mm: khugepaged: collapse_pte_mapped_thp() use pte_offset_map_rw_nolock()

In collapse_pte_mapped_thp(), we may modify the pte and pmd entry after
acquiring the ptl, so convert it to using pte_offset_map_rw_nolock().  At
this time, the pte_same() check is not performed after the PTL held.  So
we should get pgt_pmd and do pmd_same() check after the ptl held.

Link: https://lkml.kernel.org/r/055e42db68da00ac8ecab94bd2633c7cd965eb1c.1727332572.git.zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 8e0d05bd3d56026ca740e1268b2b56e3c302515e..6f8d46d107b4bf3aa9c97704974c2f05f6f1c0be 100644 (file)
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1608,7 +1608,7 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
        if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED))
                pml = pmd_lock(mm, pmd);
 
-       start_pte = pte_offset_map_nolock(mm, pmd, haddr, &ptl);
+       start_pte = pte_offset_map_rw_nolock(mm, pmd, haddr, &pgt_pmd, &ptl);
        if (!start_pte)         /* mmap_lock + page lock should prevent this */
                goto abort;
        if (!pml)
@@ -1616,6 +1616,9 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
        else if (ptl != pml)
                spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 
+       if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd))))
+               goto abort;
+
        /* step 2: clear page table and adjust rmap */
        for (i = 0, addr = haddr, pte = start_pte;
             i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) {
@@ -1648,7 +1651,6 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
                nr_ptes++;
        }
 
-       pte_unmap(start_pte);
        if (!pml)
                spin_unlock(ptl);
 
@@ -1661,14 +1663,19 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
        /* step 4: remove empty page table */
        if (!pml) {
                pml = pmd_lock(mm, pmd);
-               if (ptl != pml)
+               if (ptl != pml) {
                        spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
+                       if (unlikely(!pmd_same(pgt_pmd, pmdp_get_lockless(pmd)))) {
+                               flush_tlb_mm(mm);
+                               goto unlock;
+                       }
+               }
        }
        pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd);
        pmdp_get_lockless_sync();
+       pte_unmap_unlock(start_pte, ptl);
        if (ptl != pml)
-               spin_unlock(ptl);
-       spin_unlock(pml);
+               spin_unlock(pml);
 
        mmu_notifier_invalidate_range_end(&range);
 
@@ -1688,6 +1695,7 @@ abort:
                folio_ref_sub(folio, nr_ptes);
                add_mm_counter(mm, mm_counter_file(folio), -nr_ptes);
        }
+unlock:
        if (start_pte)
                pte_unmap_unlock(start_pte, ptl);
        if (pml && pml != ptl)