Re: [PATCH v2 13/20] arm64: Support hugetlb vmemmap optimization

[Kefeng Wang <wangkefeng.wang@huawei.com>]

On 11/7/2026 2:45 PM, Muchun Song wrote:
> 
> 
>> On Oct 3, 2026, at 08:21, James Houghton <jthoughton@google.com> wrote:
>>
>> Support HVO if HW AF and BBML3 are supported. These are the required
>> features for the vmemmap to be modified in place.
>>
>> On arm64 systems that do not have the required hardware features to
>> support HVO, the HVO sysctl will not appear, and any attempts to enable
>> HVO (either via the command line or via
>> CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON=y) will have no effect.
>>
>> Signed-off-by: James Houghton <jthoughton@google.com>
>> ---
>> arch/arm64/Kconfig               | 2 ++
>> arch/arm64/include/asm/hugetlb.h | 7 +++++++
>> mm/hugetlb_vmemmap.c             | 4 ++++
>> 3 files changed, 13 insertions(+)
>>
>> diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
>> index b51d23a62c92..e4c87487bc7f 100644
>> --- a/arch/arm64/Kconfig
>> +++ b/arch/arm64/Kconfig
>> @@ -92,7 +92,9 @@ config ARM64
>> 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
>> 	select ARCH_WANT_FRAME_POINTERS
>> 	select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36)
>> +	select ARCH_WANT_HUGETLB_VMEMMAP_RO_AFTER_INIT
>> 	select ARCH_WANT_LD_ORPHAN_WARN
>> +	select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if ARM64_HW_AFDBM
> 
> Because vmemmap optimization depends on compound_info_has_mask(), before
> enabling HVO on arm64, its vmemmap start address needs to be aligned to
> MAX_FOLIO_VMEMMAP_ALIGN. Therefore, a prerequisite patch is required.
> 

Agreed, we tried to enable ARCH_WANT_OPTIMIZE_DAX_VMEMMAP[1] on ARM64.
If the alignment is not performed, a warning will be triggered with
DEBUG_VM, see sparse_init(). The same issue applies to 
ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP.


[1] enable ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1075bc661833..649244e55c4b 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -94,6 +94,7 @@ config ARM64
         select ARCH_WANT_FRAME_POINTERS
         select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || 
(ARM64_16K_PAGES && !ARM64_VA_BITS_36)
         select ARCH_WANT_LD_ORPHAN_WARN
+       select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
         select ARCH_WANTS_EXECMEM_LATE
         select ARCH_WANTS_NO_INSTR
         select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 4e7682dfe366..6808529873a9 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -91,11 +91,9 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit;
   * has a direct correspondence, and needs to appear sufficiently aligned
   * in the virtual address space.
   */
-#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS
-#define ARM64_MEMSTART_ALIGN   (1UL << SECTION_SIZE_BITS)
-#else
-#define ARM64_MEMSTART_ALIGN   (1UL << ARM64_MEMSTART_SHIFT)
-#endif
+#define ARM64_MEMSTART_ALIGN                                          \
+       max_t(u64, 1UL << max(SECTION_SIZE_BITS, ARM64_MEMSTART_SHIFT),	\
+               PFN_PHYS(MAX_FOLIO_VMEMMAP_ALIGN / sizeof(struct page)))