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

Pablo Neira Ayuso says:

====================
Netfilter/IPVS updates for net-next

The following patchset contains another batch with Netfilter/IPVS updates
for net-next, they are:

1) Add abstracted ICMP codes to the nf_tables reject expression. We
   introduce four reasons to reject using ICMP that overlap in IPv4
   and IPv6 from the semantic point of view. This should simplify the
   maintainance of dual stack rule-sets through the inet table.

2) Move nf_send_reset() functions from header files to per-family
   nf_reject modules, suggested by Patrick McHardy.

3) We have to use IS_ENABLED(CONFIG_BRIDGE_NETFILTER) everywhere in the
   code now that br_netfilter can be modularized. Convert remaining spots
   in the network stack code.

4) Use rcu_barrier() in the nf_tables module removal path to ensure that
   we don't leave object that are still pending to be released via
   call_rcu (that may likely result in a crash).

5) Remove incomplete arch 32/64 compat from nft_compat. The original (bad)
   idea was to probe the word size based on the xtables match/target info
   size, but this assumption is wrong when you have to dump the information
   back to userspace.

6) Allow to filter from prerouting and postrouting in the nf_tables bridge.
   In order to emulate the ebtables NAT chains (which are actually simple
   filter chains with no special semantics), we have support filtering from
   this hooks too.

7) Add explicit module dependency between xt_physdev and br_netfilter.
   This provides a way to detect if the user needs br_netfilter from
   the configuration path. This should reduce the breakage of the
   br_netfilter modularization.

8) Cleanup coding style in ip_vs.h, from Simon Horman.

9) Fix crash in the recently added nf_tables masq expression. We have
   to register/unregister the notifiers to clean up the conntrack table
   entries from the module init/exit path, not from the rule addition /
   deletion path. From Arturo Borrero.
====================

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

8 files changed, 150 insertions, 27 deletions

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c8fa62476461..e35b71289156 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -516,7 +516,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
         hlen = iph->ihl * 4;
         mtu = mtu - hlen;       /* Size of data space */
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
         if (skb->nf_bridge)
                 mtu -= nf_bridge_mtu_reduction(skb);
 #endif
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 345242a79db6..4c019d5c3f57 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -61,8 +61,13 @@ config NFT_CHAIN_ROUTE_IPV4
           fields such as the source, destination, type of service and
           the packet mark.
 
+config NF_REJECT_IPV4
+        tristate "IPv4 packet rejection"
+        default m if NETFILTER_ADVANCED=n
+
 config NFT_REJECT_IPV4
         depends on NF_TABLES_IPV4
+        select NF_REJECT_IPV4
         default NFT_REJECT
         tristate
 
@@ -208,6 +213,7 @@ config IP_NF_FILTER
 config IP_NF_TARGET_REJECT
         tristate "REJECT target support"
         depends on IP_NF_FILTER
+        select NF_REJECT_IPV4
         default m if NETFILTER_ADVANCED=n
         help
           The REJECT target allows a filtering rule to specify that an ICMP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 14488cc5fd2c..f4cef5af0969 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -23,6 +23,9 @@ obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
 obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
 obj-$(CONFIG_NF_LOG_IPV4) += nf_log_ipv4.o
 
+# reject
+obj-$(CONFIG_NF_REJECT_IPV4) += nf_reject_ipv4.o
+
 # NAT helpers (nf_conntrack)
 obj-$(CONFIG_NF_NAT_H323) += nf_nat_h323.o
 obj-$(CONFIG_NF_NAT_PPTP) += nf_nat_pptp.o
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index 5b6e0df4ccff..8f48f5517e33 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -20,7 +20,7 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_REJECT.h>
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 #include <linux/netfilter_bridge.h>
 #endif
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 76bd1aef257f..7e5ca6f2d0cd 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -50,7 +50,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
                 zone = nf_ct_zone((struct nf_conn *)skb->nfct);
 #endif
 
-#ifdef CONFIG_BRIDGE_NETFILTER
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
         if (skb->nf_bridge &&
             skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
                 return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
new file mode 100644
index 000000000000..b023b4eb1a96
--- /dev/null
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -0,0 +1,127 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <net/ip.h>
+#include <net/tcp.h>
+#include <net/route.h>
+#include <net/dst.h>
+#include <linux/netfilter_ipv4.h>
+
+/* Send RST reply */
+void nf_send_reset(struct sk_buff *oldskb, int hook)
+{
+        struct sk_buff *nskb;
+        const struct iphdr *oiph;
+        struct iphdr *niph;
+        const struct tcphdr *oth;
+        struct tcphdr _otcph, *tcph;
+
+        /* IP header checks: fragment. */
+        if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+                return;
+
+        oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
+                                 sizeof(_otcph), &_otcph);
+        if (oth == NULL)
+                return;
+
+        /* No RST for RST. */
+        if (oth->rst)
+                return;
+
+        if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+                return;
+
+        /* Check checksum */
+        if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
+                return;
+        oiph = ip_hdr(oldskb);
+
+        nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+                         LL_MAX_HEADER, GFP_ATOMIC);
+        if (!nskb)
+                return;
+
+        skb_reserve(nskb, LL_MAX_HEADER);
+
+        skb_reset_network_header(nskb);
+        niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
+        niph->version   = 4;
+        niph->ihl       = sizeof(struct iphdr) / 4;
+        niph->tos       = 0;
+        niph->id        = 0;
+        niph->frag_off  = htons(IP_DF);
+        niph->protocol  = IPPROTO_TCP;
+        niph->check     = 0;
+        niph->saddr     = oiph->daddr;
+        niph->daddr     = oiph->saddr;
+
+        skb_reset_transport_header(nskb);
+        tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+        memset(tcph, 0, sizeof(*tcph));
+        tcph->source    = oth->dest;
+        tcph->dest      = oth->source;
+        tcph->doff      = sizeof(struct tcphdr) / 4;
+
+        if (oth->ack)
+                tcph->seq = oth->ack_seq;
+        else {
+                tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
+                                      oldskb->len - ip_hdrlen(oldskb) -
+                                      (oth->doff << 2));
+                tcph->ack = 1;
+        }
+
+        tcph->rst       = 1;
+        tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
+                                    niph->daddr, 0);
+        nskb->ip_summed = CHECKSUM_PARTIAL;
+        nskb->csum_start = (unsigned char *)tcph - nskb->head;
+        nskb->csum_offset = offsetof(struct tcphdr, check);
+
+        /* ip_route_me_harder expects skb->dst to be set */
+        skb_dst_set_noref(nskb, skb_dst(oldskb));
+
+        nskb->protocol = htons(ETH_P_IP);
+        if (ip_route_me_harder(nskb, RTN_UNSPEC))
+                goto free_nskb;
+
+        niph->ttl       = ip4_dst_hoplimit(skb_dst(nskb));
+
+        /* "Never happens" */
+        if (nskb->len > dst_mtu(skb_dst(nskb)))
+                goto free_nskb;
+
+        nf_ct_attach(nskb, oldskb);
+
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
+        /* If we use ip_local_out for bridged traffic, the MAC source on
+         * the RST will be ours, instead of the destination's.  This confuses
+         * some routers/firewalls, and they drop the packet.  So we need to
+         * build the eth header using the original destination's MAC as the
+         * source, and send the RST packet directly.
+         */
+        if (oldskb->nf_bridge) {
+                struct ethhdr *oeth = eth_hdr(oldskb);
+                nskb->dev = oldskb->nf_bridge->physindev;
+                niph->tot_len = htons(nskb->len);
+                ip_send_check(niph);
+                if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
+                                    oeth->h_source, oeth->h_dest, nskb->len) < 0)
+                        goto free_nskb;
+                dev_queue_xmit(nskb);
+        } else
+#endif
+                ip_local_out(nskb);
+
+        return;
+
+ free_nskb:
+        kfree_skb(nskb);
+}
+EXPORT_SYMBOL_GPL(nf_send_reset);
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index 6ea1d207b6a5..1c636d6b5b50 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -32,33 +32,12 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr,
         data[NFT_REG_VERDICT].verdict = verdict;
 }
 
-static int nft_masq_ipv4_init(const struct nft_ctx *ctx,
-                              const struct nft_expr *expr,
-                              const struct nlattr * const tb[])
-{
-        int err;
-
-        err = nft_masq_init(ctx, expr, tb);
-        if (err < 0)
-                return err;
-
-        nf_nat_masquerade_ipv4_register_notifier();
-        return 0;
-}
-
-static void nft_masq_ipv4_destroy(const struct nft_ctx *ctx,
-                                  const struct nft_expr *expr)
-{
-        nf_nat_masquerade_ipv4_unregister_notifier();
-}
-
 static struct nft_expr_type nft_masq_ipv4_type;
 static const struct nft_expr_ops nft_masq_ipv4_ops = {
         .type           = &nft_masq_ipv4_type,
         .size           = NFT_EXPR_SIZE(sizeof(struct nft_masq)),
         .eval           = nft_masq_ipv4_eval,
-        .init           = nft_masq_ipv4_init,
-        .destroy        = nft_masq_ipv4_destroy,
+        .init           = nft_masq_init,
         .dump           = nft_masq_dump,
 };
 
@@ -73,12 +52,21 @@ static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
 
 static int __init nft_masq_ipv4_module_init(void)
 {
-        return nft_register_expr(&nft_masq_ipv4_type);
+        int ret;
+
+        ret = nft_register_expr(&nft_masq_ipv4_type);
+        if (ret < 0)
+                return ret;
+
+        nf_nat_masquerade_ipv4_register_notifier();
+
+        return ret;
 }
 
 static void __exit nft_masq_ipv4_module_exit(void)
 {
         nft_unregister_expr(&nft_masq_ipv4_type);
+        nf_nat_masquerade_ipv4_unregister_notifier();
 }
 
 module_init(nft_masq_ipv4_module_init);
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index e79718a382f2..ed33299c56d1 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -16,7 +16,6 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
-#include <net/icmp.h>
 #include <net/netfilter/ipv4/nf_reject.h>
 #include <net/netfilter/nft_reject.h>