Where arch_needs_pgtable_deposit() is true, every huge PMD needs a
deposited page table. ppc64 in hash mode keeps the hash slot array of
the huge page in it, so vmf_insert_pfn_pmd() deposits one for each
special PMD it maps.

copy_huge_pmd() copies a special PMD into the child without a table.
The child then dereferences a NULL table:

- on the first hash fault on the PMD, in __hash_page_thp();
- on the zap at munmap() or exit, in hash__pmdp_huge_get_and_clear().

Allocate a table before taking the page table locks and deposit it
with the copy, as insert_pmd() does.

Fixes: d1503aa9ab805 ("powerpc/64s: Add support for huge pfnmaps")
Reported-by: Sashiko <[email protected]>
Closes: 
https://sashiko.dev/#/patchset/20261014-b4-prep-vstor-149847-copy_huge_pmd-recheck-special-pmd-v1-1-d225c60bc...@virtuozzo.com?part=1
Cc: [email protected]
Assisted-by: LLM
Signed-off-by: Konstantin Khorenko <[email protected]>
---
 mm/huge_memory.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index fcea98f0d8865..d53db73f52676 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1961,6 +1961,11 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct 
mm_struct *src_mm,
        pmd = pmdp_get_lockless(src_pmd);
        if (unlikely(pmd_present(pmd) && pmd_special(pmd) &&
                     !is_huge_zero_pmd(pmd))) {
+               if (arch_needs_pgtable_deposit()) {
+                       pgtable = pte_alloc_one(dst_mm);
+                       if (unlikely(!pgtable))
+                               goto out;
+               }
                dst_ptl = pmd_lock(dst_mm, dst_pmd);
                src_ptl = pmd_lockptr(src_mm, src_pmd);
                spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
@@ -1974,6 +1979,8 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct 
mm_struct *src_mm,
                if (unlikely(!pmd_present(pmd) || !pmd_special(pmd))) {
                        spin_unlock(src_ptl);
                        spin_unlock(dst_ptl);
+                       if (pgtable)
+                               pte_free(dst_mm, pgtable);
                        return -EAGAIN;
                }
                /*
@@ -1983,6 +1990,10 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct 
mm_struct *src_mm,
                 * wrongly write to the backend MMIO.
                 */
                VM_WARN_ON_ONCE(vma_is_cow_mapping(src_vma) && pmd_write(pmd));
+               if (pgtable) {
+                       mm_inc_nr_ptes(dst_mm);
+                       pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable);
+               }
                goto set_pmd;
        }
 

-- 
2.43.0


Reply via email to