[PATCH RFC 0/4] mm/vmscan: move vmscan tracepoints to a local header

[PATCH RFC 0/4] mm/vmscan: move vmscan tracepoints to a local header

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

Background:

This series started as an effort to add two tracepoints for MGLRU. In the
discussion, Steven suggested moving include/trace/events/vmscan.h to
mm/trace_vmscan.h [1], as several other subsystems already do. Once the
header lives under mm/, struct scan_control can be moved there too, letting
the trace events access its fields directly instead of having each callsite
copy the scalars out by hand.

The series builds in four small steps:

  1) drop the now-unused vmscan trace include from memcontrol.c;
  2) move include/trace/events/vmscan.h to mm/trace_vmscan.h, using a
     relative TRACE_INCLUDE_PATH so no Makefile change is needed;
  3) move struct scan_control into that header, guarded against the
     multi-read that define_trace.h performs;
  4) pass scan_control to the reclaim-begin tracepoints and pick the
     fields out in TP_fast_assign.

There is no functional change and no ABI change: TP_STRUCT__entry and
TP_printk are untouched, so the exported event format is identical. This
was confirmed by diffing the tracefs format files before and after, and
by capturing the direct/memcg/node reclaim-begin events under load in a
QEMU guest (order, gfp_flags and memcg_id all match).

This RFC only converts the three reclaim-begin tracepoints
(direct/memcg/node) to take a scan_control pointer as a first,
self-contained step. Other vmscan tracepoints that currently spell out
individual sc->... fields can be converted the same way once the approach
is agreed upon; 

[1] https://lore.kernel.org/linux-mm/20260916095122.50cbb620@robin/

Ridong Chen (4):
  mm/memcontrol: drop unused vmscan tracepoint include
  mm/vmscan: move vmscan tracepoints to a local header
  mm/vmscan: move struct scan_control to the local trace header
  mm/vmscan: pass scan_control to the reclaim-begin tracepoints

 MAINTAINERS                                   |   2 +
 mm/memcontrol.c                               |   2 -
 mm/shrinker.c                                 |   2 +-
 .../events/vmscan.h => mm/trace_vmscan.h      | 143 ++++++++++++++++--
 mm/vmscan.c                                   | 117 +-------------
 5 files changed, 138 insertions(+), 128 deletions(-)
 rename include/trace/events/vmscan.h => mm/trace_vmscan.h (81%)

-- 
2.34.1

[PATCH RFC 1/4] mm/memcontrol: drop unused vmscan tracepoint include

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

memcontrol.c includes <trace/events/vmscan.h> but does not use any of
the tracepoints or macros it defines: all tracepoints invoked here come
from memcg.h and writeback.h.  Removing the include still compiles
cleanly.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/memcontrol.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4d00748c8a5b..2a98c5ca46a6 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -77,8 +77,6 @@
 #include <trace/events/memcg.h>
 #undef CREATE_TRACE_POINTS
 
-#include <trace/events/vmscan.h>
-
 struct cgroup_subsys memory_cgrp_subsys __read_mostly;
 EXPORT_SYMBOL(memory_cgrp_subsys);
 
-- 
2.34.1

[PATCH RFC 2/4] mm/vmscan: move vmscan tracepoints to a local header

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

Move include/trace/events/vmscan.h to mm/trace_vmscan.h so that the
tracepoints can be extended to reference vmscan-internal structures such
as struct scan_control, which is not visible outside mm/.  This mirrors
what several other subsystems already do with their trace headers (e.g.
fs/ext2, kernel/trace/trace_benchmark).

No functional change.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 MAINTAINERS                                        | 2 ++
 mm/shrinker.c                                      | 2 +-
 include/trace/events/vmscan.h => mm/trace_vmscan.h | 4 ++++
 mm/vmscan.c                                        | 2 +-
 4 files changed, 8 insertions(+), 2 deletions(-)
 rename include/trace/events/vmscan.h => mm/trace_vmscan.h (99%)

diff --git a/MAINTAINERS b/MAINTAINERS
index e26b963d4001..c1dbb35273c4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17227,6 +17227,7 @@ F:	Documentation/admin-guide/mm/multigen_lru.rst
 F:	Documentation/mm/multigen_lru.rst
 F:	include/linux/mm_inline.h
 F:	include/linux/mmzone.h
+F:	mm/trace_vmscan.h
 F:	mm/vmscan.c
 F:	mm/workingset.c
 
@@ -17374,6 +17375,7 @@ R:	Shakeel Butt <shakeel.butt@linux.dev>
 R:	Lorenzo Stoakes <ljs@kernel.org>
 L:	linux-mm@kvack.org
 S:	Maintained
+F:	mm/trace_vmscan.h
 F:	mm/vmscan.c
 F:	mm/workingset.c
 
diff --git a/mm/shrinker.c b/mm/shrinker.c
index 7ec2a9704f6f..3c3e87c4b61c 100644
--- a/mm/shrinker.c
+++ b/mm/shrinker.c
@@ -3,7 +3,7 @@
 #include <linux/rwsem.h>
 #include <linux/shrinker.h>
 #include <linux/rculist.h>
-#include <trace/events/vmscan.h>
+#include "trace_vmscan.h"
 
 #include "internal.h"
 
diff --git a/include/trace/events/vmscan.h b/mm/trace_vmscan.h
similarity index 99%
rename from include/trace/events/vmscan.h
rename to mm/trace_vmscan.h
index 8a872990b4be..c5d824fef554 100644
--- a/include/trace/events/vmscan.h
+++ b/mm/trace_vmscan.h
@@ -648,4 +648,8 @@ TRACE_EVENT(mm_vmscan_kswapd_clear_hopeless,
 #endif /* _TRACE_VMSCAN_H */
 
 /* This part must be outside protection */
+#undef TRACE_INCLUDE_FILE
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../mm
+#define TRACE_INCLUDE_FILE trace_vmscan
 #include <trace/define_trace.h>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 91295070ca33..0eb7fa8e1d43 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -71,7 +71,7 @@
 #include "swap.h"
 
 #define CREATE_TRACE_POINTS
-#include <trace/events/vmscan.h>
+#include "trace_vmscan.h"
 
 struct scan_control {
 	/* How many pages shrink_list() should reclaim */
-- 
2.34.1

[PATCH RFC 3/4] mm/vmscan: move struct scan_control to the local trace header

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

Now that the vmscan tracepoints live in mm/trace_vmscan.h, move
struct scan_control there as well so the trace events can reference
reclaim-internal state directly. The definition is wrapped in its own
include guard because the trace header is re-read under
TRACE_HEADER_MULTI_READ, while a C struct may only be defined once.

No functional change.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/trace_vmscan.h | 115 ++++++++++++++++++++++++++++++++++++++++++++++
 mm/vmscan.c       | 108 -------------------------------------------
 2 files changed, 115 insertions(+), 108 deletions(-)

diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
index c5d824fef554..c8ac5d4e4043 100644
--- a/mm/trace_vmscan.h
+++ b/mm/trace_vmscan.h
@@ -9,8 +9,123 @@
 #include <linux/tracepoint.h>
 #include <linux/mm.h>
 #include <linux/memcontrol.h>
+#include <linux/swap.h>
 #include <trace/events/mmflags.h>
 
+/* Guard the struct against define_trace.h's repeated inclusion. */
+#ifndef _MM_VMSCAN_INTERNAL_H
+#define _MM_VMSCAN_INTERNAL_H
+
+struct scan_control {
+	/* How many pages shrink_list() should reclaim */
+	unsigned long nr_to_reclaim;
+
+	/*
+	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
+	 * are scanned.
+	 */
+	const nodemask_t *nodemask;
+
+	/*
+	 * The memory cgroup that hit its limit and as a result is the
+	 * primary target of this reclaim invocation.
+	 */
+	struct mem_cgroup *target_mem_cgroup;
+
+	/*
+	 * Scan pressure balancing between anon and file LRUs
+	 */
+	unsigned long	anon_cost;
+	unsigned long	file_cost;
+
+	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
+	int *proactive_swappiness;
+
+	/* Can active folios be deactivated as part of reclaim? */
+#define DEACTIVATE_ANON 1
+#define DEACTIVATE_FILE 2
+	unsigned int may_deactivate:2;
+	unsigned int force_deactivate:1;
+	unsigned int skipped_deactivate:1;
+
+	/* zone_reclaim_mode, boost reclaim */
+	unsigned int may_writepage:1;
+
+	/* zone_reclaim_mode */
+	unsigned int may_unmap:1;
+
+	/* zone_reclaim_mode, boost reclaim, cgroup restrictions */
+	unsigned int may_swap:1;
+
+	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
+	unsigned int no_cache_trim_mode:1;
+
+	/* Has cache_trim_mode failed at least once? */
+	unsigned int cache_trim_mode_failed:1;
+
+	/* Proactive reclaim invoked by userspace */
+	unsigned int proactive:1;
+
+	/*
+	 * Cgroup memory below memory.low is protected as long as we
+	 * don't threaten to OOM. If any cgroup is reclaimed at
+	 * reduced force or passed over entirely due to its memory.low
+	 * setting (memcg_low_skipped), and nothing is reclaimed as a
+	 * result, then go back for one more cycle that reclaims the protected
+	 * memory (memcg_low_reclaim) to avert OOM.
+	 */
+	unsigned int memcg_low_reclaim:1;
+	unsigned int memcg_low_skipped:1;
+
+	/* Shared cgroup tree walk failed, rescan the whole tree */
+	unsigned int memcg_full_walk:1;
+
+	unsigned int hibernation_mode:1;
+
+	/* One of the zones is ready for compaction */
+	unsigned int compaction_ready:1;
+
+	/* There is easily reclaimable cold cache in the current node */
+	unsigned int cache_trim_mode:1;
+
+	/* The file folios on the current node are dangerously low */
+	unsigned int file_is_tiny:1;
+
+	/* Always discard instead of demoting to lower tier memory */
+	unsigned int no_demotion:1;
+
+	/* Allocation order */
+	s8 order;
+
+	/* Scan (total_size >> priority) pages at once */
+	s8 priority;
+
+	/* The highest zone to isolate folios for reclaim from */
+	s8 reclaim_idx;
+
+	/* This context's GFP mask */
+	gfp_t gfp_mask;
+
+	/* Incremented by the number of inactive pages that were scanned */
+	unsigned long nr_scanned;
+
+	/* Number of pages freed so far during a call to shrink_zones() */
+	unsigned long nr_reclaimed;
+
+	struct {
+		unsigned int dirty;
+		unsigned int congested;
+		unsigned int writeback;
+		unsigned int immediate;
+		unsigned int taken;
+	} nr;
+
+	/* for recording the reclaimed slab by now */
+	struct reclaim_state reclaim_state;
+};
+
+#endif /* _MM_VMSCAN_INTERNAL_H */
+
 #define RECLAIM_WB_ANON		0x0001u
 #define RECLAIM_WB_FILE		0x0002u
 #define RECLAIM_WB_MIXED	0x0010u
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0eb7fa8e1d43..2fd9b42f89d8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -73,114 +73,6 @@
 #define CREATE_TRACE_POINTS
 #include "trace_vmscan.h"
 
-struct scan_control {
-	/* How many pages shrink_list() should reclaim */
-	unsigned long nr_to_reclaim;
-
-	/*
-	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
-	 * are scanned.
-	 */
-	const nodemask_t *nodemask;
-
-	/*
-	 * The memory cgroup that hit its limit and as a result is the
-	 * primary target of this reclaim invocation.
-	 */
-	struct mem_cgroup *target_mem_cgroup;
-
-	/*
-	 * Scan pressure balancing between anon and file LRUs
-	 */
-	unsigned long	anon_cost;
-	unsigned long	file_cost;
-
-	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
-	int *proactive_swappiness;
-
-	/* Can active folios be deactivated as part of reclaim? */
-#define DEACTIVATE_ANON 1
-#define DEACTIVATE_FILE 2
-	unsigned int may_deactivate:2;
-	unsigned int force_deactivate:1;
-	unsigned int skipped_deactivate:1;
-
-	/* zone_reclaim_mode, boost reclaim */
-	unsigned int may_writepage:1;
-
-	/* zone_reclaim_mode */
-	unsigned int may_unmap:1;
-
-	/* zone_reclaim_mode, boost reclaim, cgroup restrictions */
-	unsigned int may_swap:1;
-
-	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
-	unsigned int no_cache_trim_mode:1;
-
-	/* Has cache_trim_mode failed at least once? */
-	unsigned int cache_trim_mode_failed:1;
-
-	/* Proactive reclaim invoked by userspace */
-	unsigned int proactive:1;
-
-	/*
-	 * Cgroup memory below memory.low is protected as long as we
-	 * don't threaten to OOM. If any cgroup is reclaimed at
-	 * reduced force or passed over entirely due to its memory.low
-	 * setting (memcg_low_skipped), and nothing is reclaimed as a
-	 * result, then go back for one more cycle that reclaims the protected
-	 * memory (memcg_low_reclaim) to avert OOM.
-	 */
-	unsigned int memcg_low_reclaim:1;
-	unsigned int memcg_low_skipped:1;
-
-	/* Shared cgroup tree walk failed, rescan the whole tree */
-	unsigned int memcg_full_walk:1;
-
-	unsigned int hibernation_mode:1;
-
-	/* One of the zones is ready for compaction */
-	unsigned int compaction_ready:1;
-
-	/* There is easily reclaimable cold cache in the current node */
-	unsigned int cache_trim_mode:1;
-
-	/* The file folios on the current node are dangerously low */
-	unsigned int file_is_tiny:1;
-
-	/* Always discard instead of demoting to lower tier memory */
-	unsigned int no_demotion:1;
-
-	/* Allocation order */
-	s8 order;
-
-	/* Scan (total_size >> priority) pages at once */
-	s8 priority;
-
-	/* The highest zone to isolate folios for reclaim from */
-	s8 reclaim_idx;
-
-	/* This context's GFP mask */
-	gfp_t gfp_mask;
-
-	/* Incremented by the number of inactive pages that were scanned */
-	unsigned long nr_scanned;
-
-	/* Number of pages freed so far during a call to shrink_zones() */
-	unsigned long nr_reclaimed;
-
-	struct {
-		unsigned int dirty;
-		unsigned int congested;
-		unsigned int writeback;
-		unsigned int immediate;
-		unsigned int taken;
-	} nr;
-
-	/* for recording the reclaimed slab by now */
-	struct reclaim_state reclaim_state;
-};
-
 #ifdef ARCH_HAS_PREFETCHW
 static inline void prefetchw_prev_lru_folio(struct folio *folio,
 		struct list_head *base)
-- 
2.34.1

[PATCH RFC 4/4] mm/vmscan: pass scan_control to the reclaim-begin tracepoints

[Ridong Chen]

From: Ridong Chen <chenridong@xiaomi.com>

The reclaim-begin tracepoints describe the entry conditions of a reclaim
invocation, which struct scan_control already carries. Now that the struct
is visible from the trace header, pass sc directly and pick the fields out
in TP_fast_assign instead of spelling out gfp_mask and order at every
callsite. The exported event format is unchanged.

No functional change.

Assisted-by: Claude:claude-opus-4-8
Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
---
 mm/trace_vmscan.h | 24 ++++++++++++------------
 mm/vmscan.c       |  7 +++----
 2 files changed, 15 insertions(+), 16 deletions(-)

diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
index c8ac5d4e4043..c9f16267c0a2 100644
--- a/mm/trace_vmscan.h
+++ b/mm/trace_vmscan.h
@@ -291,9 +291,9 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 
-	TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
+	TP_PROTO(struct scan_control *sc, struct mem_cgroup *memcg),
 
-	TP_ARGS(gfp_flags, order, memcg),
+	TP_ARGS(sc, memcg),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	gfp_flags	)
@@ -302,8 +302,8 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 	),
 
 	TP_fast_assign(
-		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
-		__entry->order		= order;
+		__entry->gfp_flags	= (__force unsigned long)sc->gfp_mask;
+		__entry->order		= sc->order;
 		__entry->memcg_id	= mem_cgroup_id(memcg);
 	),
 
@@ -317,17 +317,17 @@ DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
 
-	TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
+	TP_PROTO(struct scan_control *sc, struct mem_cgroup *memcg),
 
-	TP_ARGS(gfp_flags, order, memcg)
+	TP_ARGS(sc, memcg)
 );
 
 #ifdef CONFIG_MEMCG
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
 
-	TP_PROTO(gfp_t gfp_flags, int order, struct mem_cgroup *memcg),
+	TP_PROTO(struct scan_control *sc, struct mem_cgroup *memcg),
 
-	TP_ARGS(gfp_flags, order, memcg)
+	TP_ARGS(sc, memcg)
 );
 #endif /* CONFIG_MEMCG */
 
@@ -664,9 +664,9 @@ TRACE_EVENT(mm_vmscan_lru_shrink_active,
 
 TRACE_EVENT(mm_vmscan_node_reclaim_begin,
 
-	TP_PROTO(int nid, int order, gfp_t gfp_flags),
+	TP_PROTO(int nid, struct scan_control *sc),
 
-	TP_ARGS(nid, order, gfp_flags),
+	TP_ARGS(nid, sc),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
@@ -676,8 +676,8 @@ TRACE_EVENT(mm_vmscan_node_reclaim_begin,
 
 	TP_fast_assign(
 		__entry->nid = nid;
-		__entry->order = order;
-		__entry->gfp_flags = (__force unsigned long)gfp_flags;
+		__entry->order = sc->order;
+		__entry->gfp_flags = (__force unsigned long)sc->gfp_mask;
 	),
 
 	TP_printk("nid=%d order=%d gfp_flags=%s",
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2fd9b42f89d8..2fed83738b4b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6885,7 +6885,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		return 1;
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
-	trace_mm_vmscan_direct_reclaim_begin(sc.gfp_mask, order, NULL);
+	trace_mm_vmscan_direct_reclaim_begin(&sc, NULL);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
@@ -6926,7 +6926,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 	struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
 
 	set_task_reclaim_state(current, &sc.reclaim_state);
-	trace_mm_vmscan_memcg_reclaim_begin(sc.gfp_mask, 0, memcg);
+	trace_mm_vmscan_memcg_reclaim_begin(&sc, memcg);
 	noreclaim_flag = memalloc_noreclaim_save();
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
@@ -7882,8 +7882,7 @@ static unsigned long __node_reclaim(struct pglist_data *pgdat,
 	unsigned int noreclaim_flag;
 	unsigned long pflags;
 
-	trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, sc->order,
-					   sc->gfp_mask);
+	trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, sc);
 
 	cond_resched();
 	psi_memstall_enter(&pflags);
-- 
2.34.1

Re: [PATCH RFC 3/4] mm/vmscan: move struct scan_control to the local trace header

[Baoquan He]

On 09/21/26 at 07:46pm, Ridong Chen wrote:
> From: Ridong Chen <chenridong@xiaomi.com>
> 
> Now that the vmscan tracepoints live in mm/trace_vmscan.h, move
> struct scan_control there as well so the trace events can reference
> reclaim-internal state directly. The definition is wrapped in its own
> include guard because the trace header is re-read under
> TRACE_HEADER_MULTI_READ, while a C struct may only be defined once.
> 
> No functional change.
> 
> Assisted-by: Claude:claude-opus-4-8
> Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
> ---
>  mm/trace_vmscan.h | 115 ++++++++++++++++++++++++++++++++++++++++++++++
>  mm/vmscan.c       | 108 -------------------------------------------
>  2 files changed, 115 insertions(+), 108 deletions(-)
> 
> diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
> index c5d824fef554..c8ac5d4e4043 100644
> --- a/mm/trace_vmscan.h
> +++ b/mm/trace_vmscan.h

This looks not good, I would rather see it's added in mm/internal.h, or
a new mm/vmscan.h. Putting scan_control in mm/trace_vmscan.h is too weird.

> @@ -9,8 +9,123 @@
>  #include <linux/tracepoint.h>
>  #include <linux/mm.h>
>  #include <linux/memcontrol.h>
> +#include <linux/swap.h>
>  #include <trace/events/mmflags.h>
>  
> +/* Guard the struct against define_trace.h's repeated inclusion. */
> +#ifndef _MM_VMSCAN_INTERNAL_H
> +#define _MM_VMSCAN_INTERNAL_H
> +
> +struct scan_control {
> +	/* How many pages shrink_list() should reclaim */
> +	unsigned long nr_to_reclaim;
> +
> +	/*
> +	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
> +	 * are scanned.
> +	 */
> +	const nodemask_t *nodemask;
> +
> +	/*
> +	 * The memory cgroup that hit its limit and as a result is the
> +	 * primary target of this reclaim invocation.
> +	 */
> +	struct mem_cgroup *target_mem_cgroup;
> +
> +	/*
> +	 * Scan pressure balancing between anon and file LRUs
> +	 */
> +	unsigned long	anon_cost;
> +	unsigned long	file_cost;
> +
> +	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
> +	int *proactive_swappiness;
> +
> +	/* Can active folios be deactivated as part of reclaim? */
> +#define DEACTIVATE_ANON 1
> +#define DEACTIVATE_FILE 2
> +	unsigned int may_deactivate:2;
> +	unsigned int force_deactivate:1;
> +	unsigned int skipped_deactivate:1;
> +
> +	/* zone_reclaim_mode, boost reclaim */
> +	unsigned int may_writepage:1;
> +
> +	/* zone_reclaim_mode */
> +	unsigned int may_unmap:1;
> +
> +	/* zone_reclaim_mode, boost reclaim, cgroup restrictions */
> +	unsigned int may_swap:1;
> +
> +	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
> +	unsigned int no_cache_trim_mode:1;
> +
> +	/* Has cache_trim_mode failed at least once? */
> +	unsigned int cache_trim_mode_failed:1;
> +
> +	/* Proactive reclaim invoked by userspace */
> +	unsigned int proactive:1;
> +
> +	/*
> +	 * Cgroup memory below memory.low is protected as long as we
> +	 * don't threaten to OOM. If any cgroup is reclaimed at
> +	 * reduced force or passed over entirely due to its memory.low
> +	 * setting (memcg_low_skipped), and nothing is reclaimed as a
> +	 * result, then go back for one more cycle that reclaims the protected
> +	 * memory (memcg_low_reclaim) to avert OOM.
> +	 */
> +	unsigned int memcg_low_reclaim:1;
> +	unsigned int memcg_low_skipped:1;
> +
> +	/* Shared cgroup tree walk failed, rescan the whole tree */
> +	unsigned int memcg_full_walk:1;
> +
> +	unsigned int hibernation_mode:1;
> +
> +	/* One of the zones is ready for compaction */
> +	unsigned int compaction_ready:1;
> +
> +	/* There is easily reclaimable cold cache in the current node */
> +	unsigned int cache_trim_mode:1;
> +
> +	/* The file folios on the current node are dangerously low */
> +	unsigned int file_is_tiny:1;
> +
> +	/* Always discard instead of demoting to lower tier memory */
> +	unsigned int no_demotion:1;
> +
> +	/* Allocation order */
> +	s8 order;
> +
> +	/* Scan (total_size >> priority) pages at once */
> +	s8 priority;
> +
> +	/* The highest zone to isolate folios for reclaim from */
> +	s8 reclaim_idx;
> +
> +	/* This context's GFP mask */
> +	gfp_t gfp_mask;
> +
> +	/* Incremented by the number of inactive pages that were scanned */
> +	unsigned long nr_scanned;
> +
> +	/* Number of pages freed so far during a call to shrink_zones() */
> +	unsigned long nr_reclaimed;
> +
> +	struct {
> +		unsigned int dirty;
> +		unsigned int congested;
> +		unsigned int writeback;
> +		unsigned int immediate;
> +		unsigned int taken;
> +	} nr;
> +
> +	/* for recording the reclaimed slab by now */
> +	struct reclaim_state reclaim_state;
> +};
> +
> +#endif /* _MM_VMSCAN_INTERNAL_H */
> +
>  #define RECLAIM_WB_ANON		0x0001u
>  #define RECLAIM_WB_FILE		0x0002u
>  #define RECLAIM_WB_MIXED	0x0010u
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 0eb7fa8e1d43..2fd9b42f89d8 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -73,114 +73,6 @@
>  #define CREATE_TRACE_POINTS
>  #include "trace_vmscan.h"
>  
> -struct scan_control {
> -	/* How many pages shrink_list() should reclaim */
> -	unsigned long nr_to_reclaim;
> -
> -	/*
> -	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
> -	 * are scanned.
> -	 */
> -	const nodemask_t *nodemask;
> -
> -	/*
> -	 * The memory cgroup that hit its limit and as a result is the
> -	 * primary target of this reclaim invocation.
> -	 */
> -	struct mem_cgroup *target_mem_cgroup;
> -
> -	/*
> -	 * Scan pressure balancing between anon and file LRUs
> -	 */
> -	unsigned long	anon_cost;
> -	unsigned long	file_cost;
> -
> -	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
> -	int *proactive_swappiness;
> -
> -	/* Can active folios be deactivated as part of reclaim? */
> -#define DEACTIVATE_ANON 1
> -#define DEACTIVATE_FILE 2
> -	unsigned int may_deactivate:2;
> -	unsigned int force_deactivate:1;
> -	unsigned int skipped_deactivate:1;
> -
> -	/* zone_reclaim_mode, boost reclaim */
> -	unsigned int may_writepage:1;
> -
> -	/* zone_reclaim_mode */
> -	unsigned int may_unmap:1;
> -
> -	/* zone_reclaim_mode, boost reclaim, cgroup restrictions */
> -	unsigned int may_swap:1;
> -
> -	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
> -	unsigned int no_cache_trim_mode:1;
> -
> -	/* Has cache_trim_mode failed at least once? */
> -	unsigned int cache_trim_mode_failed:1;
> -
> -	/* Proactive reclaim invoked by userspace */
> -	unsigned int proactive:1;
> -
> -	/*
> -	 * Cgroup memory below memory.low is protected as long as we
> -	 * don't threaten to OOM. If any cgroup is reclaimed at
> -	 * reduced force or passed over entirely due to its memory.low
> -	 * setting (memcg_low_skipped), and nothing is reclaimed as a
> -	 * result, then go back for one more cycle that reclaims the protected
> -	 * memory (memcg_low_reclaim) to avert OOM.
> -	 */
> -	unsigned int memcg_low_reclaim:1;
> -	unsigned int memcg_low_skipped:1;
> -
> -	/* Shared cgroup tree walk failed, rescan the whole tree */
> -	unsigned int memcg_full_walk:1;
> -
> -	unsigned int hibernation_mode:1;
> -
> -	/* One of the zones is ready for compaction */
> -	unsigned int compaction_ready:1;
> -
> -	/* There is easily reclaimable cold cache in the current node */
> -	unsigned int cache_trim_mode:1;
> -
> -	/* The file folios on the current node are dangerously low */
> -	unsigned int file_is_tiny:1;
> -
> -	/* Always discard instead of demoting to lower tier memory */
> -	unsigned int no_demotion:1;
> -
> -	/* Allocation order */
> -	s8 order;
> -
> -	/* Scan (total_size >> priority) pages at once */
> -	s8 priority;
> -
> -	/* The highest zone to isolate folios for reclaim from */
> -	s8 reclaim_idx;
> -
> -	/* This context's GFP mask */
> -	gfp_t gfp_mask;
> -
> -	/* Incremented by the number of inactive pages that were scanned */
> -	unsigned long nr_scanned;
> -
> -	/* Number of pages freed so far during a call to shrink_zones() */
> -	unsigned long nr_reclaimed;
> -
> -	struct {
> -		unsigned int dirty;
> -		unsigned int congested;
> -		unsigned int writeback;
> -		unsigned int immediate;
> -		unsigned int taken;
> -	} nr;
> -
> -	/* for recording the reclaimed slab by now */
> -	struct reclaim_state reclaim_state;
> -};
> -
>  #ifdef ARCH_HAS_PREFETCHW
>  static inline void prefetchw_prev_lru_folio(struct folio *folio,
>  		struct list_head *base)
> -- 
> 2.34.1
> 

Re: [PATCH RFC 3/4] mm/vmscan: move struct scan_control to the local trace header

[Ridong Chen]

On 9/22/2026 10:24 AM, Baoquan He wrote:
> On 09/21/26 at 07:46pm, Ridong Chen wrote:
>> From: Ridong Chen <chenridong@xiaomi.com>
>>
>> Now that the vmscan tracepoints live in mm/trace_vmscan.h, move
>> struct scan_control there as well so the trace events can reference
>> reclaim-internal state directly. The definition is wrapped in its own
>> include guard because the trace header is re-read under
>> TRACE_HEADER_MULTI_READ, while a C struct may only be defined once.
>>
>> No functional change.
>>
>> Assisted-by: Claude:claude-opus-4-8
>> Signed-off-by: Ridong Chen <chenridong@xiaomi.com>
>> ---
>>   mm/trace_vmscan.h | 115 ++++++++++++++++++++++++++++++++++++++++++++++
>>   mm/vmscan.c       | 108 -------------------------------------------
>>   2 files changed, 115 insertions(+), 108 deletions(-)
>>
>> diff --git a/mm/trace_vmscan.h b/mm/trace_vmscan.h
>> index c5d824fef554..c8ac5d4e4043 100644
>> --- a/mm/trace_vmscan.h
>> +++ b/mm/trace_vmscan.h
> 
> This looks not good, I would rather see it's added in mm/internal.h, or
> a new mm/vmscan.h. Putting scan_control in mm/trace_vmscan.h is too weird.
> 

Thanks.

I'm not sure whether the maintainers would be happy to make scan_control
external. I'd prefer to move scan_control to a new mm/vmscan.h, since
mm/internal.h is getting larger and larger. So I'd like to hear other
opinions.

>> @@ -9,8 +9,123 @@
>>   #include <linux/tracepoint.h>
>>   #include <linux/mm.h>
>>   #include <linux/memcontrol.h>
>> +#include <linux/swap.h>
>>   #include <trace/events/mmflags.h>
>>   
>> +/* Guard the struct against define_trace.h's repeated inclusion. */
>> +#ifndef _MM_VMSCAN_INTERNAL_H
>> +#define _MM_VMSCAN_INTERNAL_H
>> +
>> +struct scan_control {
>> +	/* How many pages shrink_list() should reclaim */
>> +	unsigned long nr_to_reclaim;
>> +
>> +	/*
>> +	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
>> +	 * are scanned.
>> +	 */
>> +	const nodemask_t *nodemask;
>> +
>> +	/*
>> +	 * The memory cgroup that hit its limit and as a result is the
>> +	 * primary target of this reclaim invocation.
>> +	 */
>> +	struct mem_cgroup *target_mem_cgroup;
>> +
>> +	/*
>> +	 * Scan pressure balancing between anon and file LRUs
>> +	 */
>> +	unsigned long	anon_cost;
>> +	unsigned long	file_cost;
>> +
>> +	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
>> +	int *proactive_swappiness;
>> +
>> +	/* Can active folios be deactivated as part of reclaim? */
>> +#define DEACTIVATE_ANON 1
>> +#define DEACTIVATE_FILE 2
>> +	unsigned int may_deactivate:2;
>> +	unsigned int force_deactivate:1;
>> +	unsigned int skipped_deactivate:1;
>> +
>> +	/* zone_reclaim_mode, boost reclaim */
>> +	unsigned int may_writepage:1;
>> +
>> +	/* zone_reclaim_mode */
>> +	unsigned int may_unmap:1;
>> +
>> +	/* zone_reclaim_mode, boost reclaim, cgroup restrictions */
>> +	unsigned int may_swap:1;
>> +
>> +	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
>> +	unsigned int no_cache_trim_mode:1;
>> +
>> +	/* Has cache_trim_mode failed at least once? */
>> +	unsigned int cache_trim_mode_failed:1;
>> +
>> +	/* Proactive reclaim invoked by userspace */
>> +	unsigned int proactive:1;
>> +
>> +	/*
>> +	 * Cgroup memory below memory.low is protected as long as we
>> +	 * don't threaten to OOM. If any cgroup is reclaimed at
>> +	 * reduced force or passed over entirely due to its memory.low
>> +	 * setting (memcg_low_skipped), and nothing is reclaimed as a
>> +	 * result, then go back for one more cycle that reclaims the protected
>> +	 * memory (memcg_low_reclaim) to avert OOM.
>> +	 */
>> +	unsigned int memcg_low_reclaim:1;
>> +	unsigned int memcg_low_skipped:1;
>> +
>> +	/* Shared cgroup tree walk failed, rescan the whole tree */
>> +	unsigned int memcg_full_walk:1;
>> +
>> +	unsigned int hibernation_mode:1;
>> +
>> +	/* One of the zones is ready for compaction */
>> +	unsigned int compaction_ready:1;
>> +
>> +	/* There is easily reclaimable cold cache in the current node */
>> +	unsigned int cache_trim_mode:1;
>> +
>> +	/* The file folios on the current node are dangerously low */
>> +	unsigned int file_is_tiny:1;
>> +
>> +	/* Always discard instead of demoting to lower tier memory */
>> +	unsigned int no_demotion:1;
>> +
>> +	/* Allocation order */
>> +	s8 order;
>> +
>> +	/* Scan (total_size >> priority) pages at once */
>> +	s8 priority;
>> +
>> +	/* The highest zone to isolate folios for reclaim from */
>> +	s8 reclaim_idx;
>> +
>> +	/* This context's GFP mask */
>> +	gfp_t gfp_mask;
>> +
>> +	/* Incremented by the number of inactive pages that were scanned */
>> +	unsigned long nr_scanned;
>> +
>> +	/* Number of pages freed so far during a call to shrink_zones() */
>> +	unsigned long nr_reclaimed;
>> +
>> +	struct {
>> +		unsigned int dirty;
>> +		unsigned int congested;
>> +		unsigned int writeback;
>> +		unsigned int immediate;
>> +		unsigned int taken;
>> +	} nr;
>> +
>> +	/* for recording the reclaimed slab by now */
>> +	struct reclaim_state reclaim_state;
>> +};
>> +
>> +#endif /* _MM_VMSCAN_INTERNAL_H */
>> +
>>   #define RECLAIM_WB_ANON		0x0001u
>>   #define RECLAIM_WB_FILE		0x0002u
>>   #define RECLAIM_WB_MIXED	0x0010u
>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>> index 0eb7fa8e1d43..2fd9b42f89d8 100644
>> --- a/mm/vmscan.c
>> +++ b/mm/vmscan.c
>> @@ -73,114 +73,6 @@
>>   #define CREATE_TRACE_POINTS
>>   #include "trace_vmscan.h"
>>   
>> -struct scan_control {
>> -	/* How many pages shrink_list() should reclaim */
>> -	unsigned long nr_to_reclaim;
>> -
>> -	/*
>> -	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
>> -	 * are scanned.
>> -	 */
>> -	const nodemask_t *nodemask;
>> -
>> -	/*
>> -	 * The memory cgroup that hit its limit and as a result is the
>> -	 * primary target of this reclaim invocation.
>> -	 */
>> -	struct mem_cgroup *target_mem_cgroup;
>> -
>> -	/*
>> -	 * Scan pressure balancing between anon and file LRUs
>> -	 */
>> -	unsigned long	anon_cost;
>> -	unsigned long	file_cost;
>> -
>> -	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
>> -	int *proactive_swappiness;
>> -
>> -	/* Can active folios be deactivated as part of reclaim? */
>> -#define DEACTIVATE_ANON 1
>> -#define DEACTIVATE_FILE 2
>> -	unsigned int may_deactivate:2;
>> -	unsigned int force_deactivate:1;
>> -	unsigned int skipped_deactivate:1;
>> -
>> -	/* zone_reclaim_mode, boost reclaim */
>> -	unsigned int may_writepage:1;
>> -
>> -	/* zone_reclaim_mode */
>> -	unsigned int may_unmap:1;
>> -
>> -	/* zone_reclaim_mode, boost reclaim, cgroup restrictions */
>> -	unsigned int may_swap:1;
>> -
>> -	/* Not allow cache_trim_mode to be turned on as part of reclaim? */
>> -	unsigned int no_cache_trim_mode:1;
>> -
>> -	/* Has cache_trim_mode failed at least once? */
>> -	unsigned int cache_trim_mode_failed:1;
>> -
>> -	/* Proactive reclaim invoked by userspace */
>> -	unsigned int proactive:1;
>> -
>> -	/*
>> -	 * Cgroup memory below memory.low is protected as long as we
>> -	 * don't threaten to OOM. If any cgroup is reclaimed at
>> -	 * reduced force or passed over entirely due to its memory.low
>> -	 * setting (memcg_low_skipped), and nothing is reclaimed as a
>> -	 * result, then go back for one more cycle that reclaims the protected
>> -	 * memory (memcg_low_reclaim) to avert OOM.
>> -	 */
>> -	unsigned int memcg_low_reclaim:1;
>> -	unsigned int memcg_low_skipped:1;
>> -
>> -	/* Shared cgroup tree walk failed, rescan the whole tree */
>> -	unsigned int memcg_full_walk:1;
>> -
>> -	unsigned int hibernation_mode:1;
>> -
>> -	/* One of the zones is ready for compaction */
>> -	unsigned int compaction_ready:1;
>> -
>> -	/* There is easily reclaimable cold cache in the current node */
>> -	unsigned int cache_trim_mode:1;
>> -
>> -	/* The file folios on the current node are dangerously low */
>> -	unsigned int file_is_tiny:1;
>> -
>> -	/* Always discard instead of demoting to lower tier memory */
>> -	unsigned int no_demotion:1;
>> -
>> -	/* Allocation order */
>> -	s8 order;
>> -
>> -	/* Scan (total_size >> priority) pages at once */
>> -	s8 priority;
>> -
>> -	/* The highest zone to isolate folios for reclaim from */
>> -	s8 reclaim_idx;
>> -
>> -	/* This context's GFP mask */
>> -	gfp_t gfp_mask;
>> -
>> -	/* Incremented by the number of inactive pages that were scanned */
>> -	unsigned long nr_scanned;
>> -
>> -	/* Number of pages freed so far during a call to shrink_zones() */
>> -	unsigned long nr_reclaimed;
>> -
>> -	struct {
>> -		unsigned int dirty;
>> -		unsigned int congested;
>> -		unsigned int writeback;
>> -		unsigned int immediate;
>> -		unsigned int taken;
>> -	} nr;
>> -
>> -	/* for recording the reclaimed slab by now */
>> -	struct reclaim_state reclaim_state;
>> -};
>> -
>>   #ifdef ARCH_HAS_PREFETCHW
>>   static inline void prefetchw_prev_lru_folio(struct folio *folio,
>>   		struct list_head *base)
>> -- 
>> 2.34.1
>>

-- 
Best regards
Ridong