linux_dsm_epyc7002/fs/ext4/ioctl.c

1118 lines
27 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 21:07:57 +07:00
// SPDX-License-Identifier: GPL-2.0
/*
* 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/capability.h>
#include <linux/time.h>
#include <linux/compat.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/quotaops.h>
#include <linux/random.h>
#include <linux/uuid.h>
#include <linux/uaccess.h>
#include <linux/delay.h>
#include <linux/iversion.h>
#include "ext4_jbd2.h"
#include "ext4.h"
#include <linux/fsmap.h>
#include "fsmap.h"
#include <trace/events/ext4.h>
/**
* Swap memory between @a and @b for @len bytes.
*
* @a: pointer to first memory area
* @b: pointer to second memory area
* @len: number of bytes to swap
*
*/
static void memswap(void *a, void *b, size_t len)
{
unsigned char *ap, *bp;
ap = (unsigned char *)a;
bp = (unsigned char *)b;
while (len-- > 0) {
swap(*ap, *bp);
ap++;
bp++;
}
}
/**
* Swap i_data and associated attributes between @inode1 and @inode2.
* This function is used for the primary swap between inode1 and inode2
* and also to revert this primary swap in case of errors.
*
* Therefore you have to make sure, that calling this method twice
* will revert all changes.
*
* @inode1: pointer to first inode
* @inode2: pointer to second inode
*/
static void swap_inode_data(struct inode *inode1, struct inode *inode2)
{
loff_t isize;
struct ext4_inode_info *ei1;
struct ext4_inode_info *ei2;
ei1 = EXT4_I(inode1);
ei2 = EXT4_I(inode2);
swap(inode1->i_flags, inode2->i_flags);
swap(inode1->i_version, inode2->i_version);
swap(inode1->i_blocks, inode2->i_blocks);
swap(inode1->i_bytes, inode2->i_bytes);
swap(inode1->i_atime, inode2->i_atime);
swap(inode1->i_mtime, inode2->i_mtime);
memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
swap(ei1->i_flags, ei2->i_flags);
swap(ei1->i_disksize, ei2->i_disksize);
ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);
isize = i_size_read(inode1);
i_size_write(inode1, i_size_read(inode2));
i_size_write(inode2, isize);
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode))
return -EINVAL;
if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN))
return -EPERM;
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
if (IS_ERR(inode_bl))
return PTR_ERR(inode_bl);
ei_bl = EXT4_I(inode_bl);
filemap_flush(inode->i_mapping);
filemap_flush(inode_bl->i_mapping);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(inode);
ext4_inode_block_unlocked_dio(inode_bl);
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_set_iversion(inode_bl, 1);
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (ext4_has_feature_extents(sb)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = current_time(inode);
inode->i_generation = prandom_u32();
inode_bl->i_generation = prandom_u32();
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
} else {
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
}
}
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
return err;
}
#ifdef CONFIG_EXT4_FS_ENCRYPTION
static int uuid_is_zero(__u8 u[16])
{
int i;
for (i = 0; i < 16; i++)
if (u[i])
return 0;
return 1;
}
#endif
static int ext4_ioctl_setflags(struct inode *inode,
unsigned int flags)
{
struct ext4_inode_info *ei = EXT4_I(inode);
handle_t *handle = NULL;
ext4: ioctl: fix erroneous return value The ext4_ioctl_setflags() function which is used in the ioctls EXT4_IOC_SETFLAGS and EXT4_IOC_FSSETXATTR may return the positive value EPERM instead of -EPERM in case of error. This bug was introduced by a recent commit 9b7365fc. The following program can be used to illustrate the wrong behavior: #include <sys/types.h> #include <sys/ioctl.h> #include <sys/stat.h> #include <fcntl.h> #include <err.h> #define FS_IOC_GETFLAGS _IOR('f', 1, long) #define FS_IOC_SETFLAGS _IOW('f', 2, long) #define FS_IMMUTABLE_FL 0x00000010 int main(void) { int fd; long flags; fd = open("file", O_RDWR|O_CREAT, 0600); if (fd < 0) err(1, "open"); if (ioctl(fd, FS_IOC_GETFLAGS, &flags) < 0) err(1, "ioctl: FS_IOC_GETFLAGS"); flags |= FS_IMMUTABLE_FL; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) < 0) err(1, "ioctl: FS_IOC_SETFLAGS"); warnx("ioctl returned no error"); return 0; } Running it gives the following result: $ strace -e ioctl ./test ioctl(3, FS_IOC_GETFLAGS, 0x7ffdbd8bfd38) = 0 ioctl(3, FS_IOC_SETFLAGS, 0x7ffdbd8bfd38) = 1 test: ioctl returned no error +++ exited with 0 +++ Running the program on a kernel with the bug fixed gives the proper result: $ strace -e ioctl ./test ioctl(3, FS_IOC_GETFLAGS, 0x7ffdd2768258) = 0 ioctl(3, FS_IOC_SETFLAGS, 0x7ffdd2768258) = -1 EPERM (Operation not permitted) test: ioctl: FS_IOC_SETFLAGS: Operation not permitted +++ exited with 1 +++ Signed-off-by: Anton Protopopov <a.s.protopopov@gmail.com> Signed-off-by: Theodore Ts'o <tytso@mit.edu>
2016-02-12 11:57:21 +07:00
int err = -EPERM, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
unsigned int jflag;
/* Is it quota file? Do not allow user to mess with it */
if (ext4_is_quota_file(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 ((flags ^ oldflags) & EXT4_EXTENTS_FL)
migrate = 1;
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) {
err = ext4_truncate(inode);
if (err)
goto flags_out;
}
handle = ext4_journal_start(inode, EXT4_HT_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;
/* These flags get special treatment later */
if (mask == EXT4_JOURNAL_DATA_FL || mask == EXT4_EXTENTS_FL)
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 = 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)) {
/*
* Changes to the journaling mode can cause unsafe changes to
* S_DAX if we are using the DAX mount option.
*/
if (test_opt(inode->i_sb, DAX)) {
err = -EBUSY;
goto flags_out;
}
err = ext4_change_inode_journal_flag(inode, jflag);
if (err)
goto flags_out;
}
if (migrate) {
if (flags & EXT4_EXTENTS_FL)
err = ext4_ext_migrate(inode);
else
err = ext4_ind_migrate(inode);
}
flags_out:
return err;
}
#ifdef CONFIG_QUOTA
static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
int err, rc;
handle_t *handle;
kprojid_t kprojid;
struct ext4_iloc iloc;
struct ext4_inode *raw_inode;
struct dquot *transfer_to[MAXQUOTAS] = { };
if (!ext4_has_feature_project(sb)) {
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
else
return 0;
}
if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE)
return -EOPNOTSUPP;
kprojid = make_kprojid(&init_user_ns, (projid_t)projid);
if (projid_eq(kprojid, EXT4_I(inode)->i_projid))
return 0;
err = mnt_want_write_file(filp);
if (err)
return err;
err = -EPERM;
inode_lock(inode);
/* Is it quota file? Do not allow user to mess with it */
if (ext4_is_quota_file(inode))
goto out_unlock;
err = ext4_get_inode_loc(inode, &iloc);
if (err)
goto out_unlock;
raw_inode = ext4_raw_inode(&iloc);
if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) {
err = ext4_expand_extra_isize(inode,
EXT4_SB(sb)->s_want_extra_isize,
&iloc);
if (err)
goto out_unlock;
} else {
brelse(iloc.bh);
}
dquot_initialize(inode);
handle = ext4_journal_start(inode, EXT4_HT_QUOTA,
EXT4_QUOTA_INIT_BLOCKS(sb) +
EXT4_QUOTA_DEL_BLOCKS(sb) + 3);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto out_unlock;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto out_stop;
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
if (!IS_ERR(transfer_to[PRJQUOTA])) {
/* __dquot_transfer() calls back ext4_get_inode_usage() which
* counts xattr inode references.
*/
down_read(&EXT4_I(inode)->xattr_sem);
err = __dquot_transfer(inode, transfer_to);
up_read(&EXT4_I(inode)->xattr_sem);
dqput(transfer_to[PRJQUOTA]);
if (err)
goto out_dirty;
}
EXT4_I(inode)->i_projid = kprojid;
inode->i_ctime = current_time(inode);
out_dirty:
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
out_stop:
ext4_journal_stop(handle);
out_unlock:
inode_unlock(inode);
mnt_drop_write_file(filp);
return err;
}
#else
static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
{
if (projid != EXT4_DEF_PROJID)
return -EOPNOTSUPP;
return 0;
}
#endif
/* Transfer internal flags to xflags */
static inline __u32 ext4_iflags_to_xflags(unsigned long iflags)
{
__u32 xflags = 0;
if (iflags & EXT4_SYNC_FL)
xflags |= FS_XFLAG_SYNC;
if (iflags & EXT4_IMMUTABLE_FL)
xflags |= FS_XFLAG_IMMUTABLE;
if (iflags & EXT4_APPEND_FL)
xflags |= FS_XFLAG_APPEND;
if (iflags & EXT4_NODUMP_FL)
xflags |= FS_XFLAG_NODUMP;
if (iflags & EXT4_NOATIME_FL)
xflags |= FS_XFLAG_NOATIME;
if (iflags & EXT4_PROJINHERIT_FL)
xflags |= FS_XFLAG_PROJINHERIT;
return xflags;
}
#define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
/* Transfer xflags flags to internal */
static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
{
unsigned long iflags = 0;
if (xflags & FS_XFLAG_SYNC)
iflags |= EXT4_SYNC_FL;
if (xflags & FS_XFLAG_IMMUTABLE)
iflags |= EXT4_IMMUTABLE_FL;
if (xflags & FS_XFLAG_APPEND)
iflags |= EXT4_APPEND_FL;
if (xflags & FS_XFLAG_NODUMP)
iflags |= EXT4_NODUMP_FL;
if (xflags & FS_XFLAG_NOATIME)
iflags |= EXT4_NOATIME_FL;
if (xflags & FS_XFLAG_PROJINHERIT)
iflags |= EXT4_PROJINHERIT_FL;
return iflags;
}
static int ext4_shutdown(struct super_block *sb, unsigned long arg)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
__u32 flags;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(flags, (__u32 __user *)arg))
return -EFAULT;
if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
return -EINVAL;
if (ext4_forced_shutdown(sbi))
return 0;
ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
switch (flags) {
case EXT4_GOING_FLAGS_DEFAULT:
freeze_bdev(sb->s_bdev);
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
thaw_bdev(sb->s_bdev, sb);
break;
case EXT4_GOING_FLAGS_LOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
(void) ext4_force_commit(sb);
jbd2_journal_abort(sbi->s_journal, 0);
}
break;
case EXT4_GOING_FLAGS_NOLOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
msleep(100);
jbd2_journal_abort(sbi->s_journal, 0);
}
break;
default:
return -EINVAL;
}
clear_opt(sb, DISCARD);
return 0;
}
struct getfsmap_info {
struct super_block *gi_sb;
struct fsmap_head __user *gi_data;
unsigned int gi_idx;
__u32 gi_last_flags;
};
static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv)
{
struct getfsmap_info *info = priv;
struct fsmap fm;
trace_ext4_getfsmap_mapping(info->gi_sb, xfm);
info->gi_last_flags = xfm->fmr_flags;
ext4_fsmap_from_internal(info->gi_sb, &fm, xfm);
if (copy_to_user(&info->gi_data->fmh_recs[info->gi_idx++], &fm,
sizeof(struct fsmap)))
return -EFAULT;
return 0;
}
static int ext4_ioc_getfsmap(struct super_block *sb,
struct fsmap_head __user *arg)
{
struct getfsmap_info info = {0};
struct ext4_fsmap_head xhead = {0};
struct fsmap_head head;
bool aborted = false;
int error;
if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
return -EFAULT;
if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
sizeof(head.fmh_keys[0].fmr_reserved)) ||
memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
sizeof(head.fmh_keys[1].fmr_reserved)))
return -EINVAL;
/*
* ext4 doesn't report file extents at all, so the only valid
* file offsets are the magic ones (all zeroes or all ones).
*/
if (head.fmh_keys[0].fmr_offset ||
(head.fmh_keys[1].fmr_offset != 0 &&
head.fmh_keys[1].fmr_offset != -1ULL))
return -EINVAL;
xhead.fmh_iflags = head.fmh_iflags;
xhead.fmh_count = head.fmh_count;
ext4_fsmap_to_internal(sb, &xhead.fmh_keys[0], &head.fmh_keys[0]);
ext4_fsmap_to_internal(sb, &xhead.fmh_keys[1], &head.fmh_keys[1]);
trace_ext4_getfsmap_low_key(sb, &xhead.fmh_keys[0]);
trace_ext4_getfsmap_high_key(sb, &xhead.fmh_keys[1]);
info.gi_sb = sb;
info.gi_data = arg;
error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info);
if (error == EXT4_QUERY_RANGE_ABORT) {
error = 0;
aborted = true;
} else if (error)
return error;
/* If we didn't abort, set the "last" flag in the last fmx */
if (!aborted && info.gi_idx) {
info.gi_last_flags |= FMR_OF_LAST;
if (copy_to_user(&info.gi_data->fmh_recs[info.gi_idx - 1].fmr_flags,
&info.gi_last_flags,
sizeof(info.gi_last_flags)))
return -EFAULT;
}
/* copy back header */
head.fmh_entries = xhead.fmh_entries;
head.fmh_oflags = xhead.fmh_oflags;
if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
return -EFAULT;
return 0;
}
static long ext4_ioctl_group_add(struct file *file,
struct ext4_new_group_data *input)
{
struct super_block *sb = file_inode(file)->i_sb;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(file);
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(file);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input->group);
group_add_out:
ext4_resize_end(sb);
return err;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
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 FS_IOC_GETFSMAP:
return ext4_ioc_getfsmap(sb, (void __user *)arg);
case EXT4_IOC_GETFLAGS:
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
if (flags & ~EXT4_FL_USER_VISIBLE)
return -EOPNOTSUPP;
/*
* chattr(1) grabs flags via GETFLAGS, modifies the result and
* passes that to SETFLAGS. So we cannot easily make SETFLAGS
* more restrictive than just silently masking off visible but
* not settable flags as we always did.
*/
flags &= EXT4_FL_USER_MODIFIABLE;
if (ext4_mask_flags(inode->i_mode, flags) != flags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
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_metadata_csum(inode->i_sb)) {
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;
}
inode_lock(inode);
handle = ext4_journal_start(inode, EXT4_HT_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 = current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
inode_unlock(inode);
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_feature_bigalloc(sb)) {
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_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
} else if (IS_DAX(inode)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with DAX");
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;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input)))
return -EFAULT;
return ext4_ioctl_group_add(filp, &input);
}
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.
*/
inode_lock((inode));
err = ext4_ext_migrate(inode);
inode_unlock((inode));
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_SWAP_BOOT:
ext4: grab missed write_count for EXT4_IOC_SWAP_BOOT Otherwise this provokes complain like follows: WARNING: CPU: 12 PID: 5795 at fs/ext4/ext4_jbd2.c:48 ext4_journal_check_start+0x4e/0xa0() Modules linked in: brd iTCO_wdt lpc_ich mfd_core igb ptp dm_mirror dm_region_hash dm_log dm_mod CPU: 12 PID: 5795 Comm: python Not tainted 3.17.0-rc2-00175-gae5344f #158 Hardware name: Intel Corporation W2600CR/W2600CR, BIOS SE5C600.86B.99.99.x028.061320111235 06/13/2011 0000000000000030 ffff8808116cfd28 ffffffff815c7dfc 0000000000000030 0000000000000000 ffff8808116cfd68 ffffffff8106ce8c ffff8808116cfdc8 ffff880813b16000 ffff880806ad6ae8 ffffffff81202008 0000000000000000 Call Trace: [<ffffffff815c7dfc>] dump_stack+0x51/0x6d [<ffffffff8106ce8c>] warn_slowpath_common+0x8c/0xc0 [<ffffffff81202008>] ? ext4_ioctl+0x9e8/0xeb0 [<ffffffff8106ceda>] warn_slowpath_null+0x1a/0x20 [<ffffffff8122867e>] ext4_journal_check_start+0x4e/0xa0 [<ffffffff81228c10>] __ext4_journal_start_sb+0x90/0x110 [<ffffffff81202008>] ext4_ioctl+0x9e8/0xeb0 [<ffffffff8107b0bd>] ? ptrace_stop+0x24d/0x2f0 [<ffffffff81088530>] ? alloc_pid+0x480/0x480 [<ffffffff8107b1f2>] ? ptrace_do_notify+0x92/0xb0 [<ffffffff81186545>] do_vfs_ioctl+0x4e5/0x550 [<ffffffff815cdbcb>] ? _raw_spin_unlock_irq+0x2b/0x40 [<ffffffff81186603>] SyS_ioctl+0x53/0x80 [<ffffffff815ce2ce>] tracesys+0xd0/0xd5 Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-10-03 23:47:23 +07:00
{
int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
ext4: grab missed write_count for EXT4_IOC_SWAP_BOOT Otherwise this provokes complain like follows: WARNING: CPU: 12 PID: 5795 at fs/ext4/ext4_jbd2.c:48 ext4_journal_check_start+0x4e/0xa0() Modules linked in: brd iTCO_wdt lpc_ich mfd_core igb ptp dm_mirror dm_region_hash dm_log dm_mod CPU: 12 PID: 5795 Comm: python Not tainted 3.17.0-rc2-00175-gae5344f #158 Hardware name: Intel Corporation W2600CR/W2600CR, BIOS SE5C600.86B.99.99.x028.061320111235 06/13/2011 0000000000000030 ffff8808116cfd28 ffffffff815c7dfc 0000000000000030 0000000000000000 ffff8808116cfd68 ffffffff8106ce8c ffff8808116cfdc8 ffff880813b16000 ffff880806ad6ae8 ffffffff81202008 0000000000000000 Call Trace: [<ffffffff815c7dfc>] dump_stack+0x51/0x6d [<ffffffff8106ce8c>] warn_slowpath_common+0x8c/0xc0 [<ffffffff81202008>] ? ext4_ioctl+0x9e8/0xeb0 [<ffffffff8106ceda>] warn_slowpath_null+0x1a/0x20 [<ffffffff8122867e>] ext4_journal_check_start+0x4e/0xa0 [<ffffffff81228c10>] __ext4_journal_start_sb+0x90/0x110 [<ffffffff81202008>] ext4_ioctl+0x9e8/0xeb0 [<ffffffff8107b0bd>] ? ptrace_stop+0x24d/0x2f0 [<ffffffff81088530>] ? alloc_pid+0x480/0x480 [<ffffffff8107b1f2>] ? ptrace_do_notify+0x92/0xb0 [<ffffffff81186545>] do_vfs_ioctl+0x4e5/0x550 [<ffffffff815cdbcb>] ? _raw_spin_unlock_irq+0x2b/0x40 [<ffffffff81186603>] SyS_ioctl+0x53/0x80 [<ffffffff815ce2ce>] tracesys+0xd0/0xd5 Reviewed-by: Jan Kara <jack@suse.cz> Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org> Signed-off-by: Theodore Ts'o <tytso@mit.edu> Cc: stable@vger.kernel.org
2014-10-03 23:47:23 +07:00
err = mnt_want_write_file(filp);
if (err)
return err;
err = swap_inode_boot_loader(sb, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
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);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
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;
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
case EXT4_IOC_SET_ENCRYPTION_POLICY:
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
int err, err2;
struct ext4_sb_info *sbi = EXT4_SB(sb);
handle_t *handle;
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
err = mnt_want_write_file(filp);
if (err)
return err;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto pwsalt_err_exit;
}
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
err2 = ext4_journal_stop(handle);
if (err2 && !err)
err = err2;
pwsalt_err_exit:
mnt_drop_write_file(filp);
if (err)
return err;
}
if (copy_to_user((void __user *) arg,
sbi->s_es->s_encrypt_pw_salt, 16))
return -EFAULT;
return 0;
#else
return -EOPNOTSUPP;
#endif
}
case EXT4_IOC_GET_ENCRYPTION_POLICY:
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
case EXT4_IOC_FSGETXATTR:
{
struct fsxattr fa;
memset(&fa, 0, sizeof(struct fsxattr));
fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
if (ext4_has_feature_project(inode->i_sb)) {
fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
EXT4_I(inode)->i_projid);
}
if (copy_to_user((struct fsxattr __user *)arg,
&fa, sizeof(fa)))
return -EFAULT;
return 0;
}
case EXT4_IOC_FSSETXATTR:
{
struct fsxattr fa;
int err;
if (copy_from_user(&fa, (struct fsxattr __user *)arg,
sizeof(fa)))
return -EFAULT;
/* Make sure caller has proper permission */
if (!inode_owner_or_capable(inode))
return -EACCES;
if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS)
return -EOPNOTSUPP;
flags = ext4_xflags_to_iflags(fa.fsx_xflags);
if (ext4_mask_flags(inode->i_mode, flags) != flags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
(flags & EXT4_FL_XFLAG_VISIBLE);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
if (err)
return err;
err = ext4_ioctl_setproject(filp, fa.fsx_projid);
if (err)
return err;
return 0;
}
case EXT4_IOC_SHUTDOWN:
return ext4_shutdown(sb, arg);
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_data input;
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;
return ext4_ioctl_group_add(file, &input);
}
case EXT4_IOC_MOVE_EXT:
case EXT4_IOC_RESIZE_FS:
case EXT4_IOC_PRECACHE_EXTENTS:
case EXT4_IOC_SET_ENCRYPTION_POLICY:
case EXT4_IOC_GET_ENCRYPTION_PWSALT:
case EXT4_IOC_GET_ENCRYPTION_POLICY:
case EXT4_IOC_SHUTDOWN:
case FS_IOC_GETFSMAP:
break;
default:
return -ENOIOCTLCMD;
}
return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
}
#endif