linux-stable/fs/qnx4/inode.c

435 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* QNX4 file system, Linux implementation.
*
* Version : 0.2.1
*
* Using parts of the xiafs filesystem.
*
* History :
*
* 01-06-1998 by Richard Frowijn : first release.
* 20-06-1998 by Frank Denis : Linux 2.1.99+ support, boot signature, misc.
* 30-06-1998 by Frank Denis : first step to write inodes.
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/highuid.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/fs_context.h>
#include "qnx4.h"
#define QNX4_VERSION 4
#define QNX4_BMNAME ".bitmap"
static const struct super_operations qnx4_sops;
static struct inode *qnx4_alloc_inode(struct super_block *sb);
static void qnx4_free_inode(struct inode *inode);
static int qnx4_statfs(struct dentry *, struct kstatfs *);
static int qnx4_get_tree(struct fs_context *fc);
static const struct super_operations qnx4_sops =
{
.alloc_inode = qnx4_alloc_inode,
.free_inode = qnx4_free_inode,
.statfs = qnx4_statfs,
};
static int qnx4_reconfigure(struct fs_context *fc)
{
struct super_block *sb = fc->root->d_sb;
struct qnx4_sb_info *qs;
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);
qs = qnx4_sb(sb);
qs->Version = QNX4_VERSION;
fc->sb_flags |= SB_RDONLY;
return 0;
}
static const struct fs_context_operations qnx4_context_opts = {
.get_tree = qnx4_get_tree,
.reconfigure = qnx4_reconfigure,
};
static int qnx4_get_block( struct inode *inode, sector_t iblock, struct buffer_head *bh, int create )
{
unsigned long phys;
QNX4DEBUG((KERN_INFO "qnx4: qnx4_get_block inode=[%ld] iblock=[%ld]\n",inode->i_ino,iblock));
phys = qnx4_block_map( inode, iblock );
if ( phys ) {
// logical block is before EOF
map_bh(bh, inode->i_sb, phys);
}
return 0;
}
static inline u32 try_extent(qnx4_xtnt_t *extent, u32 *offset)
{
u32 size = le32_to_cpu(extent->xtnt_size);
if (*offset < size)
return le32_to_cpu(extent->xtnt_blk) + *offset - 1;
*offset -= size;
return 0;
}
unsigned long qnx4_block_map( struct inode *inode, long iblock )
{
int ix;
long i_xblk;
struct buffer_head *bh = NULL;
struct qnx4_xblk *xblk = NULL;
struct qnx4_inode_entry *qnx4_inode = qnx4_raw_inode(inode);
u16 nxtnt = le16_to_cpu(qnx4_inode->di_num_xtnts);
u32 offset = iblock;
u32 block = try_extent(&qnx4_inode->di_first_xtnt, &offset);
if (block) {
// iblock is in the first extent. This is easy.
} else {
// iblock is beyond first extent. We have to follow the extent chain.
i_xblk = le32_to_cpu(qnx4_inode->di_xblk);
ix = 0;
while ( --nxtnt > 0 ) {
if ( ix == 0 ) {
// read next xtnt block.
bh = sb_bread(inode->i_sb, i_xblk - 1);
if ( !bh ) {
QNX4DEBUG((KERN_ERR "qnx4: I/O error reading xtnt block [%ld])\n", i_xblk - 1));
return -EIO;
}
xblk = (struct qnx4_xblk*)bh->b_data;
if ( memcmp( xblk->xblk_signature, "IamXblk", 7 ) ) {
QNX4DEBUG((KERN_ERR "qnx4: block at %ld is not a valid xtnt\n", qnx4_inode->i_xblk));
return -EIO;
}
}
block = try_extent(&xblk->xblk_xtnts[ix], &offset);
if (block) {
// got it!
break;
}
if ( ++ix >= xblk->xblk_num_xtnts ) {
i_xblk = le32_to_cpu(xblk->xblk_next_xblk);
ix = 0;
brelse( bh );
bh = NULL;
}
}
if ( bh )
brelse( bh );
}
QNX4DEBUG((KERN_INFO "qnx4: mapping block %ld of inode %ld = %ld\n",iblock,inode->i_ino,block));
return block;
}
static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct super_block *sb = dentry->d_sb;
u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
buf->f_type = sb->s_magic;
buf->f_bsize = sb->s_blocksize;
buf->f_blocks = le32_to_cpu(qnx4_sb(sb)->BitMap->di_size) * 8;
buf->f_bfree = qnx4_count_free_blocks(sb);
buf->f_bavail = buf->f_bfree;
buf->f_namelen = QNX4_NAME_MAX;
buf->f_fsid = u64_to_fsid(id);
return 0;
}
/*
* Check the root directory of the filesystem to make sure
* it really _is_ a qnx4 filesystem, and to check the size
* of the directory entry.
*/
static const char *qnx4_checkroot(struct super_block *sb,
struct qnx4_super_block *s)
{
struct buffer_head *bh;
struct qnx4_inode_entry *rootdir;
int rd, rl;
int i, j;
if (s->RootDir.di_fname[0] != '/' || s->RootDir.di_fname[1] != '\0')
return "no qnx4 filesystem (no root dir).";
QNX4DEBUG((KERN_NOTICE "QNX4 filesystem found on dev %s.\n", sb->s_id));
rd = le32_to_cpu(s->RootDir.di_first_xtnt.xtnt_blk) - 1;
rl = le32_to_cpu(s->RootDir.di_first_xtnt.xtnt_size);
for (j = 0; j < rl; j++) {
bh = sb_bread(sb, rd + j); /* root dir, first block */
if (bh == NULL)
return "unable to read root entry.";
rootdir = (struct qnx4_inode_entry *) bh->b_data;
for (i = 0; i < QNX4_INODES_PER_BLOCK; i++, rootdir++) {
QNX4DEBUG((KERN_INFO "rootdir entry found : [%s]\n", rootdir->di_fname));
if (strcmp(rootdir->di_fname, QNX4_BMNAME) != 0)
continue;
qnx4_sb(sb)->BitMap = kmemdup(rootdir,
sizeof(struct qnx4_inode_entry),
GFP_KERNEL);
brelse(bh);
if (!qnx4_sb(sb)->BitMap)
return "not enough memory for bitmap inode";
/* keep bitmap inode known */
return NULL;
}
brelse(bh);
}
return "bitmap file not found.";
}
static int qnx4_fill_super(struct super_block *s, struct fs_context *fc)
{
struct buffer_head *bh;
struct inode *root;
const char *errmsg;
struct qnx4_sb_info *qs;
int silent = fc->sb_flags & SB_SILENT;
qs = kzalloc(sizeof(struct qnx4_sb_info), GFP_KERNEL);
if (!qs)
return -ENOMEM;
s->s_fs_info = qs;
sb_set_blocksize(s, QNX4_BLOCK_SIZE);
s->s_op = &qnx4_sops;
s->s_magic = QNX4_SUPER_MAGIC;
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
s->s_flags |= SB_RDONLY; /* Yup, read-only yet */
s->s_time_min = 0;
s->s_time_max = U32_MAX;
/* Check the superblock signature. Since the qnx4 code is
dangerous, we should leave as quickly as possible
if we don't belong here... */
bh = sb_bread(s, 1);
if (!bh) {
printk(KERN_ERR "qnx4: unable to read the superblock\n");
return -EINVAL;
}
/* check before allocating dentries, inodes, .. */
errmsg = qnx4_checkroot(s, (struct qnx4_super_block *) bh->b_data);
brelse(bh);
if (errmsg != NULL) {
if (!silent)
printk(KERN_ERR "qnx4: %s\n", errmsg);
return -EINVAL;
}
/* does root not have inode number QNX4_ROOT_INO ?? */
root = qnx4_iget(s, QNX4_ROOT_INO * QNX4_INODES_PER_BLOCK);
if (IS_ERR(root)) {
printk(KERN_ERR "qnx4: get inode failed\n");
return PTR_ERR(root);
}
s->s_root = d_make_root(root);
if (s->s_root == NULL)
return -ENOMEM;
return 0;
}
static int qnx4_get_tree(struct fs_context *fc)
{
return get_tree_bdev(fc, qnx4_fill_super);
}
static int qnx4_init_fs_context(struct fs_context *fc)
{
fc->ops = &qnx4_context_opts;
return 0;
}
static void qnx4_kill_sb(struct super_block *sb)
{
struct qnx4_sb_info *qs = qnx4_sb(sb);
kill_block_super(sb);
if (qs) {
kfree(qs->BitMap);
kfree(qs);
}
}
static int qnx4_read_folio(struct file *file, struct folio *folio)
{
return block_read_full_folio(folio, qnx4_get_block);
}
static sector_t qnx4_bmap(struct address_space *mapping, sector_t block)
{
return generic_block_bmap(mapping,block,qnx4_get_block);
}
static const struct address_space_operations qnx4_aops = {
.read_folio = qnx4_read_folio,
.bmap = qnx4_bmap
};
struct inode *qnx4_iget(struct super_block *sb, unsigned long ino)
{
struct buffer_head *bh;
struct qnx4_inode_entry *raw_inode;
int block;
struct qnx4_inode_entry *qnx4_inode;
struct inode *inode;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (!(inode->i_state & I_NEW))
return inode;
qnx4_inode = qnx4_raw_inode(inode);
inode->i_mode = 0;
QNX4DEBUG((KERN_INFO "reading inode : [%d]\n", ino));
if (!ino) {
printk(KERN_ERR "qnx4: bad inode number on dev %s: %lu is "
"out of range\n",
sb->s_id, ino);
iget_failed(inode);
return ERR_PTR(-EIO);
}
block = ino / QNX4_INODES_PER_BLOCK;
if (!(bh = sb_bread(sb, block))) {
printk(KERN_ERR "qnx4: major problem: unable to read inode from dev "
"%s\n", sb->s_id);
iget_failed(inode);
return ERR_PTR(-EIO);
}
raw_inode = ((struct qnx4_inode_entry *) bh->b_data) +
(ino % QNX4_INODES_PER_BLOCK);
inode->i_mode = le16_to_cpu(raw_inode->di_mode);
i_uid_write(inode, (uid_t)le16_to_cpu(raw_inode->di_uid));
i_gid_write(inode, (gid_t)le16_to_cpu(raw_inode->di_gid));
set_nlink(inode, le16_to_cpu(raw_inode->di_nlink));
inode->i_size = le32_to_cpu(raw_inode->di_size);
inode_set_mtime(inode, le32_to_cpu(raw_inode->di_mtime), 0);
inode_set_atime(inode, le32_to_cpu(raw_inode->di_atime), 0);
inode_set_ctime(inode, le32_to_cpu(raw_inode->di_ctime), 0);
inode->i_blocks = le32_to_cpu(raw_inode->di_first_xtnt.xtnt_size);
memcpy(qnx4_inode, raw_inode, QNX4_DIR_ENTRY_SIZE);
if (S_ISREG(inode->i_mode)) {
inode->i_fop = &generic_ro_fops;
inode->i_mapping->a_ops = &qnx4_aops;
qnx4_i(inode)->mmu_private = inode->i_size;
} else if (S_ISDIR(inode->i_mode)) {
inode->i_op = &qnx4_dir_inode_operations;
inode->i_fop = &qnx4_dir_operations;
} else if (S_ISLNK(inode->i_mode)) {
inode->i_op = &page_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &qnx4_aops;
qnx4_i(inode)->mmu_private = inode->i_size;
} else {
printk(KERN_ERR "qnx4: bad inode %lu on dev %s\n",
ino, sb->s_id);
iget_failed(inode);
brelse(bh);
return ERR_PTR(-EIO);
}
brelse(bh);
unlock_new_inode(inode);
return inode;
}
static struct kmem_cache *qnx4_inode_cachep;
static struct inode *qnx4_alloc_inode(struct super_block *sb)
{
struct qnx4_inode_info *ei;
ei = alloc_inode_sb(sb, qnx4_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
}
static void qnx4_free_inode(struct inode *inode)
{
kmem_cache_free(qnx4_inode_cachep, qnx4_i(inode));
}
static void init_once(void *foo)
{
struct qnx4_inode_info *ei = (struct qnx4_inode_info *) foo;
inode_init_once(&ei->vfs_inode);
}
static int init_inodecache(void)
{
qnx4_inode_cachep = kmem_cache_create("qnx4_inode_cache",
sizeof(struct qnx4_inode_info),
0, (SLAB_RECLAIM_ACCOUNT|
SLAB_ACCOUNT),
init_once);
if (qnx4_inode_cachep == NULL)
return -ENOMEM;
return 0;
}
static void destroy_inodecache(void)
{
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(qnx4_inode_cachep);
}
static struct file_system_type qnx4_fs_type = {
.owner = THIS_MODULE,
.name = "qnx4",
.kill_sb = qnx4_kill_sb,
.fs_flags = FS_REQUIRES_DEV,
.init_fs_context = qnx4_init_fs_context,
};
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("qnx4");
static int __init init_qnx4_fs(void)
{
int err;
err = init_inodecache();
if (err)
return err;
err = register_filesystem(&qnx4_fs_type);
if (err) {
destroy_inodecache();
return err;
}
printk(KERN_INFO "QNX4 filesystem 0.2.3 registered.\n");
return 0;
}
static void __exit exit_qnx4_fs(void)
{
unregister_filesystem(&qnx4_fs_type);
destroy_inodecache();
}
module_init(init_qnx4_fs)
module_exit(exit_qnx4_fs)
MODULE_LICENSE("GPL");