Linux-2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

37 files changed, 28187 insertions, 0 deletions

diff --git a/mm/Makefile b/mm/Makefile
new file mode 100644
index 000000000000..097408064f6a
--- /dev/null
+++ b/mm/Makefile
@@ -0,0 +1,20 @@
+#
+# Makefile for the linux memory manager.
+#
+
+mmu-y			:= nommu.o
+mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
+			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
+			   vmalloc.o
+
+obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
+			   page_alloc.o page-writeback.o pdflush.o \
+			   readahead.o slab.o swap.o truncate.o vmscan.o \
+			   prio_tree.o $(mmu-y)
+
+obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
+obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
+obj-$(CONFIG_NUMA) 	+= mempolicy.o
+obj-$(CONFIG_SHMEM) += shmem.o
+obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
+
diff --git a/mm/bootmem.c b/mm/bootmem.c
new file mode 100644
index 000000000000..260e703850d8
--- /dev/null
+++ b/mm/bootmem.c
@@ -0,0 +1,400 @@
+/*
+ *  linux/mm/bootmem.c
+ *
+ *  Copyright (C) 1999 Ingo Molnar
+ *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
+ *
+ *  simple boot-time physical memory area allocator and
+ *  free memory collector. It's used to deal with reserved
+ *  system memory and memory holes as well.
+ */
+
+#include <linux/mm.h>
+#include <linux/kernel_stat.h>
+#include <linux/swap.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <asm/dma.h>
+#include <asm/io.h>
+#include "internal.h"
+
+/*
+ * Access to this subsystem has to be serialized externally. (this is
+ * true for the boot process anyway)
+ */
+unsigned long max_low_pfn;
+unsigned long min_low_pfn;
+unsigned long max_pfn;
+
+EXPORT_SYMBOL(max_pfn);		/* This is exported so
+				 * dma_get_required_mask(), which uses
+				 * it, can be an inline function */
+
+/* return the number of _pages_ that will be allocated for the boot bitmap */
+unsigned long __init bootmem_bootmap_pages (unsigned long pages)
+{
+	unsigned long mapsize;
+
+	mapsize = (pages+7)/8;
+	mapsize = (mapsize + ~PAGE_MASK) & PAGE_MASK;
+	mapsize >>= PAGE_SHIFT;
+
+	return mapsize;
+}
+
+/*
+ * Called once to set up the allocator itself.
+ */
+static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
+	unsigned long mapstart, unsigned long start, unsigned long end)
+{
+	bootmem_data_t *bdata = pgdat->bdata;
+	unsigned long mapsize = ((end - start)+7)/8;
+
+	pgdat->pgdat_next = pgdat_list;
+	pgdat_list = pgdat;
+
+	mapsize = (mapsize + (sizeof(long) - 1UL)) & ~(sizeof(long) - 1UL);
+	bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
+	bdata->node_boot_start = (start << PAGE_SHIFT);
+	bdata->node_low_pfn = end;
+
+	/*
+	 * Initially all pages are reserved - setup_arch() has to
+	 * register free RAM areas explicitly.
+	 */
+	memset(bdata->node_bootmem_map, 0xff, mapsize);
+
+	return mapsize;
+}
+
+/*
+ * Marks a particular physical memory range as unallocatable. Usable RAM
+ * might be used for boot-time allocations - or it might get added
+ * to the free page pool later on.
+ */
+static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
+{
+	unsigned long i;
+	/*
+	 * round up, partially reserved pages are considered
+	 * fully reserved.
+	 */
+	unsigned long sidx = (addr - bdata->node_boot_start)/PAGE_SIZE;
+	unsigned long eidx = (addr + size - bdata->node_boot_start + 
+							PAGE_SIZE-1)/PAGE_SIZE;
+	unsigned long end = (addr + size + PAGE_SIZE-1)/PAGE_SIZE;
+
+	BUG_ON(!size);
+	BUG_ON(sidx >= eidx);
+	BUG_ON((addr >> PAGE_SHIFT) >= bdata->node_low_pfn);
+	BUG_ON(end > bdata->node_low_pfn);
+
+	for (i = sidx; i < eidx; i++)
+		if (test_and_set_bit(i, bdata->node_bootmem_map)) {
+#ifdef CONFIG_DEBUG_BOOTMEM
+			printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE);
+#endif
+		}
+}
+
+static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
+{
+	unsigned long i;
+	unsigned long start;
+	/*
+	 * round down end of usable mem, partially free pages are
+	 * considered reserved.
+	 */
+	unsigned long sidx;
+	unsigned long eidx = (addr + size - bdata->node_boot_start)/PAGE_SIZE;
+	unsigned long end = (addr + size)/PAGE_SIZE;
+
+	BUG_ON(!size);
+	BUG_ON(end > bdata->node_low_pfn);
+
+	if (addr < bdata->last_success)
+		bdata->last_success = addr;
+
+	/*
+	 * Round up the beginning of the address.
+	 */
+	start = (addr + PAGE_SIZE-1) / PAGE_SIZE;
+	sidx = start - (bdata->node_boot_start/PAGE_SIZE);
+
+	for (i = sidx; i < eidx; i++) {
+		if (unlikely(!test_and_clear_bit(i, bdata->node_bootmem_map)))
+			BUG();
+	}
+}
+
+/*
+ * We 'merge' subsequent allocations to save space. We might 'lose'
+ * some fraction of a page if allocations cannot be satisfied due to
+ * size constraints on boxes where there is physical RAM space
+ * fragmentation - in these cases (mostly large memory boxes) this
+ * is not a problem.
+ *
+ * On low memory boxes we get it right in 100% of the cases.
+ *
+ * alignment has to be a power of 2 value.
+ *
+ * NOTE:  This function is _not_ reentrant.
+ */
+static void * __init
+__alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
+		unsigned long align, unsigned long goal)
+{
+	unsigned long offset, remaining_size, areasize, preferred;
+	unsigned long i, start = 0, incr, eidx;
+	void *ret;
+
+	if(!size) {
+		printk("__alloc_bootmem_core(): zero-sized request\n");
+		BUG();
+	}
+	BUG_ON(align & (align-1));
+
+	eidx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
+	offset = 0;
+	if (align &&
+	    (bdata->node_boot_start & (align - 1UL)) != 0)
+		offset = (align - (bdata->node_boot_start & (align - 1UL)));
+	offset >>= PAGE_SHIFT;
+
+	/*
+	 * We try to allocate bootmem pages above 'goal'
+	 * first, then we try to allocate lower pages.
+	 */
+	if (goal && (goal >= bdata->node_boot_start) && 
+	    ((goal >> PAGE_SHIFT) < bdata->node_low_pfn)) {
+		preferred = goal - bdata->node_boot_start;
+
+		if (bdata->last_success >= preferred)
+			preferred = bdata->last_success;
+	} else
+		preferred = 0;
+
+	preferred = ((preferred + align - 1) & ~(align - 1)) >> PAGE_SHIFT;
+	preferred += offset;
+	areasize = (size+PAGE_SIZE-1)/PAGE_SIZE;
+	incr = align >> PAGE_SHIFT ? : 1;
+
+restart_scan:
+	for (i = preferred; i < eidx; i += incr) {
+		unsigned long j;
+		i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
+		i = ALIGN(i, incr);
+		if (test_bit(i, bdata->node_bootmem_map))
+			continue;
+		for (j = i + 1; j < i + areasize; ++j) {
+			if (j >= eidx)
+				goto fail_block;
+			if (test_bit (j, bdata->node_bootmem_map))
+				goto fail_block;
+		}
+		start = i;
+		goto found;
+	fail_block:
+		i = ALIGN(j, incr);
+	}
+
+	if (preferred > offset) {
+		preferred = offset;
+		goto restart_scan;
+	}
+	return NULL;
+
+found:
+	bdata->last_success = start << PAGE_SHIFT;
+	BUG_ON(start >= eidx);
+
+	/*
+	 * Is the next page of the previous allocation-end the start
+	 * of this allocation's buffer? If yes then we can 'merge'
+	 * the previous partial page with this allocation.
+	 */
+	if (align < PAGE_SIZE &&
+	    bdata->last_offset && bdata->last_pos+1 == start) {
+		offset = (bdata->last_offset+align-1) & ~(align-1);
+		BUG_ON(offset > PAGE_SIZE);
+		remaining_size = PAGE_SIZE-offset;
+		if (size < remaining_size) {
+			areasize = 0;
+			/* last_pos unchanged */
+			bdata->last_offset = offset+size;
+			ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
+						bdata->node_boot_start);
+		} else {
+			remaining_size = size - remaining_size;
+			areasize = (remaining_size+PAGE_SIZE-1)/PAGE_SIZE;
+			ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
+						bdata->node_boot_start);
+			bdata->last_pos = start+areasize-1;
+			bdata->last_offset = remaining_size;
+		}
+		bdata->last_offset &= ~PAGE_MASK;
+	} else {
+		bdata->last_pos = start + areasize - 1;
+		bdata->last_offset = size & ~PAGE_MASK;
+		ret = phys_to_virt(start * PAGE_SIZE + bdata->node_boot_start);
+	}
+
+	/*
+	 * Reserve the area now:
+	 */
+	for (i = start; i < start+areasize; i++)
+		if (unlikely(test_and_set_bit(i, bdata->node_bootmem_map)))
+			BUG();
+	memset(ret, 0, size);
+	return ret;
+}
+
+static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
+{
+	struct page *page;
+	bootmem_data_t *bdata = pgdat->bdata;
+	unsigned long i, count, total = 0;
+	unsigned long idx;
+	unsigned long *map; 
+	int gofast = 0;
+
+	BUG_ON(!bdata->node_bootmem_map);
+
+	count = 0;
+	/* first extant page of the node */
+	page = virt_to_page(phys_to_virt(bdata->node_boot_start));
+	idx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
+	map = bdata->node_bootmem_map;
+	/* Check physaddr is O(LOG2(BITS_PER_LONG)) page aligned */
+	if (bdata->node_boot_start == 0 ||
+	    ffs(bdata->node_boot_start) - PAGE_SHIFT > ffs(BITS_PER_LONG))
+		gofast = 1;
+	for (i = 0; i < idx; ) {
+		unsigned long v = ~map[i / BITS_PER_LONG];
+		if (gofast && v == ~0UL) {
+			int j, order;
+
+			count += BITS_PER_LONG;
+			__ClearPageReserved(page);
+			order = ffs(BITS_PER_LONG) - 1;
+			set_page_refs(page, order);
+			for (j = 1; j < BITS_PER_LONG; j++) {
+				if (j + 16 < BITS_PER_LONG)
+					prefetchw(page + j + 16);
+				__ClearPageReserved(page + j);
+			}
+			__free_pages(page, order);
+			i += BITS_PER_LONG;
+			page += BITS_PER_LONG;
+		} else if (v) {
+			unsigned long m;
+			for (m = 1; m && i < idx; m<<=1, page++, i++) {
+				if (v & m) {
+					count++;
+					__ClearPageReserved(page);
+					set_page_refs(page, 0);
+					__free_page(page);
+				}
+			}
+		} else {
+			i+=BITS_PER_LONG;
+			page += BITS_PER_LONG;
+		}
+	}
+	total += count;
+
+	/*
+	 * Now free the allocator bitmap itself, it's not
+	 * needed anymore:
+	 */
+	page = virt_to_page(bdata->node_bootmem_map);
+	count = 0;
+	for (i = 0; i < ((bdata->node_low_pfn-(bdata->node_boot_start >> PAGE_SHIFT))/8 + PAGE_SIZE-1)/PAGE_SIZE; i++,page++) {
+		count++;
+		__ClearPageReserved(page);
+		set_page_count(page, 1);
+		__free_page(page);
+	}
+	total += count;
+	bdata->node_bootmem_map = NULL;
+
+	return total;
+}
+
+unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, unsigned long endpfn)
+{
+	return(init_bootmem_core(pgdat, freepfn, startpfn, endpfn));
+}
+
+void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
+{
+	reserve_bootmem_core(pgdat->bdata, physaddr, size);
+}
+
+void __init free_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
+{
+	free_bootmem_core(pgdat->bdata, physaddr, size);
+}
+
+unsigned long __init free_all_bootmem_node (pg_data_t *pgdat)
+{
+	return(free_all_bootmem_core(pgdat));
+}
+
+unsigned long __init init_bootmem (unsigned long start, unsigned long pages)
+{
+	max_low_pfn = pages;
+	min_low_pfn = start;
+	return(init_bootmem_core(NODE_DATA(0), start, 0, pages));
+}
+
+#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
+void __init reserve_bootmem (unsigned long addr, unsigned long size)
+{
+	reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size);
+}
+#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
+
+void __init free_bootmem (unsigned long addr, unsigned long size)
+{
+	free_bootmem_core(NODE_DATA(0)->bdata, addr, size);
+}
+
+unsigned long __init free_all_bootmem (void)
+{
+	return(free_all_bootmem_core(NODE_DATA(0)));
+}
+
+void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal)
+{
+	pg_data_t *pgdat = pgdat_list;
+	void *ptr;
+
+	for_each_pgdat(pgdat)
+		if ((ptr = __alloc_bootmem_core(pgdat->bdata, size,
+						align, goal)))
+			return(ptr);
+
+	/*
+	 * Whoops, we cannot satisfy the allocation request.
+	 */
+	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
+	panic("Out of memory");
+	return NULL;
+}
+
+void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal)
+{
+	void *ptr;
+
+	ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal);
+	if (ptr)
+		return (ptr);
+
+	return __alloc_bootmem(size, align, goal);
+}
+
diff --git a/mm/fadvise.c b/mm/fadvise.c
new file mode 100644
index 000000000000..57264d74b8bf
--- /dev/null
+++ b/mm/fadvise.c
@@ -0,0 +1,111 @@
+/*
+ * mm/fadvise.c
+ *
+ * Copyright (C) 2002, Linus Torvalds
+ *
+ * 11Jan2003	akpm@digeo.com
+ *		Initial version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/backing-dev.h>
+#include <linux/pagevec.h>
+#include <linux/fadvise.h>
+#include <linux/syscalls.h>
+
+#include <asm/unistd.h>
+
+/*
+ * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
+ * deactivate the pages and clear PG_Referenced.
+ */
+asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+{
+	struct file *file = fget(fd);
+	struct address_space *mapping;
+	struct backing_dev_info *bdi;
+	loff_t endbyte;
+	pgoff_t start_index;
+	pgoff_t end_index;
+	unsigned long nrpages;
+	int ret = 0;
+
+	if (!file)
+		return -EBADF;
+
+	mapping = file->f_mapping;
+	if (!mapping || len < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Careful about overflows. Len == 0 means "as much as possible" */
+	endbyte = offset + len;
+	if (!len || endbyte < len)
+		endbyte = -1;
+
+	bdi = mapping->backing_dev_info;
+
+	switch (advice) {
+	case POSIX_FADV_NORMAL:
+		file->f_ra.ra_pages = bdi->ra_pages;
+		break;
+	case POSIX_FADV_RANDOM:
+		file->f_ra.ra_pages = 0;
+		break;
+	case POSIX_FADV_SEQUENTIAL:
+		file->f_ra.ra_pages = bdi->ra_pages * 2;
+		break;
+	case POSIX_FADV_WILLNEED:
+	case POSIX_FADV_NOREUSE:
+		if (!mapping->a_ops->readpage) {
+			ret = -EINVAL;
+			break;
+		}
+
+		/* First and last PARTIAL page! */
+		start_index = offset >> PAGE_CACHE_SHIFT;
+		end_index = (endbyte-1) >> PAGE_CACHE_SHIFT;
+
+		/* Careful about overflow on the "+1" */
+		nrpages = end_index - start_index + 1;
+		if (!nrpages)
+			nrpages = ~0UL;
+		
+		ret = force_page_cache_readahead(mapping, file,
+				start_index,
+				max_sane_readahead(nrpages));
+		if (ret > 0)
+			ret = 0;
+		break;
+	case POSIX_FADV_DONTNEED:
+		if (!bdi_write_congested(mapping->backing_dev_info))
+			filemap_flush(mapping);
+
+		/* First and last FULL page! */
+		start_index = (offset + (PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
+		end_index = (endbyte >> PAGE_CACHE_SHIFT);
+
+		if (end_index > start_index)
+			invalidate_mapping_pages(mapping, start_index, end_index-1);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+out:
+	fput(file);
+	return ret;
+}
+
+#ifdef __ARCH_WANT_SYS_FADVISE64
+
+asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice)
+{
+	return sys_fadvise64_64(fd, offset, len, advice);
+}
+
+#endif
diff --git a/mm/filemap.c b/mm/filemap.c
new file mode 100644
index 000000000000..439b2bea8e34
--- /dev/null
+++ b/mm/filemap.c
@@ -0,0 +1,2306 @@
+/*
+ *	linux/mm/filemap.c
+ *
+ * Copyright (C) 1994-1999  Linus Torvalds
+ */
+
+/*
+ * This file handles the generic file mmap semantics used by
+ * most "normal" filesystems (but you don't /have/ to use this:
+ * the NFS filesystem used to do this differently, for example)
+ */
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/compiler.h>
+#include <linux/fs.h>
+#include <linux/aio.h>
+#include <linux/kernel_stat.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/hash.h>
+#include <linux/writeback.h>
+#include <linux/pagevec.h>
+#include <linux/blkdev.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+/*
+ * This is needed for the following functions:
+ *  - try_to_release_page
+ *  - block_invalidatepage
+ *  - generic_osync_inode
+ *
+ * FIXME: remove all knowledge of the buffer layer from the core VM
+ */
+#include <linux/buffer_head.h> /* for generic_osync_inode */
+
+#include <asm/uaccess.h>
+#include <asm/mman.h>
+
+/*
+ * Shared mappings implemented 30.11.1994. It's not fully working yet,
+ * though.
+ *
+ * Shared mappings now work. 15.8.1995  Bruno.
+ *
+ * finished 'unifying' the page and buffer cache and SMP-threaded the
+ * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com>
+ *
+ * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de>
+ */
+
+/*
+ * Lock ordering:
+ *
+ *  ->i_mmap_lock		(vmtruncate)
+ *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
+ *      ->swap_list_lock
+ *        ->swap_device_lock	(exclusive_swap_page, others)
+ *          ->mapping->tree_lock
+ *
+ *  ->i_sem
+ *    ->i_mmap_lock		(truncate->unmap_mapping_range)
+ *
+ *  ->mmap_sem
+ *    ->i_mmap_lock
+ *      ->page_table_lock	(various places, mainly in mmap.c)
+ *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock)
+ *
+ *  ->mmap_sem
+ *    ->lock_page		(access_process_vm)
+ *
+ *  ->mmap_sem
+ *    ->i_sem			(msync)
+ *
+ *  ->i_sem
+ *    ->i_alloc_sem             (various)
+ *
+ *  ->inode_lock
+ *    ->sb_lock			(fs/fs-writeback.c)
+ *    ->mapping->tree_lock	(__sync_single_inode)
+ *
+ *  ->i_mmap_lock
+ *    ->anon_vma.lock		(vma_adjust)
+ *
+ *  ->anon_vma.lock
+ *    ->page_table_lock		(anon_vma_prepare and various)
+ *
+ *  ->page_table_lock
+ *    ->swap_device_lock	(try_to_unmap_one)
+ *    ->private_lock		(try_to_unmap_one)
+ *    ->tree_lock		(try_to_unmap_one)
+ *    ->zone.lru_lock		(follow_page->mark_page_accessed)
+ *    ->private_lock		(page_remove_rmap->set_page_dirty)
+ *    ->tree_lock		(page_remove_rmap->set_page_dirty)
+ *    ->inode_lock		(page_remove_rmap->set_page_dirty)
+ *    ->inode_lock		(zap_pte_range->set_page_dirty)
+ *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
+ *
+ *  ->task->proc_lock
+ *    ->dcache_lock		(proc_pid_lookup)
+ */
+
+/*
+ * Remove a page from the page cache and free it. Caller has to make
+ * sure the page is locked and that nobody else uses it - or that usage
+ * is safe.  The caller must hold a write_lock on the mapping's tree_lock.
+ */
+void __remove_from_page_cache(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+
+	radix_tree_delete(&mapping->page_tree, page->index);
+	page->mapping = NULL;
+	mapping->nrpages--;
+	pagecache_acct(-1);
+}
+
+void remove_from_page_cache(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+
+	if (unlikely(!PageLocked(page)))
+		PAGE_BUG(page);
+
+	write_lock_irq(&mapping->tree_lock);
+	__remove_from_page_cache(page);
+	write_unlock_irq(&mapping->tree_lock);
+}
+
+static int sync_page(void *word)
+{
+	struct address_space *mapping;
+	struct page *page;
+
+	page = container_of((page_flags_t *)word, struct page, flags);
+
+	/*
+	 * FIXME, fercrissake.  What is this barrier here for?
+	 */
+	smp_mb();
+	mapping = page_mapping(page);
+	if (mapping && mapping->a_ops && mapping->a_ops->sync_page)
+		mapping->a_ops->sync_page(page);
+	io_schedule();
+	return 0;
+}
+
+/**
+ * filemap_fdatawrite_range - start writeback against all of a mapping's
+ * dirty pages that lie within the byte offsets <start, end>
+ * @mapping: address space structure to write
+ * @start: offset in bytes where the range starts
+ * @end : offset in bytes where the range ends
+ *
+ * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
+ * opposed to a regular memory * cleansing writeback.  The difference between
+ * these two operations is that if a dirty page/buffer is encountered, it must
+ * be waited upon, and not just skipped over.
+ */
+static int __filemap_fdatawrite_range(struct address_space *mapping,
+	loff_t start, loff_t end, int sync_mode)
+{
+	int ret;
+	struct writeback_control wbc = {
+		.sync_mode = sync_mode,
+		.nr_to_write = mapping->nrpages * 2,
+		.start = start,
+		.end = end,
+	};
+
+	if (!mapping_cap_writeback_dirty(mapping))
+		return 0;
+
+	ret = do_writepages(mapping, &wbc);
+	return ret;
+}
+
+static inline int __filemap_fdatawrite(struct address_space *mapping,
+	int sync_mode)
+{
+	return __filemap_fdatawrite_range(mapping, 0, 0, sync_mode);
+}
+
+int filemap_fdatawrite(struct address_space *mapping)
+{
+	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);
+}
+EXPORT_SYMBOL(filemap_fdatawrite);
+
+static int filemap_fdatawrite_range(struct address_space *mapping,
+	loff_t start, loff_t end)
+{
+	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
+}
+
+/*
+ * This is a mostly non-blocking flush.  Not suitable for data-integrity
+ * purposes - I/O may not be started against all dirty pages.
+ */
+int filemap_flush(struct address_space *mapping)
+{
+	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);
+}
+EXPORT_SYMBOL(filemap_flush);
+
+/*
+ * Wait for writeback to complete against pages indexed by start->end
+ * inclusive
+ */
+static int wait_on_page_writeback_range(struct address_space *mapping,
+				pgoff_t start, pgoff_t end)
+{
+	struct pagevec pvec;
+	int nr_pages;
+	int ret = 0;
+	pgoff_t index;
+
+	if (end < start)
+		return 0;
+
+	pagevec_init(&pvec, 0);
+	index = start;
+	while ((index <= end) &&
+			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+			PAGECACHE_TAG_WRITEBACK,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {
+		unsigned i;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/* until radix tree lookup accepts end_index */
+			if (page->index > end)
+				continue;
+
+			wait_on_page_writeback(page);
+			if (PageError(page))
+				ret = -EIO;
+		}
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+
+	/* Check for outstanding write errors */
+	if (test_and_clear_bit(AS_ENOSPC, &mapping->flags))
+		ret = -ENOSPC;
+	if (test_and_clear_bit(AS_EIO, &mapping->flags))
+		ret = -EIO;
+
+	return ret;
+}
+
+/*
+ * Write and wait upon all the pages in the passed range.  This is a "data
+ * integrity" operation.  It waits upon in-flight writeout before starting and
+ * waiting upon new writeout.  If there was an IO error, return it.
+ *
+ * We need to re-take i_sem during the generic_osync_inode list walk because
+ * it is otherwise livelockable.
+ */
+int sync_page_range(struct inode *inode, struct address_space *mapping,
+			loff_t pos, size_t count)
+{
+	pgoff_t start = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
+	int ret;
+
+	if (!mapping_cap_writeback_dirty(mapping) || !count)
+		return 0;
+	ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
+	if (ret == 0) {
+		down(&inode->i_sem);
+		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
+		up(&inode->i_sem);
+	}
+	if (ret == 0)
+		ret = wait_on_page_writeback_range(mapping, start, end);
+	return ret;
+}
+EXPORT_SYMBOL(sync_page_range);
+
+/*
+ * Note: Holding i_sem across sync_page_range_nolock is not a good idea
+ * as it forces O_SYNC writers to different parts of the same file
+ * to be serialised right until io completion.
+ */
+int sync_page_range_nolock(struct inode *inode, struct address_space *mapping,
+			loff_t pos, size_t count)
+{
+	pgoff_t start = pos >> PAGE_CACHE_SHIFT;
+	pgoff_t end = (pos + count - 1) >> PAGE_CACHE_SHIFT;
+	int ret;
+
+	if (!mapping_cap_writeback_dirty(mapping) || !count)
+		return 0;
+	ret = filemap_fdatawrite_range(mapping, pos, pos + count - 1);
+	if (ret == 0)
+		ret = generic_osync_inode(inode, mapping, OSYNC_METADATA);
+	if (ret == 0)
+		ret = wait_on_page_writeback_range(mapping, start, end);
+	return ret;
+}
+EXPORT_SYMBOL(sync_page_range_nolock);
+
+/**
+ * filemap_fdatawait - walk the list of under-writeback pages of the given
+ *     address space and wait for all of them.
+ *
+ * @mapping: address space structure to wait for
+ */
+int filemap_fdatawait(struct address_space *mapping)
+{
+	loff_t i_size = i_size_read(mapping->host);
+
+	if (i_size == 0)
+		return 0;
+
+	return wait_on_page_writeback_range(mapping, 0,
+				(i_size -