linux/fs/overlayfs/export.c
Amir Goldstein 3985b70a3e ovl: decode connected upper dir file handles
Until this change, we decoded upper file handles by instantiating an
overlay dentry from the real upper dentry. This is sufficient to handle
pure upper files, but insufficient to handle merge/impure dirs.

To that end, if decoded real upper dir is connected and hashed, we
lookup an overlay dentry with the same path as the real upper dir.
If decoded real upper is non-dir, we instantiate a disconnected overlay
dentry as before this change.

Because ovl_fh_to_dentry() returns a connected overlay dir dentry,
exportfs never needs to call get_parent() and get_name() to reconnect an
upper overlay dir. Because connectable non-dir file handles are not
supported, exportfs will not be able to use fh_to_parent() and get_name()
methods to reconnect a disconnected non-dir to its parent. Therefore, the
methods get_parent() and get_name() are implemented just to print out a
sanity warning and the method fh_to_parent() is implemented to warn the
user that using the 'subtree_check' exportfs option is not supported.

An alternative approach could have been to implement instantiating of
an overlay directory inode from origin/index and implement get_parent()
and get_name() by calling into underlying fs operations and them
instantiating the overlay parent dir.

The reasons for not choosing the get_parent() approach were:
- Obtaining a disconnected overlay dir dentry would requires a
  delicate re-factoring of ovl_lookup() to get a dentry with overlay
  parent info. It was preferred to avoid doing that re-factoring unless
  it was proven worthy.
- Going down the path of disconnected dir would mean that the (non
  trivial) code path of d_splice_alias() could be traveled and that
  meant writing more tests and introduces race cases that are very hard
  to hit on purpose. Taking the path of connecting overlay dentry by
  forward lookup is therefore the safe and boring way to avoid surprises.

The culprits of the chosen "connected overlay dentry" approach:
- We need to take special care to rename of ancestors while connecting
  the overlay dentry by real dentry path. These subtleties are usually
  handled by generic exportfs and VFS code.
- In a hypothetical workload, we could end up in a loop trying to connect,
  interrupted by rename and restarting connect forever.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2018-01-24 11:26:00 +01:00

425 lines
10 KiB
C

/*
* Overlayfs NFS export support.
*
* Amir Goldstein <amir73il@gmail.com>
*
* Copyright (C) 2017-2018 CTERA Networks. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published by
* the Free Software Foundation.
*/
#include <linux/fs.h>
#include <linux/cred.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"
static int ovl_d_to_fh(struct dentry *dentry, char *buf, int buflen)
{
struct dentry *upper = ovl_dentry_upper(dentry);
struct dentry *origin = ovl_dentry_lower(dentry);
struct ovl_fh *fh = NULL;
int err;
/*
* On overlay with an upper layer, overlay root inode is encoded as
* an upper file handle, because upper root dir is not indexed.
*/
if (dentry == dentry->d_sb->s_root && upper)
origin = NULL;
err = -EACCES;
if (!upper || origin)
goto fail;
/* TODO: encode non pure-upper by origin */
fh = ovl_encode_fh(upper, true);
err = -EOVERFLOW;
if (fh->len > buflen)
goto fail;
memcpy(buf, (char *)fh, fh->len);
err = fh->len;
out:
kfree(fh);
return err;
fail:
pr_warn_ratelimited("overlayfs: failed to encode file handle (%pd2, err=%i, buflen=%d, len=%d, type=%d)\n",
dentry, err, buflen, fh ? (int)fh->len : 0,
fh ? fh->type : 0);
goto out;
}
static int ovl_dentry_to_fh(struct dentry *dentry, u32 *fid, int *max_len)
{
int res, len = *max_len << 2;
res = ovl_d_to_fh(dentry, (char *)fid, len);
if (res <= 0)
return FILEID_INVALID;
len = res;
/* Round up to dwords */
*max_len = (len + 3) >> 2;
return OVL_FILEID;
}
static int ovl_encode_inode_fh(struct inode *inode, u32 *fid, int *max_len,
struct inode *parent)
{
struct dentry *dentry;
int type;
/* TODO: encode connectable file handles */
if (parent)
return FILEID_INVALID;
dentry = d_find_any_alias(inode);
if (WARN_ON(!dentry))
return FILEID_INVALID;
type = ovl_dentry_to_fh(dentry, fid, max_len);
dput(dentry);
return type;
}
/*
* Find or instantiate an overlay dentry from real dentries.
*/
static struct dentry *ovl_obtain_alias(struct super_block *sb,
struct dentry *upper,
struct ovl_path *lowerpath)
{
struct inode *inode;
struct dentry *dentry;
struct ovl_entry *oe;
void *fsdata = &oe;
/* TODO: obtain non pure-upper */
if (lowerpath)
return ERR_PTR(-EIO);
inode = ovl_get_inode(sb, dget(upper), NULL, NULL, 0);
if (IS_ERR(inode)) {
dput(upper);
return ERR_CAST(inode);
}
dentry = d_find_any_alias(inode);
if (!dentry) {
dentry = d_alloc_anon(inode->i_sb);
if (!dentry)
goto nomem;
oe = ovl_alloc_entry(0);
if (!oe)
goto nomem;
dentry->d_fsdata = oe;
ovl_dentry_set_upper_alias(dentry);
}
return d_instantiate_anon(dentry, inode);
nomem:
iput(inode);
dput(dentry);
return ERR_PTR(-ENOMEM);
}
/*
* Lookup a child overlay dentry to get a connected overlay dentry whose real
* dentry is @real. If @real is on upper layer, we lookup a child overlay
* dentry with the same name as the real dentry. Otherwise, we need to consult
* index for lookup.
*/
static struct dentry *ovl_lookup_real_one(struct dentry *connected,
struct dentry *real,
struct ovl_layer *layer)
{
struct inode *dir = d_inode(connected);
struct dentry *this, *parent = NULL;
struct name_snapshot name;
int err;
/* TODO: lookup by lower real dentry */
if (layer->idx)
return ERR_PTR(-EACCES);
/*
* Lookup child overlay dentry by real name. The dir mutex protects us
* from racing with overlay rename. If the overlay dentry that is above
* real has already been moved to a parent that is not under the
* connected overlay dir, we return -ECHILD and restart the lookup of
* connected real path from the top.
*/
inode_lock_nested(dir, I_MUTEX_PARENT);
err = -ECHILD;
parent = dget_parent(real);
if (ovl_dentry_upper(connected) != parent)
goto fail;
/*
* We also need to take a snapshot of real dentry name to protect us
* from racing with underlying layer rename. In this case, we don't
* care about returning ESTALE, only from dereferencing a free name
* pointer because we hold no lock on the real dentry.
*/
take_dentry_name_snapshot(&name, real);
this = lookup_one_len(name.name, connected, strlen(name.name));
err = PTR_ERR(this);
if (IS_ERR(this)) {
goto fail;
} else if (!this || !this->d_inode) {
dput(this);
err = -ENOENT;
goto fail;
} else if (ovl_dentry_upper(this) != real) {
dput(this);
err = -ESTALE;
goto fail;
}
out:
release_dentry_name_snapshot(&name);
dput(parent);
inode_unlock(dir);
return this;
fail:
pr_warn_ratelimited("overlayfs: failed to lookup one by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
real, layer->idx, connected, err);
this = ERR_PTR(err);
goto out;
}
/*
* Lookup a connected overlay dentry whose real dentry is @real.
* If @real is on upper layer, we lookup a child overlay dentry with the same
* path the real dentry. Otherwise, we need to consult index for lookup.
*/
static struct dentry *ovl_lookup_real(struct super_block *sb,
struct dentry *real,
struct ovl_layer *layer)
{
struct dentry *connected;
int err = 0;
/* TODO: use index when looking up by lower real dentry */
if (layer->idx)
return ERR_PTR(-EACCES);
connected = dget(sb->s_root);
while (!err) {
struct dentry *next, *this;
struct dentry *parent = NULL;
struct dentry *real_connected = ovl_dentry_upper(connected);
if (real_connected == real)
break;
/* Find the topmost dentry not yet connected */
next = dget(real);
for (;;) {
parent = dget_parent(next);
if (parent == real_connected)
break;
/*
* If real has been moved out of 'real_connected',
* we will not find 'real_connected' and hit the layer
* root. In that case, we need to restart connecting.
* This game can go on forever in the worst case. We
* may want to consider taking s_vfs_rename_mutex if
* this happens more than once.
*/
if (parent == layer->mnt->mnt_root) {
dput(connected);
connected = dget(sb->s_root);
break;
}
/*
* If real file has been moved out of the layer root
* directory, we will eventully hit the real fs root.
* This cannot happen by legit overlay rename, so we
* return error in that case.
*/
if (parent == next) {
err = -EXDEV;
break;
}
dput(next);
next = parent;
}
if (!err) {
this = ovl_lookup_real_one(connected, next, layer);
if (IS_ERR(this))
err = PTR_ERR(this);
/*
* Lookup of child in overlay can fail when racing with
* overlay rename of child away from 'connected' parent.
* In this case, we need to restart the lookup from the
* top, because we cannot trust that 'real_connected' is
* still an ancestor of 'real'.
*/
if (err == -ECHILD) {
this = dget(sb->s_root);
err = 0;
}
if (!err) {
dput(connected);
connected = this;
}
}
dput(parent);
dput(next);
}
if (err)
goto fail;
return connected;
fail:
pr_warn_ratelimited("overlayfs: failed to lookup by real (%pd2, layer=%d, connected=%pd2, err=%i)\n",
real, layer->idx, connected, err);
dput(connected);
return ERR_PTR(err);
}
/*
* Get an overlay dentry from upper/lower real dentries.
*/
static struct dentry *ovl_get_dentry(struct super_block *sb,
struct dentry *upper,
struct ovl_path *lowerpath)
{
struct ovl_fs *ofs = sb->s_fs_info;
struct ovl_layer upper_layer = { .mnt = ofs->upper_mnt };
/* TODO: get non-upper dentry */
if (!upper)
return ERR_PTR(-EACCES);
/*
* Obtain a disconnected overlay dentry from a non-dir real upper
* dentry.
*/
if (!d_is_dir(upper))
return ovl_obtain_alias(sb, upper, NULL);
/* Removed empty directory? */
if ((upper->d_flags & DCACHE_DISCONNECTED) || d_unhashed(upper))
return ERR_PTR(-ENOENT);
/*
* If real upper dentry is connected and hashed, get a connected
* overlay dentry with the same path as the real upper dentry.
*/
return ovl_lookup_real(sb, upper, &upper_layer);
}
static struct dentry *ovl_upper_fh_to_d(struct super_block *sb,
struct ovl_fh *fh)
{
struct ovl_fs *ofs = sb->s_fs_info;
struct dentry *dentry;
struct dentry *upper;
if (!ofs->upper_mnt)
return ERR_PTR(-EACCES);
upper = ovl_decode_fh(fh, ofs->upper_mnt);
if (IS_ERR_OR_NULL(upper))
return upper;
dentry = ovl_get_dentry(sb, upper, NULL);
dput(upper);
return dentry;
}
static struct dentry *ovl_fh_to_dentry(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
struct dentry *dentry = NULL;
struct ovl_fh *fh = (struct ovl_fh *) fid;
int len = fh_len << 2;
unsigned int flags = 0;
int err;
err = -EINVAL;
if (fh_type != OVL_FILEID)
goto out_err;
err = ovl_check_fh_len(fh, len);
if (err)
goto out_err;
/* TODO: decode non-upper */
flags = fh->flags;
if (flags & OVL_FH_FLAG_PATH_UPPER)
dentry = ovl_upper_fh_to_d(sb, fh);
err = PTR_ERR(dentry);
if (IS_ERR(dentry) && err != -ESTALE)
goto out_err;
return dentry;
out_err:
pr_warn_ratelimited("overlayfs: failed to decode file handle (len=%d, type=%d, flags=%x, err=%i)\n",
len, fh_type, flags, err);
return ERR_PTR(err);
}
static struct dentry *ovl_fh_to_parent(struct super_block *sb, struct fid *fid,
int fh_len, int fh_type)
{
pr_warn_ratelimited("overlayfs: connectable file handles not supported; use 'no_subtree_check' exportfs option.\n");
return ERR_PTR(-EACCES);
}
static int ovl_get_name(struct dentry *parent, char *name,
struct dentry *child)
{
/*
* ovl_fh_to_dentry() returns connected dir overlay dentries and
* ovl_fh_to_parent() is not implemented, so we should not get here.
*/
WARN_ON_ONCE(1);
return -EIO;
}
static struct dentry *ovl_get_parent(struct dentry *dentry)
{
/*
* ovl_fh_to_dentry() returns connected dir overlay dentries, so we
* should not get here.
*/
WARN_ON_ONCE(1);
return ERR_PTR(-EIO);
}
const struct export_operations ovl_export_operations = {
.encode_fh = ovl_encode_inode_fh,
.fh_to_dentry = ovl_fh_to_dentry,
.fh_to_parent = ovl_fh_to_parent,
.get_name = ovl_get_name,
.get_parent = ovl_get_parent,
};