linux-kernel - [PATCH v2 1/3] mm/ksm: refactor out try_to_merge_with_zero

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20240621-b4-ksm-scan-optimize-v2-1-1c328aa9e30b@linux.dev>
Date: Fri, 21 Jun 2024 15:54:29 +0800
From: Chengming Zhou <chengming.zhou@...ux.dev>
To: Andrew Morton <akpm@...ux-foundation.org>, david@...hat.com, 
 aarcange@...hat.com, hughd@...gle.com, shr@...kernel.io
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org, 
 zhouchengming@...edance.com, Chengming Zhou <chengming.zhou@...ux.dev>
Subject: [PATCH v2 1/3] mm/ksm: refactor out try_to_merge_with_zero_page()

In preparation for later changes, refactor out a new function called
try_to_merge_with_zero_page(), which tries to merge with zero page.

Signed-off-by: Chengming Zhou <chengming.zhou@...ux.dev>
---
 mm/ksm.c | 70 ++++++++++++++++++++++++++++++++++++----------------------------
 1 file changed, 40 insertions(+), 30 deletions(-)

diff --git a/mm/ksm.c b/mm/ksm.c
index 34c4820e0d3d..1427abd18627 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1531,6 +1531,44 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 	return err;
 }
 
+/*
+ * This function returns 0 if the pages were merged or if they are
+ * no longer merging candidates (e.g., VMA stale), -EFAULT otherwise.
+ */
+static int try_to_merge_with_zero_page(struct ksm_rmap_item *rmap_item,
+				       struct page *page)
+{
+	struct mm_struct *mm = rmap_item->mm;
+	int err = -EFAULT;
+
+	/*
+	 * Same checksum as an empty page. We attempt to merge it with the
+	 * appropriate zero page if the user enabled this via sysfs.
+	 */
+	if (ksm_use_zero_pages && (rmap_item->oldchecksum == zero_checksum)) {
+		struct vm_area_struct *vma;
+
+		mmap_read_lock(mm);
+		vma = find_mergeable_vma(mm, rmap_item->address);
+		if (vma) {
+			err = try_to_merge_one_page(vma, page,
+					ZERO_PAGE(rmap_item->address));
+			trace_ksm_merge_one_page(
+				page_to_pfn(ZERO_PAGE(rmap_item->address)),
+				rmap_item, mm, err);
+		} else {
+			/*
+			 * If the vma is out of date, we do not need to
+			 * continue.
+			 */
+			err = 0;
+		}
+		mmap_read_unlock(mm);
+	}
+
+	return err;
+}
+
 /*
  * try_to_merge_with_ksm_page - like try_to_merge_two_pages,
  * but no new kernel page is allocated: kpage must already be a ksm page.
@@ -2306,7 +2344,6 @@ static void stable_tree_append(struct ksm_rmap_item *rmap_item,
  */
 static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_item)
 {
-	struct mm_struct *mm = rmap_item->mm;
 	struct ksm_rmap_item *tree_rmap_item;
 	struct page *tree_page = NULL;
 	struct ksm_stable_node *stable_node;
@@ -2375,36 +2412,9 @@ static void cmp_and_merge_page(struct page *page, struct ksm_rmap_item *rmap_ite
 		return;
 	}
 
-	/*
-	 * Same checksum as an empty page. We attempt to merge it with the
-	 * appropriate zero page if the user enabled this via sysfs.
-	 */
-	if (ksm_use_zero_pages && (checksum == zero_checksum)) {
-		struct vm_area_struct *vma;
+	if (!try_to_merge_with_zero_page(rmap_item, page))
+		return;
 
-		mmap_read_lock(mm);
-		vma = find_mergeable_vma(mm, rmap_item->address);
-		if (vma) {
-			err = try_to_merge_one_page(vma, page,
-					ZERO_PAGE(rmap_item->address));
-			trace_ksm_merge_one_page(
-				page_to_pfn(ZERO_PAGE(rmap_item->address)),
-				rmap_item, mm, err);
-		} else {
-			/*
-			 * If the vma is out of date, we do not need to
-			 * continue.
-			 */
-			err = 0;
-		}
-		mmap_read_unlock(mm);
-		/*
-		 * In case of failure, the page was not really empty, so we
-		 * need to continue. Otherwise we're done.
-		 */
-		if (!err)
-			return;
-	}
 	tree_rmap_item =
 		unstable_tree_search_insert(rmap_item, page, &tree_page);
 	if (tree_rmap_item) {

-- 
2.45.2