[RFC 11/11] mm, THP, swap: Delay splitting THP during swap out

[Huang, Ying]

From: Huang Ying <ying.huang@xxxxxxxxx>

In this patch, the splitting huge page is delayed from almost the first
step of swapping out to after allocating the swap space for THP and
adding the THP into swap cache.  This will reduce lock
acquiring/releasing for locks used for swap space and swap cache
management.

This is the also first step for THP (Transparent Huge Page) swap
support.  The plan is to delaying splitting THP step by step and avoid
splitting THP finally.

The advantages of THP swap support are:

- Batch swap operations for THP to reduce lock acquiring/releasing,
  including allocating/freeing swap space, adding/deleting to/from swap
  cache, and writing/reading swap space, etc.

- THP swap space read/write will be 2M sequence IO.  It is particularly
  helpful for swap read, which usually are 4k random IO.

- It will help memory fragmentation, especially when THP is heavily used
  by the applications.  2M continuous pages will be free up after THP
  swapping out.

With the patchset, the swap out bandwidth improved 12.1% in
vm-scalability swap-w-seq test case with 16 processes on a Xeon E5 v3
system.  To test sequence swap out, the test case uses 16 processes
sequentially allocate and write to anonymous pages until RAM and part of
the swap device is used up.

The detailed compare result is as follow,

base             base+patchset
---------------- --------------------------
         %stddev     %change         %stddev
             \          |                \
   1118821 Â  0%     +12.1%    1254241 Â  1%  vmstat.swap.so
   2460636 Â  1%     +10.6%    2720983 Â  1%  vm-scalability.throughput
    308.79 Â  1%      -7.9%     284.53 Â  1%  vm-scalability.time.elapsed_time
      1639 Â  4%    +232.3%       5446 Â  1%  meminfo.SwapCached
      0.70 Â  3%      +8.7%       0.77 Â  5%  perf-stat.ipc
      9.82 Â  8%     -31.6%       6.72 Â  2%  perf-profile.cycles-pp._raw_spin_lock_irq.__add_to_swap_cache.add_to_swap_cache.add_to_swap.shrink_page_list

Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
---
 mm/swap_state.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 50 insertions(+), 3 deletions(-)

diff --git a/mm/swap_state.c b/mm/swap_state.c
index a41fd10..5316fbc 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,6 +17,7 @@
 #include <linux/blkdev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
+#include <linux/huge_mm.h>
 
 #include <asm/pgtable.h>
 
@@ -172,12 +173,45 @@ void __delete_from_swap_cache(struct page *page)
 	ADD_CACHE_INFO(del_total, nr);
 }
 
+int add_to_swap_trans_huge(struct page *page, struct list_head *list)
+{
+	swp_entry_t entry;
+	int ret = 0;
+
+	/* cannot split, which may be needed during swap in, skip it */
+	if (!can_split_huge_page(page))
+		return -EBUSY;
+	/* fallback to split huge page firstly if no PMD map */
+	if (!compound_mapcount(page))
+		return 0;
+	entry = get_huge_swap_page();
+	if (!entry.val)
+		return 0;
+	if (mem_cgroup_try_charge_swap(page, entry, HPAGE_PMD_NR)) {
+		__swapcache_free(entry, true);
+		return -EOVERFLOW;
+	}
+	ret = add_to_swap_cache(page, entry,
+				__GFP_HIGH | __GFP_NOMEMALLOC|__GFP_NOWARN);
+	/* -ENOMEM radix-tree allocation failure */
+	if (ret) {
+		__swapcache_free(entry, true);
+		return 0;
+	}
+	ret = split_huge_page_to_list(page, list);
+	if (ret) {
+		delete_from_swap_cache(page);
+		return -EBUSY;
+	}
+	return 1;
+}
+
 /**
  * add_to_swap - allocate swap space for a page
  * @page: page we want to move to swap
  *
  * Allocate swap space for the page and add the page to the
- * swap cache.  Caller needs to hold the page lock. 
+ * swap cache.  Caller needs to hold the page lock.
  */
 int add_to_swap(struct page *page, struct list_head *list)
 {
@@ -187,6 +221,14 @@ int add_to_swap(struct page *page, struct list_head *list)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageUptodate(page), page);
 
+	if (unlikely(PageTransHuge(page))) {
+		err = add_to_swap_trans_huge(page, list);
+		if (err < 0)
+			return 0;
+		else if (err > 0)
+			return err;
+		/* fallback to split firstly if return 0 */
+	}
 	entry = get_swap_page();
 	if (!entry.val)
 		return 0;
@@ -306,7 +348,7 @@ struct page * lookup_swap_cache(swp_entry_t entry)
 
 	page = find_get_page(swap_address_space(entry), entry.val);
 
-	if (page) {
+	if (page && likely(!PageCompound(page))) {
 		INC_CACHE_INFO(find_success);
 		if (TestClearPageReadahead(page))
 			atomic_inc(&swapin_readahead_hits);
@@ -332,8 +374,13 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * that would confuse statistics.
 		 */
 		found_page = find_get_page(swapper_space, entry.val);
-		if (found_page)
+		if (found_page) {
+			if (unlikely(PageCompound(found_page))) {
+				put_page(found_page);
+				found_page = NULL;
+			}
 			break;
+		}
 
 		/*
 		 * Get a new page to read into from swap.
-- 
2.8.1