dax: fix PMD data corruption when fault races with write

This is based on a patch from Jan Kara that fixed the equivalent race in
the DAX PTE fault path.

Currently DAX PMD read fault can race with write(2) in the following
way:

CPU1 - write(2)                 CPU2 - read fault
                                dax_iomap_pmd_fault()
                                  ->iomap_begin() - sees hole

dax_iomap_rw()
  iomap_apply()
    ->iomap_begin - allocates blocks
    dax_iomap_actor()
      invalidate_inode_pages2_range()
        - there's nothing to invalidate

                                  grab_mapping_entry()
				  - we add huge zero page to the radix tree
				    and map it to page tables

The result is that hole page is mapped into page tables (and thus zeros
are seen in mmap) while file has data written in that place.

Fix the problem by locking exception entry before mapping blocks for the
fault.  That way we are sure invalidate_inode_pages2_range() call for
racing write will either block on entry lock waiting for the fault to
finish (and unmap stale page tables after that) or read fault will see
already allocated blocks by write(2).

Fixes: 9f141d6 ("dax: Call ->iomap_begin without entry lock during dax fault")
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ross Zwisler <[email protected]>
Reviewed-by: Jan Kara <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

fs/dax.c

@@ -1387,6 +1387,16 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
+	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto fallback;
+
 	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
@@ -1395,38 +1405,26 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto fallback;
+		goto unlock_entry;
 
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
-	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto finish_iomap;
-
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
 		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto unlock_entry;
+			break;
 		result = dax_pmd_load_hole(vmf, &iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
 	}
 
- unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
@@ -1442,6 +1440,8 @@ static int dax_iomap_pmd_fault(struct vm_fault *vmf,
 		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
 				&iomap);
 	}
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
 		split_huge_pmd(vma, vmf->pmd, vmf->address);