X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Fraw.c;h=ab996f9c0fe0ec0c8210698d874022cd786add7d;hb=eaa04dc353f45404be54a61b48a3f97de12fafc3;hp=d24501a342a4e597cf4b40b14c07099edb4351f8;hpb=ab70768ec78c6784958bab3b58fbe3f4150006df;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index d24501a..ab996f9 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -5,8 +5,6 @@
  *
  *		RAW - implementation of IP "raw" sockets.
  *
- * Version:	$Id: raw.c,v 1.64 2002/02/01 22:01:04 davem Exp $
- *
  * Authors:	Ross Biro
  *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
  *
@@ -81,51 +79,43 @@
 #include <linux/netfilter_ipv4.h>
 
 static struct raw_hashinfo raw_v4_hashinfo = {
-	.lock = __RW_LOCK_UNLOCKED(),
+	.lock = __RW_LOCK_UNLOCKED(raw_v4_hashinfo.lock),
 };
 
-void raw_hash_sk(struct sock *sk, struct raw_hashinfo *h)
+void raw_hash_sk(struct sock *sk)
 {
+	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
 	struct hlist_head *head;
 
 	head = &h->ht[inet_sk(sk)->num & (RAW_HTABLE_SIZE - 1)];
 
 	write_lock_bh(&h->lock);
 	sk_add_node(sk, head);
-	sock_prot_inc_use(sk->sk_prot);
+	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
 	write_unlock_bh(&h->lock);
 }
 EXPORT_SYMBOL_GPL(raw_hash_sk);
 
-void raw_unhash_sk(struct sock *sk, struct raw_hashinfo *h)
+void raw_unhash_sk(struct sock *sk)
 {
+	struct raw_hashinfo *h = sk->sk_prot->h.raw_hash;
+
 	write_lock_bh(&h->lock);
 	if (sk_del_node_init(sk))
-		sock_prot_dec_use(sk->sk_prot);
+		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 	write_unlock_bh(&h->lock);
 }
 EXPORT_SYMBOL_GPL(raw_unhash_sk);
 
-static void raw_v4_hash(struct sock *sk)
-{
-	raw_hash_sk(sk, &raw_v4_hashinfo);
-}
-
-static void raw_v4_unhash(struct sock *sk)
-{
-	raw_unhash_sk(sk, &raw_v4_hashinfo);
-}
-
-static struct sock *__raw_v4_lookup(struct sock *sk, unsigned short num,
-			     __be32 raddr, __be32 laddr,
-			     int dif)
+static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk,
+		unsigned short num, __be32 raddr, __be32 laddr, int dif)
 {
 	struct hlist_node *node;
 
 	sk_for_each_from(sk, node) {
 		struct inet_sock *inet = inet_sk(sk);
 
-		if (inet->num == num 					&&
+		if (net_eq(sock_net(sk), net) && inet->num == num	&&
 		    !(inet->daddr && inet->daddr != raddr) 		&&
 		    !(inet->rcv_saddr && inet->rcv_saddr != laddr)	&&
 		    !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
@@ -169,12 +159,15 @@ static int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
 	struct sock *sk;
 	struct hlist_head *head;
 	int delivered = 0;
+	struct net *net;
 
 	read_lock(&raw_v4_hashinfo.lock);
 	head = &raw_v4_hashinfo.ht[hash];
 	if (hlist_empty(head))
 		goto out;
-	sk = __raw_v4_lookup(__sk_head(head), iph->protocol,
+
+	net = dev_net(skb->dev);
+	sk = __raw_v4_lookup(net, __sk_head(head), iph->protocol,
 			     iph->saddr, iph->daddr,
 			     skb->dev->ifindex);
 
@@ -187,7 +180,7 @@ static int raw_v4_input(struct sk_buff *skb, struct iphdr *iph, int hash)
 			if (clone)
 				raw_rcv(sk, clone);
 		}
-		sk = __raw_v4_lookup(sk_next(sk), iph->protocol,
+		sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol,
 				     iph->saddr, iph->daddr,
 				     skb->dev->ifindex);
 	}
@@ -254,7 +247,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 	}
 
 	if (inet->recverr) {
-		struct iphdr *iph = (struct iphdr*)skb->data;
+		struct iphdr *iph = (struct iphdr *)skb->data;
 		u8 *payload = skb->data + (iph->ihl << 2);
 
 		if (inet->hdrincl)
@@ -273,6 +266,7 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 	int hash;
 	struct sock *raw_sk;
 	struct iphdr *iph;
+	struct net *net;
 
 	hash = protocol & (RAW_HTABLE_SIZE - 1);
 
@@ -280,8 +274,10 @@ void raw_icmp_error(struct sk_buff *skb, int protocol, u32 info)
 	raw_sk = sk_head(&raw_v4_hashinfo.ht[hash]);
 	if (raw_sk != NULL) {
 		iph = (struct iphdr *)skb->data;
-		while ((raw_sk = __raw_v4_lookup(raw_sk, protocol, iph->daddr,
-						iph->saddr,
+		net = dev_net(skb->dev);
+
+		while ((raw_sk = __raw_v4_lookup(net, raw_sk, protocol,
+						iph->daddr, iph->saddr,
 						skb->dev->ifindex)) != NULL) {
 			raw_err(raw_sk, skb, info);
 			raw_sk = sk_next(raw_sk);
@@ -324,7 +320,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
 			unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
-	int hh_len;
+	struct net *net = sock_net(sk);
 	struct iphdr *iph;
 	struct sk_buff *skb;
 	unsigned int iphlen;
@@ -338,16 +334,16 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
 	if (flags&MSG_PROBE)
 		goto out;
 
-	hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
-
-	skb = sock_alloc_send_skb(sk, length+hh_len+15,
-				  flags&MSG_DONTWAIT, &err);
+	skb = sock_alloc_send_skb(sk,
+				  length + LL_ALLOCATED_SPACE(rt->u.dst.dev) + 15,
+				  flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto error;
-	skb_reserve(skb, hh_len);
+	skb_reserve(skb, LL_RESERVED_SPACE(rt->u.dst.dev));
 
 	skb->priority = sk->sk_priority;
-	skb->dst = dst_clone(&rt->u.dst);
+	skb->mark = sk->sk_mark;
+	skb_dst_set(skb, dst_clone(&rt->u.dst));
 
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
@@ -356,13 +352,24 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
 	skb->ip_summed = CHECKSUM_NONE;
 
 	skb->transport_header = skb->network_header;
-	err = memcpy_fromiovecend((void *)iph, from, 0, length);
-	if (err)
-		goto error_fault;
+	err = -EFAULT;
+	if (memcpy_fromiovecend((void *)iph, from, 0, length))
+		goto error_free;
 
-	/* We don't modify invalid header */
 	iphlen = iph->ihl * 4;
-	if (iphlen >= sizeof(*iph) && iphlen <= length) {
+
+	/*
+	 * We don't want to modify the ip header, but we do need to
+	 * be sure that it won't cause problems later along the network
+	 * stack.  Specifically we want to make sure that iph->ihl is a
+	 * sane value.  If ihl points beyond the length of the buffer passed
+	 * in, reject the frame as invalid
+	 */
+	err = -EINVAL;
+	if (iphlen > length)
+		goto error_free;
+
+	if (iphlen >= sizeof(*iph)) {
 		if (!iph->saddr)
 			iph->saddr = rt->rt_src;
 		iph->check   = 0;
@@ -373,23 +380,24 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length,
 		iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
 	}
 	if (iph->protocol == IPPROTO_ICMP)
-		icmp_out_count(((struct icmphdr *)
+		icmp_out_count(net, ((struct icmphdr *)
 			skb_transport_header(skb))->type);
 
 	err = NF_HOOK(PF_INET, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
 		      dst_output);
 	if (err > 0)
-		err = inet->recverr ? net_xmit_errno(err) : 0;
+		err = net_xmit_errno(err);
 	if (err)
 		goto error;
 out:
 	return 0;
 
-error_fault:
-	err = -EFAULT;
+error_free:
 	kfree_skb(skb);
 error:
-	IP_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
+	IP_INC_STATS(net, IPSTATS_MIB_OUTDISCARDS);
+	if (err == -ENOBUFS && !inet->recverr)
+		err = 0;
 	return err;
 }
 
@@ -469,7 +477,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	 */
 
 	if (msg->msg_namelen) {
-		struct sockaddr_in *usin = (struct sockaddr_in*)msg->msg_name;
+		struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name;
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(*usin))
 			goto out;
@@ -497,10 +505,11 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	ipc.addr = inet->saddr;
 	ipc.opt = NULL;
+	ipc.shtx.flags = 0;
 	ipc.oif = sk->sk_bound_dev_if;
 
 	if (msg->msg_controllen) {
-		err = ip_cmsg_send(msg, &ipc);
+		err = ip_cmsg_send(sock_net(sk), msg, &ipc);
 		if (err)
 			goto out;
 		if (ipc.opt)
@@ -530,7 +539,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (msg->msg_flags & MSG_DONTROUTE)
 		tos |= RTO_ONLINK;
 
-	if (MULTICAST(daddr)) {
+	if (ipv4_is_multicast(daddr)) {
 		if (!ipc.oif)
 			ipc.oif = inet->mc_index;
 		if (!saddr)
@@ -539,6 +548,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 
 	{
 		struct flowi fl = { .oif = ipc.oif,
+				    .mark = sk->sk_mark,
 				    .nl_u = { .ip4_u =
 					      { .daddr = daddr,
 						.saddr = saddr,
@@ -553,7 +563,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		}
 
 		security_sk_classify_flow(sk, &fl);
-		err = ip_route_output_flow(&rt, &fl, sk, 1);
+		err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 1);
 	}
 	if (err)
 		goto done;
@@ -575,11 +585,14 @@ back_from_confirm:
 			ipc.addr = rt->rt_dst;
 		lock_sock(sk);
 		err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0,
-					&ipc, rt, msg->msg_flags);
+					&ipc, &rt, msg->msg_flags);
 		if (err)
 			ip_flush_pending_frames(sk);
-		else if (!(msg->msg_flags & MSG_MORE))
+		else if (!(msg->msg_flags & MSG_MORE)) {
 			err = ip_push_pending_frames(sk);
+			if (err == -ENOBUFS && !inet->recverr)
+				err = 0;
+		}
 		release_sock(sk);
 	}
 done:
@@ -610,6 +623,13 @@ static void raw_close(struct sock *sk, long timeout)
 	sk_common_release(sk);
 }
 
+static void raw_destroy(struct sock *sk)
+{
+	lock_sock(sk);
+	ip_flush_pending_frames(sk);
+	release_sock(sk);
+}
+
 /* This gets rid of all the nasties in af_inet. -DaveM */
 static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -620,7 +640,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in))
 		goto out;
-	chk_addr_ret = inet_addr_type(addr->sin_addr.s_addr);
+	chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
 	ret = -EADDRNOTAVAIL;
 	if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL &&
 	    chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST)
@@ -731,7 +751,7 @@ out:	return ret;
 }
 
 static int do_raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int optlen)
+			  char __user *optval, unsigned int optlen)
 {
 	if (optname == ICMP_FILTER) {
 		if (inet_sk(sk)->num != IPPROTO_ICMP)
@@ -743,7 +763,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname,
 }
 
 static int raw_setsockopt(struct sock *sk, int level, int optname,
-			  char __user *optval, int optlen)
+			  char __user *optval, unsigned int optlen)
 {
 	if (level != SOL_RAW)
 		return ip_setsockopt(sk, level, optname, optval, optlen);
@@ -752,7 +772,7 @@ static int raw_setsockopt(struct sock *sk, int level, int optname,
 
 #ifdef CONFIG_COMPAT
 static int compat_raw_setsockopt(struct sock *sk, int level, int optname,
-				 char __user *optval, int optlen)
+				 char __user *optval, unsigned int optlen)
 {
 	if (level != SOL_RAW)
 		return compat_ip_setsockopt(sk, level, optname, optval, optlen);
@@ -794,7 +814,8 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
 	switch (cmd) {
 		case SIOCOUTQ: {
-			int amount = atomic_read(&sk->sk_wmem_alloc);
+			int amount = sk_wmem_alloc_get(sk);
+
 			return put_user(amount, (int __user *)arg);
 		}
 		case SIOCINQ: {
@@ -818,12 +839,11 @@ static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg)
 	}
 }
 
-DEFINE_PROTO_INUSE(raw)
-
 struct proto raw_prot = {
 	.name		   = "RAW",
 	.owner		   = THIS_MODULE,
 	.close		   = raw_close,
+	.destroy	   = raw_destroy,
 	.connect	   = ip4_datagram_connect,
 	.disconnect	   = udp_disconnect,
 	.ioctl		   = raw_ioctl,
@@ -834,34 +854,28 @@ struct proto raw_prot = {
 	.recvmsg	   = raw_recvmsg,
 	.bind		   = raw_bind,
 	.backlog_rcv	   = raw_rcv_skb,
-	.hash		   = raw_v4_hash,
-	.unhash		   = raw_v4_unhash,
+	.hash		   = raw_hash_sk,
+	.unhash		   = raw_unhash_sk,
 	.obj_size	   = sizeof(struct raw_sock),
+	.h.raw_hash	   = &raw_v4_hashinfo,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_raw_setsockopt,
 	.compat_getsockopt = compat_raw_getsockopt,
 #endif
-	REF_PROTO_INUSE(raw)
 };
 
 #ifdef CONFIG_PROC_FS
-struct raw_iter_state {
-	int bucket;
-};
-
-#define raw_seq_private(seq) ((struct raw_iter_state *)(seq)->private)
-
 static struct sock *raw_get_first(struct seq_file *seq)
 {
 	struct sock *sk;
-	struct raw_iter_state* state = raw_seq_private(seq);
+	struct raw_iter_state *state = raw_seq_private(seq);
 
 	for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE;
 			++state->bucket) {
 		struct hlist_node *node;
 
-		sk_for_each(sk, node, &raw_v4_hashinfo.ht[state->bucket])
-			if (sk->sk_family == PF_INET)
+		sk_for_each(sk, node, &state->h->ht[state->bucket])
+			if (sock_net(sk) == seq_file_net(seq))
 				goto found;
 	}
 	sk = NULL;
@@ -871,16 +885,16 @@ found:
 
 static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk)
 {
-	struct raw_iter_state* state = raw_seq_private(seq);
+	struct raw_iter_state *state = raw_seq_private(seq);
 
 	do {
 		sk = sk_next(sk);
 try_again:
 		;
-	} while (sk && sk->sk_family != PF_INET);
+	} while (sk && sock_net(sk) != seq_file_net(seq));
 
 	if (!sk && ++state->bucket < RAW_HTABLE_SIZE) {
-		sk = sk_head(&raw_v4_hashinfo.ht[state->bucket]);
+		sk = sk_head(&state->h->ht[state->bucket]);
 		goto try_again;
 	}
 	return sk;
@@ -896,13 +910,16 @@ static struct sock *raw_get_idx(struct seq_file *seq, loff_t pos)
 	return pos ? NULL : sk;
 }
 
-static void *raw_seq_start(struct seq_file *seq, loff_t *pos)
+void *raw_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	read_lock(&raw_v4_hashinfo.lock);
+	struct raw_iter_state *state = raw_seq_private(seq);
+
+	read_lock(&state->h->lock);
 	return *pos ? raw_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
 }
+EXPORT_SYMBOL_GPL(raw_seq_start);
 
-static void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct sock *sk;
 
@@ -913,13 +930,17 @@ static void *raw_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 	return sk;
 }
+EXPORT_SYMBOL_GPL(raw_seq_next);
 
-static void raw_seq_stop(struct seq_file *seq, void *v)
+void raw_seq_stop(struct seq_file *seq, void *v)
 {
-	read_unlock(&raw_v4_hashinfo.lock);
+	struct raw_iter_state *state = raw_seq_private(seq);
+
+	read_unlock(&state->h->lock);
 }
+EXPORT_SYMBOL_GPL(raw_seq_stop);
 
-static __inline__ char *get_raw_sock(struct sock *sp, char *tmpbuf, int i)
+static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 {
 	struct inet_sock *inet = inet_sk(sp);
 	__be32 dest = inet->daddr,
@@ -927,33 +948,23 @@ static __inline__ char *get_raw_sock(struct sock *sp, char *tmpbuf, int i)
 	__u16 destp = 0,
 	      srcp  = inet->num;
 
-	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
-		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d",
+	seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
+		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
 		i, src, srcp, dest, destp, sp->sk_state,
-		atomic_read(&sp->sk_wmem_alloc),
-		atomic_read(&sp->sk_rmem_alloc),
+		sk_wmem_alloc_get(sp),
+		sk_rmem_alloc_get(sp),
 		0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp),
 		atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
-	return tmpbuf;
 }
 
-#define TMPSZ 128
-
 static int raw_seq_show(struct seq_file *seq, void *v)
 {
-	char tmpbuf[TMPSZ+1];
-
 	if (v == SEQ_START_TOKEN)
-		seq_printf(seq, "%-*s\n", TMPSZ-1,
-			       "  sl  local_address rem_address   st tx_queue "
-			       "rx_queue tr tm->when retrnsmt   uid  timeout "
-			       "inode  drops");
-	else {
-		struct raw_iter_state *state = raw_seq_private(seq);
-
-		seq_printf(seq, "%-*s\n", TMPSZ-1,
-			   get_raw_sock(v, tmpbuf, state->bucket));
-	}
+		seq_printf(seq, "  sl  local_address rem_address   st tx_queue "
+				"rx_queue tr tm->when retrnsmt   uid  timeout "
+				"inode ref pointer drops\n");
+	else
+		raw_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
 	return 0;
 }
 
@@ -964,29 +975,60 @@ static const struct seq_operations raw_seq_ops = {
 	.show  = raw_seq_show,
 };
 
-static int raw_seq_open(struct inode *inode, struct file *file)
+int raw_seq_open(struct inode *ino, struct file *file,
+		 struct raw_hashinfo *h, const struct seq_operations *ops)
 {
-	return seq_open_private(file, &raw_seq_ops,
-			sizeof(struct raw_iter_state));
+	int err;
+	struct raw_iter_state *i;
+
+	err = seq_open_net(ino, file, ops, sizeof(struct raw_iter_state));
+	if (err < 0)
+		return err;
+
+	i = raw_seq_private((struct seq_file *)file->private_data);
+	i->h = h;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(raw_seq_open);
+
+static int raw_v4_seq_open(struct inode *inode, struct file *file)
+{
+	return raw_seq_open(inode, file, &raw_v4_hashinfo, &raw_seq_ops);
 }
 
 static const struct file_operations raw_seq_fops = {
 	.owner	 = THIS_MODULE,
-	.open	 = raw_seq_open,
+	.open	 = raw_v4_seq_open,
 	.read	 = seq_read,
 	.llseek	 = seq_lseek,
-	.release = seq_release_private,
+	.release = seq_release_net,
 };
 
-int __init raw_proc_init(void)
+static __net_init int raw_init_net(struct net *net)
 {
-	if (!proc_net_fops_create(&init_net, "raw", S_IRUGO, &raw_seq_fops))
+	if (!proc_net_fops_create(net, "raw", S_IRUGO, &raw_seq_fops))
 		return -ENOMEM;
+
 	return 0;
 }
 
+static __net_exit void raw_exit_net(struct net *net)
+{
+	proc_net_remove(net, "raw");
+}
+
+static __net_initdata struct pernet_operations raw_net_ops = {
+	.init = raw_init_net,
+	.exit = raw_exit_net,
+};
+
+int __init raw_proc_init(void)
+{
+	return register_pernet_subsys(&raw_net_ops);
+}
+
 void __init raw_proc_exit(void)
 {
-	proc_net_remove(&init_net, "raw");
+	unregister_pernet_subsys(&raw_net_ops);
 }
 #endif /* CONFIG_PROC_FS */