![Linus Torvalds](/assets/img/avatar_default.png)
using the meta_bg feature. This allows us to resize file systems which are greater than 16TB. In addition, the speed of online resizing has been improved in general. We also fix a number of races, some of which could lead to deadlocks, in ext4's Asynchronous I/O and online defrag support, thanks to good work by Dmitry Monakhov. There are also a large number of more minor bug fixes and cleanups from a number of other ext4 contributors, quite of few of which have submitted fixes for the first time. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQIcBAABCAAGBQJQbxMXAAoJENNvdpvBGATwlg4QAJZ4mHNSL2eaaxjRtTbL1pAz +FVXpJ3lhw1lSfE9hJGqPVE8EfU2fWjIqxEI7dgh95Tukc5pUnPAQ2/hBz8ZA0qq o0AFMk3mRnvCEh6HsZfumsV83eqpR3k/zEy4uFH+KtxBskPe2sEKy3B7qOxvgdKW Gh8B2WqF2BpIj9WIT1P9G6xsxZW64EMHTbWcgRhuoRD7bakDNnwQ3kElz/TJQU5q bM/5wE7pqKwU2J1L0Ho0mxDi0f/BbXeJdA9k1tQy2KM1pZwHtpj4Ls0qmfoi49GE KyZqQOXlFbAz/9tidPDceY5KoRRQm1MwZ+1MimQX1P+40cs/w3pNu3yiibcaXIru UZ63AQMCj5JHMcFNVi20sVCwjU/ibNtEO75cfDD4bzPgHJvfCj73EbHTLl21nbTu izIMffhJEHmRnmRXiiortYVuI4b19oIfnXg7eclrJoUWSuGwKKsJOc5nMjDqidG4 B7Gq4TD89sGkIYzx+50E+ll2ispcBN0BQnGqp4k2BzgDyEHhuFYk7VuVQvJgCGTi eobzQJj7JUXPWxyemcAVkQTtUq4vVbkm/IwS+/GA9b9Z80X8hR8x6EVHUW5lX3qC YHoBSCU4XKZXXWqzx0fIVCXyKKFiBzM+OXcgHOKH90vK8k6kPmPODhNCxvV3pITU jfl9q+X1dY4SpybZjLt5 =iYeV -----END PGP SIGNATURE----- Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 Pull ext4 updates from Ted Ts'o: "The big new feature added this time is supporting online resizing using the meta_bg feature. This allows us to resize file systems which are greater than 16TB. In addition, the speed of online resizing has been improved in general. We also fix a number of races, some of which could lead to deadlocks, in ext4's Asynchronous I/O and online defrag support, thanks to good work by Dmitry Monakhov. There are also a large number of more minor bug fixes and cleanups from a number of other ext4 contributors, quite of few of which have submitted fixes for the first time." * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (69 commits) ext4: fix ext4_flush_completed_IO wait semantics ext4: fix mtime update in nodelalloc mode ext4: fix ext_remove_space for punch_hole case ext4: punch_hole should wait for DIO writers ext4: serialize truncate with owerwrite DIO workers ext4: endless truncate due to nonlocked dio readers ext4: serialize unlocked dio reads with truncate ext4: serialize dio nonlocked reads with defrag workers ext4: completed_io locking cleanup ext4: fix unwritten counter leakage ext4: give i_aiodio_unwritten a more appropriate name ext4: ext4_inode_info diet ext4: convert to use leXX_add_cpu() ext4: ext4_bread usage audit fs: reserve fallocate flag codepoint ext4: remove redundant offset check in mext_check_arguments() ext4: don't clear orphan list on ro mount with errors jbd2: fix assertion failure in commit code due to lacking transaction credits ext4: release donor reference when EXT4_IOC_MOVE_EXT ioctl fails ext4: enable FITRIM ioctl on bigalloc file system ...
495 lines
11 KiB
C
495 lines
11 KiB
C
/*
|
|
* linux/fs/ext4/ioctl.c
|
|
*
|
|
* Copyright (C) 1993, 1994, 1995
|
|
* Remy Card (card@masi.ibp.fr)
|
|
* Laboratoire MASI - Institut Blaise Pascal
|
|
* Universite Pierre et Marie Curie (Paris VI)
|
|
*/
|
|
|
|
#include <linux/fs.h>
|
|
#include <linux/jbd2.h>
|
|
#include <linux/capability.h>
|
|
#include <linux/time.h>
|
|
#include <linux/compat.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/file.h>
|
|
#include <asm/uaccess.h>
|
|
#include "ext4_jbd2.h"
|
|
#include "ext4.h"
|
|
|
|
#define MAX_32_NUM ((((unsigned long long) 1) << 32) - 1)
|
|
|
|
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
|
|
{
|
|
struct inode *inode = filp->f_dentry->d_inode;
|
|
struct super_block *sb = inode->i_sb;
|
|
struct ext4_inode_info *ei = EXT4_I(inode);
|
|
unsigned int flags;
|
|
|
|
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
|
|
|
|
switch (cmd) {
|
|
case EXT4_IOC_GETFLAGS:
|
|
ext4_get_inode_flags(ei);
|
|
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
|
|
return put_user(flags, (int __user *) arg);
|
|
case EXT4_IOC_SETFLAGS: {
|
|
handle_t *handle = NULL;
|
|
int err, migrate = 0;
|
|
struct ext4_iloc iloc;
|
|
unsigned int oldflags, mask, i;
|
|
unsigned int jflag;
|
|
|
|
if (!inode_owner_or_capable(inode))
|
|
return -EACCES;
|
|
|
|
if (get_user(flags, (int __user *) arg))
|
|
return -EFAULT;
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
return err;
|
|
|
|
flags = ext4_mask_flags(inode->i_mode, flags);
|
|
|
|
err = -EPERM;
|
|
mutex_lock(&inode->i_mutex);
|
|
/* Is it quota file? Do not allow user to mess with it */
|
|
if (IS_NOQUOTA(inode))
|
|
goto flags_out;
|
|
|
|
oldflags = ei->i_flags;
|
|
|
|
/* The JOURNAL_DATA flag is modifiable only by root */
|
|
jflag = flags & EXT4_JOURNAL_DATA_FL;
|
|
|
|
/*
|
|
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
|
|
* the relevant capability.
|
|
*
|
|
* This test looks nicer. Thanks to Pauline Middelink
|
|
*/
|
|
if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
|
|
if (!capable(CAP_LINUX_IMMUTABLE))
|
|
goto flags_out;
|
|
}
|
|
|
|
/*
|
|
* The JOURNAL_DATA flag can only be changed by
|
|
* the relevant capability.
|
|
*/
|
|
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
|
|
if (!capable(CAP_SYS_RESOURCE))
|
|
goto flags_out;
|
|
}
|
|
if (oldflags & EXT4_EXTENTS_FL) {
|
|
/* We don't support clearning extent flags */
|
|
if (!(flags & EXT4_EXTENTS_FL)) {
|
|
err = -EOPNOTSUPP;
|
|
goto flags_out;
|
|
}
|
|
} else if (flags & EXT4_EXTENTS_FL) {
|
|
/* migrate the file */
|
|
migrate = 1;
|
|
flags &= ~EXT4_EXTENTS_FL;
|
|
}
|
|
|
|
if (flags & EXT4_EOFBLOCKS_FL) {
|
|
/* we don't support adding EOFBLOCKS flag */
|
|
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
|
|
err = -EOPNOTSUPP;
|
|
goto flags_out;
|
|
}
|
|
} else if (oldflags & EXT4_EOFBLOCKS_FL)
|
|
ext4_truncate(inode);
|
|
|
|
handle = ext4_journal_start(inode, 1);
|
|
if (IS_ERR(handle)) {
|
|
err = PTR_ERR(handle);
|
|
goto flags_out;
|
|
}
|
|
if (IS_SYNC(inode))
|
|
ext4_handle_sync(handle);
|
|
err = ext4_reserve_inode_write(handle, inode, &iloc);
|
|
if (err)
|
|
goto flags_err;
|
|
|
|
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
|
|
if (!(mask & EXT4_FL_USER_MODIFIABLE))
|
|
continue;
|
|
if (mask & flags)
|
|
ext4_set_inode_flag(inode, i);
|
|
else
|
|
ext4_clear_inode_flag(inode, i);
|
|
}
|
|
|
|
ext4_set_inode_flags(inode);
|
|
inode->i_ctime = ext4_current_time(inode);
|
|
|
|
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
|
|
flags_err:
|
|
ext4_journal_stop(handle);
|
|
if (err)
|
|
goto flags_out;
|
|
|
|
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
|
|
err = ext4_change_inode_journal_flag(inode, jflag);
|
|
if (err)
|
|
goto flags_out;
|
|
if (migrate)
|
|
err = ext4_ext_migrate(inode);
|
|
flags_out:
|
|
mutex_unlock(&inode->i_mutex);
|
|
mnt_drop_write_file(filp);
|
|
return err;
|
|
}
|
|
case EXT4_IOC_GETVERSION:
|
|
case EXT4_IOC_GETVERSION_OLD:
|
|
return put_user(inode->i_generation, (int __user *) arg);
|
|
case EXT4_IOC_SETVERSION:
|
|
case EXT4_IOC_SETVERSION_OLD: {
|
|
handle_t *handle;
|
|
struct ext4_iloc iloc;
|
|
__u32 generation;
|
|
int err;
|
|
|
|
if (!inode_owner_or_capable(inode))
|
|
return -EPERM;
|
|
|
|
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
|
|
EXT4_FEATURE_RO_COMPAT_METADATA_CSUM)) {
|
|
ext4_warning(sb, "Setting inode version is not "
|
|
"supported with metadata_csum enabled.");
|
|
return -ENOTTY;
|
|
}
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
return err;
|
|
if (get_user(generation, (int __user *) arg)) {
|
|
err = -EFAULT;
|
|
goto setversion_out;
|
|
}
|
|
|
|
mutex_lock(&inode->i_mutex);
|
|
handle = ext4_journal_start(inode, 1);
|
|
if (IS_ERR(handle)) {
|
|
err = PTR_ERR(handle);
|
|
goto unlock_out;
|
|
}
|
|
err = ext4_reserve_inode_write(handle, inode, &iloc);
|
|
if (err == 0) {
|
|
inode->i_ctime = ext4_current_time(inode);
|
|
inode->i_generation = generation;
|
|
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
|
|
}
|
|
ext4_journal_stop(handle);
|
|
|
|
unlock_out:
|
|
mutex_unlock(&inode->i_mutex);
|
|
setversion_out:
|
|
mnt_drop_write_file(filp);
|
|
return err;
|
|
}
|
|
case EXT4_IOC_GROUP_EXTEND: {
|
|
ext4_fsblk_t n_blocks_count;
|
|
int err, err2=0;
|
|
|
|
err = ext4_resize_begin(sb);
|
|
if (err)
|
|
return err;
|
|
|
|
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
|
|
err = -EFAULT;
|
|
goto group_extend_out;
|
|
}
|
|
|
|
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
|
|
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
|
|
ext4_msg(sb, KERN_ERR,
|
|
"Online resizing not supported with bigalloc");
|
|
err = -EOPNOTSUPP;
|
|
goto group_extend_out;
|
|
}
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
goto group_extend_out;
|
|
|
|
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
|
|
if (EXT4_SB(sb)->s_journal) {
|
|
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
|
|
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
|
|
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
|
|
}
|
|
if (err == 0)
|
|
err = err2;
|
|
mnt_drop_write_file(filp);
|
|
group_extend_out:
|
|
ext4_resize_end(sb);
|
|
return err;
|
|
}
|
|
|
|
case EXT4_IOC_MOVE_EXT: {
|
|
struct move_extent me;
|
|
struct fd donor;
|
|
int err;
|
|
|
|
if (!(filp->f_mode & FMODE_READ) ||
|
|
!(filp->f_mode & FMODE_WRITE))
|
|
return -EBADF;
|
|
|
|
if (copy_from_user(&me,
|
|
(struct move_extent __user *)arg, sizeof(me)))
|
|
return -EFAULT;
|
|
me.moved_len = 0;
|
|
|
|
donor = fdget(me.donor_fd);
|
|
if (!donor.file)
|
|
return -EBADF;
|
|
|
|
if (!(donor.file->f_mode & FMODE_WRITE)) {
|
|
err = -EBADF;
|
|
goto mext_out;
|
|
}
|
|
|
|
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
|
|
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
|
|
ext4_msg(sb, KERN_ERR,
|
|
"Online defrag not supported with bigalloc");
|
|
err = -EOPNOTSUPP;
|
|
goto mext_out;
|
|
}
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
goto mext_out;
|
|
|
|
err = ext4_move_extents(filp, donor.file, me.orig_start,
|
|
me.donor_start, me.len, &me.moved_len);
|
|
mnt_drop_write_file(filp);
|
|
|
|
if (copy_to_user((struct move_extent __user *)arg,
|
|
&me, sizeof(me)))
|
|
err = -EFAULT;
|
|
mext_out:
|
|
fdput(donor);
|
|
return err;
|
|
}
|
|
|
|
case EXT4_IOC_GROUP_ADD: {
|
|
struct ext4_new_group_data input;
|
|
int err, err2=0;
|
|
|
|
err = ext4_resize_begin(sb);
|
|
if (err)
|
|
return err;
|
|
|
|
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
|
|
sizeof(input))) {
|
|
err = -EFAULT;
|
|
goto group_add_out;
|
|
}
|
|
|
|
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
|
|
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
|
|
ext4_msg(sb, KERN_ERR,
|
|
"Online resizing not supported with bigalloc");
|
|
err = -EOPNOTSUPP;
|
|
goto group_add_out;
|
|
}
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
goto group_add_out;
|
|
|
|
err = ext4_group_add(sb, &input);
|
|
if (EXT4_SB(sb)->s_journal) {
|
|
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
|
|
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
|
|
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
|
|
}
|
|
if (err == 0)
|
|
err = err2;
|
|
mnt_drop_write_file(filp);
|
|
group_add_out:
|
|
ext4_resize_end(sb);
|
|
return err;
|
|
}
|
|
|
|
case EXT4_IOC_MIGRATE:
|
|
{
|
|
int err;
|
|
if (!inode_owner_or_capable(inode))
|
|
return -EACCES;
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
return err;
|
|
/*
|
|
* inode_mutex prevent write and truncate on the file.
|
|
* Read still goes through. We take i_data_sem in
|
|
* ext4_ext_swap_inode_data before we switch the
|
|
* inode format to prevent read.
|
|
*/
|
|
mutex_lock(&(inode->i_mutex));
|
|
err = ext4_ext_migrate(inode);
|
|
mutex_unlock(&(inode->i_mutex));
|
|
mnt_drop_write_file(filp);
|
|
return err;
|
|
}
|
|
|
|
case EXT4_IOC_ALLOC_DA_BLKS:
|
|
{
|
|
int err;
|
|
if (!inode_owner_or_capable(inode))
|
|
return -EACCES;
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
return err;
|
|
err = ext4_alloc_da_blocks(inode);
|
|
mnt_drop_write_file(filp);
|
|
return err;
|
|
}
|
|
|
|
case EXT4_IOC_RESIZE_FS: {
|
|
ext4_fsblk_t n_blocks_count;
|
|
struct super_block *sb = inode->i_sb;
|
|
int err = 0, err2 = 0;
|
|
|
|
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
|
|
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
|
|
ext4_msg(sb, KERN_ERR,
|
|
"Online resizing not (yet) supported with bigalloc");
|
|
return -EOPNOTSUPP;
|
|
}
|
|
|
|
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
|
|
sizeof(__u64))) {
|
|
return -EFAULT;
|
|
}
|
|
|
|
err = ext4_resize_begin(sb);
|
|
if (err)
|
|
return err;
|
|
|
|
err = mnt_want_write_file(filp);
|
|
if (err)
|
|
goto resizefs_out;
|
|
|
|
err = ext4_resize_fs(sb, n_blocks_count);
|
|
if (EXT4_SB(sb)->s_journal) {
|
|
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
|
|
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
|
|
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
|
|
}
|
|
if (err == 0)
|
|
err = err2;
|
|
mnt_drop_write_file(filp);
|
|
resizefs_out:
|
|
ext4_resize_end(sb);
|
|
return err;
|
|
}
|
|
|
|
case FITRIM:
|
|
{
|
|
struct request_queue *q = bdev_get_queue(sb->s_bdev);
|
|
struct fstrim_range range;
|
|
int ret = 0;
|
|
|
|
if (!capable(CAP_SYS_ADMIN))
|
|
return -EPERM;
|
|
|
|
if (!blk_queue_discard(q))
|
|
return -EOPNOTSUPP;
|
|
|
|
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
|
|
sizeof(range)))
|
|
return -EFAULT;
|
|
|
|
range.minlen = max((unsigned int)range.minlen,
|
|
q->limits.discard_granularity);
|
|
ret = ext4_trim_fs(sb, &range);
|
|
if (ret < 0)
|
|
return ret;
|
|
|
|
if (copy_to_user((struct fstrim_range __user *)arg, &range,
|
|
sizeof(range)))
|
|
return -EFAULT;
|
|
|
|
return 0;
|
|
}
|
|
|
|
default:
|
|
return -ENOTTY;
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
|
|
{
|
|
/* These are just misnamed, they actually get/put from/to user an int */
|
|
switch (cmd) {
|
|
case EXT4_IOC32_GETFLAGS:
|
|
cmd = EXT4_IOC_GETFLAGS;
|
|
break;
|
|
case EXT4_IOC32_SETFLAGS:
|
|
cmd = EXT4_IOC_SETFLAGS;
|
|
break;
|
|
case EXT4_IOC32_GETVERSION:
|
|
cmd = EXT4_IOC_GETVERSION;
|
|
break;
|
|
case EXT4_IOC32_SETVERSION:
|
|
cmd = EXT4_IOC_SETVERSION;
|
|
break;
|
|
case EXT4_IOC32_GROUP_EXTEND:
|
|
cmd = EXT4_IOC_GROUP_EXTEND;
|
|
break;
|
|
case EXT4_IOC32_GETVERSION_OLD:
|
|
cmd = EXT4_IOC_GETVERSION_OLD;
|
|
break;
|
|
case EXT4_IOC32_SETVERSION_OLD:
|
|
cmd = EXT4_IOC_SETVERSION_OLD;
|
|
break;
|
|
case EXT4_IOC32_GETRSVSZ:
|
|
cmd = EXT4_IOC_GETRSVSZ;
|
|
break;
|
|
case EXT4_IOC32_SETRSVSZ:
|
|
cmd = EXT4_IOC_SETRSVSZ;
|
|
break;
|
|
case EXT4_IOC32_GROUP_ADD: {
|
|
struct compat_ext4_new_group_input __user *uinput;
|
|
struct ext4_new_group_input input;
|
|
mm_segment_t old_fs;
|
|
int err;
|
|
|
|
uinput = compat_ptr(arg);
|
|
err = get_user(input.group, &uinput->group);
|
|
err |= get_user(input.block_bitmap, &uinput->block_bitmap);
|
|
err |= get_user(input.inode_bitmap, &uinput->inode_bitmap);
|
|
err |= get_user(input.inode_table, &uinput->inode_table);
|
|
err |= get_user(input.blocks_count, &uinput->blocks_count);
|
|
err |= get_user(input.reserved_blocks,
|
|
&uinput->reserved_blocks);
|
|
if (err)
|
|
return -EFAULT;
|
|
old_fs = get_fs();
|
|
set_fs(KERNEL_DS);
|
|
err = ext4_ioctl(file, EXT4_IOC_GROUP_ADD,
|
|
(unsigned long) &input);
|
|
set_fs(old_fs);
|
|
return err;
|
|
}
|
|
case EXT4_IOC_MOVE_EXT:
|
|
case FITRIM:
|
|
case EXT4_IOC_RESIZE_FS:
|
|
break;
|
|
default:
|
|
return -ENOIOCTLCMD;
|
|
}
|
|
return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
|
|
}
|
|
#endif
|