1 files changed, 77 insertions, 40 deletions

diff --git a/include/net/ip.h b/include/net/ip.h
index 19adacd5ece0..69d5cef46004 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -33,6 +33,7 @@
 #include <net/flow_dissector.h>
 #include <net/netns/hash.h>
 #include <net/lwtunnel.h>
+#include <net/inet_dscp.h>
 
 #define IPV4_MAX_PMTU		65535U		/* RFC 2675, Section 5.1 */
 #define IPV4_MIN_MTU		68			/* RFC 791 */
@@ -57,6 +58,8 @@ struct inet_skb_parm {
 #define IPSKB_FRAG_PMTU		BIT(6)
 #define IPSKB_L3SLAVE		BIT(7)
 #define IPSKB_NOPOLICY		BIT(8)
+#define IPSKB_MULTIPATH		BIT(9)
+#define IPSKB_MCROUTE		BIT(10)
 
 	u16			frag_max_size;
 };
@@ -79,7 +82,6 @@ struct ipcm_cookie {
 	__u8			protocol;
 	__u8			ttl;
 	__s16			tos;
-	char			priority;
 	__u16			gso_size;
 };
 
@@ -91,10 +93,12 @@ static inline void ipcm_init(struct ipcm_cookie *ipcm)
 static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 				const struct inet_sock *inet)
 {
-	ipcm_init(ipcm);
+	*ipcm = (struct ipcm_cookie) {
+		.tos = READ_ONCE(inet->tos),
+	};
+
+	sockcm_init(&ipcm->sockc, &inet->sk);
 
-	ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
-	ipcm->sockc.tsflags = inet->sk.sk_tsflags;
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
 	ipcm->protocol = inet->inet_num;
@@ -164,6 +168,7 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 int ip_local_deliver(struct sk_buff *skb);
 void ip_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int proto);
 int ip_mr_input(struct sk_buff *skb);
+int ip_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
@@ -255,14 +260,9 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
 	return RT_SCOPE_UNIVERSE;
 }
 
-static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
-{
-	return (ipc->tos != -1) ? RT_TOS(ipc->tos) : RT_TOS(inet->tos);
-}
-
 /* datagram.c */
-int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
+int ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len);
 
 void ip4_datagram_release_cb(struct sock *sk);
 
@@ -284,7 +284,8 @@ static inline __u8 ip_reply_arg_flowi_flags(const struct ip_reply_arg *arg)
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk,
+			   struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -325,11 +326,12 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o
 }
 #endif
 
-#define snmp_get_cpu_field64_batch(buff64, stats_list, mib_statistic, offset) \
+#define snmp_get_cpu_field64_batch_cnt(buff64, stats_list, cnt,	\
+				       mib_statistic, offset)	\
 { \
 	int i, c; \
 	for_each_possible_cpu(c) { \
-		for (i = 0; stats_list[i].name; i++) \
+		for (i = 0; i < cnt; i++) \
 			buff64[i] += snmp_get_cpu_field64( \
 					mib_statistic, \
 					c, stats_list[i].entry, \
@@ -337,22 +339,28 @@ static inline u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_o
 	} \
 }
 
-#define snmp_get_cpu_field_batch(buff, stats_list, mib_statistic) \
+#define snmp_get_cpu_field_batch_cnt(buff, stats_list, cnt, mib_statistic) \
 { \
 	int i, c; \
 	for_each_possible_cpu(c) { \
-		for (i = 0; stats_list[i].name; i++) \
+		for (i = 0; i < cnt; i++) \
 			buff[i] += snmp_get_cpu_field( \
 						mib_statistic, \
 						c, stats_list[i].entry); \
 	} \
 }
 
-void inet_get_local_port_range(const struct net *net, int *low, int *high);
-void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
+static inline void inet_get_local_port_range(const struct net *net, int *low, int *high)
+{
+	u32 range = READ_ONCE(net->ipv4.ip_local_ports.range);
+
+	*low = range & 0xffff;
+	*high = range >> 16;
+}
+bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
-static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
+static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port)
 {
 	if (!net->ipv4.sysctl_local_reserved_ports)
 		return false;
@@ -414,9 +422,14 @@ int ip_decrease_ttl(struct iphdr *iph)
 	return --iph->ttl;
 }
 
+static inline dscp_t ip4h_dscp(const struct iphdr *ip4h)
+{
+	return inet_dsfield_to_dscp(ip4h->tos);
+}
+
 static inline int ip_mtu_locked(const struct dst_entry *dst)
 {
-	const struct rtable *rt = (const struct rtable *)dst;
+	const struct rtable *rt = dst_rtable(dst);
 
 	return rt->rt_mtu_locked || dst_metric_locked(dst, RTAX_MTU);
 }
@@ -433,33 +446,41 @@ int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst)
 
 static inline bool ip_sk_accept_pmtu(const struct sock *sk)
 {
-	return inet_sk(sk)->pmtudisc != IP_PMTUDISC_INTERFACE &&
-	       inet_sk(sk)->pmtudisc != IP_PMTUDISC_OMIT;
+	u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
+
+	return pmtudisc != IP_PMTUDISC_INTERFACE &&
+	       pmtudisc != IP_PMTUDISC_OMIT;
 }
 
 static inline bool ip_sk_use_pmtu(const struct sock *sk)
 {
-	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_PROBE;
+	return READ_ONCE(inet_sk(sk)->pmtudisc) < IP_PMTUDISC_PROBE;
 }
 
 static inline bool ip_sk_ignore_df(const struct sock *sk)
 {
-	return inet_sk(sk)->pmtudisc < IP_PMTUDISC_DO ||
-	       inet_sk(sk)->pmtudisc == IP_PMTUDISC_OMIT;
+	u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc);
+
+	return pmtudisc < IP_PMTUDISC_DO || pmtudisc == IP_PMTUDISC_OMIT;
 }
 
 static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 						    bool forwarding)
 {
-	const struct rtable *rt = container_of(dst, struct rtable, dst);
-	struct net *net = dev_net(dst->dev);
-	unsigned int mtu;
+	const struct rtable *rt = dst_rtable(dst);
+	const struct net_device *dev;
+	unsigned int mtu, res;
+	struct net *net;
+
+	rcu_read_lock();
 
+	dev = dst_dev_rcu(dst);
+	net = dev_net_rcu(dev);
 	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    ip_mtu_locked(dst) ||
 	    !forwarding) {
 		mtu = rt->rt_pmtu;
-		if (mtu && time_before(jiffies, rt->dst.expires))
+		if (mtu && time_before(jiffies, READ_ONCE(rt->dst.expires)))
 			goto out;
 	}
 
@@ -468,7 +489,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	if (mtu)
 		goto out;
 
-	mtu = READ_ONCE(dst->dev->mtu);
+	mtu = READ_ONCE(dev->mtu);
 
 	if (unlikely(ip_mtu_locked(dst))) {
 		if (rt->rt_uses_gateway && mtu > 576)
@@ -478,26 +499,30 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 out:
 	mtu = min_t(unsigned int, mtu, IP_MAX_MTU);
 
-	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+	res = mtu - lwtunnel_headroom(dst->lwtstate, mtu);
+
+	rcu_read_unlock();
+
+	return res;
 }
 
 static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
 					  const struct sk_buff *skb)
 {
+	const struct dst_entry *dst = skb_dst(skb);
 	unsigned int mtu;
 
 	if (!sk || !sk_fullsock(sk) || ip_sk_use_pmtu(sk)) {
 		bool forwarding = IPCB(skb)->flags & IPSKB_FORWARDED;
 
-		return ip_dst_mtu_maybe_forward(skb_dst(skb), forwarding);
+		return ip_dst_mtu_maybe_forward(dst, forwarding);
 	}
 
-	mtu = min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
-	return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
+	mtu = min(READ_ONCE(dst_dev(dst)->mtu), IP_MAX_MTU);
+	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
-struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
-					int fc_mx_len,
+struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len,
 					struct netlink_ext_ack *extack);
 static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
 {
@@ -667,11 +692,24 @@ static __inline__ void inet_reset_saddr(struct sock *sk)
 
 #endif
 
+#if IS_MODULE(CONFIG_IPV6)
+#define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X)
+#define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X)
+#else
+#define EXPORT_IPV6_MOD(X)
+#define EXPORT_IPV6_MOD_GPL(X)
+#endif
+
 static inline unsigned int ipv4_addr_hash(__be32 ip)
 {
 	return (__force unsigned int) ip;
 }
 
+static inline u32 __ipv4_addr_hash(const __be32 ip, const u32 initval)
+{
+	return jhash_1word((__force u32)ip, initval);
+}
+
 static inline u32 ipv4_portaddr_hash(const struct net *net,
 				     __be32 saddr,
 				     unsigned int port)
@@ -757,7 +795,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
  *	Functions provided by ip_sockglue.c
  */
 
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst);
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,
@@ -785,9 +823,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
 	ip_cmsg_recv_offset(msg, skb->sk, skb, 0, 0);
 }
 
-bool icmp_global_allow(void);
-extern int sysctl_icmp_msgs_per_sec;
-extern int sysctl_icmp_msgs_burst;
+bool icmp_global_allow(struct net *net);
+void icmp_global_consume(struct net *net);
 
 #ifdef CONFIG_PROC_FS
 int ip_misc_proc_init(void);