[PATCH] hugetlb: fix linked list corruption in unmap_hugepage_range()

commit fe1668ae5bf0145014c71797febd9ad5670d5d05 causes kernel to oops with
libhugetlbfs test suite.  The problem is that hugetlb pages can be shared
by multiple mappings.  Multiple threads can fight over page->lru in the
unmap path and bad things happen.  We now serialize __unmap_hugepage_range
to void concurrent linked list manipulation.  Such serialization is also
needed for shared page table page on hugetlb area.  This patch will fixed
the bug and also serve as a prepatch for shared page table.

Signed-off-by: Ken Chen <kenneth.w.chen@intel.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 22 insertions, 3 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 5e03b2f67b93..4ee3f006b861 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -293,7 +293,7 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff)
                 if (h_vm_pgoff >= h_pgoff)
                         v_offset = 0;
 
-                unmap_hugepage_range(vma,
+                __unmap_hugepage_range(vma,
                                 vma->vm_start + v_offset, vma->vm_end);
         }
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c25a38d8f600..5081d27bfa27 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -17,6 +17,7 @@ int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
 int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *, struct page **, struct vm_area_struct **, unsigned long *, int *, int);
 void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
+void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
 int hugetlb_report_meminfo(char *);
 int hugetlb_report_node_meminfo(int, char *);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1d709ff528e1..2dbec90dc3ba 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -356,8 +356,8 @@ nomem:
         return -ENOMEM;
 }
 
-void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
-                          unsigned long end)
+void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+                            unsigned long end)
 {
         struct mm_struct *mm = vma->vm_mm;
         unsigned long address;
@@ -398,6 +398,24 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
         }
 }
 
+void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+                          unsigned long end)
+{
+        /*
+         * It is undesirable to test vma->vm_file as it should be non-null
+         * for valid hugetlb area. However, vm_file will be NULL in the error
+         * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails,
+         * do_mmap_pgoff() nullifies vma->vm_file before calling this function
+         * to clean up. Since no pte has actually been setup, it is safe to
+         * do nothing in this case.
+         */
+        if (vma->vm_file) {
+                spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+                __unmap_hugepage_range(vma, start, end);
+                spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+        }
+}
+
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
                         unsigned long address, pte_t *ptep, pte_t pte)
 {