[RFC PATCH v1.1] mm/damon/core: handle zero intervals in damon_max_nr_accesses()

[RFC PATCH v1.1] mm/damon/core: handle zero intervals in damon_max_nr_accesses()

[SeongJae Park]

damon_max_nr_accesses() causes a divide-by-zero if the sampling interval
is set to zero by the user.  If the aggregation interval is set to zero,
the function returns zero.  It is wrong, since the real maximum
nr_acceses in the setup should be one.  Worse yet, it can causes another
divide-by-zero from its caller, damon_hot_score(), since it uses
damon_max_nr_accesses() return value as a denominator.

Fix the problem by setting the denominator in the function as 1 when the
sampling interval is zero.  Also ensure the return value is always 1 or
greater.

The issue was dicovered [1] by Sashiko.

[1] https://lore.kernel.org/20260619202459.145010-1-sj@kernel.org

Fixes: 198f0f4c58b9 ("mm/damon/vaddr,paddr: support pageout prioritization")
Cc: <stable@vger.kernel.org> # 5.16.x
Signed-off-by: SeongJae Park <sj@kernel.org>
---
Changes from RFC v1
- rfc v1: https://lore.kernel.org/20260619205144.150664-1-sj@kernel.org
- Handle zero aggr_interval case.

 include/linux/damon.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 64d75c78f4df4..02ac34537df9a 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -1066,9 +1066,13 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx)
 
 static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs)
 {
-	/* {aggr,sample}_interval are unsigned long, hence could overflow */
-	return min(attrs->aggr_interval / attrs->sample_interval,
+	unsigned long sample_interval;
+	unsigned long max_nr_accesses;
+
+	sample_interval = attrs->sample_interval ? : 1;
+	max_nr_accesses = min(attrs->aggr_interval / sample_interval,
 			(unsigned long)UINT_MAX);
+	return max_nr_accesses ? : 1;
 }
 
 

base-commit: 7a58ae62cdf3c006a53b805bbb12079ab2621a07
-- 
2.47.3

Re: [RFC PATCH v1.1] mm/damon/core: handle zero intervals in damon_max_nr_accesses()

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] Pre-existing integer overflows when scaling `nr_accesses` based on user-defined intervals.
--

commit 2fc9b9ee26cec1a6b183b74636dd1922579cd4da
Author: SeongJae Park <sj@kernel.org>

mm/damon/core: handle zero intervals in damon_max_nr_accesses()

damon_max_nr_accesses() causes a divide-by-zero if the sampling interval
is set to zero by the user. If the aggregation interval is set to zero,
the function returns zero. It is wrong, since the real maximum
nr_acceses in the setup should be one.

Link: https://lore.kernel.org/20260619202459.145010-1-sj@kernel.org

> diff --git a/include/linux/damon.h b/include/linux/damon.h
> index 6f7edb3590ef9..888570f55b416 100644
> --- a/include/linux/damon.h
> +++ b/include/linux/damon.h
> @@ -1065,9 +1065,13 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx)
>  
>  static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs)
>  {
> -	/* {aggr,sample}_interval are unsigned long, hence could overflow */
> -	return min(attrs->aggr_interval / attrs->sample_interval,
> +	unsigned long sample_interval;
> +	unsigned long max_nr_accesses;
> +
> +	sample_interval = attrs->sample_interval ? : 1;
> +	max_nr_accesses = min(attrs->aggr_interval / sample_interval,
>  			(unsigned long)UINT_MAX);
> +	return max_nr_accesses ? : 1;
>  }

[Severity: High]
This is a pre-existing issue, but are there integer overflows when scaling
nr_accesses based on these user-defined intervals?

Since DAMON allows configuring sample_interval and aggr_interval via sysfs
without restricting their ratio, a region's nr_accesses (an unsigned int)
can grow up to aggr_interval / sample_interval.

If this ratio exceeds UINT_MAX, nr_accesses wraps around. More practically,
the codebase multiplies nr_accesses by 32-bit integer constants:

In mm/damon/core.c:damon_merge_two_regions():
    l->nr_accesses_bp = l->nr_accesses * 10000;

Can this overflow 32-bit unsigned math if the access count is greater than
429,496?

Similarly, in mm/damon/ops-common.c:damon_hot_score():
    freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / damon_max_nr_accesses(&c->attrs);

Does natively multiplying r->nr_accesses by 100 before dividing by the max
accesses cause a 32-bit integer overflow if the accesses exceed 42,949,672?

Additionally, on 32-bit platforms, can this calculation overflow unsigned
long?

In mm/damon/lru_sort.c:damon_lru_sort_apply_parameters():
    hot_thres = damon_max_nr_accesses(&attrs) * hot_thres_access_freq / 1000;

Multiplying damon_max_nr_accesses (up to UINT_MAX) by hot_thres_access_freq
natively overflows unsigned long on 32-bit architectures.

Could these overflows corrupt DAMON's core metrics, potentially causing
incorrect memory operations like aggressively swapping out hot pages under
the false impression that they are cold?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260620171413.89555-1-sj@kernel.org?part=1

Re: [RFC PATCH v1.1] mm/damon/core: handle zero intervals in damon_max_nr_accesses()

[SeongJae Park]

On Sat, 20 Jun 2026 17:25:02 +0000 sashiko-bot@kernel.org wrote:

> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> 
> Pre-existing issues:
> - [High] Pre-existing integer overflows when scaling `nr_accesses` based on user-defined intervals.
> --
> 
> commit 2fc9b9ee26cec1a6b183b74636dd1922579cd4da
> Author: SeongJae Park <sj@kernel.org>
> 
> mm/damon/core: handle zero intervals in damon_max_nr_accesses()
> 
> damon_max_nr_accesses() causes a divide-by-zero if the sampling interval
> is set to zero by the user. If the aggregation interval is set to zero,
> the function returns zero. It is wrong, since the real maximum
> nr_acceses in the setup should be one.
> 
> Link: https://lore.kernel.org/20260619202459.145010-1-sj@kernel.org
> 
> > diff --git a/include/linux/damon.h b/include/linux/damon.h
> > index 6f7edb3590ef9..888570f55b416 100644
> > --- a/include/linux/damon.h
> > +++ b/include/linux/damon.h
> > @@ -1065,9 +1065,13 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx)
> >  
> >  static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs)
> >  {
> > -	/* {aggr,sample}_interval are unsigned long, hence could overflow */
> > -	return min(attrs->aggr_interval / attrs->sample_interval,
> > +	unsigned long sample_interval;
> > +	unsigned long max_nr_accesses;
> > +
> > +	sample_interval = attrs->sample_interval ? : 1;
> > +	max_nr_accesses = min(attrs->aggr_interval / sample_interval,
> >  			(unsigned long)UINT_MAX);
> > +	return max_nr_accesses ? : 1;
> >  }
> 
> [Severity: High]
> This is a pre-existing issue, but are there integer overflows when scaling
> nr_accesses based on these user-defined intervals?
> 
> Since DAMON allows configuring sample_interval and aggr_interval via sysfs
> without restricting their ratio, a region's nr_accesses (an unsigned int)
> can grow up to aggr_interval / sample_interval.
> 
> If this ratio exceeds UINT_MAX, nr_accesses wraps around. More practically,
> the codebase multiplies nr_accesses by 32-bit integer constants:
> 
> In mm/damon/core.c:damon_merge_two_regions():
>     l->nr_accesses_bp = l->nr_accesses * 10000;
> 
> Can this overflow 32-bit unsigned math if the access count is greater than
> 429,496?
> 
> Similarly, in mm/damon/ops-common.c:damon_hot_score():
>     freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / damon_max_nr_accesses(&c->attrs);
> 
> Does natively multiplying r->nr_accesses by 100 before dividing by the max
> accesses cause a 32-bit integer overflow if the accesses exceed 42,949,672?
> 
> Additionally, on 32-bit platforms, can this calculation overflow unsigned
> long?
> 
> In mm/damon/lru_sort.c:damon_lru_sort_apply_parameters():
>     hot_thres = damon_max_nr_accesses(&attrs) * hot_thres_access_freq / 1000;
> 
> Multiplying damon_max_nr_accesses (up to UINT_MAX) by hot_thres_access_freq
> natively overflows unsigned long on 32-bit architectures.
> 
> Could these overflows corrupt DAMON's core metrics, potentially causing
> incorrect memory operations like aggressively swapping out hot pages under
> the false impression that they are cold?

We believe this happens only under very weird setup that is not realistic, and
hence ignoring this kind of issues for now.  We could revisit if a user claims
this as an issue.


Thanks,
SJ

[...]