nommu: fix shared mmap after truncate shrinkage problems

Fix a problem in NOMMU mmap with ramfs whereby a shared mmap can happen
over the end of a truncation.  The problem is that
ramfs_nommu_check_mappings() checks that the reduced file size against the
VMA tree, but not the vm_region tree.

The following sequence of events can cause the problem:

	fd = open("/tmp/x", O_RDWR|O_TRUNC|O_CREAT, 0600);
	ftruncate(fd, 32 * 1024);
	a = mmap(NULL, 32 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
	b = mmap(NULL, 16 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
	munmap(a, 32 * 1024);
	ftruncate(fd, 16 * 1024);
	c = mmap(NULL, 32 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);

Mapping 'a' creates a vm_region covering 32KB of the file.  Mapping 'b'
sees that the vm_region from 'a' is covering the region it wants and so
shares it, pinning it in memory.

Mapping 'a' then goes away and the file is truncated to the end of VMA
'b'.  However, the region allocated by 'a' is still in effect, and has
_not_ been reduced.

Mapping 'c' is then created, and because there's a vm_region covering the
desired region, get_unmapped_area() is _not_ called to repeat the check,
and the mapping is granted, even though the pages from the latter half of
the mapping have been discarded.

However:

	d = mmap(NULL, 16 * 1024, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);

Mapping 'd' should work, and should end up sharing the region allocated by
'a'.

To deal with this, we shrink the vm_region struct during the truncation,
lest do_mmap_pgoff() take it as licence to share the full region
automatically without calling the get_unmapped_area() file op again.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Al Viro <viro@zeniv.linux.org.uk>
Cc: Greg Ungerer <gerg@snapgear.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 62 insertions, 0 deletions

diff --git a/mm/nommu.c b/mm/nommu.c
index 32be0cf51ba6..48a2ecfaf059 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1914,3 +1914,65 @@ int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, in
 	mmput(mm);
 	return len;
 }
+
+/**
+ * nommu_shrink_inode_mappings - Shrink the shared mappings on an inode
+ * @inode: The inode to check
+ * @size: The current filesize of the inode
+ * @newsize: The proposed filesize of the inode
+ *
+ * Check the shared mappings on an inode on behalf of a shrinking truncate to
+ * make sure that that any outstanding VMAs aren't broken and then shrink the
+ * vm_regions that extend that beyond so that do_mmap_pgoff() doesn't
+ * automatically grant mappings that are too large.
+ */
+int nommu_shrink_inode_mappings(struct inode *inode, size_t size,
+				size_t newsize)
+{
+	struct vm_area_struct *vma;
+	struct prio_tree_iter iter;
+	struct vm_region *region;
+	pgoff_t low, high;
+	size_t r_size, r_top;
+
+	low = newsize >> PAGE_SHIFT;
+	high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	down_write(&nommu_region_sem);
+
+	/* search for VMAs that fall within the dead zone */
+	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+			      low, high) {
+		/* found one - only interested if it's shared out of the page
+		 * cache */
+		if (vma->vm_flags & VM_SHARED) {
+			up_write(&nommu_region_sem);
+			return -ETXTBSY; /* not quite true, but near enough */
+		}
+	}
+
+	/* reduce any regions that overlap the dead zone - if in existence,
+	 * these will be pointed to by VMAs that don't overlap the dead zone
+	 *
+	 * we don't check for any regions that start beyond the EOF as there
+	 * shouldn't be any
+	 */
+	vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap,
+			      0, ULONG_MAX) {
+		if (!(vma->vm_flags & VM_SHARED))
+			continue;
+
+		region = vma->vm_region;
+		r_size = region->vm_top - region->vm_start;
+		r_top = (region->vm_pgoff << PAGE_SHIFT) + r_size;
+
+		if (r_top > newsize) {
+			region->vm_top -= r_top - newsize;
+			if (region->vm_end > region->vm_top)
+				region->vm_end = region->vm_top;
+		}
+	}
+
+	up_write(&nommu_region_sem);
+	return 0;
+}