blob: a4689eb2df285eb513d049fa0c5122f1edd4b198 [file] [log] [blame]
/*
* linux/fs/namei.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* Some corrections by tytso.
*/
/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
* lookup logic.
*/
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/ima.h>
#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
#include <linux/device_cgroup.h>
#include <linux/fs_struct.h>
#include <asm/uaccess.h>
#include "internal.h"
/* [Feb-1997 T. Schoebel-Theuer]
* Fundamental changes in the pathname lookup mechanisms (namei)
* were necessary because of omirr. The reason is that omirr needs
* to know the _real_ pathname, not the user-supplied one, in case
* of symlinks (and also when transname replacements occur).
*
* The new code replaces the old recursive symlink resolution with
* an iterative one (in case of non-nested symlink chains). It does
* this with calls to <fs>_follow_link().
* As a side effect, dir_namei(), _namei() and follow_link() are now
* replaced with a single function lookup_dentry() that can handle all
* the special cases of the former code.
*
* With the new dcache, the pathname is stored at each inode, at least as
* long as the refcount of the inode is positive. As a side effect, the
* size of the dcache depends on the inode cache and thus is dynamic.
*
* [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
* resolution to correspond with current state of the code.
*
* Note that the symlink resolution is not *completely* iterative.
* There is still a significant amount of tail- and mid- recursion in
* the algorithm. Also, note that <fs>_readlink() is not used in
* lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
* may return different results than <fs>_follow_link(). Many virtual
* filesystems (including /proc) exhibit this behavior.
*/
/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
* New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
* and the name already exists in form of a symlink, try to create the new
* name indicated by the symlink. The old code always complained that the
* name already exists, due to not following the symlink even if its target
* is nonexistent. The new semantics affects also mknod() and link() when
* the name is a symlink pointing to a non-existant name.
*
* I don't know which semantics is the right one, since I have no access
* to standards. But I found by trial that HP-UX 9.0 has the full "new"
* semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
* "old" one. Personally, I think the new semantics is much more logical.
* Note that "ln old new" where "new" is a symlink pointing to a non-existing
* file does succeed in both HP-UX and SunOs, but not in Solaris
* and in the old Linux semantics.
*/
/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
* semantics. See the comments in "open_namei" and "do_link" below.
*
* [10-Sep-98 Alan Modra] Another symlink change.
*/
/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
* inside the path - always follow.
* in the last component in creation/removal/renaming - never follow.
* if LOOKUP_FOLLOW passed - follow.
* if the pathname has trailing slashes - follow.
* otherwise - don't follow.
* (applied in that order).
*
* [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
* restored for 2.4. This is the last surviving part of old 4.2BSD bug.
* During the 2.4 we need to fix the userland stuff depending on it -
* hopefully we will be able to get rid of that wart in 2.5. So far only
* XEmacs seems to be relying on it...
*/
/*
* [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
* implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives
* any extra contention...
*/
/* In order to reduce some races, while at the same time doing additional
* checking and hopefully speeding things up, we copy filenames to the
* kernel data space before using them..
*
* POSIX.1 2.4: an empty pathname is invalid (ENOENT).
* PATH_MAX includes the nul terminator --RR.
*/
static int do_getname(const char __user *filename, char *page)
{
int retval;
unsigned long len = PATH_MAX;
if (!segment_eq(get_fs(), KERNEL_DS)) {
if ((unsigned long) filename >= TASK_SIZE)
return -EFAULT;
if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
len = TASK_SIZE - (unsigned long) filename;
}
retval = strncpy_from_user(page, filename, len);
if (retval > 0) {
if (retval < len)
return 0;
return -ENAMETOOLONG;
} else if (!retval)
retval = -ENOENT;
return retval;
}
char * getname(const char __user * filename)
{
char *tmp, *result;
result = ERR_PTR(-ENOMEM);
tmp = __getname();
if (tmp) {
int retval = do_getname(filename, tmp);
result = tmp;
if (retval < 0) {
__putname(tmp);
result = ERR_PTR(retval);
}
}
audit_getname(result);
return result;
}
#ifdef CONFIG_AUDITSYSCALL
void putname(const char *name)
{
if (unlikely(!audit_dummy_context()))
audit_putname(name);
else
__putname(name);
}
EXPORT_SYMBOL(putname);
#endif
/*
* This does basic POSIX ACL permission checking
*/
static int acl_permission_check(struct inode *inode, int mask, unsigned int flags,
int (*check_acl)(struct inode *inode, int mask, unsigned int flags))
{
umode_t mode = inode->i_mode;
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (current_fsuid() == inode->i_uid)
mode >>= 6;
else {
if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
int error = check_acl(inode, mask, flags);
if (error != -EAGAIN)
return error;
}
if (in_group_p(inode->i_gid))
mode >>= 3;
}
/*
* If the DACs are ok we don't need any capability check.
*/
if ((mask & ~mode) == 0)
return 0;
return -EACCES;
}
/**
* generic_permission - check for access rights on a Posix-like filesystem
* @inode: inode to check access rights for
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
* @check_acl: optional callback to check for Posix ACLs
* @flags: IPERM_FLAG_ flags.
*
* Used to check for read/write/execute permissions on a file.
* We use "fsuid" for this, letting us set arbitrary permissions
* for filesystem access without changing the "normal" uids which
* are used for other things.
*
* generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk
* request cannot be satisfied (eg. requires blocking or too much complexity).
* It would then be called again in ref-walk mode.
*/
int generic_permission(struct inode *inode, int mask, unsigned int flags,
int (*check_acl)(struct inode *inode, int mask, unsigned int flags))
{
int ret;
/*
* Do the basic POSIX ACL permission checks.
*/
ret = acl_permission_check(inode, mask, flags, check_acl);
if (ret != -EACCES)
return ret;
/*
* Read/write DACs are always overridable.
* Executable DACs are overridable if at least one exec bit is set.
*/
if (!(mask & MAY_EXEC) || execute_ok(inode))
if (capable(CAP_DAC_OVERRIDE))
return 0;
/*
* Searching includes executable on directories, else just read.
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
if (capable(CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
}
/**
* inode_permission - check for access rights to a given inode
* @inode: inode to check permission on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Used to check for read/write/execute permissions on an inode.
* We use "fsuid" for this, letting us set arbitrary permissions
* for filesystem access without changing the "normal" uids which
* are used for other things.
*/
int inode_permission(struct inode *inode, int mask)
{
int retval;
if (mask & MAY_WRITE) {
umode_t mode = inode->i_mode;
/*
* Nobody gets write access to a read-only fs.
*/
if (IS_RDONLY(inode) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
return -EROFS;
/*
* Nobody gets write access to an immutable file.
*/
if (IS_IMMUTABLE(inode))
return -EACCES;
}
if (inode->i_op->permission)
retval = inode->i_op->permission(inode, mask, 0);
else
retval = generic_permission(inode, mask, 0,
inode->i_op->check_acl);
if (retval)
return retval;
retval = devcgroup_inode_permission(inode, mask);
if (retval)
return retval;
return security_inode_permission(inode, mask);
}
/**
* file_permission - check for additional access rights to a given file
* @file: file to check access rights for
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Used to check for read/write/execute permissions on an already opened
* file.
*
* Note:
* Do not use this function in new code. All access checks should
* be done using inode_permission().
*/
int file_permission(struct file *file, int mask)
{
return inode_permission(file->f_path.dentry->d_inode, mask);
}
/*
* get_write_access() gets write permission for a file.
* put_write_access() releases this write permission.
* This is used for regular files.
* We cannot support write (and maybe mmap read-write shared) accesses and
* MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
* can have the following values:
* 0: no writers, no VM_DENYWRITE mappings
* < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
* > 0: (i_writecount) users are writing to the file.
*
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
* except for the cases where we don't hold i_writecount yet. Then we need to
* use {get,deny}_write_access() - these functions check the sign and refuse
* to do the change if sign is wrong. Exclusion between them is provided by
* the inode->i_lock spinlock.
*/
int get_write_access(struct inode * inode)
{
spin_lock(&inode->i_lock);
if (atomic_read(&inode->i_writecount) < 0) {
spin_unlock(&inode->i_lock);
return -ETXTBSY;
}
atomic_inc(&inode->i_writecount);
spin_unlock(&inode->i_lock);
return 0;
}
int deny_write_access(struct file * file)
{
struct inode *inode = file->f_path.dentry->d_inode;
spin_lock(&inode->i_lock);
if (atomic_read(&inode->i_writecount) > 0) {
spin_unlock(&inode->i_lock);
return -ETXTBSY;
}
atomic_dec(&inode->i_writecount);
spin_unlock(&inode->i_lock);
return 0;
}
/**
* path_get - get a reference to a path
* @path: path to get the reference to
*
* Given a path increment the reference count to the dentry and the vfsmount.
*/
void path_get(struct path *path)
{
mntget(path->mnt);
dget(path->dentry);
}
EXPORT_SYMBOL(path_get);
/**
* path_put - put a reference to a path
* @path: path to put the reference to
*
* Given a path decrement the reference count to the dentry and the vfsmount.
*/
void path_put(struct path *path)
{
dput(path->dentry);
mntput(path->mnt);
}
EXPORT_SYMBOL(path_put);
/**
* nameidata_drop_rcu - drop this nameidata out of rcu-walk
* @nd: nameidata pathwalk data to drop
* Returns: 0 on success, -ECHILD on failure
*
* Path walking has 2 modes, rcu-walk and ref-walk (see
* Documentation/filesystems/path-lookup.txt). __drop_rcu* functions attempt
* to drop out of rcu-walk mode and take normal reference counts on dentries
* and vfsmounts to transition to rcu-walk mode. __drop_rcu* functions take
* refcounts at the last known good point before rcu-walk got stuck, so
* ref-walk may continue from there. If this is not successful (eg. a seqcount
* has changed), then failure is returned and path walk restarts from the
* beginning in ref-walk mode.
*
* nameidata_drop_rcu attempts to drop the current nd->path and nd->root into
* ref-walk. Must be called from rcu-walk context.
*/
static int nameidata_drop_rcu(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
struct dentry *dentry = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
if (nd->root.mnt) {
spin_lock(&fs->lock);
if (nd->root.mnt != fs->root.mnt ||
nd->root.dentry != fs->root.dentry)
goto err_root;
}
spin_lock(&dentry->d_lock);
if (!__d_rcu_to_refcount(dentry, nd->seq))
goto err;
BUG_ON(nd->inode != dentry->d_inode);
spin_unlock(&dentry->d_lock);
if (nd->root.mnt) {
path_get(&nd->root);
spin_unlock(&fs->lock);
}
mntget(nd->path.mnt);
rcu_read_unlock();
br_read_unlock(vfsmount_lock);
nd->flags &= ~LOOKUP_RCU;
return 0;
err:
spin_unlock(&dentry->d_lock);
err_root:
if (nd->root.mnt)
spin_unlock(&fs->lock);
return -ECHILD;
}
/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */
static inline int nameidata_drop_rcu_maybe(struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU)
return nameidata_drop_rcu(nd);
return 0;
}
/**
* nameidata_dentry_drop_rcu - drop nameidata and dentry out of rcu-walk
* @nd: nameidata pathwalk data to drop
* @dentry: dentry to drop
* Returns: 0 on success, -ECHILD on failure
*
* nameidata_dentry_drop_rcu attempts to drop the current nd->path and nd->root,
* and dentry into ref-walk. @dentry must be a path found by a do_lookup call on
* @nd. Must be called from rcu-walk context.
*/
static int nameidata_dentry_drop_rcu(struct nameidata *nd, struct dentry *dentry)
{
struct fs_struct *fs = current->fs;
struct dentry *parent = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
if (nd->root.mnt) {
spin_lock(&fs->lock);
if (nd->root.mnt != fs->root.mnt ||
nd->root.dentry != fs->root.dentry)
goto err_root;
}
spin_lock(&parent->d_lock);
spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
if (!__d_rcu_to_refcount(dentry, nd->seq))
goto err;
/*
* If the sequence check on the child dentry passed, then the child has
* not been removed from its parent. This means the parent dentry must
* be valid and able to take a reference at this point.
*/
BUG_ON(!IS_ROOT(dentry) && dentry->d_parent != parent);
BUG_ON(!parent->d_count);
parent->d_count++;
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
if (nd->root.mnt) {
path_get(&nd->root);
spin_unlock(&fs->lock);
}
mntget(nd->path.mnt);
rcu_read_unlock();
br_read_unlock(vfsmount_lock);
nd->flags &= ~LOOKUP_RCU;
return 0;
err:
spin_unlock(&dentry->d_lock);
spin_unlock(&parent->d_lock);
err_root:
if (nd->root.mnt)
spin_unlock(&fs->lock);
return -ECHILD;
}
/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */
static inline int nameidata_dentry_drop_rcu_maybe(struct nameidata *nd, struct dentry *dentry)
{
if (nd->flags & LOOKUP_RCU)
return nameidata_dentry_drop_rcu(nd, dentry);
return 0;
}
/**
* nameidata_drop_rcu_last - drop nameidata ending path walk out of rcu-walk
* @nd: nameidata pathwalk data to drop
* Returns: 0 on success, -ECHILD on failure
*
* nameidata_drop_rcu_last attempts to drop the current nd->path into ref-walk.
* nd->path should be the final element of the lookup, so nd->root is discarded.
* Must be called from rcu-walk context.
*/
static int nameidata_drop_rcu_last(struct nameidata *nd)
{
struct dentry *dentry = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
nd->flags &= ~LOOKUP_RCU;
nd->root.mnt = NULL;
spin_lock(&dentry->d_lock);
if (!__d_rcu_to_refcount(dentry, nd->seq))
goto err_unlock;
BUG_ON(nd->inode != dentry->d_inode);
spin_unlock(&dentry->d_lock);
mntget(nd->path.mnt);
rcu_read_unlock();
br_read_unlock(vfsmount_lock);
return 0;
err_unlock:
spin_unlock(&dentry->d_lock);
rcu_read_unlock();
br_read_unlock(vfsmount_lock);
return -ECHILD;
}
/* Try to drop out of rcu-walk mode if we were in it, otherwise do nothing. */
static inline int nameidata_drop_rcu_last_maybe(struct nameidata *nd)
{
if (likely(nd->flags & LOOKUP_RCU))
return nameidata_drop_rcu_last(nd);
return 0;
}
/**
* release_open_intent - free up open intent resources
* @nd: pointer to nameidata
*/
void release_open_intent(struct nameidata *nd)
{
struct file *file = nd->intent.open.file;
if (file && !IS_ERR(file)) {
if (file->f_path.dentry == NULL)
put_filp(file);
else
fput(file);
}
}
static inline int d_revalidate(struct dentry *dentry, struct nameidata *nd)
{
return dentry->d_op->d_revalidate(dentry, nd);
}
static struct dentry *
do_revalidate(struct dentry *dentry, struct nameidata *nd)
{
int status = d_revalidate(dentry, nd);
if (unlikely(status <= 0)) {
/*
* The dentry failed validation.
* If d_revalidate returned 0 attempt to invalidate
* the dentry otherwise d_revalidate is asking us
* to return a fail status.
*/
if (status < 0) {
dput(dentry);
dentry = ERR_PTR(status);
} else if (!d_invalidate(dentry)) {
dput(dentry);
dentry = NULL;
}
}
return dentry;
}
static inline struct dentry *
do_revalidate_rcu(struct dentry *dentry, struct nameidata *nd)
{
int status = d_revalidate(dentry, nd);
if (likely(status > 0))
return dentry;
if (status == -ECHILD) {
if (nameidata_dentry_drop_rcu(nd, dentry))
return ERR_PTR(-ECHILD);
return do_revalidate(dentry, nd);
}
if (status < 0)
return ERR_PTR(status);
/* Don't d_invalidate in rcu-walk mode */
if (nameidata_dentry_drop_rcu(nd, dentry))
return ERR_PTR(-ECHILD);
if (!d_invalidate(dentry)) {
dput(dentry);
dentry = NULL;
}
return dentry;
}
static inline int need_reval_dot(struct dentry *dentry)
{
if (likely(!(dentry->d_flags & DCACHE_OP_REVALIDATE)))
return 0;
if (likely(!(dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)))
return 0;
return 1;
}
/*
* force_reval_path - force revalidation of a dentry
*
* In some situations the path walking code will trust dentries without
* revalidating them. This causes problems for filesystems that depend on
* d_revalidate to handle file opens (e.g. NFSv4). When FS_REVAL_DOT is set
* (which indicates that it's possible for the dentry to go stale), force
* a d_revalidate call before proceeding.
*
* Returns 0 if the revalidation was successful. If the revalidation fails,
* either return the error returned by d_revalidate or -ESTALE if the
* revalidation it just returned 0. If d_revalidate returns 0, we attempt to
* invalidate the dentry. It's up to the caller to handle putting references
* to the path if necessary.
*/
static int
force_reval_path(struct path *path, struct nameidata *nd)
{
int status;
struct dentry *dentry = path->dentry;
/*
* only check on filesystems where it's possible for the dentry to
* become stale.
*/
if (!need_reval_dot(dentry))
return 0;
status = d_revalidate(dentry, nd);
if (status > 0)
return 0;
if (!status) {
d_invalidate(dentry);
status = -ESTALE;
}
return status;
}
/*
* Short-cut version of permission(), for calling on directories
* during pathname resolution. Combines parts of permission()
* and generic_permission(), and tests ONLY for MAY_EXEC permission.
*
* If appropriate, check DAC only. If not appropriate, or
* short-cut DAC fails, then call ->permission() to do more
* complete permission check.
*/
static inline int exec_permission(struct inode *inode, unsigned int flags)
{
int ret;
if (inode->i_op->permission) {
ret = inode->i_op->permission(inode, MAY_EXEC, flags);
} else {
ret = acl_permission_check(inode, MAY_EXEC, flags,
inode->i_op->check_acl);
}
if (likely(!ret))
goto ok;
if (ret == -ECHILD)
return ret;
if (capable(CAP_DAC_OVERRIDE) || capable(CAP_DAC_READ_SEARCH))
goto ok;
return ret;
ok:
return security_inode_exec_permission(inode, flags);
}
static __always_inline void set_root(struct nameidata *nd)
{
if (!nd->root.mnt)
get_fs_root(current->fs, &nd->root);
}
static int link_path_walk(const char *, struct nameidata *);
static __always_inline void set_root_rcu(struct nameidata *nd)
{
if (!nd->root.mnt) {
struct fs_struct *fs = current->fs;
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
nd->root = fs->root;
} while (read_seqcount_retry(&fs->seq, seq));
}
}
static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
int ret;
if (IS_ERR(link))
goto fail;
if (*link == '/') {
set_root(nd);
path_put(&nd->path);
nd->path = nd->root;
path_get(&nd->root);
}
nd->inode = nd->path.dentry->d_inode;
ret = link_path_walk(link, nd);
return ret;
fail:
path_put(&nd->path);
return PTR_ERR(link);
}
static void path_put_conditional(struct path *path, struct nameidata *nd)
{
dput(path->dentry);
if (path->mnt != nd->path.mnt)
mntput(path->mnt);
}
static inline void path_to_nameidata(const struct path *path,
struct nameidata *nd)
{
if (!(nd->flags & LOOKUP_RCU)) {
dput(nd->path.dentry);
if (nd->path.mnt != path->mnt)
mntput(nd->path.mnt);
}
nd->path.mnt = path->mnt;
nd->path.dentry = path->dentry;
}
static __always_inline int
__do_follow_link(const struct path *link, struct nameidata *nd, void **p)
{
int error;
struct dentry *dentry = link->dentry;
BUG_ON(nd->flags & LOOKUP_RCU);
touch_atime(link->mnt, dentry);
nd_set_link(nd, NULL);
if (link->mnt == nd->path.mnt)
mntget(link->mnt);
nd->last_type = LAST_BIND;
*p = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(*p);
if (!IS_ERR(*p)) {
char *s = nd_get_link(nd);
error = 0;
if (s)
error = __vfs_follow_link(nd, s);
else if (nd->last_type == LAST_BIND) {
error = force_reval_path(&nd->path, nd);
if (error)
path_put(&nd->path);
}
}
return error;
}
/*
* This limits recursive symlink follows to 8, while
* limiting consecutive symlinks to 40.
*
* Without that kind of total limit, nasty chains of consecutive
* symlinks can cause almost arbitrarily long lookups.
*/
static inline int do_follow_link(struct inode *inode, struct path *path, struct nameidata *nd)
{
void *cookie;
int err = -ELOOP;
/* We drop rcu-walk here */
if (nameidata_dentry_drop_rcu_maybe(nd, path->dentry))
return -ECHILD;
BUG_ON(inode != path->dentry->d_inode);
if (current->link_count >= MAX_NESTED_LINKS)
goto loop;
if (current->total_link_count >= 40)
goto loop;
BUG_ON(nd->depth >= MAX_NESTED_LINKS);
cond_resched();
err = security_inode_follow_link(path->dentry, nd);
if (err)
goto loop;
current->link_count++;
current->total_link_count++;
nd->depth++;
err = __do_follow_link(path, nd, &cookie);
if (!IS_ERR(cookie) && path->dentry->d_inode->i_op->put_link)
path->dentry->d_inode->i_op->put_link(path->dentry, nd, cookie);
path_put(path);
current->link_count--;
nd->depth--;
return err;
loop:
path_put_conditional(path, nd);
path_put(&nd->path);
return err;
}
static int follow_up_rcu(struct path *path)
{
struct vfsmount *parent;
struct dentry *mountpoint;
parent = path->mnt->mnt_parent;
if (parent == path->mnt)
return 0;
mountpoint = path->mnt->mnt_mountpoint;
path->dentry = mountpoint;
path->mnt = parent;
return 1;
}
int follow_up(struct path *path)
{
struct vfsmount *parent;
struct dentry *mountpoint;
br_read_lock(vfsmount_lock);
parent = path->mnt->mnt_parent;
if (parent == path->mnt) {
br_read_unlock(vfsmount_lock);
return 0;
}
mntget(parent);
mountpoint = dget(path->mnt->mnt_mountpoint);
br_read_unlock(vfsmount_lock);
dput(path->dentry);
path->dentry = mountpoint;
mntput(path->mnt);
path->mnt = parent;
return 1;
}
/*
* Perform an automount
* - return -EISDIR to tell follow_managed() to stop and return the path we
* were called with.
*/
static int follow_automount(struct path *path, unsigned flags,
bool *need_mntput)
{
struct vfsmount *mnt;
int err;
if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
return -EREMOTE;
/* We don't want to mount if someone supplied AT_NO_AUTOMOUNT
* and this is the terminal part of the path.
*/
if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_CONTINUE))
return -EISDIR; /* we actually want to stop here */
/* We want to mount if someone is trying to open/create a file of any
* type under the mountpoint, wants to traverse through the mountpoint
* or wants to open the mounted directory.
*
* We don't want to mount if someone's just doing a stat and they've
* set AT_SYMLINK_NOFOLLOW - unless they're stat'ing a directory and
* appended a '/' to the name.
*/
if (!(flags & LOOKUP_FOLLOW) &&
!(flags & (LOOKUP_CONTINUE | LOOKUP_DIRECTORY |
LOOKUP_OPEN | LOOKUP_CREATE)))
return -EISDIR;
current->total_link_count++;
if (current->total_link_count >= 40)
return -ELOOP;
mnt = path->dentry->d_op->d_automount(path);
if (IS_ERR(mnt)) {
/*
* The filesystem is allowed to return -EISDIR here to indicate
* it doesn't want to automount. For instance, autofs would do
* this so that its userspace daemon can mount on this dentry.
*
* However, we can only permit this if it's a terminal point in
* the path being looked up; if it wasn't then the remainder of
* the path is inaccessible and we should say so.
*/
if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_CONTINUE))
return -EREMOTE;
return PTR_ERR(mnt);
}
if (!mnt) /* mount collision */
return 0;
err = finish_automount(mnt, path);
switch (err) {
case -EBUSY:
/* Someone else made a mount here whilst we were busy */
return 0;
case 0:
dput(path->dentry);
if (*need_mntput)
mntput(path->mnt);
path->mnt = mnt;
path->dentry = dget(mnt->mnt_root);
*need_mntput = true;
return 0;
default:
return err;
}
}
/*
* Handle a dentry that is managed in some way.
* - Flagged for transit management (autofs)
* - Flagged as mountpoint
* - Flagged as automount point
*
* This may only be called in refwalk mode.
*
* Serialization is taken care of in namespace.c
*/
static int follow_managed(struct path *path, unsigned flags)
{
unsigned managed;
bool need_mntput = false;
int ret;
/* Given that we're not holding a lock here, we retain the value in a
* local variable for each dentry as we look at it so that we don't see
* the components of that value change under us */
while (managed = ACCESS_ONCE(path->dentry->d_flags),
managed &= DCACHE_MANAGED_DENTRY,
unlikely(managed != 0)) {
/* Allow the filesystem to manage the transit without i_mutex
* being held. */
if (managed & DCACHE_MANAGE_TRANSIT) {
BUG_ON(!path->dentry->d_op);
BUG_ON(!path->dentry->d_op->d_manage);
ret = path->dentry->d_op->d_manage(path->dentry,
false, false);
if (ret < 0)
return ret == -EISDIR ? 0 : ret;
}
/* Transit to a mounted filesystem. */
if (managed & DCACHE_MOUNTED) {
struct vfsmount *mounted = lookup_mnt(path);
if (mounted) {
dput(path->dentry);
if (need_mntput)
mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
need_mntput = true;
continue;
}
/* Something is mounted on this dentry in another
* namespace and/or whatever was mounted there in this
* namespace got unmounted before we managed to get the
* vfsmount_lock */
}
/* Handle an automount point */
if (managed & DCACHE_NEED_AUTOMOUNT) {
ret = follow_automount(path, flags, &need_mntput);
if (ret < 0)
return ret == -EISDIR ? 0 : ret;
continue;
}
/* We didn't change the current path point */
break;
}
return 0;
}
int follow_down_one(struct path *path)
{
struct vfsmount *mounted;
mounted = lookup_mnt(path);
if (mounted) {
dput(path->dentry);
mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
return 1;
}
return 0;
}
/*
* Skip to top of mountpoint pile in rcuwalk mode. We abort the rcu-walk if we
* meet a managed dentry and we're not walking to "..". True is returned to
* continue, false to abort.
*/
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
struct inode **inode, bool reverse_transit)
{
while (d_mountpoint(path->dentry)) {
struct vfsmount *mounted;
if (unlikely(path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) &&
!reverse_transit &&
path->dentry->d_op->d_manage(path->dentry, false, true) < 0)
return false;
mounted = __lookup_mnt(path->mnt, path->dentry, 1);
if (!mounted)
break;
path->mnt = mounted;
path->dentry = mounted->mnt_root;
nd->seq = read_seqcount_begin(&path->dentry->d_seq);
*inode = path->dentry->d_inode;
}
if (unlikely(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT))
return reverse_transit;
return true;
}
static int follow_dotdot_rcu(struct nameidata *nd)
{
struct inode *inode = nd->inode;
set_root_rcu(nd);
while (1) {
if (nd->path.dentry == nd->root.dentry &&
nd->path.mnt == nd->root.mnt) {
break;
}
if (nd->path.dentry != nd->path.mnt->mnt_root) {
struct dentry *old = nd->path.dentry;
struct dentry *parent = old->d_parent;
unsigned seq;
seq = read_seqcount_begin(&parent->d_seq);
if (read_seqcount_retry(&old->d_seq, nd->seq))
return -ECHILD;
inode = parent->d_inode;
nd->path.dentry = parent;
nd->seq = seq;
break;
}
if (!follow_up_rcu(&nd->path))
break;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
inode = nd->path.dentry->d_inode;
}
__follow_mount_rcu(nd, &nd->path, &inode, true);
nd->inode = inode;
return 0;
}
/*
* Follow down to the covering mount currently visible to userspace. At each
* point, the filesystem owning that dentry may be queried as to whether the
* caller is permitted to proceed or not.
*
* Care must be taken as namespace_sem may be held (indicated by mounting_here
* being true).
*/
int follow_down(struct path *path, bool mounting_here)
{
unsigned managed;
int ret;
while (managed = ACCESS_ONCE(path->dentry->d_flags),
unlikely(managed & DCACHE_MANAGED_DENTRY)) {
/* Allow the filesystem to manage the transit without i_mutex
* being held.
*
* We indicate to the filesystem if someone is trying to mount
* something here. This gives autofs the chance to deny anyone
* other than its daemon the right to mount on its
* superstructure.
*
* The filesystem may sleep at this point.
*/
if (managed & DCACHE_MANAGE_TRANSIT) {
BUG_ON(!path->dentry->d_op);
BUG_ON(!path->dentry->d_op->d_manage);
ret = path->dentry->d_op->d_manage(
path->dentry, mounting_here, false);
if (ret < 0)
return ret == -EISDIR ? 0 : ret;
}
/* Transit to a mounted filesystem. */
if (managed & DCACHE_MOUNTED) {
struct vfsmount *mounted = lookup_mnt(path);
if (!mounted)
break;
dput(path->dentry);
mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
continue;
}
/* Don't handle automount points here */
break;
}
return 0;
}
/*
* Skip to top of mountpoint pile in refwalk mode for follow_dotdot()
*/
static void follow_mount(struct path *path)
{
while (d_mountpoint(path->dentry)) {
struct vfsmount *mounted = lookup_mnt(path);
if (!mounted)
break;
dput(path->dentry);
mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
}
}
static void follow_dotdot(struct nameidata *nd)
{
set_root(nd);
while(1) {
struct dentry *old = nd->path.dentry;
if (nd->path.dentry == nd->root.dentry &&
nd->path.mnt == nd->root.mnt) {
break;
}
if (nd->path.dentry != nd->path.mnt->mnt_root) {
/* rare case of legitimate dget_parent()... */
nd->path.dentry = dget_parent(nd->path.dentry);
dput(old);
break;
}
if (!follow_up(&nd->path))
break;
}
follow_mount(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
/*
* Allocate a dentry with name and parent, and perform a parent
* directory ->lookup on it. Returns the new dentry, or ERR_PTR
* on error. parent->d_inode->i_mutex must be held. d_lookup must
* have verified that no child exists while under i_mutex.
*/
static struct dentry *d_alloc_and_lookup(struct dentry *parent,
struct qstr *name, struct nameidata *nd)
{
struct inode *inode = parent->d_inode;
struct dentry *dentry;
struct dentry *old;
/* Don't create child dentry for a dead directory. */
if (unlikely(IS_DEADDIR(inode)))
return ERR_PTR(-ENOENT);
dentry = d_alloc(parent, name);
if (unlikely(!dentry))
return ERR_PTR(-ENOMEM);
old = inode->i_op->lookup(inode, dentry, nd);
if (unlikely(old)) {
dput(dentry);
dentry = old;
}
return dentry;
}
/*
* It's more convoluted than I'd like it to be, but... it's still fairly
* small and for now I'd prefer to have fast path as straight as possible.
* It _is_ time-critical.
*/
static int do_lookup(struct nameidata *nd, struct qstr *name,
struct path *path, struct inode **inode)
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
struct inode *dir;
int err;
/*
* See if the low-level filesystem might want
* to use its own hash..
*/
if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
err = parent->d_op->d_hash(parent, nd->inode, name);
if (err < 0)
return err;
}
/*
* Rename seqlock is not required here because in the off chance
* of a false negative due to a concurrent rename, we're going to
* do the non-racy lookup, below.
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
*inode = nd->inode;
dentry = __d_lookup_rcu(parent, name, &seq, inode);
if (!dentry) {
if (nameidata_drop_rcu(nd))
return -ECHILD;
goto need_lookup;
}
/* Memory barrier in read_seqcount_begin of child is enough */
if (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
nd->seq = seq;
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
dentry = do_revalidate_rcu(dentry, nd);
if (!dentry)
goto need_lookup;
if (IS_ERR(dentry))
goto fail;
if (!(nd->flags & LOOKUP_RCU))
goto done;
}
path->mnt = mnt;
path->dentry = dentry;
if (likely(__follow_mount_rcu(nd, path, inode, false)))
return 0;
if (nameidata_drop_rcu(nd))
return -ECHILD;
/* fallthru */
}
dentry = __d_lookup(parent, name);
if (!dentry)
goto need_lookup;
found:
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
dentry = do_revalidate(dentry, nd);
if (!dentry)
goto need_lookup;
if (IS_ERR(dentry))
goto fail;
}
done:
path->mnt = mnt;
path->dentry = dentry;
err = follow_managed(path, nd->flags);
if (unlikely(err < 0)) {
path_put_conditional(path, nd);
return err;
}
*inode = path->dentry->d_inode;
return 0;
need_lookup:
dir = parent->d_inode;
BUG_ON(nd->inode != dir);
mutex_lock(&dir->i_mutex);
/*
* First re-do the cached lookup just in case it was created
* while we waited for the directory semaphore, or the first
* lookup failed due to an unrelated rename.
*
* This could use version numbering or similar to avoid unnecessary
* cache lookups, but then we'd have to do the first lookup in the
* non-racy way. However in the common case here, everything should
* be hot in cache, so would it be a big win?
*/
dentry = d_lookup(parent, name);
if (likely(!dentry)) {
dentry = d_alloc_and_lookup(parent, name, nd);
mutex_unlock(&dir->i_mutex);
if (IS_ERR(dentry))
goto fail;
goto done;
}
/*
* Uhhuh! Nasty case: the cache was re-populated while
* we waited on the semaphore. Need to revalidate.
*/
mutex_unlock(&dir->i_mutex);
goto found;
fail:
return PTR_ERR(dentry);
}
/*
* Name resolution.
* This is the basic name resolution function, turning a pathname into
* the final dentry. We expect 'base' to be positive and a directory.
*
* Returns 0 and nd will have valid dentry and mnt on success.
* Returns error and drops reference to input namei data on failure.
*/
static int link_path_walk(const char *name, struct nameidata *nd)
{
struct path next;
int err;
unsigned int lookup_flags = nd->flags;
while (*name=='/')
name++;
if (!*name)
goto return_reval;
if (nd->depth)
lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
/* At this point we know we have a real path component. */
for(;;) {
struct inode *inode;
unsigned long hash;
struct qstr this;
unsigned int c;
nd->flags |= LOOKUP_CONTINUE;
if (nd->flags & LOOKUP_RCU) {
err = exec_permission(nd->inode, IPERM_FLAG_RCU);
if (err == -ECHILD) {
if (nameidata_drop_rcu(nd))
return -ECHILD;
goto exec_again;
}
} else {
exec_again:
err = exec_permission(nd->inode, 0);
}
if (err)
break;
this.name = name;
c = *(const unsigned char *)name;
hash = init_name_hash();
do {
name++;
hash = partial_name_hash(c, hash);
c = *(const unsigned char *)name;
} while (c && (c != '/'));
this.len = name - (const char *) this.name;
this.hash = end_name_hash(hash);
/* remove trailing slashes? */
if (!c)
goto last_component;
while (*++name == '/');
if (!*name)
goto last_with_slashes;
/*
* "." and ".." are special - ".." especially so because it has
* to be able to know about the current root directory and
* parent relationships.
*/
if (this.name[0] == '.') switch (this.len) {
default:
break;
case 2:
if (this.name[1] != '.')
break;
if (nd->flags & LOOKUP_RCU) {
if (follow_dotdot_rcu(nd))
return -ECHILD;
} else
follow_dotdot(nd);
/* fallthrough */
case 1:
continue;
}
/* This does the actual lookups.. */
err = do_lookup(nd, &this, &next, &inode);
if (err)
break;
err = -ENOENT;
if (!inode)
goto out_dput;
if (inode->i_op->follow_link) {
err = do_follow_link(inode, &next, nd);
if (err)
goto return_err;
nd->inode = nd->path.dentry->d_inode;
err = -ENOENT;
if (!nd->inode)
break;
} else {
path_to_nameidata(&next, nd);
nd->inode = inode;
}
err = -ENOTDIR;
if (!nd->inode->i_op->lookup)
break;
continue;
/* here ends the main loop */
last_with_slashes:
lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
last_component:
/* Clear LOOKUP_CONTINUE iff it was previously unset */
nd->flags &= lookup_flags | ~LOOKUP_CONTINUE;
if (lookup_flags & LOOKUP_PARENT)
goto lookup_parent;
if (this.name[0] == '.') switch (this.len) {
default:
break;
case 2:
if (this.name[1] != '.')
break;
if (nd->flags & LOOKUP_RCU) {
if (follow_dotdot_rcu(nd))
return -ECHILD;
} else
follow_dotdot(nd);
/* fallthrough */
case 1:
goto return_reval;
}
err = do_lookup(nd, &this, &next, &inode);
if (err)
break;
if (inode && unlikely(inode->i_op->follow_link) &&
(lookup_flags & LOOKUP_FOLLOW)) {
err = do_follow_link(inode, &next, nd);
if (err)
goto return_err;
nd->inode = nd->path.dentry->d_inode;
} else {
path_to_nameidata(&next, nd);
nd->inode = inode;
}
err = -ENOENT;
if (!nd->inode)
break;
if (lookup_flags & LOOKUP_DIRECTORY) {
err = -ENOTDIR;
if (!nd->inode->i_op->lookup)
break;
}
goto return_base;
lookup_parent:
nd->last = this;
nd->last_type = LAST_NORM;
if (this.name[0] != '.')
goto return_base;
if (this.len == 1)
nd->last_type = LAST_DOT;
else if (this.len == 2 && this.name[1] == '.')
nd->last_type = LAST_DOTDOT;
else
goto return_base;
return_reval:
/*
* We bypassed the ordinary revalidation routines.
* We may need to check the cached dentry for staleness.
*/
if (need_reval_dot(nd->path.dentry)) {
if (nameidata_drop_rcu_last_maybe(nd))
return -ECHILD;
/* Note: we do not d_invalidate() */
err = d_revalidate(nd->path.dentry, nd);
if (!err)
err = -ESTALE;
if (err < 0)
break;
return 0;
}
return_base:
if (nameidata_drop_rcu_last_maybe(nd))
return -ECHILD;
return 0;
out_dput:
if (!(nd->flags & LOOKUP_RCU))
path_put_conditional(&next, nd);
break;
}
if (!(nd->flags & LOOKUP_RCU))
path_put(&nd->path);
return_err:
return err;
}
static inline int path_walk_rcu(const char *name, struct nameidata *nd)
{
current->total_link_count = 0;
return link_path_walk(name, nd);
}
static inline int path_walk_simple(const char *name, struct nameidata *nd)
{
current->total_link_count = 0;
return link_path_walk(name, nd);
}
static int path_walk(const char *name, struct nameidata *nd)
{
struct path save = nd->path;
int result;
current->total_link_count = 0;
/* make sure the stuff we saved doesn't go away */
path_get(&save);
result = link_path_walk(name, nd);
if (result == -ESTALE) {
/* nd->path had been dropped */
current->total_link_count = 0;
nd->path = save;
nd->inode = save.dentry->d_inode;
path_get(&nd->path);
nd->flags |= LOOKUP_REVAL;
result = link_path_walk(name, nd);
}
path_put(&save);
return result;
}
static void path_finish_rcu(struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
/* RCU dangling. Cancel it. */
nd->flags &= ~LOOKUP_RCU;
nd->root.mnt = NULL;
rcu_read_unlock();
br_read_unlock(vfsmount_lock);
}
if (nd->file)
fput(nd->file);
}
static int path_init_rcu(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
{
int retval = 0;
int fput_needed;
struct file *file;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_RCU;
nd->depth = 0;
nd->root.mnt = NULL;
nd->file = NULL;
if (*name=='/') {
struct fs_struct *fs = current->fs;
unsigned seq;
br_read_lock(vfsmount_lock);
rcu_read_lock();
do {
seq = read_seqcount_begin(&fs->seq);
nd->root = fs->root;
nd->path = nd->root;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
} else if (dfd == AT_FDCWD) {
struct fs_struct *fs = current->fs;
unsigned seq;
br_read_lock(vfsmount_lock);
rcu_read_lock();
do {
seq = read_seqcount_begin(&fs->seq);
nd->path = fs->pwd;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
} else {
struct dentry *dentry;
file = fget_light(dfd, &fput_needed);
retval = -EBADF;
if (!file)
goto out_fail;
dentry = file->f_path.dentry;
retval = -ENOTDIR;
if (!S_ISDIR(dentry->d_inode->i_mode))
goto fput_fail;
retval = file_permission(file, MAY_EXEC);
if (retval)
goto fput_fail;
nd->path = file->f_path;
if (fput_needed)
nd->file = file;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
br_read_lock(vfsmount_lock);
rcu_read_lock();
}
nd->inode = nd->path.dentry->d_inode;
return 0;
fput_fail:
fput_light(file, fput_needed);
out_fail:
return retval;
}
static int path_init(int dfd, const char *name, unsigned int flags, struct nameidata *nd)
{
int retval = 0;
int fput_needed;
struct file *file;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags;
nd->depth = 0;
nd->root.mnt = NULL;
if (*name=='/') {
set_root(nd);
nd->path = nd->root;
path_get(&nd->root);
} else if (dfd == AT_FDCWD) {
get_fs_pwd(current->fs, &nd->path);
} else {
struct dentry *dentry;
file = fget_light(dfd, &fput_needed);
retval = -EBADF;
if (!file)
goto out_fail;
dentry = file->f_path.dentry;
retval = -ENOTDIR;
if (!S_ISDIR(dentry->d_inode->i_mode))
goto fput_fail;
retval = file_permission(file, MAY_EXEC);
if (retval)
goto fput_fail;
nd->path = file->f_path;
path_get(&file->f_path);
fput_light(file, fput_needed);
}
nd->inode = nd->path.dentry->d_inode;
return 0;
fput_fail:
fput_light(file, fput_needed);
out_fail:
return retval;
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int do_path_lookup(int dfd, const char *name,
unsigned int flags, struct nameidata *nd)
{
int retval;
/*
* Path walking is largely split up into 2 different synchronisation
* schemes, rcu-walk and ref-walk (explained in
* Documentation/filesystems/path-lookup.txt). These share much of the
* path walk code, but some things particularly setup, cleanup, and
* following mounts are sufficiently divergent that functions are
* duplicated. Typically there is a function foo(), and its RCU
* analogue, foo_rcu().
*
* -ECHILD is the error number of choice (just to avoid clashes) that
* is returned if some aspect of an rcu-walk fails. Such an error must
* be handled by restarting a traditional ref-walk (which will always
* be able to complete).
*/
retval = path_init_rcu(dfd, name, flags, nd);
if (unlikely(retval))
return retval;
retval = path_walk_rcu(name, nd);
path_finish_rcu(nd);
if (nd->root.mnt) {
path_put(&nd->root);
nd->root.mnt = NULL;
}
if (unlikely(retval == -ECHILD || retval == -ESTALE)) {
/* slower, locked walk */
if (retval == -ESTALE)
flags |= LOOKUP_REVAL;
retval = path_init(dfd, name, flags, nd);
if (unlikely(retval))
return retval;
retval = path_walk(name, nd);
if (nd->root.mnt) {
path_put(&nd->root);
nd->root.mnt = NULL;
}
}
if (likely(!retval)) {
if (unlikely(!audit_dummy_context())) {
if (nd->path.dentry && nd->inode)
audit_inode(name, nd->path.dentry);
}
}
return retval;
}
int path_lookup(const char *name, unsigned int flags,
struct nameidata *nd)
{
return do_path_lookup(AT_FDCWD, name, flags, nd);
}
int kern_path(const char *name, unsigned int flags, struct path *path)
{
struct nameidata nd;
int res = do_path_lookup(AT_FDCWD, name, flags, &nd);
if (!res)
*path = nd.path;
return res;
}
/**
* vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
* @dentry: pointer to dentry of the base directory
* @mnt: pointer to vfs mount of the base directory
* @name: pointer to file name
* @flags: lookup flags
* @nd: pointer to nameidata
*/
int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
const char *name, unsigned int flags,
struct nameidata *nd)
{
int retval;
/* same as do_path_lookup */
nd->last_type = LAST_ROOT;
nd->flags = flags;
nd->depth = 0;
nd->path.dentry = dentry;
nd->path.mnt = mnt;
path_get(&nd->path);
nd->root = nd->path;
path_get(&nd->root);
nd->inode = nd->path.dentry->d_inode;
retval = path_walk(name, nd);
if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
nd->inode))
audit_inode(name, nd->path.dentry);
path_put(&nd->root);
nd->root.mnt = NULL;
return retval;
}
static struct dentry *__lookup_hash(struct qstr *name,
struct dentry *base, struct nameidata *nd)
{
struct inode *inode = base->d_inode;
struct dentry *dentry;
int err;
err = exec_permission(inode, 0);
if (err)
return ERR_PTR(err);
/*
* See if the low-level filesystem might want
* to use its own hash..
*/
if (base->d_flags & DCACHE_OP_HASH) {
err = base->d_op->d_hash(base, inode, name);
dentry = ERR_PTR(err);
if (err < 0)
goto out;
}
/*
* Don't bother with __d_lookup: callers are for creat as
* well as unlink, so a lot of the time it would cost
* a double lookup.
*/
dentry = d_lookup(base, name);
if (dentry && (dentry->d_flags & DCACHE_OP_REVALIDATE))
dentry = do_revalidate(dentry, nd);
if (!dentry)
dentry = d_alloc_and_lookup(base, name, nd);
out:
return dentry;
}
/*
* Restricted form of lookup. Doesn't follow links, single-component only,
* needs parent already locked. Doesn't follow mounts.
* SMP-safe.
*/
static struct dentry *lookup_hash(struct nameidata *nd)
{
return __lookup_hash(&nd->last, nd->path.dentry, nd);
}
static int __lookup_one_len(const char *name, struct qstr *this,
struct dentry *base, int len)
{
unsigned long hash;
unsigned int c;
this->name = name;
this->len = len;
if (!len)
return -EACCES;
hash = init_name_hash();
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
return -EACCES;
hash = partial_name_hash(c, hash);
}
this->hash = end_name_hash(hash);
return 0;
}
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code. Also note that by using this function the
* nameidata argument is passed to the filesystem methods and a filesystem
* using this helper needs to be prepared for that.
*/
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
int err;
struct qstr this;
WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
err = __lookup_one_len(name, &this, base, len);
if (err)
return ERR_PTR(err);
return __lookup_hash(&this, base, NULL);
}
int user_path_at(int dfd, const char __user *name, unsigned flags,
struct path *path)
{
struct nameidata nd;
char *tmp = getname(name);
int err = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
BUG_ON(flags & LOOKUP_PARENT);
err = do_path_lookup(dfd, tmp, flags, &nd);
putname(tmp);
if (!err)
*path = nd.path;
}
return err;
}
static int user_path_parent(int dfd, const char __user *path,
struct nameidata *nd, char **name)
{
char *s = getname(path);
int error;
if (IS_ERR(s))
return PTR_ERR(s);
error = do_path_lookup(dfd, s, LOOKUP_PARENT, nd);
if (error)
putname(s);
else
*name = s;
return error;
}
/*
* It's inline, so penalty for filesystems that don't use sticky bit is
* minimal.
*/
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
uid_t fsuid = current_fsuid();
if (!(dir->i_mode & S_ISVTX))
return 0;
if (inode->i_uid == fsuid)
return 0;
if (dir->i_uid == fsuid)
return 0;
return !capable(CAP_FOWNER);
}
/*
* Check whether we can remove a link victim from directory dir, check
* whether the type of victim is right.
* 1. We can't do it if dir is read-only (done in permission())
* 2. We should have write and exec permissions on dir
* 3. We can't remove anything from append-only dir
* 4. We can't do anything with immutable dir (done in permission())
* 5. If the sticky bit on dir is set we should either
* a. be owner of dir, or
* b. be owner of victim, or
* c. have CAP_FOWNER capability
* 6. If the victim is append-only or immutable we can't do antyhing with
* links pointing to it.
* 7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
* 8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
* 9. We can't remove a root or mountpoint.
* 10. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
{
int error;
if (!victim->d_inode)
return -ENOENT;
BUG_ON(victim->d_parent->d_inode != dir);
audit_inode_child(victim, dir);
error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
return -EPERM;
if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
IS_IMMUTABLE(victim->d_inode) || IS_SWAPFILE(victim->d_inode))
return -EPERM;
if (isdir) {
if (!S_ISDIR(victim->d_inode->i_mode))
return -ENOTDIR;
if (IS_ROOT(victim))
return -EBUSY;
} else if (S_ISDIR(victim->d_inode->i_mode))
return -EISDIR;
if (IS_DEADDIR(dir))
return -ENOENT;
if (victim->d_flags & DCACHE_NFSFS_RENAMED)
return -EBUSY;
return 0;
}
/* Check whether we can create an object with dentry child in directory
* dir.
* 1. We can't do it if child already exists (open has special treatment for
* this case, but since we are inlined it's OK)
* 2. We can't do it if dir is read-only (done in permission())
* 3. We should have write and exec permissions on dir
* 4. We can't do it if dir is immutable (done in permission())
*/
static inline int may_create(struct inode *dir, struct dentry *child)
{
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
return inode_permission(dir, MAY_WRITE | MAY_EXEC);
}
/*
* p1 and p2 should be directories on the same fs.
*/
struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
{
struct dentry *p;
if (p1 == p2) {
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
return NULL;
}
mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
p = d_ancestor(p2, p1);
if (p) {
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
return p;
}
p = d_ancestor(p1, p2);
if (p) {
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
return p;
}
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
return NULL;
}
void unlock_rename(struct dentry *p1, struct dentry *p2)
{
mutex_unlock(&p1->d_inode->i_mutex);
if (p1 != p2) {
mutex_unlock(&p2->d_inode->i_mutex);
mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
}
}
int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
struct nameidata *nd)
{
int error = may_create(dir, dentry);
if (error)
return error;
if (!dir->i_op->create)
return -EACCES; /* shouldn't it be ENOSYS? */
mode &= S_IALLUGO;
mode |= S_IFREG;
error = security_inode_create(dir, dentry, mode);
if (error)
return error;
error = dir->i_op->create(dir, dentry, mode, nd);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
int may_open(struct path *path, int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
struct inode *inode = dentry->d_inode;
int error;
if (!inode)
return -ENOENT;
switch (inode->i_mode & S_IFMT) {
case S_IFLNK:
return -ELOOP;
case S_IFDIR:
if (acc_mode & MAY_WRITE)
return -EISDIR;
break;
case S_IFBLK:
case S_IFCHR:
if (path->mnt->mnt_flags & MNT_NODEV)
return -EACCES;
/*FALLTHRU*/
case S_IFIFO:
case S_IFSOCK:
flag &= ~O_TRUNC;
break;
}
error = inode_permission(inode, acc_mode);
if (error)
return error;
/*
* An append-only file must be opened in append mode for writing.
*/
if (IS_APPEND(inode)) {
if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
return -EPERM;
if (flag & O_TRUNC)
return -EPERM;
}
/* O_NOATIME can only be set by the owner or superuser */
if (flag & O_NOATIME && !is_owner_or_cap(inode))
return -EPERM;
/*
* Ensure there are no outstanding leases on the file.
*/
return break_lease(inode, flag);
}
static int handle_truncate(struct file *filp)
{
struct path *path = &filp->f_path;
struct inode *inode = path->dentry->d_inode;
int error = get_write_access(inode);
if (error)
return error;
/*
* Refuse to truncate files with mandatory locks held on them.
*/
error = locks_verify_locked(inode);
if (!error)
error = security_path_truncate(path);
if (!error) {
error = do_truncate(path->dentry, 0,
ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
filp);
}
put_write_access(inode);
return error;
}
/*
* Be careful about ever adding any more callers of this
* function. Its flags must be in the namei format, not
* what get passed to sys_open().
*/
static int __open_namei_create(struct nameidata *nd, struct path *path,
int open_flag, int mode)
{
int error;
struct dentry *dir = nd->path.dentry;
if (!IS_POSIXACL(dir->d_inode))
mode &= ~current_umask();
error = security_path_mknod(&nd->path, path->dentry, mode, 0);
if (error)
goto out_unlock;
error = vfs_create(dir->d_inode, path->dentry, mode, nd);
out_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
dput(nd->path.dentry);
nd->path.dentry = path->dentry;
if (error)
return error;
/* Don't check for write permission, don't truncate */
return may_open(&nd->path, 0, open_flag & ~O_TRUNC);
}
/*
* Note that while the flag value (low two bits) for sys_open means:
* 00 - read-only
* 01 - write-only
* 10 - read-write
* 11 - special
* it is changed into
* 00 - no permissions needed
* 01 - read-permission
* 10 - write-permission
* 11 - read-write
* for the internal routines (ie open_namei()/follow_link() etc)
* This is more logical, and also allows the 00 "no perm needed"
* to be used for symlinks (where the permissions are checked
* later).
*
*/
static inline int open_to_namei_flags(int flag)
{
if ((flag+1) & O_ACCMODE)
flag++;
return flag;
}
static int open_will_truncate(int flag, struct inode *inode)
{
/*
* We'll never write to the fs underlying
* a device file.
*/
if (special_file(inode->i_mode))
return 0;
return (flag & O_TRUNC);
}
static struct file *finish_open(struct nameidata *nd,
int open_flag, int acc_mode)
{
struct file *filp;
int will_truncate;
int error;
will_truncate = open_will_truncate(open_flag, nd->path.dentry->d_inode);
if (will_truncate) {
error = mnt_want_write(nd->path.mnt);
if (error)
goto exit;
}
error = may_open(&nd->path, acc_mode, open_flag);
if (error) {
if (will_truncate)
mnt_drop_write(nd->path.mnt);
goto exit;
}
filp = nameidata_to_filp(nd);
if (!IS_ERR(filp)) {
error = ima_file_check(filp, acc_mode);
if (error) {
fput(filp);
filp = ERR_PTR(error);
}
}
if (!IS_ERR(filp)) {
if (will_truncate) {
error = handle_truncate(filp);
if (error) {
fput(filp);
filp = ERR_PTR(error);
}
}
}
/*
* It is now safe to drop the mnt write
* because the filp has had a write taken
* on its behalf.
*/
if (will_truncate)
mnt_drop_write(nd->path.mnt);
path_put(&nd->path);
return filp;
exit:
path_put(&nd->path);
return ERR_PTR(error);
}
/*
* Handle O_CREAT case for do_filp_open
*/
static struct file *do_last(struct nameidata *nd, struct path *path,
int open_flag, int acc_mode,
int mode, const char *pathname)
{
struct dentry *dir = nd->path.dentry;
struct file *filp;
int error = -EISDIR;
switch (nd->last_type) {
case LAST_DOTDOT:
follow_dotdot(nd);
dir = nd->path.dentry;
case LAST_DOT:
if (need_reval_dot(dir)) {
int status = d_revalidate(nd->path.dentry, nd);
if (!status)
status = -ESTALE;
if (status < 0) {
error = status;
goto exit;
}
}
/* fallthrough */
case LAST_ROOT:
goto exit;
case LAST_BIND:
audit_inode(pathname, dir);
goto ok;
}
/* trailing slashes? */
if (nd->last.name[nd->last.len])
goto exit;
mutex_lock(&dir->d_inode->i_mutex);
path->dentry = lookup_hash(nd);
path->mnt = nd->path.mnt;
error = PTR_ERR(path->dentry);
if (IS_ERR(path->dentry)) {
mutex_unlock(&dir->d_inode->i_mutex);
goto exit;
}
if (IS_ERR(nd->intent.open.file)) {
error = PTR_ERR(nd->intent.open.file);
goto exit_mutex_unlock;
}
/* Negative dentry, just create the file */
if (!path->dentry->d_inode) {
/*
* This write is needed to ensure that a
* ro->rw transition does not occur between
* the time when the file is created and when
* a permanent write count is taken through
* the 'struct file' in nameidata_to_filp().
*/
error = mnt_want_write(nd->path.mnt);
if (error)
goto exit_mutex_unlock;
error = __open_namei_create(nd, path, open_flag, mode);
if (error) {
mnt_drop_write(nd->path.mnt);
goto exit;
}
filp = nameidata_to_filp(nd);
mnt_drop_write(nd->path.mnt);
path_put(&nd->path);
if (!IS_ERR(filp)) {
error = ima_file_check(filp, acc_mode);
if (error) {
fput(filp);
filp = ERR_PTR(error);
}
}
return filp;
}
/*
* It already exists.
*/
mutex_unlock(&dir->d_inode->i_mutex);
audit_inode(pathname, path->dentry);
error = -EEXIST;
if (open_flag & O_EXCL)
goto exit_dput;
error = follow_managed(path, nd->flags);
if (error < 0)
goto exit_dput;
error = -ENOENT;
if (!path->dentry->d_inode)
goto exit_dput;
if (path->dentry->d_inode->i_op->follow_link)
return NULL;
path_to_nameidata(path, nd);
nd->inode = path->dentry->d_inode;
error = -EISDIR;
if (S_ISDIR(nd->inode->i_mode))
goto exit;
ok:
filp = finish_open(nd, open_flag, acc_mode);
return filp;
exit_mutex_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
path_put_conditional(path, nd);
exit:
path_put(&nd->path);
return ERR_PTR(error);
}
/*
* Note that the low bits of the passed in "open_flag"
* are not the same as in the local variable "flag". See
* open_to_namei_flags() for more details.
*/
struct file *do_filp_open(int dfd, const char *pathname,
int open_flag, int mode, int acc_mode)
{
struct file *filp;
struct nameidata nd;
int error;
struct path path;
int count = 0;
int flag = open_to_namei_flags(open_flag);
int flags;
if (!(open_flag & O_CREAT))
mode = 0;
/* Must never be set by userspace */
open_flag &= ~FMODE_NONOTIFY;
/*
* O_SYNC is implemented as __O_SYNC|O_DSYNC. As many places only
* check for O_DSYNC if the need any syncing at all we enforce it's
* always set instead of having to deal with possibly weird behaviour
* for malicious applications setting only __O_SYNC.
*/
if (open_flag & __O_SYNC)
open_flag |= O_DSYNC;
if (!acc_mode)
acc_mode = MAY_OPEN | ACC_MODE(open_flag);
/* O_TRUNC implies we need access checks for write permissions */
if (open_flag & O_TRUNC)
acc_mode |= MAY_WRITE;
/* Allow the LSM permission hook to distinguish append
access from general write access. */
if (open_flag & O_APPEND)
acc_mode |= MAY_APPEND;
flags = LOOKUP_OPEN;
if (open_flag & O_CREAT) {
flags |= LOOKUP_CREATE;
if (open_flag & O_EXCL)
flags |= LOOKUP_EXCL;
}
if (open_flag & O_DIRECTORY)
flags |= LOOKUP_DIRECTORY;
if (!(open_flag & O_NOFOLLOW))
flags |= LOOKUP_FOLLOW;
filp = get_empty_filp();
if (!filp)
return ERR_PTR(-ENFILE);
filp->f_flags = open_flag;
nd.intent.open.file = filp;
nd.intent.open.flags = flag;
nd.intent.open.create_mode = mode;
if (open_flag & O_CREAT)
goto creat;
/* !O_CREAT, simple open */
error = do_path_lookup(dfd, pathname, flags, &nd);
if (unlikely(error))
goto out_filp2;
error = -ELOOP;
if (!(nd.flags & LOOKUP_FOLLOW)) {
if (nd.inode->i_op->follow_link)
goto out_path2;
}
error = -ENOTDIR;
if (nd.flags & LOOKUP_DIRECTORY) {
if (!nd.inode->i_op->lookup)
goto out_path2;
}
audit_inode(pathname, nd.path.dentry);
filp = finish_open(&nd, open_flag, acc_mode);
out2:
release_open_intent(&nd);
return filp;
out_path2:
path_put(&nd.path);
out_filp2:
filp = ERR_PTR(error);
goto out2;
creat:
/* OK, have to create the file. Find the parent. */
error = path_init_rcu(dfd, pathname,
LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
if (error)
goto out_filp;
error = path_walk_rcu(pathname, &nd);
path_finish_rcu(&nd);
if (unlikely(error == -ECHILD || error == -ESTALE)) {
/* slower, locked walk */
if (error == -ESTALE) {
reval:
flags |= LOOKUP_REVAL;
}
error = path_init(dfd, pathname,
LOOKUP_PARENT | (flags & LOOKUP_REVAL), &nd);
if (error)
goto out_filp;
error = path_walk_simple(pathname, &nd);
}
if (unlikely(error))
goto out_filp;
if (unlikely(!audit_dummy_context()))
audit_inode(pathname, nd.path.dentry);
/*
* We have the parent and last component.
*/
nd.flags = flags;
filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
while (unlikely(!filp)) { /* trailing symlink */
struct path link = path;
struct inode *linki = link.dentry->d_inode;
void *cookie;
error = -ELOOP;
if (!(nd.flags & LOOKUP_FOLLOW))
goto exit_dput;
if (count++ == 32)
goto exit_dput;
/*
* This is subtle. Instead of calling do_follow_link() we do
* the thing by hands. The reason is that this way we have zero
* link_count and path_walk() (called from ->follow_link)
* honoring LOOKUP_PARENT. After that we have the parent and
* last component, i.e. we are in the same situation as after
* the first path_walk(). Well, almost - if the last component
* is normal we get its copy stored in nd->last.name and we will
* have to putname() it when we are done. Procfs-like symlinks
* just set LAST_BIND.
*/
nd.flags |= LOOKUP_PARENT;
error = security_inode_follow_link(link.dentry, &nd);
if (error)
goto exit_dput;
error = __do_follow_link(&link, &nd, &cookie);
if (unlikely(error)) {
if (!IS_ERR(cookie) && linki->i_op->put_link)
linki->i_op->put_link(link.dentry, &nd, cookie);
/* nd.path had been dropped */
nd.path = link;
goto out_path;
}
nd.flags &= ~LOOKUP_PARENT;
filp = do_last(&nd, &path, open_flag, acc_mode, mode, pathname);
if (linki->i_op->put_link)
linki->i_op->put_link(link.dentry, &nd, cookie);
path_put(&link);
}
out:
if (nd.root.mnt)
path_put(&nd.root);
if (filp == ERR_PTR(-ESTALE) && !(flags & LOOKUP_REVAL))
goto reval;
release_open_intent(&nd);
return filp;
exit_dput:
path_put_conditional(&path, &nd);
out_path:
path_put(&nd.path);
out_filp:
filp = ERR_PTR(error);
goto out;
}
/**
* filp_open - open file and return file pointer
*
* @filename: path to open
* @flags: open flags as per the open(2) second argument
* @mode: mode for the new file if O_CREAT is set, else ignored
*
* This is the helper to open a file from kernelspace if you really
* have to. But in generally you should not do this, so please move
* along, nothing to see here..
*/
struct file *filp_open(const char *filename, int flags, int mode)
{
return do_filp_open(AT_FDCWD, filename, flags, mode, 0);
}
EXPORT_SYMBOL(filp_open);
/**
* lookup_create - lookup a dentry, creating it if it doesn't exist
* @nd: nameidata info
* @is_dir: directory flag
*
* Simple function to lookup and return a dentry and create it
* if it doesn't exist. Is SMP-safe.
*
* Returns with nd->path.dentry->d_inode->i_mutex locked.
*/
struct dentry *lookup_create(struct nameidata *nd, int is_dir)
{
struct dentry *dentry = ERR_PTR(-EEXIST);
mutex_lock_nested(&nd->path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
/*
* Yucky last component or no last component at all?
* (foo/., foo/.., /////)
*/
if (nd->last_type != LAST_NORM)
goto fail;
nd->flags &= ~LOOKUP_PARENT;
nd->flags |= LOOKUP_CREATE | LOOKUP_EXCL;
nd->intent.open.flags = O_EXCL;
/*
* Do the final lookup.
*/
dentry = lookup_hash(nd);
if (IS_ERR(dentry))
goto fail;
if (dentry->d_inode)
goto eexist;
/*
* Special case - lookup gave negative, but... we had foo/bar/
* From the vfs_mknod() POV we just have a negative dentry -
* all is fine. Let's be bastards - you had / on the end, you've
* been asking for (non-existent) directory. -ENOENT for you.
*/
if (unlikely(!is_dir && nd->last.name[nd->last.len])) {
dput(dentry);
dentry = ERR_PTR(-ENOENT);
}
return dentry;
eexist:
dput(dentry);
dentry = ERR_PTR(-EEXIST);
fail:
return dentry;
}
EXPORT_SYMBOL_GPL(lookup_create);
int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
int error = may_create(dir, dentry);
if (error)
return error;
if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
return -EPERM;
if (!dir->i_op->mknod)
return -EPERM;
error = devcgroup_inode_mknod(mode, dev);
if (error)
return error;
error = security_inode_mknod(dir, dentry, mode, dev);
if (error)
return error;
error = dir->i_op->mknod(dir, dentry, mode, dev);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
static int may_mknod(mode_t mode)
{
switch (mode & S_IFMT) {
case S_IFREG:
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
case 0: /* zero mode translates to S_IFREG */
return 0;
case S_IFDIR:
return -EPERM;
default:
return -EINVAL;
}
}
SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, int, mode,
unsigned, dev)
{
int error;
char *tmp;
struct dentry *dentry;
struct nameidata nd;
if (S_ISDIR(mode))
return -EPERM;
error = user_path_parent(dfd, filename, &nd, &tmp);
if (error)
return error;
dentry = lookup_create(&nd, 0);
if (IS_ERR(dentry)) {
error = PTR_ERR(dentry);
goto out_unlock;
}
if (!IS_POSIXACL(nd.path.dentry->d_inode))
mode &= ~current_umask();
error = may_mknod(mode);
if (error)
goto out_dput;
error = mnt_want_write(nd.path.mnt);
if (error)
goto out_dput;
error = security_path_mknod(&nd.path, dentry, mode, dev);
if (error)
goto out_drop_write;
switch (mode & S_IFMT) {
case 0: case S_IFREG:
error = vfs_create(nd.path.dentry->d_inode,dentry,mode,&nd);
break;
case S_IFCHR: case S_IFBLK:
error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,
new_decode_dev(dev));
break;
case S_IFIFO: case S_IFSOCK:
error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,0);
break;
}
out_drop_write:
mnt_drop_write(nd.path.mnt);
out_dput:
dput(dentry);
out_unlock:
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
putname(tmp);
return error;
}
SYSCALL_DEFINE3(mknod, const char __user *, filename, int, mode, unsigned, dev)
{
return sys_mknodat(AT_FDCWD, filename, mode, dev);
}
int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
int error = may_create(dir, dentry);
if (error)
return error;
if (!dir->i_op->mkdir)
return -EPERM;
mode &= (S_IRWXUGO|S_ISVTX);
error = security_inode_mkdir(dir, dentry, mode);
if (error)
return error;
error = dir->i_op->mkdir(dir, dentry, mode);
if (!error)
fsnotify_mkdir(dir, dentry);
return error;
}
SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, int, mode)
{
int error = 0;
char * tmp;
struct dentry *dentry;
struct nameidata nd;
error = user_path_parent(dfd, pathname, &nd, &tmp);
if (error)
goto out_err;
dentry = lookup_create(&nd, 1);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto out_unlock;
if (!IS_POSIXACL(nd.path.dentry->d_inode))
mode &= ~current_umask();
error = mnt_want_write(nd.path.mnt);
if (error)
goto out_dput;
error = security_path_mkdir(&nd.path, dentry, mode);
if (error)
goto out_drop_write;
error = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
out_drop_write:
mnt_drop_write(nd.path.mnt);
out_dput:
dput(dentry);
out_unlock:
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
putname(tmp);
out_err:
return error;
}
SYSCALL_DEFINE2(mkdir, const char __user *, pathname, int, mode)
{
return sys_mkdirat(AT_FDCWD, pathname, mode);
}
/*
* We try to drop the dentry early: we should have
* a usage count of 2 if we're the only user of this
* dentry, and if that is true (possibly after pruning
* the dcache), then we drop the dentry now.
*