OpenCloudOS-Kernel/fs/ceph/acl.c

280 lines
6.4 KiB
C
Raw Normal View History

/*
* linux/fs/ceph/acl.c
*
* Copyright (C) 2013 Guangliang Zhao, <lucienchao@gmail.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/ceph/ceph_debug.h>
#include <linux/fs.h>
#include <linux/string.h>
#include <linux/xattr.h>
#include <linux/posix_acl_xattr.h>
#include <linux/posix_acl.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include "super.h"
static inline void ceph_set_cached_acl(struct inode *inode,
int type, struct posix_acl *acl)
{
struct ceph_inode_info *ci = ceph_inode(inode);
spin_lock(&ci->i_ceph_lock);
if (__ceph_caps_issued_mask(ci, CEPH_CAP_XATTR_SHARED, 0))
set_cached_acl(inode, type, acl);
posix_acl: Inode acl caching fixes When get_acl() is called for an inode whose ACL is not cached yet, the get_acl inode operation is called to fetch the ACL from the filesystem. The inode operation is responsible for updating the cached acl with set_cached_acl(). This is done without locking at the VFS level, so another task can call set_cached_acl() or forget_cached_acl() before the get_acl inode operation gets to calling set_cached_acl(), and then get_acl's call to set_cached_acl() results in caching an outdate ACL. Prevent this from happening by setting the cached ACL pointer to a task-specific sentinel value before calling the get_acl inode operation. Move the responsibility for updating the cached ACL from the get_acl inode operations to get_acl(). There, only set the cached ACL if the sentinel value hasn't changed. The sentinel values are chosen to have odd values. Likewise, the value of ACL_NOT_CACHED is odd. In contrast, ACL object pointers always have an even value (ACLs are aligned in memory). This allows to distinguish uncached ACLs values from ACL objects. In addition, switch from guarding inode->i_acl and inode->i_default_acl upates by the inode->i_lock spinlock to using xchg() and cmpxchg(). Filesystems that do not want ACLs returned from their get_acl inode operations to be cached must call forget_cached_acl() to prevent the VFS from doing so. (Patch written by Al Viro and Andreas Gruenbacher.) Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2016-03-24 21:38:37 +08:00
else
forget_cached_acl(inode, type);
spin_unlock(&ci->i_ceph_lock);
}
struct posix_acl *ceph_get_acl(struct inode *inode, int type)
{
int size;
unsigned int retry_cnt = 0;
const char *name;
char *value = NULL;
struct posix_acl *acl;
switch (type) {
case ACL_TYPE_ACCESS:
name = XATTR_NAME_POSIX_ACL_ACCESS;
break;
case ACL_TYPE_DEFAULT:
name = XATTR_NAME_POSIX_ACL_DEFAULT;
break;
default:
BUG();
}
retry:
size = __ceph_getxattr(inode, name, "", 0);
if (size > 0) {
value = kzalloc(size, GFP_NOFS);
if (!value)
return ERR_PTR(-ENOMEM);
size = __ceph_getxattr(inode, name, value, size);
}
if (size == -ERANGE && retry_cnt < 10) {
retry_cnt++;
kfree(value);
value = NULL;
goto retry;
}
if (size > 0) {
acl = posix_acl_from_xattr(&init_user_ns, value, size);
} else if (size == -ENODATA || size == 0) {
acl = NULL;
} else {
pr_err_ratelimited("get acl %llx.%llx failed, err=%d\n",
ceph_vinop(inode), size);
acl = ERR_PTR(-EIO);
}
kfree(value);
if (!IS_ERR(acl))
ceph_set_cached_acl(inode, type, acl);
return acl;
}
int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
int ret = 0, size = 0;
const char *name = NULL;
char *value = NULL;
struct iattr newattrs;
struct timespec64 old_ctime = inode->i_ctime;
umode_t new_mode = inode->i_mode, old_mode = inode->i_mode;
if (ceph_snap(inode) != CEPH_NOSNAP) {
ret = -EROFS;
goto out;
}
switch (type) {
case ACL_TYPE_ACCESS:
name = XATTR_NAME_POSIX_ACL_ACCESS;
if (acl) {
ret = posix_acl_update_mode(inode, &new_mode, &acl);
if (ret)
goto out;
}
break;
case ACL_TYPE_DEFAULT:
if (!S_ISDIR(inode->i_mode)) {
ret = acl ? -EINVAL : 0;
goto out;
}
name = XATTR_NAME_POSIX_ACL_DEFAULT;
break;
default:
ret = -EINVAL;
goto out;
}
if (acl) {
size = posix_acl_xattr_size(acl->a_count);
value = kmalloc(size, GFP_NOFS);
if (!value) {
ret = -ENOMEM;
goto out;
}
ret = posix_acl_to_xattr(&init_user_ns, acl, value, size);
if (ret < 0)
goto out_free;
}
if (new_mode != old_mode) {
newattrs.ia_ctime = current_time(inode);
newattrs.ia_mode = new_mode;
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
ret = __ceph_setattr(inode, &newattrs);
if (ret)
goto out_free;
}
ret = __ceph_setxattr(inode, name, value, size, 0);
if (ret) {
if (new_mode != old_mode) {
newattrs.ia_ctime = old_ctime;
newattrs.ia_mode = old_mode;
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
__ceph_setattr(inode, &newattrs);
}
goto out_free;
}
ceph_set_cached_acl(inode, type, acl);
out_free:
kfree(value);
out:
return ret;
}
int ceph_pre_init_acls(struct inode *dir, umode_t *mode,
struct ceph_acls_info *info)
{
struct posix_acl *acl, *default_acl;
size_t val_size1 = 0, val_size2 = 0;
struct ceph_pagelist *pagelist = NULL;
void *tmp_buf = NULL;
int err;
err = posix_acl_create(dir, mode, &default_acl, &acl);
if (err)
return err;
if (acl) {
err = posix_acl_equiv_mode(acl, mode);
if (err < 0)
goto out_err;
if (err == 0) {
posix_acl_release(acl);
acl = NULL;
}
}
if (!default_acl && !acl)
return 0;
if (acl)
val_size1 = posix_acl_xattr_size(acl->a_count);
if (default_acl)
val_size2 = posix_acl_xattr_size(default_acl->a_count);
err = -ENOMEM;
tmp_buf = kmalloc(max(val_size1, val_size2), GFP_KERNEL);
if (!tmp_buf)
goto out_err;
pagelist = kmalloc(sizeof(struct ceph_pagelist), GFP_KERNEL);
if (!pagelist)
goto out_err;
ceph_pagelist_init(pagelist);
err = ceph_pagelist_reserve(pagelist, PAGE_SIZE);
if (err)
goto out_err;
ceph_pagelist_encode_32(pagelist, acl && default_acl ? 2 : 1);
if (acl) {
size_t len = strlen(XATTR_NAME_POSIX_ACL_ACCESS);
err = ceph_pagelist_reserve(pagelist, len + val_size1 + 8);
if (err)
goto out_err;
ceph_pagelist_encode_string(pagelist, XATTR_NAME_POSIX_ACL_ACCESS,
len);
err = posix_acl_to_xattr(&init_user_ns, acl,
tmp_buf, val_size1);
if (err < 0)
goto out_err;
ceph_pagelist_encode_32(pagelist, val_size1);
ceph_pagelist_append(pagelist, tmp_buf, val_size1);
}
if (default_acl) {
size_t len = strlen(XATTR_NAME_POSIX_ACL_DEFAULT);
err = ceph_pagelist_reserve(pagelist, len + val_size2 + 8);
if (err)
goto out_err;
err = ceph_pagelist_encode_string(pagelist,
XATTR_NAME_POSIX_ACL_DEFAULT, len);
err = posix_acl_to_xattr(&init_user_ns, default_acl,
tmp_buf, val_size2);
if (err < 0)
goto out_err;
ceph_pagelist_encode_32(pagelist, val_size2);
ceph_pagelist_append(pagelist, tmp_buf, val_size2);
}
kfree(tmp_buf);
info->acl = acl;
info->default_acl = default_acl;
info->pagelist = pagelist;
return 0;
out_err:
posix_acl_release(acl);
posix_acl_release(default_acl);
kfree(tmp_buf);
if (pagelist)
ceph_pagelist_release(pagelist);
return err;
}
void ceph_init_inode_acls(struct inode* inode, struct ceph_acls_info *info)
{
if (!inode)
return;
ceph_set_cached_acl(inode, ACL_TYPE_ACCESS, info->acl);
ceph_set_cached_acl(inode, ACL_TYPE_DEFAULT, info->default_acl);
}
void ceph_release_acls_info(struct ceph_acls_info *info)
{
posix_acl_release(info->acl);
posix_acl_release(info->default_acl);
if (info->pagelist)
ceph_pagelist_release(info->pagelist);
}