[PATCH v4 05/11] mm/damon: Implement kernel space API

[<sjpark@amazon.com>]

From: SeongJae Park <sjpark@amazon.de>

This commit implements the DAMON api for the kernel.  Other kernel code
can use DAMON by calling damon_start() and damon_stop() with their own
'struct damon_ctx'.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h | 71 +++++++++++++++++++++++++++++++++++++++++++
 mm/damon.c            | 70 +++++++++++-------------------------------
 2 files changed, 89 insertions(+), 52 deletions(-)
 create mode 100644 include/linux/damon.h

diff --git a/include/linux/damon.h b/include/linux/damon.h
new file mode 100644
index 000000000000..78785cb88d42
--- /dev/null
+++ b/include/linux/damon.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * DAMON api
+ *
+ * Copyright 2019 Amazon.com, Inc. or its affiliates.  All rights reserved.
+ *
+ * Author: SeongJae Park <sjpark@amazon.de>
+ */
+
+#ifndef _DAMON_H_
+#define _DAMON_H_
+
+#include <linux/random.h>
+#include <linux/spinlock_types.h>
+#include <linux/time64.h>
+#include <linux/types.h>
+
+/* Represents a monitoring target region on the virtual address space */
+struct damon_region {
+	unsigned long vm_start;
+	unsigned long vm_end;
+	unsigned long sampling_addr;
+	unsigned int nr_accesses;
+	struct list_head list;
+};
+
+/* Represents a monitoring target task */
+struct damon_task {
+	unsigned long pid;
+	struct list_head regions_list;
+	struct list_head list;
+};
+
+struct damon_ctx {
+	unsigned long sample_interval;
+	unsigned long aggr_interval;
+	unsigned long regions_update_interval;
+	unsigned long min_nr_regions;
+	unsigned long max_nr_regions;
+
+	struct timespec64 last_aggregation;
+	struct timespec64 last_regions_update;
+
+	unsigned char *rbuf;
+	unsigned int rbuf_len;
+	unsigned int rbuf_offset;
+	char *rfile_path;
+
+	struct task_struct *kdamond;
+	bool kdamond_stop;
+	spinlock_t kdamond_lock;
+
+	struct rnd_state rndseed;
+
+	struct list_head tasks_list;	/* 'damon_task' objects */
+
+	/* callbacks */
+	void (*sample_cb)(struct damon_ctx *context);
+	void (*aggregate_cb)(struct damon_ctx *context);
+};
+
+int damon_set_pids(struct damon_ctx *ctx,
+			unsigned long *pids, ssize_t nr_pids);
+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,
+			unsigned long r, unsigned long min, unsigned long max);
+int damon_start(struct damon_ctx *ctx);
+int damon_stop(struct damon_ctx *ctx);
+
+#endif
diff --git a/mm/damon.c b/mm/damon.c
index c2c40e003580..450b85bef120 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -9,6 +9,7 @@
 
 #define pr_fmt(fmt) "damon: " fmt
 
+#include <linux/damon.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/mm.h>
@@ -40,55 +41,6 @@
 #define damon_for_each_task_safe(ctx, t, next) \
 	list_for_each_entry_safe(t, next, &(ctx)->tasks_list, list)
 
-/* Represents a monitoring target region on the virtual address space */
-struct damon_region {
-	unsigned long vm_start;
-	unsigned long vm_end;
-	unsigned long sampling_addr;
-	unsigned int nr_accesses;
-	struct list_head list;
-};
-
-/* Represents a monitoring target task */
-struct damon_task {
-	unsigned long pid;
-	struct list_head regions_list;
-	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
- * each region) for 'aggr_interval' and then flushes it to the result buffer if
- * an 'aggr_interval' surpassed.  And for each 'regions_update_interval', damon
- * checks whether the memory mapping of the target tasks has changed (e.g., by
- * mmap() calls from the applications) and applies the changes.
- *
- * All time intervals are in micro-seconds.
- */
-struct damon_ctx {
-	unsigned long sample_interval;
-	unsigned long aggr_interval;
-	unsigned long regions_update_interval;
-	unsigned long min_nr_regions;
-	unsigned long max_nr_regions;
-
-	struct timespec64 last_aggregation;
-
-	unsigned char *rbuf;
-	unsigned int rbuf_len;
-	unsigned int rbuf_offset;
-	char *rfile_path;
-
-	struct task_struct *kdamond;
-	bool kdamond_stop;
-	spinlock_t kdamond_lock;
-
-	struct rnd_state rndseed;
-
-	struct list_head tasks_list;	/* 'damon_task' objects */
-};
-
 #define LEN_RES_FILE_PATH	256
 
 /* Get a random number in [l, r) */
@@ -885,11 +837,15 @@ static int kdamond_fn(void *data)
 			}
 			mmput(mm);
 		}
+		if (ctx->sample_cb)
+			ctx->sample_cb(ctx);
 
 		if (kdamond_aggregate_interval_passed(ctx)) {
 			kdamond_merge_regions(ctx, max_nr_accesses / 10);
 			kdamond_flush_aggregated(ctx);
 			kdamond_split_regions(ctx);
+			if (ctx->aggregate_cb)
+				ctx->aggregate_cb(ctx);
 		}
 
 		if (kdamond_need_update_regions(ctx))
@@ -952,6 +908,16 @@ static int damon_turn_kdamond(struct damon_ctx *ctx, bool on)
 	return 0;
 }
 
+int damon_start(struct damon_ctx *ctx)
+{
+	return damon_turn_kdamond(ctx, true);
+}
+
+int damon_stop(struct damon_ctx *ctx)
+{
+	return damon_turn_kdamond(ctx, false);
+}
+
 static inline bool damon_is_target_pid(struct damon_ctx *c, unsigned long pid)
 {
 	struct damon_task *t;
@@ -966,7 +932,7 @@ static inline bool damon_is_target_pid(struct damon_ctx *c, unsigned long pid)
 /*
  * This function should not be called while the kdamond is running.
  */
-static int damon_set_pids(struct damon_ctx *ctx,
+int damon_set_pids(struct damon_ctx *ctx,
 			unsigned long *pids, ssize_t nr_pids)
 {
 	ssize_t i;
@@ -1007,7 +973,7 @@ static int damon_set_pids(struct damon_ctx *ctx,
  *
  * Returns 0 on success, negative error code otherwise.
  */
-static int damon_set_recording(struct damon_ctx *ctx,
+int damon_set_recording(struct damon_ctx *ctx,
 				unsigned int rbuf_len, char *path_to_rfile)
 {
 	size_t rfile_path_len;
@@ -1051,7 +1017,7 @@ static int damon_set_recording(struct damon_ctx *ctx,
  *
  * Returns 0 on success, negative error code otherwise.
  */
-static int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
+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)
 {
-- 
2.17.1