[RFC PATCH v1.2 0/2] mm/damon/stat: add kdamond_pid parameter

[RFC PATCH v1.2 0/2] mm/damon/stat: add kdamond_pid parameter

[SeongJae Park]

DAMON_STAT doesn't provide the pid of its kdamond, unlike DAMON_RECLAIM
and DAMON_LRU_SORT.  This makes user-space management of DAMON_STAT
unnecessarily complicated.  Provide the information via a new parameter,
namely kdamond_pid, and document it.

Changes from RFC v1.1
- rfc v1.1: https://lore.kernel.org/20260414235912.98174-1-sj@kernel.org
- Close the parentheses of error handling block.
Changes from RFC
- rfc: https://lore.kernel.org/20260414053742.90296-1-sj@kernel.org
- Fix damon_kdamond_pid() failure handling.

SeongJae Park (2):
  mm/damon/stat: add a parameter for reading kdamond pid
  Docs/admin-guide/mm/damon/stat: document kdamond_pid parameter

 Documentation/admin-guide/mm/damon/stat.rst |  7 +++++++
 mm/damon/stat.c                             | 18 ++++++++++++++++++
 2 files changed, 25 insertions(+)


base-commit: bf44f59d29186d80db01e4124a8ab23b3b235b32
-- 
2.47.3

[RFC PATCH v1.2 1/2] mm/damon/stat: add a parameter for reading kdamond pid

[SeongJae Park]

Knowing the pid of the kdamonds can help user-space management including
monitoring of DAMON's system resource consumption.  To make it easier,
DAMON_SYSFS, DAMON_RECLAIM and DAMON_LRU_SORT provide the pid
information.  DAMON_STAT is not providing it, though.  Expose the pid of
DAMON_STAT kdamond via a new read-only module parameter, namely
kdamond_pid.  This also makes DAMON modules usage more standardized,
because DAMON_RECLAIM and DAMON_LRU_SORT also provide the information
via their read-only parameters of the same name.

Signed-off-by: SeongJae Park <sj@kernel.org>
---
 mm/damon/stat.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/mm/damon/stat.c b/mm/damon/stat.c
index 99ba346f9e325..4901e9a7c3398 100644
--- a/mm/damon/stat.c
+++ b/mm/damon/stat.c
@@ -44,6 +44,15 @@ module_param(aggr_interval_us, ulong, 0400);
 MODULE_PARM_DESC(aggr_interval_us,
 		"Current tuned aggregation interval in microseconds");
 
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_STAT is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+static int kdamond_pid __read_mostly = -1;
+module_param(kdamond_pid, int, 0400);
+
 static struct damon_ctx *damon_stat_context;
 
 static unsigned long damon_stat_last_refresh_jiffies;
@@ -260,6 +269,14 @@ static int damon_stat_start(void)
 		damon_stat_context = NULL;
 		return err;
 	}
+	kdamond_pid = damon_kdamond_pid(damon_stat_context);
+	if (kdamond_pid < 0) {
+		err = kdamond_pid;
+		kdamond_pid = -1;
+		damon_destroy_ctx(damon_stat_context);
+		damon_stat_context = NULL;
+		return err;
+	}
 
 	damon_stat_last_refresh_jiffies = jiffies;
 	call_control.data = damon_stat_context;
@@ -269,6 +286,7 @@ static int damon_stat_start(void)
 static void damon_stat_stop(void)
 {
 	damon_stop(&damon_stat_context, 1);
+	kdamond_pid = -1;
 	damon_destroy_ctx(damon_stat_context);
 	damon_stat_context = NULL;
 }
-- 
2.47.3

Re: [RFC PATCH v1.2 1/2] mm/damon/stat: add a parameter for reading kdamond pid

[sashiko-bot]

Sashiko AI review found 1 potential issue(s):
- [Medium] Stale `kdamond_pid` exposed to userspace if `damon_call()` fails during startup.
--

commit 46eb0a4278ccd2dec190db28b78b0766b8865901
Author: SeongJae Park <sj@kernel.org>

mm/damon/stat: add a parameter for reading kdamond pid

This commit exposes the pid of the DAMON_STAT kdamond via a new read-only
module parameter named kdamond_pid, standardizing usage with other DAMON
modules.

> diff --git a/mm/damon/stat.c b/mm/damon/stat.c
> index 99ba346f9e325..4901e9a7c3398 100644
> --- a/mm/damon/stat.c
> +++ b/mm/damon/stat.c

[ ... ]

> @@ -260,6 +269,14 @@ static int damon_stat_start(void)
>  		damon_stat_context = NULL;
>  		return err;
>  	}
> +	kdamond_pid = damon_kdamond_pid(damon_stat_context);
> +	if (kdamond_pid < 0) {
> +		err = kdamond_pid;
> +		kdamond_pid = -1;
> +		damon_destroy_ctx(damon_stat_context);
> +		damon_stat_context = NULL;
> +		return err;
> +	}
>  
>  	damon_stat_last_refresh_jiffies = jiffies;
>  	call_control.data = damon_stat_context;

If damon_call() fails right after this and returns an error,
damon_stat_start() will pass that error back to its caller and the module
will revert to a disabled state.

Does this leave a stale kdamond_pid exposed to userspace? The newly added
documentation states: "If DAMON_STAT is enabled, this becomes the PID of
the worker thread. Else, -1." Since the initialization fails, the module
remains disabled, but kdamond_pid isn't reset to -1 on this error path.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260416002149.87090-1-sj@kernel.org?part=1

Re: [RFC PATCH v1.2 1/2] mm/damon/stat: add a parameter for reading kdamond pid

[SeongJae Park]

TL; DR: Sashiko found good point.  I will fix it in the next revision.

On Thu, 16 Apr 2026 00:59:35 +0000 sashiko-bot@kernel.org wrote:

> Sashiko AI review found 1 potential issue(s):
> - [Medium] Stale `kdamond_pid` exposed to userspace if `damon_call()` fails during startup.
> --
> 
> commit 46eb0a4278ccd2dec190db28b78b0766b8865901
> Author: SeongJae Park <sj@kernel.org>
> 
> mm/damon/stat: add a parameter for reading kdamond pid
> 
> This commit exposes the pid of the DAMON_STAT kdamond via a new read-only
> module parameter named kdamond_pid, standardizing usage with other DAMON
> modules.
> 
> > diff --git a/mm/damon/stat.c b/mm/damon/stat.c
> > index 99ba346f9e325..4901e9a7c3398 100644
> > --- a/mm/damon/stat.c
> > +++ b/mm/damon/stat.c
> 
> [ ... ]
> 
> > @@ -260,6 +269,14 @@ static int damon_stat_start(void)
> >  		damon_stat_context = NULL;
> >  		return err;
> >  	}
> > +	kdamond_pid = damon_kdamond_pid(damon_stat_context);
> > +	if (kdamond_pid < 0) {
> > +		err = kdamond_pid;
> > +		kdamond_pid = -1;
> > +		damon_destroy_ctx(damon_stat_context);
> > +		damon_stat_context = NULL;
> > +		return err;
> > +	}
> >  
> >  	damon_stat_last_refresh_jiffies = jiffies;
> >  	call_control.data = damon_stat_context;
> 
> If damon_call() fails right after this and returns an error,
> damon_stat_start() will pass that error back to its caller and the module
> will revert to a disabled state.
> 
> Does this leave a stale kdamond_pid exposed to userspace? The newly added
> documentation states: "If DAMON_STAT is enabled, this becomes the PID of
> the worker thread. Else, -1." Since the initialization fails, the module
> remains disabled, but kdamond_pid isn't reset to -1 on this error path.

Nice catch.  I will do the kdamond_pid setup after damon_call() success, like
below.  Also, I will remove the damon_stat_context deallocation and unset when
damon_kdamond_pid() failure, because it will be deallocated when
damon_stat_start() is called again.  The change will look like below:

--- a/mm/damon/stat.c
+++ b/mm/damon/stat.c
@@ -222,18 +222,19 @@ static int damon_stat_start(void)
                damon_stat_context = NULL;
                return err;
        }
+
+       damon_stat_last_refresh_jiffies = jiffies;
+       call_control.data = damon_stat_context;
+       err = damon_call(damon_stat_context, &call_control);
+       if (err)
+               return err;
+
        kdamond_pid = damon_kdamond_pid(damon_stat_context);
        if (kdamond_pid < 0) {
                err = kdamond_pid;
                kdamond_pid = -1;
-               damon_destroy_ctx(damon_stat_context);
-               damon_stat_context = NULL;
                return err;
        }
-
-       damon_stat_last_refresh_jiffies = jiffies;
-       call_control.data = damon_stat_context;
-       return damon_call(damon_stat_context, &call_control);
 }

 static void damon_stat_stop(void)

> 
> -- 
> Sashiko AI review · https://sashiko.dev/#/patchset/20260416002149.87090-1-sj@kernel.org?part=1


Thanks,
SJ

Re: [RFC PATCH v1.2 1/2] mm/damon/stat: add a parameter for reading kdamond pid

[SeongJae Park]

On Wed, 15 Apr 2026 20:35:45 -0700 SeongJae Park <sj@kernel.org> wrote:

> TL; DR: Sashiko found good point.  I will fix it in the next revision.
> 
> On Thu, 16 Apr 2026 00:59:35 +0000 sashiko-bot@kernel.org wrote:
> 
> > Sashiko AI review found 1 potential issue(s):
> > - [Medium] Stale `kdamond_pid` exposed to userspace if `damon_call()` fails during startup.
> > --
> > 
> > commit 46eb0a4278ccd2dec190db28b78b0766b8865901
> > Author: SeongJae Park <sj@kernel.org>
> > 
> > mm/damon/stat: add a parameter for reading kdamond pid
> > 
> > This commit exposes the pid of the DAMON_STAT kdamond via a new read-only
> > module parameter named kdamond_pid, standardizing usage with other DAMON
> > modules.
> > 
> > > diff --git a/mm/damon/stat.c b/mm/damon/stat.c
> > > index 99ba346f9e325..4901e9a7c3398 100644
> > > --- a/mm/damon/stat.c
> > > +++ b/mm/damon/stat.c
> > 
> > [ ... ]
> > 
> > > @@ -260,6 +269,14 @@ static int damon_stat_start(void)
> > >  		damon_stat_context = NULL;
> > >  		return err;
> > >  	}
> > > +	kdamond_pid = damon_kdamond_pid(damon_stat_context);
> > > +	if (kdamond_pid < 0) {
> > > +		err = kdamond_pid;
> > > +		kdamond_pid = -1;
> > > +		damon_destroy_ctx(damon_stat_context);
> > > +		damon_stat_context = NULL;
> > > +		return err;
> > > +	}
> > >  
> > >  	damon_stat_last_refresh_jiffies = jiffies;
> > >  	call_control.data = damon_stat_context;
> > 
> > If damon_call() fails right after this and returns an error,
> > damon_stat_start() will pass that error back to its caller and the module
> > will revert to a disabled state.
> > 
> > Does this leave a stale kdamond_pid exposed to userspace? The newly added
> > documentation states: "If DAMON_STAT is enabled, this becomes the PID of
> > the worker thread. Else, -1." Since the initialization fails, the module
> > remains disabled, but kdamond_pid isn't reset to -1 on this error path.
> 
> Nice catch.  I will do the kdamond_pid setup after damon_call() success, like
> below.

Wait...  The same question was also raised [1] by Sashiko on the previous
version.  And I was wrongly saying it is not this patch's fault.  That was
completely wrong.

And the kdamond can stop even after the damon_kdamond_pid() call, if the
region_store_histogram allocation fails.  In the case, kdamond_pid will again
be stale.  'enabled' parameter value will also be stale in the case.  The worst
part of it is that in the case, DAMON_STAT cannot be restarted before the
system is reboot.  The bug is similar to the one [2] that Liew found and
working on.

I will hold this patch and fix the bug first.

> Also, I will remove the damon_stat_context deallocation and unset when
> damon_kdamond_pid() failure, because it will be deallocated when
> damon_stat_start() is called again.

This also means my reply [1] to Sashiko's question about the damon_stat_context
leak on the previous version was wrong.  I was saying it is indeed a bug, but
it was not.

[1] https://lore.kernel.org/20260414053742.90296-1-sj@kernel.org
[2] https://lore.kernel.org/20260415235529.86329-1-sj@kernel.org


Thanks,
SJ

[...]

Re: [RFC PATCH v1.2 1/2] mm/damon/stat: add a parameter for reading kdamond pid

[SeongJae Park]

On Wed, 15 Apr 2026 21:06:01 -0700 SeongJae Park <sj@kernel.org> wrote:

> On Wed, 15 Apr 2026 20:35:45 -0700 SeongJae Park <sj@kernel.org> wrote:
> 
> > TL; DR: Sashiko found good point.  I will fix it in the next revision.
> > 
> > On Thu, 16 Apr 2026 00:59:35 +0000 sashiko-bot@kernel.org wrote:
> > 
> > > Sashiko AI review found 1 potential issue(s):
> > > - [Medium] Stale `kdamond_pid` exposed to userspace if `damon_call()` fails during startup.
> > > --
> > > 
> > > commit 46eb0a4278ccd2dec190db28b78b0766b8865901
> > > Author: SeongJae Park <sj@kernel.org>
> > > 
> > > mm/damon/stat: add a parameter for reading kdamond pid
> > > 
> > > This commit exposes the pid of the DAMON_STAT kdamond via a new read-only
> > > module parameter named kdamond_pid, standardizing usage with other DAMON
> > > modules.
> > > 
> > > > diff --git a/mm/damon/stat.c b/mm/damon/stat.c
> > > > index 99ba346f9e325..4901e9a7c3398 100644
> > > > --- a/mm/damon/stat.c
> > > > +++ b/mm/damon/stat.c
> > > 
> > > [ ... ]
> > > 
> > > > @@ -260,6 +269,14 @@ static int damon_stat_start(void)
> > > >  		damon_stat_context = NULL;
> > > >  		return err;
> > > >  	}
> > > > +	kdamond_pid = damon_kdamond_pid(damon_stat_context);
> > > > +	if (kdamond_pid < 0) {
> > > > +		err = kdamond_pid;
> > > > +		kdamond_pid = -1;
> > > > +		damon_destroy_ctx(damon_stat_context);
> > > > +		damon_stat_context = NULL;
> > > > +		return err;
> > > > +	}
> > > >  
> > > >  	damon_stat_last_refresh_jiffies = jiffies;
> > > >  	call_control.data = damon_stat_context;
> > > 
> > > If damon_call() fails right after this and returns an error,
> > > damon_stat_start() will pass that error back to its caller and the module
> > > will revert to a disabled state.
> > > 
> > > Does this leave a stale kdamond_pid exposed to userspace? The newly added
> > > documentation states: "If DAMON_STAT is enabled, this becomes the PID of
> > > the worker thread. Else, -1." Since the initialization fails, the module
> > > remains disabled, but kdamond_pid isn't reset to -1 on this error path.
> > 
> > Nice catch.  I will do the kdamond_pid setup after damon_call() success, like
> > below.
> 
> Wait...  The same question was also raised [1] by Sashiko on the previous
> version.  And I was wrongly saying it is not this patch's fault.  That was
> completely wrong.
> 
> And the kdamond can stop even after the damon_kdamond_pid() call, if the
> region_store_histogram allocation fails.  In the case, kdamond_pid will again
> be stale.  'enabled' parameter value will also be stale in the case.  The worst
> part of it is that in the case, DAMON_STAT cannot be restarted before the
> system is reboot.  The bug is similar to the one [2] that Liew found and
> working on.

The last two sentences are wrong...  In case of damon_stat(), writing 'N' to
'enabled' will just update the parameter even if damon_stop() fails.  Hence,
users can restart DAMON_STAT after 'enabled' value became stale, by writing 'N'
to 'enabled' parameter to reset the value, and then writing 'Y' to 'enabled'
parameter again, to invoke damon_start() call.  Still far from good user
experience, but less critical than the bug that Liew is working on.

> 
> I will hold this patch and fix the bug first.

My above opinion is same.  I will fix the bugs first.


Thanks,
SJ

[...]

[RFC PATCH v1.2 2/2] Docs/admin-guide/mm/damon/stat: document kdamond_pid parameter

[SeongJae Park]

Update DAMON_STAT usage document for newly added kdamond_pid parameter.

Signed-off-by: SeongJae Park <sj@kernel.org>
---
 Documentation/admin-guide/mm/damon/stat.rst | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/Documentation/admin-guide/mm/damon/stat.rst b/Documentation/admin-guide/mm/damon/stat.rst
index c4b14daeb2dd6..46c5dd96aa2ed 100644
--- a/Documentation/admin-guide/mm/damon/stat.rst
+++ b/Documentation/admin-guide/mm/damon/stat.rst
@@ -89,3 +89,10 @@ percentiles of the idle time values via this read-only parameter.  Reading the
 parameter returns 101 idle time values in milliseconds, separated by comma.
 Each value represents 0-th, 1st, 2nd, 3rd, ..., 99th and 100th percentile idle
 times.
+
+kdamond_pid
+-----------
+
+PID of the DAMON thread.
+
+If DAMON_STAT is enabled, this becomes the PID of the worker thread.  Else, -1.
-- 
2.47.3