1 files changed, 81 insertions, 54 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 46943a18a10d..6ce8dd19f33c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -49,6 +49,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/ethtool.h>
+#include <linux/filter.h>
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/capability.h>
@@ -459,7 +460,7 @@ static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts,
 		return TP_STATUS_TS_RAW_HARDWARE;
 
 	if ((flags & SOF_TIMESTAMPING_SOFTWARE) &&
-	    ktime_to_timespec64_cond(skb->tstamp, ts))
+	    ktime_to_timespec64_cond(skb_tstamp(skb), ts))
 		return TP_STATUS_TS_SOFTWARE;
 
 	return 0;
@@ -1349,7 +1350,7 @@ static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb)
 		if (READ_ONCE(history[i]) == rxhash)
 			count++;
 
-	victim = prandom_u32() % ROLLOVER_HLEN;
+	victim = prandom_u32_max(ROLLOVER_HLEN);
 
 	/* Avoid dirtying the cache line if possible */
 	if (READ_ONCE(history[victim]) != rxhash)
@@ -1773,6 +1774,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args)
 		match->prot_hook.dev = po->prot_hook.dev;
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
+		match->prot_hook.af_packet_net = read_pnet(&match->net);
 		match->prot_hook.id_match = match_fanout_group;
 		match->max_num_members = args->max_num_members;
 		list_add(&match->list, &fanout_list);
@@ -1787,7 +1789,10 @@ static int fanout_add(struct sock *sk, struct fanout_args *args)
 		err = -ENOSPC;
 		if (refcount_read(&match->sk_ref) < match->max_num_members) {
 			__dev_remove_pack(&po->prot_hook);
-			po->fanout = match;
+
+			/* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */
+			WRITE_ONCE(po->fanout, match);
+
 			po->rollover = rollover;
 			rollover = NULL;
 			refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
@@ -1900,7 +1905,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev,
 	 */
 
 	spkt->spkt_family = dev->type;
-	strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device));
+	strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device));
 	spkt->spkt_protocol = skb->protocol;
 
 	/*
@@ -1919,12 +1924,22 @@ oom:
 
 static void packet_parse_headers(struct sk_buff *skb, struct socket *sock)
 {
+	int depth;
+
 	if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) &&
 	    sock->type == SOCK_RAW) {
 		skb_reset_mac_header(skb);
 		skb->protocol = dev_parse_header_protocol(skb);
 	}
 
+	/* Move network header to the right position for VLAN tagged packets */
+	if (likely(skb->dev->type == ARPHRD_ETHER) &&
+	    eth_type_vlan(skb->protocol) &&
+	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0) {
+		if (pskb_may_pull(skb, depth))
+			skb_set_network_header(skb, depth);
+	}
+
 	skb_probe_transport_header(skb);
 }
 
@@ -2194,6 +2209,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	spin_lock(&sk->sk_receive_queue.lock);
 	po->stats.stats1.tp_packets++;
 	sock_skb_set_dropcount(sk, skb);
+	skb_clear_delivery_time(skb);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	spin_unlock(&sk->sk_receive_queue.lock);
 	sk->sk_data_ready(sk);
@@ -2312,8 +2328,11 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 					copy_skb = skb_get(skb);
 					skb_head = skb->data;
 				}
-				if (copy_skb)
+				if (copy_skb) {
+					memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0,
+					       sizeof(PACKET_SKB_CB(copy_skb)->sa.ll));
 					skb_set_owner_r(copy_skb, sk);
+				}
 			}
 			snaplen = po->rx_ring.frame_size - macoff;
 			if ((int)snaplen < 0) {
@@ -2372,6 +2391,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	po->stats.stats1.tp_packets++;
 	if (copy_skb) {
 		status |= TP_STATUS_COPY;
+		skb_clear_delivery_time(copy_skb);
 		__skb_queue_tail(&sk->sk_receive_queue, copy_skb);
 	}
 	spin_unlock(&sk->sk_receive_queue.lock);
@@ -2848,8 +2868,9 @@ tpacket_error:
 
 		status = TP_STATUS_SEND_REQUEST;
 		err = po->xmit(skb);
-		if (unlikely(err > 0)) {
-			err = net_xmit_errno(err);
+		if (unlikely(err != 0)) {
+			if (err > 0)
+				err = net_xmit_errno(err);
 			if (err && __packet_get_status(po, ph) ==
 				   TP_STATUS_AVAILABLE) {
 				/* skb was destructed already */
@@ -3016,8 +3037,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (err)
 		goto out_free;
 
-	if (sock->type == SOCK_RAW &&
-	    !dev_validate_header(dev, skb->data, len)) {
+	if ((sock->type == SOCK_RAW &&
+	     !dev_validate_header(dev, skb->data, len)) || !skb->len) {
 		err = -EINVAL;
 		goto out_free;
 	}
@@ -3036,6 +3057,11 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->mark = sockc.mark;
 	skb->tstamp = sockc.transmit_time;
 
+	if (unlikely(extra_len == 4))
+		skb->no_fcs = 1;
+
+	packet_parse_headers(skb, sock);
+
 	if (has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
 		if (err)
@@ -3044,14 +3070,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		virtio_net_hdr_set_proto(skb, &vnet_hdr);
 	}
 
-	packet_parse_headers(skb, sock);
-
-	if (unlikely(extra_len == 4))
-		skb->no_fcs = 1;
-
 	err = po->xmit(skb);
-	if (err > 0 && (err = net_xmit_errno(err)) != 0)
-		goto out_unlock;
+	if (unlikely(err != 0)) {
+		if (err > 0)
+			err = net_xmit_errno(err);
+		if (err)
+			goto out_unlock;
+	}
 
 	dev_put(dev);
 
@@ -3102,16 +3127,14 @@ static int packet_release(struct socket *sock)
 	sk_del_node_init_rcu(sk);
 	mutex_unlock(&net->packet.sklist_lock);
 
-	preempt_disable();
 	sock_prot_inuse_add(net, sk->sk_prot, -1);
-	preempt_enable();
 
 	spin_lock(&po->bind_lock);
 	unregister_prot_hook(sk, false);
 	packet_cached_dev_reset(po);
 
 	if (po->prot_hook.dev) {
-		dev_put(po->prot_hook.dev);
+		netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker);
 		po->prot_hook.dev = NULL;
 	}
 	spin_unlock(&po->bind_lock);
@@ -3163,12 +3186,10 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 			  __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
-	struct net_device *dev_curr;
-	__be16 proto_curr;
-	bool need_rehook;
 	struct net_device *dev = NULL;
-	int ret = 0;
 	bool unlisted = false;
+	bool need_rehook;
+	int ret = 0;
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
@@ -3193,14 +3214,10 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 		}
 	}
 
-	dev_hold(dev);
-
-	proto_curr = po->prot_hook.type;
-	dev_curr = po->prot_hook.dev;
-
-	need_rehook = proto_curr != proto || dev_curr != dev;
+	need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev;
 
 	if (need_rehook) {
+		dev_hold(dev);
 		if (po->running) {
 			rcu_read_unlock();
 			/* prevents packet_notifier() from calling
@@ -3209,7 +3226,6 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 			WRITE_ONCE(po->num, 0);
 			__unregister_prot_hook(sk, true);
 			rcu_read_lock();
-			dev_curr = po->prot_hook.dev;
 			if (dev)
 				unlisted = !dev_get_by_index_rcu(sock_net(sk),
 								 dev->ifindex);
@@ -3219,18 +3235,21 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 		WRITE_ONCE(po->num, proto);
 		po->prot_hook.type = proto;
 
+		netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker);
+
 		if (unlikely(unlisted)) {
-			dev_put(dev);
 			po->prot_hook.dev = NULL;
 			WRITE_ONCE(po->ifindex, -1);
 			packet_cached_dev_reset(po);
 		} else {
+			netdev_hold(dev, &po->prot_hook.dev_tracker,
+				    GFP_ATOMIC);
 			po->prot_hook.dev = dev;
 			WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0);
 			packet_cached_dev_assign(po, dev);
 		}
+		dev_put(dev);
 	}
-	dev_put(dev_curr);
 
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
@@ -3358,6 +3377,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 		po->prot_hook.func = packet_rcv_spkt;
 
 	po->prot_hook.af_packet_priv = sk;
+	po->prot_hook.af_packet_net = sock_net(sk);
 
 	if (proto) {
 		po->prot_hook.type = proto;
@@ -3368,9 +3388,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	sk_add_node_tail_rcu(sk, &net->packet.sklist);
 	mutex_unlock(&net->packet.sklist_lock);
 
-	preempt_disable();
 	sock_prot_inuse_add(net, &packet_proto, 1);
-	preempt_enable();
 
 	return 0;
 out2:
@@ -3418,7 +3436,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	 *	but then it will block.
 	 */
 
-	skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err);
+	skb = skb_recv_datagram(sk, flags, &err);
 
 	/*
 	 *	An error occurred so return it. Because skb_recv_datagram()
@@ -3461,9 +3479,11 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		sll->sll_protocol = skb->protocol;
 	}
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_recv_cmsgs(msg, sk, skb);
 
 	if (msg->msg_name) {
+		const size_t max_len = min(sizeof(skb->cb),
+					   sizeof(struct sockaddr_storage));
 		int copy_len;
 
 		/* If the address length field is there to be filled
@@ -3486,6 +3506,10 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 				msg->msg_namelen = sizeof(struct sockaddr_ll);
 			}
 		}
+		if (WARN_ON_ONCE(copy_len > max_len)) {
+			copy_len = max_len;
+			msg->msg_namelen = copy_len;
+		}
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
 	}
 
@@ -3541,7 +3565,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr,
 	rcu_read_lock();
 	dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex));
 	if (dev)
-		strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data));
+		strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data));
 	rcu_read_unlock();
 
 	return sizeof(*uaddr);
@@ -3939,7 +3963,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
 	}
 	case PACKET_FANOUT_DATA:
 	{
-		if (!po->fanout)
+		/* Paired with the WRITE_ONCE() in fanout_add() */
+		if (!READ_ONCE(po->fanout))
 			return -EINVAL;
 
 		return fanout_set_data(po, optval, optlen);
@@ -4142,7 +4167,8 @@ static int packet_notifier(struct notifier_block *this,
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
 					WRITE_ONCE(po->ifindex, -1);
-					dev_put(po->prot_hook.dev);
+					netdev_put(po->prot_hook.dev,
+						   &po->prot_hook.dev_tracker);
 					po->prot_hook.dev = NULL;
 				}
 				spin_unlock(&po->bind_lock);
@@ -4492,9 +4518,10 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 out_free_pg_vec:
-	bitmap_free(rx_owner_map);
-	if (pg_vec)
+	if (pg_vec) {
+		bitmap_free(rx_owner_map);
 		free_pg_vec(pg_vec, order, req->tp_block_nr);
+	}
 out:
 	return err;
 }
@@ -4698,37 +4725,37 @@ static struct pernet_operations packet_net_ops = {
 
 static void __exit packet_exit(void)
 {
-	unregister_netdevice_notifier(&packet_netdev_notifier);
-	unregister_pernet_subsys(&packet_net_ops);
 	sock_unregister(PF_PACKET);
 	proto_unregister(&packet_proto);
+	unregister_netdevice_notifier(&packet_netdev_notifier);
+	unregister_pernet_subsys(&packet_net_ops);
 }
 
 static int __init packet_init(void)
 {
 	int rc;
 
-	rc = proto_register(&packet_proto, 0);
-	if (rc)
-		goto out;
-	rc = sock_register(&packet_family_ops);
-	if (rc)
-		goto out_proto;
 	rc = register_pernet_subsys(&packet_net_ops);
 	if (rc)
-		goto out_sock;
+		goto out;
 	rc = register_netdevice_notifier(&packet_netdev_notifier);
 	if (rc)
 		goto out_pernet;
+	rc = proto_register(&packet_proto, 0);
+	if (rc)
+		goto out_notifier;
+	rc = sock_register(&packet_family_ops);
+	if (rc)
+		goto out_proto;
 
 	return 0;
 
-out_pernet:
-	unregister_pernet_subsys(&packet_net_ops);
-out_sock:
-	sock_unregister(PF_PACKET);
 out_proto:
 	proto_unregister(&packet_proto);
+out_notifier:
+	unregister_netdevice_notifier(&packet_netdev_notifier);
+out_pernet:
+	unregister_pernet_subsys(&packet_net_ops);
 out:
 	return rc;
 }