Re: [PATCH 07/17] mm/sparse-vmemmap: support section-based vmemmap optimization

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

On 2026/7/15 13:08, Mike Rapoport wrote:
>> Teach sparse-vmemmap population code to use the compound page order
>> when deciding whether a vmemmap page can be optimized.
>>
>> With this information, the common sparse-vmemmap population path can
>> allocate or reuse shared tail vmemmap pages directly instead of relying
>> on HugeTLB/DAX-specific handling.
>>
>> This centralizes vmemmap optimization logic in the sparse-vmemmap code,
>> based on section metadata, and prepares for sharing the same mechanism
>> across different users of vmemmap optimization, including HugeTLB and
>> DAX.
>>
>> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
>>
>> diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
>> index 41a1ebbe5e85..41f6a584a52a 100644
>> --- a/include/linux/mmzone.h
>> +++ b/include/linux/mmzone.h
>> @@ -1148,7 +1148,7 @@ struct zone {
>>   	/* Zone statistics */
>>   	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
>>   	atomic_long_t		vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
>> -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
>> +#ifdef CONFIG_SPARSEMEM_VMEMMAP
>>   	struct page *vmemmap_tails[NR_OPTIMIZABLE_FOLIO_ORDERS];
>>   #endif
>>   } ____cacheline_internodealigned_in_smp;
>> diff --git a/mm/internal.h b/mm/internal.h
>> index ebbab7421633..8ec8b447d75e 100644
>> --- a/mm/internal.h
>> +++ b/mm/internal.h
>> @@ -993,6 +993,9 @@ static inline void __section_mark_present(struct mem_section *ms,
>>   
>>   	ms->section_mem_map |= SECTION_MARKED_PRESENT;
>>   }
>> +
>> +int section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
>> +		struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
> What about !SPARSE_VMEMMAP case?

I need a stub here. Since I'm taking your last suggestion and not
moving this function out of sparse-vmemmap.c, I'll handle it in the
next version.

>
>>   #else
>>   static inline void sparse_init(void) {}
>>   #endif /* CONFIG_SPARSEMEM */
>> diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
>> index 99f59394feab..232f2a08afad 100644
>> --- a/mm/sparse-vmemmap.c
>> +++ b/mm/sparse-vmemmap.c
>> @@ -146,17 +146,49 @@ void __meminit vmemmap_verify(pte_t *pte, int node,
>>   			start, end - 1);
>>   }
>>   
>> +static struct zone __meminit *pfn_to_zone(unsigned long pfn, int nid)
>> +{
>> +	pg_data_t *pgdat = NODE_DATA(nid);
>> +
>> +	for (enum zone_type zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
>> +		struct zone *zone = &pgdat->node_zones[zone_type];
>> +
>> +		if (zone_spans_pfn(zone, pfn))
>> +			return zone;
>> +	}
>> +
>> +	return NULL;
>> +}
>> +
>> +static __meminit struct page *vmemmap_get_tail(unsigned int order, struct zone *zone);
>> +
> Maybe just move the entire function here?

No problem.

>
>>   static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
>>   				       struct vmem_altmap *altmap,
>>   				       unsigned long ptpfn, unsigned long flags)
>>   {
>>   	pte_t *pte = pte_offset_kernel(pmd, addr);
>> +	struct page *page = (struct page *)addr;
>> +	unsigned long pfn = page_to_pfn(page);
>> +	unsigned int order = section_order(__pfn_to_section(pfn));
>> +
>>   	if (pte_none(ptep_get(pte))) {
>>   		pte_t entry;
>> -		void *p;
>> +
>> +		if (page_vmemmap_optimizable(page, order) &&
>> +		    ptpfn == (unsigned long)-1) {
>> +			struct zone *zone = pfn_to_zone(pfn, node);
>> +
>> +			if (WARN_ON_ONCE(!zone))
>> +				return NULL;
>> +			page = vmemmap_get_tail(order, zone);
>> +			if (!page)
>> +				return NULL;
>> +			ptpfn = page_to_pfn(page);
>> +		}
>>   
>>   		if (ptpfn == (unsigned long)-1) {
>> -			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
>> +			void *p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
>> +
>>   			if (!p)
>>   				return NULL;
>>   			ptpfn = PHYS_PFN(__pa(p));
>> @@ -175,7 +207,8 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in
>>   		}
>>   		entry = pfn_pte(ptpfn, PAGE_KERNEL);
>>   		set_pte_at(&init_mm, addr, pte, entry);
>> -	}
>> +	} else if (WARN_ON_ONCE(page_vmemmap_optimizable(page, order)))
>> +		return NULL;
>>   	return pte;
>>   }
>>   
>> @@ -320,7 +353,6 @@ void vmemmap_wrprotect_hvo(unsigned long addr, unsigned long end,
>>   	}
>>   }
>>   
>> -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
>>   static __meminit struct page *vmemmap_get_tail(unsigned int order, struct zone *zone)
>>   {
>>   	struct page *p, *tail;
>> @@ -348,6 +380,7 @@ static __meminit struct page *vmemmap_get_tail(unsigned int order, struct zone *
>>   	return tail;
>>   }
>>   
>> +#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP
>>   int __meminit vmemmap_populate_hvo(unsigned long addr, unsigned long end,
>>   				       unsigned int order, struct zone *zone,
>>   				       unsigned long headsize)
>> @@ -402,6 +435,9 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
>>   	pmd_t *pmd;
>>   
>>   	for (addr = start; addr < end; addr = next) {
>> +		unsigned long pfn = page_to_pfn((struct page *)addr);
>> +		struct mem_section *ms = __pfn_to_section(pfn);
>> +
>>   		next = pmd_addr_end(addr, end);
>>   
>>   		pgd = vmemmap_pgd_populate(addr, node);
>> @@ -417,7 +453,7 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
>>   			return -ENOMEM;
>>   
>>   		pmd = pmd_offset(pud, addr);
>> -		if (pmd_none(pmdp_get(pmd))) {
>> +		if (pmd_none(pmdp_get(pmd)) && !section_vmemmap_optimizable(ms)) {
>>   			void *p;
>>   
>>   			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
>> @@ -435,8 +471,19 @@ int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
>>   				 */
>>   				return -ENOMEM;
>>   			}
>> -		} else if (vmemmap_check_pmd(pmd, node, addr, next))
>> +		} else if (vmemmap_check_pmd(pmd, node, addr, next)) {
>> +			const struct mem_section *start_ms;
>> +			unsigned long align = max(1UL << section_order(ms), PAGES_PER_SECTION);
>> +
>> +			/* HVO-covered sections must not use PMD mappings. */
>> +			start_ms = __pfn_to_section(ALIGN_DOWN(pfn, align));
>> +			if (!IS_ALIGNED(pfn, align) && section_vmemmap_optimizable(start_ms))
>> +				return -ENOTSUPP;
>> +
>> +			/* PMD mappings end HVO coverage for this section. */
>> +			section_set_order(ms, 0);
> The whole pmd block here becomes really hairy.
> I'd suggest splitting it out to a helper function and reducing the
> amount of nested ifs with early returns where possible.

The code here is actually a bit too defensive. I plan to simplify
it significantly in the next version and will only reintroduce this
logic if it becomes necessary in the future.

>
>>   			continue;
>> +		}
>>   		if (vmemmap_populate_basepages(addr, next, node, altmap))
>>   			return -ENOMEM;
>>   	}
>> @@ -642,36 +689,6 @@ void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
>>   	}
>>   }
>>   
>> -static int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
>> -		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
>> -{
>> -	const struct mem_section *ms = __pfn_to_section(pfn);
>> -	const unsigned int order = pgmap ? pgmap->vmemmap_shift : section_order(ms);
>> -	const unsigned long pages_per_compound = 1UL << order;
>> -	unsigned int vmemmap_pages = OPTIMIZED_FOLIO_VMEMMAP_PAGES;
>> -
>> -	VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SUBSECTION));
>> -	VM_WARN_ON_ONCE(nr_pages > PAGES_PER_SECTION);
>> -
>> -	if (vmemmap_can_optimize(altmap, pgmap))
>> -		vmemmap_pages = VMEMMAP_RESERVE_NR;
>> -
>> -	if (!vmemmap_can_optimize(altmap, pgmap) && !section_vmemmap_optimizable(ms))
>> -		return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);
>> -
>> -	if (order < PFN_SECTION_SHIFT) {
>> -		VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, pages_per_compound));
>> -		return vmemmap_pages * nr_pages / pages_per_compound;
>> -	}
>> -
>> -	VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION));
>> -
>> -	if (IS_ALIGNED(pfn, pages_per_compound))
>> -		return vmemmap_pages;
>> -
>> -	return 0;
>> -}
>> -
>>   static struct page * __meminit populate_section_memmap(unsigned long pfn,
>>   		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
>>   		struct dev_pagemap *pgmap)
>> diff --git a/mm/sparse.c b/mm/sparse.c
>> index 9457a4d6a6fc..3e96478a63e0 100644
>> --- a/mm/sparse.c
>> +++ b/mm/sparse.c
>> @@ -284,6 +284,36 @@ static void __init sparse_usage_fini(void)
>>   	sparse_usagebuf = sparse_usagebuf_end = NULL;
>>   }
>>   
>> +int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
>> +		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
>> +{
> I don't think moving this to sparse.c is a good idea, let's keep vmemmap
> code in sparse-vmemmap.c

OK. To make things clearer, I'll likely add a "stub" to handle
cases involving non-SPARSEMEM_VMEMMAP configurations.

Since this function is still being called by sparse.c, what do you
think about renaming it to section_nr_memmap_pages?

Muchun
Thanks.

>