netfilter: conntrack: remove central spinlock nf_conntrack_lock

nf_conntrack_lock is a monolithic lock and suffers from huge contention
on current generation servers (8 or more core/threads).

Perf locking congestion is clear on base kernel:

-  72.56%  ksoftirqd/6  [kernel.kallsyms]    [k] _raw_spin_lock_bh
   - _raw_spin_lock_bh
      + 25.33% init_conntrack
      + 24.86% nf_ct_delete_from_lists
      + 24.62% __nf_conntrack_confirm
      + 24.38% destroy_conntrack
      + 0.70% tcp_packet
+   2.21%  ksoftirqd/6  [kernel.kallsyms]    [k] fib_table_lookup
+   1.15%  ksoftirqd/6  [kernel.kallsyms]    [k] __slab_free
+   0.77%  ksoftirqd/6  [kernel.kallsyms]    [k] inet_getpeer
+   0.70%  ksoftirqd/6  [nf_conntrack]       [k] nf_ct_delete
+   0.55%  ksoftirqd/6  [ip_tables]          [k] ipt_do_table

This patch change conntrack locking and provides a huge performance
improvement.  SYN-flood attack tested on a 24-core E5-2695v2(ES) with
10Gbit/s ixgbe (with tool trafgen):

 Base kernel:   810.405 new conntrack/sec
 After patch: 2.233.876 new conntrack/sec

Notice other floods attack (SYN+ACK or ACK) can easily be deflected using:
 # iptables -A INPUT -m state --state INVALID -j DROP
 # sysctl -w net/netfilter/nf_conntrack_tcp_loose=0

Use an array of hashed spinlocks to protect insertions/deletions of
conntracks into the hash table. 1024 spinlocks seem to give good
results, at minimal cost (4KB memory). Due to lockdep max depth,
1024 becomes 8 if CONFIG_LOCKDEP=y

The hash resize is a bit tricky, because we need to take all locks in
the array. A seqcount_t is used to synchronize the hash table users
with the resizing process.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 8 insertions, 1 deletions

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index d12a631d0415..cc0c18827602 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -77,7 +77,12 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
             const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *proto);
 
-extern spinlock_t nf_conntrack_lock ;
+#ifdef CONFIG_LOCKDEP
+# define CONNTRACK_LOCKS 8
+#else
+# define CONNTRACK_LOCKS 1024
+#endif
+extern spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
 
 extern spinlock_t nf_conntrack_expect_lock;
 
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index c6a8994e9922..773cce308bc6 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -5,6 +5,7 @@
 #include <linux/list_nulls.h>
 #include <linux/atomic.h>
 #include <linux/netfilter/nf_conntrack_tcp.h>
+#include <linux/seqlock.h>
 
 struct ctl_table_header;
 struct nf_conntrack_ecache;
@@ -90,6 +91,7 @@ struct netns_ct {
         int                     sysctl_checksum;
 
         unsigned int            htable_size;
+        seqcount_t              generation;
         struct kmem_cache       *nf_conntrack_cachep;
         struct hlist_nulls_head *hash;
         struct hlist_head       *expect_hash;