From 40384999d142552b81aeb596c2ae663dd3ff60ce Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Aug 2012 21:06:50 +0000 Subject: ipv4: change inet_addr_hash() Use net_hash_mix(net) instead of hash_ptr(net, 8), and use hash_32() instead of using a serie of XOR Define IN4_ADDR_HSIZE_SHIFT for clarity __ip_dev_find() can perform the net_eq() call only if ifa_local matches the key, to avoid unneeded dereferences. remove inline attributes # size net/ipv4/devinet.o.before net/ipv4/devinet.o text data bss dec hex filename 17471 2545 2048 22064 5630 net/ipv4/devinet.o.before 17335 2545 2048 21928 55a8 net/ipv4/devinet.o Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 44bf82e3aef7..adf273f8ad2e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -94,25 +94,22 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; -/* inet_addr_hash's shifting is dependent upon this IN4_ADDR_HSIZE - * value. So if you change this define, make appropriate changes to - * inet_addr_hash as well. - */ -#define IN4_ADDR_HSIZE 256 +#define IN4_ADDR_HSIZE_SHIFT 8 +#define IN4_ADDR_HSIZE (1U << IN4_ADDR_HSIZE_SHIFT) + static struct hlist_head inet_addr_lst[IN4_ADDR_HSIZE]; static DEFINE_SPINLOCK(inet_addr_hash_lock); -static inline unsigned int inet_addr_hash(struct net *net, __be32 addr) +static u32 inet_addr_hash(struct net *net, __be32 addr) { - u32 val = (__force u32) addr ^ hash_ptr(net, 8); + u32 val = (__force u32) addr ^ net_hash_mix(net); - return ((val ^ (val >> 8) ^ (val >> 16) ^ (val >> 24)) & - (IN4_ADDR_HSIZE - 1)); + return hash_32(val, IN4_ADDR_HSIZE_SHIFT); } static void inet_hash_insert(struct net *net, struct in_ifaddr *ifa) { - unsigned int hash = inet_addr_hash(net, ifa->ifa_local); + u32 hash = inet_addr_hash(net, ifa->ifa_local); spin_lock(&inet_addr_hash_lock); hlist_add_head_rcu(&ifa->hash, &inet_addr_lst[hash]); @@ -136,18 +133,18 @@ static void inet_hash_remove(struct in_ifaddr *ifa) */ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - unsigned int hash = inet_addr_hash(net, addr); + u32 hash = inet_addr_hash(net, addr); struct net_device *result = NULL; struct in_ifaddr *ifa; struct hlist_node *node; rcu_read_lock(); hlist_for_each_entry_rcu(ifa, node, &inet_addr_lst[hash], hash) { - struct net_device *dev = ifa->ifa_dev->dev; - - if (!net_eq(dev_net(dev), net)) - continue; if (ifa->ifa_local == addr) { + struct net_device *dev = ifa->ifa_dev->dev; + + if (!net_eq(dev_net(dev), net)) + continue; result = dev; break; } @@ -182,10 +179,10 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, static void devinet_sysctl_register(struct in_device *idev); static void devinet_sysctl_unregister(struct in_device *idev); #else -static inline void devinet_sysctl_register(struct in_device *idev) +static void devinet_sysctl_register(struct in_device *idev) { } -static inline void devinet_sysctl_unregister(struct in_device *idev) +static void devinet_sysctl_unregister(struct in_device *idev) { } #endif @@ -205,7 +202,7 @@ static void inet_rcu_free_ifa(struct rcu_head *head) kfree(ifa); } -static inline void inet_free_ifa(struct in_ifaddr *ifa) +static void inet_free_ifa(struct in_ifaddr *ifa) { call_rcu(&ifa->rcu_head, inet_rcu_free_ifa); } @@ -659,7 +656,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg * Determine a default network mask, based on the IP address. */ -static inline int inet_abc_len(__be32 addr) +static int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ @@ -1124,7 +1121,7 @@ skip: } } -static inline bool inetdev_valid_mtu(unsigned int mtu) +static bool inetdev_valid_mtu(unsigned int mtu) { return mtu >= 68; } @@ -1239,7 +1236,7 @@ static struct notifier_block ip_netdev_notifier = { .notifier_call = inetdev_event, }; -static inline size_t inet_nlmsg_size(void) +static size_t inet_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(4) /* IFA_ADDRESS */ -- cgit v1.3-14-g43fede From 9eb43e765368f835d92c93844ebce30da7efeb84 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Aug 2012 21:27:25 +0000 Subject: ipv4: Introduce IN_DEV_NET_ROUTE_LOCALNET performance profiles show a high cost in the IN_DEV_ROUTE_LOCALNET() call done in ip_route_input_slow(), because of multiple dereferences, even if cache lines are clean and available in cpu caches. Since we already have the 'net' pointer, introduce IN_DEV_NET_ROUTE_LOCALNET() macro avoiding two dereferences (dev_net(in_dev->dev)) Also change the tests to use IN_DEV_NET_ROUTE_LOCALNET() only if saddr or/and daddr are loopback addresse. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/inetdevice.h | 11 +++++++++-- net/ipv4/route.c | 11 +++++++---- 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 67f9ddacb70c..d032780d0ce5 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -104,9 +104,14 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) -#define IN_DEV_ORCONF(in_dev, attr) \ - (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) || \ + +#define IN_DEV_NET_ORCONF(in_dev, net, attr) \ + (IPV4_DEVCONF_ALL(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) + +#define IN_DEV_ORCONF(in_dev, attr) \ + IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) + #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) @@ -133,6 +138,8 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) +#define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ + IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e4ba974f143c..21ad369014c0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1587,11 +1587,14 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(daddr)) goto martian_destination; - if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) { - if (ipv4_is_loopback(daddr)) + /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), + * and call it once if daddr or/and saddr are loopback addresses + */ + if (ipv4_is_loopback(daddr)) { + if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_destination; - - if (ipv4_is_loopback(saddr)) + } else if (ipv4_is_loopback(saddr)) { + if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; } -- cgit v1.3-14-g43fede From a9e050f4e7f9d36afe0dcc0bddba864ee442715e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 5 Aug 2012 22:34:50 +0000 Subject: net: tcp: GRO should be ECN friendly While doing TCP ECN tests, I discovered GRO was reordering packets if it receives one packet with CE set, while previous packets in same NAPI run have ECT(0) for the same flow : 09:25:25.857620 IP (tos 0x2,ECT(0), ttl 64, id 27893, offset 0, flags [DF], proto TCP (6), length 4396) 172.30.42.19.54550 > 172.30.42.13.44139: Flags [.], seq 233801:238145, ack 1, win 115, options [nop,nop,TS val 3397779 ecr 1990627], length 4344 09:25:25.857626 IP (tos 0x3,CE, ttl 64, id 27892, offset 0, flags [DF], proto TCP (6), length 1500) 172.30.42.19.54550 > 172.30.42.13.44139: Flags [.], seq 232353:233801, ack 1, win 115, options [nop,nop,TS val 3397779 ecr 1990627], length 1448 09:25:25.857638 IP (tos 0x0, ttl 64, id 34581, offset 0, flags [DF], proto TCP (6), length 64) 172.30.42.13.44139 > 172.30.42.19.54550: Flags [.], cksum 0xac8f (incorrect -> 0xca69), ack 232353, win 1271, options [nop,nop,TS val 1990627 ecr 3397779,nop,nop,sack 1 {233801:238145}], length 0 We have two problems here : 1) GRO reorders packets If NIC gave packet1, then packet2, which happen to be from "different flows" GRO feeds stack with packet2, then packet1. I have yet to understand how to solve this problem. 2) GRO is not ECN friendly Delivering packets out of order makes TCP stack not as fast as it could be. In this patch I suggest we make the tos test not part of the 'same_flow' determination, but part of the 'should flush' logic Signed-off-by: Eric Dumazet Cc: Herbert Xu Acked-by: Herbert Xu Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index fe4582ca969a..6681ccf5c3ee 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1364,7 +1364,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, if (*(u8 *)iph != 0x45) goto out_unlock; - if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + if (unlikely(ip_fast_csum((u8 *)iph, 5))) goto out_unlock; id = ntohl(*(__be32 *)&iph->id); @@ -1380,7 +1380,6 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, iph2 = ip_hdr(p); if ((iph->protocol ^ iph2->protocol) | - (iph->tos ^ iph2->tos) | ((__force u32)iph->saddr ^ (__force u32)iph2->saddr) | ((__force u32)iph->daddr ^ (__force u32)iph2->daddr)) { NAPI_GRO_CB(p)->same_flow = 0; @@ -1390,6 +1389,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head, /* All fields must match except length and checksum. */ NAPI_GRO_CB(p)->flush |= (iph->ttl ^ iph2->ttl) | + (iph->tos ^ iph2->tos) | ((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id); NAPI_GRO_CB(p)->flush |= flush; -- cgit v1.3-14-g43fede From aae06bf5f90403554f8d4ff83810a8281aef7f03 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Aug 2012 11:04:43 +0000 Subject: tcp: ecn: dont delay ACKS after CE While playing with CoDel and ECN marking, I discovered a non optimal behavior of receiver of CE (Congestion Encountered) segments. In pathological cases, sender has reduced its cwnd to low values, and receiver delays its ACK (by 40 ms). While RFC 3168 6.1.3 (The TCP Receiver) doesn't explicitly recommend to send immediate ACKS, we believe its better to not delay ACKS, because a CE segment should give same signal than a dropped segment, and its quite important to reduce RTT to give ECE/CWR signals as fast as possible. Note we already call tcp_enter_quickack_mode() from TCP_ECN_check_ce() if we receive a retransmit, for the same reason. Signed-off-by: Eric Dumazet Cc: Neal Cardwell Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2fd2bc9e3c64..fa2c2c2cac2d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -237,7 +237,11 @@ static inline void TCP_ECN_check_ce(struct tcp_sock *tp, const struct sk_buff *s tcp_enter_quickack_mode((struct sock *)tp); break; case INET_ECN_CE: - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { + /* Better not delay acks, sender can have a very low cwnd */ + tcp_enter_quickack_mode((struct sock *)tp); + tp->ecn_flags |= TCP_ECN_DEMAND_CWR; + } /* fallinto */ default: tp->ecn_flags |= TCP_ECN_SEEN; -- cgit v1.3-14-g43fede From 79cda75a107da0d49732b5cb642b456264dd7e0e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 7 Aug 2012 10:45:47 +0000 Subject: fib: use __fls() on non null argument __fls(x) is a bit faster than fls(x), granted we know x is non null. As Ben Hutchings pointed out, fls(x) = __fls(x) + 1 Signed-off-by: Eric Dumazet Cc: Ben Hutchings Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f0cdb30921c0..f84a0e90d675 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1550,7 +1550,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, * state.directly. */ if (pref_mismatch) { - int mp = KEYLENGTH - fls(pref_mismatch); + /* fls(x) = __fls(x) + 1 */ + int mp = KEYLENGTH - __fls(pref_mismatch) - 1; if (tkey_extract_bits(cn->key, mp, cn->pos - mp) != 0) goto backtrace; -- cgit v1.3-14-g43fede From a399a8053164ec8bcb06fed52be9941a26ecde11 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Aug 2012 21:13:53 +0000 Subject: time: jiffies_delta_to_clock_t() helper to the rescue MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Various /proc/net files sometimes report crazy timer values, expressed in clock_t units. This happens when an expired timer delta (expires - jiffies) is passed to jiffies_to_clock_t(). This function has an overflow in : return div_u64((u64)x * TICK_NSEC, NSEC_PER_SEC / USER_HZ); commit cbbc719fccdb8cb (time: Change jiffies_to_clock_t() argument type to unsigned long) only got around the problem. As we cant output negative values in /proc/net/tcp without breaking various tools, I suggest adding a jiffies_delta_to_clock_t() wrapper that caps the negative delta to a 0 value. Signed-off-by: Eric Dumazet Reported-by: Maciej Żenczykowski Cc: Thomas Gleixner Cc: Paul Gortmaker Cc: Andrew Morton Cc: hank Signed-off-by: David S. Miller --- include/linux/jiffies.h | 6 ++++++ net/bridge/br_fdb.c | 2 +- net/bridge/br_stp_timer.c | 2 +- net/core/rtnetlink.c | 2 +- net/ipv4/igmp.c | 7 +++++-- net/ipv4/tcp_ipv4.c | 13 +++++-------- net/ipv6/tcp_ipv6.c | 9 +++------ 7 files changed, 22 insertions(+), 19 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h index 265e2c3cbd1c..aded9b1ac5ca 100644 --- a/include/linux/jiffies.h +++ b/include/linux/jiffies.h @@ -303,7 +303,13 @@ extern void jiffies_to_timespec(const unsigned long jiffies, extern unsigned long timeval_to_jiffies(const struct timeval *value); extern void jiffies_to_timeval(const unsigned long jiffies, struct timeval *value); + extern clock_t jiffies_to_clock_t(unsigned long x); +static inline clock_t jiffies_delta_to_clock_t(long delta) +{ + return jiffies_to_clock_t(max(0L, delta)); +} + extern unsigned long clock_t_to_jiffies(unsigned long x); extern u64 jiffies_64_to_clock_t(u64 x); extern u64 nsec_to_clock_t(u64 x); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index d21f32383517..9ce430b4657c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -312,7 +312,7 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf, fe->is_local = f->is_local; if (!f->is_static) - fe->ageing_timer_value = jiffies_to_clock_t(jiffies - f->updated); + fe->ageing_timer_value = jiffies_delta_to_clock_t(jiffies - f->updated); ++fe; ++num; } diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index a6747e673426..c3530a81a33b 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -170,5 +170,5 @@ void br_stp_port_timer_init(struct net_bridge_port *p) unsigned long br_timer_value(const struct timer_list *timer) { return timer_pending(timer) - ? jiffies_to_clock_t(timer->expires - jiffies) : 0; + ? jiffies_delta_to_clock_t(timer->expires - jiffies) : 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2c5a0a06c4ce..db037c9a4c48 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -618,7 +618,7 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error) { struct rta_cacheinfo ci = { - .rta_lastuse = jiffies_to_clock_t(jiffies - dst->lastuse), + .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse), .rta_used = dst->__use, .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 6699f23e6f55..0b5580c69f2d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2435,6 +2435,8 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) struct ip_mc_list *im = (struct ip_mc_list *)v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; + long delta; + #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : @@ -2448,11 +2450,12 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } + delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, - im->tm_running, im->tm_running ? - jiffies_to_clock_t(im->timer.expires-jiffies) : 0, + im->tm_running, + im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 42b2a6a73092..c660d2c19a2b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2385,7 +2385,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, struct seq_file *f, int i, int uid, int *len) { const struct inet_request_sock *ireq = inet_rsk(req); - int ttd = req->expires - jiffies; + long delta = req->expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n", @@ -2397,7 +2397,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req, TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ - jiffies_to_clock_t(ttd), + jiffies_delta_to_clock_t(delta), req->retrans, uid, 0, /* non standard timer */ @@ -2448,7 +2448,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) tp->write_seq - tp->snd_una, rx_queue, timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, sock_i_uid(sk), icsk->icsk_probes_out, @@ -2467,10 +2467,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, { __be32 dest, src; __u16 destp, srcp; - int ttd = tw->tw_ttd - jiffies; - - if (ttd < 0) - ttd = 0; + long delta = tw->tw_ttd - jiffies; dest = tw->tw_daddr; src = tw->tw_rcv_saddr; @@ -2480,7 +2477,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw, seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK%n", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw, len); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c66b90f71c9b..aa41b0e6b163 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1875,7 +1875,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) tp->write_seq-tp->snd_una, (sp->sk_state == TCP_LISTEN) ? sp->sk_ack_backlog : (tp->rcv_nxt - tp->copied_seq), timer_active, - jiffies_to_clock_t(timer_expires - jiffies), + jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, sock_i_uid(sp), icsk->icsk_probes_out, @@ -1895,10 +1895,7 @@ static void get_timewait6_sock(struct seq_file *seq, const struct in6_addr *dest, *src; __u16 destp, srcp; const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - int ttd = tw->tw_ttd - jiffies; - - if (ttd < 0) - ttd = 0; + long delta = tw->tw_ttd - jiffies; dest = &tw6->tw_v6_daddr; src = &tw6->tw_v6_rcv_saddr; @@ -1914,7 +1911,7 @@ static void get_timewait6_sock(struct seq_file *seq, dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, tw->tw_substate, 0, 0, - 3, jiffies_to_clock_t(ttd), 0, 0, 0, 0, + 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, atomic_read(&tw->tw_refcnt), tw); } -- cgit v1.3-14-g43fede From 1fb9489bf190ce2b3fc03891f3de4b2d30600e28 Mon Sep 17 00:00:00 2001 From: Pavel Emelyanov Date: Wed, 8 Aug 2012 21:53:36 +0000 Subject: net: Loopback ifindex is constant now As pointed out, there are places, that access net->loopback_dev->ifindex and after ifindex generation is made per-net this value becomes constant equals 1. So go ahead and introduce the LOOPBACK_IFINDEX constant and use it where appropriate. Signed-off-by: Pavel Emelyanov Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/loopback.c | 1 + include/net/net_namespace.h | 7 +++++++ net/decnet/dn_route.c | 6 +++--- net/ipv4/fib_frontend.c | 2 +- net/ipv4/ipmr.c | 2 +- net/ipv4/netfilter/ipt_rpfilter.c | 2 +- net/ipv4/route.c | 6 +++--- net/ipv6/route.c | 2 +- 8 files changed, 18 insertions(+), 10 deletions(-) (limited to 'net/ipv4') diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index e2a06fd996d5..4a075babe193 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -197,6 +197,7 @@ static __net_init int loopback_net_init(struct net *net) if (err) goto out_free_netdev; + BUG_ON(dev->ifindex != LOOPBACK_IFINDEX); net->loopback_dev = dev; return 0; diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 6dc3db3466bf..97e441945c13 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -105,6 +105,13 @@ struct net { struct sock *diag_nlsk; }; +/* + * ifindex generation is per-net namespace, and loopback is + * always the 1st device in ns (see net_dev_init), thus any + * loopback device should get ifindex 1 + */ + +#define LOOPBACK_IFINDEX 1 #include diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 85a3604c87c8..c855e8d0738f 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -961,7 +961,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o .saddr = oldflp->saddr, .flowidn_scope = RT_SCOPE_UNIVERSE, .flowidn_mark = oldflp->flowidn_mark, - .flowidn_iif = init_net.loopback_dev->ifindex, + .flowidn_iif = LOOPBACK_IFINDEX, .flowidn_oif = oldflp->flowidn_oif, }; struct dn_route *rt = NULL; @@ -979,7 +979,7 @@ static int dn_route_output_slow(struct dst_entry **pprt, const struct flowidn *o "dn_route_output_slow: dst=%04x src=%04x mark=%d" " iif=%d oif=%d\n", le16_to_cpu(oldflp->daddr), le16_to_cpu(oldflp->saddr), - oldflp->flowidn_mark, init_net.loopback_dev->ifindex, + oldflp->flowidn_mark, LOOPBACK_IFINDEX, oldflp->flowidn_oif); /* If we have an output interface, verify its a DECnet device */ @@ -1042,7 +1042,7 @@ source_ok: if (!fld.daddr) goto out; } - fld.flowidn_oif = init_net.loopback_dev->ifindex; + fld.flowidn_oif = LOOPBACK_IFINDEX; res.type = RTN_LOCAL; goto make_route; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index c43ae3fba792..7f073a38c87d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -218,7 +218,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { fl4.flowi4_oif = 0; - fl4.flowi4_iif = net->loopback_dev->ifindex; + fl4.flowi4_iif = LOOPBACK_IFINDEX; fl4.daddr = ip_hdr(skb)->saddr; fl4.saddr = 0; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8eec8f4a0536..3a57570c8ee5 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1798,7 +1798,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) .flowi4_oif = (rt_is_output_route(rt) ? skb->dev->ifindex : 0), .flowi4_iif = (rt_is_output_route(rt) ? - net->loopback_dev->ifindex : + LOOPBACK_IFINDEX : skb->dev->ifindex), .flowi4_mark = skb->mark, }; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 31371be8174b..c30130062cd6 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -85,7 +85,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) return ipv4_is_local_multicast(iph->daddr) ^ invert; flow.flowi4_iif = 0; } else { - flow.flowi4_iif = dev_net(par->in)->loopback_dev->ifindex; + flow.flowi4_iif = LOOPBACK_IFINDEX; } flow.daddr = iph->saddr; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 21ad369014c0..c58137391a3d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1619,7 +1619,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, - net->loopback_dev->ifindex, + LOOPBACK_IFINDEX, dev, in_dev, &itag); if (err < 0) goto martian_source_keep_err; @@ -1895,7 +1895,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) orig_oif = fl4->flowi4_oif; - fl4->flowi4_iif = net->loopback_dev->ifindex; + fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); @@ -1984,7 +1984,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; - fl4->flowi4_oif = net->loopback_dev->ifindex; + fl4->flowi4_oif = LOOPBACK_IFINDEX; res.type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8e80fd279100..0ddf2d132e7f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -965,7 +965,7 @@ struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk, { int flags = 0; - fl6->flowi6_iif = net->loopback_dev->ifindex; + fl6->flowi6_iif = LOOPBACK_IFINDEX; if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) flags |= RT6_LOOKUP_F_IFACE; -- cgit v1.3-14-g43fede From 19e303d67dc2e68a7f14b0baf7949195d7327145 Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Sat, 28 Jul 2012 14:45:50 +0000 Subject: netfilter: PTR_RET can be used This quiets the coccinelle warnings: net/bridge/netfilter/ebtable_filter.c:107:1-3: WARNING: PTR_RET can be used net/bridge/netfilter/ebtable_nat.c:107:1-3: WARNING: PTR_RET can be used net/ipv6/netfilter/ip6table_filter.c:65:1-3: WARNING: PTR_RET can be used net/ipv6/netfilter/ip6table_mangle.c:100:1-3: WARNING: PTR_RET can be used net/ipv6/netfilter/ip6table_raw.c:44:1-3: WARNING: PTR_RET can be used net/ipv6/netfilter/ip6table_security.c:62:1-3: WARNING: PTR_RET can be used net/ipv4/netfilter/iptable_filter.c:72:1-3: WARNING: PTR_RET can be used net/ipv4/netfilter/iptable_mangle.c:107:1-3: WARNING: PTR_RET can be used net/ipv4/netfilter/iptable_raw.c:51:1-3: WARNING: PTR_RET can be used net/ipv4/netfilter/iptable_security.c:70:1-3: WARNING: PTR_RET can be used Signed-off-by: Fengguang Wu Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtable_filter.c | 4 +--- net/bridge/netfilter/ebtable_nat.c | 4 +--- net/ipv4/netfilter/iptable_filter.c | 4 +--- net/ipv4/netfilter/iptable_mangle.c | 4 +--- net/ipv4/netfilter/iptable_raw.c | 4 +--- net/ipv4/netfilter/iptable_security.c | 5 +---- net/ipv6/netfilter/ip6table_filter.c | 4 +--- net/ipv6/netfilter/ip6table_mangle.c | 4 +--- net/ipv6/netfilter/ip6table_raw.c | 4 +--- net/ipv6/netfilter/ip6table_security.c | 5 +---- 10 files changed, 10 insertions(+), 32 deletions(-) (limited to 'net/ipv4') diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 42e6bd094574..3c2e9dced9e0 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -100,9 +100,7 @@ static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { static int __net_init frame_filter_net_init(struct net *net) { net->xt.frame_filter = ebt_register_table(net, &frame_filter); - if (IS_ERR(net->xt.frame_filter)) - return PTR_ERR(net->xt.frame_filter); - return 0; + return PTR_RET(net->xt.frame_filter); } static void __net_exit frame_filter_net_exit(struct net *net) diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index 6dc2f878ae05..10871bc77908 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -100,9 +100,7 @@ static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { static int __net_init frame_nat_net_init(struct net *net) { net->xt.frame_nat = ebt_register_table(net, &frame_nat); - if (IS_ERR(net->xt.frame_nat)) - return PTR_ERR(net->xt.frame_nat); - return 0; + return PTR_RET(net->xt.frame_nat); } static void __net_exit frame_nat_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index 851acec852d2..d20cc374025c 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -69,9 +69,7 @@ static int __net_init iptable_filter_net_init(struct net *net) net->ipv4.iptable_filter = ipt_register_table(net, &packet_filter, repl); kfree(repl); - if (IS_ERR(net->ipv4.iptable_filter)) - return PTR_ERR(net->ipv4.iptable_filter); - return 0; + return PTR_RET(net->ipv4.iptable_filter); } static void __net_exit iptable_filter_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index aef5d1fbe77d..f38b94288cf5 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -104,9 +104,7 @@ static int __net_init iptable_mangle_net_init(struct net *net) net->ipv4.iptable_mangle = ipt_register_table(net, &packet_mangler, repl); kfree(repl); - if (IS_ERR(net->ipv4.iptable_mangle)) - return PTR_ERR(net->ipv4.iptable_mangle); - return 0; + return PTR_RET(net->ipv4.iptable_mangle); } static void __net_exit iptable_mangle_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 07fb710cd722..b21e2191e2f5 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -48,9 +48,7 @@ static int __net_init iptable_raw_net_init(struct net *net) net->ipv4.iptable_raw = ipt_register_table(net, &packet_raw, repl); kfree(repl); - if (IS_ERR(net->ipv4.iptable_raw)) - return PTR_ERR(net->ipv4.iptable_raw); - return 0; + return PTR_RET(net->ipv4.iptable_raw); } static void __net_exit iptable_raw_net_exit(struct net *net) diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index be45bdc4c602..b283d8e2601a 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -66,10 +66,7 @@ static int __net_init iptable_security_net_init(struct net *net) net->ipv4.iptable_security = ipt_register_table(net, &security_table, repl); kfree(repl); - if (IS_ERR(net->ipv4.iptable_security)) - return PTR_ERR(net->ipv4.iptable_security); - - return 0; + return PTR_RET(net->ipv4.iptable_security); } static void __net_exit iptable_security_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 325e59a0224f..beb5777d2043 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -61,9 +61,7 @@ static int __net_init ip6table_filter_net_init(struct net *net) net->ipv6.ip6table_filter = ip6t_register_table(net, &packet_filter, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_filter)) - return PTR_ERR(net->ipv6.ip6table_filter); - return 0; + return PTR_RET(net->ipv6.ip6table_filter); } static void __net_exit ip6table_filter_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 4d782405f125..7431121b87de 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -97,9 +97,7 @@ static int __net_init ip6table_mangle_net_init(struct net *net) net->ipv6.ip6table_mangle = ip6t_register_table(net, &packet_mangler, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_mangle)) - return PTR_ERR(net->ipv6.ip6table_mangle); - return 0; + return PTR_RET(net->ipv6.ip6table_mangle); } static void __net_exit ip6table_mangle_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 5b9926a011bd..60d1bddff7a0 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -40,9 +40,7 @@ static int __net_init ip6table_raw_net_init(struct net *net) net->ipv6.ip6table_raw = ip6t_register_table(net, &packet_raw, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_raw)) - return PTR_ERR(net->ipv6.ip6table_raw); - return 0; + return PTR_RET(net->ipv6.ip6table_raw); } static void __net_exit ip6table_raw_net_exit(struct net *net) diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index 91aa2b4d83c9..db155351339c 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -58,10 +58,7 @@ static int __net_init ip6table_security_net_init(struct net *net) net->ipv6.ip6table_security = ip6t_register_table(net, &security_table, repl); kfree(repl); - if (IS_ERR(net->ipv6.ip6table_security)) - return PTR_ERR(net->ipv6.ip6table_security); - - return 0; + return PTR_RET(net->ipv6.ip6table_security); } static void __net_exit ip6table_security_net_exit(struct net *net) -- cgit v1.3-14-g43fede From ad5b310228da567e35a2ea5dcb2fd62e3a36654e Mon Sep 17 00:00:00 2001 From: Igor Maravic Date: Mon, 13 Aug 2012 10:26:08 +0200 Subject: net: ipv4: fib_trie: Don't unnecessarily search for already found fib leaf We've already found leaf, don't search for it again. Same is for fib leaf info. Signed-off-by: Igor Maravic Signed-off-by: David S. Miller --- net/ipv4/fib_trie.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index f84a0e90d675..4587d344046d 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1656,7 +1656,12 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) if (!l) return -ESRCH; - fa_head = get_fa_head(l, plen); + li = find_leaf_info(l, plen); + + if (!li) + return -ESRCH; + + fa_head = &li->falh; fa = fib_find_alias(fa_head, tos, 0); if (!fa) @@ -1692,9 +1697,6 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) rtmsg_fib(RTM_DELROUTE, htonl(key), fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); - l = fib_find_node(t, key); - li = find_leaf_info(l, plen); - list_del_rcu(&fa->fa_list); if (!plen) -- cgit v1.3-14-g43fede From 1b3a6926fc3430116c97c333f7cf901b86779008 Mon Sep 17 00:00:00 2001 From: Razvan Ghitulete Date: Tue, 14 Aug 2012 16:30:20 +0300 Subject: net: remove wrong initialization for snd_wl1 The field tp->snd_wl1 is twice initialized, the second time seems to be wrong as it may overwrite any update in tcp_ack. Signed-off-by: Razvan Ghitulete Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index fa2c2c2cac2d..c423317eb719 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5744,7 +5744,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, TCP_ECN_rcv_synack(tp, th); - tp->snd_wl1 = TCP_SKB_CB(skb)->seq; + tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); tcp_ack(sk, skb, FLAG_SLOWPATH); /* Ok.. it's good. Set up sequence numbers and @@ -5757,7 +5757,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * never scaled. */ tp->snd_wnd = ntohs(th->window); - tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); if (!tp->rx_opt.wscale_ok) { tp->rx_opt.snd_wscale = tp->rx_opt.rcv_wscale = 0; -- cgit v1.3-14-g43fede From 90efbed18a30d78145419cdbd44f9ec152efeb16 Mon Sep 17 00:00:00 2001 From: Jean Sacren Date: Sun, 19 Aug 2012 15:11:32 +0000 Subject: netfilter: remove unnecessary goto statement for error recovery Usually it's a good practice to use goto statement for error recovery when initializing the module. This approach could be an overkill if: 1) there is only one fail case; 2) success and failure use the same return statement. For a cleaner approach, remove the unnecessary goto statement and directly implement error recovery. Signed-off-by: Jean Sacren Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/iptable_filter.c | 6 +----- net/ipv4/netfilter/iptable_mangle.c | 6 +----- net/ipv4/netfilter/iptable_raw.c | 6 +----- 3 files changed, 3 insertions(+), 15 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index d20cc374025c..6b3da5cf54e9 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -94,14 +94,10 @@ static int __init iptable_filter_init(void) filter_ops = xt_hook_link(&packet_filter, iptable_filter_hook); if (IS_ERR(filter_ops)) { ret = PTR_ERR(filter_ops); - goto cleanup_table; + unregister_pernet_subsys(&iptable_filter_net_ops); } return ret; - - cleanup_table: - unregister_pernet_subsys(&iptable_filter_net_ops); - return ret; } static void __exit iptable_filter_fini(void) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index f38b94288cf5..85d88f206447 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -129,14 +129,10 @@ static int __init iptable_mangle_init(void) mangle_ops = xt_hook_link(&packet_mangler, iptable_mangle_hook); if (IS_ERR(mangle_ops)) { ret = PTR_ERR(mangle_ops); - goto cleanup_table; + unregister_pernet_subsys(&iptable_mangle_net_ops); } return ret; - - cleanup_table: - unregister_pernet_subsys(&iptable_mangle_net_ops); - return ret; } static void __exit iptable_mangle_fini(void) diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index b21e2191e2f5..03d9696d3c6e 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -73,14 +73,10 @@ static int __init iptable_raw_init(void) rawtable_ops = xt_hook_link(&packet_raw, iptable_raw_hook); if (IS_ERR(rawtable_ops)) { ret = PTR_ERR(rawtable_ops); - goto cleanup_table; + unregister_pernet_subsys(&iptable_raw_net_ops); } return ret; - - cleanup_table: - unregister_pernet_subsys(&iptable_raw_net_ops); - return ret; } static void __exit iptable_raw_fini(void) -- cgit v1.3-14-g43fede From 0115e8e30d6fcdd4b8faa30d3ffd90859a591f51 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Aug 2012 17:19:46 +0000 Subject: net: remove delay at device dismantle I noticed extra one second delay in device dismantle, tracked down to a call to dst_dev_event() while some call_rcu() are still in RCU queues. These call_rcu() were posted by rt_free(struct rtable *rt) calls. We then wait a little (but one second) in netdev_wait_allrefs() before kicking again NETDEV_UNREGISTER. As the call_rcu() are now completed, dst_dev_event() can do the needed device swap on busy dst. To solve this problem, add a new NETDEV_UNREGISTER_FINAL, called after a rcu_barrier(), but outside of RTNL lock. Use NETDEV_UNREGISTER_FINAL with care ! Change dst_dev_event() handler to react to NETDEV_UNREGISTER_FINAL Also remove NETDEV_UNREGISTER_BATCH, as its not used anymore after IP cache removal. With help from Gao feng Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Cc: "Eric W. Biederman" Cc: Gao feng Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 22 ++++++++-------------- net/core/dst.c | 2 +- net/core/fib_rules.c | 3 ++- net/core/rtnetlink.c | 2 +- net/ipv4/devinet.c | 6 +++++- net/ipv4/fib_frontend.c | 8 ++++---- net/ipv6/addrconf.c | 6 +++++- 8 files changed, 27 insertions(+), 24 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 4936f09a9333..9ad7fa8c10e0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1553,7 +1553,7 @@ struct packet_type { #define NETDEV_PRE_TYPE_CHANGE 0x000E #define NETDEV_POST_TYPE_CHANGE 0x000F #define NETDEV_POST_INIT 0x0010 -#define NETDEV_UNREGISTER_BATCH 0x0011 +#define NETDEV_UNREGISTER_FINAL 0x0011 #define NETDEV_RELEASE 0x0012 #define NETDEV_NOTIFY_PEERS 0x0013 #define NETDEV_JOIN 0x0014 diff --git a/net/core/dev.c b/net/core/dev.c index 088923fe4066..0640d2a859c6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1406,7 +1406,6 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } @@ -1448,7 +1447,6 @@ int unregister_netdevice_notifier(struct notifier_block *nb) nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } unlock: @@ -1468,7 +1466,8 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - ASSERT_RTNL(); + if (val != NETDEV_UNREGISTER_FINAL) + ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -5331,10 +5330,6 @@ static void rollback_registered_many(struct list_head *head) netdev_unregister_kobject(dev); } - /* Process any work delayed until the end of the batch */ - dev = list_first_entry(head, struct net_device, unreg_list); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); list_for_each_entry(dev, head, unreg_list) @@ -5787,9 +5782,8 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users - * should have already handle it the first time */ - + rcu_barrier(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events @@ -5851,9 +5845,8 @@ void netdev_run_todo(void) __rtnl_unlock(); - /* Wait for rcu callbacks to finish before attempting to drain - * the device list. This usually avoids a 250ms wait. - */ + + /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); @@ -5862,6 +5855,8 @@ void netdev_run_todo(void) = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { pr_err("network todo '%s' but state %d\n", dev->name, dev->reg_state); @@ -6256,7 +6251,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); /* diff --git a/net/core/dst.c b/net/core/dst.c index 56d63612e1e4..f6593d238e9a 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -374,7 +374,7 @@ static int dst_dev_event(struct notifier_block *this, unsigned long event, struct dst_entry *dst, *last = NULL; switch (event) { - case NETDEV_UNREGISTER: + case NETDEV_UNREGISTER_FINAL: case NETDEV_DOWN: mutex_lock(&dst_gc_mutex); for (dst = dst_busy_list; dst; dst = dst->next) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index ab7db83236c9..585093755c23 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -711,15 +711,16 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, struct net *net = dev_net(dev); struct fib_rules_ops *ops; - ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: + ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_UNREGISTER: + ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 34d975b0f277..c64efcff8078 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2358,7 +2358,7 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi case NETDEV_PRE_TYPE_CHANGE: case NETDEV_GOING_DOWN: case NETDEV_UNREGISTER: - case NETDEV_UNREGISTER_BATCH: + case NETDEV_UNREGISTER_FINAL: case NETDEV_RELEASE: case NETDEV_JOIN: break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index adf273f8ad2e..6a5e6e4b142c 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1147,8 +1147,12 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev; + if (event == NETDEV_UNREGISTER_FINAL) + goto out; + + in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 7f073a38c87d..fd7d9ae64f16 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1041,7 +1041,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct in_device *in_dev; struct net *net = dev_net(dev); if (event == NETDEV_UNREGISTER) { @@ -1050,9 +1050,11 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo return NOTIFY_DONE; } - if (!in_dev) + if (event == NETDEV_UNREGISTER_FINAL) return NOTIFY_DONE; + in_dev = __in_dev_get_rtnl(dev); + switch (event) { case NETDEV_UP: for_ifa(in_dev) { @@ -1071,8 +1073,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo case NETDEV_CHANGE: rt_cache_flush(dev_net(dev), 0); break; - case NETDEV_UNREGISTER_BATCH: - break; } return NOTIFY_DONE; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 6bc85f7c31e3..e581009cb09e 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2566,10 +2566,14 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, void *data) { struct net_device *dev = (struct net_device *) data; - struct inet6_dev *idev = __in6_dev_get(dev); + struct inet6_dev *idev; int run_pending = 0; int err; + if (event == NETDEV_UNREGISTER_FINAL) + return NOTIFY_DONE; + + idev = __in6_dev_get(dev); switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { -- cgit v1.3-14-g43fede From 748e2d9396a18c3fd3d07d47c1b41320acf1fbf4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 22 Aug 2012 21:50:59 +0000 Subject: net: reinstate rtnl in call_netdevice_notifiers() Eric Biederman pointed out that not holding RTNL while calling call_netdevice_notifiers() was racy. This patch is a direct transcription his feedback against commit 0115e8e30d6fc (net: remove delay at device dismantle) Thanks Eric ! Signed-off-by: Eric Dumazet Cc: Tom Herbert Cc: Mahesh Bandewar Cc: "Eric W. Biederman" Cc: Gao feng Acked-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/dev.c | 9 +++++++-- net/core/fib_rules.c | 3 +-- net/ipv4/devinet.c | 6 +----- net/ipv4/fib_frontend.c | 7 ++----- net/ipv6/addrconf.c | 6 +----- 5 files changed, 12 insertions(+), 19 deletions(-) (limited to 'net/ipv4') diff --git a/net/core/dev.c b/net/core/dev.c index 0640d2a859c6..bc857fead8c8 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1466,8 +1466,7 @@ EXPORT_SYMBOL(unregister_netdevice_notifier); int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { - if (val != NETDEV_UNREGISTER_FINAL) - ASSERT_RTNL(); + ASSERT_RTNL(); return raw_notifier_call_chain(&netdev_chain, val, dev); } EXPORT_SYMBOL(call_netdevice_notifiers); @@ -5782,7 +5781,11 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + + __rtnl_unlock(); rcu_barrier(); + rtnl_lock(); + call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { @@ -5855,7 +5858,9 @@ void netdev_run_todo(void) = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); + rtnl_lock(); call_netdevice_notifiers(NETDEV_UNREGISTER_FINAL, dev); + __rtnl_unlock(); if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { pr_err("network todo '%s' but state %d\n", diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 585093755c23..ab7db83236c9 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -711,16 +711,15 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event, struct net *net = dev_net(dev); struct fib_rules_ops *ops; + ASSERT_RTNL(); switch (event) { case NETDEV_REGISTER: - ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) attach_rules(&ops->rules_list, dev); break; case NETDEV_UNREGISTER: - ASSERT_RTNL(); list_for_each_entry(ops, &net->rules_ops, list) detach_rules(&ops->rules_list, dev); break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6a5e6e4b142c..adf273f8ad2e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1147,12 +1147,8 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = ptr; - struct in_device *in_dev; - - if (event == NETDEV_UNREGISTER_FINAL) - goto out; + struct in_device *in_dev = __in_dev_get_rtnl(dev); - in_dev = __in_dev_get_rtnl(dev); ASSERT_RTNL(); if (!in_dev) { diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index fd7d9ae64f16..acdee325d972 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1050,9 +1050,6 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo return NOTIFY_DONE; } - if (event == NETDEV_UNREGISTER_FINAL) - return NOTIFY_DONE; - in_dev = __in_dev_get_rtnl(dev); switch (event) { @@ -1064,14 +1061,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(net, -1); break; case NETDEV_DOWN: fib_disable_ip(dev, 0, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(net, 0); break; } return NOTIFY_DONE; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e581009cb09e..6bc85f7c31e3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2566,14 +2566,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, void *data) { struct net_device *dev = (struct net_device *) data; - struct inet6_dev *idev; + struct inet6_dev *idev = __in6_dev_get(dev); int run_pending = 0; int err; - if (event == NETDEV_UNREGISTER_FINAL) - return NOTIFY_DONE; - - idev = __in6_dev_get(dev); switch (event) { case NETDEV_REGISTER: if (!idev && dev->mtu >= IPV6_MIN_MTU) { -- cgit v1.3-14-g43fede From 5f2d04f1f9b52604fca6ee08a77972c0df67e082 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:13:55 +0200 Subject: ipv4: fix path MTU discovery with connection tracking IPv4 conntrack defragments incoming packet at the PRE_ROUTING hook and (in case of forwarded packets) refragments them at POST_ROUTING independent of the IP_DF flag. Refragmentation uses the dst_mtu() of the local route without caring about the original fragment sizes, thereby breaking PMTUD. This patch fixes this by keeping track of the largest received fragment with IP_DF set and generates an ICMP fragmentation required error during refragmentation if that size exceeds the MTU. Signed-off-by: Patrick McHardy Acked-by: Eric Dumazet Acked-by: David S. Miller --- include/net/inet_frag.h | 2 ++ include/net/ip.h | 2 ++ net/ipv4/ip_fragment.c | 8 +++++++- net/ipv4/ip_output.c | 4 +++- 4 files changed, 14 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 2431cf83aeca..5098ee7b7e0e 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -29,6 +29,8 @@ struct inet_frag_queue { #define INET_FRAG_COMPLETE 4 #define INET_FRAG_FIRST_IN 2 #define INET_FRAG_LAST_IN 1 + + u16 max_size; }; #define INETFRAGS_HASHSZ 64 diff --git a/include/net/ip.h b/include/net/ip.h index 5a5d84d3d2c6..0707fb9551aa 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -42,6 +42,8 @@ struct inet_skb_parm { #define IPSKB_XFRM_TRANSFORMED 4 #define IPSKB_FRAG_COMPLETE 8 #define IPSKB_REROUTED 16 + + u16 frag_max_size; }; static inline unsigned int ip_hdrlen(const struct sk_buff *skb) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8d07c973409c..fa6a12c51066 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -523,6 +523,10 @@ found: if (offset == 0) qp->q.last_in |= INET_FRAG_FIRST_IN; + if (ip_hdr(skb)->frag_off & htons(IP_DF) && + skb->len + ihl > qp->q.max_size) + qp->q.max_size = skb->len + ihl; + if (qp->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && qp->q.meat == qp->q.len) return ip_frag_reasm(qp, prev, dev); @@ -646,9 +650,11 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, head->next = NULL; head->dev = dev; head->tstamp = qp->q.stamp; + IPCB(head)->frag_max_size = qp->q.max_size; iph = ip_hdr(head); - iph->frag_off = 0; + /* max_size != 0 implies at least one fragment had IP_DF set */ + iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0; iph->tot_len = htons(len); iph->tos |= ecn; IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index c196d749daf2..a5beab1dc958 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -467,7 +467,9 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) iph = ip_hdr(skb); - if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) { + if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->local_df) || + (IPCB(skb)->frag_max_size && + IPCB(skb)->frag_max_size > dst_mtu(&rt->dst)))) { IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(ip_skb_dst_mtu(skb))); -- cgit v1.3-14-g43fede From 051966c0c644a1c96092d4206e00704ade813c9a Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:04 +0200 Subject: netfilter: nf_nat: add protoff argument to packet mangling functions For mangling IPv6 packets the protocol header offset needs to be known by the NAT packet mangling functions. Add a so far unused protoff argument and convert the conntrack and NAT helpers to use it in preparation of IPv6 NAT. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_amanda.h | 1 + include/linux/netfilter/nf_conntrack_ftp.h | 1 + include/linux/netfilter/nf_conntrack_h323.h | 15 +- include/linux/netfilter/nf_conntrack_irc.h | 1 + include/linux/netfilter/nf_conntrack_pptp.h | 2 + include/linux/netfilter/nf_conntrack_sip.h | 12 +- include/net/netfilter/nf_nat_helper.h | 11 +- net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 6 +- net/ipv4/netfilter/nf_nat_amanda.c | 3 +- net/ipv4/netfilter/nf_nat_ftp.c | 3 +- net/ipv4/netfilter/nf_nat_h323.c | 48 ++++--- net/ipv4/netfilter/nf_nat_helper.c | 9 +- net/ipv4/netfilter/nf_nat_irc.c | 3 +- net/ipv4/netfilter/nf_nat_pptp.c | 6 +- net/ipv4/netfilter/nf_nat_sip.c | 96 +++++++------ net/netfilter/ipvs/ip_vs_ftp.c | 1 + net/netfilter/nf_conntrack_amanda.c | 5 +- net/netfilter/nf_conntrack_ftp.c | 3 +- net/netfilter/nf_conntrack_h323_main.c | 191 +++++++++++++++---------- net/netfilter/nf_conntrack_irc.c | 3 +- net/netfilter/nf_conntrack_pptp.c | 18 +-- net/netfilter/nf_conntrack_sip.c | 95 +++++++----- 22 files changed, 328 insertions(+), 205 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/netfilter/nf_conntrack_amanda.h b/include/linux/netfilter/nf_conntrack_amanda.h index 0bb5a6976bf3..4b59a1584959 100644 --- a/include/linux/netfilter/nf_conntrack_amanda.h +++ b/include/linux/netfilter/nf_conntrack_amanda.h @@ -4,6 +4,7 @@ extern unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_ftp.h b/include/linux/netfilter/nf_conntrack_ftp.h index 3e3aa08980c3..28f18df36525 100644 --- a/include/linux/netfilter/nf_conntrack_ftp.h +++ b/include/linux/netfilter/nf_conntrack_ftp.h @@ -34,6 +34,7 @@ struct nf_conntrack_expect; extern unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h index 26f9226ea72b..f381020eee92 100644 --- a/include/linux/netfilter/nf_conntrack_h323.h +++ b/include/linux/netfilter/nf_conntrack_h323.h @@ -36,12 +36,12 @@ extern void nf_conntrack_h245_expect(struct nf_conn *new, struct nf_conntrack_expect *this); extern void nf_conntrack_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this); -extern int (*set_h245_addr_hook) (struct sk_buff *skb, +extern int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, union nf_inet_addr *addr, __be16 port); -extern int (*set_h225_addr_hook) (struct sk_buff *skb, +extern int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, union nf_inet_addr *addr, @@ -49,40 +49,45 @@ extern int (*set_h225_addr_hook) (struct sk_buff *skb, extern int (*set_sig_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count); extern int (*set_ras_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count); extern int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, + int dataoff, H245_TransportAddress *taddr, __be16 port, __be16 rtp_port, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp); extern int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); extern int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); extern int (*nat_callforwarding_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp); extern int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_irc.h b/include/linux/netfilter/nf_conntrack_irc.h index 36282bf71b63..4bb9bae67176 100644 --- a/include/linux/netfilter/nf_conntrack_irc.h +++ b/include/linux/netfilter/nf_conntrack_irc.h @@ -7,6 +7,7 @@ extern unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); diff --git a/include/linux/netfilter/nf_conntrack_pptp.h b/include/linux/netfilter/nf_conntrack_pptp.h index 3bbde0c3a8a6..2ab2830316b7 100644 --- a/include/linux/netfilter/nf_conntrack_pptp.h +++ b/include/linux/netfilter/nf_conntrack_pptp.h @@ -303,12 +303,14 @@ struct nf_conntrack_expect; extern int (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); extern int (*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq); diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 89f2a627f3f0..1afc669a393e 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -37,10 +37,12 @@ struct sdp_media_type { struct sip_handler { const char *method; unsigned int len; - int (*request)(struct sk_buff *skb, unsigned int dataoff, + int (*request)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq); - int (*response)(struct sk_buff *skb, unsigned int dataoff, + int (*response)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code); }; @@ -105,11 +107,13 @@ enum sdp_header_types { }; extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen); extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off); extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -117,6 +121,7 @@ extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int matchoff, unsigned int matchlen); extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -125,6 +130,7 @@ extern unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, enum sdp_header_types term, const union nf_inet_addr *addr); extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -132,12 +138,14 @@ extern unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int matchlen, u_int16_t port); extern unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, const union nf_inet_addr *addr); extern unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h index 7d8fb7b46c44..b4d6bfc2af03 100644 --- a/include/net/netfilter/nf_nat_helper.h +++ b/include/net/netfilter/nf_nat_helper.h @@ -10,6 +10,7 @@ struct sk_buff; extern int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int match_offset, unsigned int match_len, const char *rep_buffer, @@ -18,12 +19,13 @@ extern int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int match_offset, unsigned int match_len, const char *rep_buffer, unsigned int rep_len) { - return __nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + return __nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, match_offset, match_len, rep_buffer, rep_len, true); } @@ -31,6 +33,7 @@ static inline int nf_nat_mangle_tcp_packet(struct sk_buff *skb, extern int nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int match_offset, unsigned int match_len, const char *rep_buffer, @@ -41,10 +44,12 @@ extern void nf_nat_set_seq_adjust(struct nf_conn *ct, __be32 seq, s16 off); extern int nf_nat_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo); + enum ip_conntrack_info ctinfo, + unsigned int protoff); extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo); + enum ip_conntrack_info ctinfo, + unsigned int protoff); /* Setup NAT on this expected conntrack so it follows master, but goes * to port ct->master->saved_proto. */ diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index e7ff2dcab6ce..4ada3295d9a7 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -31,7 +31,8 @@ int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo); + enum ip_conntrack_info ctinfo, + unsigned int protoff); EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook); static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, @@ -149,7 +150,8 @@ static unsigned int ipv4_confirm(unsigned int hooknum, typeof(nf_nat_seq_adjust_hook) seq_adjust; seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); - if (!seq_adjust || !seq_adjust(skb, ct, ctinfo)) { + if (!seq_adjust || + !seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); return NF_DROP; } diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 3c04d24e2976..75464b62f5f2 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -26,6 +26,7 @@ MODULE_ALIAS("ip_nat_amanda"); static unsigned int help(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) @@ -61,7 +62,7 @@ static unsigned int help(struct sk_buff *skb, sprintf(buffer, "%u", port); ret = nf_nat_mangle_udp_packet(skb, exp->master, ctinfo, - matchoff, matchlen, + protoff, matchoff, matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) nf_ct_unexpect_related(exp); diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index e462a957d080..5589f3af4a8e 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -55,6 +55,7 @@ static int nf_nat_ftp_fmt_cmd(enum nf_ct_ftp_type type, static unsigned int nf_nat_ftp(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) @@ -100,7 +101,7 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, pr_debug("calling nf_nat_mangle_tcp_packet\n"); - if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, matchoff, + if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, matchlen, buffer, buflen)) goto out; diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index c6784a18c1c4..d2c228db38b5 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -21,7 +21,7 @@ #include /****************************************************************************/ -static int set_addr(struct sk_buff *skb, +static int set_addr(struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, unsigned int addroff, __be32 ip, __be16 port) { @@ -40,7 +40,7 @@ static int set_addr(struct sk_buff *skb, if (ip_hdr(skb)->protocol == IPPROTO_TCP) { if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, - addroff, sizeof(buf), + protoff, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_tcp_packet error\n"); return -1; @@ -54,7 +54,7 @@ static int set_addr(struct sk_buff *skb, *data = skb->data + ip_hdrlen(skb) + th->doff * 4 + dataoff; } else { if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, - addroff, sizeof(buf), + protoff, addroff, sizeof(buf), (char *) &buf, sizeof(buf))) { net_notice_ratelimited("nf_nat_h323: nf_nat_mangle_udp_packet error\n"); return -1; @@ -69,22 +69,22 @@ static int set_addr(struct sk_buff *skb, } /****************************************************************************/ -static int set_h225_addr(struct sk_buff *skb, +static int set_h225_addr(struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, union nf_inet_addr *addr, __be16 port) { - return set_addr(skb, data, dataoff, taddr->ipAddress.ip, + return set_addr(skb, protoff, data, dataoff, taddr->ipAddress.ip, addr->ip, port); } /****************************************************************************/ -static int set_h245_addr(struct sk_buff *skb, +static int set_h245_addr(struct sk_buff *skb, unsigned protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, union nf_inet_addr *addr, __be16 port) { - return set_addr(skb, data, dataoff, + return set_addr(skb, protoff, data, dataoff, taddr->unicastAddress.iPAddress.network, addr->ip, port); } @@ -92,7 +92,7 @@ static int set_h245_addr(struct sk_buff *skb, /****************************************************************************/ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) { const struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -118,7 +118,8 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, &addr.ip, port, &ct->tuplehash[!dir].tuple.dst.u3.ip, info->sig_port[!dir]); - return set_h225_addr(skb, data, 0, &taddr[i], + return set_h225_addr(skb, protoff, data, 0, + &taddr[i], &ct->tuplehash[!dir]. tuple.dst.u3, info->sig_port[!dir]); @@ -129,7 +130,8 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, &addr.ip, port, &ct->tuplehash[!dir].tuple.src.u3.ip, info->sig_port[!dir]); - return set_h225_addr(skb, data, 0, &taddr[i], + return set_h225_addr(skb, protoff, data, 0, + &taddr[i], &ct->tuplehash[!dir]. tuple.src.u3, info->sig_port[!dir]); @@ -143,7 +145,7 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int set_ras_addr(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) { int dir = CTINFO2DIR(ctinfo); @@ -159,7 +161,7 @@ static int set_ras_addr(struct sk_buff *skb, struct nf_conn *ct, &addr.ip, ntohs(port), &ct->tuplehash[!dir].tuple.dst.u3.ip, ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port)); - return set_h225_addr(skb, data, 0, &taddr[i], + return set_h225_addr(skb, protoff, data, 0, &taddr[i], &ct->tuplehash[!dir].tuple.dst.u3, ct->tuplehash[!dir].tuple. dst.u.udp.port); @@ -172,7 +174,7 @@ static int set_ras_addr(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, __be16 rtp_port, struct nf_conntrack_expect *rtp_exp, @@ -244,7 +246,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, } /* Modify signal */ - if (set_h245_addr(skb, data, dataoff, taddr, + if (set_h245_addr(skb, protoff, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons((port & htons(1)) ? nated_port + 1 : nated_port)) == 0) { @@ -275,7 +277,7 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) { @@ -307,7 +309,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, } /* Modify signal */ - if (set_h245_addr(skb, data, dataoff, taddr, + if (set_h245_addr(skb, protoff, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons(nated_port)) < 0) { nf_ct_unexpect_related(exp); @@ -326,7 +328,7 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) { @@ -363,7 +365,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, } /* Modify signal */ - if (set_h225_addr(skb, data, dataoff, taddr, + if (set_h225_addr(skb, protoff, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons(nated_port)) == 0) { /* Save ports */ @@ -416,7 +418,8 @@ static void ip_nat_q931_expect(struct nf_conn *new, /****************************************************************************/ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, TransportAddress *taddr, int idx, + unsigned int protoff, unsigned char **data, + TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -453,7 +456,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, } /* Modify signal */ - if (set_h225_addr(skb, data, 0, &taddr[idx], + if (set_h225_addr(skb, protoff, data, 0, &taddr[idx], &ct->tuplehash[!dir].tuple.dst.u3, htons(nated_port)) == 0) { /* Save ports */ @@ -464,7 +467,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, if (idx > 0 && get_h225_addr(ct, *data, &taddr[0], &addr, &port) && (ntohl(addr.ip) & 0xff000000) == 0x7f000000) { - set_h225_addr(skb, data, 0, &taddr[0], + set_h225_addr(skb, protoff, data, 0, &taddr[0], &ct->tuplehash[!dir].tuple.dst.u3, info->sig_port[!dir]); } @@ -507,6 +510,7 @@ static void ip_nat_callforwarding_expect(struct nf_conn *new, /****************************************************************************/ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) @@ -541,7 +545,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, } /* Modify signal */ - if (!set_h225_addr(skb, data, dataoff, taddr, + if (!set_h225_addr(skb, protoff, data, dataoff, taddr, &ct->tuplehash[!dir].tuple.dst.u3, htons(nated_port)) == 0) { nf_ct_unexpect_related(exp); diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 2e59ad0b90ca..2fefec5e757c 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -206,6 +206,7 @@ static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int match_offset, unsigned int match_len, const char *rep_buffer, @@ -257,6 +258,7 @@ int nf_nat_mangle_udp_packet(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int match_offset, unsigned int match_len, const char *rep_buffer, @@ -387,7 +389,8 @@ nf_nat_sack_adjust(struct sk_buff *skb, int nf_nat_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - enum ip_conntrack_info ctinfo) + enum ip_conntrack_info ctinfo, + unsigned int protoff) { struct tcphdr *tcph; int dir; @@ -401,10 +404,10 @@ nf_nat_seq_adjust(struct sk_buff *skb, this_way = &nat->seq[dir]; other_way = &nat->seq[!dir]; - if (!skb_make_writable(skb, ip_hdrlen(skb) + sizeof(*tcph))) + if (!skb_make_writable(skb, protoff + sizeof(*tcph))) return 0; - tcph = (void *)skb->data + ip_hdrlen(skb); + tcph = (void *)skb->data + protoff; if (after(ntohl(tcph->seq), this_way->correction_pos)) seqoff = this_way->offset_after; else diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index 979ae165f4ef..5b0c20a1f08d 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -29,6 +29,7 @@ MODULE_ALIAS("ip_nat_irc"); static unsigned int help(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) @@ -66,7 +67,7 @@ static unsigned int help(struct sk_buff *skb, buffer, &ip, port); ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, - matchoff, matchlen, buffer, + protoff, matchoff, matchlen, buffer, strlen(buffer)); if (ret != NF_ACCEPT) nf_ct_unexpect_related(exp); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 388140881ebe..31ef890d894b 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -113,6 +113,7 @@ static int pptp_outbound_pkt(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq) @@ -175,7 +176,7 @@ pptp_outbound_pkt(struct sk_buff *skb, ntohs(REQ_CID(pptpReq, cid_off)), ntohs(new_callid)); /* mangle packet */ - if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, cid_off + sizeof(struct pptp_pkt_hdr) + sizeof(struct PptpControlHeader), sizeof(new_callid), (char *)&new_callid, @@ -216,6 +217,7 @@ static int pptp_inbound_pkt(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq) { @@ -268,7 +270,7 @@ pptp_inbound_pkt(struct sk_buff *skb, pr_debug("altering peer call id from 0x%04x to 0x%04x\n", ntohs(REQ_CID(pptpReq, pcid_off)), ntohs(new_pcid)); - if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + if (nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, pcid_off + sizeof(struct pptp_pkt_hdr) + sizeof(struct PptpControlHeader), sizeof(new_pcid), (char *)&new_pcid, diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 4ad9cf173992..df626af8413c 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -30,7 +30,8 @@ MODULE_DESCRIPTION("SIP NAT helper"); MODULE_ALIAS("ip_nat_sip"); -static unsigned int mangle_packet(struct sk_buff *skb, unsigned int dataoff, +static unsigned int mangle_packet(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, const char *buffer, unsigned int buflen) @@ -46,7 +47,7 @@ static unsigned int mangle_packet(struct sk_buff *skb, unsigned int dataoff, matchoff += dataoff - baseoff; if (!__nf_nat_mangle_tcp_packet(skb, ct, ctinfo, - matchoff, matchlen, + protoff, matchoff, matchlen, buffer, buflen, false)) return 0; } else { @@ -54,7 +55,7 @@ static unsigned int mangle_packet(struct sk_buff *skb, unsigned int dataoff, matchoff += dataoff - baseoff; if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, - matchoff, matchlen, + protoff, matchoff, matchlen, buffer, buflen)) return 0; } @@ -65,7 +66,8 @@ static unsigned int mangle_packet(struct sk_buff *skb, unsigned int dataoff, return 1; } -static int map_addr(struct sk_buff *skb, unsigned int dataoff, +static int map_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, union nf_inet_addr *addr, __be16 port) @@ -94,11 +96,12 @@ static int map_addr(struct sk_buff *skb, unsigned int dataoff, buflen = sprintf(buffer, "%pI4:%u", &newaddr, ntohs(newport)); - return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, - buffer, buflen); + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen); } -static int map_sip_addr(struct sk_buff *skb, unsigned int dataoff, +static int map_sip_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, enum sip_header_types type) { @@ -111,11 +114,12 @@ static int map_sip_addr(struct sk_buff *skb, unsigned int dataoff, if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, type, NULL, &matchoff, &matchlen, &addr, &port) <= 0) return 1; - return map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, - &addr, port); + return map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port); } -static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, +static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -132,8 +136,8 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, if (ct_sip_parse_request(ct, *dptr, *datalen, &matchoff, &matchlen, &addr, &port) > 0 && - !map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, - &addr, port)) + !map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) return NF_DROP; request = 1; } else @@ -164,8 +168,8 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, } olen = *datalen; - if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, - &addr, port)) + if (!map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) return NF_DROP; matchend = matchoff + matchlen + *datalen - olen; @@ -179,7 +183,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) { buflen = sprintf(buffer, "%pI4", &ct->tuplehash[!dir].tuple.dst.u3.ip); - if (!mangle_packet(skb, dataoff, dptr, datalen, + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, poff, plen, buffer, buflen)) return NF_DROP; } @@ -193,7 +197,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { buflen = sprintf(buffer, "%pI4", &ct->tuplehash[!dir].tuple.src.u3.ip); - if (!mangle_packet(skb, dataoff, dptr, datalen, + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, poff, plen, buffer, buflen)) return NF_DROP; } @@ -207,7 +211,7 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int dataoff, htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; buflen = sprintf(buffer, "%u", ntohs(p)); - if (!mangle_packet(skb, dataoff, dptr, datalen, + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, poff, plen, buffer, buflen)) return NF_DROP; } @@ -221,13 +225,14 @@ next: SIP_HDR_CONTACT, &in_header, &matchoff, &matchlen, &addr, &port) > 0) { - if (!map_addr(skb, dataoff, dptr, datalen, matchoff, matchlen, + if (!map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) return NF_DROP; } - if (!map_sip_addr(skb, dataoff, dptr, datalen, SIP_HDR_FROM) || - !map_sip_addr(skb, dataoff, dptr, datalen, SIP_HDR_TO)) + if (!map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_FROM) || + !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) return NF_DROP; return NF_ACCEPT; @@ -272,7 +277,8 @@ static void ip_nat_sip_expected(struct nf_conn *ct, } } -static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, +static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *exp, unsigned int matchoff, @@ -326,7 +332,7 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, if (exp->tuple.dst.u3.ip != exp->saved_ip || exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { buflen = sprintf(buffer, "%pI4:%u", &newip, port); - if (!mangle_packet(skb, dataoff, dptr, datalen, + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, matchoff, matchlen, buffer, buflen)) goto err; } @@ -337,7 +343,8 @@ err: return NF_DROP; } -static int mangle_content_len(struct sk_buff *skb, unsigned int dataoff, +static int mangle_content_len(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -359,11 +366,12 @@ static int mangle_content_len(struct sk_buff *skb, unsigned int dataoff, return 0; buflen = sprintf(buffer, "%u", c_len); - return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, - buffer, buflen); + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen); } -static int mangle_sdp_packet(struct sk_buff *skb, unsigned int dataoff, +static int mangle_sdp_packet(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, enum sdp_header_types type, @@ -377,11 +385,12 @@ static int mangle_sdp_packet(struct sk_buff *skb, unsigned int dataoff, if (ct_sip_get_sdp_header(ct, *dptr, sdpoff, *datalen, type, term, &matchoff, &matchlen) <= 0) return -ENOENT; - return mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, - buffer, buflen) ? 0 : -EINVAL; + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen) ? 0 : -EINVAL; } -static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, unsigned int dataoff, +static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, enum sdp_header_types type, @@ -392,14 +401,15 @@ static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, unsigned int dataoff, unsigned int buflen; buflen = sprintf(buffer, "%pI4", &addr->ip); - if (mangle_sdp_packet(skb, dataoff, dptr, datalen, sdpoff, type, term, - buffer, buflen)) + if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, + sdpoff, type, term, buffer, buflen)) return 0; - return mangle_content_len(skb, dataoff, dptr, datalen); + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); } -static unsigned int ip_nat_sdp_port(struct sk_buff *skb, unsigned int dataoff, +static unsigned int ip_nat_sdp_port(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, unsigned int matchlen, @@ -409,14 +419,15 @@ static unsigned int ip_nat_sdp_port(struct sk_buff *skb, unsigned int dataoff, unsigned int buflen; buflen = sprintf(buffer, "%u", port); - if (!mangle_packet(skb, dataoff, dptr, datalen, matchoff, matchlen, - buffer, buflen)) + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen)) return 0; - return mangle_content_len(skb, dataoff, dptr, datalen); + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); } -static unsigned int ip_nat_sdp_session(struct sk_buff *skb, unsigned int dataoff, +static unsigned int ip_nat_sdp_session(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, const union nf_inet_addr *addr) @@ -426,12 +437,12 @@ static unsigned int ip_nat_sdp_session(struct sk_buff *skb, unsigned int dataoff /* Mangle session description owner and contact addresses */ buflen = sprintf(buffer, "%pI4", &addr->ip); - if (mangle_sdp_packet(skb, dataoff, dptr, datalen, sdpoff, + if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, SDP_HDR_OWNER_IP4, SDP_HDR_MEDIA, buffer, buflen)) return 0; - switch (mangle_sdp_packet(skb, dataoff, dptr, datalen, sdpoff, + switch (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, SDP_HDR_CONNECTION_IP4, SDP_HDR_MEDIA, buffer, buflen)) { case 0: @@ -448,12 +459,13 @@ static unsigned int ip_nat_sdp_session(struct sk_buff *skb, unsigned int dataoff return 0; } - return mangle_content_len(skb, dataoff, dptr, datalen); + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); } /* So, this packet has hit the connection tracking matching code. Mangle it, and change the expectation to match the new version. */ -static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff, +static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *rtp_exp, struct nf_conntrack_expect *rtcp_exp, @@ -514,7 +526,7 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff, /* Update media port. */ if (rtp_exp->tuple.dst.u.udp.port != rtp_exp->saved_proto.udp.port && - !ip_nat_sdp_port(skb, dataoff, dptr, datalen, + !ip_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, mediaoff, medialen, port)) goto err2; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index ad70b7e4ac4a..4f53a5f04437 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -268,6 +268,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * packet. */ ret = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + iph->ihl * 4, start-data, end-start, buf, buf_len); if (ret) { diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index 184c0dc6e437..e0212b5494b1 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -40,6 +40,7 @@ MODULE_PARM_DESC(ts_algo, "textsearch algorithm to use (default kmp)"); unsigned int (*nf_nat_amanda_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) @@ -156,8 +157,8 @@ static int amanda_help(struct sk_buff *skb, nf_nat_amanda = rcu_dereference(nf_nat_amanda_hook); if (nf_nat_amanda && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) - ret = nf_nat_amanda(skb, ctinfo, off - dataoff, - len, exp); + ret = nf_nat_amanda(skb, ctinfo, protoff, + off - dataoff, len, exp); else if (nf_ct_expect_related(exp) != 0) ret = NF_DROP; nf_ct_expect_put(exp); diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index 3e1587e63c03..c0f4a5ba9016 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -48,6 +48,7 @@ module_param(loose, bool, 0600); unsigned int (*nf_nat_ftp_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, enum nf_ct_ftp_type type, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp); @@ -490,7 +491,7 @@ static int help(struct sk_buff *skb, if (nf_nat_ftp && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) ret = nf_nat_ftp(skb, ctinfo, search[dir][i].ftptype, - matchoff, matchlen, exp); + protoff, matchoff, matchlen, exp); else { /* Can't expect this? Best to drop packet now. */ if (nf_ct_expect_related(exp) != 0) diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 517c5e3fe7c6..1b30b0dee708 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -49,12 +49,12 @@ MODULE_PARM_DESC(callforward_filter, "only create call forwarding expectations " "(determined by routing information)"); /* Hooks for NAT */ -int (*set_h245_addr_hook) (struct sk_buff *skb, +int (*set_h245_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, union nf_inet_addr *addr, __be16 port) __read_mostly; -int (*set_h225_addr_hook) (struct sk_buff *skb, +int (*set_h225_addr_hook) (struct sk_buff *skb, unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, union nf_inet_addr *addr, __be16 port) @@ -62,16 +62,17 @@ int (*set_h225_addr_hook) (struct sk_buff *skb, int (*set_sig_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) __read_mostly; int (*set_ras_addr_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) __read_mostly; int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, __be16 rtp_port, @@ -80,24 +81,28 @@ int (*nat_rtp_rtcp_hook) (struct sk_buff *skb, int (*nat_t120_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; int (*nat_h245_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; int (*nat_callforwarding_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; int (*nat_q931_hook) (struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int idx, __be16 port, struct nf_conntrack_expect *exp) __read_mostly; @@ -251,6 +256,7 @@ static int get_h245_addr(struct nf_conn *ct, const unsigned char *data, /****************************************************************************/ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr) { @@ -298,7 +304,7 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* NAT needed */ - ret = nat_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = nat_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, rtp_port, rtp_exp, rtcp_exp); } else { /* Conntrack only */ if (nf_ct_expect_related(rtp_exp) == 0) { @@ -325,6 +331,7 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, static int expect_t120(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H245_TransportAddress *taddr) { @@ -357,7 +364,7 @@ static int expect_t120(struct sk_buff *skb, nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* NAT needed */ - ret = nat_t120(skb, ct, ctinfo, data, dataoff, taddr, + ret = nat_t120(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { @@ -376,6 +383,7 @@ static int expect_t120(struct sk_buff *skb, static int process_h245_channel(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, H2250LogicalChannelParameters *channel) { @@ -383,7 +391,7 @@ static int process_h245_channel(struct sk_buff *skb, if (channel->options & eH2250LogicalChannelParameters_mediaChannel) { /* RTP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, &channel->mediaChannel); if (ret < 0) return -1; @@ -392,7 +400,7 @@ static int process_h245_channel(struct sk_buff *skb, if (channel-> options & eH2250LogicalChannelParameters_mediaControlChannel) { /* RTCP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, protoff, data, dataoff, &channel->mediaControlChannel); if (ret < 0) return -1; @@ -404,6 +412,7 @@ static int process_h245_channel(struct sk_buff *skb, /****************************************************************************/ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, OpenLogicalChannel *olc) { @@ -414,7 +423,8 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, if (olc->forwardLogicalChannelParameters.multiplexParameters.choice == eOpenLogicalChannel_forwardLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters) { - ret = process_h245_channel(skb, ct, ctinfo, data, dataoff, + ret = process_h245_channel(skb, ct, ctinfo, + protoff, data, dataoff, &olc-> forwardLogicalChannelParameters. multiplexParameters. @@ -432,7 +442,8 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, eOpenLogicalChannel_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters)) { ret = - process_h245_channel(skb, ct, ctinfo, data, dataoff, + process_h245_channel(skb, ct, ctinfo, + protoff, data, dataoff, &olc-> reverseLogicalChannelParameters. multiplexParameters. @@ -450,7 +461,7 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, t120.choice == eDataProtocolCapability_separateLANStack && olc->separateStack.networkAddress.choice == eNetworkAccessParameters_networkAddress_localAreaAddress) { - ret = expect_t120(skb, ct, ctinfo, data, dataoff, + ret = expect_t120(skb, ct, ctinfo, protoff, data, dataoff, &olc->separateStack.networkAddress. localAreaAddress); if (ret < 0) @@ -463,7 +474,7 @@ static int process_olc(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, OpenLogicalChannelAck *olca) { H2250LogicalChannelAckParameters *ack; @@ -479,7 +490,8 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, choice == eOpenLogicalChannelAck_reverseLogicalChannelParameters_multiplexParameters_h2250LogicalChannelParameters)) { - ret = process_h245_channel(skb, ct, ctinfo, data, dataoff, + ret = process_h245_channel(skb, ct, ctinfo, + protoff, data, dataoff, &olca-> reverseLogicalChannelParameters. multiplexParameters. @@ -498,7 +510,8 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, if (ack->options & eH2250LogicalChannelAckParameters_mediaChannel) { /* RTP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, + protoff, data, dataoff, &ack->mediaChannel); if (ret < 0) return -1; @@ -507,7 +520,8 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, if (ack->options & eH2250LogicalChannelAckParameters_mediaControlChannel) { /* RTCP */ - ret = expect_rtp_rtcp(skb, ct, ctinfo, data, dataoff, + ret = expect_rtp_rtcp(skb, ct, ctinfo, + protoff, data, dataoff, &ack->mediaControlChannel); if (ret < 0) return -1; @@ -517,7 +531,7 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, if ((olca->options & eOpenLogicalChannelAck_separateStack) && olca->separateStack.networkAddress.choice == eNetworkAccessParameters_networkAddress_localAreaAddress) { - ret = expect_t120(skb, ct, ctinfo, data, dataoff, + ret = expect_t120(skb, ct, ctinfo, protoff, data, dataoff, &olca->separateStack.networkAddress. localAreaAddress); if (ret < 0) @@ -530,14 +544,15 @@ static int process_olca(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_h245(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, MultimediaSystemControlMessage *mscm) { switch (mscm->choice) { case eMultimediaSystemControlMessage_request: if (mscm->request.choice == eRequestMessage_openLogicalChannel) { - return process_olc(skb, ct, ctinfo, data, dataoff, + return process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &mscm->request.openLogicalChannel); } pr_debug("nf_ct_h323: H.245 Request %d\n", @@ -546,7 +561,8 @@ static int process_h245(struct sk_buff *skb, struct nf_conn *ct, case eMultimediaSystemControlMessage_response: if (mscm->response.choice == eResponseMessage_openLogicalChannelAck) { - return process_olca(skb, ct, ctinfo, data, dataoff, + return process_olca(skb, ct, ctinfo, + protoff, data, dataoff, &mscm->response. openLogicalChannelAck); } @@ -597,7 +613,8 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff, } /* Process H.245 signal */ - if (process_h245(skb, ct, ctinfo, &data, dataoff, &mscm) < 0) + if (process_h245(skb, ct, ctinfo, protoff, + &data, dataoff, &mscm) < 0) goto drop; } @@ -661,7 +678,7 @@ int get_h225_addr(struct nf_conn *ct, unsigned char *data, /****************************************************************************/ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr) { int dir = CTINFO2DIR(ctinfo); @@ -693,7 +710,7 @@ static int expect_h245(struct sk_buff *skb, struct nf_conn *ct, nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* NAT needed */ - ret = nat_h245(skb, ct, ctinfo, data, dataoff, taddr, + ret = nat_h245(skb, ct, ctinfo, protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { @@ -779,6 +796,7 @@ static int callforward_do_filter(const union nf_inet_addr *src, static int expect_callforwarding(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, TransportAddress *taddr) { @@ -817,7 +835,8 @@ static int expect_callforwarding(struct sk_buff *skb, nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* Need NAT */ - ret = nat_callforwarding(skb, ct, ctinfo, data, dataoff, + ret = nat_callforwarding(skb, ct, ctinfo, + protoff, data, dataoff, taddr, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { @@ -835,6 +854,7 @@ static int expect_callforwarding(struct sk_buff *skb, /****************************************************************************/ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Setup_UUIE *setup) { @@ -848,7 +868,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Setup\n"); if (setup->options & eSetup_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &setup->h245Address); if (ret < 0) return -1; @@ -864,7 +884,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: set destCallSignalAddress %pI6:%hu->%pI6:%hu\n", &addr, ntohs(port), &ct->tuplehash[!dir].tuple.src.u3, ntohs(ct->tuplehash[!dir].tuple.src.u.tcp.port)); - ret = set_h225_addr(skb, data, dataoff, + ret = set_h225_addr(skb, protoff, data, dataoff, &setup->destCallSignalAddress, &ct->tuplehash[!dir].tuple.src.u3, ct->tuplehash[!dir].tuple.src.u.tcp.port); @@ -881,7 +901,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: set sourceCallSignalAddress %pI6:%hu->%pI6:%hu\n", &addr, ntohs(port), &ct->tuplehash[!dir].tuple.dst.u3, ntohs(ct->tuplehash[!dir].tuple.dst.u.tcp.port)); - ret = set_h225_addr(skb, data, dataoff, + ret = set_h225_addr(skb, protoff, data, dataoff, &setup->sourceCallSignalAddress, &ct->tuplehash[!dir].tuple.dst.u3, ct->tuplehash[!dir].tuple.dst.u.tcp.port); @@ -891,7 +911,8 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, if (setup->options & eSetup_UUIE_fastStart) { for (i = 0; i < setup->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &setup->fastStart.item[i]); if (ret < 0) return -1; @@ -905,6 +926,7 @@ static int process_setup(struct sk_buff *skb, struct nf_conn *ct, static int process_callproceeding(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, CallProceeding_UUIE *callproc) { @@ -914,7 +936,7 @@ static int process_callproceeding(struct sk_buff *skb, pr_debug("nf_ct_q931: CallProceeding\n"); if (callproc->options & eCallProceeding_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &callproc->h245Address); if (ret < 0) return -1; @@ -922,7 +944,8 @@ static int process_callproceeding(struct sk_buff *skb, if (callproc->options & eCallProceeding_UUIE_fastStart) { for (i = 0; i < callproc->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &callproc->fastStart.item[i]); if (ret < 0) return -1; @@ -935,6 +958,7 @@ static int process_callproceeding(struct sk_buff *skb, /****************************************************************************/ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Connect_UUIE *connect) { @@ -944,7 +968,7 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Connect\n"); if (connect->options & eConnect_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &connect->h245Address); if (ret < 0) return -1; @@ -952,7 +976,8 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, if (connect->options & eConnect_UUIE_fastStart) { for (i = 0; i < connect->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &connect->fastStart.item[i]); if (ret < 0) return -1; @@ -965,6 +990,7 @@ static int process_connect(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Alerting_UUIE *alert) { @@ -974,7 +1000,7 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Alerting\n"); if (alert->options & eAlerting_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &alert->h245Address); if (ret < 0) return -1; @@ -982,7 +1008,8 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, if (alert->options & eAlerting_UUIE_fastStart) { for (i = 0; i < alert->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &alert->fastStart.item[i]); if (ret < 0) return -1; @@ -995,6 +1022,7 @@ static int process_alerting(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Facility_UUIE *facility) { @@ -1005,15 +1033,15 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, if (facility->reason.choice == eFacilityReason_callForwarded) { if (facility->options & eFacility_UUIE_alternativeAddress) - return expect_callforwarding(skb, ct, ctinfo, data, - dataoff, + return expect_callforwarding(skb, ct, ctinfo, + protoff, data, dataoff, &facility-> alternativeAddress); return 0; } if (facility->options & eFacility_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &facility->h245Address); if (ret < 0) return -1; @@ -1021,7 +1049,8 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, if (facility->options & eFacility_UUIE_fastStart) { for (i = 0; i < facility->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &facility->fastStart.item[i]); if (ret < 0) return -1; @@ -1034,6 +1063,7 @@ static int process_facility(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, int dataoff, Progress_UUIE *progress) { @@ -1043,7 +1073,7 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_q931: Progress\n"); if (progress->options & eProgress_UUIE_h245Address) { - ret = expect_h245(skb, ct, ctinfo, data, dataoff, + ret = expect_h245(skb, ct, ctinfo, protoff, data, dataoff, &progress->h245Address); if (ret < 0) return -1; @@ -1051,7 +1081,8 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, if (progress->options & eProgress_UUIE_fastStart) { for (i = 0; i < progress->fastStart.count; i++) { - ret = process_olc(skb, ct, ctinfo, data, dataoff, + ret = process_olc(skb, ct, ctinfo, + protoff, data, dataoff, &progress->fastStart.item[i]); if (ret < 0) return -1; @@ -1064,7 +1095,8 @@ static int process_progress(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, int dataoff, Q931 *q931) + unsigned int protoff, unsigned char **data, int dataoff, + Q931 *q931) { H323_UU_PDU *pdu = &q931->UUIE.h323_uu_pdu; int i; @@ -1072,28 +1104,29 @@ static int process_q931(struct sk_buff *skb, struct nf_conn *ct, switch (pdu->h323_message_body.choice) { case eH323_UU_PDU_h323_message_body_setup: - ret = process_setup(skb, ct, ctinfo, data, dataoff, + ret = process_setup(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.setup); break; case eH323_UU_PDU_h323_message_body_callProceeding: - ret = process_callproceeding(skb, ct, ctinfo, data, dataoff, + ret = process_callproceeding(skb, ct, ctinfo, + protoff, data, dataoff, &pdu->h323_message_body. callProceeding); break; case eH323_UU_PDU_h323_message_body_connect: - ret = process_connect(skb, ct, ctinfo, data, dataoff, + ret = process_connect(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.connect); break; case eH323_UU_PDU_h323_message_body_alerting: - ret = process_alerting(skb, ct, ctinfo, data, dataoff, + ret = process_alerting(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.alerting); break; case eH323_UU_PDU_h323_message_body_facility: - ret = process_facility(skb, ct, ctinfo, data, dataoff, + ret = process_facility(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.facility); break; case eH323_UU_PDU_h323_message_body_progress: - ret = process_progress(skb, ct, ctinfo, data, dataoff, + ret = process_progress(skb, ct, ctinfo, protoff, data, dataoff, &pdu->h323_message_body.progress); break; default: @@ -1107,7 +1140,8 @@ static int process_q931(struct sk_buff *skb, struct nf_conn *ct, if (pdu->options & eH323_UU_PDU_h245Control) { for (i = 0; i < pdu->h245Control.count; i++) { - ret = process_h245(skb, ct, ctinfo, data, dataoff, + ret = process_h245(skb, ct, ctinfo, + protoff, data, dataoff, &pdu->h245Control.item[i]); if (ret < 0) return -1; @@ -1152,7 +1186,8 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff, } /* Process Q.931 signal */ - if (process_q931(skb, ct, ctinfo, &data, dataoff, &q931) < 0) + if (process_q931(skb, ct, ctinfo, protoff, + &data, dataoff, &q931) < 0) goto drop; } @@ -1249,7 +1284,7 @@ static int set_expect_timeout(struct nf_conntrack_expect *exp, /****************************************************************************/ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - unsigned char **data, + unsigned int protoff, unsigned char **data, TransportAddress *taddr, int count) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1286,7 +1321,8 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, nat_q931 = rcu_dereference(nat_q931_hook); if (nat_q931 && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* Need NAT */ - ret = nat_q931(skb, ct, ctinfo, data, taddr, i, port, exp); + ret = nat_q931(skb, ct, ctinfo, protoff, data, + taddr, i, port, exp); } else { /* Conntrack only */ if (nf_ct_expect_related(exp) == 0) { pr_debug("nf_ct_ras: expect Q.931 "); @@ -1306,6 +1342,7 @@ static int expect_q931(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_grq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, GatekeeperRequest *grq) { typeof(set_ras_addr_hook) set_ras_addr; @@ -1315,7 +1352,7 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct, set_ras_addr = rcu_dereference(set_ras_addr_hook); if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) /* NATed */ - return set_ras_addr(skb, ct, ctinfo, data, + return set_ras_addr(skb, ct, ctinfo, protoff, data, &grq->rasAddress, 1); return 0; } @@ -1323,6 +1360,7 @@ static int process_grq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, GatekeeperConfirm *gcf) { int dir = CTINFO2DIR(ctinfo); @@ -1367,6 +1405,7 @@ static int process_gcf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, RegistrationRequest *rrq) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1375,7 +1414,7 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, pr_debug("nf_ct_ras: RRQ\n"); - ret = expect_q931(skb, ct, ctinfo, data, + ret = expect_q931(skb, ct, ctinfo, protoff, data, rrq->callSignalAddress.item, rrq->callSignalAddress.count); if (ret < 0) @@ -1384,7 +1423,7 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, set_ras_addr = rcu_dereference(set_ras_addr_hook); if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { - ret = set_ras_addr(skb, ct, ctinfo, data, + ret = set_ras_addr(skb, ct, ctinfo, protoff, data, rrq->rasAddress.item, rrq->rasAddress.count); if (ret < 0) @@ -1403,6 +1442,7 @@ static int process_rrq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, RegistrationConfirm *rcf) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1416,7 +1456,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, set_sig_addr = rcu_dereference(set_sig_addr_hook); if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { - ret = set_sig_addr(skb, ct, ctinfo, data, + ret = set_sig_addr(skb, ct, ctinfo, protoff, data, rcf->callSignalAddress.item, rcf->callSignalAddress.count); if (ret < 0) @@ -1453,6 +1493,7 @@ static int process_rcf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, UnregistrationRequest *urq) { struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1465,7 +1506,7 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, set_sig_addr = rcu_dereference(set_sig_addr_hook); if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { - ret = set_sig_addr(skb, ct, ctinfo, data, + ret = set_sig_addr(skb, ct, ctinfo, protoff, data, urq->callSignalAddress.item, urq->callSignalAddress.count); if (ret < 0) @@ -1486,6 +1527,7 @@ static int process_urq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, AdmissionRequest *arq) { const struct nf_ct_h323_master *info = nfct_help_data(ct); @@ -1505,7 +1547,7 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, nf_ct_l3num(ct) == NFPROTO_IPV4 && set_h225_addr && ct->status & IPS_NAT_MASK) { /* Answering ARQ */ - return set_h225_addr(skb, data, 0, + return set_h225_addr(skb, protoff, data, 0, &arq->destCallSignalAddress, &ct->tuplehash[!dir].tuple.dst.u3, info->sig_port[!dir]); @@ -1518,7 +1560,7 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, set_h225_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { /* Calling ARQ */ - return set_h225_addr(skb, data, 0, + return set_h225_addr(skb, protoff, data, 0, &arq->srcCallSignalAddress, &ct->tuplehash[!dir].tuple.dst.u3, port); @@ -1530,6 +1572,7 @@ static int process_arq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, AdmissionConfirm *acf) { int dir = CTINFO2DIR(ctinfo); @@ -1550,7 +1593,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, set_sig_addr = rcu_dereference(set_sig_addr_hook); if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) - return set_sig_addr(skb, ct, ctinfo, data, + return set_sig_addr(skb, ct, ctinfo, protoff, data, &acf->destCallSignalAddress, 1); return 0; } @@ -1578,6 +1621,7 @@ static int process_acf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, LocationRequest *lrq) { typeof(set_ras_addr_hook) set_ras_addr; @@ -1587,7 +1631,7 @@ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct, set_ras_addr = rcu_dereference(set_ras_addr_hook); if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) - return set_ras_addr(skb, ct, ctinfo, data, + return set_ras_addr(skb, ct, ctinfo, protoff, data, &lrq->replyAddress, 1); return 0; } @@ -1595,6 +1639,7 @@ static int process_lrq(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, LocationConfirm *lcf) { int dir = CTINFO2DIR(ctinfo); @@ -1634,6 +1679,7 @@ static int process_lcf(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, InfoRequestResponse *irr) { int ret; @@ -1645,7 +1691,7 @@ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, set_ras_addr = rcu_dereference(set_ras_addr_hook); if (set_ras_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { - ret = set_ras_addr(skb, ct, ctinfo, data, + ret = set_ras_addr(skb, ct, ctinfo, protoff, data, &irr->rasAddress, 1); if (ret < 0) return -1; @@ -1654,7 +1700,7 @@ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, set_sig_addr = rcu_dereference(set_sig_addr_hook); if (set_sig_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { - ret = set_sig_addr(skb, ct, ctinfo, data, + ret = set_sig_addr(skb, ct, ctinfo, protoff, data, irr->callSignalAddress.item, irr->callSignalAddress.count); if (ret < 0) @@ -1667,38 +1713,39 @@ static int process_irr(struct sk_buff *skb, struct nf_conn *ct, /****************************************************************************/ static int process_ras(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned char **data, RasMessage *ras) { switch (ras->choice) { case eRasMessage_gatekeeperRequest: - return process_grq(skb, ct, ctinfo, data, + return process_grq(skb, ct, ctinfo, protoff, data, &ras->gatekeeperRequest); case eRasMessage_gatekeeperConfirm: - return process_gcf(skb, ct, ctinfo, data, + return process_gcf(skb, ct, ctinfo, protoff, data, &ras->gatekeeperConfirm); case eRasMessage_registrationRequest: - return process_rrq(skb, ct, ctinfo, data, + return process_rrq(skb, ct, ctinfo, protoff, data, &ras->registrationRequest); case eRasMessage_registrationConfirm: - return process_rcf(skb, ct, ctinfo, data, + return process_rcf(skb, ct, ctinfo, protoff, data, &ras->registrationConfirm); case eRasMessage_unregistrationRequest: - return process_urq(skb, ct, ctinfo, data, + return process_urq(skb, ct, ctinfo, protoff, data, &ras->unregistrationRequest); case eRasMessage_admissionRequest: - return process_arq(skb, ct, ctinfo, data, + return process_arq(skb, ct, ctinfo, protoff, data, &ras->admissionRequest); case eRasMessage_admissionConfirm: - return process_acf(skb, ct, ctinfo, data, + return process_acf(skb, ct, ctinfo, protoff, data, &ras->admissionConfirm); case eRasMessage_locationRequest: - return process_lrq(skb, ct, ctinfo, data, + return process_lrq(skb, ct, ctinfo, protoff, data, &ras->locationRequest); case eRasMessage_locationConfirm: - return process_lcf(skb, ct, ctinfo, data, + return process_lcf(skb, ct, ctinfo, protoff, data, &ras->locationConfirm); case eRasMessage_infoRequestResponse: - return process_irr(skb, ct, ctinfo, data, + return process_irr(skb, ct, ctinfo, protoff, data, &ras->infoRequestResponse); default: pr_debug("nf_ct_ras: RAS message %d\n", ras->choice); @@ -1738,7 +1785,7 @@ static int ras_help(struct sk_buff *skb, unsigned int protoff, } /* Process RAS message */ - if (process_ras(skb, ct, ctinfo, &data, &ras) < 0) + if (process_ras(skb, ct, ctinfo, protoff, &data, &ras) < 0) goto drop; accept: diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index e06dc2fab19f..95d097cdb202 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -33,6 +33,7 @@ static DEFINE_SPINLOCK(irc_buffer_lock); unsigned int (*nf_nat_irc_hook)(struct sk_buff *skb, enum ip_conntrack_info ctinfo, + unsigned int protoff, unsigned int matchoff, unsigned int matchlen, struct nf_conntrack_expect *exp) __read_mostly; @@ -206,7 +207,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, nf_nat_irc = rcu_dereference(nf_nat_irc_hook); if (nf_nat_irc && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) - ret = nf_nat_irc(skb, ctinfo, + ret = nf_nat_irc(skb, ctinfo, protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, exp); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 6fed9ec35248..cc7669ef0b95 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -45,14 +45,14 @@ static DEFINE_SPINLOCK(nf_pptp_lock); int (*nf_nat_pptp_hook_outbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - struct PptpControlHeader *ctlh, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_outbound); int (*nf_nat_pptp_hook_inbound)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - struct PptpControlHeader *ctlh, + unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_inbound); @@ -262,7 +262,7 @@ out_unexpect_orig: } static inline int -pptp_inbound_pkt(struct sk_buff *skb, +pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq, unsigned int reqlen, @@ -376,7 +376,8 @@ pptp_inbound_pkt(struct sk_buff *skb, nf_nat_pptp_inbound = rcu_dereference(nf_nat_pptp_hook_inbound); if (nf_nat_pptp_inbound && ct->status & IPS_NAT_MASK) - return nf_nat_pptp_inbound(skb, ct, ctinfo, ctlh, pptpReq); + return nf_nat_pptp_inbound(skb, ct, ctinfo, + protoff, ctlh, pptpReq); return NF_ACCEPT; invalid: @@ -389,7 +390,7 @@ invalid: } static inline int -pptp_outbound_pkt(struct sk_buff *skb, +pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, struct PptpControlHeader *ctlh, union pptp_ctrl_union *pptpReq, unsigned int reqlen, @@ -471,7 +472,8 @@ pptp_outbound_pkt(struct sk_buff *skb, nf_nat_pptp_outbound = rcu_dereference(nf_nat_pptp_hook_outbound); if (nf_nat_pptp_outbound && ct->status & IPS_NAT_MASK) - return nf_nat_pptp_outbound(skb, ct, ctinfo, ctlh, pptpReq); + return nf_nat_pptp_outbound(skb, ct, ctinfo, + protoff, ctlh, pptpReq); return NF_ACCEPT; invalid: @@ -570,11 +572,11 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff, * established from PNS->PAC. However, RFC makes no guarantee */ if (dir == IP_CT_DIR_ORIGINAL) /* client -> server (PNS -> PAC) */ - ret = pptp_outbound_pkt(skb, ctlh, pptpReq, reqlen, ct, + ret = pptp_outbound_pkt(skb, protoff, ctlh, pptpReq, reqlen, ct, ctinfo); else /* server -> client (PAC -> PNS) */ - ret = pptp_inbound_pkt(skb, ctlh, pptpReq, reqlen, ct, + ret = pptp_inbound_pkt(skb, protoff, ctlh, pptpReq, reqlen, ct, ctinfo); pr_debug("sstate: %d->%d, cstate: %d->%d\n", oldsstate, info->sstate, oldcstate, info->cstate); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index d08e0baf4640..590f0abaab8c 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -52,8 +52,8 @@ module_param(sip_direct_media, int, 0600); MODULE_PARM_DESC(sip_direct_media, "Expect Media streams between signalling " "endpoints only (default 1)"); -unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, - const char **dptr, +unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_hook); @@ -61,6 +61,7 @@ void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_seq_adjust_hook); unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -69,7 +70,8 @@ unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int matchlen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_expect_hook); -unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int dataoff, +unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int sdpoff, @@ -79,7 +81,8 @@ unsigned int (*nf_nat_sdp_addr_hook)(struct sk_buff *skb, unsigned int dataoff, __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sdp_addr_hook); -unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int dataoff, +unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int matchoff, @@ -88,6 +91,7 @@ unsigned int (*nf_nat_sdp_port_hook)(struct sk_buff *skb, unsigned int dataoff, EXPORT_SYMBOL_GPL(nf_nat_sdp_port_hook); unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, + unsigned int protoff, unsigned int dataoff, const char **dptr, unsigned int *datalen, @@ -96,7 +100,8 @@ unsigned int (*nf_nat_sdp_session_hook)(struct sk_buff *skb, __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sdp_session_hook); -unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int dataoff, +unsigned int (*nf_nat_sdp_media_hook)(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, struct nf_conntrack_expect *rtp_exp, @@ -883,7 +888,8 @@ static void flush_expectations(struct nf_conn *ct, bool media) spin_unlock_bh(&nf_conntrack_lock); } -static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, +static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, union nf_inet_addr *daddr, __be16 port, enum sip_expectation_classes class, @@ -960,7 +966,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, if (direct_rtp) { nf_nat_sdp_port = rcu_dereference(nf_nat_sdp_port_hook); if (nf_nat_sdp_port && - !nf_nat_sdp_port(skb, dataoff, dptr, datalen, + !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, mediaoff, medialen, ntohs(rtp_port))) goto err1; } @@ -983,7 +989,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int dataoff, nf_nat_sdp_media = rcu_dereference(nf_nat_sdp_media_hook); if (nf_nat_sdp_media && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK && !direct_rtp) - ret = nf_nat_sdp_media(skb, dataoff, dptr, datalen, + ret = nf_nat_sdp_media(skb, protoff, dataoff, dptr, datalen, rtp_exp, rtcp_exp, mediaoff, medialen, daddr); else { @@ -1024,7 +1030,8 @@ static const struct sdp_media_type *sdp_media_type(const char *dptr, return NULL; } -static int process_sdp(struct sk_buff *skb, unsigned int dataoff, +static int process_sdp(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1098,7 +1105,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, else return NF_DROP; - ret = set_expected_rtp_rtcp(skb, dataoff, dptr, datalen, + ret = set_expected_rtp_rtcp(skb, protoff, dataoff, + dptr, datalen, &rtp_addr, htons(port), t->class, mediaoff, medialen); if (ret != NF_ACCEPT) @@ -1107,7 +1115,8 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, /* Update media connection address if present */ if (maddr_len && nf_nat_sdp_addr && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { - ret = nf_nat_sdp_addr(skb, dataoff, dptr, datalen, + ret = nf_nat_sdp_addr(skb, protoff, dataoff, + dptr, datalen, mediaoff, c_hdr, SDP_HDR_MEDIA, &rtp_addr); if (ret != NF_ACCEPT) @@ -1120,12 +1129,13 @@ static int process_sdp(struct sk_buff *skb, unsigned int dataoff, nf_nat_sdp_session = rcu_dereference(nf_nat_sdp_session_hook); if (nf_nat_sdp_session && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) - ret = nf_nat_sdp_session(skb, dataoff, dptr, datalen, sdpoff, - &rtp_addr); + ret = nf_nat_sdp_session(skb, protoff, dataoff, + dptr, datalen, sdpoff, &rtp_addr); return ret; } -static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, +static int process_invite_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1135,13 +1145,14 @@ static int process_invite_response(struct sk_buff *skb, unsigned int dataoff, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dataoff, dptr, datalen, cseq); + return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_update_response(struct sk_buff *skb, unsigned int dataoff, +static int process_update_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1151,13 +1162,14 @@ static int process_update_response(struct sk_buff *skb, unsigned int dataoff, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dataoff, dptr, datalen, cseq); + return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, +static int process_prack_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1167,13 +1179,14 @@ static int process_prack_response(struct sk_buff *skb, unsigned int dataoff, if ((code >= 100 && code <= 199) || (code >= 200 && code <= 299)) - return process_sdp(skb, dataoff, dptr, datalen, cseq); + return process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); else if (ct_sip_info->invite_cseq == cseq) flush_expectations(ct, true); return NF_ACCEPT; } -static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, +static int process_invite_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1183,13 +1196,14 @@ static int process_invite_request(struct sk_buff *skb, unsigned int dataoff, unsigned int ret; flush_expectations(ct, true); - ret = process_sdp(skb, dataoff, dptr, datalen, cseq); + ret = process_sdp(skb, protoff, dataoff, dptr, datalen, cseq); if (ret == NF_ACCEPT) ct_sip_info->invite_cseq = cseq; return ret; } -static int process_bye_request(struct sk_buff *skb, unsigned int dataoff, +static int process_bye_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1204,7 +1218,8 @@ static int process_bye_request(struct sk_buff *skb, unsigned int dataoff, * signalling connections. The expectation is marked inactive and is activated * when receiving a response indicating success from the registrar. */ -static int process_register_request(struct sk_buff *skb, unsigned int dataoff, +static int process_register_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq) { @@ -1280,8 +1295,8 @@ static int process_register_request(struct sk_buff *skb, unsigned int dataoff, nf_nat_sip_expect = rcu_dereference(nf_nat_sip_expect_hook); if (nf_nat_sip_expect && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) - ret = nf_nat_sip_expect(skb, dataoff, dptr, datalen, exp, - matchoff, matchlen); + ret = nf_nat_sip_expect(skb, protoff, dataoff, dptr, datalen, + exp, matchoff, matchlen); else { if (nf_ct_expect_related(exp) != 0) ret = NF_DROP; @@ -1296,7 +1311,8 @@ store_cseq: return ret; } -static int process_register_response(struct sk_buff *skb, unsigned int dataoff, +static int process_register_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen, unsigned int cseq, unsigned int code) { @@ -1378,7 +1394,8 @@ static const struct sip_handler sip_handlers[] = { SIP_HANDLER("REGISTER", process_register_request, process_register_response), }; -static int process_sip_response(struct sk_buff *skb, unsigned int dataoff, +static int process_sip_response(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -1409,13 +1426,14 @@ static int process_sip_response(struct sk_buff *skb, unsigned int dataoff, if (*datalen < matchend + handler->len || strnicmp(*dptr + matchend, handler->method, handler->len)) continue; - return handler->response(skb, dataoff, dptr, datalen, + return handler->response(skb, protoff, dataoff, dptr, datalen, cseq, code); } return NF_ACCEPT; } -static int process_sip_request(struct sk_buff *skb, unsigned int dataoff, +static int process_sip_request(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, const char **dptr, unsigned int *datalen) { enum ip_conntrack_info ctinfo; @@ -1440,27 +1458,29 @@ static int process_sip_request(struct sk_buff *skb, unsigned int dataoff, if (!cseq) return NF_DROP; - return handler->request(skb, dataoff, dptr, datalen, cseq); + return handler->request(skb, protoff, dataoff, dptr, datalen, + cseq); } return NF_ACCEPT; } static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct, - unsigned int dataoff, const char **dptr, - unsigned int *datalen) + unsigned int protoff, unsigned int dataoff, + const char **dptr, unsigned int *datalen) { typeof(nf_nat_sip_hook) nf_nat_sip; int ret; if (strnicmp(*dptr, "SIP/2.0 ", strlen("SIP/2.0 ")) != 0) - ret = process_sip_request(skb, dataoff, dptr, datalen); + ret = process_sip_request(skb, protoff, dataoff, dptr, datalen); else - ret = process_sip_response(skb, dataoff, dptr, datalen); + ret = process_sip_response(skb, protoff, dataoff, dptr, datalen); if (ret == NF_ACCEPT && nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { nf_nat_sip = rcu_dereference(nf_nat_sip_hook); - if (nf_nat_sip && !nf_nat_sip(skb, dataoff, dptr, datalen)) + if (nf_nat_sip && !nf_nat_sip(skb, protoff, dataoff, + dptr, datalen)) ret = NF_DROP; } @@ -1528,7 +1548,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, if (msglen > datalen) return NF_DROP; - ret = process_sip_msg(skb, ct, dataoff, &dptr, &msglen); + ret = process_sip_msg(skb, ct, protoff, dataoff, + &dptr, &msglen); if (ret != NF_ACCEPT) break; diff = msglen - origlen; @@ -1570,7 +1591,7 @@ static int sip_help_udp(struct sk_buff *skb, unsigned int protoff, if (datalen < strlen("SIP/2.0 200")) return NF_ACCEPT; - return process_sip_msg(skb, ct, dataoff, &dptr, &datalen); + return process_sip_msg(skb, ct, protoff, dataoff, &dptr, &datalen); } static struct nf_conntrack_helper sip[MAX_PORTS][4] __read_mostly; -- cgit v1.3-14-g43fede From c7232c9979cba684c50b64c513c4a83c9aa70563 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:06 +0200 Subject: netfilter: add protocol independent NAT core Convert the IPv4 NAT implementation to a protocol independent core and address family specific modules. Signed-off-by: Patrick McHardy --- include/linux/netfilter.h | 14 +- include/linux/netfilter/nf_nat.h | 8 + include/linux/netfilter/nfnetlink_conntrack.h | 6 +- include/linux/netfilter_ipv4.h | 1 - include/net/netfilter/nf_conntrack_expect.h | 2 +- include/net/netfilter/nf_nat.h | 2 +- include/net/netfilter/nf_nat_core.h | 5 +- include/net/netfilter/nf_nat_l3proto.h | 47 ++ include/net/netfilter/nf_nat_l4proto.h | 71 ++ include/net/netfilter/nf_nat_protocol.h | 67 -- include/net/netfilter/nf_nat_rule.h | 15 - include/net/netns/conntrack.h | 4 + include/net/netns/ipv4.h | 2 - net/ipv4/netfilter.c | 37 -- net/ipv4/netfilter/Kconfig | 64 +- net/ipv4/netfilter/Makefile | 11 +- net/ipv4/netfilter/ipt_MASQUERADE.c | 15 +- net/ipv4/netfilter/ipt_NETMAP.c | 15 +- net/ipv4/netfilter/ipt_REDIRECT.c | 15 +- net/ipv4/netfilter/iptable_nat.c | 320 +++++++++ net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 6 - net/ipv4/netfilter/nf_nat_amanda.c | 1 - net/ipv4/netfilter/nf_nat_core.c | 763 ---------------------- net/ipv4/netfilter/nf_nat_ftp.c | 1 - net/ipv4/netfilter/nf_nat_h323.c | 23 +- net/ipv4/netfilter/nf_nat_helper.c | 461 ------------- net/ipv4/netfilter/nf_nat_irc.c | 1 - net/ipv4/netfilter/nf_nat_l3proto_ipv4.c | 281 ++++++++ net/ipv4/netfilter/nf_nat_pptp.c | 15 +- net/ipv4/netfilter/nf_nat_proto_common.c | 114 ---- net/ipv4/netfilter/nf_nat_proto_dccp.c | 106 --- net/ipv4/netfilter/nf_nat_proto_gre.c | 30 +- net/ipv4/netfilter/nf_nat_proto_icmp.c | 24 +- net/ipv4/netfilter/nf_nat_proto_sctp.c | 96 --- net/ipv4/netfilter/nf_nat_proto_tcp.c | 91 --- net/ipv4/netfilter/nf_nat_proto_udp.c | 82 --- net/ipv4/netfilter/nf_nat_proto_udplite.c | 98 --- net/ipv4/netfilter/nf_nat_proto_unknown.c | 52 -- net/ipv4/netfilter/nf_nat_rule.c | 214 ------- net/ipv4/netfilter/nf_nat_sip.c | 19 +- net/ipv4/netfilter/nf_nat_standalone.c | 326 ---------- net/ipv4/netfilter/nf_nat_tftp.c | 1 - net/netfilter/Kconfig | 24 + net/netfilter/Makefile | 11 + net/netfilter/core.c | 5 + net/netfilter/nf_conntrack_core.c | 6 + net/netfilter/nf_conntrack_netlink.c | 35 +- net/netfilter/nf_conntrack_proto_tcp.c | 8 +- net/netfilter/nf_conntrack_sip.c | 6 +- net/netfilter/nf_nat_core.c | 854 +++++++++++++++++++++++++ net/netfilter/nf_nat_helper.c | 435 +++++++++++++ net/netfilter/nf_nat_proto_common.c | 112 ++++ net/netfilter/nf_nat_proto_dccp.c | 116 ++++ net/netfilter/nf_nat_proto_sctp.c | 103 +++ net/netfilter/nf_nat_proto_tcp.c | 85 +++ net/netfilter/nf_nat_proto_udp.c | 76 +++ net/netfilter/nf_nat_proto_udplite.c | 106 +++ net/netfilter/nf_nat_proto_unknown.c | 54 ++ net/netfilter/xt_nat.c | 167 +++++ 59 files changed, 3042 insertions(+), 2687 deletions(-) create mode 100644 include/net/netfilter/nf_nat_l3proto.h create mode 100644 include/net/netfilter/nf_nat_l4proto.h delete mode 100644 include/net/netfilter/nf_nat_protocol.h delete mode 100644 include/net/netfilter/nf_nat_rule.h create mode 100644 net/ipv4/netfilter/iptable_nat.c delete mode 100644 net/ipv4/netfilter/nf_nat_core.c delete mode 100644 net/ipv4/netfilter/nf_nat_helper.c create mode 100644 net/ipv4/netfilter/nf_nat_l3proto_ipv4.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_common.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_dccp.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_sctp.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_tcp.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_udp.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_udplite.c delete mode 100644 net/ipv4/netfilter/nf_nat_proto_unknown.c delete mode 100644 net/ipv4/netfilter/nf_nat_rule.c delete mode 100644 net/ipv4/netfilter/nf_nat_standalone.c create mode 100644 net/netfilter/nf_nat_core.c create mode 100644 net/netfilter/nf_nat_helper.c create mode 100644 net/netfilter/nf_nat_proto_common.c create mode 100644 net/netfilter/nf_nat_proto_dccp.c create mode 100644 net/netfilter/nf_nat_proto_sctp.c create mode 100644 net/netfilter/nf_nat_proto_tcp.c create mode 100644 net/netfilter/nf_nat_proto_udp.c create mode 100644 net/netfilter/nf_nat_proto_udplite.c create mode 100644 net/netfilter/nf_nat_proto_unknown.c create mode 100644 net/netfilter/xt_nat.c (limited to 'net/ipv4') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index c613cf0d7884..1dcf2a38e51f 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -342,7 +342,7 @@ extern int nf_register_afinfo(const struct nf_afinfo *afinfo); extern void nf_unregister_afinfo(const struct nf_afinfo *afinfo); #include -extern void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); +extern void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) @@ -350,13 +350,11 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #ifdef CONFIG_NF_NAT_NEEDED void (*decodefn)(struct sk_buff *, struct flowi *); - if (family == AF_INET) { - rcu_read_lock(); - decodefn = rcu_dereference(ip_nat_decode_session); - if (decodefn) - decodefn(skb, fl); - rcu_read_unlock(); - } + rcu_read_lock(); + decodefn = rcu_dereference(nf_nat_decode_session_hook); + if (decodefn) + decodefn(skb, fl); + rcu_read_unlock(); #endif } diff --git a/include/linux/netfilter/nf_nat.h b/include/linux/netfilter/nf_nat.h index 8df2d13730b2..bf0cc373ffb6 100644 --- a/include/linux/netfilter/nf_nat.h +++ b/include/linux/netfilter/nf_nat.h @@ -22,4 +22,12 @@ struct nf_nat_ipv4_multi_range_compat { struct nf_nat_ipv4_range range[1]; }; +struct nf_nat_range { + unsigned int flags; + union nf_inet_addr min_addr; + union nf_inet_addr max_addr; + union nf_conntrack_man_proto min_proto; + union nf_conntrack_man_proto max_proto; +}; + #endif /* _NETFILTER_NF_NAT_H */ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index f649f7423ca2..68920eab287c 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -142,8 +142,10 @@ enum ctattr_tstamp { enum ctattr_nat { CTA_NAT_UNSPEC, - CTA_NAT_MINIP, - CTA_NAT_MAXIP, + CTA_NAT_V4_MINIP, +#define CTA_NAT_MINIP CTA_NAT_V4_MINIP + CTA_NAT_V4_MAXIP, +#define CTA_NAT_MAXIP CTA_NAT_V4_MAXIP CTA_NAT_PROTO, __CTA_NAT_MAX }; diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index e2b12801378d..b962dfc695ae 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -79,7 +79,6 @@ enum nf_ip_hook_priorities { #ifdef __KERNEL__ extern int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); -extern int ip_xfrm_me_harder(struct sk_buff *skb); extern __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__KERNEL__*/ diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h index 983f00263243..cc13f377a705 100644 --- a/include/net/netfilter/nf_conntrack_expect.h +++ b/include/net/netfilter/nf_conntrack_expect.h @@ -43,7 +43,7 @@ struct nf_conntrack_expect { unsigned int class; #ifdef CONFIG_NF_NAT_NEEDED - __be32 saved_ip; + union nf_inet_addr saved_addr; /* This is the original per-proto part, used to map the * expected connection the way the recipient expects. */ union nf_conntrack_man_proto saved_proto; diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index b4de990b55f1..1752f1339054 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -50,7 +50,7 @@ struct nf_conn_nat { /* Set up the info structure to map into this range. */ extern unsigned int nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_ipv4_range *range, + const struct nf_nat_range *range, enum nf_nat_manip_type maniptype); /* Is this tuple already taken? (not by us)*/ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index b13d8d18d595..972e1e47ec79 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -12,10 +12,7 @@ extern unsigned int nf_nat_packet(struct nf_conn *ct, unsigned int hooknum, struct sk_buff *skb); -extern int nf_nat_icmp_reply_translation(struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int hooknum, - struct sk_buff *skb); +extern int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family); static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h new file mode 100644 index 000000000000..beed96961fa7 --- /dev/null +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -0,0 +1,47 @@ +#ifndef _NF_NAT_L3PROTO_H +#define _NF_NAT_L3PROTO_H + +struct nf_nat_l4proto; +struct nf_nat_l3proto { + u8 l3proto; + + bool (*in_range)(const struct nf_conntrack_tuple *t, + const struct nf_nat_range *range); + + u32 (*secure_port)(const struct nf_conntrack_tuple *t, __be16); + + bool (*manip_pkt)(struct sk_buff *skb, + unsigned int iphdroff, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype); + + void (*csum_update)(struct sk_buff *skb, unsigned int iphdroff, + __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype); + + void (*csum_recalc)(struct sk_buff *skb, u8 proto, + void *data, __sum16 *check, + int datalen, int oldlen); + + void (*decode_session)(struct sk_buff *skb, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + unsigned long statusbit, + struct flowi *fl); + + int (*nlattr_to_range)(struct nlattr *tb[], + struct nf_nat_range *range); +}; + +extern int nf_nat_l3proto_register(const struct nf_nat_l3proto *); +extern void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *); +extern const struct nf_nat_l3proto *__nf_nat_l3proto_find(u8 l3proto); + +extern int nf_nat_icmp_reply_translation(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum); + +#endif /* _NF_NAT_L3PROTO_H */ diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h new file mode 100644 index 000000000000..1f0a4f018fcf --- /dev/null +++ b/include/net/netfilter/nf_nat_l4proto.h @@ -0,0 +1,71 @@ +/* Header for use in defining a given protocol. */ +#ifndef _NF_NAT_L4PROTO_H +#define _NF_NAT_L4PROTO_H +#include +#include + +struct nf_nat_range; +struct nf_nat_l3proto; + +struct nf_nat_l4proto { + /* Protocol number. */ + u8 l4proto; + + /* Translate a packet to the target according to manip type. + * Return true if succeeded. + */ + bool (*manip_pkt)(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype); + + /* Is the manipable part of the tuple between min and max incl? */ + bool (*in_range)(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max); + + /* Alter the per-proto part of the tuple (depending on + * maniptype), to give a unique tuple in the given range if + * possible. Per-protocol part of tuple is initialized to the + * incoming packet. + */ + void (*unique_tuple)(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct); + + int (*nlattr_to_range)(struct nlattr *tb[], + struct nf_nat_range *range); +}; + +/* Protocol registration. */ +extern int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto); +extern void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto); + +extern const struct nf_nat_l4proto *__nf_nat_l4proto_find(u8 l3proto, u8 l4proto); + +/* Built-in protocols. */ +extern const struct nf_nat_l4proto nf_nat_l4proto_tcp; +extern const struct nf_nat_l4proto nf_nat_l4proto_udp; +extern const struct nf_nat_l4proto nf_nat_l4proto_icmp; +extern const struct nf_nat_l4proto nf_nat_l4proto_unknown; + +extern bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max); + +extern void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct, + u16 *rover); + +extern int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range); + +#endif /*_NF_NAT_L4PROTO_H*/ diff --git a/include/net/netfilter/nf_nat_protocol.h b/include/net/netfilter/nf_nat_protocol.h deleted file mode 100644 index 7b0b51165f70..000000000000 --- a/include/net/netfilter/nf_nat_protocol.h +++ /dev/null @@ -1,67 +0,0 @@ -/* Header for use in defining a given protocol. */ -#ifndef _NF_NAT_PROTOCOL_H -#define _NF_NAT_PROTOCOL_H -#include -#include - -struct nf_nat_ipv4_range; - -struct nf_nat_protocol { - /* Protocol number. */ - unsigned int protonum; - - /* Translate a packet to the target according to manip type. - Return true if succeeded. */ - bool (*manip_pkt)(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype); - - /* Is the manipable part of the tuple between min and max incl? */ - bool (*in_range)(const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype, - const union nf_conntrack_man_proto *min, - const union nf_conntrack_man_proto *max); - - /* Alter the per-proto part of the tuple (depending on - maniptype), to give a unique tuple in the given range if - possible. Per-protocol part of tuple is initialized to the - incoming packet. */ - void (*unique_tuple)(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct); - - int (*nlattr_to_range)(struct nlattr *tb[], - struct nf_nat_ipv4_range *range); -}; - -/* Protocol registration. */ -extern int nf_nat_protocol_register(const struct nf_nat_protocol *proto); -extern void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto); - -/* Built-in protocols. */ -extern const struct nf_nat_protocol nf_nat_protocol_tcp; -extern const struct nf_nat_protocol nf_nat_protocol_udp; -extern const struct nf_nat_protocol nf_nat_protocol_icmp; -extern const struct nf_nat_protocol nf_nat_unknown_protocol; - -extern int init_protocols(void) __init; -extern void cleanup_protocols(void); -extern const struct nf_nat_protocol *find_nat_proto(u_int16_t protonum); - -extern bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype, - const union nf_conntrack_man_proto *min, - const union nf_conntrack_man_proto *max); - -extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct, - u_int16_t *rover); - -extern int nf_nat_proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_ipv4_range *range); - -#endif /*_NF_NAT_PROTO_H*/ diff --git a/include/net/netfilter/nf_nat_rule.h b/include/net/netfilter/nf_nat_rule.h deleted file mode 100644 index 2890bdc4cd92..000000000000 --- a/include/net/netfilter/nf_nat_rule.h +++ /dev/null @@ -1,15 +0,0 @@ -#ifndef _NF_NAT_RULE_H -#define _NF_NAT_RULE_H -#include -#include -#include - -extern int nf_nat_rule_init(void) __init; -extern void nf_nat_rule_cleanup(void); -extern int nf_nat_rule_find(struct sk_buff *skb, - unsigned int hooknum, - const struct net_device *in, - const struct net_device *out, - struct nf_conn *ct); - -#endif /* _NF_NAT_RULE_H */ diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 3aecdc7a84fb..a1d83cc8bf85 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -83,6 +83,10 @@ struct netns_ct { int sysctl_auto_assign_helper; bool auto_assign_helper_warned; struct nf_ip_net nf_ct_proto; +#ifdef CONFIG_NF_NAT_NEEDED + struct hlist_head *nat_bysource; + unsigned int nat_htable_size; +#endif #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; struct ctl_table_header *acct_sysctl_header; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 1474dd65c66f..ace280d19a20 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -51,8 +51,6 @@ struct netns_ipv4 { struct xt_table *iptable_security; #endif struct xt_table *nat_table; - struct hlist_head *nat_bysource; - unsigned int nat_htable_size; #endif int sysctl_icmp_echo_ignore_all; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index ed1b36783192..f1643c0c3587 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -72,43 +72,6 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) } EXPORT_SYMBOL(ip_route_me_harder); -#ifdef CONFIG_XFRM -int ip_xfrm_me_harder(struct sk_buff *skb) -{ - struct flowi fl; - unsigned int hh_len; - struct dst_entry *dst; - - if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) - return 0; - if (xfrm_decode_session(skb, &fl, AF_INET) < 0) - return -1; - - dst = skb_dst(skb); - if (dst->xfrm) - dst = ((struct xfrm_dst *)dst)->route; - dst_hold(dst); - - dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); - if (IS_ERR(dst)) - return -1; - - skb_dst_drop(skb); - skb_dst_set(skb, dst); - - /* Change in oif may mean change in hh_len. */ - hh_len = skb_dst(skb)->dev->hard_header_len; - if (skb_headroom(skb) < hh_len && - pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) - return -1; - return 0; -} -EXPORT_SYMBOL(ip_xfrm_me_harder); -#endif - -void (*ip_nat_decode_session)(struct sk_buff *, struct flowi *); -EXPORT_SYMBOL(ip_nat_decode_session); - /* * Extra routing may needed on local out, as the QUEUE target never * returns control to the table. diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index fcc543cd987a..b26629681bdb 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -143,25 +143,22 @@ config IP_NF_TARGET_ULOG To compile it as a module, choose M here. If unsure, say N. # NAT + specific targets: nf_conntrack -config NF_NAT - tristate "Full NAT" +config NF_NAT_IPV4 + tristate "IPv4 NAT" depends on NF_CONNTRACK_IPV4 default m if NETFILTER_ADVANCED=n + select NF_NAT help - The Full NAT option allows masquerading, port forwarding and other + The IPv4 NAT option allows masquerading, port forwarding and other forms of full Network Address Port Translation. It is controlled by the `nat' table in iptables: see the man page for iptables(8). To compile it as a module, choose M here. If unsure, say N. -config NF_NAT_NEEDED - bool - depends on NF_NAT - default y +if NF_NAT_IPV4 config IP_NF_TARGET_MASQUERADE tristate "MASQUERADE target support" - depends on NF_NAT default m if NETFILTER_ADVANCED=n help Masquerading is a special case of NAT: all outgoing connections are @@ -174,7 +171,6 @@ config IP_NF_TARGET_MASQUERADE config IP_NF_TARGET_NETMAP tristate "NETMAP target support" - depends on NF_NAT depends on NETFILTER_ADVANCED help NETMAP is an implementation of static 1:1 NAT mapping of network @@ -185,7 +181,6 @@ config IP_NF_TARGET_NETMAP config IP_NF_TARGET_REDIRECT tristate "REDIRECT target support" - depends on NF_NAT depends on NETFILTER_ADVANCED help REDIRECT is a special case of NAT: all incoming connections are @@ -195,9 +190,11 @@ config IP_NF_TARGET_REDIRECT To compile it as a module, choose M here. If unsure, say N. +endif + config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" - depends on NF_CONNTRACK_SNMP && NF_NAT + depends on NF_CONNTRACK_SNMP && NF_NAT_IPV4 depends on NETFILTER_ADVANCED default NF_NAT && NF_CONNTRACK_SNMP ---help--- @@ -219,61 +216,46 @@ config NF_NAT_SNMP_BASIC # '&&' (6) # # (6) Returns the result of min(/expr/, /expr/). -config NF_NAT_PROTO_DCCP - tristate - depends on NF_NAT && NF_CT_PROTO_DCCP - default NF_NAT && NF_CT_PROTO_DCCP config NF_NAT_PROTO_GRE tristate - depends on NF_NAT && NF_CT_PROTO_GRE - -config NF_NAT_PROTO_UDPLITE - tristate - depends on NF_NAT && NF_CT_PROTO_UDPLITE - default NF_NAT && NF_CT_PROTO_UDPLITE - -config NF_NAT_PROTO_SCTP - tristate - default NF_NAT && NF_CT_PROTO_SCTP - depends on NF_NAT && NF_CT_PROTO_SCTP - select LIBCRC32C + depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE config NF_NAT_FTP tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_FTP + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_FTP config NF_NAT_IRC tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_IRC + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_IRC config NF_NAT_TFTP tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_TFTP + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_TFTP config NF_NAT_AMANDA tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_AMANDA + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_AMANDA config NF_NAT_PPTP tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_PPTP + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_PPTP select NF_NAT_PROTO_GRE config NF_NAT_H323 tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_H323 + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_H323 config NF_NAT_SIP tristate - depends on NF_CONNTRACK && NF_NAT - default NF_NAT && NF_CONNTRACK_SIP + depends on NF_CONNTRACK && NF_NAT_IPV4 + default NF_NAT_IPV4 && NF_CONNTRACK_SIP # mangle + specific targets config IP_NF_MANGLE diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index c20674dc9452..0ea3acc510e2 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -10,13 +10,11 @@ nf_conntrack_ipv4-objs += nf_conntrack_l3proto_ipv4_compat.o endif endif -nf_nat-y := nf_nat_core.o nf_nat_helper.o nf_nat_proto_unknown.o nf_nat_proto_common.o nf_nat_proto_tcp.o nf_nat_proto_udp.o nf_nat_proto_icmp.o -iptable_nat-y := nf_nat_rule.o nf_nat_standalone.o - # connection tracking obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o -obj-$(CONFIG_NF_NAT) += nf_nat.o +nf_nat_ipv4-y := nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o +obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o # defrag obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o @@ -32,10 +30,7 @@ obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o # NAT protocols (nf_nat) -obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o -obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o -obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o # generic IP tables obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o @@ -43,7 +38,7 @@ obj-$(CONFIG_IP_NF_IPTABLES) += ip_tables.o # the three instances of ip_tables obj-$(CONFIG_IP_NF_FILTER) += iptable_filter.o obj-$(CONFIG_IP_NF_MANGLE) += iptable_mangle.o -obj-$(CONFIG_NF_NAT) += iptable_nat.o +obj-$(CONFIG_NF_NAT_IPV4) += iptable_nat.o obj-$(CONFIG_IP_NF_RAW) += iptable_raw.o obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index cbb6a1a6f6f7..1c3aa28b51ae 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -19,9 +19,9 @@ #include #include #include -#include #include #include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team "); @@ -49,7 +49,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; - struct nf_nat_ipv4_range newrange; + struct nf_nat_range newrange; const struct nf_nat_ipv4_multi_range_compat *mr; const struct rtable *rt; __be32 newsrc, nh; @@ -80,10 +80,13 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) nat->masq_index = par->out->ifindex; /* Transfer from original range. */ - newrange = ((struct nf_nat_ipv4_range) - { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS, - newsrc, newsrc, - mr->range[0].min, mr->range[0].max }); + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = newsrc; + newrange.max_addr.ip = newsrc; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index b5bfbbabf70d..85028dc0425d 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Svenning Soerensen "); @@ -44,7 +44,7 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par) enum ip_conntrack_info ctinfo; __be32 new_ip, netmask; const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_ipv4_range newrange; + struct nf_nat_range newrange; NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || par->hooknum == NF_INET_POST_ROUTING || @@ -61,10 +61,13 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par) new_ip = ip_hdr(skb)->saddr & ~netmask; new_ip |= mr->range[0].min_ip & netmask; - newrange = ((struct nf_nat_ipv4_range) - { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS, - new_ip, new_ip, - mr->range[0].min, mr->range[0].max }); + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = new_ip; + newrange.max_addr.ip = new_ip; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 7c0103a5203e..11407d7d2472 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team "); @@ -48,7 +48,7 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) enum ip_conntrack_info ctinfo; __be32 newdst; const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_ipv4_range newrange; + struct nf_nat_range newrange; NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || par->hooknum == NF_INET_LOCAL_OUT); @@ -76,10 +76,13 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) } /* Transfer from original range. */ - newrange = ((struct nf_nat_ipv4_range) - { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS, - newdst, newdst, - mr->range[0].min, mr->range[0].max }); + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = newdst; + newrange.max_addr.ip = newdst; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; /* Hand modified range to generic setup. */ return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c new file mode 100644 index 000000000000..9e0ffaf1d942 --- /dev/null +++ b/net/ipv4/netfilter/iptable_nat.c @@ -0,0 +1,320 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * (C) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +static const struct xt_table nf_nat_ipv4_table = { + .name = "nat", + .valid_hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + .af = NFPROTO_IPV4, +}; + +static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + /* Force range to this IP; let proto decide mapping for + * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). + */ + struct nf_nat_range range; + + range.flags = 0; + pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, + HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip : + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); + + return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); +} + +static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum, + const struct net_device *in, + const struct net_device *out, + struct nf_conn *ct) +{ + struct net *net = nf_ct_net(ct); + unsigned int ret; + + ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table); + if (ret == NF_ACCEPT) { + if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) + ret = alloc_null_binding(ct, hooknum); + } + return ret; +} + +static unsigned int +nf_nat_ipv4_fn(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + struct nf_conn_nat *nat; + /* maniptype == SRC for postrouting. */ + enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); + + /* We never see fragments: conntrack defrags on pre-routing + * and local-out, and nf_nat_out protects post-routing. + */ + NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb))); + + ct = nf_ct_get(skb, &ctinfo); + /* Can't track? It's not due to stress, or conntrack would + * have dropped it. Hence it's the user's responsibilty to + * packet filter it out, or implement conntrack/NAT for that + * protocol. 8) --RR + */ + if (!ct) + return NF_ACCEPT; + + /* Don't try to NAT if this packet is not conntracked */ + if (nf_ct_is_untracked(ct)) + return NF_ACCEPT; + + nat = nfct_nat(ct); + if (!nat) { + /* NAT module was loaded late. */ + if (nf_ct_is_confirmed(ct)) + return NF_ACCEPT; + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } + + switch (ctinfo) { + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { + if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, + hooknum)) + return NF_DROP; + else + return NF_ACCEPT; + } + /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ + case IP_CT_NEW: + /* Seen it before? This can happen for loopback, retrans, + * or local packets. + */ + if (!nf_nat_initialized(ct, maniptype)) { + unsigned int ret; + + ret = nf_nat_rule_find(skb, hooknum, in, out, ct); + if (ret != NF_ACCEPT) + return ret; + } else + pr_debug("Already setup manip %s for ct %p\n", + maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", + ct); + break; + + default: + /* ESTABLISHED */ + NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || + ctinfo == IP_CT_ESTABLISHED_REPLY); + } + + return nf_nat_packet(ct, ctinfo, hooknum, skb); +} + +static unsigned int +nf_nat_ipv4_in(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + unsigned int ret; + __be32 daddr = ip_hdr(skb)->daddr; + + ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + daddr != ip_hdr(skb)->daddr) + skb_dst_drop(skb); + + return ret; +} + +static unsigned int +nf_nat_ipv4_out(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ +#ifdef CONFIG_XFRM + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; +#endif + unsigned int ret; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn); +#ifdef CONFIG_XFRM + if (ret != NF_DROP && ret != NF_STOLEN && + !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if ((ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all)) + if (nf_xfrm_me_harder(skb, AF_INET) < 0) + ret = NF_DROP; + } +#endif + return ret; +} + +static unsigned int +nf_nat_ipv4_local_fn(unsigned int hooknum, + struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + int (*okfn)(struct sk_buff *)) +{ + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + unsigned int ret; + + /* root is playing with raw sockets. */ + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) + return NF_ACCEPT; + + ret = nf_nat_ipv4_fn(hooknum, skb, in, out, okfn); + if (ret != NF_DROP && ret != NF_STOLEN && + (ct = nf_ct_get(skb, &ctinfo)) != NULL) { + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + + if (ct->tuplehash[dir].tuple.dst.u3.ip != + ct->tuplehash[!dir].tuple.src.u3.ip) { + if (ip_route_me_harder(skb, RTN_UNSPEC)) + ret = NF_DROP; + } +#ifdef CONFIG_XFRM + else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && + ct->tuplehash[dir].tuple.dst.u.all != + ct->tuplehash[!dir].tuple.src.u.all) + if (nf_xfrm_me_harder(skb, AF_INET) < 0) + ret = NF_DROP; +#endif + } + return ret; +} + +static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv4_in, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_PRE_ROUTING, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv4_out, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_POST_ROUTING, + .priority = NF_IP_PRI_NAT_SRC, + }, + /* Before packet filtering, change destination */ + { + .hook = nf_nat_ipv4_local_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_OUT, + .priority = NF_IP_PRI_NAT_DST, + }, + /* After packet filtering, change source */ + { + .hook = nf_nat_ipv4_fn, + .owner = THIS_MODULE, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = NF_IP_PRI_NAT_SRC, + }, +}; + +static int __net_init iptable_nat_net_init(struct net *net) +{ + struct ipt_replace *repl; + + repl = ipt_alloc_initial_table(&nf_nat_ipv4_table); + if (repl == NULL) + return -ENOMEM; + net->ipv4.nat_table = ipt_register_table(net, &nf_nat_ipv4_table, repl); + kfree(repl); + if (IS_ERR(net->ipv4.nat_table)) + return PTR_ERR(net->ipv4.nat_table); + return 0; +} + +static void __net_exit iptable_nat_net_exit(struct net *net) +{ + ipt_unregister_table(net, net->ipv4.nat_table); +} + +static struct pernet_operations iptable_nat_net_ops = { + .init = iptable_nat_net_init, + .exit = iptable_nat_net_exit, +}; + +static int __init iptable_nat_init(void) +{ + int err; + + err = register_pernet_subsys(&iptable_nat_net_ops); + if (err < 0) + goto err1; + + err = nf_register_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); + if (err < 0) + goto err2; + return 0; + +err2: + unregister_pernet_subsys(&iptable_nat_net_ops); +err1: + return err; +} + +static void __exit iptable_nat_exit(void) +{ + nf_unregister_hooks(nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); + unregister_pernet_subsys(&iptable_nat_net_ops); +} + +module_init(iptable_nat_init); +module_exit(iptable_nat_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 4ada3295d9a7..fcdd0c2406e6 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -29,12 +29,6 @@ #include #include -int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff); -EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook); - static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff, struct nf_conntrack_tuple *tuple) { diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 75464b62f5f2..42d337881171 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -16,7 +16,6 @@ #include #include #include -#include #include MODULE_AUTHOR("Brian J. Murrell "); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c deleted file mode 100644 index 44b082fd48ab..000000000000 --- a/net/ipv4/netfilter/nf_nat_core.c +++ /dev/null @@ -1,763 +0,0 @@ -/* NAT for netfilter; shared with compatibility layer. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include /* For tcp_prot in getorigdst */ -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -static DEFINE_SPINLOCK(nf_nat_lock); - -static struct nf_conntrack_l3proto *l3proto __read_mostly; - -#define MAX_IP_NAT_PROTO 256 -static const struct nf_nat_protocol __rcu *nf_nat_protos[MAX_IP_NAT_PROTO] - __read_mostly; - -static inline const struct nf_nat_protocol * -__nf_nat_proto_find(u_int8_t protonum) -{ - return rcu_dereference(nf_nat_protos[protonum]); -} - -/* We keep an extra hash for each conntrack, for fast searching. */ -static inline unsigned int -hash_by_src(const struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple) -{ - unsigned int hash; - - /* Original src, to ensure we map it consistently if poss. */ - hash = jhash_3words((__force u32)tuple->src.u3.ip, - (__force u32)tuple->src.u.all ^ zone, - tuple->dst.protonum, nf_conntrack_hash_rnd); - return ((u64)hash * net->ipv4.nat_htable_size) >> 32; -} - -/* Is this tuple already taken? (not by us) */ -int -nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, - const struct nf_conn *ignored_conntrack) -{ - /* Conntrack tracking doesn't keep track of outgoing tuples; only - incoming ones. NAT means they don't have a fixed mapping, - so we invert the tuple and look for the incoming reply. - - We could keep a separate hash if this proves too slow. */ - struct nf_conntrack_tuple reply; - - nf_ct_invert_tuplepr(&reply, tuple); - return nf_conntrack_tuple_taken(&reply, ignored_conntrack); -} -EXPORT_SYMBOL(nf_nat_used_tuple); - -/* If we source map this tuple so reply looks like reply_tuple, will - * that meet the constraints of range. */ -static int -in_range(const struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range) -{ - const struct nf_nat_protocol *proto; - int ret = 0; - - /* If we are supposed to map IPs, then we must be in the - range specified, otherwise let this drag us onto a new src IP. */ - if (range->flags & NF_NAT_RANGE_MAP_IPS) { - if (ntohl(tuple->src.u3.ip) < ntohl(range->min_ip) || - ntohl(tuple->src.u3.ip) > ntohl(range->max_ip)) - return 0; - } - - rcu_read_lock(); - proto = __nf_nat_proto_find(tuple->dst.protonum); - if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) || - proto->in_range(tuple, NF_NAT_MANIP_SRC, - &range->min, &range->max)) - ret = 1; - rcu_read_unlock(); - - return ret; -} - -static inline int -same_src(const struct nf_conn *ct, - const struct nf_conntrack_tuple *tuple) -{ - const struct nf_conntrack_tuple *t; - - t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - return (t->dst.protonum == tuple->dst.protonum && - t->src.u3.ip == tuple->src.u3.ip && - t->src.u.all == tuple->src.u.all); -} - -/* Only called for SRC manip */ -static int -find_appropriate_src(struct net *net, u16 zone, - const struct nf_conntrack_tuple *tuple, - struct nf_conntrack_tuple *result, - const struct nf_nat_ipv4_range *range) -{ - unsigned int h = hash_by_src(net, zone, tuple); - const struct nf_conn_nat *nat; - const struct nf_conn *ct; - const struct hlist_node *n; - - rcu_read_lock(); - hlist_for_each_entry_rcu(nat, n, &net->ipv4.nat_bysource[h], bysource) { - ct = nat->ct; - if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { - /* Copy source part from reply tuple. */ - nf_ct_invert_tuplepr(result, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - result->dst = tuple->dst; - - if (in_range(result, range)) { - rcu_read_unlock(); - return 1; - } - } - } - rcu_read_unlock(); - return 0; -} - -/* For [FUTURE] fragmentation handling, we want the least-used - src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus - if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports - 1-65535, we don't do pro-rata allocation based on ports; we choose - the ip with the lowest src-ip/dst-ip/proto usage. -*/ -static void -find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - const struct nf_conn *ct, - enum nf_nat_manip_type maniptype) -{ - __be32 *var_ipp; - /* Host order */ - u_int32_t minip, maxip, j; - - /* No IP mapping? Do nothing. */ - if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) - return; - - if (maniptype == NF_NAT_MANIP_SRC) - var_ipp = &tuple->src.u3.ip; - else - var_ipp = &tuple->dst.u3.ip; - - /* Fast path: only one choice. */ - if (range->min_ip == range->max_ip) { - *var_ipp = range->min_ip; - return; - } - - /* Hashing source and destination IPs gives a fairly even - * spread in practice (if there are a small number of IPs - * involved, there usually aren't that many connections - * anyway). The consistency means that servers see the same - * client coming from the same IP (some Internet Banking sites - * like this), even across reboots. */ - minip = ntohl(range->min_ip); - maxip = ntohl(range->max_ip); - j = jhash_2words((__force u32)tuple->src.u3.ip, - range->flags & NF_NAT_RANGE_PERSISTENT ? - 0 : (__force u32)tuple->dst.u3.ip ^ zone, 0); - j = ((u64)j * (maxip - minip + 1)) >> 32; - *var_ipp = htonl(minip + j); -} - -/* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING, - * we change the source to map into the range. For NF_INET_PRE_ROUTING - * and NF_INET_LOCAL_OUT, we change the destination to map into the - * range. It might not be possible to get a unique tuple, but we try. - * At worst (or if we race), we will end up with a final duplicate in - * __ip_conntrack_confirm and drop the packet. */ -static void -get_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig_tuple, - const struct nf_nat_ipv4_range *range, - struct nf_conn *ct, - enum nf_nat_manip_type maniptype) -{ - struct net *net = nf_ct_net(ct); - const struct nf_nat_protocol *proto; - u16 zone = nf_ct_zone(ct); - - /* 1) If this srcip/proto/src-proto-part is currently mapped, - and that same mapping gives a unique tuple within the given - range, use that. - - This is only required for source (ie. NAT/masq) mappings. - So far, we don't do local source mappings, so multiple - manips not an issue. */ - if (maniptype == NF_NAT_MANIP_SRC && - !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { - /* try the original tuple first */ - if (in_range(orig_tuple, range)) { - if (!nf_nat_used_tuple(orig_tuple, ct)) { - *tuple = *orig_tuple; - return; - } - } else if (find_appropriate_src(net, zone, orig_tuple, tuple, - range)) { - pr_debug("get_unique_tuple: Found current src map\n"); - if (!nf_nat_used_tuple(tuple, ct)) - return; - } - } - - /* 2) Select the least-used IP/proto combination in the given - range. */ - *tuple = *orig_tuple; - find_best_ips_proto(zone, tuple, range, ct, maniptype); - - /* 3) The per-protocol part of the manip is made to map into - the range to make a unique tuple. */ - - rcu_read_lock(); - proto = __nf_nat_proto_find(orig_tuple->dst.protonum); - - /* Only bother mapping if it's not already in range and unique */ - if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { - if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { - if (proto->in_range(tuple, maniptype, &range->min, - &range->max) && - (range->min.all == range->max.all || - !nf_nat_used_tuple(tuple, ct))) - goto out; - } else if (!nf_nat_used_tuple(tuple, ct)) { - goto out; - } - } - - /* Last change: get protocol to try to obtain unique tuple. */ - proto->unique_tuple(tuple, range, maniptype, ct); -out: - rcu_read_unlock(); -} - -unsigned int -nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype) -{ - struct net *net = nf_ct_net(ct); - struct nf_conntrack_tuple curr_tuple, new_tuple; - struct nf_conn_nat *nat; - - /* nat helper or nfctnetlink also setup binding */ - nat = nfct_nat(ct); - if (!nat) { - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } - - NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || - maniptype == NF_NAT_MANIP_DST); - BUG_ON(nf_nat_initialized(ct, maniptype)); - - /* What we've got will look like inverse of reply. Normally - this is what is in the conntrack, except for prior - manipulations (future optimization: if num_manips == 0, - orig_tp = - conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */ - nf_ct_invert_tuplepr(&curr_tuple, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); - - get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); - - if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) { - struct nf_conntrack_tuple reply; - - /* Alter conntrack table so will recognize replies. */ - nf_ct_invert_tuplepr(&reply, &new_tuple); - nf_conntrack_alter_reply(ct, &reply); - - /* Non-atomic: we own this at the moment. */ - if (maniptype == NF_NAT_MANIP_SRC) - ct->status |= IPS_SRC_NAT; - else - ct->status |= IPS_DST_NAT; - } - - if (maniptype == NF_NAT_MANIP_SRC) { - unsigned int srchash; - - srchash = hash_by_src(net, nf_ct_zone(ct), - &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); - spin_lock_bh(&nf_nat_lock); - /* nf_conntrack_alter_reply might re-allocate extension area */ - nat = nfct_nat(ct); - nat->ct = ct; - hlist_add_head_rcu(&nat->bysource, - &net->ipv4.nat_bysource[srchash]); - spin_unlock_bh(&nf_nat_lock); - } - - /* It's done. */ - if (maniptype == NF_NAT_MANIP_DST) - ct->status |= IPS_DST_NAT_DONE; - else - ct->status |= IPS_SRC_NAT_DONE; - - return NF_ACCEPT; -} -EXPORT_SYMBOL(nf_nat_setup_info); - -/* Returns true if succeeded. */ -static bool -manip_pkt(u_int16_t proto, - struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *target, - enum nf_nat_manip_type maniptype) -{ - struct iphdr *iph; - const struct nf_nat_protocol *p; - - if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) - return false; - - iph = (void *)skb->data + iphdroff; - - /* Manipulate protcol part. */ - - /* rcu_read_lock()ed by nf_hook_slow */ - p = __nf_nat_proto_find(proto); - if (!p->manip_pkt(skb, iphdroff, target, maniptype)) - return false; - - iph = (void *)skb->data + iphdroff; - - if (maniptype == NF_NAT_MANIP_SRC) { - csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); - iph->saddr = target->src.u3.ip; - } else { - csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); - iph->daddr = target->dst.u3.ip; - } - return true; -} - -/* Do packet manipulations according to nf_nat_setup_info. */ -unsigned int nf_nat_packet(struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int hooknum, - struct sk_buff *skb) -{ - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - unsigned long statusbit; - enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); - - if (mtype == NF_NAT_MANIP_SRC) - statusbit = IPS_SRC_NAT; - else - statusbit = IPS_DST_NAT; - - /* Invert if this is reply dir. */ - if (dir == IP_CT_DIR_REPLY) - statusbit ^= IPS_NAT_MASK; - - /* Non-atomic: these bits don't change. */ - if (ct->status & statusbit) { - struct nf_conntrack_tuple target; - - /* We are aiming to look like inverse of other direction. */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); - - if (!manip_pkt(target.dst.protonum, skb, 0, &target, mtype)) - return NF_DROP; - } - return NF_ACCEPT; -} -EXPORT_SYMBOL_GPL(nf_nat_packet); - -/* Dir is direction ICMP is coming from (opposite to packet it contains) */ -int nf_nat_icmp_reply_translation(struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int hooknum, - struct sk_buff *skb) -{ - struct { - struct icmphdr icmp; - struct iphdr ip; - } *inside; - struct nf_conntrack_tuple target; - int hdrlen = ip_hdrlen(skb); - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - unsigned long statusbit; - enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); - - if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) - return 0; - - inside = (void *)skb->data + hdrlen; - - /* We're actually going to mangle it beyond trivial checksum - adjustment, so make sure the current checksum is correct. */ - if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) - return 0; - - /* Must be RELATED */ - NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED || - skb->nfctinfo == IP_CT_RELATED_REPLY); - - /* Redirects on non-null nats must be dropped, else they'll - start talking to each other without our translation, and be - confused... --RR */ - if (inside->icmp.type == ICMP_REDIRECT) { - /* If NAT isn't finished, assume it and drop. */ - if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) - return 0; - - if (ct->status & IPS_NAT_MASK) - return 0; - } - - if (manip == NF_NAT_MANIP_SRC) - statusbit = IPS_SRC_NAT; - else - statusbit = IPS_DST_NAT; - - /* Invert if this is reply dir. */ - if (dir == IP_CT_DIR_REPLY) - statusbit ^= IPS_NAT_MASK; - - if (!(ct->status & statusbit)) - return 1; - - pr_debug("icmp_reply_translation: translating error %p manip %u " - "dir %s\n", skb, manip, - dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); - - /* Change inner back to look like incoming packet. We do the - opposite manip on this hook to normal, because it might not - pass all hooks (locally-generated ICMP). Consider incoming - packet: PREROUTING (DST manip), routing produces ICMP, goes - through POSTROUTING (which must correct the DST manip). */ - if (!manip_pkt(inside->ip.protocol, skb, hdrlen + sizeof(inside->icmp), - &ct->tuplehash[!dir].tuple, !manip)) - return 0; - - if (skb->ip_summed != CHECKSUM_PARTIAL) { - /* Reloading "inside" here since manip_pkt inner. */ - inside = (void *)skb->data + hdrlen; - inside->icmp.checksum = 0; - inside->icmp.checksum = - csum_fold(skb_checksum(skb, hdrlen, - skb->len - hdrlen, 0)); - } - - /* Change outer to look the reply to an incoming packet - * (proto 0 means don't invert per-proto part). */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); - if (!manip_pkt(0, skb, 0, &target, manip)) - return 0; - - return 1; -} -EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); - -/* Protocol registration. */ -int nf_nat_protocol_register(const struct nf_nat_protocol *proto) -{ - int ret = 0; - - spin_lock_bh(&nf_nat_lock); - if (rcu_dereference_protected( - nf_nat_protos[proto->protonum], - lockdep_is_held(&nf_nat_lock) - ) != &nf_nat_unknown_protocol) { - ret = -EBUSY; - goto out; - } - RCU_INIT_POINTER(nf_nat_protos[proto->protonum], proto); - out: - spin_unlock_bh(&nf_nat_lock); - return ret; -} -EXPORT_SYMBOL(nf_nat_protocol_register); - -/* No one stores the protocol anywhere; simply delete it. */ -void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto) -{ - spin_lock_bh(&nf_nat_lock); - RCU_INIT_POINTER(nf_nat_protos[proto->protonum], - &nf_nat_unknown_protocol); - spin_unlock_bh(&nf_nat_lock); - synchronize_rcu(); -} -EXPORT_SYMBOL(nf_nat_protocol_unregister); - -/* No one using conntrack by the time this called. */ -static void nf_nat_cleanup_conntrack(struct nf_conn *ct) -{ - struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); - - if (nat == NULL || nat->ct == NULL) - return; - - NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); - - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); -} - -static void nf_nat_move_storage(void *new, void *old) -{ - struct nf_conn_nat *new_nat = new; - struct nf_conn_nat *old_nat = old; - struct nf_conn *ct = old_nat->ct; - - if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) - return; - - spin_lock_bh(&nf_nat_lock); - hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); - spin_unlock_bh(&nf_nat_lock); -} - -static struct nf_ct_ext_type nat_extend __read_mostly = { - .len = sizeof(struct nf_conn_nat), - .align = __alignof__(struct nf_conn_nat), - .destroy = nf_nat_cleanup_conntrack, - .move = nf_nat_move_storage, - .id = NF_CT_EXT_NAT, - .flags = NF_CT_EXT_F_PREALLOC, -}; - -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - -#include -#include - -static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { - [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, - [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, -}; - -static int nfnetlink_parse_nat_proto(struct nlattr *attr, - const struct nf_conn *ct, - struct nf_nat_ipv4_range *range) -{ - struct nlattr *tb[CTA_PROTONAT_MAX+1]; - const struct nf_nat_protocol *npt; - int err; - - err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy); - if (err < 0) - return err; - - rcu_read_lock(); - npt = __nf_nat_proto_find(nf_ct_protonum(ct)); - if (npt->nlattr_to_range) - err = npt->nlattr_to_range(tb, range); - rcu_read_unlock(); - return err; -} - -static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { - [CTA_NAT_MINIP] = { .type = NLA_U32 }, - [CTA_NAT_MAXIP] = { .type = NLA_U32 }, - [CTA_NAT_PROTO] = { .type = NLA_NESTED }, -}; - -static int -nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_ipv4_range *range) -{ - struct nlattr *tb[CTA_NAT_MAX+1]; - int err; - - memset(range, 0, sizeof(*range)); - - err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy); - if (err < 0) - return err; - - if (tb[CTA_NAT_MINIP]) - range->min_ip = nla_get_be32(tb[CTA_NAT_MINIP]); - - if (!tb[CTA_NAT_MAXIP]) - range->max_ip = range->min_ip; - else - range->max_ip = nla_get_be32(tb[CTA_NAT_MAXIP]); - - if (range->min_ip) - range->flags |= NF_NAT_RANGE_MAP_IPS; - - if (!tb[CTA_NAT_PROTO]) - return 0; - - err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); - if (err < 0) - return err; - - return 0; -} - -static int -nfnetlink_parse_nat_setup(struct nf_conn *ct, - enum nf_nat_manip_type manip, - const struct nlattr *attr) -{ - struct nf_nat_ipv4_range range; - - if (nfnetlink_parse_nat(attr, ct, &range) < 0) - return -EINVAL; - if (nf_nat_initialized(ct, manip)) - return -EEXIST; - - return nf_nat_setup_info(ct, &range, manip); -} -#else -static int -nfnetlink_parse_nat_setup(struct nf_conn *ct, - enum nf_nat_manip_type manip, - const struct nlattr *attr) -{ - return -EOPNOTSUPP; -} -#endif - -static int __net_init nf_nat_net_init(struct net *net) -{ - /* Leave them the same for the moment. */ - net->ipv4.nat_htable_size = net->ct.htable_size; - net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0); - if (!net->ipv4.nat_bysource) - return -ENOMEM; - return 0; -} - -/* Clear NAT section of all conntracks, in case we're loaded again. */ -static int clean_nat(struct nf_conn *i, void *data) -{ - struct nf_conn_nat *nat = nfct_nat(i); - - if (!nat) - return 0; - memset(nat, 0, sizeof(*nat)); - i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | IPS_SEQ_ADJUST); - return 0; -} - -static void __net_exit nf_nat_net_exit(struct net *net) -{ - nf_ct_iterate_cleanup(net, &clean_nat, NULL); - synchronize_rcu(); - nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size); -} - -static struct pernet_operations nf_nat_net_ops = { - .init = nf_nat_net_init, - .exit = nf_nat_net_exit, -}; - -static struct nf_ct_helper_expectfn follow_master_nat = { - .name = "nat-follow-master", - .expectfn = nf_nat_follow_master, -}; - -static struct nfq_ct_nat_hook nfq_ct_nat = { - .seq_adjust = nf_nat_tcp_seq_adjust, -}; - -static int __init nf_nat_init(void) -{ - size_t i; - int ret; - - need_ipv4_conntrack(); - - ret = nf_ct_extend_register(&nat_extend); - if (ret < 0) { - printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); - return ret; - } - - ret = register_pernet_subsys(&nf_nat_net_ops); - if (ret < 0) - goto cleanup_extend; - - /* Sew in builtin protocols. */ - spin_lock_bh(&nf_nat_lock); - for (i = 0; i < MAX_IP_NAT_PROTO; i++) - RCU_INIT_POINTER(nf_nat_protos[i], &nf_nat_unknown_protocol); - RCU_INIT_POINTER(nf_nat_protos[IPPROTO_TCP], &nf_nat_protocol_tcp); - RCU_INIT_POINTER(nf_nat_protos[IPPROTO_UDP], &nf_nat_protocol_udp); - RCU_INIT_POINTER(nf_nat_protos[IPPROTO_ICMP], &nf_nat_protocol_icmp); - spin_unlock_bh(&nf_nat_lock); - - /* Initialize fake conntrack so that NAT will skip it */ - nf_ct_untracked_status_or(IPS_NAT_DONE_MASK); - - l3proto = nf_ct_l3proto_find_get((u_int16_t)AF_INET); - - nf_ct_helper_expectfn_register(&follow_master_nat); - - BUG_ON(nf_nat_seq_adjust_hook != NULL); - RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); - BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); - RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, - nfnetlink_parse_nat_setup); - BUG_ON(nf_ct_nat_offset != NULL); - RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); - RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); - return 0; - - cleanup_extend: - nf_ct_extend_unregister(&nat_extend); - return ret; -} - -static void __exit nf_nat_cleanup(void) -{ - unregister_pernet_subsys(&nf_nat_net_ops); - nf_ct_l3proto_put(l3proto); - nf_ct_extend_unregister(&nat_extend); - nf_ct_helper_expectfn_unregister(&follow_master_nat); - RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); - RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); - RCU_INIT_POINTER(nf_ct_nat_offset, NULL); - RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); - synchronize_net(); -} - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("nf-nat-ipv4"); - -module_init(nf_nat_init); -module_exit(nf_nat_cleanup); diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index 5589f3af4a8e..dd5e387fc03b 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index d2c228db38b5..9c3db10b22d3 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -15,7 +15,6 @@ #include #include -#include #include #include #include @@ -392,7 +391,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_ipv4_range range; + struct nf_nat_range range; if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */ nf_nat_follow_master(new, this); @@ -404,14 +403,15 @@ static void ip_nat_q931_expect(struct nf_conn *new, /* Change src to where master sends to */ range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip; + range.min_addr = range.max_addr = + new->tuplehash[!this->dir].tuple.src.u3; nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); - range.min = range.max = this->saved_proto; - range.min_ip = range.max_ip = - new->master->tuplehash[!this->dir].tuple.src.u3.ip; + range.min_proto = range.max_proto = this->saved_proto; + range.min_addr = range.max_addr = + new->master->tuplehash[!this->dir].tuple.src.u3; nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST); } @@ -490,20 +490,21 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_callforwarding_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_ipv4_range range; + struct nf_nat_range range; /* This must be a fresh one. */ BUG_ON(new->status & IPS_NAT_DONE_MASK); /* Change src to where master sends to */ range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip; + range.min_addr = range.max_addr = + new->tuplehash[!this->dir].tuple.src.u3; nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); - range.min = range.max = this->saved_proto; - range.min_ip = range.max_ip = this->saved_ip; + range.min_proto = range.max_proto = this->saved_proto; + range.min_addr = range.max_addr = this->saved_addr; nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST); } @@ -519,7 +520,7 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, u_int16_t nated_port; /* Set expectations for NAT */ - exp->saved_ip = exp->tuple.dst.u3.ip; + exp->saved_addr = exp->tuple.dst.u3; exp->tuple.dst.u3.ip = ct->tuplehash[!dir].tuple.dst.u3.ip; exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; exp->expectfn = ip_nat_callforwarding_expect; diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c deleted file mode 100644 index 2fefec5e757c..000000000000 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ /dev/null @@ -1,461 +0,0 @@ -/* ip_nat_helper.c - generic support functions for NAT helpers - * - * (C) 2000-2002 Harald Welte - * (C) 2003-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DUMP_OFFSET(x) \ - pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ - x->offset_before, x->offset_after, x->correction_pos); - -static DEFINE_SPINLOCK(nf_nat_seqofs_lock); - -/* Setup TCP sequence correction given this change at this sequence */ -static inline void -adjust_tcp_sequence(u32 seq, - int sizediff, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_seq *this_way = &nat->seq[dir]; - - pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", - seq, sizediff); - - pr_debug("adjust_tcp_sequence: Seq_offset before: "); - DUMP_OFFSET(this_way); - - spin_lock_bh(&nf_nat_seqofs_lock); - - /* SYN adjust. If it's uninitialized, or this is after last - * correction, record it: we don't handle more than one - * adjustment in the window, but do deal with common case of a - * retransmit */ - if (this_way->offset_before == this_way->offset_after || - before(this_way->correction_pos, seq)) { - this_way->correction_pos = seq; - this_way->offset_before = this_way->offset_after; - this_way->offset_after += sizediff; - } - spin_unlock_bh(&nf_nat_seqofs_lock); - - pr_debug("adjust_tcp_sequence: Seq_offset after: "); - DUMP_OFFSET(this_way); -} - -/* Get the offset value, for conntrack */ -s16 nf_nat_get_offset(const struct nf_conn *ct, - enum ip_conntrack_dir dir, - u32 seq) -{ - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_seq *this_way; - s16 offset; - - if (!nat) - return 0; - - this_way = &nat->seq[dir]; - spin_lock_bh(&nf_nat_seqofs_lock); - offset = after(seq, this_way->correction_pos) - ? this_way->offset_after : this_way->offset_before; - spin_unlock_bh(&nf_nat_seqofs_lock); - - return offset; -} -EXPORT_SYMBOL_GPL(nf_nat_get_offset); - -/* Frobs data inside this packet, which is linear. */ -static void mangle_contents(struct sk_buff *skb, - unsigned int dataoff, - unsigned int match_offset, - unsigned int match_len, - const char *rep_buffer, - unsigned int rep_len) -{ - unsigned char *data; - - BUG_ON(skb_is_nonlinear(skb)); - data = skb_network_header(skb) + dataoff; - - /* move post-replacement */ - memmove(data + match_offset + rep_len, - data + match_offset + match_len, - skb->tail - (skb->network_header + dataoff + - match_offset + match_len)); - - /* insert data from buffer */ - memcpy(data + match_offset, rep_buffer, rep_len); - - /* update skb info */ - if (rep_len > match_len) { - pr_debug("nf_nat_mangle_packet: Extending packet by " - "%u from %u bytes\n", rep_len - match_len, skb->len); - skb_put(skb, rep_len - match_len); - } else { - pr_debug("nf_nat_mangle_packet: Shrinking packet from " - "%u from %u bytes\n", match_len - rep_len, skb->len); - __skb_trim(skb, skb->len + rep_len - match_len); - } - - /* fix IP hdr checksum information */ - ip_hdr(skb)->tot_len = htons(skb->len); - ip_send_check(ip_hdr(skb)); -} - -/* Unusual, but possible case. */ -static int enlarge_skb(struct sk_buff *skb, unsigned int extra) -{ - if (skb->len + extra > 65535) - return 0; - - if (pskb_expand_head(skb, 0, extra - skb_tailroom(skb), GFP_ATOMIC)) - return 0; - - return 1; -} - -void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, - __be32 seq, s16 off) -{ - if (!off) - return; - set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); - adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo); - nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); -} -EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); - -void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, - u32 ctinfo, int off) -{ - const struct tcphdr *th; - - if (nf_ct_protonum(ct) != IPPROTO_TCP) - return; - - th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); - nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); -} -EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); - -static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data, - int datalen, __sum16 *check, int oldlen) -{ - struct rtable *rt = skb_rtable(skb); - - if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(rt->rt_flags & RTCF_LOCAL) && - (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + - skb_network_offset(skb) + - iph->ihl * 4; - skb->csum_offset = (void *)check - data; - *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - datalen, iph->protocol, 0); - } else { - *check = 0; - *check = csum_tcpudp_magic(iph->saddr, iph->daddr, - datalen, iph->protocol, - csum_partial(data, datalen, - 0)); - if (iph->protocol == IPPROTO_UDP && !*check) - *check = CSUM_MANGLED_0; - } - } else - inet_proto_csum_replace2(check, skb, - htons(oldlen), htons(datalen), 1); -} - -/* Generic function for mangling variable-length address changes inside - * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX - * command in FTP). - * - * Takes care about all the nasty sequence number changes, checksumming, - * skb enlargement, ... - * - * */ -int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, - unsigned int match_offset, - unsigned int match_len, - const char *rep_buffer, - unsigned int rep_len, bool adjust) -{ - struct iphdr *iph; - struct tcphdr *tcph; - int oldlen, datalen; - - if (!skb_make_writable(skb, skb->len)) - return 0; - - if (rep_len > match_len && - rep_len - match_len > skb_tailroom(skb) && - !enlarge_skb(skb, rep_len - match_len)) - return 0; - - SKB_LINEAR_ASSERT(skb); - - iph = ip_hdr(skb); - tcph = (void *)iph + iph->ihl*4; - - oldlen = skb->len - iph->ihl*4; - mangle_contents(skb, iph->ihl*4 + tcph->doff*4, - match_offset, match_len, rep_buffer, rep_len); - - datalen = skb->len - iph->ihl*4; - nf_nat_csum(skb, iph, tcph, datalen, &tcph->check, oldlen); - - if (adjust && rep_len != match_len) - nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, - (int)rep_len - (int)match_len); - - return 1; -} -EXPORT_SYMBOL(__nf_nat_mangle_tcp_packet); - -/* Generic function for mangling variable-length address changes inside - * NATed UDP connections (like the CONNECT DATA XXXXX MESG XXXXX INDEX XXXXX - * command in the Amanda protocol) - * - * Takes care about all the nasty sequence number changes, checksumming, - * skb enlargement, ... - * - * XXX - This function could be merged with nf_nat_mangle_tcp_packet which - * should be fairly easy to do. - */ -int -nf_nat_mangle_udp_packet(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff, - unsigned int match_offset, - unsigned int match_len, - const char *rep_buffer, - unsigned int rep_len) -{ - struct iphdr *iph; - struct udphdr *udph; - int datalen, oldlen; - - if (!skb_make_writable(skb, skb->len)) - return 0; - - if (rep_len > match_len && - rep_len - match_len > skb_tailroom(skb) && - !enlarge_skb(skb, rep_len - match_len)) - return 0; - - iph = ip_hdr(skb); - udph = (void *)iph + iph->ihl*4; - - oldlen = skb->len - iph->ihl*4; - mangle_contents(skb, iph->ihl*4 + sizeof(*udph), - match_offset, match_len, rep_buffer, rep_len); - - /* update the length of the UDP packet */ - datalen = skb->len - iph->ihl*4; - udph->len = htons(datalen); - - /* fix udp checksum if udp checksum was previously calculated */ - if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) - return 1; - - nf_nat_csum(skb, iph, udph, datalen, &udph->check, oldlen); - - return 1; -} -EXPORT_SYMBOL(nf_nat_mangle_udp_packet); - -/* Adjust one found SACK option including checksum correction */ -static void -sack_adjust(struct sk_buff *skb, - struct tcphdr *tcph, - unsigned int sackoff, - unsigned int sackend, - struct nf_nat_seq *natseq) -{ - while (sackoff < sackend) { - struct tcp_sack_block_wire *sack; - __be32 new_start_seq, new_end_seq; - - sack = (void *)skb->data + sackoff; - if (after(ntohl(sack->start_seq) - natseq->offset_before, - natseq->correction_pos)) - new_start_seq = htonl(ntohl(sack->start_seq) - - natseq->offset_after); - else - new_start_seq = htonl(ntohl(sack->start_seq) - - natseq->offset_before); - - if (after(ntohl(sack->end_seq) - natseq->offset_before, - natseq->correction_pos)) - new_end_seq = htonl(ntohl(sack->end_seq) - - natseq->offset_after); - else - new_end_seq = htonl(ntohl(sack->end_seq) - - natseq->offset_before); - - pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", - ntohl(sack->start_seq), new_start_seq, - ntohl(sack->end_seq), new_end_seq); - - inet_proto_csum_replace4(&tcph->check, skb, - sack->start_seq, new_start_seq, 0); - inet_proto_csum_replace4(&tcph->check, skb, - sack->end_seq, new_end_seq, 0); - sack->start_seq = new_start_seq; - sack->end_seq = new_end_seq; - sackoff += sizeof(*sack); - } -} - -/* TCP SACK sequence number adjustment */ -static inline unsigned int -nf_nat_sack_adjust(struct sk_buff *skb, - struct tcphdr *tcph, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo) -{ - unsigned int dir, optoff, optend; - struct nf_conn_nat *nat = nfct_nat(ct); - - optoff = ip_hdrlen(skb) + sizeof(struct tcphdr); - optend = ip_hdrlen(skb) + tcph->doff * 4; - - if (!skb_make_writable(skb, optend)) - return 0; - - dir = CTINFO2DIR(ctinfo); - - while (optoff < optend) { - /* Usually: option, length. */ - unsigned char *op = skb->data + optoff; - - switch (op[0]) { - case TCPOPT_EOL: - return 1; - case TCPOPT_NOP: - optoff++; - continue; - default: - /* no partial options */ - if (optoff + 1 == optend || - optoff + op[1] > optend || - op[1] < 2) - return 0; - if (op[0] == TCPOPT_SACK && - op[1] >= 2+TCPOLEN_SACK_PERBLOCK && - ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) - sack_adjust(skb, tcph, optoff+2, - optoff+op[1], &nat->seq[!dir]); - optoff += op[1]; - } - } - return 1; -} - -/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ -int -nf_nat_seq_adjust(struct sk_buff *skb, - struct nf_conn *ct, - enum ip_conntrack_info ctinfo, - unsigned int protoff) -{ - struct tcphdr *tcph; - int dir; - __be32 newseq, newack; - s16 seqoff, ackoff; - struct nf_conn_nat *nat = nfct_nat(ct); - struct nf_nat_seq *this_way, *other_way; - - dir = CTINFO2DIR(ctinfo); - - this_way = &nat->seq[dir]; - other_way = &nat->seq[!dir]; - - if (!skb_make_writable(skb, protoff + sizeof(*tcph))) - return 0; - - tcph = (void *)skb->data + protoff; - if (after(ntohl(tcph->seq), this_way->correction_pos)) - seqoff = this_way->offset_after; - else - seqoff = this_way->offset_before; - - if (after(ntohl(tcph->ack_seq) - other_way->offset_before, - other_way->correction_pos)) - ackoff = other_way->offset_after; - else - ackoff = other_way->offset_before; - - newseq = htonl(ntohl(tcph->seq) + seqoff); - newack = htonl(ntohl(tcph->ack_seq) - ackoff); - - inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); - inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); - - pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", - ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), - ntohl(newack)); - - tcph->seq = newseq; - tcph->ack_seq = newack; - - return nf_nat_sack_adjust(skb, tcph, ct, ctinfo); -} - -/* Setup NAT on this expected conntrack so it follows master. */ -/* If we fail to get a free NAT slot, we'll get dropped on confirm */ -void nf_nat_follow_master(struct nf_conn *ct, - struct nf_conntrack_expect *exp) -{ - struct nf_nat_ipv4_range range; - - /* This must be a fresh one. */ - BUG_ON(ct->status & IPS_NAT_DONE_MASK); - - /* Change src to where master sends to */ - range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_ip = range.max_ip - = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; - nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); - - /* For DST manip, map port here to where it's expected. */ - range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); - range.min = range.max = exp->saved_proto; - range.min_ip = range.max_ip - = ct->master->tuplehash[!exp->dir].tuple.src.u3.ip; - nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); -} -EXPORT_SYMBOL(nf_nat_follow_master); diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index 5b0c20a1f08d..1ce37f89ec78 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -17,7 +17,6 @@ #include #include -#include #include #include #include diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c new file mode 100644 index 000000000000..d8b2e14efddc --- /dev/null +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -0,0 +1,281 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * (C) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +static const struct nf_nat_l3proto nf_nat_l3proto_ipv4; + +#ifdef CONFIG_XFRM +static void nf_nat_ipv4_decode_session(struct sk_buff *skb, + const struct nf_conn *ct, + enum ip_conntrack_dir dir, + unsigned long statusbit, + struct flowi *fl) +{ + const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple; + struct flowi4 *fl4 = &fl->u.ip4; + + if (ct->status & statusbit) { + fl4->daddr = t->dst.u3.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl4->fl4_dport = t->dst.u.all; + } + + statusbit ^= IPS_NAT_MASK; + + if (ct->status & statusbit) { + fl4->saddr = t->src.u3.ip; + if (t->dst.protonum == IPPROTO_TCP || + t->dst.protonum == IPPROTO_UDP || + t->dst.protonum == IPPROTO_UDPLITE || + t->dst.protonum == IPPROTO_DCCP || + t->dst.protonum == IPPROTO_SCTP) + fl4->fl4_sport = t->src.u.all; + } +} +#endif /* CONFIG_XFRM */ + +static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t, + const struct nf_nat_range *range) +{ + return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) && + ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip); +} + +static u32 nf_nat_ipv4_secure_port(const struct nf_conntrack_tuple *t, + __be16 dport) +{ + return secure_ipv4_port_ephemeral(t->src.u3.ip, t->dst.u3.ip, dport); +} + +static bool nf_nat_ipv4_manip_pkt(struct sk_buff *skb, + unsigned int iphdroff, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *target, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph; + unsigned int hdroff; + + if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) + return false; + + iph = (void *)skb->data + iphdroff; + hdroff = iphdroff + iph->ihl * 4; + + if (!l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv4, iphdroff, hdroff, + target, maniptype)) + return false; + iph = (void *)skb->data + iphdroff; + + if (maniptype == NF_NAT_MANIP_SRC) { + csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); + iph->saddr = target->src.u3.ip; + } else { + csum_replace4(&iph->check, iph->daddr, target->dst.u3.ip); + iph->daddr = target->dst.u3.ip; + } + return true; +} + +static void nf_nat_ipv4_csum_update(struct sk_buff *skb, + unsigned int iphdroff, __sum16 *check, + const struct nf_conntrack_tuple *t, + enum nf_nat_manip_type maniptype) +{ + struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); + __be32 oldip, newip; + + if (maniptype == NF_NAT_MANIP_SRC) { + oldip = iph->saddr; + newip = t->src.u3.ip; + } else { + oldip = iph->daddr; + newip = t->dst.u3.ip; + } + inet_proto_csum_replace4(check, skb, oldip, newip, 1); +} + +static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, + u8 proto, void *data, __sum16 *check, + int datalen, int oldlen) +{ + const struct iphdr *iph = ip_hdr(skb); + struct rtable *rt = skb_rtable(skb); + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(rt->rt_flags & RTCF_LOCAL) && + (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + + skb_network_offset(skb) + + ip_hdrlen(skb); + skb->csum_offset = (void *)check - data; + *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, proto, 0); + } else { + *check = 0; + *check = csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, proto, + csum_partial(data, datalen, + 0)); + if (proto == IPPROTO_UDP && !*check) + *check = CSUM_MANGLED_0; + } + } else + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), 1); +} + +static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range) +{ + if (tb[CTA_NAT_V4_MINIP]) { + range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]); + range->flags |= NF_NAT_RANGE_MAP_IPS; + } + + if (tb[CTA_NAT_V4_MAXIP]) + range->max_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MAXIP]); + else + range->max_addr.ip = range->min_addr.ip; + + return 0; +} + +static const struct nf_nat_l3proto nf_nat_l3proto_ipv4 = { + .l3proto = NFPROTO_IPV4, + .in_range = nf_nat_ipv4_in_range, + .secure_port = nf_nat_ipv4_secure_port, + .manip_pkt = nf_nat_ipv4_manip_pkt, + .csum_update = nf_nat_ipv4_csum_update, + .csum_recalc = nf_nat_ipv4_csum_recalc, + .nlattr_to_range = nf_nat_ipv4_nlattr_to_range, +#ifdef CONFIG_XFRM + .decode_session = nf_nat_ipv4_decode_session, +#endif +}; + +int nf_nat_icmp_reply_translation(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum) +{ + struct { + struct icmphdr icmp; + struct iphdr ip; + } *inside; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + enum nf_nat_manip_type manip = HOOK2MANIP(hooknum); + unsigned int hdrlen = ip_hdrlen(skb); + const struct nf_nat_l4proto *l4proto; + struct nf_conntrack_tuple target; + unsigned long statusbit; + + NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY); + + if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + return 0; + if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) + return 0; + + inside = (void *)skb->data + hdrlen; + if (inside->icmp.type == ICMP_REDIRECT) { + if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK) + return 0; + if (ct->status & IPS_NAT_MASK) + return 0; + } + + if (manip == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply direction */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + + l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, inside->ip.protocol); + if (!nf_nat_ipv4_manip_pkt(skb, hdrlen + sizeof(inside->icmp), + l4proto, &ct->tuplehash[!dir].tuple, !manip)) + return 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + /* Reloading "inside" here since manip_pkt may reallocate */ + inside = (void *)skb->data + hdrlen; + inside->icmp.checksum = 0; + inside->icmp.checksum = + csum_fold(skb_checksum(skb, hdrlen, + skb->len - hdrlen, 0)); + } + + /* Change outer to look like the reply to an incoming packet */ + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + l4proto = __nf_nat_l4proto_find(NFPROTO_IPV4, 0); + if (!nf_nat_ipv4_manip_pkt(skb, 0, l4proto, &target, manip)) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); + +static int __init nf_nat_l3proto_ipv4_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_icmp); + if (err < 0) + goto err1; + err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv4); + if (err < 0) + goto err2; + return err; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp); +err1: + return err; +} + +static void __exit nf_nat_l3proto_ipv4_exit(void) +{ + nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv4); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_icmp); +} + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("nf-nat-" __stringify(AF_INET)); + +module_init(nf_nat_l3proto_ipv4_init); +module_exit(nf_nat_l3proto_ipv4_exit); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 31ef890d894b..a06d7d74817d 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -22,7 +22,6 @@ #include #include -#include #include #include #include @@ -47,7 +46,7 @@ static void pptp_nat_expected(struct nf_conn *ct, struct nf_conntrack_tuple t; const struct nf_ct_pptp_master *ct_pptp_info; const struct nf_nat_pptp *nat_pptp_info; - struct nf_nat_ipv4_range range; + struct nf_nat_range range; ct_pptp_info = nfct_help_data(master); nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info; @@ -89,21 +88,21 @@ static void pptp_nat_expected(struct nf_conn *ct, /* Change src to where master sends to */ range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_ip = range.max_ip - = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; if (exp->dir == IP_CT_DIR_ORIGINAL) { range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - range.min = range.max = exp->saved_proto; + range.min_proto = range.max_proto = exp->saved_proto; } nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_ip = range.max_ip - = ct->master->tuplehash[!exp->dir].tuple.src.u3.ip; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.src.u3; if (exp->dir == IP_CT_DIR_REPLY) { range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - range.min = range.max = exp->saved_proto; + range.min_proto = range.max_proto = exp->saved_proto; } nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); } diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c deleted file mode 100644 index 9993bc93e102..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ /dev/null @@ -1,114 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * (C) 2008 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include - -bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype, - const union nf_conntrack_man_proto *min, - const union nf_conntrack_man_proto *max) -{ - __be16 port; - - if (maniptype == NF_NAT_MANIP_SRC) - port = tuple->src.u.all; - else - port = tuple->dst.u.all; - - return ntohs(port) >= ntohs(min->all) && - ntohs(port) <= ntohs(max->all); -} -EXPORT_SYMBOL_GPL(nf_nat_proto_in_range); - -void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct, - u_int16_t *rover) -{ - unsigned int range_size, min, i; - __be16 *portptr; - u_int16_t off; - - if (maniptype == NF_NAT_MANIP_SRC) - portptr = &tuple->src.u.all; - else - portptr = &tuple->dst.u.all; - - /* If no range specified... */ - if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { - /* If it's dst rewrite, can't change port */ - if (maniptype == NF_NAT_MANIP_DST) - return; - - if (ntohs(*portptr) < 1024) { - /* Loose convention: >> 512 is credential passing */ - if (ntohs(*portptr) < 512) { - min = 1; - range_size = 511 - min + 1; - } else { - min = 600; - range_size = 1023 - min + 1; - } - } else { - min = 1024; - range_size = 65535 - 1024 + 1; - } - } else { - min = ntohs(range->min.all); - range_size = ntohs(range->max.all) - min + 1; - } - - if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) - off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip, - maniptype == NF_NAT_MANIP_SRC - ? tuple->dst.u.all - : tuple->src.u.all); - else - off = *rover; - - for (i = 0; ; ++off) { - *portptr = htons(min + off % range_size); - if (++i != range_size && nf_nat_used_tuple(tuple, ct)) - continue; - if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) - *rover = off; - return; - } - return; -} -EXPORT_SYMBOL_GPL(nf_nat_proto_unique_tuple); - -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) -int nf_nat_proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_ipv4_range *range) -{ - if (tb[CTA_PROTONAT_PORT_MIN]) { - range->min.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); - range->max.all = range->min.tcp.port; - range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - } - if (tb[CTA_PROTONAT_PORT_MAX]) { - range->max.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]); - range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; - } - return 0; -} -EXPORT_SYMBOL_GPL(nf_nat_proto_nlattr_to_range); -#endif diff --git a/net/ipv4/netfilter/nf_nat_proto_dccp.c b/net/ipv4/netfilter/nf_nat_proto_dccp.c deleted file mode 100644 index 3f67138d187c..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_dccp.c +++ /dev/null @@ -1,106 +0,0 @@ -/* - * DCCP NAT protocol helper - * - * Copyright (c) 2005, 2006. 2008 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include - -static u_int16_t dccp_port_rover; - -static void -dccp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, - &dccp_port_rover); -} - -static bool -dccp_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - const struct iphdr *iph = (const void *)(skb->data + iphdroff); - struct dccp_hdr *hdr; - unsigned int hdroff = iphdroff + iph->ihl * 4; - __be32 oldip, newip; - __be16 *portptr, oldport, newport; - int hdrsize = 8; /* DCCP connection tracking guarantees this much */ - - if (skb->len >= hdroff + sizeof(struct dccp_hdr)) - hdrsize = sizeof(struct dccp_hdr); - - if (!skb_make_writable(skb, hdroff + hdrsize)) - return false; - - iph = (struct iphdr *)(skb->data + iphdroff); - hdr = (struct dccp_hdr *)(skb->data + hdroff); - - if (maniptype == NF_NAT_MANIP_SRC) { - oldip = iph->saddr; - newip = tuple->src.u3.ip; - newport = tuple->src.u.dccp.port; - portptr = &hdr->dccph_sport; - } else { - oldip = iph->daddr; - newip = tuple->dst.u3.ip; - newport = tuple->dst.u.dccp.port; - portptr = &hdr->dccph_dport; - } - - oldport = *portptr; - *portptr = newport; - - if (hdrsize < sizeof(*hdr)) - return true; - - inet_proto_csum_replace4(&hdr->dccph_checksum, skb, oldip, newip, 1); - inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, - 0); - return true; -} - -static const struct nf_nat_protocol nf_nat_protocol_dccp = { - .protonum = IPPROTO_DCCP, - .manip_pkt = dccp_manip_pkt, - .in_range = nf_nat_proto_in_range, - .unique_tuple = dccp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, -#endif -}; - -static int __init nf_nat_proto_dccp_init(void) -{ - return nf_nat_protocol_register(&nf_nat_protocol_dccp); -} - -static void __exit nf_nat_proto_dccp_fini(void) -{ - nf_nat_protocol_unregister(&nf_nat_protocol_dccp); -} - -module_init(nf_nat_proto_dccp_init); -module_exit(nf_nat_proto_dccp_fini); - -MODULE_AUTHOR("Patrick McHardy "); -MODULE_DESCRIPTION("DCCP NAT protocol helper"); -MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index 46ba0b9ab985..ea44f02563b5 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -28,8 +28,7 @@ #include #include -#include -#include +#include #include MODULE_LICENSE("GPL"); @@ -38,8 +37,9 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE"); /* generate unique tuple ... */ static void -gre_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, +gre_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -62,8 +62,8 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple, min = 1; range_size = 0xffff; } else { - min = ntohs(range->min.gre.key); - range_size = ntohs(range->max.gre.key) - min + 1; + min = ntohs(range->min_proto.gre.key); + range_size = ntohs(range->max_proto.gre.key) - min + 1; } pr_debug("min = %u, range_size = %u\n", min, range_size); @@ -80,14 +80,14 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple, /* manipulate a GRE packet according to maniptype */ static bool -gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, +gre_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { const struct gre_hdr *greh; struct gre_hdr_pptp *pgreh; - const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); - unsigned int hdroff = iphdroff + iph->ihl * 4; /* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ @@ -117,24 +117,24 @@ gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, return true; } -static const struct nf_nat_protocol gre = { - .protonum = IPPROTO_GRE, +static const struct nf_nat_l4proto gre = { + .l4proto = IPPROTO_GRE, .manip_pkt = gre_manip_pkt, - .in_range = nf_nat_proto_in_range, + .in_range = nf_nat_l4proto_in_range, .unique_tuple = gre_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; static int __init nf_nat_proto_gre_init(void) { - return nf_nat_protocol_register(&gre); + return nf_nat_l4proto_register(NFPROTO_IPV4, &gre); } static void __exit nf_nat_proto_gre_fini(void) { - nf_nat_protocol_unregister(&gre); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &gre); } module_init(nf_nat_proto_gre_init); diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index b35172851bae..eb303471bcf6 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -15,8 +15,7 @@ #include #include #include -#include -#include +#include static bool icmp_in_range(const struct nf_conntrack_tuple *tuple, @@ -29,8 +28,9 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple, } static void -icmp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, +icmp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -38,13 +38,14 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple, unsigned int range_size; unsigned int i; - range_size = ntohs(range->max.icmp.id) - ntohs(range->min.icmp.id) + 1; + range_size = ntohs(range->max_proto.icmp.id) - + ntohs(range->min_proto.icmp.id) + 1; /* If no range specified... */ if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) range_size = 0xFFFF; for (i = 0; ; ++id) { - tuple->src.u.icmp.id = htons(ntohs(range->min.icmp.id) + + tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) + (id % range_size)); if (++i == range_size || !nf_nat_used_tuple(tuple, ct)) return; @@ -54,13 +55,12 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple, static bool icmp_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { - const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); struct icmphdr *hdr; - unsigned int hdroff = iphdroff + iph->ihl*4; if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) return false; @@ -72,12 +72,12 @@ icmp_manip_pkt(struct sk_buff *skb, return true; } -const struct nf_nat_protocol nf_nat_protocol_icmp = { - .protonum = IPPROTO_ICMP, +const struct nf_nat_l4proto nf_nat_l4proto_icmp = { + .l4proto = IPPROTO_ICMP, .manip_pkt = icmp_manip_pkt, .in_range = icmp_in_range, .unique_tuple = icmp_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_sctp.c b/net/ipv4/netfilter/nf_nat_proto_sctp.c deleted file mode 100644 index 3cce9b6c1c29..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_sctp.c +++ /dev/null @@ -1,96 +0,0 @@ -/* - * Copyright (c) 2008 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include - -#include - -static u_int16_t nf_sctp_port_rover; - -static void -sctp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, - &nf_sctp_port_rover); -} - -static bool -sctp_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); - struct sk_buff *frag; - sctp_sctphdr_t *hdr; - unsigned int hdroff = iphdroff + iph->ihl*4; - __be32 oldip, newip; - __be32 crc32; - - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) - return false; - - iph = (struct iphdr *)(skb->data + iphdroff); - hdr = (struct sctphdr *)(skb->data + hdroff); - - if (maniptype == NF_NAT_MANIP_SRC) { - /* Get rid of src ip and src pt */ - oldip = iph->saddr; - newip = tuple->src.u3.ip; - hdr->source = tuple->src.u.sctp.port; - } else { - /* Get rid of dst ip and dst pt */ - oldip = iph->daddr; - newip = tuple->dst.u3.ip; - hdr->dest = tuple->dst.u.sctp.port; - } - - crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); - skb_walk_frags(skb, frag) - crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), - crc32); - crc32 = sctp_end_cksum(crc32); - hdr->checksum = crc32; - - return true; -} - -static const struct nf_nat_protocol nf_nat_protocol_sctp = { - .protonum = IPPROTO_SCTP, - .manip_pkt = sctp_manip_pkt, - .in_range = nf_nat_proto_in_range, - .unique_tuple = sctp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, -#endif -}; - -static int __init nf_nat_proto_sctp_init(void) -{ - return nf_nat_protocol_register(&nf_nat_protocol_sctp); -} - -static void __exit nf_nat_proto_sctp_exit(void) -{ - nf_nat_protocol_unregister(&nf_nat_protocol_sctp); -} - -module_init(nf_nat_proto_sctp_init); -module_exit(nf_nat_proto_sctp_exit); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("SCTP NAT protocol helper"); -MODULE_AUTHOR("Patrick McHardy "); diff --git a/net/ipv4/netfilter/nf_nat_proto_tcp.c b/net/ipv4/netfilter/nf_nat_proto_tcp.c deleted file mode 100644 index 9fb4b4e72bbf..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_tcp.c +++ /dev/null @@ -1,91 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include - -static u_int16_t tcp_port_rover; - -static void -tcp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, &tcp_port_rover); -} - -static bool -tcp_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); - struct tcphdr *hdr; - unsigned int hdroff = iphdroff + iph->ihl*4; - __be32 oldip, newip; - __be16 *portptr, newport, oldport; - int hdrsize = 8; /* TCP connection tracking guarantees this much */ - - /* this could be a inner header returned in icmp packet; in such - cases we cannot update the checksum field since it is outside of - the 8 bytes of transport layer headers we are guaranteed */ - if (skb->len >= hdroff + sizeof(struct tcphdr)) - hdrsize = sizeof(struct tcphdr); - - if (!skb_make_writable(skb, hdroff + hdrsize)) - return false; - - iph = (struct iphdr *)(skb->data + iphdroff); - hdr = (struct tcphdr *)(skb->data + hdroff); - - if (maniptype == NF_NAT_MANIP_SRC) { - /* Get rid of src ip and src pt */ - oldip = iph->saddr; - newip = tuple->src.u3.ip; - newport = tuple->src.u.tcp.port; - portptr = &hdr->source; - } else { - /* Get rid of dst ip and dst pt */ - oldip = iph->daddr; - newip = tuple->dst.u3.ip; - newport = tuple->dst.u.tcp.port; - portptr = &hdr->dest; - } - - oldport = *portptr; - *portptr = newport; - - if (hdrsize < sizeof(*hdr)) - return true; - - inet_proto_csum_replace4(&hdr->check, skb, oldip, newip, 1); - inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0); - return true; -} - -const struct nf_nat_protocol nf_nat_protocol_tcp = { - .protonum = IPPROTO_TCP, - .manip_pkt = tcp_manip_pkt, - .in_range = nf_nat_proto_in_range, - .unique_tuple = tcp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, -#endif -}; diff --git a/net/ipv4/netfilter/nf_nat_proto_udp.c b/net/ipv4/netfilter/nf_nat_proto_udp.c deleted file mode 100644 index 9883336e628f..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_udp.c +++ /dev/null @@ -1,82 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -static u_int16_t udp_port_rover; - -static void -udp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, &udp_port_rover); -} - -static bool -udp_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); - struct udphdr *hdr; - unsigned int hdroff = iphdroff + iph->ihl*4; - __be32 oldip, newip; - __be16 *portptr, newport; - - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) - return false; - - iph = (struct iphdr *)(skb->data + iphdroff); - hdr = (struct udphdr *)(skb->data + hdroff); - - if (maniptype == NF_NAT_MANIP_SRC) { - /* Get rid of src ip and src pt */ - oldip = iph->saddr; - newip = tuple->src.u3.ip; - newport = tuple->src.u.udp.port; - portptr = &hdr->source; - } else { - /* Get rid of dst ip and dst pt */ - oldip = iph->daddr; - newip = tuple->dst.u3.ip; - newport = tuple->dst.u.udp.port; - portptr = &hdr->dest; - } - if (hdr->check || skb->ip_summed == CHECKSUM_PARTIAL) { - inet_proto_csum_replace4(&hdr->check, skb, oldip, newip, 1); - inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, - 0); - if (!hdr->check) - hdr->check = CSUM_MANGLED_0; - } - *portptr = newport; - return true; -} - -const struct nf_nat_protocol nf_nat_protocol_udp = { - .protonum = IPPROTO_UDP, - .manip_pkt = udp_manip_pkt, - .in_range = nf_nat_proto_in_range, - .unique_tuple = udp_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, -#endif -}; diff --git a/net/ipv4/netfilter/nf_nat_proto_udplite.c b/net/ipv4/netfilter/nf_nat_proto_udplite.c deleted file mode 100644 index d24d10a7beb2..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_udplite.c +++ /dev/null @@ -1,98 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * (C) 2008 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include - -#include -#include -#include -#include - -static u_int16_t udplite_port_rover; - -static void -udplite_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - nf_nat_proto_unique_tuple(tuple, range, maniptype, ct, - &udplite_port_rover); -} - -static bool -udplite_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - const struct iphdr *iph = (struct iphdr *)(skb->data + iphdroff); - struct udphdr *hdr; - unsigned int hdroff = iphdroff + iph->ihl*4; - __be32 oldip, newip; - __be16 *portptr, newport; - - if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) - return false; - - iph = (struct iphdr *)(skb->data + iphdroff); - hdr = (struct udphdr *)(skb->data + hdroff); - - if (maniptype == NF_NAT_MANIP_SRC) { - /* Get rid of src ip and src pt */ - oldip = iph->saddr; - newip = tuple->src.u3.ip; - newport = tuple->src.u.udp.port; - portptr = &hdr->source; - } else { - /* Get rid of dst ip and dst pt */ - oldip = iph->daddr; - newip = tuple->dst.u3.ip; - newport = tuple->dst.u.udp.port; - portptr = &hdr->dest; - } - - inet_proto_csum_replace4(&hdr->check, skb, oldip, newip, 1); - inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, 0); - if (!hdr->check) - hdr->check = CSUM_MANGLED_0; - - *portptr = newport; - return true; -} - -static const struct nf_nat_protocol nf_nat_protocol_udplite = { - .protonum = IPPROTO_UDPLITE, - .manip_pkt = udplite_manip_pkt, - .in_range = nf_nat_proto_in_range, - .unique_tuple = udplite_unique_tuple, -#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .nlattr_to_range = nf_nat_proto_nlattr_to_range, -#endif -}; - -static int __init nf_nat_proto_udplite_init(void) -{ - return nf_nat_protocol_register(&nf_nat_protocol_udplite); -} - -static void __exit nf_nat_proto_udplite_fini(void) -{ - nf_nat_protocol_unregister(&nf_nat_protocol_udplite); -} - -module_init(nf_nat_proto_udplite_init); -module_exit(nf_nat_proto_udplite_fini); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("UDP-Lite NAT protocol helper"); -MODULE_AUTHOR("Patrick McHardy "); diff --git a/net/ipv4/netfilter/nf_nat_proto_unknown.c b/net/ipv4/netfilter/nf_nat_proto_unknown.c deleted file mode 100644 index e0afe8112b1c..000000000000 --- a/net/ipv4/netfilter/nf_nat_proto_unknown.c +++ /dev/null @@ -1,52 +0,0 @@ -/* The "unknown" protocol. This is what is used for protocols we - * don't understand. It's returned by ip_ct_find_proto(). - */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include - -#include -#include -#include -#include - -static bool unknown_in_range(const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type manip_type, - const union nf_conntrack_man_proto *min, - const union nf_conntrack_man_proto *max) -{ - return true; -} - -static void unknown_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_ipv4_range *range, - enum nf_nat_manip_type maniptype, - const struct nf_conn *ct) -{ - /* Sorry: we can't help you; if it's not unique, we can't frob - anything. */ - return; -} - -static bool -unknown_manip_pkt(struct sk_buff *skb, - unsigned int iphdroff, - const struct nf_conntrack_tuple *tuple, - enum nf_nat_manip_type maniptype) -{ - return true; -} - -const struct nf_nat_protocol nf_nat_unknown_protocol = { - .manip_pkt = unknown_manip_pkt, - .in_range = unknown_in_range, - .unique_tuple = unknown_unique_tuple, -}; diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c deleted file mode 100644 index d2a9dc314e0e..000000000000 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ /dev/null @@ -1,214 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -/* Everything about the rules for NAT. */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include - -#define NAT_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \ - (1 << NF_INET_POST_ROUTING) | \ - (1 << NF_INET_LOCAL_OUT) | \ - (1 << NF_INET_LOCAL_IN)) - -static const struct xt_table nat_table = { - .name = "nat", - .valid_hooks = NAT_VALID_HOOKS, - .me = THIS_MODULE, - .af = NFPROTO_IPV4, -}; - -/* Source NAT */ -static unsigned int -ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - - NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING || - par->hooknum == NF_INET_LOCAL_IN); - - ct = nf_ct_get(skb, &ctinfo); - - /* Connection must be valid and new. */ - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED_REPLY)); - NF_CT_ASSERT(par->out != NULL); - - return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_SRC); -} - -static unsigned int -ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - - NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_LOCAL_OUT); - - ct = nf_ct_get(skb, &ctinfo); - - /* Connection must be valid and new. */ - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); - - return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_DST); -} - -static int ipt_snat_checkentry(const struct xt_tgchk_param *par) -{ - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - - /* Must be a valid range */ - if (mr->rangesize != 1) { - pr_info("SNAT: multiple ranges no longer supported\n"); - return -EINVAL; - } - return 0; -} - -static int ipt_dnat_checkentry(const struct xt_tgchk_param *par) -{ - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - - /* Must be a valid range */ - if (mr->rangesize != 1) { - pr_info("DNAT: multiple ranges no longer supported\n"); - return -EINVAL; - } - return 0; -} - -static unsigned int -alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) -{ - /* Force range to this IP; let proto decide mapping for - per-proto parts (hence not NF_NAT_RANGE_PROTO_SPECIFIED). - */ - struct nf_nat_ipv4_range range; - - range.flags = 0; - pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, - HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? - &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip : - &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); - - return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); -} - -int nf_nat_rule_find(struct sk_buff *skb, - unsigned int hooknum, - const struct net_device *in, - const struct net_device *out, - struct nf_conn *ct) -{ - struct net *net = nf_ct_net(ct); - int ret; - - ret = ipt_do_table(skb, hooknum, in, out, net->ipv4.nat_table); - - if (ret == NF_ACCEPT) { - if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum))) - /* NUL mapping */ - ret = alloc_null_binding(ct, hooknum); - } - return ret; -} - -static struct xt_target ipt_snat_reg __read_mostly = { - .name = "SNAT", - .target = ipt_snat_target, - .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), - .table = "nat", - .hooks = (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), - .checkentry = ipt_snat_checkentry, - .family = AF_INET, -}; - -static struct xt_target ipt_dnat_reg __read_mostly = { - .name = "DNAT", - .target = ipt_dnat_target, - .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), - .table = "nat", - .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT), - .checkentry = ipt_dnat_checkentry, - .family = AF_INET, -}; - -static int __net_init nf_nat_rule_net_init(struct net *net) -{ - struct ipt_replace *repl; - - repl = ipt_alloc_initial_table(&nat_table); - if (repl == NULL) - return -ENOMEM; - net->ipv4.nat_table = ipt_register_table(net, &nat_table, repl); - kfree(repl); - if (IS_ERR(net->ipv4.nat_table)) - return PTR_ERR(net->ipv4.nat_table); - return 0; -} - -static void __net_exit nf_nat_rule_net_exit(struct net *net) -{ - ipt_unregister_table(net, net->ipv4.nat_table); -} - -static struct pernet_operations nf_nat_rule_net_ops = { - .init = nf_nat_rule_net_init, - .exit = nf_nat_rule_net_exit, -}; - -int __init nf_nat_rule_init(void) -{ - int ret; - - ret = register_pernet_subsys(&nf_nat_rule_net_ops); - if (ret != 0) - goto out; - ret = xt_register_target(&ipt_snat_reg); - if (ret != 0) - goto unregister_table; - - ret = xt_register_target(&ipt_dnat_reg); - if (ret != 0) - goto unregister_snat; - - return ret; - - unregister_snat: - xt_unregister_target(&ipt_snat_reg); - unregister_table: - unregister_pernet_subsys(&nf_nat_rule_net_ops); - out: - return ret; -} - -void nf_nat_rule_cleanup(void) -{ - xt_unregister_target(&ipt_dnat_reg); - xt_unregister_target(&ipt_snat_reg); - unregister_pernet_subsys(&nf_nat_rule_net_ops); -} diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index df626af8413c..47a47186a791 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -19,7 +19,6 @@ #include #include -#include #include #include #include @@ -255,15 +254,15 @@ static void ip_nat_sip_seq_adjust(struct sk_buff *skb, s16 off) static void ip_nat_sip_expected(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_ipv4_range range; + struct nf_nat_range range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); /* For DST manip, map port here to where it's expected. */ range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); - range.min = range.max = exp->saved_proto; - range.min_ip = range.max_ip = exp->saved_ip; + range.min_proto = range.max_proto = exp->saved_proto; + range.min_addr = range.max_addr = exp->saved_addr; nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); /* Change src to where master sends to, but only if the connection @@ -271,8 +270,8 @@ static void ip_nat_sip_expected(struct nf_conn *ct, if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == ct->master->tuplehash[exp->dir].tuple.src.u3.ip) { range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_ip = range.max_ip - = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); } } @@ -307,7 +306,7 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, else port = ntohs(exp->tuple.dst.u.udp.port); - exp->saved_ip = exp->tuple.dst.u3.ip; + exp->saved_addr = exp->tuple.dst.u3; exp->tuple.dst.u3.ip = newip; exp->saved_proto.udp.port = exp->tuple.dst.u.udp.port; exp->dir = !dir; @@ -329,7 +328,7 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, if (port == 0) return NF_DROP; - if (exp->tuple.dst.u3.ip != exp->saved_ip || + if (exp->tuple.dst.u3.ip != exp->saved_addr.ip || exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { buflen = sprintf(buffer, "%pI4:%u", &newip, port); if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, @@ -485,13 +484,13 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, else rtp_addr->ip = ct->tuplehash[!dir].tuple.dst.u3.ip; - rtp_exp->saved_ip = rtp_exp->tuple.dst.u3.ip; + rtp_exp->saved_addr = rtp_exp->tuple.dst.u3; rtp_exp->tuple.dst.u3.ip = rtp_addr->ip; rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port; rtp_exp->dir = !dir; rtp_exp->expectfn = ip_nat_sip_expected; - rtcp_exp->saved_ip = rtcp_exp->tuple.dst.u3.ip; + rtcp_exp->saved_addr = rtcp_exp->tuple.dst.u3; rtcp_exp->tuple.dst.u3.ip = rtp_addr->ip; rtcp_exp->saved_proto.udp.port = rtcp_exp->tuple.dst.u.udp.port; rtcp_exp->dir = !dir; diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c deleted file mode 100644 index 3828a4229822..000000000000 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ /dev/null @@ -1,326 +0,0 @@ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#ifdef CONFIG_XFRM -static void nat_decode_session(struct sk_buff *skb, struct flowi *fl) -{ - struct flowi4 *fl4 = &fl->u.ip4; - const struct nf_conn *ct; - const struct nf_conntrack_tuple *t; - enum ip_conntrack_info ctinfo; - enum ip_conntrack_dir dir; - unsigned long statusbit; - - ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) - return; - dir = CTINFO2DIR(ctinfo); - t = &ct->tuplehash[dir].tuple; - - if (dir == IP_CT_DIR_ORIGINAL) - statusbit = IPS_DST_NAT; - else - statusbit = IPS_SRC_NAT; - - if (ct->status & statusbit) { - fl4->daddr = t->dst.u3.ip; - if (t->dst.protonum == IPPROTO_TCP || - t->dst.protonum == IPPROTO_UDP || - t->dst.protonum == IPPROTO_UDPLITE || - t->dst.protonum == IPPROTO_DCCP || - t->dst.protonum == IPPROTO_SCTP) - fl4->fl4_dport = t->dst.u.tcp.port; - } - - statusbit ^= IPS_NAT_MASK; - - if (ct->status & statusbit) { - fl4->saddr = t->src.u3.ip; - if (t->dst.protonum == IPPROTO_TCP || - t->dst.protonum == IPPROTO_UDP || - t->dst.protonum == IPPROTO_UDPLITE || - t->dst.protonum == IPPROTO_DCCP || - t->dst.protonum == IPPROTO_SCTP) - fl4->fl4_sport = t->src.u.tcp.port; - } -} -#endif - -static unsigned int -nf_nat_fn(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - struct nf_conn_nat *nat; - /* maniptype == SRC for postrouting. */ - enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum); - - /* We never see fragments: conntrack defrags on pre-routing - and local-out, and nf_nat_out protects post-routing. */ - NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb))); - - ct = nf_ct_get(skb, &ctinfo); - /* Can't track? It's not due to stress, or conntrack would - have dropped it. Hence it's the user's responsibilty to - packet filter it out, or implement conntrack/NAT for that - protocol. 8) --RR */ - if (!ct) - return NF_ACCEPT; - - /* Don't try to NAT if this packet is not conntracked */ - if (nf_ct_is_untracked(ct)) - return NF_ACCEPT; - - nat = nfct_nat(ct); - if (!nat) { - /* NAT module was loaded late. */ - if (nf_ct_is_confirmed(ct)) - return NF_ACCEPT; - nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); - if (nat == NULL) { - pr_debug("failed to add NAT extension\n"); - return NF_ACCEPT; - } - } - - switch (ctinfo) { - case IP_CT_RELATED: - case IP_CT_RELATED_REPLY: - if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { - if (!nf_nat_icmp_reply_translation(ct, ctinfo, - hooknum, skb)) - return NF_DROP; - else - return NF_ACCEPT; - } - /* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */ - case IP_CT_NEW: - - /* Seen it before? This can happen for loopback, retrans, - or local packets.. */ - if (!nf_nat_initialized(ct, maniptype)) { - unsigned int ret; - - ret = nf_nat_rule_find(skb, hooknum, in, out, ct); - if (ret != NF_ACCEPT) - return ret; - } else - pr_debug("Already setup manip %s for ct %p\n", - maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", - ct); - break; - - default: - /* ESTABLISHED */ - NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || - ctinfo == IP_CT_ESTABLISHED_REPLY); - } - - return nf_nat_packet(ct, ctinfo, hooknum, skb); -} - -static unsigned int -nf_nat_in(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - unsigned int ret; - __be32 daddr = ip_hdr(skb)->daddr; - - ret = nf_nat_fn(hooknum, skb, in, out, okfn); - if (ret != NF_DROP && ret != NF_STOLEN && - daddr != ip_hdr(skb)->daddr) - skb_dst_drop(skb); - - return ret; -} - -static unsigned int -nf_nat_out(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ -#ifdef CONFIG_XFRM - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; -#endif - unsigned int ret; - - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) - return NF_ACCEPT; - - ret = nf_nat_fn(hooknum, skb, in, out, okfn); -#ifdef CONFIG_XFRM - if (ret != NF_DROP && ret != NF_STOLEN && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if ((ct->tuplehash[dir].tuple.src.u3.ip != - ct->tuplehash[!dir].tuple.dst.u3.ip) || - (ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all) - ) - return ip_xfrm_me_harder(skb) == 0 ? ret : NF_DROP; - } -#endif - return ret; -} - -static unsigned int -nf_nat_local_fn(unsigned int hooknum, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - const struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - unsigned int ret; - - /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) || - ip_hdrlen(skb) < sizeof(struct iphdr)) - return NF_ACCEPT; - - ret = nf_nat_fn(hooknum, skb, in, out, okfn); - if (ret != NF_DROP && ret != NF_STOLEN && - (ct = nf_ct_get(skb, &ctinfo)) != NULL) { - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - - if (ct->tuplehash[dir].tuple.dst.u3.ip != - ct->tuplehash[!dir].tuple.src.u3.ip) { - if (ip_route_me_harder(skb, RTN_UNSPEC)) - ret = NF_DROP; - } -#ifdef CONFIG_XFRM - else if (ct->tuplehash[dir].tuple.dst.u.all != - ct->tuplehash[!dir].tuple.src.u.all) - if (ip_xfrm_me_harder(skb)) - ret = NF_DROP; -#endif - } - return ret; -} - -/* We must be after connection tracking and before packet filtering. */ - -static struct nf_hook_ops nf_nat_ops[] __read_mostly = { - /* Before packet filtering, change destination */ - { - .hook = nf_nat_in, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_PRE_ROUTING, - .priority = NF_IP_PRI_NAT_DST, - }, - /* After packet filtering, change source */ - { - .hook = nf_nat_out, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_NAT_SRC, - }, - /* Before packet filtering, change destination */ - { - .hook = nf_nat_local_fn, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_OUT, - .priority = NF_IP_PRI_NAT_DST, - }, - /* After packet filtering, change source */ - { - .hook = nf_nat_fn, - .owner = THIS_MODULE, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_NAT_SRC, - }, -}; - -static int __init nf_nat_standalone_init(void) -{ - int ret = 0; - - need_ipv4_conntrack(); - -#ifdef CONFIG_XFRM - BUG_ON(ip_nat_decode_session != NULL); - RCU_INIT_POINTER(ip_nat_decode_session, nat_decode_session); -#endif - ret = nf_nat_rule_init(); - if (ret < 0) { - pr_err("nf_nat_init: can't setup rules.\n"); - goto cleanup_decode_session; - } - ret = nf_register_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); - if (ret < 0) { - pr_err("nf_nat_init: can't register hooks.\n"); - goto cleanup_rule_init; - } - return ret; - - cleanup_rule_init: - nf_nat_rule_cleanup(); - cleanup_decode_session: -#ifdef CONFIG_XFRM - RCU_INIT_POINTER(ip_nat_decode_session, NULL); - synchronize_net(); -#endif - return ret; -} - -static void __exit nf_nat_standalone_fini(void) -{ - nf_unregister_hooks(nf_nat_ops, ARRAY_SIZE(nf_nat_ops)); - nf_nat_rule_cleanup(); -#ifdef CONFIG_XFRM - RCU_INIT_POINTER(ip_nat_decode_session, NULL); - synchronize_net(); -#endif - /* Conntrack caches are unregistered in nf_conntrack_cleanup */ -} - -module_init(nf_nat_standalone_init); -module_exit(nf_nat_standalone_fini); - -MODULE_LICENSE("GPL"); -MODULE_ALIAS("ip_nat"); diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c index 9dbb8d284f99..ccabbda71a3e 100644 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ b/net/ipv4/netfilter/nf_nat_tftp.c @@ -11,7 +11,6 @@ #include #include #include -#include #include MODULE_AUTHOR("Magnus Boden "); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index c19b214ffd57..91adddae20a4 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -356,6 +356,30 @@ config NETFILTER_NETLINK_QUEUE_CT If this option is enabled, NFQUEUE can include Connection Tracking information together with the packet is the enqueued via NFNETLINK. +config NF_NAT + tristate + +config NF_NAT_NEEDED + bool + depends on NF_NAT + default y + +config NF_NAT_PROTO_DCCP + tristate + depends on NF_NAT && NF_CT_PROTO_DCCP + default NF_NAT && NF_CT_PROTO_DCCP + +config NF_NAT_PROTO_UDPLITE + tristate + depends on NF_NAT && NF_CT_PROTO_UDPLITE + default NF_NAT && NF_CT_PROTO_UDPLITE + +config NF_NAT_PROTO_SCTP + tristate + default NF_NAT && NF_CT_PROTO_SCTP + depends on NF_NAT && NF_CT_PROTO_SCTP + select LIBCRC32C + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1c5160f2278e..09c9451bc510 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -43,6 +43,17 @@ obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o obj-$(CONFIG_NF_CONNTRACK_TFTP) += nf_conntrack_tftp.o +nf_nat-y := nf_nat_core.o nf_nat_proto_unknown.o nf_nat_proto_common.o \ + nf_nat_proto_udp.o nf_nat_proto_tcp.o nf_nat_helper.o + +obj-$(CONFIG_NF_NAT) += nf_nat.o +obj-$(CONFIG_NF_NAT) += xt_nat.o + +# NAT protocols (nf_nat) +obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o +obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o +obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o + # transparent proxy support obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8f4b0b2b6f80..e61b3ac9591b 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -275,6 +275,11 @@ EXPORT_SYMBOL_GPL(nfq_ct_nat_hook); #endif /* CONFIG_NF_CONNTRACK */ +#ifdef CONFIG_NF_NAT_NEEDED +void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *); +EXPORT_SYMBOL(nf_nat_decode_session_hook); +#endif + #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc_net_netfilter; EXPORT_SYMBOL(proc_net_netfilter); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index cf4875565d67..f83e79defed9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -55,6 +55,12 @@ int (*nfnetlink_parse_nat_setup_hook)(struct nf_conn *ct, const struct nlattr *attr) __read_mostly; EXPORT_SYMBOL_GPL(nfnetlink_parse_nat_setup_hook); +int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff); +EXPORT_SYMBOL_GPL(nf_nat_seq_adjust_hook); + DEFINE_SPINLOCK(nf_conntrack_lock); EXPORT_SYMBOL_GPL(nf_conntrack_lock); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index da4fc37a8578..966f5133a384 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -45,7 +45,7 @@ #include #ifdef CONFIG_NF_NAT_NEEDED #include -#include +#include #include #endif @@ -1096,13 +1096,14 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, const struct nlattr *attr) { typeof(nfnetlink_parse_nat_setup_hook) parse_nat_setup; + int err; parse_nat_setup = rcu_dereference(nfnetlink_parse_nat_setup_hook); if (!parse_nat_setup) { #ifdef CONFIG_MODULES rcu_read_unlock(); nfnl_unlock(); - if (request_module("nf-nat-ipv4") < 0) { + if (request_module("nf-nat") < 0) { nfnl_lock(); rcu_read_lock(); return -EOPNOTSUPP; @@ -1115,7 +1116,26 @@ ctnetlink_parse_nat_setup(struct nf_conn *ct, return -EOPNOTSUPP; } - return parse_nat_setup(ct, manip, attr); + err = parse_nat_setup(ct, manip, attr); + if (err == -EAGAIN) { +#ifdef CONFIG_MODULES + rcu_read_unlock(); + spin_unlock_bh(&nf_conntrack_lock); + nfnl_unlock(); + if (request_module("nf-nat-%u", nf_ct_l3num(ct)) < 0) { + nfnl_lock(); + spin_lock_bh(&nf_conntrack_lock); + rcu_read_lock(); + return -EOPNOTSUPP; + } + nfnl_lock(); + spin_lock_bh(&nf_conntrack_lock); + rcu_read_lock(); +#else + err = -EOPNOTSUPP; +#endif + } + return err; } #endif @@ -1979,6 +1999,8 @@ nla_put_failure: return -1; } +static const union nf_inet_addr any_addr; + static int ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) @@ -2005,7 +2027,8 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, goto nla_put_failure; #ifdef CONFIG_NF_NAT_NEEDED - if (exp->saved_ip || exp->saved_proto.all) { + if (!nf_inet_addr_cmp(&exp->saved_addr, &any_addr) || + exp->saved_proto.all) { nest_parms = nla_nest_start(skb, CTA_EXPECT_NAT | NLA_F_NESTED); if (!nest_parms) goto nla_put_failure; @@ -2014,7 +2037,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, goto nla_put_failure; nat_tuple.src.l3num = nf_ct_l3num(master); - nat_tuple.src.u3.ip = exp->saved_ip; + nat_tuple.src.u3 = exp->saved_addr; nat_tuple.dst.protonum = nf_ct_protonum(master); nat_tuple.src.u = exp->saved_proto; @@ -2410,7 +2433,7 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr, if (err < 0) return err; - exp->saved_ip = nat_tuple.src.u3.ip; + exp->saved_addr = nat_tuple.src.u3; exp->saved_proto = nat_tuple.src.u; exp->dir = ntohl(nla_get_be32(tb[CTA_EXPECT_NAT_DIR])); diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index a5ac11ebef33..9c2cc716f4a5 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -505,10 +505,10 @@ static inline s16 nat_offset(const struct nf_conn *ct, return get_offset != NULL ? get_offset(ct, dir, seq) : 0; } -#define NAT_OFFSET(pf, ct, dir, seq) \ - (pf == NFPROTO_IPV4 ? nat_offset(ct, dir, seq) : 0) +#define NAT_OFFSET(ct, dir, seq) \ + (nat_offset(ct, dir, seq)) #else -#define NAT_OFFSET(pf, ct, dir, seq) 0 +#define NAT_OFFSET(ct, dir, seq) 0 #endif static bool tcp_in_window(const struct nf_conn *ct, @@ -541,7 +541,7 @@ static bool tcp_in_window(const struct nf_conn *ct, tcp_sack(skb, dataoff, tcph, &sack); /* Take into account NAT sequence number mangling */ - receiver_offset = NAT_OFFSET(pf, ct, !dir, ack - 1); + receiver_offset = NAT_OFFSET(ct, !dir, ack - 1); ack -= receiver_offset; sack -= receiver_offset; diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 590f0abaab8c..d5174902db37 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -946,11 +946,11 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, break; #ifdef CONFIG_NF_NAT_NEEDED if (exp->tuple.src.l3num == AF_INET && !direct_rtp && - (exp->saved_ip != exp->tuple.dst.u3.ip || + (exp->saved_addr.ip != exp->tuple.dst.u3.ip || exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) && ct->status & IPS_NAT_MASK) { - daddr->ip = exp->saved_ip; - tuple.dst.u3.ip = exp->saved_ip; + daddr->ip = exp->saved_addr.ip; + tuple.dst.u3.ip = exp->saved_addr.ip; tuple.dst.u.udp.port = exp->saved_proto.udp.port; direct_rtp = 1; } else diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c new file mode 100644 index 000000000000..c577b753fb9a --- /dev/null +++ b/net/netfilter/nf_nat_core.c @@ -0,0 +1,854 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * (C) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_SPINLOCK(nf_nat_lock); + +static DEFINE_MUTEX(nf_nat_proto_mutex); +static const struct nf_nat_l3proto __rcu *nf_nat_l3protos[NFPROTO_NUMPROTO] + __read_mostly; +static const struct nf_nat_l4proto __rcu **nf_nat_l4protos[NFPROTO_NUMPROTO] + __read_mostly; + + +inline const struct nf_nat_l3proto * +__nf_nat_l3proto_find(u8 family) +{ + return rcu_dereference(nf_nat_l3protos[family]); +} + +inline const struct nf_nat_l4proto * +__nf_nat_l4proto_find(u8 family, u8 protonum) +{ + return rcu_dereference(nf_nat_l4protos[family][protonum]); +} +EXPORT_SYMBOL_GPL(__nf_nat_l4proto_find); + +#ifdef CONFIG_XFRM +static void __nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + enum ip_conntrack_dir dir; + unsigned long statusbit; + u8 family; + + ct = nf_ct_get(skb, &ctinfo); + if (ct == NULL) + return; + + family = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(family); + if (l3proto == NULL) + goto out; + + dir = CTINFO2DIR(ctinfo); + if (dir == IP_CT_DIR_ORIGINAL) + statusbit = IPS_DST_NAT; + else + statusbit = IPS_SRC_NAT; + + l3proto->decode_session(skb, ct, dir, statusbit, fl); +out: + rcu_read_unlock(); +} + +int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) +{ + struct flowi fl; + unsigned int hh_len; + struct dst_entry *dst; + + if (xfrm_decode_session(skb, &fl, family) < 0) + return -1; + + dst = skb_dst(skb); + if (dst->xfrm) + dst = ((struct xfrm_dst *)dst)->route; + dst_hold(dst); + + dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); + if (IS_ERR(dst)) + return -1; + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + /* Change in oif may mean change in hh_len. */ + hh_len = skb_dst(skb)->dev->hard_header_len; + if (skb_headroom(skb) < hh_len && + pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + return -1; + return 0; +} +EXPORT_SYMBOL(nf_xfrm_me_harder); +#endif /* CONFIG_XFRM */ + +/* We keep an extra hash for each conntrack, for fast searching. */ +static inline unsigned int +hash_by_src(const struct net *net, u16 zone, + const struct nf_conntrack_tuple *tuple) +{ + unsigned int hash; + + /* Original src, to ensure we map it consistently if poss. */ + hash = jhash2((u32 *)&tuple->src, sizeof(tuple->src) / sizeof(u32), + tuple->dst.protonum ^ zone ^ nf_conntrack_hash_rnd); + return ((u64)hash * net->ct.nat_htable_size) >> 32; +} + +/* Is this tuple already taken? (not by us) */ +int +nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, + const struct nf_conn *ignored_conntrack) +{ + /* Conntrack tracking doesn't keep track of outgoing tuples; only + * incoming ones. NAT means they don't have a fixed mapping, + * so we invert the tuple and look for the incoming reply. + * + * We could keep a separate hash if this proves too slow. + */ + struct nf_conntrack_tuple reply; + + nf_ct_invert_tuplepr(&reply, tuple); + return nf_conntrack_tuple_taken(&reply, ignored_conntrack); +} +EXPORT_SYMBOL(nf_nat_used_tuple); + +/* If we source map this tuple so reply looks like reply_tuple, will + * that meet the constraints of range. + */ +static int in_range(const struct nf_nat_l3proto *l3proto, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range) +{ + /* If we are supposed to map IPs, then we must be in the + * range specified, otherwise let this drag us onto a new src IP. + */ + if (range->flags & NF_NAT_RANGE_MAP_IPS && + !l3proto->in_range(tuple, range)) + return 0; + + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) || + l4proto->in_range(tuple, NF_NAT_MANIP_SRC, + &range->min_proto, &range->max_proto)) + return 1; + + return 0; +} + +static inline int +same_src(const struct nf_conn *ct, + const struct nf_conntrack_tuple *tuple) +{ + const struct nf_conntrack_tuple *t; + + t = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + return (t->dst.protonum == tuple->dst.protonum && + nf_inet_addr_cmp(&t->src.u3, &tuple->src.u3) && + t->src.u.all == tuple->src.u.all); +} + +/* Only called for SRC manip */ +static int +find_appropriate_src(struct net *net, u16 zone, + const struct nf_nat_l3proto *l3proto, + const struct nf_nat_l4proto *l4proto, + const struct nf_conntrack_tuple *tuple, + struct nf_conntrack_tuple *result, + const struct nf_nat_range *range) +{ + unsigned int h = hash_by_src(net, zone, tuple); + const struct nf_conn_nat *nat; + const struct nf_conn *ct; + const struct hlist_node *n; + + hlist_for_each_entry_rcu(nat, n, &net->ct.nat_bysource[h], bysource) { + ct = nat->ct; + if (same_src(ct, tuple) && nf_ct_zone(ct) == zone) { + /* Copy source part from reply tuple. */ + nf_ct_invert_tuplepr(result, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + result->dst = tuple->dst; + + if (in_range(l3proto, l4proto, result, range)) { + rcu_read_unlock(); + return 1; + } + } + } + return 0; +} + +/* For [FUTURE] fragmentation handling, we want the least-used + * src-ip/dst-ip/proto triple. Fairness doesn't come into it. Thus + * if the range specifies 1.2.3.4 ports 10000-10005 and 1.2.3.5 ports + * 1-65535, we don't do pro-rata allocation based on ports; we choose + * the ip with the lowest src-ip/dst-ip/proto usage. + */ +static void +find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + const struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + union nf_inet_addr *var_ipp; + unsigned int i, max; + /* Host order */ + u32 minip, maxip, j, dist; + bool full_range; + + /* No IP mapping? Do nothing. */ + if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) + return; + + if (maniptype == NF_NAT_MANIP_SRC) + var_ipp = &tuple->src.u3; + else + var_ipp = &tuple->dst.u3; + + /* Fast path: only one choice. */ + if (nf_inet_addr_cmp(&range->min_addr, &range->max_addr)) { + *var_ipp = range->min_addr; + return; + } + + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + max = sizeof(var_ipp->ip) / sizeof(u32) - 1; + else + max = sizeof(var_ipp->ip6) / sizeof(u32) - 1; + + /* Hashing source and destination IPs gives a fairly even + * spread in practice (if there are a small number of IPs + * involved, there usually aren't that many connections + * anyway). The consistency means that servers see the same + * client coming from the same IP (some Internet Banking sites + * like this), even across reboots. + */ + j = jhash2((u32 *)&tuple->src.u3, sizeof(tuple->src.u3), + range->flags & NF_NAT_RANGE_PERSISTENT ? + 0 : (__force u32)tuple->dst.u3.all[max] ^ zone); + + full_range = false; + for (i = 0; i <= max; i++) { + /* If first bytes of the address are at the maximum, use the + * distance. Otherwise use the full range. + */ + if (!full_range) { + minip = ntohl((__force __be32)range->min_addr.all[i]); + maxip = ntohl((__force __be32)range->max_addr.all[i]); + dist = maxip - minip + 1; + } else { + minip = 0; + dist = ~0; + } + + var_ipp->all[i] = (__force __u32) + htonl(minip + (((u64)j * dist) >> 32)); + if (var_ipp->all[i] != range->max_addr.all[i]) + full_range = true; + + if (!(range->flags & NF_NAT_RANGE_PERSISTENT)) + j ^= (__force u32)tuple->dst.u3.all[i]; + } +} + +/* Manipulate the tuple into the range given. For NF_INET_POST_ROUTING, + * we change the source to map into the range. For NF_INET_PRE_ROUTING + * and NF_INET_LOCAL_OUT, we change the destination to map into the + * range. It might not be possible to get a unique tuple, but we try. + * At worst (or if we race), we will end up with a final duplicate in + * __ip_conntrack_confirm and drop the packet. */ +static void +get_unique_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig_tuple, + const struct nf_nat_range *range, + struct nf_conn *ct, + enum nf_nat_manip_type maniptype) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + struct net *net = nf_ct_net(ct); + u16 zone = nf_ct_zone(ct); + + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(orig_tuple->src.l3num); + l4proto = __nf_nat_l4proto_find(orig_tuple->src.l3num, + orig_tuple->dst.protonum); + + /* 1) If this srcip/proto/src-proto-part is currently mapped, + * and that same mapping gives a unique tuple within the given + * range, use that. + * + * This is only required for source (ie. NAT/masq) mappings. + * So far, we don't do local source mappings, so multiple + * manips not an issue. + */ + if (maniptype == NF_NAT_MANIP_SRC && + !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + /* try the original tuple first */ + if (in_range(l3proto, l4proto, orig_tuple, range)) { + if (!nf_nat_used_tuple(orig_tuple, ct)) { + *tuple = *orig_tuple; + goto out; + } + } else if (find_appropriate_src(net, zone, l3proto, l4proto, + orig_tuple, tuple, range)) { + pr_debug("get_unique_tuple: Found current src map\n"); + if (!nf_nat_used_tuple(tuple, ct)) + goto out; + } + } + + /* 2) Select the least-used IP/proto combination in the given range */ + *tuple = *orig_tuple; + find_best_ips_proto(zone, tuple, range, ct, maniptype); + + /* 3) The per-protocol part of the manip is made to map into + * the range to make a unique tuple. + */ + + /* Only bother mapping if it's not already in range and unique */ + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { + if (l4proto->in_range(tuple, maniptype, + &range->min_proto, + &range->max_proto) && + (range->min_proto.all == range->max_proto.all || + !nf_nat_used_tuple(tuple, ct))) + goto out; + } else if (!nf_nat_used_tuple(tuple, ct)) { + goto out; + } + } + + /* Last change: get protocol to try to obtain unique tuple. */ + l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct); +out: + rcu_read_unlock(); +} + +unsigned int +nf_nat_setup_info(struct nf_conn *ct, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype) +{ + struct net *net = nf_ct_net(ct); + struct nf_conntrack_tuple curr_tuple, new_tuple; + struct nf_conn_nat *nat; + + /* nat helper or nfctnetlink also setup binding */ + nat = nfct_nat(ct); + if (!nat) { + nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC); + if (nat == NULL) { + pr_debug("failed to add NAT extension\n"); + return NF_ACCEPT; + } + } + + NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || + maniptype == NF_NAT_MANIP_DST); + BUG_ON(nf_nat_initialized(ct, maniptype)); + + /* What we've got will look like inverse of reply. Normally + * this is what is in the conntrack, except for prior + * manipulations (future optimization: if num_manips == 0, + * orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) + */ + nf_ct_invert_tuplepr(&curr_tuple, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + + get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); + + if (!nf_ct_tuple_equal(&new_tuple, &curr_tuple)) { + struct nf_conntrack_tuple reply; + + /* Alter conntrack table so will recognize replies. */ + nf_ct_invert_tuplepr(&reply, &new_tuple); + nf_conntrack_alter_reply(ct, &reply); + + /* Non-atomic: we own this at the moment. */ + if (maniptype == NF_NAT_MANIP_SRC) + ct->status |= IPS_SRC_NAT; + else + ct->status |= IPS_DST_NAT; + } + + if (maniptype == NF_NAT_MANIP_SRC) { + unsigned int srchash; + + srchash = hash_by_src(net, nf_ct_zone(ct), + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); + spin_lock_bh(&nf_nat_lock); + /* nf_conntrack_alter_reply might re-allocate extension aera */ + nat = nfct_nat(ct); + nat->ct = ct; + hlist_add_head_rcu(&nat->bysource, + &net->ct.nat_bysource[srchash]); + spin_unlock_bh(&nf_nat_lock); + } + + /* It's done. */ + if (maniptype == NF_NAT_MANIP_DST) + ct->status |= IPS_DST_NAT_DONE; + else + ct->status |= IPS_SRC_NAT_DONE; + + return NF_ACCEPT; +} +EXPORT_SYMBOL(nf_nat_setup_info); + +/* Do packet manipulations according to nf_nat_setup_info. */ +unsigned int nf_nat_packet(struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int hooknum, + struct sk_buff *skb) +{ + const struct nf_nat_l3proto *l3proto; + const struct nf_nat_l4proto *l4proto; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned long statusbit; + enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); + + if (mtype == NF_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + /* Non-atomic: these bits don't change. */ + if (ct->status & statusbit) { + struct nf_conntrack_tuple target; + + /* We are aiming to look like inverse of other direction. */ + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + + l3proto = __nf_nat_l3proto_find(target.src.l3num); + l4proto = __nf_nat_l4proto_find(target.src.l3num, + target.dst.protonum); + if (!l3proto->manip_pkt(skb, 0, l4proto, &target, mtype)) + return NF_DROP; + } + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_nat_packet); + +struct nf_nat_proto_clean { + u8 l3proto; + u8 l4proto; + bool hash; +}; + +/* Clear NAT section of all conntracks, in case we're loaded again. */ +static int nf_nat_proto_clean(struct nf_conn *i, void *data) +{ + const struct nf_nat_proto_clean *clean = data; + struct nf_conn_nat *nat = nfct_nat(i); + + if (!nat) + return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || + (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) + return 0; + + if (clean->hash) { + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + spin_unlock_bh(&nf_nat_lock); + } else { + memset(nat, 0, sizeof(*nat)); + i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | + IPS_SEQ_ADJUST); + } + return 0; +} + +static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) +{ + struct nf_nat_proto_clean clean = { + .l3proto = l3proto, + .l4proto = l4proto, + }; + struct net *net; + + rtnl_lock(); + /* Step 1 - remove from bysource hash */ + clean.hash = true; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + synchronize_rcu(); + + /* Step 2 - clean NAT section */ + clean.hash = false; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + rtnl_unlock(); +} + +static void nf_nat_l3proto_clean(u8 l3proto) +{ + struct nf_nat_proto_clean clean = { + .l3proto = l3proto, + }; + struct net *net; + + rtnl_lock(); + /* Step 1 - remove from bysource hash */ + clean.hash = true; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + synchronize_rcu(); + + /* Step 2 - clean NAT section */ + clean.hash = false; + for_each_net(net) + nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + rtnl_unlock(); +} + +/* Protocol registration. */ +int nf_nat_l4proto_register(u8 l3proto, const struct nf_nat_l4proto *l4proto) +{ + const struct nf_nat_l4proto **l4protos; + unsigned int i; + int ret = 0; + + mutex_lock(&nf_nat_proto_mutex); + if (nf_nat_l4protos[l3proto] == NULL) { + l4protos = kmalloc(IPPROTO_MAX * sizeof(struct nf_nat_l4proto *), + GFP_KERNEL); + if (l4protos == NULL) { + ret = -ENOMEM; + goto out; + } + + for (i = 0; i < IPPROTO_MAX; i++) + RCU_INIT_POINTER(l4protos[i], &nf_nat_l4proto_unknown); + + /* Before making proto_array visible to lockless readers, + * we must make sure its content is committed to memory. + */ + smp_wmb(); + + nf_nat_l4protos[l3proto] = l4protos; + } + + if (rcu_dereference_protected( + nf_nat_l4protos[l3proto][l4proto->l4proto], + lockdep_is_held(&nf_nat_proto_mutex) + ) != &nf_nat_l4proto_unknown) { + ret = -EBUSY; + goto out; + } + RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], l4proto); + out: + mutex_unlock(&nf_nat_proto_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_register); + +/* No one stores the protocol anywhere; simply delete it. */ +void nf_nat_l4proto_unregister(u8 l3proto, const struct nf_nat_l4proto *l4proto) +{ + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto][l4proto->l4proto], + &nf_nat_l4proto_unknown); + mutex_unlock(&nf_nat_proto_mutex); + synchronize_rcu(); + + nf_nat_l4proto_clean(l3proto, l4proto->l4proto); +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister); + +int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto) +{ + int err; + + err = nf_ct_l3proto_try_module_get(l3proto->l3proto); + if (err < 0) + return err; + + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP], + &nf_nat_l4proto_tcp); + RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_UDP], + &nf_nat_l4proto_udp); + mutex_unlock(&nf_nat_proto_mutex); + + RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], l3proto); + return 0; +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_register); + +void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto) +{ + mutex_lock(&nf_nat_proto_mutex); + RCU_INIT_POINTER(nf_nat_l3protos[l3proto->l3proto], NULL); + mutex_unlock(&nf_nat_proto_mutex); + synchronize_rcu(); + + nf_nat_l3proto_clean(l3proto->l3proto); + nf_ct_l3proto_module_put(l3proto->l3proto); +} +EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister); + +/* No one using conntrack by the time this called. */ +static void nf_nat_cleanup_conntrack(struct nf_conn *ct) +{ + struct nf_conn_nat *nat = nf_ct_ext_find(ct, NF_CT_EXT_NAT); + + if (nat == NULL || nat->ct == NULL) + return; + + NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); + + spin_lock_bh(&nf_nat_lock); + hlist_del_rcu(&nat->bysource); + spin_unlock_bh(&nf_nat_lock); +} + +static void nf_nat_move_storage(void *new, void *old) +{ + struct nf_conn_nat *new_nat = new; + struct nf_conn_nat *old_nat = old; + struct nf_conn *ct = old_nat->ct; + + if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) + return; + + spin_lock_bh(&nf_nat_lock); + hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); + spin_unlock_bh(&nf_nat_lock); +} + +static struct nf_ct_ext_type nat_extend __read_mostly = { + .len = sizeof(struct nf_conn_nat), + .align = __alignof__(struct nf_conn_nat), + .destroy = nf_nat_cleanup_conntrack, + .move = nf_nat_move_storage, + .id = NF_CT_EXT_NAT, + .flags = NF_CT_EXT_F_PREALLOC, +}; + +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + +#include +#include + +static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { + [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, + [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, +}; + +static int nfnetlink_parse_nat_proto(struct nlattr *attr, + const struct nf_conn *ct, + struct nf_nat_range *range) +{ + struct nlattr *tb[CTA_PROTONAT_MAX+1]; + const struct nf_nat_l4proto *l4proto; + int err; + + err = nla_parse_nested(tb, CTA_PROTONAT_MAX, attr, protonat_nla_policy); + if (err < 0) + return err; + + l4proto = __nf_nat_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct)); + if (l4proto->nlattr_to_range) + err = l4proto->nlattr_to_range(tb, range); + + return err; +} + +static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { + [CTA_NAT_V4_MINIP] = { .type = NLA_U32 }, + [CTA_NAT_V4_MAXIP] = { .type = NLA_U32 }, + [CTA_NAT_PROTO] = { .type = NLA_NESTED }, +}; + +static int +nfnetlink_parse_nat(const struct nlattr *nat, + const struct nf_conn *ct, struct nf_nat_range *range) +{ + const struct nf_nat_l3proto *l3proto; + struct nlattr *tb[CTA_NAT_MAX+1]; + int err; + + memset(range, 0, sizeof(*range)); + + err = nla_parse_nested(tb, CTA_NAT_MAX, nat, nat_nla_policy); + if (err < 0) + return err; + + rcu_read_lock(); + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) { + err = -EAGAIN; + goto out; + } + err = l3proto->nlattr_to_range(tb, range); + if (err < 0) + goto out; + + if (!tb[CTA_NAT_PROTO]) + goto out; + + err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); +out: + rcu_read_unlock(); + return err; +} + +static int +nfnetlink_parse_nat_setup(struct nf_conn *ct, + enum nf_nat_manip_type manip, + const struct nlattr *attr) +{ + struct nf_nat_range range; + int err; + + err = nfnetlink_parse_nat(attr, ct, &range); + if (err < 0) + return err; + if (nf_nat_initialized(ct, manip)) + return -EEXIST; + + return nf_nat_setup_info(ct, &range, manip); +} +#else +static int +nfnetlink_parse_nat_setup(struct nf_conn *ct, + enum nf_nat_manip_type manip, + const struct nlattr *attr) +{ + return -EOPNOTSUPP; +} +#endif + +static int __net_init nf_nat_net_init(struct net *net) +{ + /* Leave them the same for the moment. */ + net->ct.nat_htable_size = net->ct.htable_size; + net->ct.nat_bysource = nf_ct_alloc_hashtable(&net->ct.nat_htable_size, 0); + if (!net->ct.nat_bysource) + return -ENOMEM; + return 0; +} + +static void __net_exit nf_nat_net_exit(struct net *net) +{ + struct nf_nat_proto_clean clean = {}; + + nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + synchronize_rcu(); + nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); +} + +static struct pernet_operations nf_nat_net_ops = { + .init = nf_nat_net_init, + .exit = nf_nat_net_exit, +}; + +static struct nf_ct_helper_expectfn follow_master_nat = { + .name = "nat-follow-master", + .expectfn = nf_nat_follow_master, +}; + +static struct nfq_ct_nat_hook nfq_ct_nat = { + .seq_adjust = nf_nat_tcp_seq_adjust, +}; + +static int __init nf_nat_init(void) +{ + int ret; + + ret = nf_ct_extend_register(&nat_extend); + if (ret < 0) { + printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); + return ret; + } + + ret = register_pernet_subsys(&nf_nat_net_ops); + if (ret < 0) + goto cleanup_extend; + + nf_ct_helper_expectfn_register(&follow_master_nat); + + /* Initialize fake conntrack so that NAT will skip it */ + nf_ct_untracked_status_or(IPS_NAT_DONE_MASK); + + BUG_ON(nf_nat_seq_adjust_hook != NULL); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, nf_nat_seq_adjust); + BUG_ON(nfnetlink_parse_nat_setup_hook != NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, + nfnetlink_parse_nat_setup); + BUG_ON(nf_ct_nat_offset != NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, nf_nat_get_offset); + RCU_INIT_POINTER(nfq_ct_nat_hook, &nfq_ct_nat); +#ifdef CONFIG_XFRM + BUG_ON(nf_nat_decode_session_hook != NULL); + RCU_INIT_POINTER(nf_nat_decode_session_hook, __nf_nat_decode_session); +#endif + return 0; + + cleanup_extend: + nf_ct_extend_unregister(&nat_extend); + return ret; +} + +static void __exit nf_nat_cleanup(void) +{ + unsigned int i; + + unregister_pernet_subsys(&nf_nat_net_ops); + nf_ct_extend_unregister(&nat_extend); + nf_ct_helper_expectfn_unregister(&follow_master_nat); + RCU_INIT_POINTER(nf_nat_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nfnetlink_parse_nat_setup_hook, NULL); + RCU_INIT_POINTER(nf_ct_nat_offset, NULL); + RCU_INIT_POINTER(nfq_ct_nat_hook, NULL); +#ifdef CONFIG_XFRM + RCU_INIT_POINTER(nf_nat_decode_session_hook, NULL); +#endif + for (i = 0; i < NFPROTO_NUMPROTO; i++) + kfree(nf_nat_l4protos[i]); + synchronize_net(); +} + +MODULE_LICENSE("GPL"); + +module_init(nf_nat_init); +module_exit(nf_nat_cleanup); diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c new file mode 100644 index 000000000000..23c2b38676a6 --- /dev/null +++ b/net/netfilter/nf_nat_helper.c @@ -0,0 +1,435 @@ +/* nf_nat_helper.c - generic support functions for NAT helpers + * + * (C) 2000-2002 Harald Welte + * (C) 2003-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DUMP_OFFSET(x) \ + pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \ + x->offset_before, x->offset_after, x->correction_pos); + +static DEFINE_SPINLOCK(nf_nat_seqofs_lock); + +/* Setup TCP sequence correction given this change at this sequence */ +static inline void +adjust_tcp_sequence(u32 seq, + int sizediff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way = &nat->seq[dir]; + + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + seq, sizediff); + + pr_debug("adjust_tcp_sequence: Seq_offset before: "); + DUMP_OFFSET(this_way); + + spin_lock_bh(&nf_nat_seqofs_lock); + + /* SYN adjust. If it's uninitialized, or this is after last + * correction, record it: we don't handle more than one + * adjustment in the window, but do deal with common case of a + * retransmit */ + if (this_way->offset_before == this_way->offset_after || + before(this_way->correction_pos, seq)) { + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += sizediff; + } + spin_unlock_bh(&nf_nat_seqofs_lock); + + pr_debug("adjust_tcp_sequence: Seq_offset after: "); + DUMP_OFFSET(this_way); +} + +/* Get the offset value, for conntrack */ +s16 nf_nat_get_offset(const struct nf_conn *ct, + enum ip_conntrack_dir dir, + u32 seq) +{ + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way; + s16 offset; + + if (!nat) + return 0; + + this_way = &nat->seq[dir]; + spin_lock_bh(&nf_nat_seqofs_lock); + offset = after(seq, this_way->correction_pos) + ? this_way->offset_after : this_way->offset_before; + spin_unlock_bh(&nf_nat_seqofs_lock); + + return offset; +} + +/* Frobs data inside this packet, which is linear. */ +static void mangle_contents(struct sk_buff *skb, + unsigned int dataoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + unsigned char *data; + + BUG_ON(skb_is_nonlinear(skb)); + data = skb_network_header(skb) + dataoff; + + /* move post-replacement */ + memmove(data + match_offset + rep_len, + data + match_offset + match_len, + skb->tail - (skb->network_header + dataoff + + match_offset + match_len)); + + /* insert data from buffer */ + memcpy(data + match_offset, rep_buffer, rep_len); + + /* update skb info */ + if (rep_len > match_len) { + pr_debug("nf_nat_mangle_packet: Extending packet by " + "%u from %u bytes\n", rep_len - match_len, skb->len); + skb_put(skb, rep_len - match_len); + } else { + pr_debug("nf_nat_mangle_packet: Shrinking packet from " + "%u from %u bytes\n", match_len - rep_len, skb->len); + __skb_trim(skb, skb->len + rep_len - match_len); + } + + if (nf_ct_l3num((struct nf_conn *)skb->nfct) == NFPROTO_IPV4) { + /* fix IP hdr checksum information */ + ip_hdr(skb)->tot_len = htons(skb->len); + ip_send_check(ip_hdr(skb)); + } else + ipv6_hdr(skb)->payload_len = + htons(skb->len - sizeof(struct ipv6hdr)); +} + +/* Unusual, but possible case. */ +static int enlarge_skb(struct sk_buff *skb, unsigned int extra) +{ + if (skb->len + extra > 65535) + return 0; + + if (pskb_expand_head(skb, 0, extra - skb_tailroom(skb), GFP_ATOMIC)) + return 0; + + return 1; +} + +void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, + __be32 seq, s16 off) +{ + if (!off) + return; + set_bit(IPS_SEQ_ADJUST_BIT, &ct->status); + adjust_tcp_sequence(ntohl(seq), off, ct, ctinfo); + nf_conntrack_event_cache(IPCT_NATSEQADJ, ct); +} +EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); + +void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct, + u32 ctinfo, int off) +{ + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP) + return; + + th = (struct tcphdr *)(skb_network_header(skb)+ ip_hdrlen(skb)); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} +EXPORT_SYMBOL_GPL(nf_nat_tcp_seq_adjust); + +/* Generic function for mangling variable-length address changes inside + * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX + * command in FTP). + * + * Takes care about all the nasty sequence number changes, checksumming, + * skb enlargement, ... + * + * */ +int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len, bool adjust) +{ + const struct nf_nat_l3proto *l3proto; + struct tcphdr *tcph; + int oldlen, datalen; + + if (!skb_make_writable(skb, skb->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(skb) && + !enlarge_skb(skb, rep_len - match_len)) + return 0; + + SKB_LINEAR_ASSERT(skb); + + tcph = (void *)skb->data + protoff; + + oldlen = skb->len - protoff; + mangle_contents(skb, protoff + tcph->doff*4, + match_offset, match_len, rep_buffer, rep_len); + + datalen = skb->len - protoff; + + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + l3proto->csum_recalc(skb, IPPROTO_TCP, tcph, &tcph->check, + datalen, oldlen); + + if (adjust && rep_len != match_len) + nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, + (int)rep_len - (int)match_len); + + return 1; +} +EXPORT_SYMBOL(__nf_nat_mangle_tcp_packet); + +/* Generic function for mangling variable-length address changes inside + * NATed UDP connections (like the CONNECT DATA XXXXX MESG XXXXX INDEX XXXXX + * command in the Amanda protocol) + * + * Takes care about all the nasty sequence number changes, checksumming, + * skb enlargement, ... + * + * XXX - This function could be merged with nf_nat_mangle_tcp_packet which + * should be fairly easy to do. + */ +int +nf_nat_mangle_udp_packet(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int match_offset, + unsigned int match_len, + const char *rep_buffer, + unsigned int rep_len) +{ + const struct nf_nat_l3proto *l3proto; + struct udphdr *udph; + int datalen, oldlen; + + if (!skb_make_writable(skb, skb->len)) + return 0; + + if (rep_len > match_len && + rep_len - match_len > skb_tailroom(skb) && + !enlarge_skb(skb, rep_len - match_len)) + return 0; + + udph = (void *)skb->data + protoff; + + oldlen = skb->len - protoff; + mangle_contents(skb, protoff + sizeof(*udph), + match_offset, match_len, rep_buffer, rep_len); + + /* update the length of the UDP packet */ + datalen = skb->len - protoff; + udph->len = htons(datalen); + + /* fix udp checksum if udp checksum was previously calculated */ + if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) + return 1; + + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + l3proto->csum_recalc(skb, IPPROTO_UDP, udph, &udph->check, + datalen, oldlen); + + return 1; +} +EXPORT_SYMBOL(nf_nat_mangle_udp_packet); + +/* Adjust one found SACK option including checksum correction */ +static void +sack_adjust(struct sk_buff *skb, + struct tcphdr *tcph, + unsigned int sackoff, + unsigned int sackend, + struct nf_nat_seq *natseq) +{ + while (sackoff < sackend) { + struct tcp_sack_block_wire *sack; + __be32 new_start_seq, new_end_seq; + + sack = (void *)skb->data + sackoff; + if (after(ntohl(sack->start_seq) - natseq->offset_before, + natseq->correction_pos)) + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_after); + else + new_start_seq = htonl(ntohl(sack->start_seq) + - natseq->offset_before); + + if (after(ntohl(sack->end_seq) - natseq->offset_before, + natseq->correction_pos)) + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_after); + else + new_end_seq = htonl(ntohl(sack->end_seq) + - natseq->offset_before); + + pr_debug("sack_adjust: start_seq: %d->%d, end_seq: %d->%d\n", + ntohl(sack->start_seq), new_start_seq, + ntohl(sack->end_seq), new_end_seq); + + inet_proto_csum_replace4(&tcph->check, skb, + sack->start_seq, new_start_seq, 0); + inet_proto_csum_replace4(&tcph->check, skb, + sack->end_seq, new_end_seq, 0); + sack->start_seq = new_start_seq; + sack->end_seq = new_end_seq; + sackoff += sizeof(*sack); + } +} + +/* TCP SACK sequence number adjustment */ +static inline unsigned int +nf_nat_sack_adjust(struct sk_buff *skb, + unsigned int protoff, + struct tcphdr *tcph, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + unsigned int dir, optoff, optend; + struct nf_conn_nat *nat = nfct_nat(ct); + + optoff = protoff + sizeof(struct tcphdr); + optend = protoff + tcph->doff * 4; + + if (!skb_make_writable(skb, optend)) + return 0; + + dir = CTINFO2DIR(ctinfo); + + while (optoff < optend) { + /* Usually: option, length. */ + unsigned char *op = skb->data + optoff; + + switch (op[0]) { + case TCPOPT_EOL: + return 1; + case TCPOPT_NOP: + optoff++; + continue; + default: + /* no partial options */ + if (optoff + 1 == optend || + optoff + op[1] > optend || + op[1] < 2) + return 0; + if (op[0] == TCPOPT_SACK && + op[1] >= 2+TCPOLEN_SACK_PERBLOCK && + ((op[1] - 2) % TCPOLEN_SACK_PERBLOCK) == 0) + sack_adjust(skb, tcph, optoff+2, + optoff+op[1], &nat->seq[!dir]); + optoff += op[1]; + } + } + return 1; +} + +/* TCP sequence number adjustment. Returns 1 on success, 0 on failure */ +int +nf_nat_seq_adjust(struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int protoff) +{ + struct tcphdr *tcph; + int dir; + __be32 newseq, newack; + s16 seqoff, ackoff; + struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way, *other_way; + + dir = CTINFO2DIR(ctinfo); + + this_way = &nat->seq[dir]; + other_way = &nat->seq[!dir]; + + if (!skb_make_writable(skb, protoff + sizeof(*tcph))) + return 0; + + tcph = (void *)skb->data + protoff; + if (after(ntohl(tcph->seq), this_way->correction_pos)) + seqoff = this_way->offset_after; + else + seqoff = this_way->offset_before; + + if (after(ntohl(tcph->ack_seq) - other_way->offset_before, + other_way->correction_pos)) + ackoff = other_way->offset_after; + else + ackoff = other_way->offset_before; + + newseq = htonl(ntohl(tcph->seq) + seqoff); + newack = htonl(ntohl(tcph->ack_seq) - ackoff); + + inet_proto_csum_replace4(&tcph->check, skb, tcph->seq, newseq, 0); + inet_proto_csum_replace4(&tcph->check, skb, tcph->ack_seq, newack, 0); + + pr_debug("Adjusting sequence number from %u->%u, ack from %u->%u\n", + ntohl(tcph->seq), ntohl(newseq), ntohl(tcph->ack_seq), + ntohl(newack)); + + tcph->seq = newseq; + tcph->ack_seq = newack; + + return nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo); +} + +/* Setup NAT on this expected conntrack so it follows master. */ +/* If we fail to get a free NAT slot, we'll get dropped on confirm */ +void nf_nat_follow_master(struct nf_conn *ct, + struct nf_conntrack_expect *exp) +{ + struct nf_nat_range range; + + /* This must be a fresh one. */ + BUG_ON(ct->status & IPS_NAT_DONE_MASK); + + /* Change src to where master sends to */ + range.flags = NF_NAT_RANGE_MAP_IPS; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); + range.min_proto = range.max_proto = exp->saved_proto; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.src.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} +EXPORT_SYMBOL(nf_nat_follow_master); diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c new file mode 100644 index 000000000000..9baaf734c142 --- /dev/null +++ b/net/netfilter/nf_nat_proto_common.c @@ -0,0 +1,112 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * (C) 2008 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include + +bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + __be16 port; + + if (maniptype == NF_NAT_MANIP_SRC) + port = tuple->src.u.all; + else + port = tuple->dst.u.all; + + return ntohs(port) >= ntohs(min->all) && + ntohs(port) <= ntohs(max->all); +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range); + +void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct, + u16 *rover) +{ + unsigned int range_size, min, i; + __be16 *portptr; + u_int16_t off; + + if (maniptype == NF_NAT_MANIP_SRC) + portptr = &tuple->src.u.all; + else + portptr = &tuple->dst.u.all; + + /* If no range specified... */ + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { + /* If it's dst rewrite, can't change port */ + if (maniptype == NF_NAT_MANIP_DST) + return; + + if (ntohs(*portptr) < 1024) { + /* Loose convention: >> 512 is credential passing */ + if (ntohs(*portptr) < 512) { + min = 1; + range_size = 511 - min + 1; + } else { + min = 600; + range_size = 1023 - min + 1; + } + } else { + min = 1024; + range_size = 65535 - 1024 + 1; + } + } else { + min = ntohs(range->min_proto.all); + range_size = ntohs(range->max_proto.all) - min + 1; + } + + if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) + off = l3proto->secure_port(tuple, maniptype == NF_NAT_MANIP_SRC + ? tuple->dst.u.all + : tuple->src.u.all); + else + off = *rover; + + for (i = 0; ; ++off) { + *portptr = htons(min + off % range_size); + if (++i != range_size && nf_nat_used_tuple(tuple, ct)) + continue; + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) + *rover = off; + return; + } + return; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); + +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) +int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], + struct nf_nat_range *range) +{ + if (tb[CTA_PROTONAT_PORT_MIN]) { + range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); + range->max_proto.all = range->min_proto.all; + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + if (tb[CTA_PROTONAT_PORT_MAX]) { + range->max_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]); + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; + } + return 0; +} +EXPORT_SYMBOL_GPL(nf_nat_l4proto_nlattr_to_range); +#endif diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c new file mode 100644 index 000000000000..c8be2cdac0bf --- /dev/null +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -0,0 +1,116 @@ +/* + * DCCP NAT protocol helper + * + * Copyright (c) 2005, 2006, 2008 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +static u_int16_t dccp_port_rover; + +static void +dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &dccp_port_rover); +} + +static bool +dccp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct dccp_hdr *hdr; + __be16 *portptr, oldport, newport; + int hdrsize = 8; /* DCCP connection tracking guarantees this much */ + + if (skb->len >= hdroff + sizeof(struct dccp_hdr)) + hdrsize = sizeof(struct dccp_hdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) + return false; + + hdr = (struct dccp_hdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + newport = tuple->src.u.dccp.port; + portptr = &hdr->dccph_sport; + } else { + newport = tuple->dst.u.dccp.port; + portptr = &hdr->dccph_dport; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return true; + + l3proto->csum_update(skb, iphdroff, &hdr->dccph_checksum, + tuple, maniptype); + inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport, + 0); + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_dccp = { + .l4proto = IPPROTO_DCCP, + .manip_pkt = dccp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = dccp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_dccp_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_dccp); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_dccp); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_dccp); +err1: + return err; +} + +static void __exit nf_nat_proto_dccp_fini(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_dccp); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_dccp); + +} + +module_init(nf_nat_proto_dccp_init); +module_exit(nf_nat_proto_dccp_fini); + +MODULE_AUTHOR("Patrick McHardy "); +MODULE_DESCRIPTION("DCCP NAT protocol helper"); +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c new file mode 100644 index 000000000000..e64faa5ca893 --- /dev/null +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -0,0 +1,103 @@ +/* + * Copyright (c) 2008 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +#include + +static u_int16_t nf_sctp_port_rover; + +static void +sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &nf_sctp_port_rover); +} + +static bool +sctp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct sk_buff *frag; + sctp_sctphdr_t *hdr; + __be32 crc32; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct sctphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + hdr->source = tuple->src.u.sctp.port; + } else { + /* Get rid of dst port */ + hdr->dest = tuple->dst.u.sctp.port; + } + + crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); + skb_walk_frags(skb, frag) + crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), + crc32); + crc32 = sctp_end_cksum(crc32); + hdr->checksum = crc32; + + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_sctp = { + .l4proto = IPPROTO_SCTP, + .manip_pkt = sctp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = sctp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_sctp_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_sctp); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_sctp); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_sctp); +err1: + return err; +} + +static void __exit nf_nat_proto_sctp_exit(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_sctp); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_sctp); +} + +module_init(nf_nat_proto_sctp_init); +module_exit(nf_nat_proto_sctp_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SCTP NAT protocol helper"); +MODULE_AUTHOR("Patrick McHardy "); diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c new file mode 100644 index 000000000000..83ec8a6e4c36 --- /dev/null +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -0,0 +1,85 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +static u16 tcp_port_rover; + +static void +tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &tcp_port_rover); +} + +static bool +tcp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct tcphdr *hdr; + __be16 *portptr, newport, oldport; + int hdrsize = 8; /* TCP connection tracking guarantees this much */ + + /* this could be a inner header returned in icmp packet; in such + cases we cannot update the checksum field since it is outside of + the 8 bytes of transport layer headers we are guaranteed */ + if (skb->len >= hdroff + sizeof(struct tcphdr)) + hdrsize = sizeof(struct tcphdr); + + if (!skb_make_writable(skb, hdroff + hdrsize)) + return false; + + hdr = (struct tcphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + newport = tuple->src.u.tcp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.tcp.port; + portptr = &hdr->dest; + } + + oldport = *portptr; + *portptr = newport; + + if (hdrsize < sizeof(*hdr)) + return true; + + l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, oldport, newport, 0); + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_tcp = { + .l4proto = IPPROTO_TCP, + .manip_pkt = tcp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = tcp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c new file mode 100644 index 000000000000..7df613fb34a2 --- /dev/null +++ b/net/netfilter/nf_nat_proto_udp.c @@ -0,0 +1,76 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +static u16 udp_port_rover; + +static void +udp_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udp_port_rover); +} + +static bool +udp_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + __be16 *portptr, newport; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + hdr = (struct udphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of src port */ + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + if (hdr->check || skb->ip_summed == CHECKSUM_PARTIAL) { + l3proto->csum_update(skb, iphdroff, &hdr->check, + tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, + 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + } + *portptr = newport; + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_udp = { + .l4proto = IPPROTO_UDP, + .manip_pkt = udp_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udp_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; diff --git a/net/netfilter/nf_nat_proto_udplite.c b/net/netfilter/nf_nat_proto_udplite.c new file mode 100644 index 000000000000..776a0d1317b1 --- /dev/null +++ b/net/netfilter/nf_nat_proto_udplite.c @@ -0,0 +1,106 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * (C) 2008 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include + +#include +#include +#include +#include +#include + +static u16 udplite_port_rover; + +static void +udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + nf_nat_l4proto_unique_tuple(l3proto, tuple, range, maniptype, ct, + &udplite_port_rover); +} + +static bool +udplite_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + struct udphdr *hdr; + __be16 *portptr, newport; + + if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + return false; + + hdr = (struct udphdr *)(skb->data + hdroff); + + if (maniptype == NF_NAT_MANIP_SRC) { + /* Get rid of source port */ + newport = tuple->src.u.udp.port; + portptr = &hdr->source; + } else { + /* Get rid of dst port */ + newport = tuple->dst.u.udp.port; + portptr = &hdr->dest; + } + + l3proto->csum_update(skb, iphdroff, &hdr->check, tuple, maniptype); + inet_proto_csum_replace2(&hdr->check, skb, *portptr, newport, 0); + if (!hdr->check) + hdr->check = CSUM_MANGLED_0; + + *portptr = newport; + return true; +} + +static const struct nf_nat_l4proto nf_nat_l4proto_udplite = { + .l4proto = IPPROTO_UDPLITE, + .manip_pkt = udplite_manip_pkt, + .in_range = nf_nat_l4proto_in_range, + .unique_tuple = udplite_unique_tuple, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .nlattr_to_range = nf_nat_l4proto_nlattr_to_range, +#endif +}; + +static int __init nf_nat_proto_udplite_init(void) +{ + int err; + + err = nf_nat_l4proto_register(NFPROTO_IPV4, &nf_nat_l4proto_udplite); + if (err < 0) + goto err1; + err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_udplite); + if (err < 0) + goto err2; + return 0; + +err2: + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_udplite); +err1: + return err; +} + +static void __exit nf_nat_proto_udplite_fini(void) +{ + nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_udplite); + nf_nat_l4proto_unregister(NFPROTO_IPV4, &nf_nat_l4proto_udplite); +} + +module_init(nf_nat_proto_udplite_init); +module_exit(nf_nat_proto_udplite_fini); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("UDP-Lite NAT protocol helper"); +MODULE_AUTHOR("Patrick McHardy "); diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c new file mode 100644 index 000000000000..6e494d584412 --- /dev/null +++ b/net/netfilter/nf_nat_proto_unknown.c @@ -0,0 +1,54 @@ +/* The "unknown" protocol. This is what is used for protocols we + * don't understand. It's returned by ip_ct_find_proto(). + */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +#include +#include +#include + +static bool unknown_in_range(const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type manip_type, + const union nf_conntrack_man_proto *min, + const union nf_conntrack_man_proto *max) +{ + return true; +} + +static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto, + struct nf_conntrack_tuple *tuple, + const struct nf_nat_range *range, + enum nf_nat_manip_type maniptype, + const struct nf_conn *ct) +{ + /* Sorry: we can't help you; if it's not unique, we can't frob + * anything. + */ + return; +} + +static bool +unknown_manip_pkt(struct sk_buff *skb, + const struct nf_nat_l3proto *l3proto, + unsigned int iphdroff, unsigned int hdroff, + const struct nf_conntrack_tuple *tuple, + enum nf_nat_manip_type maniptype) +{ + return true; +} + +const struct nf_nat_l4proto nf_nat_l4proto_unknown = { + .manip_pkt = unknown_manip_pkt, + .in_range = unknown_in_range, + .unique_tuple = unknown_unique_tuple, +}; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c new file mode 100644 index 000000000000..7521368a6034 --- /dev/null +++ b/net/netfilter/xt_nat.c @@ -0,0 +1,167 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * (C) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +static int xt_nat_checkentry_v0(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (mr->rangesize != 1) { + pr_info("%s: multiple ranges no longer supported\n", + par->target->name); + return -EINVAL; + } + return 0; +} + +static void xt_nat_convert_range(struct nf_nat_range *dst, + const struct nf_nat_ipv4_range *src) +{ + memset(&dst->min_addr, 0, sizeof(dst->min_addr)); + memset(&dst->max_addr, 0, sizeof(dst->max_addr)); + + dst->flags = src->flags; + dst->min_addr.ip = src->min_ip; + dst->max_addr.ip = src->max_ip; + dst->min_proto = src->min; + dst->max_proto = src->max; +} + +static unsigned int +xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + xt_nat_convert_range(&range, &mr->range[0]); + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + xt_nat_convert_range(&range, &mr->range[0]); + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} + +static unsigned int +xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_DST); +} + +static struct xt_target xt_nat_target_reg[] __read_mostly = { + { + .name = "SNAT", + .revision = 0, + .checkentry = xt_nat_checkentry_v0, + .target = xt_snat_target_v0, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .family = NFPROTO_IPV4, + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 0, + .checkentry = xt_nat_checkentry_v0, + .target = xt_dnat_target_v0, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .family = NFPROTO_IPV4, + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, + { + .name = "SNAT", + .revision = 1, + .target = xt_snat_target_v1, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 1, + .target = xt_dnat_target_v1, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, +}; + +static int __init xt_nat_init(void) +{ + return xt_register_targets(xt_nat_target_reg, + ARRAY_SIZE(xt_nat_target_reg)); +} + +static void __exit xt_nat_exit(void) +{ + xt_unregister_targets(xt_nat_target_reg, ARRAY_SIZE(xt_nat_target_reg)); +} + +module_init(xt_nat_init); +module_exit(xt_nat_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_SNAT"); +MODULE_ALIAS("ipt_DNAT"); -- cgit v1.3-14-g43fede From b3f644fc8232ca761da0b5c5ccb6f30b423c4302 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:14 +0200 Subject: netfilter: ip6tables: add MASQUERADE target Signed-off-by: Patrick McHardy --- include/net/addrconf.h | 2 +- include/net/netfilter/nf_nat.h | 4 +- net/ipv4/netfilter/ipt_MASQUERADE.c | 3 +- net/ipv6/addrconf.c | 2 +- net/ipv6/netfilter/Kconfig | 12 ++++ net/ipv6/netfilter/Makefile | 1 + net/ipv6/netfilter/ip6t_MASQUERADE.c | 135 +++++++++++++++++++++++++++++++++++ 7 files changed, 155 insertions(+), 4 deletions(-) create mode 100644 net/ipv6/netfilter/ip6t_MASQUERADE.c (limited to 'net/ipv4') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 089a09d001d1..9e63e76b20e7 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -78,7 +78,7 @@ extern struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, int strict); extern int ipv6_dev_get_saddr(struct net *net, - struct net_device *dev, + const struct net_device *dev, const struct in6_addr *daddr, unsigned int srcprefs, struct in6_addr *saddr); diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 1752f1339054..bd8eea720f2e 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -43,7 +43,9 @@ struct nf_conn_nat { struct nf_conn *ct; union nf_conntrack_nat_help help; #if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \ - defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE) + defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE) || \ + defined(CONFIG_IP6_NF_TARGET_MASQUERADE) || \ + defined(CONFIG_IP6_NF_TARGET_MASQUERADE_MODULE) int masq_index; #endif }; diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 1c3aa28b51ae..5d5d4d1be9c2 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -99,7 +99,8 @@ device_cmp(struct nf_conn *i, void *ifindex) if (!nat) return 0; - + if (nf_ct_l3num(i) != NFPROTO_IPV4) + return 0; return nat->masq_index == (int)(long)ifindex; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e581009cb09e..19d4bffda9d7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1093,7 +1093,7 @@ out: return ret; } -int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, +int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index b27e0ad4b738..54a5032ea3df 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -144,6 +144,18 @@ config IP6_NF_TARGET_HL (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. +config IP6_NF_TARGET_MASQUERADE + tristate "MASQUERADE target support" + depends on NF_NAT_IPV6 + help + Masquerading is a special case of NAT: all outgoing connections are + changed to seem to come from a particular interface's address, and + if the interface goes down, those connections are lost. This is + only useful for dialup accounts with dynamic IP address (ie. your IP + address will be different on next dialup). + + To compile it as a module, choose M here. If unsure, say N. + config IP6_NF_FILTER tristate "Packet filtering" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 76779376da4c..068bad199587 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -34,4 +34,5 @@ obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets +obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c new file mode 100644 index 000000000000..60e9053bab05 --- /dev/null +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -0,0 +1,135 @@ +/* + * Copyright (c) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6 + * NAT funded by Astaro. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned int +masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct in6_addr src; + struct nf_conn *ct; + struct nf_nat_range newrange; + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY)); + + if (ipv6_dev_get_saddr(dev_net(par->out), par->out, + &ipv6_hdr(skb)->daddr, 0, &src) < 0) + return NF_DROP; + + nfct_nat(ct)->masq_index = par->out->ifindex; + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = src; + newrange.max_addr.in6 = src; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); +} + +static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (range->flags & NF_NAT_RANGE_MAP_IPS) + return -EINVAL; + return 0; +} + +static int device_cmp(struct nf_conn *ct, void *ifindex) +{ + const struct nf_conn_nat *nat = nfct_nat(ct); + + if (!nat) + return 0; + if (nf_ct_l3num(ct) != NFPROTO_IPV6) + return 0; + return nat->masq_index == (int)(long)ifindex; +} + +static int masq_device_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + const struct net_device *dev = ptr; + struct net *net = dev_net(dev); + + if (event == NETDEV_DOWN) + nf_ct_iterate_cleanup(net, device_cmp, + (void *)(long)dev->ifindex); + + return NOTIFY_DONE; +} + +static struct notifier_block masq_dev_notifier = { + .notifier_call = masq_device_event, +}; + +static int masq_inet_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + + return masq_device_event(this, event, ifa->idev->dev); +} + +static struct notifier_block masq_inet_notifier = { + .notifier_call = masq_inet_event, +}; + +static struct xt_target masquerade_tg6_reg __read_mostly = { + .name = "MASQUERADE", + .family = NFPROTO_IPV6, + .checkentry = masquerade_tg6_checkentry, + .target = masquerade_tg6, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = 1 << NF_INET_POST_ROUTING, + .me = THIS_MODULE, +}; + +static int __init masquerade_tg6_init(void) +{ + int err; + + err = xt_register_target(&masquerade_tg6_reg); + if (err == 0) { + register_netdevice_notifier(&masq_dev_notifier); + register_inet6addr_notifier(&masq_inet_notifier); + } + + return err; +} +static void __exit masquerade_tg6_exit(void) +{ + unregister_inet6addr_notifier(&masq_inet_notifier); + unregister_netdevice_notifier(&masq_dev_notifier); + xt_unregister_target(&masquerade_tg6_reg); +} + +module_init(masquerade_tg6_init); +module_exit(masquerade_tg6_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy "); +MODULE_DESCRIPTION("Xtables: automatic address SNAT"); -- cgit v1.3-14-g43fede From d33cbeeb1a46a7dc82fe9f53e40a742ce0c67c79 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:20 +0200 Subject: netfilter: nf_nat: support IPv6 in FTP NAT helper Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/Kconfig | 5 -- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/nf_nat_ftp.c | 137 ------------------------------------- net/netfilter/Kconfig | 5 ++ net/netfilter/Makefile | 3 + net/netfilter/nf_conntrack_ftp.c | 3 +- net/netfilter/nf_nat_ftp.c | 143 +++++++++++++++++++++++++++++++++++++++ 7 files changed, 152 insertions(+), 145 deletions(-) delete mode 100644 net/ipv4/netfilter/nf_nat_ftp.c create mode 100644 net/netfilter/nf_nat_ftp.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index b26629681bdb..8c6c6920b57a 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -221,11 +221,6 @@ config NF_NAT_PROTO_GRE tristate depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE -config NF_NAT_FTP - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_FTP - config NF_NAT_IRC tristate depends on NF_CONNTRACK && NF_NAT_IPV4 diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 0ea3acc510e2..4d8a4ad7816e 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -21,7 +21,6 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o # NAT helpers (nf_conntrack) obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o -obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c deleted file mode 100644 index dd5e387fc03b..000000000000 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ /dev/null @@ -1,137 +0,0 @@ -/* FTP extension for TCP NAT alteration. */ - -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Rusty Russell "); -MODULE_DESCRIPTION("ftp NAT helper"); -MODULE_ALIAS("ip_nat_ftp"); - -/* FIXME: Time out? --RR */ - -static int nf_nat_ftp_fmt_cmd(enum nf_ct_ftp_type type, - char *buffer, size_t buflen, - __be32 addr, u16 port) -{ - switch (type) { - case NF_CT_FTP_PORT: - case NF_CT_FTP_PASV: - return snprintf(buffer, buflen, "%u,%u,%u,%u,%u,%u", - ((unsigned char *)&addr)[0], - ((unsigned char *)&addr)[1], - ((unsigned char *)&addr)[2], - ((unsigned char *)&addr)[3], - port >> 8, - port & 0xFF); - case NF_CT_FTP_EPRT: - return snprintf(buffer, buflen, "|1|%pI4|%u|", &addr, port); - case NF_CT_FTP_EPSV: - return snprintf(buffer, buflen, "|||%u|", port); - } - - return 0; -} - -/* So, this packet has hit the connection tracking matching code. - Mangle it, and change the expectation to match the new version. */ -static unsigned int nf_nat_ftp(struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - enum nf_ct_ftp_type type, - unsigned int protoff, - unsigned int matchoff, - unsigned int matchlen, - struct nf_conntrack_expect *exp) -{ - __be32 newip; - u_int16_t port; - int dir = CTINFO2DIR(ctinfo); - struct nf_conn *ct = exp->master; - char buffer[sizeof("|1|255.255.255.255|65535|")]; - unsigned int buflen; - - pr_debug("FTP_NAT: type %i, off %u len %u\n", type, matchoff, matchlen); - - /* Connection will come from wherever this packet goes, hence !dir */ - newip = ct->tuplehash[!dir].tuple.dst.u3.ip; - exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; - exp->dir = !dir; - - /* When you see the packet, we need to NAT it the same as the - * this one. */ - exp->expectfn = nf_nat_follow_master; - - /* Try to get same port: if not, try to change it. */ - for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { - int ret; - - exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); - if (ret == 0) - break; - else if (ret != -EBUSY) { - port = 0; - break; - } - } - - if (port == 0) - return NF_DROP; - - buflen = nf_nat_ftp_fmt_cmd(type, buffer, sizeof(buffer), newip, port); - if (!buflen) - goto out; - - pr_debug("calling nf_nat_mangle_tcp_packet\n"); - - if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, - matchlen, buffer, buflen)) - goto out; - - return NF_ACCEPT; - -out: - nf_ct_unexpect_related(exp); - return NF_DROP; -} - -static void __exit nf_nat_ftp_fini(void) -{ - RCU_INIT_POINTER(nf_nat_ftp_hook, NULL); - synchronize_rcu(); -} - -static int __init nf_nat_ftp_init(void) -{ - BUG_ON(nf_nat_ftp_hook != NULL); - RCU_INIT_POINTER(nf_nat_ftp_hook, nf_nat_ftp); - return 0; -} - -/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ -static int warn_set(const char *val, struct kernel_param *kp) -{ - printk(KERN_INFO KBUILD_MODNAME - ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); - return 0; -} -module_param_call(ports, warn_set, NULL, NULL, 0); - -module_init(nf_nat_ftp_init); -module_exit(nf_nat_ftp_fini); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 91adddae20a4..310449450634 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -380,6 +380,11 @@ config NF_NAT_PROTO_SCTP depends on NF_NAT && NF_CT_PROTO_SCTP select LIBCRC32C +config NF_NAT_FTP + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_FTP + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 09c9451bc510..16592b1e5344 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -54,6 +54,9 @@ obj-$(CONFIG_NF_NAT_PROTO_DCCP) += nf_nat_proto_dccp.o obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o +# NAT helpers +obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o + # transparent proxy support obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index c0f4a5ba9016..f8cc26ad4456 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -488,8 +488,7 @@ static int help(struct sk_buff *skb, /* Now, NAT might want to mangle the packet, and register the * (possibly changed) expectation itself. */ nf_nat_ftp = rcu_dereference(nf_nat_ftp_hook); - if (nf_nat_ftp && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) + if (nf_nat_ftp && ct->status & IPS_NAT_MASK) ret = nf_nat_ftp(skb, ctinfo, search[dir][i].ftptype, protoff, matchoff, matchlen, exp); else { diff --git a/net/netfilter/nf_nat_ftp.c b/net/netfilter/nf_nat_ftp.c new file mode 100644 index 000000000000..e839b97b2863 --- /dev/null +++ b/net/netfilter/nf_nat_ftp.c @@ -0,0 +1,143 @@ +/* FTP extension for TCP NAT alteration. */ + +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Rusty Russell "); +MODULE_DESCRIPTION("ftp NAT helper"); +MODULE_ALIAS("ip_nat_ftp"); + +/* FIXME: Time out? --RR */ + +static int nf_nat_ftp_fmt_cmd(struct nf_conn *ct, enum nf_ct_ftp_type type, + char *buffer, size_t buflen, + union nf_inet_addr *addr, u16 port) +{ + switch (type) { + case NF_CT_FTP_PORT: + case NF_CT_FTP_PASV: + return snprintf(buffer, buflen, "%u,%u,%u,%u,%u,%u", + ((unsigned char *)&addr->ip)[0], + ((unsigned char *)&addr->ip)[1], + ((unsigned char *)&addr->ip)[2], + ((unsigned char *)&addr->ip)[3], + port >> 8, + port & 0xFF); + case NF_CT_FTP_EPRT: + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + return snprintf(buffer, buflen, "|1|%pI4|%u|", + &addr->ip, port); + else + return snprintf(buffer, buflen, "|2|%pI6|%u|", + &addr->ip6, port); + case NF_CT_FTP_EPSV: + return snprintf(buffer, buflen, "|||%u|", port); + } + + return 0; +} + +/* So, this packet has hit the connection tracking matching code. + Mangle it, and change the expectation to match the new version. */ +static unsigned int nf_nat_ftp(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + enum nf_ct_ftp_type type, + unsigned int protoff, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp) +{ + union nf_inet_addr newaddr; + u_int16_t port; + int dir = CTINFO2DIR(ctinfo); + struct nf_conn *ct = exp->master; + char buffer[sizeof("|1||65535|") + INET6_ADDRSTRLEN]; + unsigned int buflen; + + pr_debug("FTP_NAT: type %i, off %u len %u\n", type, matchoff, matchlen); + + /* Connection will come from wherever this packet goes, hence !dir */ + newaddr = ct->tuplehash[!dir].tuple.dst.u3; + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->dir = !dir; + + /* When you see the packet, we need to NAT it the same as the + * this one. */ + exp->expectfn = nf_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + + exp->tuple.dst.u.tcp.port = htons(port); + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + buflen = nf_nat_ftp_fmt_cmd(ct, type, buffer, sizeof(buffer), + &newaddr, port); + if (!buflen) + goto out; + + pr_debug("calling nf_nat_mangle_tcp_packet\n"); + + if (!nf_nat_mangle_tcp_packet(skb, ct, ctinfo, protoff, matchoff, + matchlen, buffer, buflen)) + goto out; + + return NF_ACCEPT; + +out: + nf_ct_unexpect_related(exp); + return NF_DROP; +} + +static void __exit nf_nat_ftp_fini(void) +{ + RCU_INIT_POINTER(nf_nat_ftp_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_ftp_init(void) +{ + BUG_ON(nf_nat_ftp_hook != NULL); + RCU_INIT_POINTER(nf_nat_ftp_hook, nf_nat_ftp); + return 0; +} + +/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ +static int warn_set(const char *val, struct kernel_param *kp) +{ + printk(KERN_INFO KBUILD_MODNAME + ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); + return 0; +} +module_param_call(ports, warn_set, NULL, NULL, 0); + +module_init(nf_nat_ftp_init); +module_exit(nf_nat_ftp_fini); -- cgit v1.3-14-g43fede From ee6eb96673704225164f0ba7462e1973ce10885c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:22 +0200 Subject: netfilter: nf_nat: support IPv6 in amanda NAT helper Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/Kconfig | 5 --- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/nf_nat_amanda.c | 85 ------------------------------------- net/netfilter/Kconfig | 5 +++ net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_amanda.c | 3 +- net/netfilter/nf_nat_amanda.c | 85 +++++++++++++++++++++++++++++++++++++ 7 files changed, 92 insertions(+), 93 deletions(-) delete mode 100644 net/ipv4/netfilter/nf_nat_amanda.c create mode 100644 net/netfilter/nf_nat_amanda.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 8c6c6920b57a..52c4a87007aa 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -231,11 +231,6 @@ config NF_NAT_TFTP depends on NF_CONNTRACK && NF_NAT_IPV4 default NF_NAT_IPV4 && NF_CONNTRACK_TFTP -config NF_NAT_AMANDA - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_AMANDA - config NF_NAT_PPTP tristate depends on NF_CONNTRACK && NF_NAT_IPV4 diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 4d8a4ad7816e..8baa496f6a4e 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -20,7 +20,6 @@ obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o # NAT helpers (nf_conntrack) -obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c deleted file mode 100644 index 42d337881171..000000000000 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ /dev/null @@ -1,85 +0,0 @@ -/* Amanda extension for TCP NAT alteration. - * (C) 2002 by Brian J. Murrell - * based on a copy of HW's ip_nat_irc.c as well as other modules - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include - -#include -#include -#include -#include - -MODULE_AUTHOR("Brian J. Murrell "); -MODULE_DESCRIPTION("Amanda NAT helper"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("ip_nat_amanda"); - -static unsigned int help(struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - unsigned int protoff, - unsigned int matchoff, - unsigned int matchlen, - struct nf_conntrack_expect *exp) -{ - char buffer[sizeof("65535")]; - u_int16_t port; - unsigned int ret; - - /* Connection comes from client. */ - exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; - exp->dir = IP_CT_DIR_ORIGINAL; - - /* When you see the packet, we need to NAT it the same as the - * this one (ie. same IP: it will be TCP and master is UDP). */ - exp->expectfn = nf_nat_follow_master; - - /* Try to get same port: if not, try to change it. */ - for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { - int res; - - exp->tuple.dst.u.tcp.port = htons(port); - res = nf_ct_expect_related(exp); - if (res == 0) - break; - else if (res != -EBUSY) { - port = 0; - break; - } - } - - if (port == 0) - return NF_DROP; - - sprintf(buffer, "%u", port); - ret = nf_nat_mangle_udp_packet(skb, exp->master, ctinfo, - protoff, matchoff, matchlen, - buffer, strlen(buffer)); - if (ret != NF_ACCEPT) - nf_ct_unexpect_related(exp); - return ret; -} - -static void __exit nf_nat_amanda_fini(void) -{ - RCU_INIT_POINTER(nf_nat_amanda_hook, NULL); - synchronize_rcu(); -} - -static int __init nf_nat_amanda_init(void) -{ - BUG_ON(nf_nat_amanda_hook != NULL); - RCU_INIT_POINTER(nf_nat_amanda_hook, help); - return 0; -} - -module_init(nf_nat_amanda_init); -module_exit(nf_nat_amanda_fini); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 310449450634..2eee9f1f99ef 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -380,6 +380,11 @@ config NF_NAT_PROTO_SCTP depends on NF_NAT && NF_CT_PROTO_SCTP select LIBCRC32C +config NF_NAT_AMANDA + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_AMANDA + config NF_NAT_FTP tristate depends on NF_CONNTRACK && NF_NAT diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 16592b1e5344..7d6e1ea14c9b 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -55,6 +55,7 @@ obj-$(CONFIG_NF_NAT_PROTO_UDPLITE) += nf_nat_proto_udplite.o obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o # NAT helpers +obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o # transparent proxy support diff --git a/net/netfilter/nf_conntrack_amanda.c b/net/netfilter/nf_conntrack_amanda.c index e0212b5494b1..c514fe6033d2 100644 --- a/net/netfilter/nf_conntrack_amanda.c +++ b/net/netfilter/nf_conntrack_amanda.c @@ -155,8 +155,7 @@ static int amanda_help(struct sk_buff *skb, IPPROTO_TCP, NULL, &port); nf_nat_amanda = rcu_dereference(nf_nat_amanda_hook); - if (nf_nat_amanda && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) + if (nf_nat_amanda && ct->status & IPS_NAT_MASK) ret = nf_nat_amanda(skb, ctinfo, protoff, off - dataoff, len, exp); else if (nf_ct_expect_related(exp) != 0) diff --git a/net/netfilter/nf_nat_amanda.c b/net/netfilter/nf_nat_amanda.c new file mode 100644 index 000000000000..42d337881171 --- /dev/null +++ b/net/netfilter/nf_nat_amanda.c @@ -0,0 +1,85 @@ +/* Amanda extension for TCP NAT alteration. + * (C) 2002 by Brian J. Murrell + * based on a copy of HW's ip_nat_irc.c as well as other modules + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include + +MODULE_AUTHOR("Brian J. Murrell "); +MODULE_DESCRIPTION("Amanda NAT helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat_amanda"); + +static unsigned int help(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp) +{ + char buffer[sizeof("65535")]; + u_int16_t port; + unsigned int ret; + + /* Connection comes from client. */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->dir = IP_CT_DIR_ORIGINAL; + + /* When you see the packet, we need to NAT it the same as the + * this one (ie. same IP: it will be TCP and master is UDP). */ + exp->expectfn = nf_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int res; + + exp->tuple.dst.u.tcp.port = htons(port); + res = nf_ct_expect_related(exp); + if (res == 0) + break; + else if (res != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + sprintf(buffer, "%u", port); + ret = nf_nat_mangle_udp_packet(skb, exp->master, ctinfo, + protoff, matchoff, matchlen, + buffer, strlen(buffer)); + if (ret != NF_ACCEPT) + nf_ct_unexpect_related(exp); + return ret; +} + +static void __exit nf_nat_amanda_fini(void) +{ + RCU_INIT_POINTER(nf_nat_amanda_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_amanda_init(void) +{ + BUG_ON(nf_nat_amanda_hook != NULL); + RCU_INIT_POINTER(nf_nat_amanda_hook, help); + return 0; +} + +module_init(nf_nat_amanda_init); +module_exit(nf_nat_amanda_fini); -- cgit v1.3-14-g43fede From 9a664821068739dbc8eac13770e28167b46a0c0f Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Sun, 26 Aug 2012 19:14:25 +0200 Subject: netfilter: nf_nat: support IPv6 in SIP NAT helper Add IPv6 support to the SIP NAT helper. There are no functional differences to IPv4 NAT, just different formats for addresses. Signed-off-by: Patrick McHardy --- include/linux/netfilter/nf_conntrack_sip.h | 9 +- net/ipv4/netfilter/Kconfig | 5 - net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/nf_nat_sip.c | 580 --------------------------- net/netfilter/Kconfig | 5 + net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_sip.c | 68 ++-- net/netfilter/nf_nat_sip.c | 609 +++++++++++++++++++++++++++++ 8 files changed, 653 insertions(+), 625 deletions(-) delete mode 100644 net/ipv4/netfilter/nf_nat_sip.c create mode 100644 net/netfilter/nf_nat_sip.c (limited to 'net/ipv4') diff --git a/include/linux/netfilter/nf_conntrack_sip.h b/include/linux/netfilter/nf_conntrack_sip.h index 1afc669a393e..387bdd02945d 100644 --- a/include/linux/netfilter/nf_conntrack_sip.h +++ b/include/linux/netfilter/nf_conntrack_sip.h @@ -99,10 +99,8 @@ enum sip_header_types { enum sdp_header_types { SDP_HDR_UNSPEC, SDP_HDR_VERSION, - SDP_HDR_OWNER_IP4, - SDP_HDR_CONNECTION_IP4, - SDP_HDR_OWNER_IP6, - SDP_HDR_CONNECTION_IP6, + SDP_HDR_OWNER, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, }; @@ -111,7 +109,8 @@ extern unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int dataoff, const char **dptr, unsigned int *datalen); -extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off); +extern void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, + unsigned int protoff, s16 off); extern unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, unsigned int protoff, unsigned int dataoff, diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 52c4a87007aa..30197f8003be 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -242,11 +242,6 @@ config NF_NAT_H323 depends on NF_CONNTRACK && NF_NAT_IPV4 default NF_NAT_IPV4 && NF_CONNTRACK_H323 -config NF_NAT_SIP - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_SIP - # mangle + specific targets config IP_NF_MANGLE tristate "Packet mangling" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 8baa496f6a4e..8914abffc96d 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -23,7 +23,6 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o -obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c deleted file mode 100644 index 47a47186a791..000000000000 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ /dev/null @@ -1,580 +0,0 @@ -/* SIP extension for NAT alteration. - * - * (C) 2005 by Christian Hentschel - * based on RR's ip_nat_ftp.c and other modules. - * (C) 2007 United Security Providers - * (C) 2007, 2008 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Christian Hentschel "); -MODULE_DESCRIPTION("SIP NAT helper"); -MODULE_ALIAS("ip_nat_sip"); - - -static unsigned int mangle_packet(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - unsigned int matchoff, unsigned int matchlen, - const char *buffer, unsigned int buflen) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - struct tcphdr *th; - unsigned int baseoff; - - if (nf_ct_protonum(ct) == IPPROTO_TCP) { - th = (struct tcphdr *)(skb->data + ip_hdrlen(skb)); - baseoff = ip_hdrlen(skb) + th->doff * 4; - matchoff += dataoff - baseoff; - - if (!__nf_nat_mangle_tcp_packet(skb, ct, ctinfo, - protoff, matchoff, matchlen, - buffer, buflen, false)) - return 0; - } else { - baseoff = ip_hdrlen(skb) + sizeof(struct udphdr); - matchoff += dataoff - baseoff; - - if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, - protoff, matchoff, matchlen, - buffer, buflen)) - return 0; - } - - /* Reload data pointer and adjust datalen value */ - *dptr = skb->data + dataoff; - *datalen += buflen - matchlen; - return 1; -} - -static int map_addr(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - unsigned int matchoff, unsigned int matchlen, - union nf_inet_addr *addr, __be16 port) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; - unsigned int buflen; - __be32 newaddr; - __be16 newport; - - if (ct->tuplehash[dir].tuple.src.u3.ip == addr->ip && - ct->tuplehash[dir].tuple.src.u.udp.port == port) { - newaddr = ct->tuplehash[!dir].tuple.dst.u3.ip; - newport = ct->tuplehash[!dir].tuple.dst.u.udp.port; - } else if (ct->tuplehash[dir].tuple.dst.u3.ip == addr->ip && - ct->tuplehash[dir].tuple.dst.u.udp.port == port) { - newaddr = ct->tuplehash[!dir].tuple.src.u3.ip; - newport = ct->tuplehash[!dir].tuple.src.u.udp.port; - } else - return 1; - - if (newaddr == addr->ip && newport == port) - return 1; - - buflen = sprintf(buffer, "%pI4:%u", &newaddr, ntohs(newport)); - - return mangle_packet(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, buffer, buflen); -} - -static int map_sip_addr(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - enum sip_header_types type) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - unsigned int matchlen, matchoff; - union nf_inet_addr addr; - __be16 port; - - if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, type, NULL, - &matchoff, &matchlen, &addr, &port) <= 0) - return 1; - return map_addr(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, &addr, port); -} - -static unsigned int ip_nat_sip(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - unsigned int coff, matchoff, matchlen; - enum sip_header_types hdr; - union nf_inet_addr addr; - __be16 port; - int request, in_header; - - /* Basic rules: requests and responses. */ - if (strnicmp(*dptr, "SIP/2.0", strlen("SIP/2.0")) != 0) { - if (ct_sip_parse_request(ct, *dptr, *datalen, - &matchoff, &matchlen, - &addr, &port) > 0 && - !map_addr(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, &addr, port)) - return NF_DROP; - request = 1; - } else - request = 0; - - if (nf_ct_protonum(ct) == IPPROTO_TCP) - hdr = SIP_HDR_VIA_TCP; - else - hdr = SIP_HDR_VIA_UDP; - - /* Translate topmost Via header and parameters */ - if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, - hdr, NULL, &matchoff, &matchlen, - &addr, &port) > 0) { - unsigned int olen, matchend, poff, plen, buflen, n; - char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; - - /* We're only interested in headers related to this - * connection */ - if (request) { - if (addr.ip != ct->tuplehash[dir].tuple.src.u3.ip || - port != ct->tuplehash[dir].tuple.src.u.udp.port) - goto next; - } else { - if (addr.ip != ct->tuplehash[dir].tuple.dst.u3.ip || - port != ct->tuplehash[dir].tuple.dst.u.udp.port) - goto next; - } - - olen = *datalen; - if (!map_addr(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, &addr, port)) - return NF_DROP; - - matchend = matchoff + matchlen + *datalen - olen; - - /* The maddr= parameter (RFC 2361) specifies where to send - * the reply. */ - if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, - "maddr=", &poff, &plen, - &addr, true) > 0 && - addr.ip == ct->tuplehash[dir].tuple.src.u3.ip && - addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) { - buflen = sprintf(buffer, "%pI4", - &ct->tuplehash[!dir].tuple.dst.u3.ip); - if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - poff, plen, buffer, buflen)) - return NF_DROP; - } - - /* The received= parameter (RFC 2361) contains the address - * from which the server received the request. */ - if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, - "received=", &poff, &plen, - &addr, false) > 0 && - addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip && - addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - buflen = sprintf(buffer, "%pI4", - &ct->tuplehash[!dir].tuple.src.u3.ip); - if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - poff, plen, buffer, buflen)) - return NF_DROP; - } - - /* The rport= parameter (RFC 3581) contains the port number - * from which the server received the request. */ - if (ct_sip_parse_numerical_param(ct, *dptr, matchend, *datalen, - "rport=", &poff, &plen, - &n) > 0 && - htons(n) == ct->tuplehash[dir].tuple.dst.u.udp.port && - htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { - __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; - buflen = sprintf(buffer, "%u", ntohs(p)); - if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - poff, plen, buffer, buflen)) - return NF_DROP; - } - } - -next: - /* Translate Contact headers */ - coff = 0; - in_header = 0; - while (ct_sip_parse_header_uri(ct, *dptr, &coff, *datalen, - SIP_HDR_CONTACT, &in_header, - &matchoff, &matchlen, - &addr, &port) > 0) { - if (!map_addr(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, - &addr, port)) - return NF_DROP; - } - - if (!map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_FROM) || - !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) - return NF_DROP; - - return NF_ACCEPT; -} - -static void ip_nat_sip_seq_adjust(struct sk_buff *skb, s16 off) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - const struct tcphdr *th; - - if (nf_ct_protonum(ct) != IPPROTO_TCP || off == 0) - return; - - th = (struct tcphdr *)(skb->data + ip_hdrlen(skb)); - nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); -} - -/* Handles expected signalling connections and media streams */ -static void ip_nat_sip_expected(struct nf_conn *ct, - struct nf_conntrack_expect *exp) -{ - struct nf_nat_range range; - - /* This must be a fresh one. */ - BUG_ON(ct->status & IPS_NAT_DONE_MASK); - - /* For DST manip, map port here to where it's expected. */ - range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); - range.min_proto = range.max_proto = exp->saved_proto; - range.min_addr = range.max_addr = exp->saved_addr; - nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); - - /* Change src to where master sends to, but only if the connection - * actually came from the same source. */ - if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == - ct->master->tuplehash[exp->dir].tuple.src.u3.ip) { - range.flags = NF_NAT_RANGE_MAP_IPS; - range.min_addr = range.max_addr - = ct->master->tuplehash[!exp->dir].tuple.dst.u3; - nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); - } -} - -static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - struct nf_conntrack_expect *exp, - unsigned int matchoff, - unsigned int matchlen) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - __be32 newip; - u_int16_t port; - char buffer[sizeof("nnn.nnn.nnn.nnn:nnnnn")]; - unsigned int buflen; - - /* Connection will come from reply */ - if (ct->tuplehash[dir].tuple.src.u3.ip == ct->tuplehash[!dir].tuple.dst.u3.ip) - newip = exp->tuple.dst.u3.ip; - else - newip = ct->tuplehash[!dir].tuple.dst.u3.ip; - - /* If the signalling port matches the connection's source port in the - * original direction, try to use the destination port in the opposite - * direction. */ - if (exp->tuple.dst.u.udp.port == - ct->tuplehash[dir].tuple.src.u.udp.port) - port = ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port); - else - port = ntohs(exp->tuple.dst.u.udp.port); - - exp->saved_addr = exp->tuple.dst.u3; - exp->tuple.dst.u3.ip = newip; - exp->saved_proto.udp.port = exp->tuple.dst.u.udp.port; - exp->dir = !dir; - exp->expectfn = ip_nat_sip_expected; - - for (; port != 0; port++) { - int ret; - - exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(exp); - if (ret == 0) - break; - else if (ret != -EBUSY) { - port = 0; - break; - } - } - - if (port == 0) - return NF_DROP; - - if (exp->tuple.dst.u3.ip != exp->saved_addr.ip || - exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { - buflen = sprintf(buffer, "%pI4:%u", &newip, port); - if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, buffer, buflen)) - goto err; - } - return NF_ACCEPT; - -err: - nf_ct_unexpect_related(exp); - return NF_DROP; -} - -static int mangle_content_len(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - unsigned int matchoff, matchlen; - char buffer[sizeof("65536")]; - int buflen, c_len; - - /* Get actual SDP length */ - if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen, - SDP_HDR_VERSION, SDP_HDR_UNSPEC, - &matchoff, &matchlen) <= 0) - return 0; - c_len = *datalen - matchoff + strlen("v="); - - /* Now, update SDP length */ - if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CONTENT_LENGTH, - &matchoff, &matchlen) <= 0) - return 0; - - buflen = sprintf(buffer, "%u", c_len); - return mangle_packet(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, buffer, buflen); -} - -static int mangle_sdp_packet(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - unsigned int sdpoff, - enum sdp_header_types type, - enum sdp_header_types term, - char *buffer, int buflen) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - unsigned int matchlen, matchoff; - - if (ct_sip_get_sdp_header(ct, *dptr, sdpoff, *datalen, type, term, - &matchoff, &matchlen) <= 0) - return -ENOENT; - return mangle_packet(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, buffer, buflen) ? 0 : -EINVAL; -} - -static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - unsigned int sdpoff, - enum sdp_header_types type, - enum sdp_header_types term, - const union nf_inet_addr *addr) -{ - char buffer[sizeof("nnn.nnn.nnn.nnn")]; - unsigned int buflen; - - buflen = sprintf(buffer, "%pI4", &addr->ip); - if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, - sdpoff, type, term, buffer, buflen)) - return 0; - - return mangle_content_len(skb, protoff, dataoff, dptr, datalen); -} - -static unsigned int ip_nat_sdp_port(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - unsigned int matchoff, - unsigned int matchlen, - u_int16_t port) -{ - char buffer[sizeof("nnnnn")]; - unsigned int buflen; - - buflen = sprintf(buffer, "%u", port); - if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, - matchoff, matchlen, buffer, buflen)) - return 0; - - return mangle_content_len(skb, protoff, dataoff, dptr, datalen); -} - -static unsigned int ip_nat_sdp_session(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - unsigned int sdpoff, - const union nf_inet_addr *addr) -{ - char buffer[sizeof("nnn.nnn.nnn.nnn")]; - unsigned int buflen; - - /* Mangle session description owner and contact addresses */ - buflen = sprintf(buffer, "%pI4", &addr->ip); - if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, - SDP_HDR_OWNER_IP4, SDP_HDR_MEDIA, - buffer, buflen)) - return 0; - - switch (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, - SDP_HDR_CONNECTION_IP4, SDP_HDR_MEDIA, - buffer, buflen)) { - case 0: - /* - * RFC 2327: - * - * Session description - * - * c=* (connection information - not required if included in all media) - */ - case -ENOENT: - break; - default: - return 0; - } - - return mangle_content_len(skb, protoff, dataoff, dptr, datalen); -} - -/* So, this packet has hit the connection tracking matching code. - Mangle it, and change the expectation to match the new version. */ -static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, - unsigned int dataoff, - const char **dptr, unsigned int *datalen, - struct nf_conntrack_expect *rtp_exp, - struct nf_conntrack_expect *rtcp_exp, - unsigned int mediaoff, - unsigned int medialen, - union nf_inet_addr *rtp_addr) -{ - enum ip_conntrack_info ctinfo; - struct nf_conn *ct = nf_ct_get(skb, &ctinfo); - enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - u_int16_t port; - - /* Connection will come from reply */ - if (ct->tuplehash[dir].tuple.src.u3.ip == - ct->tuplehash[!dir].tuple.dst.u3.ip) - rtp_addr->ip = rtp_exp->tuple.dst.u3.ip; - else - rtp_addr->ip = ct->tuplehash[!dir].tuple.dst.u3.ip; - - rtp_exp->saved_addr = rtp_exp->tuple.dst.u3; - rtp_exp->tuple.dst.u3.ip = rtp_addr->ip; - rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port; - rtp_exp->dir = !dir; - rtp_exp->expectfn = ip_nat_sip_expected; - - rtcp_exp->saved_addr = rtcp_exp->tuple.dst.u3; - rtcp_exp->tuple.dst.u3.ip = rtp_addr->ip; - rtcp_exp->saved_proto.udp.port = rtcp_exp->tuple.dst.u.udp.port; - rtcp_exp->dir = !dir; - rtcp_exp->expectfn = ip_nat_sip_expected; - - /* Try to get same pair of ports: if not, try to change them. */ - for (port = ntohs(rtp_exp->tuple.dst.u.udp.port); - port != 0; port += 2) { - int ret; - - rtp_exp->tuple.dst.u.udp.port = htons(port); - ret = nf_ct_expect_related(rtp_exp); - if (ret == -EBUSY) - continue; - else if (ret < 0) { - port = 0; - break; - } - rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - ret = nf_ct_expect_related(rtcp_exp); - if (ret == 0) - break; - else if (ret != -EBUSY) { - nf_ct_unexpect_related(rtp_exp); - port = 0; - break; - } - } - - if (port == 0) - goto err1; - - /* Update media port. */ - if (rtp_exp->tuple.dst.u.udp.port != rtp_exp->saved_proto.udp.port && - !ip_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, - mediaoff, medialen, port)) - goto err2; - - return NF_ACCEPT; - -err2: - nf_ct_unexpect_related(rtp_exp); - nf_ct_unexpect_related(rtcp_exp); -err1: - return NF_DROP; -} - -static struct nf_ct_helper_expectfn sip_nat = { - .name = "sip", - .expectfn = ip_nat_sip_expected, -}; - -static void __exit nf_nat_sip_fini(void) -{ - RCU_INIT_POINTER(nf_nat_sip_hook, NULL); - RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL); - RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL); - RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL); - RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); - RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); - RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); - nf_ct_helper_expectfn_unregister(&sip_nat); - synchronize_rcu(); -} - -static int __init nf_nat_sip_init(void) -{ - BUG_ON(nf_nat_sip_hook != NULL); - BUG_ON(nf_nat_sip_seq_adjust_hook != NULL); - BUG_ON(nf_nat_sip_expect_hook != NULL); - BUG_ON(nf_nat_sdp_addr_hook != NULL); - BUG_ON(nf_nat_sdp_port_hook != NULL); - BUG_ON(nf_nat_sdp_session_hook != NULL); - BUG_ON(nf_nat_sdp_media_hook != NULL); - RCU_INIT_POINTER(nf_nat_sip_hook, ip_nat_sip); - RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, ip_nat_sip_seq_adjust); - RCU_INIT_POINTER(nf_nat_sip_expect_hook, ip_nat_sip_expect); - RCU_INIT_POINTER(nf_nat_sdp_addr_hook, ip_nat_sdp_addr); - RCU_INIT_POINTER(nf_nat_sdp_port_hook, ip_nat_sdp_port); - RCU_INIT_POINTER(nf_nat_sdp_session_hook, ip_nat_sdp_session); - RCU_INIT_POINTER(nf_nat_sdp_media_hook, ip_nat_sdp_media); - nf_ct_helper_expectfn_register(&sip_nat); - return 0; -} - -module_init(nf_nat_sip_init); -module_exit(nf_nat_sip_fini); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 2eee9f1f99ef..bf3e4649efb2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -390,6 +390,11 @@ config NF_NAT_FTP depends on NF_CONNTRACK && NF_NAT default NF_NAT && NF_CONNTRACK_FTP +config NF_NAT_SIP + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_SIP + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 7d6e1ea14c9b..7d6d1a035f31 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o # NAT helpers obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o +obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o # transparent proxy support obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index d5174902db37..df8f4f284481 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -57,7 +57,8 @@ unsigned int (*nf_nat_sip_hook)(struct sk_buff *skb, unsigned int protoff, unsigned int *datalen) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_hook); -void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, s16 off) __read_mostly; +void (*nf_nat_sip_seq_adjust_hook)(struct sk_buff *skb, unsigned int protoff, + s16 off) __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_sip_seq_adjust_hook); unsigned int (*nf_nat_sip_expect_hook)(struct sk_buff *skb, @@ -742,13 +743,18 @@ static int sdp_addr_len(const struct nf_conn *ct, const char *dptr, * be tolerant and also accept records terminated with a single newline * character". We handle both cases. */ -static const struct sip_header ct_sdp_hdrs[] = { - [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), - [SDP_HDR_OWNER_IP4] = SDP_HDR("o=", "IN IP4 ", sdp_addr_len), - [SDP_HDR_CONNECTION_IP4] = SDP_HDR("c=", "IN IP4 ", sdp_addr_len), - [SDP_HDR_OWNER_IP6] = SDP_HDR("o=", "IN IP6 ", sdp_addr_len), - [SDP_HDR_CONNECTION_IP6] = SDP_HDR("c=", "IN IP6 ", sdp_addr_len), - [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), +static const struct sip_header ct_sdp_hdrs_v4[] = { + [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), + [SDP_HDR_OWNER] = SDP_HDR("o=", "IN IP4 ", sdp_addr_len), + [SDP_HDR_CONNECTION] = SDP_HDR("c=", "IN IP4 ", sdp_addr_len), + [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), +}; + +static const struct sip_header ct_sdp_hdrs_v6[] = { + [SDP_HDR_VERSION] = SDP_HDR("v=", NULL, digits_len), + [SDP_HDR_OWNER] = SDP_HDR("o=", "IN IP6 ", sdp_addr_len), + [SDP_HDR_CONNECTION] = SDP_HDR("c=", "IN IP6 ", sdp_addr_len), + [SDP_HDR_MEDIA] = SDP_HDR("m=", NULL, media_len), }; /* Linear string search within SDP header values */ @@ -774,11 +780,14 @@ int ct_sip_get_sdp_header(const struct nf_conn *ct, const char *dptr, enum sdp_header_types term, unsigned int *matchoff, unsigned int *matchlen) { - const struct sip_header *hdr = &ct_sdp_hdrs[type]; - const struct sip_header *thdr = &ct_sdp_hdrs[term]; + const struct sip_header *hdrs, *hdr, *thdr; const char *start = dptr, *limit = dptr + datalen; int shift = 0; + hdrs = nf_ct_l3num(ct) == NFPROTO_IPV4 ? ct_sdp_hdrs_v4 : ct_sdp_hdrs_v6; + hdr = &hdrs[type]; + thdr = &hdrs[term]; + for (dptr += dataoff; dptr < limit; dptr++) { /* Find beginning of line */ if (*dptr != '\r' && *dptr != '\n') @@ -945,12 +954,12 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, exp->class != class) break; #ifdef CONFIG_NF_NAT_NEEDED - if (exp->tuple.src.l3num == AF_INET && !direct_rtp && - (exp->saved_addr.ip != exp->tuple.dst.u3.ip || + if (!direct_rtp && + (!nf_inet_addr_cmp(&exp->saved_addr, &exp->tuple.dst.u3) || exp->saved_proto.udp.port != exp->tuple.dst.u.udp.port) && ct->status & IPS_NAT_MASK) { - daddr->ip = exp->saved_addr.ip; - tuple.dst.u3.ip = exp->saved_addr.ip; + *daddr = exp->saved_addr; + tuple.dst.u3 = exp->saved_addr; tuple.dst.u.udp.port = exp->saved_proto.udp.port; direct_rtp = 1; } else @@ -987,8 +996,7 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff, IPPROTO_UDP, NULL, &rtcp_port); nf_nat_sdp_media = rcu_dereference(nf_nat_sdp_media_hook); - if (nf_nat_sdp_media && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK && !direct_rtp) + if (nf_nat_sdp_media && ct->status & IPS_NAT_MASK && !direct_rtp) ret = nf_nat_sdp_media(skb, protoff, dataoff, dptr, datalen, rtp_exp, rtcp_exp, mediaoff, medialen, daddr); @@ -1044,15 +1052,12 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, unsigned int i; union nf_inet_addr caddr, maddr, rtp_addr; unsigned int port; - enum sdp_header_types c_hdr; const struct sdp_media_type *t; int ret = NF_ACCEPT; typeof(nf_nat_sdp_addr_hook) nf_nat_sdp_addr; typeof(nf_nat_sdp_session_hook) nf_nat_sdp_session; nf_nat_sdp_addr = rcu_dereference(nf_nat_sdp_addr_hook); - c_hdr = nf_ct_l3num(ct) == AF_INET ? SDP_HDR_CONNECTION_IP4 : - SDP_HDR_CONNECTION_IP6; /* Find beginning of session description */ if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen, @@ -1066,7 +1071,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, * the end of the session description. */ caddr_len = 0; if (ct_sip_parse_sdp_addr(ct, *dptr, sdpoff, *datalen, - c_hdr, SDP_HDR_MEDIA, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &matchoff, &matchlen, &caddr) > 0) caddr_len = matchlen; @@ -1096,7 +1101,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, /* The media description overrides the session description. */ maddr_len = 0; if (ct_sip_parse_sdp_addr(ct, *dptr, mediaoff, *datalen, - c_hdr, SDP_HDR_MEDIA, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &matchoff, &matchlen, &maddr) > 0) { maddr_len = matchlen; memcpy(&rtp_addr, &maddr, sizeof(rtp_addr)); @@ -1113,11 +1118,10 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, return ret; /* Update media connection address if present */ - if (maddr_len && nf_nat_sdp_addr && - nf_ct_l3num(ct) == NFPROTO_IPV4 && ct->status & IPS_NAT_MASK) { + if (maddr_len && nf_nat_sdp_addr && ct->status & IPS_NAT_MASK) { ret = nf_nat_sdp_addr(skb, protoff, dataoff, - dptr, datalen, - mediaoff, c_hdr, SDP_HDR_MEDIA, + dptr, datalen, mediaoff, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, &rtp_addr); if (ret != NF_ACCEPT) return ret; @@ -1127,8 +1131,7 @@ static int process_sdp(struct sk_buff *skb, unsigned int protoff, /* Update session connection and owner addresses */ nf_nat_sdp_session = rcu_dereference(nf_nat_sdp_session_hook); - if (nf_nat_sdp_session && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) + if (nf_nat_sdp_session && ct->status & IPS_NAT_MASK) ret = nf_nat_sdp_session(skb, protoff, dataoff, dptr, datalen, sdpoff, &rtp_addr); @@ -1293,8 +1296,7 @@ static int process_register_request(struct sk_buff *skb, unsigned int protoff, exp->flags = NF_CT_EXPECT_PERMANENT | NF_CT_EXPECT_INACTIVE; nf_nat_sip_expect = rcu_dereference(nf_nat_sip_expect_hook); - if (nf_nat_sip_expect && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) + if (nf_nat_sip_expect && ct->status & IPS_NAT_MASK) ret = nf_nat_sip_expect(skb, protoff, dataoff, dptr, datalen, exp, matchoff, matchlen); else { @@ -1476,8 +1478,7 @@ static int process_sip_msg(struct sk_buff *skb, struct nf_conn *ct, else ret = process_sip_response(skb, protoff, dataoff, dptr, datalen); - if (ret == NF_ACCEPT && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) { + if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { nf_nat_sip = rcu_dereference(nf_nat_sip_hook); if (nf_nat_sip && !nf_nat_sip(skb, protoff, dataoff, dptr, datalen)) @@ -1560,11 +1561,10 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, datalen = datalen + diff - msglen; } - if (ret == NF_ACCEPT && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) { + if (ret == NF_ACCEPT && ct->status & IPS_NAT_MASK) { nf_nat_sip_seq_adjust = rcu_dereference(nf_nat_sip_seq_adjust_hook); if (nf_nat_sip_seq_adjust) - nf_nat_sip_seq_adjust(skb, tdiff); + nf_nat_sip_seq_adjust(skb, protoff, tdiff); } return ret; diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c new file mode 100644 index 000000000000..f4db3a7bd285 --- /dev/null +++ b/net/netfilter/nf_nat_sip.c @@ -0,0 +1,609 @@ +/* SIP extension for NAT alteration. + * + * (C) 2005 by Christian Hentschel + * based on RR's ip_nat_ftp.c and other modules. + * (C) 2007 United Security Providers + * (C) 2007, 2008, 2011, 2012 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Christian Hentschel "); +MODULE_DESCRIPTION("SIP NAT helper"); +MODULE_ALIAS("ip_nat_sip"); + + +static unsigned int mangle_packet(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int matchoff, unsigned int matchlen, + const char *buffer, unsigned int buflen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + struct tcphdr *th; + unsigned int baseoff; + + if (nf_ct_protonum(ct) == IPPROTO_TCP) { + th = (struct tcphdr *)(skb->data + protoff); + baseoff = protoff + th->doff * 4; + matchoff += dataoff - baseoff; + + if (!__nf_nat_mangle_tcp_packet(skb, ct, ctinfo, + protoff, matchoff, matchlen, + buffer, buflen, false)) + return 0; + } else { + baseoff = protoff + sizeof(struct udphdr); + matchoff += dataoff - baseoff; + + if (!nf_nat_mangle_udp_packet(skb, ct, ctinfo, + protoff, matchoff, matchlen, + buffer, buflen)) + return 0; + } + + /* Reload data pointer and adjust datalen value */ + *dptr = skb->data + dataoff; + *datalen += buflen - matchlen; + return 1; +} + +static int sip_sprintf_addr(const struct nf_conn *ct, char *buffer, + const union nf_inet_addr *addr, bool delim) +{ + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + return sprintf(buffer, "%pI4", &addr->ip); + else { + if (delim) + return sprintf(buffer, "[%pI6c]", &addr->ip6); + else + return sprintf(buffer, "%pI6c", &addr->ip6); + } +} + +static int sip_sprintf_addr_port(const struct nf_conn *ct, char *buffer, + const union nf_inet_addr *addr, u16 port) +{ + if (nf_ct_l3num(ct) == NFPROTO_IPV4) + return sprintf(buffer, "%pI4:%u", &addr->ip, port); + else + return sprintf(buffer, "[%pI6c]:%u", &addr->ip6, port); +} + +static int map_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int matchoff, unsigned int matchlen, + union nf_inet_addr *addr, __be16 port) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; + unsigned int buflen; + union nf_inet_addr newaddr; + __be16 newport; + + if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, addr) && + ct->tuplehash[dir].tuple.src.u.udp.port == port) { + newaddr = ct->tuplehash[!dir].tuple.dst.u3; + newport = ct->tuplehash[!dir].tuple.dst.u.udp.port; + } else if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, addr) && + ct->tuplehash[dir].tuple.dst.u.udp.port == port) { + newaddr = ct->tuplehash[!dir].tuple.src.u3; + newport = ct->tuplehash[!dir].tuple.src.u.udp.port; + } else + return 1; + + if (nf_inet_addr_cmp(&newaddr, addr) && newport == port) + return 1; + + buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, ntohs(newport)); + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen); +} + +static int map_sip_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + enum sip_header_types type) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + unsigned int matchlen, matchoff; + union nf_inet_addr addr; + __be16 port; + + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, type, NULL, + &matchoff, &matchlen, &addr, &port) <= 0) + return 1; + return map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port); +} + +static unsigned int nf_nat_sip(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + unsigned int coff, matchoff, matchlen; + enum sip_header_types hdr; + union nf_inet_addr addr; + __be16 port; + int request, in_header; + + /* Basic rules: requests and responses. */ + if (strnicmp(*dptr, "SIP/2.0", strlen("SIP/2.0")) != 0) { + if (ct_sip_parse_request(ct, *dptr, *datalen, + &matchoff, &matchlen, + &addr, &port) > 0 && + !map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) + return NF_DROP; + request = 1; + } else + request = 0; + + if (nf_ct_protonum(ct) == IPPROTO_TCP) + hdr = SIP_HDR_VIA_TCP; + else + hdr = SIP_HDR_VIA_UDP; + + /* Translate topmost Via header and parameters */ + if (ct_sip_parse_header_uri(ct, *dptr, NULL, *datalen, + hdr, NULL, &matchoff, &matchlen, + &addr, &port) > 0) { + unsigned int olen, matchend, poff, plen, buflen, n; + char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; + + /* We're only interested in headers related to this + * connection */ + if (request) { + if (!nf_inet_addr_cmp(&addr, + &ct->tuplehash[dir].tuple.src.u3) || + port != ct->tuplehash[dir].tuple.src.u.udp.port) + goto next; + } else { + if (!nf_inet_addr_cmp(&addr, + &ct->tuplehash[dir].tuple.dst.u3) || + port != ct->tuplehash[dir].tuple.dst.u.udp.port) + goto next; + } + + olen = *datalen; + if (!map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, &addr, port)) + return NF_DROP; + + matchend = matchoff + matchlen + *datalen - olen; + + /* The maddr= parameter (RFC 2361) specifies where to send + * the reply. */ + if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, + "maddr=", &poff, &plen, + &addr, true) > 0 && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.src.u3) && + !nf_inet_addr_cmp(&addr, &ct->tuplehash[!dir].tuple.dst.u3)) { + buflen = sip_sprintf_addr(ct, buffer, + &ct->tuplehash[!dir].tuple.dst.u3, + true); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) + return NF_DROP; + } + + /* The received= parameter (RFC 2361) contains the address + * from which the server received the request. */ + if (ct_sip_parse_address_param(ct, *dptr, matchend, *datalen, + "received=", &poff, &plen, + &addr, false) > 0 && + nf_inet_addr_cmp(&addr, &ct->tuplehash[dir].tuple.dst.u3) && + !nf_inet_addr_cmp(&addr, &ct->tuplehash[!dir].tuple.src.u3)) { + buflen = sip_sprintf_addr(ct, buffer, + &ct->tuplehash[!dir].tuple.src.u3, + false); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) + return NF_DROP; + } + + /* The rport= parameter (RFC 3581) contains the port number + * from which the server received the request. */ + if (ct_sip_parse_numerical_param(ct, *dptr, matchend, *datalen, + "rport=", &poff, &plen, + &n) > 0 && + htons(n) == ct->tuplehash[dir].tuple.dst.u.udp.port && + htons(n) != ct->tuplehash[!dir].tuple.src.u.udp.port) { + __be16 p = ct->tuplehash[!dir].tuple.src.u.udp.port; + buflen = sprintf(buffer, "%u", ntohs(p)); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + poff, plen, buffer, buflen)) + return NF_DROP; + } + } + +next: + /* Translate Contact headers */ + coff = 0; + in_header = 0; + while (ct_sip_parse_header_uri(ct, *dptr, &coff, *datalen, + SIP_HDR_CONTACT, &in_header, + &matchoff, &matchlen, + &addr, &port) > 0) { + if (!map_addr(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, + &addr, port)) + return NF_DROP; + } + + if (!map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_FROM) || + !map_sip_addr(skb, protoff, dataoff, dptr, datalen, SIP_HDR_TO)) + return NF_DROP; + + return NF_ACCEPT; +} + +static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, + s16 off) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + const struct tcphdr *th; + + if (nf_ct_protonum(ct) != IPPROTO_TCP || off == 0) + return; + + th = (struct tcphdr *)(skb->data + protoff); + nf_nat_set_seq_adjust(ct, ctinfo, th->seq, off); +} + +/* Handles expected signalling connections and media streams */ +static void nf_nat_sip_expected(struct nf_conn *ct, + struct nf_conntrack_expect *exp) +{ + struct nf_nat_range range; + + /* This must be a fresh one. */ + BUG_ON(ct->status & IPS_NAT_DONE_MASK); + + /* For DST manip, map port here to where it's expected. */ + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); + range.min_proto = range.max_proto = exp->saved_proto; + range.min_addr = range.max_addr = exp->saved_addr; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); + + /* Change src to where master sends to, but only if the connection + * actually came from the same source. */ + if (nf_inet_addr_cmp(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3, + &ct->master->tuplehash[exp->dir].tuple.src.u3)) { + range.flags = NF_NAT_RANGE_MAP_IPS; + range.min_addr = range.max_addr + = ct->master->tuplehash[!exp->dir].tuple.dst.u3; + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); + } +} + +static unsigned int nf_nat_sip_expect(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + struct nf_conntrack_expect *exp, + unsigned int matchoff, + unsigned int matchlen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + union nf_inet_addr newaddr; + u_int16_t port; + char buffer[INET6_ADDRSTRLEN + sizeof("[]:nnnnn")]; + unsigned int buflen; + + /* Connection will come from reply */ + if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3)) + newaddr = exp->tuple.dst.u3; + else + newaddr = ct->tuplehash[!dir].tuple.dst.u3; + + /* If the signalling port matches the connection's source port in the + * original direction, try to use the destination port in the opposite + * direction. */ + if (exp->tuple.dst.u.udp.port == + ct->tuplehash[dir].tuple.src.u.udp.port) + port = ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port); + else + port = ntohs(exp->tuple.dst.u.udp.port); + + exp->saved_addr = exp->tuple.dst.u3; + exp->tuple.dst.u3 = newaddr; + exp->saved_proto.udp.port = exp->tuple.dst.u.udp.port; + exp->dir = !dir; + exp->expectfn = nf_nat_sip_expected; + + for (; port != 0; port++) { + int ret; + + exp->tuple.dst.u.udp.port = htons(port); + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + if (!nf_inet_addr_cmp(&exp->tuple.dst.u3, &exp->saved_addr) || + exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { + buflen = sip_sprintf_addr_port(ct, buffer, &newaddr, port); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen)) + goto err; + } + return NF_ACCEPT; + +err: + nf_ct_unexpect_related(exp); + return NF_DROP; +} + +static int mangle_content_len(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + unsigned int matchoff, matchlen; + char buffer[sizeof("65536")]; + int buflen, c_len; + + /* Get actual SDP length */ + if (ct_sip_get_sdp_header(ct, *dptr, 0, *datalen, + SDP_HDR_VERSION, SDP_HDR_UNSPEC, + &matchoff, &matchlen) <= 0) + return 0; + c_len = *datalen - matchoff + strlen("v="); + + /* Now, update SDP length */ + if (ct_sip_get_header(ct, *dptr, 0, *datalen, SIP_HDR_CONTENT_LENGTH, + &matchoff, &matchlen) <= 0) + return 0; + + buflen = sprintf(buffer, "%u", c_len); + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen); +} + +static int mangle_sdp_packet(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, + enum sdp_header_types type, + enum sdp_header_types term, + char *buffer, int buflen) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + unsigned int matchlen, matchoff; + + if (ct_sip_get_sdp_header(ct, *dptr, sdpoff, *datalen, type, term, + &matchoff, &matchlen) <= 0) + return -ENOENT; + return mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen) ? 0 : -EINVAL; +} + +static unsigned int nf_nat_sdp_addr(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, + enum sdp_header_types type, + enum sdp_header_types term, + const union nf_inet_addr *addr) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + char buffer[INET6_ADDRSTRLEN]; + unsigned int buflen; + + buflen = sip_sprintf_addr(ct, buffer, addr, false); + if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, + sdpoff, type, term, buffer, buflen)) + return 0; + + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); +} + +static unsigned int nf_nat_sdp_port(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int matchoff, + unsigned int matchlen, + u_int16_t port) +{ + char buffer[sizeof("nnnnn")]; + unsigned int buflen; + + buflen = sprintf(buffer, "%u", port); + if (!mangle_packet(skb, protoff, dataoff, dptr, datalen, + matchoff, matchlen, buffer, buflen)) + return 0; + + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); +} + +static unsigned int nf_nat_sdp_session(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + unsigned int sdpoff, + const union nf_inet_addr *addr) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + char buffer[INET6_ADDRSTRLEN]; + unsigned int buflen; + + /* Mangle session description owner and contact addresses */ + buflen = sip_sprintf_addr(ct, buffer, addr, false); + if (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, + SDP_HDR_OWNER, SDP_HDR_MEDIA, buffer, buflen)) + return 0; + + switch (mangle_sdp_packet(skb, protoff, dataoff, dptr, datalen, sdpoff, + SDP_HDR_CONNECTION, SDP_HDR_MEDIA, + buffer, buflen)) { + case 0: + /* + * RFC 2327: + * + * Session description + * + * c=* (connection information - not required if included in all media) + */ + case -ENOENT: + break; + default: + return 0; + } + + return mangle_content_len(skb, protoff, dataoff, dptr, datalen); +} + +/* So, this packet has hit the connection tracking matching code. + Mangle it, and change the expectation to match the new version. */ +static unsigned int nf_nat_sdp_media(struct sk_buff *skb, unsigned int protoff, + unsigned int dataoff, + const char **dptr, unsigned int *datalen, + struct nf_conntrack_expect *rtp_exp, + struct nf_conntrack_expect *rtcp_exp, + unsigned int mediaoff, + unsigned int medialen, + union nf_inet_addr *rtp_addr) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct = nf_ct_get(skb, &ctinfo); + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); + u_int16_t port; + + /* Connection will come from reply */ + if (nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3, + &ct->tuplehash[!dir].tuple.dst.u3)) + *rtp_addr = rtp_exp->tuple.dst.u3; + else + *rtp_addr = ct->tuplehash[!dir].tuple.dst.u3; + + rtp_exp->saved_addr = rtp_exp->tuple.dst.u3; + rtp_exp->tuple.dst.u3 = *rtp_addr; + rtp_exp->saved_proto.udp.port = rtp_exp->tuple.dst.u.udp.port; + rtp_exp->dir = !dir; + rtp_exp->expectfn = nf_nat_sip_expected; + + rtcp_exp->saved_addr = rtcp_exp->tuple.dst.u3; + rtcp_exp->tuple.dst.u3 = *rtp_addr; + rtcp_exp->saved_proto.udp.port = rtcp_exp->tuple.dst.u.udp.port; + rtcp_exp->dir = !dir; + rtcp_exp->expectfn = nf_nat_sip_expected; + + /* Try to get same pair of ports: if not, try to change them. */ + for (port = ntohs(rtp_exp->tuple.dst.u.udp.port); + port != 0; port += 2) { + int ret; + + rtp_exp->tuple.dst.u.udp.port = htons(port); + ret = nf_ct_expect_related(rtp_exp); + if (ret == -EBUSY) + continue; + else if (ret < 0) { + port = 0; + break; + } + rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); + ret = nf_ct_expect_related(rtcp_exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + port = 0; + break; + } + } + + if (port == 0) + goto err1; + + /* Update media port. */ + if (rtp_exp->tuple.dst.u.udp.port != rtp_exp->saved_proto.udp.port && + !nf_nat_sdp_port(skb, protoff, dataoff, dptr, datalen, + mediaoff, medialen, port)) + goto err2; + + return NF_ACCEPT; + +err2: + nf_ct_unexpect_related(rtp_exp); + nf_ct_unexpect_related(rtcp_exp); +err1: + return NF_DROP; +} + +static struct nf_ct_helper_expectfn sip_nat = { + .name = "sip", + .expectfn = nf_nat_sip_expected, +}; + +static void __exit nf_nat_sip_fini(void) +{ + RCU_INIT_POINTER(nf_nat_sip_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, NULL); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, NULL); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, NULL); + nf_ct_helper_expectfn_unregister(&sip_nat); + synchronize_rcu(); +} + +static int __init nf_nat_sip_init(void) +{ + BUG_ON(nf_nat_sip_hook != NULL); + BUG_ON(nf_nat_sip_seq_adjust_hook != NULL); + BUG_ON(nf_nat_sip_expect_hook != NULL); + BUG_ON(nf_nat_sdp_addr_hook != NULL); + BUG_ON(nf_nat_sdp_port_hook != NULL); + BUG_ON(nf_nat_sdp_session_hook != NULL); + BUG_ON(nf_nat_sdp_media_hook != NULL); + RCU_INIT_POINTER(nf_nat_sip_hook, nf_nat_sip); + RCU_INIT_POINTER(nf_nat_sip_seq_adjust_hook, nf_nat_sip_seq_adjust); + RCU_INIT_POINTER(nf_nat_sip_expect_hook, nf_nat_sip_expect); + RCU_INIT_POINTER(nf_nat_sdp_addr_hook, nf_nat_sdp_addr); + RCU_INIT_POINTER(nf_nat_sdp_port_hook, nf_nat_sdp_port); + RCU_INIT_POINTER(nf_nat_sdp_session_hook, nf_nat_sdp_session); + RCU_INIT_POINTER(nf_nat_sdp_media_hook, nf_nat_sdp_media); + nf_ct_helper_expectfn_register(&sip_nat); + return 0; +} + +module_init(nf_nat_sip_init); +module_exit(nf_nat_sip_fini); -- cgit v1.3-14-g43fede From 5901b6be885e2c9a30fd94803b846b3d33e351dd Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 26 Aug 2012 19:14:27 +0200 Subject: netfilter: nf_nat: support IPv6 in IRC NAT helper Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/Kconfig | 5 -- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/nf_nat_irc.c | 99 ---------------------------------------- net/netfilter/Kconfig | 5 ++ net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_irc.c | 3 +- net/netfilter/nf_nat_irc.c | 93 +++++++++++++++++++++++++++++++++++++ 7 files changed, 100 insertions(+), 107 deletions(-) delete mode 100644 net/ipv4/netfilter/nf_nat_irc.c create mode 100644 net/netfilter/nf_nat_irc.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 30197f8003be..843fe17db20d 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -221,11 +221,6 @@ config NF_NAT_PROTO_GRE tristate depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE -config NF_NAT_IRC - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_IRC - config NF_NAT_TFTP tristate depends on NF_CONNTRACK && NF_NAT_IPV4 diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 8914abffc96d..17e649bb98ba 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -21,7 +21,6 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o # NAT helpers (nf_conntrack) obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o -obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c deleted file mode 100644 index 1ce37f89ec78..000000000000 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ /dev/null @@ -1,99 +0,0 @@ -/* IRC extension for TCP NAT alteration. - * - * (C) 2000-2001 by Harald Welte - * (C) 2004 Rusty Russell IBM Corporation - * based on a copy of RR's ip_nat_ftp.c - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#include -#include -#include -#include - -#include -#include -#include -#include -#include - -MODULE_AUTHOR("Harald Welte "); -MODULE_DESCRIPTION("IRC (DCC) NAT helper"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("ip_nat_irc"); - -static unsigned int help(struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - unsigned int protoff, - unsigned int matchoff, - unsigned int matchlen, - struct nf_conntrack_expect *exp) -{ - char buffer[sizeof("4294967296 65635")]; - u_int32_t ip; - u_int16_t port; - unsigned int ret; - - /* Reply comes from server. */ - exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; - exp->dir = IP_CT_DIR_REPLY; - exp->expectfn = nf_nat_follow_master; - - /* Try to get same port: if not, try to change it. */ - for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { - int ret; - - exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); - if (ret == 0) - break; - else if (ret != -EBUSY) { - port = 0; - break; - } - } - - if (port == 0) - return NF_DROP; - - ip = ntohl(exp->master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip); - sprintf(buffer, "%u %u", ip, port); - pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n", - buffer, &ip, port); - - ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, - protoff, matchoff, matchlen, buffer, - strlen(buffer)); - if (ret != NF_ACCEPT) - nf_ct_unexpect_related(exp); - return ret; -} - -static void __exit nf_nat_irc_fini(void) -{ - RCU_INIT_POINTER(nf_nat_irc_hook, NULL); - synchronize_rcu(); -} - -static int __init nf_nat_irc_init(void) -{ - BUG_ON(nf_nat_irc_hook != NULL); - RCU_INIT_POINTER(nf_nat_irc_hook, help); - return 0; -} - -/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ -static int warn_set(const char *val, struct kernel_param *kp) -{ - printk(KERN_INFO KBUILD_MODNAME - ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); - return 0; -} -module_param_call(ports, warn_set, NULL, NULL, 0); - -module_init(nf_nat_irc_init); -module_exit(nf_nat_irc_fini); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index bf3e4649efb2..cabe4da0e191 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -390,6 +390,11 @@ config NF_NAT_FTP depends on NF_CONNTRACK && NF_NAT default NF_NAT && NF_CONNTRACK_FTP +config NF_NAT_IRC + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_IRC + config NF_NAT_SIP tristate depends on NF_CONNTRACK && NF_NAT diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 7d6d1a035f31..0dd792972cae 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_NF_NAT_PROTO_SCTP) += nf_nat_proto_sctp.o # NAT helpers obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o +obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o # transparent proxy support diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 95d097cdb202..3b20aa77cfc8 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -205,8 +205,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, IPPROTO_TCP, NULL, &port); nf_nat_irc = rcu_dereference(nf_nat_irc_hook); - if (nf_nat_irc && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) + if (nf_nat_irc && ct->status & IPS_NAT_MASK) ret = nf_nat_irc(skb, ctinfo, protoff, addr_beg_p - ib_ptr, addr_end_p - addr_beg_p, diff --git a/net/netfilter/nf_nat_irc.c b/net/netfilter/nf_nat_irc.c new file mode 100644 index 000000000000..1fedee6e7fb6 --- /dev/null +++ b/net/netfilter/nf_nat_irc.c @@ -0,0 +1,93 @@ +/* IRC extension for TCP NAT alteration. + * + * (C) 2000-2001 by Harald Welte + * (C) 2004 Rusty Russell IBM Corporation + * based on a copy of RR's ip_nat_ftp.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +MODULE_AUTHOR("Harald Welte "); +MODULE_DESCRIPTION("IRC (DCC) NAT helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat_irc"); + +static unsigned int help(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + unsigned int protoff, + unsigned int matchoff, + unsigned int matchlen, + struct nf_conntrack_expect *exp) +{ + char buffer[sizeof("4294967296 65635")]; + u_int16_t port; + unsigned int ret; + + /* Reply comes from server. */ + exp->saved_proto.tcp.port = exp->tuple.dst.u.tcp.port; + exp->dir = IP_CT_DIR_REPLY; + exp->expectfn = nf_nat_follow_master; + + /* Try to get same port: if not, try to change it. */ + for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + + exp->tuple.dst.u.tcp.port = htons(port); + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; + break; + } + } + + if (port == 0) + return NF_DROP; + + ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, + protoff, matchoff, matchlen, buffer, + strlen(buffer)); + if (ret != NF_ACCEPT) + nf_ct_unexpect_related(exp); + return ret; +} + +static void __exit nf_nat_irc_fini(void) +{ + RCU_INIT_POINTER(nf_nat_irc_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_irc_init(void) +{ + BUG_ON(nf_nat_irc_hook != NULL); + RCU_INIT_POINTER(nf_nat_irc_hook, help); + return 0; +} + +/* Prior to 2.6.11, we had a ports param. No longer, but don't break users. */ +static int warn_set(const char *val, struct kernel_param *kp) +{ + printk(KERN_INFO KBUILD_MODNAME + ": kernel >= 2.6.10 only uses 'ports' for conntrack modules\n"); + return 0; +} +module_param_call(ports, warn_set, NULL, NULL, 0); + +module_init(nf_nat_irc_init); +module_exit(nf_nat_irc_fini); -- cgit v1.3-14-g43fede From 320ff567f299ed3f0a2d53906e632a1b0eda5599 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 26 Aug 2012 19:14:29 +0200 Subject: netfilter: nf_nat: support IPv6 in TFTP NAT helper Signed-off-by: Pablo Neira Ayuso Signed-off-by: Patrick McHardy --- net/ipv4/netfilter/Kconfig | 5 ---- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/nf_nat_tftp.c | 50 --------------------------------------- net/netfilter/Kconfig | 5 ++++ net/netfilter/Makefile | 1 + net/netfilter/nf_conntrack_tftp.c | 3 +-- net/netfilter/nf_nat_tftp.c | 50 +++++++++++++++++++++++++++++++++++++++ 7 files changed, 57 insertions(+), 58 deletions(-) delete mode 100644 net/ipv4/netfilter/nf_nat_tftp.c create mode 100644 net/netfilter/nf_nat_tftp.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 843fe17db20d..131e53702e77 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -221,11 +221,6 @@ config NF_NAT_PROTO_GRE tristate depends on NF_NAT_IPV4 && NF_CT_PROTO_GRE -config NF_NAT_TFTP - tristate - depends on NF_CONNTRACK && NF_NAT_IPV4 - default NF_NAT_IPV4 && NF_CONNTRACK_TFTP - config NF_NAT_PPTP tristate depends on NF_CONNTRACK && NF_NAT_IPV4 diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 17e649bb98ba..b7dd18987237 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -23,7 +23,6 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.o -obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o # NAT protocols (nf_nat) obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o diff --git a/net/ipv4/netfilter/nf_nat_tftp.c b/net/ipv4/netfilter/nf_nat_tftp.c deleted file mode 100644 index ccabbda71a3e..000000000000 --- a/net/ipv4/netfilter/nf_nat_tftp.c +++ /dev/null @@ -1,50 +0,0 @@ -/* (C) 2001-2002 Magnus Boden - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include -#include - -#include -#include -#include -#include - -MODULE_AUTHOR("Magnus Boden "); -MODULE_DESCRIPTION("TFTP NAT helper"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("ip_nat_tftp"); - -static unsigned int help(struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_expect *exp) -{ - const struct nf_conn *ct = exp->master; - - exp->saved_proto.udp.port - = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; - exp->dir = IP_CT_DIR_REPLY; - exp->expectfn = nf_nat_follow_master; - if (nf_ct_expect_related(exp) != 0) - return NF_DROP; - return NF_ACCEPT; -} - -static void __exit nf_nat_tftp_fini(void) -{ - RCU_INIT_POINTER(nf_nat_tftp_hook, NULL); - synchronize_rcu(); -} - -static int __init nf_nat_tftp_init(void) -{ - BUG_ON(nf_nat_tftp_hook != NULL); - RCU_INIT_POINTER(nf_nat_tftp_hook, help); - return 0; -} - -module_init(nf_nat_tftp_init); -module_exit(nf_nat_tftp_fini); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index cabe4da0e191..052836e2490e 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -400,6 +400,11 @@ config NF_NAT_SIP depends on NF_CONNTRACK && NF_NAT default NF_NAT && NF_CONNTRACK_SIP +config NF_NAT_TFTP + tristate + depends on NF_CONNTRACK && NF_NAT + default NF_NAT && NF_CONNTRACK_TFTP + endif # NF_CONNTRACK # transparent proxy support diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0dd792972cae..403ea8125884 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -59,6 +59,7 @@ obj-$(CONFIG_NF_NAT_AMANDA) += nf_nat_amanda.o obj-$(CONFIG_NF_NAT_FTP) += nf_nat_ftp.o obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o +obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o # transparent proxy support obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 9363e1c66466..81fc61c05263 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -72,8 +72,7 @@ static int tftp_help(struct sk_buff *skb, nf_ct_dump_tuple(&exp->tuple); nf_nat_tftp = rcu_dereference(nf_nat_tftp_hook); - if (nf_nat_tftp && nf_ct_l3num(ct) == NFPROTO_IPV4 && - ct->status & IPS_NAT_MASK) + if (nf_nat_tftp && ct->status & IPS_NAT_MASK) ret = nf_nat_tftp(skb, ctinfo, exp); else if (nf_ct_expect_related(exp) != 0) ret = NF_DROP; diff --git a/net/netfilter/nf_nat_tftp.c b/net/netfilter/nf_nat_tftp.c new file mode 100644 index 000000000000..ccabbda71a3e --- /dev/null +++ b/net/netfilter/nf_nat_tftp.c @@ -0,0 +1,50 @@ +/* (C) 2001-2002 Magnus Boden + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include + +#include +#include +#include +#include + +MODULE_AUTHOR("Magnus Boden "); +MODULE_DESCRIPTION("TFTP NAT helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ip_nat_tftp"); + +static unsigned int help(struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + struct nf_conntrack_expect *exp) +{ + const struct nf_conn *ct = exp->master; + + exp->saved_proto.udp.port + = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.udp.port; + exp->dir = IP_CT_DIR_REPLY; + exp->expectfn = nf_nat_follow_master; + if (nf_ct_expect_related(exp) != 0) + return NF_DROP; + return NF_ACCEPT; +} + +static void __exit nf_nat_tftp_fini(void) +{ + RCU_INIT_POINTER(nf_nat_tftp_hook, NULL); + synchronize_rcu(); +} + +static int __init nf_nat_tftp_init(void) +{ + BUG_ON(nf_nat_tftp_hook != NULL); + RCU_INIT_POINTER(nf_nat_tftp_hook, help); + return 0; +} + +module_init(nf_nat_tftp_init); +module_exit(nf_nat_tftp_fini); -- cgit v1.3-14-g43fede From 98d75c3724f9b37cdfdb85f821e10edcb743959e Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Mon, 27 Aug 2012 06:30:01 +0000 Subject: ipv4: Minor logic clean-up in ipv4_mtu In ipv4_mtu there is some logic where we are testing for a non-zero value and a timer expiration, then setting the value to zero, and then testing if the value is zero we set it to a value based on the dst. Instead of bothering with the extra steps it is easier to just cleanup the logic so that we set it to the dst based value if it is zero or if the timer has expired. Signed-off-by: Alexander Duyck --- net/ipv4/route.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d2d1e153e7c4..dc9549b5eb1c 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1134,10 +1134,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) const struct rtable *rt = (const struct rtable *) dst; unsigned int mtu = rt->rt_pmtu; - if (mtu && time_after_eq(jiffies, rt->dst.expires)) - mtu = 0; - - if (!mtu) + if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu && rt_is_output_route(rt)) -- cgit v1.3-14-g43fede From 1046716368979dee857a2b8a91c4a8833f21b9cb Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Fri, 31 Aug 2012 12:29:11 +0000 Subject: tcp: TCP Fast Open Server - header & support functions This patch adds all the necessary data structure and support functions to implement TFO server side. It also documents a number of flags for the sysctl_tcp_fastopen knob, and adds a few Linux extension MIBs. In addition, it includes the following: 1. a new TCP_FASTOPEN socket option an application must call to supply a max backlog allowed in order to enable TFO on its listener. 2. A number of key data structures: "fastopen_rsk" in tcp_sock - for a big socket to access its request_sock for retransmission and ack processing purpose. It is non-NULL iff 3WHS not completed. "fastopenq" in request_sock_queue - points to a per Fast Open listener data structure "fastopen_queue" to keep track of qlen (# of outstanding Fast Open requests) and max_qlen, among other things. "listener" in tcp_request_sock - to point to the original listener for book-keeping purpose, i.e., to maintain qlen against max_qlen as part of defense against IP spoofing attack. 3. various data structure and functions, many in tcp_fastopen.c, to support server side Fast Open cookie operations, including /proc/sys/net/ipv4/tcp_fastopen_key to allow manual rekeying. Signed-off-by: H.K. Jerry Chu Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 29 +++++++++--- include/linux/snmp.h | 4 ++ include/linux/tcp.h | 45 ++++++++++++++++-- include/net/request_sock.h | 36 +++++++++++++++ include/net/tcp.h | 46 ++++++++++++++++--- net/ipv4/proc.c | 4 ++ net/ipv4/sysctl_net_ipv4.c | 45 ++++++++++++++++++ net/ipv4/tcp_fastopen.c | 83 +++++++++++++++++++++++++++++++++- net/ipv4/tcp_input.c | 4 +- 9 files changed, 276 insertions(+), 20 deletions(-) (limited to 'net/ipv4') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index d64e53124b8c..c7fc10724948 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -467,16 +467,31 @@ tcp_syncookies - BOOLEAN tcp_fastopen - INTEGER Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data in the opening SYN packet. To use this feature, the client application - must not use connect(). Instead, it should use sendmsg() or sendto() - with MSG_FASTOPEN flag which performs a TCP handshake automatically. - - The values (bitmap) are: - 1: Enables sending data in the opening SYN on the client - 5: Enables sending data in the opening SYN on the client regardless - of cookie availability. + must use sendmsg() or sendto() with MSG_FASTOPEN flag rather than + connect() to perform a TCP handshake automatically. + + The values (bitmap) are + 1: Enables sending data in the opening SYN on the client. + 2: Enables TCP Fast Open on the server side, i.e., allowing data in + a SYN packet to be accepted and passed to the application before + 3-way hand shake finishes. + 4: Send data in the opening SYN regardless of cookie availability and + without a cookie option. + 0x100: Accept SYN data w/o validating the cookie. + 0x200: Accept data-in-SYN w/o any cookie option present. + 0x400/0x800: Enable Fast Open on all listeners regardless of the + TCP_FASTOPEN socket option. The two different flags designate two + different ways of setting max_qlen without the TCP_FASTOPEN socket + option. Default: 0 + Note that the client & server side Fast Open flags (1 and 2 + respectively) must be also enabled before the rest of flags can take + effect. + + See include/net/tcp.h and the code for more details. + tcp_syn_retries - INTEGER Number of times initial SYNs for an active TCP connection attempt will be retransmitted. Should not be higher than 255. Default value diff --git a/include/linux/snmp.h b/include/linux/snmp.h index ad6e3a6bf9fb..fdfba235f9f1 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -241,6 +241,10 @@ enum LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ LINUX_MIB_TCPSYNCHALLENGE, /* TCPSYNChallenge */ LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */ + LINUX_MIB_TCPFASTOPENPASSIVE, /* TCPFastOpenPassive*/ + LINUX_MIB_TCPFASTOPENPASSIVEFAIL, /* TCPFastOpenPassiveFail */ + LINUX_MIB_TCPFASTOPENLISTENOVERFLOW, /* TCPFastOpenListenOverflow */ + LINUX_MIB_TCPFASTOPENCOOKIEREQD, /* TCPFastOpenCookieReqd */ __LINUX_MIB_MAX }; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index eb125a4c30b3..ae46df590629 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -110,6 +110,7 @@ enum { #define TCP_REPAIR_QUEUE 20 #define TCP_QUEUE_SEQ 21 #define TCP_REPAIR_OPTIONS 22 +#define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ struct tcp_repair_opt { __u32 opt_code; @@ -246,6 +247,7 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb) /* TCP Fast Open */ #define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */ #define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */ +#define TCP_FASTOPEN_COOKIE_SIZE 8 /* the size employed by this impl. */ /* TCP Fast Open Cookie as stored in memory */ struct tcp_fastopen_cookie { @@ -312,9 +314,14 @@ struct tcp_request_sock { /* Only used by TCP MD5 Signature so far. */ const struct tcp_request_sock_ops *af_specific; #endif + struct sock *listener; /* needed for TFO */ u32 rcv_isn; u32 snt_isn; u32 snt_synack; /* synack sent time */ + u32 rcv_nxt; /* the ack # by SYNACK. For + * FastOpen it's the seq# + * after data-in-SYN. + */ }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -505,14 +512,18 @@ struct tcp_sock { struct tcp_md5sig_info __rcu *md5sig_info; #endif -/* TCP fastopen related information */ - struct tcp_fastopen_request *fastopen_req; - /* When the cookie options are generated and exchanged, then this * object holds a reference to them (cookie_values->kref). Also * contains related tcp_cookie_transactions fields. */ struct tcp_cookie_values *cookie_values; + +/* TCP fastopen related information */ + struct tcp_fastopen_request *fastopen_req; + /* fastopen_rsk points to request_sock that resulted in this big + * socket. Used to retransmit SYNACKs etc. + */ + struct request_sock *fastopen_rsk; }; enum tsq_flags { @@ -552,6 +563,34 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) return (struct tcp_timewait_sock *)sk; } +static inline bool tcp_passive_fastopen(const struct sock *sk) +{ + return (sk->sk_state == TCP_SYN_RECV && + tcp_sk(sk)->fastopen_rsk != NULL); +} + +static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc) +{ + return foc->len != -1; +} + +static inline int fastopen_init_queue(struct sock *sk, int backlog) +{ + struct request_sock_queue *queue = + &inet_csk(sk)->icsk_accept_queue; + + if (queue->fastopenq == NULL) { + queue->fastopenq = kzalloc( + sizeof(struct fastopen_queue), + sk->sk_allocation); + if (queue->fastopenq == NULL) + return -ENOMEM; + spin_lock_init(&queue->fastopenq->lock); + } + queue->fastopenq->max_qlen = backlog; + return 0; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_TCP_H */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 4c0766e201e3..c3cdd6c9f448 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -106,6 +106,34 @@ struct listen_sock { struct request_sock *syn_table[0]; }; +/* + * For a TCP Fast Open listener - + * lock - protects the access to all the reqsk, which is co-owned by + * the listener and the child socket. + * qlen - pending TFO requests (still in TCP_SYN_RECV). + * max_qlen - max TFO reqs allowed before TFO is disabled. + * + * XXX (TFO) - ideally these fields can be made as part of "listen_sock" + * structure above. But there is some implementation difficulty due to + * listen_sock being part of request_sock_queue hence will be freed when + * a listener is stopped. But TFO related fields may continue to be + * accessed even after a listener is closed, until its sk_refcnt drops + * to 0 implying no more outstanding TFO reqs. One solution is to keep + * listen_opt around until sk_refcnt drops to 0. But there is some other + * complexity that needs to be resolved. E.g., a listener can be disabled + * temporarily through shutdown()->tcp_disconnect(), and re-enabled later. + */ +struct fastopen_queue { + struct request_sock *rskq_rst_head; /* Keep track of past TFO */ + struct request_sock *rskq_rst_tail; /* requests that caused RST. + * This is part of the defense + * against spoofing attack. + */ + spinlock_t lock; + int qlen; /* # of pending (TCP_SYN_RECV) reqs */ + int max_qlen; /* != 0 iff TFO is currently enabled */ +}; + /** struct request_sock_queue - queue of request_socks * * @rskq_accept_head - FIFO head of established children @@ -129,6 +157,12 @@ struct request_sock_queue { u8 rskq_defer_accept; /* 3 bytes hole, try to pack */ struct listen_sock *listen_opt; + struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been + * enabled on this listener. Check + * max_qlen != 0 in fastopen_queue + * to determine if TFO is enabled + * right at this moment. + */ }; extern int reqsk_queue_alloc(struct request_sock_queue *queue, @@ -136,6 +170,8 @@ extern int reqsk_queue_alloc(struct request_sock_queue *queue, extern void __reqsk_queue_destroy(struct request_sock_queue *queue); extern void reqsk_queue_destroy(struct request_sock_queue *queue); +extern void reqsk_fastopen_remove(struct sock *sk, + struct request_sock *req, bool reset); static inline struct request_sock * reqsk_queue_yank_acceptq(struct request_sock_queue *queue) diff --git a/include/net/tcp.h b/include/net/tcp.h index 0fca06f16463..9f8821e3293a 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -224,8 +224,24 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); /* Bit Flags for sysctl_tcp_fastopen */ #define TFO_CLIENT_ENABLE 1 +#define TFO_SERVER_ENABLE 2 #define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */ +/* Process SYN data but skip cookie validation */ +#define TFO_SERVER_COOKIE_NOT_CHKED 0x100 +/* Accept SYN data w/o any cookie option */ +#define TFO_SERVER_COOKIE_NOT_REQD 0x200 + +/* Force enable TFO on all listeners, i.e., not requiring the + * TCP_FASTOPEN socket option. SOCKOPT1/2 determine how to set max_qlen. + */ +#define TFO_SERVER_WO_SOCKOPT1 0x400 +#define TFO_SERVER_WO_SOCKOPT2 0x800 +/* Always create TFO child sockets on a TFO listener even when + * cookie/data not present. (For testing purpose!) + */ +#define TFO_SERVER_ALWAYS 0x1000 + extern struct inet_timewait_death_row tcp_death_row; /* sysctl variables for tcp */ @@ -421,12 +437,6 @@ extern void tcp_metrics_init(void); extern bool tcp_peer_is_proven(struct request_sock *req, struct dst_entry *dst, bool paws_check); extern bool tcp_remember_stamp(struct sock *sk); extern bool tcp_tw_remember_stamp(struct inet_timewait_sock *tw); -extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, - struct tcp_fastopen_cookie *cookie, - int *syn_loss, unsigned long *last_syn_loss); -extern void tcp_fastopen_cache_set(struct sock *sk, u16 mss, - struct tcp_fastopen_cookie *cookie, - bool syn_lost); extern void tcp_fetch_timewait_stamp(struct sock *sk, struct dst_entry *dst); extern void tcp_disable_fack(struct tcp_sock *tp); extern void tcp_close(struct sock *sk, long timeout); @@ -537,6 +547,7 @@ extern void tcp_send_delayed_ack(struct sock *sk); extern void tcp_cwnd_application_limited(struct sock *sk); extern void tcp_resume_early_retransmit(struct sock *sk); extern void tcp_rearm_rto(struct sock *sk); +extern void tcp_reset(struct sock *sk); /* tcp_timer.c */ extern void tcp_init_xmit_timers(struct sock *); @@ -586,6 +597,7 @@ extern int tcp_mtu_to_mss(struct sock *sk, int pmtu); extern int tcp_mss_to_mtu(struct sock *sk, int mss); extern void tcp_mtup_init(struct sock *sk); extern void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt); +extern void tcp_init_buffer_space(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) { @@ -1104,6 +1116,7 @@ static inline void tcp_openreq_init(struct request_sock *req, req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */ req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; ireq->tstamp_ok = rx_opt->tstamp_ok; @@ -1308,15 +1321,34 @@ extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key); +/* From tcp_fastopen.c */ +extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, + struct tcp_fastopen_cookie *cookie, + int *syn_loss, unsigned long *last_syn_loss); +extern void tcp_fastopen_cache_set(struct sock *sk, u16 mss, + struct tcp_fastopen_cookie *cookie, + bool syn_lost); struct tcp_fastopen_request { /* Fast Open cookie. Size 0 means a cookie request */ struct tcp_fastopen_cookie cookie; struct msghdr *data; /* data in MSG_FASTOPEN */ u16 copied; /* queued in tcp_connect() */ }; - void tcp_free_fastopen_req(struct tcp_sock *tp); +extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; +int tcp_fastopen_reset_cipher(void *key, unsigned int len); +void tcp_fastopen_cookie_gen(__be32 addr, struct tcp_fastopen_cookie *foc); + +#define TCP_FASTOPEN_KEY_LENGTH 16 + +/* Fastopen key context */ +struct tcp_fastopen_context { + struct crypto_cipher __rcu *tfm; + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + struct rcu_head rcu; +}; + /* write queue abstraction */ static inline void tcp_write_queue_purge(struct sock *sk) { diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 957acd12250b..8de53e1ddd54 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -263,6 +263,10 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE), SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE), + SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE), + SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL), + SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW), + SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3e78c79b5586..9205e492dc9d 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -232,6 +232,45 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write, return 0; } +int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; + struct tcp_fastopen_context *ctxt; + int ret; + u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + + tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); + if (!tbl.data) + return -ENOMEM; + + rcu_read_lock(); + ctxt = rcu_dereference(tcp_fastopen_ctx); + if (ctxt) + memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + rcu_read_unlock(); + + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", + user_key[0], user_key[1], user_key[2], user_key[3]); + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + + if (write && ret == 0) { + if (sscanf(tbl.data, "%x-%x-%x-%x", user_key, user_key + 1, + user_key + 2, user_key + 3) != 4) { + ret = -EINVAL; + goto bad_key; + } + tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH); + } + +bad_key: + pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", + user_key[0], user_key[1], user_key[2], user_key[3], + (char *)tbl.data, ret); + kfree(tbl.data); + return ret; +} + static struct ctl_table ipv4_table[] = { { .procname = "tcp_timestamps", @@ -385,6 +424,12 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "tcp_fastopen_key", + .mode = 0600, + .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), + .proc_handler = proc_tcp_fastopen_key, + }, { .procname = "tcp_tw_recycle", .data = &tcp_death_row.sysctl_tw_recycle, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index a7f729c409d7..8f7ef0ad80e5 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -1,10 +1,91 @@ +#include #include #include +#include +#include +#include +#include +#include +#include -int sysctl_tcp_fastopen; +int sysctl_tcp_fastopen __read_mostly; + +struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; + +static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); + +static void tcp_fastopen_ctx_free(struct rcu_head *head) +{ + struct tcp_fastopen_context *ctx = + container_of(head, struct tcp_fastopen_context, rcu); + crypto_free_cipher(ctx->tfm); + kfree(ctx); +} + +int tcp_fastopen_reset_cipher(void *key, unsigned int len) +{ + int err; + struct tcp_fastopen_context *ctx, *octx; + + ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + ctx->tfm = crypto_alloc_cipher("aes", 0, 0); + + if (IS_ERR(ctx->tfm)) { + err = PTR_ERR(ctx->tfm); +error: kfree(ctx); + pr_err("TCP: TFO aes cipher alloc error: %d\n", err); + return err; + } + err = crypto_cipher_setkey(ctx->tfm, key, len); + if (err) { + pr_err("TCP: TFO cipher key error: %d\n", err); + crypto_free_cipher(ctx->tfm); + goto error; + } + memcpy(ctx->key, key, len); + + spin_lock(&tcp_fastopen_ctx_lock); + + octx = rcu_dereference_protected(tcp_fastopen_ctx, + lockdep_is_held(&tcp_fastopen_ctx_lock)); + rcu_assign_pointer(tcp_fastopen_ctx, ctx); + spin_unlock(&tcp_fastopen_ctx_lock); + + if (octx) + call_rcu(&octx->rcu, tcp_fastopen_ctx_free); + return err; +} + +/* Computes the fastopen cookie for the peer. + * The peer address is a 128 bits long (pad with zeros for IPv4). + * + * The caller must check foc->len to determine if a valid cookie + * has been generated successfully. +*/ +void tcp_fastopen_cookie_gen(__be32 addr, struct tcp_fastopen_cookie *foc) +{ + __be32 peer_addr[4] = { addr, 0, 0, 0 }; + struct tcp_fastopen_context *ctx; + + rcu_read_lock(); + ctx = rcu_dereference(tcp_fastopen_ctx); + if (ctx) { + crypto_cipher_encrypt_one(ctx->tfm, + foc->val, + (__u8 *)peer_addr); + foc->len = TCP_FASTOPEN_COOKIE_SIZE; + } + rcu_read_unlock(); +} static int __init tcp_fastopen_init(void) { + __u8 key[TCP_FASTOPEN_KEY_LENGTH]; + + get_random_bytes(key, sizeof(key)); + tcp_fastopen_reset_cipher(key, sizeof(key)); return 0; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ce4ffe9ed556..d47d5fe8f3f0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -378,7 +378,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk) /* 4. Try to fixup all. It is made immediately after connection enters * established state. */ -static void tcp_init_buffer_space(struct sock *sk) +void tcp_init_buffer_space(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); int maxwin; @@ -4038,7 +4038,7 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq) } /* When we get a reset we do this. */ -static void tcp_reset(struct sock *sk) +void tcp_reset(struct sock *sk) { /* We want the right error as BSD sees it (and indeed as we do). */ switch (sk->sk_state) { -- cgit v1.3-14-g43fede From 8336886f786fdacbc19b719c1f7ea91eb70706d4 Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Fri, 31 Aug 2012 12:29:12 +0000 Subject: tcp: TCP Fast Open Server - support TFO listeners This patch builds on top of the previous patch to add the support for TFO listeners. This includes - 1. allocating, properly initializing, and managing the per listener fastopen_queue structure when TFO is enabled 2. changes to the inet_csk_accept code to support TFO. E.g., the request_sock can no longer be freed upon accept(), not until 3WHS finishes 3. allowing a TCP_SYN_RECV socket to properly poll() and sendmsg() if it's a TFO socket 4. properly closing a TFO listener, and a TFO socket before 3WHS finishes 5. supporting TCP_FASTOPEN socket option 6. modifying tcp_check_req() to use to check a TFO socket as well as request_sock 7. supporting TCP's TFO cookie option 8. adding a new SYN-ACK retransmit handler to use the timer directly off the TFO socket rather than the listener socket. Note that TFO server side will not retransmit anything other than SYN-ACK until the 3WHS is completed. The patch also contains an important function "reqsk_fastopen_remove()" to manage the somewhat complex relation between a listener, its request_sock, and the corresponding child socket. See the comment above the function for the detail. Signed-off-by: H.K. Jerry Chu Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- include/net/request_sock.h | 13 ------ include/net/tcp.h | 6 ++- net/core/request_sock.c | 95 +++++++++++++++++++++++++++++++++++++++++ net/ipv4/af_inet.c | 28 +++++++++++- net/ipv4/inet_connection_sock.c | 57 ++++++++++++++++++++++--- net/ipv4/syncookies.c | 1 + net/ipv4/tcp.c | 49 ++++++++++++++++++--- net/ipv4/tcp_ipv4.c | 4 +- net/ipv4/tcp_minisocks.c | 61 +++++++++++++++++++++----- net/ipv4/tcp_output.c | 21 ++++++--- net/ipv4/tcp_timer.c | 39 ++++++++++++++++- net/ipv6/syncookies.c | 1 + net/ipv6/tcp_ipv6.c | 5 ++- 13 files changed, 330 insertions(+), 50 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/request_sock.h b/include/net/request_sock.h index c3cdd6c9f448..b01d8dd9ee7c 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -226,19 +226,6 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue return req; } -static inline struct sock *reqsk_queue_get_child(struct request_sock_queue *queue, - struct sock *parent) -{ - struct request_sock *req = reqsk_queue_remove(queue); - struct sock *child = req->sk; - - WARN_ON(child == NULL); - - sk_acceptq_removed(parent); - __reqsk_free(req); - return child; -} - static inline int reqsk_queue_removed(struct request_sock_queue *queue, struct request_sock *req) { diff --git a/include/net/tcp.h b/include/net/tcp.h index 9f8821e3293a..1421b02a7905 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -424,7 +424,8 @@ extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock * const struct tcphdr *th); extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb, struct request_sock *req, - struct request_sock **prev); + struct request_sock **prev, + bool fastopen); extern int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); extern bool tcp_use_frto(struct sock *sk); @@ -478,7 +479,8 @@ extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, extern int tcp_connect(struct sock *sk); extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp); + struct request_values *rvp, + struct tcp_fastopen_cookie *foc); extern int tcp_disconnect(struct sock *sk, int flags); void tcp_connect_init(struct sock *sk); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index 9b570a6a33c5..c31d9e8668c3 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -130,3 +131,97 @@ void reqsk_queue_destroy(struct request_sock_queue *queue) kfree(lopt); } +/* + * This function is called to set a Fast Open socket's "fastopen_rsk" field + * to NULL when a TFO socket no longer needs to access the request_sock. + * This happens only after 3WHS has been either completed or aborted (e.g., + * RST is received). + * + * Before TFO, a child socket is created only after 3WHS is completed, + * hence it never needs to access the request_sock. things get a lot more + * complex with TFO. A child socket, accepted or not, has to access its + * request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts, + * until 3WHS is either completed or aborted. Afterwards the req will stay + * until either the child socket is accepted, or in the rare case when the + * listener is closed before the child is accepted. + * + * In short, a request socket is only freed after BOTH 3WHS has completed + * (or aborted) and the child socket has been accepted (or listener closed). + * When a child socket is accepted, its corresponding req->sk is set to + * NULL since it's no longer needed. More importantly, "req->sk == NULL" + * will be used by the code below to determine if a child socket has been + * accepted or not, and the check is protected by the fastopenq->lock + * described below. + * + * Note that fastopen_rsk is only accessed from the child socket's context + * with its socket lock held. But a request_sock (req) can be accessed by + * both its child socket through fastopen_rsk, and a listener socket through + * icsk_accept_queue.rskq_accept_head. To protect the access a simple spin + * lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created. + * only in the rare case when both the listener and the child locks are held, + * e.g., in inet_csk_listen_stop() do we not need to acquire the lock. + * The lock also protects other fields such as fastopenq->qlen, which is + * decremented by this function when fastopen_rsk is no longer needed. + * + * Note that another solution was to simply use the existing socket lock + * from the listener. But first socket lock is difficult to use. It is not + * a simple spin lock - one must consider sock_owned_by_user() and arrange + * to use sk_add_backlog() stuff. But what really makes it infeasible is the + * locking hierarchy violation. E.g., inet_csk_listen_stop() may try to + * acquire a child's lock while holding listener's socket lock. A corner + * case might also exist in tcp_v4_hnd_req() that will trigger this locking + * order. + * + * When a TFO req is created, it needs to sock_hold its listener to prevent + * the latter data structure from going away. + * + * This function also sets "treq->listener" to NULL and unreference listener + * socket. treq->listener is used by the listener so it is protected by the + * fastopenq->lock in this function. + */ +void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, + bool reset) +{ + struct sock *lsk = tcp_rsk(req)->listener; + struct fastopen_queue *fastopenq = + inet_csk(lsk)->icsk_accept_queue.fastopenq; + + BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk)); + + tcp_sk(sk)->fastopen_rsk = NULL; + spin_lock_bh(&fastopenq->lock); + fastopenq->qlen--; + tcp_rsk(req)->listener = NULL; + if (req->sk) /* the child socket hasn't been accepted yet */ + goto out; + + if (!reset || lsk->sk_state != TCP_LISTEN) { + /* If the listener has been closed don't bother with the + * special RST handling below. + */ + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); + reqsk_free(req); + return; + } + /* Wait for 60secs before removing a req that has triggered RST. + * This is a simple defense against TFO spoofing attack - by + * counting the req against fastopen.max_qlen, and disabling + * TFO when the qlen exceeds max_qlen. + * + * For more details see CoNext'11 "TCP Fast Open" paper. + */ + req->expires = jiffies + 60*HZ; + if (fastopenq->rskq_rst_head == NULL) + fastopenq->rskq_rst_head = req; + else + fastopenq->rskq_rst_tail->dl_next = req; + + req->dl_next = NULL; + fastopenq->rskq_rst_tail = req; + fastopenq->qlen++; +out: + spin_unlock_bh(&fastopenq->lock); + sock_put(lsk); + return; +} diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6681ccf5c3ee..4f70ef0b946d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -149,6 +149,11 @@ void inet_sock_destruct(struct sock *sk) pr_err("Attempt to release alive inet socket %p\n", sk); return; } + if (sk->sk_type == SOCK_STREAM) { + struct fastopen_queue *fastopenq = + inet_csk(sk)->icsk_accept_queue.fastopenq; + kfree(fastopenq); + } WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(atomic_read(&sk->sk_wmem_alloc)); @@ -212,6 +217,26 @@ int inet_listen(struct socket *sock, int backlog) * we can only allow the backlog to be adjusted. */ if (old_state != TCP_LISTEN) { + /* Check special setups for testing purpose to enable TFO w/o + * requiring TCP_FASTOPEN sockopt. + * Note that only TCP sockets (SOCK_STREAM) will reach here. + * Also fastopenq may already been allocated because this + * socket was in TCP_LISTEN state previously but was + * shutdown() (rather than close()). + */ + if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && + inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) { + if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) + err = fastopen_init_queue(sk, backlog); + else if ((sysctl_tcp_fastopen & + TFO_SERVER_WO_SOCKOPT2) != 0) + err = fastopen_init_queue(sk, + ((uint)sysctl_tcp_fastopen) >> 16); + else + err = 0; + if (err) + goto out; + } err = inet_csk_listen_start(sk, backlog); if (err) goto out; @@ -701,7 +726,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & - (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE))); + (TCPF_ESTABLISHED | TCPF_SYN_RECV | + TCPF_CLOSE_WAIT | TCPF_CLOSE))); sock_graft(sk2, newsock); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7f75f21d7b83..8464b79c493f 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -283,7 +283,9 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo) struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) { struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct sock *newsk; + struct request_sock *req; int error; lock_sock(sk); @@ -296,7 +298,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) goto out_err; /* Find already established connection */ - if (reqsk_queue_empty(&icsk->icsk_accept_queue)) { + if (reqsk_queue_empty(queue)) { long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK); /* If this is a non blocking socket don't sleep */ @@ -308,14 +310,32 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) if (error) goto out_err; } - - newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk); - WARN_ON(newsk->sk_state == TCP_SYN_RECV); + req = reqsk_queue_remove(queue); + newsk = req->sk; + + sk_acceptq_removed(sk); + if (sk->sk_type == SOCK_STREAM && queue->fastopenq != NULL) { + spin_lock_bh(&queue->fastopenq->lock); + if (tcp_rsk(req)->listener) { + /* We are still waiting for the final ACK from 3WHS + * so can't free req now. Instead, we set req->sk to + * NULL to signify that the child socket is taken + * so reqsk_fastopen_remove() will free the req + * when 3WHS finishes (or is aborted). + */ + req->sk = NULL; + req = NULL; + } + spin_unlock_bh(&queue->fastopenq->lock); + } out: release_sock(sk); + if (req) + __reqsk_free(req); return newsk; out_err: newsk = NULL; + req = NULL; *err = error; goto out; } @@ -720,13 +740,14 @@ EXPORT_SYMBOL_GPL(inet_csk_listen_start); void inet_csk_listen_stop(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct request_sock *acc_req; struct request_sock *req; inet_csk_delete_keepalive_timer(sk); /* make all the listen_opt local to us */ - acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue); + acc_req = reqsk_queue_yank_acceptq(queue); /* Following specs, it would be better either to send FIN * (and enter FIN-WAIT-1, it is normal close) @@ -736,7 +757,7 @@ void inet_csk_listen_stop(struct sock *sk) * To be honest, we are not able to make either * of the variants now. --ANK */ - reqsk_queue_destroy(&icsk->icsk_accept_queue); + reqsk_queue_destroy(queue); while ((req = acc_req) != NULL) { struct sock *child = req->sk; @@ -754,6 +775,19 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); + if (sk->sk_type == SOCK_STREAM && tcp_rsk(req)->listener) { + BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(sk != tcp_rsk(req)->listener); + + /* Paranoid, to prevent race condition if + * an inbound pkt destined for child is + * blocked by sock lock in tcp_v4_rcv(). + * Also to satisfy an assertion in + * tcp_v4_destroy_sock(). + */ + tcp_sk(child)->fastopen_rsk = NULL; + sock_put(sk); + } inet_csk_destroy_sock(child); bh_unlock_sock(child); @@ -763,6 +797,17 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); __reqsk_free(req); } + if (queue->fastopenq != NULL) { + /* Free all the reqs queued in rskq_rst_head. */ + spin_lock_bh(&queue->fastopenq->lock); + acc_req = queue->fastopenq->rskq_rst_head; + queue->fastopenq->rskq_rst_head = NULL; + spin_unlock_bh(&queue->fastopenq->lock); + while ((req = acc_req) != NULL) { + acc_req = req->dl_next; + __reqsk_free(req); + } + } WARN_ON(sk->sk_ack_backlog); } EXPORT_SYMBOL_GPL(inet_csk_listen_stop); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 650e1528e1e6..ba48e799b031 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -319,6 +319,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->listener = NULL; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2109ff4a1daf..df83d744e380 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -486,8 +486,9 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= POLLIN | POLLRDNORM | POLLRDHUP; - /* Connected? */ - if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) { + /* Connected or passive Fast Open socket? */ + if (sk->sk_state != TCP_SYN_SENT && + (sk->sk_state != TCP_SYN_RECV || tp->fastopen_rsk != NULL)) { int target = sock_rcvlowat(sk, 0, INT_MAX); if (tp->urg_seq == tp->copied_seq && @@ -840,10 +841,15 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse ssize_t copied; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* Wait for a connection to finish. */ - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) + /* Wait for a connection to finish. One exception is TCP Fast Open + * (passive side) where data is allowed to be sent before a connection + * is fully established. + */ + if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && + !tcp_passive_fastopen(sk)) { if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto out_err; + } clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); @@ -1042,10 +1048,15 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); - /* Wait for a connection to finish. */ - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) + /* Wait for a connection to finish. One exception is TCP Fast Open + * (passive side) where data is allowed to be sent before a connection + * is fully established. + */ + if (((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) && + !tcp_passive_fastopen(sk)) { if ((err = sk_stream_wait_connect(sk, &timeo)) != 0) goto do_error; + } if (unlikely(tp->repair)) { if (tp->repair_queue == TCP_RECV_QUEUE) { @@ -2144,6 +2155,10 @@ void tcp_close(struct sock *sk, long timeout) * they look as CLOSING or LAST_ACK for Linux) * Probably, I missed some more holelets. * --ANK + * XXX (TFO) - To start off we don't support SYN+ACK+FIN + * in a single packet! (May consider it later but will + * probably need API support or TCP_CORK SYN-ACK until + * data is written and socket is closed.) */ tcp_send_fin(sk); } @@ -2215,8 +2230,16 @@ adjudge_to_death: } } - if (sk->sk_state == TCP_CLOSE) + if (sk->sk_state == TCP_CLOSE) { + struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + /* We could get here with a non-NULL req if the socket is + * aborted (e.g., closed with unread data) before 3WHS + * finishes. + */ + if (req != NULL) + reqsk_fastopen_remove(sk, req, false); inet_csk_destroy_sock(sk); + } /* Otherwise, socket is reprieved until protocol close. */ out: @@ -2688,6 +2711,14 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else icsk->icsk_user_timeout = msecs_to_jiffies(val); break; + + case TCP_FASTOPEN: + if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE | + TCPF_LISTEN))) + err = fastopen_init_queue(sk, val); + else + err = -EINVAL; + break; default: err = -ENOPROTOOPT; break; @@ -3501,11 +3532,15 @@ EXPORT_SYMBOL(tcp_cookie_generator); void tcp_done(struct sock *sk) { + struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); tcp_clear_xmit_timers(sk); + if (req != NULL) + reqsk_fastopen_remove(sk, req, false); sk->sk_shutdown = SHUTDOWN_MASK; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 36f02f954ac1..bb148dee1edd 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -839,7 +839,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req, rvp); + skb = tcp_make_synack(sk, dst, req, rvp, NULL); if (skb) { __tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr); @@ -1554,7 +1554,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) struct request_sock *req = inet_csk_search_req(sk, &prev, th->source, iph->saddr, iph->daddr); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6ff7f10dce9d..e965319d610b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -507,6 +507,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; TCP_ECN_openreq_child(newtp, req); + newtp->fastopen_rsk = NULL; TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_PASSIVEOPENS); } @@ -515,13 +516,18 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, EXPORT_SYMBOL(tcp_create_openreq_child); /* - * Process an incoming packet for SYN_RECV sockets represented - * as a request_sock. + * Process an incoming packet for SYN_RECV sockets represented as a + * request_sock. Normally sk is the listener socket but for TFO it + * points to the child socket. + * + * XXX (TFO) - The current impl contains a special check for ack + * validation and inside tcp_v4_reqsk_send_ack(). Can we do better? */ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, - struct request_sock **prev) + struct request_sock **prev, + bool fastopen) { struct tcp_options_received tmp_opt; const u8 *hash_location; @@ -530,6 +536,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); bool paws_reject = false; + BUG_ON(fastopen == (sk->sk_state == TCP_LISTEN)); + tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(struct tcphdr)>>2)) { tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); @@ -565,6 +573,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. + * + * Note that even if there is new data in the SYN packet + * they will be thrown away too. */ req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; @@ -622,9 +633,12 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * sent (the segment carries an unacceptable ACK) ... * a reset is sent." * - * Invalid ACK: reset will be sent by listening socket + * Invalid ACK: reset will be sent by listening socket. + * Note that the ACK validity check for a Fast Open socket is done + * elsewhere and is checked directly against the child socket rather + * than req because user data may have been sent out. */ - if ((flg & TCP_FLAG_ACK) && + if ((flg & TCP_FLAG_ACK) && !fastopen && (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk)))) return sk; @@ -637,7 +651,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* RFC793: "first check sequence number". */ if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, - tcp_rsk(req)->rcv_isn + 1, tcp_rsk(req)->rcv_isn + 1 + req->rcv_wnd)) { + tcp_rsk(req)->rcv_nxt, tcp_rsk(req)->rcv_nxt + req->rcv_wnd)) { /* Out of window: send ACK and drop. */ if (!(flg & TCP_FLAG_RST)) req->rsk_ops->send_ack(sk, skb, req); @@ -648,7 +662,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ - if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_isn + 1)) + if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) req->ts_recent = tmp_opt.rcv_tsval; if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { @@ -667,10 +681,19 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* ACK sequence verified above, just make sure ACK is * set. If ACK not set, just silently drop the packet. + * + * XXX (TFO) - if we ever allow "data after SYN", the + * following check needs to be removed. */ if (!(flg & TCP_FLAG_ACK)) return NULL; + /* For Fast Open no more processing is needed (sk is the + * child socket). + */ + if (fastopen) + return sk; + /* While TCP_DEFER_ACCEPT is active, drop bare ACK. */ if (req->retrans < inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { @@ -706,11 +729,21 @@ listen_overflow: } embryonic_reset: - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); - if (!(flg & TCP_FLAG_RST)) + if (!(flg & TCP_FLAG_RST)) { + /* Received a bad SYN pkt - for TFO We try not to reset + * the local connection unless it's really necessary to + * avoid becoming vulnerable to outside attack aiming at + * resetting legit local connections. + */ req->rsk_ops->send_reset(sk, skb); - - inet_csk_reqsk_queue_drop(sk, req, prev); + } else if (fastopen) { /* received a valid RST pkt */ + reqsk_fastopen_remove(sk, req, true); + tcp_reset(sk); + } + if (!fastopen) { + inet_csk_reqsk_queue_drop(sk, req, prev); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_EMBRYONICRSTS); + } return NULL; } EXPORT_SYMBOL(tcp_check_req); @@ -719,6 +752,12 @@ EXPORT_SYMBOL(tcp_check_req); * Queue segment on the new socket if the new socket is active, * otherwise we just shortcircuit this and continue with * the new socket. + * + * For the vast majority of cases child->sk_state will be TCP_SYN_RECV + * when entering. But other states are possible due to a race condition + * where after __inet_lookup_established() fails but before the listener + * locked is obtained, other packets cause the same connection to + * be created. */ int tcp_child_process(struct sock *parent, struct sock *child, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index d04632673a9e..9383b51f3efc 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -702,7 +702,8 @@ static unsigned int tcp_synack_options(struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5, - struct tcp_extend_values *xvp) + struct tcp_extend_values *xvp, + struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -747,7 +748,15 @@ static unsigned int tcp_synack_options(struct sock *sk, if (unlikely(!ireq->tstamp_ok)) remaining -= TCPOLEN_SACKPERM_ALIGNED; } - + if (foc != NULL) { + u32 need = TCPOLEN_EXP_FASTOPEN_BASE + foc->len; + need = (need + 3) & ~3U; /* Align to 32 bits */ + if (remaining >= need) { + opts->options |= OPTION_FAST_OPEN_COOKIE; + opts->fastopen_cookie = foc; + remaining -= need; + } + } /* Similar rationale to tcp_syn_options() applies here, too. * If the options fit, the same options should fit now! */ @@ -2658,7 +2667,8 @@ int tcp_send_synack(struct sock *sk) */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, struct request_sock *req, - struct request_values *rvp) + struct request_values *rvp, + struct tcp_fastopen_cookie *foc) { struct tcp_out_options opts; struct tcp_extend_values *xvp = tcp_xv(rvp); @@ -2718,7 +2728,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #endif TCP_SKB_CB(skb)->when = tcp_time_stamp; tcp_header_size = tcp_synack_options(sk, req, mss, - skb, &opts, &md5, xvp) + skb, &opts, &md5, xvp, foc) + sizeof(*th); skb_push(skb, tcp_header_size); @@ -2772,7 +2782,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, } th->seq = htonl(TCP_SKB_CB(skb)->seq); - th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); + /* XXX data is queued and acked as is. No buffer/window check */ + th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b774a03bd1dc..fc04711e80c8 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -304,6 +304,35 @@ static void tcp_probe_timer(struct sock *sk) } } +/* + * Timer for Fast Open socket to retransmit SYNACK. Note that the + * sk here is the child socket, not the parent (listener) socket. + */ +static void tcp_fastopen_synack_timer(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + int max_retries = icsk->icsk_syn_retries ? : + sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ + struct request_sock *req; + + req = tcp_sk(sk)->fastopen_rsk; + req->rsk_ops->syn_ack_timeout(sk, req); + + if (req->retrans >= max_retries) { + tcp_write_err(sk); + return; + } + /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error + * returned from rtx_syn_ack() to make it more persistent like + * regular retransmit because if the child socket has been accepted + * it's not good to give up too easily. + */ + req->rsk_ops->rtx_syn_ack(sk, req, NULL); + req->retrans++; + inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_TIMEOUT_INIT << req->retrans, TCP_RTO_MAX); +} + /* * The TCP retransmit timer. */ @@ -317,7 +346,15 @@ void tcp_retransmit_timer(struct sock *sk) tcp_resume_early_retransmit(sk); return; } - + if (tp->fastopen_rsk) { + BUG_ON(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); + tcp_fastopen_synack_timer(sk); + /* Before we receive ACK to our SYN-ACK don't retransmit + * anything else (e.g., data or FIN segments). + */ + return; + } if (!tp->packets_out) goto out; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index bb46061c813a..182ab9a85d6c 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -190,6 +190,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq6 = inet6_rsk(req); treq = tcp_rsk(req); + treq->listener = NULL; if (security_inet_conn_request(sk, skb, req)) goto out_free; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f99b81d53cca..09078b9bc6f6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -475,7 +475,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) goto done; - skb = tcp_make_synack(sk, dst, req, rvp); + skb = tcp_make_synack(sk, dst, req, rvp, NULL); if (skb) { __tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr); @@ -987,7 +987,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, inet6_iif(skb)); if (req) - return tcp_check_req(sk, skb, req, prev); + return tcp_check_req(sk, skb, req, prev, false); nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, @@ -1179,6 +1179,7 @@ have_isn: want_cookie) goto drop_and_free; + tcp_rsk(req)->listener = NULL; inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; -- cgit v1.3-14-g43fede From 168a8f58059a22feb9e9a2dcc1b8053dbbbc12ef Mon Sep 17 00:00:00 2001 From: Jerry Chu Date: Fri, 31 Aug 2012 12:29:13 +0000 Subject: tcp: TCP Fast Open Server - main code path This patch adds the main processing path to complete the TFO server patches. A TFO request (i.e., SYN+data packet with a TFO cookie option) first gets processed in tcp_v4_conn_request(). If it passes the various TFO checks by tcp_fastopen_check(), a child socket will be created right away to be accepted by applications, rather than waiting for the 3WHS to finish. In additon to the use of TFO cookie, a simple max_qlen based scheme is put in place to fend off spoofed TFO attack. When a valid ACK comes back to tcp_rcv_state_process(), it will cause the state of the child socket to switch from either TCP_SYN_RECV to TCP_ESTABLISHED, or TCP_FIN_WAIT1 to TCP_FIN_WAIT2. At this time retransmission will resume for any unack'ed (data, FIN,...) segments. Signed-off-by: H.K. Jerry Chu Cc: Yuchung Cheng Cc: Neal Cardwell Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 71 +++++++++++--- net/ipv4/tcp_ipv4.c | 265 ++++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 309 insertions(+), 27 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d47d5fe8f3f0..8c304a400798 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3127,6 +3127,12 @@ void tcp_rearm_rto(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + /* If the retrans timer is currently being used by Fast Open + * for SYN-ACK retrans purpose, stay put. + */ + if (tp->fastopen_rsk) + return; + if (!tp->packets_out) { inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); } else { @@ -5895,7 +5901,9 @@ discard: tcp_send_synack(sk); #if 0 /* Note, we could accept data and URG from this segment. - * There are no obstacles to make this. + * There are no obstacles to make this (except that we must + * either change tcp_recvmsg() to prevent it from returning data + * before 3WHS completes per RFC793, or employ TCP Fast Open). * * However, if we ignore data in ACKless segments sometimes, * we have no reasons to accept it sometimes. @@ -5935,6 +5943,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; int queued = 0; tp->rx_opt.saw_tstamp = 0; @@ -5990,7 +5999,14 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 0; } - if (!tcp_validate_incoming(sk, skb, th, 0)) + req = tp->fastopen_rsk; + if (req != NULL) { + BUG_ON(sk->sk_state != TCP_SYN_RECV && + sk->sk_state != TCP_FIN_WAIT1); + + if (tcp_check_req(sk, skb, req, NULL, true) == NULL) + goto discard; + } else if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; /* step 5: check the ACK field */ @@ -6000,7 +6016,22 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, switch (sk->sk_state) { case TCP_SYN_RECV: if (acceptable) { - tp->copied_seq = tp->rcv_nxt; + /* Once we leave TCP_SYN_RECV, we no longer + * need req so release it. + */ + if (req) { + reqsk_fastopen_remove(sk, req, false); + } else { + /* Make sure socket is routed, for + * correct metrics. + */ + icsk->icsk_af_ops->rebuild_header(sk); + tcp_init_congestion_control(sk); + + tcp_mtup_init(sk); + tcp_init_buffer_space(sk); + tp->copied_seq = tp->rcv_nxt; + } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); @@ -6022,23 +6053,27 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; - /* Make sure socket is routed, for - * correct metrics. - */ - icsk->icsk_af_ops->rebuild_header(sk); - - tcp_init_metrics(sk); - - tcp_init_congestion_control(sk); + if (req) { + /* Re-arm the timer because data may + * have been sent out. This is similar + * to the regular data transmission case + * when new data has just been ack'ed. + * + * (TFO) - we could try to be more + * aggressive and retranmitting any data + * sooner based on when they were sent + * out. + */ + tcp_rearm_rto(sk); + } else + tcp_init_metrics(sk); /* Prevent spurious tcp_cwnd_restart() on * first data packet. */ tp->lsndtime = tcp_time_stamp; - tcp_mtup_init(sk); tcp_initialize_rcv_mss(sk); - tcp_init_buffer_space(sk); tcp_fast_path_on(tp); } else { return 1; @@ -6046,6 +6081,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, break; case TCP_FIN_WAIT1: + /* If we enter the TCP_FIN_WAIT1 state and we are a + * Fast Open socket and this is the first acceptable + * ACK we have received, this would have acknowledged + * our SYNACK so stop the SYNACK timer. + */ + if (acceptable && req != NULL) { + /* We no longer need the request sock. */ + reqsk_fastopen_remove(sk, req, false); + tcp_rearm_rto(sk); + } if (tp->snd_una == tp->write_seq) { struct dst_entry *dst; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bb148dee1edd..e64abed249cc 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -352,6 +352,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) const int code = icmp_hdr(icmp_skb)->code; struct sock *sk; struct sk_buff *skb; + struct request_sock *req; __u32 seq; __u32 remaining; int err; @@ -394,9 +395,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); + req = tp->fastopen_rsk; seq = ntohl(th->seq); if (sk->sk_state != TCP_LISTEN && - !between(seq, tp->snd_una, tp->snd_nxt)) { + !between(seq, tp->snd_una, tp->snd_nxt) && + (req == NULL || seq != tcp_rsk(req)->snt_isn)) { + /* For a Fast Open socket, allow seq to be snt_isn. */ NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -435,6 +439,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) !icsk->icsk_backoff) break; + /* XXX (TFO) - revisit the following logic for TFO */ + if (sock_owned_by_user(sk)) break; @@ -466,6 +472,14 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) goto out; } + /* XXX (TFO) - if it's a TFO socket and has been accepted, rather + * than following the TCP_SYN_RECV case and closing the socket, + * we ignore the ICMP error and keep trying like a fully established + * socket. Is this the right thing to do? + */ + if (req && req->sk == NULL) + goto out; + switch (sk->sk_state) { struct request_sock *req, **prev; case TCP_LISTEN: @@ -498,7 +512,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) case TCP_SYN_SENT: case TCP_SYN_RECV: /* Cannot happen. - It can f.e. if SYNs crossed. + It can f.e. if SYNs crossed, + or Fast Open. */ if (!sock_owned_by_user(sk)) { sk->sk_err = err; @@ -809,8 +824,12 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { - tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, - tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, + /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV + * sk->sk_state == TCP_SYN_RECV -> for Fast Open. + */ + tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ? + tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, + tcp_rsk(req)->rcv_nxt, req->rcv_wnd, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr, @@ -1272,6 +1291,178 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { }; #endif +static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct tcp_fastopen_cookie *valid_foc) +{ + bool skip_cookie = false; + struct fastopen_queue *fastopenq; + + if (likely(!fastopen_cookie_present(foc))) { + /* See include/net/tcp.h for the meaning of these knobs */ + if ((sysctl_tcp_fastopen & TFO_SERVER_ALWAYS) || + ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD) && + (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1))) + skip_cookie = true; /* no cookie to validate */ + else + return false; + } + fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; + /* A FO option is present; bump the counter. */ + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); + + /* Make sure the listener has enabled fastopen, and we don't + * exceed the max # of pending TFO requests allowed before trying + * to validating the cookie in order to avoid burning CPU cycles + * unnecessarily. + * + * XXX (TFO) - The implication of checking the max_qlen before + * processing a cookie request is that clients can't differentiate + * between qlen overflow causing Fast Open to be disabled + * temporarily vs a server not supporting Fast Open at all. + */ + if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) == 0 || + fastopenq == NULL || fastopenq->max_qlen == 0) + return false; + + if (fastopenq->qlen >= fastopenq->max_qlen) { + struct request_sock *req1; + spin_lock(&fastopenq->lock); + req1 = fastopenq->rskq_rst_head; + if ((req1 == NULL) || time_after(req1->expires, jiffies)) { + spin_unlock(&fastopenq->lock); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); + /* Avoid bumping LINUX_MIB_TCPFASTOPENPASSIVEFAIL*/ + foc->len = -1; + return false; + } + fastopenq->rskq_rst_head = req1->dl_next; + fastopenq->qlen--; + spin_unlock(&fastopenq->lock); + reqsk_free(req1); + } + if (skip_cookie) { + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + return true; + } + if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) { + if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) { + tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc); + if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) || + memcmp(&foc->val[0], &valid_foc->val[0], + TCP_FASTOPEN_COOKIE_SIZE) != 0) + return false; + valid_foc->len = -1; + } + /* Acknowledge the data received from the peer. */ + tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + return true; + } else if (foc->len == 0) { /* Client requesting a cookie */ + tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENCOOKIEREQD); + } else { + /* Client sent a cookie with wrong size. Treat it + * the same as invalid and return a valid one. + */ + tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc); + } + return false; +} + +static int tcp_v4_conn_req_fastopen(struct sock *sk, + struct sk_buff *skb, + struct sk_buff *skb_synack, + struct request_sock *req, + struct request_values *rvp) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + const struct inet_request_sock *ireq = inet_rsk(req); + struct sock *child; + + req->retrans = 0; + req->sk = NULL; + + child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); + if (child == NULL) { + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + kfree_skb(skb_synack); + return -1; + } + ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr, + ireq->rmt_addr, ireq->opt); + /* XXX (TFO) - is it ok to ignore error and continue? */ + + spin_lock(&queue->fastopenq->lock); + queue->fastopenq->qlen++; + spin_unlock(&queue->fastopenq->lock); + + /* Initialize the child socket. Have to fix some values to take + * into account the child is a Fast Open socket and is created + * only out of the bits carried in the SYN packet. + */ + tp = tcp_sk(child); + + tp->fastopen_rsk = req; + /* Do a hold on the listner sk so that if the listener is being + * closed, the child that has been accepted can live on and still + * access listen_lock. + */ + sock_hold(sk); + tcp_rsk(req)->listener = sk; + + /* RFC1323: The window in SYN & SYN/ACK segments is never + * scaled. So correct it appropriately. + */ + tp->snd_wnd = ntohs(tcp_hdr(skb)->window); + + /* Activate the retrans timer so that SYNACK can be retransmitted. + * The request socket is not added to the SYN table of the parent + * because it's been added to the accept queue directly. + */ + inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, + TCP_TIMEOUT_INIT, TCP_RTO_MAX); + + /* Add the child socket directly into the accept queue */ + inet_csk_reqsk_queue_add(sk, req, child); + + /* Now finish processing the fastopen child socket. */ + inet_csk(child)->icsk_af_ops->rebuild_header(child); + tcp_init_congestion_control(child); + tcp_mtup_init(child); + tcp_init_buffer_space(child); + tcp_init_metrics(child); + + /* Queue the data carried in the SYN packet. We need to first + * bump skb's refcnt because the caller will attempt to free it. + * + * XXX (TFO) - we honor a zero-payload TFO request for now. + * (Any reason not to?) + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq + 1) { + /* Don't queue the skb if there is no payload in SYN. + * XXX (TFO) - How about SYN+FIN? + */ + tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + } else { + skb = skb_get(skb); + skb_dst_drop(skb); + __skb_pull(skb, tcp_hdr(skb)->doff * 4); + skb_set_owner_r(skb, child); + __skb_queue_tail(&child->sk_receive_queue, skb); + tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; + } + sk->sk_data_ready(sk, 0); + bh_unlock_sock(child); + sock_put(child); + WARN_ON(req->sk == NULL); + return 0; +} + int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; @@ -1285,6 +1476,11 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; bool want_cookie = false; + struct flowi4 fl4; + struct tcp_fastopen_cookie foc = { .len = -1 }; + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; + struct sk_buff *skb_synack; + int do_fastopen; /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -1319,7 +1515,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = TCP_MSS_DEFAULT; tmp_opt.user_mss = tp->rx_opt.user_mss; - tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL); + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, + want_cookie ? NULL : &foc); if (tmp_opt.cookie_plus > 0 && tmp_opt.saw_tstamp && @@ -1377,8 +1574,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = cookie_v4_init_sequence(sk, skb, &req->mss); req->cookie_ts = tmp_opt.tstamp_ok; } else if (!isn) { - struct flowi4 fl4; - /* VJ's idea. We save last timestamp seen * from the destination in peer table, when entering * state TIME-WAIT, and check against it before @@ -1419,14 +1614,52 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->snt_isn = isn; tcp_rsk(req)->snt_synack = tcp_time_stamp; - if (tcp_v4_send_synack(sk, dst, req, - (struct request_values *)&tmp_ext, - skb_get_queue_mapping(skb), - want_cookie) || - want_cookie) + if (dst == NULL) { + dst = inet_csk_route_req(sk, &fl4, req); + if (dst == NULL) + goto drop_and_free; + } + do_fastopen = tcp_fastopen_check(sk, skb, req, &foc, &valid_foc); + + /* We don't call tcp_v4_send_synack() directly because we need + * to make sure a child socket can be created successfully before + * sending back synack! + * + * XXX (TFO) - Ideally one would simply call tcp_v4_send_synack() + * (or better yet, call tcp_send_synack() in the child context + * directly, but will have to fix bunch of other code first) + * after syn_recv_sock() except one will need to first fix the + * latter to remove its dependency on the current implementation + * of tcp_v4_send_synack()->tcp_select_initial_window(). + */ + skb_synack = tcp_make_synack(sk, dst, req, + (struct request_values *)&tmp_ext, + fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL); + + if (skb_synack) { + __tcp_v4_send_check(skb_synack, ireq->loc_addr, ireq->rmt_addr); + skb_set_queue_mapping(skb_synack, skb_get_queue_mapping(skb)); + } else + goto drop_and_free; + + if (likely(!do_fastopen)) { + int err; + err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr, + ireq->rmt_addr, ireq->opt); + err = net_xmit_eval(err); + if (err || want_cookie) + goto drop_and_free; + + tcp_rsk(req)->listener = NULL; + /* Add the request_sock to the SYN table */ + inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + if (fastopen_cookie_present(&foc) && foc.len != 0) + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPFASTOPENPASSIVEFAIL); + } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req, + (struct request_values *)&tmp_ext)) goto drop_and_free; - inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; drop_and_release: @@ -1977,6 +2210,7 @@ void tcp_v4_destroy_sock(struct sock *sk) tcp_cookie_values_release); tp->cookie_values = NULL; } + BUG_ON(tp->fastopen_rsk != NULL); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2425,6 +2659,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); + struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); @@ -2469,7 +2704,9 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, - tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh, + sk->sk_state == TCP_LISTEN ? + (fastopenq ? fastopenq->max_qlen : 0) : + (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh), len); } -- cgit v1.3-14-g43fede From ce9f3f31efb88841e4df98794b13dbac8c4901da Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Mon, 18 Jun 2012 00:18:31 +0000 Subject: netfilter: properly annotate ipv4_netfilter_{init,fini}() Despite being just a few bytes of code, they should still have proper annotations. Signed-off-by: Jan Beulich Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index f1643c0c3587..4c0cf63dd92e 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -188,12 +188,12 @@ static const struct nf_afinfo nf_ip_afinfo = { .route_key_size = sizeof(struct ip_rt_info), }; -static int ipv4_netfilter_init(void) +static int __init ipv4_netfilter_init(void) { return nf_register_afinfo(&nf_ip_afinfo); } -static void ipv4_netfilter_fini(void) +static void __exit ipv4_netfilter_fini(void) { nf_unregister_afinfo(&nf_ip_afinfo); } -- cgit v1.3-14-g43fede From 09484d1f6edb3b798c5926a6755f1badb77ece9f Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Sun, 2 Sep 2012 17:38:02 +0000 Subject: tcp: move tcp_enter_cwr() To prepare replacing rate halving with PRR algorithm in CWR state. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 8c304a400798..3ab0c7573a0b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -743,29 +743,6 @@ __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst) return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } -/* Set slow start threshold and cwnd not falling to slow start */ -void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) -{ - struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); - - tp->prior_ssthresh = 0; - tp->bytes_acked = 0; - if (icsk->icsk_ca_state < TCP_CA_CWR) { - tp->undo_marker = 0; - if (set_ssthresh) - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - tp->snd_cwnd = min(tp->snd_cwnd, - tcp_packets_in_flight(tp) + 1U); - tp->snd_cwnd_cnt = 0; - tp->high_seq = tp->snd_nxt; - tp->snd_cwnd_stamp = tcp_time_stamp; - TCP_ECN_queue_cwr(tp); - - tcp_set_ca_state(sk, TCP_CA_CWR); - } -} - /* * Packet counting of FACK is based on in-order assumptions, therefore TCP * disables it when reordering is detected @@ -2741,6 +2718,29 @@ static inline void tcp_complete_cwr(struct sock *sk) tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } +/* Set slow start threshold and cwnd not falling to slow start */ +void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) +{ + struct tcp_sock *tp = tcp_sk(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); + + tp->prior_ssthresh = 0; + tp->bytes_acked = 0; + if (icsk->icsk_ca_state < TCP_CA_CWR) { + tp->undo_marker = 0; + if (set_ssthresh) + tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); + tp->snd_cwnd = min(tp->snd_cwnd, + tcp_packets_in_flight(tp) + 1U); + tp->snd_cwnd_cnt = 0; + tp->high_seq = tp->snd_nxt; + tp->snd_cwnd_stamp = tcp_time_stamp; + TCP_ECN_queue_cwr(tp); + + tcp_set_ca_state(sk, TCP_CA_CWR); + } +} + static void tcp_try_keep_open(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); -- cgit v1.3-14-g43fede From fb4d3d1df31907eadd2e2a745e840921888b346a Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Sun, 2 Sep 2012 17:38:03 +0000 Subject: tcp: move tcp_update_cwnd_in_recovery To prepare replacing rate halving with PRR algorithm in CWR state. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 64 ++++++++++++++++++++++++++-------------------------- 1 file changed, 32 insertions(+), 32 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3ab0c7573a0b..38589e464e63 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2700,6 +2700,38 @@ static bool tcp_try_undo_loss(struct sock *sk) return false; } +/* This function implements the PRR algorithm, specifcally the PRR-SSRB + * (proportional rate reduction with slow start reduction bound) as described in + * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt. + * It computes the number of packets to send (sndcnt) based on packets newly + * delivered: + * 1) If the packets in flight is larger than ssthresh, PRR spreads the + * cwnd reductions across a full RTT. + * 2) If packets in flight is lower than ssthresh (such as due to excess + * losses and/or application stalls), do not perform any further cwnd + * reductions, but instead slow start up to ssthresh. + */ +static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, + int fast_rexmit, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + int sndcnt = 0; + int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); + + if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + + tp->prior_cwnd - 1; + sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; + } else { + sndcnt = min_t(int, delta, + max_t(int, tp->prr_delivered - tp->prr_out, + newly_acked_sacked) + 1); + } + + sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); + tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; +} + static inline void tcp_complete_cwr(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); @@ -2854,38 +2886,6 @@ void tcp_simple_retransmit(struct sock *sk) } EXPORT_SYMBOL(tcp_simple_retransmit); -/* This function implements the PRR algorithm, specifcally the PRR-SSRB - * (proportional rate reduction with slow start reduction bound) as described in - * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt. - * It computes the number of packets to send (sndcnt) based on packets newly - * delivered: - * 1) If the packets in flight is larger than ssthresh, PRR spreads the - * cwnd reductions across a full RTT. - * 2) If packets in flight is lower than ssthresh (such as due to excess - * losses and/or application stalls), do not perform any further cwnd - * reductions, but instead slow start up to ssthresh. - */ -static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, - int fast_rexmit, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - int sndcnt = 0; - int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); - - if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { - u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + - tp->prior_cwnd - 1; - sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; - } else { - sndcnt = min_t(int, delta, - max_t(int, tp->prr_delivered - tp->prr_out, - newly_acked_sacked) + 1); - } - - sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); - tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; -} - static void tcp_enter_recovery(struct sock *sk, bool ece_ack) { struct tcp_sock *tp = tcp_sk(sk); -- cgit v1.3-14-g43fede From 684bad1107571d35610a674c61b3544efb5a5b13 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Sun, 2 Sep 2012 17:38:04 +0000 Subject: tcp: use PRR to reduce cwin in CWR state Use proportional rate reduction (PRR) algorithm to reduce cwnd in CWR state, in addition to Recovery state. Retire the current rate-halving in CWR. When losses are detected via ACKs in CWR state, the sender enters Recovery state but the cwnd reduction continues and does not restart. Rename and refactor cwnd reduction functions since both CWR and Recovery use the same algorithm: tcp_init_cwnd_reduction() is new and initiates reduction state variables. tcp_cwnd_reduction() is previously tcp_update_cwnd_in_recovery(). tcp_ends_cwnd_reduction() is previously tcp_complete_cwr(). The rate halving functions and logic such as tcp_cwnd_down(), tcp_min_cwnd(), and the cwnd moderation inside tcp_enter_cwr() are removed. The unused parameter, flag, in tcp_cwnd_reduction() is also removed. Signed-off-by: Yuchung Cheng Acked-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 10 ++++- net/ipv4/tcp_input.c | 119 +++++++++++++++++--------------------------------- net/ipv4/tcp_output.c | 6 +-- 3 files changed, 52 insertions(+), 83 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index 1421b02a7905..a8cb00c0c6d9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -913,15 +913,21 @@ static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp) return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH; } +static inline bool tcp_in_cwnd_reduction(const struct sock *sk) +{ + return (TCPF_CA_CWR | TCPF_CA_Recovery) & + (1 << inet_csk(sk)->icsk_ca_state); +} + /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. - * The exception is rate halving phase, when cwnd is decreasing towards + * The exception is cwnd reduction phase, when cwnd is decreasing towards * ssthresh. */ static inline __u32 tcp_current_ssthresh(const struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); - if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery)) + if (tcp_in_cwnd_reduction(sk)) return tp->snd_ssthresh; else return max(tp->snd_ssthresh, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 38589e464e63..e2bec815ff23 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2470,35 +2470,6 @@ static inline void tcp_moderate_cwnd(struct tcp_sock *tp) tp->snd_cwnd_stamp = tcp_time_stamp; } -/* Lower bound on congestion window is slow start threshold - * unless congestion avoidance choice decides to overide it. - */ -static inline u32 tcp_cwnd_min(const struct sock *sk) -{ - const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; - - return ca_ops->min_cwnd ? ca_ops->min_cwnd(sk) : tcp_sk(sk)->snd_ssthresh; -} - -/* Decrease cwnd each second ack. */ -static void tcp_cwnd_down(struct sock *sk, int flag) -{ - struct tcp_sock *tp = tcp_sk(sk); - int decr = tp->snd_cwnd_cnt + 1; - - if ((flag & (FLAG_ANY_PROGRESS | FLAG_DSACKING_ACK)) || - (tcp_is_reno(tp) && !(flag & FLAG_NOT_DUP))) { - tp->snd_cwnd_cnt = decr & 1; - decr >>= 1; - - if (decr && tp->snd_cwnd > tcp_cwnd_min(sk)) - tp->snd_cwnd -= decr; - - tp->snd_cwnd = min(tp->snd_cwnd, tcp_packets_in_flight(tp) + 1); - tp->snd_cwnd_stamp = tcp_time_stamp; - } -} - /* Nothing was retransmitted or returned timestamp is less * than timestamp of the first retransmission. */ @@ -2700,9 +2671,8 @@ static bool tcp_try_undo_loss(struct sock *sk) return false; } -/* This function implements the PRR algorithm, specifcally the PRR-SSRB - * (proportional rate reduction with slow start reduction bound) as described in - * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt. +/* The cwnd reduction in CWR and Recovery use the PRR algorithm + * https://datatracker.ietf.org/doc/draft-ietf-tcpm-proportional-rate-reduction/ * It computes the number of packets to send (sndcnt) based on packets newly * delivered: * 1) If the packets in flight is larger than ssthresh, PRR spreads the @@ -2711,13 +2681,29 @@ static bool tcp_try_undo_loss(struct sock *sk) * losses and/or application stalls), do not perform any further cwnd * reductions, but instead slow start up to ssthresh. */ -static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, - int fast_rexmit, int flag) +static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tp->high_seq = tp->snd_nxt; + tp->bytes_acked = 0; + tp->snd_cwnd_cnt = 0; + tp->prior_cwnd = tp->snd_cwnd; + tp->prr_delivered = 0; + tp->prr_out = 0; + if (set_ssthresh) + tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); + TCP_ECN_queue_cwr(tp); +} + +static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, + int fast_rexmit) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); + tp->prr_delivered += newly_acked_sacked; if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; @@ -2732,43 +2718,29 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } -static inline void tcp_complete_cwr(struct sock *sk) +static inline void tcp_end_cwnd_reduction(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - /* Do not moderate cwnd if it's already undone in cwr or recovery. */ - if (tp->undo_marker) { - if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) { - tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); - tp->snd_cwnd_stamp = tcp_time_stamp; - } else if (tp->snd_ssthresh < TCP_INFINITE_SSTHRESH) { - /* PRR algorithm. */ - tp->snd_cwnd = tp->snd_ssthresh; - tp->snd_cwnd_stamp = tcp_time_stamp; - } + /* Reset cwnd to ssthresh in CWR or Recovery (unless it's undone) */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR || + (tp->undo_marker && tp->snd_ssthresh < TCP_INFINITE_SSTHRESH)) { + tp->snd_cwnd = tp->snd_ssthresh; + tp->snd_cwnd_stamp = tcp_time_stamp; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } -/* Set slow start threshold and cwnd not falling to slow start */ +/* Enter CWR state. Disable cwnd undo since congestion is proven with ECN */ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh) { struct tcp_sock *tp = tcp_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); tp->prior_ssthresh = 0; tp->bytes_acked = 0; - if (icsk->icsk_ca_state < TCP_CA_CWR) { + if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { tp->undo_marker = 0; - if (set_ssthresh) - tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk); - tp->snd_cwnd = min(tp->snd_cwnd, - tcp_packets_in_flight(tp) + 1U); - tp->snd_cwnd_cnt = 0; - tp->high_seq = tp->snd_nxt; - tp->snd_cwnd_stamp = tcp_time_stamp; - TCP_ECN_queue_cwr(tp); - + tcp_init_cwnd_reduction(sk, set_ssthresh); tcp_set_ca_state(sk, TCP_CA_CWR); } } @@ -2787,7 +2759,7 @@ static void tcp_try_keep_open(struct sock *sk) } } -static void tcp_try_to_open(struct sock *sk, int flag) +static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked) { struct tcp_sock *tp = tcp_sk(sk); @@ -2804,7 +2776,7 @@ static void tcp_try_to_open(struct sock *sk, int flag) if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open) tcp_moderate_cwnd(tp); } else { - tcp_cwnd_down(sk, flag); + tcp_cwnd_reduction(sk, newly_acked_sacked, 0); } } @@ -2898,7 +2870,6 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) NET_INC_STATS_BH(sock_net(sk), mib_idx); - tp->high_seq = tp->snd_nxt; tp->prior_ssthresh = 0; tp->undo_marker = tp->snd_una; tp->undo_retrans = tp->retrans_out; @@ -2906,15 +2877,8 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); - tp->snd_ssthresh = inet_csk(sk)->icsk_ca_ops->ssthresh(sk); - TCP_ECN_queue_cwr(tp); + tcp_init_cwnd_reduction(sk, true); } - - tp->bytes_acked = 0; - tp->snd_cwnd_cnt = 0; - tp->prior_cwnd = tp->snd_cwnd; - tp->prr_delivered = 0; - tp->prr_out = 0; tcp_set_ca_state(sk, TCP_CA_Recovery); } @@ -2974,7 +2938,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, /* CWR is to be held something *above* high_seq * is ACKed for CWR bit to reach receiver. */ if (tp->snd_una != tp->high_seq) { - tcp_complete_cwr(sk); + tcp_end_cwnd_reduction(sk); tcp_set_ca_state(sk, TCP_CA_Open); } break; @@ -2984,7 +2948,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_reset_reno_sack(tp); if (tcp_try_undo_recovery(sk)) return; - tcp_complete_cwr(sk); + tcp_end_cwnd_reduction(sk); break; } } @@ -3025,7 +2989,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_try_undo_dsack(sk); if (!tcp_time_to_recover(sk, flag)) { - tcp_try_to_open(sk, flag); + tcp_try_to_open(sk, flag, newly_acked_sacked); return; } @@ -3047,8 +3011,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk))) tcp_update_scoreboard(sk, fast_rexmit); - tp->prr_delivered += newly_acked_sacked; - tcp_update_cwnd_in_recovery(sk, newly_acked_sacked, fast_rexmit, flag); + tcp_cwnd_reduction(sk, newly_acked_sacked, fast_rexmit); tcp_xmit_retransmit_queue(sk); } @@ -3394,7 +3357,7 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) { const struct tcp_sock *tp = tcp_sk(sk); return (!(flag & FLAG_ECE) || tp->snd_cwnd < tp->snd_ssthresh) && - !((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_Recovery | TCPF_CA_CWR)); + !tcp_in_cwnd_reduction(sk); } /* Check that window update is acceptable. @@ -3462,9 +3425,9 @@ static void tcp_conservative_spur_to_response(struct tcp_sock *tp) } /* A conservative spurious RTO response algorithm: reduce cwnd using - * rate halving and continue in congestion avoidance. + * PRR and continue in congestion avoidance. */ -static void tcp_ratehalving_spur_to_response(struct sock *sk) +static void tcp_cwr_spur_to_response(struct sock *sk) { tcp_enter_cwr(sk, 0); } @@ -3472,7 +3435,7 @@ static void tcp_ratehalving_spur_to_response(struct sock *sk) static void tcp_undo_spur_to_response(struct sock *sk, int flag) { if (flag & FLAG_ECE) - tcp_ratehalving_spur_to_response(sk); + tcp_cwr_spur_to_response(sk); else tcp_undo_cwr(sk, true); } @@ -3579,7 +3542,7 @@ static bool tcp_process_frto(struct sock *sk, int flag) tcp_conservative_spur_to_response(tp); break; default: - tcp_ratehalving_spur_to_response(sk); + tcp_cwr_spur_to_response(sk); break; } tp->frto_counter = 0; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9383b51f3efc..cfe6ffe1c177 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2037,10 +2037,10 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (push_one) break; } - if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) - tp->prr_out += sent_pkts; if (likely(sent_pkts)) { + if (tcp_in_cwnd_reduction(sk)) + tp->prr_out += sent_pkts; tcp_cwnd_validate(sk); return false; } @@ -2542,7 +2542,7 @@ begin_fwd: } NET_INC_STATS_BH(sock_net(sk), mib_idx); - if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + if (tcp_in_cwnd_reduction(sk)) tp->prr_out += tcp_skb_pcount(skb); if (skb == tcp_write_queue_head(sk)) -- cgit v1.3-14-g43fede From d23ff701643a4a725e2c7a8ba2d567d39daa29ea Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Tue, 4 Sep 2012 11:03:15 +0000 Subject: tcp: add generic netlink support for tcp_metrics Add support for genl "tcp_metrics". No locking is changed, only that now we can unlink and delete entries after grace period. We implement get/del for single entry and dump to support show/flush filtering in user space. Del without address attribute causes flush for all addresses, sadly under genl_mutex. v2: - remove rcu_assign_pointer as suggested by Eric Dumazet, it is not needed because there are no other writes under lock - move the flushing code in tcp_metrics_flush_all v3: - remove synchronize_rcu on flush as suggested by Eric Dumazet Signed-off-by: Julian Anastasov Signed-off-by: David S. Miller --- include/linux/Kbuild | 1 + include/linux/tcp_metrics.h | 54 +++++++ net/ipv4/tcp_metrics.c | 354 ++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 396 insertions(+), 13 deletions(-) create mode 100644 include/linux/tcp_metrics.h (limited to 'net/ipv4') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 1f2c1c787f17..90da0af28352 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -363,6 +363,7 @@ header-y += sysctl.h header-y += sysinfo.h header-y += taskstats.h header-y += tcp.h +header-y += tcp_metrics.h header-y += telephony.h header-y += termios.h header-y += time.h diff --git a/include/linux/tcp_metrics.h b/include/linux/tcp_metrics.h new file mode 100644 index 000000000000..cb5157b55f32 --- /dev/null +++ b/include/linux/tcp_metrics.h @@ -0,0 +1,54 @@ +/* tcp_metrics.h - TCP Metrics Interface */ + +#ifndef _LINUX_TCP_METRICS_H +#define _LINUX_TCP_METRICS_H + +#include + +/* NETLINK_GENERIC related info + */ +#define TCP_METRICS_GENL_NAME "tcp_metrics" +#define TCP_METRICS_GENL_VERSION 0x1 + +enum tcp_metric_index { + TCP_METRIC_RTT, + TCP_METRIC_RTTVAR, + TCP_METRIC_SSTHRESH, + TCP_METRIC_CWND, + TCP_METRIC_REORDERING, + + /* Always last. */ + __TCP_METRIC_MAX, +}; + +#define TCP_METRIC_MAX (__TCP_METRIC_MAX - 1) + +enum { + TCP_METRICS_ATTR_UNSPEC, + TCP_METRICS_ATTR_ADDR_IPV4, /* u32 */ + TCP_METRICS_ATTR_ADDR_IPV6, /* binary */ + TCP_METRICS_ATTR_AGE, /* msecs */ + TCP_METRICS_ATTR_TW_TSVAL, /* u32, raw, rcv tsval */ + TCP_METRICS_ATTR_TW_TS_STAMP, /* s32, sec age */ + TCP_METRICS_ATTR_VALS, /* nested +1, u32 */ + TCP_METRICS_ATTR_FOPEN_MSS, /* u16 */ + TCP_METRICS_ATTR_FOPEN_SYN_DROPS, /* u16, count of drops */ + TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS, /* msecs age */ + TCP_METRICS_ATTR_FOPEN_COOKIE, /* binary */ + + __TCP_METRICS_ATTR_MAX, +}; + +#define TCP_METRICS_ATTR_MAX (__TCP_METRICS_ATTR_MAX - 1) + +enum { + TCP_METRICS_CMD_UNSPEC, + TCP_METRICS_CMD_GET, + TCP_METRICS_CMD_DEL, + + __TCP_METRICS_CMD_MAX, +}; + +#define TCP_METRICS_CMD_MAX (__TCP_METRICS_CMD_MAX - 1) + +#endif /* _LINUX_TCP_METRICS_H */ diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 0abe67bb4d3a..988edb63ee73 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -17,20 +18,10 @@ #include #include #include +#include int sysctl_tcp_nometrics_save __read_mostly; -enum tcp_metric_index { - TCP_METRIC_RTT, - TCP_METRIC_RTTVAR, - TCP_METRIC_SSTHRESH, - TCP_METRIC_CWND, - TCP_METRIC_REORDERING, - - /* Always last. */ - TCP_METRIC_MAX, -}; - struct tcp_fastopen_metrics { u16 mss; u16 syn_loss:10; /* Recurring Fast Open SYN losses */ @@ -45,8 +36,10 @@ struct tcp_metrics_block { u32 tcpm_ts; u32 tcpm_ts_stamp; u32 tcpm_lock; - u32 tcpm_vals[TCP_METRIC_MAX]; + u32 tcpm_vals[TCP_METRIC_MAX + 1]; struct tcp_fastopen_metrics tcpm_fastopen; + + struct rcu_head rcu_head; }; static bool tcp_metric_locked(struct tcp_metrics_block *tm, @@ -690,6 +683,325 @@ void tcp_fastopen_cache_set(struct sock *sk, u16 mss, rcu_read_unlock(); } +static struct genl_family tcp_metrics_nl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = TCP_METRICS_GENL_NAME, + .version = TCP_METRICS_GENL_VERSION, + .maxattr = TCP_METRICS_ATTR_MAX, + .netnsok = true, +}; + +static struct nla_policy tcp_metrics_nl_policy[TCP_METRICS_ATTR_MAX + 1] = { + [TCP_METRICS_ATTR_ADDR_IPV4] = { .type = NLA_U32, }, + [TCP_METRICS_ATTR_ADDR_IPV6] = { .type = NLA_BINARY, + .len = sizeof(struct in6_addr), }, + /* Following attributes are not received for GET/DEL, + * we keep them for reference + */ +#if 0 + [TCP_METRICS_ATTR_AGE] = { .type = NLA_MSECS, }, + [TCP_METRICS_ATTR_TW_TSVAL] = { .type = NLA_U32, }, + [TCP_METRICS_ATTR_TW_TS_STAMP] = { .type = NLA_S32, }, + [TCP_METRICS_ATTR_VALS] = { .type = NLA_NESTED, }, + [TCP_METRICS_ATTR_FOPEN_MSS] = { .type = NLA_U16, }, + [TCP_METRICS_ATTR_FOPEN_SYN_DROPS] = { .type = NLA_U16, }, + [TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS] = { .type = NLA_MSECS, }, + [TCP_METRICS_ATTR_FOPEN_COOKIE] = { .type = NLA_BINARY, + .len = TCP_FASTOPEN_COOKIE_MAX, }, +#endif +}; + +/* Add attributes, caller cancels its header on failure */ +static int tcp_metrics_fill_info(struct sk_buff *msg, + struct tcp_metrics_block *tm) +{ + struct nlattr *nest; + int i; + + switch (tm->tcpm_addr.family) { + case AF_INET: + if (nla_put_be32(msg, TCP_METRICS_ATTR_ADDR_IPV4, + tm->tcpm_addr.addr.a4) < 0) + goto nla_put_failure; + break; + case AF_INET6: + if (nla_put(msg, TCP_METRICS_ATTR_ADDR_IPV6, 16, + tm->tcpm_addr.addr.a6) < 0) + goto nla_put_failure; + break; + default: + return -EAFNOSUPPORT; + } + + if (nla_put_msecs(msg, TCP_METRICS_ATTR_AGE, + jiffies - tm->tcpm_stamp) < 0) + goto nla_put_failure; + if (tm->tcpm_ts_stamp) { + if (nla_put_s32(msg, TCP_METRICS_ATTR_TW_TS_STAMP, + (s32) (get_seconds() - tm->tcpm_ts_stamp)) < 0) + goto nla_put_failure; + if (nla_put_u32(msg, TCP_METRICS_ATTR_TW_TSVAL, + tm->tcpm_ts) < 0) + goto nla_put_failure; + } + + { + int n = 0; + + nest = nla_nest_start(msg, TCP_METRICS_ATTR_VALS); + if (!nest) + goto nla_put_failure; + for (i = 0; i < TCP_METRIC_MAX + 1; i++) { + if (!tm->tcpm_vals[i]) + continue; + if (nla_put_u32(msg, i + 1, tm->tcpm_vals[i]) < 0) + goto nla_put_failure; + n++; + } + if (n) + nla_nest_end(msg, nest); + else + nla_nest_cancel(msg, nest); + } + + { + struct tcp_fastopen_metrics tfom_copy[1], *tfom; + unsigned int seq; + + do { + seq = read_seqbegin(&fastopen_seqlock); + tfom_copy[0] = tm->tcpm_fastopen; + } while (read_seqretry(&fastopen_seqlock, seq)); + + tfom = tfom_copy; + if (tfom->mss && + nla_put_u16(msg, TCP_METRICS_ATTR_FOPEN_MSS, + tfom->mss) < 0) + goto nla_put_failure; + if (tfom->syn_loss && + (nla_put_u16(msg, TCP_METRICS_ATTR_FOPEN_SYN_DROPS, + tfom->syn_loss) < 0 || + nla_put_msecs(msg, TCP_METRICS_ATTR_FOPEN_SYN_DROP_TS, + jiffies - tfom->last_syn_loss) < 0)) + goto nla_put_failure; + if (tfom->cookie.len > 0 && + nla_put(msg, TCP_METRICS_ATTR_FOPEN_COOKIE, + tfom->cookie.len, tfom->cookie.val) < 0) + goto nla_put_failure; + } + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int tcp_metrics_dump_info(struct sk_buff *skb, + struct netlink_callback *cb, + struct tcp_metrics_block *tm) +{ + void *hdr; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + &tcp_metrics_nl_family, NLM_F_MULTI, + TCP_METRICS_CMD_GET); + if (!hdr) + return -EMSGSIZE; + + if (tcp_metrics_fill_info(skb, tm) < 0) + goto nla_put_failure; + + return genlmsg_end(skb, hdr); + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int tcp_metrics_nl_dump(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net *net = sock_net(skb->sk); + unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log; + unsigned int row, s_row = cb->args[0]; + int s_col = cb->args[1], col = s_col; + + for (row = s_row; row < max_rows; row++, s_col = 0) { + struct tcp_metrics_block *tm; + struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash + row; + + rcu_read_lock(); + for (col = 0, tm = rcu_dereference(hb->chain); tm; + tm = rcu_dereference(tm->tcpm_next), col++) { + if (col < s_col) + continue; + if (tcp_metrics_dump_info(skb, cb, tm) < 0) { + rcu_read_unlock(); + goto done; + } + } + rcu_read_unlock(); + } + +done: + cb->args[0] = row; + cb->args[1] = col; + return skb->len; +} + +static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, + unsigned int *hash, int optional) +{ + struct nlattr *a; + + a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV4]; + if (a) { + addr->family = AF_INET; + addr->addr.a4 = nla_get_be32(a); + *hash = (__force unsigned int) addr->addr.a4; + return 0; + } + a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6]; + if (a) { + if (nla_len(a) != sizeof(sizeof(struct in6_addr))) + return -EINVAL; + addr->family = AF_INET6; + memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6)); + *hash = ipv6_addr_hash((struct in6_addr *) addr->addr.a6); + return 0; + } + return optional ? 1 : -EAFNOSUPPORT; +} + +static int tcp_metrics_nl_cmd_get(struct sk_buff *skb, struct genl_info *info) +{ + struct tcp_metrics_block *tm; + struct inetpeer_addr addr; + unsigned int hash; + struct sk_buff *msg; + struct net *net = genl_info_net(info); + void *reply; + int ret; + + ret = parse_nl_addr(info, &addr, &hash, 0); + if (ret < 0) + return ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + reply = genlmsg_put_reply(msg, info, &tcp_metrics_nl_family, 0, + info->genlhdr->cmd); + if (!reply) + goto nla_put_failure; + + hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + ret = -ESRCH; + rcu_read_lock(); + for (tm = rcu_dereference(net->ipv4.tcp_metrics_hash[hash].chain); tm; + tm = rcu_dereference(tm->tcpm_next)) { + if (addr_same(&tm->tcpm_addr, &addr)) { + ret = tcp_metrics_fill_info(msg, tm); + break; + } + } + rcu_read_unlock(); + if (ret < 0) + goto out_free; + + genlmsg_end(msg, reply); + return genlmsg_reply(msg, info); + +nla_put_failure: + ret = -EMSGSIZE; + +out_free: + nlmsg_free(msg); + return ret; +} + +#define deref_locked_genl(p) \ + rcu_dereference_protected(p, lockdep_genl_is_held() && \ + lockdep_is_held(&tcp_metrics_lock)) + +#define deref_genl(p) rcu_dereference_protected(p, lockdep_genl_is_held()) + +static int tcp_metrics_flush_all(struct net *net) +{ + unsigned int max_rows = 1U << net->ipv4.tcp_metrics_hash_log; + struct tcpm_hash_bucket *hb = net->ipv4.tcp_metrics_hash; + struct tcp_metrics_block *tm; + unsigned int row; + + for (row = 0; row < max_rows; row++, hb++) { + spin_lock_bh(&tcp_metrics_lock); + tm = deref_locked_genl(hb->chain); + if (tm) + hb->chain = NULL; + spin_unlock_bh(&tcp_metrics_lock); + while (tm) { + struct tcp_metrics_block *next; + + next = deref_genl(tm->tcpm_next); + kfree_rcu(tm, rcu_head); + tm = next; + } + } + return 0; +} + +static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info) +{ + struct tcpm_hash_bucket *hb; + struct tcp_metrics_block *tm; + struct tcp_metrics_block __rcu **pp; + struct inetpeer_addr addr; + unsigned int hash; + struct net *net = genl_info_net(info); + int ret; + + ret = parse_nl_addr(info, &addr, &hash, 1); + if (ret < 0) + return ret; + if (ret > 0) + return tcp_metrics_flush_all(net); + + hash = hash_32(hash, net->ipv4.tcp_metrics_hash_log); + hb = net->ipv4.tcp_metrics_hash + hash; + pp = &hb->chain; + spin_lock_bh(&tcp_metrics_lock); + for (tm = deref_locked_genl(*pp); tm; + pp = &tm->tcpm_next, tm = deref_locked_genl(*pp)) { + if (addr_same(&tm->tcpm_addr, &addr)) { + *pp = tm->tcpm_next; + break; + } + } + spin_unlock_bh(&tcp_metrics_lock); + if (!tm) + return -ESRCH; + kfree_rcu(tm, rcu_head); + return 0; +} + +static struct genl_ops tcp_metrics_nl_ops[] = { + { + .cmd = TCP_METRICS_CMD_GET, + .doit = tcp_metrics_nl_cmd_get, + .dumpit = tcp_metrics_nl_dump, + .policy = tcp_metrics_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = TCP_METRICS_CMD_DEL, + .doit = tcp_metrics_nl_cmd_del, + .policy = tcp_metrics_nl_policy, + .flags = GENL_ADMIN_PERM, + }, +}; + static unsigned int tcpmhash_entries; static int __init set_tcpmhash_entries(char *str) { @@ -753,5 +1065,21 @@ static __net_initdata struct pernet_operations tcp_net_metrics_ops = { void __init tcp_metrics_init(void) { - register_pernet_subsys(&tcp_net_metrics_ops); + int ret; + + ret = register_pernet_subsys(&tcp_net_metrics_ops); + if (ret < 0) + goto cleanup; + ret = genl_register_family_with_ops(&tcp_metrics_nl_family, + tcp_metrics_nl_ops, + ARRAY_SIZE(tcp_metrics_nl_ops)); + if (ret < 0) + goto cleanup_subsys; + return; + +cleanup_subsys: + unregister_pernet_subsys(&tcp_net_metrics_ops); + +cleanup: + return; } -- cgit v1.3-14-g43fede From 7ab4551f3b391818e29263279031dca1e26417c6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 6 Sep 2012 08:07:13 +0000 Subject: tcp: fix TFO regression Fengguang Wu reported various panics and bisected to commit 8336886f786fdac (tcp: TCP Fast Open Server - support TFO listeners) Fix this by making sure socket is a TCP socket before accessing TFO data structures. [ 233.046014] kfree_debugcheck: out of range ptr ea6000000bb8h. [ 233.047399] ------------[ cut here ]------------ [ 233.048393] kernel BUG at /c/kernel-tests/src/stable/mm/slab.c:3074! [ 233.048393] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC [ 233.048393] Modules linked in: [ 233.048393] CPU 0 [ 233.048393] Pid: 3929, comm: trinity-watchdo Not tainted 3.6.0-rc3+ #4192 Bochs Bochs [ 233.048393] RIP: 0010:[] [] kfree_debugcheck+0x27/0x2d [ 233.048393] RSP: 0018:ffff88000facbca8 EFLAGS: 00010092 [ 233.048393] RAX: 0000000000000031 RBX: 0000ea6000000bb8 RCX: 00000000a189a188 [ 233.048393] RDX: 000000000000a189 RSI: ffffffff8108ad32 RDI: ffffffff810d30f9 [ 233.048393] RBP: ffff88000facbcb8 R08: 0000000000000002 R09: ffffffff843846f0 [ 233.048393] R10: ffffffff810ae37c R11: 0000000000000908 R12: 0000000000000202 [ 233.048393] R13: ffffffff823dbd5a R14: ffff88000ec5bea8 R15: ffffffff8363c780 [ 233.048393] FS: 00007faa6899c700(0000) GS:ffff88001f200000(0000) knlGS:0000000000000000 [ 233.048393] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [ 233.048393] CR2: 00007faa6841019c CR3: 0000000012c82000 CR4: 00000000000006f0 [ 233.048393] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 233.048393] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 [ 233.048393] Process trinity-watchdo (pid: 3929, threadinfo ffff88000faca000, task ffff88000faec600) [ 233.048393] Stack: [ 233.048393] 0000000000000000 0000ea6000000bb8 ffff88000facbce8 ffffffff8116ad81 [ 233.048393] ffff88000ff588a0 ffff88000ff58850 ffff88000ff588a0 0000000000000000 [ 233.048393] ffff88000facbd08 ffffffff823dbd5a ffffffff823dbcb0 ffff88000ff58850 [ 233.048393] Call Trace: [ 233.048393] [] kfree+0x5f/0xca [ 233.048393] [] inet_sock_destruct+0xaa/0x13c [ 233.048393] [] ? inet_sk_rebuild_header +0x319/0x319 [ 233.048393] [] __sk_free+0x21/0x14b [ 233.048393] [] sk_free+0x26/0x2a [ 233.048393] [] sctp_close+0x215/0x224 [ 233.048393] [] ? lock_release+0x16f/0x1b9 [ 233.048393] [] inet_release+0x7e/0x85 [ 233.048393] [] sock_release+0x1f/0x77 [ 233.048393] [] sock_close+0x27/0x2b [ 233.048393] [] __fput+0x101/0x20a [ 233.048393] [] ____fput+0xe/0x10 [ 233.048393] [] task_work_run+0x5d/0x75 [ 233.048393] [] do_exit+0x290/0x7f5 [ 233.048393] [] ? retint_swapgs+0x13/0x1b [ 233.048393] [] do_group_exit+0x7b/0xba [ 233.048393] [] sys_exit_group+0x17/0x17 [ 233.048393] [] tracesys+0xdd/0xe2 [ 233.048393] Code: 59 01 5d c3 55 48 89 e5 53 41 50 0f 1f 44 00 00 48 89 fb e8 d4 b0 f0 ff 84 c0 75 11 48 89 de 48 c7 c7 fc fa f7 82 e8 0d 0f 57 01 <0f> 0b 5f 5b 5d c3 55 48 89 e5 0f 1f 44 00 00 48 63 87 d8 00 00 [ 233.048393] RIP [] kfree_debugcheck+0x27/0x2d [ 233.048393] RSP Reported-by: Fengguang Wu Tested-by: Fengguang Wu Signed-off-by: Eric Dumazet Cc: "H.K. Jerry Chu" Acked-by: Neal Cardwell Acked-by: H.K. Jerry Chu Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 7 ++----- net/ipv4/inet_connection_sock.c | 4 ++-- 2 files changed, 4 insertions(+), 7 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 4f70ef0b946d..845372b025f6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -149,11 +149,8 @@ void inet_sock_destruct(struct sock *sk) pr_err("Attempt to release alive inet socket %p\n", sk); return; } - if (sk->sk_type == SOCK_STREAM) { - struct fastopen_queue *fastopenq = - inet_csk(sk)->icsk_accept_queue.fastopenq; - kfree(fastopenq); - } + if (sk->sk_protocol == IPPROTO_TCP) + kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(atomic_read(&sk->sk_wmem_alloc)); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 8464b79c493f..f0c5b9c1a957 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -314,7 +314,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) newsk = req->sk; sk_acceptq_removed(sk); - if (sk->sk_type == SOCK_STREAM && queue->fastopenq != NULL) { + if (sk->sk_protocol == IPPROTO_TCP && queue->fastopenq != NULL) { spin_lock_bh(&queue->fastopenq->lock); if (tcp_rsk(req)->listener) { /* We are still waiting for the final ACK from 3WHS @@ -775,7 +775,7 @@ void inet_csk_listen_stop(struct sock *sk) percpu_counter_inc(sk->sk_prot->orphan_count); - if (sk->sk_type == SOCK_STREAM && tcp_rsk(req)->listener) { + if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->listener) { BUG_ON(tcp_sk(child)->fastopen_rsk != req); BUG_ON(sk != tcp_rsk(req)->listener); -- cgit v1.3-14-g43fede From d679c5324d9a87c6295f56c2dea52d5f68834f41 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 6 Sep 2012 20:37:06 +0000 Subject: igmp: avoid drop_monitor false positives igmp should call consume_skb() for all correctly processed packets, to avoid false dropwatch/drop_monitor false positives. Reported-by: Shawn Bohrer Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 0b5580c69f2d..3479b98a00a7 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -815,14 +815,15 @@ static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) return 1; } -static void igmp_heard_report(struct in_device *in_dev, __be32 group) +/* return true if packet was dropped */ +static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) - return; + return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { @@ -832,9 +833,11 @@ static void igmp_heard_report(struct in_device *in_dev, __be32 group) } } rcu_read_unlock(); + return false; } -static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, +/* return true if packet was dropped */ +static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); @@ -866,7 +869,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { - return; /* ignore bogus packet; freed by caller */ + return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_Query_Response_Interval; @@ -883,13 +886,13 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) - return; + return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) - return; + return true; ih3 = igmpv3_query_hdr(skb); } @@ -901,9 +904,9 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, in_dev->mr_qrv = ih3->qrv; if (!group) { /* general query */ if (ih3->nsrcs) - return; /* no sources allowed */ + return false; /* no sources allowed */ igmp_gq_start_timer(in_dev); - return; + return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; @@ -939,6 +942,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, igmp_mod_timer(im, max_delay); } rcu_read_unlock(); + return false; } /* called in rcu_read_lock() section */ @@ -948,6 +952,7 @@ int igmp_rcv(struct sk_buff *skb) struct igmphdr *ih; struct in_device *in_dev = __in_dev_get_rcu(skb->dev); int len = skb->len; + bool dropped = true; if (in_dev == NULL) goto drop; @@ -969,7 +974,7 @@ int igmp_rcv(struct sk_buff *skb) ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: - igmp_heard_query(in_dev, skb, len); + dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: @@ -979,7 +984,7 @@ int igmp_rcv(struct sk_buff *skb) /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) - igmp_heard_report(in_dev, ih->group); + dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 @@ -997,7 +1002,10 @@ int igmp_rcv(struct sk_buff *skb) } drop: - kfree_skb(skb); + if (dropped) + kfree_skb(skb); + else + consume_skb(skb); return 0; } -- cgit v1.3-14-g43fede From 4ccfe6d4109252dfadcd6885f33ed600ee03dbf8 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 +- net/ipv4/arp.c | 2 +- net/ipv4/devinet.c | 6 +++--- net/ipv4/fib_frontend.c | 20 ++++++++++---------- net/ipv4/fib_rules.c | 2 +- net/ipv4/fib_trie.c | 6 +++--- net/ipv4/route.c | 19 +++---------------- 7 files changed, 22 insertions(+), 35 deletions(-) (limited to 'net/ipv4') 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, diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 77e87aff419a..47800459e4cb 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1225,7 +1225,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev)); break; default: break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index adf273f8ad2e..f14eff506743 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1500,7 +1500,7 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1 || i == IPV4_DEVCONF_ROUTE_LOCALNET - 1) if ((new_value == 0) && (old_value != 0)) - rt_cache_flush(net, 0); + rt_cache_flush(net); } return ret; @@ -1534,7 +1534,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, dev_disable_lro(idev->dev); } rtnl_unlock(); - rt_cache_flush(net, 0); + rt_cache_flush(net); } } @@ -1551,7 +1551,7 @@ static int ipv4_doint_and_flush(ctl_table *ctl, int write, struct net *net = ctl->extra2; if (write && *valp != val) - rt_cache_flush(net, 0); + rt_cache_flush(net); return ret; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index acdee325d972..8a7cd795a96e 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -148,7 +148,7 @@ static void fib_flush(struct net *net) } if (flushed) - rt_cache_flush(net, -1); + rt_cache_flush(net); } /* @@ -999,11 +999,11 @@ static void nl_fib_lookup_exit(struct net *net) net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, int force, int delay) +static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down_dev(dev, force)) fib_flush(dev_net(dev)); - rt_cache_flush(dev_net(dev), delay); + rt_cache_flush(dev_net(dev)); arp_ifdown(dev); } @@ -1020,7 +1020,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); break; case NETDEV_DOWN: fib_del_ifaddr(ifa, NULL); @@ -1029,9 +1029,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. * Disable IP. */ - fib_disable_ip(dev, 1, 0); + fib_disable_ip(dev, 1); } else { - rt_cache_flush(dev_net(dev), -1); + rt_cache_flush(dev_net(dev)); } break; } @@ -1045,7 +1045,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct net *net = dev_net(dev); if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, 2, -1); + fib_disable_ip(dev, 2); rt_flush_dev(dev); return NOTIFY_DONE; } @@ -1061,14 +1061,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo fib_sync_up(dev); #endif atomic_inc(&net->ipv4.dev_addr_genid); - rt_cache_flush(net, -1); + rt_cache_flush(net); break; case NETDEV_DOWN: - fib_disable_ip(dev, 0, 0); + fib_disable_ip(dev, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(net, 0); + rt_cache_flush(net); break; } return NOTIFY_DONE; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index a83d74e498d2..274309d3aded 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -259,7 +259,7 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) static void fib4_rule_flush_cache(struct fib_rules_ops *ops) { - rt_cache_flush(ops->fro_net, -1); + rt_cache_flush(ops->fro_net); } static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 3c820dae235e..8d766106b540 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1286,7 +1286,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) fib_release_info(fi_drop); if (state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); @@ -1333,7 +1333,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : fa_head)); - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); succeeded: @@ -1711,7 +1711,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) trie_leaf_remove(t, l); if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); + rt_cache_flush(cfg->fc_nlinfo.nl_net); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index dc9549b5eb1c..ab1e7c7c38fc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -461,11 +461,7 @@ static void rt_cache_invalidate(struct net *net) atomic_add(shuffle + 1U, &net->ipv4.rt_genid); } -/* - * delay < 0 : invalidate cache (fast : entries will be deleted later) - * delay >= 0 : invalidate & flush cache (can be long) - */ -void rt_cache_flush(struct net *net, int delay) +void rt_cache_flush(struct net *net) { rt_cache_invalidate(net); } @@ -2345,7 +2341,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) void ip_rt_multicast_event(struct in_device *in_dev) { - rt_cache_flush(dev_net(in_dev->dev), 0); + rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL @@ -2354,16 +2350,7 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write, size_t *lenp, loff_t *ppos) { if (write) { - int flush_delay; - ctl_table ctl; - struct net *net; - - memcpy(&ctl, __ctl, sizeof(ctl)); - ctl.data = &flush_delay; - proc_dointvec(&ctl, write, buffer, lenp, ppos); - - net = (struct net *)__ctl->extra1; - rt_cache_flush(net, flush_delay); + rt_cache_flush((struct net *)__ctl->extra1); return 0; } -- cgit v1.3-14-g43fede From ba8bd0ea982427258ab86144ac5fd1a9d7763a90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 7 Sep 2012 22:27:11 +0200 Subject: net: rt_cache_flush() cleanup We dont use jhash anymore since route cache removal, so we can get rid of get_random_bytes() calls for rt_genid changes. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/route.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index ab1e7c7c38fc..d39edf16d607 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -447,23 +447,9 @@ static inline bool rt_is_expired(const struct rtable *rth) return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); } -/* - * Perturbation of rt_genid by a small quantity [1..256] - * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() - * many times (2^24) without giving recent rt_genid. - * Jenkins hash is strong enough that litle changes of rt_genid are OK. - */ -static void rt_cache_invalidate(struct net *net) -{ - unsigned char shuffle; - - get_random_bytes(&shuffle, sizeof(shuffle)); - atomic_add(shuffle + 1U, &net->ipv4.rt_genid); -} - void rt_cache_flush(struct net *net) { - rt_cache_invalidate(net); + atomic_inc(&net->ipv4.rt_genid); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -2520,8 +2506,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - get_random_bytes(&net->ipv4.rt_genid, - sizeof(net->ipv4.rt_genid)); + atomic_set(&net->ipv4.rt_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); return 0; -- cgit v1.3-14-g43fede From 9f00d9776bc5beb92e8bfc884a7e96ddc5589e2e Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sat, 8 Sep 2012 02:53:54 +0000 Subject: netlink: hide struct module parameter in netlink_kernel_create This patch defines netlink_kernel_create as a wrapper function of __netlink_kernel_create to hide the struct module *me parameter (which seems to be THIS_MODULE in all existing netlink subsystems). Suggested by David S. Miller. Signed-off-by: Pablo Neira Ayuso Signed-off-by: David S. Miller --- crypto/crypto_user.c | 3 +-- drivers/connector/connector.c | 3 +-- drivers/infiniband/core/netlink.c | 2 +- drivers/scsi/scsi_netlink.c | 2 +- drivers/scsi/scsi_transport_iscsi.c | 3 +-- drivers/staging/gdm72xx/netlink_k.c | 2 +- include/linux/netlink.h | 13 ++++++++++--- kernel/audit.c | 3 +-- lib/kobject_uevent.c | 3 +-- net/bridge/netfilter/ebt_ulog.c | 3 +-- net/core/rtnetlink.c | 2 +- net/core/sock_diag.c | 3 +-- net/decnet/netfilter/dn_rtmsg.c | 3 +-- net/ipv4/fib_frontend.c | 2 +- net/ipv4/netfilter/ipt_ULOG.c | 3 +-- net/netfilter/nfnetlink.c | 2 +- net/netlink/af_netlink.c | 8 +++----- net/netlink/genetlink.c | 3 +-- net/xfrm/xfrm_user.c | 2 +- security/selinux/netlink.c | 3 +-- 20 files changed, 31 insertions(+), 37 deletions(-) (limited to 'net/ipv4') diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index ba2c611154af..165914e63ef2 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -500,8 +500,7 @@ static int __init crypto_user_init(void) .input = crypto_netlink_rcv, }; - crypto_nlsk = netlink_kernel_create(&init_net, NETLINK_CRYPTO, - THIS_MODULE, &cfg); + crypto_nlsk = netlink_kernel_create(&init_net, NETLINK_CRYPTO, &cfg); if (!crypto_nlsk) return -ENOMEM; diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c index 82fa4f0f91d6..965b7811e04f 100644 --- a/drivers/connector/connector.c +++ b/drivers/connector/connector.c @@ -264,8 +264,7 @@ static int __devinit cn_init(void) .input = dev->input, }; - dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, - THIS_MODULE, &cfg); + dev->nls = netlink_kernel_create(&init_net, NETLINK_CONNECTOR, &cfg); if (!dev->nls) return -EIO; diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c index 3ae2bfd31015..fe10a949aef9 100644 --- a/drivers/infiniband/core/netlink.c +++ b/drivers/infiniband/core/netlink.c @@ -177,7 +177,7 @@ int __init ibnl_init(void) .input = ibnl_rcv, }; - nls = netlink_kernel_create(&init_net, NETLINK_RDMA, THIS_MODULE, &cfg); + nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg); if (!nls) { pr_warn("Failed to create netlink socket\n"); return -ENOMEM; diff --git a/drivers/scsi/scsi_netlink.c b/drivers/scsi/scsi_netlink.c index 8818dd681c19..3252bc9625ee 100644 --- a/drivers/scsi/scsi_netlink.c +++ b/drivers/scsi/scsi_netlink.c @@ -501,7 +501,7 @@ scsi_netlink_init(void) } scsi_nl_sock = netlink_kernel_create(&init_net, NETLINK_SCSITRANSPORT, - THIS_MODULE, &cfg); + &cfg); if (!scsi_nl_sock) { printk(KERN_ERR "%s: register of receive handler failed\n", __func__); diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index fa1dfaa83e32..519bd5303f3f 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2969,8 +2969,7 @@ static __init int iscsi_transport_init(void) if (err) goto unregister_conn_class; - nls = netlink_kernel_create(&init_net, NETLINK_ISCSI, - THIS_MODULE, &cfg); + nls = netlink_kernel_create(&init_net, NETLINK_ISCSI, &cfg); if (!nls) { err = -ENOBUFS; goto unregister_session_class; diff --git a/drivers/staging/gdm72xx/netlink_k.c b/drivers/staging/gdm72xx/netlink_k.c index 3abb31df8f28..2109cab0a14c 100644 --- a/drivers/staging/gdm72xx/netlink_k.c +++ b/drivers/staging/gdm72xx/netlink_k.c @@ -95,7 +95,7 @@ struct sock *netlink_init(int unit, void (*cb)(struct net_device *dev, u16 type, init_MUTEX(&netlink_mutex); #endif - sock = netlink_kernel_create(&init_net, unit, THIS_MODULE, &cfg); + sock = netlink_kernel_create(&init_net, unit, &cfg); if (sock) rcv_cb = cb; diff --git a/include/linux/netlink.h b/include/linux/netlink.h index 8719a4e235a5..cd17dda5a987 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -153,6 +153,7 @@ struct nlattr { #include #include +#include #include struct net; @@ -188,9 +189,15 @@ struct netlink_kernel_cfg { unsigned int flags; }; -extern struct sock *netlink_kernel_create(struct net *net, int unit, - struct module *module, - struct netlink_kernel_cfg *cfg); +extern struct sock *__netlink_kernel_create(struct net *net, int unit, + struct module *module, + struct netlink_kernel_cfg *cfg); +static inline struct sock * +netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg) +{ + return __netlink_kernel_create(net, unit, THIS_MODULE, cfg); +} + extern void netlink_kernel_release(struct sock *sk); extern int __netlink_change_ngroups(struct sock *sk, unsigned int groups); extern int netlink_change_ngroups(struct sock *sk, unsigned int groups); diff --git a/kernel/audit.c b/kernel/audit.c index ea3b7b6191c7..a24aafa850ae 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -971,8 +971,7 @@ static int __init audit_init(void) printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); - audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, - THIS_MODULE, &cfg); + audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, &cfg); if (!audit_sock) audit_panic("cannot initialize netlink socket"); else diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index c2e97787d01e..52e5abbc41db 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -382,8 +382,7 @@ static int uevent_net_init(struct net *net) if (!ue_sk) return -ENOMEM; - ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, - THIS_MODULE, &cfg); + ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { printk(KERN_ERR "kobject_uevent: unable to create netlink socket!\n"); diff --git a/net/bridge/netfilter/ebt_ulog.c b/net/bridge/netfilter/ebt_ulog.c index 19063473c71f..3476ec469740 100644 --- a/net/bridge/netfilter/ebt_ulog.c +++ b/net/bridge/netfilter/ebt_ulog.c @@ -298,8 +298,7 @@ static int __init ebt_ulog_init(void) spin_lock_init(&ulog_buffers[i].lock); } - ebtulognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, - THIS_MODULE, &cfg); + ebtulognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, &cfg); if (!ebtulognl) ret = -ENOMEM; else if ((ret = xt_register_target(&ebt_ulog_tg_reg)) != 0) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a71806eb9cc6..508c5df4a09c 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2384,7 +2384,7 @@ static int __net_init rtnetlink_net_init(struct net *net) .flags = NL_CFG_F_NONROOT_RECV, }; - sk = netlink_kernel_create(net, NETLINK_ROUTE, THIS_MODULE, &cfg); + sk = netlink_kernel_create(net, NETLINK_ROUTE, &cfg); if (!sk) return -ENOMEM; net->rtnl = sk; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 9d8755e4a7a5..602cd637182e 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -172,8 +172,7 @@ static int __net_init diag_net_init(struct net *net) .input = sock_diag_rcv, }; - net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, - THIS_MODULE, &cfg); + net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); return net->diag_nlsk == NULL ? -ENOMEM : 0; } diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 11db0ecf342f..dfe42012a044 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -130,8 +130,7 @@ static int __init dn_rtmsg_init(void) .input = dnrmg_receive_user_skb, }; - dnrmg = netlink_kernel_create(&init_net, - NETLINK_DNRTMSG, THIS_MODULE, &cfg); + dnrmg = netlink_kernel_create(&init_net, NETLINK_DNRTMSG, &cfg); if (dnrmg == NULL) { printk(KERN_ERR "dn_rtmsg: Cannot create netlink socket"); return -ENOMEM; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 8a7cd795a96e..dc1f10ed1872 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -986,7 +986,7 @@ static int __net_init nl_fib_lookup_init(struct net *net) .input = nl_fib_input, }; - sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, THIS_MODULE, &cfg); + sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg); if (sk == NULL) return -EAFNOSUPPORT; net->ipv4.fibnl = sk; diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index 1109f7f6c254..b5ef3cba2250 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -396,8 +396,7 @@ static int __init ulog_tg_init(void) for (i = 0; i < ULOG_MAXNLGROUPS; i++) setup_timer(&ulog_buffers[i].timer, ulog_timer, i); - nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, - THIS_MODULE, &cfg); + nflognl = netlink_kernel_create(&init_net, NETLINK_NFLOG, &cfg); if (!nflognl) return -ENOMEM; diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a26503342e71..ffb92c03a358 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -241,7 +241,7 @@ static int __net_init nfnetlink_net_init(struct net *net) #endif }; - nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, THIS_MODULE, &cfg); + nfnl = netlink_kernel_create(net, NETLINK_NETFILTER, &cfg); if (!nfnl) return -ENOMEM; net->nfnl_stash = nfnl; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index b74540ce3c14..4d348e97e131 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1526,9 +1526,8 @@ static void netlink_data_ready(struct sock *sk, int len) */ struct sock * -netlink_kernel_create(struct net *net, int unit, - struct module *module, - struct netlink_kernel_cfg *cfg) +__netlink_kernel_create(struct net *net, int unit, struct module *module, + struct netlink_kernel_cfg *cfg) { struct socket *sock; struct sock *sk; @@ -1603,8 +1602,7 @@ out_sock_release_nosk: sock_release(sock); return NULL; } -EXPORT_SYMBOL(netlink_kernel_create); - +EXPORT_SYMBOL(__netlink_kernel_create); void netlink_kernel_release(struct sock *sk) diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index c1b71aef9f71..19288b7d6135 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -922,8 +922,7 @@ static int __net_init genl_pernet_init(struct net *net) }; /* we'll bump the group number right afterwards */ - net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, - THIS_MODULE, &cfg); + net->genl_sock = netlink_kernel_create(net, NETLINK_GENERIC, &cfg); if (!net->genl_sock && net_eq(net, &init_net)) panic("GENL: Cannot initialize generic netlink\n"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index ab58034c42d6..354070adb5ef 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2963,7 +2963,7 @@ static int __net_init xfrm_user_net_init(struct net *net) .input = xfrm_netlink_rcv, }; - nlsk = netlink_kernel_create(net, NETLINK_XFRM, THIS_MODULE, &cfg); + nlsk = netlink_kernel_create(net, NETLINK_XFRM, &cfg); if (nlsk == NULL) return -ENOMEM; net->xfrm.nlsk_stash = nlsk; /* Don't set to NULL */ diff --git a/security/selinux/netlink.c b/security/selinux/netlink.c index 0d2cd11f3c22..14d810ead420 100644 --- a/security/selinux/netlink.c +++ b/security/selinux/netlink.c @@ -116,8 +116,7 @@ static int __init selnl_init(void) .flags = NL_CFG_F_NONROOT_RECV, }; - selnl = netlink_kernel_create(&init_net, NETLINK_SELINUX, - THIS_MODULE, &cfg); + selnl = netlink_kernel_create(&init_net, NETLINK_SELINUX, &cfg); if (selnl == NULL) panic("SELinux: Cannot create netlink socket."); return 0; -- cgit v1.3-14-g43fede From 15e473046cb6e5d18a4d0057e61d76315230382b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Fri, 7 Sep 2012 20:12:54 +0000 Subject: netlink: Rename pid to portid to avoid confusion It is a frequent mistake to confuse the netlink port identifier with a process identifier. Try to reduce this confusion by renaming fields that hold port identifiers portid instead of pid. I have carefully avoided changing the structures exported to userspace to avoid changing the userspace API. I have successfully built an allyesconfig kernel with this change. Signed-off-by: "Eric W. Biederman" Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- crypto/crypto_user.c | 4 +- drivers/net/team/team.c | 38 +++--- drivers/net/wireless/mac80211_hwsim.c | 46 ++++---- drivers/scsi/scsi_transport_iscsi.c | 4 +- drivers/staging/gdm72xx/netlink_k.c | 2 +- fs/dlm/netlink.c | 8 +- include/linux/netlink.h | 14 +-- include/net/cfg80211.h | 2 +- include/net/genetlink.h | 34 +++--- include/net/netfilter/nf_conntrack_ecache.h | 32 +++--- include/net/netlink.h | 26 ++--- include/net/nfc/nfc.h | 2 +- include/net/xfrm.h | 6 +- kernel/audit.c | 20 ++-- kernel/taskstats.c | 4 +- net/bridge/br_fdb.c | 6 +- net/bridge/br_netlink.c | 2 +- net/can/gw.c | 2 +- net/core/fib_rules.c | 6 +- net/core/neighbour.c | 8 +- net/core/rtnetlink.c | 12 +- net/dcb/dcbnl.c | 18 +-- net/decnet/dn_dev.c | 6 +- net/decnet/dn_route.c | 10 +- net/decnet/dn_table.c | 12 +- net/ieee802154/nl-mac.c | 6 +- net/ieee802154/nl-phy.c | 6 +- net/ipv4/devinet.c | 28 ++--- net/ipv4/fib_frontend.c | 10 +- net/ipv4/fib_semantics.c | 8 +- net/ipv4/fib_trie.c | 2 +- net/ipv4/inet_diag.c | 32 +++--- net/ipv4/ipmr.c | 10 +- net/ipv4/route.c | 8 +- net/ipv4/tcp_metrics.c | 2 +- net/ipv4/udp_diag.c | 6 +- net/ipv6/addrconf.c | 32 +++--- net/ipv6/addrlabel.c | 10 +- net/ipv6/ip6mr.c | 10 +- net/ipv6/route.c | 20 ++-- net/irda/irnetlink.c | 2 +- net/key/af_key.c | 32 +++--- net/l2tp/l2tp_netlink.c | 24 ++-- net/netfilter/ipset/ip_set_core.c | 24 ++-- net/netfilter/ipvs/ip_vs_ctl.c | 6 +- net/netfilter/nf_conntrack_ecache.c | 2 +- net/netfilter/nf_conntrack_netlink.c | 78 ++++++------- net/netfilter/nfnetlink_acct.c | 12 +- net/netfilter/nfnetlink_cthelper.c | 12 +- net/netfilter/nfnetlink_cttimeout.c | 12 +- net/netfilter/nfnetlink_log.c | 18 +-- net/netfilter/nfnetlink_queue_core.c | 28 ++--- net/netlabel/netlabel_cipso_v4.c | 2 +- net/netlabel/netlabel_mgmt.c | 4 +- net/netlabel/netlabel_unlabeled.c | 2 +- net/netlink/af_netlink.c | 172 ++++++++++++++-------------- net/netlink/genetlink.c | 42 +++---- net/nfc/netlink.c | 26 ++--- net/openvswitch/actions.c | 4 +- net/openvswitch/datapath.c | 84 +++++++------- net/openvswitch/datapath.h | 2 +- net/openvswitch/vport.c | 2 +- net/openvswitch/vport.h | 6 +- net/packet/diag.c | 6 +- net/phonet/pn_netlink.c | 14 +-- net/sched/act_api.c | 52 ++++----- net/sched/cls_api.c | 14 +-- net/sched/sch_api.c | 44 +++---- net/tipc/netlink.c | 2 +- net/unix/diag.c | 14 +-- net/wireless/core.h | 2 +- net/wireless/mlme.c | 16 +-- net/wireless/nl80211.c | 110 +++++++++--------- net/xfrm/xfrm_state.c | 10 +- net/xfrm/xfrm_user.c | 62 +++++----- 75 files changed, 728 insertions(+), 728 deletions(-) (limited to 'net/ipv4') diff --git a/crypto/crypto_user.c b/crypto/crypto_user.c index 165914e63ef2..6bba414d0c61 100644 --- a/crypto/crypto_user.c +++ b/crypto/crypto_user.c @@ -166,7 +166,7 @@ static int crypto_report_alg(struct crypto_alg *alg, struct crypto_user_alg *ualg; int err = 0; - nlh = nlmsg_put(skb, NETLINK_CB(in_skb).pid, info->nlmsg_seq, + nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, info->nlmsg_seq, CRYPTO_MSG_GETALG, sizeof(*ualg), info->nlmsg_flags); if (!nlh) { err = -EMSGSIZE; @@ -216,7 +216,7 @@ static int crypto_report(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, if (err) return err; - return nlmsg_unicast(crypto_nlsk, skb, NETLINK_CB(in_skb).pid); + return nlmsg_unicast(crypto_nlsk, skb, NETLINK_CB(in_skb).portid); } static int crypto_dump_report(struct sk_buff *skb, struct netlink_callback *cb) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index b4f67b55ef79..266af7b38ebc 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1886,7 +1886,7 @@ static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq, + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &team_nl_family, 0, TEAM_CMD_NOOP); if (IS_ERR(hdr)) { err = PTR_ERR(hdr); @@ -1895,7 +1895,7 @@ static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) genlmsg_end(msg, hdr); - return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid); + return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); err_msg_put: nlmsg_free(msg); @@ -1952,7 +1952,7 @@ static int team_nl_send_generic(struct genl_info *info, struct team *team, if (err < 0) goto err_fill; - err = genlmsg_unicast(genl_info_net(info), skb, info->snd_pid); + err = genlmsg_unicast(genl_info_net(info), skb, info->snd_portid); return err; err_fill: @@ -1961,11 +1961,11 @@ err_fill: } typedef int team_nl_send_func_t(struct sk_buff *skb, - struct team *team, u32 pid); + struct team *team, u32 portid); -static int team_nl_send_unicast(struct sk_buff *skb, struct team *team, u32 pid) +static int team_nl_send_unicast(struct sk_buff *skb, struct team *team, u32 portid) { - return genlmsg_unicast(dev_net(team->dev), skb, pid); + return genlmsg_unicast(dev_net(team->dev), skb, portid); } static int team_nl_fill_one_option_get(struct sk_buff *skb, struct team *team, @@ -2050,13 +2050,13 @@ nest_cancel: } static int __send_and_alloc_skb(struct sk_buff **pskb, - struct team *team, u32 pid, + struct team *team, u32 portid, team_nl_send_func_t *send_func) { int err; if (*pskb) { - err = send_func(*pskb, team, pid); + err = send_func(*pskb, team, portid); if (err) return err; } @@ -2066,7 +2066,7 @@ static int __send_and_alloc_skb(struct sk_buff **pskb, return 0; } -static int team_nl_send_options_get(struct team *team, u32 pid, u32 seq, +static int team_nl_send_options_get(struct team *team, u32 portid, u32 seq, int flags, team_nl_send_func_t *send_func, struct list_head *sel_opt_inst_list) { @@ -2083,11 +2083,11 @@ static int team_nl_send_options_get(struct team *team, u32 pid, u32 seq, struct team_option_inst, tmp_list); start_again: - err = __send_and_alloc_skb(&skb, team, pid, send_func); + err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) return err; - hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags | NLM_F_MULTI, + hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags | NLM_F_MULTI, TEAM_CMD_OPTIONS_GET); if (IS_ERR(hdr)) return PTR_ERR(hdr); @@ -2120,15 +2120,15 @@ start_again: goto start_again; send_done: - nlh = nlmsg_put(skb, pid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, NLMSG_DONE, 0, flags | NLM_F_MULTI); if (!nlh) { - err = __send_and_alloc_skb(&skb, team, pid, send_func); + err = __send_and_alloc_skb(&skb, team, portid, send_func); if (err) goto errout; goto send_done; } - return send_func(skb, team, pid); + return send_func(skb, team, portid); nla_put_failure: err = -EMSGSIZE; @@ -2151,7 +2151,7 @@ static int team_nl_cmd_options_get(struct sk_buff *skb, struct genl_info *info) list_for_each_entry(opt_inst, &team->option_inst_list, list) list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list); - err = team_nl_send_options_get(team, info->snd_pid, info->snd_seq, + err = team_nl_send_options_get(team, info->snd_portid, info->snd_seq, NLM_F_ACK, team_nl_send_unicast, &sel_opt_inst_list); @@ -2305,7 +2305,7 @@ team_put: } static int team_nl_fill_port_list_get(struct sk_buff *skb, - u32 pid, u32 seq, int flags, + u32 portid, u32 seq, int flags, struct team *team, bool fillall) { @@ -2313,7 +2313,7 @@ static int team_nl_fill_port_list_get(struct sk_buff *skb, void *hdr; struct team_port *port; - hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags, + hdr = genlmsg_put(skb, portid, seq, &team_nl_family, flags, TEAM_CMD_PORT_LIST_GET); if (IS_ERR(hdr)) return PTR_ERR(hdr); @@ -2362,7 +2362,7 @@ static int team_nl_fill_port_list_get_all(struct sk_buff *skb, struct genl_info *info, int flags, struct team *team) { - return team_nl_fill_port_list_get(skb, info->snd_pid, + return team_nl_fill_port_list_get(skb, info->snd_portid, info->snd_seq, NLM_F_ACK, team, true); } @@ -2415,7 +2415,7 @@ static struct genl_multicast_group team_change_event_mcgrp = { }; static int team_nl_send_multicast(struct sk_buff *skb, - struct team *team, u32 pid) + struct team *team, u32 portid) { return genlmsg_multicast_netns(dev_net(team->dev), skb, 0, team_change_event_mcgrp.id, GFP_KERNEL); diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 72b0456e41bf..9d45b3bb974c 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -38,7 +38,7 @@ MODULE_AUTHOR("Jouni Malinen"); MODULE_DESCRIPTION("Software simulator of 802.11 radio(s) for mac80211"); MODULE_LICENSE("GPL"); -static u32 wmediumd_pid; +static u32 wmediumd_portid; static int radios = 2; module_param(radios, int, 0444); @@ -545,7 +545,7 @@ static bool mac80211_hwsim_addr_match(struct mac80211_hwsim_data *data, static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, struct sk_buff *my_skb, - int dst_pid) + int dst_portid) { struct sk_buff *skb; struct mac80211_hwsim_data *data = hw->priv; @@ -619,7 +619,7 @@ static void mac80211_hwsim_tx_frame_nl(struct ieee80211_hw *hw, goto nla_put_failure; genlmsg_end(skb, msg_head); - genlmsg_unicast(&init_net, skb, dst_pid); + genlmsg_unicast(&init_net, skb, dst_portid); /* Enqueue the packet */ skb_queue_tail(&data->pending, my_skb); @@ -715,7 +715,7 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, { bool ack; struct ieee80211_tx_info *txi; - u32 _pid; + u32 _portid; mac80211_hwsim_monitor_rx(hw, skb); @@ -726,10 +726,10 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw, } /* wmediumd mode check */ - _pid = ACCESS_ONCE(wmediumd_pid); + _portid = ACCESS_ONCE(wmediumd_portid); - if (_pid) - return mac80211_hwsim_tx_frame_nl(hw, skb, _pid); + if (_portid) + return mac80211_hwsim_tx_frame_nl(hw, skb, _portid); /* NO wmediumd detected, perfect medium simulation */ ack = mac80211_hwsim_tx_frame_no_nl(hw, skb); @@ -814,7 +814,7 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac, struct ieee80211_hw *hw = arg; struct sk_buff *skb; struct ieee80211_tx_info *info; - u32 _pid; + u32 _portid; hwsim_check_magic(vif); @@ -831,10 +831,10 @@ static void mac80211_hwsim_beacon_tx(void *arg, u8 *mac, mac80211_hwsim_monitor_rx(hw, skb); /* wmediumd mode check */ - _pid = ACCESS_ONCE(wmediumd_pid); + _portid = ACCESS_ONCE(wmediumd_portid); - if (_pid) - return mac80211_hwsim_tx_frame_nl(hw, skb, _pid); + if (_portid) + return mac80211_hwsim_tx_frame_nl(hw, skb, _portid); mac80211_hwsim_tx_frame_no_nl(hw, skb); dev_kfree_skb(skb); @@ -1315,7 +1315,7 @@ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif) struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct sk_buff *skb; struct ieee80211_pspoll *pspoll; - u32 _pid; + u32 _portid; if (!vp->assoc) return; @@ -1336,10 +1336,10 @@ static void hwsim_send_ps_poll(void *dat, u8 *mac, struct ieee80211_vif *vif) memcpy(pspoll->ta, mac, ETH_ALEN); /* wmediumd mode check */ - _pid = ACCESS_ONCE(wmediumd_pid); + _portid = ACCESS_ONCE(wmediumd_portid); - if (_pid) - return mac80211_hwsim_tx_frame_nl(data->hw, skb, _pid); + if (_portid) + return mac80211_hwsim_tx_frame_nl(data->hw, skb, _portid); if (!mac80211_hwsim_tx_frame_no_nl(data->hw, skb)) printk(KERN_DEBUG "%s: PS-poll frame not ack'ed\n", __func__); @@ -1353,7 +1353,7 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, struct hwsim_vif_priv *vp = (void *)vif->drv_priv; struct sk_buff *skb; struct ieee80211_hdr *hdr; - u32 _pid; + u32 _portid; if (!vp->assoc) return; @@ -1375,10 +1375,10 @@ static void hwsim_send_nullfunc(struct mac80211_hwsim_data *data, u8 *mac, memcpy(hdr->addr3, vp->bssid, ETH_ALEN); /* wmediumd mode check */ - _pid = ACCESS_ONCE(wmediumd_pid); + _portid = ACCESS_ONCE(wmediumd_portid); - if (_pid) - return mac80211_hwsim_tx_frame_nl(data->hw, skb, _pid); + if (_portid) + return mac80211_hwsim_tx_frame_nl(data->hw, skb, _portid); if (!mac80211_hwsim_tx_frame_no_nl(data->hw, skb)) printk(KERN_DEBUG "%s: nullfunc frame not ack'ed\n", __func__); @@ -1632,10 +1632,10 @@ static int hwsim_register_received_nl(struct sk_buff *skb_2, if (info == NULL) goto out; - wmediumd_pid = info->snd_pid; + wmediumd_portid = info->snd_portid; printk(KERN_DEBUG "mac80211_hwsim: received a REGISTER, " - "switching to wmediumd mode with pid %d\n", info->snd_pid); + "switching to wmediumd mode with pid %d\n", info->snd_portid); return 0; out: @@ -1672,10 +1672,10 @@ static int mac80211_hwsim_netlink_notify(struct notifier_block *nb, if (state != NETLINK_URELEASE) return NOTIFY_DONE; - if (notify->pid == wmediumd_pid) { + if (notify->portid == wmediumd_portid) { printk(KERN_INFO "mac80211_hwsim: wmediumd released netlink" " socket, switching to perfect channel medium\n"); - wmediumd_pid = 0; + wmediumd_portid = 0; } return NOTIFY_DONE; diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c index 519bd5303f3f..31969f2e13ce 100644 --- a/drivers/scsi/scsi_transport_iscsi.c +++ b/drivers/scsi/scsi_transport_iscsi.c @@ -2119,7 +2119,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) switch (nlh->nlmsg_type) { case ISCSI_UEVENT_CREATE_SESSION: err = iscsi_if_create_session(priv, ep, ev, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, ev->u.c_session.initial_cmdsn, ev->u.c_session.cmds_max, ev->u.c_session.queue_depth); @@ -2132,7 +2132,7 @@ iscsi_if_recv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, uint32_t *group) } err = iscsi_if_create_session(priv, ep, ev, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, ev->u.c_bound_session.initial_cmdsn, ev->u.c_bound_session.cmds_max, ev->u.c_bound_session.queue_depth); diff --git a/drivers/staging/gdm72xx/netlink_k.c b/drivers/staging/gdm72xx/netlink_k.c index 2109cab0a14c..20d0aec52e72 100644 --- a/drivers/staging/gdm72xx/netlink_k.c +++ b/drivers/staging/gdm72xx/netlink_k.c @@ -135,7 +135,7 @@ int netlink_send(struct sock *sock, int group, u16 type, void *msg, int len) } memcpy(nlmsg_data(nlh), msg, len); - NETLINK_CB(skb).pid = 0; + NETLINK_CB(skb).portid = 0; NETLINK_CB(skb).dst_group = 0; ret = netlink_broadcast(sock, skb, 0, group+1, GFP_ATOMIC); diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index ef17e0169da1..60a327863b11 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -14,7 +14,7 @@ #include "dlm_internal.h" static uint32_t dlm_nl_seqnum; -static uint32_t listener_nlpid; +static uint32_t listener_nlportid; static struct genl_family family = { .id = GENL_ID_GENERATE, @@ -64,13 +64,13 @@ static int send_data(struct sk_buff *skb) return rv; } - return genlmsg_unicast(&init_net, skb, listener_nlpid); + return genlmsg_unicast(&init_net, skb, listener_nlportid); } static int user_cmd(struct sk_buff *skb, struct genl_info *info) { - listener_nlpid = info->snd_pid; - printk("user_cmd nlpid %u\n", listener_nlpid); + listener_nlportid = info->snd_portid; + printk("user_cmd nlpid %u\n", listener_nlportid); return 0; } diff --git a/include/linux/netlink.h b/include/linux/netlink.h index cd17dda5a987..73ade5fbc856 100644 --- a/include/linux/netlink.h +++ b/include/linux/netlink.h @@ -165,7 +165,7 @@ static inline struct nlmsghdr *nlmsg_hdr(const struct sk_buff *skb) struct netlink_skb_parms { struct scm_creds creds; /* Skb credentials */ - __u32 pid; + __u32 portid; __u32 dst_group; struct sock *ssk; }; @@ -205,14 +205,14 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group) extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group); extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err); extern int netlink_has_listeners(struct sock *sk, unsigned int group); -extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock); -extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid, +extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock); +extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid, __u32 group, gfp_t allocation); extern int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, - __u32 pid, __u32 group, gfp_t allocation, + __u32 portid, __u32 group, gfp_t allocation, int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), void *filter_data); -extern int netlink_set_err(struct sock *ssk, __u32 pid, __u32 group, int code); +extern int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code); extern int netlink_register_notifier(struct notifier_block *nb); extern int netlink_unregister_notifier(struct notifier_block *nb); @@ -253,12 +253,12 @@ struct netlink_callback { struct netlink_notify { struct net *net; - int pid; + int portid; int protocol; }; struct nlmsghdr * -__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags); +__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags); struct netlink_dump_control { int (*dump)(struct sk_buff *skb, struct netlink_callback *); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index ba2e6160fad1..7b3b0568d289 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2458,7 +2458,7 @@ struct wireless_dev { int beacon_interval; - u32 ap_unexpected_nlpid; + u32 ap_unexpected_nlportid; #ifdef CONFIG_CFG80211_WEXT /* wext data */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 48905cd3884c..bdfbe68c1c3b 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -65,7 +65,7 @@ struct genl_family { /** * struct genl_info - receiving information * @snd_seq: sending sequence number - * @snd_pid: netlink pid of sender + * @snd_portid: netlink portid of sender * @nlhdr: netlink message header * @genlhdr: generic netlink message header * @userhdr: user specific header @@ -75,7 +75,7 @@ struct genl_family { */ struct genl_info { u32 snd_seq; - u32 snd_pid; + u32 snd_portid; struct nlmsghdr * nlhdr; struct genlmsghdr * genlhdr; void * userhdr; @@ -130,10 +130,10 @@ extern int genl_register_mc_group(struct genl_family *family, struct genl_multicast_group *grp); extern void genl_unregister_mc_group(struct genl_family *family, struct genl_multicast_group *grp); -extern void genl_notify(struct sk_buff *skb, struct net *net, u32 pid, +extern void genl_notify(struct sk_buff *skb, struct net *net, u32 portid, u32 group, struct nlmsghdr *nlh, gfp_t flags); -void *genlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, +void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, struct genl_family *family, int flags, u8 cmd); /** @@ -183,7 +183,7 @@ static inline void *genlmsg_put_reply(struct sk_buff *skb, struct genl_family *family, int flags, u8 cmd) { - return genlmsg_put(skb, info->snd_pid, info->snd_seq, family, + return genlmsg_put(skb, info->snd_portid, info->snd_seq, family, flags, cmd); } @@ -212,49 +212,49 @@ static inline void genlmsg_cancel(struct sk_buff *skb, void *hdr) * genlmsg_multicast_netns - multicast a netlink message to a specific netns * @net: the net namespace * @skb: netlink message as socket buffer - * @pid: own netlink pid to avoid sending to yourself + * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ static inline int genlmsg_multicast_netns(struct net *net, struct sk_buff *skb, - u32 pid, unsigned int group, gfp_t flags) + u32 portid, unsigned int group, gfp_t flags) { - return nlmsg_multicast(net->genl_sock, skb, pid, group, flags); + return nlmsg_multicast(net->genl_sock, skb, portid, group, flags); } /** * genlmsg_multicast - multicast a netlink message to the default netns * @skb: netlink message as socket buffer - * @pid: own netlink pid to avoid sending to yourself + * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ -static inline int genlmsg_multicast(struct sk_buff *skb, u32 pid, +static inline int genlmsg_multicast(struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { - return genlmsg_multicast_netns(&init_net, skb, pid, group, flags); + return genlmsg_multicast_netns(&init_net, skb, portid, group, flags); } /** * genlmsg_multicast_allns - multicast a netlink message to all net namespaces * @skb: netlink message as socket buffer - * @pid: own netlink pid to avoid sending to yourself + * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags * * This function must hold the RTNL or rcu_read_lock(). */ -int genlmsg_multicast_allns(struct sk_buff *skb, u32 pid, +int genlmsg_multicast_allns(struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags); /** * genlmsg_unicast - unicast a netlink message * @skb: netlink message as socket buffer - * @pid: netlink pid of the destination socket + * @portid: netlink portid of the destination socket */ -static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 pid) +static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 portid) { - return nlmsg_unicast(net->genl_sock, skb, pid); + return nlmsg_unicast(net->genl_sock, skb, portid); } /** @@ -264,7 +264,7 @@ static inline int genlmsg_unicast(struct net *net, struct sk_buff *skb, u32 pid) */ static inline int genlmsg_reply(struct sk_buff *skb, struct genl_info *info) { - return genlmsg_unicast(genl_info_net(info), skb, info->snd_pid); + return genlmsg_unicast(genl_info_net(info), skb, info->snd_portid); } /** diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 4a045cda9c60..5654d292efd4 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -17,7 +17,7 @@ struct nf_conntrack_ecache { unsigned long missed; /* missed events */ u16 ctmask; /* bitmask of ct events to be delivered */ u16 expmask; /* bitmask of expect events to be delivered */ - u32 pid; /* netlink pid of destroyer */ + u32 portid; /* netlink portid of destroyer */ struct timer_list timeout; }; @@ -60,7 +60,7 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) /* This structure is passed to event handler */ struct nf_ct_event { struct nf_conn *ct; - u32 pid; + u32 portid; int report; }; @@ -92,7 +92,7 @@ nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) static inline int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, - u32 pid, + u32 portid, int report) { int ret = 0; @@ -112,11 +112,11 @@ nf_conntrack_eventmask_report(unsigned int eventmask, if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct)) { struct nf_ct_event item = { .ct = ct, - .pid = e->pid ? e->pid : pid, + .portid = e->portid ? e->portid : portid, .report = report }; /* This is a resent of a destroy event? If so, skip missed */ - unsigned long missed = e->pid ? 0 : e->missed; + unsigned long missed = e->portid ? 0 : e->missed; if (!((eventmask | missed) & e->ctmask)) goto out_unlock; @@ -126,11 +126,11 @@ nf_conntrack_eventmask_report(unsigned int eventmask, spin_lock_bh(&ct->lock); if (ret < 0) { /* This is a destroy event that has been - * triggered by a process, we store the PID + * triggered by a process, we store the PORTID * to include it in the retransmission. */ if (eventmask & (1 << IPCT_DESTROY) && - e->pid == 0 && pid != 0) - e->pid = pid; + e->portid == 0 && portid != 0) + e->portid = portid; else e->missed |= eventmask; } else @@ -145,9 +145,9 @@ out_unlock: static inline int nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct, - u32 pid, int report) + u32 portid, int report) { - return nf_conntrack_eventmask_report(1 << event, ct, pid, report); + return nf_conntrack_eventmask_report(1 << event, ct, portid, report); } static inline int @@ -158,7 +158,7 @@ nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) struct nf_exp_event { struct nf_conntrack_expect *exp; - u32 pid; + u32 portid; int report; }; @@ -172,7 +172,7 @@ extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_even static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events event, struct nf_conntrack_expect *exp, - u32 pid, + u32 portid, int report) { struct net *net = nf_ct_exp_net(exp); @@ -191,7 +191,7 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event, if (e->expmask & (1 << event)) { struct nf_exp_event item = { .exp = exp, - .pid = pid, + .portid = portid, .report = report }; notify->fcn(1 << event, &item); @@ -216,20 +216,20 @@ static inline void nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct) {} static inline int nf_conntrack_eventmask_report(unsigned int eventmask, struct nf_conn *ct, - u32 pid, + u32 portid, int report) { return 0; } static inline int nf_conntrack_event(enum ip_conntrack_events event, struct nf_conn *ct) { return 0; } static inline int nf_conntrack_event_report(enum ip_conntrack_events event, struct nf_conn *ct, - u32 pid, + u32 portid, int report) { return 0; } static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) {} static inline void nf_ct_expect_event(enum ip_conntrack_expect_events event, struct nf_conntrack_expect *exp) {} static inline void nf_ct_expect_event_report(enum ip_conntrack_expect_events e, struct nf_conntrack_expect *exp, - u32 pid, + u32 portid, int report) {} static inline int nf_conntrack_ecache_init(struct net *net) diff --git a/include/net/netlink.h b/include/net/netlink.h index 09175d5d1fbf..9690b0f6698a 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -217,19 +217,19 @@ struct nla_policy { /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request - * @pid: Netlink PID of requesting application + * @portid: Netlink PORTID of requesting application */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; - u32 pid; + u32 portid; }; extern int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *)); extern int nlmsg_notify(struct sock *sk, struct sk_buff *skb, - u32 pid, unsigned int group, int report, + u32 portid, unsigned int group, int report, gfp_t flags); extern int nla_validate(const struct nlattr *head, @@ -444,7 +444,7 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh) /** * nlmsg_put - Add a new netlink message to an skb * @skb: socket buffer to store message in - * @pid: netlink process id + * @portid: netlink process id * @seq: sequence number of message * @type: message type * @payload: length of message payload @@ -453,13 +453,13 @@ static inline int nlmsg_report(const struct nlmsghdr *nlh) * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ -static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, +static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int payload, int flags) { if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload))) return NULL; - return __nlmsg_put(skb, pid, seq, type, payload, flags); + return __nlmsg_put(skb, portid, seq, type, payload, flags); } /** @@ -478,7 +478,7 @@ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, int type, int payload, int flags) { - return nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + return nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, type, payload, flags); } @@ -563,18 +563,18 @@ static inline void nlmsg_free(struct sk_buff *skb) * nlmsg_multicast - multicast a netlink message * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer - * @pid: own netlink pid to avoid sending to yourself + * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, - u32 pid, unsigned int group, gfp_t flags) + u32 portid, unsigned int group, gfp_t flags) { int err; NETLINK_CB(skb).dst_group = group; - err = netlink_broadcast(sk, skb, pid, group, flags); + err = netlink_broadcast(sk, skb, portid, group, flags); if (err > 0) err = 0; @@ -585,13 +585,13 @@ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, * nlmsg_unicast - unicast a netlink message * @sk: netlink socket to spread message to * @skb: netlink message as socket buffer - * @pid: netlink pid of the destination socket + * @portid: netlink portid of the destination socket */ -static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 pid) +static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 portid) { int err; - err = netlink_unicast(sk, skb, pid, MSG_DONTWAIT); + err = netlink_unicast(sk, skb, portid, MSG_DONTWAIT); if (err > 0) err = 0; diff --git a/include/net/nfc/nfc.h b/include/net/nfc/nfc.h index 6431f5e39022..6735909f826d 100644 --- a/include/net/nfc/nfc.h +++ b/include/net/nfc/nfc.h @@ -89,7 +89,7 @@ struct nfc_target { }; struct nfc_genl_data { - u32 poll_req_pid; + u32 poll_req_portid; struct mutex genl_data_mutex; }; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 36ad56ba648b..ee8613f01860 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -263,7 +263,7 @@ struct km_event { } data; u32 seq; - u32 pid; + u32 portid; u32 event; struct net *net; }; @@ -310,7 +310,7 @@ extern void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); -extern void km_state_expired(struct xfrm_state *x, int hard, u32 pid); +extern void km_state_expired(struct xfrm_state *x, int hard, u32 portid); extern int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { @@ -1554,7 +1554,7 @@ extern int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, #endif extern int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); -extern void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid); +extern void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid); extern int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); extern void xfrm_input_init(void); diff --git a/kernel/audit.c b/kernel/audit.c index a24aafa850ae..e0cf64a0ae2d 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -87,11 +87,11 @@ static int audit_failure = AUDIT_FAIL_PRINTK; /* * If audit records are to be written to the netlink socket, audit_pid - * contains the pid of the auditd process and audit_nlk_pid contains - * the pid to use to send netlink messages to that process. + * contains the pid of the auditd process and audit_nlk_portid contains + * the portid to use to send netlink messages to that process. */ int audit_pid; -static int audit_nlk_pid; +static int audit_nlk_portid; /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in @@ -401,7 +401,7 @@ static void kauditd_send_skb(struct sk_buff *skb) int err; /* take a reference in case we can't send it and we want to hold it */ skb_get(skb); - err = netlink_unicast(audit_sock, skb, audit_nlk_pid, 0); + err = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0); if (err < 0) { BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */ printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid); @@ -692,7 +692,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) status_set.backlog_limit = audit_backlog_limit; status_set.lost = atomic_read(&audit_lost); status_set.backlog = skb_queue_len(&audit_skb_queue); - audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_GET, 0, 0, + audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, &status_set, sizeof(status_set)); break; case AUDIT_SET: @@ -720,7 +720,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sessionid, sid, 1); audit_pid = new_pid; - audit_nlk_pid = NETLINK_CB(skb).pid; + audit_nlk_portid = NETLINK_CB(skb).portid; } if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(status_get->rate_limit, @@ -782,7 +782,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* fallthrough */ case AUDIT_LIST: - err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid, + err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid, uid, seq, data, nlmsg_len(nlh), loginuid, sessionid, sid); break; @@ -801,7 +801,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* fallthrough */ case AUDIT_LIST_RULES: - err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid, + err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid, uid, seq, data, nlmsg_len(nlh), loginuid, sessionid, sid); break; @@ -872,7 +872,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } - audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO, + audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, sizeof(*sig_data) + len); kfree(sig_data); break; @@ -891,7 +891,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) rcu_read_unlock(); if (!err) - audit_send_reply(NETLINK_CB(skb).pid, seq, + audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } diff --git a/kernel/taskstats.c b/kernel/taskstats.c index d0a32796550f..123793cd06f9 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -467,7 +467,7 @@ static int cmd_attr_register_cpumask(struct genl_info *info) rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) goto out; - rc = add_del_listener(info->snd_pid, mask, REGISTER); + rc = add_del_listener(info->snd_portid, mask, REGISTER); out: free_cpumask_var(mask); return rc; @@ -483,7 +483,7 @@ static int cmd_attr_deregister_cpumask(struct genl_info *info) rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) goto out; - rc = add_del_listener(info->snd_pid, mask, DEREGISTER); + rc = add_del_listener(info->snd_portid, mask, DEREGISTER); out: free_cpumask_var(mask); return rc; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9ce430b4657c..ddf93efc133c 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -467,14 +467,14 @@ static int fdb_to_nud(const struct net_bridge_fdb_entry *fdb) static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, const struct net_bridge_fdb_entry *fdb, - u32 pid, u32 seq, int type, unsigned int flags) + u32 portid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -555,7 +555,7 @@ int br_fdb_dump(struct sk_buff *skb, goto skip; if (fdb_fill_info(skb, br, f, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) < 0) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index fe41260fbf38..093f527276a3 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -127,7 +127,7 @@ static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) goto skip; if (br_fill_ifinfo(skb, port, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI) < 0) break; diff --git a/net/can/gw.c b/net/can/gw.c index b54d5e695b03..127879c55fb6 100644 --- a/net/can/gw.c +++ b/net/can/gw.c @@ -549,7 +549,7 @@ static int cgw_dump_jobs(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; - if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).pid, + if (cgw_put_job(skb, gwj, RTM_NEWROUTE, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) break; cont: diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index ab7db83236c9..58a4ba27dfe3 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -402,7 +402,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (unresolved) ops->unresolved_rules++; - notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid); flush_route_cache(ops); rules_ops_put(ops); return 0; @@ -500,7 +500,7 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) } notify_rule_change(RTM_DELRULE, rule, ops, nlh, - NETLINK_CB(skb).pid); + NETLINK_CB(skb).portid); if (ops->delete) ops->delete(rule); fib_rule_put(rule); @@ -601,7 +601,7 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb, if (idx < cb->args[1]) goto skip; - if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWRULE, NLM_F_MULTI, ops) < 0) break; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 117afaf51268..c160adb38e5a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2102,7 +2102,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid, + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) break; @@ -2115,7 +2115,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) goto next; if (neightbl_fill_param_info(skb, tbl, p, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, NLM_F_MULTI) <= 0) @@ -2244,7 +2244,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (idx < s_idx) goto next; - if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) <= 0) { @@ -2281,7 +2281,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, continue; if (idx < s_idx) goto next; - if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).pid, + if (pneigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI, tbl) <= 0) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 508c5df4a09c..92575370d9f0 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1081,7 +1081,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) goto cont; if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, 0, NLM_F_MULTI, ext_filter_mask) <= 0) @@ -1899,14 +1899,14 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (nskb == NULL) return -ENOBUFS; - err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, + err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); } else - err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).portid); return err; } @@ -2180,9 +2180,9 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, { struct netdev_hw_addr *ha; int err; - u32 pid, seq; + u32 portid, seq; - pid = NETLINK_CB(cb->skb).pid; + portid = NETLINK_CB(cb->skb).portid; seq = cb->nlh->nlmsg_seq; list_for_each_entry(ha, &list->list, list) { @@ -2190,7 +2190,7 @@ static int nlmsg_populate_fdb(struct sk_buff *skb, goto skip; err = nlmsg_populate_fdb_fill(skb, dev, ha->addr, - pid, seq, 0, NTF_SELF); + portid, seq, 0, NTF_SELF); if (err < 0) return err; skip: diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 81f2bb62dea3..70989e672304 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1319,7 +1319,7 @@ nla_put_failure: } static int dcbnl_notify(struct net_device *dev, int event, int cmd, - u32 seq, u32 pid, int dcbx_ver) + u32 seq, u32 portid, int dcbx_ver) { struct net *net = dev_net(dev); struct sk_buff *skb; @@ -1330,7 +1330,7 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd, if (!ops) return -EOPNOTSUPP; - skb = dcbnl_newmsg(event, cmd, pid, seq, 0, &nlh); + skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh); if (!skb) return -ENOBUFS; @@ -1353,16 +1353,16 @@ static int dcbnl_notify(struct net_device *dev, int event, int cmd, } int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, - u32 seq, u32 pid) + u32 seq, u32 portid) { - return dcbnl_notify(dev, event, cmd, seq, pid, DCB_CAP_DCBX_VER_IEEE); + return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_IEEE); } EXPORT_SYMBOL(dcbnl_ieee_notify); int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, - u32 seq, u32 pid) + u32 seq, u32 portid) { - return dcbnl_notify(dev, event, cmd, seq, pid, DCB_CAP_DCBX_VER_CEE); + return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_CEE); } EXPORT_SYMBOL(dcbnl_cee_notify); @@ -1656,7 +1656,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct net_device *netdev; struct dcbmsg *dcb = nlmsg_data(nlh); struct nlattr *tb[DCB_ATTR_MAX + 1]; - u32 pid = skb ? NETLINK_CB(skb).pid : 0; + u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = -EINVAL; struct sk_buff *reply_skb; struct nlmsghdr *reply_nlh = NULL; @@ -1690,7 +1690,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto out; } - reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, pid, nlh->nlmsg_seq, + reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, nlh->nlmsg_flags, &reply_nlh); if (!reply_skb) { ret = -ENOBUFS; @@ -1705,7 +1705,7 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) nlmsg_end(reply_skb, reply_nlh); - ret = rtnl_unicast(reply_skb, &init_net, pid); + ret = rtnl_unicast(reply_skb, &init_net, portid); out: dev_put(netdev); return ret; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index f3924ab1e019..7b7e561412d3 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -667,12 +667,12 @@ static inline size_t dn_ifaddr_nlmsg_size(void) } static int dn_nl_fill_ifaddr(struct sk_buff *skb, struct dn_ifaddr *ifa, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -753,7 +753,7 @@ static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) if (dn_idx < skip_naddr) continue; - if (dn_nl_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, + if (dn_nl_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI) < 0) goto done; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index c855e8d0738f..b57419cc41a4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1543,7 +1543,7 @@ static int dn_route_input(struct sk_buff *skb) return dn_route_input_slow(skb); } -static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, +static int dn_rt_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, int nowait, unsigned int flags) { struct dn_route *rt = (struct dn_route *)skb_dst(skb); @@ -1551,7 +1551,7 @@ static int dn_rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, struct nlmsghdr *nlh; long expires; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; @@ -1685,7 +1685,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); + err = dn_rt_fill_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err == 0) goto out_free; @@ -1694,7 +1694,7 @@ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void goto out_free; } - return rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).pid); + return rtnl_unicast(skb, &init_net, NETLINK_CB(in_skb).portid); out_free: kfree_skb(skb); @@ -1737,7 +1737,7 @@ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) if (idx < s_idx) continue; skb_dst_set(skb, dst_clone(&rt->dst)); - if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (dn_rt_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1, NLM_F_MULTI) <= 0) { skb_dst_drop(skb); diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index 16c986ab1228..f968c1b58f47 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -291,14 +291,14 @@ static inline size_t dn_fib_nlmsg_size(struct dn_fib_info *fi) return payload; } -static int dn_fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, +static int dn_fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 tb_id, u8 type, u8 scope, void *dst, int dst_len, struct dn_fib_info *fi, unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; @@ -374,14 +374,14 @@ static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id, struct nlmsghdr *nlh, struct netlink_skb_parms *req) { struct sk_buff *skb; - u32 pid = req ? req->pid : 0; + u32 portid = req ? req->portid : 0; int err = -ENOBUFS; skb = nlmsg_new(dn_fib_nlmsg_size(DN_FIB_INFO(f)), GFP_KERNEL); if (skb == NULL) goto errout; - err = dn_fib_dump_info(skb, pid, nlh->nlmsg_seq, event, tb_id, + err = dn_fib_dump_info(skb, portid, nlh->nlmsg_seq, event, tb_id, f->fn_type, f->fn_scope, &f->fn_key, z, DN_FIB_INFO(f), 0); if (err < 0) { @@ -390,7 +390,7 @@ static void dn_rtmsg_fib(int event, struct dn_fib_node *f, int z, u32 tb_id, kfree_skb(skb); goto errout; } - rtnl_notify(skb, &init_net, pid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL); + rtnl_notify(skb, &init_net, portid, RTNLGRP_DECnet_ROUTE, nlh, GFP_KERNEL); return; errout: if (err < 0) @@ -411,7 +411,7 @@ static __inline__ int dn_hash_dump_bucket(struct sk_buff *skb, continue; if (f->fn_state & DN_S_ZOMBIE) continue; - if (dn_fib_dump_info(skb, NETLINK_CB(cb->skb).pid, + if (dn_fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, tb->n, diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c index 1e9917124e75..96bb08abece2 100644 --- a/net/ieee802154/nl-mac.c +++ b/net/ieee802154/nl-mac.c @@ -246,7 +246,7 @@ nla_put_failure: } EXPORT_SYMBOL(ieee802154_nl_start_confirm); -static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 pid, +static int ieee802154_nl_fill_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct net_device *dev) { void *hdr; @@ -534,7 +534,7 @@ static int ieee802154_list_iface(struct sk_buff *skb, if (!msg) goto out_dev; - rc = ieee802154_nl_fill_iface(msg, info->snd_pid, info->snd_seq, + rc = ieee802154_nl_fill_iface(msg, info->snd_portid, info->snd_seq, 0, dev); if (rc < 0) goto out_free; @@ -565,7 +565,7 @@ static int ieee802154_dump_iface(struct sk_buff *skb, if (idx < s_idx || (dev->type != ARPHRD_IEEE802154)) goto cont; - if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).pid, + if (ieee802154_nl_fill_iface(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) break; cont: diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index d54be34cca94..22b1a7058fd3 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -35,7 +35,7 @@ #include "ieee802154.h" -static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, +static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct wpan_phy *phy) { void *hdr; @@ -105,7 +105,7 @@ static int ieee802154_list_phy(struct sk_buff *skb, if (!msg) goto out_dev; - rc = ieee802154_nl_fill_phy(msg, info->snd_pid, info->snd_seq, + rc = ieee802154_nl_fill_phy(msg, info->snd_portid, info->snd_seq, 0, phy); if (rc < 0) goto out_free; @@ -138,7 +138,7 @@ static int ieee802154_dump_phy_iter(struct wpan_phy *phy, void *_data) return 0; rc = ieee802154_nl_fill_phy(data->skb, - NETLINK_CB(data->cb->skb).pid, + NETLINK_CB(data->cb->skb).portid, data->cb->nlh->nlmsg_seq, NLM_F_MULTI, phy); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f14eff506743..7b00556e184b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -311,7 +311,7 @@ int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) } static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, - int destroy, struct nlmsghdr *nlh, u32 pid) + int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; struct in_ifaddr *ifa, *ifa1 = *ifap; @@ -345,7 +345,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, inet_hash_remove(ifa); *ifap1 = ifa->ifa_next; - rtmsg_ifa(RTM_DELADDR, ifa, nlh, pid); + rtmsg_ifa(RTM_DELADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa); inet_free_ifa(ifa); @@ -382,7 +382,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, is valid, it will try to restore deleted routes... Grr. So that, this order is correct. */ - rtmsg_ifa(RTM_DELADDR, ifa1, nlh, pid); + rtmsg_ifa(RTM_DELADDR, ifa1, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1); if (promote) { @@ -395,7 +395,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, } promote->ifa_flags &= ~IFA_F_SECONDARY; - rtmsg_ifa(RTM_NEWADDR, promote, nlh, pid); + rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); for (ifa = next_sec; ifa; ifa = ifa->ifa_next) { @@ -417,7 +417,7 @@ static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, } static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, - u32 pid) + u32 portid) { struct in_device *in_dev = ifa->ifa_dev; struct in_ifaddr *ifa1, **ifap, **last_primary; @@ -464,7 +464,7 @@ static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, /* Send message first, then call notifier. Notifier will trigger FIB update, so that listeners of netlink will know about new ifaddr */ - rtmsg_ifa(RTM_NEWADDR, ifa, nlh, pid); + rtmsg_ifa(RTM_NEWADDR, ifa, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa); return 0; @@ -563,7 +563,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg !inet_ifa_match(nla_get_be32(tb[IFA_ADDRESS]), ifa))) continue; - __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).pid); + __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -649,7 +649,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg if (IS_ERR(ifa)) return PTR_ERR(ifa); - return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).pid); + return __inet_insert_ifa(ifa, nlh, NETLINK_CB(skb).portid); } /* @@ -1246,12 +1246,12 @@ static size_t inet_nlmsg_size(void) } static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); if (nlh == NULL) return -EMSGSIZE; @@ -1313,7 +1313,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) if (ip_idx < s_ip_idx) continue; if (inet_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI) <= 0) { rcu_read_unlock(); @@ -1335,7 +1335,7 @@ done: } static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, - u32 pid) + u32 portid) { struct sk_buff *skb; u32 seq = nlh ? nlh->nlmsg_seq : 0; @@ -1347,14 +1347,14 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, if (skb == NULL) goto errout; - err = inet_fill_ifaddr(skb, ifa, pid, seq, event, 0); + err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, pid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); + rtnl_notify(skb, net, portid, RTNLGRP_IPV4_IFADDR, nlh, GFP_KERNEL); return; errout: if (err < 0) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index dc1f10ed1872..68c93d1bb03a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -557,7 +557,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, cfg->fc_flags = rtm->rtm_flags; cfg->fc_nlflags = nlh->nlmsg_flags; - cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = net; @@ -955,7 +955,7 @@ static void nl_fib_input(struct sk_buff *skb) struct fib_result_nl *frn; struct nlmsghdr *nlh; struct fib_table *tb; - u32 pid; + u32 portid; net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); @@ -973,10 +973,10 @@ static void nl_fib_input(struct sk_buff *skb) nl_fib_lookup(frn, tb); - pid = NETLINK_CB(skb).pid; /* pid of sending process */ - NETLINK_CB(skb).pid = 0; /* from kernel */ + portid = NETLINK_CB(skb).portid; /* pid of sending process */ + NETLINK_CB(skb).portid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ - netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT); + netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT); } static int __net_init nl_fib_lookup_init(struct net *net) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index da80dc14cc76..3509065e409a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -391,7 +391,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, if (skb == NULL) goto errout; - err = fib_dump_info(skb, info->pid, seq, event, tb_id, + err = fib_dump_info(skb, info->portid, seq, event, tb_id, fa->fa_type, key, dst_len, fa->fa_tos, fa->fa_info, nlm_flags); if (err < 0) { @@ -400,7 +400,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, kfree_skb(skb); goto errout; } - rtnl_notify(skb, info->nl_net, info->pid, RTNLGRP_IPV4_ROUTE, + rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE, info->nlh, GFP_KERNEL); return; errout: @@ -989,14 +989,14 @@ failure: return ERR_PTR(err); } -int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, +int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, unsigned int flags) { struct nlmsghdr *nlh; struct rtmsg *rtm; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags); if (nlh == NULL) return -EMSGSIZE; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 8d766106b540..31d771ca9a70 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1873,7 +1873,7 @@ static int fn_trie_dump_fa(t_key key, int plen, struct list_head *fah, continue; } - if (fib_dump_info(skb, NETLINK_CB(cb->skb).pid, + if (fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE, tb->tb_id, diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 8bc005b1435f..535584c00f91 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -70,7 +70,7 @@ static inline void inet_diag_unlock_handler( int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, - u32 pid, u32 seq, u16 nlmsg_flags, + u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { const struct inet_sock *inet = inet_sk(sk); @@ -84,7 +84,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, handler = inet_diag_table[req->sdiag_protocol]; BUG_ON(handler == NULL); - nlh = nlmsg_put(skb, pid, seq, unlh->nlmsg_type, sizeof(*r), + nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; @@ -201,23 +201,23 @@ EXPORT_SYMBOL_GPL(inet_sk_diag_fill); static int inet_csk_diag_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_req_v2 *req, struct user_namespace *user_ns, - u32 pid, u32 seq, u16 nlmsg_flags, + u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { return inet_sk_diag_fill(sk, inet_csk(sk), - skb, req, user_ns, pid, seq, nlmsg_flags, unlh); + skb, req, user_ns, portid, seq, nlmsg_flags, unlh); } static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, struct sk_buff *skb, struct inet_diag_req_v2 *req, - u32 pid, u32 seq, u16 nlmsg_flags, + u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { long tmo; struct inet_diag_msg *r; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, pid, seq, unlh->nlmsg_type, sizeof(*r), + nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), nlmsg_flags); if (!nlh) return -EMSGSIZE; @@ -260,14 +260,14 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct inet_diag_req_v2 *r, struct user_namespace *user_ns, - u32 pid, u32 seq, u16 nlmsg_flags, + u32 portid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill((struct inet_timewait_sock *)sk, - skb, r, pid, seq, nlmsg_flags, + skb, r, portid, seq, nlmsg_flags, unlh); - return inet_csk_diag_fill(sk, skb, r, user_ns, pid, seq, nlmsg_flags, unlh); + return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh); } int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, @@ -316,14 +316,14 @@ int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_s err = sk_diag_fill(sk, rep, req, sk_user_ns(NETLINK_CB(in_skb).ssk), - NETLINK_CB(in_skb).pid, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { WARN_ON(err == -EMSGSIZE); nlmsg_free(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -557,7 +557,7 @@ static int inet_csk_diag_dump(struct sock *sk, return inet_csk_diag_fill(sk, skb, r, sk_user_ns(NETLINK_CB(cb->skb).ssk), - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } @@ -592,14 +592,14 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, } return inet_twsk_diag_fill(tw, skb, r, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, struct request_sock *req, struct user_namespace *user_ns, - u32 pid, u32 seq, + u32 portid, u32 seq, const struct nlmsghdr *unlh) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -608,7 +608,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, struct nlmsghdr *nlh; long tmo; - nlh = nlmsg_put(skb, pid, seq, unlh->nlmsg_type, sizeof(*r), + nlh = nlmsg_put(skb, portid, seq, unlh->nlmsg_type, sizeof(*r), NLM_F_MULTI); if (!nlh) return -EMSGSIZE; @@ -711,7 +711,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, err = inet_diag_fill_req(skb, sk, req, sk_user_ns(NETLINK_CB(cb->skb).ssk), - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh); if (err < 0) { cb->args[3] = j + 1; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 8aa7a4cf9139..1daa95c2a0ba 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -626,7 +626,7 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) e->error = -ETIMEDOUT; memset(&e->msg, 0, sizeof(e->msg)); - rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { kfree_skb(skb); } @@ -870,7 +870,7 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, memset(&e->msg, 0, sizeof(e->msg)); } - rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else { ip_mr_forward(net, mrt, skb, c, 0); } @@ -2117,12 +2117,12 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, } static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, - u32 pid, u32 seq, struct mfc_cache *c) + u32 portid, u32 seq, struct mfc_cache *c) { struct nlmsghdr *nlh; struct rtmsg *rtm; - nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; @@ -2176,7 +2176,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (e < s_e) goto next_entry; if (ipmr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc) < 0) goto done; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d39edf16d607..940f4f4cb201 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2136,7 +2136,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, EXPORT_SYMBOL_GPL(ip_route_output_flow); static int rt_fill_info(struct net *net, __be32 dst, __be32 src, - struct flowi4 *fl4, struct sk_buff *skb, u32 pid, + struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, int event, int nowait, unsigned int flags) { struct rtable *rt = skb_rtable(skb); @@ -2146,7 +2146,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 error; u32 metrics[RTAX_MAX]; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags); if (nlh == NULL) return -EMSGSIZE; @@ -2306,12 +2306,12 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void rt->rt_flags |= RTCF_NOTIFY; err = rt_fill_info(net, dst, src, &fl4, skb, - NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err <= 0) goto errout_free; - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 988edb63ee73..4c752a6e0bcd 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -803,7 +803,7 @@ static int tcp_metrics_dump_info(struct sk_buff *skb, { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &tcp_metrics_nl_family, NLM_F_MULTI, TCP_METRICS_CMD_GET); if (!hdr) diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index d2f336ea82ca..505b30ad9182 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -26,7 +26,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, return inet_sk_diag_fill(sk, NULL, skb, req, sk_user_ns(NETLINK_CB(cb->skb).ssk), - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } @@ -72,14 +72,14 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, err = inet_sk_diag_fill(sk, NULL, rep, req, sk_user_ns(NETLINK_CB(in_skb).ssk), - NETLINK_CB(in_skb).pid, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { WARN_ON(err == -EMSGSIZE); kfree_skb(rep); goto out; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); if (err > 0) err = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 572cb660837b..1237d5d037d8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3534,12 +3534,12 @@ static inline int inet6_ifaddr_msgsize(void) } static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); if (nlh == NULL) return -EMSGSIZE; @@ -3577,7 +3577,7 @@ static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 pid, u32 seq, int event, u16 flags) + u32 portid, u32 seq, int event, u16 flags) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -3586,7 +3586,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); if (nlh == NULL) return -EMSGSIZE; @@ -3602,7 +3602,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -3611,7 +3611,7 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); if (nlh == NULL) return -EMSGSIZE; @@ -3652,7 +3652,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, if (++ip_idx < s_ip_idx) continue; err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR, NLM_F_MULTI); @@ -3668,7 +3668,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_GETMULTICAST, NLM_F_MULTI); @@ -3683,7 +3683,7 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_GETANYCAST, NLM_F_MULTI); @@ -3805,7 +3805,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_ifa; } - err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).pid, + err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWADDR, 0); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ @@ -3813,7 +3813,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, kfree_skb(skb); goto errout_ifa; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: @@ -4015,14 +4015,14 @@ static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev) } static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, - u32 pid, u32 seq, int event, unsigned int flags) + u32 portid, u32 seq, int event, unsigned int flags) { struct net_device *dev = idev->dev; struct ifinfomsg *hdr; struct nlmsghdr *nlh; void *protoinfo; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; @@ -4080,7 +4080,7 @@ static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (!idev) goto cont; if (inet6_fill_ifinfo(skb, idev, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI) <= 0) goto out; @@ -4128,14 +4128,14 @@ static inline size_t inet6_prefix_nlmsg_size(void) } static int inet6_fill_prefix(struct sk_buff *skb, struct inet6_dev *idev, - struct prefix_info *pinfo, u32 pid, u32 seq, + struct prefix_info *pinfo, u32 portid, u32 seq, int event, unsigned int flags) { struct prefixmsg *pmsg; struct nlmsghdr *nlh; struct prefix_cacheinfo ci; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*pmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*pmsg), flags); if (nlh == NULL) return -EMSGSIZE; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index eb6a63632d3c..0b0171570d17 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -470,10 +470,10 @@ static void ip6addrlbl_putmsg(struct nlmsghdr *nlh, static int ip6addrlbl_fill(struct sk_buff *skb, struct ip6addrlbl_entry *p, u32 lseq, - u32 pid, u32 seq, int event, + u32 portid, u32 seq, int event, unsigned int flags) { - struct nlmsghdr *nlh = nlmsg_put(skb, pid, seq, event, + struct nlmsghdr *nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrlblmsg), flags); if (!nlh) return -EMSGSIZE; @@ -503,7 +503,7 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) net_eq(ip6addrlbl_net(p), net)) { if ((err = ip6addrlbl_fill(skb, p, ip6addrlbl_table.seq, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDRLABEL, NLM_F_MULTI)) <= 0) @@ -574,7 +574,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, } err = ip6addrlbl_fill(skb, p, lseq, - NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWADDRLABEL, 0); ip6addrlbl_put(p); @@ -585,7 +585,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, goto out; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); out: return err; } diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 4532973f0dd4..08ea3f0b6e55 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -838,7 +838,7 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c) nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT; - rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else kfree_skb(skb); } @@ -1052,7 +1052,7 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt, skb_trim(skb, nlh->nlmsg_len); ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; } - rtnl_unicast(skb, net, NETLINK_CB(skb).pid); + rtnl_unicast(skb, net, NETLINK_CB(skb).portid); } else ip6_mr_forward(net, mrt, skb, c); } @@ -2202,12 +2202,12 @@ int ip6mr_get_route(struct net *net, } static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, - u32 pid, u32 seq, struct mfc6_cache *c) + u32 portid, u32 seq, struct mfc6_cache *c) { struct nlmsghdr *nlh; struct rtmsg *rtm; - nlh = nlmsg_put(skb, pid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); + nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*rtm), NLM_F_MULTI); if (nlh == NULL) return -EMSGSIZE; @@ -2260,7 +2260,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) if (e < s_e) goto next_entry; if (ip6mr_fill_mroute(mrt, skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc) < 0) goto done; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 339d921cf3b6..a81c6790a648 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1874,7 +1874,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), - .fc_nlinfo.pid = 0, + .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; @@ -1924,7 +1924,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), - .fc_nlinfo.pid = 0, + .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = dev_net(dev), }; @@ -2285,7 +2285,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; - cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = sock_net(skb->sk); @@ -2376,7 +2376,7 @@ static inline size_t rt6_nlmsg_size(void) static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, - int iif, int type, u32 pid, u32 seq, + int iif, int type, u32 portid, u32 seq, int prefix, int nowait, unsigned int flags) { struct rtmsg *rtm; @@ -2392,7 +2392,7 @@ static int rt6_fill_node(struct net *net, } } - nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags); + nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; @@ -2537,7 +2537,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) return rt6_fill_node(arg->net, arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, - NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, + NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, prefix, 0, NLM_F_MULTI); } @@ -2617,14 +2617,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void skb_dst_set(skb, &rt->dst); err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).pid, + RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { kfree_skb(skb); goto errout; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid); + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } @@ -2644,14 +2644,14 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->pid, seq, 0, 0, 0); + event, info->portid, seq, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } - rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE, + rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c index 6c7c4b92e4f8..c32971269280 100644 --- a/net/irda/irnetlink.c +++ b/net/irda/irnetlink.c @@ -100,7 +100,7 @@ static int irda_nl_get_mode(struct sk_buff *skb, struct genl_info *info) goto err_out; } - hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq, + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &irda_nl_family, 0, IRDA_NL_CMD_GET_MODE); if (hdr == NULL) { ret = -EMSGSIZE; diff --git a/net/key/af_key.c b/net/key/af_key.c index 334f93b8cfcb..2ca7d7f6861c 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -54,7 +54,7 @@ struct pfkey_sock { struct { uint8_t msg_version; - uint32_t msg_pid; + uint32_t msg_portid; int (*dump)(struct pfkey_sock *sk); void (*done)(struct pfkey_sock *sk); union { @@ -1447,7 +1447,7 @@ static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) hdr->sadb_msg_errno = 0; hdr->sadb_msg_reserved = 0; hdr->sadb_msg_seq = c->seq; - hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_pid = c->portid; pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xs_net(x)); @@ -1486,7 +1486,7 @@ static int pfkey_add(struct sock *sk, struct sk_buff *skb, const struct sadb_msg else c.event = XFRM_MSG_UPDSA; c.seq = hdr->sadb_msg_seq; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; km_state_notify(x, &c); out: xfrm_state_put(x); @@ -1523,7 +1523,7 @@ static int pfkey_delete(struct sock *sk, struct sk_buff *skb, const struct sadb_ goto out; c.seq = hdr->sadb_msg_seq; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_DELSA; km_state_notify(x, &c); out: @@ -1701,7 +1701,7 @@ static int key_notify_sa_flush(const struct km_event *c) hdr->sadb_msg_satype = pfkey_proto2satype(c->data.proto); hdr->sadb_msg_type = SADB_FLUSH; hdr->sadb_msg_seq = c->seq; - hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); @@ -1736,7 +1736,7 @@ static int pfkey_flush(struct sock *sk, struct sk_buff *skb, const struct sadb_m c.data.proto = proto; c.seq = hdr->sadb_msg_seq; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; c.event = XFRM_MSG_FLUSHSA; c.net = net; km_state_notify(NULL, &c); @@ -1764,7 +1764,7 @@ static int dump_sa(struct xfrm_state *x, int count, void *ptr) out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_reserved = 0; out_hdr->sadb_msg_seq = count + 1; - out_hdr->sadb_msg_pid = pfk->dump.msg_pid; + out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, @@ -1798,7 +1798,7 @@ static int pfkey_dump(struct sock *sk, struct sk_buff *skb, const struct sadb_ms return -EINVAL; pfk->dump.msg_version = hdr->sadb_msg_version; - pfk->dump.msg_pid = hdr->sadb_msg_pid; + pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sa; pfk->dump.done = pfkey_dump_sa_done; xfrm_state_walk_init(&pfk->dump.u.state, proto); @@ -2157,7 +2157,7 @@ static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_ev out_hdr->sadb_msg_type = event2poltype(c->event); out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = c->seq; - out_hdr->sadb_msg_pid = c->pid; + out_hdr->sadb_msg_pid = c->portid; pfkey_broadcast(out_skb, GFP_ATOMIC, BROADCAST_ALL, NULL, xp_net(xp)); return 0; @@ -2272,7 +2272,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ c.event = XFRM_MSG_NEWPOLICY; c.seq = hdr->sadb_msg_seq; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); xfrm_pol_put(xp); @@ -2351,7 +2351,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa goto out; c.seq = hdr->sadb_msg_seq; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; c.data.byid = 0; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, pol->sadb_x_policy_dir-1, &c); @@ -2597,7 +2597,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ if (err) goto out; c.seq = hdr->sadb_msg_seq; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; c.data.byid = 1; c.event = XFRM_MSG_DELPOLICY; km_policy_notify(xp, dir, &c); @@ -2634,7 +2634,7 @@ static int dump_sp(struct xfrm_policy *xp, int dir, int count, void *ptr) out_hdr->sadb_msg_satype = SADB_SATYPE_UNSPEC; out_hdr->sadb_msg_errno = 0; out_hdr->sadb_msg_seq = count + 1; - out_hdr->sadb_msg_pid = pfk->dump.msg_pid; + out_hdr->sadb_msg_pid = pfk->dump.msg_portid; if (pfk->dump.skb) pfkey_broadcast(pfk->dump.skb, GFP_ATOMIC, BROADCAST_ONE, @@ -2663,7 +2663,7 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, const struct sadb return -EBUSY; pfk->dump.msg_version = hdr->sadb_msg_version; - pfk->dump.msg_pid = hdr->sadb_msg_pid; + pfk->dump.msg_portid = hdr->sadb_msg_pid; pfk->dump.dump = pfkey_dump_sp; pfk->dump.done = pfkey_dump_sp_done; xfrm_policy_walk_init(&pfk->dump.u.policy, XFRM_POLICY_TYPE_MAIN); @@ -2682,7 +2682,7 @@ static int key_notify_policy_flush(const struct km_event *c) hdr = (struct sadb_msg *) skb_put(skb_out, sizeof(struct sadb_msg)); hdr->sadb_msg_type = SADB_X_SPDFLUSH; hdr->sadb_msg_seq = c->seq; - hdr->sadb_msg_pid = c->pid; + hdr->sadb_msg_pid = c->portid; hdr->sadb_msg_version = PF_KEY_V2; hdr->sadb_msg_errno = (uint8_t) 0; hdr->sadb_msg_len = (sizeof(struct sadb_msg) / sizeof(uint64_t)); @@ -2711,7 +2711,7 @@ static int pfkey_spdflush(struct sock *sk, struct sk_buff *skb, const struct sad c.data.type = XFRM_POLICY_TYPE_MAIN; c.event = XFRM_MSG_FLUSHPOLICY; - c.pid = hdr->sadb_msg_pid; + c.portid = hdr->sadb_msg_pid; c.seq = hdr->sadb_msg_seq; c.net = net; km_policy_notify(NULL, 0, &c); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index d71cd9229a47..6ec3f67ad3f1 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -78,7 +78,7 @@ static int l2tp_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) goto out; } - hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq, + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &l2tp_nl_family, 0, L2TP_CMD_NOOP); if (IS_ERR(hdr)) { ret = PTR_ERR(hdr); @@ -87,7 +87,7 @@ static int l2tp_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info) genlmsg_end(msg, hdr); - return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid); + return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); err_out: nlmsg_free(msg); @@ -235,7 +235,7 @@ out: return ret; } -static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags, +static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int flags, struct l2tp_tunnel *tunnel) { void *hdr; @@ -248,7 +248,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 pid, u32 seq, int flags, struct l2tp_stats stats; unsigned int start; - hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags, + hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, L2TP_CMD_TUNNEL_GET); if (IS_ERR(hdr)) return PTR_ERR(hdr); @@ -359,12 +359,12 @@ static int l2tp_nl_cmd_tunnel_get(struct sk_buff *skb, struct genl_info *info) goto out; } - ret = l2tp_nl_tunnel_send(msg, info->snd_pid, info->snd_seq, + ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel); if (ret < 0) goto err_out; - return genlmsg_unicast(net, msg, info->snd_pid); + return genlmsg_unicast(net, msg, info->snd_portid); err_out: nlmsg_free(msg); @@ -384,7 +384,7 @@ static int l2tp_nl_cmd_tunnel_dump(struct sk_buff *skb, struct netlink_callback if (tunnel == NULL) goto out; - if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).pid, + if (l2tp_nl_tunnel_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, tunnel) <= 0) goto out; @@ -604,7 +604,7 @@ out: return ret; } -static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags, +static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int flags, struct l2tp_session *session) { void *hdr; @@ -616,7 +616,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 pid, u32 seq, int flags sk = tunnel->sock; - hdr = genlmsg_put(skb, pid, seq, &l2tp_nl_family, flags, L2TP_CMD_SESSION_GET); + hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, L2TP_CMD_SESSION_GET); if (IS_ERR(hdr)) return PTR_ERR(hdr); @@ -705,12 +705,12 @@ static int l2tp_nl_cmd_session_get(struct sk_buff *skb, struct genl_info *info) goto out; } - ret = l2tp_nl_session_send(msg, info->snd_pid, info->snd_seq, + ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, 0, session); if (ret < 0) goto err_out; - return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid); + return genlmsg_unicast(genl_info_net(info), msg, info->snd_portid); err_out: nlmsg_free(msg); @@ -742,7 +742,7 @@ static int l2tp_nl_cmd_session_dump(struct sk_buff *skb, struct netlink_callback continue; } - if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).pid, + if (l2tp_nl_session_send(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, session) <= 0) break; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 9730882697aa..ad39ef406851 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -563,13 +563,13 @@ flag_exist(const struct nlmsghdr *nlh) } static struct nlmsghdr * -start_msg(struct sk_buff *skb, u32 pid, u32 seq, unsigned int flags, +start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags, enum ipset_cmd cmd) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - nlh = nlmsg_put(skb, pid, seq, cmd | (NFNL_SUBSYS_IPSET << 8), + nlh = nlmsg_put(skb, portid, seq, cmd | (NFNL_SUBSYS_IPSET << 8), sizeof(*nfmsg), flags); if (nlh == NULL) return NULL; @@ -1045,7 +1045,7 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) ip_set_id_t index = IPSET_INVALID_ID, max; struct ip_set *set = NULL; struct nlmsghdr *nlh = NULL; - unsigned int flags = NETLINK_CB(cb->skb).pid ? NLM_F_MULTI : 0; + unsigned int flags = NETLINK_CB(cb->skb).portid ? NLM_F_MULTI : 0; u32 dump_type, dump_flags; int ret = 0; @@ -1093,7 +1093,7 @@ dump_last: pr_debug("reference set\n"); __ip_set_get(index); } - nlh = start_msg(skb, NETLINK_CB(cb->skb).pid, + nlh = start_msg(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, IPSET_CMD_LIST); if (!nlh) { @@ -1226,7 +1226,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, skb2 = nlmsg_new(payload, GFP_KERNEL); if (skb2 == NULL) return -ENOMEM; - rep = __nlmsg_put(skb2, NETLINK_CB(skb).pid, + rep = __nlmsg_put(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = ret; @@ -1241,7 +1241,7 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, *errline = lineno; - netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); /* Signal netlink not to send its ACK/errmsg. */ return -EINTR; } @@ -1416,7 +1416,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, IPSET_CMD_HEADER); if (!nlh2) goto nlmsg_failure; @@ -1428,7 +1428,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret < 0) return ret; @@ -1476,7 +1476,7 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, IPSET_CMD_TYPE); if (!nlh2) goto nlmsg_failure; @@ -1489,7 +1489,7 @@ ip_set_type(struct sock *ctnl, struct sk_buff *skb, nlmsg_end(skb2, nlh2); pr_debug("Send TYPE, nlmsg_len: %u\n", nlh2->nlmsg_len); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret < 0) return ret; @@ -1525,7 +1525,7 @@ ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - nlh2 = start_msg(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, + nlh2 = start_msg(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, IPSET_CMD_PROTOCOL); if (!nlh2) goto nlmsg_failure; @@ -1533,7 +1533,7 @@ ip_set_protocol(struct sock *ctnl, struct sk_buff *skb, goto nla_put_failure; nlmsg_end(skb2, nlh2); - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret < 0) return ret; diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 767cc12da0fe..0f924bf19c2b 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -2939,7 +2939,7 @@ static int ip_vs_genl_dump_service(struct sk_buff *skb, { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_SERVICE); if (!hdr) @@ -3128,7 +3128,7 @@ static int ip_vs_genl_dump_dest(struct sk_buff *skb, struct ip_vs_dest *dest, { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_DEST); if (!hdr) @@ -3257,7 +3257,7 @@ static int ip_vs_genl_dump_daemon(struct sk_buff *skb, __be32 state, struct netlink_callback *cb) { void *hdr; - hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &ip_vs_genl_family, NLM_F_MULTI, IPVS_CMD_NEW_DAEMON); if (!hdr) diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index e7be79e640de..de9781b6464f 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -61,7 +61,7 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct) goto out_unlock; item.ct = ct; - item.pid = 0; + item.portid = 0; item.report = 0; ret = notify->fcn(events | missed, &item); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index a205bd6ce294..59770039b825 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -418,16 +418,16 @@ nla_put_failure: } static int -ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +ctnetlink_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct nf_conn *ct) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct nlattr *nest_parms; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_NEW); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -604,7 +604,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) goto errout; type |= NFNL_SUBSYS_CTNETLINK << 8; - nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -680,7 +680,7 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - err = nfnetlink_send(skb, net, item->pid, group, item->report, + err = nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); if (err == -ENOBUFS || err == -EAGAIN) return -ENOBUFS; @@ -757,7 +757,7 @@ restart: #endif rcu_read_lock(); res = - ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid, + ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), ct); @@ -961,7 +961,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, else { /* Flush the whole table */ nf_conntrack_flush_report(net, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); return 0; } @@ -985,7 +985,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb, if (del_timer(&ct->timeout)) { if (nf_conntrack_event_report(IPCT_DESTROY, ct, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)) < 0) { nf_ct_delete_from_lists(ct); /* we failed to report the event, try later */ @@ -1069,14 +1069,14 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, } rcu_read_lock(); - err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, + err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), ct); rcu_read_unlock(); nf_ct_put(ct); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; @@ -1616,7 +1616,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | (1 << IPCT_MARK) | events, - ct, NETLINK_CB(skb).pid, + ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_put(ct); } @@ -1638,7 +1638,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, (1 << IPCT_PROTOINFO) | (1 << IPCT_NATSEQADJ) | (1 << IPCT_MARK), - ct, NETLINK_CB(skb).pid, + ct, NETLINK_CB(skb).portid, nlmsg_report(nlh)); } } @@ -1648,15 +1648,15 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 pid, u32 seq, +ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq, __u16 cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS_CPU); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -1708,7 +1708,7 @@ ctnetlink_ct_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) st = per_cpu_ptr(net->ct.stat, cpu); if (ctnetlink_ct_stat_cpu_fill_info(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; @@ -1734,16 +1734,16 @@ ctnetlink_stat_ct_cpu(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, struct net *net) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; unsigned int nr_conntracks = atomic_read(&net->ct.count); event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_CT_GET_STATS); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -1776,14 +1776,14 @@ ctnetlink_stat_ct(struct sock *ctnl, struct sk_buff *skb, if (skb2 == NULL) return -ENOMEM; - err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).pid, + err = ctnetlink_stat_ct_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), sock_net(skb->sk)); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; @@ -2073,15 +2073,15 @@ nla_put_failure: } static int -ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq, +ctnetlink_exp_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int event, const struct nf_conntrack_expect *exp) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; event |= NFNL_SUBSYS_CTNETLINK_EXP << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -2132,7 +2132,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) goto errout; type |= NFNL_SUBSYS_CTNETLINK_EXP << 8; - nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, item->portid, 0, type, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -2147,7 +2147,7 @@ ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item) rcu_read_unlock(); nlmsg_end(skb, nlh); - nfnetlink_send(skb, net, item->pid, group, item->report, GFP_ATOMIC); + nfnetlink_send(skb, net, item->portid, group, item->report, GFP_ATOMIC); return 0; nla_put_failure: @@ -2190,7 +2190,7 @@ restart: cb->args[1] = 0; } if (ctnetlink_exp_fill_info(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp) < 0) { @@ -2283,14 +2283,14 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, } rcu_read_lock(); - err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, + err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); nf_ct_expect_put(exp); if (err <= 0) goto free; - err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (err < 0) goto out; @@ -2344,7 +2344,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, /* after list removal, usage count == 1 */ spin_lock_bh(&nf_conntrack_lock); if (del_timer(&exp->timeout)) { - nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).pid, + nf_ct_unlink_expect_report(exp, NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } @@ -2366,7 +2366,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, if (!strcmp(m_help->helper->name, name) && del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } @@ -2382,7 +2382,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb, hnode) { if (del_timer(&exp->timeout)) { nf_ct_unlink_expect_report(exp, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); nf_ct_expect_put(exp); } @@ -2447,7 +2447,7 @@ static int ctnetlink_create_expect(struct net *net, u16 zone, const struct nlattr * const cda[], u_int8_t u3, - u32 pid, int report) + u32 portid, int report) { struct nf_conntrack_tuple tuple, mask, master_tuple; struct nf_conntrack_tuple_hash *h = NULL; @@ -2560,7 +2560,7 @@ ctnetlink_create_expect(struct net *net, u16 zone, if (err < 0) goto err_out; } - err = nf_ct_expect_related_report(exp, pid, report); + err = nf_ct_expect_related_report(exp, portid, report); err_out: nf_ct_expect_put(exp); out: @@ -2603,7 +2603,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_CREATE) { err = ctnetlink_create_expect(net, zone, cda, u3, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, nlmsg_report(nlh)); } return err; @@ -2618,15 +2618,15 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb, } static int -ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int cpu, +ctnetlink_exp_stat_fill_info(struct sk_buff *skb, u32 portid, u32 seq, int cpu, const struct ip_conntrack_stat *st) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0, event; + unsigned int flags = portid ? NLM_F_MULTI : 0, event; event = (NFNL_SUBSYS_CTNETLINK << 8 | IPCTNL_MSG_EXP_GET_STATS_CPU); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -2665,7 +2665,7 @@ ctnetlink_exp_stat_cpu_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; st = per_cpu_ptr(net->ct.stat, cpu); - if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (ctnetlink_exp_stat_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cpu, st) < 0) break; diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index d7ec92879071..589d686f0b4c 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -91,16 +91,16 @@ nfnl_acct_new(struct sock *nfnl, struct sk_buff *skb, } static int -nfnl_acct_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +nfnl_acct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_acct *acct) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; u64 pkts, bytes; event |= NFNL_SUBSYS_ACCT << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -150,7 +150,7 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb) if (last && cur != last) continue; - if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (nfnl_acct_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), NFNL_MSG_ACCT_NEW, cur) < 0) { @@ -195,7 +195,7 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, break; } - ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).pid, + ret = nfnl_acct_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), NFNL_MSG_ACCT_NEW, cur); @@ -203,7 +203,7 @@ nfnl_acct_get(struct sock *nfnl, struct sk_buff *skb, kfree_skb(skb2); break; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid, + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 32a1ba3f3e27..3678073360a3 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -395,16 +395,16 @@ nla_put_failure: } static int -nfnl_cthelper_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +nfnl_cthelper_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct nf_conntrack_helper *helper) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; int status; event |= NFNL_SUBSYS_CTHELPER << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -468,7 +468,7 @@ restart: cb->args[1] = 0; } if (nfnl_cthelper_fill_info(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), NFNL_MSG_CTHELPER_NEW, cur) < 0) { @@ -538,7 +538,7 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, break; } - ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).pid, + ret = nfnl_cthelper_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), NFNL_MSG_CTHELPER_NEW, cur); @@ -547,7 +547,7 @@ nfnl_cthelper_get(struct sock *nfnl, struct sk_buff *skb, break; } - ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).pid, + ret = netlink_unicast(nfnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index cdecbc8fe965..8847b4d8be06 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -155,16 +155,16 @@ err_proto_put: } static int -ctnl_timeout_fill_info(struct sk_buff *skb, u32 pid, u32 seq, u32 type, +ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, int event, struct ctnl_timeout *timeout) { struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; - unsigned int flags = pid ? NLM_F_MULTI : 0; + unsigned int flags = portid ? NLM_F_MULTI : 0; struct nf_conntrack_l4proto *l4proto = timeout->l4proto; event |= NFNL_SUBSYS_CTNETLINK_TIMEOUT << 8; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags); if (nlh == NULL) goto nlmsg_failure; @@ -222,7 +222,7 @@ ctnl_timeout_dump(struct sk_buff *skb, struct netlink_callback *cb) if (last && cur != last) continue; - if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).pid, + if (ctnl_timeout_fill_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NFNL_MSG_TYPE(cb->nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur) < 0) { @@ -268,7 +268,7 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, break; } - ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).pid, + ret = ctnl_timeout_fill_info(skb2, NETLINK_CB(skb).portid, nlh->nlmsg_seq, NFNL_MSG_TYPE(nlh->nlmsg_type), IPCTNL_MSG_TIMEOUT_NEW, cur); @@ -276,7 +276,7 @@ cttimeout_get_timeout(struct sock *ctnl, struct sk_buff *skb, kfree_skb(skb2); break; } - ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, + ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).portid, MSG_DONTWAIT); if (ret > 0) ret = 0; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index be194b144297..8cb67c4dbd62 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -56,7 +56,7 @@ struct nfulnl_instance { struct sk_buff *skb; /* pre-allocatd skb */ struct timer_list timer; struct user_namespace *peer_user_ns; /* User namespace of the peer process */ - int peer_pid; /* PID of the peer process */ + int peer_portid; /* PORTID of the peer process */ /* configurable parameters */ unsigned int flushtimeout; /* timeout until queue flush */ @@ -133,7 +133,7 @@ instance_put(struct nfulnl_instance *inst) static void nfulnl_timer(unsigned long data); static struct nfulnl_instance * -instance_create(u_int16_t group_num, int pid, struct user_namespace *user_ns) +instance_create(u_int16_t group_num, int portid, struct user_namespace *user_ns) { struct nfulnl_instance *inst; int err; @@ -164,7 +164,7 @@ instance_create(u_int16_t group_num, int pid, struct user_namespace *user_ns) setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst); inst->peer_user_ns = user_ns; - inst->peer_pid = pid; + inst->peer_portid = portid; inst->group_num = group_num; inst->qthreshold = NFULNL_QTHRESH_DEFAULT; @@ -336,7 +336,7 @@ __nfulnl_send(struct nfulnl_instance *inst) if (!nlh) goto out; } - status = nfnetlink_unicast(inst->skb, &init_net, inst->peer_pid, + status = nfnetlink_unicast(inst->skb, &init_net, inst->peer_portid, MSG_DONTWAIT); inst->qlen = 0; @@ -703,7 +703,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this, if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; - /* destroy all instances for this pid */ + /* destroy all instances for this portid */ spin_lock_bh(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *tmp, *t2; @@ -712,7 +712,7 @@ nfulnl_rcv_nl_event(struct notifier_block *this, hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { if ((net_eq(n->net, &init_net)) && - (n->pid == inst->peer_pid)) + (n->portid == inst->peer_portid)) __instance_destroy(inst); } } @@ -774,7 +774,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, } inst = instance_lookup_get(group_num); - if (inst && inst->peer_pid != NETLINK_CB(skb).pid) { + if (inst && inst->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto out_put; } @@ -788,7 +788,7 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, } inst = instance_create(group_num, - NETLINK_CB(skb).pid, + NETLINK_CB(skb).portid, sk_user_ns(NETLINK_CB(skb).ssk)); if (IS_ERR(inst)) { ret = PTR_ERR(inst); @@ -947,7 +947,7 @@ static int seq_show(struct seq_file *s, void *v) return seq_printf(s, "%5d %6d %5d %1d %5d %6d %2d\n", inst->group_num, - inst->peer_pid, inst->qlen, + inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, inst->flushtimeout, atomic_read(&inst->use)); } diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index c0496a55ad0c..b8d9995b76a8 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -44,7 +44,7 @@ struct nfqnl_instance { struct hlist_node hlist; /* global list of queues */ struct rcu_head rcu; - int peer_pid; + int peer_portid; unsigned int queue_maxlen; unsigned int copy_range; unsigned int queue_dropped; @@ -92,7 +92,7 @@ instance_lookup(u_int16_t queue_num) } static struct nfqnl_instance * -instance_create(u_int16_t queue_num, int pid) +instance_create(u_int16_t queue_num, int portid) { struct nfqnl_instance *inst; unsigned int h; @@ -111,7 +111,7 @@ instance_create(u_int16_t queue_num, int pid) } inst->queue_num = queue_num; - inst->peer_pid = pid; + inst->peer_portid = portid; inst->queue_maxlen = NFQNL_QMAX_DEFAULT; inst->copy_range = 0xfffff; inst->copy_mode = NFQNL_COPY_NONE; @@ -440,7 +440,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } spin_lock_bh(&queue->lock); - if (!queue->peer_pid) { + if (!queue->peer_portid) { err = -EINVAL; goto err_out_free_nskb; } @@ -459,7 +459,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ - err = nfnetlink_unicast(nskb, &init_net, queue->peer_pid, MSG_DONTWAIT); + err = nfnetlink_unicast(nskb, &init_net, queue->peer_portid, MSG_DONTWAIT); if (err < 0) { queue->queue_user_dropped++; goto err_out_unlock; @@ -616,7 +616,7 @@ nfqnl_rcv_nl_event(struct notifier_block *this, if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; - /* destroy all instances for this pid */ + /* destroy all instances for this portid */ spin_lock(&instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *tmp, *t2; @@ -625,7 +625,7 @@ nfqnl_rcv_nl_event(struct notifier_block *this, hlist_for_each_entry_safe(inst, tmp, t2, head, hlist) { if ((n->net == &init_net) && - (n->pid == inst->peer_pid)) + (n->portid == inst->peer_portid)) __instance_destroy(inst); } } @@ -650,7 +650,7 @@ static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { [NFQA_MARK] = { .type = NLA_U32 }, }; -static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlpid) +static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlportid) { struct nfqnl_instance *queue; @@ -658,7 +658,7 @@ static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlpid) if (!queue) return ERR_PTR(-ENODEV); - if (queue->peer_pid != nlpid) + if (queue->peer_portid != nlportid) return ERR_PTR(-EPERM); return queue; @@ -698,7 +698,7 @@ nfqnl_recv_verdict_batch(struct sock *ctnl, struct sk_buff *skb, LIST_HEAD(batch_list); u16 queue_num = ntohs(nfmsg->res_id); - queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).pid); + queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); @@ -749,7 +749,7 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, queue = instance_lookup(queue_num); if (!queue) - queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).pid); + queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) return PTR_ERR(queue); @@ -832,7 +832,7 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, rcu_read_lock(); queue = instance_lookup(queue_num); - if (queue && queue->peer_pid != NETLINK_CB(skb).pid) { + if (queue && queue->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto err_out_unlock; } @@ -844,7 +844,7 @@ nfqnl_recv_config(struct sock *ctnl, struct sk_buff *skb, ret = -EBUSY; goto err_out_unlock; } - queue = instance_create(queue_num, NETLINK_CB(skb).pid); + queue = instance_create(queue_num, NETLINK_CB(skb).portid); if (IS_ERR(queue)) { ret = PTR_ERR(queue); goto err_out_unlock; @@ -1016,7 +1016,7 @@ static int seq_show(struct seq_file *s, void *v) return seq_printf(s, "%5d %6d %5d %1d %5d %5d %5d %8d %2d\n", inst->queue_num, - inst->peer_pid, inst->queue_total, + inst->peer_portid, inst->queue_total, inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, inst->id_sequence, 1); diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 6bf878335d94..c15042f987bd 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -627,7 +627,7 @@ static int netlbl_cipsov4_listall_cb(struct cipso_v4_doi *doi_def, void *arg) struct netlbl_cipsov4_doiwalk_arg *cb_arg = arg; void *data; - data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).pid, + data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_cipsov4_gnl_family, NLM_F_MULTI, NLBL_CIPSOV4_C_LISTALL); if (data == NULL) diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 4809e2e48b02..c5384ffc6146 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -448,7 +448,7 @@ static int netlbl_mgmt_listall_cb(struct netlbl_dom_map *entry, void *arg) struct netlbl_domhsh_walk_arg *cb_arg = arg; void *data; - data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).pid, + data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_mgmt_gnl_family, NLM_F_MULTI, NLBL_MGMT_C_LISTALL); if (data == NULL) @@ -613,7 +613,7 @@ static int netlbl_mgmt_protocols_cb(struct sk_buff *skb, int ret_val = -ENOMEM; void *data; - data = genlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + data = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &netlbl_mgmt_gnl_family, NLM_F_MULTI, NLBL_MGMT_C_PROTOCOLS); if (data == NULL) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index e7ff694f1049..b7944413b404 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1096,7 +1096,7 @@ static int netlbl_unlabel_staticlist_gen(u32 cmd, char *secctx; u32 secctx_len; - data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).pid, + data = genlmsg_put(cb_arg->skb, NETLINK_CB(cb_arg->nl_cb->skb).portid, cb_arg->seq, &netlbl_unlabel_gnl_family, NLM_F_MULTI, cmd); if (data == NULL) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4d348e97e131..0f2e3ad69c47 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -67,8 +67,8 @@ struct netlink_sock { /* struct sock has to be the first member of netlink_sock */ struct sock sk; - u32 pid; - u32 dst_pid; + u32 portid; + u32 dst_portid; u32 dst_group; u32 flags; u32 subscriptions; @@ -104,7 +104,7 @@ static inline int netlink_is_kernel(struct sock *sk) return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET; } -struct nl_pid_hash { +struct nl_portid_hash { struct hlist_head *table; unsigned long rehash_time; @@ -118,7 +118,7 @@ struct nl_pid_hash { }; struct netlink_table { - struct nl_pid_hash hash; + struct nl_portid_hash hash; struct hlist_head mc_list; struct listeners __rcu *listeners; unsigned int flags; @@ -145,9 +145,9 @@ static inline u32 netlink_group_mask(u32 group) return group ? 1 << (group - 1) : 0; } -static inline struct hlist_head *nl_pid_hashfn(struct nl_pid_hash *hash, u32 pid) +static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u32 portid) { - return &hash->table[jhash_1word(pid, hash->rnd) & hash->mask]; + return &hash->table[jhash_1word(portid, hash->rnd) & hash->mask]; } static void netlink_destroy_callback(struct netlink_callback *cb) @@ -239,17 +239,17 @@ netlink_unlock_table(void) wake_up(&nl_table_wait); } -static struct sock *netlink_lookup(struct net *net, int protocol, u32 pid) +static struct sock *netlink_lookup(struct net *net, int protocol, u32 portid) { - struct nl_pid_hash *hash = &nl_table[protocol].hash; + struct nl_portid_hash *hash = &nl_table[protocol].hash; struct hlist_head *head; struct sock *sk; struct hlist_node *node; read_lock(&nl_table_lock); - head = nl_pid_hashfn(hash, pid); + head = nl_portid_hashfn(hash, portid); sk_for_each(sk, node, head) { - if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->pid == pid)) { + if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->portid == portid)) { sock_hold(sk); goto found; } @@ -260,7 +260,7 @@ found: return sk; } -static struct hlist_head *nl_pid_hash_zalloc(size_t size) +static struct hlist_head *nl_portid_hash_zalloc(size_t size) { if (size <= PAGE_SIZE) return kzalloc(size, GFP_ATOMIC); @@ -270,7 +270,7 @@ static struct hlist_head *nl_pid_hash_zalloc(size_t size) get_order(size)); } -static void nl_pid_hash_free(struct hlist_head *table, size_t size) +static void nl_portid_hash_free(struct hlist_head *table, size_t size) { if (size <= PAGE_SIZE) kfree(table); @@ -278,7 +278,7 @@ static void nl_pid_hash_free(struct hlist_head *table, size_t size) free_pages((unsigned long)table, get_order(size)); } -static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow) +static int nl_portid_hash_rehash(struct nl_portid_hash *hash, int grow) { unsigned int omask, mask, shift; size_t osize, size; @@ -296,7 +296,7 @@ static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow) size *= 2; } - table = nl_pid_hash_zalloc(size); + table = nl_portid_hash_zalloc(size); if (!table) return 0; @@ -311,23 +311,23 @@ static int nl_pid_hash_rehash(struct nl_pid_hash *hash, int grow) struct hlist_node *node, *tmp; sk_for_each_safe(sk, node, tmp, &otable[i]) - __sk_add_node(sk, nl_pid_hashfn(hash, nlk_sk(sk)->pid)); + __sk_add_node(sk, nl_portid_hashfn(hash, nlk_sk(sk)->portid)); } - nl_pid_hash_free(otable, osize); + nl_portid_hash_free(otable, osize); hash->rehash_time = jiffies + 10 * 60 * HZ; return 1; } -static inline int nl_pid_hash_dilute(struct nl_pid_hash *hash, int len) +static inline int nl_portid_hash_dilute(struct nl_portid_hash *hash, int len) { int avg = hash->entries >> hash->shift; - if (unlikely(avg > 1) && nl_pid_hash_rehash(hash, 1)) + if (unlikely(avg > 1) && nl_portid_hash_rehash(hash, 1)) return 1; if (unlikely(len > avg) && time_after(jiffies, hash->rehash_time)) { - nl_pid_hash_rehash(hash, 0); + nl_portid_hash_rehash(hash, 0); return 1; } @@ -356,9 +356,9 @@ netlink_update_listeners(struct sock *sk) * makes sure updates are visible before bind or setsockopt return. */ } -static int netlink_insert(struct sock *sk, struct net *net, u32 pid) +static int netlink_insert(struct sock *sk, struct net *net, u32 portid) { - struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; + struct nl_portid_hash *hash = &nl_table[sk->sk_protocol].hash; struct hlist_head *head; int err = -EADDRINUSE; struct sock *osk; @@ -366,10 +366,10 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 pid) int len; netlink_table_grab(); - head = nl_pid_hashfn(hash, pid); + head = nl_portid_hashfn(hash, portid); len = 0; sk_for_each(osk, node, head) { - if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->pid == pid)) + if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->portid == portid)) break; len++; } @@ -377,17 +377,17 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 pid) goto err; err = -EBUSY; - if (nlk_sk(sk)->pid) + if (nlk_sk(sk)->portid) goto err; err = -ENOMEM; if (BITS_PER_LONG > 32 && unlikely(hash->entries >= UINT_MAX)) goto err; - if (len && nl_pid_hash_dilute(hash, len)) - head = nl_pid_hashfn(hash, pid); + if (len && nl_portid_hash_dilute(hash, len)) + head = nl_portid_hashfn(hash, portid); hash->entries++; - nlk_sk(sk)->pid = pid; + nlk_sk(sk)->portid = portid; sk_add_node(sk, head); err = 0; @@ -518,11 +518,11 @@ static int netlink_release(struct socket *sock) skb_queue_purge(&sk->sk_write_queue); - if (nlk->pid) { + if (nlk->portid) { struct netlink_notify n = { .net = sock_net(sk), .protocol = sk->sk_protocol, - .pid = nlk->pid, + .portid = nlk->portid, }; atomic_notifier_call_chain(&netlink_chain, NETLINK_URELEASE, &n); @@ -559,24 +559,24 @@ static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; struct net *net = sock_net(sk); - struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; + struct nl_portid_hash *hash = &nl_table[sk->sk_protocol].hash; struct hlist_head *head; struct sock *osk; struct hlist_node *node; - s32 pid = task_tgid_vnr(current); + s32 portid = task_tgid_vnr(current); int err; static s32 rover = -4097; retry: cond_resched(); netlink_table_grab(); - head = nl_pid_hashfn(hash, pid); + head = nl_portid_hashfn(hash, portid); sk_for_each(osk, node, head) { if (!net_eq(sock_net(osk), net)) continue; - if (nlk_sk(osk)->pid == pid) { - /* Bind collision, search negative pid values. */ - pid = rover--; + if (nlk_sk(osk)->portid == portid) { + /* Bind collision, search negative portid values. */ + portid = rover--; if (rover > -4097) rover = -4097; netlink_table_ungrab(); @@ -585,7 +585,7 @@ retry: } netlink_table_ungrab(); - err = netlink_insert(sk, net, pid); + err = netlink_insert(sk, net, portid); if (err == -EADDRINUSE) goto retry; @@ -668,8 +668,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } - if (nlk->pid) { - if (nladdr->nl_pid != nlk->pid) + if (nlk->portid) { + if (nladdr->nl_pid != nlk->portid) return -EINVAL; } else { err = nladdr->nl_pid ? @@ -715,7 +715,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (addr->sa_family == AF_UNSPEC) { sk->sk_state = NETLINK_UNCONNECTED; - nlk->dst_pid = 0; + nlk->dst_portid = 0; nlk->dst_group = 0; return 0; } @@ -726,12 +726,12 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr, if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) return -EPERM; - if (!nlk->pid) + if (!nlk->portid) err = netlink_autobind(sock); if (err == 0) { sk->sk_state = NETLINK_CONNECTED; - nlk->dst_pid = nladdr->nl_pid; + nlk->dst_portid = nladdr->nl_pid; nlk->dst_group = ffs(nladdr->nl_groups); } @@ -750,10 +750,10 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr, *addr_len = sizeof(*nladdr); if (peer) { - nladdr->nl_pid = nlk->dst_pid; + nladdr->nl_pid = nlk->dst_portid; nladdr->nl_groups = netlink_group_mask(nlk->dst_group); } else { - nladdr->nl_pid = nlk->pid; + nladdr->nl_pid = nlk->portid; nladdr->nl_groups = nlk->groups ? nlk->groups[0] : 0; } return 0; @@ -772,19 +772,19 @@ static void netlink_overrun(struct sock *sk) atomic_inc(&sk->sk_drops); } -static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid) +static struct sock *netlink_getsockbyportid(struct sock *ssk, u32 portid) { struct sock *sock; struct netlink_sock *nlk; - sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, pid); + sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, portid); if (!sock) return ERR_PTR(-ECONNREFUSED); /* Don't bother queuing skb if kernel socket has no input function */ nlk = nlk_sk(sock); if (sock->sk_state == NETLINK_CONNECTED && - nlk->dst_pid != nlk_sk(ssk)->pid) { + nlk->dst_portid != nlk_sk(ssk)->portid) { sock_put(sock); return ERR_PTR(-ECONNREFUSED); } @@ -935,7 +935,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb, } int netlink_unicast(struct sock *ssk, struct sk_buff *skb, - u32 pid, int nonblock) + u32 portid, int nonblock) { struct sock *sk; int err; @@ -945,7 +945,7 @@ int netlink_unicast(struct sock *ssk, struct sk_buff *skb, timeo = sock_sndtimeo(ssk, nonblock); retry: - sk = netlink_getsockbypid(ssk, pid); + sk = netlink_getsockbyportid(ssk, portid); if (IS_ERR(sk)) { kfree_skb(skb); return PTR_ERR(sk); @@ -1005,7 +1005,7 @@ static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) struct netlink_broadcast_data { struct sock *exclude_sk; struct net *net; - u32 pid; + u32 portid; u32 group; int failure; int delivery_failure; @@ -1026,7 +1026,7 @@ static int do_one_broadcast(struct sock *sk, if (p->exclude_sk == sk) goto out; - if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups || + if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; @@ -1078,7 +1078,7 @@ out: return 0; } -int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid, +int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation, int (*filter)(struct sock *dsk, struct sk_buff *skb, void *data), void *filter_data) @@ -1092,7 +1092,7 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid, info.exclude_sk = ssk; info.net = net; - info.pid = pid; + info.portid = portid; info.group = group; info.failure = 0; info.delivery_failure = 0; @@ -1130,17 +1130,17 @@ int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb, u32 pid, } EXPORT_SYMBOL(netlink_broadcast_filtered); -int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, +int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 portid, u32 group, gfp_t allocation) { - return netlink_broadcast_filtered(ssk, skb, pid, group, allocation, + return netlink_broadcast_filtered(ssk, skb, portid, group, allocation, NULL, NULL); } EXPORT_SYMBOL(netlink_broadcast); struct netlink_set_err_data { struct sock *exclude_sk; - u32 pid; + u32 portid; u32 group; int code; }; @@ -1156,7 +1156,7 @@ static int do_one_set_err(struct sock *sk, struct netlink_set_err_data *p) if (!net_eq(sock_net(sk), sock_net(p->exclude_sk))) goto out; - if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups || + if (nlk->portid == p->portid || p->group - 1 >= nlk->ngroups || !test_bit(p->group - 1, nlk->groups)) goto out; @@ -1174,14 +1174,14 @@ out: /** * netlink_set_err - report error to broadcast listeners * @ssk: the kernel netlink socket, as returned by netlink_kernel_create() - * @pid: the PID of a process that we want to skip (if any) + * @portid: the PORTID of a process that we want to skip (if any) * @groups: the broadcast group that will notice the error * @code: error code, must be negative (as usual in kernelspace) * * This function returns the number of broadcast listeners that have set the * NETLINK_RECV_NO_ENOBUFS socket option. */ -int netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) +int netlink_set_err(struct sock *ssk, u32 portid, u32 group, int code) { struct netlink_set_err_data info; struct hlist_node *node; @@ -1189,7 +1189,7 @@ int netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code) int ret = 0; info.exclude_sk = ssk; - info.pid = pid; + info.portid = portid; info.group = group; /* sk->sk_err wants a positive error value */ info.code = -code; @@ -1354,7 +1354,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, struct sock *sk = sock->sk; struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *addr = msg->msg_name; - u32 dst_pid; + u32 dst_portid; u32 dst_group; struct sk_buff *skb; int err; @@ -1374,18 +1374,18 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, err = -EINVAL; if (addr->nl_family != AF_NETLINK) goto out; - dst_pid = addr->nl_pid; + dst_portid = addr->nl_pid; dst_group = ffs(addr->nl_groups); err = -EPERM; - if ((dst_group || dst_pid) && + if ((dst_group || dst_portid) && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND)) goto out; } else { - dst_pid = nlk->dst_pid; + dst_portid = nlk->dst_portid; dst_group = nlk->dst_group; } - if (!nlk->pid) { + if (!nlk->portid) { err = netlink_autobind(sock); if (err) goto out; @@ -1399,7 +1399,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if (skb == NULL) goto out; - NETLINK_CB(skb).pid = nlk->pid; + NETLINK_CB(skb).portid = nlk->portid; NETLINK_CB(skb).dst_group = dst_group; NETLINK_CB(skb).creds = siocb->scm->creds; @@ -1417,9 +1417,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if (dst_group) { atomic_inc(&skb->users); - netlink_broadcast(sk, skb, dst_pid, dst_group, GFP_KERNEL); + netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL); } - err = netlink_unicast(sk, skb, dst_pid, msg->msg_flags&MSG_DONTWAIT); + err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT); out: scm_destroy(siocb->scm); @@ -1482,7 +1482,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock, struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name; addr->nl_family = AF_NETLINK; addr->nl_pad = 0; - addr->nl_pid = NETLINK_CB(skb).pid; + addr->nl_pid = NETLINK_CB(skb).portid; addr->nl_groups = netlink_group_mask(NETLINK_CB(skb).dst_group); msg->msg_namelen = sizeof(*addr); } @@ -1683,7 +1683,7 @@ void netlink_clear_multicast_users(struct sock *ksk, unsigned int group) } struct nlmsghdr * -__nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) +__nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags) { struct nlmsghdr *nlh; int size = NLMSG_LENGTH(len); @@ -1692,7 +1692,7 @@ __nlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, int type, int len, int flags) nlh->nlmsg_type = type; nlh->nlmsg_len = size; nlh->nlmsg_flags = flags; - nlh->nlmsg_pid = pid; + nlh->nlmsg_pid = portid; nlh->nlmsg_seq = seq; if (!__builtin_constant_p(size) || NLMSG_ALIGN(size) - size != 0) memset(NLMSG_DATA(nlh) + len, 0, NLMSG_ALIGN(size) - size); @@ -1788,7 +1788,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, atomic_inc(&skb->users); cb->skb = skb; - sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).pid); + sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid); if (sk == NULL) { netlink_destroy_callback(cb); return -ECONNREFUSED; @@ -1836,7 +1836,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) sk = netlink_lookup(sock_net(in_skb->sk), in_skb->sk->sk_protocol, - NETLINK_CB(in_skb).pid); + NETLINK_CB(in_skb).portid); if (sk) { sk->sk_err = ENOBUFS; sk->sk_error_report(sk); @@ -1845,12 +1845,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) return; } - rep = __nlmsg_put(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, + rep = __nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, NLMSG_ERROR, payload, 0); errmsg = nlmsg_data(rep); errmsg->error = err; memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh)); - netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); + netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); } EXPORT_SYMBOL(netlink_ack); @@ -1900,33 +1900,33 @@ EXPORT_SYMBOL(netlink_rcv_skb); * nlmsg_notify - send a notification netlink message * @sk: netlink socket to use * @skb: notification message - * @pid: destination netlink pid for reports or 0 + * @portid: destination netlink portid for reports or 0 * @group: destination multicast group or 0 * @report: 1 to report back, 0 to disable * @flags: allocation flags */ -int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid, +int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags) { int err = 0; if (group) { - int exclude_pid = 0; + int exclude_portid = 0; if (report) { atomic_inc(&skb->users); - exclude_pid = pid; + exclude_portid = portid; } /* errors reported via destination sk->sk_err, but propagate * delivery errors if NETLINK_BROADCAST_ERROR flag is set */ - err = nlmsg_multicast(sk, skb, exclude_pid, group, flags); + err = nlmsg_multicast(sk, skb, exclude_portid, group, flags); } if (report) { int err2; - err2 = nlmsg_unicast(sk, skb, pid); + err2 = nlmsg_unicast(sk, skb, portid); if (!err || err == -ESRCH) err = err2; } @@ -1951,7 +1951,7 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) loff_t off = 0; for (i = 0; i < MAX_LINKS; i++) { - struct nl_pid_hash *hash = &nl_table[i].hash; + struct nl_portid_hash *hash = &nl_table[i].hash; for (j = 0; j <= hash->mask; j++) { sk_for_each(s, node, &hash->table[j]) { @@ -1999,7 +1999,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) j = iter->hash_idx + 1; do { - struct nl_pid_hash *hash = &nl_table[i].hash; + struct nl_portid_hash *hash = &nl_table[i].hash; for (; j <= hash->mask; j++) { s = sk_head(&hash->table[j]); @@ -2038,7 +2038,7 @@ static int netlink_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "%pK %-3d %-6d %08x %-8d %-8d %pK %-8d %-8d %-8lu\n", s, s->sk_protocol, - nlk->pid, + nlk->portid, nlk->groups ? (u32)nlk->groups[0] : 0, sk_rmem_alloc_get(s), sk_wmem_alloc_get(s), @@ -2183,12 +2183,12 @@ static int __init netlink_proto_init(void) order = get_bitmask_order(min(limit, (unsigned long)UINT_MAX)) - 1; for (i = 0; i < MAX_LINKS; i++) { - struct nl_pid_hash *hash = &nl_table[i].hash; + struct nl_portid_hash *hash = &nl_table[i].hash; - hash->table = nl_pid_hash_zalloc(1 * sizeof(*hash->table)); + hash->table = nl_portid_hash_zalloc(1 * sizeof(*hash->table)); if (!hash->table) { while (i-- > 0) - nl_pid_hash_free(nl_table[i].hash.table, + nl_portid_hash_free(nl_table[i].hash.table, 1 * sizeof(*hash->table)); kfree(nl_table); goto panic; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 19288b7d6135..f2aabb6f4105 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -501,7 +501,7 @@ EXPORT_SYMBOL(genl_unregister_family); /** * genlmsg_put - Add generic netlink header to netlink message * @skb: socket buffer holding the message - * @pid: netlink pid the message is addressed to + * @portid: netlink portid the message is addressed to * @seq: sequence number (usually the one of the sender) * @family: generic netlink family * @flags: netlink message flags @@ -509,13 +509,13 @@ EXPORT_SYMBOL(genl_unregister_family); * * Returns pointer to user specific header */ -void *genlmsg_put(struct sk_buff *skb, u32 pid, u32 seq, +void *genlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, struct genl_family *family, int flags, u8 cmd) { struct nlmsghdr *nlh; struct genlmsghdr *hdr; - nlh = nlmsg_put(skb, pid, seq, family->id, GENL_HDRLEN + + nlh = nlmsg_put(skb, portid, seq, family->id, GENL_HDRLEN + family->hdrsize, flags); if (nlh == NULL) return NULL; @@ -585,7 +585,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } info.snd_seq = nlh->nlmsg_seq; - info.snd_pid = NETLINK_CB(skb).pid; + info.snd_portid = NETLINK_CB(skb).portid; info.nlhdr = nlh; info.genlhdr = nlmsg_data(nlh); info.userhdr = nlmsg_data(nlh) + GENL_HDRLEN; @@ -626,12 +626,12 @@ static struct genl_family genl_ctrl = { .netnsok = true, }; -static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, +static int ctrl_fill_info(struct genl_family *family, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; - hdr = genlmsg_put(skb, pid, seq, &genl_ctrl, flags, cmd); + hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; @@ -701,7 +701,7 @@ nla_put_failure: return -EMSGSIZE; } -static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, +static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { @@ -709,7 +709,7 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, struct nlattr *nla_grps; struct nlattr *nest; - hdr = genlmsg_put(skb, pid, seq, &genl_ctrl, flags, cmd); + hdr = genlmsg_put(skb, portid, seq, &genl_ctrl, flags, cmd); if (hdr == NULL) return -1; @@ -756,7 +756,7 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) continue; if (++n < fams_to_skip) continue; - if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).pid, + if (ctrl_fill_info(rt, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, CTRL_CMD_NEWFAMILY) < 0) goto errout; @@ -773,7 +773,7 @@ errout: } static struct sk_buff *ctrl_build_family_msg(struct genl_family *family, - u32 pid, int seq, u8 cmd) + u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; @@ -782,7 +782,7 @@ static struct sk_buff *ctrl_build_family_msg(struct genl_family *family, if (skb == NULL) return ERR_PTR(-ENOBUFS); - err = ctrl_fill_info(family, pid, seq, 0, skb, cmd); + err = ctrl_fill_info(family, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); @@ -792,7 +792,7 @@ static struct sk_buff *ctrl_build_family_msg(struct genl_family *family, } static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp, - u32 pid, int seq, u8 cmd) + u32 portid, int seq, u8 cmd) { struct sk_buff *skb; int err; @@ -801,7 +801,7 @@ static struct sk_buff *ctrl_build_mcgrp_msg(struct genl_multicast_group *grp, if (skb == NULL) return ERR_PTR(-ENOBUFS); - err = ctrl_fill_mcgrp_info(grp, pid, seq, 0, skb, cmd); + err = ctrl_fill_mcgrp_info(grp, portid, seq, 0, skb, cmd); if (err < 0) { nlmsg_free(skb); return ERR_PTR(err); @@ -853,7 +853,7 @@ static int ctrl_getfamily(struct sk_buff *skb, struct genl_info *info) return -ENOENT; } - msg = ctrl_build_family_msg(res, info->snd_pid, info->snd_seq, + msg = ctrl_build_family_msg(res, info->snd_portid, info->snd_seq, CTRL_CMD_NEWFAMILY); if (IS_ERR(msg)) return PTR_ERR(msg); @@ -971,7 +971,7 @@ problem: subsys_initcall(genl_init); -static int genlmsg_mcast(struct sk_buff *skb, u32 pid, unsigned long group, +static int genlmsg_mcast(struct sk_buff *skb, u32 portid, unsigned long group, gfp_t flags) { struct sk_buff *tmp; @@ -986,7 +986,7 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 pid, unsigned long group, goto error; } err = nlmsg_multicast(prev->genl_sock, tmp, - pid, group, flags); + portid, group, flags); if (err) goto error; } @@ -994,20 +994,20 @@ static int genlmsg_mcast(struct sk_buff *skb, u32 pid, unsigned long group, prev = net; } - return nlmsg_multicast(prev->genl_sock, skb, pid, group, flags); + return nlmsg_multicast(prev->genl_sock, skb, portid, group, flags); error: kfree_skb(skb); return err; } -int genlmsg_multicast_allns(struct sk_buff *skb, u32 pid, unsigned int group, +int genlmsg_multicast_allns(struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { - return genlmsg_mcast(skb, pid, group, flags); + return genlmsg_mcast(skb, portid, group, flags); } EXPORT_SYMBOL(genlmsg_multicast_allns); -void genl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, +void genl_notify(struct sk_buff *skb, struct net *net, u32 portid, u32 group, struct nlmsghdr *nlh, gfp_t flags) { struct sock *sk = net->genl_sock; @@ -1016,6 +1016,6 @@ void genl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, if (nlh) report = nlmsg_report(nlh); - nlmsg_notify(sk, skb, pid, group, report, flags); + nlmsg_notify(sk, skb, portid, group, report, flags); } EXPORT_SYMBOL(genl_notify); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 4c51714ee741..4bbb70e32d1e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -58,7 +58,7 @@ static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, { void *hdr; - hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &nfc_genl_family, flags, NFC_CMD_GET_TARGET); if (!hdr) return -EMSGSIZE; @@ -165,7 +165,7 @@ int nfc_genl_targets_found(struct nfc_dev *dev) struct sk_buff *msg; void *hdr; - dev->genl_data.poll_req_pid = 0; + dev->genl_data.poll_req_portid = 0; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!msg) @@ -347,13 +347,13 @@ free_msg: } static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, - u32 pid, u32 seq, + u32 portid, u32 seq, struct netlink_callback *cb, int flags) { void *hdr; - hdr = genlmsg_put(msg, pid, seq, &nfc_genl_family, flags, + hdr = genlmsg_put(msg, portid, seq, &nfc_genl_family, flags, NFC_CMD_GET_DEVICE); if (!hdr) return -EMSGSIZE; @@ -401,7 +401,7 @@ static int nfc_genl_dump_devices(struct sk_buff *skb, while (dev) { int rc; - rc = nfc_genl_send_device(skb, dev, NETLINK_CB(cb->skb).pid, + rc = nfc_genl_send_device(skb, dev, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb, NLM_F_MULTI); if (rc < 0) break; @@ -520,7 +520,7 @@ static int nfc_genl_get_device(struct sk_buff *skb, struct genl_info *info) goto out_putdev; } - rc = nfc_genl_send_device(msg, dev, info->snd_pid, info->snd_seq, + rc = nfc_genl_send_device(msg, dev, info->snd_portid, info->snd_seq, NULL, 0); if (rc < 0) goto out_free; @@ -611,7 +611,7 @@ static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) rc = nfc_start_poll(dev, im_protocols, tm_protocols); if (!rc) - dev->genl_data.poll_req_pid = info->snd_pid; + dev->genl_data.poll_req_portid = info->snd_portid; mutex_unlock(&dev->genl_data.genl_data_mutex); @@ -645,13 +645,13 @@ static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) mutex_lock(&dev->genl_data.genl_data_mutex); - if (dev->genl_data.poll_req_pid != info->snd_pid) { + if (dev->genl_data.poll_req_portid != info->snd_portid) { rc = -EBUSY; goto out; } rc = nfc_stop_poll(dev); - dev->genl_data.poll_req_pid = 0; + dev->genl_data.poll_req_portid = 0; out: mutex_unlock(&dev->genl_data.genl_data_mutex); @@ -771,15 +771,15 @@ static int nfc_genl_rcv_nl_event(struct notifier_block *this, if (event != NETLINK_URELEASE || n->protocol != NETLINK_GENERIC) goto out; - pr_debug("NETLINK_URELEASE event from id %d\n", n->pid); + pr_debug("NETLINK_URELEASE event from id %d\n", n->portid); nfc_device_iter_init(&iter); dev = nfc_device_iter_next(&iter); while (dev) { - if (dev->genl_data.poll_req_pid == n->pid) { + if (dev->genl_data.poll_req_portid == n->portid) { nfc_stop_poll(dev); - dev->genl_data.poll_req_pid = 0; + dev->genl_data.poll_req_portid = 0; } dev = nfc_device_iter_next(&iter); } @@ -792,7 +792,7 @@ out: void nfc_genl_data_init(struct nfc_genl_data *genl_data) { - genl_data->poll_req_pid = 0; + genl_data->poll_req_portid = 0; mutex_init(&genl_data->genl_data_mutex); } diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 0da687769f56..c7425f32e7db 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -286,7 +286,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, upcall.cmd = OVS_PACKET_CMD_ACTION; upcall.key = &OVS_CB(skb)->flow->key; upcall.userdata = NULL; - upcall.pid = 0; + upcall.portid = 0; for (a = nla_data(attr), rem = nla_len(attr); rem > 0; a = nla_next(a, &rem)) { @@ -296,7 +296,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb, break; case OVS_USERSPACE_ATTR_PID: - upcall.pid = nla_get_u32(a); + upcall.portid = nla_get_u32(a); break; } } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 105a0b5adc51..56327e877ed9 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -225,7 +225,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb) upcall.cmd = OVS_PACKET_CMD_MISS; upcall.key = &key; upcall.userdata = NULL; - upcall.pid = p->upcall_pid; + upcall.portid = p->upcall_portid; ovs_dp_upcall(dp, skb, &upcall); consume_skb(skb); stats_counter = &stats->n_missed; @@ -261,7 +261,7 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, int dp_ifindex; int err; - if (upcall_info->pid == 0) { + if (upcall_info->portid == 0) { err = -ENOTCONN; goto err; } @@ -395,7 +395,7 @@ static int queue_userspace_packet(struct net *net, int dp_ifindex, skb_copy_and_csum_dev(skb, nla_data(nla)); - err = genlmsg_unicast(net, user_skb, upcall_info->pid); + err = genlmsg_unicast(net, user_skb, upcall_info->portid); out: kfree_skb(nskb); @@ -780,7 +780,7 @@ static struct genl_multicast_group ovs_dp_flow_multicast_group = { /* Called with genl_lock. */ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, - struct sk_buff *skb, u32 pid, + struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { const int skb_orig_len = skb->len; @@ -795,7 +795,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, sf_acts = rcu_dereference_protected(flow->sf_acts, lockdep_genl_is_held()); - ovs_header = genlmsg_put(skb, pid, seq, &dp_flow_genl_family, flags, cmd); + ovs_header = genlmsg_put(skb, portid, seq, &dp_flow_genl_family, flags, cmd); if (!ovs_header) return -EMSGSIZE; @@ -879,7 +879,7 @@ static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow) static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, struct datapath *dp, - u32 pid, u32 seq, u8 cmd) + u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; int retval; @@ -888,7 +888,7 @@ static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_flow_cmd_fill_info(flow, dp, skb, pid, seq, 0, cmd); + retval = ovs_flow_cmd_fill_info(flow, dp, skb, portid, seq, 0, cmd); BUG_ON(retval < 0); return skb; } @@ -970,7 +970,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) flow->hash = ovs_flow_hash(&key, key_len); ovs_flow_tbl_insert(table, flow); - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid, + reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); } else { @@ -1008,7 +1008,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) ovs_flow_deferred_free_acts(old_acts); } - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid, + reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); /* Clear stats. */ @@ -1020,7 +1020,7 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) } if (!IS_ERR(reply)) - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL); else @@ -1061,7 +1061,7 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) if (!flow) return -ENOENT; - reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid, + reply = ovs_flow_cmd_build_info(flow, dp, info->snd_portid, info->snd_seq, OVS_FLOW_CMD_NEW); if (IS_ERR(reply)) return PTR_ERR(reply); @@ -1103,13 +1103,13 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_flow_tbl_remove(table, flow); - err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_pid, + err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid, info->snd_seq, 0, OVS_FLOW_CMD_DEL); BUG_ON(err < 0); ovs_flow_deferred_free(flow); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL); return 0; } @@ -1137,7 +1137,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) break; if (ovs_flow_cmd_fill_info(flow, dp, skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_FLOW_CMD_NEW) < 0) break; @@ -1191,13 +1191,13 @@ static struct genl_multicast_group ovs_dp_datapath_multicast_group = { }; static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, - u32 pid, u32 seq, u32 flags, u8 cmd) + u32 portid, u32 seq, u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_dp_stats dp_stats; int err; - ovs_header = genlmsg_put(skb, pid, seq, &dp_datapath_genl_family, + ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family, flags, cmd); if (!ovs_header) goto error; @@ -1222,7 +1222,7 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 pid, +static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; @@ -1232,7 +1232,7 @@ static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 pid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_dp_cmd_fill_info(dp, skb, pid, seq, 0, cmd); + retval = ovs_dp_cmd_fill_info(dp, skb, portid, seq, 0, cmd); if (retval < 0) { kfree_skb(skb); return ERR_PTR(retval); @@ -1311,7 +1311,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.options = NULL; parms.dp = dp; parms.port_no = OVSP_LOCAL; - parms.upcall_pid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]); + parms.upcall_portid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]); vport = new_vport(&parms); if (IS_ERR(vport)) { @@ -1322,7 +1322,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_ports_array; } - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); err = PTR_ERR(reply); if (IS_ERR(reply)) @@ -1332,7 +1332,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) list_add_tail(&dp->list_node, &ovs_net->dps); rtnl_unlock(); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_datapath_multicast_group.id, info->nlhdr, GFP_KERNEL); return 0; @@ -1394,7 +1394,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dp)) return err; - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_DEL); err = PTR_ERR(reply); if (IS_ERR(reply)) @@ -1402,7 +1402,7 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) __dp_destroy(dp); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_datapath_multicast_group.id, info->nlhdr, GFP_KERNEL); @@ -1419,7 +1419,7 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dp)) return PTR_ERR(dp); - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); if (IS_ERR(reply)) { err = PTR_ERR(reply); @@ -1428,7 +1428,7 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) return 0; } - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_datapath_multicast_group.id, info->nlhdr, GFP_KERNEL); @@ -1444,7 +1444,7 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(dp)) return PTR_ERR(dp); - reply = ovs_dp_cmd_build_info(dp, info->snd_pid, + reply = ovs_dp_cmd_build_info(dp, info->snd_portid, info->snd_seq, OVS_DP_CMD_NEW); if (IS_ERR(reply)) return PTR_ERR(reply); @@ -1461,7 +1461,7 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) list_for_each_entry(dp, &ovs_net->dps, list_node) { if (i >= skip && - ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).pid, + ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_DP_CMD_NEW) < 0) break; @@ -1521,13 +1521,13 @@ struct genl_multicast_group ovs_dp_vport_multicast_group = { /* Called with RTNL lock or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, - u32 pid, u32 seq, u32 flags, u8 cmd) + u32 portid, u32 seq, u32 flags, u8 cmd) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; int err; - ovs_header = genlmsg_put(skb, pid, seq, &dp_vport_genl_family, + ovs_header = genlmsg_put(skb, portid, seq, &dp_vport_genl_family, flags, cmd); if (!ovs_header) return -EMSGSIZE; @@ -1537,7 +1537,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, if (nla_put_u32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no) || nla_put_u32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type) || nla_put_string(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport)) || - nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid)) + nla_put_u32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_portid)) goto nla_put_failure; ovs_vport_get_stats(vport, &vport_stats); @@ -1559,7 +1559,7 @@ error: } /* Called with RTNL lock or RCU read lock. */ -struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 pid, +struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, u32 seq, u8 cmd) { struct sk_buff *skb; @@ -1569,7 +1569,7 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 pid, if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, pid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, portid, seq, 0, cmd); if (retval < 0) { kfree_skb(skb); return ERR_PTR(retval); @@ -1661,21 +1661,21 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) parms.options = a[OVS_VPORT_ATTR_OPTIONS]; parms.dp = dp; parms.port_no = port_no; - parms.upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + parms.upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); vport = new_vport(&parms); err = PTR_ERR(vport); if (IS_ERR(vport)) goto exit_unlock; - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, OVS_VPORT_CMD_NEW); if (IS_ERR(reply)) { err = PTR_ERR(reply); ovs_dp_detach_port(vport); goto exit_unlock; } - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); exit_unlock: @@ -1707,9 +1707,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) if (err) goto exit_unlock; if (a[OVS_VPORT_ATTR_UPCALL_PID]) - vport->upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); + vport->upcall_portid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]); - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, OVS_VPORT_CMD_NEW); if (IS_ERR(reply)) { netlink_set_err(sock_net(skb->sk)->genl_sock, 0, @@ -1717,7 +1717,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); exit_unlock: @@ -1743,7 +1743,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, OVS_VPORT_CMD_DEL); err = PTR_ERR(reply); if (IS_ERR(reply)) @@ -1751,7 +1751,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_dp_detach_port(vport); - genl_notify(reply, genl_info_net(info), info->snd_pid, + genl_notify(reply, genl_info_net(info), info->snd_portid, ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL); exit_unlock: @@ -1773,7 +1773,7 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) if (IS_ERR(vport)) goto exit_unlock; - reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq, + reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, OVS_VPORT_CMD_NEW); err = PTR_ERR(reply); if (IS_ERR(reply)) @@ -1808,7 +1808,7 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(vport, n, &dp->ports[i], dp_hash_node) { if (j >= skip && ovs_vport_cmd_fill_info(vport, skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_VPORT_CMD_NEW) < 0) diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h index 129ec5480758..031dfbf37c93 100644 --- a/net/openvswitch/datapath.h +++ b/net/openvswitch/datapath.h @@ -129,7 +129,7 @@ struct dp_upcall_info { u8 cmd; const struct sw_flow_key *key; const struct nlattr *userdata; - u32 pid; + u32 portid; }; static inline struct net *ovs_dp_get_net(struct datapath *dp) diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 1abd9609ba78..9055dd698c70 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -125,7 +125,7 @@ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, vport->dp = parms->dp; vport->port_no = parms->port_no; - vport->upcall_pid = parms->upcall_pid; + vport->upcall_portid = parms->upcall_portid; vport->ops = ops; INIT_HLIST_NODE(&vport->dp_hash_node); diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index c56e4836e93b..3f7961ea3c56 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -70,7 +70,7 @@ struct vport_err_stats { * @rcu: RCU callback head for deferred destruction. * @port_no: Index into @dp's @ports array. * @dp: Datapath to which this port belongs. - * @upcall_pid: The Netlink port to use for packets received on this port that + * @upcall_portid: The Netlink port to use for packets received on this port that * miss the flow table. * @hash_node: Element in @dev_table hash table in vport.c. * @dp_hash_node: Element in @datapath->ports hash table in datapath.c. @@ -83,7 +83,7 @@ struct vport { struct rcu_head rcu; u16 port_no; struct datapath *dp; - u32 upcall_pid; + u32 upcall_portid; struct hlist_node hash_node; struct hlist_node dp_hash_node; @@ -113,7 +113,7 @@ struct vport_parms { /* For ovs_vport_alloc(). */ struct datapath *dp; u16 port_no; - u32 upcall_pid; + u32 upcall_portid; }; /** diff --git a/net/packet/diag.c b/net/packet/diag.c index 39bce0d50df9..8db6e21c46bd 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -126,13 +126,13 @@ static int pdiag_put_fanout(struct packet_sock *po, struct sk_buff *nlskb) } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct packet_diag_req *req, - u32 pid, u32 seq, u32 flags, int sk_ino) + u32 portid, u32 seq, u32 flags, int sk_ino) { struct nlmsghdr *nlh; struct packet_diag_msg *rp; struct packet_sock *po = pkt_sk(sk); - nlh = nlmsg_put(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rp), flags); + nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rp), flags); if (!nlh) return -EMSGSIZE; @@ -184,7 +184,7 @@ static int packet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) if (num < s_num) goto next; - if (sk_diag_fill(sk, skb, req, NETLINK_CB(cb->skb).pid, + if (sk_diag_fill(sk, skb, req, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, sock_i_ino(sk)) < 0) goto done; diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 7dd762a464e5..83a8389619aa 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -33,7 +33,7 @@ /* Device address handling */ static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, - u32 pid, u32 seq, int event); + u32 portid, u32 seq, int event); void phonet_address_notify(int event, struct net_device *dev, u8 addr) { @@ -101,12 +101,12 @@ static int addr_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *attr) } static int fill_addr(struct sk_buff *skb, struct net_device *dev, u8 addr, - u32 pid, u32 seq, int event) + u32 portid, u32 seq, int event) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*ifm), 0); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), 0); if (nlh == NULL) return -EMSGSIZE; @@ -148,7 +148,7 @@ static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb) continue; if (fill_addr(skb, pnd->netdev, addr << 2, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWADDR) < 0) goto out; } @@ -165,12 +165,12 @@ out: /* Routes handling */ static int fill_route(struct sk_buff *skb, struct net_device *dev, u8 dst, - u32 pid, u32 seq, int event) + u32 portid, u32 seq, int event) { struct rtmsg *rtm; struct nlmsghdr *nlh; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), 0); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), 0); if (nlh == NULL) return -EMSGSIZE; @@ -276,7 +276,7 @@ static int route_dumpit(struct sk_buff *skb, struct netlink_callback *cb) if (addr_idx++ < addr_start_idx) continue; - if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).pid, + if (fill_route(skb, dev, addr << 2, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWROUTE)) goto out; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index e3d2c78cb52c..102761d294cb 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -644,7 +644,7 @@ errout: } static int -tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq, +tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 portid, u32 seq, u16 flags, int event, int bind, int ref) { struct tcamsg *t; @@ -652,7 +652,7 @@ tca_get_fill(struct sk_buff *skb, struct tc_action *a, u32 pid, u32 seq, unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*t), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags); if (!nlh) goto out_nlmsg_trim; t = nlmsg_data(nlh); @@ -678,7 +678,7 @@ out_nlmsg_trim: } static int -act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n, +act_get_notify(struct net *net, u32 portid, struct nlmsghdr *n, struct tc_action *a, int event) { struct sk_buff *skb; @@ -686,16 +686,16 @@ act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n, skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - if (tca_get_fill(skb, a, pid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { + if (tca_get_fill(skb, a, portid, n->nlmsg_seq, 0, event, 0, 0) <= 0) { kfree_skb(skb); return -EINVAL; } - return rtnl_unicast(skb, net, pid); + return rtnl_unicast(skb, net, portid); } static struct tc_action * -tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 pid) +tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 portid) { struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action *a; @@ -762,7 +762,7 @@ static struct tc_action *create_a(int i) } static int tca_action_flush(struct net *net, struct nlattr *nla, - struct nlmsghdr *n, u32 pid) + struct nlmsghdr *n, u32 portid) { struct sk_buff *skb; unsigned char *b; @@ -799,7 +799,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, if (a->ops == NULL) goto err_out; - nlh = nlmsg_put(skb, pid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); + nlh = nlmsg_put(skb, portid, n->nlmsg_seq, RTM_DELACTION, sizeof(*t), 0); if (!nlh) goto out_module_put; t = nlmsg_data(nlh); @@ -823,7 +823,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, nlh->nlmsg_flags |= NLM_F_ROOT; module_put(a->ops->owner); kfree(a); - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (err > 0) return 0; @@ -841,7 +841,7 @@ noflush_out: static int tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, - u32 pid, int event) + u32 portid, int event) { int i, ret; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; @@ -853,13 +853,13 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { if (tb[1] != NULL) - return tca_action_flush(net, tb[1], n, pid); + return tca_action_flush(net, tb[1], n, portid); else return -EINVAL; } for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) { - act = tcf_action_get_1(tb[i], n, pid); + act = tcf_action_get_1(tb[i], n, portid); if (IS_ERR(act)) { ret = PTR_ERR(act); goto err; @@ -874,7 +874,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, } if (event == RTM_GETACTION) - ret = act_get_notify(net, pid, n, head, event); + ret = act_get_notify(net, portid, n, head, event); else { /* delete */ struct sk_buff *skb; @@ -884,7 +884,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, goto err; } - if (tca_get_fill(skb, head, pid, n->nlmsg_seq, 0, event, + if (tca_get_fill(skb, head, portid, n->nlmsg_seq, 0, event, 0, 1) <= 0) { kfree_skb(skb); ret = -EINVAL; @@ -893,7 +893,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* now do the delete */ tcf_action_destroy(head, 0); - ret = rtnetlink_send(skb, net, pid, RTNLGRP_TC, + ret = rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); if (ret > 0) return 0; @@ -905,7 +905,7 @@ err: } static int tcf_add_notify(struct net *net, struct tc_action *a, - u32 pid, u32 seq, int event, u16 flags) + u32 portid, u32 seq, int event, u16 flags) { struct tcamsg *t; struct nlmsghdr *nlh; @@ -920,7 +920,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, b = skb_tail_pointer(skb); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*t), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*t), flags); if (!nlh) goto out_kfree_skb; t = nlmsg_data(nlh); @@ -940,7 +940,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, nlh->nlmsg_len = skb_tail_pointer(skb) - b; NETLINK_CB(skb).dst_group = RTNLGRP_TC; - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags & NLM_F_ECHO); + err = rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); if (err > 0) err = 0; return err; @@ -953,7 +953,7 @@ out_kfree_skb: static int tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, - u32 pid, int ovr) + u32 portid, int ovr) { int ret = 0; struct tc_action *act; @@ -971,7 +971,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* dump then free all the actions after update; inserted policy * stays intact */ - ret = tcf_add_notify(net, act, pid, seq, RTM_NEWACTION, n->nlmsg_flags); + ret = tcf_add_notify(net, act, portid, seq, RTM_NEWACTION, n->nlmsg_flags); for (a = act; a; a = act) { act = a->next; kfree(a); @@ -984,7 +984,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_ACT_MAX + 1]; - u32 pid = skb ? NETLINK_CB(skb).pid : 0; + u32 portid = skb ? NETLINK_CB(skb).portid : 0; int ret = 0, ovr = 0; ret = nlmsg_parse(n, sizeof(struct tcamsg), tca, TCA_ACT_MAX, NULL); @@ -1008,17 +1008,17 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; replay: - ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, pid, ovr); + ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, portid, ovr); if (ret == -EAGAIN) goto replay; break; case RTM_DELACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - pid, RTM_DELACTION); + portid, RTM_DELACTION); break; case RTM_GETACTION: ret = tca_action_gd(net, tca[TCA_ACT_TAB], n, - pid, RTM_GETACTION); + portid, RTM_GETACTION); break; default: BUG(); @@ -1085,7 +1085,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) goto out_module_put; } - nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, cb->nlh->nlmsg_type, sizeof(*t), 0); if (!nlh) goto out_module_put; @@ -1109,7 +1109,7 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) nla_nest_cancel(skb, nest); nlh->nlmsg_len = skb_tail_pointer(skb) - b; - if (NETLINK_CB(cb->skb).pid && ret) + if (NETLINK_CB(cb->skb).portid && ret) nlh->nlmsg_flags |= NLM_F_MULTI; module_put(a_o->owner); return skb->len; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index dc3ef5aef355..7ae02892437c 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -343,13 +343,13 @@ errout: } static int tcf_fill_node(struct sk_buff *skb, struct tcf_proto *tp, - unsigned long fh, u32 pid, u32 seq, u16 flags, int event) + unsigned long fh, u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); @@ -381,18 +381,18 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, unsigned long fh, int event) { struct sk_buff *skb; - u32 pid = oskb ? NETLINK_CB(oskb).pid : 0; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - if (tcf_fill_node(skb, tp, fh, pid, n->nlmsg_seq, 0, event) <= 0) { + if (tcf_fill_node(skb, tp, fh, portid, n->nlmsg_seq, 0, event) <= 0) { kfree_skb(skb); return -EINVAL; } - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); } @@ -407,7 +407,7 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, { struct tcf_dump_args *a = (void *)arg; - return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).pid, + return tcf_fill_node(a->skb, tp, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER); } @@ -465,7 +465,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (t > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).pid, + if (tcf_fill_node(skb, tp, 0, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) break; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index a08b4ab3e421..a18d975db59c 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1185,7 +1185,7 @@ graft: } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, - u32 pid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1193,7 +1193,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct gnet_dump d; struct qdisc_size_table *stab; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); @@ -1248,25 +1248,25 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, struct Qdisc *old, struct Qdisc *new) { struct sk_buff *skb; - u32 pid = oskb ? NETLINK_CB(oskb).pid : 0; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old)) { - if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, + if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new)) { - if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, + if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; } if (skb->len) - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); err_out: @@ -1289,7 +1289,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; } else { if (!tc_qdisc_dump_ignore(q) && - tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid, + tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; q_idx++; @@ -1300,7 +1300,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, continue; } if (!tc_qdisc_dump_ignore(q) && - tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid, + tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; q_idx++; @@ -1375,7 +1375,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) const struct Qdisc_class_ops *cops; unsigned long cl = 0; unsigned long new_cl; - u32 pid = tcm->tcm_parent; + u32 portid = tcm->tcm_parent; u32 clid = tcm->tcm_handle; u32 qid = TC_H_MAJ(clid); int err; @@ -1403,8 +1403,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) /* Step 1. Determine qdisc handle X:0 */ - if (pid != TC_H_ROOT) { - u32 qid1 = TC_H_MAJ(pid); + if (portid != TC_H_ROOT) { + u32 qid1 = TC_H_MAJ(portid); if (qid && qid1) { /* If both majors are known, they must be identical. */ @@ -1418,10 +1418,10 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) /* Now qid is genuine qdisc handle consistent * both with parent and child. * - * TC_H_MAJ(pid) still may be unspecified, complete it now. + * TC_H_MAJ(portid) still may be unspecified, complete it now. */ - if (pid) - pid = TC_H_MAKE(qid, pid); + if (portid) + portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) qid = dev->qdisc->handle; @@ -1439,7 +1439,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) /* Now try to get class */ if (clid == 0) { - if (pid == TC_H_ROOT) + if (portid == TC_H_ROOT) clid = qid; } else clid = TC_H_MAKE(qid, clid); @@ -1478,7 +1478,7 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) new_cl = cl; err = -EOPNOTSUPP; if (cops->change) - err = cops->change(q, clid, pid, tca, &new_cl); + err = cops->change(q, clid, portid, tca, &new_cl); if (err == 0) tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS); @@ -1492,7 +1492,7 @@ out: static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, unsigned long cl, - u32 pid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1500,7 +1500,7 @@ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; - nlh = nlmsg_put(skb, pid, seq, event, sizeof(*tcm), flags); + nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); @@ -1540,18 +1540,18 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, unsigned long cl, int event) { struct sk_buff *skb; - u32 pid = oskb ? NETLINK_CB(oskb).pid : 0; + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; - if (tc_fill_tclass(skb, q, cl, pid, n->nlmsg_seq, 0, event) < 0) { + if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event) < 0) { kfree_skb(skb); return -EINVAL; } - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); } @@ -1565,7 +1565,7 @@ static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walk { struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg; - return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).pid, + return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS); } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 47a839df27dc..6675914dc592 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -62,7 +62,7 @@ static int handle_cmd(struct sk_buff *skb, struct genl_info *info) rep_nlh = nlmsg_hdr(rep_buf); memcpy(rep_nlh, req_nlh, hdr_space); rep_nlh->nlmsg_len = rep_buf->len; - genlmsg_unicast(&init_net, rep_buf, NETLINK_CB(skb).pid); + genlmsg_unicast(&init_net, rep_buf, NETLINK_CB(skb).portid); } return 0; diff --git a/net/unix/diag.c b/net/unix/diag.c index 750b13408449..06748f108a57 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -110,12 +110,12 @@ static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb) } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - u32 pid, u32 seq, u32 flags, int sk_ino) + u32 portid, u32 seq, u32 flags, int sk_ino) { struct nlmsghdr *nlh; struct unix_diag_msg *rep; - nlh = nlmsg_put(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), + nlh = nlmsg_put(skb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep), flags); if (!nlh) return -EMSGSIZE; @@ -159,7 +159,7 @@ out_nlmsg_trim: } static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req, - u32 pid, u32 seq, u32 flags) + u32 portid, u32 seq, u32 flags) { int sk_ino; @@ -170,7 +170,7 @@ static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_r if (!sk_ino) return 0; - return sk_diag_fill(sk, skb, req, pid, seq, flags, sk_ino); + return sk_diag_fill(sk, skb, req, portid, seq, flags, sk_ino); } static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) @@ -200,7 +200,7 @@ static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!(req->udiag_states & (1 << sk->sk_state))) goto next; if (sk_diag_dump(sk, skb, req, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI) < 0) goto done; @@ -267,7 +267,7 @@ again: if (!rep) goto out; - err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid, + err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0, req->udiag_ino); if (err < 0) { nlmsg_free(rep); @@ -277,7 +277,7 @@ again: goto again; } - err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid, MSG_DONTWAIT); if (err > 0) err = 0; diff --git a/net/wireless/core.h b/net/wireless/core.h index bc7430b54771..a343be4a52bd 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -55,7 +55,7 @@ struct cfg80211_registered_device { int opencount; /* also protected by devlist_mtx */ wait_queue_head_t dev_wait; - u32 ap_beacons_nlpid; + u32 ap_beacons_nlportid; /* protected by RTNL only */ int num_running_ifaces; diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 8fd0242ee169..ec7fcee5bad6 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -615,7 +615,7 @@ EXPORT_SYMBOL(cfg80211_del_sta); struct cfg80211_mgmt_registration { struct list_head list; - u32 nlpid; + u32 nlportid; int match_len; @@ -624,7 +624,7 @@ struct cfg80211_mgmt_registration { u8 match[]; }; -int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, +int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid, u16 frame_type, const u8 *match_data, int match_len) { @@ -672,7 +672,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, memcpy(nreg->match, match_data, match_len); nreg->match_len = match_len; - nreg->nlpid = snd_pid; + nreg->nlportid = snd_portid; nreg->frame_type = cpu_to_le16(frame_type); list_add(&nreg->list, &wdev->mgmt_registrations); @@ -685,7 +685,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_pid, return err; } -void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid) +void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid) { struct wiphy *wiphy = wdev->wiphy; struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); @@ -694,7 +694,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid) spin_lock_bh(&wdev->mgmt_registrations_lock); list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) { - if (reg->nlpid != nlpid) + if (reg->nlportid != nlportid) continue; if (rdev->ops->mgmt_frame_register) { @@ -710,8 +710,8 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlpid) spin_unlock_bh(&wdev->mgmt_registrations_lock); - if (nlpid == wdev->ap_unexpected_nlpid) - wdev->ap_unexpected_nlpid = 0; + if (nlportid == wdev->ap_unexpected_nlportid) + wdev->ap_unexpected_nlportid = 0; } void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev) @@ -872,7 +872,7 @@ bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_mbm, /* found match! */ /* Indicate the received Action frame to user space */ - if (nl80211_send_mgmt(rdev, wdev, reg->nlpid, + if (nl80211_send_mgmt(rdev, wdev, reg->nlportid, freq, sig_mbm, buf, len, gfp)) continue; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 787aeaa902fe..34eb5c07a567 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -496,11 +496,11 @@ static bool is_valid_ie_attr(const struct nlattr *attr) } /* message building helper */ -static inline void *nl80211hdr_put(struct sk_buff *skb, u32 pid, u32 seq, +static inline void *nl80211hdr_put(struct sk_buff *skb, u32 portid, u32 seq, int flags, u8 cmd) { /* since there is no private header just add the generic one */ - return genlmsg_put(skb, pid, seq, &nl80211_fam, flags, cmd); + return genlmsg_put(skb, portid, seq, &nl80211_fam, flags, cmd); } static int nl80211_msg_put_channel(struct sk_buff *msg, @@ -851,7 +851,7 @@ nla_put_failure: return -ENOBUFS; } -static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, +static int nl80211_send_wiphy(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *dev) { void *hdr; @@ -866,7 +866,7 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, const struct ieee80211_txrx_stypes *mgmt_stypes = dev->wiphy.mgmt_stypes; - hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_WIPHY); + hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_WIPHY); if (!hdr) return -1; @@ -1267,7 +1267,7 @@ static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) continue; if (++idx <= start) continue; - if (nl80211_send_wiphy(skb, NETLINK_CB(cb->skb).pid, + if (nl80211_send_wiphy(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, dev) < 0) { idx--; @@ -1290,7 +1290,7 @@ static int nl80211_get_wiphy(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - if (nl80211_send_wiphy(msg, info->snd_pid, info->snd_seq, 0, dev) < 0) { + if (nl80211_send_wiphy(msg, info->snd_portid, info->snd_seq, 0, dev) < 0) { nlmsg_free(msg); return -ENOBUFS; } @@ -1736,14 +1736,14 @@ static inline u64 wdev_id(struct wireless_dev *wdev) ((u64)wiphy_to_dev(wdev->wiphy)->wiphy_idx << 32); } -static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, +static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { struct net_device *dev = wdev->netdev; void *hdr; - hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_INTERFACE); + hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_INTERFACE); if (!hdr) return -1; @@ -1807,7 +1807,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx++; continue; } - if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).pid, + if (nl80211_send_iface(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev) < 0) { mutex_unlock(&rdev->devlist_mtx); @@ -1838,7 +1838,7 @@ static int nl80211_get_interface(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, + if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0, dev, wdev) < 0) { nlmsg_free(msg); return -ENOBUFS; @@ -2056,7 +2056,7 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info) break; } - if (nl80211_send_iface(msg, info->snd_pid, info->snd_seq, 0, + if (nl80211_send_iface(msg, info->snd_portid, info->snd_seq, 0, rdev, wdev) < 0) { nlmsg_free(msg); return -ENOBUFS; @@ -2191,7 +2191,7 @@ static int nl80211_get_key(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_NEW_KEY); if (IS_ERR(hdr)) return PTR_ERR(hdr); @@ -2769,7 +2769,7 @@ nla_put_failure: return false; } -static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, +static int nl80211_send_station(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct cfg80211_registered_device *rdev, struct net_device *dev, @@ -2778,7 +2778,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, void *hdr; struct nlattr *sinfoattr, *bss_param; - hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_STATION); + hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_STATION); if (!hdr) return -1; @@ -2931,7 +2931,7 @@ static int nl80211_dump_station(struct sk_buff *skb, goto out_err; if (nl80211_send_station(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, dev, netdev, mac_addr, &sinfo) < 0) @@ -2977,7 +2977,7 @@ static int nl80211_get_station(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - if (nl80211_send_station(msg, info->snd_pid, info->snd_seq, 0, + if (nl80211_send_station(msg, info->snd_portid, info->snd_seq, 0, rdev, dev, mac_addr, &sinfo) < 0) { nlmsg_free(msg); return -ENOBUFS; @@ -3303,7 +3303,7 @@ static int nl80211_del_station(struct sk_buff *skb, struct genl_info *info) return rdev->ops->del_station(&rdev->wiphy, dev, mac_addr); } -static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, +static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) @@ -3311,7 +3311,7 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, void *hdr; struct nlattr *pinfoattr; - hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_STATION); + hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_STATION); if (!hdr) return -1; @@ -3389,7 +3389,7 @@ static int nl80211_dump_mpath(struct sk_buff *skb, if (err) goto out_err; - if (nl80211_send_mpath(skb, NETLINK_CB(cb->skb).pid, + if (nl80211_send_mpath(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, netdev, dst, next_hop, &pinfo) < 0) @@ -3438,7 +3438,7 @@ static int nl80211_get_mpath(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - if (nl80211_send_mpath(msg, info->snd_pid, info->snd_seq, 0, + if (nl80211_send_mpath(msg, info->snd_portid, info->snd_seq, 0, dev, dst, next_hop, &pinfo) < 0) { nlmsg_free(msg); return -ENOBUFS; @@ -3679,7 +3679,7 @@ static int nl80211_get_mesh_config(struct sk_buff *skb, msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_MESH_CONFIG); if (!hdr) goto out; @@ -3998,7 +3998,7 @@ static int nl80211_get_reg(struct sk_buff *skb, struct genl_info *info) goto out; } - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_REG); if (!hdr) goto put_failure; @@ -4616,7 +4616,7 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, ASSERT_WDEV_LOCK(wdev); - hdr = nl80211hdr_put(msg, NETLINK_CB(cb->skb).pid, seq, flags, + hdr = nl80211hdr_put(msg, NETLINK_CB(cb->skb).portid, seq, flags, NL80211_CMD_NEW_SCAN_RESULTS); if (!hdr) return -1; @@ -4735,14 +4735,14 @@ static int nl80211_dump_scan(struct sk_buff *skb, return skb->len; } -static int nl80211_send_survey(struct sk_buff *msg, u32 pid, u32 seq, +static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq, int flags, struct net_device *dev, struct survey_info *survey) { void *hdr; struct nlattr *infoattr; - hdr = nl80211hdr_put(msg, pid, seq, flags, + hdr = nl80211hdr_put(msg, portid, seq, flags, NL80211_CMD_NEW_SURVEY_RESULTS); if (!hdr) return -ENOMEM; @@ -4836,7 +4836,7 @@ static int nl80211_dump_survey(struct sk_buff *skb, } if (nl80211_send_survey(skb, - NETLINK_CB(cb->skb).pid, + NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, netdev, &survey) < 0) @@ -5451,7 +5451,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, } while (1) { - void *hdr = nl80211hdr_put(skb, NETLINK_CB(cb->skb).pid, + void *hdr = nl80211hdr_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, NL80211_CMD_TESTMODE); struct nlattr *tmdata; @@ -5491,7 +5491,7 @@ static int nl80211_testmode_dump(struct sk_buff *skb, static struct sk_buff * __cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev, - int approxlen, u32 pid, u32 seq, gfp_t gfp) + int approxlen, u32 portid, u32 seq, gfp_t gfp) { struct sk_buff *skb; void *hdr; @@ -5501,7 +5501,7 @@ __cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev, if (!skb) return NULL; - hdr = nl80211hdr_put(skb, pid, seq, 0, NL80211_CMD_TESTMODE); + hdr = nl80211hdr_put(skb, portid, seq, 0, NL80211_CMD_TESTMODE); if (!hdr) { kfree_skb(skb); return NULL; @@ -5531,7 +5531,7 @@ struct sk_buff *cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy, return NULL; return __cfg80211_testmode_alloc_skb(rdev, approxlen, - rdev->testmode_info->snd_pid, + rdev->testmode_info->snd_portid, rdev->testmode_info->snd_seq, GFP_KERNEL); } @@ -5867,7 +5867,7 @@ static int nl80211_remain_on_channel(struct sk_buff *skb, if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_REMAIN_ON_CHANNEL); if (IS_ERR(hdr)) { @@ -6086,7 +6086,7 @@ static int nl80211_register_mgmt(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->mgmt_tx) return -EOPNOTSUPP; - return cfg80211_mlme_register_mgmt(wdev, info->snd_pid, frame_type, + return cfg80211_mlme_register_mgmt(wdev, info->snd_portid, frame_type, nla_data(info->attrs[NL80211_ATTR_FRAME_MATCH]), nla_len(info->attrs[NL80211_ATTR_FRAME_MATCH])); } @@ -6167,7 +6167,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_FRAME); if (IS_ERR(hdr)) { @@ -6284,7 +6284,7 @@ static int nl80211_get_power_save(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_POWER_SAVE); if (!hdr) { err = -ENOBUFS; @@ -6486,7 +6486,7 @@ static int nl80211_get_wowlan(struct sk_buff *skb, struct genl_info *info) if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_GET_WOWLAN); if (!hdr) goto nla_put_failure; @@ -6760,10 +6760,10 @@ static int nl80211_register_unexpected_frame(struct sk_buff *skb, wdev->iftype != NL80211_IFTYPE_P2P_GO) return -EINVAL; - if (wdev->ap_unexpected_nlpid) + if (wdev->ap_unexpected_nlportid) return -EBUSY; - wdev->ap_unexpected_nlpid = info->snd_pid; + wdev->ap_unexpected_nlportid = info->snd_portid; return 0; } @@ -6793,7 +6793,7 @@ static int nl80211_probe_client(struct sk_buff *skb, if (!msg) return -ENOMEM; - hdr = nl80211hdr_put(msg, info->snd_pid, info->snd_seq, 0, + hdr = nl80211hdr_put(msg, info->snd_portid, info->snd_seq, 0, NL80211_CMD_PROBE_CLIENT); if (IS_ERR(hdr)) { @@ -6828,10 +6828,10 @@ static int nl80211_register_beacons(struct sk_buff *skb, struct genl_info *info) if (!(rdev->wiphy.flags & WIPHY_FLAG_REPORTS_OBSS)) return -EOPNOTSUPP; - if (rdev->ap_beacons_nlpid) + if (rdev->ap_beacons_nlportid) return -EBUSY; - rdev->ap_beacons_nlpid = info->snd_pid; + rdev->ap_beacons_nlportid = info->snd_portid; return 0; } @@ -7628,12 +7628,12 @@ static int nl80211_add_scan_req(struct sk_buff *msg, static int nl80211_send_scan_msg(struct sk_buff *msg, struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, - u32 pid, u32 seq, int flags, + u32 portid, u32 seq, int flags, u32 cmd) { void *hdr; - hdr = nl80211hdr_put(msg, pid, seq, flags, cmd); + hdr = nl80211hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -1; @@ -7657,11 +7657,11 @@ static int nl80211_send_sched_scan_msg(struct sk_buff *msg, struct cfg80211_registered_device *rdev, struct net_device *netdev, - u32 pid, u32 seq, int flags, u32 cmd) + u32 portid, u32 seq, int flags, u32 cmd) { void *hdr; - hdr = nl80211hdr_put(msg, pid, seq, flags, cmd); + hdr = nl80211hdr_put(msg, portid, seq, flags, cmd); if (!hdr) return -1; @@ -8370,9 +8370,9 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, struct sk_buff *msg; void *hdr; int err; - u32 nlpid = ACCESS_ONCE(wdev->ap_unexpected_nlpid); + u32 nlportid = ACCESS_ONCE(wdev->ap_unexpected_nlportid); - if (!nlpid) + if (!nlportid) return false; msg = nlmsg_new(100, gfp); @@ -8396,7 +8396,7 @@ static bool __nl80211_unexpected_frame(struct net_device *dev, u8 cmd, return true; } - genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlpid); + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); return true; nla_put_failure: @@ -8420,7 +8420,7 @@ bool nl80211_unexpected_4addr_frame(struct net_device *dev, } int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, - struct wireless_dev *wdev, u32 nlpid, + struct wireless_dev *wdev, u32 nlportid, int freq, int sig_dbm, const u8 *buf, size_t len, gfp_t gfp) { @@ -8449,7 +8449,7 @@ int nl80211_send_mgmt(struct cfg80211_registered_device *rdev, genlmsg_end(msg, hdr); - return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlpid); + return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); nla_put_failure: genlmsg_cancel(msg, hdr); @@ -8804,9 +8804,9 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy, struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); struct sk_buff *msg; void *hdr; - u32 nlpid = ACCESS_ONCE(rdev->ap_beacons_nlpid); + u32 nlportid = ACCESS_ONCE(rdev->ap_beacons_nlportid); - if (!nlpid) + if (!nlportid) return; msg = nlmsg_new(len + 100, gfp); @@ -8829,7 +8829,7 @@ void cfg80211_report_obss_beacon(struct wiphy *wiphy, genlmsg_end(msg, hdr); - genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlpid); + genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); return; nla_put_failure: @@ -8853,9 +8853,9 @@ static int nl80211_netlink_notify(struct notifier_block * nb, list_for_each_entry_rcu(rdev, &cfg80211_rdev_list, list) { list_for_each_entry_rcu(wdev, &rdev->wdev_list, list) - cfg80211_mlme_unregister_socket(wdev, notify->pid); - if (rdev->ap_beacons_nlpid == notify->pid) - rdev->ap_beacons_nlpid = 0; + cfg80211_mlme_unregister_socket(wdev, notify->portid); + if (rdev->ap_beacons_nlportid == notify->portid) + rdev->ap_beacons_nlportid = 0; } rcu_read_unlock(); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 7856c33898fa..30edad44e7fc 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -166,7 +166,7 @@ static DEFINE_SPINLOCK(xfrm_state_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); -void km_state_expired(struct xfrm_state *x, int hard, u32 pid); +void km_state_expired(struct xfrm_state *x, int hard, u32 portid); static struct xfrm_state_afinfo *xfrm_state_lock_afinfo(unsigned int family) { @@ -1674,13 +1674,13 @@ void km_state_notify(struct xfrm_state *x, const struct km_event *c) EXPORT_SYMBOL(km_policy_notify); EXPORT_SYMBOL(km_state_notify); -void km_state_expired(struct xfrm_state *x, int hard, u32 pid) +void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { struct net *net = xs_net(x); struct km_event c; c.data.hard = hard; - c.pid = pid; + c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); @@ -1726,13 +1726,13 @@ int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) } EXPORT_SYMBOL(km_new_mapping); -void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid) +void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { struct net *net = xp_net(pol); struct km_event c; c.data.hard = hard; - c.pid = pid; + c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 354070adb5ef..b313d932d678 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -603,7 +603,7 @@ static int xfrm_add_sa(struct sk_buff *skb, struct nlmsghdr *nlh, } c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; c.event = nlh->nlmsg_type; km_state_notify(x, &c); @@ -676,7 +676,7 @@ static int xfrm_del_sa(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; c.event = nlh->nlmsg_type; km_state_notify(x, &c); @@ -826,7 +826,7 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr) struct nlmsghdr *nlh; int err; - nlh = nlmsg_put(skb, NETLINK_CB(in_skb).pid, sp->nlmsg_seq, + nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq, XFRM_MSG_NEWSA, sizeof(*p), sp->nlmsg_flags); if (nlh == NULL) return -EMSGSIZE; @@ -904,7 +904,7 @@ static inline size_t xfrm_spdinfo_msgsize(void) } static int build_spdinfo(struct sk_buff *skb, struct net *net, - u32 pid, u32 seq, u32 flags) + u32 portid, u32 seq, u32 flags) { struct xfrmk_spdinfo si; struct xfrmu_spdinfo spc; @@ -913,7 +913,7 @@ static int build_spdinfo(struct sk_buff *skb, struct net *net, int err; u32 *f; - nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0); + nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSPDINFO, sizeof(u32), 0); if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; @@ -946,17 +946,17 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct sk_buff *r_skb; u32 *flags = nlmsg_data(nlh); - u32 spid = NETLINK_CB(skb).pid; + u32 sportid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; r_skb = nlmsg_new(xfrm_spdinfo_msgsize(), GFP_ATOMIC); if (r_skb == NULL) return -ENOMEM; - if (build_spdinfo(r_skb, net, spid, seq, *flags) < 0) + if (build_spdinfo(r_skb, net, sportid, seq, *flags) < 0) BUG(); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); + return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); } static inline size_t xfrm_sadinfo_msgsize(void) @@ -967,7 +967,7 @@ static inline size_t xfrm_sadinfo_msgsize(void) } static int build_sadinfo(struct sk_buff *skb, struct net *net, - u32 pid, u32 seq, u32 flags) + u32 portid, u32 seq, u32 flags) { struct xfrmk_sadinfo si; struct xfrmu_sadhinfo sh; @@ -975,7 +975,7 @@ static int build_sadinfo(struct sk_buff *skb, struct net *net, int err; u32 *f; - nlh = nlmsg_put(skb, pid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0); + nlh = nlmsg_put(skb, portid, seq, XFRM_MSG_NEWSADINFO, sizeof(u32), 0); if (nlh == NULL) /* shouldn't really happen ... */ return -EMSGSIZE; @@ -1003,17 +1003,17 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct sk_buff *r_skb; u32 *flags = nlmsg_data(nlh); - u32 spid = NETLINK_CB(skb).pid; + u32 sportid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; r_skb = nlmsg_new(xfrm_sadinfo_msgsize(), GFP_ATOMIC); if (r_skb == NULL) return -ENOMEM; - if (build_sadinfo(r_skb, net, spid, seq, *flags) < 0) + if (build_sadinfo(r_skb, net, sportid, seq, *flags) < 0) BUG(); - return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); + return nlmsg_unicast(net->xfrm.nlsk, r_skb, sportid); } static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -1033,7 +1033,7 @@ static int xfrm_get_sa(struct sk_buff *skb, struct nlmsghdr *nlh, if (IS_ERR(resp_skb)) { err = PTR_ERR(resp_skb); } else { - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).pid); + err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); } xfrm_state_put(x); out_noput: @@ -1114,7 +1114,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh, goto out; } - err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).pid); + err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid); out: xfrm_state_put(x); @@ -1401,7 +1401,7 @@ static int xfrm_add_policy(struct sk_buff *skb, struct nlmsghdr *nlh, c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; km_policy_notify(xp, p->dir, &c); xfrm_pol_put(xp); @@ -1486,7 +1486,7 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr struct nlmsghdr *nlh; int err; - nlh = nlmsg_put(skb, NETLINK_CB(in_skb).pid, sp->nlmsg_seq, + nlh = nlmsg_put(skb, NETLINK_CB(in_skb).portid, sp->nlmsg_seq, XFRM_MSG_NEWPOLICY, sizeof(*p), sp->nlmsg_flags); if (nlh == NULL) return -EMSGSIZE; @@ -1621,7 +1621,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, err = PTR_ERR(resp_skb); } else { err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, - NETLINK_CB(skb).pid); + NETLINK_CB(skb).portid); } } else { uid_t loginuid = audit_get_loginuid(current); @@ -1638,7 +1638,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, c.data.byid = p->index; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; km_policy_notify(xp, p->dir, &c); } @@ -1668,7 +1668,7 @@ static int xfrm_flush_sa(struct sk_buff *skb, struct nlmsghdr *nlh, c.data.proto = p->proto; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; c.net = net; km_state_notify(NULL, &c); @@ -1695,7 +1695,7 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct struct nlmsghdr *nlh; int err; - nlh = nlmsg_put(skb, c->pid, c->seq, XFRM_MSG_NEWAE, sizeof(*id), 0); + nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_NEWAE, sizeof(*id), 0); if (nlh == NULL) return -EMSGSIZE; @@ -1777,11 +1777,11 @@ static int xfrm_get_ae(struct sk_buff *skb, struct nlmsghdr *nlh, spin_lock_bh(&x->lock); c.data.aevent = p->flags; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; if (build_aevent(r_skb, x, &c) < 0) BUG(); - err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).pid); + err = nlmsg_unicast(net->xfrm.nlsk, r_skb, NETLINK_CB(skb).portid); spin_unlock_bh(&x->lock); xfrm_state_put(x); return err; @@ -1827,7 +1827,7 @@ static int xfrm_new_ae(struct sk_buff *skb, struct nlmsghdr *nlh, c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; c.data.aevent = XFRM_AE_CU; km_state_notify(x, &c); err = 0; @@ -1862,7 +1862,7 @@ static int xfrm_flush_policy(struct sk_buff *skb, struct nlmsghdr *nlh, c.data.type = type; c.event = nlh->nlmsg_type; c.seq = nlh->nlmsg_seq; - c.pid = nlh->nlmsg_pid; + c.portid = nlh->nlmsg_pid; c.net = net; km_policy_notify(NULL, 0, &c); return 0; @@ -2370,7 +2370,7 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct struct nlmsghdr *nlh; int err; - nlh = nlmsg_put(skb, c->pid, 0, XFRM_MSG_EXPIRE, sizeof(*ue), 0); + nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_EXPIRE, sizeof(*ue), 0); if (nlh == NULL) return -EMSGSIZE; @@ -2429,7 +2429,7 @@ static int xfrm_notify_sa_flush(const struct km_event *c) if (skb == NULL) return -ENOMEM; - nlh = nlmsg_put(skb, c->pid, c->seq, XFRM_MSG_FLUSHSA, sizeof(*p), 0); + nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHSA, sizeof(*p), 0); if (nlh == NULL) { kfree_skb(skb); return -EMSGSIZE; @@ -2497,7 +2497,7 @@ static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) if (skb == NULL) return -ENOMEM; - nlh = nlmsg_put(skb, c->pid, c->seq, c->event, headlen, 0); + nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0); err = -EMSGSIZE; if (nlh == NULL) goto out_free_skb; @@ -2696,7 +2696,7 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, struct nlmsghdr *nlh; int err; - nlh = nlmsg_put(skb, c->pid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe), 0); + nlh = nlmsg_put(skb, c->portid, 0, XFRM_MSG_POLEXPIRE, sizeof(*upe), 0); if (nlh == NULL) return -EMSGSIZE; @@ -2756,7 +2756,7 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e if (skb == NULL) return -ENOMEM; - nlh = nlmsg_put(skb, c->pid, c->seq, c->event, headlen, 0); + nlh = nlmsg_put(skb, c->portid, c->seq, c->event, headlen, 0); err = -EMSGSIZE; if (nlh == NULL) goto out_free_skb; @@ -2810,7 +2810,7 @@ static int xfrm_notify_policy_flush(const struct km_event *c) if (skb == NULL) return -ENOMEM; - nlh = nlmsg_put(skb, c->pid, c->seq, XFRM_MSG_FLUSHPOLICY, 0, 0); + nlh = nlmsg_put(skb, c->portid, c->seq, XFRM_MSG_FLUSHPOLICY, 0, 0); err = -EMSGSIZE; if (nlh == NULL) goto out_free_skb; -- cgit v1.3-14-g43fede From 6b78f16e4bdde3936b11690bdb970be423e07a07 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 13 Sep 2012 21:25:33 +0000 Subject: gre: add GSO support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add GSO support to GRE tunnels. Signed-off-by: Eric Dumazet Cc: Maciej Żenczykowski Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b062a98574f2..f233c1da2077 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -745,6 +745,10 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev __be32 dst; int mtu; + if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_help(skb)) + goto tx_error; + if (dev->type == ARPHRD_ETHER) IPCB(skb)->flags = 0; @@ -1296,6 +1300,11 @@ static void ipgre_dev_free(struct net_device *dev) free_netdev(dev); } +#define GRE_FEATURES (NETIF_F_SG | \ + NETIF_F_FRAGLIST | \ + NETIF_F_HIGHDMA | \ + NETIF_F_HW_CSUM) + static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; @@ -1309,6 +1318,9 @@ static void ipgre_tunnel_setup(struct net_device *dev) dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + + dev->features |= GRE_FEATURES; + dev->hw_features |= GRE_FEATURES; } static int ipgre_tunnel_init(struct net_device *dev) -- cgit v1.3-14-g43fede From 6b102865e7ba9ff1e3c49c32c7187bb427d91798 Mon Sep 17 00:00:00 2001 From: Amerigo Wang Date: Tue, 18 Sep 2012 16:50:11 +0000 Subject: ipv6: unify fragment thresh handling code MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Cc: Herbert Xu Cc: Michal Kubeček Cc: David Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/inet_frag.h | 2 +- net/ipv4/inet_fragment.c | 9 +++++++-- net/ipv4/ip_fragment.c | 5 ++--- net/ipv6/netfilter/nf_conntrack_reasm.c | 8 +++----- net/ipv6/reassembly.c | 16 +++++----------- 5 files changed, 18 insertions(+), 22 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 5098ee7b7e0e..32786a044718 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -61,7 +61,7 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f); void inet_frag_kill(struct inet_frag_queue *q, struct inet_frags *f); void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, int *work); -int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f); +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); diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 85190e69297b..4750d2b74d79 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -89,7 +89,7 @@ void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f) nf->low_thresh = 0; local_bh_disable(); - inet_frag_evictor(nf, f); + inet_frag_evictor(nf, f, true); local_bh_enable(); } EXPORT_SYMBOL(inet_frags_exit_net); @@ -158,11 +158,16 @@ void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f, } EXPORT_SYMBOL(inet_frag_destroy); -int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f) +int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force) { struct inet_frag_queue *q; int work, evicted = 0; + if (!force) { + if (atomic_read(&nf->mem) <= nf->high_thresh) + return 0; + } + work = atomic_read(&nf->mem) - nf->low_thresh; while (work > 0) { read_lock(&f->lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fa6a12c51066..448e68546827 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -219,7 +219,7 @@ static void ip_evictor(struct net *net) { int evicted; - evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags); + evicted = inet_frag_evictor(&net->ipv4.frags, &ip4_frags, false); if (evicted) IP_ADD_STATS_BH(net, IPSTATS_MIB_REASMFAILS, evicted); } @@ -684,8 +684,7 @@ int ip_defrag(struct sk_buff *skb, u32 user) IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Start by cleaning up the memory. */ - if (atomic_read(&net->ipv4.frags.mem) > net->ipv4.frags.high_thresh) - ip_evictor(net); + ip_evictor(net); /* Lookup (or create) queue header */ if ((qp = ip_find(net, ip_hdr(skb), user)) != NULL) { diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 54274c33a0b1..1af12fde08df 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -566,11 +566,9 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user) hdr = ipv6_hdr(clone); fhdr = (struct frag_hdr *)skb_transport_header(clone); - if (atomic_read(&net->nf_frag.frags.mem) > net->nf_frag.frags.high_thresh) { - local_bh_disable(); - inet_frag_evictor(&net->nf_frag.frags, &nf_frags); - local_bh_enable(); - } + local_bh_disable(); + inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false); + local_bh_enable(); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr); if (fq == NULL) { diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index cf74f4e79356..da8a4e301b1b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -131,15 +131,6 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_init); -static void ip6_evictor(struct net *net, struct inet6_dev *idev) -{ - int evicted; - - evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags); - if (evicted) - IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_REASMFAILS, evicted); -} - void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq, struct inet_frags *frags) { @@ -515,6 +506,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); + int evicted; IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMREQDS); @@ -539,8 +531,10 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - if (atomic_read(&net->ipv6.frags.mem) > net->ipv6.frags.high_thresh) - ip6_evictor(net, ip6_dst_idev(skb_dst(skb))); + evicted = inet_frag_evictor(&net->ipv6.frags, &ip6_frags, false); + if (evicted) + IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASMFAILS, evicted); fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr); if (fq != NULL) { -- cgit v1.3-14-g43fede From bb68b64724a4fd6b93d83b39aeffa4aadb2562fc Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Tue, 18 Sep 2012 14:19:23 +0000 Subject: ipv4: Don't add TCP-code in inet_sock_destruct Signed-off-by: Christoph Paasch Acked-by: H.K. Jerry Chu Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 ++++ net/ipv4/af_inet.c | 2 -- net/ipv4/tcp.c | 7 +++++++ 3 files changed, 11 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index ae46df590629..67c789ae719c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -574,6 +574,8 @@ static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc) return foc->len != -1; } +extern void tcp_sock_destruct(struct sock *sk); + static inline int fastopen_init_queue(struct sock *sk, int backlog) { struct request_sock_queue *queue = @@ -585,6 +587,8 @@ static inline int fastopen_init_queue(struct sock *sk, int backlog) sk->sk_allocation); if (queue->fastopenq == NULL) return -ENOMEM; + + sk->sk_destruct = tcp_sock_destruct; spin_lock_init(&queue->fastopenq->lock); } queue->fastopenq->max_qlen = backlog; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 845372b025f6..766c59658563 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -149,8 +149,6 @@ void inet_sock_destruct(struct sock *sk) pr_err("Attempt to release alive inet socket %p\n", sk); return; } - if (sk->sk_protocol == IPPROTO_TCP) - kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(atomic_read(&sk->sk_wmem_alloc)); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index df83d744e380..7b1e940393cf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2325,6 +2325,13 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); +void tcp_sock_destruct(struct sock *sk) +{ + inet_sock_destruct(sk); + + kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); +} + static inline bool tcp_can_repair_sock(const struct sock *sk) { return capable(CAP_NET_ADMIN) && -- cgit v1.3-14-g43fede From 4308fc58dceda40fac8a8d9c05b7cfba0a6bbed3 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 19 Sep 2012 15:46:06 +0100 Subject: tcp: Document use of undefined variable. Both tcp_timewait_state_process and tcp_check_req use the same basic construct of struct tcp_options received tmp_opt; tmp_opt.saw_tstamp = 0; then call tcp_parse_options However if they are fed a frame containing a TCP_SACK then tbe code behaviour is undefined because opt_rx->sack_ok is undefined data. This ought to be documented if it is intentional. Signed-off-by: Alan Cox Signed-off-by: David S. Miller --- net/ipv4/tcp_minisocks.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e965319d610b..5792577b5bc5 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -85,6 +85,8 @@ static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) * spinlock it. I do not want! Well, probability of misbehaviour * is ridiculously low and, seems, we could use some mb() tricks * to avoid misread sequence numbers, states etc. --ANK + * + * We don't need to initialize tmp_out.sack_ok as we don't use the results */ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, @@ -522,6 +524,8 @@ EXPORT_SYMBOL(tcp_create_openreq_child); * * XXX (TFO) - The current impl contains a special check for ack * validation and inside tcp_v4_reqsk_send_ack(). Can we do better? + * + * We don't need to initialize tmp_opt.sack_ok as we don't use the results */ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, -- cgit v1.3-14-g43fede From b3d54b3e406b5d6ac391590bf7524e887e8e13c3 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 21 Sep 2012 11:37:59 +0200 Subject: netfilter: combine ipt_NETMAP and ip6t_NETMAP Combine more modules since the actual code is so small anyway that the kmod metadata and the module in its loaded state totally outweighs the combined actual code size. IP_NF_TARGET_NETMAP becomes a compat option; IP6_NF_TARGET_NETMAP is completely eliminated since it has not see a release yet. Signed-off-by: Jan Engelhardt Acked-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/Kconfig | 11 ++- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/ipt_NETMAP.c | 101 ------------------------ net/ipv6/netfilter/Kconfig | 9 --- net/ipv6/netfilter/Makefile | 1 - net/ipv6/netfilter/ip6t_NETMAP.c | 94 ---------------------- net/netfilter/Kconfig | 10 +++ net/netfilter/Makefile | 1 + net/netfilter/xt_NETMAP.c | 165 +++++++++++++++++++++++++++++++++++++++ 9 files changed, 181 insertions(+), 212 deletions(-) delete mode 100644 net/ipv4/netfilter/ipt_NETMAP.c delete mode 100644 net/ipv6/netfilter/ip6t_NETMAP.c create mode 100644 net/netfilter/xt_NETMAP.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 131e53702e77..6f140084004f 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -172,12 +172,11 @@ config IP_NF_TARGET_MASQUERADE config IP_NF_TARGET_NETMAP tristate "NETMAP target support" depends on NETFILTER_ADVANCED - help - NETMAP is an implementation of static 1:1 NAT mapping of network - addresses. It maps the network address part, while keeping the host - address part intact. - - To compile it as a module, choose M here. If unsure, say N. + select NETFILTER_XT_TARGET_NETMAP + ---help--- + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_TARGET_NETMAP. config IP_NF_TARGET_REDIRECT tristate "REDIRECT target support" diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index b7dd18987237..f4446c5d6595 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o -obj-$(CONFIG_IP_NF_TARGET_NETMAP) += ipt_NETMAP.o obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c deleted file mode 100644 index 85028dc0425d..000000000000 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ /dev/null @@ -1,101 +0,0 @@ -/* NETMAP - static NAT mapping of IP network addresses (1:1). - * The mapping can be applied to source (POSTROUTING), - * destination (PREROUTING), or both (with separate rules). - */ - -/* (C) 2000-2001 Svenning Soerensen - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Svenning Soerensen "); -MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of IPv4 subnets"); - -static int netmap_tg_check(const struct xt_tgchk_param *par) -{ - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - - if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) { - pr_debug("bad MAP_IPS.\n"); - return -EINVAL; - } - if (mr->rangesize != 1) { - pr_debug("bad rangesize %u.\n", mr->rangesize); - return -EINVAL; - } - return 0; -} - -static unsigned int -netmap_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - __be32 new_ip, netmask; - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range newrange; - - NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_POST_ROUTING || - par->hooknum == NF_INET_LOCAL_OUT || - par->hooknum == NF_INET_LOCAL_IN); - ct = nf_ct_get(skb, &ctinfo); - - netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip); - - if (par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_LOCAL_OUT) - new_ip = ip_hdr(skb)->daddr & ~netmask; - else - new_ip = ip_hdr(skb)->saddr & ~netmask; - new_ip |= mr->range[0].min_ip & netmask; - - memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); - memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); - newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; - newrange.min_addr.ip = new_ip; - newrange.max_addr.ip = new_ip; - newrange.min_proto = mr->range[0].min; - newrange.max_proto = mr->range[0].max; - - /* Hand modified range to generic setup. */ - return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); -} - -static struct xt_target netmap_tg_reg __read_mostly = { - .name = "NETMAP", - .family = NFPROTO_IPV4, - .target = netmap_tg, - .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), - .table = "nat", - .hooks = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_LOCAL_IN), - .checkentry = netmap_tg_check, - .me = THIS_MODULE -}; - -static int __init netmap_tg_init(void) -{ - return xt_register_target(&netmap_tg_reg); -} - -static void __exit netmap_tg_exit(void) -{ - xt_unregister_target(&netmap_tg_reg); -} - -module_init(netmap_tg_init); -module_exit(netmap_tg_exit); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index d8f276b9fd8a..007bb450f04f 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -209,15 +209,6 @@ config IP6_NF_TARGET_MASQUERADE To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_NETMAP - tristate "NETMAP target support" - help - NETMAP is an implementation of static 1:1 NAT mapping of network - addresses. It maps the network address part, while keeping the host - address part intact. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_TARGET_REDIRECT tristate "REDIRECT target support" help diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index 5752132ca159..de8e0d11338d 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -35,7 +35,6 @@ obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o -obj-$(CONFIG_IP6_NF_TARGET_NETMAP) += ip6t_NETMAP.o obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o obj-$(CONFIG_IP6_NF_TARGET_REDIRECT) += ip6t_REDIRECT.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6t_NETMAP.c b/net/ipv6/netfilter/ip6t_NETMAP.c deleted file mode 100644 index 4f3bf360e50f..000000000000 --- a/net/ipv6/netfilter/ip6t_NETMAP.c +++ /dev/null @@ -1,94 +0,0 @@ -/* - * Copyright (c) 2011 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on Svenning Soerensen's IPv4 NETMAP target. Development of IPv6 - * NAT funded by Astaro. - */ - -#include -#include -#include -#include -#include -#include -#include - -static unsigned int -netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct nf_nat_range *range = par->targinfo; - struct nf_nat_range newrange; - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - union nf_inet_addr new_addr, netmask; - unsigned int i; - - ct = nf_ct_get(skb, &ctinfo); - for (i = 0; i < ARRAY_SIZE(range->min_addr.ip6); i++) - netmask.ip6[i] = ~(range->min_addr.ip6[i] ^ - range->max_addr.ip6[i]); - - if (par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_LOCAL_OUT) - new_addr.in6 = ipv6_hdr(skb)->daddr; - else - new_addr.in6 = ipv6_hdr(skb)->saddr; - - for (i = 0; i < ARRAY_SIZE(new_addr.ip6); i++) { - new_addr.ip6[i] &= ~netmask.ip6[i]; - new_addr.ip6[i] |= range->min_addr.ip6[i] & - netmask.ip6[i]; - } - - newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; - newrange.min_addr = new_addr; - newrange.max_addr = new_addr; - newrange.min_proto = range->min_proto; - newrange.max_proto = range->max_proto; - - return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); -} - -static int netmap_tg6_checkentry(const struct xt_tgchk_param *par) -{ - const struct nf_nat_range *range = par->targinfo; - - if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) - return -EINVAL; - return 0; -} - -static struct xt_target netmap_tg6_reg __read_mostly = { - .name = "NETMAP", - .family = NFPROTO_IPV6, - .target = netmap_tg6, - .targetsize = sizeof(struct nf_nat_range), - .table = "nat", - .hooks = (1 << NF_INET_PRE_ROUTING) | - (1 << NF_INET_POST_ROUTING) | - (1 << NF_INET_LOCAL_OUT) | - (1 << NF_INET_LOCAL_IN), - .checkentry = netmap_tg6_checkentry, - .me = THIS_MODULE, -}; - -static int __init netmap_tg6_init(void) -{ - return xt_register_target(&netmap_tg6_reg); -} - -static void netmap_tg6_exit(void) -{ - xt_unregister_target(&netmap_tg6_reg); -} - -module_init(netmap_tg6_init); -module_exit(netmap_tg6_exit); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of IPv6 subnets"); -MODULE_AUTHOR("Patrick McHardy "); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 3f4b3b4a7762..ad0e0da62ede 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -648,6 +648,16 @@ config NETFILTER_XT_TARGET_MARK (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_MARK (combined mark/MARK module). +config NETFILTER_XT_TARGET_NETMAP + tristate '"NETMAP" target support' + depends on NF_NAT + ---help--- + NETMAP is an implementation of static 1:1 NAT mapping of network + addresses. It maps the network address part, while keeping the host + address part intact. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_NFLOG tristate '"NFLOG" target support' default m if NETFILTER_ADVANCED=n diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0baa3f104fcb..600d28ba514c 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -83,6 +83,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o obj-$(CONFIG_NETFILTER_XT_TARGET_HMARK) += xt_HMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o obj-$(CONFIG_NETFILTER_XT_TARGET_LOG) += xt_LOG.o +obj-$(CONFIG_NETFILTER_XT_TARGET_NETMAP) += xt_NETMAP.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c new file mode 100644 index 000000000000..b253e07cb1c5 --- /dev/null +++ b/net/netfilter/xt_NETMAP.c @@ -0,0 +1,165 @@ +/* + * (C) 2000-2001 Svenning Soerensen + * Copyright (c) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned int +netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + struct nf_nat_range newrange; + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + union nf_inet_addr new_addr, netmask; + unsigned int i; + + ct = nf_ct_get(skb, &ctinfo); + for (i = 0; i < ARRAY_SIZE(range->min_addr.ip6); i++) + netmask.ip6[i] = ~(range->min_addr.ip6[i] ^ + range->max_addr.ip6[i]); + + if (par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT) + new_addr.in6 = ipv6_hdr(skb)->daddr; + else + new_addr.in6 = ipv6_hdr(skb)->saddr; + + for (i = 0; i < ARRAY_SIZE(new_addr.ip6); i++) { + new_addr.ip6[i] &= ~netmask.ip6[i]; + new_addr.ip6[i] |= range->min_addr.ip6[i] & + netmask.ip6[i]; + } + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr = new_addr; + newrange.max_addr = new_addr; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); +} + +static int netmap_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) + return -EINVAL; + return 0; +} + +static unsigned int +netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + __be32 new_ip, netmask; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range newrange; + + NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_POST_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT || + par->hooknum == NF_INET_LOCAL_IN); + ct = nf_ct_get(skb, &ctinfo); + + netmask = ~(mr->range[0].min_ip ^ mr->range[0].max_ip); + + if (par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT) + new_ip = ip_hdr(skb)->daddr & ~netmask; + else + new_ip = ip_hdr(skb)->saddr & ~netmask; + new_ip |= mr->range[0].min_ip & netmask; + + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = new_ip; + newrange.max_addr.ip = new_ip; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; + + /* Hand modified range to generic setup. */ + return nf_nat_setup_info(ct, &newrange, HOOK2MANIP(par->hooknum)); +} + +static int netmap_tg4_check(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) { + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; + } + if (mr->rangesize != 1) { + pr_debug("bad rangesize %u.\n", mr->rangesize); + return -EINVAL; + } + return 0; +} + +static struct xt_target netmap_tg_reg[] __read_mostly = { + { + .name = "NETMAP", + .family = NFPROTO_IPV6, + .revision = 0, + .target = netmap_tg6, + .targetsize = sizeof(struct nf_nat_range), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .checkentry = netmap_tg6_checkentry, + .me = THIS_MODULE, + }, + { + .name = "NETMAP", + .family = NFPROTO_IPV4, + .revision = 0, + .target = netmap_tg4, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_LOCAL_IN), + .checkentry = netmap_tg4_check, + .me = THIS_MODULE, + }, +}; + +static int __init netmap_tg_init(void) +{ + return xt_register_targets(netmap_tg_reg, ARRAY_SIZE(netmap_tg_reg)); +} + +static void netmap_tg_exit(void) +{ + xt_unregister_targets(netmap_tg_reg, ARRAY_SIZE(netmap_tg_reg)); +} + +module_init(netmap_tg_init); +module_exit(netmap_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of subnets"); +MODULE_AUTHOR("Patrick McHardy "); +MODULE_ALIAS("ip6t_NETMAP"); +MODULE_ALIAS("ipt_NETMAP"); -- cgit v1.3-14-g43fede From 2cbc78a29e76a2e92c172651204f3117491877d2 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Fri, 21 Sep 2012 11:41:34 +0200 Subject: netfilter: combine ipt_REDIRECT and ip6t_REDIRECT Combine more modules since the actual code is so small anyway that the kmod metadata and the module in its loaded state totally outweighs the combined actual code size. IP_NF_TARGET_REDIRECT becomes a compat option; IP6_NF_TARGET_REDIRECT is completely eliminated since it has not see a release yet. Signed-off-by: Jan Engelhardt Acked-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/Kconfig | 12 +-- net/ipv4/netfilter/Makefile | 1 - net/ipv4/netfilter/ipt_REDIRECT.c | 113 ---------------------- net/ipv6/netfilter/Kconfig | 10 -- net/ipv6/netfilter/Makefile | 1 - net/ipv6/netfilter/ip6t_REDIRECT.c | 98 ------------------- net/netfilter/Kconfig | 11 +++ net/netfilter/Makefile | 1 + net/netfilter/xt_REDIRECT.c | 190 +++++++++++++++++++++++++++++++++++++ 9 files changed, 207 insertions(+), 230 deletions(-) delete mode 100644 net/ipv4/netfilter/ipt_REDIRECT.c delete mode 100644 net/ipv6/netfilter/ip6t_REDIRECT.c create mode 100644 net/netfilter/xt_REDIRECT.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 6f140084004f..d8d6f2a5bf12 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -181,13 +181,11 @@ config IP_NF_TARGET_NETMAP config IP_NF_TARGET_REDIRECT tristate "REDIRECT target support" depends on NETFILTER_ADVANCED - help - REDIRECT is a special case of NAT: all incoming connections are - mapped onto the incoming interface's address, causing the packets to - come to the local machine instead of passing through. This is - useful for transparent proxies. - - To compile it as a module, choose M here. If unsure, say N. + select NETFILTER_XT_TARGET_REDIRECT + ---help--- + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_TARGET_REDIRECT. endif diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index f4446c5d6595..007b128eecc9 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -45,7 +45,6 @@ obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o obj-$(CONFIG_IP_NF_TARGET_ECN) += ipt_ECN.o obj-$(CONFIG_IP_NF_TARGET_MASQUERADE) += ipt_MASQUERADE.o -obj-$(CONFIG_IP_NF_TARGET_REDIRECT) += ipt_REDIRECT.o obj-$(CONFIG_IP_NF_TARGET_REJECT) += ipt_REJECT.o obj-$(CONFIG_IP_NF_TARGET_ULOG) += ipt_ULOG.o diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c deleted file mode 100644 index 11407d7d2472..000000000000 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ /dev/null @@ -1,113 +0,0 @@ -/* Redirect. Simple mapping which alters dst to a local IP address. */ -/* (C) 1999-2001 Paul `Rusty' Russell - * (C) 2002-2006 Netfilter Core Team - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Netfilter Core Team "); -MODULE_DESCRIPTION("Xtables: Connection redirection to localhost"); - -/* FIXME: Take multiple ranges --RR */ -static int redirect_tg_check(const struct xt_tgchk_param *par) -{ - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - - if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) { - pr_debug("bad MAP_IPS.\n"); - return -EINVAL; - } - if (mr->rangesize != 1) { - pr_debug("bad rangesize %u.\n", mr->rangesize); - return -EINVAL; - } - return 0; -} - -static unsigned int -redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) -{ - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; - __be32 newdst; - const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range newrange; - - NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || - par->hooknum == NF_INET_LOCAL_OUT); - - ct = nf_ct_get(skb, &ctinfo); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); - - /* Local packets: make them go to loopback */ - if (par->hooknum == NF_INET_LOCAL_OUT) - newdst = htonl(0x7F000001); - else { - struct in_device *indev; - struct in_ifaddr *ifa; - - newdst = 0; - - rcu_read_lock(); - indev = __in_dev_get_rcu(skb->dev); - if (indev && (ifa = indev->ifa_list)) - newdst = ifa->ifa_local; - rcu_read_unlock(); - - if (!newdst) - return NF_DROP; - } - - /* Transfer from original range. */ - memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); - memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); - newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; - newrange.min_addr.ip = newdst; - newrange.max_addr.ip = newdst; - newrange.min_proto = mr->range[0].min; - newrange.max_proto = mr->range[0].max; - - /* Hand modified range to generic setup. */ - return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); -} - -static struct xt_target redirect_tg_reg __read_mostly = { - .name = "REDIRECT", - .family = NFPROTO_IPV4, - .target = redirect_tg, - .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), - .table = "nat", - .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT), - .checkentry = redirect_tg_check, - .me = THIS_MODULE, -}; - -static int __init redirect_tg_init(void) -{ - return xt_register_target(&redirect_tg_reg); -} - -static void __exit redirect_tg_exit(void) -{ - xt_unregister_target(&redirect_tg_reg); -} - -module_init(redirect_tg_init); -module_exit(redirect_tg_exit); diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig index 007bb450f04f..c72532a60d88 100644 --- a/net/ipv6/netfilter/Kconfig +++ b/net/ipv6/netfilter/Kconfig @@ -209,16 +209,6 @@ config IP6_NF_TARGET_MASQUERADE To compile it as a module, choose M here. If unsure, say N. -config IP6_NF_TARGET_REDIRECT - tristate "REDIRECT target support" - help - REDIRECT is a special case of NAT: all incoming connections are - mapped onto the incoming interface's address, causing the packets to - come to the local machine instead of passing through. This is - useful for transparent proxies. - - To compile it as a module, choose M here. If unsure, say N. - config IP6_NF_TARGET_NPT tristate "NPT (Network Prefix translation) target support" help diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile index de8e0d11338d..2d11fcc2cf3c 100644 --- a/net/ipv6/netfilter/Makefile +++ b/net/ipv6/netfilter/Makefile @@ -36,5 +36,4 @@ obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o # targets obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o -obj-$(CONFIG_IP6_NF_TARGET_REDIRECT) += ip6t_REDIRECT.o obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o diff --git a/net/ipv6/netfilter/ip6t_REDIRECT.c b/net/ipv6/netfilter/ip6t_REDIRECT.c deleted file mode 100644 index 60497a3c6004..000000000000 --- a/net/ipv6/netfilter/ip6t_REDIRECT.c +++ /dev/null @@ -1,98 +0,0 @@ -/* - * Copyright (c) 2011 Patrick McHardy - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6 - * NAT funded by Astaro. - */ - -#include -#include -#include -#include -#include -#include -#include - -static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT; - -static unsigned int -redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par) -{ - const struct nf_nat_range *range = par->targinfo; - struct nf_nat_range newrange; - struct in6_addr newdst; - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - - ct = nf_ct_get(skb, &ctinfo); - if (par->hooknum == NF_INET_LOCAL_OUT) - newdst = loopback_addr; - else { - struct inet6_dev *idev; - struct inet6_ifaddr *ifa; - bool addr = false; - - rcu_read_lock(); - idev = __in6_dev_get(skb->dev); - if (idev != NULL) { - list_for_each_entry(ifa, &idev->addr_list, if_list) { - newdst = ifa->addr; - addr = true; - break; - } - } - rcu_read_unlock(); - - if (!addr) - return NF_DROP; - } - - newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; - newrange.min_addr.in6 = newdst; - newrange.max_addr.in6 = newdst; - newrange.min_proto = range->min_proto; - newrange.max_proto = range->max_proto; - - return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); -} - -static int redirect_tg6_checkentry(const struct xt_tgchk_param *par) -{ - const struct nf_nat_range *range = par->targinfo; - - if (range->flags & NF_NAT_RANGE_MAP_IPS) - return -EINVAL; - return 0; -} - -static struct xt_target redirect_tg6_reg __read_mostly = { - .name = "REDIRECT", - .family = NFPROTO_IPV6, - .checkentry = redirect_tg6_checkentry, - .target = redirect_tg6, - .targetsize = sizeof(struct nf_nat_range), - .table = "nat", - .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT), - .me = THIS_MODULE, -}; - -static int __init redirect_tg6_init(void) -{ - return xt_register_target(&redirect_tg6_reg); -} - -static void __exit redirect_tg6_exit(void) -{ - xt_unregister_target(&redirect_tg6_reg); -} - -module_init(redirect_tg6_init); -module_exit(redirect_tg6_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy "); -MODULE_DESCRIPTION("Xtables: Connection redirection to localhost"); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index ad0e0da62ede..fefa514b9917 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -690,6 +690,17 @@ config NETFILTER_XT_TARGET_RATEEST To compile it as a module, choose M here. If unsure, say N. +config NETFILTER_XT_TARGET_REDIRECT + tristate "REDIRECT target support" + depends on NF_NAT + ---help--- + REDIRECT is a special case of NAT: all incoming connections are + mapped onto the incoming interface's address, causing the packets to + come to the local machine instead of passing through. This is + useful for transparent proxies. + + To compile it as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_TEE tristate '"TEE" - packet cloning to alternate destination' depends on NETFILTER_ADVANCED diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 600d28ba514c..32596978df1d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -87,6 +87,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_NETMAP) += xt_NETMAP.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o obj-$(CONFIG_NETFILTER_XT_TARGET_RATEEST) += xt_RATEEST.o +obj-$(CONFIG_NETFILTER_XT_TARGET_REDIRECT) += xt_REDIRECT.o obj-$(CONFIG_NETFILTER_XT_TARGET_SECMARK) += xt_SECMARK.o obj-$(CONFIG_NETFILTER_XT_TARGET_TPROXY) += xt_TPROXY.o obj-$(CONFIG_NETFILTER_XT_TARGET_TCPMSS) += xt_TCPMSS.o diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c new file mode 100644 index 000000000000..22a10309297c --- /dev/null +++ b/net/netfilter/xt_REDIRECT.c @@ -0,0 +1,190 @@ +/* + * (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2006 Netfilter Core Team + * Copyright (c) 2011 Patrick McHardy + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Based on Rusty Russell's IPv4 REDIRECT target. Development of IPv6 + * NAT funded by Astaro. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT; + +static unsigned int +redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + struct nf_nat_range newrange; + struct in6_addr newdst; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + if (par->hooknum == NF_INET_LOCAL_OUT) + newdst = loopback_addr; + else { + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + bool addr = false; + + rcu_read_lock(); + idev = __in6_dev_get(skb->dev); + if (idev != NULL) { + list_for_each_entry(ifa, &idev->addr_list, if_list) { + newdst = ifa->addr; + addr = true; + break; + } + } + rcu_read_unlock(); + + if (!addr) + return NF_DROP; + } + + newrange.flags = range->flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.in6 = newdst; + newrange.max_addr.in6 = newdst; + newrange.min_proto = range->min_proto; + newrange.max_proto = range->max_proto; + + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); +} + +static int redirect_tg6_checkentry(const struct xt_tgchk_param *par) +{ + const struct nf_nat_range *range = par->targinfo; + + if (range->flags & NF_NAT_RANGE_MAP_IPS) + return -EINVAL; + return 0; +} + +/* FIXME: Take multiple ranges --RR */ +static int redirect_tg4_check(const struct xt_tgchk_param *par) +{ + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + + if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) { + pr_debug("bad MAP_IPS.\n"); + return -EINVAL; + } + if (mr->rangesize != 1) { + pr_debug("bad rangesize %u.\n", mr->rangesize); + return -EINVAL; + } + return 0; +} + +static unsigned int +redirect_tg4(struct sk_buff *skb, const struct xt_action_param *par) +{ + struct nf_conn *ct; + enum ip_conntrack_info ctinfo; + __be32 newdst; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_range newrange; + + NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || + par->hooknum == NF_INET_LOCAL_OUT); + + ct = nf_ct_get(skb, &ctinfo); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); + + /* Local packets: make them go to loopback */ + if (par->hooknum == NF_INET_LOCAL_OUT) + newdst = htonl(0x7F000001); + else { + struct in_device *indev; + struct in_ifaddr *ifa; + + newdst = 0; + + rcu_read_lock(); + indev = __in_dev_get_rcu(skb->dev); + if (indev && (ifa = indev->ifa_list)) + newdst = ifa->ifa_local; + rcu_read_unlock(); + + if (!newdst) + return NF_DROP; + } + + /* Transfer from original range. */ + memset(&newrange.min_addr, 0, sizeof(newrange.min_addr)); + memset(&newrange.max_addr, 0, sizeof(newrange.max_addr)); + newrange.flags = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS; + newrange.min_addr.ip = newdst; + newrange.max_addr.ip = newdst; + newrange.min_proto = mr->range[0].min; + newrange.max_proto = mr->range[0].max; + + /* Hand modified range to generic setup. */ + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); +} + +static struct xt_target redirect_tg_reg[] __read_mostly = { + { + .name = "REDIRECT", + .family = NFPROTO_IPV6, + .revision = 0, + .table = "nat", + .checkentry = redirect_tg6_checkentry, + .target = redirect_tg6, + .targetsize = sizeof(struct nf_nat_range), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, + { + .name = "REDIRECT", + .family = NFPROTO_IPV4, + .revision = 0, + .table = "nat", + .target = redirect_tg4, + .checkentry = redirect_tg4_check, + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, +}; + +static int __init redirect_tg_init(void) +{ + return xt_register_targets(redirect_tg_reg, + ARRAY_SIZE(redirect_tg_reg)); +} + +static void __exit redirect_tg_exit(void) +{ + xt_unregister_targets(redirect_tg_reg, ARRAY_SIZE(redirect_tg_reg)); +} + +module_init(redirect_tg_init); +module_exit(redirect_tg_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick McHardy "); +MODULE_DESCRIPTION("Xtables: Connection redirection to localhost"); +MODULE_ALIAS("ip6t_REDIRECT"); +MODULE_ALIAS("ipt_REDIRECT"); -- cgit v1.3-14-g43fede From 5e953778a2aab04929a5e7b69f53dc26e39b079e Mon Sep 17 00:00:00 2001 From: Christoph Fritz Date: Fri, 21 Sep 2012 08:31:19 +0000 Subject: ipconfig: add nameserver IPs to kernel-parameter ip= On small systems (e.g. embedded ones) IP addresses are often configured by bootloaders and get assigned to kernel via parameter "ip=". If set to "ip=dhcp", even nameserver entries from DHCP daemons are handled. These entries exported in /proc/net/pnp are commonly linked by /etc/resolv.conf. To configure nameservers for networks without DHCP, this patch adds option and to kernel-parameter 'ip='. Signed-off-by: Christoph Fritz Tested-by: Jan Weitzel Signed-off-by: David S. Miller --- Documentation/filesystems/nfs/nfsroot.txt | 10 +++++++- net/ipv4/ipconfig.c | 39 ++++++++++++++++++++++++++++--- 2 files changed, 45 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index ffdd9d866ad7..2d66ed688125 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -78,7 +78,8 @@ nfsroot=[:][,] flags = hard, nointr, noposix, cto, ac -ip=:::::: +ip=::::::: + : This parameter tells the kernel how to configure IP addresses of devices and also how to set up the IP routing table. It was originally called @@ -158,6 +159,13 @@ ip=:::::: Default: any + IP address of first nameserver. + Value gets exported by /proc/net/pnp which is often linked + on embedded systems by /etc/resolv.conf. + + IP address of secound nameserver. + Same as above. + nfsrootdebug diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 67e8a6b086ea..1c0e7e051044 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -743,14 +743,22 @@ static void __init ic_bootp_init_ext(u8 *e) /* - * Initialize the DHCP/BOOTP mechanism. + * Predefine Nameservers */ -static inline void __init ic_bootp_init(void) +static inline void __init ic_nameservers_predef(void) { int i; for (i = 0; i < CONF_NAMESERVERS_MAX; i++) ic_nameservers[i] = NONE; +} + +/* + * Initialize the DHCP/BOOTP mechanism. + */ +static inline void __init ic_bootp_init(void) +{ + ic_nameservers_predef(); dev_add_pack(&bootp_packet_type); } @@ -1379,6 +1387,7 @@ static int __init ip_auto_config(void) int retries = CONF_OPEN_RETRIES; #endif int err; + unsigned int i; #ifdef CONFIG_PROC_FS proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops); @@ -1499,7 +1508,15 @@ static int __init ip_auto_config(void) &ic_servaddr, &root_server_addr, root_server_path); if (ic_dev_mtu) pr_cont(", mtu=%d", ic_dev_mtu); - pr_cont("\n"); + for (i = 0; i < CONF_NAMESERVERS_MAX; i++) + if (ic_nameservers[i] != NONE) { + pr_info(" nameserver%u=%pI4", + i, &ic_nameservers[i]); + break; + } + for (i++; i < CONF_NAMESERVERS_MAX; i++) + if (ic_nameservers[i] != NONE) + pr_cont(", nameserver%u=%pI4\n", i, &ic_nameservers[i]); #endif /* !SILENT */ return 0; @@ -1570,6 +1587,8 @@ static int __init ip_auto_config_setup(char *addrs) return 1; } + ic_nameservers_predef(); + /* Parse string for static IP assignment. */ ip = addrs; while (ip && *ip) { @@ -1613,6 +1632,20 @@ static int __init ip_auto_config_setup(char *addrs) ic_enable = 0; } break; + case 7: + if (CONF_NAMESERVERS_MAX >= 1) { + ic_nameservers[0] = in_aton(ip); + if (ic_nameservers[0] == ANY) + ic_nameservers[0] = NONE; + } + break; + case 8: + if (CONF_NAMESERVERS_MAX >= 2) { + ic_nameservers[1] = in_aton(ip); + if (ic_nameservers[1] == ANY) + ic_nameservers[1] = NONE; + } + break; } } ip = cp; -- cgit v1.3-14-g43fede From 623df484a777f3c00c1ea3d6a7565b8d8ac688a1 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 22 Sep 2012 04:18:54 +0000 Subject: tcp: extract code to compute SYNACK RTT In preparation for adding another spot where we compute the SYNACK RTT, extract this code so that it can be shared. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 9 +++++++++ net/ipv4/tcp_ipv4.c | 4 +--- net/ipv6/tcp_ipv6.c | 4 +--- 3 files changed, 11 insertions(+), 6 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index a8cb00c0c6d9..a718d0e3d8e7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1137,6 +1137,15 @@ static inline void tcp_openreq_init(struct request_sock *req, ireq->loc_port = tcp_hdr(skb)->dest; } +/* Compute time elapsed between SYNACK and the ACK completing 3WHS */ +static inline void tcp_synack_rtt_meas(struct sock *sk, + struct request_sock *req) +{ + if (tcp_rsk(req)->snt_synack) + tcp_valid_rtt_meas(sk, + tcp_time_stamp - tcp_rsk(req)->snt_synack); +} + extern void tcp_enter_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index e64abed249cc..1e66f7fb4fe6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1733,9 +1733,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - if (tcp_rsk(req)->snt_synack) - tcp_valid_rtt_meas(newsk, - tcp_time_stamp - tcp_rsk(req)->snt_synack); + tcp_synack_rtt_meas(newsk, req); newtp->total_retrans = req->retrans; #ifdef CONFIG_TCP_MD5SIG diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f3bfb8bbfdec..cfeeeb7fcf54 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1348,9 +1348,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - if (tcp_rsk(req)->snt_synack) - tcp_valid_rtt_meas(newsk, - tcp_time_stamp - tcp_rsk(req)->snt_synack); + tcp_synack_rtt_meas(newsk, req); newtp->total_retrans = req->retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; -- cgit v1.3-14-g43fede From 016818d076871c4ee34db1e8d74dc17ac1de626a Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 22 Sep 2012 04:18:55 +0000 Subject: tcp: TCP Fast Open Server - take SYNACK RTT after completing 3WHS When taking SYNACK RTT samples for servers using TCP Fast Open, fix the code to ensure that we only call tcp_valid_rtt_meas() after we receive the ACK that completes the 3-way handshake. Previously we were always taking an RTT sample in tcp_v4_syn_recv_sock(). However, for TCP Fast Open connections tcp_v4_conn_req_fastopen() calls tcp_v4_syn_recv_sock() at the time we receive the SYN. So for TFO we must wait until tcp_rcv_state_process() to take the RTT sample. To fix this, we wait until after TFO calls tcp_v4_syn_recv_sock() before we set the snt_synack timestamp, since tcp_synack_rtt_meas() already ensures that we only take a SYNACK RTT sample if snt_synack is non-zero. To be careful, we only take a snt_synack timestamp when a SYNACK transmit or retransmit succeeds. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 1 + net/ipv4/tcp_ipv4.c | 12 +++++++++--- net/ipv6/tcp_ipv6.c | 2 +- 4 files changed, 12 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index a718d0e3d8e7..6feeccd83dd7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1125,6 +1125,7 @@ static inline void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + tcp_rsk(req)->snt_synack = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; ireq->tstamp_ok = rx_opt->tstamp_ok; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e2bec815ff23..bb326684495b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5983,6 +5983,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * need req so release it. */ if (req) { + tcp_synack_rtt_meas(sk, req); reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 1e66f7fb4fe6..0a7e020f16b5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -868,6 +868,8 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, ireq->rmt_addr, ireq->opt); err = net_xmit_eval(err); + if (!tcp_rsk(req)->snt_synack && !err) + tcp_rsk(req)->snt_synack = tcp_time_stamp; } return err; @@ -1382,6 +1384,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const struct inet_request_sock *ireq = inet_rsk(req); struct sock *child; + int err; req->retrans = 0; req->sk = NULL; @@ -1393,8 +1396,11 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk, kfree_skb(skb_synack); return -1; } - ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr, - ireq->rmt_addr, ireq->opt); + err = ip_build_and_send_pkt(skb_synack, sk, ireq->loc_addr, + ireq->rmt_addr, ireq->opt); + err = net_xmit_eval(err); + if (!err) + tcp_rsk(req)->snt_synack = tcp_time_stamp; /* XXX (TFO) - is it ok to ignore error and continue? */ spin_lock(&queue->fastopenq->lock); @@ -1612,7 +1618,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v4_init_sequence(skb); } tcp_rsk(req)->snt_isn = isn; - tcp_rsk(req)->snt_synack = tcp_time_stamp; if (dst == NULL) { dst = inet_csk_route_req(sk, &fl4, req); @@ -1650,6 +1655,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (err || want_cookie) goto drop_and_free; + tcp_rsk(req)->snt_synack = tcp_time_stamp; tcp_rsk(req)->listener = NULL; /* Add the request_sock to the SYN table */ inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index cfeeeb7fcf54..d6212d6bc8d8 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1169,7 +1169,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) } have_isn: tcp_rsk(req)->snt_isn = isn; - tcp_rsk(req)->snt_synack = tcp_time_stamp; if (security_inet_conn_request(sk, skb, req)) goto drop_and_release; @@ -1180,6 +1179,7 @@ have_isn: want_cookie) goto drop_and_free; + tcp_rsk(req)->snt_synack = tcp_time_stamp; tcp_rsk(req)->listener = NULL; inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); return 0; -- cgit v1.3-14-g43fede From 072539880156fafd86c753070e598c23e8e74586 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 22 Sep 2012 04:18:56 +0000 Subject: tcp: TCP Fast Open Server - note timestamps and retransmits for SYNACK RTT Previously, when using TCP Fast Open a server would return from tcp_check_req() before updating snt_synack based on TCP timestamp echo replies and whether or not we've retransmitted the SYNACK. The result was that (a) for TFO connections using timestamps we used an incorrect baseline SYNACK send time (tcp_time_stamp of SYNACK send instead of rcv_tsecr), and (b) for TFO connections that do not have TCP timestamps but retransmit the SYNACK we took a SYNACK RTT sample when we should not take a sample. This fix merely moves the snt_synack update logic a bit earlier in the function, so that connections using TCP Fast Open will properly do these updates when the ACK for the SYNACK arrives. Moving this snt_synack update logic means that with TCP_DEFER_ACCEPT enabled we do a few instructions of wasted work on each bare ACK, but that seems OK. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_minisocks.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 5792577b5bc5..27536ba16c9d 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -692,6 +692,12 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; + /* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */ + if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) + tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; + else if (req->retrans) /* don't take RTT sample if retrans && ~TS */ + tcp_rsk(req)->snt_synack = 0; + /* For Fast Open no more processing is needed (sk is the * child socket). */ @@ -705,10 +711,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP); return NULL; } - if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) - tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; - else if (req->retrans) /* don't take RTT sample if retrans && ~TS */ - tcp_rsk(req)->snt_synack = 0; /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all -- cgit v1.3-14-g43fede From e69bebde46b5ddfb7d8f17cae66031e282ebc464 Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 22 Sep 2012 04:18:57 +0000 Subject: tcp: TCP Fast Open Server - call tcp_validate_incoming() for all packets A TCP Fast Open (TFO) passive connection must call both tcp_check_req() and tcp_validate_incoming() for all incoming ACKs that are attempting to complete the 3WHS. This is needed to parallel all the action that happens for a non-TFO connection, where for an ACK that is attempting to complete the 3WHS we call both tcp_check_req() and tcp_validate_incoming(). For example, upon receiving the ACK that completes the 3WHS, we need to call tcp_fast_parse_options() and update ts_recent based on the incoming timestamp value in the ACK. One symptom of the problem with the previous code was that for passive TFO connections using TCP timestamps, the outgoing TS ecr values ignored the incoming TS val value on the ACK that completed the 3WHS. Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bb326684495b..36e069a1f47b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5969,7 +5969,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (tcp_check_req(sk, skb, req, NULL, true) == NULL) goto discard; - } else if (!tcp_validate_incoming(sk, skb, th, 0)) + } + if (!tcp_validate_incoming(sk, skb, th, 0)) return 0; /* step 5: check the ACK field */ -- cgit v1.3-14-g43fede From 30099b2e9b3a1f88250d31472edf2b6d6f0a7d8b Mon Sep 17 00:00:00 2001 From: Neal Cardwell Date: Sat, 22 Sep 2012 17:03:47 +0000 Subject: tcp: TCP Fast Open Server - record retransmits after 3WHS When recording the number of SYNACK retransmits for servers using TCP Fast Open, fix the code to ensure that we copy over the retransmit count from the request_sock after we receive the ACK that completes the 3-way handshake. The story here is similar to that of SYNACK RTT measurements. Previously we were always doing this in tcp_v4_syn_recv_sock(). However, for TCP Fast Open connections tcp_v4_conn_req_fastopen() calls tcp_v4_syn_recv_sock() at the time we receive the SYN. So for TFO we must copy the final SYNACK retransmit count in tcp_rcv_state_process(). Note that copying over the SYNACK retransmit count will give us the correct count since, as is mentioned in a comment in tcp_retransmit_timer(), before we receive an ACK for our SYN-ACK a TFO passive connection does not retransmit anything else (e.g., data or FIN segments). Signed-off-by: Neal Cardwell Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 36e069a1f47b..e037697c3b77 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5985,6 +5985,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, */ if (req) { tcp_synack_rtt_meas(sk, req); + tp->total_retrans = req->retrans; + reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for -- cgit v1.3-14-g43fede From 5640f7685831e088fe6c2e1f863a6805962f8e81 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 23 Sep 2012 23:04:42 +0000 Subject: net: use a per task frag allocator We currently use a per socket order-0 page cache for tcp_sendmsg() operations. This page is used to build fragments for skbs. Its done to increase probability of coalescing small write() into single segments in skbs still in write queue (not yet sent) But it wastes a lot of memory for applications handling many mostly idle sockets, since each socket holds one page in sk->sk_sndmsg_page Its also quite inefficient to build TSO 64KB packets, because we need about 16 pages per skb on arches where PAGE_SIZE = 4096, so we hit page allocator more than wanted. This patch adds a per task frag allocator and uses bigger pages, if available. An automatic fallback is done in case of memory pressure. (up to 32768 bytes per frag, thats order-3 pages on x86) This increases TCP stream performance by 20% on loopback device, but also benefits on other network devices, since 8x less frags are mapped on transmit and unmapped on tx completion. Alexander Duyck mentioned a probable performance win on systems with IOMMU enabled. Its possible some SG enabled hardware cant cope with bigger fragments, but their ndo_start_xmit() should already handle this, splitting a fragment in sub fragments, since some arches have PAGE_SIZE=65536 Successfully tested on various ethernet devices. (ixgbe, igb, bnx2x, tg3, mellanox mlx4) Signed-off-by: Eric Dumazet Cc: Ben Hutchings Cc: Vijay Subramanian Cc: Alexander Duyck Tested-by: Vijay Subramanian Signed-off-by: David S. Miller --- include/linux/sched.h | 3 ++ include/net/inet_sock.h | 4 +-- include/net/sock.h | 27 +++++++++-------- kernel/exit.c | 3 ++ kernel/fork.c | 1 + net/core/skbuff.c | 37 ++++++----------------- net/core/sock.c | 49 ++++++++++++++++++++++++++++-- net/ipv4/ip_output.c | 70 ++++++++++++++++++------------------------- net/ipv4/raw.c | 19 +++++++----- net/ipv4/tcp.c | 79 ++++++++++++++----------------------------------- net/ipv4/tcp_ipv4.c | 8 ----- net/ipv6/ip6_output.c | 65 ++++++++++++++++------------------------ net/sched/em_meta.c | 2 +- 13 files changed, 167 insertions(+), 200 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8c86648a2f9..a8e2413f6bc3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1530,6 +1530,9 @@ struct task_struct { * cache last used pipe for splice */ struct pipe_inode_info *splice_pipe; + + struct page_frag task_frag; + #ifdef CONFIG_TASK_DELAY_ACCT struct task_delay_info *delays; #endif diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 613cfa401672..256c1ed2d69a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -101,10 +101,8 @@ struct inet_cork { __be32 addr; struct ip_options *opt; unsigned int fragsize; - struct dst_entry *dst; int length; /* Total length of all frames */ - struct page *page; - u32 off; + struct dst_entry *dst; u8 tx_flags; }; diff --git a/include/net/sock.h b/include/net/sock.h index 84bdaeca1314..f036493b9a61 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -247,8 +247,7 @@ struct cg_proto; * @sk_stamp: time stamp of last packet received * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data - * @sk_sndmsg_page: cached page for sendmsg - * @sk_sndmsg_off: cached offset for sendmsg + * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit * @sk_security: used by security modules @@ -362,9 +361,8 @@ struct sock { ktime_t sk_stamp; struct socket *sk_socket; void *sk_user_data; - struct page *sk_sndmsg_page; + struct page_frag sk_frag; struct sk_buff *sk_send_head; - __u32 sk_sndmsg_off; __s32 sk_peek_off; int sk_write_pending; #ifdef CONFIG_SECURITY @@ -2034,18 +2032,23 @@ static inline void sk_stream_moderate_sndbuf(struct sock *sk) struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp); -static inline struct page *sk_stream_alloc_page(struct sock *sk) +/** + * sk_page_frag - return an appropriate page_frag + * @sk: socket + * + * If socket allocation mode allows current thread to sleep, it means its + * safe to use the per task page_frag instead of the per socket one. + */ +static inline struct page_frag *sk_page_frag(struct sock *sk) { - struct page *page = NULL; + if (sk->sk_allocation & __GFP_WAIT) + return ¤t->task_frag; - page = alloc_pages(sk->sk_allocation, 0); - if (!page) { - sk_enter_memory_pressure(sk); - sk_stream_moderate_sndbuf(sk); - } - return page; + return &sk->sk_frag; } +extern bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); + /* * Default write policy as shown to user space via poll/select/SIGIO */ diff --git a/kernel/exit.c b/kernel/exit.c index f65345f9e5bb..42f25952edd9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1046,6 +1046,9 @@ void do_exit(long code) if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); + if (tsk->task_frag.page) + put_page(tsk->task_frag.page); + validate_creds_for_do_exit(tsk); preempt_disable(); diff --git a/kernel/fork.c b/kernel/fork.c index 2c8857e12855..01565b9ce0f3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -330,6 +330,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; + tsk->task_frag.page = NULL; account_kernel_stack(ti, 1); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index fe00d1208167..2ede3cfa8ffa 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1655,38 +1655,19 @@ static struct page *linear_to_page(struct page *page, unsigned int *len, unsigned int *offset, struct sk_buff *skb, struct sock *sk) { - struct page *p = sk->sk_sndmsg_page; - unsigned int off; + struct page_frag *pfrag = sk_page_frag(sk); - if (!p) { -new_page: - p = sk->sk_sndmsg_page = alloc_pages(sk->sk_allocation, 0); - if (!p) - return NULL; - - off = sk->sk_sndmsg_off = 0; - /* hold one ref to this page until it's full */ - } else { - unsigned int mlen; - - /* If we are the only user of the page, we can reset offset */ - if (page_count(p) == 1) - sk->sk_sndmsg_off = 0; - off = sk->sk_sndmsg_off; - mlen = PAGE_SIZE - off; - if (mlen < 64 && mlen < *len) { - put_page(p); - goto new_page; - } + if (!sk_page_frag_refill(sk, pfrag)) + return NULL; - *len = min_t(unsigned int, *len, mlen); - } + *len = min_t(unsigned int, *len, pfrag->size - pfrag->offset); - memcpy(page_address(p) + off, page_address(page) + *offset, *len); - sk->sk_sndmsg_off += *len; - *offset = off; + memcpy(page_address(pfrag->page) + pfrag->offset, + page_address(page) + *offset, *len); + *offset = pfrag->offset; + pfrag->offset += *len; - return p; + return pfrag->page; } static bool spd_can_coalesce(const struct splice_pipe_desc *spd, diff --git a/net/core/sock.c b/net/core/sock.c index 2693f7649222..727114cd6f7e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1744,6 +1744,45 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, } EXPORT_SYMBOL(sock_alloc_send_skb); +/* On 32bit arches, an skb frag is limited to 2^15 */ +#define SKB_FRAG_PAGE_ORDER get_order(32768) + +bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) +{ + int order; + + if (pfrag->page) { + if (atomic_read(&pfrag->page->_count) == 1) { + pfrag->offset = 0; + return true; + } + if (pfrag->offset < pfrag->size) + return true; + put_page(pfrag->page); + } + + /* We restrict high order allocations to users that can afford to wait */ + order = (sk->sk_allocation & __GFP_WAIT) ? SKB_FRAG_PAGE_ORDER : 0; + + do { + gfp_t gfp = sk->sk_allocation; + + if (order) + gfp |= __GFP_COMP | __GFP_NOWARN; + pfrag->page = alloc_pages(gfp, order); + if (likely(pfrag->page)) { + pfrag->offset = 0; + pfrag->size = PAGE_SIZE << order; + return true; + } + } while (--order >= 0); + + sk_enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return false; +} +EXPORT_SYMBOL(sk_page_frag_refill); + static void __lock_sock(struct sock *sk) __releases(&sk->sk_lock.slock) __acquires(&sk->sk_lock.slock) @@ -2173,8 +2212,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_error_report = sock_def_error_report; sk->sk_destruct = sock_def_destruct; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; + sk->sk_frag.page = NULL; + sk->sk_frag.offset = 0; sk->sk_peek_off = -1; sk->sk_peer_pid = NULL; @@ -2417,6 +2456,12 @@ void sk_common_release(struct sock *sk) xfrm_sk_free_policy(sk); sk_refcnt_debug_release(sk); + + if (sk->sk_frag.page) { + put_page(sk->sk_frag.page); + sk->sk_frag.page = NULL; + } + sock_put(sk); } EXPORT_SYMBOL(sk_common_release); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a5beab1dc958..24a29a39e9a8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -793,6 +793,7 @@ static int __ip_append_data(struct sock *sk, struct flowi4 *fl4, struct sk_buff_head *queue, struct inet_cork *cork, + struct page_frag *pfrag, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, @@ -987,47 +988,30 @@ alloc_new_skb: } } else { int i = skb_shinfo(skb)->nr_frags; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1]; - struct page *page = cork->page; - int off = cork->off; - unsigned int left; - - if (page && (left = PAGE_SIZE - off) > 0) { - if (copy >= left) - copy = left; - if (page != skb_frag_page(frag)) { - if (i == MAX_SKB_FRAGS) { - err = -EMSGSIZE; - goto error; - } - skb_fill_page_desc(skb, i, page, off, 0); - skb_frag_ref(skb, i); - frag = &skb_shinfo(skb)->frags[i]; - } - } else if (i < MAX_SKB_FRAGS) { - if (copy > PAGE_SIZE) - copy = PAGE_SIZE; - page = alloc_pages(sk->sk_allocation, 0); - if (page == NULL) { - err = -ENOMEM; - goto error; - } - cork->page = page; - cork->off = 0; - skb_fill_page_desc(skb, i, page, 0, 0); - frag = &skb_shinfo(skb)->frags[i]; - } else { - err = -EMSGSIZE; - goto error; - } - if (getfrag(from, skb_frag_address(frag)+skb_frag_size(frag), - offset, copy, skb->len, skb) < 0) { - err = -EFAULT; + err = -ENOMEM; + if (!sk_page_frag_refill(sk, pfrag)) goto error; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + err = -EMSGSIZE; + if (i == MAX_SKB_FRAGS) + goto error; + + __skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, 0); + skb_shinfo(skb)->nr_frags = ++i; + get_page(pfrag->page); } - cork->off += copy; - skb_frag_size_add(frag, copy); + copy = min_t(int, copy, pfrag->size - pfrag->offset); + if (getfrag(from, + page_address(pfrag->page) + pfrag->offset, + offset, copy, skb->len, skb) < 0) + goto error_efault; + + pfrag->offset += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -1039,6 +1023,8 @@ alloc_new_skb: return 0; +error_efault: + err = -EFAULT; error: cork->length -= length; IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTDISCARDS); @@ -1079,8 +1065,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->dst = &rt->dst; cork->length = 0; cork->tx_flags = ipc->tx_flags; - cork->page = NULL; - cork->off = 0; return 0; } @@ -1117,7 +1101,8 @@ int ip_append_data(struct sock *sk, struct flowi4 *fl4, transhdrlen = 0; } - return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, getfrag, + return __ip_append_data(sk, fl4, &sk->sk_write_queue, &inet->cork.base, + sk_page_frag(sk), getfrag, from, length, transhdrlen, flags); } @@ -1439,7 +1424,8 @@ struct sk_buff *ip_make_skb(struct sock *sk, if (err) return ERR_PTR(err); - err = __ip_append_data(sk, fl4, &queue, &cork, getfrag, + err = __ip_append_data(sk, fl4, &queue, &cork, + ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { __ip_flush_pending_frames(sk, &queue, &cork); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index f2425785d40a..a80740ba4248 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -131,18 +131,23 @@ found: * 0 - deliver * 1 - block */ -static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb) +static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) { - int type; - - if (!pskb_may_pull(skb, sizeof(struct icmphdr))) + struct icmphdr _hdr; + const struct icmphdr *hdr; + + pr_err("icmp_filter skb_transport_offset %d data-head %ld len %d/%d\n", + skb_transport_offset(skb), skb->data - skb->head, skb->len, skb->data_len); + hdr = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_hdr), &_hdr); + pr_err("head %p data %p hdr %p type %d\n", skb->head, skb->data, hdr, hdr ? hdr->type : -1); + if (!hdr) return 1; - type = icmp_hdr(skb)->type; - if (type < 32) { + if (hdr->type < 32) { __u32 data = raw_sk(sk)->filter.data; - return ((1 << type) & data) != 0; + return ((1U << hdr->type) & data) != 0; } /* Do not block unknown ICMP types */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 7b1e940393cf..72ea4752f21b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1150,78 +1150,43 @@ new_segment: if (err) goto do_fault; } else { - bool merge = false; + bool merge = true; int i = skb_shinfo(skb)->nr_frags; - struct page *page = sk->sk_sndmsg_page; - int off; - - if (page && page_count(page) == 1) - sk->sk_sndmsg_off = 0; - - off = sk->sk_sndmsg_off; - - if (skb_can_coalesce(skb, i, page, off) && - off != PAGE_SIZE) { - /* We can extend the last page - * fragment. */ - merge = true; - } else if (i == MAX_SKB_FRAGS || !sg) { - /* Need to add new fragment and cannot - * do this because interface is non-SG, - * or because all the page slots are - * busy. */ - tcp_mark_push(tp, skb); - goto new_segment; - } else if (page) { - if (off == PAGE_SIZE) { - put_page(page); - sk->sk_sndmsg_page = page = NULL; - off = 0; + struct page_frag *pfrag = sk_page_frag(sk); + + if (!sk_page_frag_refill(sk, pfrag)) + goto wait_for_memory; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + if (i == MAX_SKB_FRAGS || !sg) { + tcp_mark_push(tp, skb); + goto new_segment; } - } else - off = 0; + merge = false; + } - if (copy > PAGE_SIZE - off) - copy = PAGE_SIZE - off; + copy = min_t(int, copy, pfrag->size - pfrag->offset); if (!sk_wmem_schedule(sk, copy)) goto wait_for_memory; - if (!page) { - /* Allocate new cache page. */ - if (!(page = sk_stream_alloc_page(sk))) - goto wait_for_memory; - } - - /* Time to copy data. We are close to - * the end! */ err = skb_copy_to_page_nocache(sk, from, skb, - page, off, copy); - if (err) { - /* If this page was new, give it to the - * socket so it does not get leaked. - */ - if (!sk->sk_sndmsg_page) { - sk->sk_sndmsg_page = page; - sk->sk_sndmsg_off = 0; - } + pfrag->page, + pfrag->offset, + copy); + if (err) goto do_error; - } /* Update the skb. */ if (merge) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { - skb_fill_page_desc(skb, i, page, off, copy); - if (sk->sk_sndmsg_page) { - get_page(page); - } else if (off + copy < PAGE_SIZE) { - get_page(page); - sk->sk_sndmsg_page = page; - } + skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, copy); + get_page(pfrag->page); } - - sk->sk_sndmsg_off = off + copy; + pfrag->offset += copy; } if (!copied) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0a7e020f16b5..93406c583f43 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2200,14 +2200,6 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - /* - * If sendmsg cached page exists, toss it. - */ - if (sk->sk_sndmsg_page) { - __free_page(sk->sk_sndmsg_page); - sk->sk_sndmsg_page = NULL; - } - /* TCP Cookie Transactions */ if (tp->cookie_values != NULL) { kref_put(&tp->cookie_values->kref, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 3dd4a37488d5..aece3e792f84 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1279,8 +1279,6 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, if (dst_allfrag(rt->dst.path)) cork->flags |= IPCORK_ALLFRAG; cork->length = 0; - sk->sk_sndmsg_page = NULL; - sk->sk_sndmsg_off = 0; exthdrlen = (opt ? opt->opt_flen : 0) - rt->rt6i_nfheader_len; length += exthdrlen; transhdrlen += exthdrlen; @@ -1504,48 +1502,31 @@ alloc_new_skb: } } else { int i = skb_shinfo(skb)->nr_frags; - skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1]; - struct page *page = sk->sk_sndmsg_page; - int off = sk->sk_sndmsg_off; - unsigned int left; - - if (page && (left = PAGE_SIZE - off) > 0) { - if (copy >= left) - copy = left; - if (page != skb_frag_page(frag)) { - if (i == MAX_SKB_FRAGS) { - err = -EMSGSIZE; - goto error; - } - skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0); - skb_frag_ref(skb, i); - frag = &skb_shinfo(skb)->frags[i]; - } - } else if(i < MAX_SKB_FRAGS) { - if (copy > PAGE_SIZE) - copy = PAGE_SIZE; - page = alloc_pages(sk->sk_allocation, 0); - if (page == NULL) { - err = -ENOMEM; - goto error; - } - sk->sk_sndmsg_page = page; - sk->sk_sndmsg_off = 0; + struct page_frag *pfrag = sk_page_frag(sk); - skb_fill_page_desc(skb, i, page, 0, 0); - frag = &skb_shinfo(skb)->frags[i]; - } else { - err = -EMSGSIZE; + err = -ENOMEM; + if (!sk_page_frag_refill(sk, pfrag)) goto error; + + if (!skb_can_coalesce(skb, i, pfrag->page, + pfrag->offset)) { + err = -EMSGSIZE; + if (i == MAX_SKB_FRAGS) + goto error; + + __skb_fill_page_desc(skb, i, pfrag->page, + pfrag->offset, 0); + skb_shinfo(skb)->nr_frags = ++i; + get_page(pfrag->page); } + copy = min_t(int, copy, pfrag->size - pfrag->offset); if (getfrag(from, - skb_frag_address(frag) + skb_frag_size(frag), - offset, copy, skb->len, skb) < 0) { - err = -EFAULT; - goto error; - } - sk->sk_sndmsg_off += copy; - skb_frag_size_add(frag, copy); + page_address(pfrag->page) + pfrag->offset, + offset, copy, skb->len, skb) < 0) + goto error_efault; + + pfrag->offset += copy; + skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); skb->len += copy; skb->data_len += copy; skb->truesize += copy; @@ -1554,7 +1535,11 @@ alloc_new_skb: offset += copy; length -= copy; } + return 0; + +error_efault: + err = -EFAULT; error: cork->length -= length; IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 4ab6e3325573..7c3de6ffa516 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -461,7 +461,7 @@ META_COLLECTOR(int_sk_sndtimeo) META_COLLECTOR(int_sk_sendmsg_off) { SKIP_NONLOCAL(skb); - dst->value = skb->sk->sk_sndmsg_off; + dst->value = skb->sk->sk_frag.offset; } META_COLLECTOR(int_sk_write_pend) -- cgit v1.3-14-g43fede From 8489c1d9a80e6263fb71de5bc7f39773712cfa7e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Sep 2012 08:21:16 +0200 Subject: net: raw: revert unrelated change Commit 5640f7685831 ("net: use a per task frag allocator") accidentally contained an unrelated change to net/ipv4/raw.c, later committed (without the pr_err() debugging bits) in net tree as commit ab43ed8b749 (ipv4: raw: fix icmp_filter()) This patch reverts this glitch, noticed by Stephen Rothwell. Reported-by: Stephen Rothwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/raw.c | 19 +++++++------------ 1 file changed, 7 insertions(+), 12 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index a80740ba4248..f2425785d40a 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -131,23 +131,18 @@ found: * 0 - deliver * 1 - block */ -static int icmp_filter(const struct sock *sk, const struct sk_buff *skb) +static __inline__ int icmp_filter(struct sock *sk, struct sk_buff *skb) { - struct icmphdr _hdr; - const struct icmphdr *hdr; - - pr_err("icmp_filter skb_transport_offset %d data-head %ld len %d/%d\n", - skb_transport_offset(skb), skb->data - skb->head, skb->len, skb->data_len); - hdr = skb_header_pointer(skb, skb_transport_offset(skb), - sizeof(_hdr), &_hdr); - pr_err("head %p data %p hdr %p type %d\n", skb->head, skb->data, hdr, hdr ? hdr->type : -1); - if (!hdr) + int type; + + if (!pskb_may_pull(skb, sizeof(struct icmphdr))) return 1; - if (hdr->type < 32) { + type = icmp_hdr(skb)->type; + if (type < 32) { __u32 data = raw_sk(sk)->filter.data; - return ((1U << hdr->type) & data) != 0; + return ((1 << type) & data) != 0; } /* Do not block unknown ICMP types */ -- cgit v1.3-14-g43fede From 842b08bbee448b2069aaebb7f18b40942ad2a1bd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 24 Sep 2012 22:09:58 +0000 Subject: ipconfig: fix trivial build error The commit 5e953778a2aab04929a5e7b69f53dc26e39b079e ("ipconfig: add nameserver IPs to kernel-parameter ip=") introduces ic_nameservers_predef() that defined only for BOOTP. However it is used by ip_auto_config_setup() as well. This patch moves it outside of #ifdef BOOTP. Signed-off-by: Andy Shevchenko Cc: Christoph Fritz Cc: David S. Miller Signed-off-by: David S. Miller --- net/ipv4/ipconfig.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 1c0e7e051044..798358b10717 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -582,6 +582,17 @@ static void __init ic_rarp_send_if(struct ic_device *d) } #endif +/* + * Predefine Nameservers + */ +static inline void __init ic_nameservers_predef(void) +{ + int i; + + for (i = 0; i < CONF_NAMESERVERS_MAX; i++) + ic_nameservers[i] = NONE; +} + /* * DHCP/BOOTP support. */ @@ -742,17 +753,6 @@ static void __init ic_bootp_init_ext(u8 *e) } -/* - * Predefine Nameservers - */ -static inline void __init ic_nameservers_predef(void) -{ - int i; - - for (i = 0; i < CONF_NAMESERVERS_MAX; i++) - ic_nameservers[i] = NONE; -} - /* * Initialize the DHCP/BOOTP mechanism. */ -- cgit v1.3-14-g43fede From d208328765a0ab425e36b5b828285f3337a85451 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 24 Sep 2012 18:12:23 +0000 Subject: gre: fix handling of key 0 GRE driver incorrectly uses zero as a flag value. Zero is a perfectly valid value for key, and the tunnel should match packets with no key only with tunnels created without key, and vice versa. This is a slightly visible change since previously it might be possible to construct a working tunnel that sent key 0 and received only because of the key wildcard of zero. I.e the sender sent key of zero, but tunnel was defined without key. Note: using gre key 0 requires iproute2 utilities v3.2 or later. The original utility code was broken as well. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 44 ++++++++++++++++++++++++++++++++++---------- 1 file changed, 34 insertions(+), 10 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index f233c1da2077..0d4c3832d490 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -214,11 +214,25 @@ static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, return tot; } +/* Does key in tunnel parameters match packet */ +static bool ipgre_key_match(const struct ip_tunnel_parm *p, + __u32 flags, __be32 key) +{ + if (p->i_flags & GRE_KEY) { + if (flags & GRE_KEY) + return key == p->i_key; + else + return false; /* key expected, none present */ + } else + return !(flags & GRE_KEY); +} + /* Given src, dst and key, find appropriate for input tunnel. */ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, __be32 remote, __be32 local, - __be32 key, __be16 gre_proto) + __u32 flags, __be32 key, + __be16 gre_proto) { struct net *net = dev_net(dev); int link = dev->ifindex; @@ -233,10 +247,12 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || - key != t->parms.i_key || !(t->dev->flags & IFF_UP)) continue; + if (!ipgre_key_match(&t->parms, flags, key)) + continue; + if (t->dev->type != ARPHRD_IPGRE && t->dev->type != dev_type) continue; @@ -257,10 +273,12 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { if (remote != t->parms.iph.daddr || - key != t->parms.i_key || !(t->dev->flags & IFF_UP)) continue; + if (!ipgre_key_match(&t->parms, flags, key)) + continue; + if (t->dev->type != ARPHRD_IPGRE && t->dev->type != dev_type) continue; @@ -283,10 +301,12 @@ static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, if ((local != t->parms.iph.saddr && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) || - key != t->parms.i_key || !(t->dev->flags & IFF_UP)) continue; + if (!ipgre_key_match(&t->parms, flags, key)) + continue; + if (t->dev->type != ARPHRD_IPGRE && t->dev->type != dev_type) continue; @@ -489,6 +509,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; __be16 flags; + __be32 key = 0; flags = p[0]; if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) { @@ -505,6 +526,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info) if (skb_headlen(skb) < grehlen) return; + if (flags & GRE_KEY) + key = *(((__be32 *)p) + (grehlen / 4) - 1); + switch (type) { default: case ICMP_PARAMETERPROB: @@ -535,9 +559,8 @@ static void ipgre_err(struct sk_buff *skb, u32 info) rcu_read_lock(); t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr, - flags & GRE_KEY ? - *(((__be32 *)p) + (grehlen / 4) - 1) : 0, - p[1]); + flags, key, p[1]); + if (t == NULL) goto out; @@ -642,9 +665,10 @@ static int ipgre_rcv(struct sk_buff *skb) gre_proto = *(__be16 *)(h + 2); rcu_read_lock(); - if ((tunnel = ipgre_tunnel_lookup(skb->dev, - iph->saddr, iph->daddr, key, - gre_proto))) { + tunnel = ipgre_tunnel_lookup(skb->dev, + iph->saddr, iph->daddr, flags, key, + gre_proto); + if (tunnel) { struct pcpu_tstats *tstats; secpath_reset(skb); -- cgit v1.3-14-g43fede From 0c5794a66c7c6443759e6098841767958a031187 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 24 Sep 2012 18:12:24 +0000 Subject: gre: remove unnecessary rcu_read_lock/unlock The gre function pointers for receive and error handling are always called (from gre.c) with rcu_read_lock already held. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 21 +++++++-------------- net/ipv6/ip6_gre.c | 14 +++----------- 2 files changed, 10 insertions(+), 25 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 0d4c3832d490..1c012cb2cb94 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -557,37 +557,34 @@ static void ipgre_err(struct sk_buff *skb, u32 info) break; } - rcu_read_lock(); t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr, flags, key, p[1]); if (t == NULL) - goto out; + return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, t->parms.link, 0, IPPROTO_GRE, 0); - goto out; + return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0, IPPROTO_GRE, 0); - goto out; + return; } if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) - goto out; + return; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) - goto out; + return; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; -out: - rcu_read_unlock(); } static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb) @@ -625,7 +622,7 @@ static int ipgre_rcv(struct sk_buff *skb) __be16 gre_proto; if (!pskb_may_pull(skb, 16)) - goto drop_nolock; + goto drop; iph = ip_hdr(skb); h = skb->data; @@ -636,7 +633,7 @@ static int ipgre_rcv(struct sk_buff *skb) - We do not support routing headers. */ if (flags&(GRE_VERSION|GRE_ROUTING)) - goto drop_nolock; + goto drop; if (flags&GRE_CSUM) { switch (skb->ip_summed) { @@ -664,7 +661,6 @@ static int ipgre_rcv(struct sk_buff *skb) gre_proto = *(__be16 *)(h + 2); - rcu_read_lock(); tunnel = ipgre_tunnel_lookup(skb->dev, iph->saddr, iph->daddr, flags, key, gre_proto); @@ -740,14 +736,11 @@ static int ipgre_rcv(struct sk_buff *skb) netif_rx(skb); - rcu_read_unlock(); return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: - rcu_read_unlock(); -drop_nolock: kfree_skb(skb); return 0; } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 424d11a4e7ff..b987d4db790f 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -437,14 +437,12 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6h = (const struct ipv6hdr *)skb->data; p = (__be16 *)(skb->data + offset); - rcu_read_lock(); - t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, flags & GRE_KEY ? *(((__be32 *)p) + (grehlen / 4) - 1) : 0, p[1]); if (t == NULL) - goto out; + return; switch (type) { __u32 teli; @@ -489,8 +487,6 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, else t->err_count = 1; t->err_time = jiffies; -out: - rcu_read_unlock(); } static inline void ip6gre_ecn_decapsulate_ipv4(const struct ip6_tnl *t, @@ -528,7 +524,7 @@ static int ip6gre_rcv(struct sk_buff *skb) __be16 gre_proto; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) - goto drop_nolock; + goto drop; ipv6h = ipv6_hdr(skb); h = skb->data; @@ -539,7 +535,7 @@ static int ip6gre_rcv(struct sk_buff *skb) - We do not support routing headers. */ if (flags&(GRE_VERSION|GRE_ROUTING)) - goto drop_nolock; + goto drop; if (flags&GRE_CSUM) { switch (skb->ip_summed) { @@ -567,7 +563,6 @@ static int ip6gre_rcv(struct sk_buff *skb) gre_proto = *(__be16 *)(h + 2); - rcu_read_lock(); tunnel = ip6gre_tunnel_lookup(skb->dev, &ipv6h->saddr, &ipv6h->daddr, key, gre_proto); @@ -646,14 +641,11 @@ static int ip6gre_rcv(struct sk_buff *skb) netif_rx(skb); - rcu_read_unlock(); return 0; } icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: - rcu_read_unlock(); -drop_nolock: kfree_skb(skb); return 0; } -- cgit v1.3-14-g43fede From b0558ef24a792906914fcad277f3befe2420e618 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 24 Sep 2012 18:12:25 +0000 Subject: xfrm: remove extranous rcu_read_lock The handlers for xfrm_tunnel are always invoked with rcu read lock already. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/ip_vti.c | 5 ----- net/ipv4/ipip.c | 9 +-------- net/ipv6/sit.c | 6 ------ 3 files changed, 1 insertion(+), 19 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 3511ffba7bd4..978bca4818ae 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -304,7 +304,6 @@ static int vti_err(struct sk_buff *skb, u32 info) err = -ENOENT; - rcu_read_lock(); t = vti_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); if (t == NULL) goto out; @@ -326,7 +325,6 @@ static int vti_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - rcu_read_unlock(); return err; } @@ -336,7 +334,6 @@ static int vti_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); - rcu_read_lock(); tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); if (tunnel != NULL) { struct pcpu_tstats *tstats; @@ -348,10 +345,8 @@ static int vti_rcv(struct sk_buff *skb) u64_stats_update_end(&tstats->syncp); skb->dev = tunnel->dev; - rcu_read_unlock(); return 1; } - rcu_read_unlock(); return -1; } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 99af1f0cc658..618bde867ac1 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -365,8 +365,6 @@ static int ipip_err(struct sk_buff *skb, u32 info) } err = -ENOENT; - - rcu_read_lock(); t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); if (t == NULL) goto out; @@ -398,7 +396,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - rcu_read_unlock(); + return err; } @@ -416,13 +414,11 @@ static int ipip_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); - rcu_read_lock(); tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); if (tunnel != NULL) { struct pcpu_tstats *tstats; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -445,11 +441,8 @@ static int ipip_rcv(struct sk_buff *skb) ipip_ecn_decapsulate(iph, skb); netif_rx(skb); - - rcu_read_unlock(); return 0; } - rcu_read_unlock(); return -1; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3bd1bfc01f85..3ed54ffd8d50 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -545,7 +545,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - rcu_read_lock(); t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, @@ -579,7 +578,6 @@ static int ipip6_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - rcu_read_unlock(); return err; } @@ -599,7 +597,6 @@ static int ipip6_rcv(struct sk_buff *skb) iph = ip_hdr(skb); - rcu_read_lock(); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -615,7 +612,6 @@ static int ipip6_rcv(struct sk_buff *skb) if ((tunnel->dev->priv_flags & IFF_ISATAP) && !isatap_chksrc(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; - rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -630,12 +626,10 @@ static int ipip6_rcv(struct sk_buff *skb) netif_rx(skb); - rcu_read_unlock(); return 0; } /* no tunnel matched, let upstream know, ipsec may handle it */ - rcu_read_unlock(); return 1; out: kfree_skb(skb); -- cgit v1.3-14-g43fede From eccc1bb8d4b4cf68d3c9becb083fa94ada7d495c Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Tue, 25 Sep 2012 11:02:48 +0000 Subject: tunnel: drop packet if ECN present with not-ECT Linux tunnels were written before RFC6040 and therefore never implemented the corner case of ECN getting set in the outer header and the inner header not being ready for it. Section 4.2. Default Tunnel Egress Behaviour. o If the inner ECN field is Not-ECT, the decapsulator MUST NOT propagate any other ECN codepoint onwards. This is because the inner Not-ECT marking is set by transports that rely on dropped packets as an indication of congestion and would not understand or respond to any other ECN codepoint [RFC4774]. Specifically: * If the inner ECN field is Not-ECT and the outer ECN field is CE, the decapsulator MUST drop the packet. * If the inner ECN field is Not-ECT and the outer ECN field is Not-ECT, ECT(0), or ECT(1), the decapsulator MUST forward the outgoing packet with the ECN field cleared to Not-ECT. This patch moves the ECN decap logic out of the individual tunnels into a common place. It also adds logging to allow detecting broken systems that set ECN bits incorrectly when tunneling (or an intermediate router might be changing the header). Overloads rx_frame_error to keep track of ECN related error. Thanks to Chris Wright who caught this while reviewing the new VXLAN tunnel. This code was tested by injecting faulty logic in other end GRE to send incorrectly encapsulated packets. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- include/net/inet_ecn.h | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/ip_gre.c | 38 ++++++++++++++----------- net/ipv4/ipip.c | 42 +++++++++++++++++----------- net/ipv6/ip6_gre.c | 54 ++++++++++++++++------------------- 4 files changed, 147 insertions(+), 63 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index 2fa14691869c..aab73757bc4d 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -15,6 +15,8 @@ enum { INET_ECN_MASK = 3, }; +extern int sysctl_tunnel_ecn_log; + static inline int INET_ECN_is_ce(__u8 dsfield) { return (dsfield & INET_ECN_MASK) == INET_ECN_CE; @@ -145,4 +147,78 @@ static inline int INET_ECN_set_ce(struct sk_buff *skb) return 0; } +/* + * RFC 6080 4.2 + * To decapsulate the inner header at the tunnel egress, a compliant + * tunnel egress MUST set the outgoing ECN field to the codepoint at the + * intersection of the appropriate arriving inner header (row) and outer + * header (column) in Figure 4 + * + * +---------+------------------------------------------------+ + * |Arriving | Arriving Outer Header | + * | Inner +---------+------------+------------+------------+ + * | Header | Not-ECT | ECT(0) | ECT(1) | CE | + * +---------+---------+------------+------------+------------+ + * | Not-ECT | Not-ECT |Not-ECT(!!!)|Not-ECT(!!!)| (!!!)| + * | ECT(0) | ECT(0) | ECT(0) | ECT(1) | CE | + * | ECT(1) | ECT(1) | ECT(1) (!) | ECT(1) | CE | + * | CE | CE | CE | CE(!!!)| CE | + * +---------+---------+------------+------------+------------+ + * + * Figure 4: New IP in IP Decapsulation Behaviour + * + * returns 0 on success + * 1 if something is broken and should be logged (!!! above) + * 2 if packet should be dropped + */ +static inline int INET_ECN_decapsulate(struct sk_buff *skb, + __u8 outer, __u8 inner) +{ + if (INET_ECN_is_not_ect(inner)) { + switch (outer & INET_ECN_MASK) { + case INET_ECN_NOT_ECT: + return 0; + case INET_ECN_ECT_0: + case INET_ECN_ECT_1: + return 1; + case INET_ECN_CE: + return 2; + } + } + + if (INET_ECN_is_ce(outer)) + INET_ECN_set_ce(skb); + + return 0; +} + +static inline int IP_ECN_decapsulate(const struct iphdr *oiph, + struct sk_buff *skb) +{ + __u8 inner; + + if (skb->protocol == htons(ETH_P_IP)) + inner = ip_hdr(skb)->tos; + else if (skb->protocol == htons(ETH_P_IPV6)) + inner = ipv6_get_dsfield(ipv6_hdr(skb)); + else + return 0; + + return INET_ECN_decapsulate(skb, oiph->tos, inner); +} + +static inline int IP6_ECN_decapsulate(const struct ipv6hdr *oipv6h, + struct sk_buff *skb) +{ + __u8 inner; + + if (skb->protocol == htons(ETH_P_IP)) + inner = ip_hdr(skb)->tos; + else if (skb->protocol == htons(ETH_P_IPV6)) + inner = ipv6_get_dsfield(ipv6_hdr(skb)); + else + return 0; + + return INET_ECN_decapsulate(skb, ipv6_get_dsfield(oipv6h), inner); +} #endif diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 1c012cb2cb94..ef0b861ce044 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -120,6 +120,10 @@ Alexey Kuznetsov. */ +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + static struct rtnl_link_ops ipgre_link_ops __read_mostly; static int ipgre_tunnel_init(struct net_device *dev); static void ipgre_tunnel_setup(struct net_device *dev); @@ -204,7 +208,9 @@ static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, tot->rx_crc_errors = dev->stats.rx_crc_errors; tot->rx_fifo_errors = dev->stats.rx_fifo_errors; tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; tot->tx_carrier_errors = dev->stats.tx_carrier_errors; tot->tx_dropped = dev->stats.tx_dropped; @@ -587,17 +593,6 @@ static void ipgre_err(struct sk_buff *skb, u32 info) t->err_time = jiffies; } -static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb) -{ - if (INET_ECN_is_ce(iph->tos)) { - if (skb->protocol == htons(ETH_P_IP)) { - IP_ECN_set_ce(ip_hdr(skb)); - } else if (skb->protocol == htons(ETH_P_IPV6)) { - IP6_ECN_set_ce(ipv6_hdr(skb)); - } - } -} - static inline u8 ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb) { @@ -620,6 +615,7 @@ static int ipgre_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; int offset = 4; __be16 gre_proto; + int err; if (!pskb_may_pull(skb, 16)) goto drop; @@ -723,17 +719,27 @@ static int ipgre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } + __skb_tunnel_rx(skb, tunnel->dev); + + skb_reset_network_header(skb); + err = IP_ECN_decapsulate(iph, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &iph->saddr, iph->tos); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto drop; + } + } + tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - __skb_tunnel_rx(skb, tunnel->dev); - - skb_reset_network_header(skb); - ipgre_ecn_decapsulate(iph, skb); - netif_rx(skb); return 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 618bde867ac1..e15b45297c09 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -120,6 +120,10 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + static int ipip_net_id __read_mostly; struct ipip_net { struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; @@ -400,28 +404,18 @@ out: return err; } -static inline void ipip_ecn_decapsulate(const struct iphdr *outer_iph, - struct sk_buff *skb) -{ - struct iphdr *inner_iph = ip_hdr(skb); - - if (INET_ECN_is_ce(outer_iph->tos)) - IP_ECN_set_ce(inner_iph); -} - static int ipip_rcv(struct sk_buff *skb) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); + int err; tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); if (tunnel != NULL) { struct pcpu_tstats *tstats; - if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - kfree_skb(skb); - return 0; - } + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; secpath_reset(skb); @@ -430,21 +424,35 @@ static int ipip_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); skb->pkt_type = PACKET_HOST; + __skb_tunnel_rx(skb, tunnel->dev); + + err = IP_ECN_decapsulate(iph, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", + &iph->saddr, iph->tos); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto drop; + } + } + tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - __skb_tunnel_rx(skb, tunnel->dev); - - ipip_ecn_decapsulate(iph, skb); - netif_rx(skb); return 0; } return -1; + +drop: + kfree_skb(skb); + return 0; } /* diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index b987d4db790f..613a16647741 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -56,6 +56,10 @@ #include +static bool log_ecn_error = true; +module_param(log_ecn_error, bool, 0644); +MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); + #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 @@ -149,7 +153,9 @@ static struct rtnl_link_stats64 *ip6gre_get_stats64(struct net_device *dev, tot->rx_crc_errors = dev->stats.rx_crc_errors; tot->rx_fifo_errors = dev->stats.rx_fifo_errors; tot->rx_length_errors = dev->stats.rx_length_errors; + tot->rx_frame_errors = dev->stats.rx_frame_errors; tot->rx_errors = dev->stats.rx_errors; + tot->tx_fifo_errors = dev->stats.tx_fifo_errors; tot->tx_carrier_errors = dev->stats.tx_carrier_errors; tot->tx_dropped = dev->stats.tx_dropped; @@ -489,28 +495,6 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, t->err_time = jiffies; } -static inline void ip6gre_ecn_decapsulate_ipv4(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, struct sk_buff *skb) -{ - __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; - - if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) - ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); - - if (INET_ECN_is_ce(dsfield)) - IP_ECN_set_ce(ip_hdr(skb)); -} - -static inline void ip6gre_ecn_decapsulate_ipv6(const struct ip6_tnl *t, - const struct ipv6hdr *ipv6h, struct sk_buff *skb) -{ - if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) - ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); - - if (INET_ECN_is_ce(ipv6_get_dsfield(ipv6h))) - IP6_ECN_set_ce(ipv6_hdr(skb)); -} - static int ip6gre_rcv(struct sk_buff *skb) { const struct ipv6hdr *ipv6h; @@ -522,6 +506,7 @@ static int ip6gre_rcv(struct sk_buff *skb) struct ip6_tnl *tunnel; int offset = 4; __be16 gre_proto; + int err; if (!pskb_may_pull(skb, sizeof(struct in6_addr))) goto drop; @@ -625,20 +610,29 @@ static int ip6gre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } + __skb_tunnel_rx(skb, tunnel->dev); + + skb_reset_network_header(skb); + + err = IP6_ECN_decapsulate(ipv6h, skb); + if (unlikely(err)) { + if (log_ecn_error) + net_info_ratelimited("non-ECT from %pI6 with dsfield=%#x\n", + &ipv6h->saddr, + ipv6_get_dsfield(ipv6h)); + if (err > 1) { + ++tunnel->dev->stats.rx_frame_errors; + ++tunnel->dev->stats.rx_errors; + goto drop; + } + } + tstats = this_cpu_ptr(tunnel->dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - __skb_tunnel_rx(skb, tunnel->dev); - - skb_reset_network_header(skb); - if (skb->protocol == htons(ETH_P_IP)) - ip6gre_ecn_decapsulate_ipv4(tunnel, ipv6h, skb); - else if (skb->protocol == htons(ETH_P_IPV6)) - ip6gre_ecn_decapsulate_ipv6(tunnel, ipv6h, skb); - netif_rx(skb); return 0; -- cgit v1.3-14-g43fede From 5dff747b7038d10f9c174a1245263fd1c36a644d Mon Sep 17 00:00:00 2001 From: Christoph Paasch Date: Wed, 26 Sep 2012 11:59:09 +0000 Subject: tcp: Remove unused parameter from tcp_v4_save_options struct sock *sk is not used inside tcp_v4_save_options. Thus it can be removed. Signed-off-by: Christoph Paasch Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 93406c583f43..385eb79cf6aa 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -925,8 +925,7 @@ EXPORT_SYMBOL(tcp_syn_flood_action); /* * Save and compile IPv4 options into the request_sock if needed. */ -static struct ip_options_rcu *tcp_v4_save_options(struct sock *sk, - struct sk_buff *skb) +static struct ip_options_rcu *tcp_v4_save_options(struct sk_buff *skb) { const struct ip_options *opt = &(IPCB(skb)->opt); struct ip_options_rcu *dopt = NULL; @@ -1568,7 +1567,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq->loc_addr = daddr; ireq->rmt_addr = saddr; ireq->no_srccheck = inet_sk(sk)->transparent; - ireq->opt = tcp_v4_save_options(sk, skb); + ireq->opt = tcp_v4_save_options(skb); if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; -- cgit v1.3-14-g43fede From 861b650101eb0c627d171eb18de81dddb93d395e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Sep 2012 02:14:53 +0000 Subject: tcp: gro: add checksuming helpers skb with CHECKSUM_NONE cant currently be handled by GRO, and we notice this deep in GRO stack in tcp[46]_gro_receive() But there are cases where GRO can be a benefit, even with a lack of checksums. This preliminary work is needed to add GRO support to tunnels. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 19 ++++++++++++++++--- net/ipv6/tcp_ipv6.c | 20 +++++++++++++++++--- 2 files changed, 33 insertions(+), 6 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 385eb79cf6aa..75735c9a6a9d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2803,6 +2803,8 @@ void tcp4_proc_exit(void) struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) { const struct iphdr *iph = skb_gro_network_header(skb); + __wsum wsum; + __sum16 sum; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -2811,11 +2813,22 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) skb->ip_summed = CHECKSUM_UNNECESSARY; break; } - - /* fall through */ - case CHECKSUM_NONE: +flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; + + case CHECKSUM_NONE: + wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb_gro_len(skb), IPPROTO_TCP, 0); + sum = csum_fold(skb_checksum(skb, + skb_gro_offset(skb), + skb_gro_len(skb), + wsum)); + if (sum) + goto flush; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; } return tcp_gro_receive(head, skb); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d6212d6bc8d8..49c890386ce9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -763,6 +763,8 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, struct sk_buff *skb) { const struct ipv6hdr *iph = skb_gro_network_header(skb); + __wsum wsum; + __sum16 sum; switch (skb->ip_summed) { case CHECKSUM_COMPLETE: @@ -771,11 +773,23 @@ static struct sk_buff **tcp6_gro_receive(struct sk_buff **head, skb->ip_summed = CHECKSUM_UNNECESSARY; break; } - - /* fall through */ - case CHECKSUM_NONE: +flush: NAPI_GRO_CB(skb)->flush = 1; return NULL; + + case CHECKSUM_NONE: + wsum = ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), + IPPROTO_TCP, 0)); + sum = csum_fold(skb_checksum(skb, + skb_gro_offset(skb), + skb_gro_len(skb), + wsum)); + if (sum) + goto flush; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; } return tcp_gro_receive(head, skb); -- cgit v1.3-14-g43fede From 60769a5dcd8755715c7143b4571d5c44f01796f1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 27 Sep 2012 02:48:50 +0000 Subject: ipv4: gre: add GRO capability Add GRO capability to IPv4 GRE tunnels, using the gro_cells infrastructure. Tested using IPv4 and IPv6 TCP traffic inside this tunnel, and checking GRO is building large packets. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/ipip.h | 3 +++ net/ipv4/ip_gre.c | 13 +++++++++++-- 2 files changed, 14 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/ipip.h b/include/net/ipip.h index a93cf6d7e94b..ddc077c51f32 100644 --- a/include/net/ipip.h +++ b/include/net/ipip.h @@ -2,6 +2,7 @@ #define __NET_IPIP_H 1 #include +#include #include /* Keep error state on tunnel for 30 sec */ @@ -36,6 +37,8 @@ struct ip_tunnel { #endif struct ip_tunnel_prl_entry __rcu *prl; /* potential router list */ unsigned int prl_count; /* # of entries in PRL */ + + struct gro_cells gro_cells; }; struct ip_tunnel_prl_entry { diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index ef0b861ce044..b1871d993d22 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -740,8 +740,7 @@ static int ipgre_rcv(struct sk_buff *skb) tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); - netif_rx(skb); - + gro_cells_receive(&tunnel->gro_cells, skb); return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -1319,6 +1318,9 @@ static const struct net_device_ops ipgre_netdev_ops = { static void ipgre_dev_free(struct net_device *dev) { + struct ip_tunnel *tunnel = netdev_priv(dev); + + gro_cells_destroy(&tunnel->gro_cells); free_percpu(dev->tstats); free_netdev(dev); } @@ -1350,6 +1352,7 @@ static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; struct iphdr *iph; + int err; tunnel = netdev_priv(dev); iph = &tunnel->parms.iph; @@ -1376,6 +1379,12 @@ static int ipgre_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; + err = gro_cells_init(&tunnel->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + return 0; } -- cgit v1.3-14-g43fede From 9fbef059d63cbc3249a3ddfd9a12cb511c8be55e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 1 Oct 2012 05:21:14 +0000 Subject: gre: fix sparse warning Use be16 consistently when looking at flags. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index b1871d993d22..7240f8e2dd45 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -222,7 +222,7 @@ static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev, /* Does key in tunnel parameters match packet */ static bool ipgre_key_match(const struct ip_tunnel_parm *p, - __u32 flags, __be32 key) + __be16 flags, __be32 key) { if (p->i_flags & GRE_KEY) { if (flags & GRE_KEY) @@ -237,7 +237,7 @@ static bool ipgre_key_match(const struct ip_tunnel_parm *p, static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev, __be32 remote, __be32 local, - __u32 flags, __be32 key, + __be16 flags, __be32 key, __be16 gre_proto) { struct net *net = dev_net(dev); -- cgit v1.3-14-g43fede From 193ba924524e6afe192217982b2c2d67e4715d33 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 1 Oct 2012 12:32:34 +0000 Subject: igmp: export symbol ip_mc_leave_group Needed for VXLAN. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/igmp.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv4') diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 3479b98a00a7..736ab70fd179 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1904,6 +1904,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_unlock(); return ret; } +EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) -- cgit v1.3-14-g43fede