Merge commit 'v2.6.38-rc6' into for-2.6.39/core

Conflicts:
	block/cfq-iosched.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

11 files changed, 92 insertions, 97 deletions

diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 85dabb8..4aa614b 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -133,6 +133,7 @@ unsigned int nf_iterate(struct list_head *head,
 
 		/* Optimization: we don't need to hold module
 		   reference here, since function can't sleep. --RR */
+repeat:
 		verdict = elem->hook(hook, skb, indev, outdev, okfn);
 		if (verdict != NF_ACCEPT) {
 #ifdef CONFIG_NETFILTER_DEBUG
@@ -145,7 +146,7 @@ unsigned int nf_iterate(struct list_head *head,
 #endif
 			if (verdict != NF_REPEAT)
 				return verdict;
-			*i = (*i)->prev;
+			goto repeat;
 		}
 	}
 	return NF_ACCEPT;
@@ -173,9 +174,11 @@ next_hook:
 			     outdev, &elem, okfn, hook_thresh);
 	if (verdict == NF_ACCEPT || verdict == NF_STOP) {
 		ret = 1;
-	} else if (verdict == NF_DROP) {
+	} else if ((verdict & NF_VERDICT_MASK) == NF_DROP) {
 		kfree_skb(skb);
-		ret = -EPERM;
+		ret = -(verdict >> NF_VERDICT_BITS);
+		if (ret == 0)
+			ret = -EPERM;
 	} else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) {
 		if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
 			      verdict >> NF_VERDICT_BITS))
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 5f5daa3..22f7ad5 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -110,10 +110,8 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr)
 	struct rt6_info *rt;
 	struct flowi fl = {
 		.oif = 0,
-		.nl_u = {
-			.ip6_u = {
-				.daddr = *addr,
-				.saddr = { .s6_addr32 = {0, 0, 0, 0} }, } },
+		.fl6_dst = *addr,
+		.fl6_src = { .s6_addr32 = {0, 0, 0, 0} },
 	};
 
 	rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl);
@@ -3432,7 +3430,7 @@ void ip_vs_control_cleanup(void)
 {
 	EnterFunction(2);
 	ip_vs_trash_cleanup();
-	cancel_rearming_delayed_work(&defense_work);
+	cancel_delayed_work_sync(&defense_work);
 	cancel_work_sync(&defense_work.work);
 	ip_vs_kill_estimator(&ip_vs_stats);
 	unregister_sysctl_table(sysctl_header);
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index de04ea3..5325a3f 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -96,12 +96,8 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		if (!(rt = (struct rtable *)
 		      __ip_vs_dst_check(dest, rtos))) {
 			struct flowi fl = {
-				.oif = 0,
-				.nl_u = {
-					.ip4_u = {
-						.daddr = dest->addr.ip,
-						.saddr = 0,
-						.tos = rtos, } },
+				.fl4_dst = dest->addr.ip,
+				.fl4_tos = rtos,
 			};
 
 			if (ip_route_output_key(net, &rt, &fl)) {
@@ -118,12 +114,8 @@ __ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
 		spin_unlock(&dest->dst_lock);
 	} else {
 		struct flowi fl = {
-			.oif = 0,
-			.nl_u = {
-				.ip4_u = {
-					.daddr = daddr,
-					.saddr = 0,
-					.tos = rtos, } },
+			.fl4_dst = daddr,
+			.fl4_tos = rtos,
 		};
 
 		if (ip_route_output_key(net, &rt, &fl)) {
@@ -169,7 +161,7 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 	struct net *net = dev_net(dev);
 	struct iphdr *iph = ip_hdr(skb);
 
-	if (rt->fl.iif) {
+	if (rt_is_input_route(rt)) {
 		unsigned long orefdst = skb->_skb_refdst;
 
 		if (ip_route_input(skb, iph->daddr, iph->saddr,
@@ -178,14 +170,9 @@ __ip_vs_reroute_locally(struct sk_buff *skb)
 		refdst_drop(orefdst);
 	} else {
 		struct flowi fl = {
-			.oif = 0,
-			.nl_u = {
-				.ip4_u = {
-					.daddr = iph->daddr,
-					.saddr = iph->saddr,
-					.tos = RT_TOS(iph->tos),
-				}
-			},
+			.fl4_dst = iph->daddr,
+			.fl4_src = iph->saddr,
+			.fl4_tos = RT_TOS(iph->tos),
 			.mark = skb->mark,
 		};
 		struct rtable *rt;
@@ -216,12 +203,7 @@ __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
 {
 	struct dst_entry *dst;
 	struct flowi fl = {
-		.oif = 0,
-		.nl_u = {
-			.ip6_u = {
-				.daddr = *daddr,
-			},
-		},
+		.fl6_dst = *daddr,
 	};
 
 	dst = ip6_route_output(net, NULL, &fl);
@@ -552,7 +534,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #endif
 
 	/* From world but DNAT to loopback address? */
-	if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) {
+	if (local && ipv4_is_loopback(rt->rt_dst) &&
+	    rt_is_input_route(skb_rtable(skb))) {
 		IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
 				 "stopping DNAT to loopback address");
 		goto tx_error_put;
@@ -1165,7 +1148,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 #endif
 
 	/* From world but DNAT to loopback address? */
-	if (local && ipv4_is_loopback(rt->rt_dst) && skb_rtable(skb)->fl.iif) {
+	if (local && ipv4_is_loopback(rt->rt_dst) &&
+	    rt_is_input_route(skb_rtable(skb))) {
 		IP_VS_DBG(1, "%s(): "
 			  "stopping DNAT to loopback %pI4\n",
 			  __func__, &cp->daddr.ip);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 27a5ea6..84f4fcc 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_max);
 DEFINE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
 EXPORT_PER_CPU_SYMBOL(nf_conntrack_untracked);
 
-static unsigned int nf_conntrack_hash_rnd __read_mostly;
+unsigned int nf_conntrack_hash_rnd __read_mostly;
 
 static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, u16 zone)
 {
@@ -596,6 +596,21 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 	return dropped;
 }
 
+void init_nf_conntrack_hash_rnd(void)
+{
+	unsigned int rand;
+
+	/*
+	 * Why not initialize nf_conntrack_rnd in a "init()" function ?
+	 * Because there isn't enough entropy when system initializing,
+	 * and we initialize it as late as possible.
+	 */
+	do {
+		get_random_bytes(&rand, sizeof(rand));
+	} while (!rand);
+	cmpxchg(&nf_conntrack_hash_rnd, 0, rand);
+}
+
 static struct nf_conn *
 __nf_conntrack_alloc(struct net *net, u16 zone,
 		     const struct nf_conntrack_tuple *orig,
@@ -605,18 +620,7 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 	struct nf_conn *ct;
 
 	if (unlikely(!nf_conntrack_hash_rnd)) {
-		unsigned int rand;
-
-		/*
-		 * Why not initialize nf_conntrack_rnd in a "init()" function ?
-		 * Because there isn't enough entropy when system initializing,
-		 * and we initialize it as late as possible.
-		 */
-		do {
-			get_random_bytes(&rand, sizeof(rand));
-		} while (!rand);
-		cmpxchg(&nf_conntrack_hash_rnd, 0, rand);
-
+		init_nf_conntrack_hash_rnd();
 		/* recompute the hash as nf_conntrack_hash_rnd is initialized */
 		hash = hash_conntrack_raw(orig, zone);
 	}
@@ -938,8 +942,15 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	if (set_reply && !test_and_set_bit(IPS_SEEN_REPLY_BIT, &ct->status))
 		nf_conntrack_event_cache(IPCT_REPLY, ct);
 out:
-	if (tmpl)
-		nf_ct_put(tmpl);
+	if (tmpl) {
+		/* Special case: we have to repeat this hook, assign the
+		 * template again to this packet. We assume that this packet
+		 * has no conntrack assigned. This is used by nf_ct_tcp. */
+		if (ret == NF_REPEAT)
+			skb->nfct = (struct nf_conntrack *)tmpl;
+		else
+			nf_ct_put(tmpl);
+	}
 
 	return ret;
 }
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index 5702de3..63a1b91 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -63,6 +63,9 @@ void nf_ct_deliver_cached_events(struct nf_conn *ct)
 		 * this does not harm and it happens very rarely. */
 		unsigned long missed = e->missed;
 
+		if (!((events | missed) & e->ctmask))
+			goto out_unlock;
+
 		ret = notify->fcn(events | missed, &item);
 		if (unlikely(ret < 0 || missed)) {
 			spin_lock_bh(&ct->lock);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 46e8966..a20fb0b 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -32,9 +32,7 @@
 unsigned int nf_ct_expect_hsize __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_expect_hsize);
 
-static unsigned int nf_ct_expect_hash_rnd __read_mostly;
 unsigned int nf_ct_expect_max __read_mostly;
-static int nf_ct_expect_hash_rnd_initted __read_mostly;
 
 static struct kmem_cache *nf_ct_expect_cachep __read_mostly;
 
@@ -77,15 +75,13 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
 {
 	unsigned int hash;
 
-	if (unlikely(!nf_ct_expect_hash_rnd_initted)) {
-		get_random_bytes(&nf_ct_expect_hash_rnd,
-				 sizeof(nf_ct_expect_hash_rnd));
-		nf_ct_expect_hash_rnd_initted = 1;
+	if (unlikely(!nf_conntrack_hash_rnd)) {
+		init_nf_conntrack_hash_rnd();
 	}
 
 	hash = jhash2(tuple->dst.u3.all, ARRAY_SIZE(tuple->dst.u3.all),
 		      (((tuple->dst.protonum ^ tuple->src.l3num) << 16) |
-		       (__force __u16)tuple->dst.u.all) ^ nf_ct_expect_hash_rnd);
+		       (__force __u16)tuple->dst.u.all) ^ nf_conntrack_hash_rnd);
 	return ((u64)hash * nf_ct_expect_hsize) >> 32;
 }
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index b729ace..eead9db 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -254,7 +254,7 @@ ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
 
 	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
 	if (ret)
-		return ret;
+		return 0;
 
 	ret = -1;
 	nest_secctx = nla_nest_start(skb, CTA_SECCTX | NLA_F_NESTED);
@@ -453,16 +453,22 @@ ctnetlink_counters_size(const struct nf_conn *ct)
 	       ;
 }
 
-#ifdef CONFIG_NF_CONNTRACK_SECMARK
-static int ctnetlink_nlmsg_secctx_size(const struct nf_conn *ct)
+static inline int
+ctnetlink_secctx_size(const struct nf_conn *ct)
 {
-	int len;
+#ifdef CONFIG_NF_CONNTRACK_SECMARK
+	int len, ret;
 
-	security_secid_to_secctx(ct->secmark, NULL, &len);
+	ret = security_secid_to_secctx(ct->secmark, NULL, &len);
+	if (ret)
+		return 0;
 
-	return sizeof(char) * len;
-}
+	return nla_total_size(0) /* CTA_SECCTX */
+	       + nla_total_size(sizeof(char) * len); /* CTA_SECCTX_NAME */
+#else
+	return 0;
 #endif
+}
 
 static inline size_t
 ctnetlink_nlmsg_size(const struct nf_conn *ct)
@@ -479,10 +485,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 	       + nla_total_size(0) /* CTA_PROTOINFO */
 	       + nla_total_size(0) /* CTA_HELP */
 	       + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
-#ifdef CONFIG_NF_CONNTRACK_SECMARK
-	       + nla_total_size(0) /* CTA_SECCTX */
-	       + nla_total_size(ctnetlink_nlmsg_secctx_size(ct)) /* CTA_SECCTX_NAME */
-#endif
+	       + ctnetlink_secctx_size(ct)
 #ifdef CONFIG_NF_NAT_NEEDED
 	       + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
 	       + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
@@ -642,30 +645,29 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
 
-	rcu_read_lock();
+	spin_lock_bh(&nf_conntrack_lock);
 	last = (struct nf_conn *)cb->args[1];
 	for (; cb->args[0] < net->ct.htable_size; cb->args[0]++) {
 restart:
-		hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[cb->args[0]],
+		hlist_nulls_for_each_entry(h, n, &net->ct.hash[cb->args[0]],
 					 hnnode) {
 			if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
 				continue;
 			ct = nf_ct_tuplehash_to_ctrack(h);
-			if (!atomic_inc_not_zero(&ct->ct_general.use))
-				continue;
 			/* Dump entries of a given L3 protocol number.
 			 * If it is not specified, ie. l3proto == 0,
 			 * then dump everything. */
 			if (l3proto && nf_ct_l3num(ct) != l3proto)
-				goto releasect;
+				continue;
 			if (cb->args[1]) {
 				if (ct != last)
-					goto releasect;
+					continue;
 				cb->args[1] = 0;
 			}
 			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
 						cb->nlh->nlmsg_seq,
 						IPCTNL_MSG_CT_NEW, ct) < 0) {
+				nf_conntrack_get(&ct->ct_general);
 				cb->args[1] = (unsigned long)ct;
 				goto out;
 			}
@@ -678,8 +680,6 @@ restart:
 				if (acct)
 					memset(acct, 0, sizeof(struct nf_conn_counter[IP_CT_DIR_MAX]));
 			}
-releasect:
-		nf_ct_put(ct);
 		}
 		if (cb->args[1]) {
 			cb->args[1] = 0;
@@ -687,7 +687,7 @@ releasect:
 		}
 	}
 out:
-	rcu_read_unlock();
+	spin_unlock_bh(&nf_conntrack_lock);
 	if (last)
 		nf_ct_put(last);
 
@@ -973,7 +973,8 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 free:
 	kfree_skb(skb2);
 out:
-	return err;
+	/* this avoids a loop in nfnetlink. */
+	return err == -EAGAIN ? -ENOBUFS : err;
 }
 
 #ifdef CONFIG_NF_NAT_NEEDED
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 0fb6570..b4d7f0f 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -118,7 +118,7 @@ static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct)
 
 	ret = security_secid_to_secctx(ct->secmark, &secctx, &len);
 	if (ret)
-		return ret;
+		return 0;
 
 	ret = seq_printf(s, "secctx=%s ", secctx);
 
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 8046350..c942376 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1325,7 +1325,8 @@ static int __init xt_init(void)
 
 	for_each_possible_cpu(i) {
 		struct xt_info_lock *lock = &per_cpu(xt_info_locks, i);
-		spin_lock_init(&lock->lock);
+
+		seqlock_init(&lock->lock);
 		lock->readers = 0;
 	}
 
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 22a2d42..5128a6c 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -70,9 +70,9 @@ tee_tg_route4(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 			return false;
 		fl.oif = info->priv->oif;
 	}
-	fl.nl_u.ip4_u.daddr = info->gw.ip;
-	fl.nl_u.ip4_u.tos   = RT_TOS(iph->tos);
-	fl.nl_u.ip4_u.scope = RT_SCOPE_UNIVERSE;
+	fl.fl4_dst = info->gw.ip;
+	fl.fl4_tos = RT_TOS(iph->tos);
+	fl.fl4_scope = RT_SCOPE_UNIVERSE;
 	if (ip_route_output_key(net, &rt, &fl) != 0)
 		return false;
 
@@ -150,9 +150,9 @@ tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 			return false;
 		fl.oif = info->priv->oif;
 	}
-	fl.nl_u.ip6_u.daddr = info->gw.in6;
-	fl.nl_u.ip6_u.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
-				  (iph->flow_lbl[1] << 8) | iph->flow_lbl[2];
+	fl.fl6_dst = info->gw.in6;
+	fl.fl6_flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
+			   (iph->flow_lbl[1] << 8) | iph->flow_lbl[2];
 	dst = ip6_route_output(net, NULL, &fl);
 	if (dst == NULL)
 		return false;
diff --git a/net/netfilter/xt_iprange.c b/net/netfilter/xt_iprange.c
index 88f7c35..73c33a4 100644
--- a/net/netfilter/xt_iprange.c
+++ b/net/netfilter/xt_iprange.c
@@ -53,15 +53,13 @@ iprange_mt4(const struct sk_buff *skb, struct xt_action_param *par)
 }
 
 static inline int
-iprange_ipv6_sub(const struct in6_addr *a, const struct in6_addr *b)
+iprange_ipv6_lt(const struct in6_addr *a, const struct in6_addr *b)
 {
 	unsigned int i;
-	int r;
 
 	for (i = 0; i < 4; ++i) {
-		r = ntohl(a->s6_addr32[i]) - ntohl(b->s6_addr32[i]);
-		if (r != 0)
-			return r;
+		if (a->s6_addr32[i] != b->s6_addr32[i])
+			return ntohl(a->s6_addr32[i]) < ntohl(b->s6_addr32[i]);
 	}
 
 	return 0;
@@ -75,15 +73,15 @@ iprange_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 	bool m;
 
 	if (info->flags & IPRANGE_SRC) {
-		m  = iprange_ipv6_sub(&iph->saddr, &info->src_min.in6) < 0;
-		m |= iprange_ipv6_sub(&iph->saddr, &info->src_max.in6) > 0;
+		m  = iprange_ipv6_lt(&iph->saddr, &info->src_min.in6);
+		m |= iprange_ipv6_lt(&info->src_max.in6, &iph->saddr);
 		m ^= !!(info->flags & IPRANGE_SRC_INV);
 		if (m)
 			return false;
 	}
 	if (info->flags & IPRANGE_DST) {
-		m  = iprange_ipv6_sub(&iph->daddr, &info->dst_min.in6) < 0;
-		m |= iprange_ipv6_sub(&iph->daddr, &info->dst_max.in6) > 0;
+		m  = iprange_ipv6_lt(&iph->daddr, &info->dst_min.in6);
+		m |= iprange_ipv6_lt(&info->dst_max.in6, &iph->daddr);
 		m ^= !!(info->flags & IPRANGE_DST_INV);
 		if (m)
 			return false;