[PATCH v12 07/16] mm/damon: Apply dynamic memory mapping changes

[SeongJae Park]

From: SeongJae Park <sjpark@xxxxxxxxx>

Only a number of parts in the virtual address space of the processes is
mapped to physical memory and accessed.  Thus, tracking the unmapped
address regions is just wasteful.  However, tracking every memory
mapping change might incur an overhead.  For the reason, DAMON applies
the dynamic memory mapping changes to the tracking regions only for each
of a user-specified time interval (``regions update interval``).

Signed-off-by: SeongJae Park <sjpark@xxxxxxxxx>
---
 include/linux/damon.h |  10 +++--
 mm/damon.c            | 101 +++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 106 insertions(+), 5 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index f1c3f491fc50..62b9f90ed87b 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -34,17 +34,21 @@ struct damon_task {
 /*
  * 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 each 'aggr_interval' time.
+ * each region) for 'aggr_interval' time.  DAMON also checks whether the memory
+ * mapping of the target tasks has changed (e.g., by mmap() calls from the
+ * application) and applies the changes for each 'regions_update_interval'.
  *
  * 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;
+	struct timespec64 last_regions_update;
 
 	struct task_struct *kdamond;
 	bool kdamond_stop;
@@ -54,8 +58,8 @@ struct damon_ctx {
 };
 
 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,
+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_start(struct damon_ctx *ctx);
 int damon_stop(struct damon_ctx *ctx);
diff --git a/mm/damon.c b/mm/damon.c
index bbd5b1d921da..38a8a68b7beb 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -714,6 +714,98 @@ static void kdamond_split_regions(struct damon_ctx *ctx)
 		last_nr_regions = nr_regions;
 }
 
+/*
+ * Check whether it is time to check and apply the dynamic mmap changes
+ *
+ * Returns true if it is.
+ */
+static bool kdamond_need_update_regions(struct damon_ctx *ctx)
+{
+	return damon_check_reset_time_interval(&ctx->last_regions_update,
+			ctx->regions_update_interval);
+}
+
+/*
+ * Check whether regions are intersecting
+ *
+ * Note that this function checks 'struct damon_region' and 'struct region'.
+ *
+ * Returns true if it is.
+ */
+static bool damon_intersect(struct damon_region *r, struct region *re)
+{
+	return !(r->vm_end <= re->start || re->end <= r->vm_start);
+}
+
+/*
+ * Update damon regions for the three big regions of the given task
+ *
+ * t		the given task
+ * bregions	the three big regions of the task
+ */
+static void damon_apply_three_regions(struct damon_ctx *ctx,
+		struct damon_task *t, struct region bregions[3])
+{
+	struct damon_region *r, *next;
+	unsigned int i = 0;
+
+	/* Remove regions which are not in the three big regions now */
+	damon_for_each_region_safe(r, next, t) {
+		for (i = 0; i < 3; i++) {
+			if (damon_intersect(r, &bregions[i]))
+				break;
+		}
+		if (i == 3)
+			damon_destroy_region(r);
+	}
+
+	/* Adjust intersecting regions to fit with the three big regions */
+	for (i = 0; i < 3; i++) {
+		struct damon_region *first = NULL, *last;
+		struct damon_region *newr;
+		struct region *br;
+
+		br = &bregions[i];
+		/* Get the first and last regions which intersects with br */
+		damon_for_each_region(r, t) {
+			if (damon_intersect(r, br)) {
+				if (!first)
+					first = r;
+				last = r;
+			}
+			if (r->vm_start >= br->end)
+				break;
+		}
+		if (!first) {
+			/* no damon_region intersects with this big region */
+			newr = damon_new_region(ctx,
+					ALIGN_DOWN(br->start, MIN_REGION),
+					ALIGN(br->end, MIN_REGION));
+			if (!newr)
+				continue;
+			damon_insert_region(newr, damon_prev_region(r), r);
+		} else {
+			first->vm_start = ALIGN_DOWN(br->start, MIN_REGION);
+			last->vm_end = ALIGN(br->end, MIN_REGION);
+		}
+	}
+}
+
+/*
+ * Update regions for current memory mappings
+ */
+static void kdamond_update_regions(struct damon_ctx *ctx)
+{
+	struct region three_regions[3];
+	struct damon_task *t;
+
+	damon_for_each_task(t, ctx) {
+		if (damon_three_regions_of(t, three_regions))
+			continue;
+		damon_apply_three_regions(ctx, t, three_regions);
+	}
+}
+
 /*
  * Check whether current monitoring should be stopped
  *
@@ -769,6 +861,9 @@ static int kdamond_fn(void *data)
 			kdamond_reset_aggregated(ctx);
 			kdamond_split_regions(ctx);
 		}
+
+		if (kdamond_need_update_regions(ctx))
+			kdamond_update_regions(ctx);
 	}
 	damon_for_each_task(t, ctx) {
 		damon_for_each_region_safe(r, next, t)
@@ -876,6 +971,7 @@ int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids)
  * damon_set_attrs() - Set attributes for the monitoring.
  * @ctx:		monitoring context
  * @sample_int:		time interval between samplings
+ * @regions_update_int:	time interval between vma update checks
  * @aggr_int:		time interval between aggregations
  * @min_nr_reg:		minimal number of regions
  * @max_nr_reg:		maximum number of regions
@@ -885,8 +981,8 @@ int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids)
  *
  * Return: 0 on success, negative error code otherwise.
  */
-int damon_set_attrs(struct damon_ctx *ctx,
-		    unsigned long sample_int, unsigned long aggr_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)
 {
 	if (min_nr_reg < 3) {
@@ -902,6 +998,7 @@ int damon_set_attrs(struct damon_ctx *ctx,
 
 	ctx->sample_interval = sample_int;
 	ctx->aggr_interval = aggr_int;
+	ctx->regions_update_interval = regions_update_int;
 	ctx->min_nr_regions = min_nr_reg;
 	ctx->max_nr_regions = max_nr_reg;
 
-- 
2.17.1