* [PATCH 2/9] netfilter: Libify xt_TPROXY
2018-06-02 23:14 [PATCH 0/9] Netfilter updates for net-next Pablo Neira Ayuso
2018-06-02 23:14 ` [PATCH 1/9] netfilter: Decrease code duplication regarding transparent socket option Pablo Neira Ayuso
@ 2018-06-02 23:14 ` Pablo Neira Ayuso
2018-06-02 23:14 ` [PATCH 3/9] netfilter: nf_tables: pass context to object destroy indirection Pablo Neira Ayuso
` (6 subsequent siblings)
8 siblings, 0 replies; 10+ messages in thread
From: Pablo Neira Ayuso @ 2018-06-02 23:14 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
From: Máté Eckl <ecklm94@gmail.com>
The extracted functions will likely be usefull to implement tproxy
support in nf_tables.
Extrancted functions:
- nf_tproxy_sk_is_transparent
- nf_tproxy_laddr4
- nf_tproxy_handle_time_wait4
- nf_tproxy_get_sock_v4
- nf_tproxy_laddr6
- nf_tproxy_handle_time_wait6
- nf_tproxy_get_sock_v6
(nf_)tproxy_handle_time_wait6 also needed some refactor as its current
implementation was xtables-specific.
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_tproxy.h | 113 ++++++++++++
net/ipv4/netfilter/Kconfig | 5 +-
net/ipv4/netfilter/Makefile | 1 +
net/ipv4/netfilter/nf_tproxy_ipv4.c | 147 +++++++++++++++
net/ipv6/netfilter/Kconfig | 5 +-
net/ipv6/netfilter/Makefile | 1 +
net/ipv6/netfilter/nf_tproxy_ipv6.c | 146 +++++++++++++++
net/netfilter/Kconfig | 2 +
net/netfilter/xt_TPROXY.c | 355 ++----------------------------------
9 files changed, 436 insertions(+), 339 deletions(-)
create mode 100644 include/net/netfilter/nf_tproxy.h
create mode 100644 net/ipv4/netfilter/nf_tproxy_ipv4.c
create mode 100644 net/ipv6/netfilter/nf_tproxy_ipv6.c
diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h
new file mode 100644
index 000000000000..9754a50ecde9
--- /dev/null
+++ b/include/net/netfilter/nf_tproxy.h
@@ -0,0 +1,113 @@
+#ifndef _NF_TPROXY_H_
+#define _NF_TPROXY_H_
+
+#include <net/tcp.h>
+
+enum nf_tproxy_lookup_t {
+ NF_TPROXY_LOOKUP_LISTENER,
+ NF_TPROXY_LOOKUP_ESTABLISHED,
+};
+
+static inline bool nf_tproxy_sk_is_transparent(struct sock *sk)
+{
+ if (inet_sk_transparent(sk))
+ return true;
+
+ sock_gen_put(sk);
+ return false;
+}
+
+__be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr);
+
+/**
+ * nf_tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections
+ * @skb: The skb being processed.
+ * @laddr: IPv4 address to redirect to or zero.
+ * @lport: TCP port to redirect to or zero.
+ * @sk: The TIME_WAIT TCP socket found by the lookup.
+ *
+ * We have to handle SYN packets arriving to TIME_WAIT sockets
+ * differently: instead of reopening the connection we should rather
+ * redirect the new connection to the proxy if there's a listener
+ * socket present.
+ *
+ * nf_tproxy_handle_time_wait4() consumes the socket reference passed in.
+ *
+ * Returns the listener socket if there's one, the TIME_WAIT socket if
+ * no such listener is found, or NULL if the TCP header is incomplete.
+ */
+struct sock *
+nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
+ __be32 laddr, __be16 lport, struct sock *sk);
+
+/*
+ * This is used when the user wants to intercept a connection matching
+ * an explicit iptables rule. In this case the sockets are assumed
+ * matching in preference order:
+ *
+ * - match: if there's a fully established connection matching the
+ * _packet_ tuple, it is returned, assuming the redirection
+ * already took place and we process a packet belonging to an
+ * established connection
+ *
+ * - match: if there's a listening socket matching the redirection
+ * (e.g. on-port & on-ip of the connection), it is returned,
+ * regardless if it was bound to 0.0.0.0 or an explicit
+ * address. The reasoning is that if there's an explicit rule, it
+ * does not really matter if the listener is bound to an interface
+ * or to 0. The user already stated that he wants redirection
+ * (since he added the rule).
+ *
+ * Please note that there's an overlap between what a TPROXY target
+ * and a socket match will match. Normally if you have both rules the
+ * "socket" match will be the first one, effectively all packets
+ * belonging to established connections going through that one.
+ */
+struct sock *
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+ const u8 protocol,
+ const __be32 saddr, const __be32 daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in,
+ const enum nf_tproxy_lookup_t lookup_type);
+
+const struct in6_addr *
+nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
+ const struct in6_addr *daddr);
+
+/**
+ * nf_tproxy_handle_time_wait6 - handle IPv6 TCP TIME_WAIT reopen redirections
+ * @skb: The skb being processed.
+ * @tproto: Transport protocol.
+ * @thoff: Transport protocol header offset.
+ * @net: Network namespace.
+ * @laddr: IPv6 address to redirect to.
+ * @lport: TCP port to redirect to or zero.
+ * @sk: The TIME_WAIT TCP socket found by the lookup.
+ *
+ * We have to handle SYN packets arriving to TIME_WAIT sockets
+ * differently: instead of reopening the connection we should rather
+ * redirect the new connection to the proxy if there's a listener
+ * socket present.
+ *
+ * nf_tproxy_handle_time_wait6() consumes the socket reference passed in.
+ *
+ * Returns the listener socket if there's one, the TIME_WAIT socket if
+ * no such listener is found, or NULL if the TCP header is incomplete.
+ */
+struct sock *
+nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
+ struct net *net,
+ const struct in6_addr *laddr,
+ const __be16 lport,
+ struct sock *sk);
+
+struct sock *
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+ const u8 protocol,
+ const struct in6_addr *saddr, const struct in6_addr *daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in,
+ const enum nf_tproxy_lookup_t lookup_type);
+
+#endif /* _NF_TPROXY_H_ */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index d03bc5a01a70..bbfc356cb1b5 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -29,7 +29,10 @@ config NF_SOCKET_IPV4
tristate "IPv4 socket lookup support"
help
This option enables the IPv4 socket lookup infrastructure. This is
- is required by the iptables socket match.
+ is required by the {ip,nf}tables socket match.
+
+config NF_TPROXY_IPV4
+ tristate "IPv4 tproxy support"
if NF_TABLES
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index c4b05b174091..8394c17c269f 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
obj-$(CONFIG_NF_DEFRAG_IPV4) += nf_defrag_ipv4.o
obj-$(CONFIG_NF_SOCKET_IPV4) += nf_socket_ipv4.o
+obj-$(CONFIG_NF_TPROXY_IPV4) += nf_tproxy_ipv4.o
# logging
obj-$(CONFIG_NF_LOG_ARP) += nf_log_arp.o
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
new file mode 100644
index 000000000000..805e83ec3ad9
--- /dev/null
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (C) 2007-2008 BalaBit IT Ltd.
+ * Author: Krisztian Kovacs
+ *
+ * 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/netfilter/nf_tproxy.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/inet_sock.h>
+#include <linux/ip.h>
+#include <net/checksum.h>
+#include <net/udp.h>
+#include <net/tcp.h>
+#include <linux/inetdevice.h>
+
+struct sock *
+nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
+ __be32 laddr, __be16 lport, struct sock *sk)
+{
+ const struct iphdr *iph = ip_hdr(skb);
+ struct tcphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
+ if (hp == NULL) {
+ inet_twsk_put(inet_twsk(sk));
+ return NULL;
+ }
+
+ if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
+ /* SYN to a TIME_WAIT socket, we'd rather redirect it
+ * to a listener socket if there's one */
+ struct sock *sk2;
+
+ sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+ iph->saddr, laddr ? laddr : iph->daddr,
+ hp->source, lport ? lport : hp->dest,
+ skb->dev, NF_TPROXY_LOOKUP_LISTENER);
+ if (sk2) {
+ inet_twsk_deschedule_put(inet_twsk(sk));
+ sk = sk2;
+ }
+ }
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait4);
+
+__be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
+{
+ struct in_device *indev;
+ __be32 laddr;
+
+ if (user_laddr)
+ return user_laddr;
+
+ laddr = 0;
+ indev = __in_dev_get_rcu(skb->dev);
+ for_primary_ifa(indev) {
+ laddr = ifa->ifa_local;
+ break;
+ } endfor_ifa(indev);
+
+ return laddr ? laddr : daddr;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
+
+struct sock *
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+ const u8 protocol,
+ const __be32 saddr, const __be32 daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in,
+ const enum nf_tproxy_lookup_t lookup_type)
+{
+ struct sock *sk;
+ struct tcphdr *tcph;
+
+ switch (protocol) {
+ case IPPROTO_TCP:
+ switch (lookup_type) {
+ case NF_TPROXY_LOOKUP_LISTENER:
+ tcph = hp;
+ sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
+ ip_hdrlen(skb) +
+ __tcp_hdrlen(tcph),
+ saddr, sport,
+ daddr, dport,
+ in->ifindex, 0);
+
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
+ /* NOTE: we return listeners even if bound to
+ * 0.0.0.0, those are filtered out in
+ * xt_socket, since xt_TPROXY needs 0 bound
+ * listeners too
+ */
+ break;
+ case NF_TPROXY_LOOKUP_ESTABLISHED:
+ sk = inet_lookup_established(net, &tcp_hashinfo,
+ saddr, sport, daddr, dport,
+ in->ifindex);
+ break;
+ default:
+ BUG();
+ }
+ break;
+ case IPPROTO_UDP:
+ sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
+ in->ifindex);
+ if (sk) {
+ int connected = (sk->sk_state == TCP_ESTABLISHED);
+ int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
+
+ /* NOTE: we return listeners even if bound to
+ * 0.0.0.0, those are filtered out in
+ * xt_socket, since xt_TPROXY needs 0 bound
+ * listeners too
+ */
+ if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED &&
+ (!connected || wildcard)) ||
+ (lookup_type == NF_TPROXY_LOOKUP_LISTENER && connected)) {
+ sock_put(sk);
+ sk = NULL;
+ }
+ }
+ break;
+ default:
+ WARN_ON(1);
+ sk = NULL;
+ }
+
+ pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
+ protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v4);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs");
+MODULE_DESCRIPTION("Netfilter IPv4 transparent proxy support");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 9f5b00a39adf..37b14dc9d863 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -29,7 +29,10 @@ config NF_SOCKET_IPV6
tristate "IPv6 socket lookup support"
help
This option enables the IPv6 socket lookup infrastructure. This
- is used by the ip6tables socket match.
+ is used by the {ip6,nf}tables socket match.
+
+config NF_TPROXY_IPV6
+ tristate "IPv6 tproxy support"
if NF_TABLES
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 71518f22ae39..10a5a1c87320 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -26,6 +26,7 @@ nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
obj-$(CONFIG_NF_SOCKET_IPV6) += nf_socket_ipv6.o
+obj-$(CONFIG_NF_TPROXY_IPV6) += nf_tproxy_ipv6.o
# logging
obj-$(CONFIG_NF_LOG_IPV6) += nf_log_ipv6.o
diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c
new file mode 100644
index 000000000000..bf1d6c421e3b
--- /dev/null
+++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c
@@ -0,0 +1,146 @@
+#include <net/netfilter/nf_tproxy.h>
+#include <linux/module.h>
+#include <net/inet6_hashtables.h>
+#include <net/addrconf.h>
+#include <net/udp.h>
+#include <net/tcp.h>
+
+const struct in6_addr *
+nf_tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
+ const struct in6_addr *daddr)
+{
+ struct inet6_dev *indev;
+ struct inet6_ifaddr *ifa;
+ struct in6_addr *laddr;
+
+ if (!ipv6_addr_any(user_laddr))
+ return user_laddr;
+ laddr = NULL;
+
+ indev = __in6_dev_get(skb->dev);
+ if (indev) {
+ read_lock_bh(&indev->lock);
+ list_for_each_entry(ifa, &indev->addr_list, if_list) {
+ if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
+ continue;
+
+ laddr = &ifa->addr;
+ break;
+ }
+ read_unlock_bh(&indev->lock);
+ }
+
+ return laddr ? laddr : daddr;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_laddr6);
+
+struct sock *
+nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
+ struct net *net,
+ const struct in6_addr *laddr,
+ const __be16 lport,
+ struct sock *sk)
+{
+ const struct ipv6hdr *iph = ipv6_hdr(skb);
+ struct tcphdr _hdr, *hp;
+
+ hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+ if (hp == NULL) {
+ inet_twsk_put(inet_twsk(sk));
+ return NULL;
+ }
+
+ if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
+ /* SYN to a TIME_WAIT socket, we'd rather redirect it
+ * to a listener socket if there's one */
+ struct sock *sk2;
+
+ sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto,
+ &iph->saddr,
+ nf_tproxy_laddr6(skb, laddr, &iph->daddr),
+ hp->source,
+ lport ? lport : hp->dest,
+ skb->dev, NF_TPROXY_LOOKUP_LISTENER);
+ if (sk2) {
+ inet_twsk_deschedule_put(inet_twsk(sk));
+ sk = sk2;
+ }
+ }
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6);
+
+struct sock *
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+ const u8 protocol,
+ const struct in6_addr *saddr, const struct in6_addr *daddr,
+ const __be16 sport, const __be16 dport,
+ const struct net_device *in,
+ const enum nf_tproxy_lookup_t lookup_type)
+{
+ struct sock *sk;
+ struct tcphdr *tcph;
+
+ switch (protocol) {
+ case IPPROTO_TCP:
+ switch (lookup_type) {
+ case NF_TPROXY_LOOKUP_LISTENER:
+ tcph = hp;
+ sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
+ thoff + __tcp_hdrlen(tcph),
+ saddr, sport,
+ daddr, ntohs(dport),
+ in->ifindex, 0);
+
+ if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
+ sk = NULL;
+ /* NOTE: we return listeners even if bound to
+ * 0.0.0.0, those are filtered out in
+ * xt_socket, since xt_TPROXY needs 0 bound
+ * listeners too
+ */
+ break;
+ case NF_TPROXY_LOOKUP_ESTABLISHED:
+ sk = __inet6_lookup_established(net, &tcp_hashinfo,
+ saddr, sport, daddr, ntohs(dport),
+ in->ifindex, 0);
+ break;
+ default:
+ BUG();
+ }
+ break;
+ case IPPROTO_UDP:
+ sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
+ in->ifindex);
+ if (sk) {
+ int connected = (sk->sk_state == TCP_ESTABLISHED);
+ int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr);
+
+ /* NOTE: we return listeners even if bound to
+ * 0.0.0.0, those are filtered out in
+ * xt_socket, since xt_TPROXY needs 0 bound
+ * listeners too
+ */
+ if ((lookup_type == NF_TPROXY_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
+ (lookup_type == NF_TPROXY_LOOKUP_LISTENER && connected)) {
+ sock_put(sk);
+ sk = NULL;
+ }
+ }
+ break;
+ default:
+ WARN_ON(1);
+ sk = NULL;
+ }
+
+ pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n",
+ protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk);
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(nf_tproxy_get_sock_v6);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Balazs Scheidler, Krisztian Kovacs");
+MODULE_DESCRIPTION("Netfilter IPv4 transparent proxy support");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 276e1e32f44e..41240abd755f 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -989,6 +989,8 @@ config NETFILTER_XT_TARGET_TPROXY
depends on IP_NF_MANGLE
select NF_DEFRAG_IPV4
select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n
+ select NF_TPROXY_IPV4
+ select NF_TPROXY_IPV6 if IP6_NF_IPTABLES
help
This option adds a `TPROXY' target, which is somewhat similar to
REDIRECT. It can only be used in the mangle table and is useful
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 74df7977c17c..58fce4e749a9 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -33,253 +33,9 @@
#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
#endif
+#include <net/netfilter/nf_tproxy.h>
#include <linux/netfilter/xt_TPROXY.h>
-enum nf_tproxy_lookup_t {
- NFT_LOOKUP_LISTENER,
- NFT_LOOKUP_ESTABLISHED,
-};
-
-static bool tproxy_sk_is_transparent(struct sock *sk)
-{
- if (inet_sk_transparent(sk))
- return true;
-
- sock_gen_put(sk);
- return false;
-}
-
-static inline __be32
-tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
-{
- struct in_device *indev;
- __be32 laddr;
-
- if (user_laddr)
- return user_laddr;
-
- laddr = 0;
- indev = __in_dev_get_rcu(skb->dev);
- for_primary_ifa(indev) {
- laddr = ifa->ifa_local;
- break;
- } endfor_ifa(indev);
-
- return laddr ? laddr : daddr;
-}
-
-/*
- * This is used when the user wants to intercept a connection matching
- * an explicit iptables rule. In this case the sockets are assumed
- * matching in preference order:
- *
- * - match: if there's a fully established connection matching the
- * _packet_ tuple, it is returned, assuming the redirection
- * already took place and we process a packet belonging to an
- * established connection
- *
- * - match: if there's a listening socket matching the redirection
- * (e.g. on-port & on-ip of the connection), it is returned,
- * regardless if it was bound to 0.0.0.0 or an explicit
- * address. The reasoning is that if there's an explicit rule, it
- * does not really matter if the listener is bound to an interface
- * or to 0. The user already stated that he wants redirection
- * (since he added the rule).
- *
- * Please note that there's an overlap between what a TPROXY target
- * and a socket match will match. Normally if you have both rules the
- * "socket" match will be the first one, effectively all packets
- * belonging to established connections going through that one.
- */
-static inline struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
- const u8 protocol,
- const __be32 saddr, const __be32 daddr,
- const __be16 sport, const __be16 dport,
- const struct net_device *in,
- const enum nf_tproxy_lookup_t lookup_type)
-{
- struct sock *sk;
- struct tcphdr *tcph;
-
- switch (protocol) {
- case IPPROTO_TCP:
- switch (lookup_type) {
- case NFT_LOOKUP_LISTENER:
- tcph = hp;
- sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
- ip_hdrlen(skb) +
- __tcp_hdrlen(tcph),
- saddr, sport,
- daddr, dport,
- in->ifindex, 0);
-
- if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
- sk = NULL;
- /* NOTE: we return listeners even if bound to
- * 0.0.0.0, those are filtered out in
- * xt_socket, since xt_TPROXY needs 0 bound
- * listeners too
- */
- break;
- case NFT_LOOKUP_ESTABLISHED:
- sk = inet_lookup_established(net, &tcp_hashinfo,
- saddr, sport, daddr, dport,
- in->ifindex);
- break;
- default:
- BUG();
- }
- break;
- case IPPROTO_UDP:
- sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
- if (sk) {
- int connected = (sk->sk_state == TCP_ESTABLISHED);
- int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
-
- /* NOTE: we return listeners even if bound to
- * 0.0.0.0, those are filtered out in
- * xt_socket, since xt_TPROXY needs 0 bound
- * listeners too
- */
- if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
- (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
- sock_put(sk);
- sk = NULL;
- }
- }
- break;
- default:
- WARN_ON(1);
- sk = NULL;
- }
-
- pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
- protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
-
- return sk;
-}
-
-#ifdef XT_TPROXY_HAVE_IPV6
-static inline struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
- const u8 protocol,
- const struct in6_addr *saddr, const struct in6_addr *daddr,
- const __be16 sport, const __be16 dport,
- const struct net_device *in,
- const enum nf_tproxy_lookup_t lookup_type)
-{
- struct sock *sk;
- struct tcphdr *tcph;
-
- switch (protocol) {
- case IPPROTO_TCP:
- switch (lookup_type) {
- case NFT_LOOKUP_LISTENER:
- tcph = hp;
- sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
- thoff + __tcp_hdrlen(tcph),
- saddr, sport,
- daddr, ntohs(dport),
- in->ifindex, 0);
-
- if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
- sk = NULL;
- /* NOTE: we return listeners even if bound to
- * 0.0.0.0, those are filtered out in
- * xt_socket, since xt_TPROXY needs 0 bound
- * listeners too
- */
- break;
- case NFT_LOOKUP_ESTABLISHED:
- sk = __inet6_lookup_established(net, &tcp_hashinfo,
- saddr, sport, daddr, ntohs(dport),
- in->ifindex, 0);
- break;
- default:
- BUG();
- }
- break;
- case IPPROTO_UDP:
- sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
- in->ifindex);
- if (sk) {
- int connected = (sk->sk_state == TCP_ESTABLISHED);
- int wildcard = ipv6_addr_any(&sk->sk_v6_rcv_saddr);
-
- /* NOTE: we return listeners even if bound to
- * 0.0.0.0, those are filtered out in
- * xt_socket, since xt_TPROXY needs 0 bound
- * listeners too
- */
- if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
- (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
- sock_put(sk);
- sk = NULL;
- }
- }
- break;
- default:
- WARN_ON(1);
- sk = NULL;
- }
-
- pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n",
- protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk);
-
- return sk;
-}
-#endif
-
-/**
- * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections
- * @skb: The skb being processed.
- * @laddr: IPv4 address to redirect to or zero.
- * @lport: TCP port to redirect to or zero.
- * @sk: The TIME_WAIT TCP socket found by the lookup.
- *
- * We have to handle SYN packets arriving to TIME_WAIT sockets
- * differently: instead of reopening the connection we should rather
- * redirect the new connection to the proxy if there's a listener
- * socket present.
- *
- * tproxy_handle_time_wait4() consumes the socket reference passed in.
- *
- * Returns the listener socket if there's one, the TIME_WAIT socket if
- * no such listener is found, or NULL if the TCP header is incomplete.
- */
-static struct sock *
-tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
- __be32 laddr, __be16 lport, struct sock *sk)
-{
- const struct iphdr *iph = ip_hdr(skb);
- struct tcphdr _hdr, *hp;
-
- hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
- if (hp == NULL) {
- inet_twsk_put(inet_twsk(sk));
- return NULL;
- }
-
- if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
- /* SYN to a TIME_WAIT socket, we'd rather redirect it
- * to a listener socket if there's one */
- struct sock *sk2;
-
- sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
- iph->saddr, laddr ? laddr : iph->daddr,
- hp->source, lport ? lport : hp->dest,
- skb->dev, NFT_LOOKUP_LISTENER);
- if (sk2) {
- inet_twsk_deschedule_put(inet_twsk(sk));
- sk = sk2;
- }
- }
-
- return sk;
-}
-
/* assign a socket to the skb -- consumes sk */
static void
nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
@@ -308,26 +64,26 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
iph->saddr, iph->daddr,
hp->source, hp->dest,
- skb->dev, NFT_LOOKUP_ESTABLISHED);
+ skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED);
- laddr = tproxy_laddr4(skb, laddr, iph->daddr);
+ laddr = nf_tproxy_laddr4(skb, laddr, iph->daddr);
if (!lport)
lport = hp->dest;
/* UDP has no TCP_TIME_WAIT state, so we never enter here */
if (sk && sk->sk_state == TCP_TIME_WAIT)
/* reopening a TIME_WAIT connection needs special handling */
- sk = tproxy_handle_time_wait4(net, skb, laddr, lport, sk);
+ sk = nf_tproxy_handle_time_wait4(net, skb, laddr, lport, sk);
else if (!sk)
/* no, there's no established connection, check if
* there's a listener on the redirected addr/port */
sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
iph->saddr, laddr,
hp->source, lport,
- skb->dev, NFT_LOOKUP_LISTENER);
+ skb->dev, NF_TPROXY_LOOKUP_LISTENER);
/* NOTE: assign_sock consumes our sk reference */
- if (sk && tproxy_sk_is_transparent(sk)) {
+ if (sk && nf_tproxy_sk_is_transparent(sk)) {
/* This should be in a separate target, but we don't do multiple
targets on the same rule yet */
skb->mark = (skb->mark & ~mark_mask) ^ mark_value;
@@ -366,87 +122,6 @@ tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par)
#ifdef XT_TPROXY_HAVE_IPV6
-static inline const struct in6_addr *
-tproxy_laddr6(struct sk_buff *skb, const struct in6_addr *user_laddr,
- const struct in6_addr *daddr)
-{
- struct inet6_dev *indev;
- struct inet6_ifaddr *ifa;
- struct in6_addr *laddr;
-
- if (!ipv6_addr_any(user_laddr))
- return user_laddr;
- laddr = NULL;
-
- indev = __in6_dev_get(skb->dev);
- if (indev) {
- read_lock_bh(&indev->lock);
- list_for_each_entry(ifa, &indev->addr_list, if_list) {
- if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DEPRECATED))
- continue;
-
- laddr = &ifa->addr;
- break;
- }
- read_unlock_bh(&indev->lock);
- }
-
- return laddr ? laddr : daddr;
-}
-
-/**
- * tproxy_handle_time_wait6 - handle IPv6 TCP TIME_WAIT reopen redirections
- * @skb: The skb being processed.
- * @tproto: Transport protocol.
- * @thoff: Transport protocol header offset.
- * @par: Iptables target parameters.
- * @sk: The TIME_WAIT TCP socket found by the lookup.
- *
- * We have to handle SYN packets arriving to TIME_WAIT sockets
- * differently: instead of reopening the connection we should rather
- * redirect the new connection to the proxy if there's a listener
- * socket present.
- *
- * tproxy_handle_time_wait6() consumes the socket reference passed in.
- *
- * Returns the listener socket if there's one, the TIME_WAIT socket if
- * no such listener is found, or NULL if the TCP header is incomplete.
- */
-static struct sock *
-tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
- const struct xt_action_param *par,
- struct sock *sk)
-{
- const struct ipv6hdr *iph = ipv6_hdr(skb);
- struct tcphdr _hdr, *hp;
- const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;
-
- hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
- if (hp == NULL) {
- inet_twsk_put(inet_twsk(sk));
- return NULL;
- }
-
- if (hp->syn && !hp->rst && !hp->ack && !hp->fin) {
- /* SYN to a TIME_WAIT socket, we'd rather redirect it
- * to a listener socket if there's one */
- struct sock *sk2;
-
- sk2 = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
- &iph->saddr,
- tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr),
- hp->source,
- tgi->lport ? tgi->lport : hp->dest,
- skb->dev, NFT_LOOKUP_LISTENER);
- if (sk2) {
- inet_twsk_deschedule_put(inet_twsk(sk));
- sk = sk2;
- }
- }
-
- return sk;
-}
-
static unsigned int
tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
{
@@ -478,25 +153,31 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
&iph->saddr, &iph->daddr,
hp->source, hp->dest,
- xt_in(par), NFT_LOOKUP_ESTABLISHED);
+ xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED);
- laddr = tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr);
+ laddr = nf_tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr);
lport = tgi->lport ? tgi->lport : hp->dest;
/* UDP has no TCP_TIME_WAIT state, so we never enter here */
- if (sk && sk->sk_state == TCP_TIME_WAIT)
+ if (sk && sk->sk_state == TCP_TIME_WAIT) {
+ const struct xt_tproxy_target_info_v1 *tgi = par->targinfo;
/* reopening a TIME_WAIT connection needs special handling */
- sk = tproxy_handle_time_wait6(skb, tproto, thoff, par, sk);
+ sk = nf_tproxy_handle_time_wait6(skb, tproto, thoff,
+ xt_net(par),
+ &tgi->laddr.in6,
+ tgi->lport,
+ sk);
+ }
else if (!sk)
/* no there's no established connection, check if
* there's a listener on the redirected addr/port */
sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp,
tproto, &iph->saddr, laddr,
hp->source, lport,
- xt_in(par), NFT_LOOKUP_LISTENER);
+ xt_in(par), NF_TPROXY_LOOKUP_LISTENER);
/* NOTE: assign_sock consumes our sk reference */
- if (sk && tproxy_sk_is_transparent(sk)) {
+ if (sk && nf_tproxy_sk_is_transparent(sk)) {
/* This should be in a separate target, but we don't do multiple
targets on the same rule yet */
skb->mark = (skb->mark & ~tgi->mark_mask) ^ tgi->mark_value;
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread* [PATCH 9/9] netfilter: nf_tables: handle chain name lookups via rhltable
2018-06-02 23:14 [PATCH 0/9] Netfilter updates for net-next Pablo Neira Ayuso
` (7 preceding siblings ...)
2018-06-02 23:14 ` [PATCH 8/9] netfilter: nf_tables: add connlimit support Pablo Neira Ayuso
@ 2018-06-02 23:14 ` Pablo Neira Ayuso
8 siblings, 0 replies; 10+ messages in thread
From: Pablo Neira Ayuso @ 2018-06-02 23:14 UTC (permalink / raw)
To: netfilter-devel; +Cc: davem, netdev
From: Florian Westphal <fw@strlen.de>
If there is a significant amount of chains list search is too slow, so
add an rhlist table for this.
This speeds up ruleset loading: for every new rule we have to check if
the name already exists in current generation.
We need to be able to cope with duplicate chain names in case a transaction
drops the nfnl mutex (for request_module) and the abort of this old
transaction is still pending.
The list is kept -- we need a way to iterate chains even if hash resize is
in progress without missing an entry.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
include/net/netfilter/nf_tables.h | 7 ++-
net/netfilter/nf_tables_api.c | 113 +++++++++++++++++++++++++++++++++-----
2 files changed, 104 insertions(+), 16 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 83e7b83ecf3e..08c005ce56e9 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -9,6 +9,7 @@
#include <linux/netfilter/x_tables.h>
#include <linux/netfilter/nf_tables.h>
#include <linux/u64_stats_sync.h>
+#include <linux/rhashtable.h>
#include <net/netfilter/nf_flow_table.h>
#include <net/netlink.h>
@@ -860,6 +861,7 @@ enum nft_chain_flags {
*
* @rules: list of rules in the chain
* @list: used internally
+ * @rhlhead: used internally
* @table: table that this chain belongs to
* @handle: chain handle
* @use: number of jump references to this chain
@@ -872,6 +874,7 @@ struct nft_chain {
struct nft_rule *__rcu *rules_gen_1;
struct list_head rules;
struct list_head list;
+ struct rhlist_head rhlhead;
struct nft_table *table;
u64 handle;
u32 use;
@@ -965,7 +968,8 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
* struct nft_table - nf_tables table
*
* @list: used internally
- * @chains: chains in the table
+ * @chains_ht: chains in the table
+ * @chains: same, for stable walks
* @sets: sets in the table
* @objects: stateful objects in the table
* @flowtables: flow tables in the table
@@ -979,6 +983,7 @@ unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
*/
struct nft_table {
struct list_head list;
+ struct rhltable chains_ht;
struct list_head chains;
struct list_head sets;
struct list_head objects;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0a6eafa49879..2e8fd961746d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -34,6 +34,20 @@ enum {
NFT_VALIDATE_DO,
};
+static u32 nft_chain_hash(const void *data, u32 len, u32 seed);
+static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed);
+static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *);
+
+static const struct rhashtable_params nft_chain_ht_params = {
+ .head_offset = offsetof(struct nft_chain, rhlhead),
+ .key_offset = offsetof(struct nft_chain, name),
+ .hashfn = nft_chain_hash,
+ .obj_hashfn = nft_chain_hash_obj,
+ .obj_cmpfn = nft_chain_hash_cmp,
+ .locks_mul = 1,
+ .automatic_shrinking = true,
+};
+
static void nft_validate_state_update(struct net *net, u8 new_validate_state)
{
switch (net->nft.validate_state) {
@@ -720,6 +734,29 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
return ret;
}
+static u32 nft_chain_hash(const void *data, u32 len, u32 seed)
+{
+ const char *name = data;
+
+ return jhash(name, strlen(name), seed);
+}
+
+static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed)
+{
+ const struct nft_chain *chain = data;
+
+ return nft_chain_hash(chain->name, 0, seed);
+}
+
+static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg,
+ const void *ptr)
+{
+ const struct nft_chain *chain = ptr;
+ const char *name = arg->key;
+
+ return strcmp(chain->name, name);
+}
+
static int nf_tables_newtable(struct net *net, struct sock *nlsk,
struct sk_buff *skb, const struct nlmsghdr *nlh,
const struct nlattr * const nla[],
@@ -766,6 +803,10 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
if (table->name == NULL)
goto err_strdup;
+ err = rhltable_init(&table->chains_ht, &nft_chain_ht_params);
+ if (err)
+ goto err_chain_ht;
+
INIT_LIST_HEAD(&table->chains);
INIT_LIST_HEAD(&table->sets);
INIT_LIST_HEAD(&table->objects);
@@ -782,6 +823,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
list_add_tail_rcu(&table->list, &net->nft.tables);
return 0;
err_trans:
+ rhltable_destroy(&table->chains_ht);
+err_chain_ht:
kfree(table->name);
err_strdup:
kfree(table);
@@ -922,6 +965,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
{
BUG_ON(ctx->table->use > 0);
+ rhltable_destroy(&ctx->table->chains_ht);
kfree(ctx->table->name);
kfree(ctx->table);
}
@@ -967,21 +1011,35 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask)
return ERR_PTR(-ENOENT);
}
-static struct nft_chain *nft_chain_lookup(const struct nft_table *table,
+static struct nft_chain *nft_chain_lookup(struct nft_table *table,
const struct nlattr *nla, u8 genmask)
{
+ char search[NFT_CHAIN_MAXNAMELEN + 1];
+ struct rhlist_head *tmp, *list;
struct nft_chain *chain;
if (nla == NULL)
return ERR_PTR(-EINVAL);
- list_for_each_entry_rcu(chain, &table->chains, list) {
- if (!nla_strcmp(nla, chain->name) &&
- nft_active_genmask(chain, genmask))
- return chain;
- }
+ nla_strlcpy(search, nla, sizeof(search));
- return ERR_PTR(-ENOENT);
+ WARN_ON(!rcu_read_lock_held() &&
+ !lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+
+ chain = ERR_PTR(-ENOENT);
+ rcu_read_lock();
+ list = rhltable_lookup(&table->chains_ht, search, nft_chain_ht_params);
+ if (!list)
+ goto out_unlock;
+
+ rhl_for_each_entry_rcu(chain, tmp, list, rhlhead) {
+ if (nft_active_genmask(chain, genmask))
+ goto out_unlock;
+ }
+ chain = ERR_PTR(-ENOENT);
+out_unlock:
+ rcu_read_unlock();
+ return chain;
}
static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
@@ -1185,8 +1243,8 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
- const struct nft_table *table;
const struct nft_chain *chain;
+ struct nft_table *table;
struct sk_buff *skb2;
int family = nfmsg->nfgen_family;
int err;
@@ -1504,9 +1562,17 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
if (err < 0)
goto err1;
+ err = rhltable_insert_key(&table->chains_ht, chain->name,
+ &chain->rhlhead, nft_chain_ht_params);
+ if (err)
+ goto err2;
+
err = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
- if (err < 0)
+ if (err < 0) {
+ rhltable_remove(&table->chains_ht, &chain->rhlhead,
+ nft_chain_ht_params);
goto err2;
+ }
table->use++;
list_add_tail_rcu(&chain->list, &table->chains);
@@ -2206,9 +2272,9 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
{
const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
u8 genmask = nft_genmask_cur(net);
- const struct nft_table *table;
const struct nft_chain *chain;
const struct nft_rule *rule;
+ struct nft_table *table;
struct sk_buff *skb2;
int family = nfmsg->nfgen_family;
int err;
@@ -5981,8 +6047,16 @@ static void nft_chain_commit_update(struct nft_trans *trans)
{
struct nft_base_chain *basechain;
- if (nft_trans_chain_name(trans))
+ if (nft_trans_chain_name(trans)) {
+ rhltable_remove(&trans->ctx.table->chains_ht,
+ &trans->ctx.chain->rhlhead,
+ nft_chain_ht_params);
swap(trans->ctx.chain->name, nft_trans_chain_name(trans));
+ rhltable_insert_key(&trans->ctx.table->chains_ht,
+ trans->ctx.chain->name,
+ &trans->ctx.chain->rhlhead,
+ nft_chain_ht_params);
+ }
if (!nft_is_base_chain(trans->ctx.chain))
return;
@@ -6159,6 +6233,15 @@ static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *cha
nf_tables_commit_chain_free_rules_old(g0);
}
+static void nft_chain_del(struct nft_chain *chain)
+{
+ struct nft_table *table = chain->table;
+
+ WARN_ON_ONCE(rhltable_remove(&table->chains_ht, &chain->rhlhead,
+ nft_chain_ht_params));
+ list_del_rcu(&chain->list);
+}
+
static int nf_tables_commit(struct net *net, struct sk_buff *skb)
{
struct nft_trans *trans, *next;
@@ -6233,7 +6316,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nft_trans_destroy(trans);
break;
case NFT_MSG_DELCHAIN:
- list_del_rcu(&trans->ctx.chain->list);
+ nft_chain_del(trans->ctx.chain);
nf_tables_chain_notify(&trans->ctx, NFT_MSG_DELCHAIN);
nf_tables_unregister_hook(trans->ctx.net,
trans->ctx.table,
@@ -6384,7 +6467,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
nft_trans_destroy(trans);
} else {
trans->ctx.table->use--;
- list_del_rcu(&trans->ctx.chain->list);
+ nft_chain_del(trans->ctx.chain);
nf_tables_unregister_hook(trans->ctx.net,
trans->ctx.table,
trans->ctx.chain);
@@ -6986,7 +7069,7 @@ int __nft_release_basechain(struct nft_ctx *ctx)
ctx->chain->use--;
nf_tables_rule_release(ctx, rule);
}
- list_del(&ctx->chain->list);
+ nft_chain_del(ctx->chain);
ctx->table->use--;
nf_tables_chain_destroy(ctx);
@@ -7042,7 +7125,7 @@ static void __nft_release_tables(struct net *net)
}
list_for_each_entry_safe(chain, nc, &table->chains, list) {
ctx.chain = chain;
- list_del(&chain->list);
+ nft_chain_del(chain);
table->use--;
nf_tables_chain_destroy(&ctx);
}
--
2.11.0
^ permalink raw reply related [flat|nested] 10+ messages in thread