X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fnetlink%2Faf_netlink.c;h=8b6bbb3032b0ca1718037ff0b3139e883c3d813a;hb=38938bfe3489394e2eed5e40c9bb8f66a2ce1405;hp=21f9e30184e20f1eb89d9d726b82d22e8cc3544d;hpb=3f25252675770e08d97bc112e52208e8c70ce0e5;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 21f9e30..8b6bbb3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1,7 +1,7 @@
 /*
  * NETLINK      Kernel-user communication protocol.
  *
- * 		Authors:	Alan Cox <alan@redhat.com>
+ * 		Authors:	Alan Cox <alan@lxorguk.ukuu.org.uk>
  * 				Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
  *
  *		This program is free software; you can redistribute it and/or
@@ -54,7 +54,6 @@
 #include <linux/mm.h>
 #include <linux/types.h>
 #include <linux/audit.h>
-#include <linux/selinux.h>
 #include <linux/mutex.h>
 
 #include <net/net_namespace.h>
@@ -86,6 +85,8 @@ struct netlink_sock {
 
 #define NETLINK_KERNEL_SOCKET	0x1
 #define NETLINK_RECV_PKTINFO	0x2
+#define NETLINK_BROADCAST_SEND_ERROR	0x4
+#define NETLINK_RECV_NO_ENOBUFS	0x8
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
 {
@@ -159,9 +160,10 @@ static void netlink_sock_destruct(struct sock *sk)
 		printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
 		return;
 	}
-	BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
-	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
-	BUG_TRAP(!nlk_sk(sk)->groups);
+
+	WARN_ON(atomic_read(&sk->sk_rmem_alloc));
+	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
+	WARN_ON(nlk_sk(sk)->groups);
 }
 
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
@@ -228,7 +230,7 @@ static inline struct sock *netlink_lookup(struct net *net, int protocol,
 	read_lock(&nl_table_lock);
 	head = nl_pid_hashfn(hash, pid);
 	sk_for_each(sk, node, head) {
-		if ((sk->sk_net == net) && (nlk_sk(sk)->pid == pid)) {
+		if (net_eq(sock_net(sk), net) && (nlk_sk(sk)->pid == pid)) {
 			sock_hold(sk);
 			goto found;
 		}
@@ -348,7 +350,7 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 pid)
 	head = nl_pid_hashfn(hash, pid);
 	len = 0;
 	sk_for_each(osk, node, head) {
-		if ((osk->sk_net == net) && (nlk_sk(osk)->pid == pid))
+		if (net_eq(sock_net(osk), net) && (nlk_sk(osk)->pid == pid))
 			break;
 		len++;
 	}
@@ -435,7 +437,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol)
 		return -EPROTONOSUPPORT;
 
 	netlink_lock_table();
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
 	if (!nl_table[protocol].registered) {
 		netlink_unlock_table();
 		request_module("net-pf-%d-proto-%d", PF_NETLINK, protocol);
@@ -452,6 +454,10 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol)
 	if (err < 0)
 		goto out_module;
 
+	local_bh_disable();
+	sock_prot_inuse_add(net, &netlink_proto, 1);
+	local_bh_enable();
+
 	nlk = nlk_sk(sock->sk);
 	nlk->module = module;
 out:
@@ -486,7 +492,7 @@ static int netlink_release(struct socket *sock)
 
 	if (nlk->pid && !nlk->subscriptions) {
 		struct netlink_notify n = {
-						.net = sk->sk_net,
+						.net = sock_net(sk),
 						.protocol = sk->sk_protocol,
 						.pid = nlk->pid,
 					  };
@@ -498,9 +504,12 @@ static int netlink_release(struct socket *sock)
 
 	netlink_table_grab();
 	if (netlink_is_kernel(sk)) {
-		kfree(nl_table[sk->sk_protocol].listeners);
-		nl_table[sk->sk_protocol].module = NULL;
-		nl_table[sk->sk_protocol].registered = 0;
+		BUG_ON(nl_table[sk->sk_protocol].registered == 0);
+		if (--nl_table[sk->sk_protocol].registered == 0) {
+			kfree(nl_table[sk->sk_protocol].listeners);
+			nl_table[sk->sk_protocol].module = NULL;
+			nl_table[sk->sk_protocol].registered = 0;
+		}
 	} else if (nlk->subscriptions)
 		netlink_update_listeners(sk);
 	netlink_table_ungrab();
@@ -508,6 +517,9 @@ static int netlink_release(struct socket *sock)
 	kfree(nlk->groups);
 	nlk->groups = NULL;
 
+	local_bh_disable();
+	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
+	local_bh_enable();
 	sock_put(sk);
 	return 0;
 }
@@ -515,7 +527,7 @@ static int netlink_release(struct socket *sock)
 static int netlink_autobind(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
-	struct net *net = sk->sk_net;
+	struct net *net = sock_net(sk);
 	struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash;
 	struct hlist_head *head;
 	struct sock *osk;
@@ -529,7 +541,7 @@ retry:
 	netlink_table_grab();
 	head = nl_pid_hashfn(hash, pid);
 	sk_for_each(osk, node, head) {
-		if ((osk->sk_net != net))
+		if (!net_eq(sock_net(osk), net))
 			continue;
 		if (nlk_sk(osk)->pid == pid) {
 			/* Bind collision, search negative pid values. */
@@ -608,7 +620,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 			int addr_len)
 {
 	struct sock *sk = sock->sk;
-	struct net *net = sk->sk_net;
+	struct net *net = sock_net(sk);
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err;
@@ -706,10 +718,15 @@ static int netlink_getname(struct socket *sock, struct sockaddr *addr,
 
 static void netlink_overrun(struct sock *sk)
 {
-	if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
-		sk->sk_err = ENOBUFS;
-		sk->sk_error_report(sk);
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (!(nlk->flags & NETLINK_RECV_NO_ENOBUFS)) {
+		if (!test_and_set_bit(0, &nlk_sk(sk)->state)) {
+			sk->sk_err = ENOBUFS;
+			sk->sk_error_report(sk);
+		}
 	}
+	atomic_inc(&sk->sk_drops);
 }
 
 static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
@@ -717,7 +734,7 @@ static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid)
 	struct sock *sock;
 	struct netlink_sock *nlk;
 
-	sock = netlink_lookup(ssk->sk_net, ssk->sk_protocol, pid);
+	sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, pid);
 	if (!sock)
 		return ERR_PTR(-ECONNREFUSED);
 
@@ -757,7 +774,7 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
  * 0: continue
  * 1: repeat lookup - reference dropped while waiting for socket memory.
  */
-int netlink_attachskb(struct sock *sk, struct sk_buff *skb, int nonblock,
+int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 		      long *timeo, struct sock *ssk)
 {
 	struct netlink_sock *nlk;
@@ -883,7 +900,14 @@ retry:
 	if (netlink_is_kernel(sk))
 		return netlink_unicast_kernel(sk, skb);
 
-	err = netlink_attachskb(sk, skb, nonblock, &timeo, ssk);
+	if (sk_filter(sk, skb)) {
+		err = skb->len;
+		kfree_skb(skb);
+		sock_put(sk);
+		return err;
+	}
+
+	err = netlink_attachskb(sk, skb, &timeo, ssk);
 	if (err == 1)
 		goto retry;
 	if (err)
@@ -933,6 +957,7 @@ struct netlink_broadcast_data {
 	u32 pid;
 	u32 group;
 	int failure;
+	int delivery_failure;
 	int congested;
 	int delivered;
 	gfp_t allocation;
@@ -952,7 +977,7 @@ static inline int do_one_broadcast(struct sock *sk,
 	    !test_bit(p->group - 1, nlk->groups))
 		goto out;
 
-	if ((sk->sk_net != p->net))
+	if (!net_eq(sock_net(sk), p->net))
 		goto out;
 
 	if (p->failure) {
@@ -977,8 +1002,15 @@ static inline int do_one_broadcast(struct sock *sk,
 		netlink_overrun(sk);
 		/* Clone failed. Notify ALL listeners. */
 		p->failure = 1;
+		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+			p->delivery_failure = 1;
+	} else if (sk_filter(sk, p->skb2)) {
+		kfree_skb(p->skb2);
+		p->skb2 = NULL;
 	} else if ((val = netlink_broadcast_deliver(sk, p->skb2)) < 0) {
 		netlink_overrun(sk);
+		if (nlk->flags & NETLINK_BROADCAST_SEND_ERROR)
+			p->delivery_failure = 1;
 	} else {
 		p->congested |= val;
 		p->delivered = 1;
@@ -993,7 +1025,7 @@ out:
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 		      u32 group, gfp_t allocation)
 {
-	struct net *net = ssk->sk_net;
+	struct net *net = sock_net(ssk);
 	struct netlink_broadcast_data info;
 	struct hlist_node *node;
 	struct sock *sk;
@@ -1005,6 +1037,7 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 	info.pid = pid;
 	info.group = group;
 	info.failure = 0;
+	info.delivery_failure = 0;
 	info.congested = 0;
 	info.delivered = 0;
 	info.allocation = allocation;
@@ -1022,16 +1055,16 @@ int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid,
 
 	netlink_unlock_table();
 
-	if (info.skb2)
-		kfree_skb(info.skb2);
+	kfree_skb(info.skb2);
+
+	if (info.delivery_failure)
+		return -ENOBUFS;
 
 	if (info.delivered) {
 		if (info.congested && (allocation & __GFP_WAIT))
 			yield();
 		return 0;
 	}
-	if (info.failure)
-		return -ENOBUFS;
 	return -ESRCH;
 }
 EXPORT_SYMBOL(netlink_broadcast);
@@ -1051,7 +1084,7 @@ static inline int do_one_set_err(struct sock *sk,
 	if (sk == p->exclude_sk)
 		goto out;
 
-	if (sk->sk_net != p->exclude_sk->sk_net)
+	if (sock_net(sk) != sock_net(p->exclude_sk))
 		goto out;
 
 	if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups ||
@@ -1064,6 +1097,13 @@ out:
 	return 0;
 }
 
+/**
+ * netlink_set_err - report error to broadcast listeners
+ * @ssk: the kernel netlink socket, as returned by netlink_kernel_create()
+ * @pid: the PID of a process that we want to skip (if any)
+ * @groups: the broadcast group that will notice the error
+ * @code: error code, must be negative (as usual in kernelspace)
+ */
 void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 {
 	struct netlink_set_err_data info;
@@ -1073,7 +1113,8 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 	info.exclude_sk = ssk;
 	info.pid = pid;
 	info.group = group;
-	info.code = code;
+	/* sk->sk_err wants a positive error value */
+	info.code = -code;
 
 	read_lock(&nl_table_lock);
 
@@ -1082,6 +1123,7 @@ void netlink_set_err(struct sock *ssk, u32 pid, u32 group, int code)
 
 	read_unlock(&nl_table_lock);
 }
+EXPORT_SYMBOL(netlink_set_err);
 
 /* must be called with netlink table grabbed */
 static void netlink_update_socket_mc(struct netlink_sock *nlk,
@@ -1139,6 +1181,22 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		err = 0;
 		break;
 	}
+	case NETLINK_BROADCAST_ERROR:
+		if (val)
+			nlk->flags |= NETLINK_BROADCAST_SEND_ERROR;
+		else
+			nlk->flags &= ~NETLINK_BROADCAST_SEND_ERROR;
+		err = 0;
+		break;
+	case NETLINK_NO_ENOBUFS:
+		if (val) {
+			nlk->flags |= NETLINK_RECV_NO_ENOBUFS;
+			clear_bit(0, &nlk->state);
+			wake_up_interruptible(&nlk->wait);
+		} else
+			nlk->flags &= ~NETLINK_RECV_NO_ENOBUFS;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1171,6 +1229,26 @@ static int netlink_getsockopt(struct socket *sock, int level, int optname,
 			return -EFAULT;
 		err = 0;
 		break;
+	case NETLINK_BROADCAST_ERROR:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_BROADCAST_SEND_ERROR ? 1 : 0;
+		if (put_user(len, optlen) ||
+		    put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
+	case NETLINK_NO_ENOBUFS:
+		if (len < sizeof(int))
+			return -EINVAL;
+		len = sizeof(int);
+		val = nlk->flags & NETLINK_RECV_NO_ENOBUFS ? 1 : 0;
+		if (put_user(len, optlen) ||
+		    put_user(val, optval))
+			return -EFAULT;
+		err = 0;
+		break;
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -1235,8 +1313,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 
 	NETLINK_CB(skb).pid	= nlk->pid;
 	NETLINK_CB(skb).dst_group = dst_group;
-	NETLINK_CB(skb).loginuid = audit_get_loginuid(current->audit_context);
-	selinux_get_task_sid(current, &(NETLINK_CB(skb).sid));
+	NETLINK_CB(skb).loginuid = audit_get_loginuid(current);
+	NETLINK_CB(skb).sessionid = audit_get_sessionid(current);
+	security_task_getsecid(current, &(NETLINK_CB(skb).sid));
 	memcpy(NETLINK_CREDS(skb), &siocb->scm->creds, sizeof(struct ucred));
 
 	/* What can I do? Netlink is asynchronous, so that
@@ -1359,8 +1438,17 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups,
 	if (sock_create_lite(PF_NETLINK, SOCK_DGRAM, unit, &sock))
 		return NULL;
 
-	if (__netlink_create(net, sock, cb_mutex, unit) < 0)
-		goto out_sock_release;
+	/*
+	 * We have to just have a reference on the net from sk, but don't
+	 * get_net it. Besides, we cannot get and then put the net here.
+	 * So we create one inside init_net and the move it to net.
+	 */
+
+	if (__netlink_create(&init_net, sock, cb_mutex, unit) < 0)
+		goto out_sock_release_nosk;
+
+	sk = sock->sk;
+	sk_change_net(sk, net);
 
 	if (groups < 32)
 		groups = 32;
@@ -1369,7 +1457,6 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups,
 	if (!listeners)
 		goto out_sock_release;
 
-	sk = sock->sk;
 	sk->sk_data_ready = netlink_data_ready;
 	if (input)
 		nlk_sk(sk)->netlink_rcv = input;
@@ -1389,18 +1476,31 @@ netlink_kernel_create(struct net *net, int unit, unsigned int groups,
 		nl_table[unit].registered = 1;
 	} else {
 		kfree(listeners);
+		nl_table[unit].registered++;
 	}
 	netlink_table_ungrab();
-
 	return sk;
 
 out_sock_release:
 	kfree(listeners);
+	netlink_kernel_release(sk);
+	return NULL;
+
+out_sock_release_nosk:
 	sock_release(sock);
 	return NULL;
 }
 EXPORT_SYMBOL(netlink_kernel_create);
 
+
+void
+netlink_kernel_release(struct sock *sk)
+{
+	sk_release_kernel(sk);
+}
+EXPORT_SYMBOL(netlink_kernel_release);
+
+
 /**
  * netlink_change_ngroups - change number of multicast groups
  *
@@ -1475,8 +1575,7 @@ EXPORT_SYMBOL(netlink_set_nonroot);
 
 static void netlink_destroy_callback(struct netlink_callback *cb)
 {
-	if (cb->skb)
-		kfree_skb(cb->skb);
+	kfree_skb(cb->skb);
 	kfree(cb);
 }
 
@@ -1509,8 +1608,13 @@ static int netlink_dump(struct sock *sk)
 
 	if (len > 0) {
 		mutex_unlock(nlk->cb_mutex);
-		skb_queue_tail(&sk->sk_receive_queue, skb);
-		sk->sk_data_ready(sk, len);
+
+		if (sk_filter(sk, skb))
+			kfree_skb(skb);
+		else {
+			skb_queue_tail(&sk->sk_receive_queue, skb);
+			sk->sk_data_ready(sk, skb->len);
+		}
 		return 0;
 	}
 
@@ -1520,8 +1624,12 @@ static int netlink_dump(struct sock *sk)
 
 	memcpy(nlmsg_data(nlh), &len, sizeof(len));
 
-	skb_queue_tail(&sk->sk_receive_queue, skb);
-	sk->sk_data_ready(sk, skb->len);
+	if (sk_filter(sk, skb))
+		kfree_skb(skb);
+	else {
+		skb_queue_tail(&sk->sk_receive_queue, skb);
+		sk->sk_data_ready(sk, skb->len);
+	}
 
 	if (cb->done)
 		cb->done(cb);
@@ -1558,7 +1666,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	atomic_inc(&skb->users);
 	cb->skb = skb;
 
-	sk = netlink_lookup(ssk->sk_net, ssk->sk_protocol, NETLINK_CB(skb).pid);
+	sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).pid);
 	if (sk == NULL) {
 		netlink_destroy_callback(cb);
 		return -ECONNREFUSED;
@@ -1600,7 +1708,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 	if (!skb) {
 		struct sock *sk;
 
-		sk = netlink_lookup(in_skb->sk->sk_net,
+		sk = netlink_lookup(sock_net(in_skb->sk),
 				    in_skb->sk->sk_protocol,
 				    NETLINK_CB(in_skb).pid);
 		if (sk) {
@@ -1684,12 +1792,18 @@ int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 pid,
 			exclude_pid = pid;
 		}
 
-		/* errors reported via destination sk->sk_err */
-		nlmsg_multicast(sk, skb, exclude_pid, group, flags);
+		/* errors reported via destination sk->sk_err, but propagate
+		 * delivery errors if NETLINK_BROADCAST_ERROR flag is set */
+		err = nlmsg_multicast(sk, skb, exclude_pid, group, flags);
 	}
 
-	if (report)
-		err = nlmsg_unicast(sk, skb, pid);
+	if (report) {
+		int err2;
+
+		err2 = nlmsg_unicast(sk, skb, pid);
+		if (!err || err == -ESRCH)
+			err = err2;
+	}
 
 	return err;
 }
@@ -1715,7 +1829,7 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos)
 
 		for (j = 0; j <= hash->mask; j++) {
 			sk_for_each(s, node, &hash->table[j]) {
-				if (iter->p.net != s->sk_net)
+				if (sock_net(s) != seq_file_net(seq))
 					continue;
 				if (off == pos) {
 					iter->link = i;
@@ -1751,7 +1865,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	s = v;
 	do {
 		s = sk_next(s);
-	} while (s && (iter->p.net != s->sk_net));
+	} while (s && sock_net(s) != seq_file_net(seq));
 	if (s)
 		return s;
 
@@ -1763,7 +1877,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 
 		for (; j <= hash->mask; j++) {
 			s = sk_head(&hash->table[j]);
-			while (s && (iter->p.net != s->sk_net))
+			while (s && sock_net(s) != seq_file_net(seq))
 				s = sk_next(s);
 			if (s) {
 				iter->link = i;
@@ -1790,12 +1904,12 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 	if (v == SEQ_START_TOKEN)
 		seq_puts(seq,
 			 "sk       Eth Pid    Groups   "
-			 "Rmem     Wmem     Dump     Locks\n");
+			 "Rmem     Wmem     Dump     Locks     Drops\n");
 	else {
 		struct sock *s = v;
 		struct netlink_sock *nlk = nlk_sk(s);
 
-		seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %d\n",
+		seq_printf(seq, "%p %-3d %-6d %08x %-8d %-8d %p %-8d %-8d\n",
 			   s,
 			   s->sk_protocol,
 			   nlk->pid,
@@ -1803,7 +1917,8 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 			   atomic_read(&s->sk_rmem_alloc),
 			   atomic_read(&s->sk_wmem_alloc),
 			   nlk->cb,
-			   atomic_read(&s->sk_refcnt)
+			   atomic_read(&s->sk_refcnt),
+			   atomic_read(&s->sk_drops)
 			);
 
 	}