Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Cross-merge networking fixes after downstream PR.

No conflicts or adjacent changes.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

11 files changed, 73 insertions, 68 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index ba06ed42e428..2be2d4922557 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -1132,7 +1132,7 @@ static int esp_init_authenc(struct xfrm_state *x,
 	err = crypto_aead_setkey(aead, key, keylen);
 
 free_key:
-	kfree(key);
+	kfree_sensitive(key);
 
 error:
 	return err;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0cc19cfbb673..aeebe8816689 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1019,7 +1019,7 @@ static void reqsk_timer_handler(struct timer_list *t)
 
 	icsk = inet_csk(sk_listener);
 	net = sock_net(sk_listener);
-	max_syn_ack_retries = icsk->icsk_syn_retries ? :
+	max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? :
 		READ_ONCE(net->ipv4.sysctl_tcp_synack_retries);
 	/* Normally all the openreqs are young and become mature
 	 * (i.e. converted to established socket) for first timeout.
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index e7391bf310a7..0819d6001b9a 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -650,20 +650,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	spin_lock(lock);
 	if (osk) {
 		WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
-		ret = sk_hashed(osk);
-		if (ret) {
-			/* Before deleting the node, we insert a new one to make
-			 * sure that the look-up-sk process would not miss either
-			 * of them and that at least one node would exist in ehash
-			 * table all the time. Otherwise there's a tiny chance
-			 * that lookup process could find nothing in ehash table.
-			 */
-			__sk_nulls_add_node_tail_rcu(sk, list);
-			sk_nulls_del_node_init_rcu(osk);
-		}
-		goto unlock;
-	}
-	if (found_dup_sk) {
+		ret = sk_nulls_del_node_init_rcu(osk);
+	} else if (found_dup_sk) {
 		*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
 		if (*found_dup_sk)
 			ret = false;
@@ -672,7 +660,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 	if (ret)
 		__sk_nulls_add_node_rcu(sk, list);
 
-unlock:
 	spin_unlock(lock);
 
 	return ret;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 40052414c7c7..2c1b245dba8e 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -88,10 +88,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw)
 }
 EXPORT_SYMBOL_GPL(inet_twsk_put);
 
-static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw,
-					struct hlist_nulls_head *list)
+static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+				   struct hlist_nulls_head *list)
 {
-	hlist_nulls_add_tail_rcu(&tw->tw_node, list);
+	hlist_nulls_add_head_rcu(&tw->tw_node, list);
 }
 
 static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw,
@@ -144,7 +144,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
 
 	spin_lock(lock);
 
-	inet_twsk_add_node_tail_rcu(tw, &ehead->chain);
+	inet_twsk_add_node_rcu(tw, &ehead->chain);
 
 	/* Step 3: Remove SK from hash chain */
 	if (__sk_nulls_del_node_init_rcu(sk))
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 81a1cce1a7d1..22a26d1d29a0 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -548,7 +548,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto err_free_skb;
 
 	if (skb->len > dev->mtu + dev->hard_header_len) {
-		pskb_trim(skb, dev->mtu + dev->hard_header_len);
+		if (pskb_trim(skb, dev->mtu + dev->hard_header_len))
+			goto err_free_skb;
 		truncate = true;
 	}
 
@@ -689,7 +690,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 		goto free_skb;
 
 	if (skb->len > dev->mtu + dev->hard_header_len) {
-		pskb_trim(skb, dev->mtu + dev->hard_header_len);
+		if (pskb_trim(skb, dev->mtu + dev->hard_header_len))
+			goto free_skb;
 		truncate = true;
 	}
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 88f4ebab12ac..aca5620cf3ba 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3292,7 +3292,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val)
 		return -EINVAL;
 
 	lock_sock(sk);
-	inet_csk(sk)->icsk_syn_retries = val;
+	WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val);
 	release_sock(sk);
 	return 0;
 }
@@ -3301,7 +3301,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt);
 void tcp_sock_set_user_timeout(struct sock *sk, u32 val)
 {
 	lock_sock(sk);
-	inet_csk(sk)->icsk_user_timeout = val;
+	WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val);
 	release_sock(sk);
 }
 EXPORT_SYMBOL(tcp_sock_set_user_timeout);
@@ -3313,7 +3313,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val)
 	if (val < 1 || val > MAX_TCP_KEEPIDLE)
 		return -EINVAL;
 
-	tp->keepalive_time = val * HZ;
+	/* Paired with WRITE_ONCE() in keepalive_time_when() */
+	WRITE_ONCE(tp->keepalive_time, val * HZ);
 	if (sock_flag(sk, SOCK_KEEPOPEN) &&
 	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
 		u32 elapsed = keepalive_time_elapsed(tp);
@@ -3345,7 +3346,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val)
 		return -EINVAL;
 
 	lock_sock(sk);
-	tcp_sk(sk)->keepalive_intvl = val * HZ;
+	WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ);
 	release_sock(sk);
 	return 0;
 }
@@ -3357,7 +3358,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val)
 		return -EINVAL;
 
 	lock_sock(sk);
-	tcp_sk(sk)->keepalive_probes = val;
+	/* Paired with READ_ONCE() in keepalive_probes() */
+	WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val);
 	release_sock(sk);
 	return 0;
 }
@@ -3559,19 +3561,19 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		if (val < 1 || val > MAX_TCP_KEEPINTVL)
 			err = -EINVAL;
 		else
-			tp->keepalive_intvl = val * HZ;
+			WRITE_ONCE(tp->keepalive_intvl, val * HZ);
 		break;
 	case TCP_KEEPCNT:
 		if (val < 1 || val > MAX_TCP_KEEPCNT)
 			err = -EINVAL;
 		else
-			tp->keepalive_probes = val;
+			WRITE_ONCE(tp->keepalive_probes, val);
 		break;
 	case TCP_SYNCNT:
 		if (val < 1 || val > MAX_TCP_SYNCNT)
 			err = -EINVAL;
 		else
-			icsk->icsk_syn_retries = val;
+			WRITE_ONCE(icsk->icsk_syn_retries, val);
 		break;
 
 	case TCP_SAVE_SYN:
@@ -3584,18 +3586,18 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 
 	case TCP_LINGER2:
 		if (val < 0)
-			tp->linger2 = -1;
+			WRITE_ONCE(tp->linger2, -1);
 		else if (val > TCP_FIN_TIMEOUT_MAX / HZ)
-			tp->linger2 = TCP_FIN_TIMEOUT_MAX;
+			WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX);
 		else
-			tp->linger2 = val * HZ;
+			WRITE_ONCE(tp->linger2, val * HZ);
 		break;
 
 	case TCP_DEFER_ACCEPT:
 		/* Translate value in seconds to number of retransmits */
-		icsk->icsk_accept_queue.rskq_defer_accept =
-			secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
-					TCP_RTO_MAX / HZ);
+		WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept,
+			   secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
+					   TCP_RTO_MAX / HZ));
 		break;
 
 	case TCP_WINDOW_CLAMP:
@@ -3619,7 +3621,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		if (val < 0)
 			err = -EINVAL;
 		else
-			icsk->icsk_user_timeout = val;
+			WRITE_ONCE(icsk->icsk_user_timeout, val);
 		break;
 
 	case TCP_FASTOPEN:
@@ -3657,13 +3659,13 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		if (!tp->repair)
 			err = -EPERM;
 		else
-			tp->tsoffset = val - tcp_time_stamp_raw();
+			WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw());
 		break;
 	case TCP_REPAIR_WINDOW:
 		err = tcp_repair_set_window(tp, optval, optlen);
 		break;
 	case TCP_NOTSENT_LOWAT:
-		tp->notsent_lowat = val;
+		WRITE_ONCE(tp->notsent_lowat, val);
 		sk->sk_write_space(sk);
 		break;
 	case TCP_INQ:
@@ -3675,7 +3677,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 	case TCP_TX_DELAY:
 		if (val)
 			tcp_enable_tx_delay();
-		tp->tcp_tx_delay = val;
+		WRITE_ONCE(tp->tcp_tx_delay, val);
 		break;
 	default:
 		err = -ENOPROTOOPT;
@@ -3992,17 +3994,18 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		val = keepalive_probes(tp);
 		break;
 	case TCP_SYNCNT:
-		val = icsk->icsk_syn_retries ? :
+		val = READ_ONCE(icsk->icsk_syn_retries) ? :
 			READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
 		break;
 	case TCP_LINGER2:
-		val = tp->linger2;
+		val = READ_ONCE(tp->linger2);
 		if (val >= 0)
 			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,
-				      TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ);
+		val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept);
+		val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ,
+				      TCP_RTO_MAX / HZ);
 		break;
 	case TCP_WINDOW_CLAMP:
 		val = tp->window_clamp;
@@ -4139,11 +4142,11 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_USER_TIMEOUT:
-		val = icsk->icsk_user_timeout;
+		val = READ_ONCE(icsk->icsk_user_timeout);
 		break;
 
 	case TCP_FASTOPEN:
-		val = icsk->icsk_accept_queue.fastopenq.max_qlen;
+		val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen);
 		break;
 
 	case TCP_FASTOPEN_CONNECT:
@@ -4155,14 +4158,14 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_TX_DELAY:
-		val = tp->tcp_tx_delay;
+		val = READ_ONCE(tp->tcp_tx_delay);
 		break;
 
 	case TCP_TIMESTAMP:
-		val = tcp_time_stamp_raw() + tp->tsoffset;
+		val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset);
 		break;
 	case TCP_NOTSENT_LOWAT:
-		val = tp->notsent_lowat;
+		val = READ_ONCE(tp->notsent_lowat);
 		break;
 	case TCP_INQ:
 		val = tp->recvmsg_inq;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 45cc7f1ca296..85e4953f1182 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -296,6 +296,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 static bool tcp_fastopen_queue_check(struct sock *sk)
 {
 	struct fastopen_queue *fastopenq;
+	int max_qlen;
 
 	/* Make sure the listener has enabled fastopen, and we don't
 	 * exceed the max # of pending TFO requests allowed before trying
@@ -308,10 +309,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk)
 	 * temporarily vs a server not supporting Fast Open at all.
 	 */
 	fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq;
-	if (fastopenq->max_qlen == 0)
+	max_qlen = READ_ONCE(fastopenq->max_qlen);
+	if (max_qlen == 0)
 		return false;
 
-	if (fastopenq->qlen >= fastopenq->max_qlen) {
+	if (fastopenq->qlen >= max_qlen) {
 		struct request_sock *req1;
 		spin_lock(&fastopenq->lock);
 		req1 = fastopenq->rskq_rst_head;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cecd5a135e64..09cffbc82d32 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -308,8 +308,9 @@ 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(net, inet->inet_saddr,
-						 inet->inet_daddr);
+		WRITE_ONCE(tp->tsoffset,
+			   secure_tcp_ts_off(net, inet->inet_saddr,
+					     inet->inet_daddr));
 	}
 
 	inet->inet_id = get_random_u16();
@@ -989,11 +990,12 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_nxt,
 			req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
-			req->ts_recent,
+			READ_ONCE(req->ts_recent),
 			0,
 			tcp_md5_do_lookup(sk, l3index, addr, AF_INET),
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
-			ip_hdr(skb)->tos, tcp_rsk(req)->txhash);
+			ip_hdr(skb)->tos,
+			READ_ONCE(tcp_rsk(req)->txhash));
 }
 
 /*
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 04fc328727e6..c8f2aa003387 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -528,7 +528,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
 
 	newtp->lsndtime = tcp_jiffies32;
-	newsk->sk_txhash = treq->txhash;
+	newsk->sk_txhash = READ_ONCE(treq->txhash);
 	newtp->total_retrans = req->num_retrans;
 
 	tcp_init_xmit_timers(newsk);
@@ -555,7 +555,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	newtp->max_window = newtp->snd_wnd;
 
 	if (newtp->rx_opt.tstamp_ok) {
-		newtp->rx_opt.ts_recent = req->ts_recent;
+		newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent);
 		newtp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 		newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
 	} else {
@@ -619,7 +619,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
-			tmp_opt.ts_recent = req->ts_recent;
+			tmp_opt.ts_recent = READ_ONCE(req->ts_recent);
 			if (tmp_opt.rcv_tsecr)
 				tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off;
 			/* We do not store true stamp, but it is not required,
@@ -758,8 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	/* In sequence, PAWS is OK. */
 
+	/* TODO: We probably should defer ts_recent change once
+	 * we take ownership of @req.
+	 */
 	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
-		req->ts_recent = tmp_opt.rcv_tsval;
+		WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
 
 	if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
 		/* Truncate SYN, it is out of window starting
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 2cb39b6dad02..51d8638d4b4c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -878,7 +878,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 	if (likely(ireq->tstamp_ok)) {
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off;
-		opts->tsecr = req->ts_recent;
+		opts->tsecr = READ_ONCE(req->ts_recent);
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
 	if (likely(ireq->sack_ok)) {
@@ -3660,7 +3660,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	rcu_read_lock();
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
-	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+	skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4);
 	/* bpf program will be interested in the tcp_flags */
 	TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
@@ -4210,7 +4210,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 
 	/* Paired with WRITE_ONCE() in sock_setsockopt() */
 	if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED)
-		tcp_rsk(req)->txhash = net_tx_rndhash();
+		WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash());
 	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
 				  NULL);
 	if (!res) {
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 75aa4de5b731..f402946da344 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -274,13 +274,20 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	__sum16 check;
 	__be16 newlen;
 
-	if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)
-		return __udp_gso_segment_list(gso_skb, features, is_ipv6);
-
 	mss = skb_shinfo(gso_skb)->gso_size;
 	if (gso_skb->len <= sizeof(*uh) + mss)
 		return ERR_PTR(-EINVAL);
 
+	if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
+		/* Packet is from an untrusted source, reset gso_segs. */
+		skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
+							     mss);
+		return NULL;
+	}
+
+	if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)
+		return __udp_gso_segment_list(gso_skb, features, is_ipv6);
+
 	skb_pull(gso_skb, sizeof(*uh));
 
 	/* clear destructor to avoid skb_segment assigning it to tail */
@@ -388,8 +395,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
 		goto out;
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 &&
-	    !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST))
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
 		return __udp_gso_segment(skb, features, false);
 
 	mss = skb_shinfo(skb)->gso_size;