Re: [PATCH v7 1/2] mm/memory hotplug: fix zone->contiguous always false when hotplug

[David Hildenbrand (Red Hat)]

On 12/22/25 15:58, Tianyou Li wrote:
> Function set_zone_contiguous used __pageblock_pfn_to_page to
> check the whole pageblock is in the same zone. One assumption is
> the memory section must online, otherwise the __pageblock_pfn_to_page
> will return NULL, then the set_zone_contiguous will be false.
> When move_pfn_range_to_zone invoked set_zone_contiguous, since the
> memory section did not online, the return value will always be false.
>
> To fix this issue, we removed the set_zone_contiguous from the
> move_pfn_range_to_zone, and place it after memory section onlined.
>
> Function remove_pfn_range_from_zone did not have this issue because
> memory section remains online at the time set_zone_contiguous invoked.

The description is a bit hard to follow. Let me try:


"set_zone_contiguous() uses __pageblock_pfn_to_page() to detect 
pageblocks that either do not exist (hole) or that do not belong to the 
same zone.

__pageblock_pfn_to_page(), however, relies on pfn_to_online_page(), 
effectively always returning NULL for memory ranges that were not 
onlined yet. So when called on a range-to-be-onlined, it indicates a 
memory hole to set_zone_contiguous().

Consequently, the set_zone_contiguous() call in 
move_pfn_range_to_zone(), which happens early during memory onlining, 
will never detect a zone as being contiguous. Bad.

To fix the issue, move the set_zone_contiguous() call to a later stage
in memory onlining, where pfn_to_online_page() will succeed: after we
mark the memory sections to be online"


Now, there is no need to add the handling to 
mhp_init_memmap_on_memory(). Note how mhp_init_memmap_on_memory() in 
memory_block_online() is always followed by online_pages().

So, it's sufficient to move it after the online_pages_range(). I would 
also add a comment there saying something like:

/*
 * Now that the ranges are indicated as online, check whether the whole
 * zone is contiguous.
 */


Can we find some Fixes: tag (which commit introduced the regression)? 
Likely we want to CC stable.

--
Cheers

David