[RFC v14 2/7] mm/damon: Implement data access monitoring-based operation schemes

[SeongJae Park]

From: SeongJae Park <sjpark@xxxxxxxxx>

In many cases, users might use DAMON for simple data access aware
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".

Most simple form of the solution would be doing offline data access
pattern profiling using DAMON and modifying the application source code
or system configuration based on the profiling results.  Or, developing
a daemon constructed with two modules (one for access monitoring and the
other for applying memory management actions via mlock(), madvise(),
sysctl, etc) is imaginable.

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.  Then, DAMON will
automatically apply the schemes to the the user-specified target
processes.

Each of the schemes is composed with conditions for filtering of the
target memory regions and desired memory management action for the
target.  Specifically, 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 significantly changed or the action of a scheme was
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@xxxxxxxxx>
---
 include/linux/damon.h |  48 ++++++++++++++
 mm/damon.c            | 146 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 194 insertions(+)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index ca5bd8de4aa4..df10bd00443e 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -67,6 +67,50 @@ struct damon_target {
 	struct list_head list;
 };
 
+/**
+ * enum damos_action - Represents an action of a Data Access Monitoring-based
+ * Operation Scheme.
+ *
+ * @DAMOS_WILLNEED:	Call ``madvise()`` for the region with MADV_WILLNEED.
+ * @DAMOS_COLD:		Call ``madvise()`` for the region with MADV_COLD.
+ * @DAMOS_PAGEOUT:	Call ``madvise()`` for the region with MADV_PAGEOUT.
+ * @DAMOS_HUGEPAGE:	Call ``madvise()`` for the region with MADV_HUGEPAGE.
+ * @DAMOS_NOHUGEPAGE:	Call ``madvise()`` for the region with MADV_NOHUGEPAGE.
+ */
+enum damos_action {
+	DAMOS_WILLNEED,
+	DAMOS_COLD,
+	DAMOS_PAGEOUT,
+	DAMOS_HUGEPAGE,
+	DAMOS_NOHUGEPAGE,
+};
+
+/**
+ * struct damos - Represents a Data Access Monitoring-based Operation Scheme.
+ * @min_sz_region:	Minimum size of target regions.
+ * @max_sz_region:	Maximum size of target regions.
+ * @min_nr_accesses:	Minimum ``->nr_accesses`` of target regions.
+ * @max_nr_accesses:	Maximum ``->nr_accesses`` of target regions.
+ * @min_age_region:	Minimum age of target regions.
+ * @max_age_region:	Maximum age of target regions.
+ * @action:		&damo_action to be applied to the target regions.
+ * @list:		List head for siblings.
+ *
+ * For each aggregation interval, DAMON applies @action to monitoring target
+ * regions fit in the condition and updates the statistics.  Note that both
+ * the minimums and the maximums are inclusive.
+ */
+struct damos {
+	unsigned long min_sz_region;
+	unsigned long 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 - Represents a context for each monitoring.  This is the
  * main interface that allows users to set the attributes and get the results
@@ -113,6 +157,7 @@ struct damon_target {
  * @kdamond_lock.  Accesses to other fields must be protected by themselves.
  *
  * @targets_list:	Head of monitoring targets (&damon_target) list.
+ * @schemes_list:	Head of schemes (&damos) list.
  *
  * @init_target_regions:	Constructs initial monitoring target regions.
  * @update_target_regions:	Updates monitoring target regions.
@@ -167,6 +212,7 @@ struct damon_ctx {
 	struct mutex kdamond_lock;
 
 	struct list_head targets_list;	/* 'damon_target' objects */
+	struct list_head schemes_list;	/* 'damos' objects */
 
 	/* callbacks */
 	void (*init_target_regions)(struct damon_ctx *context);
@@ -190,6 +236,8 @@ int damon_set_targets(struct damon_ctx *ctx,
 int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
 		unsigned long aggr_int, unsigned long regions_update_int,
 		unsigned long min_nr_reg, unsigned long max_nr_reg);
+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_start(struct damon_ctx *ctx);
diff --git a/mm/damon.c b/mm/damon.c
index 69090aa22207..e402717a2c0e 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -23,6 +23,7 @@
 
 #define CREATE_TRACE_POINTS
 
+#include <asm-generic/mman-common.h>
 #include <linux/damon.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
@@ -66,6 +67,12 @@
 #define damon_for_each_target_safe(t, next, ctx) \
 	list_for_each_entry_safe(t, next, &(ctx)->targets_list, list)
 
+#define damon_for_each_scheme(s, ctx) \
+	list_for_each_entry(s, &(ctx)->schemes_list, list)
+
+#define damon_for_each_scheme_safe(s, next, ctx) \
+	list_for_each_entry_safe(s, next, &(ctx)->schemes_list, list)
+
 #define MIN_RECORD_BUFFER_LEN	1024
 #define MAX_RECORD_BUFFER_LEN	(4 * 1024 * 1024)
 #define MAX_RFILE_PATH_LEN	256
@@ -187,6 +194,27 @@ static void damon_destroy_target(struct damon_target *t)
 	damon_free_target(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);
+}
+
 static unsigned int nr_damon_targets(struct damon_ctx *ctx)
 {
 	struct damon_target *t;
@@ -890,6 +918,98 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
 	}
 }
 
+#ifndef CONFIG_ADVISE_SYSCALLS
+static int damos_madvise(struct damon_target *target, struct damon_region *r,
+			int behavior)
+{
+	return -EINVAL;
+}
+#else
+static int damos_madvise(struct damon_target *target, struct damon_region *r,
+			int behavior)
+{
+	struct task_struct *t;
+	struct mm_struct *mm;
+	int ret = -ENOMEM;
+
+	t = damon_get_task_struct(target);
+	if (!t)
+		goto out;
+	mm = damon_get_mm(target);
+	if (!mm)
+		goto put_task_out;
+
+	ret = do_madvise(t, mm, PAGE_ALIGN(r->ar.start),
+			PAGE_ALIGN(r->ar.end - r->ar.start), behavior);
+	mmput(mm);
+put_task_out:
+	put_task_struct(t);
+out:
+	return ret;
+}
+#endif	/* CONFIG_ADVISE_SYSCALLS */
+
+static int damos_do_action(struct damon_target *target, struct damon_region *r,
+			enum damos_action action)
+{
+	int madv_action;
+
+	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);
+		return -EINVAL;
+	}
+
+	return damos_madvise(target, r, madv_action);
+}
+
+static void damon_do_apply_schemes(struct damon_ctx *c,
+				   struct damon_target *t,
+				   struct damon_region *r)
+{
+	struct damos *s;
+	unsigned long sz;
+
+	damon_for_each_scheme(s, c) {
+		sz = r->ar.end - r->ar.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_target *t;
+	struct damon_region *r;
+
+	damon_for_each_target(t, c) {
+		damon_for_each_region(r, t)
+			damon_do_apply_schemes(c, t, r);
+	}
+}
+
 #define sz_damon_region(r) (r->ar.end - r->ar.start)
 
 /*
@@ -1122,6 +1242,7 @@ static int kdamond_fn(void *data)
 				ctx->aggregate_cb(ctx);
 			kdamond_merge_regions(ctx, max_nr_accesses / 10,
 					sz_limit);
+			kdamond_apply_schemes(ctx);
 			kdamond_reset_aggregated(ctx);
 			kdamond_split_regions(ctx);
 		}
@@ -1207,6 +1328,30 @@ int damon_stop(struct damon_ctx *ctx)
 	return -EPERM;
 }
 
+/**
+ * damon_set_schemes() - Set data access monitoring based operation schemes.
+ * @ctx:	monitoring context
+ * @schemes:	array of the schemes
+ * @nr_schemes:	number of entries in @schemes
+ *
+ * This function should not be called while the kdamond of the context is
+ * running.
+ *
+ * Return: 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_scheme_safe(s, next, ctx)
+		damon_destroy_scheme(s);
+	for (i = 0; i < nr_schemes; i++)
+		damon_add_scheme(ctx, schemes[i]);
+	return 0;
+}
+
 /**
  * damon_set_targets() - Set monitoring targets.
  * @ctx:	monitoring context
@@ -1718,6 +1863,7 @@ static int __init damon_init_user_ctx(void)
 	mutex_init(&ctx->kdamond_lock);
 
 	INIT_LIST_HEAD(&ctx->targets_list);
+	INIT_LIST_HEAD(&ctx->schemes_list);
 
 	return 0;
 }
-- 
2.17.1