1 files changed, 81 insertions, 75 deletions

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 57b25b1fc9d9..2debdf085a3b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -58,7 +58,9 @@
 #include <net/timewait_sock.h>
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
+#include <net/hotdata.h>
 #include <net/busy_poll.h>
+#include <net/rstreason.h>
 
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
@@ -68,7 +70,8 @@
 
 #include <trace/events/tcp.h>
 
-static void	tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb);
+static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
+			      enum sk_rst_reason reason);
 static void	tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 				      struct request_sock *req);
 
@@ -94,11 +97,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 	struct dst_entry *dst = skb_dst(skb);
 
 	if (dst && dst_hold_safe(dst)) {
-		const struct rt6_info *rt = (const struct rt6_info *)dst;
-
 		rcu_assign_pointer(sk->sk_rx_dst, dst);
 		sk->sk_rx_dst_ifindex = skb->skb_iif;
-		sk->sk_rx_dst_cookie = rt6_get_cookie(rt);
+		sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst));
 	}
 }
 
@@ -489,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 		ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
 
-		if (!sock_owned_by_user(sk)) {
-			WRITE_ONCE(sk->sk_err, err);
-			sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */
-
-			tcp_done(sk);
-		} else {
+		if (!sock_owned_by_user(sk))
+			tcp_done_with_error(sk, err);
+		else
 			WRITE_ONCE(sk->sk_err_soft, err);
-		}
 		goto out;
 	case TCP_LISTEN:
 		break;
@@ -792,7 +789,8 @@ clear_hash_nostart:
 
 static void tcp_v6_init_req(struct request_sock *req,
 			    const struct sock *sk_listener,
-			    struct sk_buff *skb)
+			    struct sk_buff *skb,
+			    u32 tw_isn)
 {
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 	struct inet_request_sock *ireq = inet_rsk(req);
@@ -806,7 +804,7 @@ static void tcp_v6_init_req(struct request_sock *req,
 	    ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL)
 		ireq->ir_iif = tcp_v6_iif(skb);
 
-	if (!TCP_SKB_CB(skb)->tcp_tw_isn &&
+	if (!tw_isn &&
 	    (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) ||
 	     np->rxopt.bits.rxinfo ||
 	     np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim ||
@@ -819,9 +817,10 @@ static void tcp_v6_init_req(struct request_sock *req,
 static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
 					  struct sk_buff *skb,
 					  struct flowi *fl,
-					  struct request_sock *req)
+					  struct request_sock *req,
+					  u32 tw_isn)
 {
-	tcp_v6_init_req(req, sk, skb);
+	tcp_v6_init_req(req, sk, skb, tw_isn);
 
 	if (security_inet_conn_request(sk, skb, req))
 		return NULL;
@@ -968,11 +967,14 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	}
 
 	if (sk) {
+		/* unconstify the socket only to attach it to buff with care. */
+		skb_set_owner_edemux(buff, (struct sock *)sk);
+
 		if (sk->sk_state == TCP_TIME_WAIT)
 			mark = inet_twsk(sk)->tw_mark;
 		else
 			mark = READ_ONCE(sk->sk_mark);
-		skb_set_delivery_time(buff, tcp_transmit_time(sk), true);
+		skb_set_delivery_time(buff, tcp_transmit_time(sk), SKB_CLOCK_MONOTONIC);
 	}
 	if (txhash) {
 		/* autoflowlabel/skb_get_hash_flowi6 rely on buff->hash */
@@ -1005,7 +1007,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	kfree_skb(buff);
 }
 
-static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
+static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
+			      enum sk_rst_reason reason)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
@@ -1112,7 +1115,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 	if (sk) {
 		oif = sk->sk_bound_dev_if;
 		if (sk_fullsock(sk)) {
-			trace_tcp_send_reset(sk, skb);
 			if (inet6_test_bit(REPFLOW, sk))
 				label = ip6_flowlabel(ipv6h);
 			priority = READ_ONCE(sk->sk_priority);
@@ -1128,6 +1130,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 			label = ip6_flowlabel(ipv6h);
 	}
 
+	trace_tcp_send_reset(sk, skb, reason);
+
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
 			     ipv6_get_dsfield(ipv6h), label, priority, txhash,
 			     &key);
@@ -1168,8 +1172,8 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh))
 				goto out;
 			if (aoh)
-				key.ao_key = tcp_ao_established_key(ao_info,
-						aoh->rnext_keyid, -1);
+				key.ao_key = tcp_ao_established_key(sk, ao_info,
+								    aoh->rnext_keyid, -1);
 		}
 	}
 	if (key.ao_key) {
@@ -1192,12 +1196,13 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 #endif
 	}
 
-	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt,
+			READ_ONCE(tcptw->tw_rcv_nxt),
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_tw_tsval(tcptw),
-			tcptw->tw_ts_recent, tw->tw_bound_dev_if, &key,
-			tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority,
-			tw->tw_txhash);
+			READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,
+			&key, tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel),
+			tw->tw_priority, tw->tw_txhash);
 
 #ifdef CONFIG_TCP_AO
 out:
@@ -1267,15 +1272,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	/* RFC 7323 2.3
-	 * The window field (SEG.WND) of every outgoing segment, with the
-	 * exception of <SYN> segments, MUST be right-shifted by
-	 * Rcv.Wind.Shift bits:
-	 */
 	tcp_v6_send_ack(sk, skb, (sk->sk_state == TCP_LISTEN) ?
 			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
 			tcp_rsk(req)->rcv_nxt,
-			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
+			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
 			tcp_rsk_tsval(tcp_rsk(req)),
 			READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
 			&key, ipv6_get_dsfield(ipv6_hdr(skb)), 0,
@@ -1439,7 +1439,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	 */
 
 	newsk->sk_gso_type = SKB_GSO_TCPV6;
-	ip6_dst_store(newsk, dst, NULL, NULL);
 	inet6_sk_rx_dst_set(newsk, skb);
 
 	inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk);
@@ -1450,6 +1449,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
+	ip6_dst_store(newsk, dst, NULL, NULL);
+
 	newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
 	newnp->saddr = ireq->ir_v6_loc_addr;
 	newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
@@ -1620,10 +1621,9 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	   by tcp. Feel free to propose better solution.
 					       --ANK (980728)
 	 */
-	if (np->rxopt.all)
+	if (np->rxopt.all && sk->sk_state != TCP_LISTEN)
 		opt_skb = skb_clone_and_charge_r(skb, sk);
 
-	reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
 		struct dst_entry *dst;
 
@@ -1653,31 +1653,30 @@ int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
 	if (sk->sk_state == TCP_LISTEN) {
 		struct sock *nsk = tcp_v6_cookie_check(sk, skb);
 
-		if (!nsk)
-			goto discard;
-
 		if (nsk != sk) {
-			if (tcp_child_process(sk, nsk, skb))
-				goto reset;
-			if (opt_skb)
-				__kfree_skb(opt_skb);
+			if (nsk) {
+				reason = tcp_child_process(sk, nsk, skb);
+				if (reason)
+					goto reset;
+			}
 			return 0;
 		}
 	} else
 		sock_rps_save_rxhash(sk, skb);
 
-	if (tcp_rcv_state_process(sk, skb))
+	reason = tcp_rcv_state_process(sk, skb);
+	if (reason)
 		goto reset;
 	if (opt_skb)
 		goto ipv6_pktoptions;
 	return 0;
 
 reset:
-	tcp_v6_send_reset(sk, skb);
+	tcp_v6_send_reset(sk, skb, sk_rst_convert_drop_reason(reason));
 discard:
 	if (opt_skb)
 		__kfree_skb(opt_skb);
-	kfree_skb_reason(skb, reason);
+	sk_skb_reason_drop(sk, skb, reason);
 	return 0;
 csum_err:
 	reason = SKB_DROP_REASON_TCP_CSUM;
@@ -1737,7 +1736,6 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 				    skb->len - th->doff*4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
 	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
-	TCP_SKB_CB(skb)->tcp_tw_isn = 0;
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
@@ -1751,9 +1749,10 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 	int dif = inet6_iif(skb);
 	const struct tcphdr *th;
 	const struct ipv6hdr *hdr;
+	struct sock *sk = NULL;
 	bool refcounted;
-	struct sock *sk;
 	int ret;
+	u32 isn;
 	struct net *net = dev_net(skb->dev);
 
 	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
@@ -1790,7 +1789,6 @@ lookup:
 	if (!sk)
 		goto no_tcp_socket;
 
-process:
 	if (sk->sk_state == TCP_TIME_WAIT)
 		goto do_time_wait;
 
@@ -1856,15 +1854,21 @@ process:
 		if (nsk == sk) {
 			reqsk_put(req);
 			tcp_v6_restore_cb(skb);
-		} else if (tcp_child_process(sk, nsk, skb)) {
-			tcp_v6_send_reset(nsk, skb);
-			goto discard_and_relse;
 		} else {
+			drop_reason = tcp_child_process(sk, nsk, skb);
+			if (drop_reason) {
+				enum sk_rst_reason rst_reason;
+
+				rst_reason = sk_rst_convert_drop_reason(drop_reason);
+				tcp_v6_send_reset(nsk, skb, rst_reason);
+				goto discard_and_relse;
+			}
 			sock_put(sk);
 			return 0;
 		}
 	}
 
+process:
 	if (static_branch_unlikely(&ip6_min_hopcount)) {
 		/* min_hopcount can be changed concurrently from do_ipv6_setsockopt() */
 		if (unlikely(hdr->hop_limit < READ_ONCE(tcp_inet6_sk(sk)->min_hopcount))) {
@@ -1933,12 +1937,12 @@ csum_error:
 bad_packet:
 		__TCP_INC_STATS(net, TCP_MIB_INERRS);
 	} else {
-		tcp_v6_send_reset(NULL, skb);
+		tcp_v6_send_reset(NULL, skb, sk_rst_convert_drop_reason(drop_reason));
 	}
 
 discard_it:
 	SKB_DR_OR(drop_reason, NOT_SPECIFIED);
-	kfree_skb_reason(skb, drop_reason);
+	sk_skb_reason_drop(sk, skb, drop_reason);
 	return 0;
 
 discard_and_relse:
@@ -1961,7 +1965,7 @@ do_time_wait:
 		goto csum_error;
 	}
 
-	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
+	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) {
 	case TCP_TW_SYN:
 	{
 		struct sock *sk2;
@@ -1979,6 +1983,7 @@ do_time_wait:
 			sk = sk2;
 			tcp_v6_restore_cb(skb);
 			refcounted = false;
+			__this_cpu_write(tcp_tw_isn, isn);
 			goto process;
 		}
 	}
@@ -1988,7 +1993,7 @@ do_time_wait:
 		tcp_v6_timewait_ack(sk, skb);
 		break;
 	case TCP_TW_RST:
-		tcp_v6_send_reset(sk, skb);
+		tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET);
 		inet_twsk_deschedule_put(inet_twsk(sk));
 		goto discard_it;
 	case TCP_TW_SUCCESS:
@@ -2038,7 +2043,6 @@ void tcp_v6_early_demux(struct sk_buff *skb)
 
 static struct timewait_sock_ops tcp6_timewait_sock_ops = {
 	.twsk_obj_size	= sizeof(struct tcp6_timewait_sock),
-	.twsk_unique	= tcp_twsk_unique,
 	.twsk_destructor = tcp_twsk_destructor,
 };
 
@@ -2174,6 +2178,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	const struct tcp_sock *tp = tcp_sk(sp);
 	const struct inet_connection_sock *icsk = inet_csk(sp);
 	const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq;
+	u8 icsk_pending;
 	int rx_queue;
 	int state;
 
@@ -2182,12 +2187,13 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
 	destp = ntohs(inet->inet_dport);
 	srcp  = ntohs(inet->inet_sport);
 
-	if (icsk->icsk_pending == ICSK_TIME_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT ||
-	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+	icsk_pending = smp_load_acquire(&icsk->icsk_pending);
+	if (icsk_pending == ICSK_TIME_RETRANS ||
+	    icsk_pending == ICSK_TIME_REO_TIMEOUT ||
+	    icsk_pending == ICSK_TIME_LOSS_PROBE) {
 		timer_active	= 1;
 		timer_expires	= icsk->icsk_timeout;
-	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
+	} else if (icsk_pending == ICSK_TIME_PROBE0) {
 		timer_active	= 4;
 		timer_expires	= icsk->icsk_timeout;
 	} else if (timer_pending(&sp->sk_timer)) {
@@ -2256,7 +2262,7 @@ static void get_timewait6_sock(struct seq_file *seq,
 		   src->s6_addr32[2], src->s6_addr32[3], srcp,
 		   dest->s6_addr32[0], dest->s6_addr32[1],
 		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
-		   tw->tw_substate, 0, 0,
+		   READ_ONCE(tw->tw_substate), 0, 0,
 		   3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
 		   refcount_read(&tw->tw_refcnt), tw);
 }
@@ -2365,11 +2371,6 @@ struct proto tcpv6_prot = {
 };
 EXPORT_SYMBOL_GPL(tcpv6_prot);
 
-static const struct inet6_protocol tcpv6_protocol = {
-	.handler	=	tcp_v6_rcv,
-	.err_handler	=	tcp_v6_err,
-	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
-};
 
 static struct inet_protosw tcpv6_protosw = {
 	.type		=	SOCK_STREAM,
@@ -2382,8 +2383,14 @@ static struct inet_protosw tcpv6_protosw = {
 
 static int __net_init tcpv6_net_init(struct net *net)
 {
-	return inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
-				    SOCK_RAW, IPPROTO_TCP, net);
+	int res;
+
+	res = inet_ctl_sock_create(&net->ipv6.tcp_sk, PF_INET6,
+				   SOCK_RAW, IPPROTO_TCP, net);
+	if (!res)
+		net->ipv6.tcp_sk->sk_clockid = CLOCK_MONOTONIC;
+
+	return res;
 }
 
 static void __net_exit tcpv6_net_exit(struct net *net)
@@ -2391,22 +2398,21 @@ static void __net_exit tcpv6_net_exit(struct net *net)
 	inet_ctl_sock_destroy(net->ipv6.tcp_sk);
 }
 
-static void __net_exit tcpv6_net_exit_batch(struct list_head *net_exit_list)
-{
-	tcp_twsk_purge(net_exit_list, AF_INET6);
-}
-
 static struct pernet_operations tcpv6_net_ops = {
 	.init	    = tcpv6_net_init,
 	.exit	    = tcpv6_net_exit,
-	.exit_batch = tcpv6_net_exit_batch,
 };
 
 int __init tcpv6_init(void)
 {
 	int ret;
 
-	ret = inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP);
+	net_hotdata.tcpv6_protocol = (struct inet6_protocol) {
+		.handler     = tcp_v6_rcv,
+		.err_handler = tcp_v6_err,
+		.flags	     = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL,
+	};
+	ret = inet6_add_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP);
 	if (ret)
 		goto out;
 
@@ -2431,7 +2437,7 @@ out_tcpv6_pernet_subsys:
 out_tcpv6_protosw:
 	inet6_unregister_protosw(&tcpv6_protosw);
 out_tcpv6_protocol:
-	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
+	inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP);
 	goto out;
 }
 
@@ -2439,5 +2445,5 @@ void tcpv6_exit(void)
 {
 	unregister_pernet_subsys(&tcpv6_net_ops);
 	inet6_unregister_protosw(&tcpv6_protosw);
-	inet6_del_protocol(&tcpv6_protocol, IPPROTO_TCP);
+	inet6_del_protocol(&net_hotdata.tcpv6_protocol, IPPROTO_TCP);
 }