path: root/mm/readahead.c

/*
 * mm/readahead.c - address_space-level file readahead.
 *
 * Copyright (C) 2002, Linus Torvalds
 *
 * 09Apr2002	Andrew Morton
 *		Initial version.
 */

#include <linux/kernel.h>
#include <linux/dax.h>
#include <linux/gfp.h>
#include <linux/export.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/pagevec.h>
#include <linux/pagemap.h>
#include <linux/syscalls.h>
#include <linux/file.h>
#include <linux/mm_inline.h>

#include "internal.h"

/*
 * Initialise a struct file's readahead state.  Assumes that the caller has
 * memset *ra to zero.
 */
void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping)
{
	ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages;
	ra->prev_pos = -1;
}
EXPORT_SYMBOL_GPL(file_ra_state_init);

/*
 * see if a page needs releasing upon read_cache_pages() failure
 * - the caller of read_cache_pages() may have set PG_private or PG_fscache
 *   before calling, such as the NFS fs marking pages that are cached locally
 *   on disk, thus we need to give the fs a chance to clean up in the event of
 *   an error
 */
static void read_cache_pages_invalidate_page(struct address_space *mapping,
					     struct page *page)
{
	if (page_has_private(page)) {
		if (!trylock_page(page))
			BUG();
		page->mapping = mapping;
		do_invalidatepage(page, 0, PAGE_SIZE);
		page->mapping = NULL;
		unlock_page(page);
	}
	put_page(page);
}

/*
 * release a list of pages, invalidating them first if need be
 */
static void read_cache_pages_invalidate_pages(struct address_space *mapping,
					      struct list_head *pages)
{
	struct page *victim;

	while (!list_empty(pages)) {
		victim = lru_to_page(pages);
		list_del(&victim->lru);
		read_cache_pages_invalidate_page(mapping, victim);
	}
}

/**
 * read_cache_pages - populate an address space with some pages & start reads against them
 * @mapping: the address_space
 * @pages: The address of a list_head which contains the target pages.  These
 *   pages have their ->index populated and are otherwise uninitialised.
 * @filler: callback routine for filling a single page.
 * @data: private data for the callback routine.
 *
 * Hides the details of the LRU cache etc from the filesystems.
 */
int read_cache_pages(struct address_space *mapping, struct list_head *pages,
			int (*filler)(void *, struct page *), void *data)
{
	struct page *page;
	int ret = 0;

	while (!list_empty(pages)) {
		page = lru_to_page(pages);
		list_del(&page->lru);
		if (add_to_page_cache_lru(page, mapping, page->index,
				readahead_gfp_mask(mapping))) {
			read_cache_pages_invalidate_page(mapping, page);
			continue;
		}
		put_page(page);

		ret = filler(data, page);
		if (unlikely(ret)) {
			read_cache_pages_invalidate_pages(mapping, pages);
			break;
		}
		task_io_account_read(PAGE_SIZE);
	}
	return ret;
}

EXPORT_SYMBOL(read_cache_pages);

static int read_pages(struct address_space *mapping, struct file *filp,
		struct list_head *pages, unsigned int nr_pages, gfp_t gfp)
{
	struct blk_plug plug;
	unsigned page_idx;
	int ret;

	blk_start_plug(&plug);

	if (mapping->a_ops->readpages) {
		ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages);
		/* Clean up the remaining pages */
		put_pages_list(pages);
		goto out;
	}

	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
		struct page *page = lru_to_page(pages);
		list_del(&page->lru);
		if (!add_to_page_cache_lru(page, mapping, page->index, gfp))
			mapping->a_ops->readpage(filp, page);
		put_page(page);
	}
	ret = 0;

out:
	blk_finish_plug(&plug);

	return ret;
}

/*
 * __do_page_cache_readahead() actually reads a chunk of disk.  It allocates all
 * the pages first, then submits them all for I/O. This avoids the very bad
 * behaviour which would occur if page allocations are causing VM writeback.
 * We really don't want to intermingle reads and writes like that.
 *
 * Returns the number of pages requested, or the maximum amount of I/O allowed.
 */
int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
			pgoff_t offset, unsigned long nr_to_read,
			unsigned long lookahead_size)
{
	struct inode *inode = mapping->host;
	struct page *page;
	unsigned long end_index;	/* The last page we want to read */
	LIST_HEAD(page_pool);
	int page_idx;
	int ret = 0;
	loff_t isize = i_size_read(inode);
	gfp_t gfp_mask = readahead_gfp_mask(mapping);

	if (isize == 0)
		goto out;

	end_index = ((isize - 1) >> PAGE_SHIFT);

	/*
	 * Preallocate as many pages as we will need.
	 */
	for (page_idx = 0; page_idx < nr_to_read; page_idx++) {
		pgoff_t page_offset = offset + page_idx;

		if (page_offset > end_index)
			break;

		rcu_read_lock();
		page = radix_tree_lookup(&mapping->i_pages, page_offset);
		rcu_read_unlock();
		if (page && !radix_tree_exceptional_entry(page))
			continue;

		page = __page_cache_alloc(gfp_mask);
		if (!page)
			break;
		page->index = page_offset;
		list_add(&page->lru, &page_pool);
		if (page_idx == nr_to_read - lookahead_size)
			SetPageReadahead(page);
		ret++;
	}

	/*
	 * Now start the IO.  We ignore I/O errors - if the page is not
	 * uptodate then the caller will launch readpage again, and
	 * will then handle the error.
	 */
	if (ret)
		read_pages(mapping, filp, &page_pool, ret, gfp_mask);
	BUG_ON(!list_empty(&page_pool));
out:
	return ret;
}

/*
 * Chunk the readahead into 2 megabyte units, so that we don't pin too much
 * memory at once.
 */
int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
			       pgoff_t offset, unsigned long nr_to_read)
{
	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
	struct file_ra_state *ra = &filp->f_ra;
	unsigned long max_pages;

	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
		return -EINVAL;

	/*
	 * If the request exceeds the readahead window, allow the read to
	 * be up to the optimal hardware IO size
	 */
	max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
	nr_to_read = min(nr_to_read, max_pages);
	while (nr_to_read) {
		int err;

		unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE;

		if (this_chunk > nr_to_read)
			this_chunk = nr_to_read;
		err = __do_page_cache_readahead(mapping, filp,
						offset, this_chunk, 0);
		if (err < 0)
			return err;

		offset += this_chunk;
		nr_to_read -= this_chunk;
	}
	return 0;
}

/*
 * Set the initial window size, round to next power of 2 and square
 * for small size, x 4 for medium, and x 2 for large
 * for 128k (32 page) max ra
 * 1-8 page = 32k initial, > 8 page = 128k initial
 */
static unsigned long get_init_ra_size(unsigned