---
 include/linux/gfp.h      |    4 ++
 include/linux/slub_def.h |    6 ++-
 mm/page_alloc.c          |   94 +++++++++++++++++++++++++++++++++++++++++++++++
 mm/slub.c                |    5 ++
 4 files changed, 107 insertions(+), 2 deletions(-)

Index: linux-2.6/include/linux/gfp.h
===================================================================
--- linux-2.6.orig/include/linux/gfp.h	2008-02-12 14:06:53.579840450 -0800
+++ linux-2.6/include/linux/gfp.h	2008-02-12 14:17:32.205168641 -0800
@@ -230,4 +230,8 @@ void page_alloc_init(void);
 static inline void drain_all_pages(void) {}
 static inline void drain_local_pages(void *dummy) {}
 
+struct page *fast_alloc(gfp_t gfp_mask);
+void fast_free(struct page *page);
+void flush_fast_pages(void);
+void *fast_alloc_addr(gfp_t gfp_mask);
 #endif /* __LINUX_GFP_H */
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c	2008-02-12 14:06:53.599840561 -0800
+++ linux-2.6/mm/page_alloc.c	2008-02-12 14:17:32.221168801 -0800
@@ -1303,6 +1303,7 @@ restart:
 	if (page)
 		goto got_pg;
 
+	flush_fast_pages();
 	/*
 	 * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
 	 * __GFP_NOWARN set) should not cause reclaim since the subsystem
@@ -4298,3 +4299,96 @@ __offline_isolated_pages(unsigned long s
 	spin_unlock_irqrestore(&zone->lock, flags);
 }
 #endif
+
+#if defined(CONFIG_FAST_CMPXCHG_LOCAL) && !defined(CONFIG_PREEMPT)
+#define PAGE_ALLOC_FASTPATH
+#endif
+
+DEFINE_PER_CPU(struct page *, fast_pages);
+
+void flush_fast_pages_cpu(void *dummy)
+{
+	struct page *page;
+
+	while (__get_cpu_var(fast_pages)) {
+		page = __get_cpu_var(fast_pages);
+#ifdef PAGE_ALLOC_FASTPATH
+		if (cmpxchg_local(&__get_cpu_var(fast_pages), page,
+				(struct page *)page->lru.next) != page)
+			continue;
+#else
+		__get_cpu_var(fast_pages) = (struct page *)page->lru.next;
+#endif
+		__free_page(page);
+	}
+}
+
+void flush_fast_pages(void)
+{
+	printk("flush_fast_pages\n");
+	on_each_cpu(flush_fast_pages_cpu, NULL, 0, 1);
+}
+
+struct page *fast_alloc(gfp_t mask)
+{
+	struct page *page;
+
+#ifdef PAGE_ALLOC_FASTPATH
+	do {
+		page = __get_cpu_var(fast_pages);
+		if (unlikely(!page))
+			goto slow;
+
+	} while (unlikely(cmpxchg_local(&__get_cpu_var(fast_pages),
+			page, (struct page *)page->lru.next) != page));
+#else
+	unsigned long flags;
+
+	local_irq_save(flags);
+	page = __get_cpu_var(fast_pages);
+	if (unlikely(!page)) {
+		local_irq_restore(flags);
+		goto slow;
+	}
+
+	__get_cpu_var(fast_pages) = (struct page *)page->lru.next;
+	local_irq_restore(flags);
+#endif
+	if (unlikely(mask & __GFP_ZERO))
+		memset(page_address(page), 0, PAGE_SIZE);
+	return page;
+
+slow:
+	return alloc_page(mask);
+}
+
+void fast_free(struct page *page)
+{
+#ifdef PAGE_ALLOC_FASTPAH
+	struct page *old;
+
+	do {
+		p = &__get_cpu_var(fast_pages);
+		old = *p;
+		page->lru.next = (void *)old;
+	} while (unlikely(cmpxchg_local(p, old, page) != old));
+#else
+	unsigned long flags;
+
+	local_irq_save(flags);
+	page->lru.next = (void *)__get_cpu_var(fast_pages);
+	__get_cpu_var(fast_pages) = page;
+	local_irq_restore(flags);
+#endif
+}
+
+void *fast_alloc_addr(gfp_t gfp_mask)
+{
+	struct page * page;
+
+	page = fast_alloc(gfp_mask);
+	if (likely(page))
+		return (void *) page_address(page);
+
+	return NULL;
+}
Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c	2008-02-12 14:06:48.903814196 -0800
+++ linux-2.6/mm/slub.c	2008-02-12 14:17:32.221168801 -0800
@@ -2750,7 +2750,10 @@ void kfree(const void *x)
 
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
-		put_page(page);
+		if (unlikely(PageCompound(page)))
+			put_page(page);
+		else
+			fast_free(page);
 		return;
 	}
 	slab_free(page->slab, page, object, __builtin_return_address(0));
Index: linux-2.6/include/linux/slub_def.h
===================================================================
--- linux-2.6.orig/include/linux/slub_def.h	2008-02-12 14:06:48.887814073 -0800
+++ linux-2.6/include/linux/slub_def.h	2008-02-12 14:17:32.245169048 -0800
@@ -190,7 +190,11 @@ void *__kmalloc(size_t size, gfp_t flags
 
 static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
 {
-	return (void *)__get_free_pages(flags | __GFP_COMP, get_order(size));
+	if (size <= PAGE_SIZE)
+		return fast_alloc_addr(flags);
+	else
+		return (void *)__get_free_pages(flags | __GFP_COMP,
+							get_order(size));
 }
 
 static __always_inline void *kmalloc(size_t size, gfp_t flags)