Merge branch 'metrics_restructure'

This patch series works towards the goal of minimizing the amount
of things that can change in an ipv4 route.

In a regime where the routing cache is removed, route changes will
lead to cloning in the FIB tables or similar.

The largest trigger of route metrics writes, TCP, now has it's own
cache of dynamic metric state.  The timewait timestamps are stored
there now as well.

As a result of that, pre-cowing metrics is no longer necessary,
and therefore FLOWI_FLAG_PRECOW_METRICS is removed.

Redirect and PMTU handling is moved back into the ipv4 routes.  I'm
sorry for all the headaches trying to do this in the inetpeer has
caused, it was the wrong approach for sure.

Since metrics become read-only for ipv4 we no longer need the inetpeer
hung off of the ipv4 routes either.  So those disappear too.

Also, timewait sockets no longer need to hold onto an inetpeer either.

After this series, we still have some details to resolve wrt. PMTU and
redirects for a route-cache-less system:

1) With just the plain route cache removal, PMTU will continue to
   work mostly fine.  This is because of how the local route users
   call down into the PMTU update code with the route they already
   hold.

   However, if we wish to cache pre-computed routes in fib_info
   nexthops (which we want for performance), then we need to add
   route cloning for PMTU events.

2) Redirects require more work.  First, redirects must be changed to
   be handled like PMTU.  Wherein we call down into the sockets and
   other entities, and then they call back into the routing code with
   the route they were using.

   So we'll be adding an ->update_nexthop() method alongside
   ->update_pmtu().

   And then, like for PMTU, we'll need cloning support once we start
   caching routes in the fib_info nexthops.

But that's it, we can completely pull the trigger and remove the
routing cache with minimal disruptions.

As it is, this patch series alone helps a lot of things.  For one,
routing cache entry creation should be a lot faster, because we no
longer do inetpeer lookups (even to check if an entry exists).

This patch series also opens the door for non-DST_HOST ipv4 routes,
because nothing fundamentally cares about rt->rt_dst any more.  It
can be removed with the base routing cache removal patch.  In fact,
that was the primary goal of this patch series.

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 17 insertions, 82 deletions

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index ea60b0854109..db71c4ad8624 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -619,8 +619,7 @@ extern void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid,
 extern void rtnl_set_sk_err(struct net *net, u32 group, int error);
 extern int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics);
 extern int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst,
-			      u32 id, u32 ts, u32 tsage, long expires,
-			      u32 error);
+			      u32 id, long expires, u32 error);
 
 extern void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change);
 
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 7d3bcedc062a..2de9cf46f9fc 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -506,7 +506,6 @@ struct tcp_timewait_sock {
 	u32			  tw_rcv_wnd;
 	u32			  tw_ts_recent;
 	long			  tw_ts_recent_stamp;
-	struct inet_peer	  *tw_peer;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key	  *tw_md5_key;
 #endif
diff --git a/include/net/dst.h b/include/net/dst.h
index b2634e446613..51610468c63d 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -209,12 +209,6 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr
 	return msecs_to_jiffies(dst_metric(dst, metric));
 }
 
-static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric,
-				      unsigned long rtt)
-{
-	dst_metric_set(dst, metric, jiffies_to_msecs(rtt));
-}
-
 static inline u32
 dst_allfrag(const struct dst_entry *dst)
 {
diff --git a/include/net/flow.h b/include/net/flow.h
index bd524f598561..ce9cb7656b47 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -20,9 +20,8 @@ struct flowi_common {
 	__u8	flowic_proto;
 	__u8	flowic_flags;
 #define FLOWI_FLAG_ANYSRC		0x01
-#define FLOWI_FLAG_PRECOW_METRICS	0x02
-#define FLOWI_FLAG_CAN_SLEEP		0x04
-#define FLOWI_FLAG_RT_NOCACHE		0x08
+#define FLOWI_FLAG_CAN_SLEEP		0x02
+#define FLOWI_FLAG_RT_NOCACHE		0x04
 	__u32	flowic_secid;
 };
 
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index af3c743a40e4..291e7cee14e7 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -43,7 +43,6 @@ struct inet_connection_sock_af_ops {
 	struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req,
 				      struct dst_entry *dst);
-	struct inet_peer *(*get_peer)(struct sock *sk);
 	u16	    net_header_len;
 	u16	    net_frag_header_len;
 	u16	    sockaddr_len;
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index ae17e1352d7e..924d7b98ab60 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -245,8 +245,6 @@ static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
 
 	if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl)
 		flags |= FLOWI_FLAG_ANYSRC;
-	if (sk->sk_protocol == IPPROTO_TCP)
-		flags |= FLOWI_FLAG_PRECOW_METRICS;
 	return flags;
 }
 
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index c27c8f10ebdc..53f464d7cddc 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -36,25 +36,19 @@ struct inet_peer {
 	u32			metrics[RTAX_MAX];
 	u32			rate_tokens;	/* rate limiting for ICMP */
 	unsigned long		rate_last;
-	unsigned long		pmtu_expires;
-	u32			pmtu_orig;
-	u32			pmtu_learned;
-	struct inetpeer_addr_base redirect_learned;
 	union {
 		struct list_head	gc_list;
 		struct rcu_head     gc_rcu;
 	};
 	/*
 	 * Once inet_peer is queued for deletion (refcnt == -1), following fields
-	 * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp
+	 * are not available: rid, ip_id_count
 	 * We can share memory with rcu_head to help keep inet_peer small.
 	 */
 	union {
 		struct {
 			atomic_t			rid;		/* Frag reception counter */
 			atomic_t			ip_id_count;	/* IP ID for the next packet */
-			__u32				tcp_ts;
-			__u32				tcp_ts_stamp;
 		};
 		struct rcu_head         rcu;
 		struct inet_peer	*gc_next;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 599e48fa97cb..2e089a99d603 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -7,6 +7,7 @@
 
 #include <net/inet_frag.h>
 
+struct tcpm_hash_bucket;
 struct ctl_table_header;
 struct ipv4_devconf;
 struct fib_rules_ops;
@@ -39,6 +40,8 @@ struct netns_ipv4 {
 	struct sock		**icmp_sk;
 	struct sock		*tcp_sock;
 	struct inet_peer_base	*peers;
+	struct tcpm_hash_bucket	*tcp_metrics_hash;
+	unsigned int		tcp_metrics_hash_mask;
 	struct netns_frags	frags;
 #ifdef CONFIG_NETFILTER
 	struct xt_table		*iptable_filter;
diff --git a/include/net/route.h b/include/net/route.h
index 211e2665139b..52362368af09 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -40,7 +40,6 @@
 #define RT_CONN_FLAGS(sk)   (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE))
 
 struct fib_nh;
-struct inet_peer;
 struct fib_info;
 struct rtable {
 	struct dst_entry	dst;
@@ -65,45 +64,10 @@ struct rtable {
 	__be32			rt_gateway;
 
 	/* Miscellaneous cached information */
-	u32			rt_peer_genid;
-	unsigned long		_peer; /* long-living peer info */
+	u32			rt_pmtu;
 	struct fib_info		*fi; /* for client ref to shared metrics */
 };
 
-static inline struct inet_peer *rt_peer_ptr(struct rtable *rt)
-{
-	return inetpeer_ptr(rt->_peer);
-}
-
-static inline bool rt_has_peer(struct rtable *rt)
-{
-	return inetpeer_ptr_is_peer(rt->_peer);
-}
-
-static inline void __rt_set_peer(struct rtable *rt, struct inet_peer *peer)
-{
-	__inetpeer_ptr_set_peer(&rt->_peer, peer);
-}
-
-static inline bool rt_set_peer(struct rtable *rt, struct inet_peer *peer)
-{
-	return inetpeer_ptr_set_peer(&rt->_peer, peer);
-}
-
-static inline void rt_init_peer(struct rtable *rt, struct inet_peer_base *base)
-{
-	inetpeer_init_ptr(&rt->_peer, base);
-}
-
-static inline void rt_transfer_peer(struct rtable *rt, struct rtable *ort)
-{
-	rt->_peer = ort->_peer;
-	if (rt_has_peer(ort)) {
-		struct inet_peer *peer = rt_peer_ptr(ort);
-		atomic_inc(&peer->refcnt);
-	}
-}
-
 static inline bool rt_is_input_route(const struct rtable *rt)
 {
 	return rt->rt_route_iif != 0;
@@ -278,8 +242,6 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32
 
 	if (inet_sk(sk)->transparent)
 		flow_flags |= FLOWI_FLAG_ANYSRC;
-	if (protocol == IPPROTO_TCP)
-		flow_flags |= FLOWI_FLAG_PRECOW_METRICS;
 	if (can_sleep)
 		flow_flags |= FLOWI_FLAG_CAN_SLEEP;
 
@@ -328,27 +290,6 @@ static inline struct rtable *ip_route_newports(struct flowi4 *fl4, struct rtable
 	return rt;
 }
 
-extern void rt_bind_peer(struct rtable *rt, __be32 daddr, int create);
-
-static inline struct inet_peer *__rt_get_peer(struct rtable *rt, __be32 daddr, int create)
-{
-	if (rt_has_peer(rt))
-		return rt_peer_ptr(rt);
-
-	rt_bind_peer(rt, daddr, create);
-	return (rt_has_peer(rt) ? rt_peer_ptr(rt) : NULL);
-}
-
-static inline struct inet_peer *rt_get_peer(struct rtable *rt, __be32 daddr)
-{
-	return __rt_get_peer(rt, daddr, 0);
-}
-
-static inline struct inet_peer *rt_get_peer_create(struct rtable *rt, __be32 daddr)
-{
-	return __rt_get_peer(rt, daddr, 1);
-}
-
 static inline int inet_iif(const struct sk_buff *skb)
 {
 	return skb_rtable(skb)->rt_iif;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 53fb7d814170..3618fefae049 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -388,6 +388,13 @@ extern void tcp_enter_frto(struct sock *sk);
 extern void tcp_enter_loss(struct sock *sk, int how);
 extern void tcp_clear_retrans(struct tcp_sock *tp);
 extern void tcp_update_metrics(struct sock *sk);
+extern void tcp_init_metrics(struct sock *sk);
+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_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);
 extern void tcp_init_sock(struct sock *sk);
 extern unsigned int tcp_poll(struct file * file, struct socket *sock,
@@ -556,6 +563,8 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
 	return (tp->srtt >> 3) + tp->rttvar;
 }
 
+extern void tcp_set_rto(struct sock *sk);
+
 static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
 {
 	tp->pred_flags = htonl((tp->tcp_header_len << 26) |