Re: [PATCH v12 mm-new 03/15] khugepaged: generalize hugepage_vma_revalidate for mTHP support

[Lance Yang]

On 2025/10/23 02:37, Nico Pache wrote:

For khugepaged to support different mTHP orders, we must generalize this
to check if the PMD is not shared by another VMA and that the order is
enabled.

No functional change in this patch. Also correct a comment about the
functionality of the revalidation.

Reviewed-by: Baolin Wang <baolin.w...@linux.alibaba.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoa...@oracle.com>
Acked-by: David Hildenbrand <da...@redhat.com>
Co-developed-by: Dev Jain <dev.j...@arm.com>
Signed-off-by: Dev Jain <dev.j...@arm.com>
Signed-off-by: Nico Pache <npa...@redhat.com>
---

LGTM!

Reviewed-by: Lance Yang <lance.y...@linux.dev>

  mm/khugepaged.c | 20 +++++++++++---------
  1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 36e31d99e507..6cf8700823f9 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -893,14 +893,13 @@ static int collapse_find_target_node(struct 
collapse_control *cc)

/*

   * If mmap_lock temporarily dropped, revalidate vma
- * before taking mmap_lock.
+ * after taking the mmap_lock again.
   * Returns enum scan_result value.
   */

static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,

-                                  bool expect_anon,
-                                  struct vm_area_struct **vmap,
-                                  struct collapse_control *cc)
+               bool expect_anon, struct vm_area_struct **vmap,
+               struct collapse_control *cc, unsigned int order)
  {
        struct vm_area_struct *vma;
        enum tva_type type = cc->is_khugepaged ? TVA_KHUGEPAGED :
@@ -913,15 +912,16 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, 
unsigned long address,
        if (!vma)
                return SCAN_VMA_NULL;

+ /* Always check the PMD order to ensure its not shared by another VMA */

        if (!thp_vma_suitable_order(vma, address, PMD_ORDER))
                return SCAN_ADDRESS_RANGE;
-       if (!thp_vma_allowable_order(vma, vma->vm_flags, type, PMD_ORDER))
+       if (!thp_vma_allowable_orders(vma, vma->vm_flags, type, BIT(order)))
                return SCAN_VMA_CHECK;
        /*
         * Anon VMA expected, the address may be unmapped then
         * remapped to file after khugepaged reaquired the mmap_lock.
         *
-        * thp_vma_allowable_order may return true for qualified file
+        * thp_vma_allowable_orders may return true for qualified file
         * vmas.
         */
        if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap)))
@@ -1117,7 +1117,8 @@ static int collapse_huge_page(struct mm_struct *mm, 
unsigned long address,
                goto out_nolock;

mmap_read_lock(mm);

-       result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
+       result = hugepage_vma_revalidate(mm, address, true, &vma, cc,
+                                        HPAGE_PMD_ORDER);
        if (result != SCAN_SUCCEED) {
                mmap_read_unlock(mm);
                goto out_nolock;
@@ -1151,7 +1152,8 @@ static int collapse_huge_page(struct mm_struct *mm, 
unsigned long address,
         * mmap_lock.
         */
        mmap_write_lock(mm);
-       result = hugepage_vma_revalidate(mm, address, true, &vma, cc);
+       result = hugepage_vma_revalidate(mm, address, true, &vma, cc,
+                                        HPAGE_PMD_ORDER);
        if (result != SCAN_SUCCEED)
                goto out_up_write;
        /* check if the pmd is still valid */
@@ -2792,7 +2794,7 @@ int madvise_collapse(struct vm_area_struct *vma, unsigned 
long start,
                        mmap_read_lock(mm);
                        mmap_locked = true;
                        result = hugepage_vma_revalidate(mm, addr, false, &vma,
-                                                        cc);
+                                                        cc, HPAGE_PMD_ORDER);
                        if (result  != SCAN_SUCCEED) {
                                last_fail = result;
                                goto out_nolock;