linux_dsm_epyc7002/fs/openpromfs/inode.c

472 lines
9.6 KiB
C
Raw Normal View History

/* inode.c: /proc/openprom handling routines
*
* Copyright (C) 1996-1999 Jakub Jelinek (jakub@redhat.com)
* Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be)
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/seq_file.h>
#include <linux/magic.h>
#include <asm/openprom.h>
#include <asm/oplib.h>
#include <asm/prom.h>
#include <linux/uaccess.h>
static DEFINE_MUTEX(op_mutex);
#define OPENPROM_ROOT_INO 0
enum op_inode_type {
op_inode_node,
op_inode_prop,
};
union op_inode_data {
struct device_node *node;
struct property *prop;
};
struct op_inode_info {
struct inode vfs_inode;
enum op_inode_type type;
union op_inode_data u;
};
static struct inode *openprom_iget(struct super_block *sb, ino_t ino);
static inline struct op_inode_info *OP_I(struct inode *inode)
{
return container_of(inode, struct op_inode_info, vfs_inode);
}
static int is_string(unsigned char *p, int len)
{
int i;
for (i = 0; i < len; i++) {
unsigned char val = p[i];
if ((i && !val) ||
(val >= ' ' && val <= '~'))
continue;
return 0;
}
return 1;
}
static int property_show(struct seq_file *f, void *v)
{
struct property *prop = f->private;
void *pval;
int len;
len = prop->length;
pval = prop->value;
if (is_string(pval, len)) {
while (len > 0) {
int n = strlen(pval);
seq_printf(f, "%s", (char *) pval);
/* Skip over the NULL byte too. */
pval += n + 1;
len -= n + 1;
if (len > 0)
seq_printf(f, " + ");
}
} else {
if (len & 3) {
while (len) {
len--;
if (len)
seq_printf(f, "%02x.",
*(unsigned char *) pval);
else
seq_printf(f, "%02x",
*(unsigned char *) pval);
pval++;
}
} else {
while (len >= 4) {
len -= 4;
if (len)
seq_printf(f, "%08x.",
*(unsigned int *) pval);
else
seq_printf(f, "%08x",
*(unsigned int *) pval);
pval += 4;
}
}
}
seq_printf(f, "\n");
return 0;
}
static void *property_start(struct seq_file *f, loff_t *pos)
{
if (*pos == 0)
return pos;
return NULL;
}
static void *property_next(struct seq_file *f, void *v, loff_t *pos)
{
(*pos)++;
return NULL;
}
static void property_stop(struct seq_file *f, void *v)
{
/* Nothing to do */
}
static const struct seq_operations property_op = {
.start = property_start,
.next = property_next,
.stop = property_stop,
.show = property_show
};
static int property_open(struct inode *inode, struct file *file)
{
struct op_inode_info *oi = OP_I(inode);
int ret;
BUG_ON(oi->type != op_inode_prop);
ret = seq_open(file, &property_op);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = oi->u.prop;
}
return ret;
}
static const struct file_operations openpromfs_prop_ops = {
.open = property_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static int openpromfs_readdir(struct file *, struct dir_context *);
static const struct file_operations openprom_operations = {
.read = generic_read_dir,
.iterate_shared = openpromfs_readdir,
.llseek = generic_file_llseek,
};
static struct dentry *openpromfs_lookup(struct inode *, struct dentry *, unsigned int);
static const struct inode_operations openprom_inode_operations = {
.lookup = openpromfs_lookup,
};
static struct dentry *openpromfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct op_inode_info *ent_oi, *oi = OP_I(dir);
struct device_node *dp, *child;
struct property *prop;
enum op_inode_type ent_type;
union op_inode_data ent_data;
const char *name;
struct inode *inode;
unsigned int ino;
int len;
BUG_ON(oi->type != op_inode_node);
dp = oi->u.node;
name = dentry->d_name.name;
len = dentry->d_name.len;
mutex_lock(&op_mutex);
child = dp->child;
while (child) {
const char *node_name = kbasename(child->full_name);
int n = strlen(node_name);
if (len == n &&
!strncmp(node_name, name, len)) {
ent_type = op_inode_node;
ent_data.node = child;
ino = child->unique_id;
goto found;
}
child = child->sibling;
}
prop = dp->properties;
while (prop) {
int n = strlen(prop->name);
if (len == n && !strncmp(prop->name, name, len)) {
ent_type = op_inode_prop;
ent_data.prop = prop;
ino = prop->unique_id;
goto found;
}
prop = prop->next;
}
mutex_unlock(&op_mutex);
return ERR_PTR(-ENOENT);
found:
inode = openprom_iget(dir->i_sb, ino);
mutex_unlock(&op_mutex);
if (IS_ERR(inode))
return ERR_CAST(inode);
ent_oi = OP_I(inode);
ent_oi->type = ent_type;
ent_oi->u = ent_data;
switch (ent_type) {
case op_inode_node:
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
inode->i_op = &openprom_inode_operations;
inode->i_fop = &openprom_operations;
set_nlink(inode, 2);
break;
case op_inode_prop:
if (of_node_name_eq(dp, "options") && (len == 17) &&
!strncmp (name, "security-password", 17))
inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR;
else
inode->i_mode = S_IFREG | S_IRUGO;
inode->i_fop = &openpromfs_prop_ops;
set_nlink(inode, 1);
inode->i_size = ent_oi->u.prop->length;
break;
}
return d_splice_alias(inode, dentry);
}
static int openpromfs_readdir(struct file *file, struct dir_context *ctx)
{
struct inode *inode = file_inode(file);
struct op_inode_info *oi = OP_I(inode);
struct device_node *dp = oi->u.node;
struct device_node *child;
struct property *prop;
int i;
mutex_lock(&op_mutex);
if (ctx->pos == 0) {
if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR))
goto out;
ctx->pos = 1;
}
if (ctx->pos == 1) {
if (!dir_emit(ctx, "..", 2,
(dp->parent == NULL ?
OPENPROM_ROOT_INO :
dp->parent->unique_id), DT_DIR))
goto out;
ctx->pos = 2;
}
i = ctx->pos - 2;
/* First, the children nodes as directories. */
child = dp->child;
while (i && child) {
child = child->sibling;
i--;
}
while (child) {
if (!dir_emit(ctx,
kbasename(child->full_name),
strlen(kbasename(child->full_name)),
child->unique_id, DT_DIR))
goto out;
ctx->pos++;
child = child->sibling;
}
/* Next, the properties as files. */
prop = dp->properties;
while (i && prop) {
prop = prop->next;
i--;
}
while (prop) {
if (!dir_emit(ctx, prop->name, strlen(prop->name),
prop->unique_id, DT_REG))
goto out;
ctx->pos++;
prop = prop->next;
}
out:
mutex_unlock(&op_mutex);
return 0;
}
static struct kmem_cache *op_inode_cachep;
static struct inode *openprom_alloc_inode(struct super_block *sb)
{
struct op_inode_info *oi;
oi = kmem_cache_alloc(op_inode_cachep, GFP_KERNEL);
if (!oi)
return NULL;
return &oi->vfs_inode;
}
2011-01-07 13:49:49 +07:00
static void openprom_i_callback(struct rcu_head *head)
{
2011-01-07 13:49:49 +07:00
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(op_inode_cachep, OP_I(inode));
}
2011-01-07 13:49:49 +07:00
static void openprom_destroy_inode(struct inode *inode)
{
call_rcu(&inode->i_rcu, openprom_i_callback);
}
static struct inode *openprom_iget(struct super_block *sb, ino_t ino)
{
struct inode *inode;
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
if (inode->i_state & I_NEW) {
inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
if (inode->i_ino == OPENPROM_ROOT_INO) {
inode->i_op = &openprom_inode_operations;
inode->i_fop = &openprom_operations;
inode->i_mode = S_IFDIR | S_IRUGO | S_IXUGO;
}
unlock_new_inode(inode);
}
return inode;
}
static int openprom_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 21:14:33 +07:00
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>
2017-11-28 04:05:09 +07:00
*flags |= SB_NOATIME;
return 0;
}
static const struct super_operations openprom_sops = {
.alloc_inode = openprom_alloc_inode,
.destroy_inode = openprom_destroy_inode,
.statfs = simple_statfs,
.remount_fs = openprom_remount,
};
static int openprom_fill_super(struct super_block *s, void *data, int silent)
{
struct inode *root_inode;
struct op_inode_info *oi;
int ret;
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>
2017-11-28 04:05:09 +07:00
s->s_flags |= SB_NOATIME;
s->s_blocksize = 1024;
s->s_blocksize_bits = 10;
s->s_magic = OPENPROM_SUPER_MAGIC;
s->s_op = &openprom_sops;
s->s_time_gran = 1;
root_inode = openprom_iget(s, OPENPROM_ROOT_INO);
if (IS_ERR(root_inode)) {
ret = PTR_ERR(root_inode);
goto out_no_root;
}
oi = OP_I(root_inode);
oi->type = op_inode_node;
oi->u.node = of_find_node_by_path("/");
s->s_root = d_make_root(root_inode);
if (!s->s_root)
goto out_no_root_dentry;
return 0;
out_no_root_dentry:
ret = -ENOMEM;
out_no_root:
printk("openprom_fill_super: get root inode failed\n");
return ret;
}
static struct dentry *openprom_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_single(fs_type, flags, data, openprom_fill_super);
}
static struct file_system_type openprom_fs_type = {
.owner = THIS_MODULE,
.name = "openpromfs",
.mount = openprom_mount,
.kill_sb = kill_anon_super,
};
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 10:39:14 +07:00
MODULE_ALIAS_FS("openpromfs");
static void op_inode_init_once(void *data)
{
struct op_inode_info *oi = (struct op_inode_info *) data;
inode_init_once(&oi->vfs_inode);
}
static int __init init_openprom_fs(void)
{
int err;
op_inode_cachep = kmem_cache_create("op_inode_cache",
sizeof(struct op_inode_info),
0,
(SLAB_RECLAIM_ACCOUNT |
2016-01-15 06:18:21 +07:00
SLAB_MEM_SPREAD | SLAB_ACCOUNT),
op_inode_init_once);
if (!op_inode_cachep)
return -ENOMEM;
err = register_filesystem(&openprom_fs_type);
if (err)
kmem_cache_destroy(op_inode_cachep);
return err;
}
static void __exit exit_openprom_fs(void)
{
unregister_filesystem(&openprom_fs_type);
/*
* Make sure all delayed rcu free inodes are flushed before we
* destroy cache.
*/
rcu_barrier();
kmem_cache_destroy(op_inode_cachep);
}
module_init(init_openprom_fs)
module_exit(exit_openprom_fs)
MODULE_LICENSE("GPL");