[PATCH] vmtrunc: vm_truncate_count race caution

Fix some unlikely races in respect of vm_truncate_count.

Firstly, it's supposed to be guarded by i_mmap_lock, but some places copy a
vma structure by *new_vma = *old_vma: if the compiler implements that with a
bytewise copy, new_vma->vm_truncate_count could be munged, and new_vma later
appear up-to-date when it's not; so set it properly once under lock.

vma_link set vm_truncate_count to mapping->truncate_count when adding an empty
vma: if new vmas are being added profusely while vmtruncate is in progess,
this lets them be skipped without scanning.

vma_adjust has vm_truncate_count problem much like it had with anon_vma under
mprotect merge: when merging be careful not to leave vma marked as up-to-date
when it might not be, lest unmap_mapping_range in progress - set
vm_truncate_count 0 when in doubt.  Similarly when mremap moving ptes from one
vma to another.

Cut a little code from __anon_vma_merge: now vma_adjust sets "importer" in the
remove_next case (to get its vm_truncate_count right), its anon_vma is already
linked by the time __anon_vma_merge is called.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 24 insertions, 15 deletions

diff --git a/mm/mmap.c b/mm/mmap.c
index 98ae4fcd2e0019..cfa09ba8b826d3 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -308,8 +308,10 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (vma->vm_file)
 		mapping = vma->vm_file->f_mapping;
 
-	if (mapping)
+	if (mapping) {
 		spin_lock(&mapping->i_mmap_lock);
+		vma->vm_truncate_count = mapping->truncate_count;
+	}
 	anon_vma_lock(vma);
 
 	__vma_link(mm, vma, prev, rb_link, rb_parent);
@@ -380,6 +382,7 @@ void vma_adjust(struct vm_area_struct *vma, unsigned long start,
 again:			remove_next = 1 + (end > next->vm_end);
 			end = next->vm_end;
 			anon_vma = next->anon_vma;
+			importer = vma;
 		} else if (end > next->vm_start) {
 			/*
 			 * vma expands, overlapping part of the next:
@@ -405,7 +408,16 @@ again:			remove_next = 1 + (end > next->vm_end);
 		if (!(vma->vm_flags & VM_NONLINEAR))
 			root = &mapping->i_mmap;
 		spin_lock(&mapping->i_mmap_lock);
+		if (importer &&
+		    vma->vm_truncate_count != next->vm_truncate_count) {
+			/*
+			 * unmap_mapping_range might be in progress:
+			 * ensure that the expanding vma is rescanned.
+			 */
+			importer->vm_truncate_count = 0;
+		}
 		if (insert) {
+			insert->vm_truncate_count = vma->vm_truncate_count;
 			/*
 			 * Put into prio_tree now, so instantiated pages
 			 * are visible to arm/parisc __flush_dcache_page
diff --git a/mm/mremap.c b/mm/mremap.c
index daf4ac4f1b2a77..ebdf621984ac42 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -100,7 +100,7 @@ static inline pte_t *alloc_one_pte_map(struct mm_struct *mm, unsigned long addr)
 
 static int
 move_one_page(struct vm_area_struct *vma, unsigned long old_addr,
-		unsigned long new_addr)
+		struct vm_area_struct *new_vma, unsigned long new_addr)
 {
 	struct address_space *mapping = NULL;
 	struct mm_struct *mm = vma->vm_mm;
@@ -116,6 +116,9 @@ move_one_page(struct vm_area_struct *vma, unsigned long old_addr,
 		 */
 		mapping = vma->vm_file->f_mapping;
 		spin_lock(&mapping->i_mmap_lock);
+		if (new_vma->vm_truncate_count &&
+		    new_vma->vm_truncate_count != vma->vm_truncate_count)
+			new_vma->vm_truncate_count = 0;
 	}
 	spin_lock(&mm->page_table_lock);
 
@@ -162,8 +165,8 @@ move_one_page(struct vm_area_struct *vma, unsigned long old_addr,
 }
 
 static unsigned long move_page_tables(struct vm_area_struct *vma,
-		unsigned long new_addr, unsigned long old_addr,
-		unsigned long len)
+		unsigned long old_addr, struct vm_area_struct *new_vma,
+		unsigned long new_addr, unsigned long len)
 {
 	unsigned long offset;
 
@@ -175,7 +178,8 @@ static unsigned long move_page_tables(struct vm_area_struct *vma,
 	 * only a few pages.. This also makes error recovery easier.
 	 */
 	for (offset = 0; offset < len; offset += PAGE_SIZE) {
-		if (move_one_page(vma, old_addr+offset, new_addr+offset) < 0)
+		if (move_one_page(vma, old_addr + offset,
+				new_vma, new_addr + offset) < 0)
 			break;
 		cond_resched();
 	}
@@ -206,14 +210,14 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (!new_vma)
 		return -ENOMEM;
 
-	moved_len = move_page_tables(vma, new_addr, old_addr, old_len);
+	moved_len = move_page_tables(vma, old_addr, new_vma, new_addr, old_len);
 	if (moved_len < old_len) {
 		/*
 		 * On error, move entries back from new area to old,
 		 * which will succeed since page tables still there,
 		 * and then proceed to unmap new area instead of old.
 		 */
-		move_page_tables(new_vma, old_addr, new_addr, moved_len);
+		move_page_tables(new_vma, new_addr, vma, old_addr, moved_len);
 		vma = new_vma;
 		old_len = new_len;
 		old_addr = new_addr;
diff --git a/mm/rmap.c b/mm/rmap.c
index 8e198864146a44..4ff8183fa18e9e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -121,14 +121,7 @@ int anon_vma_prepare(struct vm_area_struct *vma)
 
 void __anon_vma_merge(struct vm_area_struct *vma, struct vm_area_struct *next)
 {
-	if (!vma->anon_vma) {
-		BUG_ON(!next->anon_vma);
-		vma->anon_vma = next->anon_vma;
-		list_add(&vma->anon_vma_node, &next->anon_vma_node);
-	} else {
-		/* if they're both non-null they must be the same */
-		BUG_ON(vma->anon_vma != next->anon_vma);
-	}
+	BUG_ON(vma->anon_vma != next->anon_vma);
 	list_del(&next->anon_vma_node);
 }