From: Huang Ying <ying.hu...@intel.com>
In the patch, the swap writing is enhanced to support to write a
THP (Transparent Huge Page) as a whole. This is a part of the THP
swap optimization and will improve swap write IO performance for the
more large continuous IOs.
Signed-off-by: "Huang, Ying" <ying.hu...@intel.com>
Cc: Johannes Weiner <han...@cmpxchg.org>
Cc: Minchan Kim <minc...@kernel.org>
Cc: Hugh Dickins <hu...@google.com>
Cc: Shaohua Li <s...@kernel.org>
Cc: Rik van Riel <r...@redhat.com>
Cc: Jens Axboe <ax...@fb.com>
---
include/linux/page-flags.h | 4 ++--
include/linux/vm_event_item.h | 1 +
mm/page_io.c | 21 ++++++++++++++++-----
mm/vmstat.c | 1 +
4 files changed, 20 insertions(+), 7 deletions(-)
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index d33e3280c8ad..ba2d470d2d0a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -303,8 +303,8 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
* Only test-and-set exist for PG_writeback. The unconditional operators are
* risky: they bypass page accounting.
*/
-TESTPAGEFLAG(Writeback, writeback, PF_NO_COMPOUND)
- TESTSCFLAG(Writeback, writeback, PF_NO_COMPOUND)
+TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL)
+ TESTSCFLAG(Writeback, writeback, PF_NO_TAIL)
PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL)
/* PG_readahead is only used for reads; PG_reclaim is only for writes */
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index d84ae90ccd5c..5b5b0f094060 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -84,6 +84,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
#endif
THP_ZERO_PAGE_ALLOC,
THP_ZERO_PAGE_ALLOC_FAILED,
+ THP_SWPOUT,
#endif
#ifdef CONFIG_MEMORY_BALLOON
BALLOON_INFLATE,
diff --git a/mm/page_io.c b/mm/page_io.c
index 23f6d0d3470f..ec5229fb3607 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -27,16 +27,18 @@
static struct bio *get_swap_bio(gfp_t gfp_flags,
struct page *page, bio_end_io_t end_io)
{
+ int i, nr = hpage_nr_pages(page);
struct bio *bio;
- bio = bio_alloc(gfp_flags, 1);
+ bio = bio_alloc(gfp_flags, nr);
if (bio) {
bio->bi_iter.bi_sector = map_swap_page(page, &bio->bi_bdev);
bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9;
bio->bi_end_io = end_io;
- bio_add_page(bio, page, PAGE_SIZE, 0);
- BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE);
+ for (i = 0; i < nr; i++)
+ bio_add_page(bio, page + i, PAGE_SIZE, 0);
+ VM_BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE * nr);
}
return bio;
}
@@ -257,6 +259,15 @@ 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, hpage_nr_pages(page));
+}
+
int __swap_writepage(struct page *page, struct writeback_control *wbc,
bio_end_io_t end_write_func)
{
@@ -308,7 +319,7 @@ int __swap_writepage(struct page *page, struct
writeback_control *wbc,
ret = bdev_write_page(sis->bdev, swap_page_sector(page), page, wbc);
if (!ret) {
- count_vm_event(PSWPOUT);
+ count_swpout_vm_event(page);
return 0;
}
@@ -321,7 +332,7 @@ int __swap_writepage(struct page *page, struct
writeback_control *wbc,
goto out;
}
bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
- count_vm_event(PSWPOUT);
+ count_swpout_vm_event(page);
set_page_writeback(page);
unlock_page(page);
submit_bio(bio);
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c432e581f9a9..ebfd79df1008 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1070,6 +1070,7 @@ const char * const vmstat_text[] = {
#endif
"thp_zero_page_alloc",
"thp_zero_page_alloc_failed",
+ "thp_swpout",
#endif
#ifdef CONFIG_MEMORY_BALLOON
"balloon_inflate",
--
2.11.0
