1 files changed, 366 insertions, 125 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 275d901d7e4..e6fac7e3db5 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -57,6 +57,7 @@
 #include <linux/audit.h>
 #include <linux/mutex.h>
 #include <linux/vmalloc.h>
+#include <linux/if_arp.h>
 #include <asm/cacheflush.h>
 
 #include <net/net_namespace.h>
@@ -101,6 +102,9 @@ static atomic_t nl_table_users = ATOMIC_INIT(0);
 
 static ATOMIC_NOTIFIER_HEAD(netlink_chain);
 
+static DEFINE_SPINLOCK(netlink_tap_lock);
+static struct list_head netlink_tap_all __read_mostly;
+
 static inline u32 netlink_group_mask(u32 group)
 {
 	return group ? 1 << (group - 1) : 0;
@@ -111,6 +115,138 @@ static inline struct hlist_head *nl_portid_hashfn(struct nl_portid_hash *hash, u
 	return &hash->table[jhash_1word(portid, hash->rnd) & hash->mask];
 }
 
+int netlink_add_tap(struct netlink_tap *nt)
+{
+	if (unlikely(nt->dev->type != ARPHRD_NETLINK))
+		return -EINVAL;
+
+	spin_lock(&netlink_tap_lock);
+	list_add_rcu(&nt->list, &netlink_tap_all);
+	spin_unlock(&netlink_tap_lock);
+
+	if (nt->module)
+		__module_get(nt->module);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(netlink_add_tap);
+
+static int __netlink_remove_tap(struct netlink_tap *nt)
+{
+	bool found = false;
+	struct netlink_tap *tmp;
+
+	spin_lock(&netlink_tap_lock);
+
+	list_for_each_entry(tmp, &netlink_tap_all, list) {
+		if (nt == tmp) {
+			list_del_rcu(&nt->list);
+			found = true;
+			goto out;
+		}
+	}
+
+	pr_warn("__netlink_remove_tap: %p not found\n", nt);
+out:
+	spin_unlock(&netlink_tap_lock);
+
+	if (found && nt->module)
+		module_put(nt->module);
+
+	return found ? 0 : -ENODEV;
+}
+
+int netlink_remove_tap(struct netlink_tap *nt)
+{
+	int ret;
+
+	ret = __netlink_remove_tap(nt);
+	synchronize_net();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(netlink_remove_tap);
+
+static bool netlink_filter_tap(const struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	bool pass = false;
+
+	/* We take the more conservative approach and
+	 * whitelist socket protocols that may pass.
+	 */
+	switch (sk->sk_protocol) {
+	case NETLINK_ROUTE:
+	case NETLINK_USERSOCK:
+	case NETLINK_SOCK_DIAG:
+	case NETLINK_NFLOG:
+	case NETLINK_XFRM:
+	case NETLINK_FIB_LOOKUP:
+	case NETLINK_NETFILTER:
+	case NETLINK_GENERIC:
+		pass = true;
+		break;
+	}
+
+	return pass;
+}
+
+static int __netlink_deliver_tap_skb(struct sk_buff *skb,
+				     struct net_device *dev)
+{
+	struct sk_buff *nskb;
+	struct sock *sk = skb->sk;
+	int ret = -ENOMEM;
+
+	dev_hold(dev);
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (nskb) {
+		nskb->dev = dev;
+		nskb->protocol = htons((u16) sk->sk_protocol);
+		nskb->pkt_type = netlink_is_kernel(sk) ?
+				 PACKET_KERNEL : PACKET_USER;
+
+		ret = dev_queue_xmit(nskb);
+		if (unlikely(ret > 0))
+			ret = net_xmit_errno(ret);
+	}
+
+	dev_put(dev);
+	return ret;
+}
+
+static void __netlink_deliver_tap(struct sk_buff *skb)
+{
+	int ret;
+	struct netlink_tap *tmp;
+
+	if (!netlink_filter_tap(skb))
+		return;
+
+	list_for_each_entry_rcu(tmp, &netlink_tap_all, list) {
+		ret = __netlink_deliver_tap_skb(skb, tmp->dev);
+		if (unlikely(ret))
+			break;
+	}
+}
+
+static void netlink_deliver_tap(struct sk_buff *skb)
+{
+	rcu_read_lock();
+
+	if (unlikely(!list_empty(&netlink_tap_all)))
+		__netlink_deliver_tap(skb);
+
+	rcu_read_unlock();
+}
+
+static void netlink_deliver_tap_kernel(struct sock *dst, struct sock *src,
+				       struct sk_buff *skb)
+{
+	if (!(netlink_is_kernel(dst) && netlink_is_kernel(src)))
+		netlink_deliver_tap(skb);
+}
+
 static void netlink_overrun(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -196,14 +332,14 @@ static void **alloc_pg_vec(struct netlink_sock *nlk,
 {
 	unsigned int block_nr = req->nm_block_nr;
 	unsigned int i;
-	void **pg_vec, *ptr;
+	void **pg_vec;
 
 	pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL);
 	if (pg_vec == NULL)
 		return NULL;
 
 	for (i = 0; i < block_nr; i++) {
-		pg_vec[i] = ptr = alloc_one_pg_vec_page(order);
+		pg_vec[i] = alloc_one_pg_vec_page(order);
 		if (pg_vec[i] == NULL)
 			goto err1;
 	}
@@ -497,10 +633,10 @@ static unsigned int netlink_poll(struct file *file, struct socket *sock,
 		 * for dumps is performed here. A dump is allowed to continue
 		 * if at least half the ring is unused.
 		 */
-		while (nlk->cb != NULL && netlink_dump_space(nlk)) {
+		while (nlk->cb_running && netlink_dump_space(nlk)) {
 			err = netlink_dump(sk);
 			if (err < 0) {
-				sk->sk_err = err;
+				sk->sk_err = -err;
 				sk->sk_error_report(sk);
 				break;
 			}
@@ -704,18 +840,6 @@ static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
 #define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb)	0
 #endif /* CONFIG_NETLINK_MMAP */
 
-static void netlink_destroy_callback(struct netlink_callback *cb)
-{
-	kfree_skb(cb->skb);
-	kfree(cb);
-}
-
-static void netlink_consume_callback(struct netlink_callback *cb)
-{
-	consume_skb(cb->skb);
-	kfree(cb);
-}
-
 static void netlink_skb_destructor(struct sk_buff *skb)
 {
 #ifdef CONFIG_NETLINK_MMAP
@@ -751,7 +875,10 @@ static void netlink_skb_destructor(struct sk_buff *skb)
 	}
 #endif
 	if (is_vmalloc_addr(skb->head)) {
-		vfree(skb->head);
+		if (!skb->cloned ||
+		    !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
+			vfree(skb->head);
+
 		skb->head = NULL;
 	}
 	if (skb->sk != NULL)
@@ -771,12 +898,12 @@ static void netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
-	if (nlk->cb) {
-		if (nlk->cb->done)
-			nlk->cb->done(nlk->cb);
+	if (nlk->cb_running) {
+		if (nlk->cb.done)
+			nlk->cb.done(&nlk->cb);
 
-		module_put(nlk->cb->module);
-		netlink_destroy_callback(nlk->cb);
+		module_put(nlk->cb.module);
+		kfree_skb(nlk->cb.skb);
 	}
 
 	skb_queue_purge(&sk->sk_receive_queue);
@@ -1079,7 +1206,8 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	struct module *module = NULL;
 	struct mutex *cb_mutex;
 	struct netlink_sock *nlk;
-	void (*bind)(int group);
+	int (*bind)(int group);
+	void (*unbind)(int group);
 	int err = 0;
 
 	sock->state = SS_UNCONNECTED;
@@ -1105,6 +1233,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 		err = -EPROTONOSUPPORT;
 	cb_mutex = nl_table[protocol].cb_mutex;
 	bind = nl_table[protocol].bind;
+	unbind = nl_table[protocol].unbind;
 	netlink_unlock_table();
 
 	if (err < 0)
@@ -1121,6 +1250,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol,
 	nlk = nlk_sk(sock->sk);
 	nlk->module = module;
 	nlk->netlink_bind = bind;
+	nlk->netlink_unbind = unbind;
 out:
 	return err;
 
@@ -1174,6 +1304,7 @@ static int netlink_release(struct socket *sock)
 			kfree_rcu(old, rcu);
 			nl_table[sk->sk_protocol].module = NULL;
 			nl_table[sk->sk_protocol].bind = NULL;
+			nl_table[sk->sk_protocol].unbind = NULL;
 			nl_table[sk->sk_protocol].flags = 0;
 			nl_table[sk->sk_protocol].registered = 0;
 		}
@@ -1233,7 +1364,74 @@ retry:
 	return err;
 }
 
-static inline int netlink_capable(const struct socket *sock, unsigned int flag)
+/**
+ * __netlink_ns_capable - General netlink message capability test
+ * @nsp: NETLINK_CB of the socket buffer holding a netlink command from userspace.
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
+			struct user_namespace *user_ns, int cap)
+{
+	return ((nsp->flags & NETLINK_SKB_DST) ||
+		file_ns_capable(nsp->sk->sk_socket->file, user_ns, cap)) &&
+		ns_capable(user_ns, cap);
+}
+EXPORT_SYMBOL(__netlink_ns_capable);
+
+/**
+ * netlink_ns_capable - General netlink message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @user_ns: The user namespace of the capability to use
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in the user namespace @user_ns.
+ */
+bool netlink_ns_capable(const struct sk_buff *skb,
+			struct user_namespace *user_ns, int cap)
+{
+	return __netlink_ns_capable(&NETLINK_CB(skb), user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_ns_capable);
+
+/**
+ * netlink_capable - Netlink global message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap in all user namespaces.
+ */
+bool netlink_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, &init_user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_capable);
+
+/**
+ * netlink_net_capable - Netlink network namespace message capability test
+ * @skb: socket buffer holding a netlink command from userspace
+ * @cap: The capability to use
+ *
+ * Test to see if the opener of the socket we received the message
+ * from had when the netlink socket was created and the sender of the
+ * message has has the capability @cap over the network namespace of
+ * the socket we received the message from.
+ */
+bool netlink_net_capable(const struct sk_buff *skb, int cap)
+{
+	return netlink_ns_capable(skb, sock_net(skb->sk)->user_ns, cap);
+}
+EXPORT_SYMBOL(netlink_net_capable);
+
+static inline int netlink_allowed(const struct socket *sock, unsigned int flag)
 {
 	return (nl_table[sock->sk->sk_protocol].flags & flag) ||
 		ns_capable(sock_net(sock->sk)->user_ns, CAP_NET_ADMIN);
@@ -1284,6 +1482,19 @@ static int netlink_realloc_groups(struct sock *sk)
 	return err;
 }
 
+static void netlink_unbind(int group, long unsigned int groups,
+			   struct netlink_sock *nlk)
+{
+	int undo;
+
+	if (!nlk->netlink_unbind)
+		return;
+
+	for (undo = 0; undo < group; undo++)
+		if (test_bit(group, &groups))
+			nlk->netlink_unbind(undo);
+}
+
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			int addr_len)
 {
@@ -1292,6 +1503,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
+	long unsigned int groups = nladdr->nl_groups;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
 		return -EINVAL;
@@ -1300,45 +1512,53 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	/* Only superuser is allowed to listen multicasts */
-	if (nladdr->nl_groups) {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+	if (groups) {
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 	}
 
-	if (nlk->portid) {
+	if (nlk->portid)
 		if (nladdr->nl_pid != nlk->portid)
 			return -EINVAL;
-	} else {
+
+	if (nlk->netlink_bind && groups) {
+		int group;
+
+		for (group = 0; group < nlk->ngroups; group++) {
+			if (!test_bit(group, &groups))
+				continue;
+			err = nlk->netlink_bind(group);
+			if (!err)
+				continue;
+			netlink_unbind(group, groups, nlk);
+			return err;
+		}
+	}
+
+	if (!nlk->portid) {
 		err = nladdr->nl_pid ?
 			netlink_insert(sk, net, nladdr->nl_pid) :
 			netlink_autobind(sock);
-		if (err)
+		if (err) {
+			netlink_unbind(nlk->ngroups - 1, groups, nlk);
 			return err;
+		}
 	}
 
-	if (!nladdr->nl_groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
+	if (!groups && (nlk->groups == NULL || !(u32)nlk->groups[0]))
 		return 0;
 
 	netlink_table_grab();
 	netlink_update_subscriptions(sk, nlk->subscriptions +
-					 hweight32(nladdr->nl_groups) -
+					 hweight32(groups) -
 					 hweight32(nlk->groups[0]));
-	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | nladdr->nl_groups;
+	nlk->groups[0] = (nlk->groups[0] & ~0xffffffffUL) | groups;
 	netlink_update_listeners(sk);
 	netlink_table_ungrab();
 
-	if (nlk->netlink_bind && nlk->groups[0]) {
-		int i;
-
-		for (i=0; i<nlk->ngroups; i++) {
-			if (test_bit(i, nlk->groups))
-				nlk->netlink_bind(i);
-		}
-	}
-
 	return 0;
 }
 
@@ -1362,8 +1582,8 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 	if (addr->sa_family != AF_NETLINK)
 		return -EINVAL;
 
-	/* Only superuser is allowed to send multicasts */
-	if (nladdr->nl_groups && !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	if ((nladdr->nl_groups || nladdr->nl_pid) &&
+	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
@@ -1434,33 +1654,31 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
 	return sock;
 }
 
-static struct sk_buff *netlink_alloc_large_skb(unsigned int size)
+static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
+					       int broadcast)
 {
 	struct sk_buff *skb;
 	void *data;
 
-	if (size <= NLMSG_GOODSIZE)
+	if (size <= NLMSG_GOODSIZE || broadcast)
 		return alloc_skb(size, GFP_KERNEL);
 
-	skb = alloc_skb_head(GFP_KERNEL);
-	if (skb == NULL)
-		return NULL;
+	size = SKB_DATA_ALIGN(size) +
+	       SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	data = vmalloc(size);
 	if (data == NULL)
-		goto err;
+		return NULL;
 
-	skb->head	= data;
-	skb->data	= data;
-	skb_reset_tail_pointer(skb);
-	skb->end	= skb->tail + size;
-	skb->len	= 0;
-	skb->destructor = netlink_skb_destructor;
+	skb = build_skb(data, size);
+	if (skb == NULL)
+		vfree(data);
+	else {
+		skb->head_frag = 0;
+		skb->destructor = netlink_skb_destructor;
+	}
 
 	return skb;
-err:
-	kfree_skb(skb);
-	return NULL;
 }
 
 /*
@@ -1518,6 +1736,8 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 {
 	int len = skb->len;
 
+	netlink_deliver_tap(skb);
+
 #ifdef CONFIG_NETLINK_MMAP
 	if (netlink_skb_is_mmaped(skb))
 		netlink_queue_mmaped_skb(sk, skb);
@@ -1526,7 +1746,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 	else
 #endif /* CONFIG_NETLINK_MMAP */
 		skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, len);
+	sk->sk_data_ready(sk);
 	return len;
 }
 
@@ -1581,6 +1801,7 @@ static int netlink_unicast_kernel(struct sock *sk, struct sk_buff *skb,
 		ret = skb->len;
 		netlink_skb_set_owner_r(skb, sk);
 		NETLINK_CB(skb).sk = ssk;
+		netlink_deliver_tap_kernel(sk, ssk, skb);
 		nlk->netlink_rcv(skb);
 		consume_skb(skb);
 	} else {
@@ -1645,6 +1866,9 @@ 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)
+		goto out_put;
+
 	skb = alloc_skb_head(gfp_mask);
 	if (skb == NULL)
 		goto err1;
@@ -1654,6 +1878,7 @@ struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 	if (ring->pg_vec == NULL)
 		goto out_free;
 
+	/* check again under lock */
 	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
 	if (maxlen < size)
 		goto out_free;
@@ -1893,7 +2118,7 @@ out:
  * netlink_set_err - report error to broadcast listeners
  * @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
  * @portid: the PORTID of a process that we want to skip (if any)
- * @groups: the broadcast group that will notice the error
+ * @group: the broadcast group that will notice the error
  * @code: error code, must be negative (as usual in kernelspace)
  *
  * This function returns the number of broadcast listeners that have set the
@@ -1964,20 +2189,24 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		break;
 	case NETLINK_ADD_MEMBERSHIP:
 	case NETLINK_DROP_MEMBERSHIP: {
-		if (!netlink_capable(sock, NL_CFG_F_NONROOT_RECV))
+		if (!netlink_allowed(sock, NL_CFG_F_NONROOT_RECV))
 			return -EPERM;
 		err = netlink_realloc_groups(sk);
 		if (err)
 			return err;
 		if (!val || val - 1 >= nlk->ngroups)
 			return -EINVAL;
+		if (optname == NETLINK_ADD_MEMBERSHIP && nlk->netlink_bind) {
+			err = nlk->netlink_bind(val);
+			if (err)
+				return err;
+		}
 		netlink_table_grab();
 		netlink_update_socket_mc(nlk, val,
 					 optname == NETLINK_ADD_MEMBERSHIP);
 		netlink_table_ungrab();
-
-		if (nlk->netlink_bind)
-			nlk->netlink_bind(val);
+		if (optname == NETLINK_DROP_MEMBERSHIP && nlk->netlink_unbind)
+			nlk->netlink_unbind(val);
 
 		err = 0;
 		break;
@@ -2090,12 +2319,13 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sock_iocb *siocb = kiocb_to_siocb(kiocb);
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	struct sockaddr_nl *addr = msg->msg_name;
+	DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
 	u32 dst_portid;
 	u32 dst_group;
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2115,8 +2345,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 		dst_group = ffs(addr->nl_groups);
 		err =  -EPERM;
 		if ((dst_group || dst_portid) &&
-		    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+		    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 			goto out;
+		netlink_skb_flags |= NETLINK_SKB_DST;
 	} else {
 		dst_portid = nlk->dst_portid;
 		dst_group = nlk->dst_group;
@@ -2139,13 +2370,14 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	if (len > sk->sk_sndbuf - 32)
 		goto out;
 	err = -ENOBUFS;
-	skb = netlink_alloc_large_skb(len);
+	skb = netlink_alloc_large_skb(len, dst_group);
 	if (skb == NULL)
 		goto out;
 
 	NETLINK_CB(skb).portid	= nlk->portid;
 	NETLINK_CB(skb).dst_group = dst_group;
 	NETLINK_CB(skb).creds	= siocb->scm->creds;
+	NETLINK_CB(skb).flags	= netlink_skb_flags;
 
 	err = -EFAULT;
 	if (memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len)) {
@@ -2211,7 +2443,10 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 #endif
 
-	msg->msg_namelen = 0;
+	/* Record the max length of recvmsg() calls for future allocations */
+	nlk->max_recvmsg_len = max(nlk->max_recvmsg_len, len);
+	nlk->max_recvmsg_len = min_t(size_t, nlk->max_recvmsg_len,
+				     16384);
 
 	copied = data_skb->len;
 	if (len < copied) {
@@ -2223,7 +2458,7 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	err = skb_copy_datagram_iovec(data_skb, 0, msg->msg_iov, copied);
 
 	if (msg->msg_name) {
-		struct sockaddr_nl *addr = (struct sockaddr_nl *)msg->msg_name;
+		DECLARE_SOCKADDR(struct sockaddr_nl *, addr, msg->msg_name);
 		addr->nl_family = AF_NETLINK;
 		addr->nl_pad    = 0;
 		addr->nl_pid	= NETLINK_CB(skb).portid;
@@ -2244,10 +2479,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 
 	skb_free_datagram(sk, skb);
 
-	if (nlk->cb && atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
+	if (nlk->cb_running &&
+	    atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf / 2) {
 		ret = netlink_dump(sk);
 		if (ret) {
-			sk->sk_err = ret;
+			sk->sk_err = -ret;
 			sk->sk_error_report(sk);
 		}
 	}
@@ -2258,7 +2494,7 @@ out:
 	return err ? : copied;
 }
 
-static void netlink_data_ready(struct sock *sk, int len)
+static void netlink_data_ready(struct sock *sk)
 {
 	BUG();
 }
@@ -2412,28 +2648,13 @@ void __netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
 		netlink_update_socket_mc(nlk_sk(sk), group, 0);
 }
 
-/**
- * netlink_clear_multicast_users - kick off multicast listeners
- *
- * This function removes all listeners from the given group.
- * @ksk: The kernel netlink socket, as returned by
- *	netlink_kernel_create().
- * @group: The multicast group to clear.
- */
-void netlink_clear_multicast_users(struct sock *ksk, unsigned int group)
-{
-	netlink_table_grab();
-	__netlink_clear_multicast_users(ksk, group);
-	netlink_table_ungrab();
-}
-
 struct nlmsghdr *
 __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int flags)
 {
 	struct nlmsghdr *nlh;
 	int size = nlmsg_msg_size(len);
 
-	nlh = (struct nlmsghdr*)skb_put(skb, NLMSG_ALIGN(size));
+	nlh = (struct nlmsghdr *)skb_put(skb, NLMSG_ALIGN(size));
 	nlh->nlmsg_type = type;
 	nlh->nlmsg_len = size;
 	nlh->nlmsg_flags = flags;
@@ -2460,19 +2681,38 @@ static int netlink_dump(struct sock *sk)
 	int alloc_size;
 
 	mutex_lock(nlk->cb_mutex);
-
-	cb = nlk->cb;
-	if (cb == NULL) {
+	if (!nlk->cb_running) {
 		err = -EINVAL;
 		goto errout_skb;
 	}
 
+	cb = &nlk->cb;
 	alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
 
 	if (!netlink_rx_is_mmaped(sk) &&
 	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
-	skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
+
+	/* NLMSG_GOODSIZE is small to avoid high order allocations being
+	 * required, but it makes sense to _attempt_ a 16K bytes allocation
+	 * to reduce number of system calls on dump operations, if user
+	 * ever provided a big enough buffer.
+	 */
+	if (alloc_size < nlk->max_recvmsg_len) {
+		skb = netlink_alloc_skb(sk,
+					nlk->max_recvmsg_len,
+					nlk->portid,
+					GFP_KERNEL |
+					__GFP_NOWARN |
+					__GFP_NORETRY);
+		/* available room should be exact amount to avoid MSG_TRUNC */
+		if (skb)
+			skb_reserve(skb, skb_tailroom(skb) -
+					 nlk->max_recvmsg_len);
+	}
+	if (!skb)
+		skb = netlink_alloc_skb(sk, alloc_size, nlk->portid,
+					GFP_KERNEL);
 	if (!skb)
 		goto errout_skb;
 	netlink_skb_set_owner_r(skb, sk);
@@ -2504,11 +2744,11 @@ static int netlink_dump(struct sock *sk)
 
 	if (cb->done)
 		cb->done(cb);
-	nlk->cb = NULL;
-	mutex_unlock(nlk->cb_mutex);
 
+	nlk->cb_running = false;
+	mutex_unlock(nlk->cb_mutex);
 	module_put(cb->module);
-	netlink_consume_callback(cb);
+	consume_skb(cb->skb);
 	return 0;
 
 errout_skb:
@@ -2526,59 +2766,51 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	struct netlink_sock *nlk;
 	int ret;
 
-	cb = kzalloc(sizeof(*cb), GFP_KERNEL);
-	if (cb == NULL)
-		return -ENOBUFS;
-
 	/* Memory mapped dump requests need to be copied to avoid looping
 	 * on the pending state in netlink_mmap_sendmsg() while the CB hold
 	 * a reference to the skb.
 	 */
 	if (netlink_skb_is_mmaped(skb)) {
 		skb = skb_copy(skb, GFP_KERNEL);
-		if (skb == NULL) {
-			kfree(cb);
+		if (skb == NULL)
 			return -ENOBUFS;
-		}
 	} else
 		atomic_inc(&skb->users);
 
-	cb->dump = control->dump;
-	cb->done = control->done;
-	cb->nlh = nlh;
-	cb->data = control->data;
-	cb->module = control->module;
-	cb->min_dump_alloc = control->min_dump_alloc;
-	cb->skb = skb;
-
 	sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid);
 	if (sk == NULL) {
-		netlink_destroy_callback(cb);
-		return -ECONNREFUSED;
+		ret = -ECONNREFUSED;
+		goto error_free;
 	}
-	nlk = nlk_sk(sk);
 
+	nlk = nlk_sk(sk);
 	mutex_lock(nlk->cb_mutex);
 	/* A dump is in progress... */
-	if (nlk->cb) {
-		mutex_unlock(nlk->cb_mutex);
-		netlink_destroy_callback(cb);
+	if (nlk->cb_running) {
 		ret = -EBUSY;
-		goto out;
+		goto error_unlock;
 	}
 	/* add reference of module which cb->dump belongs to */
-	if (!try_module_get(cb->module)) {
-		mutex_unlock(nlk->cb_mutex);
-		netlink_destroy_callback(cb);
+	if (!try_module_get(control->module)) {
 		ret = -EPROTONOSUPPORT;
-		goto out;
+		goto error_unlock;
 	}
 
-	nlk->cb = cb;
+	cb = &nlk->cb;
+	memset(cb, 0, sizeof(*cb));
+	cb->dump = control->dump;
+	cb->done = control->done;
+	cb->nlh = nlh;
+	cb->data = control->data;
+	cb->module = control->module;
+	cb->min_dump_alloc = control->min_dump_alloc;
+	cb->skb = skb;
+
+	nlk->cb_running = true;
+
 	mutex_unlock(nlk->cb_mutex);
 
 	ret = netlink_dump(sk);
-out:
 	sock_put(sk);
 
 	if (ret)
@@ -2588,6 +2820,13 @@ out:
 	 * signal not to send ACK even if it was requested.
 	 */
 	return -EINTR;
+
+error_unlock:
+	sock_put(sk);
+	mutex_unlock(nlk->cb_mutex);
+error_free:
+	kfree_skb(skb);
+	return ret;
 }
 EXPORT_SYMBOL(__netlink_dump_start);
 
@@ -2810,14 +3049,14 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 		struct sock *s = v;
 		struct netlink_sock *nlk = nlk_sk(s);
 
-		seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %pK %-8d %-8d %-8lu\n",
+		seq_printf(seq, "%pK %-3d %-6u %08x %-8d %-8d %d %-8d %-8d %-8lu\n",
 			   s,
 			   s->sk_protocol,
 			   nlk->portid,
 			   nlk->groups ? (u32)nlk->groups[0] : 0,
 			   sk_rmem_alloc_get(s),
 			   sk_wmem_alloc_get(s),
-			   nlk->cb,
+			   nlk->cb_running,
 			   atomic_read(&s->sk_refcnt),
 			   atomic_read(&s->sk_drops),
 			   sock_i_ino(s)
@@ -2975,6 +3214,8 @@ static int __init netlink_proto_init(void)
 		nl_table[i].compare = netlink_compare;
 	}
 
+	INIT_LIST_HEAD(&netlink_tap_all);
+
 	netlink_add_usersock_entry();
 
 	sock_register(&netlink_family_ops);