1 files changed, 81 insertions, 64 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 79c325a07ba5..8a39ee794891 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -326,7 +326,7 @@ void tcp_enter_memory_pressure(struct sock *sk)
 {
 	unsigned long val;
 
-	if (tcp_memory_pressure)
+	if (READ_ONCE(tcp_memory_pressure))
 		return;
 	val = jiffies;
 
@@ -341,7 +341,7 @@ void tcp_leave_memory_pressure(struct sock *sk)
 {
 	unsigned long val;
 
-	if (!tcp_memory_pressure)
+	if (!READ_ONCE(tcp_memory_pressure))
 		return;
 	val = xchg(&tcp_memory_pressure, 0);
 	if (val)
@@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_sync_mss = tcp_sync_mss;
 
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
-	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
+	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]);
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_route_forced_caps = NETIF_F_GSO;
@@ -477,7 +477,7 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags)
 static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 					  int target, struct sock *sk)
 {
-	return (tp->rcv_nxt - tp->copied_seq >= target) ||
+	return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) ||
 		(sk->sk_prot->stream_memory_read ?
 		sk->sk_prot->stream_memory_read(sk) : false);
 }
@@ -543,10 +543,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 	/* Connected or passive Fast Open socket? */
 	if (state != TCP_SYN_SENT &&
-	    (state != TCP_SYN_RECV || tp->fastopen_rsk)) {
+	    (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) {
 		int target = sock_rcvlowat(sk, 0, INT_MAX);
 
-		if (tp->urg_seq == tp->copied_seq &&
+		if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) &&
 		    !sock_flag(sk, SOCK_URGINLINE) &&
 		    tp->urg_data)
 			target++;
@@ -584,7 +584,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR;
 
 	return mask;
@@ -607,7 +607,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		unlock_sock_fast(sk, slow);
 		break;
 	case SIOCATMARK:
-		answ = tp->urg_data && tp->urg_seq == tp->copied_seq;
+		answ = tp->urg_data &&
+		       READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq);
 		break;
 	case SIOCOUTQ:
 		if (sk->sk_state == TCP_LISTEN)
@@ -616,7 +617,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = tp->write_seq - tp->snd_una;
+			answ = READ_ONCE(tp->write_seq) - tp->snd_una;
 		break;
 	case SIOCOUTQNSD:
 		if (sk->sk_state == TCP_LISTEN)
@@ -625,7 +626,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
 			answ = 0;
 		else
-			answ = tp->write_seq - tp->snd_nxt;
+			answ = READ_ONCE(tp->write_seq) -
+			       READ_ONCE(tp->snd_nxt);
 		break;
 	default:
 		return -ENOIOCTLCMD;
@@ -657,7 +659,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb)
 	tcb->sacked  = 0;
 	__skb_header_release(skb);
 	tcp_add_write_queue_tail(sk, skb);
-	sk->sk_wmem_queued += skb->truesize;
+	sk_wmem_queued_add(sk, skb->truesize);
 	sk_mem_charge(sk, skb->truesize);
 	if (tp->nonagle & TCP_NAGLE_PUSH)
 		tp->nonagle &= ~TCP_NAGLE_PUSH;
@@ -1032,10 +1034,10 @@ new_segment:
 		skb->len += copy;
 		skb->data_len += copy;
 		skb->truesize += copy;
-		sk->sk_wmem_queued += copy;
+		sk_wmem_queued_add(sk, copy);
 		sk_mem_charge(sk, copy);
 		skb->ip_summed = CHECKSUM_PARTIAL;
-		tp->write_seq += copy;
+		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 		TCP_SKB_CB(skb)->end_seq += copy;
 		tcp_skb_pcount_set(skb, 0);
 
@@ -1362,7 +1364,7 @@ new_segment:
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
 
-		tp->write_seq += copy;
+		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
 		TCP_SKB_CB(skb)->end_seq += copy;
 		tcp_skb_pcount_set(skb, 0);
 
@@ -1668,9 +1670,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		sk_eat_skb(sk, skb);
 		if (!desc->count)
 			break;
-		tp->copied_seq = seq;
+		WRITE_ONCE(tp->copied_seq, seq);
 	}
-	tp->copied_seq = seq;
+	WRITE_ONCE(tp->copied_seq, seq);
 
 	tcp_rcv_space_adjust(sk);
 
@@ -1699,7 +1701,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	else
 		cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
 	val = min(val, cap);
-	sk->sk_rcvlowat = val ? : 1;
+	WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
 
 	/* Check if we need to signal EPOLLIN right now */
 	tcp_data_ready(sk);
@@ -1709,7 +1711,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 
 	val <<= 1;
 	if (val > sk->sk_rcvbuf) {
-		sk->sk_rcvbuf = val;
+		WRITE_ONCE(sk->sk_rcvbuf, val);
 		tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val);
 	}
 	return 0;
@@ -1739,8 +1741,8 @@ static int tcp_zerocopy_receive(struct sock *sk,
 				struct tcp_zerocopy_receive *zc)
 {
 	unsigned long address = (unsigned long)zc->address;
+	u32 length = 0, seq, offset, zap_len;
 	const skb_frag_t *frags = NULL;
-	u32 length = 0, seq, offset;
 	struct vm_area_struct *vma;
 	struct sk_buff *skb = NULL;
 	struct tcp_sock *tp;
@@ -1767,12 +1769,12 @@ static int tcp_zerocopy_receive(struct sock *sk,
 	seq = tp->copied_seq;
 	inq = tcp_inq(sk);
 	zc->length = min_t(u32, zc->length, inq);
-	zc->length &= ~(PAGE_SIZE - 1);
-	if (zc->length) {
-		zap_page_range(vma, address, zc->length);
+	zap_len = zc->length & ~(PAGE_SIZE - 1);
+	if (zap_len) {
+		zap_page_range(vma, address, zap_len);
 		zc->recv_skip_hint = 0;
 	} else {
-		zc->recv_skip_hint = inq;
+		zc->recv_skip_hint = zc->length;
 	}
 	ret = 0;
 	while (length + PAGE_SIZE <= zc->length) {
@@ -1798,13 +1800,11 @@ static int tcp_zerocopy_receive(struct sock *sk,
 		}
 		if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) {
 			int remaining = zc->recv_skip_hint;
-			int size = skb_frag_size(frags);
 
-			while (remaining && (size != PAGE_SIZE ||
+			while (remaining && (skb_frag_size(frags) != PAGE_SIZE ||
 					     skb_frag_off(frags))) {
-				remaining -= size;
+				remaining -= skb_frag_size(frags);
 				frags++;
-				size = skb_frag_size(frags);
 			}
 			zc->recv_skip_hint -= remaining;
 			break;
@@ -1821,7 +1821,7 @@ static int tcp_zerocopy_receive(struct sock *sk,
 out:
 	up_read(&current->mm->mmap_sem);
 	if (length) {
-		tp->copied_seq = seq;
+		WRITE_ONCE(tp->copied_seq, seq);
 		tcp_rcv_space_adjust(sk);
 
 		/* Clean up data we have read: This will do ACK frames. */
@@ -1864,29 +1864,33 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
 		if (sock_flag(sk, SOCK_RCVTSTAMP)) {
 			if (sock_flag(sk, SOCK_RCVTSTAMPNS)) {
 				if (new_tstamp) {
-					struct __kernel_timespec kts = {tss->ts[0].tv_sec, tss->ts[0].tv_nsec};
-
+					struct __kernel_timespec kts = {
+						.tv_sec = tss->ts[0].tv_sec,
+						.tv_nsec = tss->ts[0].tv_nsec,
+					};
 					put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
 						 sizeof(kts), &kts);
 				} else {
-					struct timespec ts_old = timespec64_to_timespec(tss->ts[0]);
-
+					struct __kernel_old_timespec ts_old = {
+						.tv_sec = tss->ts[0].tv_sec,
+						.tv_nsec = tss->ts[0].tv_nsec,
+					};
 					put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD,
 						 sizeof(ts_old), &ts_old);
 				}
 			} else {
 				if (new_tstamp) {
-					struct __kernel_sock_timeval stv;
-
-					stv.tv_sec = tss->ts[0].tv_sec;
-					stv.tv_usec = tss->ts[0].tv_nsec / 1000;
+					struct __kernel_sock_timeval stv = {
+						.tv_sec = tss->ts[0].tv_sec,
+						.tv_usec = tss->ts[0].tv_nsec / 1000,
+					};
 					put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW,
 						 sizeof(stv), &stv);
 				} else {
-					struct __kernel_old_timeval tv;
-
-					tv.tv_sec = tss->ts[0].tv_sec;
-					tv.tv_usec = tss->ts[0].tv_nsec / 1000;
+					struct __kernel_old_timeval tv = {
+						.tv_sec = tss->ts[0].tv_sec,
+						.tv_usec = tss->ts[0].tv_nsec / 1000,
+					};
 					put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD,
 						 sizeof(tv), &tv);
 				}
@@ -1958,13 +1962,12 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
 	struct scm_timestamping_internal tss;
-	bool has_tss = false;
-	bool has_cmsg;
+	int cmsg_flags;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
 
-	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
 		sk_busy_loop(sk, nonblock);
 
@@ -1974,7 +1977,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	has_cmsg = tp->recvmsg_inq;
+	cmsg_flags = tp->recvmsg_inq ? 1 : 0;
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	/* Urgent data needs to be handled specially. */
@@ -2047,7 +2050,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 
 		/* Well, if we have backlog, try to process it now yet. */
 
-		if (copied >= target && !sk->sk_backlog.tail)
+		if (copied >= target && !READ_ONCE(sk->sk_backlog.tail))
 			break;
 
 		if (copied) {
@@ -2119,7 +2122,7 @@ found_ok_skb:
 			if (urg_offset < used) {
 				if (!urg_offset) {
 					if (!sock_flag(sk, SOCK_URGINLINE)) {
-						++*seq;
+						WRITE_ONCE(*seq, *seq + 1);
 						urg_hole++;
 						offset++;
 						used--;
@@ -2141,7 +2144,7 @@ found_ok_skb:
 			}
 		}
 
-		*seq += used;
+		WRITE_ONCE(*seq, *seq + used);
 		copied += used;
 		len -= used;
 
@@ -2157,8 +2160,7 @@ skip_copy:
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
 			tcp_update_recv_tstamps(skb, &tss);
-			has_tss = true;
-			has_cmsg = true;
+			cmsg_flags |= 2;
 		}
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 			goto found_fin_ok;
@@ -2168,7 +2170,7 @@ skip_copy:
 
 found_fin_ok:
 		/* Process the FIN. */
-		++*seq;
+		WRITE_ONCE(*seq, *seq + 1);
 		if (!(flags & MSG_PEEK))
 			sk_eat_skb(sk, skb);
 		break;
@@ -2183,10 +2185,10 @@ found_fin_ok:
 
 	release_sock(sk);
 
-	if (has_cmsg) {
-		if (has_tss)
+	if (cmsg_flags) {
+		if (cmsg_flags & 2)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (tp->recvmsg_inq) {
+		if (cmsg_flags & 1) {
 			inq = tcp_inq_hint(sk);
 			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
 		}
@@ -2489,7 +2491,10 @@ adjudge_to_death:
 	}
 
 	if (sk->sk_state == TCP_CLOSE) {
-		struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+		struct request_sock *req;
+
+		req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk,
+						lockdep_sock_is_held(sk));
 		/* We could get here with a non-NULL req if the socket is
 		 * aborted (e.g., closed with unread data) before 3WHS
 		 * finishes.
@@ -2561,6 +2566,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	int old_state = sk->sk_state;
+	u32 seq;
 
 	if (old_state != TCP_CLOSE)
 		tcp_set_state(sk, TCP_CLOSE);
@@ -2587,7 +2593,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 		__kfree_skb(sk->sk_rx_skb_cache);
 		sk->sk_rx_skb_cache = NULL;
 	}
-	tp->copied_seq = tp->rcv_nxt;
+	WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 	tp->urg_data = 0;
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
@@ -2603,9 +2609,12 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->srtt_us = 0;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	tp->rcv_rtt_last_tsecr = 0;
-	tp->write_seq += tp->max_window + 2;
-	if (tp->write_seq == 0)
-		tp->write_seq = 1;
+
+	seq = tp->write_seq + tp->max_window + 2;
+	if (!seq)
+		seq = 1;
+	WRITE_ONCE(tp->write_seq, seq);
+
 	icsk->icsk_backoff = 0;
 	tp->snd_cwnd = 2;
 	icsk->icsk_probes_out = 0;
@@ -2659,6 +2668,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
 	inet->defer_connect = 0;
+	tp->fastopen_client_fail = 0;
 
 	WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
 
@@ -2932,9 +2942,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		if (sk->sk_state != TCP_CLOSE)
 			err = -EPERM;
 		else if (tp->repair_queue == TCP_SEND_QUEUE)
-			tp->write_seq = val;
+			WRITE_ONCE(tp->write_seq, val);
 		else if (tp->repair_queue == TCP_RECV_QUEUE)
-			tp->rcv_nxt = val;
+			WRITE_ONCE(tp->rcv_nxt, val);
 		else
 			err = -EINVAL;
 		break;
@@ -3217,8 +3227,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		 * tcpi_unacked -> Number of children ready for accept()
 		 * tcpi_sacked  -> max backlog
 		 */
-		info->tcpi_unacked = sk->sk_ack_backlog;
-		info->tcpi_sacked = sk->sk_max_ack_backlog;
+		info->tcpi_unacked = READ_ONCE(sk->sk_ack_backlog);
+		info->tcpi_sacked = READ_ONCE(sk->sk_max_ack_backlog);
 		return;
 	}
 
@@ -3298,6 +3308,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_reord_seen = tp->reord_seen;
 	info->tcpi_rcv_ooopack = tp->rcv_ooopack;
 	info->tcpi_snd_wnd = tp->snd_wnd;
+	info->tcpi_fastopen_client_fail = tp->fastopen_client_fail;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3833,7 +3844,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
 
 void tcp_done(struct sock *sk)
 {
-	struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
+	struct request_sock *req;
+
+	/* We might be called with a new socket, after
+	 * inet_csk_prepare_forced_close() has been called
+	 * so we can not use lockdep_sock_is_held(sk)
+	 */
+	req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1);
 
 	if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
 		TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS);