[PATCH v11 7/7] mm: Don't split THP page when syscall is called

[Minchan Kim]

We don't need to split THP page when MADV_FREE syscall is
called. It could be done when VM decide really frees it so
we could avoid unnecessary THP split.

Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
---
 mm/madvise.c | 20 +++++++++++++++++++-
 mm/rmap.c    |  7 +++----
 mm/vmscan.c  | 28 ++++++++++++++++++----------
 3 files changed, 40 insertions(+), 15 deletions(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index a6aa7d4c4e02..77f13a99584c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -272,7 +272,25 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	pte_t *pte, ptent;
 	struct page *page;
 
-	split_huge_page_pmd(vma, addr, pmd);
+	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+		struct page *page;
+		pmd_t orig_pmd;
+
+		orig_pmd = pmdp_get_and_clear(mm, addr, pmd);
+
+		/* No hugepage in swapcache */
+		page = pmd_page(orig_pmd);
+		VM_BUG_ON_PAGE(PageSwapCache(page), page);
+
+		orig_pmd = pmd_mkold(orig_pmd);
+		orig_pmd = pmd_mkclean(orig_pmd);
+
+		set_pmd_at(mm, addr, pmd, orig_pmd);
+		tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+		spin_unlock(ptl);
+		return 0;
+	}
+
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
diff --git a/mm/rmap.c b/mm/rmap.c
index a8e34596dc97..67e1c1859c1d 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -703,10 +703,9 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 		if (pmdp_clear_flush_young_notify(vma, address, pmd))
 			referenced++;
 
-		/*
-		 * In this implmentation, MADV_FREE doesn't support THP free
-		 */
-		dirty++;
+		if (pmd_dirty(*pmd))
+			dirty++;
+
 		spin_unlock(ptl);
 	} else {
 		pte_t *pte;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d88413ccadcc..6557f0b36321 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -971,17 +971,25 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
-			if (!(sc->gfp_mask & __GFP_IO))
-				goto keep_locked;
-			if (!add_to_swap(page, page_list))
-				goto activate_locked;
-			may_enter_fs = 1;
-
-			/* Adding to swap updated mapping */
-			mapping = page_mapping(page);
+		if (PageAnon(page) && !PageSwapCache(page)) {
+			if (!freeable) {
+				if (!(sc->gfp_mask & __GFP_IO))
+					goto keep_locked;
+				if (!add_to_swap(page, page_list))
+					goto activate_locked;
+				may_enter_fs = 1;
+				/* Adding to swap updated mapping */
+				mapping = page_mapping(page);
+			} else {
+				if (likely(!PageTransHuge(page)))
+					goto unmap;
+				/* try_to_unmap isn't aware of THP page */
+				if (unlikely(split_huge_page_to_list(page,
+								page_list)))
+					goto keep_locked;
+			}
 		}
-
+unmap:
 		/*
 		 * The page is mapped into the page tables of one or more
 		 * processes. Try to unmap it here.
-- 
2.0.0

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/