force u16)dport); + for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++) + secret[i] = net_secret[i]; + + md5_transform(hash, secret); + + seq = hash[0] | (((u64)hash[1]) << 32); + seq += ktime_to_ns(ktime_get_real()); + seq &= (1ull << 48) - 1; + + return seq; +} +EXPORT_SYMBOL(secure_dccpv6_sequence_number); +#endif +#endif diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2beda82..27002df 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1369,8 +1369,21 @@ pull_pages: } EXPORT_SYMBOL(__pskb_pull_tail); -/* Copy some data bits from skb to kernel buffer. */ - +/** + * skb_copy_bits - copy bits from skb to kernel buffer + * @skb: source skb + * @offset: offset in source + * @to: destination buffer + * @len: number of bytes to copy + * + * Copy the specified number of bytes from the source skb to the + * destination buffer. + * + * CAUTION ! : + * If its prototype is ever changed, + * check arch/{*}/net/{*}.S files, + * since it is called from BPF assembly code. + */ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { int start = skb_headlen(skb); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 8c36adf..332639b 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -26,6 +26,7 @@ #include <net/timewait_sock.h> #include <net/tcp_states.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "ackvec.h" #include "ccid.h" diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 8dc4348..b74f761 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -29,6 +29,7 @@ #include <net/transp_v6.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "dccp.h" #include "ipv6.h" @@ -69,13 +70,7 @@ static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr); } -static inline __u32 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport ) -{ - return secure_tcpv6_sequence_number(saddr, daddr, sport, dport); -} - -static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) +static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 83532d2..7069522 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1718,7 +1718,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[sfmode]--; for (j=0; j<i; j++) - (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); + (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 3c0369a..984ec65 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -21,6 +21,7 @@ #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> +#include <net/secure_seq.h> #include <net/ip.h> /* diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index e382138..86f13c67 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -19,6 +19,7 @@ #include <linux/net.h> #include <net/ip.h> #include <net/inetpeer.h> +#include <net/secure_seq.h> /* * Theory of operations. diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index ccaaa85..8c65633 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -122,6 +122,7 @@ static int ip_dev_loopback_xmit(struct sk_buff *newskb) newskb->pkt_type = PACKET_LOOPBACK; newskb->ip_summed = CHECKSUM_UNNECESSARY; WARN_ON(!skb_dst(newskb)); + skb_dst_force(newskb); netif_rx_ni(newskb); return 0; } @@ -204,9 +205,15 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } + rcu_read_lock(); neigh = dst_get_neighbour(dst); - if (neigh) - return neigh_output(neigh, skb); + if (neigh) { + int res = neigh_output(neigh, skb); + + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); if (net_ratelimit()) printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index ab0c9ef..8905e92 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1067,7 +1067,7 @@ EXPORT_SYMBOL(compat_ip_setsockopt); */ static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + char __user *optval, int __user *optlen, unsigned flags) { struct inet_sock *inet = inet_sk(sk); int val; @@ -1240,7 +1240,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, msg.msg_control = optval; msg.msg_controllen = len; - msg.msg_flags = 0; + msg.msg_flags = flags; if (inet->cmsg_flags & IP_CMSG_PKTINFO) { struct in_pktinfo info; @@ -1294,7 +1294,7 @@ int ip_getsockopt(struct sock *sk, int level, { int err; - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ if (err == -ENOPROTOOPT && optname != IP_PKTOPTIONS && @@ -1327,7 +1327,8 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, return compat_mc_getsockopt(sk, level, optname, optval, optlen, ip_getsockopt); - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, optval, optlen, + MSG_CMSG_COMPAT); #ifdef CONFIG_NETFILTER /* we need to exclude all possible ENOPROTOOPTs except default case */ diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 2e97e3e..929b27b 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -18,17 +18,15 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) struct rtable *rt; struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; - __u8 flags = 0; + __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; unsigned int hh_len; - if (!skb->sk && addr_type != RTN_LOCAL) { - if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); - if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) - flags |= FLOWI_FLAG_ANYSRC; - else - saddr = 0; - } + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(net, saddr); + if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) + flags |= FLOWI_FLAG_ANYSRC; + else + saddr = 0; /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. @@ -38,7 +36,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; fl4.flowi4_mark = skb->mark; - fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags; + fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) return -1; diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index 3e61faf..f52d41e 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -12,6 +12,7 @@ #include <linux/ip.h> #include <linux/netfilter.h> +#include <net/secure_seq.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_rule.h> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1457acb..61714bd 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -563,7 +563,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, - FLOWI_FLAG_CAN_SLEEP, daddr, saddr, 0, 0); + inet_sk_flowi_flags(sk) | FLOWI_FLAG_CAN_SLEEP, + daddr, saddr, 0, 0); if (!inet->hdrincl) { err = raw_probe_proto_opt(&fl4, msg); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 1730689..cb7efe0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -109,6 +109,7 @@ #include <linux/sysctl.h> #endif #include <net/atmclip.h> +#include <net/secure_seq.h> #define RT_FL_TOS(oldflp4) \ ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) @@ -730,6 +731,7 @@ static inline int compare_keys(struct rtable *rt1, struct rtable *rt2) ((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) | (rt1->rt_mark ^ rt2->rt_mark) | (rt1->rt_key_tos ^ rt2->rt_key_tos) | + (rt1->rt_route_iif ^ rt2->rt_route_iif) | (rt1->rt_oif ^ rt2->rt_oif) | (rt1->rt_iif ^ rt2->rt_iif)) == 0; } @@ -1628,16 +1630,18 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; - struct neighbour *n; + struct neighbour *n, *old_n; dst_confirm(&rt->dst); - neigh_release(dst_get_neighbour(&rt->dst)); - dst_set_neighbour(&rt->dst, NULL); - rt->rt_gateway = peer->redirect_learned.a4; - rt_bind_neighbour(rt); - n = dst_get_neighbour(&rt->dst); + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); if (!n || !(n->nud_state & NUD_VALID)) { if (n) neigh_event_send(n, NULL); @@ -2318,8 +2322,8 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) | ((__force u32)rth->rt_key_src ^ (__force u32)saddr) | (rth->rt_iif ^ iif) | - rth->rt_oif | (rth->rt_key_tos ^ tos)) == 0 && + rt_is_input_route(rth) && rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 955b8e6..1c12b8e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -72,6 +72,7 @@ #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/netdma.h> +#include <net/secure_seq.h> #include <linux/inet.h> #include <linux/ipv6.h> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7d82123..8f1e5be 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -656,7 +656,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, * layer address of our nexhop router */ - if (dst_get_neighbour(&rt->dst) == NULL) + if (dst_get_neighbour_raw(&rt->dst) == NULL) ifa->flags &= ~IFA_F_OPTIMISTIC; ifa->idev = idev; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 1656033..9ef1831 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -33,6 +33,11 @@ #include <linux/errqueue.h> #include <asm/uaccess.h> +static inline int ipv6_mapped_addr_any(const struct in6_addr *a) +{ + return (ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0)); +} + int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; @@ -102,10 +107,12 @@ ipv4_connected: ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); - if (ipv6_addr_any(&np->saddr)) + if (ipv6_addr_any(&np->saddr) || + ipv6_mapped_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) { + if (ipv6_addr_any(&np->rcv_saddr) || + ipv6_mapped_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); if (sk->sk_prot->rehash) diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b531972..73f1a00 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -20,6 +20,7 @@ #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> +#include <net/secure_seq.h> #include <net/ip.h> int __inet6_hash(struct sock *sk, struct inet_timewait_sock *tw) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 54a4678..320d91d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1455,7 +1455,7 @@ 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(&rt->dst)->flags & NTF_ROUTER))) { + (!(dst_get_neighbour_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 32e5339..4c882cf 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -135,10 +135,15 @@ static int ip6_finish_output2(struct sk_buff *skb) skb->len); } + rcu_read_lock(); neigh = dst_get_neighbour(dst); - if (neigh) - return neigh_output(neigh, skb); + if (neigh) { + int res = neigh_output(neigh, skb); + rcu_read_unlock(); + return res; + } + rcu_read_unlock(); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); @@ -975,12 +980,14 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry and replace it instead with the * dst entry of the nexthop router */ + rcu_read_lock(); n = dst_get_neighbour(*dst); if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; + rcu_read_unlock(); ifp = ipv6_get_ifaddr(net, &fl6->saddr, (*dst)->dev, 1); @@ -1000,6 +1007,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, if ((err = (*dst)->error)) goto out_err_release; } + } else { + rcu_read_unlock(); } #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e8987da..9e69eb0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -364,7 +364,7 @@ out: #ifdef CONFIG_IPV6_ROUTER_PREF static void rt6_probe(struct rt6_info *rt) { - struct neighbour *neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; + struct neighbour *neigh; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it @@ -373,8 +373,10 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ + rcu_read_lock(); + neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; if (!neigh || (neigh->nud_state & NUD_VALID)) - return; + goto out; read_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) { @@ -387,8 +389,11 @@ static void rt6_probe(struct rt6_info *rt) target = (struct in6_addr *)&neigh->primary_key; addrconf_addr_solict_mult(target, &mcaddr); ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL); - } else + } else { read_unlock_bh(&neigh->lock); + } +out: + rcu_read_unlock(); } #else static inline void rt6_probe(struct rt6_info *rt) @@ -412,8 +417,11 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) static inline int rt6_check_neigh(struct rt6_info *rt) { - struct neighbour *neigh = dst_get_neighbour(&rt->dst); + struct neighbour *neigh; int m; + + rcu_read_lock(); + neigh = dst_get_neighbour(&rt->dst); if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) m = 1; @@ -430,6 +438,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt) read_unlock_bh(&neigh->lock); } else m = 0; + rcu_read_unlock(); return m; } @@ -769,7 +778,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; rt->dst.flags |= DST_HOST; - dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour(&ort->dst))); + dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst))); } return rt; } @@ -803,7 +812,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_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); @@ -1587,7 +1596,7 @@ 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(&rt->dst)) + if (neigh == dst_get_neighbour_raw(&rt->dst)) goto out; nrt = ip6_rt_copy(rt, dest); @@ -1682,7 +1691,7 @@ again: 1. It is connected route. Action: COW 2. It is gatewayed route or NONEXTHOP route. Action: clone it. */ - if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, daddr, saddr); else nrt = rt6_alloc_clone(rt, daddr); @@ -2326,6 +2335,7 @@ static int rt6_fill_node(struct net *net, struct nlmsghdr *nlh; long expires; u32 table; + struct neighbour *n; if (prefix) { /* user wants prefix routes only */ if (!(rt->rt6i_flags & RTF_PREFIX_RT)) { @@ -2414,8 +2424,11 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - if (dst_get_neighbour(&rt->dst)) - NLA_PUT(skb, RTA_GATEWAY, 16, &dst_get_neighbour(&rt->dst)->primary_key); + rcu_read_lock(); + n = dst_get_neighbour(&rt->dst); + if (n) + NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key); + rcu_read_unlock(); if (rt->dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); @@ -2608,12 +2621,14 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif + rcu_read_lock(); n = dst_get_neighbour(&rt->dst); if (n) { seq_printf(m, "%pi6", n->primary_key); } else { seq_puts(m, "00000000000000000000000000000000"); } + rcu_read_unlock(); seq_printf(m, " %08x %08x %08x %08x %8s\n", rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), rt->dst.__use, rt->rt6i_flags, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 78aa534..d1fb63f 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -61,6 +61,7 @@ #include <net/timewait_sock.h> #include <net/netdma.h> #include <net/inet_common.h> +#include <net/secure_seq.h> #include <asm/uaccess.h> diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index c1894ae..99ffd28 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -312,6 +312,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) } break; case NF_STOLEN: + break; default: kfree_skb(skb); } diff --git a/net/netlabel/Makefile b/net/netlabel/Makefile index ea750e9..d2732fc 100644 --- a/net/netlabel/Makefile +++ b/net/netlabel/Makefile @@ -1,8 +1,6 @@ # # Makefile for the NetLabel subsystem. # -# Feb 9, 2006, Paul Moore <paul.moore@hp.com> -# # base objects obj-y := netlabel_user.o netlabel_kapi.o diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c index c051913..96b749d 100644 --- a/net/netlabel/netlabel_addrlist.c +++ b/net/netlabel/netlabel_addrlist.c @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h index 2b9644e..fdbc1d2 100644 --- a/net/netlabel/netlabel_addrlist.h +++ b/net/netlabel/netlabel_addrlist.h @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index dd53a36..6bf8783 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_cipso_v4.h b/net/netlabel/netlabel_cipso_v4.h index af7f335..d24d774 100644 --- a/net/netlabel/netlabel_cipso_v4.h +++ b/net/netlabel/netlabel_cipso_v4.h @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index c0594cd..3f905e5 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h index 0261dda..bfcc0f7 100644 --- a/net/netlabel/netlabel_domainhash.h +++ b/net/netlabel/netlabel_domainhash.h @@ -6,7 +6,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index b528dd9..58107d0 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -5,7 +5,7 @@ * system manages static and dynamic label mappings for network protocols such * as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index dff8a08..bfa5558 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_mgmt.h b/net/netlabel/netlabel_mgmt.h index 8db37f4..5a9f31c 100644 --- a/net/netlabel/netlabel_mgmt.h +++ b/net/netlabel/netlabel_mgmt.h @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 5a587cf..e251c2c 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -5,7 +5,7 @@ * NetLabel system. The NetLabel system manages static and dynamic label * mappings for network protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_unlabeled.h b/net/netlabel/netlabel_unlabeled.h index 0bc8dc3..700af49 100644 --- a/net/netlabel/netlabel_unlabeled.h +++ b/net/netlabel/netlabel_unlabeled.h @@ -5,7 +5,7 @@ * NetLabel system. The NetLabel system manages static and dynamic label * mappings for network protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c index a3fd75a..9fae63f 100644 --- a/net/netlabel/netlabel_user.c +++ b/net/netlabel/netlabel_user.c @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/netlabel/netlabel_user.h b/net/netlabel/netlabel_user.h index f4fc4c9..8196978 100644 --- a/net/netlabel/netlabel_user.h +++ b/net/netlabel/netlabel_user.h @@ -5,7 +5,7 @@ * NetLabel system manages static and dynamic label mappings for network * protocols such as CIPSO and RIPSO. * - * Author: Paul Moore <paul.moore@hp.com> + * Author: Paul Moore <paul@paul-moore.com> * */ diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 4536ee6..4f5510e 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -410,7 +410,12 @@ sfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* Return Congestion Notification only if we dropped a packet * from this flow. */ - return (qlen != slot->qlen) ? NET_XMIT_CN : NET_XMIT_SUCCESS; + if (qlen != slot->qlen) + return NET_XMIT_CN; + + /* As we dropped a packet, better let upper stack know this */ + qdisc_tree_decrease_qlen(sch, 1); + return NET_XMIT_SUCCESS; } static struct sk_buff * diff --git a/net/socket.c b/net/socket.c index 7ec8f9b..2517e11 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1871,8 +1871,14 @@ SYSCALL_DEFINE2(shutdown, int, fd, int, how) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) +struct used_address { + struct sockaddr_storage name; + unsigned int name_len; +}; + static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, - struct msghdr *msg_sys, unsigned flags, int nosec) + struct msghdr *msg_sys, unsigned flags, + struct used_address *used_address) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *)msg; @@ -1953,8 +1959,28 @@ static int __sys_sendmsg(struct socket *sock, struct msghdr __user *msg, if (sock->file->f_flags & O_NONBLOCK) msg_sys->msg_flags |= MSG_DONTWAIT; - err = (nosec ? sock_sendmsg_nosec : sock_sendmsg)(sock, msg_sys, - total_len); + /* + * If this is sendmmsg() and current destination address is same as + * previously succeeded address, omit asking LSM's decision. + * used_address->name_len is initialized to UINT_MAX so that the first + * destination address never matches. + */ + if (used_address && used_address->name_len == msg_sys->msg_namelen && + !memcmp(&used_address->name, msg->msg_name, + used_address->name_len)) { + err = sock_sendmsg_nosec(sock, msg_sys, total_len); + goto out_freectl; + } + err = sock_sendmsg(sock, msg_sys, total_len); + /* + * If this is sendmmsg() and sending to current destination address was + * successful, remember it. + */ + if (used_address && err >= 0) { + used_address->name_len = msg_sys->msg_namelen; + memcpy(&used_address->name, msg->msg_name, + used_address->name_len); + } out_freectl: if (ctl_buf != ctl) @@ -1979,7 +2005,7 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct msghdr __user *, msg, unsigned, flags) if (!sock) goto out; - err = __sys_sendmsg(sock, msg, &msg_sys, flags, 0); + err = __sys_sendmsg(sock, msg, &msg_sys, flags, NULL); fput_light(sock->file, fput_needed); out: @@ -1998,6 +2024,10 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; + struct used_address used_address; + + if (vlen > UIO_MAXIOV) + vlen = UIO_MAXIOV; datagrams = 0; @@ -2005,27 +2035,22 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, if (!sock) return err; - err = sock_error(sock->sk); - if (err) - goto out_put; - + used_address.name_len = UINT_MAX; entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; + err = 0; while (datagrams < vlen) { - /* - * No need to ask LSM for more than the first datagram. - */ if (MSG_CMSG_COMPAT & flags) { err = __sys_sendmsg(sock, (struct msghdr __user *)compat_entry, - &msg_sys, flags, datagrams); + &msg_sys, flags, &used_address); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = __sys_sendmsg(sock, (struct msghdr __user *)entry, - &msg_sys, flags, datagrams); + &msg_sys, flags, &used_address); if (err < 0) break; err = put_user(err, &entry->msg_len); @@ -2037,29 +2062,11 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, ++datagrams; } -out_put: fput_light(sock->file, fput_needed); - if (err == 0) - return datagrams; - - if (datagrams != 0) { - /* - * We may send less entries than requested (vlen) if the - * sock is non blocking... - */ - if (err != -EAGAIN) { - /* - * ... or if sendmsg returns an error after we - * send some datagrams, where we record the - * error to return on the next call or if the - * app asks about it using getsockopt(SO_ERROR). - */ - sock->sk->sk_err = -err; - } - + /* We only return an error if no datagrams were able to be sent */ + if (datagrams != 0) return datagrams; - } return err; } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 28d2aa1..e83e7fe 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3464,7 +3464,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) tmp) { enum ieee80211_band band = nla_type(attr); - if (band < 0 || band > IEEE80211_NUM_BANDS) { + if (band < 0 || band >= IEEE80211_NUM_BANDS) { err = -EINVAL; goto out_free; } |