linux-kernel - [PATCH 2/4] mm: swap: correctly use maxpages in swapon syscall to avoid potensial deadloop

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: <20250522122554.12209-3-shikemeng@huaweicloud.com>
Date: Thu, 22 May 2025 20:25:52 +0800
From: Kemeng Shi <shikemeng@...weicloud.com>
To: akpm@...ux-foundation.org
Cc: kasong@...cent.com,
	bhe@...hat.com,
	hannes@...xchg.org,
	linux-mm@...ck.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH 2/4] mm: swap: correctly use maxpages in swapon syscall to avoid potensial deadloop

We use maxpages from read_swap_header() to initialize swap_info_struct,
however the maxpages might be reduced in setup_swap_extents() and the
si->max is assigned with the reduced maxpages from the
setup_swap_extents().
Obviously, this could lead to memory waste as we allocated memory based on
larger maxpages, besides, this could lead to a potensial deadloop as
following:
1) When calling setup_clusters() with larger maxpages, unavailable pages
within range [si->max, larger maxpages) are not accounted with
inc_cluster_info_page(). As a result, these pages are assumed available
but can not be allocated. The cluster contains these pages can be moved
to frag_clusters list after it's all available pages were allocated.
2) When the cluster mentioned in 1) is the only cluster in frag_clusters
list, cluster_alloc_swap_entry() assume order 0 allocation will never
failed and will enter a deadloop by keep trying to allocate page from the
only cluster in frag_clusters which contains no actually available page.

Call setup_swap_extents() to get the final maxpages before swap_info_struct
initialization to fix the issue.

Fixes: 661383c6111a3 ("mm: swap: relaim the cached parts that got scanned")
Signed-off-by: Kemeng Shi <shikemeng@...weicloud.com>
---
 mm/swapfile.c | 47 ++++++++++++++++++++---------------------------
 1 file changed, 20 insertions(+), 27 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 75b69213c2e7..a82f4ebefca3 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3141,43 +3141,30 @@ static unsigned long read_swap_header(struct swap_info_struct *si,
 	return maxpages;
 }
 
-static int setup_swap_map_and_extents(struct swap_info_struct *si,
-					union swap_header *swap_header,
-					unsigned char *swap_map,
-					unsigned long maxpages,
-					sector_t *span)
+static int setup_swap_map(struct swap_info_struct *si,
+			  union swap_header *swap_header,
+			  unsigned char *swap_map,
+			  unsigned long maxpages)
 {
-	unsigned int nr_good_pages;
 	unsigned long i;
-	int nr_extents;
-
-	nr_good_pages = maxpages - 1;	/* omit header page */
 
+	swap_map[0] = SWAP_MAP_BAD; /* omit header page */
 	for (i = 0; i < swap_header->info.nr_badpages; i++) {
 		unsigned int page_nr = swap_header->info.badpages[i];
 		if (page_nr == 0 || page_nr > swap_header->info.last_page)
 			return -EINVAL;
 		if (page_nr < maxpages) {
 			swap_map[page_nr] = SWAP_MAP_BAD;
-			nr_good_pages--;
+			si->pages--;
 		}
 	}
 
-	if (nr_good_pages) {
-		swap_map[0] = SWAP_MAP_BAD;
-		si->max = maxpages;
-		si->pages = nr_good_pages;
-		nr_extents = setup_swap_extents(si, span);
-		if (nr_extents < 0)
-			return nr_extents;
-		nr_good_pages = si->pages;
-	}
-	if (!nr_good_pages) {
+	if (!si->pages) {
 		pr_warn("Empty swap-file\n");
 		return -EINVAL;
 	}
 
-	return nr_extents;
+	return 0;
 }
 
 #define SWAP_CLUSTER_INFO_COLS						\
@@ -3217,7 +3204,7 @@ static struct swap_cluster_info *setup_clusters(struct swap_info_struct *si,
 	 * Mark unusable pages as unavailable. The clusters aren't
 	 * marked free yet, so no list operations are involved yet.
 	 *
-	 * See setup_swap_map_and_extents(): header page, bad pages,
+	 * See setup_swap_map(): header page, bad pages,
 	 * and the EOF part of the last cluster.
 	 */
 	inc_cluster_info_page(si, cluster_info, 0);
@@ -3354,6 +3341,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		goto bad_swap_unlock_inode;
 	}
 
+	si->max = maxpages;
+	si->pages = maxpages - 1;
+	nr_extents = setup_swap_extents(si, &span);
+	if (nr_extents < 0) {
+		error = nr_extents;
+		goto bad_swap_unlock_inode;
+	}
+	maxpages = si->max;
+
 	/* OK, set up the swap map and apply the bad block list */
 	swap_map = vzalloc(maxpages);
 	if (!swap_map) {
@@ -3365,12 +3361,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	if (error)
 		goto bad_swap_unlock_inode;
 
-	nr_extents = setup_swap_map_and_extents(si, swap_header, swap_map,
-						maxpages, &span);
-	if (unlikely(nr_extents < 0)) {
-		error = nr_extents;
+	error = setup_swap_map(si, swap_header, swap_map, maxpages);
+	if (error)
 		goto bad_swap_unlock_inode;
-	}
 
 	/*
 	 * Use kvmalloc_array instead of bitmap_zalloc as the allocation order might
-- 
2.30.0