Large Blocksize Support V3

Index: linux-2.6.21-rc7/fs/buffer.c
===================================================================
@@ -1803,17 +1803,12 @@ static int __block_prepare_write(struct 
 					continue;
 				}
 				if (block_end > to || block_start < from) {
-					void *kaddr;
-
-					kaddr = kmap_atomic(page, KM_USER0);
 					if (block_end > to)
-						memset(kaddr+to, 0,
-							block_end-to);
+						memclear_highpage_flush(page,
+							to, block_end - to);
 					if (block_start < from)
-						memset(kaddr+block_start,
-							0, from-block_start);
-					flush_dcache_page(page);
-					kunmap_atomic(kaddr, KM_USER0);
+						memclear_highpage_flush(page,
+						block_start, from - block_start);
 				}
 				continue;
 			}

@@ -1861,13 +1856,8 @@ static int __block_prepare_write(struct 
 		if (block_start >= to)
 			break;
 		if (buffer_new(bh)) {
-			void *kaddr;
-
 			clear_buffer_new(bh);
-			kaddr = kmap_atomic(page, KM_USER0);
-			memset(kaddr+block_start, 0, bh->b_size);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr, KM_USER0);
+			memclear_highpage_flush(page, block_start, bh->b_size);
 			set_buffer_uptodate(bh);
 			mark_buffer_dirty(bh);
 		}

@@ -1955,10 +1945,7 @@ int block_read_full_page(struct page *pa
 					SetPageError(page);
 			}
 			if (!buffer_mapped(bh)) {
-				void *kaddr = kmap_atomic(page, KM_USER0);
-				memset(kaddr + i * blocksize, 0, blocksize);
-				flush_dcache_page(page);
-				kunmap_atomic(kaddr, KM_USER0);
+				memclear_highpage_flush(page, i * blocksize, blocksize);
 				if (!err)
 					set_buffer_uptodate(bh);
 				continue;

@@ -2101,7 +2088,6 @@ int cont_prepare_write(struct page *page
 	long status;
 	unsigned zerofrom;
 	unsigned blocksize = 1 << inode->i_blkbits;
-	void *kaddr;
 
 	while(page->index > (pgpos = *bytes>>PAGE_CACHE_SHIFT)) {
 		status = -ENOMEM;

@@ -2123,10 +2109,8 @@ int cont_prepare_write(struct page *page
 						PAGE_CACHE_SIZE, get_block);
 		if (status)
 			goto out_unmap;
-		kaddr = kmap_atomic(new_page, KM_USER0);
-		memset(kaddr+zerofrom, 0, PAGE_CACHE_SIZE-zerofrom);
-		flush_dcache_page(new_page);
-		kunmap_atomic(kaddr, KM_USER0);
+		memclear_highpage_flush(new_page, zerofrom,
+					PAGE_CACHE_SIZE - zerofrom);
 		generic_commit_write(NULL, new_page, zerofrom, PAGE_CACHE_SIZE);
 		unlock_page(new_page);
 		page_cache_release(new_page);

@@ -2153,10 +2137,7 @@ int cont_prepare_write(struct page *page
 	if (status)
 		goto out1;
 	if (zerofrom < offset) {
-		kaddr = kmap_atomic(page, KM_USER0);
-		memset(kaddr+zerofrom, 0, offset-zerofrom);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr, KM_USER0);
+		memclear_highpage_flush(page, zerofrom, offset - zerofrom);
 		__block_commit_write(inode, page, zerofrom, offset);
 	}
 	return 0;

@@ -2243,7 +2224,6 @@ int nobh_prepare_write(struct page *page
 	unsigned block_in_page;
 	unsigned block_start;
 	sector_t block_in_file;
-	char *kaddr;
 	int nr_reads = 0;
 	int i;
 	int ret = 0;

@@ -2283,13 +2263,12 @@ int nobh_prepare_write(struct page *page
 		if (PageUptodate(page))
 			continue;
 		if (buffer_new(&map_bh) || !buffer_mapped(&map_bh)) {
-			kaddr = kmap_atomic(page, KM_USER0);
 			if (block_start < from)
-				memset(kaddr+block_start, 0, from-block_start);
+				memclear_highpage_flush(page,
+					block_start, from - block_start);
 			if (block_end > to)
-				memset(kaddr + to, 0, block_end - to);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr, KM_USER0);
+				memclear_highpage_flush(page,
+					to, block_end - to);
 			continue;
 		}
 		if (buffer_uptodate(&map_bh))

@@ -2355,10 +2334,7 @@ failed:
 	 * Error recovery is pretty slack.  Clear the page and mark it dirty
 	 * so we'll later zero out any blocks which _were_ allocated.
 	 */
-	kaddr = kmap_atomic(page, KM_USER0);
-	memset(kaddr, 0, PAGE_CACHE_SIZE);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
+	memclear_highpage_flush(page, 0, PAGE_SIZE);
 	SetPageUptodate(page);
 	set_page_dirty(page);
 	return ret;

@@ -2397,7 +2373,6 @@ int nobh_writepage(struct page *page, ge
 	loff_t i_size = i_size_read(inode);
 	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
 	unsigned offset;
-	void *kaddr;
 	int ret;
 
 	/* Is the page fully inside i_size? */

@@ -2428,10 +2403,7 @@ int nobh_writepage(struct page *page, ge
 	 * the  page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	kaddr = kmap_atomic(page, KM_USER0);
-	memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
+	memclear_highpage_flush(page, offset, PAGE_CACHE_SIZE - offset);
 out:
 	ret = mpage_writepage(page, get_block, wbc);
 	if (ret == -EAGAIN)

@@ -2452,7 +2424,6 @@ int nobh_truncate_page(struct address_sp
 	unsigned to;
 	struct page *page;
 	const struct address_space_operations *a_ops = mapping->a_ops;
-	char *kaddr;
 	int ret = 0;
 
 	if ((offset & (blocksize - 1)) == 0)

@@ -2466,10 +2437,7 @@ int nobh_truncate_page(struct address_sp
 	to = (offset + blocksize) & ~(blocksize - 1);
 	ret = a_ops->prepare_write(NULL, page, offset, to);
 	if (ret == 0) {
-		kaddr = kmap_atomic(page, KM_USER0);
-		memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr, KM_USER0);
+		memclear_highpage_flush(page, offset, PAGE_CACHE_SIZE - offset);
 		/*
 		 * It would be more correct to call aops->commit_write()
 		 * here, but this is more efficient.

@@ -2495,7 +2463,6 @@ int block_truncate_page(struct address_s
 	struct inode *inode = mapping->host;
 	struct page *page;
 	struct buffer_head *bh;
-	void *kaddr;
 	int err;
 
 	blocksize = 1 << inode->i_blkbits;

@@ -2549,11 +2516,7 @@ int block_truncate_page(struct address_s
 			goto unlock;
 	}
 
-	kaddr = kmap_atomic(page, KM_USER0);
-	memset(kaddr + offset, 0, length);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
-
+	memclear_highpage_flush(page, offset, length);
 	mark_buffer_dirty(bh);
 	err = 0;
 

@@ -2574,7 +2537,6 @@ int block_write_full_page(struct page *p
 	loff_t i_size = i_size_read(inode);
 	const pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
 	unsigned offset;
-	void *kaddr;
 
 	/* Is the page fully inside i_size? */
 	if (page->index < end_index)

@@ -2600,10 +2562,7 @@ int block_write_full_page(struct page *p
 	 * the  page size, the remaining memory is zeroed when mapped, and
 	 * writes to that region are not written out to the file."
 	 */
-	kaddr = kmap_atomic(page, KM_USER0);
-	memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
-	flush_dcache_page(page);
-	kunmap_atomic(kaddr, KM_USER0);
+	memclear_highpage_flush(page, offset, PAGE_CACHE_SIZE - offset);
 	return __block_write_full_page(inode, page, get_block, wbc);
 }
 

Index: linux-2.6.21-rc7/fs/direct-io.c
===================================================================
@@ -867,7 +867,6 @@ static int do_direct_IO(struct dio *dio)
 do_holes:
 			/* Handle holes */
 			if (!buffer_mapped(map_bh)) {
-				char *kaddr;
 				loff_t i_size_aligned;
 
 				/* AKPM: eargh, -ENOTBLK is a hack */

@@ -888,11 +887,8 @@ do_holes:
 					page_cache_release(page);
 					goto out;
 				}
-				kaddr = kmap_atomic(page, KM_USER0);
-				memset(kaddr + (block_in_page << blkbits),
-						0, 1 << blkbits);
-				flush_dcache_page(page);
-				kunmap_atomic(kaddr, KM_USER0);
+				memclear_highpage_flush(page,
+					block_in_page << blkbits, 1 << blkbits);
 				dio->block_in_file++;
 				block_in_page++;
 				goto next_block;

Index: linux-2.6.21-rc7/fs/libfs.c
===================================================================
@@ -332,11 +332,11 @@ int simple_prepare_write(struct file *fi
 {
 	if (!PageUptodate(page)) {
 		if (to - from != PAGE_CACHE_SIZE) {
-			void *kaddr = kmap_atomic(page, KM_USER0);
-			memset(kaddr, 0, from);
-			memset(kaddr + to, 0, PAGE_CACHE_SIZE - to);
-			flush_dcache_page(page);
-			kunmap_atomic(kaddr, KM_USER0);
+			if (from)
+				memclear_highpage_flush(page, 0, from);
+			if (to < PAGE_CACHE_SIZE)
+				memclear_highpage_flush(page, to,
+					PAGE_CACHE_SIZE - to);
 		}
 	}
 	return 0;

Index: linux-2.6.21-rc7/fs/mpage.c
===================================================================
@@ -284,11 +284,8 @@ do_mpage_readpage(struct bio *bio, struc
 	}
 
 	if (first_hole != blocks_per_page) {
-		char *kaddr = kmap_atomic(page, KM_USER0);
-		memset(kaddr + (first_hole << blkbits), 0,
+		memclear_highpage_flush(page, first_hole << blkbits,
 				PAGE_CACHE_SIZE - (first_hole << blkbits));
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr, KM_USER0);
 		if (first_hole == 0) {
 			SetPageUptodate(page);
 			unlock_page(page);

@@ -576,14 +573,11 @@ page_is_mapped:
 		 * written out to the file."
 		 */
 		unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
-		char *kaddr;
 
 		if (page->index > end_index || !offset)
 			goto confused;
-		kaddr = kmap_atomic(page, KM_USER0);
-		memset(kaddr + offset, 0, PAGE_CACHE_SIZE - offset);
-		flush_dcache_page(page);
-		kunmap_atomic(kaddr, KM_USER0);
+		memclear_highpage_flush(page, offset,
+			PAGE_CACHE_SIZE - offset);
 	}
 
 	/*

Index: linux-2.6.21-rc7/mm/filemap_xip.c
===================================================================
@@ -458,11 +458,7 @@ xip_truncate_page(struct address_space *
 		else
 			return PTR_ERR(page);
 	}
-	kaddr = kmap_atomic(page, KM_USER0);
-	memset(kaddr + offset, 0, length);
-	kunmap_atomic(kaddr, KM_USER0);
-
-	flush_dcache_page(page);
+	memclear_highpage_flush(page, offset, length);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xip_truncate_page);

Index: linux-2.6.21-rc7/fs/buffer.c
===================================================================
@@ -988,7 +988,8 @@ grow_dev_page(struct block_device *bdev,
 	struct page *page;
 	struct buffer_head *bh;
 
-	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
+	page = find_or_create_page(inode->i_mapping, index,
+		mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
 	if (!page)
 		return NULL;
 

Index: linux-2.6.21-rc7/mm/filemap.c
===================================================================
@@ -648,7 +648,8 @@ EXPORT_SYMBOL(find_lock_page);
  * find_or_create_page - locate or add a pagecache page
  * @mapping: the page's address_space
  * @index: the page's index into the mapping
- * @gfp_mask: page allocation mode
+ * @gfp_mask: page allocation mode. This must be derived from the
+ * 	allocation flags of the mapping!
  *
  * Locates a page in the pagecache.  If the page is not present, a new page
  * is allocated using @gfp_mask and is added to the pagecache and to the VM's

@@ -670,7 +671,8 @@ repeat:
 	page = find_lock_page(mapping, index);
 	if (!page) {
 		if (!cached_page) {
-			cached_page = alloc_page(gfp_mask);
+			cached_page =
+				__page_cache_alloc(gfp_mask);
 			if (!cached_page)
 				return NULL;
 		}

Index: linux-2.6.21-rc7/include/linux/mm.h
===================================================================
@@ -263,21 +263,24 @@ static inline int put_page_testzero(stru
  */
 static inline int get_page_unless_zero(struct page *page)
 {
-	VM_BUG_ON(PageCompound(page));
 	return atomic_inc_not_zero(&page->_count);
 }
 
+static inline struct page *compound_head(struct page *page)
+{
+	if (unlikely(PageTail(page)))
+		return (struct page *)page->private;
+	return page;
+}
+
 static inline int page_count(struct page *page)
 {
-	if (unlikely(PageCompound(page)))
-		page = (struct page *)page_private(page);
-	return atomic_read(&page->_count);
+	return atomic_read(&compound_head(page)->_count);
 }
 
 static inline void get_page(struct page *page)
 {
-	if (unlikely(PageCompound(page)))
-		page = (struct page *)page_private(page);
+	page = compound_head(page);
 	VM_BUG_ON(atomic_read(&page->_count) == 0);
 	atomic_inc(&page->_count);
 }

@@ -314,6 +317,19 @@ static inline compound_page_dtor *get_co
 	return (compound_page_dtor *)page[1].lru.next;
 }
 
+static inline void set_compound_order(struct page *page, unsigned long order)
+{
+	page[1].lru.prev = (void *)order;
+}
+
+static inline int compound_order(struct page *page)
+{
+	if (!PageCompound(page) || PageTail(page))
+		return 0;
+
+	return (unsigned long)page[1].lru.prev;
+}
+
 /*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of

Index: linux-2.6.21-rc7/include/linux/page-flags.h
===================================================================
@@ -91,6 +91,8 @@
 #define PG_nosave_free		18	/* Used for system suspend/resume */
 #define PG_buddy		19	/* Page is free, on buddy lists */
 
+#define PG_tail			20	/* Page is tail of a compound page */
+
 /* PG_owner_priv_1 users should have descriptive aliases */
 #define PG_checked		PG_owner_priv_1 /* Used by some filesystems */
 

@@ -241,6 +243,10 @@ static inline void SetPageUptodate(struc
 #define __SetPageCompound(page)	__set_bit(PG_compound, &(page)->flags)
 #define __ClearPageCompound(page) __clear_bit(PG_compound, &(page)->flags)
 
+#define PageTail(page)	test_bit(PG_tail, &(page)->flags)
+#define __SetPageTail(page)	__set_bit(PG_tail, &(page)->flags)
+#define __ClearPageTail(page)	__clear_bit(PG_tail, &(page)->flags)
+
 #ifdef CONFIG_SWAP
 #define PageSwapCache(page)	test_bit(PG_swapcache, &(page)->flags)
 #define SetPageSwapCache(page)	set_bit(PG_swapcache, &(page)->flags)

Index: linux-2.6.21-rc7/mm/internal.h
===================================================================
@@ -24,7 +24,7 @@ static inline void set_page_count(struct
  */
 static inline void set_page_refcounted(struct page *page)
 {
-	VM_BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page);
+	VM_BUG_ON(PageTail(page));
 	VM_BUG_ON(atomic_read(&page->_count));
 	set_page_count(page, 1);
 }

Index: linux-2.6.21-rc7/mm/page_alloc.c
===================================================================
@@ -227,7 +227,7 @@ 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 +236,14 @@ static void prep_compound_page(struct pa
 	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);
+	__SetPageCompound(page);
+	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 
+		__SetPageTail(p);
 		__SetPageCompound(p);
-		set_page_private(p, (unsigned long)page);
+		p->private = (unsigned long)page;
 	}
 }
 

@@ -250,15 +252,19 @@ static void destroy_compound_page(struct
 	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(!PageCompound(page)))
+			bad_page(page);
+	__ClearPageCompound(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(!PageCompound(p) | !PageTail(p) |
+				((struct page *)p->private != page)))
 			bad_page(page);
+		__ClearPageTail(p);
 		__ClearPageCompound(p);
 	}
 }

@@ -1438,8 +1444,17 @@ void __pagevec_free(struct pagevec *pvec
 {
 	int i = pagevec_count(pvec);
 
-	while (--i >= 0)
-		free_hot_cold_page(pvec->pages[i], pvec->cold);
+	while (--i >= 0) {
+		struct page *page = pvec->pages[i];
+
+		if (PageCompound(page)) {
+			compound_page_dtor *dtor;
+
+			dtor = get_compound_page_dtor(page);
+			(*dtor)(page);
+		} else
+			free_hot_cold_page(page, pvec->cold);
+	}
 }
 
 fastcall void __free_pages(struct page *page, unsigned int order)

Index: linux-2.6.21-rc7/mm/slab.c
===================================================================
@@ -592,8 +592,7 @@ static inline void page_set_cache(struct
 
 static inline struct kmem_cache *page_get_cache(struct page *page)
 {
-	if (unlikely(PageCompound(page)))
-		page = (struct page *)page_private(page);
+	page = compound_head(page);
 	BUG_ON(!PageSlab(page));
 	return (struct kmem_cache *)page->lru.next;
 }

@@ -605,8 +604,7 @@ static inline void page_set_slab(struct 
 
 static inline struct slab *page_get_slab(struct page *page)
 {
-	if (unlikely(PageCompound(page)))
-		page = (struct page *)page_private(page);
+	page = compound_head(page);
 	BUG_ON(!PageSlab(page));
 	return (struct slab *)page->lru.prev;
 }

Index: linux-2.6.21-rc7/mm/swap.c
===================================================================
@@ -55,7 +55,7 @@ static void fastcall __page_cache_releas
 
 static void put_compound_page(struct page *page)
 {
-	page = (struct page *)page_private(page);
+	page = compound_head(page);
 	if (put_page_testzero(page)) {
 		compound_page_dtor *dtor;
 

Index: linux-2.6.21-rc7/arch/ia64/mm/init.c
===================================================================
@@ -121,7 +121,7 @@ lazy_mmu_prot_update (pte_t pte)
 		return;				/* i-cache is already coherent with d-cache */
 
 	if (PageCompound(page)) {
-		order = (unsigned long) (page[1].lru.prev);
+		order = compound_order(page);
 		flush_icache_range(addr, addr + (1UL << order << PAGE_SHIFT));
 	}
 	else

Index: linux-2.6.21-rc7/include/linux/mm.h
===================================================================
@@ -330,6 +330,21 @@ static inline int compound_order(struct 
 	return (unsigned long)page[1].lru.prev;
 }
 
+static inline int compound_pages(struct page *page)
+{
+ 	return 1 << compound_order(page);
+}
+
+static inline int compound_shift(struct page *page)
+{
+ 	return PAGE_SHIFT + compound_order(page);
+}
+
+static inline int compound_size(struct page *page)
+{
+	return PAGE_SIZE << compound_order(page);
+}
+
 /*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of

Index: linux-2.6.21-rc7/mm/swap.c
===================================================================
@@ -263,7 +263,13 @@ void release_pages(struct page **pages, 
 	for (i = 0; i < nr; i++) {
 		struct page *page = pages[i];
 
-		if (unlikely(PageCompound(page))) {
+		/*
+		 * If we have a tail page on the LRU then we need to
+		 * decrement the page count of the head page. There
+		 * is no further need to do anything since tail pages
+		 * cannot be on the LRU.
+		 */
+		if (unlikely(PageTail(page))) {
 			if (zone) {
 				spin_unlock_irq(&zone->lru_lock);
 				zone = NULL;

Index: linux-2.6.21-rc7/mm/vmstat.c
===================================================================
@@ -223,7 +223,7 @@ void __inc_zone_state(struct zone *zone,
 
 void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
 {
-	__inc_zone_state(page_zone(page), item);
+	__mod_zone_page_state(page_zone(page), item, compound_pages(page));
 }
 EXPORT_SYMBOL(__inc_zone_page_state);
 

@@ -244,7 +244,7 @@ void __dec_zone_state(struct zone *zone,
 
 void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 {
-	__dec_zone_state(page_zone(page), item);
+	__mod_zone_page_state(page_zone(page), item, -compound_pages(page));
 }
 EXPORT_SYMBOL(__dec_zone_page_state);
 

@@ -260,11 +260,9 @@ void inc_zone_state(struct zone *zone, e
 void inc_zone_page_state(struct page *page, enum zone_stat_item item)
 {
 	unsigned long flags;
-	struct zone *zone;
 
-	zone = page_zone(page);
 	local_irq_save(flags);
-	__inc_zone_state(zone, item);
+	__inc_zone_page_state(page, item);
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(inc_zone_page_state);

Index: linux-2.6.21-rc7/include/linux/mm_inline.h
===================================================================
@@ -2,28 +2,28 @@ static inline void
 add_page_to_active_list(struct zone *zone, struct page *page)
 {
 	list_add(&page->lru, &zone->active_list);
-	__inc_zone_state(zone, NR_ACTIVE);
+	__inc_zone_page_state(page, NR_ACTIVE);
 }
 
 static inline void
 add_page_to_inactive_list(struct zone *zone, struct page *page)
 {
 	list_add(&page->lru, &zone->inactive_list);
-	__inc_zone_state(zone, NR_INACTIVE);
+	__inc_zone_page_state(page, NR_INACTIVE);
 }
 
 static inline void
 del_page_from_active_list(struct zone *zone, struct page *page)
 {
 	list_del(&page->lru);
-	__dec_zone_state(zone, NR_ACTIVE);
+	__dec_zone_page_state(page, NR_ACTIVE);
 }
 
 static inline void
 del_page_from_inactive_list(struct zone *zone, struct page *page)
 {
 	list_del(&page->lru);
-	__dec_zone_state(zone, NR_INACTIVE);
+	__dec_zone_page_state(page, NR_INACTIVE);
 }
 
 static inline void

@@ -32,9 +32,9 @@ del_page_from_lru(struct zone *zone, str
 	list_del(&page->lru);
 	if (PageActive(page)) {
 		__ClearPageActive(page);
-		__dec_zone_state(zone, NR_ACTIVE);
+		__dec_zone_page_state(page, NR_ACTIVE);
 	} else {
-		__dec_zone_state(zone, NR_INACTIVE);
+		__dec_zone_page_state(page, NR_INACTIVE);
 	}
 }
 

Index: linux-2.6.21-rc7/include/linux/vmstat.h
===================================================================
@@ -235,7 +235,7 @@ static inline void __inc_zone_state(stru
 static inline void __inc_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
-	__inc_zone_state(page_zone(page), item);
+	__mod_zone_page_state(page_zone(page), item, compound_pages(page));
 }
 
 static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)

@@ -247,8 +247,7 @@ static inline void __dec_zone_state(stru
 static inline void __dec_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
-	atomic_long_dec(&page_zone(page)->vm_stat[item]);
-	atomic_long_dec(&vm_stat[item]);
+	__mod_zone_page_state(page_zone(page), item, -compound_pages(page));
 }
 
 /*

Index: linux-2.6.21-rc7/include/linux/pagemap.h
===================================================================
@@ -32,6 +32,10 @@ static inline void mapping_set_gfp_mask(
 {
 	m->flags = (m->flags & ~(__force unsigned long)__GFP_BITS_MASK) |
 				(__force unsigned long)mask;
+#ifdef CONFIG_LARGE_BLOCKSIZE
+	if (m->order)
+		m->flags |= __GFP_COMP;
+#endif
 }
 
 /*

@@ -41,33 +45,134 @@ static inline void mapping_set_gfp_mask(
  * space in smaller chunks for same flexibility).
  *
  * Or rather, it _will_ be done in larger chunks.
+ *
+ * The following constants can be used if a filesystem only supports a single
+ * page size.
  */
 #define PAGE_CACHE_SHIFT	PAGE_SHIFT
 #define PAGE_CACHE_SIZE		PAGE_SIZE
 #define PAGE_CACHE_MASK		PAGE_MASK
 #define PAGE_CACHE_ALIGN(addr)	(((addr)+PAGE_CACHE_SIZE-1)&PAGE_CACHE_MASK)
 
+/*
+ * The next set of functions allow to write code that is capable of dealing
+ * with multiple page sizes.
+ */
+#ifdef CONFIG_LARGE_BLOCKSIZE
+static inline void set_mapping_order(struct address_space *a, int order)
+{
+	a->order = order;
+	a->shift = order + PAGE_SHIFT;
+	a->offset_mask = (1UL << a->shift) - 1;
+	if (order)
+		a->flags |= __GFP_COMP;
+}
+
+static inline int mapping_order(struct address_space *a)
+{
+	return a->order;
+}
+
+static inline int page_cache_shift(struct address_space *a)
+{
+	return a->shift;
+}
+
+static inline unsigned int page_cache_size(struct address_space *a)
+{
+	return a->offset_mask + 1;
+}
+
+static inline loff_t page_cache_mask(struct address_space *a)
+{
+	return ~a->offset_mask;
+}
+
+static inline unsigned int page_cache_offset(struct address_space *a,
+		loff_t pos)
+{
+	return pos & a->offset_mask;
+}
+#else
+/*
+ * Kernel configured for a fixed PAGE_SIZEd page cache
+ */
+static inline void set_mapping_order(struct address_space *a, int order)
+{
+	BUG_ON(order);
+}
+
+static inline int mapping_order(struct address_space *a)
+{
+	return 0;
+}
+
+static inline int page_cache_shift(struct address_space *a)
+{
+	return PAGE_SHIFT;
+}
+
+static inline unsigned int page_cache_size(struct address_space *a)
+{
+	return PAGE_SIZE;
+}
+
+static inline loff_t page_cache_mask(struct address_space *a)
+{
+	return (loff_t)PAGE_MASK;
+}
+
+static inline unsigned int page_cache_offset(struct address_space *a,
+		loff_t pos)
+{
+	return pos & ~PAGE_MASK;
+}
+#endif
+
+static inline pgoff_t page_cache_index(struct address_space *a,
+		loff_t pos)
+{
+	return pos >> page_cache_shift(a);
+}
+
+/*
+ * Index of the page starting on or after the given position.
+ */
+static inline pgoff_t page_cache_next(struct address_space *a,
+		loff_t pos)
+{
+	return page_cache_index(a, pos + page_cache_size(a) - 1);
+}
+
+static inline loff_t page_cache_pos(struct address_space *a,
+		pgoff_t index, unsigned long offset)
+{
+	return ((loff_t)index << page_cache_shift(a)) + offset;
+}
+
 #define page_cache_get(page)		get_page(page)
 #define page_cache_release(page)	put_page(page)
 void release_pages(struct page **pages, int nr, int cold);
 
 #ifdef CONFIG_NUMA
-extern struct page *__page_cache_alloc(gfp_t gfp);
+extern struct page *__page_cache_alloc(gfp_t gfp, int order);
 #else
-static inline struct page *__page_cache_alloc(gfp_t gfp)
+static inline struct page *__page_cache_alloc(gfp_t gfp, int order)
 {
-	return alloc_pages(gfp, 0);
+	return alloc_pages(gfp, order);
 }
 #endif
 
 static inline struct page *page_cache_alloc(struct address_space *x)
 {
-	return __page_cache_alloc(mapping_gfp_mask(x));
+	return __page_cache_alloc(mapping_gfp_mask(x),
+			mapping_order(x));
 }
 
 static inline struct page *page_cache_alloc_cold(struct address_space *x)
 {
-	return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD);
+	return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD,
+			mapping_order(x));
 }
 
 typedef int filler_t(void *, struct page *);

Index: linux-2.6.21-rc7/include/linux/fs.h
===================================================================
@@ -435,6 +435,11 @@ struct address_space {
 	struct inode		*host;		/* owner: inode, block_device */
 	struct radix_tree_root	page_tree;	/* radix tree of all pages */
 	rwlock_t		tree_lock;	/* and rwlock protecting it */
+#ifdef CONFIG_LARGE_BLOCKSIZE
+	unsigned int		order;		/* Page order of the pages in here */
+	unsigned int		shift;		/* Shift of index */
+	loff_t			offset_mask;	/* Mask to get to offset bits */
+#endif
 	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
 	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */

Index: linux-2.6.21-rc7/mm/filemap.c
===================================================================
@@ -467,13 +467,13 @@ int add_to_page_cache_lru(struct page *p
 }
 
 #ifdef CONFIG_NUMA
-struct page *__page_cache_alloc(gfp_t gfp)
+struct page *__page_cache_alloc(gfp_t gfp, int order)
 {
 	if (cpuset_do_page_mem_spread()) {
 		int n = cpuset_mem_spread_node();
-		return alloc_pages_node(n, gfp, 0);
+		return alloc_pages_node(n, gfp, order);
 	}
-	return alloc_pages(gfp, 0);
+	return alloc_pages(gfp, order);
 }
 EXPORT_SYMBOL(__page_cache_alloc);
 #endif

@@ -672,7 +672,8 @@ repeat:
 	if (!page) {
 		if (!cached_page) {
 			cached_page =
-				__page_cache_alloc(gfp_mask);
+				__page_cache_alloc(gfp_mask,
+					mapping_order(mapping));
 			if (!cached_page)
 				return NULL;
 		}

@@ -805,7 +806,8 @@ grab_cache_page_nowait(struct address_sp
 		page_cache_release(page);
 		return NULL;
 	}
-	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
+	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS,
+				mapping_order(mapping));
 	if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) {
 		page_cache_release(page);
 		page = NULL;

Index: linux-2.6.21-rc7/fs/libfs.c
===================================================================
@@ -330,13 +330,15 @@ int simple_readpage(struct file *file, s
 int simple_prepare_write(struct file *file, struct page *page,
 			unsigned from, unsigned to)
 {
+	unsigned int page_size = page_cache_size(file->f_mapping);
+
 	if (!PageUptodate(page)) {
-		if (to - from != PAGE_CACHE_SIZE) {
+		if (to - from != page_size) {
 			if (from)
 				memclear_highpage_flush(page, 0, from);
-			if (to < PAGE_CACHE_SIZE)
+			if (to < page_size)
 				memclear_highpage_flush(page, to,
-					PAGE_CACHE_SIZE - to);
+					page_size - to);
 		}
 	}
 	return 0;

@@ -345,8 +347,9 @@ int simple_prepare_write(struct file *fi
 int simple_commit_write(struct file *file, struct page *page,
 			unsigned from, unsigned to)
 {
-	struct inode *inode = page->mapping->host;
-	loff_t pos = ((loff_t)page->index << PAGE_CACHE_SHIFT) + to;
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+	loff_t pos = page_cache_pos(mapping, page->index, to);
 
 	if (!PageUptodate(page))
 		SetPageUptodate(page);

164 lines not on this page · raw message

Index: linux-2.6.21-rc7/fs/sync.c
===================================================================
@@ -254,8 +254,8 @@ int do_sync_file_range(struct file *file
 	ret = 0;
 	if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
 		ret = wait_on_page_writeback_range(mapping,
-					offset >> PAGE_CACHE_SHIFT,
-					endbyte >> PAGE_CACHE_SHIFT);
+					page_cache_index(mapping, offset),
+					page_cache_index(mapping, endbyte));
 		if (ret < 0)
 			goto out;
 	}

@@ -269,8 +269,8 @@ int do_sync_file_range(struct file *file
 
 	if (flags & SYNC_FILE_RANGE_WAIT_AFTER) {
 		ret = wait_on_page_writeback_range(mapping,
-					offset >> PAGE_CACHE_SHIFT,
-					endbyte >> PAGE_CACHE_SHIFT);
+					page_cache_index(mapping, offset),
+					page_cache_index(mapping, endbyte));
 	}
 out:
 	return ret;

Index: linux-2.6.21-rc7/mm/fadvise.c
===================================================================
@@ -79,8 +79,8 @@ asmlinkage long sys_fadvise64_64(int fd,
 		}
 
 		/* First and last PARTIAL page! */
-		start_index = offset >> PAGE_CACHE_SHIFT;
-		end_index = endbyte >> PAGE_CACHE_SHIFT;
+		start_index = page_cache_index(mapping, offset);
+		end_index = page_cache_index(mapping, endbyte);
 
 		/* Careful about overflow on the "+1" */
 		nrpages = end_index - start_index + 1;

@@ -100,8 +100,8 @@ asmlinkage long sys_fadvise64_64(int fd,
 			filemap_flush(mapping);
 
 		/* First and last FULL page! */
-		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
-		end_index = (endbyte >> PAGE_CACHE_SHIFT);
+		start_index = page_cache_next(mapping, offset);
+		end_index = page_cache_index(mapping, endbyte);
 
 		if (end_index >= start_index)
 			invalidate_mapping_pages(mapping, start_index,

Index: linux-2.6.21-rc7/mm/page-writeback.c
===================================================================
@@ -606,8 +606,8 @@ int generic_writepages(struct address_sp
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = page_cache_index(mapping, wbc->range_start);
+		end = page_cache_index(mapping, wbc->range_end);
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
 		scanned = 1;

Index: linux-2.6.21-rc7/mm/truncate.c
===================================================================
@@ -46,7 +46,8 @@ void do_invalidatepage(struct page *page
 
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
-	memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
+	memclear_highpage_flush(page, partial,
+		compound_size(page) - partial);
 	if (PagePrivate(page))
 		do_invalidatepage(page, partial);
 }

@@ -94,7 +95,7 @@ truncate_complete_page(struct address_sp
 	if (page->mapping != mapping)
 		return;
 
-	cancel_dirty_page(page, PAGE_CACHE_SIZE);
+	cancel_dirty_page(page, page_cache_size(mapping));
 
 	if (PagePrivate(page))
 		do_invalidatepage(page, 0);

@@ -156,9 +157,9 @@ invalidate_complete_page(struct address_
 void truncate_inode_pages_range(struct address_space *mapping,
 				loff_t lstart, loff_t lend)
 {
-	const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+	const pgoff_t start = page_cache_next(mapping, lstart);
 	pgoff_t end;
-	const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
+	const unsigned partial = page_cache_offset(mapping, lstart);
 	struct pagevec pvec;
 	pgoff_t next;
 	int i;

@@ -166,8 +167,9 @@ void truncate_inode_pages_range(struct a
 	if (mapping->nrpages == 0)
 		return;
 
-	BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
-	end = (lend >> PAGE_CACHE_SHIFT);
+	BUG_ON(page_cache_offset(mapping, lend) !=
+				page_cache_size(mapping) - 1);
+	end = page_cache_index(mapping, lend);
 
 	pagevec_init(&pvec, 0);
 	next = start;

@@ -402,9 +404,8 @@ int invalidate_inode_pages2_range(struct
 					 * Zap the rest of the file in one hit.
 					 */
 					unmap_mapping_range(mapping,
-					   (loff_t)page_index<<PAGE_CACHE_SHIFT,
-					   (loff_t)(end - page_index + 1)
-							<< PAGE_CACHE_SHIFT,
+					   page_cache_pos(mapping, page_index, 0),
+					   page_cache_pos(mapping, end - page_index + 1, 0),
 					    0);
 					did_range_unmap = 1;
 				} else {

@@ -412,8 +413,8 @@ int invalidate_inode_pages2_range(struct
 					 * Just zap this page
 					 */
 					unmap_mapping_range(mapping,
-					  (loff_t)page_index<<PAGE_CACHE_SHIFT,
-					  PAGE_CACHE_SIZE, 0);
+					  page_cache_pos(mapping, page_index, 0),
+					  page_cache_size(mapping), 0);
 				}
 			}
 			ret = do_launder_page(mapping, page);

311 lines not on this page · raw message

Index: linux-2.6.21-rc7/fs/mpage.c
===================================================================
@@ -133,7 +133,8 @@ mpage_alloc(struct block_device *bdev,
 static void 
 map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block) 
 {
-	struct inode *inode = page->mapping->host;
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
 	struct buffer_head *page_bh, *head;
 	int block = 0;
 

@@ -142,9 +143,9 @@ map_buffer_to_page(struct page *page, st
 		 * don't make any buffers if there is only one buffer on
 		 * the page and the page just needs to be set up to date
 		 */
-		if (inode->i_blkbits == PAGE_CACHE_SHIFT && 
+		if (inode->i_blkbits == page_cache_shift(mapping) &&
 		    buffer_uptodate(bh)) {
-			SetPageUptodate(page);    
+			SetPageUptodate(page);
 			return;
 		}
 		create_empty_buffers(page, 1 << inode->i_blkbits, 0);

@@ -177,9 +178,10 @@ do_mpage_readpage(struct bio *bio, struc
 		sector_t *last_block_in_bio, struct buffer_head *map_bh,
 		unsigned long *first_logical_block, get_block_t get_block)
 {
-	struct inode *inode = page->mapping->host;
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
-	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+	const unsigned blocks_per_page = page_cache_size(mapping) >> blkbits;
 	const unsigned blocksize = 1 << blkbits;
 	sector_t block_in_file;
 	sector_t last_block;

@@ -196,7 +198,7 @@ do_mpage_readpage(struct bio *bio, struc
 	if (page_has_buffers(page))
 		goto confused;
 
-	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+	block_in_file = (sector_t)page->index << (page_cache_shift(mapping) - blkbits);
 	last_block = block_in_file + nr_pages * blocks_per_page;
 	last_block_in_file = (i_size_read(inode) + blocksize - 1) >> blkbits;
 	if (last_block > last_block_in_file)

@@ -285,7 +287,7 @@ do_mpage_readpage(struct bio *bio, struc
 
 	if (first_hole != blocks_per_page) {
 		memclear_highpage_flush(page, first_hole << blkbits,
-				PAGE_CACHE_SIZE - (first_hole << blkbits));
+			page_cache_size(mapping) - (first_hole << blkbits));
 		if (first_hole == 0) {
 			SetPageUptodate(page);
 			unlock_page(page);

@@ -462,7 +464,7 @@ __mpage_writepage(struct bio *bio, struc
 	struct inode *inode = page->mapping->host;
 	const unsigned blkbits = inode->i_blkbits;
 	unsigned long end_index;
-	const unsigned blocks_per_page = PAGE_CACHE_SIZE >> blkbits;
+	const unsigned blocks_per_page = page_cache_size(mapping) >> blkbits;
 	sector_t last_block;
 	sector_t block_in_file;
 	sector_t blocks[MAX_BUF_PER_PAGE];

@@ -530,7 +532,7 @@ __mpage_writepage(struct bio *bio, struc
 	 * The page has no buffers: map it to disk
 	 */
 	BUG_ON(!PageUptodate(page));
-	block_in_file = (sector_t)page->index << (PAGE_CACHE_SHIFT - blkbits);
+	block_in_file = (sector_t)page->index << (page_cache_shift(mapping) - blkbits);
 	last_block = (i_size - 1) >> blkbits;
 	map_bh.b_page = page;
 	for (page_block = 0; page_block < blocks_per_page; ) {

@@ -562,7 +564,7 @@ __mpage_writepage(struct bio *bio, struc
 	first_unmapped = page_block;
 
 page_is_mapped:
-	end_index = i_size >> PAGE_CACHE_SHIFT;
+	end_index = page_cache_index(mapping, i_size);
 	if (page->index >= end_index) {
 		/*
 		 * The page straddles i_size.  It must be zeroed out on each

@@ -572,12 +574,12 @@ page_is_mapped:
 		 * is zeroed when mapped, and writes to that region are not
 		 * written out to the file."
 		 */
-		unsigned offset = i_size & (PAGE_CACHE_SIZE - 1);
+		unsigned offset = page_cache_offset(mapping, i_size);
 
 		if (page->index > end_index || !offset)
 			goto confused;
 		memclear_highpage_flush(page, offset,
-			PAGE_CACHE_SIZE - offset);
+			page_cache_size(mapping) - offset);
 	}
 
 	/*

@@ -721,8 +723,8 @@ mpage_writepages(struct address_space *m
 		index = mapping->writeback_index; /* Start from prev offset */
 		end = -1;
 	} else {
-		index = wbc->range_start >> PAGE_CACHE_SHIFT;
-		end = wbc->range_end >> PAGE_CACHE_SHIFT;
+		index = page_cache_index(mapping, wbc->range_start);
+		end = page_cache_index(mapping, wbc->range_end);
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
 		scanned = 1;

Index: linux-2.6.21-rc7/include/linux/buffer_head.h
===================================================================
@@ -129,7 +129,14 @@ BUFFER_FNS(Ordered, ordered)
 BUFFER_FNS(Eopnotsupp, eopnotsupp)
 BUFFER_FNS(Unwritten, unwritten)
 
-#define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
+static inline unsigned long bh_offset(struct buffer_head *bh)
+{
+	/* Cannot use the mapping since it may be set to NULL. */
+	unsigned long mask = compound_size(bh->b_page) - 1;
+
+	return (unsigned long)bh->b_data & mask;
+}
+
 #define touch_buffer(bh)	mark_page_accessed(bh->b_page)
 
 /* If we *know* page->private refers to buffer_heads */

Index: linux-2.6.21-rc7/include/linux/pagemap.h
===================================================================
@@ -291,6 +291,31 @@ static inline void wait_on_page_writebac
 
 extern void end_page_writeback(struct page *page);
 
+/* Support for clearing higher order pages */
+static inline void clear_mapping_page(struct page *page)
+{
+	int nr_pages = compound_pages(page);
+	int i;
+
+	for (i = 0; i < nr_pages; i++)
+		clear_highpage(page + i);
+}
+
+/*
+ * Support for flushing higher order pages.
+ *
+ * A bit stupid: On many platforms flushing the first page
+ * will flush any TLB starting there
+ */
+static inline void flush_mapping_page(struct page *page)
+{
+	int nr_pages = compound_pages(page);
+	int i;
+
+	for (i = 0; i < nr_pages; i++)
+		flush_dcache_page(page + i);
+}
+
 /*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *

Index: linux-2.6.21-rc7/fs/libfs.c
===================================================================
@@ -320,8 +320,8 @@ int simple_rename(struct inode *old_dir,
 
 int simple_readpage(struct file *file, struct page *page)
 {
-	clear_highpage(page);
-	flush_dcache_page(page);
+	clear_mapping_page(page);
+	flush_mapping_page(page);
 	SetPageUptodate(page);
 	unlock_page(page);
 	return 0;

Index: linux-2.6.21-rc7/include/linux/highmem.h
===================================================================
@@ -81,6 +81,17 @@ static inline void clear_highpage(struct
 	kunmap_atomic(kaddr, KM_USER0);
 }
 
+#ifdef CONFIG_LARGE_BLOCKSIZE
+/*
+ * Macro needed because flush_mapping_page definition is not available yet
+ * CONFIG_LARGE_BLOCKSIZE means !HIGHMEM
+ */
+#define memclear_highpage_flush(__page,__offset,__size) \
+{									\
+	memset(page_address(__page), (__offset), (__size));		\
+	flush_mapping_page(__page);					\
+}
+#else
 /*
  * Same but also flushes aliased cache contents to RAM.
  */

@@ -95,6 +106,7 @@ static inline void memclear_highpage_flu
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr, KM_USER0);
 }
+#endif
 
 #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE
 

Index: linux-2.6.21-rc7/mm/filemap.c
===================================================================
@@ -925,7 +925,7 @@ page_ok:
 		 * before reading the page on the kernel side.
 		 */
 		if (mapping_writably_mapped(mapping))
-			flush_dcache_page(page);
+			flush_mapping_page(page);
 
 		/*
 		 * When (part of) the same page is read multiple times

@@ -2139,7 +2139,7 @@ generic_file_buffered_write(struct kiocb
 		else
 			copied = filemap_copy_from_user_iovec(page, offset,
 						cur_iov, iov_base, bytes);
-		flush_dcache_page(page);
+		flush_mapping_page(page);
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (status == AOP_TRUNCATED_PAGE) {
 			page_cache_release(page);

Index: linux-2.6.21-rc7/include/linux/mm.h
===================================================================
@@ -1115,7 +1115,7 @@ unsigned long page_cache_readahead(struc
 			  unsigned long size);
 void handle_ra_miss(struct address_space *mapping, 
 		    struct file_ra_state *ra, pgoff_t offset);
-unsigned long max_sane_readahead(unsigned long nr);
+unsigned long max_sane_readahead(unsigned long nr, int order);
 
 /* Do stack extension */
 extern int expand_stack(struct vm_area_struct *vma, unsigned long address);

Index: linux-2.6.21-rc7/mm/fadvise.c
===================================================================
@@ -86,10 +86,11 @@ asmlinkage long sys_fadvise64_64(int fd,
 		nrpages = end_index - start_index + 1;
 		if (!nrpages)
 			nrpages = ~0UL;
-		
+
 		ret = force_page_cache_readahead(mapping, file,
 				start_index,
-				max_sane_readahead(nrpages));
+				max_sane_readahead(nrpages,
+					mapping_order(mapping)));
 		if (ret > 0)
 			ret = 0;
 		break;

Index: linux-2.6.21-rc7/mm/filemap.c
===================================================================
@@ -1246,7 +1246,7 @@ do_readahead(struct address_space *mappi
 		return -EINVAL;
 
 	force_page_cache_readahead(mapping, filp, index,
-					max_sane_readahead(nr));
+				max_sane_readahead(nr, mapping_order(mapping)));
 	return 0;
 }
 

@@ -1381,7 +1381,8 @@ retry_find:
 			count_vm_event(PGMAJFAULT);
 		}
 		did_readaround = 1;
-		ra_pages = max_sane_readahead(file->f_ra.ra_pages);
+		ra_pages = max_sane_readahead(file->f_ra.ra_pages,
+						mapping_order(mapping));
 		if (ra_pages) {
 			pgoff_t start = 0;
 

Index: linux-2.6.21-rc7/mm/madvise.c
===================================================================
@@ -105,7 +105,9 @@ static long madvise_willneed(struct vm_a
 	end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 	force_page_cache_readahead(file->f_mapping,
-			file, start, max_sane_readahead(end - start));
+			file, start,
+			max_sane_readahead(end - start,
+				mapping_order(file->f_mapping)));
 	return 0;
 }
 

Index: linux-2.6.21-rc7/mm/readahead.c
===================================================================
@@ -152,7 +152,7 @@ int read_cache_pages(struct address_spac
 			put_pages_list(pages);
 			break;
 		}
-		task_io_account_read(PAGE_CACHE_SIZE);
+		task_io_account_read(page_cache_size(mapping));
 	}
 	pagevec_lru_add(&lru_pvec);
 	return ret;

@@ -276,7 +276,7 @@ __do_page_cache_readahead(struct address
 	if (isize == 0)
 		goto out;
 
- 	end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+ 	end_index = page_cache_index(mapping, isize - 1);
 
 	/*
 	 * Preallocate as many pages as we will need.

@@ -330,7 +330,11 @@ int force_page_cache_readahead(struct ad
 	while (nr_to_read) {
 		int err;
 
-		unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_CACHE_SIZE;
+		/*
+		 * FIXME: Note the 2M constant here that may prove to
+		 * be a problem if page sizes become bigger than one megabyte.
+		 */
+		unsigned long this_chunk = page_cache_index(mapping, 2 * 1024 * 1024);
 
 		if (this_chunk > nr_to_read)
 			this_chunk = nr_to_read;

@@ -570,11 +574,13 @@ void handle_ra_miss(struct address_space
 }
 
 /*
- * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
+ * Given a desired number of page order readahead pages, return a
  * sensible upper limit.
  */
-unsigned long max_sane_readahead(unsigned long nr)
+unsigned long max_sane_readahead(unsigned long nr, int order)
 {
-	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE)
-		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
+	unsigned long base_pages = node_page_state(numa_node_id(), NR_INACTIVE)
+			+ node_page_state(numa_node_id(), NR_FREE_PAGES);
+
+	return min(nr, (base_pages / 2) >> order);
 }

Index: linux-2.6.21-rc7/mm/vmscan.c
===================================================================
@@ -471,14 +471,14 @@ static unsigned long shrink_page_list(st
 
 		VM_BUG_ON(PageActive(page));
 
-		sc->nr_scanned++;
+		sc->nr_scanned += compound_pages(page);
 
 		if (!sc->may_swap && page_mapped(page))
 			goto keep_locked;
 
 		/* Double the slab pressure for mapped and swapcache pages */
 		if (page_mapped(page) || PageSwapCache(page))
-			sc->nr_scanned++;
+			sc->nr_scanned += compound_pages(page);
 
 		if (PageWriteback(page))
 			goto keep_locked;

@@ -581,7 +581,7 @@ static unsigned long shrink_page_list(st
 
 free_it:
 		unlock_page(page);
-		nr_reclaimed++;
+		nr_reclaimed += compound_pages(page);
 		if (!pagevec_add(&freed_pvec, page))
 			__pagevec_release_nonlru(&freed_pvec);
 		continue;

@@ -627,7 +627,7 @@ static unsigned long isolate_lru_pages(u
 	struct page *page;
 	unsigned long scan;
 
-	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+	for (scan = 0; scan < nr_to_scan && !list_empty(src); ) {
 		struct list_head *target;
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);

@@ -644,10 +644,11 @@ static unsigned long isolate_lru_pages(u
 			 */
 			ClearPageLRU(page);
 			target = dst;
-			nr_taken++;
+			nr_taken += compound_pages(page);
 		} /* else it is being freed elsewhere */
 
 		list_add(&page->lru, target);
+		scan += compound_pages(page);
 	}
 
 	*scanned = scan;

@@ -856,7 +857,7 @@ force_reclaim_mapped:
 		ClearPageActive(page);
 
 		list_move(&page->lru, &zone->inactive_list);
-		pgmoved++;
+		pgmoved += compound_pages(page);
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
 			spin_unlock_irq(&zone->lru_lock);

@@ -884,7 +885,7 @@ force_reclaim_mapped:
 		SetPageLRU(page);
 		VM_BUG_ON(!PageActive(page));
 		list_move(&page->lru, &zone->active_list);
-		pgmoved++;
+		pgmoved += compound_pages(page);
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
 			pgmoved = 0;

Index: linux-2.6.21-rc7/fs/block_dev.c
===================================================================
@@ -60,12 +60,12 @@ static void kill_bdev(struct block_devic
 {
 	invalidate_bdev(bdev, 1);
 	truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
-}	
+}
 
 int set_blocksize(struct block_device *bdev, int size)
 {
-	/* Size must be a power of two, and between 512 and PAGE_SIZE */
-	if (size > PAGE_SIZE || size < 512 || (size & (size-1)))
+	/* Size must be a power of two, and greater than 512 */
+	if (size < 512 || (size & (size-1)))
 		return -EINVAL;
 
 	/* Size cannot be smaller than the size supported by the device */

@@ -74,10 +74,16 @@ int set_blocksize(struct block_device *b
 
 	/* Don't change the size if it is same as current */
 	if (bdev->bd_block_size != size) {
+		int bits = blksize_bits(size);
+		struct address_space *mapping =
+			bdev->bd_inode->i_mapping;
+
 		sync_blockdev(bdev);
-		bdev->bd_block_size = size;
-		bdev->bd_inode->i_blkbits = blksize_bits(size);
 		kill_bdev(bdev);
+		bdev->bd_block_size = size;
+		bdev->bd_inode->i_blkbits = bits;
+		set_mapping_order(mapping,
+			bits < PAGE_SHIFT ? 0 : bits - PAGE_SHIFT);
 	}
 	return 0;
 }

@@ -88,8 +94,10 @@ int sb_set_blocksize(struct super_block 
 {
 	if (set_blocksize(sb->s_bdev, size))
 		return 0;
-	/* If we get here, we know size is power of two
-	 * and it's value is between 512 and PAGE_SIZE */
+	/*
+	 * If we get here, we know size is power of two
+	 * and it's value is larger than 512
+	 */
 	sb->s_blocksize = size;
 	sb->s_blocksize_bits = blksize_bits(size);
 	return sb->s_blocksize;

Index: linux-2.6.21-rc7/fs/buffer.c
===================================================================
@@ -1084,7 +1084,7 @@ __getblk_slow(struct block_device *bdev,
 {
 	/* Size must be multiple of hard sectorsize */
 	if (unlikely(size & (bdev_hardsect_size(bdev)-1) ||
-			(size < 512 || size > PAGE_SIZE))) {
+			size < 512)) {
 		printk(KERN_ERR "getblk(): invalid block size %d requested\n",
 					size);
 		printk(KERN_ERR "hardsect size: %d\n",

Index: linux-2.6.21-rc7/fs/inode.c
===================================================================
@@ -146,6 +146,11 @@ static struct inode *alloc_inode(struct 
  		mapping->host = inode;
 		mapping->flags = 0;
 		mapping_set_gfp_mask(mapping, GFP_HIGHUSER);
+		if (inode->i_blkbits > PAGE_SHIFT)
+			set_mapping_order(mapping,
+				inode->i_blkbits - PAGE_SHIFT);
+		else
+			set_mapping_order(mapping, 0);
 		mapping->assoc_mapping = NULL;
 		mapping->backing_dev_info = &default_backing_dev_info;
 

Index: linux-2.6.21-rc7/mm/filemap.c
===================================================================
@@ -127,6 +127,7 @@ void remove_from_page_cache(struct page 
 	struct address_space *mapping = page->mapping;
 
 	BUG_ON(!PageLocked(page));
+	VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 
 	write_lock_irq(&mapping->tree_lock);
 	__remove_from_page_cache(page);

@@ -268,6 +269,7 @@ int wait_on_page_writeback_range(struct 
 			if (page->index > end)
 				continue;
 
+			VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 			wait_on_page_writeback(page);
 			if (PageError(page))
 				ret = -EIO;

@@ -439,6 +441,7 @@ int add_to_page_cache(struct page *page,
 {
 	int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
 
+	VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 	if (error == 0) {
 		write_lock_irq(&mapping->tree_lock);
 		error = radix_tree_insert(&mapping->page_tree, offset, page);

@@ -598,8 +601,10 @@ struct page * find_get_page(struct addre
 
 	read_lock_irq(&mapping->tree_lock);
 	page = radix_tree_lookup(&mapping->page_tree, offset);
-	if (page)
+	if (page) {
+		VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 		page_cache_get(page);
+	}
 	read_unlock_irq(&mapping->tree_lock);
 	return page;
 }

@@ -624,6 +629,7 @@ struct page *find_lock_page(struct addre
 repeat:
 	page = radix_tree_lookup(&mapping->page_tree, offset);
 	if (page) {
+		VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 		page_cache_get(page);
 		if (TestSetPageLocked(page)) {
 			read_unlock_irq(&mapping->tree_lock);

@@ -685,6 +691,7 @@ repeat:
 		} else if (err == -EEXIST)
 			goto repeat;
 	}
+	VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 	if (cached_page)
 		page_cache_release(cached_page);
 	return page;

@@ -716,8 +723,10 @@ unsigned find_get_pages(struct address_s
 	read_lock_irq(&mapping->tree_lock);
 	ret = radix_tree_gang_lookup(&mapping->page_tree,
 				(void **)pages, start, nr_pages);
-	for (i = 0; i < ret; i++)
+	for (i = 0; i < ret; i++) {
+		VM_BUG_ON(mapping_order(mapping) != compound_order(pages[i]));
 		page_cache_get(pages[i]);
+	}
 	read_unlock_irq(&mapping->tree_lock);
 	return ret;
 }

@@ -747,6 +756,7 @@ unsigned find_get_pages_contig(struct ad
 		if (pages[i]->mapping == NULL || pages[i]->index != index)
 			break;
 
+		VM_BUG_ON(mapping_order(mapping) != compound_order(pages[i]));
 		page_cache_get(pages[i]);
 		index++;
 	}

@@ -774,8 +784,10 @@ unsigned find_get_pages_tag(struct addre
 	read_lock_irq(&mapping->tree_lock);
 	ret = radix_tree_gang_lookup_tag(&mapping->page_tree,
 				(void **)pages, *index, nr_pages, tag);
-	for (i = 0; i < ret; i++)
+	for (i = 0; i < ret; i++) {
+		VM_BUG_ON(mapping_order(mapping) != compound_order(pages[i]));
 		page_cache_get(pages[i]);
+	}
 	if (ret)
 		*index = pages[ret - 1]->index + 1;
 	read_unlock_irq(&mapping->tree_lock);

@@ -2457,6 +2469,7 @@ int try_to_release_page(struct page *pag
 	struct address_space * const mapping = page->mapping;
 
 	BUG_ON(!PageLocked(page));
+	VM_BUG_ON(mapping_order(mapping) != compound_order(page));
 	if (PageWriteback(page))
 		return 0;
 

Index: linux-2.6.21-rc7/fs/ramfs/file-mmu.c
===================================================================
@@ -45,6 +45,17 @@ const struct file_operations ramfs_file_
 	.llseek		= generic_file_llseek,
 };
 
+/* Higher order mappings do not support mmmap */
+const struct file_operations ramfs_file_higher_order_operations = {
+	.read		= do_sync_read,
+	.aio_read	= generic_file_aio_read,
+	.write		= do_sync_write,
+	.aio_write	= generic_file_aio_write,
+	.fsync		= simple_sync_file,
+	.sendfile	= generic_file_sendfile,
+	.llseek		= generic_file_llseek,
+};
+
 const struct inode_operations ramfs_file_inode_operations = {
 	.getattr	= simple_getattr,
 };

Index: linux-2.6.21-rc7/fs/ramfs/inode.c
===================================================================
@@ -61,6 +61,8 @@ struct inode *ramfs_get_inode(struct sup
 		inode->i_blocks = 0;
 		inode->i_mapping->a_ops = &ramfs_aops;
 		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
+		set_mapping_order(inode->i_mapping,
+			sb->s_blocksize_bits - PAGE_CACHE_SHIFT);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		switch (mode & S_IFMT) {
 		default:

@@ -68,7 +70,10 @@ struct inode *ramfs_get_inode(struct sup
 			break;
 		case S_IFREG:
 			inode->i_op = &ramfs_file_inode_operations;
-			inode->i_fop = &ramfs_file_operations;
+			if (mapping_order(inode->i_mapping))
+				inode->i_fop = &ramfs_file_higher_order_operations;
+			else
+				inode->i_fop = &ramfs_file_operations;
 			break;
 		case S_IFDIR:
 			inode->i_op = &ramfs_dir_inode_operations;

@@ -164,10 +169,15 @@ static int ramfs_fill_super(struct super
 {
 	struct inode * inode;
 	struct dentry * root;
+	int order = 0;
+	char *options = data;
+
+	if (options && *options)
+		order = simple_strtoul(options, NULL, 10);
 
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
-	sb->s_blocksize = PAGE_CACHE_SIZE;
-	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
+	sb->s_blocksize = PAGE_CACHE_SIZE << order;
+	sb->s_blocksize_bits = order + PAGE_CACHE_SHIFT;
 	sb->s_magic = RAMFS_MAGIC;
 	sb->s_op = &ramfs_ops;
 	sb->s_time_gran = 1;

Index: linux-2.6.21-rc7/include/linux/ramfs.h
===================================================================
@@ -16,6 +16,7 @@ extern int ramfs_nommu_mmap(struct file 
 #endif
 
 extern const struct file_operations ramfs_file_operations;
+extern const struct file_operations ramfs_file_higher_order_operations;
 extern struct vm_operations_struct generic_file_vm_ops;
 extern int __init init_rootfs(void);
 

Index: linux-2.6.21-rc7/fs/ext2/dir.c
===================================================================
@@ -44,7 +44,8 @@ static inline void ext2_put_page(struct 
 
 static inline unsigned long dir_pages(struct inode *inode)
 {
-	return (inode->i_size+PAGE_CACHE_SIZE-1)>>PAGE_CACHE_SHIFT;
+	return (inode->i_size+page_cache_size(inode->i_mapping)-1)>>
+			page_cache_shift(inode->i_mapping);
 }
 
 /*

@@ -55,10 +56,11 @@ static unsigned
 ext2_last_byte(struct inode *inode, unsigned long page_nr)
 {
 	unsigned last_byte = inode->i_size;
+	struct address_space *mapping = inode->i_mapping;
 
-	last_byte -= page_nr << PAGE_CACHE_SHIFT;
-	if (last_byte > PAGE_CACHE_SIZE)
-		last_byte = PAGE_CACHE_SIZE;
+	last_byte -= page_nr << page_cache_shift(mapping);
+	if (last_byte > page_cache_size(mapping))
+		last_byte = page_cache_size(mapping);
 	return last_byte;
 }
 

@@ -77,18 +79,19 @@ static int ext2_commit_chunk(struct page
 
 static void ext2_check_page(struct page *page)
 {
-	struct inode *dir = page->mapping->host;
+	struct address_space *mapping = page->mapping;
+	struct inode *dir = mapping->host;
 	struct super_block *sb = dir->i_sb;
 	unsigned chunk_size = ext2_chunk_size(dir);
 	char *kaddr = page_address(page);
 	u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
 	unsigned offs, rec_len;
-	unsigned limit = PAGE_CACHE_SIZE;
+	unsigned limit = page_cache_size(mapping);
 	ext2_dirent *p;
 	char *error;
 
-	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
-		limit = dir->i_size & ~PAGE_CACHE_MASK;
+	if (page_cache_index(mapping, dir->i_size) == page->index) {
+		limit = page_cache_offset(mapping, dir->i_size);
 		if (limit & (chunk_size - 1))
 			goto Ebadsize;
 		if (!limit)

@@ -140,7 +143,7 @@ Einumber:
 bad_entry:
 	ext2_error (sb, "ext2_check_page", "bad entry in directory #%lu: %s - "
 		"offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
-		dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		dir->i_ino, error, page_cache_pos(mapping, page->index, offs),
 		(unsigned long) le32_to_cpu(p->inode),
 		rec_len, p->name_len);
 	goto fail;

@@ -149,7 +152,7 @@ Eend:
 	ext2_error (sb, "ext2_check_page",
 		"entry in directory #%lu spans the page boundary"
 		"offset=%lu, inode=%lu",
-		dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		dir->i_ino, page_cache_pos(mapping, page->index, offs),
 		(unsigned long) le32_to_cpu(p->inode));
 fail:
 	SetPageChecked(page);

@@ -250,8 +253,9 @@ ext2_readdir (struct file * filp, void *
 	loff_t pos = filp->f_pos;
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct super_block *sb = inode->i_sb;
-	unsigned int offset = pos & ~PAGE_CACHE_MASK;
-	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	struct address_space *mapping = inode->i_mapping;
+	unsigned int offset = page_cache_offset(mapping, pos);
+	unsigned long n = page_cache_index(mapping, pos);
 	unsigned long npages = dir_pages(inode);
 	unsigned chunk_mask = ~(ext2_chunk_size(inode)-1);
 	unsigned char *types = NULL;

@@ -272,14 +276,14 @@ ext2_readdir (struct file * filp, void *
 			ext2_error(sb, __FUNCTION__,
 				   "bad page in #%lu",
 				   inode->i_ino);
-			filp->f_pos += PAGE_CACHE_SIZE - offset;
+			filp->f_pos += page_cache_size(mapping) - offset;
 			return -EIO;
 		}
 		kaddr = page_address(page);
 		if (unlikely(need_revalidate)) {
 			if (offset) {
 				offset = ext2_validate_entry(kaddr, offset, chunk_mask);
-				filp->f_pos = (n<<PAGE_CACHE_SHIFT) + offset;
+				filp->f_pos = page_cache_pos(mapping, n, offset);
 			}
 			filp->f_version = inode->i_version;
 			need_revalidate = 0;

@@ -302,7 +306,7 @@ ext2_readdir (struct file * filp, void *
 
 				offset = (char *)de - kaddr;
 				over = filldir(dirent, de->name, de->name_len,
-						(n<<PAGE_CACHE_SHIFT) | offset,
+						page_cache_pos(mapping, n, offset),
 						le32_to_cpu(de->inode), d_type);
 				if (over) {
 					ext2_put_page(page);

@@ -328,6 +332,7 @@ struct ext2_dir_entry_2 * ext2_find_entr
 			struct dentry *dentry, struct page ** res_page)
 {
 	const char *name = dentry->d_name.name;
+	struct address_space *mapping = dir->i_mapping;
 	int namelen = dentry->d_name.len;
 	unsigned reclen = EXT2_DIR_REC_LEN(namelen);
 	unsigned long start, n;

@@ -369,7 +374,7 @@ struct ext2_dir_entry_2 * ext2_find_entr
 		if (++n >= npages)
 			n = 0;
 		/* next page is past the blocks we've got */
-		if (unlikely(n > (dir->i_blocks >> (PAGE_CACHE_SHIFT - 9)))) {
+		if (unlikely(n > (dir->i_blocks >> (page_cache_shift(mapping) - 9)))) {
 			ext2_error(dir->i_sb, __FUNCTION__,
 				"dir %lu size %lld exceeds block count %llu",
 				dir->i_ino, dir->i_size,

@@ -438,6 +443,7 @@ void ext2_set_link(struct inode *dir, st
 int ext2_add_link (struct dentry *dentry, struct inode *inode)
 {
 	struct inode *dir = dentry->d_parent->d_inode;
+	struct address_space *mapping = inode->i_mapping;
 	const char *name = dentry->d_name.name;
 	int namelen = dentry->d_name.len;
 	unsigned chunk_size = ext2_chunk_size(dir);

@@ -467,7 +473,7 @@ int ext2_add_link (struct dentry *dentry
 		kaddr = page_address(page);
 		dir_end = kaddr + ext2_last_byte(dir, n);
 		de = (ext2_dirent *)kaddr;
-		kaddr += PAGE_CACHE_SIZE - reclen;
+		kaddr += page_cache_size(mapping) - reclen;
 		while ((char *)de <= kaddr) {
 			if ((char *)de == dir_end) {
 				/* We hit i_size */

Index: linux-2.6.21-rc7/fs/ext2/ext2.h
===================================================================
@@ -160,6 +160,7 @@ extern const struct file_operations ext2
 /* file.c */
 extern const struct inode_operations ext2_file_inode_operations;
 extern const struct file_operations ext2_file_operations;
+extern const struct file_operations ext2_no_mmap_file_operations;
 extern const struct file_operations ext2_xip_file_operations;
 
 /* inode.c */

Index: linux-2.6.21-rc7/fs/ext2/file.c
===================================================================
@@ -58,6 +58,24 @@ const struct file_operations ext2_file_o
 	.splice_write	= generic_file_splice_write,
 };
 
+const struct file_operations ext2_no_mmap_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= generic_file_aio_write,
+	.ioctl		= ext2_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= ext2_compat_ioctl,
+#endif
+	.open		= generic_file_open,
+	.release	= ext2_release_file,
+	.fsync		= ext2_sync_file,
+	.sendfile	= generic_file_sendfile,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+};
+
 #ifdef CONFIG_EXT2_FS_XIP
 const struct file_operations ext2_xip_file_operations = {
 	.llseek		= generic_file_llseek,

Index: linux-2.6.21-rc7/fs/ext2/inode.c
===================================================================
@@ -1128,10 +1128,16 @@ void ext2_read_inode (struct inode * ino
 			inode->i_fop = &ext2_xip_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
-			inode->i_fop = &ext2_file_operations;
+			if (mapping_order(inode->i_mapping))
+				inode->i_fop = &ext2_no_mmap_file_operations;
+			else
+				inode->i_fop = &ext2_file_operations;
 		} else {
 			inode->i_mapping->a_ops = &ext2_aops;
-			inode->i_fop = &ext2_file_operations;
+			if (mapping_order(inode->i_mapping))
+				inode->i_fop = &ext2_no_mmap_file_operations;
+			else
+				inode->i_fop = &ext2_file_operations;
 		}
 	} else if (S_ISDIR(inode->i_mode)) {
 		inode->i_op = &ext2_dir_inode_operations;

Index: linux-2.6.21-rc7/fs/ext2/namei.c
===================================================================
@@ -114,10 +114,16 @@ static int ext2_create (struct inode * d
 			inode->i_fop = &ext2_xip_file_operations;
 		} else if (test_opt(inode->i_sb, NOBH)) {
 			inode->i_mapping->a_ops = &ext2_nobh_aops;
-			inode->i_fop = &ext2_file_operations;
+			if (mapping_order(inode->i_mapping))
+				inode->i_fop = &ext2_no_mmap_file_operations;
+			else
+				inode->i_fop = &ext2_file_operations;
 		} else {
 			inode->i_mapping->a_ops = &ext2_aops;
-			inode->i_fop = &ext2_file_operations;
+			if (mapping_order(inode->i_mapping))
+				inode->i_fop = &ext2_no_mmap_file_operations;
+			else
+				inode->i_fop = &ext2_file_operations;
 		}
 		mark_inode_dirty(inode);
 		err = ext2_add_nondir(dentry, inode);

@@ -330,7 +330,7 @@
 int simple_prepare_write(struct file *file, struct page *page,
 			unsigned from, unsigned to)
 {
-	unsigned int page_size = page_cache_size(file->f_mapping);
+	unsigned int page_size = page_cache_size(page->mapping);
 
 	if (!PageUptodate(page)) {
 		if (to - from != page_size) {