X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=net%2Fipv6%2Ficmp.c;h=3dcc4b7f41b4cc65e5e7386842323f8d98938c8a;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=18637221a75066ae8ac00e3fb673342ac087a2be;hpb=6a77f38946aaee1cd85eeec6cf4229b204c15071;p=linux-2.6.git

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 18637221a..3dcc4b7f4 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -42,6 +42,7 @@
 #include <linux/net.h>
 #include <linux/skbuff.h>
 #include <linux/init.h>
+#include <linux/netfilter.h>
 
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
@@ -67,7 +68,7 @@
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
-DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics);
+DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly;
 
 /*
  *	The ICMP socket(s). This is the most convenient way to flow control
@@ -79,7 +80,7 @@ DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics);
 static DEFINE_PER_CPU(struct socket *, __icmpv6_socket) = NULL;
 #define icmpv6_socket	__get_cpu_var(__icmpv6_socket)
 
-static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp);
+static int icmpv6_rcv(struct sk_buff **pskb);
 
 static struct inet6_protocol icmpv6_protocol = {
 	.handler	=	icmpv6_rcv,
@@ -135,7 +136,7 @@ static int is_ineligible(struct sk_buff *skb)
 	if (len < 0)
 		return 1;
 
-	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, len);
+	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr);
 	if (ptr < 0)
 		return 0;
 	if (nexthdr == IPPROTO_ICMPV6) {
@@ -150,7 +151,7 @@ static int is_ineligible(struct sk_buff *skb)
 	return 0;
 }
 
-static int sysctl_icmpv6_time = 1*HZ; 
+static int sysctl_icmpv6_time __read_mostly = 1*HZ;
 
 /* 
  * Check the ICMP output rate limit 
@@ -176,7 +177,8 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
 	 */
 	dst = ip6_route_output(sk, fl);
 	if (dst->error) {
-		IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
+		IP6_INC_STATS(ip6_dst_idev(dst),
+			      IPSTATS_MIB_OUTNOROUTES);
 	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
 		res = 1;
 	} else {
@@ -232,7 +234,7 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct
 						      len, fl->proto,
 						      skb->csum);
 	} else {
-		u32 tmp_csum = 0;
+		__wsum tmp_csum = 0;
 
 		skb_queue_walk(&sk->sk_write_queue, skb) {
 			tmp_csum = csum_add(tmp_csum, skb->csum);
@@ -240,13 +242,11 @@ static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct
 
 		tmp_csum = csum_partial((char *)icmp6h,
 					sizeof(struct icmp6hdr), tmp_csum);
-		tmp_csum = csum_ipv6_magic(&fl->fl6_src,
-					   &fl->fl6_dst,
-					   len, fl->proto, tmp_csum);
-		icmp6h->icmp6_cksum = tmp_csum;
+		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
+						      &fl->fl6_dst,
+						      len, fl->proto,
+						      tmp_csum);
 	}
-	if (icmp6h->icmp6_cksum == 0)
-		icmp6h->icmp6_cksum = -1;
 	ip6_push_pending_frames(sk);
 out:
 	return err;
@@ -255,20 +255,46 @@ out:
 struct icmpv6_msg {
 	struct sk_buff	*skb;
 	int		offset;
+	uint8_t		type;
 };
 
 static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
 {
 	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
 	struct sk_buff *org_skb = msg->skb;
-	__u32 csum = 0;
+	__wsum csum = 0;
 
 	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
 				      to, len, csum);
 	skb->csum = csum_block_add(skb->csum, csum, odd);
+	if (!(msg->type & ICMPV6_INFOMSG_MASK))
+		nf_ct_attach(skb, org_skb);
 	return 0;
 }
 
+#ifdef CONFIG_IPV6_MIP6
+static void mip6_addr_swap(struct sk_buff *skb)
+{
+	struct ipv6hdr *iph = skb->nh.ipv6h;
+	struct inet6_skb_parm *opt = IP6CB(skb);
+	struct ipv6_destopt_hao *hao;
+	struct in6_addr tmp;
+	int off;
+
+	if (opt->dsthao) {
+		off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
+		if (likely(off >= 0)) {
+			hao = (struct ipv6_destopt_hao *)(skb->nh.raw + off);
+			ipv6_addr_copy(&tmp, &iph->saddr);
+			ipv6_addr_copy(&iph->saddr, &hao->addr);
+			ipv6_addr_copy(&hao->addr, &tmp);
+		}
+	}
+}
+#else
+static inline void mip6_addr_swap(struct sk_buff *skb) {}
+#endif
+
 /*
  *	Send an ICMP message in response to a packet in error
  */
@@ -277,8 +303,8 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 {
 	struct inet6_dev *idev = NULL;
 	struct ipv6hdr *hdr = skb->nh.ipv6h;
-	struct sock *sk = icmpv6_socket->sk;
-	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct sock *sk;
+	struct ipv6_pinfo *np;
 	struct in6_addr *saddr = NULL;
 	struct dst_entry *dst;
 	struct icmp6hdr tmp_hdr;
@@ -287,7 +313,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	int iif = 0;
 	int addr_type = 0;
 	int len;
-	int hlimit;
+	int hlimit, tclass;
 	int err = 0;
 
 	if ((u8*)hdr < skb->head || (u8*)(hdr+1) > skb->tail)
@@ -328,12 +354,13 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 		iif = skb->dev->ifindex;
 
 	/*
-	 *	Must not send if we know that source is Anycast also.
-	 *	for now we don't know that.
+	 *	Must not send error if the source does not uniquely
+	 *	identify a single node (RFC2463 Section 2.4).
+	 *	We check unspecified / multicast addresses here,
+	 *	and anycast addresses will be checked later.
 	 */
 	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
-		LIMIT_NETDEBUG(
-			printk(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n"));
+		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n");
 		return;
 	}
 
@@ -341,11 +368,12 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	 *	Never answer to a ICMP packet.
 	 */
 	if (is_ineligible(skb)) {
-		LIMIT_NETDEBUG(
-			printk(KERN_DEBUG "icmpv6_send: no reply to icmp error\n")); 
+		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: no reply to icmp error\n");
 		return;
 	}
 
+	mip6_addr_swap(skb);
+
 	memset(&fl, 0, sizeof(fl));
 	fl.proto = IPPROTO_ICMPV6;
 	ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
@@ -354,10 +382,14 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	fl.oif = iif;
 	fl.fl_icmp_type = type;
 	fl.fl_icmp_code = code;
+	security_skb_classify_flow(skb, &fl);
 
 	if (icmpv6_xmit_lock())
 		return;
 
+	sk = icmpv6_socket->sk;
+	np = inet6_sk(sk);
+
 	if (!icmpv6_xrlim_allow(sk, type, &fl))
 		goto out;
 
@@ -372,8 +404,18 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	err = ip6_dst_lookup(sk, &dst, &fl);
 	if (err)
 		goto out;
-	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+
+	/*
+	 * We won't send icmp if the destination is known
+	 * anycast.
+	 */
+	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
+		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n");
 		goto out_dst_release;
+	}
+
+	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+		goto out;
 
 	if (ipv6_addr_is_multicast(&fl.fl6_dst))
 		hlimit = np->mcast_hops;
@@ -381,15 +423,21 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 		hlimit = np->hop_limit;
 	if (hlimit < 0)
 		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
+	if (hlimit < 0)
+		hlimit = ipv6_get_hoplimit(dst->dev);
+
+	tclass = np->tclass;
+	if (tclass < 0)
+		tclass = 0;
 
 	msg.skb = skb;
 	msg.offset = skb->nh.raw - skb->data;
+	msg.type = type;
 
 	len = skb->len - msg.offset;
 	len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) -sizeof(struct icmp6hdr));
 	if (len < 0) {
-		LIMIT_NETDEBUG(
-			printk(KERN_DEBUG "icmp: len problem\n"));
+		LIMIT_NETDEBUG(KERN_DEBUG "icmp: len problem\n");
 		goto out_dst_release;
 	}
 
@@ -398,7 +446,7 @@ void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg,
 			      len + sizeof(struct icmp6hdr),
 			      sizeof(struct icmp6hdr),
-			      hlimit, NULL, &fl, (struct rt6_info*)dst,
+			      hlimit, tclass, NULL, &fl, (struct rt6_info*)dst,
 			      MSG_DONTWAIT);
 	if (err) {
 		ip6_flush_pending_frames(sk);
@@ -421,9 +469,9 @@ out:
 
 static void icmpv6_echo_reply(struct sk_buff *skb)
 {
-	struct sock *sk = icmpv6_socket->sk;
+	struct sock *sk;
 	struct inet6_dev *idev;
-	struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_pinfo *np;
 	struct in6_addr *saddr = NULL;
 	struct icmp6hdr *icmph = (struct icmp6hdr *) skb->h.raw;
 	struct icmp6hdr tmp_hdr;
@@ -432,6 +480,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int err = 0;
 	int hlimit;
+	int tclass;
 
 	saddr = &skb->nh.ipv6h->daddr;
 
@@ -448,10 +497,14 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		ipv6_addr_copy(&fl.fl6_src, saddr);
 	fl.oif = skb->dev->ifindex;
 	fl.fl_icmp_type = ICMPV6_ECHO_REPLY;
+	security_skb_classify_flow(skb, &fl);
 
 	if (icmpv6_xmit_lock())
 		return;
 
+	sk = icmpv6_socket->sk;
+	np = inet6_sk(sk);
+
 	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
 		fl.oif = np->mcast_oif;
 
@@ -459,7 +512,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (err)
 		goto out;
 	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
-		goto out_dst_release;
+		goto out;
 
 	if (ipv6_addr_is_multicast(&fl.fl6_dst))
 		hlimit = np->mcast_hops;
@@ -467,14 +520,21 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 		hlimit = np->hop_limit;
 	if (hlimit < 0)
 		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
+	if (hlimit < 0)
+		hlimit = ipv6_get_hoplimit(dst->dev);
+
+	tclass = np->tclass;
+	if (tclass < 0)
+		tclass = 0;
 
 	idev = in6_dev_get(skb->dev);
 
 	msg.skb = skb;
 	msg.offset = 0;
+	msg.type = ICMPV6_ECHO_REPLY;
 
 	err = ip6_append_data(sk, icmpv6_getfrag, &msg, skb->len + sizeof(struct icmp6hdr),
-				sizeof(struct icmp6hdr), hlimit, NULL, &fl,
+				sizeof(struct icmp6hdr), hlimit, tclass, NULL, &fl,
 				(struct rt6_info*)dst, MSG_DONTWAIT);
 
 	if (err) {
@@ -489,13 +549,12 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 out_put: 
 	if (likely(idev != NULL))
 		in6_dev_put(idev);
-out_dst_release:
 	dst_release(dst);
 out: 
 	icmpv6_xmit_unlock();
 }
 
-static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info)
+static void icmpv6_notify(struct sk_buff *skb, int type, int code, __be32 info)
 {
 	struct in6_addr *saddr, *daddr;
 	struct inet6_protocol *ipprot;
@@ -510,7 +569,7 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info)
 	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
 	if (ipv6_ext_hdr(nexthdr)) {
 		/* now skip over extension headers */
-		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, skb->len - sizeof(struct ipv6hdr));
+		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
 		if (inner_offset<0)
 			return;
 	} else {
@@ -541,7 +600,8 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info)
 
 	read_lock(&raw_v6_lock);
 	if ((sk = sk_head(&raw_v6_htable[hash])) != NULL) {
-		while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr))) {
+		while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr,
+					    IP6CB(skb)->iif))) {
 			rawv6_err(sk, skb, NULL, type, code, inner_offset, info);
 			sk = sk_next(sk);
 		}
@@ -553,7 +613,7 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, u32 info)
  *	Handle icmp messages
  */
 
-static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
+static int icmpv6_rcv(struct sk_buff **pskb)
 {
 	struct sk_buff *skb = *pskb;
 	struct net_device *dev = skb->dev;
@@ -569,21 +629,18 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
 	daddr = &skb->nh.ipv6h->daddr;
 
 	/* Perform checksum. */
-	if (skb->ip_summed == CHECKSUM_HW) {
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
-				    skb->csum)) {
-			LIMIT_NETDEBUG(
-				printk(KERN_DEBUG "ICMPv6 hw checksum failed\n"));
-			skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
-	if (skb->ip_summed == CHECKSUM_NONE) {
-		if (csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
-				    skb_checksum(skb, 0, skb->len, 0))) {
-			LIMIT_NETDEBUG(
-				printk(KERN_DEBUG "ICMPv6 checksum failed [%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x > %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x]\n",
-				       NIP6(*saddr), NIP6(*daddr)));
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (!csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_ICMPV6,
+				     skb->csum))
+			break;
+		/* fall through */
+	case CHECKSUM_NONE:
+		skb->csum = ~csum_unfold(csum_ipv6_magic(saddr, daddr, skb->len,
+					     IPPROTO_ICMPV6, 0));
+		if (__skb_checksum_complete(skb)) {
+			LIMIT_NETDEBUG(KERN_DEBUG "ICMPv6 checksum failed [" NIP6_FMT " > " NIP6_FMT "]\n",
+				       NIP6(*saddr), NIP6(*daddr));
 			goto discard_it;
 		}
 	}
@@ -659,8 +716,7 @@ static int icmpv6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
 		break;
 
 	default:
-		LIMIT_NETDEBUG(
-			printk(KERN_DEBUG "icmpv6: msg of unknown type\n"));
+		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6: msg of unknown type\n");
 
 		/* informational */
 		if (type & ICMPV6_INFOMSG_MASK)
@@ -682,15 +738,17 @@ discard_it:
 	return 0;
 }
 
+/*
+ * Special lock-class for __icmpv6_socket:
+ */
+static struct lock_class_key icmpv6_socket_sk_dst_lock_key;
+
 int __init icmpv6_init(struct net_proto_family *ops)
 {
 	struct sock *sk;
 	int err, i, j;
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_possible(i))
-			continue;
-
+	for_each_possible_cpu(i) {
 		err = sock_create_kern(PF_INET6, SOCK_RAW, IPPROTO_ICMPV6,
 				       &per_cpu(__icmpv6_socket, i));
 		if (err < 0) {
@@ -703,6 +761,14 @@ int __init icmpv6_init(struct net_proto_family *ops)
 
 		sk = per_cpu(__icmpv6_socket, i)->sk;
 		sk->sk_allocation = GFP_ATOMIC;
+		/*
+		 * Split off their lock-class, because sk->sk_dst_lock
+		 * gets used from softirqs, which is safe for
+		 * __icmpv6_socket (because those never get directly used
+		 * via userspace syscalls), but unsafe for normal sockets.
+		 */
+		lockdep_set_class(&sk->sk_dst_lock,
+				  &icmpv6_socket_sk_dst_lock_key);
 
 		/* Enough space for 2 64K ICMP packets, including
 		 * sk_buff struct overhead.
@@ -736,15 +802,13 @@ void icmpv6_cleanup(void)
 {
 	int i;
 
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_possible(i))
-			continue;
+	for_each_possible_cpu(i) {
 		sock_release(per_cpu(__icmpv6_socket, i));
 	}
 	inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
 }
 
-static struct icmp6_err {
+static const struct icmp6_err {
 	int err;
 	int fatal;
 } tab_unreach[] = {