[PATCH v13 08/15] mm/damon: Implement access pattern recording

[SeongJae Park <sjpark@amazon.com>]

From: SeongJae Park <sjpark@amazon.de>

This commit implements the recording feature of DAMON. If this feature
is enabled, DAMON writes the monitored access patterns in its binary
format into a file which specified by the user. This is already able to
be implemented by each user using the callbacks.  However, as the
recording is expected to be used widely, this commit implements the
feature in the DAMON, for more convenience and efficiency.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h |  15 +++++
 mm/damon.c            | 131 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 143 insertions(+), 3 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index e77518dd7f0d..31d436fd2843 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -66,6 +66,14 @@ struct damon_task {
  * in case of virtual memory monitoring) and applies the changes for each
  * @regions_update_interval.  All time intervals are in micro-seconds.
  *
+ * @rbuf: In-memory buffer for monitoring result recording.
+ * @rbuf_len: The length of @rbuf.
+ * @rbuf_offset: The offset for next write to @rbuf.
+ * @rfile_path: Record file path.
+ *
+ * If @rbuf, @rbuf_len, and @rfile_path are set, the monitored results are
+ * automatically stored in @rfile_path file.
+ *
  * @kdamond:		Kernel thread who does the monitoring.
  * @kdamond_stop:	Notifies whether kdamond should stop.
  * @kdamond_lock:	Mutex for the synchronizations with @kdamond.
@@ -100,6 +108,11 @@ struct damon_ctx {
 	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;
 	struct mutex kdamond_lock;
@@ -115,6 +128,8 @@ int damon_set_pids(struct damon_ctx *ctx, int *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_recording(struct damon_ctx *ctx,
+				unsigned int rbuf_len, char *rfile_path);
 int damon_start(struct damon_ctx *ctx);
 int damon_stop(struct damon_ctx *ctx);
 
diff --git a/mm/damon.c b/mm/damon.c
index 98367c91596a..ba002e0c3013 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -44,6 +44,9 @@
 #define damon_for_each_task_safe(t, next, ctx) \
 	list_for_each_entry_safe(t, next, &(ctx)->tasks_list, list)
 
+#define MAX_RECORD_BUFFER_LEN	(4 * 1024 * 1024)
+#define MAX_RFILE_PATH_LEN	256
+
 /* Get a random number in [l, r) */
 #define damon_rand(l, r) (l + prandom_u32() % (r - l))
 
@@ -565,16 +568,80 @@ static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx)
 }
 
 /*
- * Reset the aggregated monitoring results
+ * Flush the content in the result buffer to the result file
+ */
+static void damon_flush_rbuffer(struct damon_ctx *ctx)
+{
+	ssize_t sz;
+	loff_t pos = 0;
+	struct file *rfile;
+
+	rfile = filp_open(ctx->rfile_path, O_CREAT | O_RDWR | O_APPEND, 0644);
+	if (IS_ERR(rfile)) {
+		pr_err("Cannot open the result file %s\n",
+				ctx->rfile_path);
+		return;
+	}
+
+	while (ctx->rbuf_offset) {
+		sz = kernel_write(rfile, ctx->rbuf, ctx->rbuf_offset, &pos);
+		if (sz < 0)
+			break;
+		ctx->rbuf_offset -= sz;
+	}
+	filp_close(rfile, NULL);
+}
+
+/*
+ * Write a data into the result buffer
+ */
+static void damon_write_rbuf(struct damon_ctx *ctx, void *data, ssize_t size)
+{
+	if (!ctx->rbuf_len || !ctx->rbuf)
+		return;
+	if (ctx->rbuf_offset + size > ctx->rbuf_len)
+		damon_flush_rbuffer(ctx);
+
+	memcpy(&ctx->rbuf[ctx->rbuf_offset], data, size);
+	ctx->rbuf_offset += size;
+}
+
+/*
+ * Flush the aggregated monitoring results to the result buffer
+ *
+ * Stores current tracking results to the result buffer and reset 'nr_accesses'
+ * of each region.  The format for the result buffer is as below:
+ *
+ *   <time> <number of tasks> <array of task infos>
+ *
+ *   task info: <pid> <number of regions> <array of region infos>
+ *   region info: <start address> <end address> <nr_accesses>
  */
 static void kdamond_reset_aggregated(struct damon_ctx *c)
 {
 	struct damon_task *t;
-	struct damon_region *r;
+	struct timespec64 now;
+	unsigned int nr;
+
+	ktime_get_coarse_ts64(&now);
+
+	damon_write_rbuf(c, &now, sizeof(struct timespec64));
+	nr = nr_damon_tasks(c);
+	damon_write_rbuf(c, &nr, sizeof(nr));
 
 	damon_for_each_task(t, c) {
-		damon_for_each_region(r, t)
+		struct damon_region *r;
+
+		damon_write_rbuf(c, &t->pid, sizeof(t->pid));
+		nr = nr_damon_regions(t);
+		damon_write_rbuf(c, &nr, sizeof(nr));
+		damon_for_each_region(r, t) {
+			damon_write_rbuf(c, &r->vm_start, sizeof(r->vm_start));
+			damon_write_rbuf(c, &r->vm_end, sizeof(r->vm_end));
+			damon_write_rbuf(c, &r->nr_accesses,
+					sizeof(r->nr_accesses));
 			r->nr_accesses = 0;
+		}
 	}
 }
 
@@ -837,6 +904,14 @@ static bool kdamond_need_stop(struct damon_ctx *ctx)
 	return true;
 }
 
+static void kdamond_write_record_header(struct damon_ctx *ctx)
+{
+	int recfmt_ver = 1;
+
+	damon_write_rbuf(ctx, "damon_recfmt_ver", 16);
+	damon_write_rbuf(ctx, &recfmt_ver, sizeof(recfmt_ver));
+}
+
 /*
  * The monitoring daemon that runs as a kernel thread
  */
@@ -849,6 +924,9 @@ static int kdamond_fn(void *data)
 
 	pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
 	kdamond_init_regions(ctx);
+
+	kdamond_write_record_header(ctx);
+
 	while (!kdamond_need_stop(ctx)) {
 		kdamond_prepare_access_checks(ctx);
 		if (ctx->sample_cb)
@@ -869,6 +947,7 @@ static int kdamond_fn(void *data)
 		if (kdamond_need_update_regions(ctx))
 			kdamond_update_regions(ctx);
 	}
+	damon_flush_rbuffer(ctx);
 	damon_for_each_task(t, ctx) {
 		damon_for_each_region_safe(r, next, t)
 			damon_destroy_region(r);
@@ -971,6 +1050,52 @@ int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids)
 	return 0;
 }
 
+/**
+ * damon_set_recording() - Set attributes for the recording.
+ * @ctx:	target kdamond context
+ * @rbuf_len:	length of the result buffer
+ * @rfile_path:	path to the monitor result files
+ *
+ * Setting 'rbuf_len' 0 disables recording.
+ *
+ * This function should not be called while the kdamond is running.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_set_recording(struct damon_ctx *ctx,
+			unsigned int rbuf_len, char *rfile_path)
+{
+	size_t rfile_path_len;
+
+	if (rbuf_len > MAX_RECORD_BUFFER_LEN) {
+		pr_err("too long (>%d) result buffer length\n",
+				MAX_RECORD_BUFFER_LEN);
+		return -EINVAL;
+	}
+	rfile_path_len = strnlen(rfile_path, MAX_RFILE_PATH_LEN);
+	if (rfile_path_len >= MAX_RFILE_PATH_LEN) {
+		pr_err("too long (>%d) result file path %s\n",
+				MAX_RFILE_PATH_LEN, rfile_path);
+		return -EINVAL;
+	}
+	ctx->rbuf_len = rbuf_len;
+	kfree(ctx->rbuf);
+	kfree(ctx->rfile_path);
+	ctx->rfile_path = NULL;
+	if (!rbuf_len) {
+		ctx->rbuf = NULL;
+	} else {
+		ctx->rbuf = kvmalloc(rbuf_len, GFP_KERNEL);
+		if (!ctx->rbuf)
+			return -ENOMEM;
+	}
+	ctx->rfile_path = kmalloc(rfile_path_len + 1, GFP_KERNEL);
+	if (!ctx->rfile_path)
+		return -ENOMEM;
+	strncpy(ctx->rfile_path, rfile_path, rfile_path_len + 1);
+	return 0;
+}
+
 /**
  * damon_set_attrs() - Set attributes for the monitoring.
  * @ctx:		monitoring context
-- 
2.17.1