1 files changed, 82 insertions, 39 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3d555c79a7b5..2bd0d1949312 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -409,6 +409,9 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
 		break;
 	case TPACKET_V3:
+		h.h3->tp_status = status;
+		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
+		break;
 	default:
 		WARN(1, "TPACKET version not supported.\n");
 		BUG();
@@ -432,6 +435,8 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
 		flush_dcache_page(pgv_to_page(&h.h2->tp_status));
 		return h.h2->tp_status;
 	case TPACKET_V3:
+		flush_dcache_page(pgv_to_page(&h.h3->tp_status));
+		return h.h3->tp_status;
 	default:
 		WARN(1, "TPACKET version not supported.\n");
 		BUG();
@@ -476,6 +481,9 @@ static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame,
 		h.h2->tp_nsec = ts.tv_nsec;
 		break;
 	case TPACKET_V3:
+		h.h3->tp_sec = ts.tv_sec;
+		h.h3->tp_nsec = ts.tv_nsec;
+		break;
 	default:
 		WARN(1, "TPACKET version not supported.\n");
 		BUG();
@@ -1497,6 +1505,8 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po)
 	f->arr[f->num_members] = sk;
 	smp_wmb();
 	f->num_members++;
+	if (f->num_members == 1)
+		dev_add_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1513,6 +1523,8 @@ static void __fanout_unlink(struct sock *sk, struct packet_sock *po)
 	BUG_ON(i >= f->num_members);
 	f->arr[i] = f->arr[f->num_members - 1];
 	f->num_members--;
+	if (f->num_members == 0)
+		__dev_remove_pack(&f->prot_hook);
 	spin_unlock(&f->lock);
 }
 
@@ -1619,6 +1631,7 @@ static void fanout_release_data(struct packet_fanout *f)
 
 static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 {
+	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
@@ -1641,23 +1654,28 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		return -EINVAL;
 	}
 
+	mutex_lock(&fanout_mutex);
+
+	err = -EINVAL;
 	if (!po->running)
-		return -EINVAL;
+		goto out;
 
+	err = -EALREADY;
 	if (po->fanout)
-		return -EALREADY;
+		goto out;
 
 	if (type == PACKET_FANOUT_ROLLOVER ||
 	    (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) {
-		po->rollover = kzalloc(sizeof(*po->rollover), GFP_KERNEL);
-		if (!po->rollover)
-			return -ENOMEM;
-		atomic_long_set(&po->rollover->num, 0);
-		atomic_long_set(&po->rollover->num_huge, 0);
-		atomic_long_set(&po->rollover->num_failed, 0);
+		err = -ENOMEM;
+		rollover = kzalloc(sizeof(*rollover), GFP_KERNEL);
+		if (!rollover)
+			goto out;
+		atomic_long_set(&rollover->num, 0);
+		atomic_long_set(&rollover->num_huge, 0);
+		atomic_long_set(&rollover->num_failed, 0);
+		po->rollover = rollover;
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1687,7 +1705,6 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
 		match->prot_hook.id_match = match_fanout_group;
-		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1704,36 +1721,40 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 out:
-	mutex_unlock(&fanout_mutex);
-	if (err) {
-		kfree(po->rollover);
+	if (err && rollover) {
+		kfree(rollover);
 		po->rollover = NULL;
 	}
+	mutex_unlock(&fanout_mutex);
 	return err;
 }
 
-static void fanout_release(struct sock *sk)
+/* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes
+ * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout.
+ * It is the responsibility of the caller to call fanout_release_data() and
+ * free the returned packet_fanout (after synchronize_net())
+ */
+static struct packet_fanout *fanout_release(struct sock *sk)
 {
 	struct packet_sock *po = pkt_sk(sk);
 	struct packet_fanout *f;
 
+	mutex_lock(&fanout_mutex);
 	f = po->fanout;
-	if (!f)
-		return;
+	if (f) {
+		po->fanout = NULL;
 
-	mutex_lock(&fanout_mutex);
-	po->fanout = NULL;
+		if (atomic_dec_and_test(&f->sk_ref))
+			list_del(&f->list);
+		else
+			f = NULL;
 
-	if (atomic_dec_and_test(&f->sk_ref)) {
-		list_del(&f->list);
-		dev_remove_pack(&f->prot_hook);
-		fanout_release_data(f);
-		kfree(f);
+		if (po->rollover)
+			kfree_rcu(po->rollover, rcu);
 	}
 	mutex_unlock(&fanout_mutex);
 
-	if (po->rollover)
-		kfree_rcu(po->rollover, rcu);
+	return f;
 }
 
 static bool packet_extra_vlan_len_allowed(const struct net_device *dev,
@@ -2497,6 +2518,13 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
 	ph.raw = frame;
 
 	switch (po->tp_version) {
+	case TPACKET_V3:
+		if (ph.h3->tp_next_offset != 0) {
+			pr_warn_once("variable sized slot not supported");
+			return -EINVAL;
+		}
+		tp_len = ph.h3->tp_len;
+		break;
 	case TPACKET_V2:
 		tp_len = ph.h2->tp_len;
 		break;
@@ -2516,6 +2544,9 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
 		off_max = po->tx_ring.frame_size - tp_len;
 		if (po->sk.sk_type == SOCK_DGRAM) {
 			switch (po->tp_version) {
+			case TPACKET_V3:
+				off = ph.h3->tp_net;
+				break;
 			case TPACKET_V2:
 				off = ph.h2->tp_net;
 				break;
@@ -2525,6 +2556,9 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame,
 			}
 		} else {
 			switch (po->tp_version) {
+			case TPACKET_V3:
+				off = ph.h3->tp_mac;
+				break;
 			case TPACKET_V2:
 				off = ph.h2->tp_mac;
 				break;
@@ -2755,7 +2789,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int offset = 0;
 	struct packet_sock *po = pkt_sk(sk);
-	int hlen, tlen;
+	int hlen, tlen, linear;
 	int extra_len = 0;
 
 	/*
@@ -2816,8 +2850,9 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	err = -ENOBUFS;
 	hlen = LL_RESERVED_SPACE(dev);
 	tlen = dev->needed_tailroom;
-	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len,
-			       __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len),
+	linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len);
+	linear = max(linear, min_t(int, len, dev->hard_header_len));
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
@@ -2906,6 +2941,7 @@ static int packet_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct packet_sock *po;
+	struct packet_fanout *f;
 	struct net *net;
 	union tpacket_req_u req_u;
 
@@ -2945,9 +2981,14 @@ static int packet_release(struct socket *sock)
 		packet_set_ring(sk, &req_u, 1, 1);
 	}
 
-	fanout_release(sk);
+	f = fanout_release(sk);
 
 	synchronize_net();
+
+	if (f) {
+		fanout_release_data(f);
+		kfree(f);
+	}
 	/*
 	 *	Now the socket is dead. No more input will appear.
 	 */
@@ -3899,7 +3940,6 @@ static int packet_notifier(struct notifier_block *this,
 				}
 				if (msg == NETDEV_UNREGISTER) {
 					packet_cached_dev_reset(po);
-					fanout_release(sk);
 					po->ifindex = -1;
 					if (po->prot_hook.dev)
 						dev_put(po->prot_hook.dev);
@@ -4113,11 +4153,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	struct tpacket_req *req = &req_u->req;
 
 	lock_sock(sk);
-	/* Opening a Tx-ring is NOT supported in TPACKET_V3 */
-	if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
-		net_warn_ratelimited("Tx-ring is not supported.\n");
-		goto out;
-	}
 
 	rb = tx_ring ? &po->tx_ring : &po->rx_ring;
 	rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
@@ -4177,11 +4212,19 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 		switch (po->tp_version) {
 		case TPACKET_V3:
-		/* Transmit path is not supported. We checked
-		 * it above but just being paranoid
-		 */
-			if (!tx_ring)
+			/* Block transmit is not supported yet */
+			if (!tx_ring) {
 				init_prb_bdqc(po, rb, pg_vec, req_u);
+			} else {
+				struct tpacket_req3 *req3 = &req_u->req3;
+
+				if (req3->tp_retire_blk_tov ||
+				    req3->tp_sizeof_priv ||
+				    req3->tp_feature_req_word) {
+					err = -EINVAL;
+					goto out;
+				}
+			}
 			break;
 		default:
 			break;