linux/fs/quota/quota.c

1014 lines
28 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 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Quota code necessary even when VFS quota support is not compiled
* into the kernel. The interesting stuff is over in dquot.c, here
* we have symbols for initial quotactl(2) handling, the sysctl(2)
* variables, etc - things needed even when quota support disabled.
*/
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/slab.h>
#include <asm/current.h>
#include <linux/blkdev.h>
#include <linux/uaccess.h>
#include <linux/kernel.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/capability.h>
#include <linux/quotaops.h>
#include <linux/types.h>
#include <linux/mount.h>
#include <linux/writeback.h>
fs/quota: Fix spectre gadget in do_quotactl 'type' is user-controlled, so sanitize it after the bounds check to avoid using it in speculative execution. This covers the following potential gadgets detected with the help of smatch: * fs/ext4/super.c:5741 ext4_quota_read() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/ext4/super.c:5778 ext4_quota_write() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/f2fs/super.c:1552 f2fs_quota_read() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/f2fs/super.c:1608 f2fs_quota_write() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/quota/dquot.c:412 mark_info_dirty() warn: potential spectre issue 'sb_dqopt(sb)->info' [w] * fs/quota/dquot.c:933 dqinit_needed() warn: potential spectre issue 'dquots' [r] * fs/quota/dquot.c:2112 dquot_commit_info() warn: potential spectre issue 'dqopt->ops' [r] * fs/quota/dquot.c:2362 vfs_load_quota_inode() warn: potential spectre issue 'dqopt->files' [w] (local cap) * fs/quota/dquot.c:2369 vfs_load_quota_inode() warn: potential spectre issue 'dqopt->ops' [w] (local cap) * fs/quota/dquot.c:2370 vfs_load_quota_inode() warn: potential spectre issue 'dqopt->info' [w] (local cap) * fs/quota/quota.c:110 quota_getfmt() warn: potential spectre issue 'sb_dqopt(sb)->info' [r] * fs/quota/quota_v2.c:84 v2_check_quota_file() warn: potential spectre issue 'quota_magics' [w] * fs/quota/quota_v2.c:85 v2_check_quota_file() warn: potential spectre issue 'quota_versions' [w] * fs/quota/quota_v2.c:96 v2_read_file_info() warn: potential spectre issue 'dqopt->info' [r] * fs/quota/quota_v2.c:172 v2_write_file_info() warn: potential spectre issue 'dqopt->info' [r] Additionally, a quick inspection indicates there are array accesses with 'type' in quota_on() and quota_off() functions which are also addressed by this. Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Jeremy Cline <jcline@redhat.com> Signed-off-by: Jan Kara <jack@suse.cz>
2018-07-31 09:37:31 +08:00
#include <linux/nospec.h>
#include "compat.h"
#include "../internal.h"
static int check_quotactl_permission(struct super_block *sb, int type, int cmd,
qid_t id)
{
switch (cmd) {
/* these commands do not require any special privilegues */
case Q_GETFMT:
case Q_SYNC:
case Q_GETINFO:
case Q_XGETQSTAT:
case Q_XGETQSTATV:
case Q_XQUOTASYNC:
break;
/* allow to query information for dquots we "own" */
case Q_GETQUOTA:
case Q_XGETQUOTA:
if ((type == USRQUOTA && uid_eq(current_euid(), make_kuid(current_user_ns(), id))) ||
(type == GRPQUOTA && in_egroup_p(make_kgid(current_user_ns(), id))))
break;
fallthrough;
default:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
}
return security_quotactl(cmd, type, id, sb);
}
static void quota_sync_one(struct super_block *sb, void *arg)
{
int type = *(int *)arg;
if (sb->s_qcop && sb->s_qcop->quota_sync &&
(sb->s_quota_types & (1 << type)))
sb->s_qcop->quota_sync(sb, type);
}
static int quota_sync_all(int type)
{
int ret;
ret = security_quotactl(Q_SYNC, type, 0, NULL);
if (!ret)
iterate_supers(quota_sync_one, &type);
return ret;
}
unsigned int qtype_enforce_flag(int type)
{
switch (type) {
case USRQUOTA:
return FS_QUOTA_UDQ_ENFD;
case GRPQUOTA:
return FS_QUOTA_GDQ_ENFD;
case PRJQUOTA:
return FS_QUOTA_PDQ_ENFD;
}
return 0;
}
static int quota_quotaon(struct super_block *sb, int type, qid_t id,
const struct path *path)
{
if (!sb->s_qcop->quota_on && !sb->s_qcop->quota_enable)
return -ENOSYS;
if (sb->s_qcop->quota_enable)
return sb->s_qcop->quota_enable(sb, qtype_enforce_flag(type));
if (IS_ERR(path))
return PTR_ERR(path);
return sb->s_qcop->quota_on(sb, type, id, path);
}
static int quota_quotaoff(struct super_block *sb, int type)
{
if (!sb->s_qcop->quota_off && !sb->s_qcop->quota_disable)
return -ENOSYS;
if (sb->s_qcop->quota_disable)
return sb->s_qcop->quota_disable(sb, qtype_enforce_flag(type));
return sb->s_qcop->quota_off(sb, type);
}
static int quota_getfmt(struct super_block *sb, int type, void __user *addr)
{
__u32 fmt;
if (!sb_has_quota_active(sb, type))
return -ESRCH;
fmt = sb_dqopt(sb)->info[type].dqi_format->qf_fmt_id;
if (copy_to_user(addr, &fmt, sizeof(fmt)))
return -EFAULT;
return 0;
}
static int quota_getinfo(struct super_block *sb, int type, void __user *addr)
{
struct qc_state state;
struct qc_type_state *tstate;
struct if_dqinfo uinfo;
int ret;
if (!sb->s_qcop->get_state)
return -ENOSYS;
ret = sb->s_qcop->get_state(sb, &state);
if (ret)
return ret;
tstate = state.s_state + type;
if (!(tstate->flags & QCI_ACCT_ENABLED))
return -ESRCH;
memset(&uinfo, 0, sizeof(uinfo));
uinfo.dqi_bgrace = tstate->spc_timelimit;
uinfo.dqi_igrace = tstate->ino_timelimit;
if (tstate->flags & QCI_SYSFILE)
uinfo.dqi_flags |= DQF_SYS_FILE;
if (tstate->flags & QCI_ROOT_SQUASH)
uinfo.dqi_flags |= DQF_ROOT_SQUASH;
uinfo.dqi_valid = IIF_ALL;
if (copy_to_user(addr, &uinfo, sizeof(uinfo)))
return -EFAULT;
return 0;
}
static int quota_setinfo(struct super_block *sb, int type, void __user *addr)
{
struct if_dqinfo info;
struct qc_info qinfo;
if (copy_from_user(&info, addr, sizeof(info)))
return -EFAULT;
if (!sb->s_qcop->set_info)
return -ENOSYS;
if (info.dqi_valid & ~(IIF_FLAGS | IIF_BGRACE | IIF_IGRACE))
return -EINVAL;
memset(&qinfo, 0, sizeof(qinfo));
if (info.dqi_valid & IIF_FLAGS) {
if (info.dqi_flags & ~DQF_SETINFO_MASK)
return -EINVAL;
if (info.dqi_flags & DQF_ROOT_SQUASH)
qinfo.i_flags |= QCI_ROOT_SQUASH;
qinfo.i_fieldmask |= QC_FLAGS;
}
if (info.dqi_valid & IIF_BGRACE) {
qinfo.i_spc_timelimit = info.dqi_bgrace;
qinfo.i_fieldmask |= QC_SPC_TIMER;
}
if (info.dqi_valid & IIF_IGRACE) {
qinfo.i_ino_timelimit = info.dqi_igrace;
qinfo.i_fieldmask |= QC_INO_TIMER;
}
return sb->s_qcop->set_info(sb, type, &qinfo);
}
static inline qsize_t qbtos(qsize_t blocks)
{
return blocks << QIF_DQBLKSIZE_BITS;
}
static inline qsize_t stoqb(qsize_t space)
{
return (space + QIF_DQBLKSIZE - 1) >> QIF_DQBLKSIZE_BITS;
}
static void copy_to_if_dqblk(struct if_dqblk *dst, struct qc_dqblk *src)
{
memset(dst, 0, sizeof(*dst));
dst->dqb_bhardlimit = stoqb(src->d_spc_hardlimit);
dst->dqb_bsoftlimit = stoqb(src->d_spc_softlimit);
dst->dqb_curspace = src->d_space;
dst->dqb_ihardlimit = src->d_ino_hardlimit;
dst->dqb_isoftlimit = src->d_ino_softlimit;
dst->dqb_curinodes = src->d_ino_count;
dst->dqb_btime = src->d_spc_timer;
dst->dqb_itime = src->d_ino_timer;
dst->dqb_valid = QIF_ALL;
}
static int quota_getquota(struct super_block *sb, int type, qid_t id,
void __user *addr)
{
struct kqid qid;
struct qc_dqblk fdq;
struct if_dqblk idq;
int ret;
if (!sb->s_qcop->get_dqblk)
return -ENOSYS;
qid = make_kqid(current_user_ns(), type, id);
if (!qid_has_mapping(sb->s_user_ns, qid))
return -EINVAL;
ret = sb->s_qcop->get_dqblk(sb, qid, &fdq);
if (ret)
return ret;
copy_to_if_dqblk(&idq, &fdq);
if (compat_need_64bit_alignment_fixup()) {
struct compat_if_dqblk __user *compat_dqblk = addr;
if (copy_to_user(compat_dqblk, &idq, sizeof(*compat_dqblk)))
return -EFAULT;
if (put_user(idq.dqb_valid, &compat_dqblk->dqb_valid))
return -EFAULT;
} else {
if (copy_to_user(addr, &idq, sizeof(idq)))
return -EFAULT;
}
return 0;
}
/*
* Return quota for next active quota >= this id, if any exists,
* otherwise return -ENOENT via ->get_nextdqblk
*/
static int quota_getnextquota(struct super_block *sb, int type, qid_t id,
void __user *addr)
{
struct kqid qid;
struct qc_dqblk fdq;
struct if_nextdqblk idq;
int ret;
if (!sb->s_qcop->get_nextdqblk)
return -ENOSYS;
qid = make_kqid(current_user_ns(), type, id);
if (!qid_has_mapping(sb->s_user_ns, qid))
return -EINVAL;
ret = sb->s_qcop->get_nextdqblk(sb, &qid, &fdq);
if (ret)
return ret;
/* struct if_nextdqblk is a superset of struct if_dqblk */
copy_to_if_dqblk((struct if_dqblk *)&idq, &fdq);
idq.dqb_id = from_kqid(current_user_ns(), qid);
if (copy_to_user(addr, &idq, sizeof(idq)))
return -EFAULT;
return 0;
}
static void copy_from_if_dqblk(struct qc_dqblk *dst, struct if_dqblk *src)
{
dst->d_spc_hardlimit = qbtos(src->dqb_bhardlimit);
dst->d_spc_softlimit = qbtos(src->dqb_bsoftlimit);
dst->d_space = src->dqb_curspace;
dst->d_ino_hardlimit = src->dqb_ihardlimit;
dst->d_ino_softlimit = src->dqb_isoftlimit;
dst->d_ino_count = src->dqb_curinodes;
dst->d_spc_timer = src->dqb_btime;
dst->d_ino_timer = src->dqb_itime;
dst->d_fieldmask = 0;
if (src->dqb_valid & QIF_BLIMITS)
dst->d_fieldmask |= QC_SPC_SOFT | QC_SPC_HARD;
if (src->dqb_valid & QIF_SPACE)
dst->d_fieldmask |= QC_SPACE;
if (src->dqb_valid & QIF_ILIMITS)
dst->d_fieldmask |= QC_INO_SOFT | QC_INO_HARD;
if (src->dqb_valid & QIF_INODES)
dst->d_fieldmask |= QC_INO_COUNT;
if (src->dqb_valid & QIF_BTIME)
dst->d_fieldmask |= QC_SPC_TIMER;
if (src->dqb_valid & QIF_ITIME)
dst->d_fieldmask |= QC_INO_TIMER;
}
static int quota_setquota(struct super_block *sb, int type, qid_t id,
void __user *addr)
{
struct qc_dqblk fdq;
struct if_dqblk idq;
struct kqid qid;
if (compat_need_64bit_alignment_fixup()) {
struct compat_if_dqblk __user *compat_dqblk = addr;
if (copy_from_user(&idq, compat_dqblk, sizeof(*compat_dqblk)) ||
get_user(idq.dqb_valid, &compat_dqblk->dqb_valid))
return -EFAULT;
} else {
if (copy_from_user(&idq, addr, sizeof(idq)))
return -EFAULT;
}
if (!sb->s_qcop->set_dqblk)
return -ENOSYS;
qid = make_kqid(current_user_ns(), type, id);
if (!qid_has_mapping(sb->s_user_ns, qid))
return -EINVAL;
copy_from_if_dqblk(&fdq, &idq);
return sb->s_qcop->set_dqblk(sb, qid, &fdq);
}
static int quota_enable(struct super_block *sb, void __user *addr)
{
__u32 flags;
if (copy_from_user(&flags, addr, sizeof(flags)))
return -EFAULT;
if (!sb->s_qcop->quota_enable)
return -ENOSYS;
return sb->s_qcop->quota_enable(sb, flags);
}
static int quota_disable(struct super_block *sb, void __user *addr)
{
__u32 flags;
if (copy_from_user(&flags, addr, sizeof(flags)))
return -EFAULT;
if (!sb->s_qcop->quota_disable)
return -ENOSYS;
return sb->s_qcop->quota_disable(sb, flags);
}
static int quota_state_to_flags(struct qc_state *state)
{
int flags = 0;
if (state->s_state[USRQUOTA].flags & QCI_ACCT_ENABLED)
flags |= FS_QUOTA_UDQ_ACCT;
if (state->s_state[USRQUOTA].flags & QCI_LIMITS_ENFORCED)
flags |= FS_QUOTA_UDQ_ENFD;
if (state->s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED)
flags |= FS_QUOTA_GDQ_ACCT;
if (state->s_state[GRPQUOTA].flags & QCI_LIMITS_ENFORCED)
flags |= FS_QUOTA_GDQ_ENFD;
if (state->s_state[PRJQUOTA].flags & QCI_ACCT_ENABLED)
flags |= FS_QUOTA_PDQ_ACCT;
if (state->s_state[PRJQUOTA].flags & QCI_LIMITS_ENFORCED)
flags |= FS_QUOTA_PDQ_ENFD;
return flags;
}
static int quota_getstate(struct super_block *sb, int type,
struct fs_quota_stat *fqs)
{
struct qc_state state;
int ret;
memset(&state, 0, sizeof (struct qc_state));
ret = sb->s_qcop->get_state(sb, &state);
if (ret < 0)
return ret;
memset(fqs, 0, sizeof(*fqs));
fqs->qs_version = FS_QSTAT_VERSION;
fqs->qs_flags = quota_state_to_flags(&state);
/* No quota enabled? */
if (!fqs->qs_flags)
return -ENOSYS;
fqs->qs_incoredqs = state.s_incoredqs;
fqs->qs_btimelimit = state.s_state[type].spc_timelimit;
fqs->qs_itimelimit = state.s_state[type].ino_timelimit;
fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit;
fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit;
fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit;
/* Inodes may be allocated even if inactive; copy out if present */
if (state.s_state[USRQUOTA].ino) {
fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino;
fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks;
fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents;
}
if (state.s_state[GRPQUOTA].ino) {
fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino;
fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks;
fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents;
}
if (state.s_state[PRJQUOTA].ino) {
/*
* Q_XGETQSTAT doesn't have room for both group and project
* quotas. So, allow the project quota values to be copied out
* only if there is no group quota information available.
*/
if (!(state.s_state[GRPQUOTA].flags & QCI_ACCT_ENABLED)) {
fqs->qs_gquota.qfs_ino = state.s_state[PRJQUOTA].ino;
fqs->qs_gquota.qfs_nblks =
state.s_state[PRJQUOTA].blocks;
fqs->qs_gquota.qfs_nextents =
state.s_state[PRJQUOTA].nextents;
}
}
return 0;
}
static int compat_copy_fs_qfilestat(struct compat_fs_qfilestat __user *to,
struct fs_qfilestat *from)
{
if (copy_to_user(to, from, sizeof(*to)) ||
put_user(from->qfs_nextents, &to->qfs_nextents))
return -EFAULT;
return 0;
}
static int compat_copy_fs_quota_stat(struct compat_fs_quota_stat __user *to,
struct fs_quota_stat *from)
{
if (put_user(from->qs_version, &to->qs_version) ||
put_user(from->qs_flags, &to->qs_flags) ||
put_user(from->qs_pad, &to->qs_pad) ||
compat_copy_fs_qfilestat(&to->qs_uquota, &from->qs_uquota) ||
compat_copy_fs_qfilestat(&to->qs_gquota, &from->qs_gquota) ||
put_user(from->qs_incoredqs, &to->qs_incoredqs) ||
put_user(from->qs_btimelimit, &to->qs_btimelimit) ||
put_user(from->qs_itimelimit, &to->qs_itimelimit) ||
put_user(from->qs_rtbtimelimit, &to->qs_rtbtimelimit) ||
put_user(from->qs_bwarnlimit, &to->qs_bwarnlimit) ||
put_user(from->qs_iwarnlimit, &to->qs_iwarnlimit))
return -EFAULT;
return 0;
}
static int quota_getxstate(struct super_block *sb, int type, void __user *addr)
{
struct fs_quota_stat fqs;
int ret;
if (!sb->s_qcop->get_state)
return -ENOSYS;
ret = quota_getstate(sb, type, &fqs);
if (ret)
return ret;
if (compat_need_64bit_alignment_fixup())
return compat_copy_fs_quota_stat(addr, &fqs);
if (copy_to_user(addr, &fqs, sizeof(fqs)))
return -EFAULT;
return 0;
}
static int quota_getstatev(struct super_block *sb, int type,
struct fs_quota_statv *fqs)
{
struct qc_state state;
int ret;
memset(&state, 0, sizeof (struct qc_state));
ret = sb->s_qcop->get_state(sb, &state);
if (ret < 0)
return ret;
memset(fqs, 0, sizeof(*fqs));
fqs->qs_version = FS_QSTAT_VERSION;
fqs->qs_flags = quota_state_to_flags(&state);
/* No quota enabled? */
if (!fqs->qs_flags)
return -ENOSYS;
fqs->qs_incoredqs = state.s_incoredqs;
fqs->qs_btimelimit = state.s_state[type].spc_timelimit;
fqs->qs_itimelimit = state.s_state[type].ino_timelimit;
fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit;
fqs->qs_bwarnlimit = state.s_state[type].spc_warnlimit;
fqs->qs_iwarnlimit = state.s_state[type].ino_warnlimit;
fqs->qs_rtbwarnlimit = state.s_state[type].rt_spc_warnlimit;
/* Inodes may be allocated even if inactive; copy out if present */
if (state.s_state[USRQUOTA].ino) {
fqs->qs_uquota.qfs_ino = state.s_state[USRQUOTA].ino;
fqs->qs_uquota.qfs_nblks = state.s_state[USRQUOTA].blocks;
fqs->qs_uquota.qfs_nextents = state.s_state[USRQUOTA].nextents;
}
if (state.s_state[GRPQUOTA].ino) {
fqs->qs_gquota.qfs_ino = state.s_state[GRPQUOTA].ino;
fqs->qs_gquota.qfs_nblks = state.s_state[GRPQUOTA].blocks;
fqs->qs_gquota.qfs_nextents = state.s_state[GRPQUOTA].nextents;
}
if (state.s_state[PRJQUOTA].ino) {
fqs->qs_pquota.qfs_ino = state.s_state[PRJQUOTA].ino;
fqs->qs_pquota.qfs_nblks = state.s_state[PRJQUOTA].blocks;
fqs->qs_pquota.qfs_nextents = state.s_state[PRJQUOTA].nextents;
}
return 0;
}
static int quota_getxstatev(struct super_block *sb, int type, void __user *addr)
{
struct fs_quota_statv fqs;
int ret;
if (!sb->s_qcop->get_state)
return -ENOSYS;
memset(&fqs, 0, sizeof(fqs));
if (copy_from_user(&fqs, addr, 1)) /* Just read qs_version */
return -EFAULT;
/* If this kernel doesn't support user specified version, fail */
switch (fqs.qs_version) {
case FS_QSTATV_VERSION1:
break;
default:
return -EINVAL;
}
ret = quota_getstatev(sb, type, &fqs);
if (!ret && copy_to_user(addr, &fqs, sizeof(fqs)))
return -EFAULT;
return ret;
}
/*
* XFS defines BBTOB and BTOBB macros inside fs/xfs/ and we cannot move them
* out of there as xfsprogs rely on definitions being in that header file. So
* just define same functions here for quota purposes.
*/
#define XFS_BB_SHIFT 9
static inline u64 quota_bbtob(u64 blocks)
{
return blocks << XFS_BB_SHIFT;
}
static inline u64 quota_btobb(u64 bytes)
{
return (bytes + (1 << XFS_BB_SHIFT) - 1) >> XFS_BB_SHIFT;
}
static inline s64 copy_from_xfs_dqblk_ts(const struct fs_disk_quota *d,
__s32 timer, __s8 timer_hi)
{
if (d->d_fieldmask & FS_DQ_BIGTIME)
return (u32)timer | (s64)timer_hi << 32;
return timer;
}
static void copy_from_xfs_dqblk(struct qc_dqblk *dst, struct fs_disk_quota *src)
{
dst->d_spc_hardlimit = quota_bbtob(src->d_blk_hardlimit);
dst->d_spc_softlimit = quota_bbtob(src->d_blk_softlimit);
dst->d_ino_hardlimit = src->d_ino_hardlimit;
dst->d_ino_softlimit = src->d_ino_softlimit;
dst->d_space = quota_bbtob(src->d_bcount);
dst->d_ino_count = src->d_icount;
dst->d_ino_timer = copy_from_xfs_dqblk_ts(src, src->d_itimer,
src->d_itimer_hi);
dst->d_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_btimer,
src->d_btimer_hi);
dst->d_ino_warns = src->d_iwarns;
dst->d_spc_warns = src->d_bwarns;
dst->d_rt_spc_hardlimit = quota_bbtob(src->d_rtb_hardlimit);
dst->d_rt_spc_softlimit = quota_bbtob(src->d_rtb_softlimit);
dst->d_rt_space = quota_bbtob(src->d_rtbcount);
dst->d_rt_spc_timer = copy_from_xfs_dqblk_ts(src, src->d_rtbtimer,
src->d_rtbtimer_hi);
dst->d_rt_spc_warns = src->d_rtbwarns;
dst->d_fieldmask = 0;
if (src->d_fieldmask & FS_DQ_ISOFT)
dst->d_fieldmask |= QC_INO_SOFT;
if (src->d_fieldmask & FS_DQ_IHARD)
dst->d_fieldmask |= QC_INO_HARD;
if (src->d_fieldmask & FS_DQ_BSOFT)
dst->d_fieldmask |= QC_SPC_SOFT;
if (src->d_fieldmask & FS_DQ_BHARD)
dst->d_fieldmask |= QC_SPC_HARD;
if (src->d_fieldmask & FS_DQ_RTBSOFT)
dst->d_fieldmask |= QC_RT_SPC_SOFT;
if (src->d_fieldmask & FS_DQ_RTBHARD)
dst->d_fieldmask |= QC_RT_SPC_HARD;
if (src->d_fieldmask & FS_DQ_BTIMER)
dst->d_fieldmask |= QC_SPC_TIMER;
if (src->d_fieldmask & FS_DQ_ITIMER)
dst->d_fieldmask |= QC_INO_TIMER;
if (src->d_fieldmask & FS_DQ_RTBTIMER)
dst->d_fieldmask |= QC_RT_SPC_TIMER;
if (src->d_fieldmask & FS_DQ_BWARNS)
dst->d_fieldmask |= QC_SPC_WARNS;
if (src->d_fieldmask & FS_DQ_IWARNS)
dst->d_fieldmask |= QC_INO_WARNS;
if (src->d_fieldmask & FS_DQ_RTBWARNS)
dst->d_fieldmask |= QC_RT_SPC_WARNS;
if (src->d_fieldmask & FS_DQ_BCOUNT)
dst->d_fieldmask |= QC_SPACE;
if (src->d_fieldmask & FS_DQ_ICOUNT)
dst->d_fieldmask |= QC_INO_COUNT;
if (src->d_fieldmask & FS_DQ_RTBCOUNT)
dst->d_fieldmask |= QC_RT_SPACE;
}
static void copy_qcinfo_from_xfs_dqblk(struct qc_info *dst,
struct fs_disk_quota *src)
{
memset(dst, 0, sizeof(*dst));
dst->i_spc_timelimit = src->d_btimer;
dst->i_ino_timelimit = src->d_itimer;
dst->i_rt_spc_timelimit = src->d_rtbtimer;
dst->i_ino_warnlimit = src->d_iwarns;
dst->i_spc_warnlimit = src->d_bwarns;
dst->i_rt_spc_warnlimit = src->d_rtbwarns;
if (src->d_fieldmask & FS_DQ_BWARNS)
dst->i_fieldmask |= QC_SPC_WARNS;
if (src->d_fieldmask & FS_DQ_IWARNS)
dst->i_fieldmask |= QC_INO_WARNS;
if (src->d_fieldmask & FS_DQ_RTBWARNS)
dst->i_fieldmask |= QC_RT_SPC_WARNS;
if (src->d_fieldmask & FS_DQ_BTIMER)
dst->i_fieldmask |= QC_SPC_TIMER;
if (src->d_fieldmask & FS_DQ_ITIMER)
dst->i_fieldmask |= QC_INO_TIMER;
if (src->d_fieldmask & FS_DQ_RTBTIMER)
dst->i_fieldmask |= QC_RT_SPC_TIMER;
}
static int quota_setxquota(struct super_block *sb, int type, qid_t id,
void __user *addr)
{
struct fs_disk_quota fdq;
struct qc_dqblk qdq;
struct kqid qid;
if (copy_from_user(&fdq, addr, sizeof(fdq)))
return -EFAULT;
if (!sb->s_qcop->set_dqblk)
return -ENOSYS;
qid = make_kqid(current_user_ns(), type, id);
if (!qid_has_mapping(sb->s_user_ns, qid))
return -EINVAL;
/* Are we actually setting timer / warning limits for all users? */
if (from_kqid(sb->s_user_ns, qid) == 0 &&
fdq.d_fieldmask & (FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK)) {
struct qc_info qinfo;
int ret;
if (!sb->s_qcop->set_info)
return -EINVAL;
copy_qcinfo_from_xfs_dqblk(&qinfo, &fdq);
ret = sb->s_qcop->set_info(sb, type, &qinfo);
if (ret)
return ret;
/* These are already done */
fdq.d_fieldmask &= ~(FS_DQ_WARNS_MASK | FS_DQ_TIMER_MASK);
}
copy_from_xfs_dqblk(&qdq, &fdq);
return sb->s_qcop->set_dqblk(sb, qid, &qdq);
}
static inline void copy_to_xfs_dqblk_ts(const struct fs_disk_quota *d,
__s32 *timer_lo, __s8 *timer_hi, s64 timer)
{
*timer_lo = timer;
if (d->d_fieldmask & FS_DQ_BIGTIME)
*timer_hi = timer >> 32;
}
static inline bool want_bigtime(s64 timer)
{
return timer > S32_MAX || timer < S32_MIN;
}
static void copy_to_xfs_dqblk(struct fs_disk_quota *dst, struct qc_dqblk *src,
int type, qid_t id)
{
memset(dst, 0, sizeof(*dst));
if (want_bigtime(src->d_ino_timer) || want_bigtime(src->d_spc_timer) ||
want_bigtime(src->d_rt_spc_timer))
dst->d_fieldmask |= FS_DQ_BIGTIME;
dst->d_version = FS_DQUOT_VERSION;
dst->d_id = id;
if (type == USRQUOTA)
dst->d_flags = FS_USER_QUOTA;
else if (type == PRJQUOTA)
dst->d_flags = FS_PROJ_QUOTA;
else
dst->d_flags = FS_GROUP_QUOTA;
dst->d_blk_hardlimit = quota_btobb(src->d_spc_hardlimit);
dst->d_blk_softlimit = quota_btobb(src->d_spc_softlimit);
dst->d_ino_hardlimit = src->d_ino_hardlimit;
dst->d_ino_softlimit = src->d_ino_softlimit;
dst->d_bcount = quota_btobb(src->d_space);
dst->d_icount = src->d_ino_count;
copy_to_xfs_dqblk_ts(dst, &dst->d_itimer, &dst->d_itimer_hi,
src->d_ino_timer);
copy_to_xfs_dqblk_ts(dst, &dst->d_btimer, &dst->d_btimer_hi,
src->d_spc_timer);
dst->d_iwarns = src->d_ino_warns;
dst->d_bwarns = src->d_spc_warns;
dst->d_rtb_hardlimit = quota_btobb(src->d_rt_spc_hardlimit);
dst->d_rtb_softlimit = quota_btobb(src->d_rt_spc_softlimit);
dst->d_rtbcount = quota_btobb(src->d_rt_space);
copy_to_xfs_dqblk_ts(dst, &dst->d_rtbtimer, &dst->d_rtbtimer_hi,
src->d_rt_spc_timer);
dst->d_rtbwarns = src->d_rt_spc_warns;
}
static int quota_getxquota(struct super_block *sb, int type, qid_t id,
void __user *addr)
{
struct fs_disk_quota fdq;
struct qc_dqblk qdq;
struct kqid qid;
int ret;
if (!sb->s_qcop->get_dqblk)
return -ENOSYS;
qid = make_kqid(current_user_ns(), type, id);
if (!qid_has_mapping(sb->s_user_ns, qid))
return -EINVAL;
ret = sb->s_qcop->get_dqblk(sb, qid, &qdq);
if (ret)
return ret;
copy_to_xfs_dqblk(&fdq, &qdq, type, id);
if (copy_to_user(addr, &fdq, sizeof(fdq)))
return -EFAULT;
return ret;
}
/*
* Return quota for next active quota >= this id, if any exists,
* otherwise return -ENOENT via ->get_nextdqblk.
*/
static int quota_getnextxquota(struct super_block *sb, int type, qid_t id,
void __user *addr)
{
struct fs_disk_quota fdq;
struct qc_dqblk qdq;
struct kqid qid;
qid_t id_out;
int ret;
if (!sb->s_qcop->get_nextdqblk)
return -ENOSYS;
qid = make_kqid(current_user_ns(), type, id);
if (!qid_has_mapping(sb->s_user_ns, qid))
return -EINVAL;
ret = sb->s_qcop->get_nextdqblk(sb, &qid, &qdq);
if (ret)
return ret;
id_out = from_kqid(current_user_ns(), qid);
copy_to_xfs_dqblk(&fdq, &qdq, type, id_out);
if (copy_to_user(addr, &fdq, sizeof(fdq)))
return -EFAULT;
return ret;
}
static int quota_rmxquota(struct super_block *sb, void __user *addr)
{
__u32 flags;
if (copy_from_user(&flags, addr, sizeof(flags)))
return -EFAULT;
if (!sb->s_qcop->rm_xquota)
return -ENOSYS;
return sb->s_qcop->rm_xquota(sb, flags);
}
/* Copy parameters and call proper function */
static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id,
void __user *addr, const struct path *path)
{
int ret;
fs/quota: Fix spectre gadget in do_quotactl 'type' is user-controlled, so sanitize it after the bounds check to avoid using it in speculative execution. This covers the following potential gadgets detected with the help of smatch: * fs/ext4/super.c:5741 ext4_quota_read() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/ext4/super.c:5778 ext4_quota_write() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/f2fs/super.c:1552 f2fs_quota_read() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/f2fs/super.c:1608 f2fs_quota_write() warn: potential spectre issue 'sb_dqopt(sb)->files' [r] * fs/quota/dquot.c:412 mark_info_dirty() warn: potential spectre issue 'sb_dqopt(sb)->info' [w] * fs/quota/dquot.c:933 dqinit_needed() warn: potential spectre issue 'dquots' [r] * fs/quota/dquot.c:2112 dquot_commit_info() warn: potential spectre issue 'dqopt->ops' [r] * fs/quota/dquot.c:2362 vfs_load_quota_inode() warn: potential spectre issue 'dqopt->files' [w] (local cap) * fs/quota/dquot.c:2369 vfs_load_quota_inode() warn: potential spectre issue 'dqopt->ops' [w] (local cap) * fs/quota/dquot.c:2370 vfs_load_quota_inode() warn: potential spectre issue 'dqopt->info' [w] (local cap) * fs/quota/quota.c:110 quota_getfmt() warn: potential spectre issue 'sb_dqopt(sb)->info' [r] * fs/quota/quota_v2.c:84 v2_check_quota_file() warn: potential spectre issue 'quota_magics' [w] * fs/quota/quota_v2.c:85 v2_check_quota_file() warn: potential spectre issue 'quota_versions' [w] * fs/quota/quota_v2.c:96 v2_read_file_info() warn: potential spectre issue 'dqopt->info' [r] * fs/quota/quota_v2.c:172 v2_write_file_info() warn: potential spectre issue 'dqopt->info' [r] Additionally, a quick inspection indicates there are array accesses with 'type' in quota_on() and quota_off() functions which are also addressed by this. Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: stable@vger.kernel.org Signed-off-by: Jeremy Cline <jcline@redhat.com> Signed-off-by: Jan Kara <jack@suse.cz>
2018-07-31 09:37:31 +08:00
type = array_index_nospec(type, MAXQUOTAS);
/*
* Quota not supported on this fs? Check this before s_quota_types
* since they needn't be set if quota is not supported at all.
*/
if (!sb->s_qcop)
return -ENOSYS;
if (!(sb->s_quota_types & (1 << type)))
return -EINVAL;
ret = check_quotactl_permission(sb, type, cmd, id);
if (ret < 0)
return ret;
switch (cmd) {
case Q_QUOTAON:
return quota_quotaon(sb, type, id, path);
case Q_QUOTAOFF:
return quota_quotaoff(sb, type);
case Q_GETFMT:
return quota_getfmt(sb, type, addr);
case Q_GETINFO:
return quota_getinfo(sb, type, addr);
case Q_SETINFO:
return quota_setinfo(sb, type, addr);
case Q_GETQUOTA:
return quota_getquota(sb, type, id, addr);
case Q_GETNEXTQUOTA:
return quota_getnextquota(sb, type, id, addr);
case Q_SETQUOTA:
return quota_setquota(sb, type, id, addr);
case Q_SYNC:
if (!sb->s_qcop->quota_sync)
return -ENOSYS;
return sb->s_qcop->quota_sync(sb, type);
case Q_XQUOTAON:
return quota_enable(sb, addr);
case Q_XQUOTAOFF:
return quota_disable(sb, addr);
case Q_XQUOTARM:
return quota_rmxquota(sb, addr);
case Q_XGETQSTAT:
return quota_getxstate(sb, type, addr);
case Q_XGETQSTATV:
return quota_getxstatev(sb, type, addr);
case Q_XSETQLIM:
return quota_setxquota(sb, type, id, addr);
case Q_XGETQUOTA:
return quota_getxquota(sb, type, id, addr);
case Q_XGETNEXTQUOTA:
return quota_getnextxquota(sb, type, id, addr);
case Q_XQUOTASYNC:
if (sb_rdonly(sb))
return -EROFS;
/* XFS quotas are fully coherent now, making this call a noop */
return 0;
default:
return -EINVAL;
}
}
/* Return 1 if 'cmd' will block on frozen filesystem */
static int quotactl_cmd_write(int cmd)
{
/*
* We cannot allow Q_GETQUOTA and Q_GETNEXTQUOTA without write access
* as dquot_acquire() may allocate space for new structure and OCFS2
* needs to increment on-disk use count.
*/
switch (cmd) {
case Q_GETFMT:
case Q_GETINFO:
case Q_SYNC:
case Q_XGETQSTAT:
case Q_XGETQSTATV:
case Q_XGETQUOTA:
case Q_XGETNEXTQUOTA:
case Q_XQUOTASYNC:
return 0;
}
return 1;
}
/* Return true if quotactl command is manipulating quota on/off state */
static bool quotactl_cmd_onoff(int cmd)
{
quota: Lock s_umount in exclusive mode for Q_XQUOTA{ON,OFF} quotactls. Commit 1fa5efe3622db58cb8c7b9a50665e9eb9a6c7e97 (ext4: Use generic helpers for quotaon and quotaoff) made possible to call quotactl(Q_XQUOTAON/OFF) on ext4 filesystems with sysfile quota support. This leads to calling dquot_enable/disable without s_umount held in excl. mode, because quotactl_cmd_onoff checks only for Q_QUOTAON/OFF. The following WARN_ON_ONCE triggers (in this case for dquot_enable, ext4, latest Linus' tree): [ 117.807056] EXT4-fs (dm-0): mounted filesystem with ordered data mode. Opts: quota,prjquota [...] [ 155.036847] WARNING: CPU: 0 PID: 2343 at fs/quota/dquot.c:2469 dquot_enable+0x34/0xb9 [ 155.036851] Modules linked in: quota_v2 quota_tree ipv6 af_packet joydev mousedev psmouse serio_raw pcspkr i2c_piix4 intel_agp intel_gtt e1000 ttm drm_kms_helper drm agpgart fb_sys_fops syscopyarea sysfillrect sysimgblt i2c_core input_leds kvm_intel kvm irqbypass qemu_fw_cfg floppy evdev parport_pc parport button crc32c_generic dm_mod ata_generic pata_acpi ata_piix libata loop ext4 crc16 mbcache jbd2 usb_storage usbcore sd_mod scsi_mod [ 155.036901] CPU: 0 PID: 2343 Comm: qctl Not tainted 4.20.0-rc6-00025-gf5d582777bcb #9 [ 155.036903] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 [ 155.036911] RIP: 0010:dquot_enable+0x34/0xb9 [ 155.036915] Code: 41 56 41 55 41 54 55 53 4c 8b 6f 28 74 02 0f 0b 4d 8d 7d 70 49 89 fc 89 cb 41 89 d6 89 f5 4c 89 ff e8 23 09 ea ff 85 c0 74 0a <0f> 0b 4c 89 ff e8 8b 09 ea ff 85 db 74 6a 41 8b b5 f8 00 00 00 0f [ 155.036918] RSP: 0018:ffffb09b00493e08 EFLAGS: 00010202 [ 155.036922] RAX: 0000000000000001 RBX: 0000000000000008 RCX: 0000000000000008 [ 155.036924] RDX: 0000000000000001 RSI: 0000000000000002 RDI: ffff9781b67cd870 [ 155.036926] RBP: 0000000000000002 R08: 0000000000000000 R09: 61c8864680b583eb [ 155.036929] R10: ffffb09b00493e48 R11: ffffffffff7ce7d4 R12: ffff9781b7ee8d78 [ 155.036932] R13: ffff9781b67cd800 R14: 0000000000000004 R15: ffff9781b67cd870 [ 155.036936] FS: 00007fd813250b88(0000) GS:ffff9781ba000000(0000) knlGS:0000000000000000 [ 155.036939] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 155.036942] CR2: 00007fd812ff61d6 CR3: 000000007c882000 CR4: 00000000000006b0 [ 155.036951] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 155.036953] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 155.036955] Call Trace: [ 155.037004] dquot_quota_enable+0x8b/0xd0 [ 155.037011] kernel_quotactl+0x628/0x74e [ 155.037027] ? do_mprotect_pkey+0x2a6/0x2cd [ 155.037034] __x64_sys_quotactl+0x1a/0x1d [ 155.037041] do_syscall_64+0x55/0xe4 [ 155.037078] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 155.037105] RIP: 0033:0x7fd812fe1198 [ 155.037109] Code: 02 77 0d 48 89 c1 48 c1 e9 3f 75 04 48 8b 04 24 48 83 c4 50 5b c3 48 83 ec 08 49 89 ca 48 63 d2 48 63 ff b8 b3 00 00 00 0f 05 <48> 89 c7 e8 c1 eb ff ff 5a c3 48 63 ff b8 bb 00 00 00 0f 05 48 89 [ 155.037112] RSP: 002b:00007ffe8cd7b050 EFLAGS: 00000206 ORIG_RAX: 00000000000000b3 [ 155.037116] RAX: ffffffffffffffda RBX: 00007ffe8cd7b148 RCX: 00007fd812fe1198 [ 155.037119] RDX: 0000000000000000 RSI: 00007ffe8cd7cea9 RDI: 0000000000580102 [ 155.037121] RBP: 00007ffe8cd7b0f0 R08: 000055fc8eba8a9d R09: 0000000000000000 [ 155.037124] R10: 00007ffe8cd7b074 R11: 0000000000000206 R12: 00007ffe8cd7b168 [ 155.037126] R13: 000055fc8eba8897 R14: 0000000000000000 R15: 0000000000000000 [ 155.037131] ---[ end trace 210f864257175c51 ]--- and then the syscall proceeds without s_umount locking. This patch locks the superblock ->s_umount sem. in exclusive mode for all Q_XQUOTAON/OFF quotactls too in addition to Q_QUOTAON/OFF. AFAICT, other than ext4, only xfs and ocfs2 are affected by this change. The VFS will now call in xfs_quota_* functions with s_umount held, which wasn't the case before. This looks good to me but I can not say for sure. Ext4 and ocfs2 where already beeing called with s_umount exclusive via quota_quotaon/off which is basically the same. Signed-off-by: Javier Barrio <javier.barrio.mart@gmail.com> Signed-off-by: Jan Kara <jack@suse.cz>
2018-12-13 08:06:29 +08:00
return (cmd == Q_QUOTAON) || (cmd == Q_QUOTAOFF) ||
(cmd == Q_XQUOTAON) || (cmd == Q_XQUOTAOFF);
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
/*
* look up a superblock on which quota ops will be performed
* - use the name of a block device to find the superblock thereon
*/
static struct super_block *quotactl_block(const char __user *special, int cmd)
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
{
#ifdef CONFIG_BLOCK
struct super_block *sb;
struct filename *tmp = getname(special);
bool excl = false, thawed = false;
int error;
dev_t dev;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
if (IS_ERR(tmp))
return ERR_CAST(tmp);
error = lookup_bdev(tmp->name, &dev);
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
putname(tmp);
if (error)
return ERR_PTR(error);
if (quotactl_cmd_onoff(cmd)) {
excl = true;
thawed = true;
} else if (quotactl_cmd_write(cmd)) {
thawed = true;
}
retry:
sb = user_get_super(dev, excl);
if (!sb)
return ERR_PTR(-ENODEV);
if (thawed && sb->s_writers.frozen != SB_UNFROZEN) {
if (excl)
up_write(&sb->s_umount);
else
up_read(&sb->s_umount);
wait_event(sb->s_writers.wait_unfrozen,
sb->s_writers.frozen == SB_UNFROZEN);
put_super(sb);
goto retry;
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
return sb;
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-10-01 02:45:40 +08:00
#else
return ERR_PTR(-ENODEV);
#endif
}
/*
* This is the system call interface. This communicates with
* the user-level programs. Currently this only supports diskquota
* calls. Maybe we need to add the process quotas etc. in the future,
* but we probably should use rlimits for that.
*/
SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
qid_t, id, void __user *, addr)
{
uint cmds, type;
struct super_block *sb = NULL;
struct path path, *pathp = NULL;
int ret;
cmds = cmd >> SUBCMDSHIFT;
type = cmd & SUBCMDMASK;
if (type >= MAXQUOTAS)
return -EINVAL;
/*
* As a special case Q_SYNC can be called without a specific device.
* It will iterate all superblocks that have quota enabled and call
* the sync action on each of them.
*/
if (!special) {
if (cmds == Q_SYNC)
return quota_sync_all(type);
return -ENODEV;
}
/*
* Path for quotaon has to be resolved before grabbing superblock
* because that gets s_umount sem which is also possibly needed by path
* resolution (think about autofs) and thus deadlocks could arise.
*/
if (cmds == Q_QUOTAON) {
ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
if (ret)
pathp = ERR_PTR(ret);
else
pathp = &path;
}
sb = quotactl_block(special, cmds);
if (IS_ERR(sb)) {
ret = PTR_ERR(sb);
goto out;
}
ret = do_quotactl(sb, type, cmds, id, addr, pathp);
if (!quotactl_cmd_onoff(cmds))
drop_super(sb);
else
drop_super_exclusive(sb);
out:
if (pathp && !IS_ERR(pathp))
path_put(pathp);
return ret;
}
SYSCALL_DEFINE4(quotactl_fd, unsigned int, fd, unsigned int, cmd,
qid_t, id, void __user *, addr)
{
struct super_block *sb;
unsigned int cmds = cmd >> SUBCMDSHIFT;
unsigned int type = cmd & SUBCMDMASK;
struct fd f;
int ret;
f = fdget_raw(fd);
if (!f.file)
return -EBADF;
ret = -EINVAL;
if (type >= MAXQUOTAS)
goto out;
if (quotactl_cmd_write(cmds)) {
ret = mnt_want_write(f.file->f_path.mnt);
if (ret)
goto out;
}
sb = f.file->f_path.mnt->mnt_sb;
if (quotactl_cmd_onoff(cmds))
down_write(&sb->s_umount);
else
down_read(&sb->s_umount);
ret = do_quotactl(sb, type, cmds, id, addr, ERR_PTR(-EINVAL));
if (quotactl_cmd_onoff(cmds))
up_write(&sb->s_umount);
else
up_read(&sb->s_umount);
if (quotactl_cmd_write(cmds))
mnt_drop_write(f.file->f_path.mnt);
out:
fdput(f);
return ret;
}