[PATCH v2] hugetlbfs: remove call to huge_pte_alloc without i_mmap_rwsem

[Mike Kravetz]

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")
Cc: <stable@xxxxxxxxxxxxxxx>
Suggested-by: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
---
 include/linux/fs.h      | 10 ++++++++++
 include/linux/hugetlb.h |  8 +++++---
 mm/hugetlb.c            | 15 +++++++--------
 mm/rmap.c               |  2 +-
 4 files changed, 23 insertions(+), 12 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f5abba86107d..2dab217c6047 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -549,6 +549,16 @@ static inline void i_mmap_unlock_read(struct address_space *mapping)
 	up_read(&mapping->i_mmap_rwsem);
 }
 
+static inline void i_mmap_assert_locked(struct address_space *mapping)
+{
+	lockdep_assert_held(&mapping->i_mmap_rwsem);
+}
+
+static inline void i_mmap_assert_write_locked(struct address_space *mapping)
+{
+	lockdep_assert_held_write(&mapping->i_mmap_rwsem);
+}
+
 /*
  * Might pages of this file be mapped into userspace?
  */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 50650d0d01b9..a520bf26e5d8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -164,7 +164,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm,
 		       unsigned long addr, unsigned long sz);
-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);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
@@ -203,8 +204,9 @@ static inline struct address_space *hugetlb_page_mapping_lock_write(
 	return NULL;
 }
 
-static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
-					pte_t *ptep)
+static inline 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/hugetlb.c b/mm/hugetlb.c
index 590111ea6975..6ac686b09bb6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3952,7 +3952,7 @@ 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.
@@ -4539,10 +4539,6 @@ 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;
 	}
 
 	/*
@@ -5019,7 +5015,7 @@ 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;
@@ -5404,12 +5400,14 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
  * 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;
@@ -5427,7 +5425,8 @@ 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
-- 
2.25.4