[PATCH] mm: swap: correctly use maxpages in swapon syscall to avoid potential deadloop

[PATCH] mm: swap: correctly use maxpages in swapon syscall to avoid potential deadloop

[Kemeng Shi]

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 potential 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.

After this change, span will include badblocks and will become large
value which I think is correct value:
In summary, there are two kinds of swapfile_activate operations.
1. Filesystem style: Treat all blocks logical continuity and find
usable physical extents in logical range. In this way, si->pages
will be actual usable physical blocks and span will be "1 +
highest_block - lowest_block".
2. Block device style: Treat all blocks physically continue and
only one single extent is added. In this way, si->pages will be
si->max and span will be "si->pages - 1".
Actually, si->pages and si->max is only used in block device style
and span value is set with si->pages. As a result, span value in
block device style will become a larger value as you mentioned.

I think larger value is correct based on:
1. Span value in filesystem style is "1 + highest_block -
lowest_block" which is the range cover all possible phisical blocks
including the badblocks.
2. For block device style, si->pages is the actual usable block
number and is already in pr_info. The original span value before
this patch is also refer to usable block number which is redundant
in pr_info.

Link: https://lkml.kernel.org/r/20250522122554.12209-3-shikemeng@huaweicloud.com
Fixes: 661383c6111a ("mm: swap: relaim the cached parts that got scanned")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Baoquan He <bhe@redhat.com>
---
v1->v2:
-Fix typo
-Add description of behavior change of "span" in git log
-Ensure si->pages == si->max - 1 after setup_swap_extents()

 mm/swapfile.c | 53 +++++++++++++++++++++++++--------------------------
 1 file changed, 26 insertions(+), 27 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 68ce283e84be..57397434929e 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);
@@ -3363,6 +3350,21 @@ 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;
+	}
+	if (si->pages != si->max - 1) {
+		pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max);
+		error = -EINVAL;
+		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) {
@@ -3374,12 +3376,9 @@ 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
-- 
2.36.1

Re: [PATCH] mm: swap: correctly use maxpages in swapon syscall to avoid potential deadloop

[Andrew Morton]

On Fri, 18 Jul 2025 14:51:39 +0800 Kemeng Shi <shikemeng@huaweicloud.com> wrote:

> 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 potential 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.
> 
> After this change, span will include badblocks and will become large
> value which I think is correct value:
> In summary, there are two kinds of swapfile_activate operations.
> 1. Filesystem style: Treat all blocks logical continuity and find
> usable physical extents in logical range. In this way, si->pages
> will be actual usable physical blocks and span will be "1 +
> highest_block - lowest_block".
> 2. Block device style: Treat all blocks physically continue and
> only one single extent is added. In this way, si->pages will be
> si->max and span will be "si->pages - 1".
> Actually, si->pages and si->max is only used in block device style
> and span value is set with si->pages. As a result, span value in
> block device style will become a larger value as you mentioned.
> 
> I think larger value is correct based on:
> 1. Span value in filesystem style is "1 + highest_block -
> lowest_block" which is the range cover all possible phisical blocks
> including the badblocks.
> 2. For block device style, si->pages is the actual usable block
> number and is already in pr_info. The original span value before
> this patch is also refer to usable block number which is redundant
> in pr_info.
>
> Link: https://lkml.kernel.org/r/20250522122554.12209-3-shikemeng@huaweicloud.com
> Fixes: 661383c6111a ("mm: swap: relaim the cached parts that got scanned")
> Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
> Reviewed-by: Baoquan He <bhe@redhat.com>
> ---
> v1->v2:
> -Fix typo
> -Add description of behavior change of "span" in git log

I queued this change:

> -Ensure si->pages == si->max - 1 after setup_swap_extents()

as a -fix against the v1 patch and updated the base patch's changelog,
thanks.

--- a/mm/swapfile.c~mm-swap-correctly-use-maxpages-in-swapon-syscall-to-avoid-potensial-deadloop-fix
+++ a/mm/swapfile.c
@@ -3357,6 +3357,12 @@ SYSCALL_DEFINE2(swapon, const char __use
 		error = nr_extents;
 		goto bad_swap_unlock_inode;
 	}
+	if (si->pages != si->max - 1) {
+		pr_err("swap:%u != (max:%u - 1)\n", si->pages, si->max);
+		error = -EINVAL;
+		goto bad_swap_unlock_inode;
+	}
+
 	maxpages = si->max;
 
 	/* OK, set up the swap map and apply the bad block list */
_