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

[Ridong Chen <ridong.chen@linux.dev>]

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