ipv6: make lookups simpler and faster

TCP listener refactoring, part 4 :

To speed up inet lookups, we moved IPv4 addresses from inet to struct
sock_common

Now is time to do the same for IPv6, because it permits us to have fast
lookups for all kind of sockets, including upcoming SYN_RECV.

Getting IPv6 addresses in TCP lookups currently requires two extra cache
lines, plus a dereference (and memory stall).

inet6_sk(sk) does the dereference of inet_sk(__sk)->pinet6

This patch is way bigger than its IPv4 counter part, because for IPv4,
we could add aliases (inet_daddr, inet_rcv_saddr), while on IPv6,
it's not doable easily.

inet6_sk(sk)->daddr becomes sk->sk_v6_daddr
inet6_sk(sk)->rcv_saddr becomes sk->sk_v6_rcv_saddr

And timewait socket also have tw->tw_v6_daddr & tw->tw_v6_rcv_saddr
at the same offset.

We get rid of INET6_TW_MATCH() as INET6_MATCH() is now the generic
macro.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 40 insertions, 59 deletions

diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8e1e40653357..ecc179d676e4 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -121,13 +121,13 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-		const struct ipv6_pinfo *np = inet6_sk(sk);
 
-		*(struct in6_addr *)r->id.idiag_src = np->rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = np->daddr;
+		*(struct in6_addr *)r->id.idiag_src = sk->sk_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = sk->sk_v6_daddr;
 
 		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
-			if (nla_put_u8(skb, INET_DIAG_TCLASS, np->tclass) < 0)
+			if (nla_put_u8(skb, INET_DIAG_TCLASS,
+				       inet6_sk(sk)->tclass) < 0)
 				goto errout;
 	}
 #endif
@@ -255,11 +255,8 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->idiag_inode	      = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (tw->tw_family == AF_INET6) {
-		const struct inet6_timewait_sock *tw6 =
-						inet6_twsk((struct sock *)tw);
-
-		*(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr;
-		*(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr;
+		*(struct in6_addr *)r->id.idiag_src = tw->tw_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = tw->tw_v6_daddr;
 	}
 #endif
 
@@ -273,10 +270,11 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 			const struct nlmsghdr *unlh)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
-		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
-					   skb, r, portid, seq, nlmsg_flags,
-					   unlh);
-	return inet_csk_diag_fill(sk, skb, r, user_ns, portid, seq, nlmsg_flags, unlh);
+		return inet_twsk_diag_fill(inet_twsk(sk), skb, r, portid, 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,
@@ -489,10 +487,9 @@ int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
 	entry.family = sk->sk_family;
 #if IS_ENABLED(CONFIG_IPV6)
 	if (entry.family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
 
-		entry.saddr = np->rcv_saddr.s6_addr32;
-		entry.daddr = np->daddr.s6_addr32;
+		entry.saddr = sk->sk_v6_rcv_saddr.s6_addr32;
+		entry.daddr = sk->sk_v6_daddr.s6_addr32;
 	} else
 #endif
 	{
@@ -649,10 +646,8 @@ static int inet_twsk_diag_dump(struct sock *sk,
 		entry.family = tw->tw_family;
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
-			struct inet6_timewait_sock *tw6 =
-						inet6_twsk((struct sock *)tw);
-			entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32;
-			entry.daddr = tw6->tw_v6_daddr.s6_addr32;
+			entry.saddr = tw->tw_v6_rcv_saddr.s6_addr32;
+			entry.daddr = tw->tw_v6_daddr.s6_addr32;
 		} else
 #endif
 		{
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a62610443152..ccefc07beacd 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -202,15 +202,14 @@ static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
 #if IS_ENABLED(CONFIG_IPV6)
 		} else if (skb->protocol == htons(ETH_P_IPV6) &&
 			   sk->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 
 			pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
 				 (int) isk->inet_num,
-				 &inet6_sk(sk)->rcv_saddr,
+				 &sk->sk_v6_rcv_saddr,
 				 sk->sk_bound_dev_if);
 
-			if (!ipv6_addr_any(&np->rcv_saddr) &&
-			    !ipv6_addr_equal(&np->rcv_saddr,
+			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
+			    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
 					     &ipv6_hdr(skb)->daddr))
 				continue;
 #endif
@@ -362,7 +361,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
 	} else if (saddr->sa_family == AF_INET6) {
 		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
 		struct ipv6_pinfo *np = inet6_sk(sk);
-		np->rcv_saddr = np->saddr = addr->sin6_addr;
+		sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr;
 #endif
 	}
 }
@@ -376,7 +375,7 @@ static void ping_clear_saddr(struct sock *sk, int dif)
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (sk->sk_family == AF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
-		memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
 		memset(&np->saddr, 0, sizeof(np->saddr));
 #endif
 	}
@@ -418,7 +417,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	err = 0;
 	if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
 	    (sk->sk_family == AF_INET6 &&
-	     !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
+	     !ipv6_addr_any(&sk->sk_v6_rcv_saddr)))
 		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
 
 	if (snum)
@@ -429,7 +428,7 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6)
-		memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
 #endif
 
 	sk_dst_reset(sk);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 52f3c6b971d2..27535fd5ea10 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -240,7 +240,6 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 
 static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock *tw)
 {
-	struct inet6_timewait_sock *tw6;
 	struct tcp_metrics_block *tm;
 	struct inetpeer_addr addr;
 	unsigned int hash;
@@ -253,9 +252,8 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
 	case AF_INET6:
-		tw6 = inet6_twsk((struct sock *)tw);
-		*(struct in6_addr *)addr.addr.a6 = tw6->tw_v6_daddr;
-		hash = ipv6_addr_hash(&tw6->tw_v6_daddr);
+		*(struct in6_addr *)addr.addr.a6 = tw->tw_v6_daddr;
+		hash = ipv6_addr_hash(&tw->tw_v6_daddr);
 		break;
 	default:
 		return NULL;
@@ -289,8 +287,8 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 		hash = (__force unsigned int) addr.addr.a4;
 		break;
 	case AF_INET6:
-		*(struct in6_addr *)addr.addr.a6 = inet6_sk(sk)->daddr;
-		hash = ipv6_addr_hash(&inet6_sk(sk)->daddr);
+		*(struct in6_addr *)addr.addr.a6 = sk->sk_v6_daddr;
+		hash = ipv6_addr_hash(&sk->sk_v6_daddr);
 		break;
 	default:
 		return NULL;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 58a3e69aef64..97b684159861 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -293,12 +293,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 #if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
-			struct inet6_timewait_sock *tw6;
 
-			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
-			tw6 = inet6_twsk((struct sock *)tw);
-			tw6->tw_v6_daddr = np->daddr;
-			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
+			tw->tw_v6_daddr = sk->sk_v6_daddr;
+			tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
 			tw->tw_tclass = np->tclass;
 			tw->tw_ipv6only = np->ipv6only;
 		}
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 611beab38a00..8b97d71e193b 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -101,22 +101,6 @@ static inline int tcp_probe_avail(void)
 		si4.sin_addr.s_addr = inet->inet_##mem##addr;	\
 	} while (0)						\
 
-#if IS_ENABLED(CONFIG_IPV6)
-#define tcp_probe_copy_fl_to_si6(inet, si6, mem)		\
-	do {							\
-		struct ipv6_pinfo *pi6 = inet->pinet6;		\
-		si6.sin6_family = AF_INET6;			\
-		si6.sin6_port = inet->inet_##mem##port;		\
-		si6.sin6_addr = pi6->mem##addr;			\
-		si6.sin6_flowinfo = 0; /* No need here. */	\
-		si6.sin6_scope_id = 0;	/* No need here. */	\
-	} while (0)
-#else
-#define tcp_probe_copy_fl_to_si6(fl, si6, mem)			\
-	do {							\
-		memset(&si6, 0, sizeof(si6));			\
-	} while (0)
-#endif
 
 /*
  * Hook inserted to be called before each receive packet.
@@ -147,8 +131,17 @@ static void jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
 				tcp_probe_copy_fl_to_si4(inet, p->dst.v4, d);
 				break;
 			case AF_INET6:
-				tcp_probe_copy_fl_to_si6(inet, p->src.v6, s);
-				tcp_probe_copy_fl_to_si6(inet, p->dst.v6, d);
+				memset(&p->src.v6, 0, sizeof(p->src.v6));
+				memset(&p->dst.v6, 0, sizeof(p->dst.v6));
+#if IS_ENABLED(CONFIG_IPV6)
+				p->src.v6.sin6_family = AF_INET6;
+				p->src.v6.sin6_port = inet->inet_sport;
+				p->src.v6.sin6_addr = inet6_sk(sk)->saddr;
+
+				p->dst.v6.sin6_family = AF_INET6;
+				p->dst.v6.sin6_port = inet->inet_dport;
+				p->dst.v6.sin6_addr = sk->sk_v6_daddr;
+#endif
 				break;
 			default:
 				BUG();
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 4b85e6f636c9..af07b5b23ebf 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -374,9 +374,8 @@ void tcp_retransmit_timer(struct sock *sk)
 		}
 #if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
 			LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"),
-				       &np->daddr,
+				       &sk->sk_v6_daddr,
 				       ntohs(inet->inet_dport), inet->inet_num,
 				       tp->snd_una, tp->snd_nxt);
 		}