1 files changed, 60 insertions, 48 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index a2696acbcd9d..9fc020fd7ecc 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -266,7 +266,8 @@ static void packet_cached_dev_reset(struct packet_sock *po)
 
 static bool packet_use_direct_xmit(const struct packet_sock *po)
 {
-	return po->xmit == packet_direct_xmit;
+	/* Paired with WRITE_ONCE() in packet_setsockopt() */
+	return READ_ONCE(po->xmit) == packet_direct_xmit;
 }
 
 static u16 packet_pick_tx_queue(struct sk_buff *skb)
@@ -362,18 +363,20 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 {
 	union tpacket_uhdr h;
 
+	/* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */
+
 	h.raw = frame;
 	switch (po->tp_version) {
 	case TPACKET_V1:
-		h.h1->tp_status = status;
+		WRITE_ONCE(h.h1->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h1->tp_status));
 		break;
 	case TPACKET_V2:
-		h.h2->tp_status = status;
+		WRITE_ONCE(h.h2->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
 		break;
 	case TPACKET_V3:
-		h.h3->tp_status = status;
+		WRITE_ONCE(h.h3->tp_status, status);
 		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
 		break;
 	default:
@@ -390,17 +393,19 @@ static int __packet_get_status(const struct packet_sock *po, void *frame)
 
 	smp_rmb();
 
+	/* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */
+
 	h.raw = frame;
 	switch (po->tp_version) {
 	case TPACKET_V1:
 		flush_dcache_page(pgv_to_page(&h.h1->tp_status));
-		return h.h1->tp_status;
+		return READ_ONCE(h.h1->tp_status);
 	case TPACKET_V2:
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
-		return h.h2->tp_status;
+		return READ_ONCE(h.h2->tp_status);
 	case TPACKET_V3:
 		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
-		return h.h3->tp_status;
+		return READ_ONCE(h.h3->tp_status);
 	default:
 		WARN(1, "TPACKET version not supported.\n");
 		BUG();
@@ -1845,7 +1850,7 @@ 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;
 
 	/*
@@ -1864,12 +1869,20 @@ 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_and_depth(skb, skb->protocol, &depth) != 0)
+		skb_set_network_header(skb, depth);
+
 	skb_probe_transport_header(skb);
 }
 
@@ -1964,7 +1977,7 @@ retry:
 		goto retry;
 	}
 
-	if (!dev_validate_header(dev, skb->data, len)) {
+	if (!dev_validate_header(dev, skb->data, len) || !skb->len) {
 		err = -EINVAL;
 		goto out_unlock;
 	}
@@ -2114,7 +2127,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	sll = &PACKET_SKB_CB(skb)->sa.ll;
 	sll->sll_hatype = dev->type;
 	sll->sll_pkttype = skb->pkt_type;
-	if (unlikely(po->origdev))
+	if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
 		sll->sll_ifindex = orig_dev->ifindex;
 	else
 		sll->sll_ifindex = dev->ifindex;
@@ -2222,8 +2235,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		status |= TP_STATUS_CSUMNOTREADY;
 	else if (skb->pkt_type != PACKET_OUTGOING &&
-		 (skb->ip_summed == CHECKSUM_COMPLETE ||
-		  skb_csum_unnecessary(skb)))
+		 skb_csum_unnecessary(skb))
 		status |= TP_STATUS_CSUM_VALID;
 
 	if (snaplen > res)
@@ -2383,7 +2395,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	sll->sll_hatype = dev->type;
 	sll->sll_protocol = skb->protocol;
 	sll->sll_pkttype = skb->pkt_type;
-	if (unlikely(po->origdev))
+	if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
 		sll->sll_ifindex = orig_dev->ifindex;
 	else
 		sll->sll_ifindex = dev->ifindex;
@@ -2790,7 +2802,8 @@ tpacket_error:
 		packet_inc_pending(&po->tx_ring);
 
 		status = TP_STATUS_SEND_REQUEST;
-		err = po->xmit(skb);
+		/* Paired with WRITE_ONCE() in packet_setsockopt() */
+		err = READ_ONCE(po->xmit)(skb);
 		if (unlikely(err != 0)) {
 			if (err > 0)
 				err = net_xmit_errno(err);
@@ -2960,8 +2973,8 @@ 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;
 	}
@@ -2980,6 +2993,11 @@ 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)
@@ -2988,12 +3006,8 @@ 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);
+	/* Paired with WRITE_ONCE() in packet_setsockopt() */
+	err = READ_ONCE(po->xmit)(skb);
 	if (unlikely(err != 0)) {
 		if (err > 0)
 			err = net_xmit_errno(err);
@@ -3118,6 +3132,9 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex,
 
 	lock_sock(sk);
 	spin_lock(&po->bind_lock);
+	if (!proto)
+		proto = po->num;
+
 	rcu_read_lock();
 
 	if (po->fanout) {
@@ -3220,7 +3237,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 	memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data));
 	name[sizeof(uaddr->sa_data)] = 0;
 
-	return packet_do_bind(sk, name, 0, pkt_sk(sk)->num);
+	return packet_do_bind(sk, name, 0, 0);
 }
 
 static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
@@ -3237,8 +3254,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len
 	if (sll->sll_family != AF_PACKET)
 		return -EINVAL;
 
-	return packet_do_bind(sk, NULL, sll->sll_ifindex,
-			      sll->sll_protocol ? : pkt_sk(sk)->num);
+	return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol);
 }
 
 static struct proto packet_proto = {
@@ -3444,15 +3460,14 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
 	}
 
-	if (pkt_sk(sk)->auxdata) {
+	if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) {
 		struct tpacket_auxdata aux;
 
 		aux.tp_status = TP_STATUS_USER;
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			aux.tp_status |= TP_STATUS_CSUMNOTREADY;
 		else if (skb->pkt_type != PACKET_OUTGOING &&
-			 (skb->ip_summed == CHECKSUM_COMPLETE ||
-			  skb_csum_unnecessary(skb)))
+			 skb_csum_unnecessary(skb))
 			aux.tp_status |= TP_STATUS_CSUM_VALID;
 
 		aux.tp_len = origlen;
@@ -3496,7 +3511,7 @@ 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);
@@ -3828,9 +3843,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
-		lock_sock(sk);
-		po->auxdata = !!val;
-		release_sock(sk);
+		packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val);
 		return 0;
 	}
 	case PACKET_ORIGDEV:
@@ -3842,9 +3855,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
-		lock_sock(sk);
-		po->origdev = !!val;
-		release_sock(sk);
+		packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val);
 		return 0;
 	}
 	case PACKET_VNET_HDR:
@@ -3910,7 +3921,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (val < 0 || val > 1)
 			return -EINVAL;
 
-		po->prot_hook.ignore_outgoing = !!val;
+		WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val);
 		return 0;
 	}
 	case PACKET_TX_HAS_OFF:
@@ -3941,7 +3952,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
 
-		po->xmit = val ? packet_direct_xmit : dev_queue_xmit;
+		/* Paired with all lockless reads of po->xmit */
+		WRITE_ONCE(po->xmit, val ? packet_direct_xmit : dev_queue_xmit);
 		return 0;
 	}
 	default:
@@ -3992,10 +4004,10 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 
 		break;
 	case PACKET_AUXDATA:
-		val = po->auxdata;
+		val = packet_sock_flag(po, PACKET_SOCK_AUXDATA);
 		break;
 	case PACKET_ORIGDEV:
-		val = po->origdev;
+		val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV);
 		break;
 	case PACKET_VNET_HDR:
 		val = po->has_vnet_hdr;
@@ -4041,7 +4053,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 		       0);
 		break;
 	case PACKET_IGNORE_OUTGOING:
-		val = po->prot_hook.ignore_outgoing;
+		val = READ_ONCE(po->prot_hook.ignore_outgoing);
 		break;
 	case PACKET_ROLLOVER_STATS:
 		if (!po->rollover)
@@ -4228,7 +4240,7 @@ static void packet_mm_open(struct vm_area_struct *vma)
 	struct sock *sk = sock->sk;
 
 	if (sk)
-		atomic_inc(&pkt_sk(sk)->mapped);
+		atomic_long_inc(&pkt_sk(sk)->mapped);
 }
 
 static void packet_mm_close(struct vm_area_struct *vma)
@@ -4238,7 +4250,7 @@ static void packet_mm_close(struct vm_area_struct *vma)
 	struct sock *sk = sock->sk;
 
 	if (sk)
-		atomic_dec(&pkt_sk(sk)->mapped);
+		atomic_long_dec(&pkt_sk(sk)->mapped);
 }
 
 static const struct vm_operations_struct packet_mmap_ops = {
@@ -4333,7 +4345,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 	err = -EBUSY;
 	if (!closing) {
-		if (atomic_read(&po->mapped))
+		if (atomic_long_read(&po->mapped))
 			goto out;
 		if (packet_read_pending(rb))
 			goto out;
@@ -4436,7 +4448,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 
 	err = -EBUSY;
 	mutex_lock(&po->pg_vec_lock);
-	if (closing || atomic_read(&po->mapped) == 0) {
+	if (closing || atomic_long_read(&po->mapped) == 0) {
 		err = 0;
 		spin_lock_bh(&rb_queue->lock);
 		swap(rb->pg_vec, pg_vec);
@@ -4454,9 +4466,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		po->prot_hook.func = (po->rx_ring.pg_vec) ?
 						tpacket_rcv : packet_rcv;
 		skb_queue_purge(rb_queue);
-		if (atomic_read(&po->mapped))
-			pr_err("packet_mmap: vma is busy: %d\n",
-			       atomic_read(&po->mapped));
+		if (atomic_long_read(&po->mapped))
+			pr_err("packet_mmap: vma is busy: %ld\n",
+			       atomic_long_read(&po->mapped));
 	}
 	mutex_unlock(&po->pg_vec_lock);
 
@@ -4534,7 +4546,7 @@ static int packet_mmap(struct file *file, struct socket *sock,
 		}
 	}
 
-	atomic_inc(&po->mapped);
+	atomic_long_inc(&po->mapped);
 	vma->vm_ops = &packet_mmap_ops;
 	err = 0;