All of lore.kernel.org
 help / color / mirror / Atom feed
* [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions()
@ 2026-06-27 17:00 SeongJae Park
  2026-06-27 17:19 ` sashiko-bot
  2026-06-27 17:26 ` SeongJae Park
  0 siblings, 2 replies; 4+ messages in thread
From: SeongJae Park @ 2026-06-27 17:00 UTC (permalink / raw)
  Cc: SeongJae Park, Andrew Morton, Yang Yingliang, damon, linux-kernel,
	linux-mm, stable

DAMON core logic assumes zero length regions don't exist.  However, a
few DAMON API callers including DAMON_SYSFS, DAMON_RECLAIM and
DAMON_LRU_SORT allow users to set empty monitoring target regions.  This
could result in WARN_ONCE() on CONFIG_DAMON_DEBUG_SANITY enabled kernel,
and divide-by-zero from damon_merge_two_regions().

For example, the WANR_ONCE() can be triggered like below.

    # grep DAMON_DEBUG_SANITY /boot/config-$(uname -r)
    # CONFIG_DAMON_DEBUG_SANITY=y
    # damo start
    # cd /sys/kernel/mm/damon/admin/kdamonds/0
    # echo 0 > contexts/0/targets/0/regions/0/start
    # echo 0 > contexts/0/targets/0/regions/0/end
    # echo commit > state
    # dmesg
    [....]
    [   73.705780] ------------[ cut here ]------------
    [   73.707552] start 0 >= end 0
    [   73.708452] WARNING: mm/damon/core.c:359 at damon_new_region+0x6e/0x80, CPU#1: kdamond.0/758
    [...]

Disallow empty region user inputs by updating the validation logic.

Fixes: 43b0536cb471 ("mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)")
Cc: <stable@vger.kernel.org> # 5.16.x
Signed-off-by: SeongJae Park <sj@kernel.org>
---
 mm/damon/core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 7e4b9affc5b06..b3100d7fa5596 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -358,6 +358,11 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
 	unsigned int i;
 	int err;
 
+	for (i = 0; i < nr_ranges; i++) {
+		if (ranges[i].start >= ranges[i].end)
+			return -EINVAL;
+	}
+
 	/* Remove regions which are not in the new ranges */
 	damon_for_each_region_safe(r, next, t) {
 		for (i = 0; i < nr_ranges; i++) {

base-commit: f5cde2d41633df3fb1965efa00bfa827ca41836c
-- 
2.47.3


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* Re: [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions()
  2026-06-27 17:00 [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions() SeongJae Park
@ 2026-06-27 17:19 ` sashiko-bot
  2026-06-27 17:24   ` SeongJae Park
  2026-06-27 17:26 ` SeongJae Park
  1 sibling, 1 reply; 4+ messages in thread
From: sashiko-bot @ 2026-06-27 17:19 UTC (permalink / raw)
  To: SeongJae Park; +Cc: damon

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:

Pre-existing issues:
- [High] The validation check to prevent empty regions is bypassed due to integer overflow in ALIGN(), leaving the divide-by-zero vulnerability unpatched.
- [High] Memory allocation failure during region updates leaves the running DAMON context with a corrupted, partially updated region list.
--

commit e67b2388e5d46f77944a06f1bd1d3d550638fade
Author: SeongJae Park <sj@kernel.org>

mm/damon/core: validate ranges in damon_set_regions()

This patch updates damon_set_regions() to validate ranges and reject
inputs where the start address is greater than or equal to the end
address. This aims to prevent zero-length regions which can cause
divide-by-zero errors in damon_merge_two_regions().

> diff --git a/mm/damon/core.c b/mm/damon/core.c
> index 7e4b9affc5b06..b3100d7fa5596 100644
> --- a/mm/damon/core.c
> +++ b/mm/damon/core.c
> @@ -358,6 +358,11 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
>  	unsigned int i;
>  	int err;
>  
> +	for (i = 0; i < nr_ranges; i++) {
> +		if (ranges[i].start >= ranges[i].end)
> +			return -EINVAL;
> +	}
> +

[Severity: High]
This isn't a bug introduced by this patch, but does this validation check 
sufficiently protect against overflow when the regions are aligned later?

If a user supplies a region where the end address is ULONG_MAX,
ALIGN(ULONG_MAX, min_region_sz) will wrap around to 0.

Since this validation check uses unaligned inputs, ULONG_MAX passes
the check here. Later, during allocation:

damon_set_regions() {
    ...
    r = damon_new_region(
            ALIGN_DOWN(ranges[i].start, min_region_sz),
            ALIGN(ranges[i].end, min_region_sz));
    ...
}

This creates a region with a wrapped and inverted size. If the adjacent
regions sum to a size of 0, for example 4096 + (ULONG_MAX - 4095),
can this lead to a divide-by-zero crash in damon_merge_two_regions()
when the sizes are added together?

damon_merge_two_regions() {
    ...
    l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
            (sz_l + sz_r);
    ...
}

[Severity: High]
This is also a pre-existing issue, but what happens to the region list if
memory allocation fails after existing regions are destroyed?

In damon_set_regions(), existing regions not in the new ranges are
destroyed. If a subsequent damon_new_region() fails and returns -ENOMEM:

damon_set_regions() {
    ...
    if (!r)
        return -ENOMEM;
    damon_add_region(r, t);
    ...
}

The error rollback path in damon_revert_target_commits() does not restore
the regions_list state:

damon_revert_target_commits() {
    ...
    damon_for_each_target(target, dst) {
        if (target == failed)
            return;
        put_pid(target->pid);
    }
}

Will this transient allocation failure permanently leave the running damon
context with a corrupted or partially updated region list, silencing
reclamation daemons?

>  	/* Remove regions which are not in the new ranges */
>  	damon_for_each_region_safe(r, next, t) {
[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260627170057.1867-1-sj@kernel.org?part=1

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions()
  2026-06-27 17:19 ` sashiko-bot
@ 2026-06-27 17:24   ` SeongJae Park
  0 siblings, 0 replies; 4+ messages in thread
From: SeongJae Park @ 2026-06-27 17:24 UTC (permalink / raw)
  To: sashiko-bot; +Cc: SeongJae Park, damon

On Sat, 27 Jun 2026 17:19:10 +0000 sashiko-bot@kernel.org wrote:

> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> 
> Pre-existing issues:
> - [High] The validation check to prevent empty regions is bypassed due to integer overflow in ALIGN(), leaving the divide-by-zero vulnerability unpatched.
> - [High] Memory allocation failure during region updates leaves the running DAMON context with a corrupted, partially updated region list.
> --
> 
> commit e67b2388e5d46f77944a06f1bd1d3d550638fade
> Author: SeongJae Park <sj@kernel.org>
> 
> mm/damon/core: validate ranges in damon_set_regions()
> 
> This patch updates damon_set_regions() to validate ranges and reject
> inputs where the start address is greater than or equal to the end
> address. This aims to prevent zero-length regions which can cause
> divide-by-zero errors in damon_merge_two_regions().
> 
> > diff --git a/mm/damon/core.c b/mm/damon/core.c
> > index 7e4b9affc5b06..b3100d7fa5596 100644
> > --- a/mm/damon/core.c
> > +++ b/mm/damon/core.c
> > @@ -358,6 +358,11 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
> >  	unsigned int i;
> >  	int err;
> >  
> > +	for (i = 0; i < nr_ranges; i++) {
> > +		if (ranges[i].start >= ranges[i].end)
> > +			return -EINVAL;
> > +	}
> > +
> 
> [Severity: High]
> This isn't a bug introduced by this patch, but does this validation check 
> sufficiently protect against overflow when the regions are aligned later?
> 
> If a user supplies a region where the end address is ULONG_MAX,
> ALIGN(ULONG_MAX, min_region_sz) will wrap around to 0.
> 
> Since this validation check uses unaligned inputs, ULONG_MAX passes
> the check here. Later, during allocation:
> 
> damon_set_regions() {
>     ...
>     r = damon_new_region(
>             ALIGN_DOWN(ranges[i].start, min_region_sz),
>             ALIGN(ranges[i].end, min_region_sz));
>     ...
> }
> 
> This creates a region with a wrapped and inverted size. If the adjacent
> regions sum to a size of 0, for example 4096 + (ULONG_MAX - 4095),
> can this lead to a divide-by-zero crash in damon_merge_two_regions()
> when the sizes are added together?
> 
> damon_merge_two_regions() {
>     ...
>     l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
>             (sz_l + sz_r);
>     ...
> }

Nice catch.  The next revision will do the validation with the aligned
addresses.

> 
> [Severity: High]
> This is also a pre-existing issue, but what happens to the region list if
> memory allocation fails after existing regions are destroyed?
> 
> In damon_set_regions(), existing regions not in the new ranges are
> destroyed. If a subsequent damon_new_region() fails and returns -ENOMEM:
> 
> damon_set_regions() {
>     ...
>     if (!r)
>         return -ENOMEM;
>     damon_add_region(r, t);
>     ...
> }
> 
> The error rollback path in damon_revert_target_commits() does not restore
> the regions_list state:
> 
> damon_revert_target_commits() {
>     ...
>     damon_for_each_target(target, dst) {
>         if (target == failed)
>             return;
>         put_pid(target->pid);
>     }
> }
> 
> Will this transient allocation failure permanently leave the running damon
> context with a corrupted or partially updated region list, silencing
> reclamation daemons?

No issue.  The caller should destroy the context in the case.


Thanks,
SJ

[...]

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions()
  2026-06-27 17:00 [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions() SeongJae Park
  2026-06-27 17:19 ` sashiko-bot
@ 2026-06-27 17:26 ` SeongJae Park
  1 sibling, 0 replies; 4+ messages in thread
From: SeongJae Park @ 2026-06-27 17:26 UTC (permalink / raw)
  To: SeongJae Park
  Cc: Andrew Morton, Yang Yingliang, damon, linux-kernel, linux-mm,
	stable

On Sat, 27 Jun 2026 10:00:56 -0700 SeongJae Park <sj@kernel.org> wrote:

> DAMON core logic assumes zero length regions don't exist.  However, a
> few DAMON API callers including DAMON_SYSFS, DAMON_RECLAIM and
> DAMON_LRU_SORT allow users to set empty monitoring target regions.  This
> could result in WARN_ONCE() on CONFIG_DAMON_DEBUG_SANITY enabled kernel,
> and divide-by-zero from damon_merge_two_regions().
> 
> For example, the WANR_ONCE() can be triggered like below.
> 
>     # grep DAMON_DEBUG_SANITY /boot/config-$(uname -r)
>     # CONFIG_DAMON_DEBUG_SANITY=y
>     # damo start
>     # cd /sys/kernel/mm/damon/admin/kdamonds/0
>     # echo 0 > contexts/0/targets/0/regions/0/start
>     # echo 0 > contexts/0/targets/0/regions/0/end
>     # echo commit > state
>     # dmesg
>     [....]
>     [   73.705780] ------------[ cut here ]------------
>     [   73.707552] start 0 >= end 0
>     [   73.708452] WARNING: mm/damon/core.c:359 at damon_new_region+0x6e/0x80, CPU#1: kdamond.0/758
>     [...]
> 
> Disallow empty region user inputs by updating the validation logic.

The above description is wrong, since this is not updating an existing
validation but adding a new validation.

> 
> Fixes: 43b0536cb471 ("mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)")
> Cc: <stable@vger.kernel.org> # 5.16.x
> Signed-off-by: SeongJae Park <sj@kernel.org>
> ---
>  mm/damon/core.c | 5 +++++
>  1 file changed, 5 insertions(+)
> 
> diff --git a/mm/damon/core.c b/mm/damon/core.c
> index 7e4b9affc5b06..b3100d7fa5596 100644
> --- a/mm/damon/core.c
> +++ b/mm/damon/core.c
> @@ -358,6 +358,11 @@ int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
>  	unsigned int i;
>  	int err;
>  
> +	for (i = 0; i < nr_ranges; i++) {
> +		if (ranges[i].start >= ranges[i].end)
> +			return -EINVAL;
> +	}
> +

Sashiko found [1] this is not complete, since eventually this function uses
aligned addresses.  I will address that in the next revision by doing the
validation with the aligned addresses.

[1] https://lore.kernel.org/20260627172406.3794-1-sj@kernel.org


Thanks,
SJ

[...]

^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2026-06-27 17:26 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-27 17:00 [RFC PATCH] mm/damon/core: validate ranges in damon_set_regions() SeongJae Park
2026-06-27 17:19 ` sashiko-bot
2026-06-27 17:24   ` SeongJae Park
2026-06-27 17:26 ` SeongJae Park

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.