From 34ae204f18519f0920bd50a644abd6fefc8dbfcf Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Tue, 11 Aug 2020 18:31:38 -0700 Subject: hugetlbfs: remove call to huge_pte_alloc without i_mmap_rwsem Commit c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization") requires callers of huge_pte_alloc to hold i_mmap_rwsem in at least read mode. This is because the explicit locking in huge_pmd_share (called by huge_pte_alloc) was removed. When restructuring the code, the call to huge_pte_alloc in the else block at the beginning of hugetlb_fault was missed. Unfortunately, that else clause is exercised when there is no page table entry. This will likely lead to a call to huge_pmd_share. If huge_pmd_share thinks pmd sharing is possible, it will traverse the mapping tree (i_mmap) without holding i_mmap_rwsem. If someone else is modifying the tree, bad things such as addressing exceptions or worse could happen. Simply remove the else clause. It should have been removed previously. The code following the else will call huge_pte_alloc with the appropriate locking. To prevent this type of issue in the future, add routines to assert that i_mmap_rwsem is held, and call these routines in huge pmd sharing routines. Fixes: c0d0381ade79 ("hugetlbfs: use i_mmap_rwsem for more pmd sharing synchronization") Suggested-by: Matthew Wilcox Signed-off-by: Mike Kravetz Signed-off-by: Andrew Morton Cc: Michal Hocko Cc: Hugh Dickins Cc: Naoya Horiguchi Cc: "Aneesh Kumar K.V" Cc: Andrea Arcangeli Cc: "Kirill A.Shutemov" Cc: Davidlohr Bueso Cc: Prakash Sangappa Cc: Link: http://lkml.kernel.org/r/e670f327-5cf9-1959-96e4-6dc7cc30d3d5@oracle.com Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 15 +++++++-------- mm/rmap.c | 2 +- 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index dffafb5bf2ed..8a18f1234e80 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3967,7 +3967,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, continue; ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, &address, ptep)) { spin_unlock(ptl); /* * We just unmapped a page of PMDs by clearing a PUD. @@ -4554,10 +4554,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); - } else { - ptep = huge_pte_alloc(mm, haddr, huge_page_size(h)); - if (!ptep) - return VM_FAULT_OOM; } /* @@ -5034,7 +5030,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); - if (huge_pmd_unshare(mm, &address, ptep)) { + if (huge_pmd_unshare(mm, vma, &address, ptep)) { pages++; spin_unlock(ptl); shared_pmd = true; @@ -5415,12 +5411,14 @@ out: * returns: 1 successfully unmapped a shared pte page * 0 the underlying pte page is not shared, or it is the last user */ -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { pgd_t *pgd = pgd_offset(mm, *addr); p4d_t *p4d = p4d_offset(pgd, *addr); pud_t *pud = pud_offset(p4d, *addr); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); BUG_ON(page_count(virt_to_page(ptep)) == 0); if (page_count(virt_to_page(ptep)) == 1) return 0; @@ -5438,7 +5436,8 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) return NULL; } -int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long *addr, pte_t *ptep) { return 0; } diff --git a/mm/rmap.c b/mm/rmap.c index 5fe2dedce1fc..6cce9ef06753 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1469,7 +1469,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, * do this outside rmap routines. */ VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); - if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) { /* * huge_pmd_unshare unmapped an entire PMD * page. There is no way of knowing exactly -- cgit v1.2.3