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!

1 files changed, 2306 insertions, 0 deletions

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 - 1) >> PAGE_CACHE_SHIFT);
+}
+EXPORT_SYMBOL(filemap_fdatawait);
+
+int filemap_write_and_wait(struct address_space *mapping)
+{
+	int retval = 0;
+
+	if (mapping->nrpages) {
+		retval = filemap_fdatawrite(mapping);
+		if (retval == 0)
+			retval = filemap_fdatawait(mapping);
+	}
+	return retval;
+}
+
+int filemap_write_and_wait_range(struct address_space *mapping,
+				 loff_t lstart, loff_t lend)
+{
+	int retval = 0;
+
+	if (mapping->nrpages) {
+		retval = __filemap_fdatawrite_range(mapping, lstart, lend,
+						    WB_SYNC_ALL);
+		if (retval == 0)
+			retval = wait_on_page_writeback_range(mapping,
+						    lstart >> PAGE_CACHE_SHIFT,
+						    lend >> PAGE_CACHE_SHIFT);
+	}
+	return retval;
+}
+
+/*
+ * This function is used to add newly allocated pagecache pages:
+ * the page is new, so we can just run SetPageLocked() against it.
+ * The other page state flags were set by rmqueue().
+ *
+ * This function does not add the page to the LRU.  The caller must do that.
+ */
+int add_to_page_cache(struct page *page, struct address_space *mapping,
+		pgoff_t offset, int gfp_mask)
+{
+	int error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+
+	if (error == 0) {
+		write_lock_irq(&mapping->tree_lock);
+		error = radix_tree_insert(&mapping->page_tree, offset, page);
+		if (!error) {
+			page_cache_get(page);
+			SetPageLocked(page);
+			page->mapping = mapping;
+			page->index = offset;
+			mapping->nrpages++;
+			pagecache_acct(1);
+		}
+		write_unlock_irq(&mapping->tree_lock);
+		radix_tree_preload_end();
+	}
+	return error;
+}
+
+EXPORT_SYMBOL(add_to_page_cache);
+
+int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
+				pgoff_t offset, int gfp_mask)
+{
+	int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
+	if (ret == 0)
+		lru_cache_add(page);
+	return ret;
+}
+
+/*
+ * In order to wait for pages to become available there must be
+ * waitqueues associated with pages. By using a hash table of
+ * waitqueues where the bucket discipline is to maintain all
+ * waiters on the same queue and wake all when any of the pages
+ * become available, and for the woken contexts to check to be
+ * sure the appropriate page became available, this saves space
+ * at a cost of "thundering herd" phenomena during rare hash
+ * collisions.
+ */
+static wait_queue_head_t *page_waitqueue(struct page *page)
+{
+	const struct zone *zone = page_zone(page);
+
+	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
+}
+
+static inline void wake_up_page(struct page *page, int bit)
+{
+	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
+}
+
+void fastcall wait_on_page_bit(struct page *page, int bit_nr)
+{
+	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);
+
+	if (test_bit(bit_nr, &page->flags))
+		__wait_on_bit(page_waitqueue(page), &wait, sync_page,
+							TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_on_page_bit);
+
+/**
+ * unlock_page() - unlock a locked page
+ *
+ * @page: the page
+ *
+ * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
+ * Also wakes sleepers in wait_on_page_writeback() because the wakeup
+ * mechananism between PageLocked pages and PageWriteback pages is shared.
+ * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
+ *
+ * The first mb is necessary to safely close the critical section opened by the
+ * TestSetPageLocked(), the second mb is necessary to enforce ordering between
+ * the clear_bit and the read of the waitqueue (to avoid SMP races with a
+ * parallel wait_on_page_locked()).
+ */
+void fastcall unlock_page(struct page *page)
+{
+	smp_mb__before_clear_bit();
+	if (!TestClearPageLocked(page))
+		BUG();
+	smp_mb__after_clear_bit(); 
+	wake_up_page(page, PG_locked);
+}
+EXPORT_SYMBOL(unlock_page);
+
+/*
+ * End writeback against a page.
+ */
+void end_page_writeback(struct page *page)
+{
+	if (!TestClearPageReclaim(page) || rotate_reclaimable_page(page)) {
+		if (!test_clear_page_writeback(page))
+			BUG();
+	}
+	smp_mb__after_clear_bit();
+	wake_up_page(page, PG_writeback);
+}
+EXPORT_SYMBOL(end_page_writeback);
+
+/*
+ * Get a lock on the page, assuming we need to sleep to get it.
+ *
+ * Ugly: running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
+ * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
+ * chances are that on the second loop, the block layer's plug list is empty,
+ * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
+ */
+void fastcall __lock_page(struct page *page)
+{
+	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
+
+	__wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
+							TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(__lock_page);
+
+/*
+ * a rather lightweight function, finding and getting a reference to a
+ * hashed page atomically.
+ */
+struct page * find_get_page(struct address_space *mapping, unsigned long offset)
+{
+	struct page *page;
+
+	read_lock_irq(&mapping->tree_lock);
+	page = radix_tree_lookup(&mapping->page_tree, offset);
+	if (page)
+		page_cache_get(page);
+	read_unlock_irq(&mapping->tree_lock);
+	return page;
+}
+
+EXPORT_SYMBOL(find_get_page);
+
+/*
+ * Same as above, but trylock it instead of incrementing the count.
+ */
+struct page *find_trylock_page(struct address_space *mapping, unsigned long offset)
+{
+	struct page *page;
+
+	read_lock_irq(&mapping->tree_lock);
+	page = radix_tree_lookup(&mapping->page_tree, offset);
+	if (page && TestSetPageLocked(page))
+		page = NULL;
+	read_unlock_irq(&mapping->tree_lock);
+	return page;
+}
+
+EXPORT_SYMBOL(find_trylock_page);
+
+/**
+ * find_lock_page - locate, pin and lock a pagecache page
+ *
+ * @mapping - the address_space to search
+ * @offset - the page index
+ *
+ * Locates the desired pagecache page, locks it, increments its reference
+ * count and returns its address.
+ *
+ * Returns zero if the page was not present. find_lock_page() may sleep.
+ */
+struct page *find_lock_page(struct address_space *mapping,
+				unsigned long offset)
+{
+	struct page *page;
+
+	read_lock_irq(&mapping->tree_lock);
+repeat:
+	page = radix_tree_lookup(&mapping->page_tree, offset);
+	if (page) {
+		page_cache_get(page);
+		if (TestSetPageLocked(page)) {
+			read_unlock_irq(&mapping->tree_lock);
+			lock_page(page);
+			read_lock_irq(&mapping->tree_lock);
+
+			/* Has the page been truncated while we slept? */
+			if (page->mapping != mapping || page->index != offset) {
+				unlock_page(page);
+				page_cache_release(page);
+				goto repeat;
+			}
+		}
+	}
+	read_unlock_irq(&mapping->tree_lock);
+	return page;
+}
+
+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
+ *
+ * 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
+ * LRU list.  The returned page is locked and has its reference count
+ * incremented.
+ *
+ * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
+ * allocation!
+ *
+ * find_or_create_page() returns the desired page's address, or zero on
+ * memory exhaustion.
+ */
+struct page *find_or_create_page(struct address_space *mapping,
+		unsigned long index, unsigned int gfp_mask)
+{
+	struct page *page, *cached_page = NULL;
+	int err;
+repeat:
+	page = find_lock_page(mapping, index);
+	if (!page) {
+		if (!cached_page) {
+			cached_page = alloc_page(gfp_mask);
+			if (!cached_page)
+				return NULL;
+		}
+		err = add_to_page_cache_lru(cached_page, mapping,
+					index, gfp_mask);
+		if (!err) {
+			page = cached_page;
+			cached_page = NULL;
+		} else if (err == -EEXIST)
+			goto repeat;
+	}
+	if (cached_page)
+		page_cache_release(cached_page);
+	return page;
+}
+
+EXPORT_SYMBOL(find_or_create_page);
+
+/**
+ * find_get_pages - gang pagecache lookup
+ * @mapping:	The address_space to search
+ * @start:	The starting page index
+ * @nr_pages:	The maximum number of pages
+ * @pages:	Where the resulting pages are placed
+ *
+ * find_get_pages() will search for and return a group of up to
+ * @nr_pages pages in the mapping.  The pages are placed at @pages.
+ * find_get_pages() takes a reference against the returned pages.
+ *
+ * The search returns a group of mapping-contiguous pages with ascending
+ * indexes.  There may be holes in the indices due to not-present pages.
+ *
+ * find_get_pages() returns the number of pages which were found.
+ */
+unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
+			    unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+	unsigned int ret;
+
+	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++)
+		page_cache_get(pages[i]);
+	read_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
+
+/*
+ * Like find_get_pages, except we only return pages which are tagged with
+ * `tag'.   We update *index to index the next page for the traversal.
+ */
+unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
+			int tag, unsigned int nr_pages, struct page **pages)
+{
+	unsigned int i;
+	unsigned int ret;
+
+	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++)
+		page_cache_get(pages[i]);
+	if (ret)
+		*index = pages[ret - 1]->index + 1;
+	read_unlock_irq(&mapping->tree_lock);
+	return ret;
+}
+
+/*
+ * Same as grab_cache_page, but do not wait if the page is unavailable.
+ * This is intended for speculative data generators, where the data can
+ * be regenerated if the page couldn't be grabbed.  This routine should
+ * be safe to call while holding the lock for another page.
+ *
+ * Clear __GFP_FS when allocating the page to avoid recursion into the fs
+ * and deadlock against the caller's locked page.
+ */
+struct page *
+grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
+{
+	struct page *page = find_get_page(mapping, index);
+	unsigned int gfp_mask;
+
+	if (page) {
+		if (!TestSetPageLocked(page))
+			return page;
+		page_cache_release(page);
+		return NULL;
+	}
+	gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS;
+	page = alloc_pages(gfp_mask, 0);
+	if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) {
+		page_cache_release(page);
+		page = NULL;
+	}
+	return page;
+}
+
+EXPORT_SYMBOL(grab_cache_page_nowait);
+
+/*
+ * This is a generic file read routine, and uses the
+ * mapping->a_ops->readpage() function for the actual low-level
+ * stuff.
+ *
+ * This is really ugly. But the goto's actually try to clarify some
+ * of the logic when it comes to error handling etc.
+ *
+ * Note the struct file* is only passed for the use of readpage.  It may be
+ * NULL.
+ */
+void do_generic_mapping_read(struct address_space *mapping,
+			     struct file_ra_state *_ra,
+			     struct file *filp,
+			     loff_t *ppos,
+			     read_descriptor_t *desc,
+			     read_actor_t actor)
+{
+	struct inode *inode = mapping->host;
+	unsigned long index;
+	unsigned long end_index;
+	unsigned long offset;
+	unsigned long last_index;
+	unsigned long next_index;
+	unsigned long prev_index;
+	loff_t isize;
+	struct page *cached_page;
+	int error;
+	struct file_ra_state ra = *_ra;
+
+	cached_page = NULL;
+	index = *ppos >> PAGE_CACHE_SHIFT;
+	next_index = index;
+	prev_index = ra.prev_page;
+	last_index = (*ppos + desc->count + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
+	offset = *ppos & ~PAGE_CACHE_MASK;
+
+	isize = i_size_read(inode);
+	if (!isize)
+		goto out;
+
+	end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+	for (;;) {
+		struct page *page;
+		unsigned long nr, ret;
+
+		/* nr is the maximum number of bytes to copy from this page */
+		nr = PAGE_CACHE_SIZE;
+		if (index >= end_index) {
+			if (index > end_index)
+				goto out;
+			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+			if (nr <= offset) {
+				goto out;
+			}
+		}
+		nr = nr - offset;
+
+		cond_resched();
+		if (index == next_index)
+			next_index = page_cache_readahead(mapping, &ra, filp,
+					index, last_index - index);
+
+find_page:
+		page = find_get_page(mapping, index);
+		if (unlikely(page == NULL)) {
+			handle_ra_miss(mapping, &ra, index);
+			goto no_cached_page;
+		}
+		if (!PageUptodate(page))
+			goto page_not_up_to_date;
+page_ok:
+
+		/* If users can be writing to this page using arbitrary
+		 * virtual addresses, take care about potential aliasing
+		 * before reading the page on the kernel side.
+		 */
+		if (mapping_writably_mapped(mapping))
+			flush_dcache_page(page);
+
+		/*
+		 * When (part of) the same page is read multiple times
+		 * in succession, only mark it as accessed the first time.
+		 */
+		if (prev_index != index)
+			mark_page_accessed(page);
+		prev_index = index;
+
+		/*
+		 * Ok, we have the page, and it's up-to-date, so
+		 * now we can copy it to user space...
+		 *
+		 * The actor routine returns how many bytes were actually used..
+		 * NOTE! This may not be the same as how much of a user buffer
+		 * we filled up (we may be padding etc), so we can only update
+		 * "pos" here (the actor routine has to update the user buffer
+		 * pointers and the remaining count).
+		 */
+		ret = actor(desc, page, offset, nr);
+		offset += ret;
+		index += offset >> PAGE_CACHE_SHIFT;
+		offset &= ~PAGE_CACHE_MASK;
+
+		page_cache_release(page);
+		if (ret == nr && desc->count)
+			continue;
+		goto out;
+
+page_not_up_to_date:
+		/* Get exclusive access to the page ... */
+		lock_page(page);
+
+		/* Did it get unhashed before we got the lock? */
+		if (!page->mapping) {
+			unlock_page(page);
+			page_cache_release(page);
+			continue;
+		}
+
+		/* Did somebody else fill it already? */
+		if (PageUptodate(page)) {
+			unlock_page(page);
+			goto page_ok;
+		}
+
+readpage:
+		/* Start the actual read. The read will unlock the page. */
+		error = mapping->a_ops->readpage(filp, page);
+
+		if (unlikely(error))
+			goto readpage_error;
+
+		if (!PageUptodate(page)) {
+			lock_page(page);
+			if (!PageUptodate(page)) {
+				if (page->mapping == NULL) {
+					/*
+					 * invalidate_inode_pages got it
+					 */
+					unlock_page(page);
+					page_cache_release(page);
+					goto find_page;
+				}
+				unlock_page(page);
+				error = -EIO;
+				goto readpage_error;
+			}
+			unlock_page(page);
+		}
+
+		/*
+		 * i_size must be checked after we have done ->readpage.
+		 *
+		 * Checking i_size after the readpage allows us to calculate
+		 * the correct value for "nr", which means the zero-filled
+		 * part of the page is not copied back to userspace (unless
+		 * another truncate extends the file - this is desired though).
+		 */
+		isize = i_size_read(inode);
+		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+		if (unlikely(!isize || index > end_index)) {
+			page_cache_release(page);
+			goto out;
+		}
+
+		/* nr is the maximum number of bytes to copy from this page */
+		nr = PAGE_CACHE_SIZE;
+		if (index == end_index) {
+			nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+			if (nr <= offset) {
+				page_cache_release(page);
+				goto out;
+			}
+		}
+		nr = nr - offset;
+		goto page_ok;
+
+readpage_error:
+		/* UHHUH! A synchronous read error occurred. Report it */
+		desc->error = error;
+		page_cache_release(page);
+		goto out;
+
+no_cached_page:
+		/*
+		 * Ok, it wasn't cached, so we need to create a new
+		 * page..
+		 */
+		if (!cached_page) {
+			cached_page = page_cache_alloc_cold(mapping);
+			if (!cached_page) {
+				desc->error = -ENOMEM;
+				goto out;
+			}
+		}
+		error = add_to_page_cache_lru(cached_page, mapping,
+						index, GFP_KERNEL);
+		if (error) {
+			if (error == -EEXIST)
+				goto find_page;
+			desc->error = error;
+			goto out;
+		}
+		page = cached_page;
+		cached_page = NULL;
+		goto readpage;
+	}
+
+out:
+	*_ra = ra;
+
+	*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
+	if (cached_page)
+		page_cache_release(cached_page);
+	if (filp)
+		file_accessed(filp);
+}
+
+EXPORT_SYMBOL(do_generic_mapping_read);
+
+int file_read_actor(read_descriptor_t *desc, struct page *page,
+			unsigned long offset, unsigned long size)
+{
+	char *kaddr;
+	unsigned long left, count = desc->count;
+
+	if (size > count)
+		size = count;
+
+	/*
+	 * Faults on the destination of a read are common, so do it before
+	 * taking the kmap.
+	 */
+	if (!fault_in_pages_writeable(desc->arg.buf, size)) {
+		kaddr = kmap_atomic(page, KM_USER0);
+		left = __copy_to_user_inatomic(desc->arg.buf,
+						kaddr + offset, size);
+		kunmap_atomic(kaddr, KM_USER0);
+		if (left == 0)
+			goto success;
+	}
+
+	/* Do it the slow way */
+	kaddr = kmap(page);
+	left = __copy_to_user(desc->arg.buf, kaddr + offset, size);
+	kunmap(page);
+
+	if (left) {
+		size -= left;
+		desc->error = -EFAULT;
+	}
+success:
+	desc->count = count - size;
+	desc->written += size;
+	desc->arg.buf += size;
+	return size;
+}
+
+/*
+ * This is the "read()" routine for all filesystems
+ * that can use the page cache directly.
+ */
+ssize_t
+__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
+		unsigned long nr_segs, loff_t *ppos)
+{
+	struct file *filp = iocb->ki_filp;
+	ssize_t retval;
+	unsigned long seg;
+	size_t count;
+
+	count = 0;
+	for (seg = 0; seg < nr_segs; seg++) {
+		const struct iovec *iv = &iov[seg];
+
+		/*
+		 * If any segment has a negative length, or the cumulative
+		 * length ever wraps negative then return -EINVAL.
+		 */
+		count += iv->iov_len;
+		if (unlikely((ssize_t)(count|iv->iov_len) < 0))
+			return -EINVAL;
+		if (access_ok(VERIFY_WRITE, iv->iov_base, iv->iov_len))
+			continue;
+		if (seg == 0)
+			return -EFAULT;
+		nr_segs = seg;
+		count -= iv->iov_len;	/* This segment is no good */
+		break;
+	}
+
+	/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
+	if (filp->f_flags & O_DIRECT) {
+		loff_t pos = *ppos, size;
+		struct address_space *mapping;
+		struct inode *inode;
+
+		mapping = filp->f_mapping;
+		inode = mapping->host;
+		retval = 0;
+		if (!count)
+			goto out; /* skip atime */
+		size = i_size_read(inode);
+		if (pos < size) {
+			retval = generic_file_direct_IO(READ, iocb,
+						iov, pos, nr_segs);
+			if (retval >= 0 && !is_sync_kiocb(iocb))
+				retval = -EIOCBQUEUED;
+			if (retval > 0)
+				*ppos = pos + retval;
+		}
+		file_accessed(filp);
+		goto out;
+	}
+
+	retval = 0;
+	if (count) {
+		for (seg = 0; seg < nr_segs; seg++) {
+			read_descriptor_t desc;
+
+			desc.written = 0;
+			desc.arg.buf = iov[seg].iov_base;
+			desc.count = iov[seg].iov_len;
+			if (desc.count == 0)
+				continue;
+			desc.error = 0;
+			do_generic_file_read(filp,ppos,&desc,file_read_actor);
+			retval += desc.written;
+			if (!retval) {
+				retval = desc.error;
+				break;
+			}
+		}
+	}
+out:
+	return retval;
+}
+
+EXPORT_SYMBOL(__generic_file_aio_read);
+
+ssize_t
+generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos)
+{
+	struct iovec local_iov = { .iov_base = buf, .iov_len = count };
+
+	BUG_ON(iocb->ki_pos != pos);
+	return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos);
+}
+
+EXPORT_SYMBOL(generic_file_aio_read);
+
+ssize_t
+generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct iovec local_iov = { .iov_base = buf, .iov_len = count };
+	struct kiocb kiocb;
+	ssize_t ret;
+
+	init_sync_kiocb(&kiocb, filp);
+	ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos);
+	if (-EIOCBQUEUED == ret)
+		ret = wait_on_sync_kiocb(&kiocb);
+	return ret;
+}
+
+EXPORT_SYMBOL(generic_file_read);
+
+int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
+{
+	ssize_t written;
+	unsigned long count = desc->count;
+	struct file *file = desc->arg.data;
+
+	if (size > count)
+		size = count;
+
+	written = file->f_op->sendpage(file, page, offset,
+				       size, &file->f_pos, size<count);
+	if (written < 0) {
+		desc->error = written;
+		written = 0;
+	}
+	desc->count = count - written;
+	desc->written += written;
+	return written;
+}
+
+ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos,
+			 size_t count, read_actor_t actor, void *target)
+{
+	read_descriptor_t desc;
+
+	if (!count)
+		return 0;
+
+	desc.written = 0;
+	desc.count = count;
+	desc.arg.data = target;
+	desc.error = 0;
+
+	do_generic_file_read(in_file, ppos, &desc, actor);
+	if (desc.written)
+		return desc.written;
+	return desc.error;
+}
+
+EXPORT_SYMBOL(generic_file_sendfile);
+
+static ssize_t
+do_readahead(struct address_space *mapping, struct file *filp,
+	     unsigned long index, unsigned long nr)
+{
+	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
+		return -EINVAL;
+
+	force_page_cache_readahead(mapping, filp, index,
+					max_sane_readahead(nr));
+	return 0;
+}
+
+asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
+{
+	ssize_t ret;
+	struct file *file;
+
+	ret = -EBADF;
+	file = fget(fd);
+	if (file) {
+		if (file->f_mode & FMODE_READ) {
+			struct address_space *mapping = file->f_mapping;
+			unsigned long start = offset >> PAGE_CACHE_SHIFT;
+			unsigned long end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
+			unsigned long len = end - start + 1;
+			ret = do_readahead(mapping, file, start, len);
+		}
+		fput(file);
+	}
+	return ret;
+}
+
+#ifdef CONFIG_MMU
+/*
+ * This adds the requested page to the page cache if it isn't already there,
+ * and schedules an I/O to read in its contents from disk.
+ */
+static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
+static int fastcall page_cache_read(struct file * file, unsigned long offset)
+{
+	struct address_space *mapping = file->f_mapping;
+	struct page *page; 
+	int error;
+
+	page = page_cache_alloc_cold(mapping);
+	if (!page)
+		return -ENOMEM;
+
+	error = add_to_page_cache_lru(page, mapping, offset, GFP_KERNEL);
+	if (!error) {
+		error = mapping->a_ops->readpage(file, page);
+		page_cache_release(page);
+		return error;
+	}
+
+	/*
+	 * We arrive here in the unlikely event that someone 
+	 * raced with us and added our page to the cache first
+	 * or we are out of memory for radix-tree nodes.
+	 */
+	page_cache_release(page);
+	return error == -EEXIST ? 0 : error;
+}
+
+#define MMAP_LOTSAMISS  (100)
+
+/*
+ * filemap_nopage() is invoked via the vma operations vector for a
+ * mapped memory region to read in file data during a page fault.
+ *
+ * The goto's are kind of ugly, but this streamlines the normal case of having
+ * it in the page cache, and handles the special cases reasonably without
+ * having a lot of duplicated code.
+ */
+struct page *filemap_nopage(struct vm_area_struct *area,
+				unsigned long address, int *type)
+{
+	int error;
+	struct file *file = area->vm_file;
+	struct address_space *mapping = file->f_mapping;
+	struct file_ra_state *ra = &file->f_ra;
+	struct inode *inode = mapping->h