1 files changed, 49 insertions, 59 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf18fbcbf123..766881775abb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -429,7 +429,7 @@ void tcp_init_sock(struct sock *sk)
 	 * algorithms that we must have the following bandaid to talk
 	 * efficiently to them.  -DaveM
 	 */
-	tp->snd_cwnd = TCP_INIT_CWND;
+	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 
 	/* There's a bubble in the pipe until at least the first ACK. */
 	tp->app_limited = ~0U;
@@ -441,7 +441,7 @@ void tcp_init_sock(struct sock *sk)
 	tp->snd_cwnd_clamp = ~0;
 	tp->mss_cache = TCP_MSS_DEFAULT;
 
-	tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
+	tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering);
 	tcp_assign_congestion_control(sk);
 
 	tp->tsoffset = 0;
@@ -452,8 +452,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
-	WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+	WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
 
 	sk_sockets_allocated_inc(sk);
 }
@@ -686,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 				int size_goal)
 {
 	return skb->len < size_goal &&
-	       sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+	       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
 	       !tcp_rtx_queue_empty(sk) &&
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize &&
 	       tcp_skb_can_collapse_to(skb);
@@ -843,7 +843,6 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 	}
 
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 
 	if (spliced)
 		return spliced;
@@ -1151,7 +1150,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	struct sockaddr *uaddr = msg->msg_name;
 	int err, flags;
 
-	if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+	if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) &
+	      TFO_CLIENT_ENABLE) ||
 	    (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
 	     uaddr->sa_family == AF_UNSPEC))
 		return -EOPNOTSUPP;
@@ -1589,20 +1589,6 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
-void __sk_defer_free_flush(struct sock *sk)
-{
-	struct llist_node *head;
-	struct sk_buff *skb, *n;
-
-	head = llist_del_all(&sk->defer_list);
-	llist_for_each_entry_safe(skb, n, head, ll_node) {
-		prefetch(n);
-		skb_mark_not_on_list(skb);
-		__kfree_skb(skb);
-	}
-}
-EXPORT_SYMBOL(__sk_defer_free_flush);
-
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
@@ -1610,11 +1596,7 @@ static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 		sock_rfree(skb);
 		skb->destructor = NULL;
 		skb->sk = NULL;
-		if (!skb_queue_empty(&sk->sk_receive_queue) ||
-		    !llist_empty(&sk->defer_list)) {
-			llist_add(&skb->ll_node, &sk->defer_list);
-			return;
-		}
+		return skb_attempt_defer_free(skb);
 	}
 	__kfree_skb(skb);
 }
@@ -1742,7 +1724,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
 		cap = sk->sk_rcvbuf >> 1;
 	else
-		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+		cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
 	val = min(val, cap);
 	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
@@ -1877,8 +1859,7 @@ static void tcp_zerocopy_set_hint_for_skb(struct sock *sk,
 }
 
 static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
-			      int nonblock, int flags,
-			      struct scm_timestamping_internal *tss,
+			      int flags, struct scm_timestamping_internal *tss,
 			      int *cmsg_flags);
 static int receive_fallback_to_copy(struct sock *sk,
 				    struct tcp_zerocopy_receive *zc, int inq,
@@ -1900,7 +1881,7 @@ static int receive_fallback_to_copy(struct sock *sk,
 	if (err)
 		return err;
 
-	err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0,
+	err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT,
 				 tss, &zc->msg_flags);
 	if (err < 0)
 		return err;
@@ -2316,8 +2297,7 @@ static int tcp_inq_hint(struct sock *sk)
  */
 
 static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
-			      int nonblock, int flags,
-			      struct scm_timestamping_internal *tss,
+			      int flags, struct scm_timestamping_internal *tss,
 			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2335,9 +2315,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	if (tp->recvmsg_inq)
+	if (tp->recvmsg_inq) {
 		*cmsg_flags = TCP_CMSG_INQ;
-	timeo = sock_rcvtimeo(sk, nonblock);
+		msg->msg_get_inq = 1;
+	}
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	/* Urgent data needs to be handled specially. */
 	if (flags & MSG_OOB)
@@ -2455,7 +2437,6 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			__sk_flush_backlog(sk);
 		} else {
 			tcp_cleanup_rbuf(sk, copied);
-			sk_defer_free_flush(sk);
 			sk_wait_data(sk, &timeo, last);
 		}
 
@@ -2556,10 +2537,10 @@ recv_sndq:
 	goto out;
 }
 
-int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
-		int flags, int *addr_len)
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
+		int *addr_len)
 {
-	int cmsg_flags = 0, ret, inq;
+	int cmsg_flags = 0, ret;
 	struct scm_timestamping_internal tss;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
@@ -2568,20 +2549,20 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (sk_can_busy_loop(sk) &&
 	    skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    sk->sk_state == TCP_ESTABLISHED)
-		sk_busy_loop(sk, nonblock);
+		sk_busy_loop(sk, flags & MSG_DONTWAIT);
 
 	lock_sock(sk);
-	ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss,
-				 &cmsg_flags);
+	ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags);
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 
-	if (cmsg_flags && ret >= 0) {
+	if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
 		if (cmsg_flags & TCP_CMSG_TS)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (cmsg_flags & TCP_CMSG_INQ) {
-			inq = tcp_inq_hint(sk);
-			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+		if (msg->msg_get_inq) {
+			msg->msg_inq = tcp_inq_hint(sk);
+			if (cmsg_flags & TCP_CMSG_INQ)
+				put_cmsg(msg, SOL_TCP, TCP_CM_INQ,
+					 sizeof(msg->msg_inq), &msg->msg_inq);
 		}
 	}
 	return ret;
@@ -2735,7 +2716,8 @@ static void tcp_orphan_update(struct timer_list *unused)
 
 static bool tcp_too_many_orphans(int shift)
 {
-	return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans;
+	return READ_ONCE(tcp_orphan_cache) << shift >
+		READ_ONCE(sysctl_tcp_max_orphans);
 }
 
 bool tcp_check_oom(struct sock *sk, int shift)
@@ -3033,7 +3015,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_rto_min = TCP_RTO_MIN;
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-	tp->snd_cwnd = TCP_INIT_CWND;
+	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tp->delivered = 0;
@@ -3099,7 +3081,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 		sk->sk_frag.page = NULL;
 		sk->sk_frag.offset = 0;
 	}
-	sk_defer_free_flush(sk);
 	sk_error_report(sk);
 	return 0;
 }
@@ -3637,7 +3618,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_FASTOPEN_CONNECT:
 		if (val > 1 || val < 0) {
 			err = -EINVAL;
-		} else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+		} else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) &
+			   TFO_CLIENT_ENABLE) {
 			if (sk->sk_state == TCP_CLOSE)
 				tp->fastopen_connect = val;
 			else
@@ -3744,7 +3726,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_max_pacing_rate = rate64;
 
 	info->tcpi_reordering = tp->reordering;
-	info->tcpi_snd_cwnd = tp->snd_cwnd;
+	info->tcpi_snd_cwnd = tcp_snd_cwnd(tp);
 
 	if (info->tcpi_state == TCP_LISTEN) {
 		/* listeners aliased fields :
@@ -3915,7 +3897,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 	rate64 = tcp_compute_delivery_rate(tp);
 	nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD);
 
-	nla_put_u32(stats, TCP_NLA_SND_CWND, tp->snd_cwnd);
+	nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp));
 	nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering);
 	nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp));
 
@@ -3987,12 +3969,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = keepalive_probes(tp);
 		break;
 	case TCP_SYNCNT:
-		val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
+		val = icsk->icsk_syn_retries ? :
+			READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
 		break;
 	case TCP_LINGER2:
 		val = tp->linger2;
 		if (val >= 0)
-			val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
+			val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
 		break;
 	case TCP_DEFER_ACCEPT:
 		val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
@@ -4228,7 +4211,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
 							  &zc, &len, err);
 		release_sock(sk);
-		sk_defer_free_flush(sk);
 		if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
 			goto zerocopy_rcv_cmsg;
 		switch (len) {
@@ -4477,9 +4459,18 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb,
 		return SKB_DROP_REASON_TCP_MD5UNEXPECTED;
 	}
 
-	/* check the signature */
-	genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected,
-						 NULL, skb);
+	/* Check the signature.
+	 * To support dual stack listeners, we need to handle
+	 * IPv4-mapped case.
+	 */
+	if (family == AF_INET)
+		genhash = tcp_v4_md5_hash_skb(newhash,
+					      hash_expected,
+					      NULL, skb);
+	else
+		genhash = tp->af_specific->calc_md5_hash(newhash,
+							 hash_expected,
+							 NULL, skb);
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
@@ -4617,7 +4608,6 @@ void __init tcp_init(void)
 	timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE);
 	mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD);
 
-	inet_hashinfo_init(&tcp_hashinfo);
 	inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash",
 			    thash_entries, 21,  /* one slot per 2 MB*/
 			    0, 64 * 1024);