[RFC v2 0/4] Implement Data Access Monitoring-based Memory Operation Schemes

[RFC v2 0/4] Implement Data Access Monitoring-based Memory Operation Schemes

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

DAMON[1] can be used as a primitive for data access awared memory management
optimizations.  That said, users who want such optimizations should run DAMON,
read the monitoring results, analyze it, plan a new memory management scheme,
and apply the new scheme by themselves.  Such efforts will be inevitable for
some complicated optimizations.

However, in many other cases, the users would just want the system to apply an
memory management action to a memory region of a specific size having a
specific access frequency for a specific time.  For example, "page out a memory
region larger than 100 MiB keeping only rare accesses more than 10 minutes", or
"Use THP for a memory region larger than 2 MiB maintaing frequent accesses for
more than 5 seconds".

This RFC patchset makes DAMON to handle such data access monitoring-based
operation schemes.  With this change, users can do the data access awared
optimizations by simply specifying their schemes to DAMON.


Sequence Of Patches
===================

The patches are based on the v5.5 plus v5 DAMON patchset[1] and Minchan's
``madvise()`` factor-out patch[2].  Minchan's patch was necessary for reuse of
``madvise()`` code in DAMON.  You can also clone the complete git tree:

    $ git clone git://github.com/sjp38/linux -b damos/rfc/v2

The web is also available:
https://github.com/sjp38/linux/releases/tag/damos/rfc/v2

The first patch allows DAMON to reuse ``madvise()`` code for the actions.  The
second patch accounts age of each region.  Third patch implements the handling
of the schemes in DAMON and exports a kernel space programming interface for
it.  Finally, the fourth patch implements a debugfs interface for privileged
people and programs.

[1] https://lore.kernel.org/linux-mm/20200217103110.30817-1-sjpark@amazon.com/
[2] https://lore.kernel.org/linux-mm/20200128001641.5086-2-minchan@kernel.org/


Patch History
=============

Changes from RFC v1
(https://lore.kernel.org/linux-mm/20200210150921.32482-1-sjpark@amazon.com/)
 - Properly adjust age accounting related properties after splitting, merging,
   and action applying

SeongJae Park (4):
  mm/madvise: Export madvise_common() to mm internal code
  mm/damon: Account age of target regions
  mm/damon: Implement data access monitoring-based operation schemes
  mm/damon/schemes: Implement a debugfs interface

 include/linux/damon.h |  29 ++++
 mm/damon.c            | 360 +++++++++++++++++++++++++++++++++++++++++-
 mm/internal.h         |   4 +
 mm/madvise.c          |   3 +-
 4 files changed, 388 insertions(+), 8 deletions(-)

-- 
2.17.1

[RFC v2 1/4] mm/madvise: Export madvise_common() to mm internal code

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

This commit exports ``madvise_common()`` to ``mm/`` code for future
reuse.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 mm/internal.h | 4 ++++
 mm/madvise.c  | 3 ++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/mm/internal.h b/mm/internal.h
index 3cf20ab3ca01..dcdfe00e02ff 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -576,4 +576,8 @@ static inline bool is_migrate_highatomic_page(struct page *page)
 
 void setup_zone_pageset(struct zone *zone);
 extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
+
+
+int madvise_common(struct task_struct *task, struct mm_struct *mm,
+			unsigned long start, size_t len_in, int behavior);
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/madvise.c b/mm/madvise.c
index 0c901de531e4..4fa9dfc770bc 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1005,7 +1005,7 @@ madvise_behavior_valid(int behavior)
  * @task could be a zombie leader if it calls sys_exit so accessing mm_struct
  * via task->mm is prohibited. Please use @mm instead of task->mm.
  */
-static int madvise_common(struct task_struct *task, struct mm_struct *mm,
+int madvise_common(struct task_struct *task, struct mm_struct *mm,
 			unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
@@ -1103,6 +1103,7 @@ static int madvise_common(struct task_struct *task, struct mm_struct *mm,
 
 	return error;
 }
+EXPORT_SYMBOL_GPL(madvise_common);
 
 /*
  * The madvise(2) system call.
-- 
2.17.1

[RFC v2 2/4] mm/damon: Account age of target regions

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

DAMON can be used as a primitive for data access pattern awared memory
maangement optimizations.  However, users who want such optimizations
should run DAMON, read the monitoring results, analyze it, plan a new
memory management scheme, and apply the new scheme by themselves.  It
would not be too hard, but still require some level of efforts.  For
complicated optimizations, this effort is inevitable.

That said, in many cases, users would simply want to apply an actions to
a memory region of a specific size having a specific access frequency
for a specific time.  For example, "page out a memory region larger than
100 MiB but having a low access frequency more than 10 minutes", or "Use
THP for a memory region larger than 2 MiB having a high access frequency
for more than 2 seconds".

For such optimizations, users will need to first account the age of each
region themselves.  To reduce such efforts, this commit implements a
simple age account of each region in DAMON.  For each aggregation step,
DAMON compares the access frequency and start/end address of each region
with those from last aggregation and reset the age of the region if the
change is significant.  Else, the age is incremented.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h |  5 ++++
 mm/damon.c            | 58 +++++++++++++++++++++++++++++++++++++++----
 2 files changed, 58 insertions(+), 5 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 78785cb88d42..50fbe308590e 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -22,6 +22,11 @@ struct damon_region {
 	unsigned long sampling_addr;
 	unsigned int nr_accesses;
 	struct list_head list;
+
+	unsigned int age;
+	unsigned long last_vm_start;
+	unsigned long last_vm_end;
+	unsigned int last_nr_accesses;
 };
 
 /* Represents a monitoring target task */
diff --git a/mm/damon.c b/mm/damon.c
index ca9a32ecc61d..c9bce7c97709 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -87,6 +87,10 @@ static struct damon_region *damon_new_region(struct damon_ctx *ctx,
 	ret->sampling_addr = damon_rand(ctx, vm_start, vm_end);
 	INIT_LIST_HEAD(&ret->list);
 
+	ret->age = 0;
+	ret->last_vm_start = vm_start;
+	ret->last_vm_end = vm_end;
+
 	return ret;
 }
 
@@ -600,11 +604,44 @@ static void kdamond_flush_aggregated(struct damon_ctx *c)
 			damon_write_rbuf(c, &r->vm_end, sizeof(r->vm_end));
 			damon_write_rbuf(c, &r->nr_accesses,
 					sizeof(r->nr_accesses));
+			r->last_nr_accesses = r->nr_accesses;
 			r->nr_accesses = 0;
 		}
 	}
 }
 
+#define diff_of(a, b) (a > b ? a - b : b - a)
+
+/*
+ * Increase or reset the age of the given monitoring target region
+ *
+ * If the area or '->nr_accesses' has changed significantly, reset the '->age'.
+ * Else, increase the age.
+ */
+static void damon_do_count_age(struct damon_region *r, unsigned int threshold)
+{
+	unsigned long sz_threshold = (r->vm_end - r->vm_start) / 5;
+
+	if (diff_of(r->vm_start, r->last_vm_start) +
+			diff_of(r->vm_end, r->last_vm_end) > sz_threshold)
+		r->age = 0;
+	else if (diff_of(r->nr_accesses, r->last_nr_accesses) > threshold)
+		r->age = 0;
+	else
+		r->age++;
+}
+
+static void kdamond_count_age(struct damon_ctx *c, unsigned int threshold)
+{
+	struct damon_task *t;
+	struct damon_region *r;
+
+	damon_for_each_task(c, t) {
+		damon_for_each_region(r, t)
+			damon_do_count_age(r, threshold);
+	}
+}
+
 #define sz_damon_region(r) (r->vm_end - r->vm_start)
 
 /*
@@ -613,15 +650,19 @@ static void kdamond_flush_aggregated(struct damon_ctx *c)
 static void damon_merge_two_regions(struct damon_region *l,
 				struct damon_region *r)
 {
-	l->nr_accesses = (l->nr_accesses * sz_damon_region(l) +
-			r->nr_accesses * sz_damon_region(r)) /
-			(sz_damon_region(l) + sz_damon_region(r));
+	unsigned long sz_l = sz_damon_region(l), sz_r = sz_damon_region(r);
+
+	l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
+			(sz_l + sz_r);
+	l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r);
+	if (sz_l < sz_r) {
+		l->last_vm_start = r->last_vm_start;
+		l->last_vm_end = r->last_vm_end;
+	}
 	l->vm_end = r->vm_end;
 	damon_destroy_region(r);
 }
 
-#define diff_of(a, b) (a > b ? a - b : b - a)
-
 /*
  * Merge adjacent regions having similar access frequencies
  *
@@ -674,6 +715,12 @@ static void damon_split_region_at(struct damon_ctx *ctx,
 	struct damon_region *new;
 
 	new = damon_new_region(ctx, r->vm_start + sz_r, r->vm_end);
+	new->age = r->age;
+	new->last_vm_start = r->vm_start;
+	new->last_nr_accesses = r->last_nr_accesses;
+
+	r->last_vm_start = r->vm_start;
+	r->last_vm_end = r->vm_end;
 	r->vm_end = new->vm_start;
 
 	damon_add_region(new, r, damon_next_region(r));
@@ -865,6 +912,7 @@ static int kdamond_fn(void *data)
 
 		if (kdamond_aggregate_interval_passed(ctx)) {
 			kdamond_merge_regions(ctx, max_nr_accesses / 10);
+			kdamond_count_age(ctx, max_nr_accesses / 10);
 			if (ctx->aggregate_cb)
 				ctx->aggregate_cb(ctx);
 			kdamond_flush_aggregated(ctx);
-- 
2.17.1

[RFC v2 3/4] mm/damon: Implement data access monitoring-based operation schemes

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

In many cases, users might use DAMON for simple data access awared
memory management optimizations such as applying an operation scheme to
a memory region of a specific size having a specific access frequency
for a specific time.  For example, "page out a memory region larger than
100 MiB but having a low access frequency more than 10 minutes", or "Use
THP for a memory region larger than 2 MiB having a high access frequency
for more than 2 seconds".

To minimize users from spending their time for implementation of such
simple data access monitoring-based operation schemes, this commit makes
DAMON to handle such schemes directly.  With this commit, users can
simply specify their desired schemes to DAMON.

Each of the schemes is composed with conditions for filtering of the
target memory regions and desired memory management action for the
target.  In specific, the format is::

    <min/max size> <min/max access frequency> <min/max age> <action>

The filtering conditions are size of memory region, number of accesses
to the region monitored by DAMON, and the age of the region.  The age of
region is incremented periodically but reset when its addresses or
access frequency has significanly changed or the action of a scheme has
applied.  For the action, current implementation supports only a few of
madvise() hints, ``MADV_WILLNEED``, ``MADV_COLD``, ``MADV_PAGEOUT``,
``MADV_HUGEPAGE``, and ``MADV_NOHUGEPAGE``.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h |  24 ++++++++
 mm/damon.c            | 131 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 155 insertions(+)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 50fbe308590e..8cb2452579ee 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -36,6 +36,27 @@ struct damon_task {
 	struct list_head list;
 };
 
+/* Data Access Monitoring-based Operation Scheme */
+enum damos_action {
+	DAMOS_WILLNEED,
+	DAMOS_COLD,
+	DAMOS_PAGEOUT,
+	DAMOS_HUGEPAGE,
+	DAMOS_NOHUGEPAGE,
+	DAMOS_ACTION_LEN,
+};
+
+struct damos {
+	unsigned int min_sz_region;
+	unsigned int max_sz_region;
+	unsigned int min_nr_accesses;
+	unsigned int max_nr_accesses;
+	unsigned int min_age_region;
+	unsigned int max_age_region;
+	enum damos_action action;
+	struct list_head list;
+};
+
 struct damon_ctx {
 	unsigned long sample_interval;
 	unsigned long aggr_interval;
@@ -58,6 +79,7 @@ struct damon_ctx {
 	struct rnd_state rndseed;
 
 	struct list_head tasks_list;	/* 'damon_task' objects */
+	struct list_head schemes_list;	/* 'damos' objects */
 
 	/* callbacks */
 	void (*sample_cb)(struct damon_ctx *context);
@@ -66,6 +88,8 @@ struct damon_ctx {
 
 int damon_set_pids(struct damon_ctx *ctx,
 			unsigned long *pids, ssize_t nr_pids);
+int damon_set_schemes(struct damon_ctx *ctx,
+			struct damos **schemes, ssize_t nr_schemes);
 int damon_set_recording(struct damon_ctx *ctx,
 			unsigned int rbuf_len, char *rfile_path);
 int damon_set_attrs(struct damon_ctx *ctx, unsigned long s, unsigned long a,
diff --git a/mm/damon.c b/mm/damon.c
index c9bce7c97709..45139d344f58 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -11,6 +11,7 @@
 
 #define CREATE_TRACE_POINTS
 
+#include <asm-generic/mman-common.h>
 #include <linux/damon.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
@@ -24,6 +25,8 @@
 #include <linux/slab.h>
 #include <trace/events/damon.h>
 
+#include "internal.h"
+
 #define damon_get_task_struct(t) \
 	(get_pid_task(find_vpid(t->pid), PIDTYPE_PID))
 
@@ -45,6 +48,12 @@
 #define damon_for_each_task_safe(ctx, t, next) \
 	list_for_each_entry_safe(t, next, &(ctx)->tasks_list, list)
 
+#define damon_for_each_schemes(ctx, r) \
+	list_for_each_entry(r, &(ctx)->schemes_list, list)
+
+#define damon_for_each_schemes_safe(ctx, r, next) \
+	list_for_each_entry_safe(r, next, &(ctx)->schemes_list, list)
+
 #define MAX_RFILE_PATH_LEN	256
 
 /* Get a random number in [l, r) */
@@ -190,6 +199,27 @@ static void damon_destroy_task(struct damon_task *t)
 	damon_free_task(t);
 }
 
+static void damon_add_scheme(struct damon_ctx *ctx, struct damos *s)
+{
+	list_add_tail(&s->list, &ctx->schemes_list);
+}
+
+static void damon_del_scheme(struct damos *s)
+{
+	list_del(&s->list);
+}
+
+static void damon_free_scheme(struct damos *s)
+{
+	kfree(s);
+}
+
+static void damon_destroy_scheme(struct damos *s)
+{
+	damon_del_scheme(s);
+	damon_free_scheme(s);
+}
+
 /*
  * Returns number of monitoring target tasks
  */
@@ -642,6 +672,84 @@ static void kdamond_count_age(struct damon_ctx *c, unsigned int threshold)
 	}
 }
 
+static int damos_do_action(struct damon_task *task, struct damon_region *r,
+			enum damos_action action)
+{
+	struct task_struct *t;
+	struct mm_struct *mm;
+	int madv_action;
+	int ret = -EINVAL;
+
+	switch (action) {
+	case DAMOS_WILLNEED:
+		madv_action = MADV_WILLNEED;
+		break;
+	case DAMOS_COLD:
+		madv_action = MADV_COLD;
+		break;
+	case DAMOS_PAGEOUT:
+		madv_action = MADV_PAGEOUT;
+		break;
+	case DAMOS_HUGEPAGE:
+		madv_action = MADV_HUGEPAGE;
+		break;
+	case DAMOS_NOHUGEPAGE:
+		madv_action = MADV_NOHUGEPAGE;
+		break;
+	default:
+		pr_warn("Wrong action %d\n", action);
+		goto out;
+	}
+
+	t = damon_get_task_struct(task);
+	if (!t)
+		goto out;
+	mm = damon_get_mm(task);
+	if (!mm)
+		goto put_task_out;
+
+	ret = madvise_common(t, mm, PAGE_ALIGN(r->vm_start),
+			PAGE_ALIGN(r->vm_end - r->vm_start), madv_action);
+
+	mmput(mm);
+put_task_out:
+	put_task_struct(t);
+out:
+	return ret;
+}
+
+static void damon_do_apply_schemes(struct damon_ctx *c, struct damon_task *t,
+				struct damon_region *r)
+{
+	struct damos *s;
+	unsigned long sz;
+
+	damon_for_each_schemes(c, s) {
+		sz = r->vm_end - r->vm_start;
+		if (sz < s->min_sz_region ||  s->max_sz_region < sz)
+			continue;
+		if (r->nr_accesses < s->min_nr_accesses ||
+				s->max_nr_accesses < r->nr_accesses)
+			continue;
+		if (r->age < s->min_age_region ||
+				s->max_age_region < r->age)
+			continue;
+		damos_do_action(t, r, s->action);
+		r->age = 0;
+	}
+}
+
+static void kdamond_apply_schemes(struct damon_ctx *c)
+{
+	struct damon_task *t;
+	struct damon_region *r;
+
+	damon_for_each_task(c, t) {
+		damon_for_each_region(r, t)
+			damon_do_apply_schemes(c, t, r);
+	}
+}
+
 #define sz_damon_region(r) (r->vm_end - r->vm_start)
 
 /*
@@ -915,6 +1023,7 @@ static int kdamond_fn(void *data)
 			kdamond_count_age(ctx, max_nr_accesses / 10);
 			if (ctx->aggregate_cb)
 				ctx->aggregate_cb(ctx);
+			kdamond_apply_schemes(ctx);
 			kdamond_flush_aggregated(ctx);
 			kdamond_split_regions(ctx);
 		}
@@ -989,6 +1098,27 @@ int damon_stop(struct damon_ctx *ctx)
 	return damon_turn_kdamond(ctx, false);
 }
 
+/*
+ * Set the data access monitoring oriented schemes
+ *
+ * NOTE: This function should not be called while the kdamond of the context is
+ * running.
+ *
+ * Returns 0 if success, or negative error code otherwise.
+ */
+int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes,
+			ssize_t nr_schemes)
+{
+	struct damos *s, *next;
+	ssize_t i;
+
+	damon_for_each_schemes_safe(ctx, s, next)
+		damon_destroy_scheme(s);
+	for (i = 0; i < nr_schemes; i++)
+		damon_add_scheme(ctx, schemes[i]);
+	return 0;
+}
+
 /*
  * This function should not be called while the kdamond is running.
  */
@@ -1431,6 +1561,7 @@ static int __init damon_init_user_ctx(void)
 
 	prandom_seed_state(&ctx->rndseed, 42);
 	INIT_LIST_HEAD(&ctx->tasks_list);
+	INIT_LIST_HEAD(&ctx->schemes_list);
 
 	ctx->sample_cb = NULL;
 	ctx->aggregate_cb = NULL;
-- 
2.17.1

[RFC v2 4/4] mm/damon/schemes: Implement a debugfs interface

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

This commit implements a debugfs interface for the data access
monitoring oriented memory management schemes.  It is supposed to be
used by administrators and privileged user space programs.  Users read
and update the rules using ``<debugfs>/damon/schemes`` file.  The format
is::

    <min/max size> <min/max access frequency> <min/max age> <action>

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 mm/damon.c | 171 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 169 insertions(+), 2 deletions(-)

diff --git a/mm/damon.c b/mm/damon.c
index 45139d344f58..de3e2b343139 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -199,6 +199,29 @@ static void damon_destroy_task(struct damon_task *t)
 	damon_free_task(t);
 }
 
+static struct damos *damon_new_scheme(
+		unsigned int min_sz_region, unsigned int max_sz_region,
+		unsigned int min_nr_accesses, unsigned int max_nr_accesses,
+		unsigned int min_age_region, unsigned int max_age_region,
+		enum damos_action action)
+{
+	struct damos *ret;
+
+	ret = kmalloc(sizeof(struct damos), GFP_KERNEL);
+	if (!ret)
+		return NULL;
+	ret->min_sz_region = min_sz_region;
+	ret->max_sz_region = max_sz_region;
+	ret->min_nr_accesses = min_nr_accesses;
+	ret->max_nr_accesses = max_nr_accesses;
+	ret->min_age_region = min_age_region;
+	ret->max_age_region = max_age_region;
+	ret->action = action;
+	INIT_LIST_HEAD(&ret->list);
+
+	return ret;
+}
+
 static void damon_add_scheme(struct damon_ctx *ctx, struct damos *s)
 {
 	list_add_tail(&s->list, &ctx->schemes_list);
@@ -1273,6 +1296,144 @@ static ssize_t debugfs_monitor_on_write(struct file *file,
 	return ret;
 }
 
+static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len)
+{
+	struct damos *s;
+	int written = 0;
+	int rc;
+
+	damon_for_each_schemes(c, s) {
+		rc = snprintf(&buf[written], len - written,
+				"%u %u %u %u %u %u %d\n",
+				s->min_sz_region, s->max_sz_region,
+				s->min_nr_accesses, s->max_nr_accesses,
+				s->min_age_region, s->max_age_region,
+				s->action);
+		if (!rc)
+			return -ENOMEM;
+		written += rc;
+	}
+	return written;
+}
+
+static ssize_t debugfs_schemes_read(struct file *file, char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	char *kbuf;
+	ssize_t ret;
+
+	kbuf = kmalloc(count, GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	ret = sprint_schemes(ctx, kbuf, count);
+	if (ret < 0)
+		goto out;
+	ret = simple_read_from_buffer(buf, count, ppos, kbuf, ret);
+
+out:
+	kfree(kbuf);
+	return ret;
+}
+
+static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes)
+{
+	ssize_t i;
+
+	for (i = 0; i < nr_schemes; i++)
+		kfree(schemes[i]);
+	kfree(schemes);
+}
+
+/*
+ * Converts a string into an array of struct damos pointers
+ *
+ * Returns an array of struct damos pointers that converted if the conversion
+ * success, or NULL otherwise.
+ */
+static struct damos **str_to_schemes(const char *str, ssize_t len,
+				ssize_t *nr_schemes)
+{
+	struct damos *scheme, **schemes;
+	const int max_nr_schemes = 256;
+	int pos = 0, parsed, ret;
+	unsigned int min_sz, max_sz, min_nr_a, max_nr_a, min_age, max_age;
+	int action;
+
+	schemes = kmalloc_array(max_nr_schemes, sizeof(struct damos *),
+			GFP_KERNEL);
+	if (!schemes)
+		return NULL;
+
+	*nr_schemes = 0;
+	while (pos < len && *nr_schemes < max_nr_schemes) {
+		ret = sscanf(&str[pos], "%u %u %u %u %u %u %d%n",
+				&min_sz, &max_sz, &min_nr_a, &max_nr_a,
+				&min_age, &max_age, &action, &parsed);
+		pos += parsed;
+		if (ret != 7)
+			break;
+		if (action >= DAMOS_ACTION_LEN) {
+			pr_err("wrong action %d\n", action);
+			goto error;
+		}
+
+		scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,
+				min_age, max_age, action);
+		if (!scheme)
+			goto error;
+
+		schemes[*nr_schemes] = scheme;
+		*nr_schemes += 1;
+	}
+	return schemes;
+error:
+	free_schemes_arr(schemes, *nr_schemes);
+	return NULL;
+}
+
+static ssize_t debugfs_schemes_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	struct damon_ctx *ctx = &damon_user_ctx;
+	char *kbuf;
+	struct damos **schemes;
+	ssize_t nr_schemes, ret;
+
+	kbuf = kmalloc_array(count, sizeof(char), GFP_KERNEL);
+	if (!kbuf)
+		return -ENOMEM;
+
+	ret = simple_write_to_buffer(kbuf, count, ppos, buf, count);
+	if (ret < 0)
+		goto out;
+
+	schemes = str_to_schemes(kbuf, ret, &nr_schemes);
+	if (!schemes) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	spin_lock(&ctx->kdamond_lock);
+	if (ctx->kdamond)
+		goto monitor_running;
+
+	damon_set_schemes(ctx, schemes, nr_schemes);
+	spin_unlock(&ctx->kdamond_lock);
+	goto free_schemes_out;
+
+monitor_running:
+	spin_unlock(&ctx->kdamond_lock);
+	pr_err("%s: kdamond is running. Turn it off first.\n", __func__);
+	ret = -EINVAL;
+free_schemes_out:
+	free_schemes_arr(schemes, nr_schemes);
+out:
+	kfree(kbuf);
+	return ret;
+}
+
 static ssize_t damon_sprint_pids(struct damon_ctx *ctx, char *buf, ssize_t len)
 {
 	struct damon_task *t;
@@ -1502,6 +1663,12 @@ static const struct file_operations pids_fops = {
 	.write = debugfs_pids_write,
 };
 
+static const struct file_operations schemes_fops = {
+	.owner = THIS_MODULE,
+	.read = debugfs_schemes_read,
+	.write = debugfs_schemes_write,
+};
+
 static const struct file_operations record_fops = {
 	.owner = THIS_MODULE,
 	.read = debugfs_record_read,
@@ -1518,10 +1685,10 @@ static struct dentry *debugfs_root;
 
 static int __init debugfs_init(void)
 {
-	const char * const file_names[] = {"attrs", "record",
+	const char * const file_names[] = {"attrs", "record", "schemes",
 		"pids", "monitor_on"};
 	const struct file_operations *fops[] = {&attrs_fops, &record_fops,
-		&pids_fops, &monitor_on_fops};
+		&schemes_fops, &pids_fops, &monitor_on_fops};
 	int i;
 
 	debugfs_root = debugfs_create_dir("damon", NULL);
-- 
2.17.1