1 files changed, 43 insertions, 41 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ad5064362c5c..e681b852ced1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -152,7 +152,6 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 
 static struct dst_ops ipv4_dst_ops = {
 	.family =		AF_INET,
-	.protocol =		cpu_to_be16(ETH_P_IP),
 	.check =		ipv4_dst_check,
 	.default_advmss =	ipv4_default_advmss,
 	.mtu =			ipv4_mtu,
@@ -458,12 +457,9 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
 }
 
 #define IP_IDENTS_SZ 2048u
-struct ip_ident_bucket {
-	atomic_t	id;
-	u32		stamp32;
-};
 
-static struct ip_ident_bucket *ip_idents __read_mostly;
+static atomic_t *ip_idents __read_mostly;
+static u32 *ip_tstamps __read_mostly;
 
 /* In order to protect privacy, we add a perturbation to identifiers
  * if one generator is seldom used. This makes hard for an attacker
@@ -471,19 +467,20 @@ static struct ip_ident_bucket *ip_idents __read_mostly;
  */
 u32 ip_idents_reserve(u32 hash, int segs)
 {
-	struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ;
-	u32 old = ACCESS_ONCE(bucket->stamp32);
+	u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ;
+	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
+	u32 old = ACCESS_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
 	u32 delta = 0;
 
-	if (old != now && cmpxchg(&bucket->stamp32, old, now) == old)
+	if (old != now && cmpxchg(p_tstamp, old, now) == old)
 		delta = prandom_u32_max(now - old);
 
-	return atomic_add_return(segs + delta, &bucket->id) - segs;
+	return atomic_add_return(segs + delta, p_id) - segs;
 }
 EXPORT_SYMBOL(ip_idents_reserve);
 
-void __ip_select_ident(struct iphdr *iph, int segs)
+void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
 {
 	static u32 ip_idents_hashrnd __read_mostly;
 	u32 hash, id;
@@ -492,7 +489,7 @@ void __ip_select_ident(struct iphdr *iph, int segs)
 
 	hash = jhash_3words((__force u32)iph->daddr,
 			    (__force u32)iph->saddr,
-			    iph->protocol,
+			    iph->protocol ^ net_hash_mix(net),
 			    ip_idents_hashrnd);
 	id = ip_idents_reserve(hash, segs);
 	iph->id = htons(id);
@@ -750,7 +747,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 		if (!(n->nud_state & NUD_VALID)) {
 			neigh_event_send(n, NULL);
 		} else {
-			if (fib_lookup(net, fl4, &res) == 0) {
+			if (fib_lookup(net, fl4, &res, 0) == 0) {
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
@@ -903,6 +900,10 @@ static int ip_error(struct sk_buff *skb)
 	bool send;
 	int code;
 
+	/* IP on this device is disabled. */
+	if (!in_dev)
+		goto out;
+
 	net = dev_net(rt->dst.dev);
 	if (!IN_DEV_FORWARD(in_dev)) {
 		switch (rt->dst.error) {
@@ -963,10 +964,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 	if (dst_metric_locked(dst, RTAX_MTU))
 		return;
 
-	if (dst->dev->mtu < mtu)
-		return;
-
-	if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+	if (ipv4_mtu(dst) < mtu)
 		return;
 
 	if (mtu < ip_rt_min_pmtu)
@@ -977,7 +975,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 		return;
 
 	rcu_read_lock();
-	if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
+	if (fib_lookup(dev_net(dst->dev), fl4, &res, 0) == 0) {
 		struct fib_nh *nh = &FIB_RES_NH(res);
 
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
@@ -1057,7 +1055,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 	__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
 
 	rt = (struct rtable *)odst;
-	if (odst->obsolete && odst->ops->check(odst, 0) == NULL) {
+	if (odst->obsolete && !odst->ops->check(odst, 0)) {
 		rt = ip_route_output_flow(sock_net(sk), &fl4, sk);
 		if (IS_ERR(rt))
 			goto out;
@@ -1188,7 +1186,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
 		fl4.flowi4_mark = skb->mark;
 
 		rcu_read_lock();
-		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
+		if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0)
 			src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
 		else
 			src = inet_select_addr(rt->dst.dev,
@@ -1451,7 +1449,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	/* Primary sanity checks. */
 
-	if (in_dev == NULL)
+	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
@@ -1554,7 +1552,7 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	/* get a working reference to the output device */
 	out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
-	if (out_dev == NULL) {
+	if (!out_dev) {
 		net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n");
 		return -EINVAL;
 	}
@@ -1592,7 +1590,7 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe != NULL)
+		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
 		else
 			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
@@ -1718,7 +1716,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
-	err = fib_lookup(net, &fl4, &res);
+	err = fib_lookup(net, &fl4, &res, 0);
 	if (err != 0) {
 		if (!IN_DEV_FORWARD(in_dev))
 			err = -EHOSTUNREACH;
@@ -2055,7 +2053,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 		     ipv4_is_lbcast(fl4->daddr))) {
 			/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
 			dev_out = __ip_dev_find(net, fl4->saddr, false);
-			if (dev_out == NULL)
+			if (!dev_out)
 				goto out;
 
 			/* Special hack: user can direct multicasts
@@ -2088,7 +2086,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	if (fl4->flowi4_oif) {
 		dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif);
 		rth = ERR_PTR(-ENODEV);
-		if (dev_out == NULL)
+		if (!dev_out)
 			goto out;
 
 		/* RACE: Check return value of inet_select_addr instead. */
@@ -2097,7 +2095,8 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 			goto out;
 		}
 		if (ipv4_is_local_multicast(fl4->daddr) ||
-		    ipv4_is_lbcast(fl4->daddr)) {
+		    ipv4_is_lbcast(fl4->daddr) ||
+		    fl4->flowi4_proto == IPPROTO_IGMP) {
 			if (!fl4->saddr)
 				fl4->saddr = inet_select_addr(dev_out, 0,
 							      RT_SCOPE_LINK);
@@ -2124,7 +2123,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 		goto make_route;
 	}
 
-	if (fib_lookup(net, fl4, &res)) {
+	if (fib_lookup(net, fl4, &res, 0)) {
 		res.fi = NULL;
 		res.table = NULL;
 		if (fl4->flowi4_oif) {
@@ -2177,7 +2176,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
 	if (!res.prefixlen &&
 	    res.table->tb_num_default > 1 &&
 	    res.type == RTN_UNICAST && !fl4->flowi4_oif)
-		fib_select_default(&res);
+		fib_select_default(fl4, &res);
 
 	if (!fl4->saddr)
 		fl4->saddr = FIB_RES_PREFSRC(net, res);
@@ -2225,7 +2224,6 @@ static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
 
 static struct dst_ops ipv4_dst_blackhole_ops = {
 	.family			=	AF_INET,
-	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.check			=	ipv4_blackhole_dst_check,
 	.mtu			=	ipv4_blackhole_mtu,
 	.default_advmss		=	ipv4_default_advmss,
@@ -2301,7 +2299,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	u32 metrics[RTAX_MAX];
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*r), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	r = nlmsg_data(nlh);
@@ -2321,11 +2319,11 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 	if (IPCB(skb)->flags & IPSKB_DOREDIRECT)
 		r->rtm_flags |= RTCF_DOREDIRECT;
 
-	if (nla_put_be32(skb, RTA_DST, dst))
+	if (nla_put_in_addr(skb, RTA_DST, dst))
 		goto nla_put_failure;
 	if (src) {
 		r->rtm_src_len = 32;
-		if (nla_put_be32(skb, RTA_SRC, src))
+		if (nla_put_in_addr(skb, RTA_SRC, src))
 			goto nla_put_failure;
 	}
 	if (rt->dst.dev &&
@@ -2338,11 +2336,11 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 #endif
 	if (!rt_is_input_route(rt) &&
 	    fl4->saddr != src) {
-		if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
+		if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
 	if (rt->rt_uses_gateway &&
-	    nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
+	    nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gateway))
 		goto nla_put_failure;
 
 	expires = rt->dst.expires;
@@ -2423,7 +2421,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	rtm = nlmsg_data(nlh);
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (skb == NULL) {
+	if (!skb) {
 		err = -ENOBUFS;
 		goto errout;
 	}
@@ -2438,8 +2436,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 	ip_hdr(skb)->protocol = IPPROTO_ICMP;
 	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
 
-	src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0;
-	dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
+	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
+	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
 	mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
 
@@ -2454,7 +2452,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh)
 		struct net_device *dev;
 
 		dev = __dev_get_by_index(net, iif);
-		if (dev == NULL) {
+		if (!dev) {
 			err = -ENODEV;
 			goto errout_free;
 		}
@@ -2653,7 +2651,7 @@ static __net_init int sysctl_route_net_init(struct net *net)
 	tbl = ipv4_route_flush_table;
 	if (!net_eq(net, &init_net)) {
 		tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
-		if (tbl == NULL)
+		if (!tbl)
 			goto err_dup;
 
 		/* Don't export sysctls to unprivileged users */
@@ -2663,7 +2661,7 @@ static __net_init int sysctl_route_net_init(struct net *net)
 	tbl[0].extra1 = net;
 
 	net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl);
-	if (net->ipv4.route_hdr == NULL)
+	if (!net->ipv4.route_hdr)
 		goto err_reg;
 	return 0;
 
@@ -2743,6 +2741,10 @@ int __init ip_rt_init(void)
 
 	prandom_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents));
 
+	ip_tstamps = kcalloc(IP_IDENTS_SZ, sizeof(*ip_tstamps), GFP_KERNEL);
+	if (!ip_tstamps)
+		panic("IP: failed to allocate ip_tstamps\n");
+
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu);