Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
netfilter/ipvs fixes for net

The following patchset contains netfilter/ipvs fixes, they are:

1) Small fix for the FTP helper in IPVS, a diff variable may be left
   unset when CONFIG_IP_VS_IPV6 is set. Patch from Dan Carpenter.

2) Fix nf_tables port NAT in little endian archs, patch from leroy
   christophe.

3) Fix race condition between conntrack confirmation and flush from
   userspace. This is the second reincarnation to resolve this problem.

4) Make sure inner messages in the batch come with the nfnetlink header.

5) Relax strict check from nfnetlink_bind() that may break old userspace
   applications using all 1s group mask.

6) Schedule removal of chains once no sets and rules refer to them in
   the new nf_tables ruleset flush command. Reported by Asbjoern Sloth
   Toennesen.

Note that this batch comes later than usual because of the short
winter holidays.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 38 insertions, 35 deletions

diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
index ff2d23d..6ecfce6 100644
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ b/net/ipv4/netfilter/nft_redir_ipv4.c
@@ -27,10 +27,10 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr,
 
 	memset(&mr, 0, sizeof(mr));
 	if (priv->sreg_proto_min) {
-		mr.range[0].min.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		mr.range[0].max.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		mr.range[0].min.all =
+			*(__be16 *)&data[priv->sreg_proto_min].data[0];
+		mr.range[0].max.all =
+			*(__be16 *)&data[priv->sreg_proto_max].data[0];
 		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
index 2433a6b..11820b6 100644
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ b/net/ipv6/netfilter/nft_redir_ipv6.c
@@ -27,10 +27,10 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr,
 
 	memset(&range, 0, sizeof(range));
 	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		range.min_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_min].data[0];
+		range.max_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_max].data[0];
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}
 
diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c
index 1d5341f..5d3daae 100644
--- a/net/netfilter/ipvs/ip_vs_ftp.c
+++ b/net/netfilter/ipvs/ip_vs_ftp.c
@@ -183,6 +183,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct nf_conn *ct;
 	struct net *net;
 
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -191,8 +193,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
@@ -322,6 +322,9 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 	struct ip_vs_conn *n_cp;
 	struct net *net;
 
+	/* no diff required for incoming packets */
+	*diff = 0;
+
 #ifdef CONFIG_IP_VS_IPV6
 	/* This application helper doesn't work with IPv6 yet,
 	 * so turn this into a no-op for IPv6 packets
@@ -330,9 +333,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp,
 		return 1;
 #endif
 
-	/* no diff required for incoming packets */
-	*diff = 0;
-
 	/* Only useful for established sessions */
 	if (cp->state != IP_VS_TCP_S_ESTABLISHED)
 		return 1;
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index a116748..46d1b26 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -611,16 +611,15 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	 */
 	NF_CT_ASSERT(!nf_ct_is_confirmed(ct));
 	pr_debug("Confirming conntrack %p\n", ct);
-	/* We have to check the DYING flag inside the lock to prevent
-	   a race against nf_ct_get_next_corpse() possibly called from
-	   user context, else we insert an already 'dead' hash, blocking
-	   further use of that particular connection -JM */
+	/* We have to check the DYING flag after unlink to prevent
+	 * a race against nf_ct_get_next_corpse() possibly called from
+	 * user context, else we insert an already 'dead' hash, blocking
+	 * further use of that particular connection -JM.
+	 */
+	nf_ct_del_from_dying_or_unconfirmed_list(ct);
 
-	if (unlikely(nf_ct_is_dying(ct))) {
-		nf_conntrack_double_unlock(hash, reply_hash);
-		local_bh_enable();
-		return NF_ACCEPT;
-	}
+	if (unlikely(nf_ct_is_dying(ct)))
+		goto out;
 
 	/* See if there's one in the list already, including reverse:
 	   NAT could have grabbed it without realizing, since we're
@@ -636,8 +635,6 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 		    zone == nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)))
 			goto out;
 
-	nf_ct_del_from_dying_or_unconfirmed_list(ct);
-
 	/* Timer relative to confirmation time, not original
 	   setting time, otherwise we'd get timer wrap in
 	   weird delay cases. */
@@ -673,6 +670,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	return NF_ACCEPT;
 
 out:
+	nf_ct_add_to_dying_list(ct);
 	nf_conntrack_double_unlock(hash, reply_hash);
 	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 129a8da..3b3ddb4 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -713,16 +713,12 @@ static int nft_flush_table(struct nft_ctx *ctx)
 	struct nft_chain *chain, *nc;
 	struct nft_set *set, *ns;
 
-	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+	list_for_each_entry(chain, &ctx->table->chains, list) {
 		ctx->chain = chain;
 
 		err = nft_delrule_by_chain(ctx);
 		if (err < 0)
 			goto out;
-
-		err = nft_delchain(ctx);
-		if (err < 0)
-			goto out;
 	}
 
 	list_for_each_entry_safe(set, ns, &ctx->table->sets, list) {
@@ -735,6 +731,14 @@ static int nft_flush_table(struct nft_ctx *ctx)
 			goto out;
 	}
 
+	list_for_each_entry_safe(chain, nc, &ctx->table->chains, list) {
+		ctx->chain = chain;
+
+		err = nft_delchain(ctx);
+		if (err < 0)
+			goto out;
+	}
+
 	err = nft_deltable(ctx);
 out:
 	return err;
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index cde4a67..c421d94 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -321,7 +321,8 @@ replay:
 		nlh = nlmsg_hdr(skb);
 		err = 0;
 
-		if (nlh->nlmsg_len < NLMSG_HDRLEN) {
+		if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) ||
+		    skb->len < nlh->nlmsg_len) {
 			err = -EINVAL;
 			goto ack;
 		}
@@ -469,7 +470,7 @@ static int nfnetlink_bind(struct net *net, int group)
 	int type;
 
 	if (group <= NFNLGRP_NONE || group > NFNLGRP_MAX)
-		return -EINVAL;
+		return 0;
 
 	type = nfnl_group2type[group];
 
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index afe2b0b..aff54fb1 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -65,10 +65,10 @@ static void nft_nat_eval(const struct nft_expr *expr,
 	}
 
 	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)
-					data[priv->sreg_proto_min].data[0];
-		range.max_proto.all = (__force __be16)
-					data[priv->sreg_proto_max].data[0];
+		range.min_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_min].data[0];
+		range.max_proto.all =
+			*(__be16 *)&data[priv->sreg_proto_max].data[0];
 		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
 	}