mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-12 13:55:32 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
-----BEGIN PGP SIGNATURE----- iQJEBAABCAAuFiEEwPw5LcreJtl1+l5K99NY+ylx4KYFAl+EWUgQHGF4Ym9lQGtl cm5lbC5kawAKCRD301j7KXHgpnoxEADCVSNBRkpV0OVkOEC3wf8EGhXhk01Jnjtl u5Mg2V55hcgJ0thQxBV/V28XyqmsEBrmAVi0Yf8Vr9Qbq4Ze08Wae4ChS4rEOyh1 jTcGYWx5aJB3ChLvV/HI0nWQ3bkj03mMrL3SW8rhhf5DTyKHsVeTenpx42Qu/FKf fRzi09FSr3Pjd0B+EX6gunwJnlyXQC5Fa4AA0GhnXJzAznANXxHkkcXu8a6Yw75x e28CfhIBliORsK8sRHLoUnPpeTe1vtxCBhBMsE+gJAj9ZUOWMzvNFIPP4FvfawDy 6cCQo2m1azJ/IdZZCDjFUWyjh+wxdKMp+NNryEcoV+VlqIoc3n98rFwrSL+GIq5Z WVwEwq+AcwoMCsD29Lu1ytL2PQ/RVqcJP5UheMrbL4vzefNfJFumQVZLIcX0k943 8dFL2QHL+H/hM9Dx5y5rjeiWkAlq75v4xPKVjh/DHb4nehddCqn/+DD5HDhNANHf c1kmmEuYhvLpIaC4DHjE6DwLh8TPKahJjwsGuBOTr7D93NUQD+OOWsIhX6mNISIl FFhP8cd0/ZZVV//9j+q+5B4BaJsT+ZtwmrelKFnPdwPSnh+3iu8zPRRWO+8P8fRC YvddxuJAmE6BLmsAYrdz6Xb/wqfyV44cEiyivF0oBQfnhbtnXwDnkDWSfJD1bvCm ZwfpDh2+Tg== =LzyE -----END PGP SIGNATURE----- Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block Pull block updates from Jens Axboe: - Series of merge handling cleanups (Baolin, Christoph) - Series of blk-throttle fixes and cleanups (Baolin) - Series cleaning up BDI, seperating the block device from the backing_dev_info (Christoph) - Removal of bdget() as a generic API (Christoph) - Removal of blkdev_get() as a generic API (Christoph) - Cleanup of is-partition checks (Christoph) - Series reworking disk revalidation (Christoph) - Series cleaning up bio flags (Christoph) - bio crypt fixes (Eric) - IO stats inflight tweak (Gabriel) - blk-mq tags fixes (Hannes) - Buffer invalidation fixes (Jan) - Allow soft limits for zone append (Johannes) - Shared tag set improvements (John, Kashyap) - Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel) - DM no-wait support (Mike, Konstantin) - Request allocation improvements (Ming) - Allow md/dm/bcache to use IO stat helpers (Song) - Series improving blk-iocost (Tejun) - Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang, Xianting, Yang, Yufen, yangerkun) * tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits) block: fix uapi blkzoned.h comments blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue blk-mq: get rid of the dead flush handle code path block: get rid of unnecessary local variable block: fix comment and add lockdep assert blk-mq: use helper function to test hw stopped block: use helper function to test queue register block: remove redundant mq check block: invoke blk_mq_exit_sched no matter whether have .exit_sched percpu_ref: don't refer to ref->data if it isn't allocated block: ratelimit handle_bad_sector() message blk-throttle: Re-use the throtl_set_slice_end() blk-throttle: Open code __throtl_de/enqueue_tg() blk-throttle: Move service tree validation out of the throtl_rb_first() blk-throttle: Move the list operation after list validation blk-throttle: Fix IO hang for a corner case blk-throttle: Avoid tracking latency if low limit is invalid blk-throttle: Avoid getting the current time if tg->last_finish_time is 0 blk-throttle: Remove a meaningless parameter for throtl_downgrade_state() block: Remove redundant 'return' statement ...
478 lines
12 KiB
C
478 lines
12 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>
|
|
|
|
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) {
|
|
struct block_device *bdev;
|
|
|
|
bio->bi_iter.bi_sector = map_swap_page(page, &bdev);
|
|
bio_set_dev(bio, bdev);
|
|
bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
|
|
bio->bi_end_io = end_io;
|
|
|
|
bio_add_page(bio, page, thp_size(page), 0);
|
|
}
|
|
return bio;
|
|
}
|
|
|
|
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 rotate_reclaimable_page()
|
|
*/
|
|
set_page_dirty(page);
|
|
pr_alert("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 swap_slot_free_notify(struct page *page)
|
|
{
|
|
struct swap_info_struct *sis;
|
|
struct gendisk *disk;
|
|
swp_entry_t entry;
|
|
|
|
/*
|
|
* There is no guarantee that the page is in swap cache - the software
|
|
* suspend code (at least) uses end_swap_bio_read() against a non-
|
|
* swapcache page. So we must check PG_swapcache before proceeding with
|
|
* this optimization.
|
|
*/
|
|
if (unlikely(!PageSwapCache(page)))
|
|
return;
|
|
|
|
sis = page_swap_info(page);
|
|
if (data_race(!(sis->flags & SWP_BLKDEV)))
|
|
return;
|
|
|
|
/*
|
|
* The swap subsystem performs lazy swap slot freeing,
|
|
* expecting that the page will be swapped out again.
|
|
* So we can avoid an unnecessary write if the page
|
|
* isn't redirtied.
|
|
* This is good for real swap storage because we can
|
|
* reduce unnecessary I/O and enhance wear-leveling
|
|
* if an SSD is used as the as swap device.
|
|
* But if in-memory swap device (eg zram) is used,
|
|
* this causes a duplicated copy between uncompressed
|
|
* data in VM-owned memory and compressed data in
|
|
* zram-owned memory. So let's free zram-owned memory
|
|
* and make the VM-owned decompressed page *dirty*,
|
|
* so the page should be swapped out somewhere again if
|
|
* we again wish to reclaim it.
|
|
*/
|
|
disk = sis->bdev->bd_disk;
|
|
entry.val = page_private(page);
|
|
if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
|
|
unsigned long offset;
|
|
|
|
offset = swp_offset(entry);
|
|
|
|
SetPageDirty(page);
|
|
disk->fops->swap_slot_free_notify(sis->bdev,
|
|
offset);
|
|
}
|
|
}
|
|
|
|
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("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);
|
|
swap_slot_free_notify(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 sector_t swap_page_sector(struct page *page)
|
|
{
|
|
return (sector_t)__page_file_index(page) << (PAGE_SHIFT - 9);
|
|
}
|
|
|
|
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;
|
|
|
|
if (!page->mem_cgroup)
|
|
return;
|
|
|
|
rcu_read_lock();
|
|
css = cgroup_e_css(page->mem_cgroup->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)) {
|
|
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
|
|
* 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 (%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;
|
|
}
|
|
|
|
ret = 0;
|
|
bio = get_swap_bio(GFP_NOIO, page, end_write_func);
|
|
if (bio == NULL) {
|
|
set_page_dirty(page);
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
|
|
bio_associate_blkg_from_page(bio, page);
|
|
count_swpout_vm_event(page);
|
|
set_page_writeback(page);
|
|
unlock_page(page);
|
|
submit_bio(bio);
|
|
out:
|
|
return ret;
|
|
}
|
|
|
|
int swap_readpage(struct page *page, bool synchronous)
|
|
{
|
|
struct bio *bio;
|
|
int ret = 0;
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
blk_qc_t qc;
|
|
struct gendisk *disk;
|
|
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.
|
|
*/
|
|
psi_memstall_enter(&pflags);
|
|
|
|
if (frontswap_load(page) == 0) {
|
|
SetPageUptodate(page);
|
|
unlock_page(page);
|
|
goto out;
|
|
}
|
|
|
|
if (data_race(sis->flags & SWP_FS)) {
|
|
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) {
|
|
if (trylock_page(page)) {
|
|
swap_slot_free_notify(page);
|
|
unlock_page(page);
|
|
}
|
|
|
|
count_vm_event(PSWPIN);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
ret = 0;
|
|
bio = get_swap_bio(GFP_KERNEL, page, end_swap_bio_read);
|
|
if (bio == NULL) {
|
|
unlock_page(page);
|
|
ret = -ENOMEM;
|
|
goto out;
|
|
}
|
|
disk = bio->bi_disk;
|
|
/*
|
|
* Keep this task valid during swap readpage because the oom killer may
|
|
* attempt to access it in the page fault retry time check.
|
|
*/
|
|
bio_set_op_attrs(bio, REQ_OP_READ, 0);
|
|
if (synchronous) {
|
|
bio->bi_opf |= REQ_HIPRI;
|
|
get_task_struct(current);
|
|
bio->bi_private = current;
|
|
}
|
|
count_vm_event(PSWPIN);
|
|
bio_get(bio);
|
|
qc = submit_bio(bio);
|
|
while (synchronous) {
|
|
set_current_state(TASK_UNINTERRUPTIBLE);
|
|
if (!READ_ONCE(bio->bi_private))
|
|
break;
|
|
|
|
if (!blk_poll(disk->queue, qc, true))
|
|
blk_io_schedule();
|
|
}
|
|
__set_current_state(TASK_RUNNING);
|
|
bio_put(bio);
|
|
|
|
out:
|
|
psi_memstall_leave(&pflags);
|
|
return ret;
|
|
}
|
|
|
|
int swap_set_page_dirty(struct page *page)
|
|
{
|
|
struct swap_info_struct *sis = page_swap_info(page);
|
|
|
|
if (data_race(sis->flags & SWP_FS)) {
|
|
struct address_space *mapping = sis->swap_file->f_mapping;
|
|
|
|
VM_BUG_ON_PAGE(!PageSwapCache(page), page);
|
|
return mapping->a_ops->set_page_dirty(page);
|
|
} else {
|
|
return __set_page_dirty_no_writeback(page);
|
|
}
|
|
}
|