o list.h: improve hlist

This changeset:

1. Implements hlist_add_after
2. uses prefetch in hlist_for_each, using a trick that ends up being
   equivalent to having the prefetch instruction in the first block
   of the hlist_for_each for block, the compiler optimizes the second
   "test" away, as its result is constant
3. implements hlist_for_each_entry and hlist_for_each_entry safe,
   using a struct hlist_node as iterator to avoid the extra branches a
   similar implementation to list_for_each_entry would have if used
   a typed iterator, but while avoiding having to have the explicit
   hlist_entry as in hlist_for_each.

4. Converts the hlist_for_each users that had explicit prefetches, i.e.
   removed the explicit prefetch

5. fix a harmless list_entry use in a hlist_for_each in inode.c
   

fs/dcache.c

@@ -984,8 +984,6 @@ struct dentry * __d_lookup(struct dentry * parent, struct qstr * name)
 		unsigned long move_count;
 		struct qstr * qstr;
 
-		prefetch(node->next);
-
 		smp_read_barrier_depends();
 		dentry = hlist_entry(node, struct dentry, d_hash);
 
@@ -1072,7 +1070,6 @@ int d_validate(struct dentry *dentry, struct dentry *dparent)
 	spin_lock(&dcache_lock);
 	base = d_hash(dparent, dentry->d_name.hash);
 	hlist_for_each(lhp,base) { 
-		prefetch(lhp->next);
 		/* read_barrier_depends() not required for d_hash list
 		 * as it is parsed under dcache_lock
 		 */

fs/inode.c

@@ -484,7 +484,6 @@ static struct inode * find_inode(struct super_block * sb, struct hlist_head *hea
 
 repeat:
 	hlist_for_each (node, head) { 
-		prefetch(node->next);
 		inode = hlist_entry(node, struct inode, i_hash);
 		if (inode->i_sb != sb)
 			continue;
@@ -510,8 +509,7 @@ static struct inode * find_inode_fast(struct super_block * sb, struct hlist_head
 
 repeat:
 	hlist_for_each (node, head) {
-		prefetch(node->next);
-		inode = list_entry(node, struct inode, i_hash);
+		inode = hlist_entry(node, struct inode, i_hash);
 		if (inode->i_ino != ino)
 			continue;
 		if (inode->i_sb != sb)

include/linux/list.h

@@ -443,17 +443,50 @@ static __inline__ void hlist_add_before(struct hlist_node *n, struct hlist_node
 	*(n->pprev) = n;
 }
 
+static __inline__ void hlist_add_after(struct hlist_node *n,
+				       struct hlist_node *next)
+{
+	next->next	= n->next;
+	*(next->pprev)	= n;
+	n->next		= next;
+}
+
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 /* Cannot easily do prefetch unfortunately */
 #define hlist_for_each(pos, head) \
-	for (pos = (head)->first; pos; \
+	for (pos = (head)->first; pos && ({ prefetch(pos->next); 1; }); \
 	     pos = pos->next) 
 
 #define hlist_for_each_safe(pos, n, head) \
 	for (pos = (head)->first; n = pos ? pos->next : 0, pos; \
 	     pos = n)
 
+/**
+ * hlist_for_each_entry	- iterate over list of given type
+ * @tpos:	the type * to use as a loop counter.
+ * @pos:	the &struct hlist_node to use as a loop counter.
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry(tpos, pos, head, member)			 \
+	for (pos = (head)->first;					 \
+	     pos && ({ prefetch(pos->next); 1;}) &&			 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = pos->next)
+/**
+ * hlist_for_each_entry_safe - iterate over list of given type safe against removal of list entry
+ * @tpos:	the type * to use as a loop counter.
+ * @pos:	the &struct hlist_node to use as a loop counter.
+ * @n:		another &struct hlist_node to use as temporary storage
+ * @head:	the head for your list.
+ * @member:	the name of the hlist_node within the struct.
+ */
+#define hlist_for_each_entry_safe(tpos, pos, n, head, member) 		 \
+	for (pos = (head)->first;					 \
+	     pos && ({ n = pos->next; 1; }) && 				 \
+		({ tpos = hlist_entry(pos, typeof(*tpos), member); 1;}); \
+	     pos = n)
 #else
 #warning "don't include kernel headers in userspace"
 #endif /* __KERNEL__ */