Re: [PATCH 07/12] mm: hugetlb_vmemmap: simplify shared tail page handling

[Muchun Song <muchun.song@linux.dev>]

On 2026/10/23 10:20, Lance Yang wrote:
> On Tue, Oct 20, 2026 at 07:58:19PM +0800, Muchun Song wrote:
>> The remap walker currently carries a shared tail page selected by its
>> caller, even though the optimize and restore callbacks can derive the
>> same information from the folio being processed.  This adds redundant
>> state to the walker and couples its interface to caller-side preparation.
>>
>> Derive the shared mapping state in the callbacks instead, keeping the
>> mapping policy with the PTE being processed and simplifying the remap
>> interface.
>>
>> No functional change intended.
>>
>> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
>> ---
>> include/linux/vmemmap-optimization.h |  6 +-
>> mm/hugetlb_vmemmap.c                 | 89 ++++++++++++----------------
>> mm/mm_init.c                         |  6 +-
>> mm/sparse-vmemmap.c                  |  5 +-
>> 4 files changed, 49 insertions(+), 57 deletions(-)
>>
>> diff --git a/include/linux/vmemmap-optimization.h b/include/linux/vmemmap-optimization.h
>> index 065840f3c241..858311a71b0c 100644
>> --- a/include/linux/vmemmap-optimization.h
>> +++ b/include/linux/vmemmap-optimization.h
>> @@ -91,11 +91,13 @@ static inline struct page *vmemmap_shared_tail_page(unsigned int order,
>> }
>> #endif /* CONFIG_VMEMMAP_OPTIMIZATION */
>>
>> -static inline bool vmemmap_optimizable_pfn(unsigned long pfn)
>> +static inline bool vmemmap_optimizable_pfn(unsigned long pfn, unsigned int order)
>> {
>> -	const unsigned int order = pfn_to_section_compound_order(pfn);
>> 	const unsigned long nr_pages = 1UL << order;
>>
>> +	if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION))
>> +		return false;
>> +
>> 	if (!is_power_of_2(sizeof(struct page)))
>> 		return false;
>>
>> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
>> index 18b72d553955..8fac61b7d74a 100644
>> --- a/mm/hugetlb_vmemmap.c
>> +++ b/mm/hugetlb_vmemmap.c
>> @@ -24,22 +24,18 @@
>>   * struct vmemmap_remap_walk - walk vmemmap page table
>>   *
>>   * @remap_pte:		called for each lowest-level entry (PTE).
>> - * @nr_walked:		the number of walked pte.
>> - * @vmemmap_tail:	the page to be installed as non-first in the vmemmap range
>> + * @nr_walked:		the number of PTEs successfully remapped.
>>   * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
>>   *			or is mapped from.
>>   * @flags:		used to modify behavior in vmemmap page table walking
>>   *			operations.
>>   */
>> struct vmemmap_remap_walk {
>> -	void			(*remap_pte)(pte_t *pte, unsigned long addr,
>> +	int			(*remap_pte)(pte_t *pte, unsigned long addr,
>> 					     struct vmemmap_remap_walk *walk);
>> -
>> 	unsigned long		nr_walked;
>> -	struct page		*vmemmap_tail;
>> 	struct list_head	*vmemmap_pages;
>>
>> -
>> /* Skip the TLB flush while updating the vmemmap page tables. */
>> #define VMEMMAP_REMAP_NO_TLB_FLUSH	BIT(0)
>> 	unsigned long		flags;
>> @@ -140,12 +136,14 @@ static int vmemmap_pmd_entry(pmd_t *pmd, unsigned long addr,
>> static int vmemmap_pte_entry(pte_t *pte, unsigned long addr,
>> 			     unsigned long next, struct mm_walk *walk)
>> {
>> +	int ret;
>> 	struct vmemmap_remap_walk *vmemmap_walk = walk->private;
>>
>> -	vmemmap_walk->remap_pte(pte, addr, vmemmap_walk);
>> -	vmemmap_walk->nr_walked++;
>> +	ret = vmemmap_walk->remap_pte(pte, addr, vmemmap_walk);
>> +	if (!ret)
>> +		vmemmap_walk->nr_walked++;
>>
>> -	return 0;
>> +	return ret;
>> }
>>
>> static const struct mm_walk_ops vmemmap_remap_ops = {
>> @@ -213,51 +211,51 @@ static struct page *vmemmap_dup_page_from_list(const struct page *src,
>> 	return dst;
>> }
>>
>> -static void vmemmap_optimize_pte(pte_t *pte, unsigned long addr,
>> -				 struct vmemmap_remap_walk *walk)
>> +static inline struct page *folio_vmemmap_shared_tail_page(const struct folio *folio)
>> {
>> -	struct page *page = pte_page(ptep_get(pte));
>> -	pte_t entry;
>> -
>> -	/* Remapping the head page requires r/w */
>> -	if (unlikely(walk->nr_walked == 0)) {
>> -		struct page *head;
>> +	return vmemmap_shared_tail_page(folio_order(folio), folio_zone(folio));
>> +}
>>
>> -		VM_WARN_ON_ONCE(!PageHead((const struct page *)addr));
>> +static int vmemmap_optimize_pte(pte_t *pte, unsigned long addr,
>> +				struct vmemmap_remap_walk *walk)
>> +{
>> +	pte_t entry;
>> +	struct page *src = pte_page(ptep_get(pte)), *dst;
>> +	const struct page *page = (const struct page *)addr;
>> +	const struct folio *folio = page_folio(page);
>>
>> -		head = vmemmap_dup_page_from_list(page, walk->vmemmap_pages);
>> -		entry = mk_pte(head, PAGE_KERNEL);
>> +	if (likely(vmemmap_optimizable_pfn(page_to_pfn(page), folio_order(folio)))) {
>> +		dst = folio_vmemmap_shared_tail_page(folio);
>> +		if (!dst)
>> +			return -ENOMEM;
> One thing caught my eye here ... shared tail allocation can now fail after
> we've already remapped the head.

Right. Once the shared page has been allocated successfully, this
shouldn't be a common case.

>
> IIUC, nothing to worry about there, though :) since rollback keeps the
> new head mapped and flushes before clearing the optimized flag or freeing
> the old backing page.

Yes.

>
> [...]
>
> Reviewed-by: Lance Yang <lance.yang@linux.dev>

Thanks.