14 files changed, 153 insertions, 79 deletions

diff --git a/include/net/checksum.h b/include/net/checksum.h
index 0a55ac715077..2d1d73cb773e 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -122,7 +122,9 @@ static inline __wsum csum_partial_ext(const void *buff, int len, __wsum sum)
 
 static inline void csum_replace4(__sum16 *sum, __be32 from, __be32 to)
 {
-	*sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from), to));
+	__wsum tmp = csum_sub(~csum_unfold(*sum), (__force __wsum)from);
+
+	*sum = csum_fold(csum_add(tmp, (__force __wsum)to));
 }
 
 /* Implements RFC 1624 (Incremental Internet Checksum)
diff --git a/include/net/geneve.h b/include/net/geneve.h
index 14fb8d3390b4..2a0543a1899d 100644
--- a/include/net/geneve.h
+++ b/include/net/geneve.h
@@ -62,6 +62,11 @@ struct genevehdr {
 	struct geneve_opt options[];
 };
 
+static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
+{
+	return (struct genevehdr *)(udp_hdr(skb) + 1);
+}
+
 #ifdef CONFIG_INET
 struct geneve_sock;
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 48a815823587..497bc14cdb85 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -129,9 +129,10 @@ struct inet_connection_sock {
 
 		u32		  probe_timestamp;
 	} icsk_mtup;
-	u32			  icsk_ca_priv[16];
 	u32			  icsk_user_timeout;
-#define ICSK_CA_PRIV_SIZE	(16 * sizeof(u32))
+
+	u64			  icsk_ca_priv[64 / sizeof(u64)];
+#define ICSK_CA_PRIV_SIZE      (8 * sizeof(u64))
 };
 
 #define ICSK_TIME_RETRANS	1	/* Retransmit timer */
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 8d1765577acc..e1300b3dd597 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -43,7 +43,7 @@ enum {
  * @len: total length of the original datagram
  * @meat: length of received fragments so far
  * @flags: fragment queue flags
- * @max_size: (ipv4 only) maximum received fragment size with IP_DF set
+ * @max_size: maximum received fragment size
  * @net: namespace that this frag belongs to
  */
 struct inet_frag_queue {
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 73fe0f9525d9..b73c88a19dd4 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -24,7 +24,6 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/wait.h>
-#include <linux/vmalloc.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_sock.h>
@@ -148,8 +147,6 @@ struct inet_hashinfo {
 	 */
 	struct inet_listen_hashbucket	listening_hash[INET_LHTABLE_SIZE]
 					____cacheline_aligned_in_smp;
-
-	atomic_t			bsockets;
 };
 
 static inline struct inet_ehash_bucket *inet_ehash_bucket(
@@ -166,52 +163,12 @@ static inline spinlock_t *inet_ehash_lockp(
 	return &hashinfo->ehash_locks[hash & hashinfo->ehash_locks_mask];
 }
 
-static inline int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
-{
-	unsigned int i, size = 256;
-#if defined(CONFIG_PROVE_LOCKING)
-	unsigned int nr_pcpus = 2;
-#else
-	unsigned int nr_pcpus = num_possible_cpus();
-#endif
-	if (nr_pcpus >= 4)
-		size = 512;
-	if (nr_pcpus >= 8)
-		size = 1024;
-	if (nr_pcpus >= 16)
-		size = 2048;
-	if (nr_pcpus >= 32)
-		size = 4096;
-	if (sizeof(spinlock_t) != 0) {
-#ifdef CONFIG_NUMA
-		if (size * sizeof(spinlock_t) > PAGE_SIZE)
-			hashinfo->ehash_locks = vmalloc(size * sizeof(spinlock_t));
-		else
-#endif
-		hashinfo->ehash_locks =	kmalloc(size * sizeof(spinlock_t),
-						GFP_KERNEL);
-		if (!hashinfo->ehash_locks)
-			return ENOMEM;
-		for (i = 0; i < size; i++)
-			spin_lock_init(&hashinfo->ehash_locks[i]);
-	}
-	hashinfo->ehash_locks_mask = size - 1;
-	return 0;
-}
+int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo);
 
 static inline void inet_ehash_locks_free(struct inet_hashinfo *hashinfo)
 {
-	if (hashinfo->ehash_locks) {
-#ifdef CONFIG_NUMA
-		unsigned int size = (hashinfo->ehash_locks_mask + 1) *
-							sizeof(spinlock_t);
-		if (size > PAGE_SIZE)
-			vfree(hashinfo->ehash_locks);
-		else
-#endif
-		kfree(hashinfo->ehash_locks);
-		hashinfo->ehash_locks = NULL;
-	}
+	kvfree(hashinfo->ehash_locks);
+	hashinfo->ehash_locks = NULL;
 }
 
 struct inet_bind_bucket *
diff --git a/include/net/ip.h b/include/net/ip.h
index 0ed6d768e606..9b976cf99122 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -45,6 +45,7 @@ struct inet_skb_parm {
 #define IPSKB_FRAG_COMPLETE	BIT(3)
 #define IPSKB_REROUTED		BIT(4)
 #define IPSKB_DOREDIRECT	BIT(5)
+#define IPSKB_FRAG_PMTU		BIT(6)
 
 	u16			frag_max_size;
 };
@@ -108,9 +109,8 @@ int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct sock *sk, struct sk_buff *skb);
 int ip_mc_output(struct sock *sk, struct sk_buff *skb);
-int ip_fragment(struct sock *sk, struct sk_buff *skb,
-		int (*output)(struct sock *, struct sk_buff *));
-int ip_do_nat(struct sk_buff *skb);
+int ip_do_fragment(struct sock *sk, struct sk_buff *skb,
+		   int (*output)(struct sock *, struct sk_buff *));
 void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct sk_buff *skb);
 int ip_local_out_sk(struct sock *sk, struct sk_buff *skb);
@@ -478,6 +478,16 @@ enum ip_defrag_users {
 	IP_DEFRAG_MACVLAN,
 };
 
+/* Return true if the value of 'user' is between 'lower_bond'
+ * and 'upper_bond' inclusively.
+ */
+static inline bool ip_defrag_user_in_between(u32 user,
+					     enum ip_defrag_users lower_bond,
+					     enum ip_defrag_users upper_bond)
+{
+	return user >= lower_bond && user <= upper_bond;
+}
+
 int ip_defrag(struct sk_buff *skb, u32 user);
 #ifdef CONFIG_INET
 struct sk_buff *ip_check_defrag(struct sk_buff *skb, u32 user);
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index e00018011028..3b76849c190f 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -120,7 +120,11 @@ struct rt6_info {
 	struct rt6key			rt6i_src;
 	struct rt6key			rt6i_prefsrc;
 
+	struct list_head		rt6i_uncached;
+	struct uncached_list		*rt6i_uncached_list;
+
 	struct inet6_dev		*rt6i_idev;
+	struct rt6_info * __percpu	*rt6i_pcpu;
 
 	u32				rt6i_metric;
 	u32				rt6i_pmtu;
@@ -159,6 +163,14 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
 	rt0->rt6i_flags |= RTF_EXPIRES;
 }
 
+static inline u32 rt6_get_cookie(const struct rt6_info *rt)
+{
+	if (rt->rt6i_flags & RTF_PCPU || unlikely(rt->dst.flags & DST_NOCACHE))
+		rt = (struct rt6_info *)(rt->dst.from);
+
+	return rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+}
+
 static inline void ip6_rt_put(struct rt6_info *rt)
 {
 	/* dst_release() accepts a NULL parameter.
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 5e192068e6cb..297629aadb19 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -145,7 +145,7 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst,
 #ifdef CONFIG_IPV6_SUBTREES
 	np->saddr_cache = saddr;
 #endif
-	np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
+	np->dst_cookie = rt6_get_cookie(rt);
 }
 
 static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst,
@@ -163,11 +163,14 @@ static inline bool ipv6_unicast_destination(const struct sk_buff *skb)
 	return rt->rt6i_flags & RTF_LOCAL;
 }
 
-static inline bool ipv6_anycast_destination(const struct sk_buff *skb)
+static inline bool ipv6_anycast_destination(const struct dst_entry *dst,
+					    const struct in6_addr *daddr)
 {
-	struct rt6_info *rt = (struct rt6_info *) skb_dst(skb);
+	struct rt6_info *rt = (struct rt6_info *)dst;
 
-	return rt->rt6i_flags & RTF_ANYCAST;
+	return rt->rt6i_flags & RTF_ANYCAST ||
+		(rt->rt6i_dst.plen != 128 &&
+		 ipv6_addr_equal(&rt->rt6i_dst.addr, daddr));
 }
 
 int ip6_fragment(struct sock *sk, struct sk_buff *skb,
@@ -194,9 +197,15 @@ static inline bool ip6_sk_ignore_df(const struct sock *sk)
 	       inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT;
 }
 
-static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt)
+static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
+					   struct in6_addr *daddr)
 {
-	return &rt->rt6i_gateway;
+	if (rt->rt6i_flags & RTF_GATEWAY)
+		return &rt->rt6i_gateway;
+	else if (unlikely(rt->rt6i_flags & RTF_CACHE))
+		return &rt->rt6i_dst.addr;
+	else
+		return daddr;
 }
 
 #endif
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index aab8190d16e8..35d485c78080 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -671,8 +671,9 @@ static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_add
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
-void ipv6_select_ident(struct net *net, struct frag_hdr *fhdr,
-		       struct rt6_info *rt);
+__be32 ipv6_select_ident(struct net *net,
+			 const struct in6_addr *daddr,
+			 const struct in6_addr *saddr);
 void ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 3f850acc844e..72eb23723294 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -58,6 +58,7 @@ struct net {
 	struct list_head	exit_list;	/* Use only net_mutex */
 
 	struct user_namespace   *user_ns;	/* Owning user namespace */
+	spinlock_t		nsid_lock;
 	struct idr		netns_ids;
 
 	struct ns_common	ns;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 614a49be68a9..c68926b4899c 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -19,6 +19,7 @@ struct sock;
 struct local_ports {
 	seqlock_t	lock;
 	int		range[2];
+	bool		warned;
 };
 
 struct ping_group_range {
@@ -77,6 +78,8 @@ struct netns_ipv4 {
 	struct local_ports ip_local_ports;
 
 	int sysctl_tcp_ecn;
+	int sysctl_tcp_ecn_fallback;
+
 	int sysctl_ip_no_pmtu_disc;
 	int sysctl_ip_fwd_use_pmtu;
 	int sysctl_ip_nonlocal_bind;
diff --git a/include/net/sock.h b/include/net/sock.h
index d882f4c8e438..26c1c3171e00 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1368,7 +1368,7 @@ static inline struct inode *SOCK_INODE(struct socket *socket)
  * Functions for memory accounting
  */
 int __sk_mem_schedule(struct sock *sk, int size, int kind);
-void __sk_mem_reclaim(struct sock *sk);
+void __sk_mem_reclaim(struct sock *sk, int amount);
 
 #define SK_MEM_QUANTUM ((int)PAGE_SIZE)
 #define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
@@ -1409,7 +1409,7 @@ static inline void sk_mem_reclaim(struct sock *sk)
 	if (!sk_has_account(sk))
 		return;
 	if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
-		__sk_mem_reclaim(sk);
+		__sk_mem_reclaim(sk, sk->sk_forward_alloc);
 }
 
 static inline void sk_mem_reclaim_partial(struct sock *sk)
@@ -1417,7 +1417,7 @@ static inline void sk_mem_reclaim_partial(struct sock *sk)
 	if (!sk_has_account(sk))
 		return;
 	if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
-		__sk_mem_reclaim(sk);
+		__sk_mem_reclaim(sk, sk->sk_forward_alloc - 1);
 }
 
 static inline void sk_mem_charge(struct sock *sk, int size)
@@ -2025,7 +2025,8 @@ 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);
+struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
+				    bool force_schedule);
 
 /**
  * sk_page_frag - return an appropriate page_frag
diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index ea5b1c230d3d..437f8fe75705 100644
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -47,11 +47,13 @@ enum switchdev_obj_id {
 	SWITCHDEV_OBJ_UNDEFINED,
 	SWITCHDEV_OBJ_PORT_VLAN,
 	SWITCHDEV_OBJ_IPV4_FIB,
+	SWITCHDEV_OBJ_PORT_FDB,
 };
 
 struct switchdev_obj {
 	enum switchdev_obj_id id;
 	enum switchdev_trans trans;
+	int (*cb)(struct net_device *dev, struct switchdev_obj *obj);
 	union {
 		struct switchdev_obj_vlan {		/* PORT_VLAN */
 			u16 flags;
@@ -67,6 +69,10 @@ struct switchdev_obj {
 			u32 nlflags;
 			u32 tb_id;
 		} ipv4_fib;
+		struct switchdev_obj_fdb {		/* PORT_FDB */
+			const unsigned char *addr;
+			u16 vid;
+		} fdb;
 	} u;
 };
 
@@ -80,6 +86,8 @@ struct switchdev_obj {
  * @switchdev_port_obj_add: Add an object to port (see switchdev_obj).
  *
  * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj).
+ *
+ * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj).
  */
 struct switchdev_ops {
 	int	(*switchdev_port_attr_get)(struct net_device *dev,
@@ -90,6 +98,8 @@ struct switchdev_ops {
 					  struct switchdev_obj *obj);
 	int	(*switchdev_port_obj_del)(struct net_device *dev,
 					  struct switchdev_obj *obj);
+	int	(*switchdev_port_obj_dump)(struct net_device *dev,
+					  struct switchdev_obj *obj);
 };
 
 enum switchdev_notifier_type {
@@ -121,6 +131,7 @@ int switchdev_port_attr_set(struct net_device *dev,
 			    struct switchdev_attr *attr);
 int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj);
 int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj);
+int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj);
 int register_switchdev_notifier(struct notifier_block *nb);
 int unregister_switchdev_notifier(struct notifier_block *nb);
 int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
@@ -137,6 +148,15 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi,
 int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi,
 			   u8 tos, u8 type, u32 tb_id);
 void switchdev_fib_ipv4_abort(struct fib_info *fi);
+int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+			   struct net_device *dev, const unsigned char *addr,
+			   u16 vid, u16 nlm_flags);
+int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+			   struct net_device *dev, const unsigned char *addr,
+			   u16 vid);
+int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
+			    struct net_device *dev,
+			    struct net_device *filter_dev, int idx);
 
 #else
 
@@ -164,6 +184,12 @@ static inline int switchdev_port_obj_del(struct net_device *dev,
 	return -EOPNOTSUPP;
 }
 
+static inline int switchdev_port_obj_dump(struct net_device *dev,
+					  struct switchdev_obj *obj)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int register_switchdev_notifier(struct notifier_block *nb)
 {
 	return 0;
@@ -221,6 +247,30 @@ static inline void switchdev_fib_ipv4_abort(struct fib_info *fi)
 {
 }
 
+static inline int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
+					 struct net_device *dev,
+					 const unsigned char *addr,
+					 u16 vid, u16 nlm_flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
+					 struct net_device *dev,
+					 const unsigned char *addr, u16 vid)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
+					  struct netlink_callback *cb,
+					  struct net_device *dev,
+					  struct net_device *filter_dev,
+					  int idx)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* _LINUX_SWITCHDEV_H_ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index b8ea12880fd9..2bb2bad21d5c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -286,6 +286,14 @@ extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
 extern int tcp_memory_pressure;
 
+/* optimized version of sk_under_memory_pressure() for TCP sockets */
+static inline bool tcp_under_memory_pressure(const struct sock *sk)
+{
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return !!sk->sk_cgrp->memory_pressure;
+
+	return tcp_memory_pressure;
+}
 /*
  * The next routines deal with comparing 32 bit unsigned ints
  * and worry about wraparound (automatic with unsigned arithmetic).
@@ -311,6 +319,8 @@ static inline bool tcp_out_of_memory(struct sock *sk)
 	return false;
 }
 
+void sk_forced_mem_schedule(struct sock *sk, int size);
+
 static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 {
 	struct percpu_counter *ocp = sk->sk_prot->orphan_count;
@@ -326,18 +336,6 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 
 bool tcp_check_oom(struct sock *sk, int shift);
 
-/* syncookies: remember time of last synqueue overflow */
-static inline void tcp_synq_overflow(struct sock *sk)
-{
-	tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies;
-}
-
-/* syncookies: no recent synqueue overflow on this listening socket? */
-static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
-{
-	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	return time_after(jiffies, last_overflow + TCP_TIMEOUT_FALLBACK);
-}
 
 extern struct proto tcp_prot;
 
@@ -483,13 +481,35 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
  * i.e. a sent cookie is valid only at most for 2*60 seconds (or less if
  * the counter advances immediately after a cookie is generated).
  */
-#define MAX_SYNCOOKIE_AGE 2
+#define MAX_SYNCOOKIE_AGE	2
+#define TCP_SYNCOOKIE_PERIOD	(60 * HZ)
+#define TCP_SYNCOOKIE_VALID	(MAX_SYNCOOKIE_AGE * TCP_SYNCOOKIE_PERIOD)
+
+/* syncookies: remember time of last synqueue overflow
+ * But do not dirty this field too often (once per second is enough)
+ */
+static inline void tcp_synq_overflow(struct sock *sk)
+{
+	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned long now = jiffies;
+
+	if (time_after(now, last_overflow + HZ))
+		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
+}
+
+/* syncookies: no recent synqueue overflow on this listening socket? */
+static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
+{
+	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+
+	return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID);
+}
 
 static inline u32 tcp_cookie_time(void)
 {
 	u64 val = get_jiffies_64();
 
-	do_div(val, 60 * HZ);
+	do_div(val, TCP_SYNCOOKIE_PERIOD);
 	return val;
 }
 
@@ -692,6 +712,8 @@ static inline u32 tcp_skb_timestamp(const struct sk_buff *skb)
 #define TCPHDR_ECE 0x40
 #define TCPHDR_CWR 0x80
 
+#define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
+
 /* This is what the send packet queuing engine uses to pass
  * TCP per-packet control information to the transmission code.
  * We also store the host-order sequence numbers in here too.