[PATCH 0/2] mm/damon/paddr: fix large folios access and schemes handling

[PATCH 0/2] mm/damon/paddr: fix large folios access and schemes handling

[SeongJae Park]

DAMON operations set for physical address space, namely 'paddr', treats
tail pages as unaccessed always.  It can also apply DAMOS action to
a large folio multiple times within single DAMOS' regions walking.  As a
result, the monitoring output has poor quality and DAMOS works in
unexpected ways when large folios are being used.  Fix those.

The patches were parts of Usama's hugepage_size DAMOS filter patch
series[1].  The first fix has collected from there with a slight commit
message change for the subject prefix.  The second fix is re-written by
SJ and posted as an RFC before this series.  The second one also got a
slight commit message change for the subject prefix.

[1] https://lore.kernel.org/20250203225604.44742-1-usamaarif642@gmail.com
[2] https://lore.kernel.org/20250206231103.38298-1-sj@kernel.org

SeongJae Park (1):
  mm/damon: avoid applying DAMOS action to same entity multiple times

Usama Arif (1):
  mm/damon/ops: have damon_get_folio return folio even for tail pages

 include/linux/damon.h | 11 +++++++++
 mm/damon/core.c       |  1 +
 mm/damon/ops-common.c |  2 +-
 mm/damon/paddr.c      | 57 +++++++++++++++++++++++++++++++------------
 4 files changed, 55 insertions(+), 16 deletions(-)


base-commit: 9c9a75a50e600803a157f4fc76cb856326406ce4
-- 
2.39.5

[PATCH 1/2] mm/damon/ops: have damon_get_folio return folio even for tail pages

[SeongJae Park]

From: Usama Arif <usamaarif642@gmail.com>

This effectively adds support for large folios in damon for paddr,
as damon_pa_mkold/young won't get a null folio from this function
and won't ignore it, hence access will be checked and reported.
This also means that larger folios will be considered for
different DAMOS actions like pageout, prioritization and migration.
As these DAMOS actions will consider larger folios, iterate through
the region at folio_size and not PAGE_SIZE intervals.
This should not have an affect on vaddr, as damon_young_pmd_entry
considers pmd entries.

Fixes: a28397beb55b ("mm/damon: implement primitives for physical address space monitoring")
Cc: <stable@vger.kernel.org>
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: SeongJae Park <sj@kernel.org>
---
 mm/damon/ops-common.c |  2 +-
 mm/damon/paddr.c      | 24 ++++++++++++++++++------
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/mm/damon/ops-common.c b/mm/damon/ops-common.c
index d25d99cb5f2b..d511be201c4c 100644
--- a/mm/damon/ops-common.c
+++ b/mm/damon/ops-common.c
@@ -24,7 +24,7 @@ struct folio *damon_get_folio(unsigned long pfn)
 	struct page *page = pfn_to_online_page(pfn);
 	struct folio *folio;
 
-	if (!page || PageTail(page))
+	if (!page)
 		return NULL;
 
 	folio = page_folio(page);
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 0f9ae14f884d..0fb61f6ddb8d 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -266,11 +266,14 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
 		damos_add_filter(s, filter);
 	}
 
-	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
+	addr = r->ar.start;
+	while (addr < r->ar.end) {
 		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
 
-		if (!folio)
+		if (!folio) {
+			addr += PAGE_SIZE;
 			continue;
+		}
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
@@ -286,6 +289,7 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
 		else
 			list_add(&folio->lru, &folio_list);
 put_folio:
+		addr += folio_size(folio);
 		folio_put(folio);
 	}
 	if (install_young_filter)
@@ -301,11 +305,14 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 {
 	unsigned long addr, applied = 0;
 
-	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
+	addr = r->ar.start;
+	while (addr < r->ar.end) {
 		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
 
-		if (!folio)
+		if (!folio) {
+			addr += PAGE_SIZE;
 			continue;
+		}
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
@@ -318,6 +325,7 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 			folio_deactivate(folio);
 		applied += folio_nr_pages(folio);
 put_folio:
+		addr += folio_size(folio);
 		folio_put(folio);
 	}
 	return applied * PAGE_SIZE;
@@ -464,11 +472,14 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s,
 	unsigned long addr, applied;
 	LIST_HEAD(folio_list);
 
-	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
+	addr = r->ar.start;
+	while (addr < r->ar.end) {
 		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
 
-		if (!folio)
+		if (!folio) {
+			addr += PAGE_SIZE;
 			continue;
+		}
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
@@ -479,6 +490,7 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s,
 			goto put_folio;
 		list_add(&folio->lru, &folio_list);
 put_folio:
+		addr += folio_size(folio);
 		folio_put(folio);
 	}
 	applied = damon_pa_migrate_pages(&folio_list, s->target_nid);
-- 
2.39.5

[PATCH 2/2] mm/damon: avoid applying DAMOS action to same entity multiple times

[SeongJae Park]

'paddr' DAMON operations set can apply a DAMOS scheme's action to a
large folio multiple times in single DAMOS-regions-walk if the folio is
laid on multiple DAMON regions.  Add a field for DAMOS scheme object
that can be used by the underlying ops to know what was the last entity
that the scheme's action has applied.  The core layer unsets the field
when each DAMOS-regions-walk is done for the given scheme.  And update
'paddr' ops to use the infrastructure to avoid the problem.

Fixes: 57223ac29584 ("mm/damon/paddr: support the pageout scheme")
Cc: <stable@vger.kernel.org>
Reported-by: Usama Arif <usamaarif642@gmail.com>
Closes: https://lore.kernel.org/20250203225604.44742-3-usamaarif642@gmail.com
Signed-off-by: SeongJae Park <sj@kernel.org>
---
 include/linux/damon.h | 11 +++++++++++
 mm/damon/core.c       |  1 +
 mm/damon/paddr.c      | 39 +++++++++++++++++++++++++++------------
 3 files changed, 39 insertions(+), 12 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index af525252b853..a390af84cf0f 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -432,6 +432,7 @@ struct damos_access_pattern {
  * @wmarks:		Watermarks for automated (in)activation of this scheme.
  * @target_nid:		Destination node if @action is "migrate_{hot,cold}".
  * @filters:		Additional set of &struct damos_filter for &action.
+ * @last_applied:	Last @action applied ops-managing entity.
  * @stat:		Statistics of this scheme.
  * @list:		List head for siblings.
  *
@@ -454,6 +455,15 @@ struct damos_access_pattern {
  * implementation could check pages of the region and skip &action to respect
  * &filters
  *
+ * The minimum entity that @action can be applied depends on the underlying
+ * &struct damon_operations.  Since it may not be aligned with the core layer
+ * abstract, namely &struct damon_region, &struct damon_operations could apply
+ * @action to same entity multiple times.  Large folios that underlying on
+ * multiple &struct damon region objects could be such examples.  The &struct
+ * damon_operations can use @last_applied to avoid that.  DAMOS core logic
+ * unsets @last_applied when each regions walking for applying the scheme is
+ * finished.
+ *
  * After applying the &action to each region, &stat_count and &stat_sz is
  * updated to reflect the number of regions and total size of regions that the
  * &action is applied.
@@ -477,6 +487,7 @@ struct damos {
 		int target_nid;
 	};
 	struct list_head filters;
+	void *last_applied;
 	struct damos_stat stat;
 	struct list_head list;
 };
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c7b981308862..1a4dd644949b 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1851,6 +1851,7 @@ static void kdamond_apply_schemes(struct damon_ctx *c)
 		s->next_apply_sis = c->passed_sample_intervals +
 			(s->apply_interval_us ? s->apply_interval_us :
 			 c->attrs.aggr_interval) / sample_interval;
+		s->last_applied = NULL;
 	}
 }
 
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 0fb61f6ddb8d..d64c6fe28667 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -243,6 +243,17 @@ static bool damos_pa_filter_out(struct damos *scheme, struct folio *folio)
 	return false;
 }
 
+static bool damon_pa_invalid_damos_folio(struct folio *folio, struct damos *s)
+{
+	if (!folio)
+		return true;
+	if (folio == s->last_applied) {
+		folio_put(folio);
+		return true;
+	}
+	return false;
+}
+
 static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
 		unsigned long *sz_filter_passed)
 {
@@ -250,6 +261,7 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
 	LIST_HEAD(folio_list);
 	bool install_young_filter = true;
 	struct damos_filter *filter;
+	struct folio *folio;
 
 	/* check access in page level again by default */
 	damos_for_each_filter(filter, s) {
@@ -268,9 +280,8 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
 
 	addr = r->ar.start;
 	while (addr < r->ar.end) {
-		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
-
-		if (!folio) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
 			addr += PAGE_SIZE;
 			continue;
 		}
@@ -296,6 +307,7 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s,
 		damos_destroy_filter(filter);
 	applied = reclaim_pages(&folio_list);
 	cond_resched();
+	s->last_applied = folio;
 	return applied * PAGE_SIZE;
 }
 
@@ -304,12 +316,12 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 		unsigned long *sz_filter_passed)
 {
 	unsigned long addr, applied = 0;
+	struct folio *folio;
 
 	addr = r->ar.start;
 	while (addr < r->ar.end) {
-		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
-
-		if (!folio) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
 			addr += PAGE_SIZE;
 			continue;
 		}
@@ -328,6 +340,7 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 		addr += folio_size(folio);
 		folio_put(folio);
 	}
+	s->last_applied = folio;
 	return applied * PAGE_SIZE;
 }
 
@@ -471,12 +484,12 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s,
 {
 	unsigned long addr, applied;
 	LIST_HEAD(folio_list);
+	struct folio *folio;
 
 	addr = r->ar.start;
 	while (addr < r->ar.end) {
-		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
-
-		if (!folio) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
 			addr += PAGE_SIZE;
 			continue;
 		}
@@ -495,6 +508,7 @@ static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s,
 	}
 	applied = damon_pa_migrate_pages(&folio_list, s->target_nid);
 	cond_resched();
+	s->last_applied = folio;
 	return applied * PAGE_SIZE;
 }
 
@@ -512,15 +526,15 @@ static unsigned long damon_pa_stat(struct damon_region *r, struct damos *s,
 {
 	unsigned long addr;
 	LIST_HEAD(folio_list);
+	struct folio *folio;
 
 	if (!damon_pa_scheme_has_filter(s))
 		return 0;
 
 	addr = r->ar.start;
 	while (addr < r->ar.end) {
-		struct folio *folio = damon_get_folio(PHYS_PFN(addr));
-
-		if (!folio) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
 			addr += PAGE_SIZE;
 			continue;
 		}
@@ -530,6 +544,7 @@ static unsigned long damon_pa_stat(struct damon_region *r, struct damos *s,
 		addr += folio_size(folio);
 		folio_put(folio);
 	}
+	s->last_applied = folio;
 	return 0;
 }
 
-- 
2.39.5