mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-21 08:19:28 +00:00
![Minchan Kim](/assets/img/avatar_default.png)
Two processes under CLONE_VM cloning, user process can be corrupted by
seeing zeroed page unexpectedly.
CPU A CPU B
do_swap_page do_swap_page
SWP_SYNCHRONOUS_IO path SWP_SYNCHRONOUS_IO path
swap_readpage valid data
swap_slot_free_notify
delete zram entry
swap_readpage zeroed(invalid) data
pte_lock
map the *zero data* to userspace
pte_unlock
pte_lock
if (!pte_same)
goto out_nomap;
pte_unlock
return and next refault will
read zeroed data
The swap_slot_free_notify is bogus for CLONE_VM case since it doesn't
increase the refcount of swap slot at copy_mm so it couldn't catch up
whether it's safe or not to discard data from backing device. In the
case, only the lock it could rely on to synchronize swap slot freeing is
page table lock. Thus, this patch gets rid of the swap_slot_free_notify
function. With this patch, CPU A will see correct data.
CPU A CPU B
do_swap_page do_swap_page
SWP_SYNCHRONOUS_IO path SWP_SYNCHRONOUS_IO path
swap_readpage original data
pte_lock
map the original data
swap_free
swap_range_free
bd_disk->fops->swap_slot_free_notify
swap_readpage read zeroed data
pte_unlock
pte_lock
if (!pte_same)
goto out_nomap;
pte_unlock
return
on next refault will see mapped data by CPU B
The concern of the patch would increase memory consumption since it
could keep wasted memory with compressed form in zram as well as
uncompressed form in address space. However, most of cases of zram uses
no readahead and do_swap_page is followed by swap_free so it will free
the compressed form from in zram quickly.
Link: https://lkml.kernel.org/r/YjTVVxIAsnKAXjTd@google.com
Fixes: 0bcac06f27
("mm, swap: skip swapcache for swapin of synchronous device")
Reported-by: Ivan Babrou <ivan@cloudflare.com>
Tested-by: Ivan Babrou <ivan@cloudflare.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: David Hildenbrand <david@redhat.com>
Cc: <stable@vger.kernel.org> [4.14+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
403 lines
9.7 KiB
C
403 lines
9.7 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* 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 <linux/blkdev.h>
|
|
#include <linux/psi.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/delayacct.h>
|
|
|
|
void end_swap_bio_write(struct bio *bio)
|
|
{
|
|
struct page *page = bio_first_page_all(bio);
|
|
|
|
if (bio->bi_status) {
|
|
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 folio_rotate_reclaimable()
|
|
*/
|
|
set_page_dirty(page);
|
|
pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
|
|
MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
|
|
(unsigned long long)bio->bi_iter.bi_sector);
|
|
ClearPageReclaim(page);
|
|
}
|
|
end_page_writeback(page);
|
|
bio_put(bio);
|
|
}
|
|
|
|
static void end_swap_bio_read(struct bio *bio)
|
|
{
|
|
struct page *page = bio_first_page_all(bio);
|
|
struct task_struct *waiter = bio->bi_private;
|
|
|
|
if (bio->bi_status) {
|
|
SetPageError(page);
|
|
ClearPageUptodate(page);
|
|
pr_alert_ratelimited("Read-error on swap-device (%u:%u:%llu)\n",
|
|
MAJOR(bio_dev(bio)), MINOR(bio_dev(bio)),
|
|
(unsigned long long)bio->bi_iter.bi_sector);
|
|
goto out;
|
|
}
|
|
|
|
SetPageUptodate(page);
|
|
out:
|
|
unlock_page(page);
|
|
WRITE_ONCE(bio->bi_private, NULL);
|
|
bio_put(bio);
|
|
if (waiter) {
|
|
blk_wake_io_task(waiter);
|
|
put_task_struct(waiter);
|
|
}
|
|
}
|
|
|
|
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 tree. 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;
|
|
|
|
cond_resched();
|
|
|
|
first_block = probe_block;
|
|
ret = bmap(inode, &first_block);
|
|
if (ret || !first_block)
|
|
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 = probe_block + block_in_page;
|
|
ret = bmap(inode, &block);
|
|
if (ret || !block)
|
|
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:
|
|
pr_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;
|
|
}
|
|
/*
|
|
* Arch code may have to preserve more data than just the page
|
|
* contents, e.g. memory tags.
|
|
*/
|
|
ret = arch_prepare_to_swap(page);
|
|
if (ret) {
|
|
set_page_dirty(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;
|
|
}
|
|
|
|
static inline void count_swpout_vm_event(struct page *page)
|
|
{
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
if (unlikely(PageTransHuge(page)))
|
|
count_vm_event(THP_SWPOUT);
|
|
#endif
|
|
count_vm_events(PSWPOUT, thp_nr_pages(page));
|
|
}
|
|
|
|
#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
|
|
static void bio_associate_blkg_from_page(struct bio *bio, struct page *page)
|
|
{
|
|
struct cgroup_subsys_state *css;
|
|
struct mem_cgroup *memcg;
|
|
|
|
memcg = page_memcg(page);
|
|
if (!memcg)
|
|
return;
|
|
|
|
rcu_read_lock();
|
|
css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys);
|
|
bio_associate_blkg_from_css(bio, css);
|
|
rcu_read_unlock();
|
|
}
|
|
#else
|
|
#define bio_associate_blkg_from_page(bio, page) do { } while (0)
|
|
#endif /* CONFIG_MEMCG && CONFIG_BLK_CGROUP */
|
|
|
|
int __swap_writepage(struct page *page, struct writeback_control *wbc,
|
|
bio_end_io_t end_write_func)
|
|
{
|
|
struct bio *bio;
|
|
int ret;
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
|
|
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
|
|
if (data_race(sis->flags & SWP_FS_OPS)) {
|
|
struct kiocb kiocb;
|
|
struct file *swap_file = sis->swap_file;
|
|
struct address_space *mapping = swap_file->f_mapping;
|
|
struct bio_vec bv = {
|
|
.bv_page = page,
|
|
.bv_len = PAGE_SIZE,
|
|
.bv_offset = 0
|
|
};
|
|
struct iov_iter from;
|
|
|
|
iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE);
|
|
init_sync_kiocb(&kiocb, swap_file);
|
|
kiocb.ki_pos = page_file_offset(page);
|
|
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
ret = mapping->a_ops->direct_IO(&kiocb, &from);
|
|
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
|
|
* folio_rotate_reclaimable 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 (%llu)\n",
|
|
page_file_offset(page));
|
|
}
|
|
end_page_writeback(page);
|
|
return ret;
|
|
}
|
|
|
|
ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
|
|
if (!ret) {
|
|
count_swpout_vm_event(page);
|
|
return 0;
|
|
}
|
|
|
|
bio = bio_alloc(sis->bdev, 1,
|
|
REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc),
|
|
GFP_NOIO);
|
|
bio->bi_iter.bi_sector = swap_page_sector(page);
|
|
bio->bi_end_io = end_write_func;
|
|
bio_add_page(bio, page, thp_size(page), 0);
|
|
|
|
bio_associate_blkg_from_page(bio, page);
|
|
count_swpout_vm_event(page);
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
submit_bio(bio);
|
|
|
|
return 0;
|
|
}
|
|
|
|
int swap_readpage(struct page *page, bool synchronous)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0;
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
bool workingset = PageWorkingset(page);
|
|
unsigned long pflags;
|
|
|
|
VM_BUG_ON_PAGE(!PageSwapCache(page) && !synchronous, page);
|
|
VM_BUG_ON_PAGE(!PageLocked(page), page);
|
|
VM_BUG_ON_PAGE(PageUptodate(page), page);
|
|
|
|
/*
|
|
* Count submission time as memory stall. When the device is congested,
|
|
* or the submitting cgroup IO-throttled, submission can be a
|
|
* significant part of overall IO time.
|
|
*/
|
|
if (workingset)
|
|
psi_memstall_enter(&pflags);
|
|
delayacct_swapin_start();
|
|
|
|
if (frontswap_load(page) == 0) {
|
|
SetPageUptodate(page);
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
|
|
if (data_race(sis->flags & SWP_FS_OPS)) {
|
|
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);
|
|
goto out;
|
|
}
|
|
|
|
if (sis->flags & SWP_SYNCHRONOUS_IO) {
|
|
ret = bdev_read_page(sis->bdev, swap_page_sector(page), page);
|
|
if (!ret) {
|
|
count_vm_event(PSWPIN);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
ret = 0;
|
|
bio = bio_alloc(sis->bdev, 1, REQ_OP_READ, GFP_KERNEL);
|
|
bio->bi_iter.bi_sector = swap_page_sector(page);
|
|
bio->bi_end_io = end_swap_bio_read;
|
|
bio_add_page(bio, page, thp_size(page), 0);
|
|
/*
|
|
* Keep this task valid during swap readpage because the oom killer may
|
|
* attempt to access it in the page fault retry time check.
|
|
*/
|
|
if (synchronous) {
|
|
bio->bi_opf |= REQ_POLLED;
|
|
get_task_struct(current);
|
|
bio->bi_private = current;
|
|
}
|
|
count_vm_event(PSWPIN);
|
|
bio_get(bio);
|
|
submit_bio(bio);
|
|
while (synchronous) {
|
|
set_current_state(TASK_UNINTERRUPTIBLE);
|
|
if (!READ_ONCE(bio->bi_private))
|
|
break;
|
|
|
|
if (!bio_poll(bio, NULL, 0))
|
|
blk_io_schedule();
|
|
}
|
|
__set_current_state(TASK_RUNNING);
|
|
bio_put(bio);
|
|
|
|
out:
|
|
if (workingset)
|
|
psi_memstall_leave(&pflags);
|
|
delayacct_swapin_end();
|
|
return ret;
|
|
}
|
|
|
|
bool swap_dirty_folio(struct address_space *mapping, struct folio *folio)
|
|
{
|
|
struct swap_info_struct *sis = swp_swap_info(folio_swap_entry(folio));
|
|
|
|
if (data_race(sis->flags & SWP_FS_OPS)) {
|
|
const struct address_space_operations *aops;
|
|
|
|
mapping = sis->swap_file->f_mapping;
|
|
aops = mapping->a_ops;
|
|
|
|
VM_BUG_ON_FOLIO(!folio_test_swapcache(folio), folio);
|
|
return aops->dirty_folio(mapping, folio);
|
|
} else {
|
|
return noop_dirty_folio(mapping, folio);
|
|
}
|
|
}
|