diff mbox series

[v9,3/3] hugetlb: don't delete vma_lock in hugetlb MADV_DONTNEED processing

Message ID 20221111232628.290160-4-mike.kravetz@oracle.com (mailing list archive)
State New
Headers show
Series fix hugetlb MADV_DONTNEED vma_lock handling | expand

Commit Message

Mike Kravetz Nov. 11, 2022, 11:26 p.m. UTC
madvise(MADV_DONTNEED) ends up calling zap_page_range() to clear page
tables associated with the address range.  For hugetlb vmas,
zap_page_range will call __unmap_hugepage_range_final.  However,
__unmap_hugepage_range_final assumes the passed vma is about to be removed
and deletes the vma_lock to prevent pmd sharing as the vma is on the way
out.  In the case of madvise(MADV_DONTNEED) the vma remains, but the
missing vma_lock prevents pmd sharing and could potentially lead to issues
with truncation/fault races.

This issue was originally reported here [1] as a BUG triggered in
page_try_dup_anon_rmap.  Prior to the introduction of the hugetlb
vma_lock, __unmap_hugepage_range_final cleared the VM_MAYSHARE flag to
prevent pmd sharing.  Subsequent faults on this vma were confused as
VM_MAYSHARE indicates a sharable vma, but was not set so page_mapping was
not set in new pages added to the page table.  This resulted in pages that
appeared anonymous in a VM_SHARED vma and triggered the BUG.

Address issue by adding a new zap flag ZAP_FLAG_UNMAP to indicate an unmap
call from unmap_vmas().  This is used to indicate the 'final' unmapping of
a hugetlb vma.  When called via MADV_DONTNEED, this flag is not set and the
vm_lock is not deleted.

[1] https://lore.kernel.org/lkml/CAO4mrfdLMXsao9RF4fUE8-Wfde8xmjsKrTNMNC9wjUb6JudD0g@mail.gmail.com/
Fixes: 90e7e7f5ef3f ("mm: enable MADV_DONTNEED for hugetlb mappings")
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Reported-by: Wei Chen <harperchen1110@gmail.com>
Cc: <stable@vger.kernel.org>
---
 include/linux/mm.h |  2 ++
 mm/hugetlb.c       | 27 ++++++++++++++++-----------
 mm/memory.c        |  2 +-
 3 files changed, 19 insertions(+), 12 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9e7cad65dfde..d0e8d5007343 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1897,6 +1897,8 @@  struct zap_details {
  * default, the flag is not set.
  */
 #define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+/* Set in unmap_vmas() to indicate a final unmap call.  Only used by hugetlb */
+#define  ZAP_FLAG_UNMAP              ((__force zap_flags_t) BIT(1))
 
 #ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 205c67c6787a..0cdefa63f474 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5202,17 +5202,22 @@  void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 	/* mmu notification performed in caller */
 	__unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags);
 
-	/*
-	 * Unlock and free the vma lock before releasing i_mmap_rwsem.  When
-	 * the vma_lock is freed, this makes the vma ineligible for pmd
-	 * sharing.  And, i_mmap_rwsem is required to set up pmd sharing.
-	 * This is important as page tables for this unmapped range will
-	 * be asynchrously deleted.  If the page tables are shared, there
-	 * will be issues when accessed by someone else.
-	 */
-	__hugetlb_vma_unlock_write_free(vma);
-
-	i_mmap_unlock_write(vma->vm_file->f_mapping);
+	if (zap_flags & ZAP_FLAG_UNMAP) {	/* final unmap */
+		/*
+		 * Unlock and free the vma lock before releasing i_mmap_rwsem.
+		 * When the vma_lock is freed, this makes the vma ineligible
+		 * for pmd sharing.  And, i_mmap_rwsem is required to set up
+		 * pmd sharing.  This is important as page tables for this
+		 * unmapped range will be asynchrously deleted.  If the page
+		 * tables are shared, there will be issues when accessed by
+		 * someone else.
+		 */
+		__hugetlb_vma_unlock_write_free(vma);
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+	} else {
+		i_mmap_unlock_write(vma->vm_file->f_mapping);
+		hugetlb_vma_unlock_write(vma);
+	}
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
diff --git a/mm/memory.c b/mm/memory.c
index ebdbd395cfad..2d453736f87c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1673,7 +1673,7 @@  void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 {
 	struct mmu_notifier_range range;
 	struct zap_details details = {
-		.zap_flags = ZAP_FLAG_DROP_MARKER,
+		.zap_flags = ZAP_FLAG_DROP_MARKER | ZAP_FLAG_UNMAP,
 		/* Careful - we need to zap private pages too! */
 		.even_cows = true,
 	};