1 files changed, 105 insertions, 10 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 04748ab649c..f22757a29cd 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1360,7 +1360,74 @@ 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);
@@ -1428,7 +1495,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 
 	/* Only superuser is allowed to listen multicasts */
 	if (nladdr->nl_groups) {
-		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)
@@ -1460,7 +1527,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	if (nlk->netlink_bind && nlk->groups[0]) {
 		int i;
 
-		for (i=0; i<nlk->ngroups; i++) {
+		for (i = 0; i < nlk->ngroups; i++) {
 			if (test_bit(i, nlk->groups))
 				nlk->netlink_bind(i);
 		}
@@ -1490,7 +1557,7 @@ static int netlink_connect(struct socket *sock, struct sockaddr *addr,
 		return -EINVAL;
 
 	if ((nladdr->nl_groups || nladdr->nl_pid) &&
-	    !netlink_capable(sock, NL_CFG_F_NONROOT_SEND))
+	    !netlink_allowed(sock, NL_CFG_F_NONROOT_SEND))
 		return -EPERM;
 
 	if (!nlk->portid)
@@ -1653,7 +1720,7 @@ 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;
 }
 
@@ -2096,7 +2163,7 @@ 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)
@@ -2228,6 +2295,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	struct sk_buff *skb;
 	int err;
 	struct scm_cookie scm;
+	u32 netlink_skb_flags = 0;
 
 	if (msg->msg_flags&MSG_OOB)
 		return -EOPNOTSUPP;
@@ -2247,8 +2315,9 @@ 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;
@@ -2278,6 +2347,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 	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)) {
@@ -2343,6 +2413,11 @@ static int netlink_recvmsg(struct kiocb *kiocb, struct socket *sock,
 	}
 #endif
 
+	/* 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) {
 		msg->msg_flags |= MSG_TRUNC;
@@ -2389,7 +2464,7 @@ out:
 	return err ? : copied;
 }
 
-static void netlink_data_ready(struct sock *sk, int len)
+static void netlink_data_ready(struct sock *sk)
 {
 	BUG();
 }
@@ -2549,7 +2624,7 @@ __nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int len, int fla
 	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;
@@ -2587,7 +2662,27 @@ static int netlink_dump(struct sock *sk)
 	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);