Merge tag 'ovl-update-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs

Pull overlayfs updates from Miklos Szeredi:
 "This contains two new features:

   - Stack file operations: this allows removal of several hacks from
     the VFS, proper interaction of read-only open files with copy-up,
     possibility to implement fs modifying ioctls properly, and others.

   - Metadata only copy-up: when file is on lower layer and only
     metadata is modified (except size) then only copy up the metadata
     and continue to use the data from the lower file"

* tag 'ovl-update-4.19' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs: (66 commits)
  ovl: Enable metadata only feature
  ovl: Do not do metacopy only for ioctl modifying file attr
  ovl: Do not do metadata only copy-up for truncate operation
  ovl: add helper to force data copy-up
  ovl: Check redirect on index as well
  ovl: Set redirect on upper inode when it is linked
  ovl: Set redirect on metacopy files upon rename
  ovl: Do not set dentry type ORIGIN for broken hardlinks
  ovl: Add an inode flag OVL_CONST_INO
  ovl: Treat metacopy dentries as type OVL_PATH_MERGE
  ovl: Check redirects for metacopy files
  ovl: Move some dir related ovl_lookup_single() code in else block
  ovl: Do not expose metacopy only dentry from d_real()
  ovl: Open file with data except for the case of fsync
  ovl: Add helper ovl_inode_realdata()
  ovl: Store lower data inode in ovl_inode
  ovl: Fix ovl_getattr() to get number of blocks from lower
  ovl: Add helper ovl_dentry_lowerdata() to get lower data dentry
  ovl: Copy up meta inode data from lowest data inode
  ovl: Modify ovl_lookup() and friends to lookup metacopy dentry
  ...

1 files changed, 246 insertions, 6 deletions

diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 6f1078028c66..8cfb62cc8672 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -133,8 +133,10 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 		 * Non-dir dentry can hold lower dentry of its copy up origin.
 		 */
 		if (oe->numlower) {
-			type |= __OVL_PATH_ORIGIN;
-			if (d_is_dir(dentry))
+			if (ovl_test_flag(OVL_CONST_INO, d_inode(dentry)))
+				type |= __OVL_PATH_ORIGIN;
+			if (d_is_dir(dentry) ||
+			    !ovl_has_upperdata(d_inode(dentry)))
 				type |= __OVL_PATH_MERGE;
 		}
 	} else {
@@ -164,6 +166,18 @@ void ovl_path_lower(struct dentry *dentry, struct path *path)
 	}
 }
 
+void ovl_path_lowerdata(struct dentry *dentry, struct path *path)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	if (oe->numlower) {
+		path->mnt = oe->lowerstack[oe->numlower - 1].layer->mnt;
+		path->dentry = oe->lowerstack[oe->numlower - 1].dentry;
+	} else {
+		*path = (struct path) { };
+	}
+}
+
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
 {
 	enum ovl_path_type type = ovl_path_type(dentry);
@@ -195,6 +209,19 @@ struct ovl_layer *ovl_layer_lower(struct dentry *dentry)
 	return oe->numlower ? oe->lowerstack[0].layer : NULL;
 }
 
+/*
+ * ovl_dentry_lower() could return either a data dentry or metacopy dentry
+ * dependig on what is stored in lowerstack[0]. At times we need to find
+ * lower dentry which has data (and not metacopy dentry). This helper
+ * returns the lower data dentry.
+ */
+struct dentry *ovl_dentry_lowerdata(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return oe->numlower ? oe->lowerstack[oe->numlower - 1].dentry : NULL;
+}
+
 struct dentry *ovl_dentry_real(struct dentry *dentry)
 {
 	return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);
@@ -222,6 +249,26 @@ struct inode *ovl_inode_real(struct inode *inode)
 	return ovl_inode_upper(inode) ?: ovl_inode_lower(inode);
 }
 
+/* Return inode which contains lower data. Do not return metacopy */
+struct inode *ovl_inode_lowerdata(struct inode *inode)
+{
+	if (WARN_ON(!S_ISREG(inode->i_mode)))
+		return NULL;
+
+	return OVL_I(inode)->lowerdata ?: ovl_inode_lower(inode);
+}
+
+/* Return real inode which contains data. Does not return metacopy inode */
+struct inode *ovl_inode_realdata(struct inode *inode)
+{
+	struct inode *upperinode;
+
+	upperinode = ovl_inode_upper(inode);
+	if (upperinode && ovl_has_upperdata(inode))
+		return upperinode;
+
+	return ovl_inode_lowerdata(inode);
+}
 
 struct ovl_dir_cache *ovl_dir_cache(struct inode *inode)
 {
@@ -279,6 +326,62 @@ void ovl_dentry_set_upper_alias(struct dentry *dentry)
 	ovl_dentry_set_flag(OVL_E_UPPER_ALIAS, dentry);
 }
 
+static bool ovl_should_check_upperdata(struct inode *inode)
+{
+	if (!S_ISREG(inode->i_mode))
+		return false;
+
+	if (!ovl_inode_lower(inode))
+		return false;
+
+	return true;
+}
+
+bool ovl_has_upperdata(struct inode *inode)
+{
+	if (!ovl_should_check_upperdata(inode))
+		return true;
+
+	if (!ovl_test_flag(OVL_UPPERDATA, inode))
+		return false;
+	/*
+	 * Pairs with smp_wmb() in ovl_set_upperdata(). Main user of
+	 * ovl_has_upperdata() is ovl_copy_up_meta_inode_data(). Make sure
+	 * if setting of OVL_UPPERDATA is visible, then effects of writes
+	 * before that are visible too.
+	 */
+	smp_rmb();
+	return true;
+}
+
+void ovl_set_upperdata(struct inode *inode)
+{
+	/*
+	 * Pairs with smp_rmb() in ovl_has_upperdata(). Make sure
+	 * if OVL_UPPERDATA flag is visible, then effects of write operations
+	 * before it are visible as well.
+	 */
+	smp_wmb();
+	ovl_set_flag(OVL_UPPERDATA, inode);
+}
+
+/* Caller should hold ovl_inode->lock */
+bool ovl_dentry_needs_data_copy_up_locked(struct dentry *dentry, int flags)
+{
+	if (!ovl_open_flags_need_copy_up(flags))
+		return false;
+
+	return !ovl_test_flag(OVL_UPPERDATA, d_inode(dentry));
+}
+
+bool ovl_dentry_needs_data_copy_up(struct dentry *dentry, int flags)
+{
+	if (!ovl_open_flags_need_copy_up(flags))
+		return false;
+
+	return !ovl_has_upperdata(d_inode(dentry));
+}
+
 bool ovl_redirect_dir(struct super_block *sb)
 {
 	struct ovl_fs *ofs = sb->s_fs_info;
@@ -300,7 +403,7 @@ void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect)
 }
 
 void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
-		    struct dentry *lowerdentry)
+		    struct dentry *lowerdentry, struct dentry *lowerdata)
 {
 	struct inode *realinode = d_inode(upperdentry ?: lowerdentry);
 
@@ -308,8 +411,11 @@ void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
 		OVL_I(inode)->__upperdentry = upperdentry;
 	if (lowerdentry)
 		OVL_I(inode)->lower = igrab(d_inode(lowerdentry));
+	if (lowerdata)
+		OVL_I(inode)->lowerdata = igrab(d_inode(lowerdata));
 
 	ovl_copyattr(realinode, inode);
+	ovl_copyflags(realinode, inode);
 	if (!inode->i_ino)
 		inode->i_ino = realinode->i_ino;
 }
@@ -333,7 +439,7 @@ void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
 	}
 }
 
-void ovl_dentry_version_inc(struct dentry *dentry, bool impurity)
+static void ovl_dentry_version_inc(struct dentry *dentry, bool impurity)
 {
 	struct inode *inode = d_inode(dentry);
 
@@ -348,6 +454,14 @@ void ovl_dentry_version_inc(struct dentry *dentry, bool impurity)
 		OVL_I(inode)->version++;
 }
 
+void ovl_dir_modified(struct dentry *dentry, bool impurity)
+{
+	/* Copy mtime/ctime */
+	ovl_copyattr(d_inode(ovl_dentry_upper(dentry)), d_inode(dentry));
+
+	ovl_dentry_version_inc(dentry, impurity);
+}
+
 u64 ovl_dentry_version_get(struct dentry *dentry)
 {
 	struct inode *inode = d_inode(dentry);
@@ -368,13 +482,51 @@ struct file *ovl_path_open(struct path *path, int flags)
 	return dentry_open(path, flags | O_NOATIME, current_cred());
 }
 
-int ovl_copy_up_start(struct dentry *dentry)
+/* Caller should hold ovl_inode->lock */
+static bool ovl_already_copied_up_locked(struct dentry *dentry, int flags)
+{
+	bool disconnected = dentry->d_flags & DCACHE_DISCONNECTED;
+
+	if (ovl_dentry_upper(dentry) &&
+	    (ovl_dentry_has_upper_alias(dentry) || disconnected) &&
+	    !ovl_dentry_needs_data_copy_up_locked(dentry, flags))
+		return true;
+
+	return false;
+}
+
+bool ovl_already_copied_up(struct dentry *dentry, int flags)
+{
+	bool disconnected = dentry->d_flags & DCACHE_DISCONNECTED;
+
+	/*
+	 * Check if copy-up has happened as well as for upper alias (in
+	 * case of hard links) is there.
+	 *
+	 * Both checks are lockless:
+	 *  - false negatives: will recheck under oi->lock
+	 *  - false positives:
+	 *    + ovl_dentry_upper() uses memory barriers to ensure the
+	 *      upper dentry is up-to-date
+	 *    + ovl_dentry_has_upper_alias() relies on locking of
+	 *      upper parent i_rwsem to prevent reordering copy-up
+	 *      with rename.
+	 */
+	if (ovl_dentry_upper(dentry) &&
+	    (ovl_dentry_has_upper_alias(dentry) || disconnected) &&
+	    !ovl_dentry_needs_data_copy_up(dentry, flags))
+		return true;
+
+	return false;
+}
+
+int ovl_copy_up_start(struct dentry *dentry, int flags)
 {
 	struct ovl_inode *oi = OVL_I(d_inode(dentry));
 	int err;
 
 	err = mutex_lock_interruptible(&oi->lock);
-	if (!err && ovl_dentry_has_upper_alias(dentry)) {
+	if (!err && ovl_already_copied_up_locked(dentry, flags)) {
 		err = 1; /* Already copied up */
 		mutex_unlock(&oi->lock);
 	}
@@ -675,3 +827,91 @@ err:
 	pr_err("overlayfs: failed to lock workdir+upperdir\n");
 	return -EIO;
 }
+
+/* err < 0, 0 if no metacopy xattr, 1 if metacopy xattr found */
+int ovl_check_metacopy_xattr(struct dentry *dentry)
+{
+	int res;
+
+	/* Only regular files can have metacopy xattr */
+	if (!S_ISREG(d_inode(dentry)->i_mode))
+		return 0;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_METACOPY, NULL, 0);
+	if (res < 0) {
+		if (res == -ENODATA || res == -EOPNOTSUPP)
+			return 0;
+		goto out;
+	}
+
+	return 1;
+out:
+	pr_warn_ratelimited("overlayfs: failed to get metacopy (%i)\n", res);
+	return res;
+}
+
+bool ovl_is_metacopy_dentry(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	if (!d_is_reg(dentry))
+		return false;
+
+	if (ovl_dentry_upper(dentry)) {
+		if (!ovl_has_upperdata(d_inode(dentry)))
+			return true;
+		return false;
+	}
+
+	return (oe->numlower > 1);
+}
+
+char *ovl_get_redirect_xattr(struct dentry *dentry, int padding)
+{
+	int res;
+	char *s, *next, *buf = NULL;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, NULL, 0);
+	if (res < 0) {
+		if (res == -ENODATA || res == -EOPNOTSUPP)
+			return NULL;
+		goto fail;
+	}
+
+	buf = kzalloc(res + padding + 1, GFP_KERNEL);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	if (res == 0)
+		goto invalid;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_REDIRECT, buf, res);
+	if (res < 0)
+		goto fail;
+	if (res == 0)
+		goto invalid;
+
+	if (buf[0] == '/') {
+		for (s = buf; *s++ == '/'; s = next) {
+			next = strchrnul(s, '/');
+			if (s == next)
+				goto invalid;
+		}
+	} else {
+		if (strchr(buf, '/') != NULL)
+			goto invalid;
+	}
+
+	return buf;
+
+err_free:
+	kfree(buf);
+	return ERR_PTR(res);
+fail:
+	pr_warn_ratelimited("overlayfs: failed to get redirect (%i)\n", res);
+	goto err_free;
+invalid:
+	pr_warn_ratelimited("overlayfs: invalid redirect (%s)\n", buf);
+	res = -EINVAL;
+	goto err_free;
+}