linux/mm/page_io.c
Peter Zijlstra 6ddab3b9eb [PATCH] mm: swap write failure fixup
Currently we can silently drop data if the write to swap failed.  It
usually doesn't result in data-corruption because on page-in the process
will receive SIGBUS (assuming write-failure implies read-failure).

This assumption might or might not be valid.

This patch will avoid the page being discarded after a failed write.  But
will print a warning the sysadmin _should_ take to heart, if a lot of swap
space becomes un-writeable, OOM is not far off.

Tested by making the write fail 'randomly' once every 50 writes or so.

[akpm@osdl.org: printk warning fix]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 08:48:48 -07:00

182 lines
4.2 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/pagemap.h>
#include <linux/swap.h>
#include <linux/bio.h>
#include <linux/swapops.h>
#include <linux/writeback.h>
#include <asm/pgtable.h>
static struct bio *get_swap_bio(gfp_t gfp_flags, pgoff_t index,
struct page *page, bio_end_io_t end_io)
{
struct bio *bio;
bio = bio_alloc(gfp_flags, 1);
if (bio) {
struct swap_info_struct *sis;
swp_entry_t entry = { .val = index, };
sis = get_swap_info_struct(swp_type(entry));
bio->bi_sector = map_swap_page(sis, swp_offset(entry)) *
(PAGE_SIZE >> 9);
bio->bi_bdev = sis->bdev;
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 int end_swap_bio_write(struct bio *bio, unsigned int bytes_done, int err)
{
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct page *page = bio->bi_io_vec[0].bv_page;
if (bio->bi_size)
return 1;
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);
return 0;
}
static int end_swap_bio_read(struct bio *bio, unsigned int bytes_done, int err)
{
const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
struct page *page = bio->bi_io_vec[0].bv_page;
if (bio->bi_size)
return 1;
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);
return 0;
}
/*
* 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;
if (remove_exclusive_swap_page(page)) {
unlock_page(page);
goto out;
}
bio = get_swap_bio(GFP_NOIO, page_private(page), 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 |= (1 << BIO_RW_SYNC);
count_vm_event(PSWPOUT);
set_page_writeback(page);
unlock_page(page);
submit_bio(rw, bio);
out:
return ret;
}
int swap_readpage(struct file *file, struct page *page)
{
struct bio *bio;
int ret = 0;
BUG_ON(!PageLocked(page));
ClearPageUptodate(page);
bio = get_swap_bio(GFP_KERNEL, page_private(page), 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;
}
#ifdef CONFIG_SOFTWARE_SUSPEND
/*
* A scruffy utility function to read or write an arbitrary swap page
* and wait on the I/O. The caller must have a ref on the page.
*
* We use end_swap_bio_read() even for writes, because it happens to do what
* we want.
*/
int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page)
{
struct bio *bio;
int ret = 0;
lock_page(page);
bio = get_swap_bio(GFP_KERNEL, entry.val, page, end_swap_bio_read);
if (bio == NULL) {
unlock_page(page);
ret = -ENOMEM;
goto out;
}
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
wait_on_page_locked(page);
if (!PageUptodate(page) || PageError(page))
ret = -EIO;
out:
return ret;
}
#endif