Merging upstream version 6.7.12.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

10 files changed, 49 insertions, 40 deletions

diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4ccfc104f1..fe501d2186 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -95,7 +95,7 @@ static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
 			     __alignof__(struct scatterlist));
 }
 
-static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
+static void esp_ssg_unref(struct xfrm_state *x, void *tmp, struct sk_buff *skb)
 {
 	struct crypto_aead *aead = x->data;
 	int extralen = 0;
@@ -114,7 +114,7 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
 	 */
 	if (req->src != req->dst)
 		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
-			put_page(sg_page(sg));
+			skb_page_unref(skb, sg_page(sg), false);
 }
 
 #ifdef CONFIG_INET_ESPINTCP
@@ -260,7 +260,7 @@ static void esp_output_done(void *data, int err)
 	}
 
 	tmp = ESP_SKB_CB(skb)->tmp;
-	esp_ssg_unref(x, tmp);
+	esp_ssg_unref(x, tmp, skb);
 	kfree(tmp);
 
 	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
@@ -639,7 +639,7 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	}
 
 	if (sg != dsg)
-		esp_ssg_unref(x, tmp);
+		esp_ssg_unref(x, tmp, skb);
 
 	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
 		err = esp_output_tail_tcp(x, skb);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 7d0e7aaa71..5f7fdbd01c 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -57,7 +57,7 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
 		return ERR_PTR(-ENOENT);
 	}
 
-	if (!inet_diag_table[proto])
+	if (!READ_ONCE(inet_diag_table[proto]))
 		sock_load_diag_module(AF_INET, proto);
 
 	mutex_lock(&inet_diag_table_mutex);
@@ -1419,7 +1419,7 @@ int inet_diag_register(const struct inet_diag_handler *h)
 	mutex_lock(&inet_diag_table_mutex);
 	err = -EEXIST;
 	if (!inet_diag_table[type]) {
-		inet_diag_table[type] = h;
+		WRITE_ONCE(inet_diag_table[type], h);
 		err = 0;
 	}
 	mutex_unlock(&inet_diag_table_mutex);
@@ -1436,7 +1436,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h)
 		return;
 
 	mutex_lock(&inet_diag_table_mutex);
-	inet_diag_table[type] = NULL;
+	WRITE_ONCE(inet_diag_table[type], NULL);
 	mutex_unlock(&inet_diag_table_mutex);
 }
 EXPORT_SYMBOL_GPL(inet_diag_unregister);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9456bf9e27..7967ff7e02 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1137,7 +1137,7 @@ error:
 		sock_prot_inuse_add(net, sk->sk_prot, -1);
 
 		spin_lock(lock);
-		sk_nulls_del_node_init_rcu(sk);
+		__sk_nulls_del_node_init_rcu(sk);
 		spin_unlock(lock);
 
 		sk->sk_hash = 0;
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index dd37a5bf68..757ae3a4e2 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -278,12 +278,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm)
 }
 EXPORT_SYMBOL_GPL(__inet_twsk_schedule);
 
+/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */
 void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family)
 {
-	struct inet_timewait_sock *tw;
-	struct sock *sk;
 	struct hlist_nulls_node *node;
 	unsigned int slot;
+	struct sock *sk;
 
 	for (slot = 0; slot <= hashinfo->ehash_mask; slot++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
@@ -292,38 +292,35 @@ restart_rcu:
 		rcu_read_lock();
 restart:
 		sk_nulls_for_each_rcu(sk, node, &head->chain) {
-			if (sk->sk_state != TCP_TIME_WAIT) {
-				/* A kernel listener socket might not hold refcnt for net,
-				 * so reqsk_timer_handler() could be fired after net is
-				 * freed.  Userspace listener and reqsk never exist here.
-				 */
-				if (unlikely(sk->sk_state == TCP_NEW_SYN_RECV &&
-					     hashinfo->pernet)) {
-					struct request_sock *req = inet_reqsk(sk);
-
-					inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);
-				}
+			int state = inet_sk_state_load(sk);
 
+			if ((1 << state) & ~(TCPF_TIME_WAIT |
+					     TCPF_NEW_SYN_RECV))
 				continue;
-			}
 
-			tw = inet_twsk(sk);
-			if ((tw->tw_family != family) ||
-				refcount_read(&twsk_net(tw)->ns.count))
+			if (sk->sk_family != family ||
+			    refcount_read(&sock_net(sk)->ns.count))
 				continue;
 
-			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
+			if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
 				continue;
 
-			if (unlikely((tw->tw_family != family) ||
-				     refcount_read(&twsk_net(tw)->ns.count))) {
-				inet_twsk_put(tw);
+			if (unlikely(sk->sk_family != family ||
+				     refcount_read(&sock_net(sk)->ns.count))) {
+				sock_gen_put(sk);
 				goto restart;
 			}
 
 			rcu_read_unlock();
 			local_bh_disable();
-			inet_twsk_deschedule_put(tw);
+			if (state == TCP_TIME_WAIT) {
+				inet_twsk_deschedule_put(inet_twsk(sk));
+			} else {
+				struct request_sock *req = inet_reqsk(sk);
+
+				inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
+								  req);
+			}
 			local_bh_enable();
 			goto restart_rcu;
 		}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 2d29fce7c5..b1b6dcf216 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -378,7 +378,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  bool log_ecn_error)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	int err;
+	int nh, err;
 
 #ifdef CONFIG_NET_IPGRE_BROADCAST
 	if (ipv4_is_multicast(iph->daddr)) {
@@ -404,8 +404,21 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		tunnel->i_seqno = ntohl(tpi->seq) + 1;
 	}
 
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0);
 
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(tunnel->dev, rx_length_errors);
+		DEV_STATS_INC(tunnel->dev, rx_errors);
+		goto drop;
+	}
+	iph = (struct iphdr *)(skb->head + nh);
+
 	err = IP_ECN_decapsulate(iph, skb);
 	if (unlikely(err)) {
 		if (log_ecn_error)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index e49242706b..66eade3fb6 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1603,9 +1603,11 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
 
 	if (copy_from_sockptr(&olr, optlen, sizeof(int)))
 		return -EFAULT;
-	olr = min_t(unsigned int, olr, sizeof(int));
 	if (olr < 0)
 		return -EINVAL;
+
+	olr = min_t(unsigned int, olr, sizeof(int));
+
 	if (copy_to_sockptr(optlen, &olr, sizeof(int)))
 		return -EFAULT;
 	if (copy_to_sockptr(optval, &val, olr))
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index aea89326c6..288f1846b3 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -350,6 +350,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 		goto error;
 	skb_reserve(skb, hlen);
 
+	skb->protocol = htons(ETH_P_IP);
 	skb->priority = READ_ONCE(sk->sk_priority);
 	skb->mark = sockc->mark;
 	skb->tstamp = sockc->transmit_time;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b30ef770a6..0d03d48702 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4011,11 +4011,11 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	if (copy_from_sockptr(&len, optlen, sizeof(int)))
 		return -EFAULT;
 
-	len = min_t(unsigned int, len, sizeof(int));
-
 	if (len < 0)
 		return -EINVAL;
 
+	len = min_t(unsigned int, len, sizeof(int));
+
 	switch (optname) {
 	case TCP_MAXSEG:
 		val = tp->mss_cache;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 9e85f2a0bd..0ecc7311dc 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -398,10 +398,6 @@ void tcp_twsk_purge(struct list_head *net_exit_list, int family)
 			/* Even if tw_refcount == 1, we must clean up kernel reqsk */
 			inet_twsk_purge(net->ipv4.tcp_death_row.hashinfo, family);
 		} else if (!purged_once) {
-			/* The last refcount is decremented in tcp_sk_exit_batch() */
-			if (refcount_read(&net->ipv4.tcp_death_row.tw_refcount) == 1)
-				continue;
-
 			inet_twsk_purge(&tcp_hashinfo, family);
 			purged_once = true;
 		}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e474b20190..17231c0f88 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2792,11 +2792,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 	if (get_user(len, optlen))
 		return -EFAULT;
 
-	len = min_t(unsigned int, len, sizeof(int));
-
 	if (len < 0)
 		return -EINVAL;
 
+	len = min_t(unsigned int, len, sizeof(int));
+
 	switch (optname) {
 	case UDP_CORK:
 		val = udp_test_bit(CORK, sk);