netfilter: conntrack: get rid of conntrack timer

With stats enabled this eats 80 bytes on x86_64 per nf_conn entry, as
Eric Dumazet pointed out during netfilter workshop 2016.

Eric also says: "Another reason was the fact that Thomas was about to
change max timer range [..]" (500462a9de657f8, 'timers: Switch to
a non-cascading wheel').

Remove the timer and use a 32bit jiffies value containing timestamp until
entry is valid.

During conntrack lookup, even before doing tuple comparision, check
the timeout value and evict the entry in case it is too old.

The dying bit is used as a synchronization point to avoid races where
multiple cpus try to evict the same entry.

Because lookup is always lockless, we need to bump the refcnt once
when we evict, else we could try to evict already-dead entry that
is being recycled.

This is the standard/expected way when conntrack entries are destroyed.

Followup patches will introduce garbage colliction via work queue
and further places where we can reap obsoleted entries (e.g. during
netlink dumps), this is needed to avoid expired conntracks from hanging
around for too long when lookup rate is low after a busy period.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 18 insertions, 5 deletions

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 2a127480d4cc..7277751128e8 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -42,7 +42,6 @@ union nf_conntrack_expect_proto {
 
 #include <linux/types.h>
 #include <linux/skbuff.h>
-#include <linux/timer.h>
 
 #ifdef CONFIG_NETFILTER_DEBUG
 #define NF_CT_ASSERT(x)		WARN_ON(!(x))
@@ -73,7 +72,7 @@ struct nf_conn_help {
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 
 struct nf_conn {
-	/* Usage count in here is 1 for hash table/destruct timer, 1 per skb,
+	/* Usage count in here is 1 for hash table, 1 per skb,
 	 * plus 1 for any connection(s) we are `master' for
 	 *
 	 * Hint, SKB address this struct and refcnt via skb->nfct and
@@ -96,8 +95,8 @@ struct nf_conn {
 	/* Have we seen traffic both ways yet? (bitset) */
 	unsigned long status;
 
-	/* Timer function; drops refcnt when it goes off. */
-	struct timer_list timeout;
+	/* jiffies32 when this ct is considered dead */
+	u32 timeout;
 
 	possible_net_t ct_net;
 
@@ -291,14 +290,28 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 	return skb->dev && skb->skb_iif && skb->dev->flags & IFF_LOOPBACK;
 }
 
+#define nfct_time_stamp ((u32)(jiffies))
+
 /* jiffies until ct expires, 0 if already expired */
 static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
 {
-	long timeout = (long)ct->timeout.expires - (long)jiffies;
+	s32 timeout = ct->timeout - nfct_time_stamp;
 
 	return timeout > 0 ? timeout : 0;
 }
 
+static inline bool nf_ct_is_expired(const struct nf_conn *ct)
+{
+	return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+}
+
+/* use after obtaining a reference count */
+static inline bool nf_ct_should_gc(const struct nf_conn *ct)
+{
+	return nf_ct_is_expired(ct) && nf_ct_is_confirmed(ct) &&
+	       !nf_ct_is_dying(ct);
+}
+
 struct kernel_param;
 
 int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);