[PATCH] mm/hugetlb: avoid unnecessary TLB flush for empty folio list in vmemmap optimize

[PATCH] mm/hugetlb: avoid unnecessary TLB flush for empty folio list in vmemmap optimize

[Wentao Guan]

__hugetlb_vmemmap_optimize_folios() unconditionally issues a final
flush_tlb_all() in its out path.  However, a TLB flush must be paired
with an actual page table modification.

When the input folio list is empty, neither PMD splitting nor PTE
remapping takes place, so no page tables are modified and the flush is
pure overhead.  An empty list is reached in common paths such as
gather_bootmem_prealloc_node() on nodes without bootmem gigantic pages,
hugetlb_pages_alloc_boot_node() when no pages were allocated, and
runtime allocation failure paths in set_max_huge_pages().

Add an early return for empty lists.  This restores the basic invariant
that TLB flushes are only issued when page tables have been modified,
and it also makes the NULL hstate passed by gather_bootmem_prealloc_node()
on an empty list harmless.

Assisted-by: kimi-cli:kimi-k2.7 code
Assisted-by: Github Copilot:gpt-5.2 #Reported-by

Fixes: 79359d6d24df ("hugetlb: perform vmemmap optimization on a list of pages")
Signed-off-by: Wentao Guan <guanwentao@uniontech.com>
---
 mm/hugetlb_vmemmap.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 133b46dfb09f5..d45d5355d1af1 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -624,6 +624,9 @@ static void __hugetlb_vmemmap_optimize_folios(struct hstate *h,
 	LIST_HEAD(vmemmap_pages);
 	unsigned long flags = VMEMMAP_REMAP_NO_TLB_FLUSH;
 
+	if (list_empty(folio_list))
+		return;
+
 	nr_to_optimize = 0;
 	list_for_each_entry(folio, folio_list, lru) {
 		int ret;
-- 
2.30.2

Re: [PATCH] mm/hugetlb: avoid unnecessary TLB flush for empty folio list in vmemmap optimize

[Muchun Song]

> On Jun 30, 2026, at 19:38, Wentao Guan <guanwentao@uniontech.com> wrote:
> 
> __hugetlb_vmemmap_optimize_folios() unconditionally issues a final
> flush_tlb_all() in its out path.  However, a TLB flush must be paired
> with an actual page table modification.
> 
> When the input folio list is empty, neither PMD splitting nor PTE
> remapping takes place, so no page tables are modified and the flush is
> pure overhead.  An empty list is reached in common paths such as
> gather_bootmem_prealloc_node() on nodes without bootmem gigantic pages,
> hugetlb_pages_alloc_boot_node() when no pages were allocated, and
> runtime allocation failure paths in set_max_huge_pages().
> 
> Add an early return for empty lists.  This restores the basic invariant
> that TLB flushes are only issued when page tables have been modified,
> and it also makes the NULL hstate passed by gather_bootmem_prealloc_node()
> on an empty list harmless.
> 
> Assisted-by: kimi-cli:kimi-k2.7 code
> Assisted-by: Github Copilot:gpt-5.2 #Reported-by
> 
> Fixes: 79359d6d24df ("hugetlb: perform vmemmap optimization on a list of pages")

Actually, this is an optimization, so it doesn't need a bugfix—unless it's a hot
path or causing a massive performance degradation, that's clearly not the case
here.

> Signed-off-by: Wentao Guan <guanwentao@uniontech.com>

I actually have a local optimization that covers this, so LGTM:

Reviewed-by: Muchun Song <muchun.song@linux.dev>

Thanks.