linux/fs/overlayfs/file.c
Amir Goldstein b833a36603 ovl: add ovl_fadvise()
Implement stacked fadvise to fix syscalls readahead(2) and fadvise64(2)
on an overlayfs file.

Suggested-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: d1d04ef857 ("ovl: stack file ops")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2018-09-03 09:43:10 +02:00

529 lines
11 KiB
C

/*
* Copyright (C) 2017 Red Hat, Inc.
*
* 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/cred.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/xattr.h>
#include <linux/uio.h>
#include "overlayfs.h"
static char ovl_whatisit(struct inode *inode, struct inode *realinode)
{
if (realinode != ovl_inode_upper(inode))
return 'l';
if (ovl_has_upperdata(inode))
return 'u';
else
return 'm';
}
static struct file *ovl_open_realfile(const struct file *file,
struct inode *realinode)
{
struct inode *inode = file_inode(file);
struct file *realfile;
const struct cred *old_cred;
old_cred = ovl_override_creds(inode->i_sb);
realfile = open_with_fake_path(&file->f_path, file->f_flags | O_NOATIME,
realinode, current_cred());
revert_creds(old_cred);
pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n",
file, file, ovl_whatisit(inode, realinode), file->f_flags,
realfile, IS_ERR(realfile) ? 0 : realfile->f_flags);
return realfile;
}
#define OVL_SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT)
static int ovl_change_flags(struct file *file, unsigned int flags)
{
struct inode *inode = file_inode(file);
int err;
/* No atime modificaton on underlying */
flags |= O_NOATIME;
/* If some flag changed that cannot be changed then something's amiss */
if (WARN_ON((file->f_flags ^ flags) & ~OVL_SETFL_MASK))
return -EIO;
flags &= OVL_SETFL_MASK;
if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode))
return -EPERM;
if (flags & O_DIRECT) {
if (!file->f_mapping->a_ops ||
!file->f_mapping->a_ops->direct_IO)
return -EINVAL;
}
if (file->f_op->check_flags) {
err = file->f_op->check_flags(flags);
if (err)
return err;
}
spin_lock(&file->f_lock);
file->f_flags = (file->f_flags & ~OVL_SETFL_MASK) | flags;
spin_unlock(&file->f_lock);
return 0;
}
static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
bool allow_meta)
{
struct inode *inode = file_inode(file);
struct inode *realinode;
real->flags = 0;
real->file = file->private_data;
if (allow_meta)
realinode = ovl_inode_real(inode);
else
realinode = ovl_inode_realdata(inode);
/* Has it been copied up since we'd opened it? */
if (unlikely(file_inode(real->file) != realinode)) {
real->flags = FDPUT_FPUT;
real->file = ovl_open_realfile(file, realinode);
return PTR_ERR_OR_ZERO(real->file);
}
/* Did the flags change since open? */
if (unlikely((file->f_flags ^ real->file->f_flags) & ~O_NOATIME))
return ovl_change_flags(real->file, file->f_flags);
return 0;
}
static int ovl_real_fdget(const struct file *file, struct fd *real)
{
return ovl_real_fdget_meta(file, real, false);
}
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);
if (err)
return err;
/* No longer need these flags, so don't pass them on to underlying fs */
file->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
realfile = ovl_open_realfile(file, ovl_inode_realdata(inode));
if (IS_ERR(realfile))
return PTR_ERR(realfile);
file->private_data = realfile;
return 0;
}
static int ovl_release(struct inode *inode, struct file *file)
{
fput(file->private_data);
return 0;
}
static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
{
struct inode *realinode = ovl_inode_real(file_inode(file));
return generic_file_llseek_size(file, offset, whence,
realinode->i_sb->s_maxbytes,
i_size_read(realinode));
}
static void ovl_file_accessed(struct file *file)
{
struct inode *inode, *upperinode;
if (file->f_flags & O_NOATIME)
return;
inode = file_inode(file);
upperinode = ovl_inode_upper(inode);
if (!upperinode)
return;
if ((!timespec64_equal(&inode->i_mtime, &upperinode->i_mtime) ||
!timespec64_equal(&inode->i_ctime, &upperinode->i_ctime))) {
inode->i_mtime = upperinode->i_mtime;
inode->i_ctime = upperinode->i_ctime;
}
touch_atime(&file->f_path);
}
static rwf_t ovl_iocb_to_rwf(struct kiocb *iocb)
{
int ifl = iocb->ki_flags;
rwf_t flags = 0;
if (ifl & IOCB_NOWAIT)
flags |= RWF_NOWAIT;
if (ifl & IOCB_HIPRI)
flags |= RWF_HIPRI;
if (ifl & IOCB_DSYNC)
flags |= RWF_DSYNC;
if (ifl & IOCB_SYNC)
flags |= RWF_SYNC;
return flags;
}
static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct fd real;
const struct cred *old_cred;
ssize_t ret;
if (!iov_iter_count(iter))
return 0;
ret = ovl_real_fdget(file, &real);
if (ret)
return ret;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_iter_read(real.file, iter, &iocb->ki_pos,
ovl_iocb_to_rwf(iocb));
revert_creds(old_cred);
ovl_file_accessed(file);
fdput(real);
return ret;
}
static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct fd real;
const struct cred *old_cred;
ssize_t ret;
if (!iov_iter_count(iter))
return 0;
inode_lock(inode);
/* Update mode */
ovl_copyattr(ovl_inode_real(inode), inode);
ret = file_remove_privs(file);
if (ret)
goto out_unlock;
ret = ovl_real_fdget(file, &real);
if (ret)
goto out_unlock;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
ovl_iocb_to_rwf(iocb));
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode), inode);
fdput(real);
out_unlock:
inode_unlock(inode);
return ret;
}
static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
struct fd real;
const struct cred *old_cred;
int ret;
ret = ovl_real_fdget_meta(file, &real, !datasync);
if (ret)
return ret;
/* Don't sync lower file for fear of receiving EROFS error */
if (file_inode(real.file) == ovl_inode_upper(file_inode(file))) {
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_fsync_range(real.file, start, end, datasync);
revert_creds(old_cred);
}
fdput(real);
return ret;
}
static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
{
struct file *realfile = file->private_data;
const struct cred *old_cred;
int ret;
if (!realfile->f_op->mmap)
return -ENODEV;
if (WARN_ON(file != vma->vm_file))
return -EIO;
vma->vm_file = get_file(realfile);
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = call_mmap(vma->vm_file, vma);
revert_creds(old_cred);
if (ret) {
/* Drop reference count from new vm_file value */
fput(realfile);
} else {
/* Drop reference count from previous vm_file value */
fput(file);
}
ovl_file_accessed(file);
return ret;
}
static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
struct inode *inode = file_inode(file);
struct fd real;
const struct cred *old_cred;
int ret;
ret = ovl_real_fdget(file, &real);
if (ret)
return ret;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_fallocate(real.file, mode, offset, len);
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode), inode);
fdput(real);
return ret;
}
static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
{
struct fd real;
const struct cred *old_cred;
int ret;
ret = ovl_real_fdget(file, &real);
if (ret)
return ret;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_fadvise(real.file, offset, len, advice);
revert_creds(old_cred);
fdput(real);
return ret;
}
static long ovl_real_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
struct fd real;
const struct cred *old_cred;
long ret;
ret = ovl_real_fdget(file, &real);
if (ret)
return ret;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
ret = vfs_ioctl(real.file, cmd, arg);
revert_creds(old_cred);
fdput(real);
return ret;
}
static long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
long ret;
struct inode *inode = file_inode(file);
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);
break;
default:
ret = -ENOTTY;
}
return ret;
}
static long ovl_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
switch (cmd) {
case FS_IOC32_GETFLAGS:
cmd = FS_IOC_GETFLAGS;
break;
case FS_IOC32_SETFLAGS:
cmd = FS_IOC_SETFLAGS;
break;
default:
return -ENOIOCTLCMD;
}
return ovl_ioctl(file, cmd, arg);
}
enum ovl_copyop {
OVL_COPY,
OVL_CLONE,
OVL_DEDUPE,
};
static ssize_t ovl_copyfile(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
u64 len, unsigned int flags, enum ovl_copyop op)
{
struct inode *inode_out = file_inode(file_out);
struct fd real_in, real_out;
const struct cred *old_cred;
ssize_t ret;
ret = ovl_real_fdget(file_out, &real_out);
if (ret)
return ret;
ret = ovl_real_fdget(file_in, &real_in);
if (ret) {
fdput(real_out);
return ret;
}
old_cred = ovl_override_creds(file_inode(file_out)->i_sb);
switch (op) {
case OVL_COPY:
ret = vfs_copy_file_range(real_in.file, pos_in,
real_out.file, pos_out, len, flags);
break;
case OVL_CLONE:
ret = vfs_clone_file_range(real_in.file, pos_in,
real_out.file, pos_out, len);
break;
case OVL_DEDUPE:
ret = vfs_dedupe_file_range_one(real_in.file, pos_in,
real_out.file, pos_out, len);
break;
}
revert_creds(old_cred);
/* Update size */
ovl_copyattr(ovl_inode_real(inode_out), inode_out);
fdput(real_in);
fdput(real_out);
return ret;
}
static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
size_t len, unsigned int flags)
{
return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, flags,
OVL_COPY);
}
static int ovl_clone_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out, u64 len)
{
return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0,
OVL_CLONE);
}
static int ovl_dedupe_file_range(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out, u64 len)
{
/*
* Don't copy up because of a dedupe request, this wouldn't make sense
* most of the time (data would be duplicated instead of deduplicated).
*/
if (!ovl_inode_upper(file_inode(file_in)) ||
!ovl_inode_upper(file_inode(file_out)))
return -EPERM;
return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, 0,
OVL_DEDUPE);
}
const struct file_operations ovl_file_operations = {
.open = ovl_open,
.release = ovl_release,
.llseek = ovl_llseek,
.read_iter = ovl_read_iter,
.write_iter = ovl_write_iter,
.fsync = ovl_fsync,
.mmap = ovl_mmap,
.fallocate = ovl_fallocate,
.fadvise = ovl_fadvise,
.unlocked_ioctl = ovl_ioctl,
.compat_ioctl = ovl_compat_ioctl,
.copy_file_range = ovl_copy_file_range,
.clone_file_range = ovl_clone_file_range,
.dedupe_file_range = ovl_dedupe_file_range,
};