mm/hugetlb: make detecting shared pte more reliable

If the pagetables are shared, we shouldn't copy or take references.  Since
src could have unshared and dst shares with another vma, huge_pte_none()
is thus used to determine whether dst_pte is shared.  But this check isn't
reliable.  A shared pte could have pte none in pagetable in fact.  The
page count of ptep page should be checked here in order to reliably
determine whether pte is shared.

[lukas.bulwahn@gmail.com: remove unused local variable dst_entry in copy_hugetlb_page_range()]
Link: https://lkml.kernel.org/r/20220822082525.26071-1-lukas.bulwahn@gmail.com
Link: https://lkml.kernel.org/r/20220816130553.31406-7-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 648d9f5..de12ab6 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4750,7 +4750,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                            struct vm_area_struct *dst_vma,
                            struct vm_area_struct *src_vma)
 {
-       pte_t *src_pte, *dst_pte, entry, dst_entry;
+       pte_t *src_pte, *dst_pte, entry;
        struct page *ptepage;
        unsigned long addr;
        bool cow = is_cow_mapping(src_vma->vm_flags);
@@ -4795,15 +4795,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 
                /*
                 * If the pagetables are shared don't copy or take references.
-                * dst_pte == src_pte is the common case of src/dest sharing.
                 *
+                * dst_pte == src_pte is the common case of src/dest sharing.
                 * However, src could have 'unshared' and dst shares with
-                * another vma.  If dst_pte !none, this implies sharing.
-                * Check here before taking page table lock, and once again
-                * after taking the lock below.
+                * another vma. So page_count of ptep page is checked instead
+                * to reliably determine whether pte is shared.
                 */
-               dst_entry = huge_ptep_get(dst_pte);
-               if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) {
+               if (page_count(virt_to_page(dst_pte)) > 1) {
                        addr |= last_addr_mask;
                        continue;
                }
@@ -4812,13 +4810,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
                src_ptl = huge_pte_lockptr(h, src, src_pte);
                spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
                entry = huge_ptep_get(src_pte);
-               dst_entry = huge_ptep_get(dst_pte);
 again:
-               if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
+               if (huge_pte_none(entry)) {
                        /*
-                        * Skip if src entry none.  Also, skip in the
-                        * unlikely case dst entry !none as this implies
-                        * sharing with another vma.
+                        * Skip if src entry none.
                         */
                        ;
                } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) {
@@ -4897,7 +4892,7 @@ again:
                                        restore_reserve_on_error(h, dst_vma, addr,
                                                                new);
                                        put_page(new);
-                                       /* dst_entry won't change as in child */
+                                       /* huge_ptep of dst_pte won't change as in child */
                                        goto again;
                                }
                                hugetlb_install_page(dst_vma, dst_pte, addr, new);