1 files changed, 82 insertions, 53 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 80cf633d9f4a..726ea5e8180a 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 and rt_check_expire() fixes.
  *
  *              This program is free software; you can redistribute it and/or
  *              modify it under the terms of the GNU General Public License
@@ -70,6 +71,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/bootmem.h>
 #include <linux/string.h>
 #include <linux/socket.h>
 #include <linux/sockios.h>
@@ -201,8 +203,37 @@ __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;
@@ -575,19 +606,26 @@ static struct rtable **rt_remove_balanced_route(struct rtable **chain_head,
 /* This runs via a timer and thus is always in BH context. */
 static void rt_check_expire(unsigned long dummy)
 {
-        static int rover;
-        int i = rover, t;
+        static unsigned int rover;
+        unsigned int i = rover, goal;
         struct rtable *rth, **rthp;
         unsigned long now = jiffies;
-
-        for (t = ip_rt_gc_interval << rt_hash_log; t >= 0;
-             t -= ip_rt_gc_timeout) {
+        u64 mult;
+
+        mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
+        if (ip_rt_gc_timeout > 1)
+                do_div(mult, ip_rt_gc_timeout);
+        goal = (unsigned int)mult;
+        if (goal > rt_hash_mask) goal = rt_hash_mask + 1;
+        for (; goal > 0; goal--) {
                 unsigned long tmo = ip_rt_gc_timeout;
 
                 i = (i + 1) & rt_hash_mask;
                 rthp = &rt_hash_table[i].chain;
 
-                spin_lock(&rt_hash_table[i].lock);
+                if (*rthp == 0)
+                        continue;
+                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 */
@@ -620,14 +658,14 @@ 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))
                         break;
         }
         rover = i;
-        mod_timer(&rt_periodic_timer, now + ip_rt_gc_interval);
+        mod_timer(&rt_periodic_timer, jiffies + ip_rt_gc_interval);
 }
 
 /* This can run from both BH and non-BH contexts, the latter
@@ -643,11 +681,11 @@ 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 +818,7 @@ 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 +850,7 @@ 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 +920,7 @@ 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 +946,7 @@ 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 +987,7 @@ 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 +1028,7 @@ 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 +1096,7 @@ 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 +1105,7 @@ 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,
@@ -1909,7 +1947,7 @@ static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr,
          */
         if ((err = fib_lookup(&fl, &res)) != 0) {
                 if (!IN_DEV_FORWARD(in_dev))
-                        goto e_inval;
+                        goto e_hostunreach;
                 goto no_route;
         }
         free_res = 1;
@@ -1933,7 +1971,7 @@ static int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr,
         }
 
         if (!IN_DEV_FORWARD(in_dev))
-                goto e_inval;
+                goto e_hostunreach;
         if (res.type != RTN_UNICAST)
                 goto martian_destination;
 
@@ -2025,6 +2063,11 @@ martian_destination:
                         "%u.%u.%u.%u, dev %s\n",
                         NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
 #endif
+
+e_hostunreach:
+        err = -EHOSTUNREACH;
+        goto done;
+
 e_inval:
         err = -EINVAL;
         goto done;
@@ -3068,12 +3111,14 @@ __setup("rhash_entries=", set_rhash_entries);
 
 int __init ip_rt_init(void)
 {
-        int i, order, goal, rc = 0;
+        int rc = 0;
 
         rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^
                              (jiffies ^ (jiffies >> 7)));
 
 #ifdef CONFIG_NET_CLS_ROUTE
+        {
+        int order;
         for (order = 0;
              (PAGE_SIZE << order) < 256 * sizeof(struct ip_rt_acct) * NR_CPUS; order++)
                 /* NOTHING */;
@@ -3081,6 +3126,7 @@ int __init ip_rt_init(void)
         if (!ip_rt_acct)
                 panic("IP: failed to allocate ip_rt_acct\n");
         memset(ip_rt_acct, 0, PAGE_SIZE << order);
+        }
 #endif
 
         ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache",
@@ -3091,36 +3137,19 @@ int __init ip_rt_init(void)
         if (!ipv4_dst_ops.kmem_cachep)
                 panic("IP: failed to allocate ip_dst_cache\n");
 
-        goal = num_physpages >> (26 - PAGE_SHIFT);
-        if (rhash_entries)
-                goal = (rhash_entries * sizeof(struct rt_hash_bucket)) >> PAGE_SHIFT;
-        for (order = 0; (1UL << order) < goal; order++)
-                /* NOTHING */;
-
-        do {
-                rt_hash_mask = (1UL << order) * PAGE_SIZE /
-                        sizeof(struct rt_hash_bucket);
-                while (rt_hash_mask & (rt_hash_mask - 1))
-                        rt_hash_mask--;
-                rt_hash_table = (struct rt_hash_bucket *)
-                        __get_free_pages(GFP_ATOMIC, order);
-        } while (rt_hash_table == NULL && --order > 0);
-
-        if (!rt_hash_table)
-                panic("Failed to allocate IP route cache hash table\n");
-
-        printk(KERN_INFO "IP: routing cache hash table of %u buckets, %ldKbytes\n",
-               rt_hash_mask,
-               (long) (rt_hash_mask * sizeof(struct rt_hash_bucket)) / 1024);
-
-        for (rt_hash_log = 0; (1 << rt_hash_log) != rt_hash_mask; rt_hash_log++)
-                /* 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;
-        }
+        rt_hash_table = (struct rt_hash_bucket *)
+                alloc_large_system_hash("IP route cache",
+                                        sizeof(struct rt_hash_bucket),
+                                        rhash_entries,
+                                        (num_physpages >= 128 * 1024) ?
+                                                (27 - PAGE_SHIFT) :
+                                                (29 - PAGE_SHIFT),
+                                        HASH_HIGHMEM,
+                                        &rt_hash_log,
+                                        &rt_hash_mask,
+                                        0);
+        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;