ovl: A new xattr OVL_XATTR_METACOPY for file on upper

Now we will have the capability to have upper inodes which might be only
metadata copy up and data is still on lower inode.  So add a new xattr
OVL_XATTR_METACOPY to distinguish between two cases.

Presence of OVL_XATTR_METACOPY reflects that file has been copied up
metadata only and and data will be copied up later from lower origin.  So
this xattr is set when a metadata copy takes place and cleared when data
copy takes place.

We also use a bit in ovl_inode->flags to cache OVL_UPPERDATA which reflects
whether ovl inode has data or not (as opposed to metadata only copy up).

If a file is copied up metadata only and later when same file is opened for
WRITE, then data copy up takes place.  We copy up data, remove METACOPY
xattr and then set the UPPERDATA flag in ovl_inode->flags.  While all these
operations happen with oi->lock held, read side of oi->flags can be
lockless.  That is another thread on another cpu can check if UPPERDATA
flag is set or not.

So this gives us an ordering requirement w.r.t UPPERDATA flag.  That is, if
another cpu sees UPPERDATA flag set, then it should be guaranteed that
effects of data copy up and remove xattr operations are also visible.

For example.

	CPU1				CPU2
ovl_open()				acquire(oi->lock)
 ovl_open_maybe_copy_up()                ovl_copy_up_data()
  open_open_need_copy_up()		 vfs_removexattr()
   ovl_already_copied_up()
    ovl_dentry_needs_data_copy_up()	 ovl_set_flag(OVL_UPPERDATA)
     ovl_test_flag(OVL_UPPERDATA)       release(oi->lock)

Say CPU2 is copying up data and in the end sets UPPERDATA flag.  But if
CPU1 perceives the effects of setting UPPERDATA flag but not the effects of
preceding operations (ex. upper that is not fully copied up), it will be a
problem.

Hence this patch introduces smp_wmb() on setting UPPERDATA flag operation
and smp_rmb() on UPPERDATA flag test operation.

May be some other lock or barrier is already covering it. But I am not sure
what that is and is it obvious enough that we will not break it in future.

So hence trying to be safe here and introducing barriers explicitly for
UPPERDATA flag/bit.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

1 files changed, 51 insertions, 5 deletions

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aa3c62a4e462..7e6664d6643d 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -180,6 +180,16 @@ out_fput:
 	return error;
 }
 
+static int ovl_set_size(struct dentry *upperdentry, struct kstat *stat)
+{
+	struct iattr attr = {
+		.ia_valid = ATTR_SIZE,
+		.ia_size = stat->size,
+	};
+
+	return notify_change(upperdentry, &attr, NULL);
+}
+
 static int ovl_set_timestamps(struct dentry *upperdentry, struct kstat *stat)
 {
 	struct iattr attr = {
@@ -520,8 +530,18 @@ static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
 			return err;
 	}
 
+	if (c->metacopy) {
+		err = ovl_check_setxattr(c->dentry, temp, OVL_XATTR_METACOPY,
+					 NULL, 0, -EOPNOTSUPP);
+		if (err)
+			return err;
+	}
+
 	inode_lock(temp->d_inode);
-	err = ovl_set_attr(temp, &c->stat);
+	if (c->metacopy)
+		err = ovl_set_size(temp, &c->stat);
+	if (!err)
+		err = ovl_set_attr(temp, &c->stat);
 	inode_unlock(temp->d_inode);
 
 	return err;
@@ -559,6 +579,8 @@ static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
 	if (err)
 		goto out;
 
+	if (!c->metacopy)
+		ovl_set_upperdata(d_inode(c->dentry));
 	inode = d_inode(c->dentry);
 	ovl_inode_update(inode, newdentry);
 	if (S_ISDIR(inode->i_mode))
@@ -681,6 +703,28 @@ static bool ovl_need_meta_copy_up(struct dentry *dentry, umode_t mode,
 	return true;
 }
 
+/* Copy up data of an inode which was copied up metadata only in the past. */
+static int ovl_copy_up_meta_inode_data(struct ovl_copy_up_ctx *c)
+{
+	struct path upperpath;
+	int err;
+
+	ovl_path_upper(c->dentry, &upperpath);
+	if (WARN_ON(upperpath.dentry == NULL))
+		return -EIO;
+
+	err = ovl_copy_up_data(&c->lowerpath, &upperpath, c->stat.size);
+	if (err)
+		return err;
+
+	err = vfs_removexattr(upperpath.dentry, OVL_XATTR_METACOPY);
+	if (err)
+		return err;
+
+	ovl_set_upperdata(d_inode(c->dentry));
+	return err;
+}
+
 static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 			   int flags)
 {
@@ -726,7 +770,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 			return PTR_ERR(ctx.link);
 	}
 
-	err = ovl_copy_up_start(dentry);
+	err = ovl_copy_up_start(dentry, flags);
 	/* err < 0: interrupted, err > 0: raced with another copy-up */
 	if (unlikely(err)) {
 		if (err > 0)
@@ -736,6 +780,8 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 			err = ovl_do_copy_up(&ctx);
 		if (!err && parent && !ovl_dentry_has_upper_alias(dentry))
 			err = ovl_link_up(&ctx);
+		if (!err && ovl_dentry_needs_data_copy_up_locked(dentry, flags))
+			err = ovl_copy_up_meta_inode_data(&ctx);
 		ovl_copy_up_end(dentry);
 	}
 	do_delayed_call(&done);
@@ -761,7 +807,7 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 		struct dentry *next;
 		struct dentry *parent = NULL;
 
-		if (ovl_already_copied_up(dentry))
+		if (ovl_already_copied_up(dentry, flags))
 			break;
 
 		next = dget(dentry);
@@ -789,13 +835,13 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
 {
 	/* Copy up of disconnected dentry does not set upper alias */
-	if (ovl_already_copied_up(dentry))
+	if (ovl_already_copied_up(dentry, flags))
 		return false;
 
 	if (special_file(d_inode(dentry)->i_mode))
 		return false;
 
-	if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC))
+	if (!ovl_open_flags_need_copy_up(flags))
 		return false;
 
 	return true;