netfilter: connlimit: use rbtree for per-host conntrack obj storage

With current match design every invocation of the connlimit_match
function means we have to perform (number_of_conntracks % 256) lookups
in the conntrack table [ to perform GC/delete stale entries ].
This is also the reason why ____nf_conntrack_find() in perf top has
> 20% cpu time per core.

This patch changes the storage to rbtree which cuts down the number of
ct objects that need testing.

When looking up a new tuple, we only test the connections of the host
objects we visit while searching for the wanted host/network (or
the leaf we need to insert at).

The slot count is reduced to 32.  Increasing slot count doesn't
speed up things much because of rbtree nature.

before patch (50kpps rx, 10kpps tx):
+  20.95%  ksoftirqd/0  [nf_conntrack] [k] ____nf_conntrack_find
+  20.50%  ksoftirqd/1  [nf_conntrack] [k] ____nf_conntrack_find
+  20.27%  ksoftirqd/2  [nf_conntrack] [k] ____nf_conntrack_find
+   5.76%  ksoftirqd/1  [nf_conntrack] [k] hash_conntrack_raw
+   5.39%  ksoftirqd/2  [nf_conntrack] [k] hash_conntrack_raw
+   5.35%  ksoftirqd/0  [nf_conntrack] [k] hash_conntrack_raw

after (90kpps, 51kpps tx):
+  17.24%       swapper  [nf_conntrack]    [k] ____nf_conntrack_find
+   6.60%   ksoftirqd/2  [nf_conntrack]    [k] ____nf_conntrack_find
+   2.73%       swapper  [nf_conntrack]    [k] hash_conntrack_raw
+   2.36%       swapper  [xt_connlimit]    [k] count_tree

Obvious disadvantages to previous version are the increase in code
complexity and the increased memory cost.

Partially based on Eric Dumazets fq scheduler.

Reviewed-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 177 insertions, 47 deletions

diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index dc5207f7a7fa..458464e7bd7a 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -19,6 +19,7 @@
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/skbuff.h>
@@ -31,8 +32,9 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 
-#define CONNLIMIT_SLOTS 256
+#define CONNLIMIT_SLOTS         32
 #define CONNLIMIT_LOCK_SLOTS    32
+#define CONNLIMIT_GC_MAX_NODES  8
 
 /* we will save the tuples of all connections we care about */
 struct xt_connlimit_conn {
@@ -41,12 +43,20 @@ struct xt_connlimit_conn {
         union nf_inet_addr              addr;
 };
 
+struct xt_connlimit_rb {
+        struct rb_node node;
+        struct hlist_head hhead; /* connections/hosts in same subnet */
+        union nf_inet_addr addr; /* search key */
+};
+
 struct xt_connlimit_data {
-        struct hlist_head       iphash[CONNLIMIT_SLOTS];
+        struct rb_root climit_root4[CONNLIMIT_SLOTS];
+        struct rb_root climit_root6[CONNLIMIT_SLOTS];
         spinlock_t              locks[CONNLIMIT_LOCK_SLOTS];
 };
 
 static u_int32_t connlimit_rnd __read_mostly;
+static struct kmem_cache *connlimit_rb_cachep __read_mostly;
 static struct kmem_cache *connlimit_conn_cachep __read_mostly;
 
 static inline unsigned int connlimit_iphash(__be32 addr)
@@ -99,19 +109,33 @@ same_source_net(const union nf_inet_addr *addr,
         }
 }
 
-static int count_hlist(struct net *net,
-                       struct hlist_head *head,
-                       const struct nf_conntrack_tuple *tuple,
-                       const union nf_inet_addr *addr,
-                       const union nf_inet_addr *mask,
-                       u_int8_t family, bool *addit)
+static bool add_hlist(struct hlist_head *head,
+                      const struct nf_conntrack_tuple *tuple,
+                      const union nf_inet_addr *addr)
+{
+        struct xt_connlimit_conn *conn;
+
+        conn = kmem_cache_alloc(connlimit_conn_cachep, GFP_ATOMIC);
+        if (conn == NULL)
+                return false;
+        conn->tuple = *tuple;
+        conn->addr = *addr;
+        hlist_add_head(&conn->node, head);
+        return true;
+}
+
+static unsigned int check_hlist(struct net *net,
+                                struct hlist_head *head,
+                                const struct nf_conntrack_tuple *tuple,
+                                bool *addit)
 {
         const struct nf_conntrack_tuple_hash *found;
         struct xt_connlimit_conn *conn;
         struct hlist_node *n;
         struct nf_conn *found_ct;
-        int matches = 0;
+        unsigned int length = 0;
 
+        *addit = true;
         rcu_read_lock();
 
         /* check the saved connections */
@@ -144,30 +168,114 @@ static int count_hlist(struct net *net,
                         continue;
                 }
 
-                if (same_source_net(addr, mask, &conn->addr, family) == 0)
-                        /* same source network -> be counted! */
-                        ++matches;
                 nf_ct_put(found_ct);
+                length++;
         }
 
         rcu_read_unlock();
 
-        return matches;
+        return length;
 }
 
-static bool add_hlist(struct hlist_head *head,
-                      const struct nf_conntrack_tuple *tuple,
-                      const union nf_inet_addr *addr)
+static void tree_nodes_free(struct rb_root *root,
+                            struct xt_connlimit_rb *gc_nodes[],
+                            unsigned int gc_count)
+{
+        struct xt_connlimit_rb *rbconn;
+
+        while (gc_count) {
+                rbconn = gc_nodes[--gc_count];
+                rb_erase(&rbconn->node, root);
+                kmem_cache_free(connlimit_rb_cachep, rbconn);
+        }
+}
+
+static unsigned int
+count_tree(struct net *net, struct rb_root *root,
+           const struct nf_conntrack_tuple *tuple,
+           const union nf_inet_addr *addr, const union nf_inet_addr *mask,
+           u8 family)
 {
+        struct xt_connlimit_rb *gc_nodes[CONNLIMIT_GC_MAX_NODES];
+        struct rb_node **rbnode, *parent;
+        struct xt_connlimit_rb *rbconn;
         struct xt_connlimit_conn *conn;
+        unsigned int gc_count;
+        bool no_gc = false;
+
+ restart:
+        gc_count = 0;
+        parent = NULL;
+        rbnode = &(root->rb_node);
+        while (*rbnode) {
+                int diff;
+                bool addit;
+
+                rbconn = container_of(*rbnode, struct xt_connlimit_rb, node);
+
+                parent = *rbnode;
+                diff = same_source_net(addr, mask, &rbconn->addr, family);
+                if (diff < 0) {
+                        rbnode = &((*rbnode)->rb_left);
+                } else if (diff > 0) {
+                        rbnode = &((*rbnode)->rb_right);
+                } else {
+                        /* same source network -> be counted! */
+                        unsigned int count;
+                        count = check_hlist(net, &rbconn->hhead, tuple, &addit);
+
+                        tree_nodes_free(root, gc_nodes, gc_count);
+                        if (!addit)
+                                return count;
+
+                        if (!add_hlist(&rbconn->hhead, tuple, addr))
+                                return 0; /* hotdrop */
+
+                        return count + 1;
+                }
+
+                if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
+                        continue;
+
+                /* only used for GC on hhead, retval and 'addit' ignored */
+                check_hlist(net, &rbconn->hhead, tuple, &addit);
+                if (hlist_empty(&rbconn->hhead))
+                        gc_nodes[gc_count++] = rbconn;
+        }
+
+        if (gc_count) {
+                no_gc = true;
+                tree_nodes_free(root, gc_nodes, gc_