linux/fs/freevxfs/vxfs_super.c

335 lines
7.4 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2000-2001 Christoph Hellwig.
* Copyright (c) 2016 Krzysztof Blaszkowski
*/
/*
* Veritas filesystem driver - superblock related routines.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/stat.h>
#include <linux/vfs.h>
#include <linux/mount.h>
#include "vxfs.h"
#include "vxfs_extern.h"
#include "vxfs_dir.h"
#include "vxfs_inode.h"
MODULE_AUTHOR("Christoph Hellwig, Krzysztof Blaszkowski");
MODULE_DESCRIPTION("Veritas Filesystem (VxFS) driver");
MODULE_LICENSE("Dual BSD/GPL");
static struct kmem_cache *vxfs_inode_cachep;
/**
* vxfs_put_super - free superblock resources
* @sbp: VFS superblock.
*
* Description:
* vxfs_put_super frees all resources allocated for @sbp
* after the last instance of the filesystem is unmounted.
*/
static void
vxfs_put_super(struct super_block *sbp)
{
struct vxfs_sb_info *infp = VXFS_SBI(sbp);
iput(infp->vsi_fship);
iput(infp->vsi_ilist);
iput(infp->vsi_stilist);
brelse(infp->vsi_bp);
kfree(infp);
}
/**
* vxfs_statfs - get filesystem information
* @dentry: VFS dentry to locate superblock
* @bufp: output buffer
*
* Description:
* vxfs_statfs fills the statfs buffer @bufp with information
* about the filesystem described by @dentry.
*
* Returns:
* Zero.
*
* Locking:
* No locks held.
*
* Notes:
* This is everything but complete...
*/
static int
vxfs_statfs(struct dentry *dentry, struct kstatfs *bufp)
{
struct vxfs_sb_info *infp = VXFS_SBI(dentry->d_sb);
struct vxfs_sb *raw_sb = infp->vsi_raw;
bufp->f_type = VXFS_SUPER_MAGIC;
bufp->f_bsize = dentry->d_sb->s_blocksize;
bufp->f_blocks = fs32_to_cpu(infp, raw_sb->vs_dsize);
bufp->f_bfree = fs32_to_cpu(infp, raw_sb->vs_free);
bufp->f_bavail = 0;
bufp->f_files = 0;
bufp->f_ffree = fs32_to_cpu(infp, raw_sb->vs_ifree);
bufp->f_namelen = VXFS_NAMELEN;
return 0;
}
static int vxfs_remount(struct super_block *sb, int *flags, char *data)
{
fs: push sync_filesystem() down to the file system's remount_fs() Previously, the no-op "mount -o mount /dev/xxx" operation when the file system is already mounted read-write causes an implied, unconditional syncfs(). This seems pretty stupid, and it's certainly documented or guaraunteed to do this, nor is it particularly useful, except in the case where the file system was mounted rw and is getting remounted read-only. However, it's possible that there might be some file systems that are actually depending on this behavior. In most file systems, it's probably fine to only call sync_filesystem() when transitioning from read-write to read-only, and there are some file systems where this is not needed at all (for example, for a pseudo-filesystem or something like romfs). Signed-off-by: "Theodore Ts'o" <tytso@mit.edu> Cc: linux-fsdevel@vger.kernel.org Cc: Christoph Hellwig <hch@infradead.org> Cc: Artem Bityutskiy <dedekind1@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Evgeniy Dushistov <dushistov@mail.ru> Cc: Jan Kara <jack@suse.cz> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Anders Larsen <al@alarsen.net> Cc: Phillip Lougher <phillip@squashfs.org.uk> Cc: Kees Cook <keescook@chromium.org> Cc: Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz> Cc: Petr Vandrovec <petr@vandrovec.name> Cc: xfs@oss.sgi.com Cc: linux-btrfs@vger.kernel.org Cc: linux-cifs@vger.kernel.org Cc: samba-technical@lists.samba.org Cc: codalist@coda.cs.cmu.edu Cc: linux-ext4@vger.kernel.org Cc: linux-f2fs-devel@lists.sourceforge.net Cc: fuse-devel@lists.sourceforge.net Cc: cluster-devel@redhat.com Cc: linux-mtd@lists.infradead.org Cc: jfs-discussion@lists.sourceforge.net Cc: linux-nfs@vger.kernel.org Cc: linux-nilfs@vger.kernel.org Cc: linux-ntfs-dev@lists.sourceforge.net Cc: ocfs2-devel@oss.oracle.com Cc: reiserfs-devel@vger.kernel.org
2014-03-13 14:14:33 +00:00
sync_filesystem(sb);
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
*flags |= SB_RDONLY;
return 0;
}
static struct inode *vxfs_alloc_inode(struct super_block *sb)
{
struct vxfs_inode_info *vi;
vi = alloc_inode_sb(sb, vxfs_inode_cachep, GFP_KERNEL);
if (!vi)
return NULL;
inode_init_once(&vi->vfs_inode);
return &vi->vfs_inode;
}
static void vxfs_free_inode(struct inode *inode)
{
kmem_cache_free(vxfs_inode_cachep, VXFS_INO(inode));
}
static const struct super_operations vxfs_super_ops = {
.alloc_inode = vxfs_alloc_inode,
.free_inode = vxfs_free_inode,
.evict_inode = vxfs_evict_inode,
.put_super = vxfs_put_super,
.statfs = vxfs_statfs,
.remount_fs = vxfs_remount,
};
static int vxfs_try_sb_magic(struct super_block *sbp, int silent,
unsigned blk, __fs32 magic)
{
struct buffer_head *bp;
struct vxfs_sb *rsbp;
struct vxfs_sb_info *infp = VXFS_SBI(sbp);
int rc = -ENOMEM;
bp = sb_bread(sbp, blk);
do {
if (!bp || !buffer_mapped(bp)) {
if (!silent) {
printk(KERN_WARNING
"vxfs: unable to read disk superblock at %u\n",
blk);
}
break;
}
rc = -EINVAL;
rsbp = (struct vxfs_sb *)bp->b_data;
if (rsbp->vs_magic != magic) {
if (!silent)
printk(KERN_NOTICE
"vxfs: WRONG superblock magic %08x at %u\n",
rsbp->vs_magic, blk);
break;
}
rc = 0;
infp->vsi_raw = rsbp;
infp->vsi_bp = bp;
} while (0);
if (rc) {
infp->vsi_raw = NULL;
infp->vsi_bp = NULL;
brelse(bp);
}
return rc;
}
/**
* vxfs_read_super - read superblock into memory and initialize filesystem
* @sbp: VFS superblock (to fill)
* @dp: fs private mount data
* @silent: do not complain loudly when sth is wrong
*
* Description:
* We are called on the first mount of a filesystem to read the
* superblock into memory and do some basic setup.
*
* Returns:
* The superblock on success, else %NULL.
*
* Locking:
* We are under @sbp->s_lock.
*/
static int vxfs_fill_super(struct super_block *sbp, void *dp, int silent)
{
struct vxfs_sb_info *infp;
struct vxfs_sb *rsbp;
u_long bsize;
struct inode *root;
int ret = -EINVAL;
u32 j;
Rename superblock flags (MS_xyz -> SB_xyz) This is a pure automated search-and-replace of the internal kernel superblock flags. The s_flags are now called SB_*, with the names and the values for the moment mirroring the MS_* flags that they're equivalent to. Note how the MS_xyz flags are the ones passed to the mount system call, while the SB_xyz flags are what we then use in sb->s_flags. The script to do this was: # places to look in; re security/*: it generally should *not* be # touched (that stuff parses mount(2) arguments directly), but # there are two places where we really deal with superblock flags. FILES="drivers/mtd drivers/staging/lustre fs ipc mm \ include/linux/fs.h include/uapi/linux/bfs_fs.h \ security/apparmor/apparmorfs.c security/apparmor/include/lib.h" # the list of MS_... constants SYMS="RDONLY NOSUID NODEV NOEXEC SYNCHRONOUS REMOUNT MANDLOCK \ DIRSYNC NOATIME NODIRATIME BIND MOVE REC VERBOSE SILENT \ POSIXACL UNBINDABLE PRIVATE SLAVE SHARED RELATIME KERNMOUNT \ I_VERSION STRICTATIME LAZYTIME SUBMOUNT NOREMOTELOCK NOSEC BORN \ ACTIVE NOUSER" SED_PROG= for i in $SYMS; do SED_PROG="$SED_PROG -e s/MS_$i/SB_$i/g"; done # we want files that contain at least one of MS_..., # with fs/namespace.c and fs/pnode.c excluded. L=$(for i in $SYMS; do git grep -w -l MS_$i $FILES; done| sort|uniq|grep -v '^fs/namespace.c'|grep -v '^fs/pnode.c') for f in $L; do sed -i $f $SED_PROG; done Requested-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-27 21:05:09 +00:00
sbp->s_flags |= SB_RDONLY;
infp = kzalloc(sizeof(*infp), GFP_KERNEL);
if (!infp) {
printk(KERN_WARNING "vxfs: unable to allocate incore superblock\n");
return -ENOMEM;
}
bsize = sb_min_blocksize(sbp, BLOCK_SIZE);
if (!bsize) {
printk(KERN_WARNING "vxfs: unable to set blocksize\n");
goto out;
}
sbp->s_op = &vxfs_super_ops;
sbp->s_fs_info = infp;
sbp->s_time_min = 0;
sbp->s_time_max = U32_MAX;
if (!vxfs_try_sb_magic(sbp, silent, 1,
(__force __fs32)cpu_to_le32(VXFS_SUPER_MAGIC))) {
/* Unixware, x86 */
infp->byte_order = VXFS_BO_LE;
} else if (!vxfs_try_sb_magic(sbp, silent, 8,
(__force __fs32)cpu_to_be32(VXFS_SUPER_MAGIC))) {
/* HP-UX, parisc */
infp->byte_order = VXFS_BO_BE;
} else {
if (!silent)
printk(KERN_NOTICE "vxfs: can't find superblock.\n");
goto out;
}
rsbp = infp->vsi_raw;
j = fs32_to_cpu(infp, rsbp->vs_version);
if ((j < 2 || j > 4) && !silent) {
printk(KERN_NOTICE "vxfs: unsupported VxFS version (%d)\n", j);
goto out;
}
#ifdef DIAGNOSTIC
printk(KERN_DEBUG "vxfs: supported VxFS version (%d)\n", j);
printk(KERN_DEBUG "vxfs: blocksize: %d\n",
fs32_to_cpu(infp, rsbp->vs_bsize));
#endif
sbp->s_magic = fs32_to_cpu(infp, rsbp->vs_magic);
infp->vsi_oltext = fs32_to_cpu(infp, rsbp->vs_oltext[0]);
infp->vsi_oltsize = fs32_to_cpu(infp, rsbp->vs_oltsize);
j = fs32_to_cpu(infp, rsbp->vs_bsize);
if (!sb_set_blocksize(sbp, j)) {
printk(KERN_WARNING "vxfs: unable to set final block size\n");
goto out;
}
if (vxfs_read_olt(sbp, bsize)) {
printk(KERN_WARNING "vxfs: unable to read olt\n");
goto out;
}
if (vxfs_read_fshead(sbp)) {
printk(KERN_WARNING "vxfs: unable to read fshead\n");
goto out;
}
root = vxfs_iget(sbp, VXFS_ROOT_INO);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
sbp->s_root = d_make_root(root);
if (!sbp->s_root) {
printk(KERN_WARNING "vxfs: unable to get root dentry.\n");
goto out_free_ilist;
}
return 0;
out_free_ilist:
iput(infp->vsi_fship);
iput(infp->vsi_ilist);
iput(infp->vsi_stilist);
out:
brelse(infp->vsi_bp);
kfree(infp);
return ret;
}
/*
* The usual module blurb.
*/
static struct dentry *vxfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_bdev(fs_type, flags, dev_name, data, vxfs_fill_super);
}
static struct file_system_type vxfs_fs_type = {
.owner = THIS_MODULE,
.name = "vxfs",
.mount = vxfs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
};
fs: Limit sys_mount to only request filesystem modules. Modify the request_module to prefix the file system type with "fs-" and add aliases to all of the filesystems that can be built as modules to match. A common practice is to build all of the kernel code and leave code that is not commonly needed as modules, with the result that many users are exposed to any bug anywhere in the kernel. Looking for filesystems with a fs- prefix limits the pool of possible modules that can be loaded by mount to just filesystems trivially making things safer with no real cost. Using aliases means user space can control the policy of which filesystem modules are auto-loaded by editing /etc/modprobe.d/*.conf with blacklist and alias directives. Allowing simple, safe, well understood work-arounds to known problematic software. This also addresses a rare but unfortunate problem where the filesystem name is not the same as it's module name and module auto-loading would not work. While writing this patch I saw a handful of such cases. The most significant being autofs that lives in the module autofs4. This is relevant to user namespaces because we can reach the request module in get_fs_type() without having any special permissions, and people get uncomfortable when a user specified string (in this case the filesystem type) goes all of the way to request_module. After having looked at this issue I don't think there is any particular reason to perform any filtering or permission checks beyond making it clear in the module request that we want a filesystem module. The common pattern in the kernel is to call request_module() without regards to the users permissions. In general all a filesystem module does once loaded is call register_filesystem() and go to sleep. Which means there is not much attack surface exposed by loading a filesytem module unless the filesystem is mounted. In a user namespace filesystems are not mounted unless .fs_flags = FS_USERNS_MOUNT, which most filesystems do not set today. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Acked-by: Kees Cook <keescook@chromium.org> Reported-by: Kees Cook <keescook@google.com> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2013-03-03 03:39:14 +00:00
MODULE_ALIAS_FS("vxfs"); /* makes mount -t vxfs autoload the module */
MODULE_ALIAS("vxfs");
static int __init
vxfs_init(void)
{
int rv;
vxfs: Define usercopy region in vxfs_inode slab cache vxfs symlink pathnames, stored in struct vxfs_inode_info field vii_immed.vi_immed and therefore contained in the vxfs_inode slab cache, need to be copied to/from userspace. cache object allocation: fs/freevxfs/vxfs_super.c: vxfs_alloc_inode(...): ... vi = kmem_cache_alloc(vxfs_inode_cachep, GFP_KERNEL); ... return &vi->vfs_inode; fs/freevxfs/vxfs_inode.c: cxfs_iget(...): ... inode->i_link = vip->vii_immed.vi_immed; example usage trace: readlink_copy+0x43/0x70 vfs_readlink+0x62/0x110 SyS_readlinkat+0x100/0x130 fs/namei.c: readlink_copy(..., link): ... copy_to_user(..., link, len); (inlined in vfs_readlink) generic_readlink(dentry, ...): struct inode *inode = d_inode(dentry); const char *link = inode->i_link; ... readlink_copy(..., link); In support of usercopy hardening, this patch defines a region in the vxfs_inode slab cache in which userspace copy operations are allowed. This region is known as the slab cache's usercopy region. Slab caches can now check that each dynamically sized copy operation involving cache-managed memory falls entirely within the slab's usercopy region. This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY whitelisting code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Signed-off-by: David Windsor <dave@nullcore.net> [kees: adjust commit log, provide usage trace] Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Kees Cook <keescook@chromium.org>
2017-06-11 02:50:37 +00:00
vxfs_inode_cachep = kmem_cache_create_usercopy("vxfs_inode",
sizeof(struct vxfs_inode_info), 0,
vxfs: Define usercopy region in vxfs_inode slab cache vxfs symlink pathnames, stored in struct vxfs_inode_info field vii_immed.vi_immed and therefore contained in the vxfs_inode slab cache, need to be copied to/from userspace. cache object allocation: fs/freevxfs/vxfs_super.c: vxfs_alloc_inode(...): ... vi = kmem_cache_alloc(vxfs_inode_cachep, GFP_KERNEL); ... return &vi->vfs_inode; fs/freevxfs/vxfs_inode.c: cxfs_iget(...): ... inode->i_link = vip->vii_immed.vi_immed; example usage trace: readlink_copy+0x43/0x70 vfs_readlink+0x62/0x110 SyS_readlinkat+0x100/0x130 fs/namei.c: readlink_copy(..., link): ... copy_to_user(..., link, len); (inlined in vfs_readlink) generic_readlink(dentry, ...): struct inode *inode = d_inode(dentry); const char *link = inode->i_link; ... readlink_copy(..., link); In support of usercopy hardening, this patch defines a region in the vxfs_inode slab cache in which userspace copy operations are allowed. This region is known as the slab cache's usercopy region. Slab caches can now check that each dynamically sized copy operation involving cache-managed memory falls entirely within the slab's usercopy region. This patch is modified from Brad Spengler/PaX Team's PAX_USERCOPY whitelisting code in the last public patch of grsecurity/PaX based on my understanding of the code. Changes or omissions from the original code are mine and don't reflect the original grsecurity/PaX code. Signed-off-by: David Windsor <dave@nullcore.net> [kees: adjust commit log, provide usage trace] Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Kees Cook <keescook@chromium.org>
2017-06-11 02:50:37 +00:00
SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
offsetof(struct vxfs_inode_info, vii_immed.vi_immed),
sizeof_field(struct vxfs_inode_info,
vii_immed.vi_immed),
NULL);
if (!vxfs_inode_cachep)
return -ENOMEM;
rv = register_filesystem(&vxfs_fs_type);
if (rv < 0)
kmem_cache_destroy(vxfs_inode_cachep);
return rv;
}
static void __exit
vxfs_cleanup(void)
{
unregister_filesystem(&vxfs_fs_type);
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(vxfs_inode_cachep);
}
module_init(vxfs_init);
module_exit(vxfs_cleanup);