5a178119b0
The patch "mm: add support for a filesystem to activate swap files and use direct_IO for writing swap pages" added support for using direct_IO to write swap pages but it is insufficient for highmem pages. To support highmem pages, this patch kmaps() the page before calling the direct_IO() handler. As direct_IO deals with virtual addresses an additional helper is necessary for get_kernel_pages() to lookup the struct page for a kmap virtual address. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: David S. Miller <davem@davemloft.net> Cc: Eric B Munson <emunson@mgebm.net> Cc: Eric Paris <eparis@redhat.com> Cc: James Morris <jmorris@namei.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Mike Christie <michaelc@cs.wisc.edu> Cc: Neil Brown <neilb@suse.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: Xiaotian Feng <dfeng@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
293 lines
6.8 KiB
C
293 lines
6.8 KiB
C
/*
|
|
* linux/mm/page_io.c
|
|
*
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
*
|
|
* Swap reorganised 29.12.95,
|
|
* Asynchronous swapping added 30.12.95. Stephen Tweedie
|
|
* Removed race in async swapping. 14.4.1996. Bruno Haible
|
|
* Add swap of shared pages through the page cache. 20.2.1998. Stephen Tweedie
|
|
* Always use brw_page, life becomes simpler. 12 May 1998 Eric Biederman
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/bio.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/frontswap.h>
|
|
#include <asm/pgtable.h>
|
|
|
|
static struct bio *get_swap_bio(gfp_t gfp_flags,
|
|
struct page *page, bio_end_io_t end_io)
|
|
{
|
|
struct bio *bio;
|
|
|
|
bio = bio_alloc(gfp_flags, 1);
|
|
if (bio) {
|
|
bio->bi_sector = map_swap_page(page, &bio->bi_bdev);
|
|
bio->bi_sector <<= PAGE_SHIFT - 9;
|
|
bio->bi_io_vec[0].bv_page = page;
|
|
bio->bi_io_vec[0].bv_len = PAGE_SIZE;
|
|
bio->bi_io_vec[0].bv_offset = 0;
|
|
bio->bi_vcnt = 1;
|
|
bio->bi_idx = 0;
|
|
bio->bi_size = PAGE_SIZE;
|
|
bio->bi_end_io = end_io;
|
|
}
|
|
return bio;
|
|
}
|
|
|
|
static void end_swap_bio_write(struct bio *bio, int err)
|
|
{
|
|
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
|
|
struct page *page = bio->bi_io_vec[0].bv_page;
|
|
|
|
if (!uptodate) {
|
|
SetPageError(page);
|
|
/*
|
|
* We failed to write the page out to swap-space.
|
|
* Re-dirty the page in order to avoid it being reclaimed.
|
|
* Also print a dire warning that things will go BAD (tm)
|
|
* very quickly.
|
|
*
|
|
* Also clear PG_reclaim to avoid rotate_reclaimable_page()
|
|
*/
|
|
set_page_dirty(page);
|
|
printk(KERN_ALERT "Write-error on swap-device (%u:%u:%Lu)\n",
|
|
imajor(bio->bi_bdev->bd_inode),
|
|
iminor(bio->bi_bdev->bd_inode),
|
|
(unsigned long long)bio->bi_sector);
|
|
ClearPageReclaim(page);
|
|
}
|
|
end_page_writeback(page);
|
|
bio_put(bio);
|
|
}
|
|
|
|
void end_swap_bio_read(struct bio *bio, int err)
|
|
{
|
|
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
|
|
struct page *page = bio->bi_io_vec[0].bv_page;
|
|
|
|
if (!uptodate) {
|
|
SetPageError(page);
|
|
ClearPageUptodate(page);
|
|
printk(KERN_ALERT "Read-error on swap-device (%u:%u:%Lu)\n",
|
|
imajor(bio->bi_bdev->bd_inode),
|
|
iminor(bio->bi_bdev->bd_inode),
|
|
(unsigned long long)bio->bi_sector);
|
|
} else {
|
|
SetPageUptodate(page);
|
|
}
|
|
unlock_page(page);
|
|
bio_put(bio);
|
|
}
|
|
|
|
int generic_swapfile_activate(struct swap_info_struct *sis,
|
|
struct file *swap_file,
|
|
sector_t *span)
|
|
{
|
|
struct address_space *mapping = swap_file->f_mapping;
|
|
struct inode *inode = mapping->host;
|
|
unsigned blocks_per_page;
|
|
unsigned long page_no;
|
|
unsigned blkbits;
|
|
sector_t probe_block;
|
|
sector_t last_block;
|
|
sector_t lowest_block = -1;
|
|
sector_t highest_block = 0;
|
|
int nr_extents = 0;
|
|
int ret;
|
|
|
|
blkbits = inode->i_blkbits;
|
|
blocks_per_page = PAGE_SIZE >> blkbits;
|
|
|
|
/*
|
|
* Map all the blocks into the extent list. This code doesn't try
|
|
* to be very smart.
|
|
*/
|
|
probe_block = 0;
|
|
page_no = 0;
|
|
last_block = i_size_read(inode) >> blkbits;
|
|
while ((probe_block + blocks_per_page) <= last_block &&
|
|
page_no < sis->max) {
|
|
unsigned block_in_page;
|
|
sector_t first_block;
|
|
|
|
first_block = bmap(inode, probe_block);
|
|
if (first_block == 0)
|
|
goto bad_bmap;
|
|
|
|
/*
|
|
* It must be PAGE_SIZE aligned on-disk
|
|
*/
|
|
if (first_block & (blocks_per_page - 1)) {
|
|
probe_block++;
|
|
goto reprobe;
|
|
}
|
|
|
|
for (block_in_page = 1; block_in_page < blocks_per_page;
|
|
block_in_page++) {
|
|
sector_t block;
|
|
|
|
block = bmap(inode, probe_block + block_in_page);
|
|
if (block == 0)
|
|
goto bad_bmap;
|
|
if (block != first_block + block_in_page) {
|
|
/* Discontiguity */
|
|
probe_block++;
|
|
goto reprobe;
|
|
}
|
|
}
|
|
|
|
first_block >>= (PAGE_SHIFT - blkbits);
|
|
if (page_no) { /* exclude the header page */
|
|
if (first_block < lowest_block)
|
|
lowest_block = first_block;
|
|
if (first_block > highest_block)
|
|
highest_block = first_block;
|
|
}
|
|
|
|
/*
|
|
* We found a PAGE_SIZE-length, PAGE_SIZE-aligned run of blocks
|
|
*/
|
|
ret = add_swap_extent(sis, page_no, 1, first_block);
|
|
if (ret < 0)
|
|
goto out;
|
|
nr_extents += ret;
|
|
page_no++;
|
|
probe_block += blocks_per_page;
|
|
reprobe:
|
|
continue;
|
|
}
|
|
ret = nr_extents;
|
|
*span = 1 + highest_block - lowest_block;
|
|
if (page_no == 0)
|
|
page_no = 1; /* force Empty message */
|
|
sis->max = page_no;
|
|
sis->pages = page_no - 1;
|
|
sis->highest_bit = page_no - 1;
|
|
out:
|
|
return ret;
|
|
bad_bmap:
|
|
printk(KERN_ERR "swapon: swapfile has holes\n");
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* We may have stale swap cache pages in memory: notice
|
|
* them here and get rid of the unnecessary final write.
|
|
*/
|
|
int swap_writepage(struct page *page, struct writeback_control *wbc)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0, rw = WRITE;
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
|
|
if (try_to_free_swap(page)) {
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
if (frontswap_store(page) == 0) {
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
end_page_writeback(page);
|
|
goto out;
|
|
}
|
|
|
|
if (sis->flags & SWP_FILE) {
|
|
struct kiocb kiocb;
|
|
struct file *swap_file = sis->swap_file;
|
|
struct address_space *mapping = swap_file->f_mapping;
|
|
struct iovec iov = {
|
|
.iov_base = kmap(page),
|
|
.iov_len = PAGE_SIZE,
|
|
};
|
|
|
|
init_sync_kiocb(&kiocb, swap_file);
|
|
kiocb.ki_pos = page_file_offset(page);
|
|
kiocb.ki_left = PAGE_SIZE;
|
|
kiocb.ki_nbytes = PAGE_SIZE;
|
|
|
|
unlock_page(page);
|
|
ret = mapping->a_ops->direct_IO(KERNEL_WRITE,
|
|
&kiocb, &iov,
|
|
kiocb.ki_pos, 1);
|
|
kunmap(page);
|
|
if (ret == PAGE_SIZE) {
|
|
count_vm_event(PSWPOUT);
|
|
ret = 0;
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write);
|
|
if (bio == NULL) {
|
|
set_page_dirty(page);
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
if (wbc->sync_mode == WB_SYNC_ALL)
|
|
rw |= REQ_SYNC;
|
|
count_vm_event(PSWPOUT);
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
submit_bio(rw, bio);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
int swap_readpage(struct page *page)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0;
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
|
|
VM_BUG_ON(!PageLocked(page));
|
|
VM_BUG_ON(PageUptodate(page));
|
|
if (frontswap_load(page) == 0) {
|
|
SetPageUptodate(page);
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
|
|
if (sis->flags & SWP_FILE) {
|
|
struct file *swap_file = sis->swap_file;
|
|
struct address_space *mapping = swap_file->f_mapping;
|
|
|
|
ret = mapping->a_ops->readpage(swap_file, page);
|
|
if (!ret)
|
|
count_vm_event(PSWPIN);
|
|
return ret;
|
|
}
|
|
|
|
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
|
|
if (bio == NULL) {
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
count_vm_event(PSWPIN);
|
|
submit_bio(READ, bio);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
int swap_set_page_dirty(struct page *page)
|
|
{
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
|
|
if (sis->flags & SWP_FILE) {
|
|
struct address_space *mapping = sis->swap_file->f_mapping;
|
|
return mapping->a_ops->set_page_dirty(page);
|
|
} else {
|
|
return __set_page_dirty_no_writeback(page);
|
|
}
|
|
}
|