Re: [PATCH v6 2/2] mm/memory_hotplug: improve shrink_zone_span() subsection boundary checks

[David Hildenbrand (Arm)]

On 7/23/26 10:49, Yuan Liu wrote:
> When shrinking a zone span after removing a PFN range,
> find_smallest_section_pfn() and find_biggest_section_pfn()
> only checked one edge PFN in each subsection for nid/zone matching.
> 
> If a memory or hole boundary falls in the middle of a subsection,
> that edge PFN may belong to a different nid/zone, causing the helpers
> to miss a valid PFN within that subsection.
> 
> Fix this by checking both subsection edge PFNs for nid/zone matching.
> Keep a single pfn_to_online_page() check per subsection, since online
> state is the same for all PFNs in a subsection.
> 
> Reviewed-by: Jason Zeng <jason.zeng@xxxxxxxxx>
> Signed-off-by: Yuan Liu <yuan1.liu@xxxxxxxxx>
> ---
>  mm/memory_hotplug.c | 42 +++++++++++++++++++++++++++---------------
>  1 file changed, 27 insertions(+), 15 deletions(-)
> 
> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
> index 4c699fd9c479..3a281d595207 100644
> --- a/mm/memory_hotplug.c
> +++ b/mm/memory_hotplug.c
> @@ -427,17 +427,24 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
>  				     unsigned long start_pfn,
>  				     unsigned long end_pfn)
>  {
> -	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) {
> -		if (unlikely(!pfn_to_online_page(start_pfn)))
> -			continue;
> +	unsigned long next_pfn;
>  
> -		if (unlikely(pfn_to_nid(start_pfn) != nid))
> -			continue;
> +	for (; start_pfn < end_pfn; start_pfn = next_pfn) {
> +		unsigned long tail_pfn;
>  
> -		if (zone != page_zone(pfn_to_page(start_pfn)))
> +		next_pfn = start_pfn + PAGES_PER_SUBSECTION;
> +		tail_pfn = next_pfn - 1;
> +
> +		if (unlikely(!pfn_to_online_page(start_pfn)))
>  			continue;
>  
> -		return start_pfn;
> +		if (likely(pfn_to_nid(start_pfn) == nid) &&
> +		    zone == page_zone(pfn_to_page(start_pfn)))
> +			return start_pfn;
> +
> +		if (likely(pfn_to_nid(tail_pfn) == nid) &&
> +		    zone == page_zone(pfn_to_page(tail_pfn)))
> +			return start_pfn;
>  	}
>  
>  	return 0;
> @@ -448,21 +455,26 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
>  				    unsigned long start_pfn,
>  				    unsigned long end_pfn)
>  {
> -	unsigned long pfn;
> +	unsigned long pfn, prev_pfn;
>  
>  	/* pfn is the end pfn of a memory section. */
>  	pfn = end_pfn - 1;
> -	for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) {
> -		if (unlikely(!pfn_to_online_page(pfn)))
> -			continue;
> +	for (; pfn >= start_pfn; pfn = prev_pfn) {
> +		unsigned long head_pfn;
>  
> -		if (unlikely(pfn_to_nid(pfn) != nid))
> -			continue;
> +		prev_pfn = pfn - PAGES_PER_SUBSECTION;
> +		head_pfn = prev_pfn + 1;
>  
> -		if (zone != page_zone(pfn_to_page(pfn)))
> +		if (unlikely(!pfn_to_online_page(pfn)))
>  			continue;
>  
> -		return pfn;
> +		if (likely(pfn_to_nid(pfn) == nid) &&
> +		    zone == page_zone(pfn_to_page(pfn)))
> +			return pfn;
> +
> +		if (likely(pfn_to_nid(head_pfn) == nid) &&
> +		    zone == page_zone(pfn_to_page(head_pfn)))
> +			return pfn;
>  	}
>  
>  	return 0;


I think improving that should be patch #1.

But I think we can do much better code-wise. What about the following
cleanup instead: