The patch titled
Subject: mm: use an on-stack bio for synchronous swapin
has been added to the -mm mm-unstable branch. Its filename is
mm-use-an-on-stack-bio-for-synchronous-swapin.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-use-an-on-stack-bio-for-synchronous-swapin.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Christoph Hellwig <hch@xxxxxx>
Subject: mm: use an on-stack bio for synchronous swapin
Date: Wed, 25 Jan 2023 14:34:33 +0100
Optimize the synchronous swap in case by using an on-stack bio instead of
allocating one using bio_alloc.
Link: https://lkml.kernel.org/r/20230125133436.447864-5-hch@xxxxxx
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Keith Busch <kbusch@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Sergey Senozhatsky <senozhatsky@xxxxxxxxxxxx>
Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
--- a/mm/page_io.c~mm-use-an-on-stack-bio-for-synchronous-swapin
+++ a/mm/page_io.c
@@ -51,10 +51,9 @@ static void end_swap_bio_write(struct bi
bio_put(bio);
}
-static void end_swap_bio_read(struct bio *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);
@@ -62,18 +61,16 @@ static void end_swap_bio_read(struct bio
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;
+ } else {
+ SetPageUptodate(page);
}
-
- SetPageUptodate(page);
-out:
unlock_page(page);
- WRITE_ONCE(bio->bi_private, NULL);
+}
+
+static void end_swap_bio_read(struct bio *bio)
+{
+ __end_swap_bio_read(bio);
bio_put(bio);
- if (waiter) {
- blk_wake_io_task(waiter);
- put_task_struct(waiter);
- }
}
int generic_swapfile_activate(struct swap_info_struct *sis,
@@ -444,10 +441,11 @@ static void swap_readpage_fs(struct page
*plug = sio;
}
-static void swap_readpage_bdev(struct page *page, bool synchronous,
+static void swap_readpage_bdev_sync(struct page *page,
struct swap_info_struct *sis)
{
- struct bio *bio;
+ struct bio_vec bv;
+ struct bio bio;
if ((sis->flags & SWP_SYNCHRONOUS_IO) &&
!bdev_read_page(sis->bdev, swap_page_sector(page), page)) {
@@ -455,30 +453,37 @@ static void swap_readpage_bdev(struct pa
return;
}
- 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);
+ bio_init(&bio, sis->bdev, &bv, 1, REQ_OP_READ);
+ bio.bi_iter.bi_sector = swap_page_sector(page);
+ 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) {
- get_task_struct(current);
- bio->bi_private = current;
- }
+ get_task_struct(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;
+ submit_bio_wait(&bio);
+ __end_swap_bio_read(&bio);
+ put_task_struct(current);
+}
+
+static void swap_readpage_bdev_async(struct page *page,
+ struct swap_info_struct *sis)
+{
+ struct bio *bio;
- blk_io_schedule();
+ if ((sis->flags & SWP_SYNCHRONOUS_IO) &&
+ !bdev_read_page(sis->bdev, swap_page_sector(page), page)) {
+ count_vm_event(PSWPIN);
+ return;
}
- __set_current_state(TASK_RUNNING);
- bio_put(bio);
+
+ 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);
+ count_vm_event(PSWPIN);
+ submit_bio(bio);
}
void swap_readpage(struct page *page, bool synchronous, struct swap_iocb **plug)
@@ -508,8 +513,10 @@ void swap_readpage(struct page *page, bo
unlock_page(page);
} else if (data_race(sis->flags & SWP_FS_OPS)) {
swap_readpage_fs(page, plug);
+ } else if (synchronous) {
+ swap_readpage_bdev_sync(page, sis);
} else {
- swap_readpage_bdev(page, synchronous, sis);
+ swap_readpage_bdev_async(page, sis);
}
if (workingset) {
_
Patches currently in -mm which might be from hch@xxxxxx are
revert-remoteproc-qcom_q6v5_mss-map-unmap-metadata-region-before-after-use.patch
mm-reject-vmap-with-vm_flush_reset_perms.patch
mm-remove-__vfree.patch
mm-remove-__vfree_deferred.patch
mm-move-vmalloc_init-and-free_work-down-in-vmallocc.patch
mm-call-vfree-instead-of-__vunmap-from-delayed_vfree_work.patch
mm-move-__remove_vm_area-out-of-va_remove_mappings.patch
mm-use-remove_vm_area-in-__vunmap.patch
mm-move-debug-checks-from-__vunmap-to-remove_vm_area.patch
mm-split-__vunmap.patch
mm-refactor-va_remove_mappings.patch
mpage-stop-using-bdev_readwrite_page.patch
mm-remove-the-swap_readpage-return-value.patch
mm-factor-out-a-swap_readpage_bdev-helper.patch
mm-use-an-on-stack-bio-for-synchronous-swapin.patch
mm-remove-the-__swap_writepage-return-value.patch
mm-factor-out-a-swap_writepage_bdev-helper.patch
block-remove-rw_page.patch
