netfilter: revised locking for x_tables

The x_tables are organized with a table structure and a per-cpu copies
of the counters and rules. On older kernels there was a reader/writer 
lock per table which was a performance bottleneck. In 2.6.30-rc, this
was converted to use RCU and the counters/rules which solved the performance
problems for do_table but made replacing rules much slower because of
the necessary RCU grace period.

This version uses a per-cpu set of spinlocks and counters to allow to
table processing to proceed without the cache thrashing of a global
reader lock and keeps the same performance for table updates.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 28 insertions, 25 deletions

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 509a95621f9f..150e5cf62f85 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -625,20 +625,6 @@ void xt_free_table_info(struct xt_table_info *info)
 }
 EXPORT_SYMBOL(xt_free_table_info);
 
-void xt_table_entry_swap_rcu(struct xt_table_info *oldinfo,
-			     struct xt_table_info *newinfo)
-{
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu) {
-		void *p = oldinfo->entries[cpu];
-		rcu_assign_pointer(oldinfo->entries[cpu], newinfo->entries[cpu]);
-		newinfo->entries[cpu] = p;
-	}
-
-}
-EXPORT_SYMBOL_GPL(xt_table_entry_swap_rcu);
-
 /* Find table by name, grabs mutex & ref.  Returns ERR_PTR() on error. */
 struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
 				    const char *name)
@@ -676,32 +662,43 @@ void xt_compat_unlock(u_int8_t af)
 EXPORT_SYMBOL_GPL(xt_compat_unlock);
 #endif
 
+DEFINE_PER_CPU(struct xt_info_lock, xt_info_locks);
+EXPORT_PER_CPU_SYMBOL_GPL(xt_info_locks);
+
+
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
 	      struct xt_table_info *newinfo,
 	      int *error)
 {
-	struct xt_table_info *oldinfo, *private;
+	struct xt_table_info *private;
 
 	/* Do the substitution. */
-	mutex_lock(&table->lock);
+	local_bh_disable();
 	private = table->private;
+
 	/* Check inside lock: is the old number correct? */
 	if (num_counters != private->number) {
 		duprintf("num_counters != table->private->number (%u/%u)\n",
 			 num_counters, private->number);
-		mutex_unlock(&table->lock);
+		local_bh_enable();
 		*error = -EAGAIN;
 		return NULL;
 	}
-	oldinfo = private;
-	rcu_assign_pointer(table->private, newinfo);
-	newinfo->initial_entries = oldinfo->initial_entries;
-	mutex_unlock(&table->lock);
 
-	synchronize_net();
-	return oldinfo;
+	table->private = newinfo;
+	newinfo->initial_entries = private->initial_entries;
+
+	/*
+	 * Even though table entries have now been swapped, other CPU's
+	 * may still be using the old entries. This is okay, because
+	 * resynchronization happens because of the locking done
+	 * during the get_counters() routine.
+	 */
+	local_bh_enable();
+
+	return private;
 }
 EXPORT_SYMBOL_GPL(xt_replace_table);
 
@@ -734,7 +731,6 @@ struct xt_table *xt_register_table(struct net *net, struct xt_table *table,
 
 	/* Simplifies replace_table code. */
 	table->private = bootstrap;
-	mutex_init(&table->lock);
 
 	if (!xt_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
@@ -1147,7 +1143,14 @@ static struct pernet_operations xt_net_ops = {
 
 static int __init xt_init(void)
 {
-	int i, rv;
+	unsigned int i;
+	int rv;
+
+	for_each_possible_cpu(i) {
+		struct xt_info_lock *lock = &per_cpu(xt_info_locks, i);
+		spin_lock_init(&lock->lock);
+		lock->readers = 0;
+	}
 
 	xt = kmalloc(sizeof(struct xt_af) * NFPROTO_NUMPROTO, GFP_KERNEL);
 	if (!xt)