Merge branch 'linux-2.6'

23 files changed, 4100 insertions, 241 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 7942b333e46..1ac718f636e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -163,3 +163,8 @@ config ZONE_DMA_FLAG
 	default "0" if !ZONE_DMA
 	default "1"
 
+config NR_QUICK
+	int
+	depends on QUICKLIST
+	default "1"
+
diff --git a/mm/Makefile b/mm/Makefile
index f3c077eb0b8..a9148ea329a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -25,7 +25,10 @@ obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
 obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
 obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_SLAB) += slab.o
+obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_SMP) += allocpercpu.o
+obj-$(CONFIG_QUICKLIST) += quicklist.o
+
diff --git a/mm/filemap.c b/mm/filemap.c
index 5dfc093ceb3..5631d6b2a62 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -868,6 +868,7 @@ void do_generic_mapping_read(struct address_space *mapping,
 	unsigned long last_index;
 	unsigned long next_index;
 	unsigned long prev_index;
+	unsigned int prev_offset;
 	loff_t isize;
 	struct page *cached_page;
 	int error;
@@ -876,7 +877,8 @@ void do_generic_mapping_read(struct address_space *mapping,
 	cached_page = NULL;
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
-	prev_index = ra.prev_page;
+	prev_index = ra.prev_index;
+	prev_offset = ra.prev_offset;
 	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
 	offset = *ppos & ~PAGE_CACHE_MASK;
 
@@ -924,10 +926,10 @@ page_ok:
 			flush_dcache_page(page);
 
 		/*
-		 * When (part of) the same page is read multiple times
-		 * in succession, only mark it as accessed the first time.
+		 * When a sequential read accesses a page several times,
+		 * only mark it as accessed the first time.
 		 */
-		if (prev_index != index)
+		if (prev_index != index || offset != prev_offset)
 			mark_page_accessed(page);
 		prev_index = index;
 
@@ -945,6 +947,8 @@ page_ok:
 		offset += ret;
 		index += offset >> PAGE_CACHE_SHIFT;
 		offset &= ~PAGE_CACHE_MASK;
+		prev_offset = offset;
+		ra.prev_offset = offset;
 
 		page_cache_release(page);
 		if (ret == nr && desc->count)
@@ -1446,30 +1450,6 @@ page_not_uptodate:
 		majmin = VM_FAULT_MAJOR;
 		count_vm_event(PGMAJFAULT);
 	}
-	lock_page(page);
-
-	/* Did it get unhashed while we waited for it? */
-	if (!page->mapping) {
-		unlock_page(page);
-		page_cache_release(page);
-		goto retry_all;
-	}
-
-	/* Did somebody else get it up-to-date? */
-	if (PageUptodate(page)) {
-		unlock_page(page);
-		goto success;
-	}
-
-	error = mapping->a_ops->readpage(file, page);
-	if (!error) {
-		wait_on_page_locked(page);
-		if (PageUptodate(page))
-			goto success;
-	} else if (error == AOP_TRUNCATED_PAGE) {
-		page_cache_release(page);
-		goto retry_find;
-	}
 
 	/*
 	 * Umm, take care of errors if the page isn't up-to-date.
@@ -1726,7 +1706,7 @@ int generic_file_readonly_mmap(struct file * file, struct vm_area_struct * vma)
 EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
-static inline struct page *__read_cache_page(struct address_space *mapping,
+static struct page *__read_cache_page(struct address_space *mapping,
 				unsigned long index,
 				int (*filler)(void *,struct page*),
 				void *data)
@@ -1763,17 +1743,11 @@ repeat:
 	return page;
 }
 
-/**
- * read_cache_page - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	destination for read data
- *
- * Read into the page cache. If a page already exists,
- * and PageUptodate() is not set, try to fill the page.
+/*
+ * Same as read_cache_page, but don't wait for page to become unlocked
+ * after submitting it to the filler.
  */
-struct page *read_cache_page(struct address_space *mapping,
+struct page *read_cache_page_async(struct address_space *mapping,
 				unsigned long index,
 				int (*filler)(void *,struct page*),
 				void *data)
@@ -1805,6 +1779,39 @@ retry:
 		page = ERR_PTR(err);
 	}
  out:
+	mark_page_accessed(page);
+	return page;
+}
+EXPORT_SYMBOL(read_cache_page_async);
+
+/**
+ * read_cache_page - read into page cache, fill it if needed
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @filler:	function to perform the read
+ * @data:	destination for read data
+ *
+ * Read into the page cache. If a page already exists, and PageUptodate() is
+ * not set, try to fill the page then wait for it to become unlocked.
+ *
+ * If the page does not get brought uptodate, return -EIO.
+ */
+struct page *read_cache_page(struct address_space *mapping,
+				unsigned long index,
+				int (*filler)(void *,struct page*),
+				void *data)
+{
+	struct page *page;
+
+	page = read_cache_page_async(mapping, index, filler, data);
+	if (IS_ERR(page))
+		goto out;
+	wait_on_page_locked(page);
+	if (!PageUptodate(page)) {
+		page_cache_release(page);
+		page = ERR_PTR(-EIO);
+	}
+ out:
 	return page;
 }
 EXPORT_SYMBOL(read_cache_page);
diff --git a/mm/highmem.c b/mm/highmem.c
index 51e1c1995fe..be8f8d36a8b 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -99,6 +99,15 @@ static void flush_all_zero_pkmaps(void)
 	flush_tlb_kernel_range(PKMAP_ADDR(0), PKMAP_ADDR(LAST_PKMAP));
 }
 
+/* Flush all unused kmap mappings in order to remove stray
+   mappings. */
+void kmap_flush_unused(void)
+{
+	spin_lock(&kmap_lock);
+	flush_all_zero_pkmaps();
+	spin_unlock(&kmap_lock);
+}
+
 static inline unsigned long map_new_virtual(struct page *page)
 {
 	unsigned long vaddr;
diff --git a/mm/internal.h b/mm/internal.h
index d527b80b292..a3110c02aea 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -24,7 +24,7 @@ static inline void set_page_count(struct page *page, int v)
  */
 static inline void set_page_refcounted(struct page *page)
 {
-	VM_BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page);
+	VM_BUG_ON(PageCompound(page) && PageTail(page));
 	VM_BUG_ON(atomic_read(&page->_count));
 	set_page_count(page, 1);
 }
diff --git a/mm/madvise.c b/mm/madvise.c
index 603c5257ed6..e75096b5a6d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -12,6 +12,24 @@
 #include <linux/hugetlb.h>
 
 /*
+ * Any behaviour which results in changes to the vma->vm_flags needs to
+ * take mmap_sem for writing. Others, which simply traverse vmas, need
+ * to only take it for reading.
+ */
+static int madvise_need_mmap_write(int behavior)
+{
+	switch (behavior) {
+	case MADV_REMOVE:
+	case MADV_WILLNEED:
+	case MADV_DONTNEED:
+		return 0;
+	default:
+		/* be safe, default to 1. list exceptions explicitly */
+		return 1;
+	}
+}
+
+/*
  * We can potentially split a vm area into separate
  * areas, each area with its own behavior.
  */
@@ -183,9 +201,9 @@ static long madvise_remove(struct vm_area_struct *vma,
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
 	/* vmtruncate_range needs to take i_mutex and i_alloc_sem */
-	up_write(&current->mm->mmap_sem);
+	up_read(&current->mm->mmap_sem);
 	error = vmtruncate_range(mapping->host, offset, endoff);
-	down_write(&current->mm->mmap_sem);
+	down_read(&current->mm->mmap_sem);
 	return error;
 }
 
@@ -270,7 +288,10 @@ asmlinkage long sys_madvise(unsigned long start, size_t len_in, int behavior)
 	int error = -EINVAL;
 	size_t len;
 
-	down_write(&current->mm->mmap_sem);
+	if (madvise_need_mmap_write(behavior))
+		down_write(&current->mm->mmap_sem);
+	else
+		down_read(&current->mm->mmap_sem);
 
 	if (start & ~PAGE_MASK)
 		goto out;
@@ -332,6 +353,10 @@ asmlinkage long sys_madvise(unsigned long start, size_t len_in, int behavior)
 			vma = find_vma(current->mm, start);
 	}
 out:
-	up_write(&current->mm->mmap_sem);
+	if (madvise_need_mmap_write(behavior))
+		up_write(&current->mm->mmap_sem);
+	else
+		up_read(&current->mm->mmap_sem);
+
 	return error;
 }
diff --git a/mm/memory.c b/mm/memory.c
index e7066e71dfa..1d647ab0ee7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1448,6 +1448,100 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(remap_pfn_range);
 
+static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
+				     unsigned long addr, unsigned long end,
+				     pte_fn_t fn, void *data)
+{
+	pte_t *pte;
+	int err;
+	struct page *pmd_page;
+	spinlock_t *uninitialized_var(ptl);
+
+	pte = (mm == &init_mm) ?
+		pte_alloc_kernel(pmd, addr) :
+		pte_alloc_map_lock(mm, pmd, addr, &ptl);
+	if (!pte)
+		return -ENOMEM;
+
+	BUG_ON(pmd_huge(*pmd));
+
+	pmd_page = pmd_page(*pmd);
+
+	do {
+		err = fn(pte, pmd_page, addr, data);
+		if (err)
+			break;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+
+	if (mm != &init_mm)
+		pte_unmap_unlock(pte-1, ptl);
+	return err;
+}
+
+static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
+				     unsigned long addr, unsigned long end,
+				     pte_fn_t fn, void *data)
+{
+	pmd_t *pmd;
+	unsigned long next;
+	int err;
+
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return -ENOMEM;
+	do {
+		next = pmd_addr_end(addr, end);
+		err = apply_to_pte_range(mm, pmd, addr, next, fn, data);
+		if (err)
+			break;
+	} while (pmd++, addr = next, addr != end);
+	return err;
+}
+
+static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+				     unsigned long addr, unsigned long end,
+				     pte_fn_t fn, void *data)
+{
+	pud_t *pud;
+	unsigned long next;
+	int err;
+
+	pud = pud_alloc(mm, pgd, addr);
+	if (!pud)
+		return -ENOMEM;
+	do {
+		next = pud_addr_end(addr, end);
+		err = apply_to_pmd_range(mm, pud, addr, next, fn, data);
+		if (err)
+			break;
+	} while (pud++, addr = next, addr != end);
+	return err;
+}
+
+/*
+ * Scan a region of virtual memory, filling in page tables as necessary
+ * and calling a provided function on each leaf page table.
+ */
+int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
+			unsigned long size, pte_fn_t fn, void *data)
+{
+	pgd_t *pgd;
+	unsigned long next;
+	unsigned long end = addr + size;
+	int err;
+
+	BUG_ON(addr >= end);
+	pgd = pgd_offset(mm, addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+		if (err)
+			break;
+	} while (pgd++, addr = next, addr != end);
+	return err;
+}
+EXPORT_SYMBOL_GPL(apply_to_page_range);
+
 /*
  * handle_pte_fault chooses page fault handler according to an entry
  * which was read non-atomically.  Before making any commitment, on
@@ -2539,12 +2633,6 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
-#else
-/* Workaround for gcc 2.96 */
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
-{
-	return 0;
-}
 #endif /* __PAGETABLE_PUD_FOLDED */
 
 #ifndef __PAGETABLE_PMD_FOLDED
@@ -2573,12 +2661,6 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
-#else
-/* Workaround for gcc 2.96 */
-int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
-{
-	return 0;
-}
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 int make_pages_present(unsigned long addr, unsigned long end)
diff --git a/mm/mmap.c b/mm/mmap.c
index 84f997da78d..52646d61ff6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -29,6 +29,7 @@
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
 #include <asm/tlb.h>
+#include <asm/mmu_context.h>
 
 #ifndef arch_mmap_check
 #define arch_mmap_check(addr, len, flags)	(0)
@@ -1199,6 +1200,9 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
+	if (flags & MAP_FIXED)
+		return addr;
+
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
 		vma = find_vma(mm, addr);
@@ -1272,6 +1276,9 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
+	if (flags & MAP_FIXED)
+		return addr;
+
 	/* requesting a specific address */
 	if (addr) {
 		addr = PAGE_ALIGN(addr);
@@ -1360,38 +1367,21 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 		unsigned long pgoff, unsigned long flags)
 {
 	unsigned long ret;
-
-	if (!(flags & MAP_FIXED)) {
-		unsigned long (*get_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
-
-		get_area = current->mm->get_unmapped_area;
-		if (file && file->f_op && file->f_op->get_unmapped_area)
-			get_area = file->f_op->get_unmapped_area;
-		addr = get_area(file, addr, len, pgoff, flags);
-		if (IS_ERR_VALUE(addr))
-			return addr;
-	}
+	unsigned long (*get_area)(struct file *, unsigned long,
+				  unsigned long, unsigned long, unsigned long);
+
+	get_area = current->mm->get_unmapped_area;
+	if (file && file->f_op && file->f_op->get_unmapped_area)
+		get_area = file->f_op->get_unmapped_area;
+	addr = get_area(file, addr, len, pgoff, flags);
+	if (IS_ERR_VALUE(addr))
+		return addr;
 
 	if (addr > TASK_SIZE - len)
 		return -ENOMEM;
 	if (addr & ~PAGE_MASK)
 		return -EINVAL;
-	if (file && is_file_hugepages(file))  {
-		/*
-		 * Check if the given range is hugepage aligned, and
-		 * can be made suitable for hugepages.
-		 */
-		ret = prepare_hugepage_range(addr, len, pgoff);
-	} else {
-		/*
-		 * Ensure that a normal request is not falling in a
-		 * reserved hugepage range.  For some archs like IA-64,
-		 * there is a separate region for hugepages.
-		 */
-		ret = is_hugepage_only_range(current->mm, addr, len);
-	}
-	if (ret)
-		return -EINVAL;
+
 	return addr;
 }
 
@@ -1979,6 +1969,9 @@ void exit_mmap(struct mm_struct *mm)
 	unsigned long nr_accounted = 0;
 	unsigned long end;
 
+	/* mm's last user has gone, and its about to be pulled down */
+	arch_exit_mmap(mm);
+
 	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb = tlb_gather_mmu(mm, 1);
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 3791edfffee..a7001410ab1 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -147,9 +147,11 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	 * Adjust the score by oomkilladj.
 	 */
 	if (p->oomkilladj) {
-		if (p->oomkilladj > 0)
+		if (p->oomkilladj > 0) {
+			if (!points)
+				points = 1;
 			points <<= p->oomkilladj;
-		else
+		} else
 			points >>= -(p->oomkilladj);
 	}
 
@@ -397,6 +399,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 	struct task_struct *p;
 	unsigned long points = 0;
 	unsigned long freed = 0;
+	int constraint;
 
 	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
 	if (freed > 0)
@@ -411,14 +414,18 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 		show_mem();
 	}
 
-	cpuset_lock();
-	read_lock(&tasklist_lock);
+	if (sysctl_panic_on_oom == 2)
+		panic("out of memory. Compulsory panic_on_oom is selected.\n");
 
 	/*
 	 * Check if there were limitations on the allocation (only relevant for
 	 * NUMA) that may require different handling.
 	 */
-	switch (constrained_alloc(zonelist, gfp_mask)) {
+	constraint = constrained_alloc(zonelist, gfp_mask);
+	cpuset_lock();
+	read_lock(&tasklist_lock);
+
+	switch (constraint) {
 	case CONSTRAINT_MEMORY_POLICY:
 		oom_kill_process(current, points,
 				"No available memory (MPOL_BIND)");
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a794945fd19..029dfad5a23 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -119,6 +119,44 @@ static void background_writeout(unsigned long _min_pages);
  * We make sure that the background writeout level is below the adjusted
  * clamping level.
  */
+
+static unsigned long highmem_dirtyable_memory(unsigned long total)
+{
+#ifdef CONFIG_HIGHMEM
+	int node;
+	unsigned long x = 0;
+
+	for_each_online_node(node) {
+		struct zone *z =
+			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
+
+		x += zone_page_state(z, NR_FREE_PAGES)
+			+ zone_page_state(z, NR_INACTIVE)
+			+ zone_page_state(z, NR_ACTIVE);
+	}
+	/*
+	 * Make sure that the number of highmem pages is never larger
+	 * than the number of the total dirtyable memory. This can only
+	 * occur in very strange VM situations but we want to make sure
+	 * that this does not occur.
+	 */
+	return min(x, total);
+#else
+	return 0;
+#endif
+}
+
+static unsigned long determine_dirtyable_memory(void)
+{
+	unsigned long x;
+
+	x = global_page_state(NR_FREE_PAGES)
+		+ global_page_state(NR_INACTIVE)
+		+ global_page_state(NR_ACTIVE);
+	x -= highmem_dirtyable_memory(x);
+	return x + 1;	/* Ensure that we never return 0 */
+}
+
 static void
 get_dirty_limits(long *pbackground, long *pdirty,
 					struct address_space *mapping)
@@ -128,20 +166,12 @@ get_dirty_limits(long *pbackground, long *pdirty,
 	int unmapped_ratio;
 	long background;
 	long dirty;
-	unsigned long available_memory = vm_total_pages;
+	unsigned long available_memory = determine_dirtyable_memory();
 	struct task_struct *tsk;
 
-#ifdef CONFIG_HIGHMEM
-	/*
-	 * We always exclude high memory from our count.
-	 */
-	available_memory -= totalhigh_pages;
-#endif
-
-
 	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES)) * 100) /
-					vm_total_pages;
+					available_memory;
 
 	dirty_ratio = vm_dirty_ratio;
 	if (dirty_ratio > unmapped_ratio / 2)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 353ce9039a8..59164313167 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -156,10 +156,8 @@ static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 
 static int page_is_consistent(struct zone *zone, struct page *page)
 {
-#ifdef CONFIG_HOLES_IN_ZONE
-	if (!pfn_valid(page_to_pfn(page)))
+	if (!pfn_valid_within(page_to_pfn(page)))
 		return 0;
-#endif
 	if (zone != page_zone(page))
 		return 0;
 
@@ -227,7 +225,7 @@ static void bad_page(struct page *page)
 
 static void free_compound_page(struct page *page)
 {
-	__free_pages_ok(page, (unsigned long)page[1].lru.prev);
+	__free_pages_ok(page, compound_order(page));
 }
 
 static void prep_compound_page(struct page *page, unsigned long order)
@@ -236,12 +234,13 @@ static void prep_compound_page(struct page *page, unsigned long order)
 	int nr_pages = 1 << order;
 
 	set_compound_page_dtor(page, free_compound_page);
-	page[1].lru.prev = (void *)order;
-	for (i = 0; i < nr_pages; i++) {
+	set_compound_order(page, order);
+	__SetPageHead(page);
+	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 
-		__SetPageCompound(p);
-		set_page_private(p, (unsigned long)page);
+		__SetPageTail(p);
+		p->first_page = page;
 	}
 }
 
@@ -250,16 +249,19 @@ static void destroy_compound_page(struct page *page, unsigned long order)
 	int i;
 	int nr_pages = 1 << order;
 
-	if (unlikely((unsigned long)page[1].lru.prev != order))
+	if (unlikely(compound_order(page) != order))
 		bad_page(page);
 
-	for (i = 0; i < nr_pages; i++) {
+	if (unlikely(!PageHead(page)))
+			bad_page(page);
+	__ClearPageHead(page);
+	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 
-		if (unlikely(!PageCompound(p) |
-				(page_private(p) != (unsigned long)page)))
+		if (unlikely(!PageTail(p) |
+				(p->first_page != page)))
 			bad_page(page);
-		__ClearPageCompound(p);
+		__ClearPageTail(p);
 	}
 }
 
@@ -346,10 +348,8 @@ __find_combined_index(unsigned long page_idx, unsigned int order)
 static inline int page_is_buddy(struct page *page, struct page *buddy,
 								int order)
 {
-#ifdef CONFIG_HOLES_IN_ZONE
-	if (!pfn_valid(page_to_pfn(buddy)))
+	if (!pfn_valid_within(page_to_pfn(buddy)))
 		return 0;
-#endif
 
 	if (page_zone_id(page) != page_zone_id(buddy))
 		return 0;
@@ -433,13 +433,18 @@ static inline int free_pages_check(struct page *page)
 			1 << PG_private |
 			1 << PG_locked	|
 			1 << PG_active	|
-			1 << PG_reclaim	|
 			1 << PG_slab	|
 			1 << PG_swapcache |
 			1 << PG_writeback |
 			1 << PG_reserved |
 			1 << PG_buddy ))))
 		bad_page(page);
+	/*
+	 * PageReclaim == PageTail. It is only an error
+	 * for PageReclaim to be set if PageCompound is clear.
+	 */
+	if (unlikely(!PageCompound(page) && PageReclaim(page)))
+		bad_page(page);
 	if (PageDirty(page))
 		__ClearPageDirty(page);
 	/*
@@ -665,7 +670,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 }
 
 #if MAX_NUMNODES > 1
-int nr_node_ids __read_mostly;
+int nr_node_ids __read_mostly = MAX_NUMNODES;
 EXPORT_SYMBOL(nr_node_ids);
 
 /*
@@ -770,8 +775,8 @@ void mark_free_pages(struct zone *zone)
 		if (pfn_valid(pfn)) {
 			struct page *page = pfn_to_page(pfn);
 
-			if (!PageNosave(page))
-				ClearPageNosaveFree(page);
+			if (!swsusp_page_is_forbidden(page))
+				swsusp_unset_page_free(page);
 		}
 
 	for (order = MAX_ORDER - 1; order >= 0; --order)
@@ -780,7 +785,7 @@ void mark_free_pages(struct zone *zone)
 
 			pfn = page_to_pfn(list_entry(curr, struct page, lru));
 			for (i = 0; i < (1UL << order); i++)
-				SetPageNosaveFree(pfn_to_page(pfn + i));
+				swsusp_set_page_free(pfn_to_page(pfn + i));
 		}
 
 	spin_unlock_irqrestore(&zone->lock, flags);
@@ -3203,7 +3208,8 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
 	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
 {
 	proc_dointvec(table, write, file, buffer, length, ppos);
-	setup_per_zone_pages_min();
+	if (write)
+		setup_per_zone_pages_min();
 	return 0;
 }
 
diff --git a/mm/quicklist.c b/mm/quicklist.c
new file mode 100644
index 00000000000..ae8189c2799
--- /dev/null
+++ b/mm/quicklist.c
@@ -0,0 +1,88 @@
+/*
+ * Quicklist support.
+ *
+ * Quicklists are light weight lists of pages that have a defined state
+ * on alloc and free. Pages must be in the quicklist specific defined state
+ * (zero by default) when the page is freed. It seems that the initial idea
+ * for such lists first came from Dave Miller and then various other people
+ * improved on it.
+ *
+ * Copyright (C) 2007 SGI,
+ * 	Christoph Lameter <clameter@sgi.com>
+ * 		Generalized, added support for multiple lists and
+ * 		constructors / destructors.
+ */
+#include <linux/kernel.h>
+
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/quicklist.h>
+
+DEFINE_PER_CPU(struct quicklist, quicklist)[CONFIG_NR_QUICK];
+
+#define FRACTION_OF_NODE_MEM	16
+
+static unsigned long max_pages(unsigned long min_pages)
+{
+	unsigned long node_free_pages, max;
+
+	node_free_pages = node_page_state(numa_node_id(),
+			NR_FREE_PAGES);
+	max = node_free_pages / FRACTION_OF_NODE_MEM;
+	return max(max, min_pages);
+}
+
+static long min_pages_to_free(struct quicklist *q,
+	unsigned long min_pages, long max_free)
+{
+	long pages_to_free;
+
+	pages_to_free = q->nr_pages - max_pages(min_pages);
+
+	return min(pages_to_free, max_free);
+}
+
+/*
+ * Trim down the number of pages in the quicklist
+ */
+void quicklist_trim(int nr, void (*dtor)(void *),
+	unsigned long min_pages, unsigned long max_free)
+{
+	long pages_to_free;
+	struct quicklist *q;
+
+	q = &get_cpu_var(quicklist)[nr];
+	if (q->nr_pages > min_pages) {
+		pages_to_free = min_pages_to_free(q, min_pages, max_free);
+
+		while (pages_to_free > 0) {
+			/*
+			 * We pass a gfp_t of 0 to quicklist_alloc here
+			 * because we will never call into the page allocator.
+			 */
+			void *p = quicklist_alloc(nr, 0, NULL);
+
+			if (dtor)
+				dtor(p);
+			free_page((unsigned long)p);
+			pages_to_free--;
+		}
+	}
+	put_cpu_var(quicklist);
+}
+
+unsigned long quicklist_total_size(void)
+{
+	unsigned long count = 0;
+	int cpu;
+	struct quicklist *ql, *q;
+
+	for_each_online_cpu(cpu) {
+		ql = per_cpu(quicklist, cpu);
+		for (q = ql; q < ql + CONFIG_NR_QUICK; q++)
+			count += q->nr_pages;
+	}
+	return count;
+}
+
diff --git a/mm/readahead.c b/mm/readahead.c
index 93d9ee692fd..9861e883fe5 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -37,7 +37,7 @@ void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
 {
 	ra->ra_pages = mapping->backing_dev_info->ra_pages;
-	ra->prev_page = -1;
+	ra->prev_index = -1;
 }
 EXPORT_SYMBOL_GPL(file_ra_state_init);
 
@@ -202,17 +202,19 @@ out:
  * size:	Number of pages in that read
  *              Together, these form the "current window".
  *              Together, start and size represent the `readahead window'.
- * prev_page:   The page which the readahead algorithm most-recently inspected.
+ * prev_index:  The page which the readahead algorithm most-recently inspected.
  *              It is mainly used to detect sequential file reading.
  *              If page_cache_readahead sees that it is again being called for
  *              a page which it just looked at, it can return immediately without
  *              making any state changes.
+ * offset:      Offset in the prev_index where the last read ended - used for
+ *              detection of sequential file reading.
  * ahead_start,
  * ahead_size:  Together, these form the "ahead window".
  * ra_pages:	The externally controlled max readahead for this fd.
  *
  * When readahead is in the off state (size == 0), readahead is disabled.
- * In this state, prev_page is used to detect the resumption of sequential I/O.
+ * In this state, prev_index is used to detect the resumption of sequential I/O.
  *
  * The readahead code manages two windows - the "current" and the "ahead"
  * windows.  The intent is that while the application is walking the pages
@@ -415,7 +417,7 @@ static int make_ahead_window(struct address_space *mapping, struct file *filp,
 	ra->ahead_size = get_next_ra_size(ra);
 	ra->ahead_start = ra->start + ra->size;
 
-	block = force || (ra->prev_page >= ra->ahead_start);
+	block = force || (ra->prev_index >= ra->ahead_start);
 	ret = blockable_page_cache_readahead(mapping, filp,
 			ra->ahead_start, ra->ahead_size, ra, block);
 
@@ -467,12 +469,13 @@ page_cache_readahead(struct address_space *mapping, struct file_ra_state *ra,
 	 * We avoid doing extra work and bogusly perturbing the readahead
 	 * window expansion logic.
 	 */
-	if (offset == ra->prev_page && --req_size)
+	if (offset == ra->prev_index && --req_size)
 		++offset;
 
-	/* Note that prev_page == -1 if it is a first read */
-	sequential = (offset == ra->prev_page + 1);
-	ra->prev_page = offset;
+	/* Note that prev_index == -1 if it is a first read */
+	sequential = (offset == ra->prev_index + 1);
+	ra->prev_index = offset;
+	ra->prev_offset = 0;
 
 	max = get_max_readahead(ra);
 	newsize = min(req_size, max);
@@ -481,7 +484,7 @@ page_cache_readahead(struct address_space *mapping, struct file_ra_state *ra,
 	if (newsize == 0 || (ra->flags & RA_FLAG_INCACHE))
 		goto out;
 
-	ra->prev_page += newsize - 1;
+	ra->prev_index += newsize - 1;
 
 	/*
 	 * Special case - first read at start of file. We'll assume it's
@@ -537,18 +540,18 @@ page_cache_readahead(struct address_space *mapping, struct file_ra_state *ra,
 	 * we get called back on the first page of the ahead window which
 	 * will allow us to submit more IO.
 	 */
-	if (ra->prev_page >= ra->ahead_start) {
+	if (ra->prev_index >= ra->ahead_start) {
 		ra->start = ra->ahead_start;
 		ra->size = ra->ahead_size;
 		make_ahead_window(mapping, filp, ra, 0);
 recheck:
-		/* prev_page shouldn't overrun the ahead window */
-		ra->prev_page = min(ra->prev_page,
+		/* prev_index shouldn't overrun the ahead window */
+		ra->prev_index = min(ra->prev_index,
 			ra->ahead_start + ra->ahead_size - 1);
 	}
 
 out:
-	return ra->prev_page + 1;
+	return ra->prev_index + 1;
 }
 EXPORT_SYM