Re: [PATCH v3 15/19] mm/hugetlb_vmemmap: Move bootmem HVO setup to early init

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

On 2026/6/3 20:02, Usama Arif wrote:
> On Tue,  2 Jun 2026 18:10:35 +0800 Muchun Song <songmuchun@bytedance.com> wrote:
>
>> Bootmem HugeTLB pages currently defer HVO setup to
>> hugetlb_vmemmap_init_late(), because the optimization needs zone
>> information.
>>
>> Now that zone initialization is available earlier, the bootmem HVO setup
>> can be done directly from hugetlb_vmemmap_init_early(). This lets
>> gigantic HugeTLB pages apply HVO as soon as they are allocated.
>>
>> Bootmem gigantic pages that span multiple zones are now filtered out
>> when they are allocated, so the remaining bootmem gigantic pages seen by
>> later hugetlb initialization are already zone-valid. As a result,
>> hugetlb_vmemmap_init_late() no longer needs to handle bootmem HVO setup.
>>
>> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
>> ---
>>   mm/hugetlb_vmemmap.c | 67 +++++++++-----------------------------------
>>   1 file changed, 13 insertions(+), 54 deletions(-)
>>
>> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
>> index ea6af85bfec1..464578ee246e 100644
>> --- a/mm/hugetlb_vmemmap.c
>> +++ b/mm/hugetlb_vmemmap.c
>> @@ -745,6 +745,8 @@ static bool vmemmap_should_optimize_bootmem_page(struct huge_bootmem_page *m)
>>   	return true;
>>   }
>>   
>> +static struct zone *pfn_to_zone(unsigned nid, unsigned long pfn);
>> +
>>   /*
>>    * Initialize memmap section for a gigantic page, HVO-style.
>>    */
>> @@ -752,6 +754,7 @@ void __init hugetlb_vmemmap_init_early(int nid)
>>   {
>>   	unsigned long psize, paddr, section_size;
>>   	unsigned long ns, i, pnum, pfn, nr_pages;
>> +	unsigned long start, end;
>>   	struct huge_bootmem_page *m = NULL;
>>   	void *map;
>>   
>> @@ -761,6 +764,8 @@ void __init hugetlb_vmemmap_init_early(int nid)
>>   	section_size = (1UL << PA_SECTION_SHIFT);
>>   
>>   	list_for_each_entry(m, &huge_boot_pages[nid], list) {
>> +		struct zone *zone;
>> +
>>   		if (!vmemmap_should_optimize_bootmem_page(m))
>>   			continue;
>>   
>> @@ -769,6 +774,14 @@ void __init hugetlb_vmemmap_init_early(int nid)
>>   		paddr = virt_to_phys(m);
>>   		pfn = PHYS_PFN(paddr);
>>   		map = pfn_to_page(pfn);
>> +		start = (unsigned long)map;
>> +		end = start + hugetlb_vmemmap_size(m->hstate);
>> +		zone = pfn_to_zone(nid, pfn);
>> +
>> +		if (vmemmap_populate_hvo(start, end, huge_page_order(m->hstate),
>> +					 zone, HUGETLB_VMEMMAP_RESERVE_SIZE))
>> +			panic("Failed to allocate memmap for HugeTLB page\n");
> The replaced hugetlb_vmemmap_init_late() path used to fall back to
> vmemmap_populate() if vmemmap_populate_hvo() returned an error and
> just lost the HVO optimization for that page.
>
> The new path panics on any non-zero return.  Is the panic intended,
> given that vmemmap_populate_hvo() returns -ENOMEM on allocation
> failure and HVO is normally treated as an optimization rather than a
> hard requirement?

This is intentional; see patch 6:

     mm/sparse: Panic on memmap and usemap allocation failure

We already panic on OOM anyway.

Muchun,
Thanks.

>
>> +		memmap_boot_pages_add(DIV_ROUND_UP(HUGETLB_VMEMMAP_RESERVE_SIZE, PAGE_SIZE));
>>   
>>   		pnum = pfn_to_section_nr(pfn);
>>   		ns = psize / section_size;
>> @@ -800,60 +813,6 @@ static struct zone *pfn_to_zone(unsigned nid, unsigned long pfn)
>>   
>>   void __init hugetlb_vmemmap_init_late(int nid)
>>   {
>> -	struct huge_bootmem_page *m, *tm;
>> -	unsigned long phys, nr_pages, start, end;
>> -	unsigned long pfn, nr_mmap;
>> -	struct zone *zone = NULL;
>> -	struct hstate *h;
>> -	void *map;
>> -
>> -	if (!READ_ONCE(vmemmap_optimize_enabled))
>> -		return;
>> -
>> -	list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) {
>> -		if (!(m->flags & HUGE_BOOTMEM_HVO))
>> -			continue;
>> -
>> -		phys = virt_to_phys(m);
>> -		h = m->hstate;
>> -		pfn = PHYS_PFN(phys);
>> -		nr_pages = pages_per_huge_page(h);
>> -		map = pfn_to_page(pfn);
>> -		start = (unsigned long)map;
>> -		end = start + nr_pages * sizeof(struct page);
>> -
>> -		if (!hugetlb_bootmem_page_zones_valid(nid, m)) {
>> -			/*
>> -			 * Oops, the hugetlb page spans multiple zones.
>> -			 * Remove it from the list, and populate it normally.
>> -			 */
>> -			list_del(&m->list);
>> -
>> -			vmemmap_populate(start, end, nid, NULL);
>> -			nr_mmap = end - start;
>> -			memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE));
>> -
>> -			memblock_phys_free(phys, huge_page_size(h));
>> -			continue;
>> -		}
>> -
>> -		if (!zone || !zone_spans_pfn(zone, pfn))
>> -			zone = pfn_to_zone(nid, pfn);
>> -		if (WARN_ON_ONCE(!zone))
>> -			continue;
>> -
>> -		if (vmemmap_populate_hvo(start, end, huge_page_order(h), zone,
>> -					 HUGETLB_VMEMMAP_RESERVE_SIZE) < 0) {
>> -			/* Fallback if HVO population fails */
>> -			vmemmap_populate(start, end, nid, NULL);
>> -			nr_mmap = end - start;
>> -		} else {
>> -			m->flags |= HUGE_BOOTMEM_ZONES_VALID;
>> -			nr_mmap = HUGETLB_VMEMMAP_RESERVE_SIZE;
>> -		}
>> -
>> -		memmap_boot_pages_add(DIV_ROUND_UP(nr_mmap, PAGE_SIZE));
>> -	}
>>   }
>>   #endif
>>   
>> -- 
>> 2.54.0
>>
>>