1 files changed, 167 insertions, 74 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 9a0ae7172f92..8f060d7f9a0e 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -84,6 +84,7 @@ struct listeners {
 #define NETLINK_F_BROADCAST_SEND_ERROR	0x4
 #define NETLINK_F_RECV_NO_ENOBUFS	0x8
 #define NETLINK_F_LISTEN_ALL_NSID	0x10
+#define NETLINK_F_CAP_ACK		0x20
 
 static inline int netlink_is_kernel(struct sock *sk)
 {
@@ -124,6 +125,24 @@ static inline u32 netlink_group_mask(u32 group)
 	return group ? 1 << (group - 1) : 0;
 }
 
+static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb,
+					   gfp_t gfp_mask)
+{
+	unsigned int len = skb_end_offset(skb);
+	struct sk_buff *new;
+
+	new = alloc_skb(len, gfp_mask);
+	if (new == NULL)
+		return NULL;
+
+	NETLINK_CB(new).portid = NETLINK_CB(skb).portid;
+	NETLINK_CB(new).dst_group = NETLINK_CB(skb).dst_group;
+	NETLINK_CB(new).creds = NETLINK_CB(skb).creds;
+
+	memcpy(skb_put(new, len), skb->data, len);
+	return new;
+}
+
 int netlink_add_tap(struct netlink_tap *nt)
 {
 	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
@@ -205,7 +224,11 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 	int ret = -ENOMEM;
 
 	dev_hold(dev);
-	nskb = skb_clone(skb, GFP_ATOMIC);
+
+	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
+	else
+		nskb = skb_clone(skb, GFP_ATOMIC);
 	if (nskb) {
 		nskb->dev = dev;
 		nskb->protocol = htons((u16) sk->sk_protocol);
@@ -278,11 +301,6 @@ static void netlink_rcv_wake(struct sock *sk)
 }
 
 #ifdef CONFIG_NETLINK_MMAP
-static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-}
-
 static bool netlink_rx_is_mmaped(struct sock *sk)
 {
 	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
@@ -357,25 +375,52 @@ err1:
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -407,31 +452,19 @@ static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -578,16 +611,6 @@ netlink_current_frame(const struct netlink_ring *ring,
 	return netlink_lookup_frame(ring, ring->head, status);
 }
 
-static struct nl_mmap_hdr *
-netlink_previous_frame(const struct netlink_ring *ring,
-		       enum nl_mmap_status status)
-{
-	unsigned int prev;
-
-	prev = ring->head ? ring->head - 1 : ring->frame_max;
-	return netlink_lookup_frame(ring, prev, status);
-}
-
 static void netlink_increment_head(struct netlink_ring *ring)
 {
 	ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0;
@@ -595,11 +618,11 @@ static void netlink_increment_head(struct netlink_ring *ring)
 
 static void netlink_forward_ring(struct netlink_ring *ring)
 {
-	unsigned int head = ring->head, pos = head;
+	unsigned int head = ring->head;
 	const struct nl_mmap_hdr *hdr;
 
 	do {
-		hdr = __netlink_lookup_frame(ring, pos);
+		hdr = __netlink_lookup_frame(ring, ring->head);
 		if (hdr->nm_status == NL_MMAP_STATUS_UNUSED)
 			break;
 		if (hdr->nm_status != NL_MMAP_STATUS_SKIP)
@@ -608,6 +631,21 @@ static void netlink_forward_ring(struct netlink_ring *ring)
 	} while (ring->head != head);
 }
 
+static bool netlink_has_valid_frame(struct netlink_ring *ring)
+{
+	unsigned int head = ring->head, pos = head;
+	const struct nl_mmap_hdr *hdr;
+
+	do {
+		hdr = __netlink_lookup_frame(ring, pos);
+		if (hdr->nm_status == NL_MMAP_STATUS_VALID)
+			return true;
+		pos = pos != 0 ? pos - 1 : ring->frame_max;
+	} while (pos != head);
+
+	return false;
+}
+
 static bool netlink_dump_space(struct netlink_sock *nlk)
 {
 	struct netlink_ring *ring = &nlk->rx_ring;
@@ -653,13 +691,19 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 
 	mask = datagram_poll(file, sock, wait);
 
-	spin_lock_bh(&sk->sk_receive_queue.lock);
-	if (nlk->rx_ring.pg_vec) {
-		netlink_forward_ring(&nlk->rx_ring);
-		if (!netlink_previous_frame(&nlk->rx_ring, NL_MMAP_STATUS_UNUSED))
-			mask |= POLLIN | POLLRDNORM;
+	/* We could already have received frames in the normal receive
+	 * queue, that will show up as NL_MMAP_STATUS_COPY in the ring,
+	 * so if mask contains pollin/etc already, there's no point
+	 * walking the ring.
+	 */
+	if ((mask & (POLLIN | POLLRDNORM)) != (POLLIN | POLLRDNORM)) {
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		if (nlk->rx_ring.pg_vec) {
+			if (netlink_has_valid_frame(&nlk->rx_ring))
+				mask |= POLLIN | POLLRDNORM;
+		}
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
 	}
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
 
 	spin_lock_bh(&sk->sk_write_queue.lock);
 	if (nlk->tx_ring.pg_vec) {
@@ -819,7 +863,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 }
 
 #else /* CONFIG_NETLINK_MMAP */
-#define netlink_skb_is_mmaped(skb)	false
 #define netlink_rx_is_mmaped(sk)	false
 #define netlink_tx_is_mmaped(sk)	false
 #define netlink_mmap			sock_no_mmap
@@ -900,10 +943,10 @@ static void netlink_sock_destruct(struct sock *sk)
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -1067,8 +1110,8 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	lock_sock(sk);
 
-	err = -EBUSY;
-	if (nlk_sk(sk)->portid)
+	err = nlk_sk(sk)->portid == portid ? 0 : -EBUSY;
+	if (nlk_sk(sk)->bound)
 		goto err;
 
 	err = -ENOMEM;
@@ -1081,12 +1124,21 @@ static int netlink_insert(struct sock *sk, u32 portid)
 
 	err = __netlink_insert(table, sk);
 	if (err) {
+		/* In case the hashtable backend returns with -EBUSY
+		 * from here, it must not escape to the caller.
+		 */
+		if (unlikely(err == -EBUSY))
+			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
-		nlk_sk(sk)->portid = 0;
 		sock_put(sk);
+		goto err;
 	}
 
+	/* We need to ensure that the socket is hashed and visible. */
+	smp_wmb();
+	nlk_sk(sk)->bound = portid;
+
 err:
 	release_sock(sk);
 	return err;
@@ -1471,6 +1523,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
 	long unsigned int groups = nladdr->nl_groups;
+	bool bound;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1487,9 +1540,14 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			return err;
 	}
 
-	if (nlk->portid)
+	bound = nlk->bound;
+	if (bound) {
+		/* Ensure nlk->portid is up-to-date. */
+		smp_rmb();
+
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
+	}
 
 	if (nlk->netlink_bind && groups) {
 		int group;
@@ -1505,7 +1563,10 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		}
 	}
 
-	if (!nlk->portid) {
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!bound) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, nladdr->nl_pid) :
 			netlink_autobind(sock);
@@ -1553,7 +1614,10 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
-	if (!nlk->portid)
+	/* No need for barriers here as we return to user-space without
+	 * using any of the bound attributes.
+	 */
+	if (!nlk->bound)
 		err = netlink_autobind(sock);
 
 	if (err == 0) {
@@ -1812,15 +1876,16 @@ retry:
 }
 EXPORT_SYMBOL(netlink_unicast);
 
-struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
-				  u32 dst_portid, gfp_t gfp_mask)
+struct sk_buff *__netlink_alloc_skb(struct sock *ssk, unsigned int size,
+				    unsigned int ldiff, u32 dst_portid,
+				    gfp_t gfp_mask)
 {
 #ifdef CONFIG_NETLINK_MMAP
+	unsigned int maxlen, linear_size;
 	struct sock *sk = NULL;
 	struct sk_buff *skb;
 	struct netlink_ring *ring;
 	struct nl_mmap_hdr *hdr;
-	unsigned int maxlen;
 
 	sk = netlink_getsockbyportid(ssk, dst_portid);
 	if (IS_ERR(sk))
@@ -1831,7 +1896,11 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 	if (ring->pg_vec == NULL)
 		goto out_put;
 
-	if (ring->frame_size - NL_MMAP_HDRLEN < size)
+	/* We need to account the full linear size needed as a ring
+	 * slot cannot have non-linear parts.
+	 */
+	linear_size = size + ldiff;
+	if (ring->frame_size - NL_MMAP_HDRLEN < linear_size)
 		goto out_put;
 
 	skb = alloc_skb_head(gfp_mask);
@@ -1845,13 +1914,14 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 
 	/* check again under lock */
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
-	if (maxlen < size)
+	if (maxlen < linear_size)
 		goto out_free;
 
 	netlink_forward_ring(ring);
 	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
 	if (hdr == NULL)
 		goto err2;
+
 	netlink_ring_setup_skb(skb, sk, ring, hdr);
 	netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
 	atomic_inc(&ring->pending);
@@ -1877,7 +1947,7 @@ out:
 #endif
 	return alloc_skb(size, gfp_mask);
 }
-EXPORT_SYMBOL_GPL(netlink_alloc_skb);
+EXPORT_SYMBOL_GPL(__netlink_alloc_skb);
 
 int netlink_has_listeners(struct sock *sk, unsigned int group)
 {
@@ -2223,7 +2293,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		break;
 	}
@@ -2238,6 +2308,13 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 			nlk->flags &= ~NETLINK_F_LISTEN_ALL_NSID;
 		err = 0;
 		break;
+	case NETLINK_CAP_ACK:
+		if (val)
+			nlk->flags |= NETLINK_F_CAP_ACK;
+		else
+			nlk->flags &= ~NETLINK_F_CAP_ACK;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2312,6 +2389,16 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 		netlink_table_ungrab();
 		break;
 	}
+	case NETLINK_CAP_ACK:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_F_CAP_ACK ? 1 : 0;
+		if (put_user(len, optlen) ||
+		    put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2371,17 +2458,20 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		dst_group = nlk->dst_group;
 	}
 
-	if (!nlk->portid) {
+	if (!nlk->bound) {
 		err = netlink_autobind(sock);
 		if (err)
 			goto out;
+	} else {
+		/* Ensure nlk is hashed and visible. */
+		smp_rmb();
 	}
 
 	/* It's a really convoluted way for userland to ask for mmaped
 	 * sendmsg(), but that's what we've got...
 	 */
 	if (netlink_tx_is_mmaped(sk) &&
-	    msg->msg_iter.type == ITER_IOVEC &&
+	    iter_is_iovec(&msg->msg_iter) &&
 	    msg->msg_iter.nr_segs == 1 &&
 	    msg->msg_iter.iov->iov_base == NULL) {
 		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
@@ -2853,9 +2943,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 	struct nlmsghdr *rep;
 	struct nlmsgerr *errmsg;
 	size_t payload = sizeof(*errmsg);
+	struct netlink_sock *nlk = nlk_sk(NETLINK_CB(in_skb).sk);
 
-	/* error messages get the original request appened */
-	if (err)
+	/* Error messages get the original request appened, unless the user
+	 * requests to cap the error message.
+	 */
+	if (!(nlk->flags & NETLINK_F_CAP_ACK) && err)
 		payload += nlmsg_len(nlh);
 
 	skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload),
@@ -2878,7 +2971,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 			  NLMSG_ERROR, payload, 0);
 	errmsg = nlmsg_data(rep);
 	errmsg->error = err;
-	memcpy(&errmsg->msg, nlh, err ? nlh->nlmsg_len : sizeof(*nlh));
+	memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) ? nlh->nlmsg_len : sizeof(*nlh));
 	netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT);
 }
 EXPORT_SYMBOL(netlink_ack);