[RFC PATCH 0/4] DAMON: Make Configurable for Various Address Spaces Including Physical Memory

[RFC PATCH 0/4] DAMON: Make Configurable for Various Address Spaces Including Physical Memory

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

DAMON[1] is currently supporing only virtual memory address spaces of several
target processes.  Therefore, the user of DAMON should first select the target
processes.  This could be cumbersome in some cases and even makes no sense if
the user want to monitor non-virtual address spaces.  Especially, there were
many requests and questions for support of physical memory monitoring.

There were also many questions about use of different access check mechanisms
such as dedicated H/W features[2], idle page tracking, or perf-mem, instead of
the PTE Accessed bit checking, which is currently used by DAMON.  Supporting
various access check mechanisms will make DAMON to be highly tunable for
specific cases.

Fortunately, the core mechanisms of DAMON, the region-based sampling and
adaptive regions adjustment, are not coupled with the virtual memory spaces and
Accessed bit based access check.  As long as there is a way to 1) address every
region in the space and 2) check access to specific address, the core
mechanisms could be applied.  Nonetheless, current implementation of DAMON is
highly coupled with the virtual memory address spaces.

[1] https://lore.kernel.org/linux-mm/20200406130938.14066-1-sjpark@amazon.com/
[2] https://images.anandtech.com/doci/10591/HC28.AMD.Mike%20Clark.final-page-016.jpg


Baseline and Complete Git Trees
===============================

The patches are based on the v5.6 plus DAMON v8 patchset[1] and DAMOS RFC v6[2]
patchset.  You can also clone the complete git tree:

    $ git clone git://github.com/sjp38/linux -b cdamon/rfc/v1

The web is also available:
https://github.com/sjp38/linux/releases/tag/cdamon/rfc/v1

This patchset breaks the couplings and allows the target region definition and
the access check to be configurable by users so that it can support various
types of address spaces and use cases.  Based on this patchset, you can
configure DAMON to monitor physical memory or other special address spaces with
your preferred access check mechanism.

[1] https://lore.kernel.org/linux-mm/20200406130938.14066-1-sjpark@amazon.com/
[2] https://lore.kernel.org/linux-mm/20200407100007.3894-1-sjpark@amazon.com/


Sequence of Patches
===================

The sequence of patches is as follow.  The first patch defines the monitoring
region again based on pure address range abstraction so that there is no
assumption of virtual memory in there.  The following patch cleans up code
using the new abstraction.  The third patch allows users to configure the
initialization and dynamic update of the target address regions, which were
highly coupled with virtual memory area, with their own things.  Finally, the
fourth patch further make the access check mechanism, which were based on PTE
Accessed bit, configurable.

SeongJae Park (4):
  mm/damon: Use vm-independent address range concept
  mm/damon: Clean up code using 'struct damon_addr_range'
  mm/damon: Make monitoring target regions init/update configurable
  mm/damon: Make access check configurable

 include/linux/damon.h |  15 +++-
 mm/damon-test.h       |  82 ++++++++++----------
 mm/damon.c            | 174 ++++++++++++++++++++----------------------
 3 files changed, 136 insertions(+), 135 deletions(-)

-- 
2.17.1

[RFC PATCH 1/4] mm/damon: Use vm-independent address range concept

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

DAMON's main idea is not limited to virtual address space.  To prepare
for further expansion of the support for other address spaces including
physical memory, this commit modifies one of its core struct, 'struct
damon_region' to use virtual memory independent address space concept.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h | 11 ++++---
 mm/damon-test.h       | 46 +++++++++++++-------------
 mm/damon.c            | 76 +++++++++++++++++++++----------------------
 3 files changed, 68 insertions(+), 65 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index b0fa898ed6d8..d72dd524924f 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -15,17 +15,20 @@
 #include <linux/time64.h>
 #include <linux/types.h>
 
+struct damon_addr_range {
+	unsigned long start;
+	unsigned long end;
+};
+
 /* Represents a monitoring target region on the virtual address space */
 struct damon_region {
-	unsigned long vm_start;
-	unsigned long vm_end;
+	struct damon_addr_range ar;
 	unsigned long sampling_addr;
 	unsigned int nr_accesses;
 	struct list_head list;
 
 	unsigned int age;
-	unsigned long last_vm_start;
-	unsigned long last_vm_end;
+	struct damon_addr_range last_ar;
 	unsigned int last_nr_accesses;
 };
 
diff --git a/mm/damon-test.h b/mm/damon-test.h
index af6a1e84b8eb..7fd66df1e493 100644
--- a/mm/damon-test.h
+++ b/mm/damon-test.h
@@ -78,8 +78,8 @@ static void damon_test_regions(struct kunit *test)
 	struct damon_task *t;
 
 	r = damon_new_region(&damon_user_ctx, 1, 2);
-	KUNIT_EXPECT_EQ(test, 1ul, r->vm_start);
-	KUNIT_EXPECT_EQ(test, 2ul, r->vm_end);
+	KUNIT_EXPECT_EQ(test, 1ul, r->ar.start);
+	KUNIT_EXPECT_EQ(test, 2ul, r->ar.end);
 	KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses);
 
 	t = damon_new_task(42);
@@ -255,7 +255,7 @@ static void damon_test_aggregate(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, 3, it);
 
 	/* The aggregated information should be written in the buffer */
-	sr = sizeof(r->vm_start) + sizeof(r->vm_end) + sizeof(r->nr_accesses);
+	sr = sizeof(r->ar.start) + sizeof(r->ar.end) + sizeof(r->nr_accesses);
 	sp = sizeof(t->pid) + sizeof(unsigned int) + 3 * sr;
 	sz = sizeof(struct timespec64) + sizeof(unsigned int) + 3 * sp;
 	KUNIT_EXPECT_EQ(test, (unsigned int)sz, ctx->rbuf_offset);
@@ -325,8 +325,8 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
 
 	for (i = 0; i < nr_expected / 2; i++) {
 		r = damon_nth_region_of(t, i);
-		KUNIT_EXPECT_EQ(test, r->vm_start, expected[i * 2]);
-		KUNIT_EXPECT_EQ(test, r->vm_end, expected[i * 2 + 1]);
+		KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
+		KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
 	}
 
 	damon_cleanup_global_state();
@@ -445,8 +445,8 @@ static void damon_test_split_evenly(struct kunit *test)
 
 	i = 0;
 	damon_for_each_region(r, t) {
-		KUNIT_EXPECT_EQ(test, r->vm_start, i++ * 10);
-		KUNIT_EXPECT_EQ(test, r->vm_end, i * 10);
+		KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
+		KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
 	}
 	damon_free_task(t);
 
@@ -460,11 +460,11 @@ static void damon_test_split_evenly(struct kunit *test)
 	damon_for_each_region(r, t) {
 		if (i == 4)
 			break;
-		KUNIT_EXPECT_EQ(test, r->vm_start, 5 + 10 * i++);
-		KUNIT_EXPECT_EQ(test, r->vm_end, 5 + 10 * i);
+		KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
+		KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
 	}
-	KUNIT_EXPECT_EQ(test, r->vm_start, 5 + 10 * i);
-	KUNIT_EXPECT_EQ(test, r->vm_end, 59ul);
+	KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
+	KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
 	damon_free_task(t);
 
 	t = damon_new_task(42);
@@ -474,8 +474,8 @@ static void damon_test_split_evenly(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, nr_damon_regions(t), 1u);
 
 	damon_for_each_region(r, t) {
-		KUNIT_EXPECT_EQ(test, r->vm_start, 5ul);
-		KUNIT_EXPECT_EQ(test, r->vm_end, 6ul);
+		KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
+		KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
 	}
 	damon_free_task(t);
 }
@@ -489,12 +489,12 @@ static void damon_test_split_at(struct kunit *test)
 	r = damon_new_region(&damon_user_ctx, 0, 100);
 	damon_add_region(r, t);
 	damon_split_region_at(&damon_user_ctx, r, 25);
-	KUNIT_EXPECT_EQ(test, r->vm_start, 0ul);
-	KUNIT_EXPECT_EQ(test, r->vm_end, 25ul);
+	KUNIT_EXPECT_EQ(test, r->ar.start, 0ul);
+	KUNIT_EXPECT_EQ(test, r->ar.end, 25ul);
 
 	r = damon_next_region(r);
-	KUNIT_EXPECT_EQ(test, r->vm_start, 25ul);
-	KUNIT_EXPECT_EQ(test, r->vm_end, 100ul);
+	KUNIT_EXPECT_EQ(test, r->ar.start, 25ul);
+	KUNIT_EXPECT_EQ(test, r->ar.end, 100ul);
 
 	damon_free_task(t);
 }
@@ -514,8 +514,8 @@ static void damon_test_merge_two(struct kunit *test)
 	damon_add_region(r2, t);
 
 	damon_merge_two_regions(r, r2);
-	KUNIT_EXPECT_EQ(test, r->vm_start, 0ul);
-	KUNIT_EXPECT_EQ(test, r->vm_end, 300ul);
+	KUNIT_EXPECT_EQ(test, r->ar.start, 0ul);
+	KUNIT_EXPECT_EQ(test, r->ar.end, 300ul);
 	KUNIT_EXPECT_EQ(test, r->nr_accesses, 16u);
 
 	i = 0;
@@ -554,10 +554,10 @@ static void damon_test_merge_regions_of(struct kunit *test)
 	KUNIT_EXPECT_EQ(test, nr_damon_regions(t), 5u);
 	for (i = 0; i < 5; i++) {
 		r = damon_nth_region_of(t, i);
-		KUNIT_EXPECT_EQ(test, r->vm_start, saddrs[i]);
-		KUNIT_EXPECT_EQ(test, r->vm_end, eaddrs[i]);
-		KUNIT_EXPECT_EQ(test, r->last_vm_start, lsa[i]);
-		KUNIT_EXPECT_EQ(test, r->last_vm_end, lea[i]);
+		KUNIT_EXPECT_EQ(test, r->ar.start, saddrs[i]);
+		KUNIT_EXPECT_EQ(test, r->ar.end, eaddrs[i]);
+		KUNIT_EXPECT_EQ(test, r->last_ar.start, lsa[i]);
+		KUNIT_EXPECT_EQ(test, r->last_ar.end, lea[i]);
 
 	}
 	damon_free_task(t);
diff --git a/mm/damon.c b/mm/damon.c
index 3f93da898d72..f9958952d09e 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -72,7 +72,7 @@ static struct damon_ctx damon_user_ctx = {
  * Returns the pointer to the new struct if success, or NULL otherwise
  */
 static struct damon_region *damon_new_region(struct damon_ctx *ctx,
-				unsigned long vm_start, unsigned long vm_end)
+				unsigned long start, unsigned long end)
 {
 	struct damon_region *region;
 
@@ -80,14 +80,14 @@ static struct damon_region *damon_new_region(struct damon_ctx *ctx,
 	if (!region)
 		return NULL;
 
-	region->vm_start = vm_start;
-	region->vm_end = vm_end;
+	region->ar.start = start;
+	region->ar.end = end;
 	region->nr_accesses = 0;
 	INIT_LIST_HEAD(&region->list);
 
 	region->age = 0;
-	region->last_vm_start = vm_start;
-	region->last_vm_end = vm_end;
+	region->last_ar.start = start;
+	region->last_ar.end = end;
 
 	return region;
 }
@@ -282,16 +282,16 @@ static int damon_split_region_evenly(struct damon_ctx *ctx,
 	if (!r || !nr_pieces)
 		return -EINVAL;
 
-	orig_end = r->vm_end;
-	sz_orig = r->vm_end - r->vm_start;
+	orig_end = r->ar.end;
+	sz_orig = r->ar.end - r->ar.start;
 	sz_piece = sz_orig / nr_pieces;
 
 	if (!sz_piece)
 		return -EINVAL;
 
-	r->vm_end = r->vm_start + sz_piece;
+	r->ar.end = r->ar.start + sz_piece;
 	next = damon_next_region(r);
-	for (start = r->vm_end; start + sz_piece <= orig_end;
+	for (start = r->ar.end; start + sz_piece <= orig_end;
 			start += sz_piece) {
 		n = damon_new_region(ctx, start, start + sz_piece);
 		damon_insert_region(n, r, next);
@@ -299,7 +299,7 @@ static int damon_split_region_evenly(struct damon_ctx *ctx,
 	}
 	/* complement last region for possible rounding error */
 	if (n)
-		n->vm_end = orig_end;
+		n->ar.end = orig_end;
 
 	return 0;
 }
@@ -507,7 +507,7 @@ static void damon_mkold(struct mm_struct *mm, unsigned long addr)
 static void damon_prepare_access_check(struct damon_ctx *ctx,
 			struct mm_struct *mm, struct damon_region *r)
 {
-	r->sampling_addr = damon_rand(ctx, r->vm_start, r->vm_end);
+	r->sampling_addr = damon_rand(ctx, r->ar.start, r->ar.end);
 
 	damon_mkold(mm, r->sampling_addr);
 }
@@ -708,12 +708,12 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
 		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->ar.start, sizeof(r->ar.start));
+			damon_write_rbuf(c, &r->ar.end, sizeof(r->ar.end));
 			damon_write_rbuf(c, &r->nr_accesses,
 					sizeof(r->nr_accesses));
 			trace_damon_aggregated(t->pid, nr,
-					r->vm_start, r->vm_end, r->nr_accesses);
+					r->ar.start, r->ar.end, r->nr_accesses);
 			r->last_nr_accesses = r->nr_accesses;
 			r->nr_accesses = 0;
 		}
@@ -730,10 +730,10 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
  */
 static void damon_do_count_age(struct damon_region *r, unsigned int threshold)
 {
-	unsigned long sz_threshold = (r->vm_end - r->vm_start) / 5;
+	unsigned long sz_threshold = (r->ar.end - r->ar.start) / 5;
 
-	if (diff_of(r->vm_start, r->last_vm_start) +
-			diff_of(r->vm_end, r->last_vm_end) > sz_threshold)
+	if (diff_of(r->ar.start, r->last_ar.start) +
+			diff_of(r->ar.end, r->last_ar.end) > sz_threshold)
 		r->age = 0;
 	else if (diff_of(r->nr_accesses, r->last_nr_accesses) > threshold)
 		r->age = 0;
@@ -773,8 +773,8 @@ static int damos_madvise(struct damon_task *task, struct damon_region *r,
 	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);
+	ret = do_madvise(t, mm, PAGE_ALIGN(r->ar.start),
+			PAGE_ALIGN(r->ar.end - r->ar.start), behavior);
 	mmput(mm);
 put_task_out:
 	put_task_struct(t);
@@ -819,7 +819,7 @@ static void damon_do_apply_schemes(struct damon_ctx *c, struct damon_task *t,
 	unsigned long sz;
 
 	damon_for_each_schemes(c, s) {
-		sz = r->vm_end - r->vm_start;
+		sz = r->ar.end - r->ar.start;
 		if ((s->min_sz_region && sz < s->min_sz_region) ||
 				(s->max_sz_region && s->max_sz_region < sz))
 			continue;
@@ -847,7 +847,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 	}
 }
 
-#define sz_damon_region(r) (r->vm_end - r->vm_start)
+#define sz_damon_region(r) (r->ar.end - r->ar.start)
 
 /*
  * Merge two adjacent regions into one region
@@ -860,20 +860,20 @@ static void damon_merge_two_regions(struct damon_region *l,
 	l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
 			(sz_l + sz_r);
 	l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r);
-	l->vm_end = r->vm_end;
+	l->ar.end = r->ar.end;
 	damon_destroy_region(r);
 }
 
 static inline void set_last_area(struct damon_region *r, struct region *last)
 {
-	r->last_vm_start = last->start;
-	r->last_vm_end = last->end;
+	r->last_ar.start = last->start;
+	r->last_ar.end = last->end;
 }
 
 static inline void get_last_area(struct damon_region *r, struct region *last)
 {
-	last->start = r->last_vm_start;
-	last->end = r->last_vm_end;
+	last->start = r->last_ar.start;
+	last->end = r->last_ar.end;
 }
 
 /*
@@ -905,7 +905,7 @@ static void damon_merge_regions_of(struct damon_task *t, unsigned int thres)
 	unsigned long sz_mergee = 0;	/* size of current mergee */
 
 	damon_for_each_region_safe(r, next, t) {
-		if (!prev || prev->vm_end != r->vm_start ||
+		if (!prev || prev->ar.end != r->ar.start ||
 		    diff_of(prev->nr_accesses, r->nr_accesses) > thres) {
 			if (sz_biggest)
 				set_last_area(prev, &biggest_mergee);
@@ -928,7 +928,7 @@ static void damon_merge_regions_of(struct damon_task *t, unsigned int thres)
 		 * If next region and current region is not originated from
 		 * same region, initialize the size of mergee.
 		 */
-		if (r->last_vm_start != next->last_vm_start)
+		if (r->last_ar.start != next->last_ar.start)
 			sz_mergee = 0;
 
 		damon_merge_two_regions(prev, r);
@@ -966,14 +966,14 @@ static void damon_split_region_at(struct damon_ctx *ctx,
 {
 	struct damon_region *new;
 
-	new = damon_new_region(ctx, r->vm_start + sz_r, r->vm_end);
+	new = damon_new_region(ctx, r->ar.start + sz_r, r->ar.end);
 	new->age = r->age;
-	new->last_vm_start = r->vm_start;
+	new->last_ar.start = r->ar.start;
 	new->last_nr_accesses = r->last_nr_accesses;
 
-	r->last_vm_start = r->vm_start;
-	r->last_vm_end = r->vm_end;
-	r->vm_end = new->vm_start;
+	r->last_ar.start = r->ar.start;
+	r->last_ar.end = r->ar.end;
+	r->ar.end = new->ar.start;
 
 	damon_insert_region(new, r, damon_next_region(r));
 }
@@ -989,7 +989,7 @@ static void damon_split_regions_of(struct damon_ctx *ctx, struct damon_task *t)
 		 * 10 percent and at most 90% of original region
 		 */
 		sz_left_region = (prandom_u32_state(&ctx->rndseed) % 9 + 1) *
-			(r->vm_end - r->vm_start) / 10;
+			(r->ar.end - r->ar.start) / 10;
 		/* Do not allow blank region */
 		if (sz_left_region == 0)
 			continue;
@@ -1034,7 +1034,7 @@ static bool kdamond_need_update_regions(struct damon_ctx *ctx)
 
 static bool damon_intersect(struct damon_region *r, struct region *re)
 {
-	return !(r->vm_end <= re->start || re->end <= r->vm_start);
+	return !(r->ar.end <= re->start || re->end <= r->ar.start);
 }
 
 /*
@@ -1073,7 +1073,7 @@ static void damon_apply_three_regions(struct damon_ctx *ctx,
 					first = r;
 				last = r;
 			}
-			if (r->vm_start >= br->end)
+			if (r->ar.start >= br->end)
 				break;
 		}
 		if (!first) {
@@ -1081,8 +1081,8 @@ static void damon_apply_three_regions(struct damon_ctx *ctx,
 			newr = damon_new_region(ctx, br->start, br->end);
 			damon_insert_region(newr, damon_prev_region(r), r);
 		} else {
-			first->vm_start = br->start;
-			last->vm_end = br->end;
+			first->ar.start = br->start;
+			last->ar.end = br->end;
 		}
 	}
 }
-- 
2.17.1

[RFC PATCH 2/4] mm/damon: Clean up code using 'struct damon_addr_range'

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

There are unnecessarily duplicated code in DAMON, that can be eliminated
by using the new struct, 'damon_addr_range'.  This commit cleans up the
DAMON code in the way.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 mm/damon-test.h | 36 ++++++++++++++--------------
 mm/damon.c      | 64 +++++++++++++++++++------------------------------
 2 files changed, 42 insertions(+), 58 deletions(-)

diff --git a/mm/damon-test.h b/mm/damon-test.h
index 7fd66df1e493..7b2c903f1357 100644
--- a/mm/damon-test.h
+++ b/mm/damon-test.h
@@ -165,7 +165,7 @@ static void damon_test_set_pids(struct kunit *test)
  */
 static void damon_test_three_regions_in_vmas(struct kunit *test)
 {
-	struct region regions[3] = {0,};
+	struct damon_addr_range regions[3] = {0,};
 	/* 10-20-25, 200-210-220, 300-305, 307-330 */
 	struct vm_area_struct vmas[] = {
 		(struct vm_area_struct) {.vm_start = 10, .vm_end = 20},
@@ -306,7 +306,7 @@ static void damon_test_write_rbuf(struct kunit *test)
  */
 static void damon_do_test_apply_three_regions(struct kunit *test,
 				unsigned long *regions, int nr_regions,
-				struct region *three_regions,
+				struct damon_addr_range *three_regions,
 				unsigned long *expected, int nr_expected)
 {
 	struct damon_task *t;
@@ -344,10 +344,10 @@ static void damon_test_apply_three_regions1(struct kunit *test)
 	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
 				70, 80, 80, 90, 90, 100};
 	/* 5-27, 45-55, 73-104 */
-	struct region new_three_regions[3] = {
-		(struct region){.start = 5, .end = 27},
-		(struct region){.start = 45, .end = 55},
-		(struct region){.start = 73, .end = 104} };
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 27},
+		(struct damon_addr_range){.start = 45, .end = 55},
+		(struct damon_addr_range){.start = 73, .end = 104} };
 	/* 5-20-27, 45-55, 73-80-90-104 */
 	unsigned long expected[] = {5, 20, 20, 27, 45, 55,
 				73, 80, 80, 90, 90, 104};
@@ -366,10 +366,10 @@ static void damon_test_apply_three_regions2(struct kunit *test)
 	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
 				70, 80, 80, 90, 90, 100};
 	/* 5-27, 56-57, 65-104 */
-	struct region new_three_regions[3] = {
-		(struct region){.start = 5, .end = 27},
-		(struct region){.start = 56, .end = 57},
-		(struct region){.start = 65, .end = 104} };
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 27},
+		(struct damon_addr_range){.start = 56, .end = 57},
+		(struct damon_addr_range){.start = 65, .end = 104} };
 	/* 5-20-27, 56-57, 65-80-90-104 */
 	unsigned long expected[] = {5, 20, 20, 27, 56, 57,
 				65, 80, 80, 90, 90, 104};
@@ -390,10 +390,10 @@ static void damon_test_apply_three_regions3(struct kunit *test)
 	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
 				70, 80, 80, 90, 90, 100};
 	/* 5-27, 61-63, 65-104 */
-	struct region new_three_regions[3] = {
-		(struct region){.start = 5, .end = 27},
-		(struct region){.start = 61, .end = 63},
-		(struct region){.start = 65, .end = 104} };
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 27},
+		(struct damon_addr_range){.start = 61, .end = 63},
+		(struct damon_addr_range){.start = 65, .end = 104} };
 	/* 5-20-27, 61-63, 65-80-90-104 */
 	unsigned long expected[] = {5, 20, 20, 27, 61, 63,
 				65, 80, 80, 90, 90, 104};
@@ -415,10 +415,10 @@ static void damon_test_apply_three_regions4(struct kunit *test)
 	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
 				70, 80, 80, 90, 90, 100};
 	/* 5-7, 30-32, 65-68 */
-	struct region new_three_regions[3] = {
-		(struct region){.start = 5, .end = 7},
-		(struct region){.start = 30, .end = 32},
-		(struct region){.start = 65, .end = 68} };
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 7},
+		(struct damon_addr_range){.start = 30, .end = 32},
+		(struct damon_addr_range){.start = 65, .end = 68} };
 	/* expect 5-7, 30-32, 65-68 */
 	unsigned long expected[] = {5, 7, 30, 32, 65, 68};
 
diff --git a/mm/damon.c b/mm/damon.c
index f9958952d09e..80fa3cab7720 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -304,19 +304,15 @@ static int damon_split_region_evenly(struct damon_ctx *ctx,
 	return 0;
 }
 
-struct region {
-	unsigned long start;
-	unsigned long end;
-};
-
-static unsigned long sz_region(struct region *r)
+static unsigned long sz_range(struct damon_addr_range *r)
 {
 	return r->end - r->start;
 }
 
-static void swap_regions(struct region *r1, struct region *r2)
+static void swap_ranges(struct damon_addr_range *r1,
+			struct damon_addr_range *r2)
 {
-	struct region tmp;
+	struct damon_addr_range tmp;
 
 	tmp = *r1;
 	*r1 = *r2;
@@ -327,7 +323,7 @@ static void swap_regions(struct region *r1, struct region *r2)
  * Find the three regions in an address space
  *
  * vma		the head vma of the target address space
- * regions	an array of three 'struct region's that results will be saved
+ * regions	an array of three address ranges that results will be saved
  *
  * This function receives an address space and finds three regions in it which
  * separated by the two biggest unmapped regions in the space.  Please refer to
@@ -337,9 +333,9 @@ static void swap_regions(struct region *r1, struct region *r2)
  * Returns 0 if success, or negative error code otherwise.
  */
 static int damon_three_regions_in_vmas(struct vm_area_struct *vma,
-		struct region regions[3])
+		struct damon_addr_range regions[3])
 {
-	struct region gap = {0,}, first_gap = {0,}, second_gap = {0,};
+	struct damon_addr_range gap = {0,}, first_gap = {0,}, second_gap = {0,};
 	struct vm_area_struct *last_vma = NULL;
 	unsigned long start = 0;
 
@@ -352,20 +348,20 @@ static int damon_three_regions_in_vmas(struct vm_area_struct *vma,
 		}
 		gap.start = last_vma->vm_end;
 		gap.end = vma->vm_start;
-		if (sz_region(&gap) > sz_region(&second_gap)) {
-			swap_regions(&gap, &second_gap);
-			if (sz_region(&second_gap) > sz_region(&first_gap))
-				swap_regions(&second_gap, &first_gap);
+		if (sz_range(&gap) > sz_range(&second_gap)) {
+			swap_ranges(&gap, &second_gap);
+			if (sz_range(&second_gap) > sz_range(&first_gap))
+				swap_ranges(&second_gap, &first_gap);
 		}
 		last_vma = vma;
 	}
 
-	if (!sz_region(&second_gap) || !sz_region(&first_gap))
+	if (!sz_range(&second_gap) || !sz_range(&first_gap))
 		return -EINVAL;
 
 	/* Sort the two biggest gaps by address */
 	if (first_gap.start > second_gap.start)
-		swap_regions(&first_gap, &second_gap);
+		swap_ranges(&first_gap, &second_gap);
 
 	/* Store the result */
 	regions[0].start = start;
@@ -384,7 +380,7 @@ static int damon_three_regions_in_vmas(struct vm_area_struct *vma,
  * Returns 0 on success, negative error code otherwise.
  */
 static int damon_three_regions_of(struct damon_task *t,
-				struct region regions[3])
+				struct damon_addr_range regions[3])
 {
 	struct mm_struct *mm;
 	int rc;
@@ -446,7 +442,7 @@ static int damon_three_regions_of(struct damon_task *t,
 static void damon_init_regions_of(struct damon_ctx *c, struct damon_task *t)
 {
 	struct damon_region *r;
-	struct region regions[3];
+	struct damon_addr_range regions[3];
 	int i;
 
 	if (damon_three_regions_of(t, regions)) {
@@ -864,18 +860,6 @@ static void damon_merge_two_regions(struct damon_region *l,
 	damon_destroy_region(r);
 }
 
-static inline void set_last_area(struct damon_region *r, struct region *last)
-{
-	r->last_ar.start = last->start;
-	r->last_ar.end = last->end;
-}
-
-static inline void get_last_area(struct damon_region *r, struct region *last)
-{
-	last->start = r->last_ar.start;
-	last->end = r->last_ar.end;
-}
-
 /*
  * Merge adjacent regions having similar access frequencies
  *
@@ -900,7 +884,7 @@ static inline void get_last_area(struct damon_region *r, struct region *last)
 static void damon_merge_regions_of(struct damon_task *t, unsigned int thres)
 {
 	struct damon_region *r, *prev = NULL, *next;
-	struct region biggest_mergee;	/* the biggest region being merged */
+	struct damon_addr_range biggest_mergee;
 	unsigned long sz_biggest = 0;	/* size of the biggest_mergee */
 	unsigned long sz_mergee = 0;	/* size of current mergee */
 
@@ -908,11 +892,11 @@ static void damon_merge_regions_of(struct damon_task *t, unsigned int thres)
 		if (!prev || prev->ar.end != r->ar.start ||
 		    diff_of(prev->nr_accesses, r->nr_accesses) > thres) {
 			if (sz_biggest)
-				set_last_area(prev, &biggest_mergee);
+				prev->last_ar = biggest_mergee;
 
 			prev = r;
 			sz_biggest = sz_damon_region(prev);
-			get_last_area(prev, &biggest_mergee);
+			biggest_mergee = prev->ar;
 			continue;
 		}
 
@@ -921,7 +905,7 @@ static void damon_merge_regions_of(struct damon_task *t, unsigned int thres)
 		sz_mergee += sz_damon_region(r);
 		if (sz_mergee > sz_biggest) {
 			sz_biggest = sz_mergee;
-			get_last_area(r, &biggest_mergee);
+			biggest_mergee = r->ar;
 		}
 
 		/*
@@ -934,7 +918,7 @@ static void damon_merge_regions_of(struct damon_task *t, unsigned int thres)
 		damon_merge_two_regions(prev, r);
 	}
 	if (sz_biggest)
-		set_last_area(prev, &biggest_mergee);
+		prev->last_ar = biggest_mergee;
 }
 
 /*
@@ -1032,7 +1016,7 @@ static bool kdamond_need_update_regions(struct damon_ctx *ctx)
 			ctx->regions_update_interval);
 }
 
-static bool damon_intersect(struct damon_region *r, struct region *re)
+static bool damon_intersect(struct damon_region *r, struct damon_addr_range *re)
 {
 	return !(r->ar.end <= re->start || re->end <= r->ar.start);
 }
@@ -1044,7 +1028,7 @@ static bool damon_intersect(struct damon_region *r, struct region *re)
  * 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_task *t, struct damon_addr_range bregions[3])
 {
 	struct damon_region *r, *next;
 	unsigned int i = 0;
@@ -1063,7 +1047,7 @@ static void damon_apply_three_regions(struct damon_ctx *ctx,
 	for (i = 0; i < 3; i++) {
 		struct damon_region *first = NULL, *last;
 		struct damon_region *newr;
-		struct region *br;
+		struct damon_addr_range *br;
 
 		br = &bregions[i];
 		/* Get the first and last regions which intersects with br */
@@ -1092,7 +1076,7 @@ static void damon_apply_three_regions(struct damon_ctx *ctx,
  */
 static void kdamond_update_regions(struct damon_ctx *ctx)
 {
-	struct region three_regions[3];
+	struct damon_addr_range three_regions[3];
 	struct damon_task *t;
 
 	damon_for_each_task(ctx, t) {
-- 
2.17.1

[RFC PATCH 3/4] mm/damon: Make monitoring target regions init/update configurable

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

This commit allows DAMON users to configure their own monitoring target
regions initializer / updater.  Using this, users can confine the
monitoring address spaces as they want.  For example, users can track
only stack, heap, or shared memory area, as they want.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h |  2 ++
 mm/damon.c            | 20 +++++++++++++-------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index d72dd524924f..a051b5d966ed 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -93,6 +93,8 @@ struct damon_ctx {
 	struct list_head schemes_list;	/* 'damos' objects */
 
 	/* callbacks */
+	void (*init_target_regions)(struct damon_ctx *context);
+	void (*update_target_regions)(struct damon_ctx *context);
 	void (*sample_cb)(struct damon_ctx *context);
 	void (*aggregate_cb)(struct damon_ctx *context);
 };
diff --git a/mm/damon.c b/mm/damon.c
index 80fa3cab7720..da0e7efdf1e1 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -57,6 +57,9 @@
 /* Get a random number in [l, r) */
 #define damon_rand(ctx, l, r) (l + prandom_u32_state(&ctx->rndseed) % (r - l))
 
+static void kdamond_init_vm_regions(struct damon_ctx *ctx);
+static void kdamond_update_vm_regions(struct damon_ctx *ctx);
+
 /* A monitoring context for debugfs interface users. */
 static struct damon_ctx damon_user_ctx = {
 	.sample_interval = 5 * 1000,
@@ -64,6 +67,9 @@ static struct damon_ctx damon_user_ctx = {
 	.regions_update_interval = 1000 * 1000,
 	.min_nr_regions = 10,
 	.max_nr_regions = 1000,
+
+	.init_target_regions = kdamond_init_vm_regions,
+	.update_target_regions = kdamond_update_vm_regions,
 };
 
 /*
@@ -327,7 +333,7 @@ static void swap_ranges(struct damon_addr_range *r1,
  *
  * This function receives an address space and finds three regions in it which
  * separated by the two biggest unmapped regions in the space.  Please refer to
- * below comments of 'damon_init_regions_of()' function to know why this is
+ * below comments of 'damon_init_vm_regions_of()' function to know why this is
  * necessary.
  *
  * Returns 0 if success, or negative error code otherwise.
@@ -439,7 +445,7 @@ static int damon_three_regions_of(struct damon_task *t,
  *   <BIG UNMAPPED REGION 2>
  *   <stack>
  */
-static void damon_init_regions_of(struct damon_ctx *c, struct damon_task *t)
+static void damon_init_vm_regions_of(struct damon_ctx *c, struct damon_task *t)
 {
 	struct damon_region *r;
 	struct damon_addr_range regions[3];
@@ -463,12 +469,12 @@ static void damon_init_regions_of(struct damon_ctx *c, struct damon_task *t)
 }
 
 /* Initialize '->regions_list' of every task */
-static void kdamond_init_regions(struct damon_ctx *ctx)
+static void kdamond_init_vm_regions(struct damon_ctx *ctx)
 {
 	struct damon_task *t;
 
 	damon_for_each_task(ctx, t)
-		damon_init_regions_of(ctx, t);
+		damon_init_vm_regions_of(ctx, t);
 }
 
 static void damon_mkold(struct mm_struct *mm, unsigned long addr)
@@ -1074,7 +1080,7 @@ static void damon_apply_three_regions(struct damon_ctx *ctx,
 /*
  * Update regions for current memory mappings
  */
-static void kdamond_update_regions(struct damon_ctx *ctx)
+static void kdamond_update_vm_regions(struct damon_ctx *ctx)
 {
 	struct damon_addr_range three_regions[3];
 	struct damon_task *t;
@@ -1126,7 +1132,7 @@ static int kdamond_fn(void *data)
 	unsigned int max_nr_accesses = 0;
 
 	pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
-	kdamond_init_regions(ctx);
+	ctx->init_target_regions(ctx);
 	while (!kdamond_need_stop(ctx)) {
 		kdamond_prepare_access_checks(ctx);
 		if (ctx->sample_cb)
@@ -1147,7 +1153,7 @@ static int kdamond_fn(void *data)
 		}
 
 		if (kdamond_need_update_regions(ctx))
-			kdamond_update_regions(ctx);
+			ctx->update_target_regions(ctx);
 	}
 	damon_flush_rbuffer(ctx);
 	damon_for_each_task(ctx, t) {
-- 
2.17.1

[RFC PATCH 4/4] mm/damon: Make access check configurable

[SeongJae Park]

From: SeongJae Park <sjpark@amazon.de>

DAMON assumes the target region is in virtual address space and
therefore uses PTE Accessed bit checking for access checking.  However,
some users might want to use architecture-specific, more accurate and
light-weight access checking features.  Also, some users might want to
use DAMON for different address spaces such as physical memory space,
which needs different ways to check the access.

This commit allows DAMON users to configure the access check function to
their own version.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h |  2 ++
 mm/damon.c            | 22 +++++++++++++---------
 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index a051b5d966ed..188d5b89b303 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -95,6 +95,8 @@ struct damon_ctx {
 	/* callbacks */
 	void (*init_target_regions)(struct damon_ctx *context);
 	void (*update_target_regions)(struct damon_ctx *context);
+	void (*prepare_access_checks)(struct damon_ctx *context);
+	unsigned int (*check_accesses)(struct damon_ctx *context);
 	void (*sample_cb)(struct damon_ctx *context);
 	void (*aggregate_cb)(struct damon_ctx *context);
 };
diff --git a/mm/damon.c b/mm/damon.c
index da0e7efdf1e1..20a66a6307d1 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -59,6 +59,8 @@
 
 static void kdamond_init_vm_regions(struct damon_ctx *ctx);
 static void kdamond_update_vm_regions(struct damon_ctx *ctx);
+static void kdamond_prepare_vm_access_checks(struct damon_ctx *ctx);
+static unsigned int kdamond_check_vm_accesses(struct damon_ctx *ctx);
 
 /* A monitoring context for debugfs interface users. */
 static struct damon_ctx damon_user_ctx = {
@@ -70,6 +72,8 @@ static struct damon_ctx damon_user_ctx = {
 
 	.init_target_regions = kdamond_init_vm_regions,
 	.update_target_regions = kdamond_update_vm_regions,
+	.prepare_access_checks = kdamond_prepare_vm_access_checks,
+	.check_accesses = kdamond_check_vm_accesses,
 };
 
 /*
@@ -506,7 +510,7 @@ static void damon_mkold(struct mm_struct *mm, unsigned long addr)
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 }
 
-static void damon_prepare_access_check(struct damon_ctx *ctx,
+static void damon_prepare_vm_access_check(struct damon_ctx *ctx,
 			struct mm_struct *mm, struct damon_region *r)
 {
 	r->sampling_addr = damon_rand(ctx, r->ar.start, r->ar.end);
@@ -514,7 +518,7 @@ static void damon_prepare_access_check(struct damon_ctx *ctx,
 	damon_mkold(mm, r->sampling_addr);
 }
 
-static void kdamond_prepare_access_checks(struct damon_ctx *ctx)
+static void kdamond_prepare_vm_access_checks(struct damon_ctx *ctx)
 {
 	struct damon_task *t;
 	struct mm_struct *mm;
@@ -525,7 +529,7 @@ static void kdamond_prepare_access_checks(struct damon_ctx *ctx)
 		if (!mm)
 			continue;
 		damon_for_each_region(r, t)
-			damon_prepare_access_check(ctx, mm, r);
+			damon_prepare_vm_access_check(ctx, mm, r);
 		mmput(mm);
 	}
 }
@@ -563,7 +567,7 @@ static bool damon_young(struct mm_struct *mm, unsigned long addr,
  * mm	'mm_struct' for the given virtual address space
  * r	the region to be checked
  */
-static void damon_check_access(struct damon_ctx *ctx,
+static void damon_check_vm_access(struct damon_ctx *ctx,
 			struct mm_struct *mm, struct damon_region *r)
 {
 	static struct mm_struct *last_mm;
@@ -587,7 +591,7 @@ static void damon_check_access(struct damon_ctx *ctx,
 	last_addr = r->sampling_addr;
 }
 
-static unsigned int kdamond_check_accesses(struct damon_ctx *ctx)
+static unsigned int kdamond_check_vm_accesses(struct damon_ctx *ctx)
 {
 	struct damon_task *t;
 	struct mm_struct *mm;
@@ -599,12 +603,12 @@ static unsigned int kdamond_check_accesses(struct damon_ctx *ctx)
 		if (!mm)
 			continue;
 		damon_for_each_region(r, t) {
-			damon_check_access(ctx, mm, r);
+			damon_check_vm_access(ctx, mm, r);
 			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
 		}
-
 		mmput(mm);
 	}
+
 	return max_nr_accesses;
 }
 
@@ -1134,13 +1138,13 @@ static int kdamond_fn(void *data)
 	pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
 	ctx->init_target_regions(ctx);
 	while (!kdamond_need_stop(ctx)) {
-		kdamond_prepare_access_checks(ctx);
+		ctx->prepare_access_checks(ctx);
 		if (ctx->sample_cb)
 			ctx->sample_cb(ctx);
 
 		usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
 
-		max_nr_accesses = kdamond_check_accesses(ctx);
+		max_nr_accesses = ctx->check_accesses(ctx);
 
 		if (kdamond_aggregate_interval_passed(ctx)) {
 			kdamond_merge_regions(ctx, max_nr_accesses / 10);
-- 
2.17.1