[PATCH -mm -V3 10/21] mm, THP, swap: Support to count THP swapin and its fallback

[Huang, Ying]

From: Huang Ying <ying.huang@xxxxxxxxx>

2 new /proc/vmstat fields are added, "thp_swapin" and
"thp_swapin_fallback" to count swapin a THP from swap device as a
whole and fallback to normal page swapin.

Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
---
 Documentation/vm/transhuge.rst | 10 +++++++++-
 include/linux/vm_event_item.h  |  2 ++
 mm/huge_memory.c               |  4 +++-
 mm/page_io.c                   | 15 ++++++++++++---
 mm/vmstat.c                    |  2 ++
 5 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/Documentation/vm/transhuge.rst b/Documentation/vm/transhuge.rst
index 2c6867fca6ff..a87b1d880cd4 100644
--- a/Documentation/vm/transhuge.rst
+++ b/Documentation/vm/transhuge.rst
@@ -360,10 +360,18 @@ thp_swpout
 	piece without splitting.
 
 thp_swpout_fallback
-	is incremented if a huge page has to be split before swapout.
+	is incremented if a huge page is split before swapout.
 	Usually because failed to allocate some continuous swap space
 	for the huge page.
 
+thp_swpin
+	is incremented every time a huge page is swapin in one piece
+	without splitting.
+
+thp_swpin_fallback
+	is incremented if a huge page is split during swapin.  Usually
+	because failed to allocate a huge page.
+
 As the system ages, allocating huge pages may be expensive as the
 system uses memory compaction to copy data around memory to free a
 huge page for use. There are some counters in ``/proc/vmstat`` to help
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 5c7f010676a7..7b438548a78e 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -88,6 +88,8 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		THP_ZERO_PAGE_ALLOC_FAILED,
 		THP_SWPOUT,
 		THP_SWPOUT_FALLBACK,
+		THP_SWPIN,
+		THP_SWPIN_FALLBACK,
 #endif
 #ifdef CONFIG_MEMORY_BALLOON
 		BALLOON_INFLATE,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8303fa021c42..c2437914c632 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1664,8 +1664,10 @@ int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
 				/* swapoff occurs under us */
 				} else if (ret == -EINVAL)
 					ret = 0;
-				else
+				else {
+					count_vm_event(THP_SWPIN_FALLBACK);
 					goto fallback;
+				}
 			}
 			delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 			goto out;
diff --git a/mm/page_io.c b/mm/page_io.c
index b41cf9644585..96277058681e 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -347,6 +347,15 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 	return ret;
 }
 
+static inline void count_swpin_vm_event(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	if (unlikely(PageTransHuge(page)))
+		count_vm_event(THP_SWPIN);
+#endif
+	count_vm_events(PSWPIN, hpage_nr_pages(page));
+}
+
 int swap_readpage(struct page *page, bool synchronous)
 {
 	struct bio *bio;
@@ -370,7 +379,7 @@ int swap_readpage(struct page *page, bool synchronous)
 
 		ret = mapping->a_ops->readpage(swap_file, page);
 		if (!ret)
-			count_vm_event(PSWPIN);
+			count_swpin_vm_event(page);
 		return ret;
 	}
 
@@ -381,7 +390,7 @@ int swap_readpage(struct page *page, bool synchronous)
 			unlock_page(page);
 		}
 
-		count_vm_event(PSWPIN);
+		count_swpin_vm_event(page);
 		return 0;
 	}
 
@@ -400,7 +409,7 @@ int swap_readpage(struct page *page, bool synchronous)
 	get_task_struct(current);
 	bio->bi_private = current;
 	bio_set_op_attrs(bio, REQ_OP_READ, 0);
-	count_vm_event(PSWPIN);
+	count_swpin_vm_event(page);
 	bio_get(bio);
 	qc = submit_bio(bio);
 	while (synchronous) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 75eda9c2b260..259c7bddbb6e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1263,6 +1263,8 @@ const char * const vmstat_text[] = {
 	"thp_zero_page_alloc_failed",
 	"thp_swpout",
 	"thp_swpout_fallback",
+	"thp_swpin",
+	"thp_swpin_fallback",
 #endif
 #ifdef CONFIG_MEMORY_BALLOON
 	"balloon_inflate",
-- 
2.16.1