path: root/fs/overlayfs/super.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 *
 * Copyright (C) 2011 Novell Inc.
 */

#include <uapi/linux/magic.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/mount.h>
#include <linux/parser.h>
#include <linux/module.h>
#include <linux/statfs.h>
#include <linux/seq_file.h>
#include <linux/posix_acl_xattr.h>
#include <linux/exportfs.h>
#include <linux/file.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include "overlayfs.h"
#include "params.h"

MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Overlay filesystem");
MODULE_LICENSE("GPL");


struct ovl_dir_cache;

static struct dentry *ovl_d_real(struct dentry *dentry,
				 const struct inode *inode)
{
	struct dentry *real = NULL, *lower;
	int err;

	/* It's an overlay file */
	if (inode && d_inode(dentry) == inode)
		return dentry;

	if (!d_is_reg(dentry)) {
		if (!inode || inode == d_inode(dentry))
			return dentry;
		goto bug;
	}

	real = ovl_dentry_upper(dentry);
	if (real && (inode == d_inode(real)))
		return real;

	if (real && !inode && ovl_has_upperdata(d_inode(dentry)))
		return real;

	/*
	 * Best effort lazy lookup of lowerdata for !inode case to return
	 * the real lowerdata dentry.  The only current caller of d_real() with
	 * NULL inode is d_real_inode() from trace_uprobe and this caller is
	 * likely going to be followed reading from the file, before placing
	 * uprobes on offset within the file, so lowerdata should be available
	 * when setting the uprobe.
	 */
	err = ovl_verify_lowerdata(dentry);
	if (err)
		goto bug;
	lower = ovl_dentry_lowerdata(dentry);
	if (!lower)
		goto bug;
	real = lower;

	/* Handle recursion */
	real = d_real(real, inode);

	if (!inode || inode == d_inode(real))
		return real;
bug:
	WARN(1, "%s(%pd4, %s:%lu): real dentry (%p/%lu) not found\n",
	     __func__, dentry, inode ? inode->i_sb->s_id : "NULL",
	     inode ? inode->i_ino : 0, real,
	     real && d_inode(real) ? d_inode(real)->i_ino : 0);
	return dentry;
}

static int ovl_revalidate_real(struct dentry *d, unsigned int flags, bool weak)
{
	int ret = 1;

	if (!d)
		return 1;

	if (weak) {
		if (d->d_flags & DCACHE_OP_WEAK_REVALIDATE)
			ret =  d->d_op->d_weak_revalidate(d, flags);
	} else if (d->d_flags & DCACHE_OP_REVALIDATE) {
		ret = d->d_op->d_revalidate(d, flags);
		if (!ret) {
			if (!(flags & LOOKUP_RCU))
				d_invalidate(d);
			ret = -ESTALE;
		}
	}
	return ret;
}

static int ovl_dentry_revalidate_common(struct dentry *dentry,
					unsigned int flags, bool weak)
{
	struct ovl_entry *oe;
	struct ovl_path *lowerstack;
	struct inode *inode = d_inode_rcu(dentry);
	struct dentry *upper;
	unsigned int i;
	int ret = 1;

	/* Careful in RCU mode */
	if (!inode)
		return -ECHILD;

	oe = OVL_I_E(inode);
	lowerstack = ovl_lowerstack(oe);
	upper = ovl_i_dentry_upper(inode);
	if (upper)
		ret = ovl_revalidate_real(upper, flags, weak);

	for (i = 0; ret > 0 && i < ovl_numlower(oe); i++)
		ret = ovl_revalidate_real(lowerstack[i].dentry, flags, weak);

	return ret;
}

static int ovl_dentry_revalidate(struct dentry *dentry, unsigned int flags)
{
	return ovl_dentry_revalidate_common(dentry, flags, false);
}

static int ovl_dentry_weak_revalidate(struct dentry *dentry, unsigned int flags)
{
	return ovl_dentry_revalidate_common(dentry, flags, true);
}

static const struct dentry_operations ovl_dentry_operations = {
	.d_real = ovl_d_real,
	.d_revalidate = ovl_dentry_revalidate,
	.d_weak_revalidate = ovl_dentry_weak_revalidate,
};

static struct kmem_cache *ovl_inode_cachep;

static struct inode *ovl_alloc_inode(struct super_block *sb)
{
	struct ovl_inode *oi = alloc_inode_sb(sb, ovl_inode_cachep, GFP_KERNEL);

	if (!oi)
		return NULL;

	oi->cache = NULL;
	oi->redirect = NULL;
	oi->version = 0;
	oi->flags = 0;
	oi->__upperdentry = NULL;
	oi->lowerdata_redirect = NULL;
	oi->oe = NULL;
	mutex_init(&oi->lock);

	return &oi->vfs_inode;
}

static void ovl_free_inode(struct inode *inode)
{
	struct ovl_inode *oi = OVL_I(inode);

	kfree(oi->redirect);
	kfree(oi->oe);
	mutex_destroy(&oi->lock);
	kmem_cache_free(ovl_inode_cachep, oi);
}

static void ovl_destroy_inode(struct inode *inode)
{
	struct ovl_inode *oi = OVL_I(inode);

	dput(oi->__upperdentry);
	ovl_stack_put(ovl_lowerstack(oi->oe), ovl_numlower(oi->oe));
	if (S_ISDIR(inode->i_mode))
		ovl_dir_cache_free(inode);
	else
		kfree(oi->lowerdata_redirect);
}

static void ovl_put_super(struct super_block *sb)
{
	struct ovl_fs *ofs = OVL_FS(sb);

	if (ofs)
		ovl_free_fs(ofs);
}

/* Sync real dirty inodes in upper filesystem (if it exists) */
static int ovl_sync_fs(struct super_block *sb, int wait)
{
	struct ovl_fs *ofs = OVL_FS(sb);
	struct super_block *upper_sb;
	int ret;

	ret = ovl_sync_status(ofs);
	/*
	 * We have to always set the err, because the return value isn't
	 * checked in syncfs, and instead indirectly return an error via
	 * the sb's writeback errseq, which VFS inspects after this call.
	 */
	if (ret < 0) {
		errseq_set(&sb->s_wb_err, -EIO);
		return -EIO;
	}

	if (!ret)
		return ret;

	/*
	 * Not called for sync(2) call or an emergency sync (SB_I_SKIP_SYNC).
	 * All the super blocks will be iterated, including upper_sb.
	 *
	 * If this is a syncfs(2) call, then we do need to call
	 * sync_filesystem() on upper_sb, but enough if we do it when being
	 * called with wait == 1.
	 */
	if (!wait)
		return 0;

	upper_sb = ovl_upper_mnt(ofs)->mnt_sb;

	down_read(&upper_sb->s_umount);
	ret = sync_filesystem(upper_sb);
	up_read(&upper_sb->s_umount);

	return ret;
}

/**
 * ovl_statfs
 * @dentry: The dentry to query
 * @buf: The struct kstatfs to fill in with stats
 *
 * Get the filesystem statistics.  As writes always target the upper layer
 * filesystem pass the statfs to the upper filesystem (if it exists)
 */
static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct ovl_fs *ofs = OVL_FS(sb);
	struct dentry *root_dentry = sb->s_root;
	struct path path;
	int err;

	ovl_path_real(root_dentry, &path);

	err = vfs_statfs(&path, buf);
	if (!err) {
		buf->f_namelen = ofs->namelen;
		buf->f_type = OVERLAYFS_SUPER_M