Merge branch 'topic/ctxfi' into for-linus

[pandora-kernel.git] / net / ipv4 / route.c

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c40debe..28205e5 100644 (file)
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -784,8 +784,8 @@ static void rt_check_expire(void)
 {
        static unsigned int rover;
        unsigned int i = rover, goal;
-       struct rtable *rth, **rthp;
-       unsigned long length = 0, samples = 0;
+       struct rtable *rth, *aux, **rthp;
+       unsigned long samples = 0;
        unsigned long sum = 0, sum2 = 0;
        u64 mult;
 
@@ -795,9 +795,9 @@ static void rt_check_expire(void)
        goal = (unsigned int)mult;
        if (goal > rt_hash_mask)
                goal = rt_hash_mask + 1;
-       length = 0;
        for (; goal > 0; goal--) {
                unsigned long tmo = ip_rt_gc_timeout;
+               unsigned long length;
 
                i = (i + 1) & rt_hash_mask;
                rthp = &rt_hash_table[i].chain;
@@ -809,8 +809,10 @@ static void rt_check_expire(void)
 
                if (*rthp == NULL)
                        continue;
+               length = 0;
                spin_lock_bh(rt_hash_lock_addr(i));
                while ((rth = *rthp) != NULL) {
+                       prefetch(rth->u.dst.rt_next);
                        if (rt_is_expired(rth)) {
                                *rthp = rth->u.dst.rt_next;
                                rt_free(rth);
@@ -819,33 +821,30 @@ static void rt_check_expire(void)
                        if (rth->u.dst.expires) {
                                /* Entry is expired even if it is in use */
                                if (time_before_eq(jiffies, rth->u.dst.expires)) {
+nofree:
                                        tmo >>= 1;
                                        rthp = &rth->u.dst.rt_next;
                                        /*
-                                        * Only bump our length if the hash
-                                        * inputs on entries n and n+1 are not
-                                        * the same, we only count entries on
+                                        * We only count entries on
                                         * a chain with equal hash inputs once
                                         * so that entries for different QOS
                                         * levels, and other non-hash input
                                         * attributes don't unfairly skew
                                         * the length computation
                                         */
-                                       if ((*rthp == NULL) ||
-                                           !compare_hash_inputs(&(*rthp)->fl,
-                                                                &rth->fl))
-                                               length += ONE;
+                                       for (aux = rt_hash_table[i].chain;;) {
+                                               if (aux == rth) {
+                                                       length += ONE;
+                                                       break;
+                                               }
+                                               if (compare_hash_inputs(&aux->fl, &rth->fl))
+                                                       break;
+                                               aux = aux->u.dst.rt_next;
+                                       }
                                        continue;
                                }
-                       } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
-                               tmo >>= 1;
-                               rthp = &rth->u.dst.rt_next;
-                               if ((*rthp == NULL) ||
-                                   !compare_hash_inputs(&(*rthp)->fl,
-                                                        &rth->fl))
-                                       length += ONE;
-                               continue;
-                       }
+                       } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+                               goto nofree;
 
                        /* Cleanup aged off entries. */
                        *rthp = rth->u.dst.rt_next;
@@ -1068,7 +1067,6 @@ out:      return 0;
 static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
 {
        struct rtable   *rth, **rthp;
-       struct rtable   *rthi;
        unsigned long   now;
        struct rtable *cand, **candp;
        u32             min_score;
@@ -1088,7 +1086,6 @@ restart:
        }
 
        rthp = &rt_hash_table[hash].chain;
-       rthi = NULL;
 
        spin_lock_bh(rt_hash_lock_addr(hash));
        while ((rth = *rthp) != NULL) {
@@ -1134,17 +1131,6 @@ restart:
                chain_length++;
 
                rthp = &rth->u.dst.rt_next;
-
-               /*
-                * check to see if the next entry in the chain
-                * contains the same hash input values as rt.  If it does
-                * This is where we will insert into the list, instead of
-                * at the head.  This groups entries that differ by aspects not
-                * relvant to the hash function together, which we use to adjust
-                * our chain length
-                */
-               if (*rthp && compare_hash_inputs(&(*rthp)->fl, &rt->fl))
-                       rthi = rth;
        }
 
        if (cand) {
@@ -1205,10 +1191,7 @@ restart:
                }
        }
 
-       if (rthi)
-               rt->u.dst.rt_next = rthi->u.dst.rt_next;
-       else
-               rt->u.dst.rt_next = rt_hash_table[hash].chain;
+       rt->u.dst.rt_next = rt_hash_table[hash].chain;
 
 #if RT_CACHE_DEBUG >= 2
        if (rt->u.dst.rt_next) {
@@ -1224,10 +1207,7 @@ restart:
         * previous writes to rt are comitted to memory
         * before making rt visible to other CPUS.
         */
-       if (rthi)
-               rcu_assign_pointer(rthi->u.dst.rt_next, rt);
-       else
-               rcu_assign_pointer(rt_hash_table[hash].chain, rt);
+       rcu_assign_pointer(rt_hash_table[hash].chain, rt);
 
        spin_unlock_bh(rt_hash_lock_addr(hash));
        *rp = rt;
@@ -3397,7 +3377,7 @@ int __init ip_rt_init(void)
                                        0,
                                        &rt_hash_log,
                                        &rt_hash_mask,
-                                       0);
+                                       rhash_entries ? 0 : 512 * 1024);
        memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
        rt_hash_lock_init();