1 files changed, 159 insertions, 67 deletions

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3d555c79a7b5..008bb34ee324 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -188,7 +188,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 #define BLOCK_PRIV(x)		((void *)((char *)(x) + BLOCK_O2PRIV(x)))
 
 struct packet_sock;
-static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
 static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 		       struct packet_type *pt, struct net_device *orig_dev);
 
@@ -196,8 +195,7 @@ static void *packet_previous_frame(struct packet_sock *po,
 		struct packet_ring_buffer *rb,
 		int status);
 static void packet_increment_head(struct packet_ring_buffer *buff);
-static int prb_curr_blk_in_use(struct tpacket_kbdq_core *,
-			struct tpacket_block_desc *);
+static int prb_curr_blk_in_use(struct tpacket_block_desc *);
 static void *prb_dispatch_next_block(struct tpacket_kbdq_core *,
 			struct packet_sock *);
 static void prb_retire_current_block(struct tpacket_kbdq_core *,
@@ -216,6 +214,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *,
 static void prb_fill_vlan_info(struct tpacket_kbdq_core *,
 		struct tpacket3_hdr *);
 static void packet_flush_mclist(struct sock *sk);
+static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb);
 
 struct packet_skb_cb {
 	union {
@@ -262,6 +261,7 @@ static int packet_direct_xmit(struct sk_buff *skb)
 	if (skb != orig_skb)
 		goto drop;
 
+	packet_pick_tx_queue(dev, skb);
 	txq = skb_get_tx_queue(dev, skb);
 
 	local_bh_disable();
@@ -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();
@@ -713,7 +721,7 @@ static void prb_retire_rx_blk_timer_expired(unsigned long data)
 			/* Case 1. Queue was frozen because user-space was
 			 *	   lagging behind.
 			 */
-			if (prb_curr_blk_in_use(pkc, pbd)) {
+			if (prb_curr_blk_in_use(pbd)) {
 				/*
 				 * Ok, user-space is still behind.
 				 * So just refresh the timer.
@@ -964,8 +972,7 @@ static void prb_retire_current_block(struct tpacket_kbdq_core *pkc,
 	}
 }
 
-static int prb_curr_blk_in_use(struct tpacket_kbdq_core *pkc,
-				      struct tpacket_block_desc *pbd)
+static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd)
 {
 	return TP_STATUS_USER & BLOCK_STATUS(pbd);
 }
@@ -1056,7 +1063,7 @@ static void *__packet_lookup_frame_in_block(struct packet_sock *po,
 		 * Check if that last block which caused the queue to freeze,
 		 * is still in_use by user-space.
 		 */
-		if (prb_curr_blk_in_use(pkc, pbd)) {
+		if (prb_curr_blk_in_use(pbd)) {
 			/* Can't record this packet */
 			return NULL;
 		} else {
@@ -1312,7 +1319,7 @@ static void packet_sock_destruct(struct sock *sk)
 	skb_queue_purge(&sk->sk_error_queue);
 
 	WARN_ON(atomic_read(&sk->sk_rmem_alloc));
-	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
+	WARN_ON(refcount_read(&sk->sk_wmem_alloc));
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
 		pr_err("Attempt to release alive packet socket: %p\n", sk);
@@ -1488,6 +1495,7 @@ static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev,
 DEFINE_MUTEX(fanout_mutex);
 EXPORT_SYMBOL_GPL(fanout_mutex);
 static LIST_HEAD(fanout_list);
+static u16 fanout_next_id;
 
 static void __fanout_link(struct sock *sk, struct packet_sock *po)
 {
@@ -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);
 }
 
@@ -1617,8 +1629,39 @@ static void fanout_release_data(struct packet_fanout *f)
 	};
 }
 
+static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id)
+{
+	struct packet_fanout *f;
+
+	list_for_each_entry(f, &fanout_list, list) {
+		if (f->id == candidate_id &&
+		    read_pnet(&f->net) == sock_net(sk)) {
+			return false;
+		}
+	}
+	return true;
+}
+
+static bool fanout_find_new_id(struct sock *sk, u16 *new_id)
+{
+	u16 id = fanout_next_id;
+
+	do {
+		if (__fanout_id_is_free(sk, id)) {
+			*new_id = id;
+			fanout_next_id = id + 1;
+			return true;
+		}
+
+		id++;
+	} while (id != fanout_next_id);
+
+	return false;
+}
+
 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 +1684,41 @@ 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;
+	}
+
+	if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) {
+		if (id != 0) {
+			err = -EINVAL;
+			goto out;
+		}
+		if (!fanout_find_new_id(sk, &id)) {
+			err = -ENOMEM;
+			goto out;
+		}
+		/* ephemeral flag for the first socket in the group: drop it */
+		flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8);
 	}
 
-	mutex_lock(&fanout_mutex);
 	match = NULL;
 	list_for_each_entry(f, &fanout_list, list) {
 		if (f->id == id &&
@@ -1680,14 +1741,13 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->flags = flags;
 		INIT_LIST_HEAD(&match->list);
 		spin_lock_init(&match->lock);
-		atomic_set(&match->sk_ref, 0);
+		refcount_set(&match->sk_ref, 0);
 		fanout_init_data(match);
 		match->prot_hook.type = po->prot_hook.type;
 		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.id_match = match_fanout_group;
-		dev_add_pack(&match->prot_hook);
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1695,45 +1755,49 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	    match->prot_hook.type == po->prot_hook.type &&
 	    match->prot_hook.dev == po->prot_hook.dev) {
 		err = -ENOSPC;
-		if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
+		if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
 			__dev_remove_pack(&po->prot_hook);
 			po->fanout = match;
-			atomic_inc(&match->sk_ref);
+			refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1);
 			__fanout_link(sk, po);
 			err = 0;
 		}
 	}
 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 (refcount_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,
@@ -2461,7 +2525,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->data_len = to_write;
 	skb->len += to_write;
 	skb->truesize += to_write;
-	atomic_add(to_write, &po->sk.sk_wmem_alloc);
+	refcount_add(to_write, &po->sk.sk_wmem_alloc);
 
 	while (likely(to_write)) {
 		nr_frags = skb_shinfo(skb)->nr_frags;
@@ -2497,6 +2561,13 @@ 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 +2587,9 @@ 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 +2599,9 @@ 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;
@@ -2580,13 +2657,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
 	}
 
-	sockc.tsflags = po->sk.sk_tsflags;
-	if (msg->msg_controllen) {
-		err = sock_cmsg_send(&po->sk, msg, &sockc);
-		if (unlikely(err))
-			goto out;
-	}
-
 	err = -ENXIO;
 	if (unlikely(dev == NULL))
 		goto out;
@@ -2594,6 +2664,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	sockc.tsflags = po->sk.sk_tsflags;
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(&po->sk, msg, &sockc);
+		if (unlikely(err))
+			goto out_put;
+	}
+
 	if (po->sk.sk_socket->type == SOCK_RAW)
 		reserve = dev->hard_header_len;
 	size_max = po->tx_ring.frame_size
@@ -2672,8 +2749,6 @@ tpacket_error:
 			goto tpacket_error;
 		}
 
-		packet_pick_tx_queue(dev, skb);
-
 		skb->destructor = tpacket_destruct_skb;
 		__packet_set_status(po, ph, TP_STATUS_SENDING);
 		packet_inc_pending(&po->tx_ring);
@@ -2755,7 +2830,7 @@ 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 +2891,9 @@ 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;
@@ -2855,8 +2931,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->priority = sk->sk_priority;
 	skb->mark = sockc.mark;
 
-	packet_pick_tx_queue(dev, skb);
-
 	if (po->has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
 		if (err)
@@ -2906,6 +2980,7 @@ 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 +3020,14 @@ 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.
 	 */
@@ -3062,7 +3142,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 			    int addr_len)
 {
 	struct sock *sk = sock->sk;
-	char name[15];
+	char name[sizeof(uaddr->sa_data) + 1];
 
 	/*
 	 *	Check legality
@@ -3070,7 +3150,11 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr,
 
 	if (addr_len != sizeof(struct sockaddr))
 		return -EINVAL;
-	strlcpy(name, uaddr->sa_data, sizeof(name));
+	/* uaddr->sa_data comes from the userspace, it's not guaranteed to be
+	 * zero-terminated.
+	 */
+	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);
 }
@@ -3620,6 +3704,8 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
 			return -EBUSY;
 		if (copy_from_user(&val, optval, sizeof(val)))
 			return -EFAULT;
+		if (val > INT_MAX)
+			return -EINVAL;
 		po->tp_reserve = val;
 		return 0;
 	}
@@ -3789,6 +3875,8 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
 	case PACKET_HDRLEN:
 		if (len > sizeof(int))
 			len = sizeof(int);
+		if (len < sizeof(int))
+			return -EINVAL;
 		if (copy_from_user(&val, optval, len))
 			return -EFAULT;
 		switch (val) {
@@ -3899,7 +3987,6 @@ 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 +4200,6 @@ 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;
@@ -4154,8 +4236,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		if (unlikely(!PAGE_ALIGNED(req->tp_block_size)))
 			goto out;
 		if (po->tp_version >= TPACKET_V3 &&
-		    (int)(req->tp_block_size -
-			  BLK_PLUS_PRIV(req_u->req3.tp_sizeof_priv)) <= 0)
+		    req->tp_block_size <=
+			  BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv))
 			goto out;
 		if (unlikely(req->tp_frame_size < po->tp_hdrlen +
 					po->tp_reserve))
@@ -4166,6 +4248,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frames_per_block = req->tp_block_size / req->tp_frame_size;
 		if (unlikely(rb->frames_per_block == 0))
 			goto out;
+		if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr))
+			goto out;
 		if (unlikely((rb->frames_per_block * req->tp_block_nr) !=
 					req->tp_frame_nr))
 			goto out;
@@ -4177,11 +4261,19 @@ 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;
@@ -4401,7 +4493,7 @@ static int packet_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq,
 			   "%pK %-6d %-4d %04x   %-5d %1d %-6u %-6u %-6lu\n",
 			   s,
-			   atomic_read(&s->sk_refcnt),
+			   refcount_read(&s->sk_refcnt),
 			   s->sk_type,
 			   ntohs(po->num),
 			   po->ifindex,