mm/damon/core: implement DAMON-based Operation Schemes (DAMOS)

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 avoid users spending their time for implementation of such simple
data access monitoring-based operation schemes, this makes DAMON to
handle such schemes directly.  With this change, users can simply
specify their desired schemes to DAMON.  Then, DAMON will automatically
apply the schemes to 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 a few of
madvise()-like hints, ``WILLNEED``, ``COLD``, ``PAGEOUT``, ``HUGEPAGE``,
and ``NOHUGEPAGE``.

Because DAMON supports various address spaces and application of the
actions to a monitoring target region is dependent to the type of the
target address space, the application code should be implemented by each
primitives and registered to the framework.  Note that this only
implements the framework part.  Following commit will implement the
action applications for virtual address spaces primitives.

Link: https://lkml.kernel.org/r/20211001125604.29660-3-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Amit Shah <amit@kernel.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Rienjes <rientjes@google.com>
Cc: David Woodhouse <dwmw@amazon.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Leonard Foerster <foersleo@amazon.de>
Cc: Marco Elver <elver@google.com>
Cc: Markus Boehme <markubo@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 109 insertions, 0 deletions

diff --git a/mm/damon/core.c b/mm/damon/core.c
index 3efbe80779db..0ed97b21cbb6 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -85,6 +85,50 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t)
 	damon_free_region(r);
 }
 
+struct damos *damon_new_scheme(
+		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 damos *scheme;
+
+	scheme = kmalloc(sizeof(*scheme), GFP_KERNEL);
+	if (!scheme)
+		return NULL;
+	scheme->min_sz_region = min_sz_region;
+	scheme->max_sz_region = max_sz_region;
+	scheme->min_nr_accesses = min_nr_accesses;
+	scheme->max_nr_accesses = max_nr_accesses;
+	scheme->min_age_region = min_age_region;
+	scheme->max_age_region = max_age_region;
+	scheme->action = action;
+	INIT_LIST_HEAD(&scheme->list);
+
+	return scheme;
+}
+
+void damon_add_scheme(struct damon_ctx *ctx, struct damos *s)
+{
+	list_add_tail(&s->list, &ctx->schemes);
+}
+
+static void damon_del_scheme(struct damos *s)
+{
+	list_del(&s->list);
+}
+
+static void damon_free_scheme(struct damos *s)
+{
+	kfree(s);
+}
+
+void damon_destroy_scheme(struct damos *s)
+{
+	damon_del_scheme(s);
+	damon_free_scheme(s);
+}
+
 /*
  * Construct a damon_target struct
  *
@@ -156,6 +200,7 @@ struct damon_ctx *damon_new_ctx(void)
 	ctx->max_nr_regions = 1000;
 
 	INIT_LIST_HEAD(&ctx->adaptive_targets);
+	INIT_LIST_HEAD(&ctx->schemes);
 
 	return ctx;
 }
@@ -175,7 +220,13 @@ static void damon_destroy_targets(struct damon_ctx *ctx)
 
 void damon_destroy_ctx(struct damon_ctx *ctx)
 {
+	struct damos *s, *next_s;
+
 	damon_destroy_targets(ctx);
+
+	damon_for_each_scheme_safe(s, next_s, ctx)
+		damon_destroy_scheme(s);
+
 	kfree(ctx);
 }
 
@@ -251,6 +302,30 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
 }
 
 /**
+ * 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_nr_running_ctxs() - Return number of currently running contexts.
  */
 int damon_nr_running_ctxs(void)
@@ -453,6 +528,39 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
 	}
 }
 
+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;
+		if (c->primitive.apply_scheme)
+			c->primitive.apply_scheme(c, t, r, s);
+		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)
 
 /*
@@ -693,6 +801,7 @@ static int kdamond_fn(void *data)
 			if (ctx->callback.after_aggregation &&
 					ctx->callback.after_aggregation(ctx))
 				set_kdamond_stop(ctx);
+			kdamond_apply_schemes(ctx);
 			kdamond_reset_aggregated(ctx);
 			kdamond_split_regions(ctx);
 			if (ctx->primitive.reset_aggregated)