[NET]: Hashed spinlocks in net/ipv4/route.c

- Locking abstraction
- Spinlocks moved out of rt hash table : Less memory (50%) used by rt 
  hash table. it's a win even on UP.
- Sizing of spinlocks table depends on NR_CPUS

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 47 insertions, 19 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 12a1cf3..daf82f8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -54,6 +54,7 @@
  *		Marc Boucher	:	routing by fwmark
  *	Robert Olsson		:	Added rt_cache statistics
  *	Arnaldo C. Melo		:	Convert proc stuff to seq_file
+ *	Eric Dumazet		:	hashed spinlocks
  *
  *		This program is free software; you can redistribute it and/or
  *		modify it under the terms of the GNU General Public License
@@ -201,8 +202,37 @@ __u8 ip_tos2prio[16] = {
 
 struct rt_hash_bucket {
 	struct rtable	*chain;
-	spinlock_t	lock;
-} __attribute__((__aligned__(8)));
+};
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+/*
+ * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
+ * The size of this table is a power of two and depends on the number of CPUS.
+ */
+#if NR_CPUS >= 32
+#define RT_HASH_LOCK_SZ	4096
+#elif NR_CPUS >= 16
+#define RT_HASH_LOCK_SZ	2048
+#elif NR_CPUS >= 8
+#define RT_HASH_LOCK_SZ	1024
+#elif NR_CPUS >= 4
+#define RT_HASH_LOCK_SZ	512
+#else
+#define RT_HASH_LOCK_SZ	256
+#endif
+
+static spinlock_t	*rt_hash_locks;
+# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
+# define rt_hash_lock_init()	{ \
+		int i; \
+		rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, GFP_KERNEL); \
+		if (!rt_hash_locks) panic("IP: failed to allocate rt_hash_locks\n"); \
+		for (i = 0; i < RT_HASH_LOCK_SZ; i++) \
+			spin_lock_init(&rt_hash_locks[i]); \
+		}
+#else
+# define rt_hash_lock_addr(slot) NULL
+# define rt_hash_lock_init()
+#endif
 
 static struct rt_hash_bucket 	*rt_hash_table;
 static unsigned			rt_hash_mask;
@@ -587,7 +617,7 @@ static void rt_check_expire(unsigned long dummy)
 		i = (i + 1) & rt_hash_mask;
 		rthp = &rt_hash_table[i].chain;
 
-		spin_lock(&rt_hash_table[i].lock);
+		spin_lock(rt_hash_lock_addr(i));
 		while ((rth = *rthp) != NULL) {
 			if (rth->u.dst.expires) {
 				/* Entry is expired even if it is in use */
@@ -620,7 +650,7 @@ static void rt_check_expire(unsigned long dummy)
  			rt_free(rth);
 #endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
 		}
-		spin_unlock(&rt_hash_table[i].lock);
+		spin_unlock(rt_hash_lock_addr(i));
 
 		/* Fallback loop breaker. */
 		if (time_after(jiffies, now))
@@ -643,11 +673,11 @@ static void rt_run_flush(unsigned long dummy)
 	get_random_bytes(&rt_hash_rnd, 4);
 
 	for (i = rt_hash_mask; i >= 0; i--) {
-		spin_lock_bh(&rt_hash_table[i].lock);
+		spin_lock_bh(rt_hash_lock_addr(i));
 		rth = rt_hash_table[i].chain;
 		if (rth)
 			rt_hash_table[i].chain = NULL;
-		spin_unlock_bh(&rt_hash_table[i].lock);
+		spin_unlock_bh(rt_hash_lock_addr(i));
 
 		for (; rth; rth = next) {
 			next = rth->u.rt_next;
@@ -780,7 +810,7 @@ static int rt_garbage_collect(void)
 
 			k = (k + 1) & rt_hash_mask;
 			rthp = &rt_hash_table[k].chain;
-			spin_lock_bh(&rt_hash_table[k].lock);
+			spin_lock_bh(rt_hash_lock_addr(k));
 			while ((rth = *rthp) != NULL) {
 				if (!rt_may_expire(rth, tmo, expire)) {
 					tmo >>= 1;
@@ -812,7 +842,7 @@ static int rt_garbage_collect(void)
 				goal--;
 #endif /* CONFIG_IP_ROUTE_MULTIPATH_CACHED */
 			}
-			spin_unlock_bh(&rt_hash_table[k].lock);
+			spin_unlock_bh(rt_hash_lock_addr(k));
 			if (goal <= 0)
 				break;
 		}
@@ -882,7 +912,7 @@ restart:
 
 	rthp = &rt_hash_table[hash].chain;
 
-	spin_lock_bh(&rt_hash_table[hash].lock);
+	spin_lock_bh(rt_hash_lock_addr(hash));
 	while ((rth = *rthp) != NULL) {
 #ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
 		if (!(rth->u.dst.flags & DST_BALANCED) &&
@@ -908,7 +938,7 @@ restart:
 			rth->u.dst.__use++;
 			dst_hold(&rth->u.dst);
 			rth->u.dst.lastuse = now;
-			spin_unlock_bh(&rt_hash_table[hash].lock);
+			spin_unlock_bh(rt_hash_lock_addr(hash));
 
 			rt_drop(rt);
 			*rp = rth;
@@ -949,7 +979,7 @@ restart:
 	if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
 		int err = arp_bind_neighbour(&rt->u.dst);
 		if (err) {
-			spin_unlock_bh(&rt_hash_table[hash].lock);
+			spin_unlock_bh(rt_hash_lock_addr(hash));
 
 			if (err != -ENOBUFS) {
 				rt_drop(rt);
@@ -990,7 +1020,7 @@ restart:
 	}
 #endif
 	rt_hash_table[hash].chain = rt;
-	spin_unlock_bh(&rt_hash_table[hash].lock);
+	spin_unlock_bh(rt_hash_lock_addr(hash));
 	*rp = rt;
 	return 0;
 }
@@ -1058,7 +1088,7 @@ static void rt_del(unsigned hash, struct rtable *rt)
 {
 	struct rtable **rthp;
 
-	spin_lock_bh(&rt_hash_table[hash].lock);
+	spin_lock_bh(rt_hash_lock_addr(hash));
 	ip_rt_put(rt);
 	for (rthp = &rt_hash_table[hash].chain; *rthp;
 	     rthp = &(*rthp)->u.rt_next)
@@ -1067,7 +1097,7 @@ static void rt_del(unsigned hash, struct rtable *rt)
 			rt_free(rt);
 			break;
 		}
-	spin_unlock_bh(&rt_hash_table[hash].lock);
+	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
 void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
@@ -3073,7 +3103,7 @@ __setup("rhash_entries=", set_rhash_entries);
 
 int __init ip_rt_init(void)
 {
-	int i, order, goal, rc = 0;
+	int order, goal, rc = 0;
 
 	rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^
 			     (jiffies ^ (jiffies >> 7)));
@@ -3122,10 +3152,8 @@ int __init ip_rt_init(void)
 		/* NOTHING */;
 
 	rt_hash_mask--;
-	for (i = 0; i <= rt_hash_mask; i++) {
-		spin_lock_init(&rt_hash_table[i].lock);
-		rt_hash_table[i].chain = NULL;
-	}
+	memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
+	rt_hash_lock_init();
 
 	ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
 	ip_rt_max_size = (rt_hash_mask + 1) * 16;