[PATCHv3 23/24] ksm: split huge pages on follow_page()

[Kirill A. Shutemov]

Let's split THP with FOLL_SPLIT. Attempting to split them laterk would
always fail bacause we take references on tail pages.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
 mm/ksm.c | 58 ++++++++--------------------------------------------------
 1 file changed, 8 insertions(+), 50 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c
index a8a88b0f6f62..8d977f074a74 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -441,20 +441,6 @@ static void break_cow(struct rmap_item *rmap_item)
 	up_read(&mm->mmap_sem);
 }
 
-static struct page *page_trans_compound_anon(struct page *page)
-{
-	if (PageTransCompound(page)) {
-		struct page *head = compound_head(page);
-		/*
-		 * head may actually be splitted and freed from under
-		 * us but it's ok here.
-		 */
-		if (PageAnon(head))
-			return head;
-	}
-	return NULL;
-}
-
 static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 {
 	struct mm_struct *mm = rmap_item->mm;
@@ -467,10 +453,10 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 	if (!vma)
 		goto out;
 
-	page = follow_page(vma, addr, FOLL_GET);
+	page = follow_page(vma, addr, FOLL_GET | FOLL_SPLIT);
 	if (IS_ERR_OR_NULL(page))
 		goto out;
-	if (PageAnon(page) || page_trans_compound_anon(page)) {
+	if (PageAnon(page)) {
 		flush_anon_page(vma, page, addr);
 		flush_dcache_page(page);
 	} else {
@@ -976,35 +962,6 @@ out:
 	return err;
 }
 
-static int page_trans_compound_anon_split(struct page *page)
-{
-	int ret = 0;
-	struct page *transhuge_head = page_trans_compound_anon(page);
-	if (transhuge_head) {
-		/* Get the reference on the head to split it. */
-		if (get_page_unless_zero(transhuge_head)) {
-			/*
-			 * Recheck we got the reference while the head
-			 * was still anonymous.
-			 */
-			if (PageAnon(transhuge_head)) {
-				lock_page(transhuge_head);
-				ret = split_huge_page(transhuge_head);
-				unlock_page(transhuge_head);
-			} else
-				/*
-				 * Retry later if split_huge_page run
-				 * from under us.
-				 */
-				ret = 1;
-			put_page(transhuge_head);
-		} else
-			/* Retry later if split_huge_page run from under us. */
-			ret = 1;
-	}
-	return ret;
-}
-
 /*
  * try_to_merge_one_page - take two pages and merge them into one
  * @vma: the vma that holds the pte pointing to page
@@ -1025,9 +982,10 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 
 	if (!(vma->vm_flags & VM_MERGEABLE))
 		goto out;
-	if (PageTransCompound(page) && page_trans_compound_anon_split(page))
-		goto out;
+
+	/* huge pages must be split by this time */
 	BUG_ON(PageTransCompound(page));
+
 	if (!PageAnon(page))
 		goto out;
 
@@ -1616,14 +1574,14 @@ next_mm:
 		while (ksm_scan.address < vma->vm_end) {
 			if (ksm_test_exit(mm))
 				break;
-			*page = follow_page(vma, ksm_scan.address, FOLL_GET);
+			*page = follow_page(vma, ksm_scan.address,
+					FOLL_GET | FOLL_SPLIT);
 			if (IS_ERR_OR_NULL(*page)) {
 				ksm_scan.address += PAGE_SIZE;
 				cond_resched();
 				continue;
 			}
-			if (PageAnon(*page) ||
-			    page_trans_compound_anon(*page)) {
+			if (PageAnon(*page)) {
 				flush_anon_page(vma, *page, ksm_scan.address);
 				flush_dcache_page(*page);
 				rmap_item = get_next_rmap_item(slot,
-- 
2.1.4

--
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/