fib_trie: Remove checks for index >= tnode_child_length from tnode_get_child

For some reason the compiler doesn't seem to understand that when we are in
a loop that runs from tnode_child_length - 1 to 0 we don't expect the value
of tn->bits to change.  As such every call to tnode_get_child was rerunning
tnode_chile_length which ended up consuming quite a bit of space in the
resultant assembly code.

I have gone though and verified that in all cases where tnode_get_child
is used we are either winding though a fixed loop from tnode_child_length -
1 to 0, or are in a fastpath case where we are verifying the value by
either checking for any remaining bits after shifting index by bits and
testing for leaf, or by using tnode_child_length.

size net/ipv4/fib_trie.o
Before:
   text	   data	    bss	    dec	    hex	filename
  15506	    376	      8	  15890	   3e12	net/ipv4/fib_trie.o

After:
   text	   data	    bss	    dec	    hex	filename
  14827	    376	      8	  15211	   3b6b	net/ipv4/fib_trie.o

Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 0c88df0..87fc9a4 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -186,8 +186,6 @@
 static inline struct tnode *tnode_get_child(const struct tnode *tn,
 					    unsigned long i)
 {
-	BUG_ON(i >= tnode_child_length(tn));
-
 	return rtnl_dereference(tn->child[i]);
 }
 
@@ -195,8 +193,6 @@
 static inline struct tnode *tnode_get_child_rcu(const struct tnode *tn,
 						unsigned long i)
 {
-	BUG_ON(i >= tnode_child_length(tn));
-
 	return rcu_dereference_rtnl(tn->child[i]);
 }
 
@@ -371,7 +367,7 @@
  */
 static void put_child(struct tnode *tn, unsigned long i, struct tnode *n)
 {
-	struct tnode *chi = rtnl_dereference(tn->child[i]);
+	struct tnode *chi = tnode_get_child(tn, i);
 	int isfull, wasfull;
 
 	BUG_ON(i >= tnode_child_length(tn));
@@ -867,7 +863,7 @@
 		if (IS_LEAF(n))
 			break;
 
-		n = rcu_dereference_rtnl(n->child[index]);
+		n = tnode_get_child_rcu(n, index);
 	}
 
 	return n;
@@ -934,7 +930,7 @@
 		}
 
 		tp = n;
-		n = rcu_dereference_rtnl(n->child[index]);
+		n = tnode_get_child_rcu(n, index);
 	}
 
 	l = leaf_new(key);
@@ -1215,7 +1211,7 @@
 			cindex = index;
 		}
 
-		n = rcu_dereference(n->child[index]);
+		n = tnode_get_child_rcu(n, index);
 		if (unlikely(!n))
 			goto backtrace;
 	}
@@ -1835,7 +1831,7 @@
 			if (n->bits < MAX_STAT_DEPTH)
 				s->nodesizes[n->bits]++;
 
-			for (i = 0; i < tnode_child_length(n); i++) {
+			for (i = tnode_child_length(n); i--;) {
 				if (!rcu_access_pointer(n->child[i]))
 					s->nullpointers++;
 			}