linux_dsm_epyc7002/mm/page_io.c
Mel Gorman 0cdc444a67 mm: swap: mark swap pages writeback before queueing for direct IO
As pointed out by Andrew Morton, the swap-over-NFS writeback is not
setting PageWriteback before it is queued for direct IO.  While swap
pages do not participate in BDI or process dirty accounting and the IO
is synchronous, the writeback bit is still required and not setting it
in this case was an oversight.  swapoff depends on the page writeback to
synchronoise all pending writes on a swap page before it is reused.
Swapcache freeing and reuse depend on checking the PageWriteback under
lock to ensure the page is safe to reuse.

Direct IO handlers and the direct IO handler for NFS do not deal with
PageWriteback as they are synchronous writes.  In the case of NFS, it
schedules pages (or a page in the case of swap) for IO and then waits
synchronously for IO to complete in nfs_direct_write().  It is
recognised that this is a slowdown from normal swap handling which is
asynchronous and uses a completion handler.  Shoving PageWriteback
handling down into direct IO handlers looks like a bad fit to handle the
swap case although it may have to be dealt with some day if swap is
converted to use direct IO in general and bmap is finally done away
with.  At that point it will be necessary to refit asynchronous direct
IO with completion handlers onto the swap subsystem.

As swapcache currently depends on PageWriteback to protect against
races, this patch sets PageWriteback under the page lock before queueing
it for direct IO.  It is cleared when the direct IO handler returns.  IO
errors are treated similarly to the direct-to-bio case except PageError
is not set as in the case of swap-over-NFS, it is likely to be a
transient error.

It was asked what prevents such a page being reclaimed in parallel.
With this patch applied, such a page will now be skipped (most of the
time) or blocked until the writeback completes.  Reclaim checks
PageWriteback under the page lock before calling try_to_free_swap and
the page lock should prevent the page being requeued for IO before it is
freed.

This and Jerome's related patch should considered for -stable as far
back as 3.6 when swap-over-NFS was introduced.

[akpm@linux-foundation.org: use pr_err_ratelimited()]
[akpm@linux-foundation.org: remove hopefully-unneeded cast in printk]
Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>	[3.6+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-29 15:54:39 -07:00

319 lines
7.5 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/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;
}
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)
{
int ret = 0;
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;
}
ret = __swap_writepage(page, wbc, end_swap_bio_write);
out:
return ret;
}
int __swap_writepage(struct page *page, struct writeback_control *wbc,
void (*end_write_func)(struct bio *, int))
{
struct bio *bio;
int ret = 0, rw = WRITE;
struct swap_info_struct *sis = page_swap_info(page);
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;
set_page_writeback(page);
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;
} else {
/*
* In the case of swap-over-nfs, this can be a
* temporary failure if the system has limited
* memory for allocating transmit buffers.
* Mark the page dirty and avoid
* rotate_reclaimable_page but rate-limit the
* messages but do not flag PageError like
* the normal direct-to-bio case as it could
* be temporary.
*/
set_page_dirty(page);
ClearPageReclaim(page);
pr_err_ratelimited("Write error on dio swapfile (%Lu)\n",
page_file_offset(page));
}
end_page_writeback(page);
return ret;
}
bio = get_swap_bio(GFP_NOIO, page, end_write_func);
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);
}
}