Merge tag 'ovl-update-5.2' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/mszeredi/vfs

Pull overlayfs update from Miklos Szeredi:
 "Just bug fixes in this small update"

* tag 'ovl-update-5.2' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs:
  ovl: relax WARN_ON() for overlapping layers use case
  ovl: check the capability before cred overridden
  ovl: do not generate duplicate fsnotify events for "fake" path
  ovl: support stacked SEEK_HOLE/SEEK_DATA
  ovl: fix missing upper fs freeze protection on copy up for ioctl

fs/overlayfs/copy_up.c

@@ -909,14 +909,14 @@ static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
 	return true;
 }
 
-int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
+int ovl_maybe_copy_up(struct dentry *dentry, int flags)
 {
 	int err = 0;
 
-	if (ovl_open_need_copy_up(dentry, file_flags)) {
+	if (ovl_open_need_copy_up(dentry, flags)) {
 		err = ovl_want_write(dentry);
 		if (!err) {
-			err = ovl_copy_up_flags(dentry, file_flags);
+			err = ovl_copy_up_flags(dentry, flags);
 			ovl_drop_write(dentry);
 		}
 	}

fs/overlayfs/dir.c

@@ -260,7 +260,7 @@ static int ovl_instantiate(struct dentry *dentry, struct inode *inode,
 		 * hashed directory inode aliases.
 		 */
 		inode = ovl_get_inode(dentry->d_sb, &oip);
-		if (WARN_ON(IS_ERR(inode)))
+		if (IS_ERR(inode))
 			return PTR_ERR(inode);
 	} else {
 		WARN_ON(ovl_inode_real(inode) != d_inode(newdentry));

fs/overlayfs/file.c

@@ -11,6 +11,7 @@
 #include <linux/mount.h>
 #include <linux/xattr.h>
 #include <linux/uio.h>
+#include <linux/uaccess.h>
 #include "overlayfs.h"
 
 static char ovl_whatisit(struct inode *inode, struct inode *realinode)
@@ -29,10 +30,11 @@ static struct file *ovl_open_realfile(const struct file *file,
 	struct inode *inode = file_inode(file);
 	struct file *realfile;
 	const struct cred *old_cred;
+	int flags = file->f_flags | O_NOATIME | FMODE_NONOTIFY;
 
 	old_cred = ovl_override_creds(inode->i_sb);
-	realfile = open_with_fake_path(&file->f_path, file->f_flags | O_NOATIME,
-				       realinode, current_cred());
+	realfile = open_with_fake_path(&file->f_path, flags, realinode,
+				       current_cred());
 	revert_creds(old_cred);
 
 	pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n",
@@ -50,7 +52,7 @@ static int ovl_change_flags(struct file *file, unsigned int flags)
 	int err;
 
 	/* No atime modificaton on underlying */
-	flags |= O_NOATIME;
+	flags |= O_NOATIME | FMODE_NONOTIFY;
 
 	/* If some flag changed that cannot be changed then something's amiss */
 	if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK))
@@ -116,11 +118,10 @@ static int ovl_real_fdget(const struct file *file, struct fd *real)
 
 static int ovl_open(struct inode *inode, struct file *file)
 {
-	struct dentry *dentry = file_dentry(file);
 	struct file *realfile;
 	int err;
 
-	err = ovl_open_maybe_copy_up(dentry, file->f_flags);
+	err = ovl_maybe_copy_up(file_dentry(file), file->f_flags);
 	if (err)
 		return err;
 
@@ -145,11 +146,47 @@ static int ovl_release(struct inode *inode, struct file *file)
 
 static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
 {
-	struct inode *realinode = ovl_inode_real(file_inode(file));
+	struct inode *inode = file_inode(file);
+	struct fd real;
+	const struct cred *old_cred;
+	ssize_t ret;
+
+	/*
+	 * The two special cases below do not need to involve real fs,
+	 * so we can optimizing concurrent callers.
+	 */
+	if (offset == 0) {
+		if (whence == SEEK_CUR)
+			return file->f_pos;
+
+		if (whence == SEEK_SET)
+			return vfs_setpos(file, 0, 0);
+	}
+
+	ret = ovl_real_fdget(file, &real);
+	if (ret)
+		return ret;
+
+	/*
+	 * Overlay file f_pos is the master copy that is preserved
+	 * through copy up and modified on read/write, but only real
+	 * fs knows how to SEEK_HOLE/SEEK_DATA and real fs may impose
+	 * limitations that are more strict than ->s_maxbytes for specific
+	 * files, so we use the real file to perform seeks.
+	 */
+	inode_lock(inode);
+	real.file->f_pos = file->f_pos;
+
+	old_cred = ovl_override_creds(inode->i_sb);
+	ret = vfs_llseek(real.file, offset, whence);
+	revert_creds(old_cred);
+
+	file->f_pos = real.file->f_pos;
+	inode_unlock(inode);
+
+	fdput(real);
 
-	return generic_file_llseek_size(file, offset, whence,
-					realinode->i_sb->s_maxbytes,
-					i_size_read(realinode));
+	return ret;
 }
 
 static void ovl_file_accessed(struct file *file)
@@ -372,34 +409,76 @@ static long ovl_real_ioctl(struct file *file, unsigned int cmd,
 	return ret;
 }
 
-static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+static unsigned int ovl_get_inode_flags(struct inode *inode)
+{
+	unsigned int flags = READ_ONCE(inode->i_flags);
+	unsigned int ovl_iflags = 0;
+
+	if (flags & S_SYNC)
+		ovl_iflags |= FS_SYNC_FL;
+	if (flags & S_APPEND)
+		ovl_iflags |= FS_APPEND_FL;
+	if (flags & S_IMMUTABLE)
+		ovl_iflags |= FS_IMMUTABLE_FL;
+	if (flags & S_NOATIME)
+		ovl_iflags |= FS_NOATIME_FL;
+
+	return ovl_iflags;
+}
+
+static long ovl_ioctl_set_flags(struct file *file, unsigned long arg)
 {
 	long ret;
 	struct inode *inode = file_inode(file);
+	unsigned int flags;
+	unsigned int old_flags;
+
+	if (!inode_owner_or_capable(inode))
+		return -EACCES;
+
+	if (get_user(flags, (int __user *) arg))
+		return -EFAULT;
+
+	ret = mnt_want_write_file(file);
+	if (ret)
+		return ret;
+
+	inode_lock(inode);
+
+	/* Check the capability before cred override */
+	ret = -EPERM;
+	old_flags = ovl_get_inode_flags(inode);
+	if (((flags ^ old_flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		goto unlock;
+
+	ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY);
+	if (ret)
+		goto unlock;
+
+	ret = ovl_real_ioctl(file, FS_IOC_SETFLAGS, arg);
+
+	ovl_copyflags(ovl_inode_real(inode), inode);
+unlock:
+	inode_unlock(inode);
+
+	mnt_drop_write_file(file);
+
+	return ret;
+
+}
+
+static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	long ret;
 
 	switch (cmd) {
 	case FS_IOC_GETFLAGS:
 		ret = ovl_real_ioctl(file, cmd, arg);
 		break;
 
 	case FS_IOC_SETFLAGS:
-		if (!inode_owner_or_capable(inode))
-			return -EACCES;
-
-		ret = mnt_want_write_file(file);
-		if (ret)
-			return ret;
-
-		ret = ovl_copy_up_with_data(file_dentry(file));
-		if (!ret) {
-			ret = ovl_real_ioctl(file, cmd, arg);
-
-			inode_lock(inode);
-			ovl_copyflags(ovl_inode_real(inode), inode);
-			inode_unlock(inode);
-		}
-
-		mnt_drop_write_file(file);
+		ret = ovl_ioctl_set_flags(file, arg);
 		break;
 
 	default:

fs/overlayfs/inode.c

@@ -832,7 +832,7 @@ struct inode *ovl_get_inode(struct super_block *sb,
 	int fsid = bylower ? oip->lowerpath->layer->fsid : 0;
 	bool is_dir, metacopy = false;
 	unsigned long ino = 0;
-	int err = -ENOMEM;
+	int err = oip->newinode ? -EEXIST : -ENOMEM;
 
 	if (!realinode)
 		realinode = d_inode(lowerdentry);
@@ -917,6 +917,7 @@ struct inode *ovl_get_inode(struct super_block *sb,
 	return inode;
 
 out_err:
+	pr_warn_ratelimited("overlayfs: failed to get inode (%i)\n", err);
 	inode = ERR_PTR(err);
 	goto out;
 }

fs/overlayfs/overlayfs.h

@@ -421,7 +421,7 @@ extern const struct file_operations ovl_file_operations;
 int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_with_data(struct dentry *dentry);
 int ovl_copy_up_flags(struct dentry *dentry, int flags);
-int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags);
+int ovl_maybe_copy_up(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
 struct ovl_fh *ovl_encode_real_fh(struct dentry *real, bool is_upper);