mm: test code to write THP to swap device as a whole

To support delay splitting THP (Transparent Huge Page) after swapped
out, we need to enhance swap writing code to support to write a THP as a
whole.  This will improve swap write IO performance.

As Ming Lei <ming.lei@redhat.com> pointed out, this should be based on
multipage bvec support, which hasn't been merged yet.  So this patch is
only for testing the functionality of the other patches in the series.
And will be reimplemented after multipage bvec support is merged.

Link: http://lkml.kernel.org/r/20170724051840.2309-7-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Ross Zwisler <ross.zwisler@intel.com> [for brd.c, zram_drv.c, pmem.c]
Cc: Shaohua Li <shli@kernel.org>
Cc: Vishal L Verma <vishal.l.verma@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7b1cf4b..1f0720d 100644 (file)
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -38,7 +38,15 @@
 #define BIO_BUG_ON
 #endif
 
+#ifdef CONFIG_THP_SWAP
+#if HPAGE_PMD_NR > 256
+#define BIO_MAX_PAGES          HPAGE_PMD_NR
+#else
 #define BIO_MAX_PAGES          256
+#endif
+#else
+#define BIO_MAX_PAGES          256
+#endif
 
 #define bio_prio(bio)                  (bio)->bi_ioprio
 #define bio_set_prio(bio, prio)                ((bio)->bi_ioprio = prio)

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index d33e328..ba2d470 100644 (file)
--- 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 37e8d31..c75024e 100644 (file)
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -85,6 +85,7 @@ 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 5f61b54..20139b9 100644 (file)
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -28,16 +28,18 @@
 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;
 }
@@ -262,6 +264,15 @@ 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)
 {
@@ -313,7 +324,7 @@ 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;
        }
 
@@ -326,7 +337,7 @@ 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 9a4441b..bccf426 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1071,6 +1071,7 @@ const char * const vmstat_text[] = {
 #endif
        "thp_zero_page_alloc",
        "thp_zero_page_alloc_failed",
+       "thp_swpout",
 #endif
 #ifdef CONFIG_MEMORY_BALLOON
        "balloon_inflate",