From 4eb2b1dcd598f8489130405c81c60c289896d92a Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 14 Dec 2009 17:59:53 -0800 Subject: hugetlb: acquire the i_mmap_lock before walking the prio_tree to unmap a page When the owner of a mapping fails COW because a child process is holding a reference, the children VMAs are walked and the page is unmapped. The i_mmap_lock is taken for the unmapping of the page but not the walking of the prio_tree. In theory, that tree could be changing if the lock is not held. This patch takes the i_mmap_lock properly for the duration of the prio_tree walk. [hugh.dickins@tiscali.co.uk: Spotted the problem in the first place] Signed-off-by: Mel Gorman Acked-by: Hugh Dickins Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'mm/hugetlb.c') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2ef66a2a148d..6df8065039eb 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2237,6 +2237,12 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, + (vma->vm_pgoff >> PAGE_SHIFT); mapping = (struct address_space *)page_private(page); + /* + * Take the mapping lock for the duration of the table walk. As + * this mapping should be shared between all the VMAs, + * __unmap_hugepage_range() is called as the lock is already held + */ + spin_lock(&mapping->i_mmap_lock); vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) @@ -2250,10 +2256,11 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) - unmap_hugepage_range(iter_vma, + __unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), page); } + spin_unlock(&mapping->i_mmap_lock); return 1; } -- cgit v1.2.3-55-g7522