Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
IronPort-SDR: wj6kxm553tygYfzaCNOEPfZj2tee8FULjvoIHK+Kun+duTab3SjOugm0Aa6I9/uae1Fc4PM3xQ
 9L/d+vEDak7w==
From:   SeongJae Park <sjpark@amazon.com>
To:     <akpm@linux-foundation.org>
CC:     SeongJae Park <sjpark@amazon.de>, <Jonathan.Cameron@Huawei.com>,
        <aarcange@redhat.com>, <acme@kernel.org>,
        <alexander.shishkin@linux.intel.com>, <amit@kernel.org>,
        <brendan.d.gregg@gmail.com>, <brendanhiggins@google.com>,
        <cai@lca.pw>, <colin.king@canonical.com>, <corbet@lwn.net>,
        <dwmw@amazon.com>, <jolsa@redhat.com>, <kirill@shutemov.name>,
        <mark.rutland@arm.com>, <mgorman@suse.de>, <minchan@kernel.org>,
        <mingo@redhat.com>, <namhyung@kernel.org>, <peterz@infradead.org>,
        <rdunlap@infradead.org>, <riel@surriel.com>, <rientjes@google.com>,
        <rostedt@goodmis.org>, <shakeelb@google.com>, <shuah@kernel.org>,
        <sj38.park@gmail.com>, <vbabka@suse.cz>, <vdavydov.dev@gmail.com>,
        <yang.shi@linux.alibaba.com>, <ying.huang@intel.com>,
        <linux-mm@kvack.org>, <linux-doc@vger.kernel.org>,
        <linux-kernel@vger.kernel.org>
Subject: [RFC v6 3/7] mm/damon: Implement data access monitoring-based operation schemes
Date:   Tue, 7 Apr 2020 12:00:02 +0200
Message-ID: <20200407100007.3894-4-sjpark@amazon.com>
In-Reply-To: <20200407100007.3894-1-sjpark@amazon.com>
References: <20200407100007.3894-1-sjpark@amazon.com>
MIME-Version: 1.0
Content-Type: text/plain
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

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            | 149 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 173 insertions(+)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 49205c71c63d..b0fa898ed6d8 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;
+};
+
 /*
  * For each 'sample_interval', DAMON checks whether each region is accessed or
  * not.  It aggregates and keeps the access information (number of accesses to
@@ -66,6 +87,7 @@ 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);
@@ -76,6 +98,8 @@ int damon_set_pids(struct damon_ctx *ctx, unsigned long *pids, ssize_t nr_pids);
 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 7e56011b9b5f..3c10ff3a487c 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>
@@ -45,6 +46,12 @@
 #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, s, next) \
+	list_for_each_entry_safe(s, next, &(ctx)->schemes_list, list)
+
 #define MAX_RFILE_PATH_LEN	256
 
 /* Get a random number in [l, r) */
@@ -173,6 +180,27 @@ 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);
+}
+
 static unsigned int nr_damon_tasks(struct damon_ctx *ctx)
 {
 	struct damon_task *t;
@@ -701,6 +729,101 @@ static void kdamond_count_age(struct damon_ctx *c, unsigned int threshold)
 	}
 }
 
+#ifndef CONFIG_ADVISE_SYSCALLS
+static int damos_madvise(struct damon_task *task, struct damon_region *r,
+			int behavior)
+{
+	return -EINVAL;
+}
+#else
+static int damos_madvise(struct damon_task *task, struct damon_region *r,
+			int behavior)
+{
+	struct task_struct *t;
+	struct mm_struct *mm;
+	int ret = -ENOMEM;
+
+	t = damon_get_task_struct(task);
+	if (!t)
+		goto out;
+	mm = damon_get_mm(task);
+	if (!mm)
+		goto put_task_out;
+
+	ret = do_madvise(t, mm, PAGE_ALIGN(r->vm_start),
+			PAGE_ALIGN(r->vm_end - r->vm_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_task *task, 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(task, r, madv_action);
+}
+
+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 ((s->min_sz_region && sz < s->min_sz_region) ||
+				(s->max_sz_region && s->max_sz_region < sz))
+			continue;
+		if ((s->min_nr_accesses && r->nr_accesses < s->min_nr_accesses)
+				|| (s->max_nr_accesses &&
+					s->max_nr_accesses < r->nr_accesses))
+			continue;
+		if ((s->min_age_region && r->age < s->min_age_region) ||
+				(s->max_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)
 
 /*
@@ -1011,6 +1134,7 @@ 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_reset_aggregated(ctx);
 			kdamond_split_regions(ctx);
 		}
@@ -1090,6 +1214,30 @@ int damon_stop(struct damon_ctx *ctx)
 	return -EBUSY;
 }
 
+/**
+ * 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_schemes_safe(ctx, s, next)
+		damon_destroy_scheme(s);
+	for (i = 0; i < nr_schemes; i++)
+		damon_add_scheme(ctx, schemes[i]);
+	return 0;
+}
+
 /**
  * damon_set_pids() - Set monitoring target processes.
  * @ctx:	monitoring context
@@ -1526,6 +1674,7 @@ 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);
 
 	return 0;
 }
-- 
2.17.1