FAILED: patch "[PATCH] mm/damon/lru_sort: detect and use fresh enabled and" failed to apply to 6.1-stable tree

The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

To reproduce the conflict and resubmit, you may use the following commands:

git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y
git checkout FETCH_HEAD
git cherry-pick -x b98b7ff6025ae82570d4915e083f0cbd8d48b3cf
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026051243-crevice-spool-75d8@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^..

Possible dependencies:

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From b98b7ff6025ae82570d4915e083f0cbd8d48b3cf Mon Sep 17 00:00:00 2001
From: SeongJae Park <[email protected]>
Date: Sun, 19 Apr 2026 09:10:01 -0700
Subject: [PATCH] mm/damon/lru_sort: detect and use fresh enabled and
kdamond_pid values

DAMON_LRU_SORT updates 'enabled' and 'kdamond_pid' parameter values, which represents the running status of its kdamond, when the user explicitly requests start/stop of the kdamond. The kdamond can, however, be stopped in events other than the explicit user request in the following three events.

1. ctx->regions_score_histogram allocation failure at beginning of the execution,
2. damon_commit_ctx() failure due to invalid user input, and
3. damon_commit_ctx() failure due to its internal allocation failures.

Hence, if the kdamond is stopped by the above three events, the values of the status parameters can be stale. Users could show the stale values and be confused. This is already bad, but the real consequence is worse. DAMON_LRU_SORT avoids unnecessary damon_start() and damon_stop() calls based on the 'enabled' parameter value. And the update of 'enabled' parameter value depends on the damon_start() and damon_stop() call results. Hence, once the kdamond has stopped by the unintentional events, the user cannot restart the kdamond before the system reboot. For example, the issue can be reproduced via below steps.

    # cd /sys/module/damon_lru_sort/parameters
    #
    # # start DAMON_LRU_SORT
    # echo Y > enabled
    # ps -ef | grep kdamond
    root         806       2  0 17:53 ?        00:00:00 [kdamond.0]
    root         808     803  0 17:53 pts/4    00:00:00 grep kdamond
    #
    # # commit wrong input to stop kdamond withou explicit stop request
    # echo 3 > addr_unit
    # echo Y > commit_inputs
    bash: echo: write error: Invalid argument
    #
    # # confirm kdamond is stopped
    # ps -ef | grep kdamond
    root         811     803  0 17:53 pts/4    00:00:00 grep kdamond
    #
    # # users casn now show stable status
    # cat enabled
    Y
    # cat kdamond_pid
    806
    #
    # # even after fixing the wrong parameter,
    # # kdamond cannot be restarted.
    # echo 1 > addr_unit
    # echo Y > enabled
    # ps -ef | grep kdamond
    root         815     803  0 17:54 pts/4    00:00:00 grep kdamond

The problem will only rarely happen in real and common setups for the following reasons. The allocation failures are unlikely in such setups since those allocations are arguably too small to fail. Also sane users on real production environments may not commit wrong input parameters. But once it happens, the consequence is quite bad. And the bug is a bug.

The issue stems from the fact that there are multiple events that can change the status, and following all the events is challenging. Dynamically detect and use the fresh status for the parameters when those are requested.

index 554559d72976..8494040b1ee4 100644
@@ -161,15 +161,6 @@ module_param(monitor_region_end, ulong, 0600);
  */
 static unsigned long addr_unit __read_mostly = 1;
 
-/*
- * PID of the DAMON thread
- *
- * If DAMON_LRU_SORT 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 damos_stat damon_lru_sort_hot_stat;
 DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_hot_stat,
 		lru_sort_tried_hot_regions, lru_sorted_hot_regions,

@@ -386,12 +377,8 @@ static int damon_lru_sort_turn(bool on)
 {
 	int err;
 
-	if (!on) {
-		err = damon_stop(&ctx, 1);
-		if (!err)
-			kdamond_pid = -1;
-		return err;
-	}
+	if (!on)
+		return damon_stop(&ctx, 1);
 
 	err = damon_lru_sort_apply_parameters();
 	if (err)

@@ -400,9 +387,6 @@ static int damon_lru_sort_turn(bool on)
 	err = damon_start(&ctx, 1, true);
 	if (err)
 		return err;
-	kdamond_pid = damon_kdamond_pid(ctx);
-	if (kdamond_pid < 0)
-		return kdamond_pid;
 	return damon_call(ctx, &call_control);
 }
 

@@ -430,42 +414,83 @@ module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600);
 MODULE_PARM_DESC(addr_unit,
 	"Scale factor for DAMON_LRU_SORT to ops address conversion (default: 1)");
 
+static bool damon_lru_sort_enabled(void)
+{
+	if (!ctx)
+		return false;
+	return damon_is_running(ctx);
+}
+
 static int damon_lru_sort_enabled_store(const char *val,
 		const struct kernel_param *kp)
 {
-	bool is_enabled = enabled;
-	bool enable;
 	int err;
 
-	err = kstrtobool(val, &enable);
+	err = kstrtobool(val, &enabled);
 	if (err)
 		return err;
 
-	if (is_enabled == enable)
+	if (damon_lru_sort_enabled() == enabled)
 		return 0;
 
 	/* Called before init function.  The function will handle this. */
 	if (!damon_initialized())
-		goto set_param_out;
+		return 0;
 
-	err = damon_lru_sort_turn(enable);
-	if (err)
-		return err;
+	return damon_lru_sort_turn(enabled);
+}
 
-set_param_out:
-	enabled = enable;
-	return err;
+static int damon_lru_sort_enabled_load(char *buffer,
+		const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%c\n", damon_lru_sort_enabled() ? 'Y' : 'N');
 }
 
 static const struct kernel_param_ops enabled_param_ops = {
 	.set = damon_lru_sort_enabled_store,
-	.get = param_get_bool,
+	.get = damon_lru_sort_enabled_load,
 };
 
 module_param_cb(enabled, &enabled_param_ops, &enabled, 0600);
 MODULE_PARM_DESC(enabled,
 	"Enable or disable DAMON_LRU_SORT (default: disabled)");
 
+static int damon_lru_sort_kdamond_pid_store(const char *val,
+		const struct kernel_param *kp)
+{
+	/*
+	 * kdamond_pid is read-only, but kernel command line could write it.
+	 * Do nothing here.
+	 */
+	return 0;
+}
+
+static int damon_lru_sort_kdamond_pid_load(char *buffer,
+		const struct kernel_param *kp)
+{
+	int kdamond_pid = -1;
+
+	if (ctx) {
+		kdamond_pid = damon_kdamond_pid(ctx);
+		if (kdamond_pid < 0)
+			kdamond_pid = -1;
+	}
+	return sprintf(buffer, "%d\n", kdamond_pid);
+}
+
+static const struct kernel_param_ops kdamond_pid_param_ops = {
+	.set = damon_lru_sort_kdamond_pid_store,
+	.get = damon_lru_sort_kdamond_pid_load,
+};
+
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400);
+
 static int __init damon_lru_sort_init(void)
 {
 	int err;

Patch series "mm/damon: hide kdamond and kdamond_lock from API callers".

'kdamond' and 'kdamond_lock' fields initially exposed to DAMON API callers for flexible synchronization and use cases. As DAMON API became somewhat complicated compared to the early days, Keeping those exposed could only encourage the API callers to invent more creative but complicated and difficult-to-debug use cases.

Fortunately DAMON API callers didn't invent that many creative use cases. There exist only two use cases of 'kdamond' and 'kdamond_lock'. Finding whether the kdamond is actively running, and getting the pid of the kdamond. For the first use case, a dedicated API function, namely 'damon_is_running()' is provided, and all DAMON API callers are using the function for the use case. Hence only the second use case is where the fields are directly being used by DAMON API callers.

To prevent future invention of complicated and erroneous use cases of the fields, hide the fields from the API callers. For that, provide new dedicated DAMON API functions for the remaining use case, namely damon_kdamond_pid(), migrate DAMON API callers to use the new function, and mark the fields as private fields.

This patch (of 5):

'kdamond' and 'kdamond_lock' are directly being used by DAMON API callers for getting the pid of the corresponding kdamond. To discourage invention of creative but complicated and erroneous new usages of the fields that require careful synchronization, implement a new API function that can simply be used without the manual synchronizations.

---
The second patch depends on this commit, so porting this together.

 include/linux/damon.h |  1 +
 mm/damon/core.c       | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

index e6941b239f449..7eeec0eaaf1f5 100644
@@ -572,6 +572,7 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs
 
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+int damon_kdamond_pid(struct damon_ctx *ctx);
 
 int damon_set_region_biggest_system_ram_default(struct damon_target *t,
 				unsigned long *start, unsigned long *end);

index ab5c351b276ce..fc68364c9ad2e 100644
@@ -643,6 +643,23 @@ static bool damon_check_reset_time_interval(struct timespec64 *baseline,
 	return true;
 }
 
+/**
+ * damon_kdamond_pid() - Return pid of a given DAMON context's worker thread.
+ * @ctx:	The DAMON context of the question.
+ *
+ * Return: pid if @ctx is running, negative error code otherwise.
+ */
+int damon_kdamond_pid(struct damon_ctx *ctx)
+{
+	int pid = -EINVAL;
+
+	mutex_lock(&ctx->kdamond_lock);
+	if (ctx->kdamond)
+		pid = ctx->kdamond->pid;
+	mutex_unlock(&ctx->kdamond_lock);
+	return pid;
+}
+
 /*
  * Check whether it is time to flush the aggregated information
  */

2.47.3

Sashiko is correct, this description is inaccurate. But that's intentional for stable kernel backports.

Thanks,
SJ

DAMON_LRU_SORT updates 'enabled' and 'kdamond_pid' parameter values, which represents the running status of its kdamond, when the user explicitly requests start/stop of the kdamond. The kdamond can, however, be stopped in events other than the explicit user request in the following three events.

1. ctx->regions_score_histogram allocation failure at beginning of the execution,
2. damon_commit_ctx() failure due to invalid user input, and
3. damon_commit_ctx() failure due to its internal allocation failures.

Hence, if the kdamond is stopped by the above three events, the values of the status parameters can be stale. Users could show the stale values and be confused. This is already bad, but the real consequence is worse. DAMON_LRU_SORT avoids unnecessary damon_start() and damon_stop() calls based on the 'enabled' parameter value. And the update of 'enabled' parameter value depends on the damon_start() and damon_stop() call results. Hence, once the kdamond has stopped by the unintentional events, the user cannot restart the kdamond before the system reboot. For example, the issue can be reproduced via below steps.

    # cd /sys/module/damon_lru_sort/parameters
    #
    # # start DAMON_LRU_SORT
    # echo Y > enabled
    # ps -ef | grep kdamond
    root         806       2  0 17:53 ?        00:00:00 [kdamond.0]
    root         808     803  0 17:53 pts/4    00:00:00 grep kdamond
    #
    # # commit wrong input to stop kdamond withou explicit stop request
    # echo 3 > addr_unit
    # echo Y > commit_inputs
    bash: echo: write error: Invalid argument
    #
    # # confirm kdamond is stopped
    # ps -ef | grep kdamond
    root         811     803  0 17:53 pts/4    00:00:00 grep kdamond
    #
    # # users casn now show stable status
    # cat enabled
    Y
    # cat kdamond_pid
    806
    #
    # # even after fixing the wrong parameter,
    # # kdamond cannot be restarted.
    # echo 1 > addr_unit
    # echo Y > enabled
    # ps -ef | grep kdamond
    root         815     803  0 17:54 pts/4    00:00:00 grep kdamond

The problem will only rarely happen in real and common setups for the following reasons. The allocation failures are unlikely in such setups since those allocations are arguably too small to fail. Also sane users on real production environments may not commit wrong input parameters. But once it happens, the consequence is quite bad. And the bug is a bug.

The issue stems from the fact that there are multiple events that can change the status, and following all the events is challenging. Dynamically detect and use the fresh status for the parameters when those are requested.

(port parts of 42b7491af14c ("mm/damon/core: introduce damon_call()") and d2b5be741a50 ("mm/damon/sysfs: use DAMON core API damon_is_running()") for damon_is_running() dependency)

---
 include/linux/damon.h |  1 +
 mm/damon/core.c       | 16 ++++++++++
 mm/damon/lru_sort.c   | 74 +++++++++++++++++++++++++++++++------------
 3 files changed, 70 insertions(+), 21 deletions(-)

index 7eeec0eaaf1f5..7133131433547 100644
@@ -572,6 +572,7 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs
 
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+bool damon_is_running(struct damon_ctx *ctx);
 int damon_kdamond_pid(struct damon_ctx *ctx);
 
 int damon_set_region_biggest_system_ram_default(struct damon_target *t,

index fc68364c9ad2e..1c041d011b8ef 100644
@@ -643,6 +643,22 @@ static bool damon_check_reset_time_interval(struct timespec64 *baseline,
 	return true;
 }
 
+/**
+ * damon_is_running() - Returns if a given DAMON context is running.
+ * @ctx:	The DAMON context to see if running.
+ *
+ * Return: true if @ctx is running, false otherwise.
+ */
+bool damon_is_running(struct damon_ctx *ctx)
+{
+	bool running;
+
+	mutex_lock(&ctx->kdamond_lock);
+	running = ctx->kdamond != NULL;
+	mutex_unlock(&ctx->kdamond_lock);
+	return running;
+}
+
 /**
  * damon_kdamond_pid() - Return pid of a given DAMON context's worker thread.
  * @ctx:	The DAMON context of the question.

2.47.3

So, damon_lru_sort_init() callse damon_modules_new_paddr_ctx_target(), which calls damon_select_ops(). The damon_select_ops() cannot fail because DAMON_LRU_SORT depends on DAMON_PADDR, and the damon_select_ops() is for paddr ops setup.

But, damon_modules_new_paddr_ctx_target() calls damon_new_target() after that. It could theoretically fail due to an allocation failure.

Makes sense. I will work on this. Not a blocker of this patch though.

Correct, damon_lru_sort_enabled_store() part upstream change is not properly ported. I will post a new version.

Thanks,
SJ

On Tue, 12 May 2026 21:30:36 -0700 SeongJae Park <[email protected]> wrote:
[...]

Sashiko found this backport is incomplete. Please read my reply [1] for details. I will send a complete version as a reply to this mail.

[1] https://lore.kernel.org/[email protected]

Thanks,
SJ

[...]

DAMON_LRU_SORT updates 'enabled' and 'kdamond_pid' parameter values, which represents the running status of its kdamond, when the user explicitly requests start/stop of the kdamond. The kdamond can, however, be stopped in events other than the explicit user request in the following three events.

1. ctx->regions_score_histogram allocation failure at beginning of the execution,
2. damon_commit_ctx() failure due to invalid user input, and
3. damon_commit_ctx() failure due to its internal allocation failures.

Hence, if the kdamond is stopped by the above three events, the values of the status parameters can be stale. Users could show the stale values and be confused. This is already bad, but the real consequence is worse. DAMON_LRU_SORT avoids unnecessary damon_start() and damon_stop() calls based on the 'enabled' parameter value. And the update of 'enabled' parameter value depends on the damon_start() and damon_stop() call results. Hence, once the kdamond has stopped by the unintentional events, the user cannot restart the kdamond before the system reboot. For example, the issue can be reproduced via below steps.

    # cd /sys/module/damon_lru_sort/parameters
    #
    # # start DAMON_LRU_SORT
    # echo Y > enabled
    # ps -ef | grep kdamond
    root         806       2  0 17:53 ?        00:00:00 [kdamond.0]
    root         808     803  0 17:53 pts/4    00:00:00 grep kdamond
    #
    # # commit wrong input to stop kdamond withou explicit stop request
    # echo 3 > addr_unit
    # echo Y > commit_inputs
    bash: echo: write error: Invalid argument
    #
    # # confirm kdamond is stopped
    # ps -ef | grep kdamond
    root         811     803  0 17:53 pts/4    00:00:00 grep kdamond
    #
    # # users casn now show stable status
    # cat enabled
    Y
    # cat kdamond_pid
    806
    #
    # # even after fixing the wrong parameter,
    # # kdamond cannot be restarted.
    # echo 1 > addr_unit
    # echo Y > enabled
    # ps -ef | grep kdamond
    root         815     803  0 17:54 pts/4    00:00:00 grep kdamond

The problem will only rarely happen in real and common setups for the following reasons. The allocation failures are unlikely in such setups since those allocations are arguably too small to fail. Also sane users on real production environments may not commit wrong input parameters. But once it happens, the consequence is quite bad. And the bug is a bug.

The issue stems from the fact that there are multiple events that can change the status, and following all the events is challenging. Dynamically detect and use the fresh status for the parameters when those are requested.

(port parts of 42b7491af14c ("mm/damon/core: introduce damon_call()") and d2b5be741a50 ("mm/damon/sysfs: use DAMON core API damon_is_running()") for damon_is_running() dependency)

---
Changes from v1
- v1: https://lore.kernel.org/[email protected]
- Fixup incomplete enabled_store() part porting

 include/linux/damon.h |  1 +
 mm/damon/core.c       | 16 +++++++++
 mm/damon/lru_sort.c   | 84 ++++++++++++++++++++++++++++---------------
 3 files changed, 73 insertions(+), 28 deletions(-)

index 7eeec0eaaf1f5..7133131433547 100644
@@ -572,6 +572,7 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs
 
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+bool damon_is_running(struct damon_ctx *ctx);
 int damon_kdamond_pid(struct damon_ctx *ctx);
 
 int damon_set_region_biggest_system_ram_default(struct damon_target *t,

index fc68364c9ad2e..1c041d011b8ef 100644
@@ -643,6 +643,22 @@ static bool damon_check_reset_time_interval(struct timespec64 *baseline,
 	return true;
 }
 
+/**
+ * damon_is_running() - Returns if a given DAMON context is running.
+ * @ctx:	The DAMON context to see if running.
+ *
+ * Return: true if @ctx is running, false otherwise.
+ */
+bool damon_is_running(struct damon_ctx *ctx)
+{
+	bool running;
+
+	mutex_lock(&ctx->kdamond_lock);
+	running = ctx->kdamond != NULL;
+	mutex_unlock(&ctx->kdamond_lock);
+	return running;
+}
+
 /**
  * damon_kdamond_pid() - Return pid of a given DAMON context's worker thread.
  * @ctx:	The DAMON context of the question.

2.47.3