1 files changed, 107 insertions, 98 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5ab2aac5ca19..85164d4d3e53 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -80,12 +80,11 @@
 #include <linux/stddef.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/inetdevice.h>
 
 #include <crypto/hash.h>
 #include <linux/scatterlist.h>
 
-int sysctl_tcp_low_latency __read_mostly;
-
 #ifdef CONFIG_TCP_MD5SIG
 static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 			       __be32 daddr, __be32 saddr, const struct tcphdr *th);
@@ -102,10 +101,9 @@ static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 			      tcp_hdr(skb)->source);
 }
 
-static u32 tcp_v4_init_ts_off(const struct sk_buff *skb)
+static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
 {
-	return secure_tcp_ts_off(ip_hdr(skb)->daddr,
-				 ip_hdr(skb)->saddr);
+	return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr);
 }
 
 int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
@@ -242,7 +240,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 						       inet->inet_daddr,
 						       inet->inet_sport,
 						       usin->sin_port);
-		tp->tsoffset = secure_tcp_ts_off(inet->inet_saddr,
+		tp->tsoffset = secure_tcp_ts_off(sock_net(sk),
+						 inet->inet_saddr,
 						 inet->inet_daddr);
 	}
 
@@ -376,14 +375,15 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	struct sock *sk;
 	struct sk_buff *skb;
 	struct request_sock *fastopen;
-	__u32 seq, snd_una;
-	__u32 remaining;
+	u32 seq, snd_una;
+	s32 remaining;
+	u32 delta_us;
 	int err;
 	struct net *net = dev_net(icmp_skb->dev);
 
 	sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr,
 				       th->dest, iph->saddr, ntohs(th->source),
-				       inet_iif(icmp_skb));
+				       inet_iif(icmp_skb), 0);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;
@@ -483,11 +483,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 		skb = tcp_write_queue_head(sk);
 		BUG_ON(!skb);
 
+		tcp_mstamp_refresh(tp);
+		delta_us = (u32)(tp->tcp_mstamp - skb->skb_mstamp);
 		remaining = icsk->icsk_rto -
-			    min(icsk->icsk_rto,
-				tcp_time_stamp - tcp_skb_timestamp(skb));
+			    usecs_to_jiffies(delta_us);
 
-		if (remaining) {
+		if (remaining > 0) {
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 						  remaining, TCP_RTO_MAX);
 		} else {
@@ -658,7 +659,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 		sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0,
 					     ip_hdr(skb)->saddr,
 					     th->source, ip_hdr(skb)->daddr,
-					     ntohs(th->source), inet_iif(skb));
+					     ntohs(th->source), inet_iif(skb),
+					     tcp_v4_sdif(skb));
 		/* don't send rst if it can't find key */
 		if (!sk1)
 			goto out;
@@ -811,7 +813,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	tcp_v4_send_ack(sk, skb,
 			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
-			tcp_time_stamp + tcptw->tw_ts_offset,
+			tcp_time_stamp_raw() + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
 			tw->tw_bound_dev_if,
 			tcp_twsk_md5_key(tcptw),
@@ -839,7 +841,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	tcp_v4_send_ack(sk, skb, seq,
 			tcp_rsk(req)->rcv_nxt,
 			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
-			tcp_time_stamp + tcp_rsk(req)->ts_off,
+			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			req->ts_recent,
 			0,
 			tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
@@ -904,6 +906,48 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
+	const struct tcp_md5sig_info *md5sig;
+	__be32 mask;
+	struct tcp_md5sig_key *best_match = NULL;
+	bool match;
+
+	/* caller either holds rcu_read_lock() or socket lock */
+	md5sig = rcu_dereference_check(tp->md5sig_info,
+				       lockdep_sock_is_held(sk));
+	if (!md5sig)
+		return NULL;
+
+	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
+		if (key->family != family)
+			continue;
+
+		if (family == AF_INET) {
+			mask = inet_make_mask(key->prefixlen);
+			match = (key->addr.a4.s_addr & mask) ==
+				(addr->a4.s_addr & mask);
+#if IS_ENABLED(CONFIG_IPV6)
+		} else if (family == AF_INET6) {
+			match = ipv6_prefix_equal(&key->addr.a6, &addr->a6,
+						  key->prefixlen);
+#endif
+		} else {
+			match = false;
+		}
+
+		if (match && (!best_match ||
+			      key->prefixlen > best_match->prefixlen))
+			best_match = key;
+	}
+	return best_match;
+}
+EXPORT_SYMBOL(tcp_md5_do_lookup);
+
+static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
+						      const union tcp_md5_addr *addr,
+						      int family, u8 prefixlen)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	struct tcp_md5sig_key *key;
 	unsigned int size = sizeof(struct in_addr);
 	const struct tcp_md5sig_info *md5sig;
 
@@ -919,12 +963,12 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk,
 	hlist_for_each_entry_rcu(key, &md5sig->head, node) {
 		if (key->family != family)
 			continue;
-		if (!memcmp(&key->addr, addr, size))
+		if (!memcmp(&key->addr, addr, size) &&
+		    key->prefixlen == prefixlen)
 			return key;
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(tcp_md5_do_lookup);
 
 struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk)
@@ -938,14 +982,15 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
 /* This can be called on a newly created socket, from other files */
 int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
-		   int family, const u8 *newkey, u8 newkeylen, gfp_t gfp)
+		   int family, u8 prefixlen, const u8 *newkey, u8 newkeylen,
+		   gfp_t gfp)
 {
 	/* Add Key to the list */
 	struct tcp_md5sig_key *key;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_info *md5sig;
 
-	key = tcp_md5_do_lookup(sk, addr, family);
+	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
 	if (key) {
 		/* Pre-existing entry - just update that one. */
 		memcpy(key->key, newkey, newkeylen);
@@ -976,6 +1021,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	memcpy(key->key, newkey, newkeylen);
 	key->keylen = newkeylen;
 	key->family = family;
+	key->prefixlen = prefixlen;
 	memcpy(&key->addr, addr,
 	       (family == AF_INET6) ? sizeof(struct in6_addr) :
 				      sizeof(struct in_addr));
@@ -984,11 +1030,12 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 }
 EXPORT_SYMBOL(tcp_md5_do_add);
 
-int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
+int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
+		   u8 prefixlen)
 {
 	struct tcp_md5sig_key *key;
 
-	key = tcp_md5_do_lookup(sk, addr, family);
+	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen);
 	if (!key)
 		return -ENOENT;
 	hlist_del_rcu(&key->node);
@@ -1014,11 +1061,12 @@ static void tcp_clear_md5_list(struct sock *sk)
 	}
 }
 
-static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
-				 int optlen)
+static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
+				 char __user *optval, int optlen)
 {
 	struct tcp_md5sig cmd;
 	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
+	u8 prefixlen = 32;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -1029,15 +1077,22 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
 	if (sin->sin_family != AF_INET)
 		return -EINVAL;
 
+	if (optname == TCP_MD5SIG_EXT &&
+	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
+		prefixlen = cmd.tcpm_prefixlen;
+		if (prefixlen > 32)
+			return -EINVAL;
+	}
+
 	if (!cmd.tcpm_keylen)
 		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
-				      AF_INET);
+				      AF_INET, prefixlen);
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
 		return -EINVAL;
 
 	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr,
-			      AF_INET, cmd.tcpm_key, cmd.tcpm_keylen,
+			      AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen,
 			      GFP_KERNEL);
 }
 
@@ -1213,7 +1268,7 @@ static void tcp_v4_init_req(struct request_sock *req,
 
 	sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr);
 	sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr);
-	ireq->opt = tcp_v4_save_options(skb);
+	ireq->opt = tcp_v4_save_options(sock_net(sk_listener), skb);
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
@@ -1340,7 +1395,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		 * across. Shucks.
 		 */
 		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr,
-			       AF_INET, key->key, key->keylen, GFP_ATOMIC);
+			       AF_INET, 32, key->key, key->keylen, GFP_ATOMIC);
 		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
 	}
 #endif
@@ -1402,7 +1457,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 				sk->sk_rx_dst = NULL;
 			}
 		}
-		tcp_rcv_established(sk, skb, tcp_hdr(skb), skb->len);
+		tcp_rcv_established(sk, skb, tcp_hdr(skb));
 		return 0;
 	}
 
@@ -1448,28 +1503,28 @@ csum_err:
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-void tcp_v4_early_demux(struct sk_buff *skb)
+int tcp_v4_early_demux(struct sk_buff *skb)
 {
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
 
 	if (skb->pkt_type != PACKET_HOST)
-		return;
+		return 0;
 
 	if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr)))
-		return;
+		return 0;
 
 	iph = ip_hdr(skb);
 	th = tcp_hdr(skb);
 
 	if (th->doff < sizeof(struct tcphdr) / 4)
-		return;
+		return 0;
 
 	sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo,
 				       iph->saddr, th->source,
 				       iph->daddr, ntohs(th->dest),
-				       skb->skb_iif);
+				       skb->skb_iif, inet_sdif(skb));
 	if (sk) {
 		skb->sk = sk;
 		skb->destructor = sock_edemux;
@@ -1483,63 +1538,9 @@ void tcp_v4_early_demux(struct sk_buff *skb)
 				skb_dst_set_noref(skb, dst);
 		}
 	}
+	return 0;
 }
 
-/* Packet is added to VJ-style prequeue for processing in process
- * context, if a reader task is waiting. Apparently, this exciting
- * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
- * failed somewhere. Latency? Burstiness? Well, at least now we will
- * see, why it failed. 8)8)				  --ANK
- *
- */
-bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	if (sysctl_tcp_low_latency || !tp->ucopy.task)
-		return false;
-
-	if (skb->len <= tcp_hdrlen(skb) &&
-	    skb_queue_len(&tp->ucopy.prequeue) == 0)
-		return false;
-
-	/* Before escaping RCU protected region, we need to take care of skb
-	 * dst. Prequeue is only enabled for established sockets.
-	 * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
-	 * Instead of doing full sk_rx_dst validity here, let's perform
-	 * an optimistic check.
-	 */
-	if (likely(sk->sk_rx_dst))
-		skb_dst_drop(skb);
-	else
-		skb_dst_force_safe(skb);
-
-	__skb_queue_tail(&tp->ucopy.prequeue, skb);
-	tp->ucopy.memory += skb->truesize;
-	if (skb_queue_len(&tp->ucopy.prequeue) >= 32 ||
-	    tp->ucopy.memory + atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
-		struct sk_buff *skb1;
-
-		BUG_ON(sock_owned_by_user(sk));
-		__NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED,
-				skb_queue_len(&tp->ucopy.prequeue));
-
-		while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-			sk_backlog_rcv(sk, skb1);
-
-		tp->ucopy.memory = 0;
-	} else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
-		wake_up_interruptible_sync_poll(sk_sleep(sk),
-					   POLLIN | POLLRDNORM | POLLRDBAND);
-		if (!inet_csk_ack_scheduled(sk))
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						  (3 * tcp_rto_min(sk)) / 4,
-						  TCP_RTO_MAX);
-	}
-	return true;
-}
-EXPORT_SYMBOL(tcp_prequeue);
-
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
@@ -1589,6 +1590,7 @@ EXPORT_SYMBOL(tcp_filter);
 int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	int sdif = inet_sdif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	bool refcounted;
@@ -1636,10 +1638,12 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
+	TCP_SKB_CB(skb)->has_rxtstamp =
+			skb->tstamp || skb_hwtstamps(skb)->hwtstamp;
 
 lookup:
 	sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source,
-			       th->dest, &refcounted);
+			       th->dest, sdif, &refcounted);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1666,7 +1670,9 @@ process:
 		 */
 		sock_hold(sk);
 		refcounted = true;
-		nsk = tcp_check_req(sk, skb, req, false);
+		nsk = NULL;
+		if (!tcp_filter(sk, skb))
+			nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
 			goto discard_and_relse;
@@ -1712,8 +1718,7 @@ process:
 	tcp_segs_in(tcp_sk(sk), skb);
 	ret = 0;
 	if (!sock_owned_by_user(sk)) {
-		if (!tcp_prequeue(sk, skb))
-			ret = tcp_v4_do_rcv(sk, skb);
+		ret = tcp_v4_do_rcv(sk, skb);
 	} else if (tcp_add_backlog(sk, skb)) {
 		goto discard_and_relse;
 	}
@@ -1766,7 +1771,8 @@ do_time_wait:
 							__tcp_hdrlen(th),
 							iph->saddr, th->source,
 							iph->daddr, th->dest,
-							inet_iif(skb));
+							inet_iif(skb),
+							sdif);
 		if (sk2) {
 			inet_twsk_deschedule_put(inet_twsk(sk));
 			sk = sk2;
@@ -1858,6 +1864,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
 	tcp_cleanup_congestion_control(sk);
 
+	tcp_cleanup_ulp(sk);
+
 	/* Cleanup up the write buffer. */
 	tcp_write_queue_purge(sk);
 
@@ -1876,9 +1884,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
 	}
 #endif
 
-	/* Clean prequeue, it must be empty really */
-	__skb_queue_purge(&tp->ucopy.prequeue);
-
 	/* Clean up a referenced TCP bind bucket. */
 	if (inet_csk(sk)->icsk_bind_hash)
 		inet_put_port(sk);
@@ -2263,7 +2268,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i)
 		from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)),
 		icsk->icsk_probes_out,
 		sock_i_ino(sk),
-		atomic_read(&sk->sk_refcnt), sk,
+		refcount_read(&sk->sk_refcnt), sk,
 		jiffies_to_clock_t(icsk->icsk_rto),
 		jiffies_to_clock_t(icsk->icsk_ack.ato),
 		(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
@@ -2289,7 +2294,7 @@ static void get_timewait4_sock(const struct inet_timewait_sock *tw,
 		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK",
 		i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
 		3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
-		atomic_read(&tw->tw_refcnt), tw);
+		refcount_read(&tw->tw_refcnt), tw);
 }
 
 #define TMPSZ 150
@@ -2385,6 +2390,7 @@ struct proto tcp_prot = {
 	.unhash			= inet_unhash,
 	.get_port		= inet_csk_get_port,
 	.enter_memory_pressure	= tcp_enter_memory_pressure,
+	.leave_memory_pressure	= tcp_leave_memory_pressure,
 	.stream_memory_free	= tcp_stream_memory_free,
 	.sockets_allocated	= &tcp_sockets_allocated,
 	.orphan_count		= &tcp_orphan_count,
@@ -2463,6 +2469,9 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
 	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+	net->ipv4.sysctl_tcp_sack = 1;
+	net->ipv4.sysctl_tcp_window_scaling = 1;
+	net->ipv4.sysctl_tcp_timestamps = 1;
 
 	return 0;
 fail: