netfilter: nf_dup{4, 6}: Move duplication check to task_struct

nf_skb_duplicated is a per-CPU variable and relies on disabled BH for its
locking. Without per-CPU locking in local_bh_disable() on PREEMPT_RT
this data structure requires explicit locking.

Due to the recursion involved, the simplest change is to make it a
per-task variable.

Move the per-CPU variable nf_skb_duplicated to task_struct and name it
in_nf_duplicate. Add it to the existing bitfield so it doesn't use
additional memory.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Valentin Schneider <vschneid@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

7 files changed, 9 insertions, 22 deletions

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 2b8aac2c70ad..892d12823ed4 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -498,17 +498,6 @@ extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook;
 extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook;
 
 /*
- * nf_skb_duplicated - TEE target has sent a packet
- *
- * When a xtables target sends a packet, the OUTPUT and POSTROUTING
- * hooks are traversed again, i.e. nft and xtables are invoked recursively.
- *
- * This is used by xtables TEE target to prevent the duplicated skb from
- * being duplicated again.
- */
-DECLARE_PER_CPU(bool, nf_skb_duplicated);
-
-/*
  * Contains bitmask of ctnetlink event subscribers, if any.
  * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag.
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f96ac1982893..52d9c52dc8f2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1044,6 +1044,7 @@ struct task_struct {
 	/* delay due to memory thrashing */
 	unsigned                        in_thrashing:1;
 #endif
+	unsigned			in_nf_duplicate:1;
 #ifdef CONFIG_PREEMPT_RT
 	struct netdev_xmit		net_xmit;
 #endif
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 3d101613f27f..23c8deff8095 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -270,7 +270,7 @@ ipt_do_table(void *priv,
 	 * but it is no problem since absolute verdict is issued by these.
 	 */
 	if (static_key_false(&xt_tee_enabled))
-		jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated);
+		jumpstack += private->stacksize * current->in_nf_duplicate;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index 25e1e8eb18dd..ed08fb78cfa8 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -54,7 +54,7 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 	struct iphdr *iph;
 
 	local_bh_disable();
-	if (this_cpu_read(nf_skb_duplicated))
+	if (current->in_nf_duplicate)
 		goto out;
 	/*
 	 * Copy the skb, and route the copy. Will later return %XT_CONTINUE for
@@ -86,9 +86,9 @@ void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 		--iph->ttl;
 
 	if (nf_dup_ipv4_route(net, skb, gw, oif)) {
-		__this_cpu_write(nf_skb_duplicated, true);
+		current->in_nf_duplicate = true;
 		ip_local_out(net, skb->sk, skb);
-		__this_cpu_write(nf_skb_duplicated, false);
+		current->in_nf_duplicate = false;
 	} else {
 		kfree_skb(skb);
 	}
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7d5602950ae7..d585ac3c1113 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -292,7 +292,7 @@ ip6t_do_table(void *priv, struct sk_buff *skb,
 	 * but it is no problem since absolute verdict is issued by these.
 	 */
 	if (static_key_false(&xt_tee_enabled))
-		jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated);
+		jumpstack += private->stacksize * current->in_nf_duplicate;
 
 	e = get_entry(table_base, private->hook_entry[hook]);
 
diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c
index 0c39c77fe8a8..b903c62c00c9 100644
--- a/net/ipv6/netfilter/nf_dup_ipv6.c
+++ b/net/ipv6/netfilter/nf_dup_ipv6.c
@@ -48,7 +48,7 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 		 const struct in6_addr *gw, int oif)
 {
 	local_bh_disable();
-	if (this_cpu_read(nf_skb_duplicated))
+	if (current->in_nf_duplicate)
 		goto out;
 	skb = pskb_copy(skb, GFP_ATOMIC);
 	if (skb == NULL)
@@ -64,9 +64,9 @@ void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum,
 		--iph->hop_limit;
 	}
 	if (nf_dup_ipv6_route(net, skb, gw, oif)) {
-		__this_cpu_write(nf_skb_duplicated, true);
+		current->in_nf_duplicate = true;
 		ip6_local_out(net, skb->sk, skb);
-		__this_cpu_write(nf_skb_duplicated, false);
+		current->in_nf_duplicate = false;
 	} else {
 		kfree_skb(skb);
 	}
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index b9f551f02c81..11a702065bab 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -31,9 +31,6 @@
 const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ipv6_ops);
 
-DEFINE_PER_CPU(bool, nf_skb_duplicated);
-EXPORT_SYMBOL_GPL(nf_skb_duplicated);
-
 #ifdef CONFIG_JUMP_LABEL
 struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 EXPORT_SYMBOL(nf_hooks_needed);