38b5faf4b1
This patch, 2of4, contains the changes to the core swap subsystem. This includes: (1) makes available core swap data structures (swap_lock, swap_list and swap_info) that are needed by frontswap.c but we don't need to expose them to the dozens of files that include swap.h so we create a new swapfile.h just to extern-ify these and modify their declarations to non-static (2) adds frontswap-related elements to swap_info_struct. Frontswap_map points to vzalloc'ed one-bit-per-swap-page metadata that indicates whether the swap page is in frontswap or in the device and frontswap_pages counts how many pages are in frontswap. (3) adds hooks in the swap subsystem and extends try_to_unuse so that frontswap_shrink can do a "partial swapoff". Note that a failed frontswap_map allocation is safe... failure is noted by lack of "FS" in the subsequent printk. --- [v14: rebase to 3.4-rc2] [v10: no change] [v9: akpm@linux-foundation.org: mark some statics __read_mostly] [v9: akpm@linux-foundation.org: add clarifying comments] [v9: akpm@linux-foundation.org: no need to loop repeating try_to_unuse] [v9: error27@gmail.com: remove superfluous check for NULL] [v8: rebase to 3.0-rc4] [v8: kamezawa.hiroyu@jp.fujitsu.com: change counter to atomic_t to avoid races] [v8: kamezawa.hiroyu@jp.fujitsu.com: comment to clarify informational counters] [v7: rebase to 3.0-rc3] [v7: JBeulich@novell.com: add new swap struct elements only if config'd] [v6: rebase to 3.0-rc1] [v6: lliubbo@gmail.com: fix null pointer deref if vzalloc fails] [v6: konrad.wilk@oracl.com: various checks and code clarifications/comments] [v5: no change from v4] [v4: rebase to 2.6.39] Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com> Reviewed-by: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Acked-by: Jan Beulich <JBeulich@novell.com> Acked-by: Seth Jennings <sjenning@linux.vnet.ibm.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Chris Mason <chris.mason@oracle.com> Cc: Rik Riel <riel@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> [v11: Rebased, fixed mm/swapfile.c context change] Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
148 lines
3.5 KiB
C
148 lines
3.5 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/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);
|
|
}
|
|
|
|
/*
|
|
* 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 (try_to_free_swap(page)) {
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
if (frontswap_put_page(page) == 0) {
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
end_page_writeback(page);
|
|
goto out;
|
|
}
|
|
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;
|
|
|
|
VM_BUG_ON(!PageLocked(page));
|
|
VM_BUG_ON(PageUptodate(page));
|
|
if (frontswap_get_page(page) == 0) {
|
|
SetPageUptodate(page);
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
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;
|
|
}
|