blob: 9155ecb547ce62464dd8b304e63ed73b7cf2b73e [file] [log] [blame] [edit]
// SPDX-License-Identifier: GPL-2.0
/*
* 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/export.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/pagemap.h>
#include <linux/sched/mm.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 <linux/posix_acl.h>
#include <linux/hash.h>
#include <linux/bitops.h>
#include <linux/init_task.h>
#include <linux/uaccess.h>
#include "internal.h"
#include "mount.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-existent 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.
*/
#define EMBEDDED_NAME_MAX (PATH_MAX - offsetof(struct filename, iname))
struct filename *
getname_flags(const char __user *filename, int flags, int *empty)
{
struct filename *result;
char *kname;
int len;
result = audit_reusename(filename);
if (result)
return result;
result = __getname();
if (unlikely(!result))
return ERR_PTR(-ENOMEM);
/*
* First, try to embed the struct filename inside the names_cache
* allocation
*/
kname = (char *)result->iname;
result->name = kname;
len = strncpy_from_user(kname, filename, EMBEDDED_NAME_MAX);
if (unlikely(len < 0)) {
__putname(result);
return ERR_PTR(len);
}
/*
* Uh-oh. We have a name that's approaching PATH_MAX. Allocate a
* separate struct filename so we can dedicate the entire
* names_cache allocation for the pathname, and re-do the copy from
* userland.
*/
if (unlikely(len == EMBEDDED_NAME_MAX)) {
const size_t size = offsetof(struct filename, iname[1]);
kname = (char *)result;
/*
* size is chosen that way we to guarantee that
* result->iname[0] is within the same object and that
* kname can't be equal to result->iname, no matter what.
*/
result = kzalloc(size, GFP_KERNEL);
if (unlikely(!result)) {
__putname(kname);
return ERR_PTR(-ENOMEM);
}
result->name = kname;
len = strncpy_from_user(kname, filename, PATH_MAX);
if (unlikely(len < 0)) {
__putname(kname);
kfree(result);
return ERR_PTR(len);
}
if (unlikely(len == PATH_MAX)) {
__putname(kname);
kfree(result);
return ERR_PTR(-ENAMETOOLONG);
}
}
result->refcnt = 1;
/* The empty path is special. */
if (unlikely(!len)) {
if (empty)
*empty = 1;
if (!(flags & LOOKUP_EMPTY)) {
putname(result);
return ERR_PTR(-ENOENT);
}
}
result->uptr = filename;
result->aname = NULL;
audit_getname(result);
return result;
}
struct filename *
getname_uflags(const char __user *filename, int uflags)
{
int flags = (uflags & AT_EMPTY_PATH) ? LOOKUP_EMPTY : 0;
return getname_flags(filename, flags, NULL);
}
struct filename *
getname(const char __user * filename)
{
return getname_flags(filename, 0, NULL);
}
struct filename *
getname_kernel(const char * filename)
{
struct filename *result;
int len = strlen(filename) + 1;
result = __getname();
if (unlikely(!result))
return ERR_PTR(-ENOMEM);
if (len <= EMBEDDED_NAME_MAX) {
result->name = (char *)result->iname;
} else if (len <= PATH_MAX) {
const size_t size = offsetof(struct filename, iname[1]);
struct filename *tmp;
tmp = kmalloc(size, GFP_KERNEL);
if (unlikely(!tmp)) {
__putname(result);
return ERR_PTR(-ENOMEM);
}
tmp->name = (char *)result;
result = tmp;
} else {
__putname(result);
return ERR_PTR(-ENAMETOOLONG);
}
memcpy((char *)result->name, filename, len);
result->uptr = NULL;
result->aname = NULL;
result->refcnt = 1;
audit_getname(result);
return result;
}
void putname(struct filename *name)
{
if (IS_ERR(name))
return;
BUG_ON(name->refcnt <= 0);
if (--name->refcnt > 0)
return;
if (name->name != name->iname) {
__putname(name->name);
kfree(name);
} else
__putname(name);
}
/**
* check_acl - perform ACL permission checking
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to check permissions on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
*
* This function performs the ACL permission checking. Since this function
* retrieve POSIX acls it needs to know whether it is called from a blocking or
* non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then take
* care to map the inode according to @mnt_userns before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply passs init_user_ns.
*/
static int check_acl(struct user_namespace *mnt_userns,
struct inode *inode, int mask)
{
#ifdef CONFIG_FS_POSIX_ACL
struct posix_acl *acl;
if (mask & MAY_NOT_BLOCK) {
acl = get_cached_acl_rcu(inode, ACL_TYPE_ACCESS);
if (!acl)
return -EAGAIN;
/* no ->get_acl() calls in RCU mode... */
if (is_uncached_acl(acl))
return -ECHILD;
return posix_acl_permission(mnt_userns, inode, acl, mask);
}
acl = get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl) {
int error = posix_acl_permission(mnt_userns, inode, acl, mask);
posix_acl_release(acl);
return error;
}
#endif
return -EAGAIN;
}
/**
* acl_permission_check - perform basic UNIX permission checking
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to check permissions on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
*
* This function performs the basic UNIX permission checking. Since this
* function may retrieve POSIX acls it needs to know whether it is called from a
* blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit.
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then take
* care to map the inode according to @mnt_userns before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply passs init_user_ns.
*/
static int acl_permission_check(struct user_namespace *mnt_userns,
struct inode *inode, int mask)
{
unsigned int mode = inode->i_mode;
kuid_t i_uid;
/* Are we the owner? If so, ACL's don't matter */
i_uid = i_uid_into_mnt(mnt_userns, inode);
if (likely(uid_eq(current_fsuid(), i_uid))) {
mask &= 7;
mode >>= 6;
return (mask & ~mode) ? -EACCES : 0;
}
/* Do we have ACL's? */
if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
int error = check_acl(mnt_userns, inode, mask);
if (error != -EAGAIN)
return error;
}
/* Only RWX matters for group/other mode bits */
mask &= 7;
/*
* Are the group permissions different from
* the other permissions in the bits we care
* about? Need to check group ownership if so.
*/
if (mask & (mode ^ (mode >> 3))) {
kgid_t kgid = i_gid_into_mnt(mnt_userns, inode);
if (in_group_p(kgid))
mode >>= 3;
}
/* Bits in 'mode' clear that we require? */
return (mask & ~mode) ? -EACCES : 0;
}
/**
* generic_permission - check for access rights on a Posix-like filesystem
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to check access rights for
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC,
* %MAY_NOT_BLOCK ...)
*
* 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.
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then take
* care to map the inode according to @mnt_userns before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply passs init_user_ns.
*/
int generic_permission(struct user_namespace *mnt_userns, struct inode *inode,
int mask)
{
int ret;
/*
* Do the basic permission checks.
*/
ret = acl_permission_check(mnt_userns, inode, mask);
if (ret != -EACCES)
return ret;
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
if (!(mask & MAY_WRITE))
if (capable_wrt_inode_uidgid(mnt_userns, inode,
CAP_DAC_READ_SEARCH))
return 0;
if (capable_wrt_inode_uidgid(mnt_userns, inode,
CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
/*
* Searching includes executable on directories, else just read.
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ)
if (capable_wrt_inode_uidgid(mnt_userns, inode,
CAP_DAC_READ_SEARCH))
return 0;
/*
* Read/write DACs are always overridable.
* Executable DACs are overridable when there is
* at least one exec bit set.
*/
if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
if (capable_wrt_inode_uidgid(mnt_userns, inode,
CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
EXPORT_SYMBOL(generic_permission);
/**
* do_inode_permission - UNIX permission checking
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: inode to check permissions on
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...)
*
* We _really_ want to just do "generic_permission()" without
* even looking at the inode->i_op values. So we keep a cache
* flag in inode->i_opflags, that says "this has not special
* permission function, use the fast case".
*/
static inline int do_inode_permission(struct user_namespace *mnt_userns,
struct inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
if (likely(inode->i_op->permission))
return inode->i_op->permission(mnt_userns, inode, mask);
/* This gets set once for the inode lifetime */
spin_lock(&inode->i_lock);
inode->i_opflags |= IOP_FASTPERM;
spin_unlock(&inode->i_lock);
}
return generic_permission(mnt_userns, inode, mask);
}
/**
* sb_permission - Check superblock-level permissions
* @sb: Superblock of inode to check permission on
* @inode: Inode to check permission on
* @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Separate out file-system wide checks from inode-specific permission checks.
*/
static int sb_permission(struct super_block *sb, struct inode *inode, int mask)
{
if (unlikely(mask & MAY_WRITE)) {
umode_t mode = inode->i_mode;
/* Nobody gets write access to a read-only fs. */
if (sb_rdonly(sb) && (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
return -EROFS;
}
return 0;
}
/**
* inode_permission - Check for access rights to a given inode
* @mnt_userns: User namespace of the mount the inode was found from
* @inode: Inode to check permission on
* @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
*
* Check for read/write/execute permissions on an inode. We use fs[ug]id for
* this, letting us set arbitrary permissions for filesystem access without
* changing the "normal" UIDs which are used for other things.
*
* When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
*/
int inode_permission(struct user_namespace *mnt_userns,
struct inode *inode, int mask)
{
int retval;
retval = sb_permission(inode->i_sb, inode, mask);
if (retval)
return retval;
if (unlikely(mask & MAY_WRITE)) {
/*
* Nobody gets write access to an immutable file.
*/
if (IS_IMMUTABLE(inode))
return -EPERM;
/*
* Updating mtime will likely cause i_uid and i_gid to be
* written back improperly if their true value is unknown
* to the vfs.
*/
if (HAS_UNMAPPED_ID(mnt_userns, inode))
return -EACCES;
}
retval = do_inode_permission(mnt_userns, inode, mask);
if (retval)
return retval;
retval = devcgroup_inode_permission(inode, mask);
if (retval)
return retval;
return security_inode_permission(inode, mask);
}
EXPORT_SYMBOL(inode_permission);
/**
* 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(const 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(const struct path *path)
{
dput(path->dentry);
mntput(path->mnt);
}
EXPORT_SYMBOL(path_put);
#define EMBEDDED_LEVELS 2
struct nameidata {
struct path path;
struct qstr last;
struct path root;
struct inode *inode; /* path.dentry.d_inode */
unsigned int flags, state;
unsigned seq, next_seq, m_seq, r_seq;
int last_type;
unsigned depth;
int total_link_count;
struct saved {
struct path link;
struct delayed_call done;
const char *name;
unsigned seq;
} *stack, internal[EMBEDDED_LEVELS];
struct filename *name;
struct nameidata *saved;
unsigned root_seq;
int dfd;
kuid_t dir_uid;
umode_t dir_mode;
} __randomize_layout;
#define ND_ROOT_PRESET 1
#define ND_ROOT_GRABBED 2
#define ND_JUMPED 4
static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name)
{
struct nameidata *old = current->nameidata;
p->stack = p->internal;
p->depth = 0;
p->dfd = dfd;
p->name = name;
p->path.mnt = NULL;
p->path.dentry = NULL;
p->total_link_count = old ? old->total_link_count : 0;
p->saved = old;
current->nameidata = p;
}
static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name,
const struct path *root)
{
__set_nameidata(p, dfd, name);
p->state = 0;
if (unlikely(root)) {
p->state = ND_ROOT_PRESET;
p->root = *root;
}
}
static void restore_nameidata(void)
{
struct nameidata *now = current->nameidata, *old = now->saved;
current->nameidata = old;
if (old)
old->total_link_count = now->total_link_count;
if (now->stack != now->internal)
kfree(now->stack);
}
static bool nd_alloc_stack(struct nameidata *nd)
{
struct saved *p;
p= kmalloc_array(MAXSYMLINKS, sizeof(struct saved),
nd->flags & LOOKUP_RCU ? GFP_ATOMIC : GFP_KERNEL);
if (unlikely(!p))
return false;
memcpy(p, nd->internal, sizeof(nd->internal));
nd->stack = p;
return true;
}
/**
* path_connected - Verify that a dentry is below mnt.mnt_root
*
* Rename can sometimes move a file or directory outside of a bind
* mount, path_connected allows those cases to be detected.
*/
static bool path_connected(struct vfsmount *mnt, struct dentry *dentry)
{
struct super_block *sb = mnt->mnt_sb;
/* Bind mounts can have disconnected paths */
if (mnt->mnt_root == sb->s_root)
return true;
return is_subdir(dentry, mnt->mnt_root);
}
static void drop_links(struct nameidata *nd)
{
int i = nd->depth;
while (i--) {
struct saved *last = nd->stack + i;
do_delayed_call(&last->done);
clear_delayed_call(&last->done);
}
}
static void leave_rcu(struct nameidata *nd)
{
nd->flags &= ~LOOKUP_RCU;
nd->seq = nd->next_seq = 0;
rcu_read_unlock();
}
static void terminate_walk(struct nameidata *nd)
{
drop_links(nd);
if (!(nd->flags & LOOKUP_RCU)) {
int i;
path_put(&nd->path);
for (i = 0; i < nd->depth; i++)
path_put(&nd->stack[i].link);
if (nd->state & ND_ROOT_GRABBED) {
path_put(&nd->root);
nd->state &= ~ND_ROOT_GRABBED;
}
} else {
leave_rcu(nd);
}
nd->depth = 0;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
}
/* path_put is needed afterwards regardless of success or failure */
static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq)
{
int res = __legitimize_mnt(path->mnt, mseq);
if (unlikely(res)) {
if (res > 0)
path->mnt = NULL;
path->dentry = NULL;
return false;
}
if (unlikely(!lockref_get_not_dead(&path->dentry->d_lockref))) {
path->dentry = NULL;
return false;
}
return !read_seqcount_retry(&path->dentry->d_seq, seq);
}
static inline bool legitimize_path(struct nameidata *nd,
struct path *path, unsigned seq)
{
return __legitimize_path(path, seq, nd->m_seq);
}
static bool legitimize_links(struct nameidata *nd)
{
int i;
if (unlikely(nd->flags & LOOKUP_CACHED)) {
drop_links(nd);
nd->depth = 0;
return false;
}
for (i = 0; i < nd->depth; i++) {
struct saved *last = nd->stack + i;
if (unlikely(!legitimize_path(nd, &last->link, last->seq))) {
drop_links(nd);
nd->depth = i + 1;
return false;
}
}
return true;
}
static bool legitimize_root(struct nameidata *nd)
{
/* Nothing to do if nd->root is zero or is managed by the VFS user. */
if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET))
return true;
nd->state |= ND_ROOT_GRABBED;
return legitimize_path(nd, &nd->root, nd->root_seq);
}
/*
* Path walking has 2 modes, rcu-walk and ref-walk (see
* Documentation/filesystems/path-lookup.txt). In situations when we can't
* continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
* normal reference counts on dentries and vfsmounts to transition to ref-walk
* mode. Refcounts are grabbed 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 it's up to caller
* to restart the path walk from the beginning in ref-walk mode.
*/
/**
* try_to_unlazy - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* Returns: true on success, false on failure
*
* try_to_unlazy attempts to legitimize the current nd->path and nd->root
* for ref-walk mode.
* Must be called from rcu-walk context.
* Nothing should touch nameidata between try_to_unlazy() failure and
* terminate_walk().
*/
static bool try_to_unlazy(struct nameidata *nd)
{
struct dentry *parent = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
if (unlikely(!legitimize_links(nd)))
goto out1;
if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
goto out;
if (unlikely(!legitimize_root(nd)))
goto out;
leave_rcu(nd);
BUG_ON(nd->inode != parent->d_inode);
return true;
out1:
nd->path.mnt = NULL;
nd->path.dentry = NULL;
out:
leave_rcu(nd);
return false;
}
/**
* try_to_unlazy_next - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* @dentry: next dentry to step into
* Returns: true on success, false on failure
*
* Similar to try_to_unlazy(), but here we have the next dentry already
* picked by rcu-walk and want to legitimize that in addition to the current
* nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context.
* Nothing should touch nameidata between try_to_unlazy_next() failure and
* terminate_walk().
*/
static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry)
{
int res;
BUG_ON(!(nd->flags & LOOKUP_RCU));
if (unlikely(!legitimize_links(nd)))
goto out2;
res = __legitimize_mnt(nd->path.mnt, nd->m_seq);
if (unlikely(res)) {
if (res > 0)
goto out2;
goto out1;
}
if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
goto out1;
/*
* We need to move both the parent and the dentry from the RCU domain
* to be properly refcounted. And the sequence number in the dentry
* validates *both* dentry counters, since we checked the sequence
* number of the parent after we got the child sequence number. So we
* know the parent must still be valid if the child sequence number is
*/
if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
goto out;
if (read_seqcount_retry(&dentry->d_seq, nd->next_seq))
goto out_dput;
/*
* Sequence counts matched. Now make sure that the root is
* still valid and get it if required.
*/
if (unlikely(!legitimize_root(nd)))
goto out_dput;
leave_rcu(nd);
return true;
out2:
nd->path.mnt = NULL;
out1:
nd->path.dentry = NULL;
out:
leave_rcu(nd);
return false;
out_dput:
leave_rcu(nd);
dput(dentry);
return false;
}
static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
return dentry->d_op->d_revalidate(dentry, flags);
else
return 1;
}
/**
* complete_walk - successful completion of path walk
* @nd: pointer nameidata
*
* If we had been in RCU mode, drop out of it and legitimize nd->path.
* Revalidate the final result, unless we'd already done that during
* the path walk or the filesystem doesn't ask for it. Return 0 on
* success, -error on failure. In case of failure caller does not
* need to drop nd->path.
*/
static int complete_walk(struct nameidata *nd)
{
struct dentry *dentry = nd->path.dentry;
int status;
if (nd->flags & LOOKUP_RCU) {
/*
* We don't want to zero nd->root for scoped-lookups or
* externally-managed nd->root.
*/
if (!(nd->state & ND_ROOT_PRESET))
if (!(nd->flags & LOOKUP_IS_SCOPED))
nd->root.mnt = NULL;
nd->flags &= ~LOOKUP_CACHED;
if (!try_to_unlazy(nd))
return -ECHILD;
}
if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
/*
* While the guarantee of LOOKUP_IS_SCOPED is (roughly) "don't
* ever step outside the root during lookup" and should already
* be guaranteed by the rest of namei, we want to avoid a namei
* BUG resulting in userspace being given a path that was not
* scoped within the root at some point during the lookup.
*
* So, do a final sanity-check to make sure that in the
* worst-case scenario (a complete bypass of LOOKUP_IS_SCOPED)
* we won't silently return an fd completely outside of the
* requested root to userspace.
*
* Userspace could move the path outside the root after this
* check, but as discussed elsewhere this is not a concern (the
* resolved file was inside the root at some point).
*/
if (!path_is_under(&nd->path, &nd->root))
return -EXDEV;
}
if (likely(!(nd->state & ND_JUMPED)))
return 0;
if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
return 0;
status = dentry->d_op->d_weak_revalidate(dentry, nd->flags);
if (status > 0)
return 0;
if (!status)
status = -ESTALE;
return status;
}
static int set_root(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
/*
* Jumping to the real root in a scoped-lookup is a BUG in namei, but we
* still have to ensure it doesn't happen because it will cause a breakout
* from the dirfd.
*/
if (WARN_ON(nd->flags & LOOKUP_IS_SCOPED))
return -ENOTRECOVERABLE;
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
nd->root = fs->root;
nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
} else {
get_fs_root(fs, &nd->root);
nd->state |= ND_ROOT_GRABBED;
}
return 0;
}
static int nd_jump_root(struct nameidata *nd)
{
if (unlikely(nd->flags & LOOKUP_BENEATH))
return -EXDEV;
if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
/* Absolute path arguments to path_init() are allowed. */
if (nd->path.mnt != NULL && nd->path.mnt != nd->root.mnt)
return -EXDEV;
}
if (!nd->root.mnt) {
int error = set_root(nd);
if (error)
return error;
}
if (nd->flags & LOOKUP_RCU) {
struct dentry *d;
nd->path = nd->root;
d = nd->path.dentry;
nd->inode = d->d_inode;
nd->seq = nd->root_seq;
if (read_seqcount_retry(&d->d_seq, nd->seq))
return -ECHILD;
} else {
path_put(&nd->path);
nd->path = nd->root;
path_get(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
nd->state |= ND_JUMPED;
return 0;
}
/*
* Helper to directly jump to a known parsed path from ->get_link,
* caller must have taken a reference to path beforehand.
*/
int nd_jump_link(const struct path *path)
{
int error = -ELOOP;
struct nameidata *nd = current->nameidata;
if (unlikely(nd->flags & LOOKUP_NO_MAGICLINKS))
goto err;
error = -EXDEV;
if (unlikely(nd->flags & LOOKUP_NO_XDEV)) {
if (nd->path.mnt != path->mnt)
goto err;
}
/* Not currently safe for scoped-lookups. */
if (unlikely(nd->flags & LOOKUP_IS_SCOPED))
goto err;
path_put(&nd->path);
nd->path = *path;
nd->inode = nd->path.dentry->d_inode;
nd->state |= ND_JUMPED;
return 0;
err:
path_put(path);
return error;
}
static inline void put_link(struct nameidata *nd)
{
struct saved *last = nd->stack + --nd->depth;
do_delayed_call(&last->done);
if (!(nd->flags & LOOKUP_RCU))
path_put(&last->link);
}
static int sysctl_protected_symlinks __read_mostly;
static int sysctl_protected_hardlinks __read_mostly;
static int sysctl_protected_fifos __read_mostly;
static int sysctl_protected_regular __read_mostly;
#ifdef CONFIG_SYSCTL
static struct ctl_table namei_sysctls[] = {
{
.procname = "protected_symlinks",
.data = &sysctl_protected_symlinks,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{
.procname = "protected_hardlinks",
.data = &sysctl_protected_hardlinks,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
{
.procname = "protected_fifos",
.data = &sysctl_protected_fifos,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{
.procname = "protected_regular",
.data = &sysctl_protected_regular,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_TWO,
},
{ }
};
static int __init init_fs_namei_sysctls(void)
{
register_sysctl_init("fs", namei_sysctls);
return 0;
}
fs_initcall(init_fs_namei_sysctls);
#endif /* CONFIG_SYSCTL */
/**
* may_follow_link - Check symlink following for unsafe situations
* @nd: nameidata pathwalk data
*
* In the case of the sysctl_protected_symlinks sysctl being enabled,
* CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is
* in a sticky world-writable directory. This is to protect privileged
* processes from failing races against path names that may change out
* from under them by way of other users creating malicious symlinks.
* It will permit symlinks to be followed only when outside a sticky
* world-writable directory, or when the uid of the symlink and follower
* match, or when the directory owner matches the symlink's owner.
*
* Returns 0 if following the symlink is allowed, -ve on error.
*/
static inline int may_follow_link(struct nameidata *nd, const struct inode *inode)
{
struct user_namespace *mnt_userns;
kuid_t i_uid;
if (!sysctl_protected_symlinks)
return 0;
mnt_userns = mnt_user_ns(nd->path.mnt);
i_uid = i_uid_into_mnt(mnt_userns, inode);
/* Allowed if owner and follower match. */
if (uid_eq(current_cred()->fsuid, i_uid))
return 0;
/* Allowed if parent directory not sticky and world-writable. */
if ((nd->dir_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
return 0;
/* Allowed if parent directory and link owner match. */
if (uid_valid(nd->dir_uid) && uid_eq(nd->dir_uid, i_uid))
return 0;
if (nd->flags & LOOKUP_RCU)
return -ECHILD;
audit_inode(nd->name, nd->stack[0].link.dentry, 0);
audit_log_path_denied(AUDIT_ANOM_LINK, "follow_link");
return -EACCES;
}
/**
* safe_hardlink_source - Check for safe hardlink conditions
* @mnt_userns: user namespace of the mount the inode was found from
* @inode: the source inode to hardlink from
*
* Return false if at least one of the following conditions:
* - inode is not a regular file
* - inode is setuid
* - inode is setgid and group-exec
* - access failure for read and write
*
* Otherwise returns true.
*/
static bool safe_hardlink_source(struct user_namespace *mnt_userns,
struct inode *inode)
{
umode_t mode = inode->i_mode;
/* Special files should not get pinned to the filesystem. */
if (!S_ISREG(mode))
return false;
/* Setuid files should not get pinned to the filesystem. */
if (mode & S_ISUID)
return false;
/* Executable setgid files should not get pinned to the filesystem. */
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP))
return false;
/* Hardlinking to unreadable or unwritable sources is dangerous. */
if (inode_permission(mnt_userns, inode, MAY_READ | MAY_WRITE))
return false;
return true;
}
/**
* may_linkat - Check permissions for creating a hardlink
* @mnt_userns: user namespace of the mount the inode was found from
* @link: the source to hardlink from
*
* Block hardlink when all of:
* - sysctl_protected_hardlinks enabled
* - fsuid does not match inode
* - hardlink source is unsafe (see safe_hardlink_source() above)
* - not CAP_FOWNER in a namespace with the inode owner uid mapped
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then take
* care to map the inode according to @mnt_userns before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply passs init_user_ns.
*
* Returns 0 if successful, -ve on error.
*/
int may_linkat(struct user_namespace *mnt_userns, const struct path *link)
{
struct inode *inode = link->dentry->d_inode;
/* Inode writeback is not safe when the uid or gid are invalid. */
if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
!gid_valid(i_gid_into_mnt(mnt_userns, inode)))
return -EOVERFLOW;
if (!sysctl_protected_hardlinks)
return 0;
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
if (safe_hardlink_source(mnt_userns, inode) ||
inode_owner_or_capable(mnt_userns, inode))
return 0;
audit_log_path_denied(AUDIT_ANOM_LINK, "linkat");
return -EPERM;
}
/**
* may_create_in_sticky - Check whether an O_CREAT open in a sticky directory
* should be allowed, or not, on files that already
* exist.
* @mnt_userns: user namespace of the mount the inode was found from
* @nd: nameidata pathwalk data
* @inode: the inode of the file to open
*
* Block an O_CREAT open of a FIFO (or a regular file) when:
* - sysctl_protected_fifos (or sysctl_protected_regular) is enabled
* - the file already exists
* - we are in a sticky directory
* - we don't own the file
* - the owner of the directory doesn't own the file
* - the directory is world writable
* If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2
* the directory doesn't have to be world writable: being group writable will
* be enough.
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then take
* care to map the inode according to @mnt_userns before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply passs init_user_ns.
*
* Returns 0 if the open is allowed, -ve on error.
*/
static int may_create_in_sticky(struct user_namespace *mnt_userns,
struct nameidata *nd, struct inode *const inode)
{
umode_t dir_mode = nd->dir_mode;
kuid_t dir_uid = nd->dir_uid;
if ((!sysctl_protected_fifos && S_ISFIFO(inode->i_mode)) ||
(!sysctl_protected_regular && S_ISREG(inode->i_mode)) ||
likely(!(dir_mode & S_ISVTX)) ||
uid_eq(i_uid_into_mnt(mnt_userns, inode), dir_uid) ||
uid_eq(current_fsuid(), i_uid_into_mnt(mnt_userns, inode)))
return 0;
if (likely(dir_mode & 0002) ||
(dir_mode & 0020 &&
((sysctl_protected_fifos >= 2 && S_ISFIFO(inode->i_mode)) ||
(sysctl_protected_regular >= 2 && S_ISREG(inode->i_mode))))) {
const char *operation = S_ISFIFO(inode->i_mode) ?
"sticky_create_fifo" :
"sticky_create_regular";
audit_log_path_denied(AUDIT_ANOM_CREAT, operation);
return -EACCES;
}
return 0;
}
/*
* follow_up - Find the mountpoint of path's vfsmount
*
* Given a path, find the mountpoint of its source file system.
* Replace @path with the path of the mountpoint in the parent mount.
* Up is towards /.
*
* Return 1 if we went up a level and 0 if we were already at the
* root.
*/
int follow_up(struct path *path)
{
struct mount *mnt = real_mount(path->mnt);
struct mount *parent;
struct dentry *mountpoint;
read_seqlock_excl(&mount_lock);
parent = mnt->mnt_parent;
if (parent == mnt) {
read_sequnlock_excl(&mount_lock);
return 0;
}
mntget(&parent->mnt);
mountpoint = dget(mnt->mnt_mountpoint);
read_sequnlock_excl(&mount_lock);
dput(path->dentry);
path->dentry = mountpoint;
mntput(path->mnt);
path->mnt = &parent->mnt;
return 1;
}
EXPORT_SYMBOL(follow_up);
static bool choose_mountpoint_rcu(struct mount *m, const struct path *root,
struct path *path, unsigned *seqp)
{
while (mnt_has_parent(m)) {
struct dentry *mountpoint = m->mnt_mountpoint;
m = m->mnt_parent;
if (unlikely(root->dentry == mountpoint &&
root->mnt == &m->mnt))
break;
if (mountpoint != m->mnt.mnt_root) {
path->mnt = &m->mnt;
path->dentry = mountpoint;
*seqp = read_seqcount_begin(&mountpoint->d_seq);
return true;
}
}
return false;
}
static bool choose_mountpoint(struct mount *m, const struct path *root,
struct path *path)
{
bool found;
rcu_read_lock();
while (1) {
unsigned seq, mseq = read_seqbegin(&mount_lock);
found = choose_mountpoint_rcu(m, root, path, &seq);
if (unlikely(!found)) {
if (!read_seqretry(&mount_lock, mseq))
break;
} else {
if (likely(__legitimize_path(path, seq, mseq)))
break;
rcu_read_unlock();
path_put(path);
rcu_read_lock();
}
}
rcu_read_unlock();
return found;
}
/*
* 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, int *count, unsigned lookup_flags)
{
struct dentry *dentry = path->dentry;
/* We don't want to mount if someone's just doing a stat -
* unless they're stat'ing a directory and appended a '/' to
* the name.
*
* We do, however, want to mount if someone wants to open or
* create a file of any type under the mountpoint, wants to
* traverse through the mountpoint or wants to open the
* mounted directory. Also, autofs may mark negative dentries
* as being automount points. These will need the attentions
* of the daemon to instantiate them before they can be used.
*/
if (!(lookup_flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
dentry->d_inode)
return -EISDIR;
if (count && (*count)++ >= MAXSYMLINKS)
return -ELOOP;
return finish_automount(dentry->d_op->d_automount(path), path);
}
/*
* mount traversal - out-of-line part. One note on ->d_flags accesses -
* dentries are pinned but not locked here, so negative dentry can go
* positive right under us. Use of smp_load_acquire() provides a barrier
* sufficient for ->d_inode and ->d_flags consistency.
*/
static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped,
int *count, unsigned lookup_flags)
{
struct vfsmount *mnt = path->mnt;
bool need_mntput = false;
int ret = 0;
while (flags & DCACHE_MANAGED_DENTRY) {
/* Allow the filesystem to manage the transit without i_mutex
* being held. */
if (flags & DCACHE_MANAGE_TRANSIT) {
ret = path->dentry->d_op->d_manage(path, false);
flags = smp_load_acquire(&path->dentry->d_flags);
if (ret < 0)
break;
}
if (flags & DCACHE_MOUNTED) { // something's mounted on it..
struct vfsmount *mounted = lookup_mnt(path);
if (mounted) { // ... in our namespace
dput(path->dentry);
if (need_mntput)
mntput(path->mnt);
path->mnt = mounted;
path->dentry = dget(mounted->mnt_root);
// here we know it's positive
flags = path->dentry->d_flags;
need_mntput = true;
continue;
}
}
if (!(flags & DCACHE_NEED_AUTOMOUNT))
break;
// uncovered automount point
ret = follow_automount(path, count, lookup_flags);
flags = smp_load_acquire(&path->dentry->d_flags);
if (ret < 0)
break;
}
if (ret == -EISDIR)
ret = 0;
// possible if you race with several mount --move
if (need_mntput && path->mnt == mnt)
mntput(path->mnt);
if (!ret && unlikely(d_flags_negative(flags)))
ret = -ENOENT;
*jumped = need_mntput;
return ret;
}
static inline int traverse_mounts(struct path *path, bool *jumped,
int *count, unsigned lookup_flags)
{
unsigned flags = smp_load_acquire(&path->dentry->d_flags);
/* fastpath */
if (likely(!(flags & DCACHE_MANAGED_DENTRY))) {
*jumped = false;
if (unlikely(d_flags_negative(flags)))
return -ENOENT;
return 0;
}
return __traverse_mounts(path, flags, jumped, count, lookup_flags);
}
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;
}
EXPORT_SYMBOL(follow_down_one);
/*
* 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.
*/
int follow_down(struct path *path)
{
struct vfsmount *mnt = path->mnt;
bool jumped;
int ret = traverse_mounts(path, &jumped, NULL, 0);
if (path->mnt != mnt)
mntput(mnt);
return ret;
}
EXPORT_SYMBOL(follow_down);
/*
* Try to skip to top of mountpoint pile in rcuwalk mode. Fail if
* we meet a managed dentry that would need blocking.
*/
static bool __follow_mount_rcu(struct nameidata *nd, struct path *path)
{
struct dentry *dentry = path->dentry;
unsigned int flags = dentry->d_flags;
if (likely(!(flags & DCACHE_MANAGED_DENTRY)))
return true;
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
return false;
for (;;) {
/*
* Don't forget we might have a non-mountpoint managed dentry
* that wants to block transit.
*/
if (unlikely(flags & DCACHE_MANAGE_TRANSIT)) {
int res = dentry->d_op->d_manage(path, true);
if (res)
return res == -EISDIR;
flags = dentry->d_flags;
}
if (flags & DCACHE_MOUNTED) {
struct mount *mounted = __lookup_mnt(path->mnt, dentry);
if (mounted) {
path->mnt = &mounted->mnt;
dentry = path->dentry = mounted->mnt.mnt_root;
nd->state |= ND_JUMPED;
nd->next_seq = read_seqcount_begin(&dentry->d_seq);
flags = dentry->d_flags;
// makes sure that non-RCU pathwalk could reach
// this state.
if (read_seqretry(&mount_lock, nd->m_seq))
return false;
continue;
}
if (read_seqretry(&mount_lock, nd->m_seq))
return false;
}
return !(flags & DCACHE_NEED_AUTOMOUNT);
}
}
static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
struct path *path)
{
bool jumped;
int ret;
path->mnt = nd->path.mnt;
path->dentry = dentry;
if (nd->flags & LOOKUP_RCU) {
unsigned int seq = nd->next_seq;
if (likely(__follow_mount_rcu(nd, path)))
return 0;
// *path and nd->next_seq might've been clobbered
path->mnt = nd->path.mnt;
path->dentry = dentry;
nd->next_seq = seq;
if (!try_to_unlazy_next(nd, dentry))
return -ECHILD;
}
ret = traverse_mounts(path, &jumped, &nd->total_link_count, nd->flags);
if (jumped) {
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
ret = -EXDEV;
else
nd->state |= ND_JUMPED;
}
if (unlikely(ret)) {
dput(path->dentry);
if (path->mnt != nd->path.mnt)
mntput(path->mnt);
}
return ret;
}
/*
* This looks up the name in dcache and possibly revalidates the found dentry.
* NULL is returned if the dentry does not exist in the cache.
*/
static struct dentry *lookup_dcache(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
struct dentry *dentry = d_lookup(dir, name);
if (dentry) {
int error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
if (!error)
d_invalidate(dentry);
dput(dentry);
return ERR_PTR(error);
}
}
return dentry;
}
/*
* Parent directory has inode locked exclusive. This is one
* and only case when ->lookup() gets called on non in-lookup
* dentries - as the matter of fact, this only gets called
* when directory is guaranteed to have no in-lookup children
* at all.
*/
static struct dentry *__lookup_hash(const struct qstr *name,
struct dentry *base, unsigned int flags)
{
struct dentry *dentry = lookup_dcache(name, base, flags);
struct dentry *old;
struct inode *dir = base->d_inode;
if (dentry)
return dentry;
/* Don't create child dentry for a dead directory. */
if (unlikely(IS_DEADDIR(dir)))
return ERR_PTR(-ENOENT);
dentry = d_alloc(base, name);
if (unlikely(!dentry))
return ERR_PTR(-ENOMEM);
old = dir->i_op->lookup(dir, dentry, flags);
if (unlikely(old)) {
dput(dentry);
dentry = old;
}
return dentry;
}
static struct dentry *lookup_fast(struct nameidata *nd)
{
struct dentry *dentry, *parent = nd->path.dentry;
int status = 1;
/*
* Rename seqlock is not required here because in the off chance
* of a false negative due to a concurrent rename, the caller is
* going to fall back to non-racy lookup.
*/
if (nd->flags & LOOKUP_RCU) {
dentry = __d_lookup_rcu(parent, &nd->last, &nd->next_seq);
if (unlikely(!dentry)) {
if (!try_to_unlazy(nd))
return ERR_PTR(-ECHILD);
return NULL;
}
/*
* This sequence count validates that the parent had no
* changes while we did the lookup of the dentry above.
*/
if (read_seqcount_retry(&parent->d_seq, nd->seq))
return ERR_PTR(-ECHILD);
status = d_revalidate(dentry, nd->flags);
if (likely(status > 0))
return dentry;
if (!try_to_unlazy_next(nd, dentry))
return ERR_PTR(-ECHILD);
if (status == -ECHILD)
/* we'd been told to redo it in non-rcu mode */
status = d_revalidate(dentry, nd->flags);
} else {
dentry = __d_lookup(parent, &nd->last);
if (unlikely(!dentry))
return NULL;
status = d_revalidate(dentry, nd->flags);
}
if (unlikely(status <= 0)) {
if (!status)
d_invalidate(dentry);
dput(dentry);
return ERR_PTR(status);
}
return dentry;
}
/* Fast lookup failed, do it the slow way */
static struct dentry *__lookup_slow(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
struct dentry *dentry, *old;
struct inode *inode = dir->d_inode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
/* Don't go there if it's already dead */
if (unlikely(IS_DEADDIR(inode)))
return ERR_PTR(-ENOENT);
again:
dentry = d_alloc_parallel(dir, name, &wq);
if (IS_ERR(dentry))
return dentry;
if (unlikely(!d_in_lookup(dentry))) {
int error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
if (!error) {
d_invalidate(dentry);
dput(dentry);
goto again;
}
dput(dentry);
dentry = ERR_PTR(error);
}
} else {
old = inode->i_op->lookup(inode, dentry, flags);
d_lookup_done(dentry);
if (unlikely(old)) {
dput(dentry);
dentry = old;
}
}
return dentry;
}
static struct dentry *lookup_slow(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
struct inode *inode = dir->d_inode;
struct dentry *res;
inode_lock_shared(inode);
res = __lookup_slow(name, dir, flags);
inode_unlock_shared(inode);
return res;
}
static inline int may_lookup(struct user_namespace *mnt_userns,
struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
int err = inode_permission(mnt_userns, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD || !try_to_unlazy(nd))
return err;
}
return inode_permission(mnt_userns, nd->inode, MAY_EXEC);
}
static int reserve_stack(struct nameidata *nd, struct path *link)
{
if (unlikely(nd->total_link_count++ >= MAXSYMLINKS))
return -ELOOP;
if (likely(nd->depth != EMBEDDED_LEVELS))
return 0;
if (likely(nd->stack != nd->internal))
return 0;
if (likely(nd_alloc_stack(nd)))
return 0;
if (nd->flags & LOOKUP_RCU) {
// we need to grab link before we do unlazy. And we can't skip
// unlazy even if we fail to grab the link - cleanup needs it
bool grabbed_link = legitimize_path(nd, link, nd->next_seq);
if (!try_to_unlazy(nd) || !grabbed_link)
return -ECHILD;
if (nd_alloc_stack(nd))
return 0;
}
return -ENOMEM;
}
enum {WALK_TRAILING = 1, WALK_MORE = 2, WALK_NOFOLLOW = 4};
static const char *pick_link(struct nameidata *nd, struct path *link,
struct inode *inode, int flags)
{
struct saved *last;
const char *res;
int error = reserve_stack(nd, link);
if (unlikely(error)) {
if (!(nd->flags & LOOKUP_RCU))
path_put(link);
return ERR_PTR(error);
}
last = nd->stack + nd->depth++;
last->link = *link;
clear_delayed_call(&last->done);
last->seq = nd->next_seq;
if (flags & WALK_TRAILING) {
error = may_follow_link(nd, inode);
if (unlikely(error))
return ERR_PTR(error);
}
if (unlikely(nd->flags & LOOKUP_NO_SYMLINKS) ||
unlikely(link->mnt->mnt_flags & MNT_NOSYMFOLLOW))
return ERR_PTR(-ELOOP);
if (!(nd->flags & LOOKUP_RCU)) {
touch_atime(&last->link);
cond_resched();
} else if (atime_needs_update(&last->link, inode)) {
if (!try_to_unlazy(nd))
return ERR_PTR(-ECHILD);
touch_atime(&last->link);
}
error = security_inode_follow_link(link->dentry, inode,
nd->flags & LOOKUP_RCU);
if (unlikely(error))
return ERR_PTR(error);
res = READ_ONCE(inode->i_link);
if (!res) {
const char * (*get)(struct dentry *, struct inode *,
struct delayed_call *);
get = inode->i_op->get_link;
if (nd->flags & LOOKUP_RCU) {
res = get(NULL, inode, &last->done);
if (res == ERR_PTR(-ECHILD) && try_to_unlazy(nd))
res = get(link->dentry, inode, &last->done);
} else {
res = get(link->dentry, inode, &last->done);
}
if (!res)
goto all_done;
if (IS_ERR(res))
return res;
}
if (*res == '/') {
error = nd_jump_root(nd);
if (unlikely(error))
return ERR_PTR(error);
while (unlikely(*++res == '/'))
;
}
if (*res)
return res;
all_done: // pure jump
put_link(nd);
return NULL;
}
/*
* Do we need to follow links? We _really_ want to be able
* to do this check without having to look at inode->i_op,
* so we keep a cache of "no, this doesn't need follow_link"
* for the common case.
*
* NOTE: dentry must be what nd->next_seq had been sampled from.
*/
static const char *step_into(struct nameidata *nd, int flags,
struct dentry *dentry)
{
struct path path;
struct inode *inode;
int err = handle_mounts(nd, dentry, &path);
if (err < 0)
return ERR_PTR(err);
inode = path.dentry->d_inode;
if (likely(!d_is_symlink(path.dentry)) ||
((flags & WALK_TRAILING) && !(nd->flags & LOOKUP_FOLLOW)) ||
(flags & WALK_NOFOLLOW)) {
/* not a symlink or should not follow */
if (nd->flags & LOOKUP_RCU) {
if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
return ERR_PTR(-ECHILD);
if (unlikely(!inode))
return ERR_PTR(-ENOENT);
} else {
dput(nd->path.dentry);
if (nd->path.mnt != path.mnt)
mntput(nd->path.mnt);
}
nd->path = path;
nd->inode = inode;
nd->seq = nd->next_seq;
return NULL;
}
if (nd->flags & LOOKUP_RCU) {
/* make sure that d_is_symlink above matches inode */
if (read_seqcount_retry(&path.dentry->d_seq, nd->next_seq))
return ERR_PTR(-ECHILD);
} else {
if (path.mnt == nd->path.mnt)
mntget(path.mnt);
}
return pick_link(nd, &path, inode, flags);
}
static struct dentry *follow_dotdot_rcu(struct nameidata *nd)
{
struct dentry *parent, *old;
if (path_equal(&nd->path, &nd->root))
goto in_root;
if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) {
struct path path;
unsigned seq;
if (!choose_mountpoint_rcu(real_mount(nd->path.mnt),
&nd->root, &path, &seq))
goto in_root;
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
return ERR_PTR(-ECHILD);
nd->path = path;
nd->inode = path.dentry->d_inode;
nd->seq = seq;
// makes sure that non-RCU pathwalk could reach this state
if (read_seqretry(&mount_lock, nd->m_seq))
return ERR_PTR(-ECHILD);
/* we know that mountpoint was pinned */
}
old = nd->path.dentry;
parent = old->d_parent;
nd->next_seq = read_seqcount_begin(&parent->d_seq);
// makes sure that non-RCU pathwalk could reach this state
if (read_seqcount_retry(&old->d_seq, nd->seq))
return ERR_PTR(-ECHILD);
if (unlikely(!path_connected(nd->path.mnt, parent)))
return ERR_PTR(-ECHILD);
return parent;
in_root:
if (read_seqretry(&mount_lock, nd->m_seq))
return ERR_PTR(-ECHILD);
if (unlikely(nd->flags & LOOKUP_BENEATH))
return ERR_PTR(-ECHILD);
nd->next_seq = nd->seq;
return nd->path.dentry;
}
static struct dentry *follow_dotdot(struct nameidata *nd)
{
struct dentry *parent;
if (path_equal(&nd->path, &nd->root))
goto in_root;
if (unlikely(nd->path.dentry == nd->path.mnt->mnt_root)) {
struct path path;
if (!choose_mountpoint(real_mount(nd->path.mnt),
&nd->root, &path))
goto in_root;
path_put(&nd->path);
nd->path = path;
nd->inode = path.dentry->d_inode;
if (unlikely(nd->flags & LOOKUP_NO_XDEV))
return ERR_PTR(-EXDEV);
}
/* rare case of legitimate dget_parent()... */
parent = dget_parent(nd->path.dentry);
if (unlikely(!path_connected(nd->path.mnt, parent))) {
dput(parent);
return ERR_PTR(-ENOENT);
}
return parent;
in_root:
if (unlikely(nd->flags & LOOKUP_BENEATH))
return ERR_PTR(-EXDEV);
return dget(nd->path.dentry);
}
static const char *handle_dots(struct nameidata *nd, int type)
{
if (type == LAST_DOTDOT) {
const char *error = NULL;
struct dentry *parent;
if (!nd->root.mnt) {
error = ERR_PTR(set_root(nd));
if (error)
return error;
}
if (nd->flags & LOOKUP_RCU)
parent = follow_dotdot_rcu(nd);
else
parent = follow_dotdot(nd);
if (IS_ERR(parent))
return ERR_CAST(parent);
error = step_into(nd, WALK_NOFOLLOW, parent);
if (unlikely(error))
return error;
if (unlikely(nd->flags & LOOKUP_IS_SCOPED)) {
/*
* If there was a racing rename or mount along our
* path, then we can't be sure that ".." hasn't jumped
* above nd->root (and so userspace should retry or use
* some fallback).
*/
smp_rmb();
if (__read_seqcount_retry(&mount_lock.seqcount, nd->m_seq))
return ERR_PTR(-EAGAIN);
if (__read_seqcount_retry(&rename_lock.seqcount, nd->r_seq))
return ERR_PTR(-EAGAIN);
}
}
return NULL;
}
static const char *walk_component(struct nameidata *nd, int flags)
{
struct dentry *dentry;
/*
* "." and ".." are special - ".." especially so because it has
* to be able to know about the current root directory and
* parent relationships.
*/
if (unlikely(nd->last_type != LAST_NORM)) {
if (!(flags & WALK_MORE) && nd->depth)
put_link(nd);
return handle_dots(nd, nd->last_type);
}
dentry = lookup_fast(nd);
if (IS_ERR(dentry))
return ERR_CAST(dentry);
if (unlikely(!dentry)) {
dentry = lookup_slow(&nd->last, nd->path.dentry, nd->flags);
if (IS_ERR(dentry))
return ERR_CAST(dentry);
}
if (!(flags & WALK_MORE) && nd->depth)
put_link(nd);
return step_into(nd, flags, dentry);
}
/*
* We can do the critical dentry name comparison and hashing
* operations one word at a time, but we are limited to:
*
* - Architectures with fast unaligned word accesses. We could
* do a "get_unaligned()" if this helps and is sufficiently
* fast.
*
* - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we
* do not trap on the (extremely unlikely) case of a page
* crossing operation.
*
* - Furthermore, we need an efficient 64-bit compile for the
* 64-bit case in order to generate the "number of bytes in
* the final mask". Again, that could be replaced with a
* efficient population count instruction or similar.
*/
#ifdef CONFIG_DCACHE_WORD_ACCESS
#include <asm/word-at-a-time.h>
#ifdef HASH_MIX
/* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */
#elif defined(CONFIG_64BIT)
/*
* Register pressure in the mixing function is an issue, particularly
* on 32-bit x86, but almost any function requires one state value and
* one temporary. Instead, use a function designed for two state values
* and no temporaries.
*
* This function cannot create a collision in only two iterations, so
* we have two iterations to achieve avalanche. In those two iterations,
* we have six layers of mixing, which is enough to spread one bit's
* influence out to 2^6 = 64 state bits.
*
* Rotate constants are scored by considering either 64 one-bit input
* deltas or 64*63/2 = 2016 two-bit input deltas, and finding the
* probability of that delta causing a change to each of the 128 output
* bits, using a sample of random initial states.
*
* The Shannon entropy of the computed probabilities is then summed
* to produce a score. Ideally, any input change has a 50% chance of
* toggling any given output bit.
*
* Mixing scores (in bits) for (12,45):
* Input delta: 1-bit 2-bit
* 1 round: 713.3 42542.6
* 2 rounds: 2753.7 140389.8
* 3 rounds: 5954.1 233458.2
* 4 rounds: 7862.6 256672.2
* Perfect: 8192 258048
* (64*128) (64*63/2 * 128)
*/
#define HASH_MIX(x, y, a) \
( x ^= (a), \
y ^= x, x = rol64(x,12),\
x += y, y = rol64(y,45),\
y *= 9 )
/*
* Fold two longs into one 32-bit hash value. This must be fast, but
* latency isn't quite as critical, as there is a fair bit of additional
* work done before the hash value is used.
*/
static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
y ^= x * GOLDEN_RATIO_64;
y *= GOLDEN_RATIO_64;
return y >> 32;
}
#else /* 32-bit case */
/*
* Mixing scores (in bits) for (7,20):
* Input delta: 1-bit 2-bit
* 1 round: 330.3 9201.6
* 2 rounds: 1246.4 25475.4
* 3 rounds: 1907.1 31295.1
* 4 rounds: 2042.3 31718.6
* Perfect: 2048 31744
* (32*64) (32*31/2 * 64)
*/
#define HASH_MIX(x, y, a) \
( x ^= (a), \
y ^= x, x = rol32(x, 7),\
x += y, y = rol32(y,20),\
y *= 9 )
static inline unsigned int fold_hash(unsigned long x, unsigned long y)
{
/* Use arch-optimized multiply if one exists */
return __hash_32(y ^ __hash_32(x));
}
#endif
/*
* Return the hash of a string of known length. This is carfully
* designed to match hash_name(), which is the more critical function.
* In particular, we must end by hashing a final word containing 0..7
* payload bytes, to match the way that hash_name() iterates until it
* finds the delimiter after the name.
*/
unsigned int full_name_hash(const void *salt, const char *name, unsigned int len)
{
unsigned long a, x = 0, y = (unsigned long)salt;
for (;;) {
if (!len)
goto done;
a = load_unaligned_zeropad(name);
if (len < sizeof(unsigned long))
break;
HASH_MIX(x, y, a);
name += sizeof(unsigned long);
len -= sizeof(unsigned long);
}
x ^= a & bytemask_from_count(len);
done:
return fold_hash(x, y);
}
EXPORT_SYMBOL(full_name_hash);
/* Return the "hash_len" (hash and length) of a null-terminated string */
u64 hashlen_string(const void *salt, const char *name)
{
unsigned long a = 0, x = 0, y = (unsigned long)salt;
unsigned long adata, mask, len;
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
len = 0;
goto inside;
do {
HASH_MIX(x, y, a);
len += sizeof(unsigned long);
inside:
a = load_unaligned_zeropad(name+len);
} while (!has_zero(a, &adata, &constants));
adata = prep_zero_mask(a, adata, &constants);
mask = create_zero_mask(adata);
x ^= a & zero_bytemask(mask);
return hashlen_create(fold_hash(x, y), len + find_zero(mask));
}
EXPORT_SYMBOL(hashlen_string);
/*
* Calculate the length and hash of the path component, and
* return the "hash_len" as the result.
*/
static inline u64 hash_name(const void *salt, const char *name)
{
unsigned long a = 0, b, x = 0, y = (unsigned long)salt;
unsigned long adata, bdata, mask, len;
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
len = 0;
goto inside;
do {
HASH_MIX(x, y, a);
len += sizeof(unsigned long);
inside:
a = load_unaligned_zeropad(name+len);
b = a ^ REPEAT_BYTE('/');
} while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));
adata = prep_zero_mask(a, adata, &constants);
bdata = prep_zero_mask(b, bdata, &constants);
mask = create_zero_mask(adata | bdata);
x ^= a & zero_bytemask(mask);
return hashlen_create(fold_hash(x, y), len + find_zero(mask));
}
#else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */
/* Return the hash of a string of known length */
unsigned int full_name_hash(const void *salt, const char *name, unsigned int len)
{
unsigned long hash = init_name_hash(salt);
while (len--)
hash = partial_name_hash((unsigned char)*name++, hash);
return end_name_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);
/* Return the "hash_len" (hash and length) of a null-terminated string */
u64 hashlen_string(const void *salt, const char *name)
{
unsigned long hash = init_name_hash(salt);
unsigned long len = 0, c;
c = (unsigned char)*name;
while (c) {
len++;
hash = partial_name_hash(c, hash);
c = (unsigned char)name[len];
}
return hashlen_create(end_name_hash(hash), len);
}
EXPORT_SYMBOL(hashlen_string);
/*
* We know there's a real path component here of at least
* one character.
*/
static inline u64 hash_name(const void *salt, const char *name)
{
unsigned long hash = init_name_hash(salt);
unsigned long len = 0, c;
c = (unsigned char)*name;
do {
len++;
hash = partial_name_hash(c, hash);
c = (unsigned char)name[len];
} while (c && c != '/');
return hashlen_create(end_name_hash(hash), len);
}
#endif
/*
* 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)
{
int depth = 0; // depth <= nd->depth
int err;
nd->last_type = LAST_ROOT;
nd->flags |= LOOKUP_PARENT;
if (IS_ERR(name))
return PTR_ERR(name);
while (*name=='/')
name++;
if (!*name) {
nd->dir_mode = 0; // short-circuit the 'hardening' idiocy
return 0;
}
/* At this point we know we have a real path component. */
for(;;) {
struct user_namespace *mnt_userns;
const char *link;
u64 hash_len;
int type;
mnt_userns = mnt_user_ns(nd->path.mnt);
err = may_lookup(mnt_userns, nd);
if (err)
return err;
hash_len = hash_name(nd->path.dentry, name);
type = LAST_NORM;
if (name[0] == '.') switch (hashlen_len(hash_len)) {
case 2:
if (name[1] == '.') {
type = LAST_DOTDOT;
nd->state |= ND_JUMPED;
}
break;
case 1:
type = LAST_DOT;
}
if (likely(type == LAST_NORM)) {
struct dentry *parent = nd->path.dentry;
nd->state &= ~ND_JUMPED;
if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
struct qstr this = { { .hash_len = hash_len }, .name = name };
err = parent->d_op->d_hash(parent, &this);
if (err < 0)
return err;
hash_len = this.hash_len;
name = this.name;
}
}
nd->last.hash_len = hash_len;
nd->last.name = name;
nd->last_type = type;
name += hashlen_len(hash_len);
if (!*name)
goto OK;
/*
* If it wasn't NUL, we know it was '/'. Skip that
* slash, and continue until no more slashes.
*/
do {
name++;
} while (unlikely(*name == '/'));
if (unlikely(!*name)) {
OK:
/* pathname or trailing symlink, done */
if (!depth) {
nd->dir_uid = i_uid_into_mnt(mnt_userns, nd->inode);
nd->dir_mode = nd->inode->i_mode;
nd->flags &= ~LOOKUP_PARENT;
return 0;
}
/* last component of nested symlink */
name = nd->stack[--depth].name;
link = walk_component(nd, 0);
} else {
/* not the last component */
link = walk_component(nd, WALK_MORE);
}
if (unlikely(link)) {
if (IS_ERR(link))
return PTR_ERR(link);
/* a symlink to follow */
nd->stack[depth++].name = name;
name = link;
continue;
}
if (unlikely(!d_can_lookup(nd->path.dentry))) {
if (nd->flags & LOOKUP_RCU) {
if (!try_to_unlazy(nd))
return -ECHILD;
}
return -ENOTDIR;
}
}
}
/* must be paired with terminate_walk() */
static const char *path_init(struct nameidata *nd, unsigned flags)
{
int error;
const char *s = nd->name->name;
/* LOOKUP_CACHED requires RCU, ask caller to retry */
if ((flags & (LOOKUP_RCU | LOOKUP_CACHED)) == LOOKUP_CACHED)
return ERR_PTR(-EAGAIN);
if (!*s)
flags &= ~LOOKUP_RCU;
if (flags & LOOKUP_RCU)
rcu_read_lock();
else
nd->seq = nd->next_seq = 0;
nd->flags = flags;
nd->state |= ND_JUMPED;
nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount);
nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);
smp_rmb();
if (nd->state & ND_ROOT_PRESET) {
struct dentry *root = nd->root.dentry;
struct inode *inode = root->d_inode;
if (*s && unlikely(!d_can_lookup(root)))
return ERR_PTR(-ENOTDIR);
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
nd->root_seq = nd->seq;
} else {
path_get(&nd->path);
}
return s;
}
nd->root.mnt = NULL;
/* Absolute pathname -- fetch the root (LOOKUP_IN_ROOT uses nd->dfd). */
if (*s == '/' && !(flags & LOOKUP_IN_ROOT)) {
error = nd_jump_root(nd);
if (unlikely(error))
return ERR_PTR(error);
return s;
}
/* Relative pathname -- get the starting-point it is relative to. */
if (nd->dfd == AT_FDCWD) {
if (flags & LOOKUP_RCU) {
struct fs_struct *fs = current->fs;
unsigned seq;
do {
seq = read_seqcount_begin(&fs->seq);
nd->path = fs->pwd;
nd->inode = nd->path.dentry->d_inode;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
} else {
get_fs_pwd(current->fs, &nd->path);
nd->inode = nd->path.dentry->d_inode;
}
} else {
/* Caller must check execute permissions on the starting path component */
struct fd f = fdget_raw(nd->dfd);
struct dentry *dentry;
if (!f.file)
return ERR_PTR(-EBADF);
dentry = f.file->f_path.dentry;
if (*s && unlikely(!d_can_lookup(dentry))) {
fdput(f);
return ERR_PTR(-ENOTDIR);
}
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
nd->inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
} else {
path_get(&nd->path);
nd->inode = nd->path.dentry->d_inode;
}
fdput(f);
}
/* For scoped-lookups we need to set the root to the dirfd as well. */
if (flags & LOOKUP_IS_SCOPED) {
nd->root = nd->path;
if (flags & LOOKUP_RCU) {
nd->root_seq = nd->seq;
} else {
path_get(&nd->root);
nd->state |= ND_ROOT_GRABBED;
}
}
return s;
}
static inline const char *lookup_last(struct nameidata *nd)
{
if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
return walk_component(nd, WALK_TRAILING);
}
static int handle_lookup_down(struct nameidata *nd)
{
if (!(nd->flags & LOOKUP_RCU))
dget(nd->path.dentry);
nd->next_seq = nd->seq;
return PTR_ERR(step_into(nd, WALK_NOFOLLOW, nd->path.dentry));
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
const char *s = path_init(nd, flags);
int err;
if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
err = handle_lookup_down(nd);
if (unlikely(err < 0))
s = ERR_PTR(err);
}
while (!(err = link_path_walk(s, nd)) &&
(s = lookup_last(nd)) != NULL)
;
if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
err = handle_lookup_down(nd);
nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please...
}
if (!err)
err = complete_walk(nd);
if (!err && nd->flags & LOOKUP_DIRECTORY)
if (!d_can_lookup(nd->path.dentry))
err = -ENOTDIR;
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
}
terminate_walk(nd);
return err;
}
int filename_lookup(int dfd, struct filename *name, unsigned flags,
struct path *path, struct path *root)
{
int retval;
struct nameidata nd;
if (IS_ERR(name))
return PTR_ERR(name);
set_nameidata(&nd, dfd, name, root);
retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
if (unlikely(retval == -ECHILD))
retval = path_lookupat(&nd, flags, path);
if (unlikely(retval == -ESTALE))
retval = path_lookupat(&nd, flags | LOOKUP_REVAL, path);
if (likely(!retval))
audit_inode(name, path->dentry,
flags & LOOKUP_MOUNTPOINT ? AUDIT_INODE_NOEVAL : 0);
restore_nameidata();
return retval;
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_parentat(struct nameidata *nd, unsigned flags,
struct path *parent)
{
const char *s = path_init(nd, flags);
int err = link_path_walk(s, nd);
if (!err)
err = complete_walk(nd);
if (!err) {
*parent = nd->path;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
}
terminate_walk(nd);
return err;
}
/* Note: this does not consume "name" */
static int filename_parentat(int dfd, struct filename *name,
unsigned int flags, struct path *parent,
struct qstr *last, int *type)
{
int retval;
struct nameidata nd;
if (IS_ERR(name))
return PTR_ERR(name);
set_nameidata(&nd, dfd, name, NULL);
retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
if (unlikely(retval == -ECHILD))
retval = path_parentat(&nd, flags, parent);
if (unlikely(retval == -ESTALE))
retval = path_parentat(&nd, flags | LOOKUP_REVAL, parent);
if (likely(!retval)) {
*last = nd.last;
*type = nd.last_type;
audit_inode(name, parent->dentry, AUDIT_INODE_PARENT);
}
restore_nameidata();
return retval;
}
/* does lookup, returns the object with parent locked */
static struct dentry *__kern_path_locked(struct filename *name, struct path *path)
{
struct dentry *d;
struct qstr last;
int type, error;
error = filename_parentat(AT_FDCWD, name, 0, path, &last, &type);
if (error)
return ERR_PTR(error);
if (unlikely(type != LAST_NORM)) {
path_put(path);
return ERR_PTR(-EINVAL);
}
inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
d = __lookup_hash(&last, path->dentry, 0);
if (IS_ERR(d)) {
inode_unlock(path->dentry->d_inode);
path_put(path);
}
return d;
}
struct dentry *kern_path_locked(const char *name, struct path *path)
{
struct filename *filename = getname_kernel(name);
struct dentry *res = __kern_path_locked(filename, path);
putname(filename);
return res;
}
int kern_path(const char *name, unsigned int flags, struct path *path)
{
struct filename *filename = getname_kernel(name);
int ret = filename_lookup(AT_FDCWD, filename, flags, path, NULL);
putname(filename);
return ret;
}
EXPORT_SYMBOL(kern_path);
/**
* 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
* @path: pointer to struct path to fill
*/
int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
const char *name, unsigned int flags,
struct path *path)
{
struct filename *filename;
struct path root = {.mnt = mnt, .dentry = dentry};
int ret;
filename = getname_kernel(name);
/* the first argument of filename_lookup() is ignored with root */
ret = filename_lookup(AT_FDCWD, filename, flags, path, &root);
putname(filename);
return ret;
}
EXPORT_SYMBOL(vfs_path_lookup);
static int lookup_one_common(struct user_namespace *mnt_userns,
const char *name, struct dentry *base, int len,
struct qstr *this)
{
this->name = name;
this->len = len;
this->hash = full_name_hash(base, name, len);
if (!len)
return -EACCES;
if (unlikely(name[0] == '.')) {
if (len < 2 || (len == 2 && name[1] == '.'))
return -EACCES;
}
while (len--) {
unsigned int c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
return -EACCES;
}
/*
* See if the low-level filesystem might want
* to use its own hash..
*/
if (base->d_flags & DCACHE_OP_HASH) {
int err = base->d_op->d_hash(base, this);
if (err < 0)
return err;
}
return inode_permission(mnt_userns, base->d_inode, MAY_EXEC);
}
/**
* try_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
*
* Look up a dentry by name in the dcache, returning NULL if it does not
* currently exist. The function does not try to create a dentry.
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* The caller must hold base->i_mutex.
*/
struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len)
{
struct qstr this;
int err;
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
err = lookup_one_common(&init_user_ns, name, base, len, &this);
if (err)
return ERR_PTR(err);
return lookup_dcache(&this, base, 0);
}
EXPORT_SYMBOL(try_lookup_one_len);
/**
* 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.
*
* The caller must hold base->i_mutex.
*/
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
struct dentry *dentry;
struct qstr this;
int err;
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
err = lookup_one_common(&init_user_ns, name, base, len, &this);
if (err)
return ERR_PTR(err);
dentry = lookup_dcache(&this, base, 0);
return dentry ? dentry : __lookup_slow(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one_len);
/**
* lookup_one - filesystem helper to lookup single pathname component
* @mnt_userns: user namespace of the mount the lookup is performed from
* @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.
*
* The caller must hold base->i_mutex.
*/
struct dentry *lookup_one(struct user_namespace *mnt_userns, const char *name,
struct dentry *base, int len)
{
struct dentry *dentry;
struct qstr this;
int err;
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
err = lookup_one_common(mnt_userns, name, base, len, &this);
if (err)
return ERR_PTR(err);
dentry = lookup_dcache(&this, base, 0);
return dentry ? dentry : __lookup_slow(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one);
/**
* lookup_one_unlocked - filesystem helper to lookup single pathname component
* @mnt_userns: idmapping of the mount the lookup is performed from
* @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.
*
* Unlike lookup_one_len, it should be called without the parent
* i_mutex held, and will take the i_mutex itself if necessary.
*/
struct dentry *lookup_one_unlocked(struct user_namespace *mnt_userns,
const char *name, struct dentry *base,
int len)
{
struct qstr this;
int err;
struct dentry *ret;
err = lookup_one_common(mnt_userns, name, base, len, &this);
if (err)
return ERR_PTR(err);
ret = lookup_dcache(&this, base, 0);
if (!ret)
ret = lookup_slow(&this, base, 0);
return ret;
}
EXPORT_SYMBOL(lookup_one_unlocked);
/**
* lookup_one_positive_unlocked - filesystem helper to lookup single
* pathname component
* @mnt_userns: idmapping of the mount the lookup is performed from
* @name: pathname component to lookup
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns
* known positive or ERR_PTR(). This is what most of the users want.
*
* Note that pinned negative with unlocked parent _can_ become positive at any
* time, so callers of lookup_one_unlocked() need to be very careful; pinned
* positives have >d_inode stable, so this one avoids such problems.
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code.
*
* The helper should be called without i_mutex held.
*/
struct dentry *lookup_one_positive_unlocked(struct user_namespace *mnt_userns,
const char *name,
struct dentry *base, int len)
{
struct dentry *ret = lookup_one_unlocked(mnt_userns, name, base, len);
if (!IS_ERR(ret) && d_flags_negative(smp_load_acquire(&ret->d_flags))) {
dput(ret);
ret = ERR_PTR(-ENOENT);
}
return ret;
}
EXPORT_SYMBOL(lookup_one_positive_unlocked);
/**
* lookup_one_len_unlocked - 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.
*
* Unlike lookup_one_len, it should be called without the parent
* i_mutex held, and will take the i_mutex itself if necessary.
*/
struct dentry *lookup_one_len_unlocked(const char *name,
struct dentry *base, int len)
{
return lookup_one_unlocked(&init_user_ns, name, base, len);
}
EXPORT_SYMBOL(lookup_one_len_unlocked);
/*
* Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT)
* on negatives. Returns known positive or ERR_PTR(); that's what
* most of the users want. Note that pinned negative with unlocked parent
* _can_ become positive at any time, so callers of lookup_one_len_unlocked()
* need to be very careful; pinned positives have ->d_inode stable, so
* this one avoids such problems.
*/
struct dentry *lookup_positive_unlocked(const char *name,
struct dentry *base, int len)
{
return lookup_one_positive_unlocked(&init_user_ns, name, base, len);
}
EXPORT_SYMBOL(lookup_positive_unlocked);
#ifdef CONFIG_UNIX98_PTYS
int path_pts(struct path *path)
{
/* Find something mounted on "pts" in the same directory as
* the input path.
*/
struct dentry *parent = dget_parent(path->dentry);
struct dentry *child;
struct qstr this = QSTR_INIT("pts", 3);
if (unlikely(!path_connected(path->mnt, parent))) {
dput(parent);
return -ENOENT;
}
dput(path->dentry);
path->dentry = parent;
child = d_hash_and_lookup(parent, &this);
if (!child)
return -ENOENT;
path->dentry = child;
dput(parent);
follow_down(path);
return 0;
}
#endif
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
struct path *path, int *empty)
{
struct filename *filename = getname_flags(name, flags, empty);
int ret = filename_lookup(dfd, filename, flags, path, NULL);
putname(filename);
return ret;
}
EXPORT_SYMBOL(user_path_at_empty);
int __check_sticky(struct user_namespace *mnt_userns, struct inode *dir,
struct inode *inode)
{
kuid_t fsuid = current_fsuid();
if (uid_eq(i_uid_into_mnt(mnt_userns, inode), fsuid))
return 0;
if (uid_eq(i_uid_into_mnt(mnt_userns, dir), fsuid))
return 0;
return !capable_wrt_inode_uidgid(mnt_userns, inode, CAP_FOWNER);
}
EXPORT_SYMBOL(__check_sticky);
/*
* 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 the victim has an unknown uid or gid we can't change the inode.
* 8. If we were asked to remove a directory and victim isn't one - ENOTDIR.
* 9. If we were asked to remove a non-directory and victim isn't one - EISDIR.
* 10. We can't remove a root or mountpoint.
* 11. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
static int may_delete(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *victim, bool isdir)
{
struct inode *inode = d_backing_inode(victim);
int error;
if (d_is_negative(victim))
return -ENOENT;
BUG_ON(!inode);
BUG_ON(victim->d_parent->d_inode != dir);
/* Inode writeback is not safe when the uid or gid are invalid. */
if (!uid_valid(i_uid_into_mnt(mnt_userns, inode)) ||
!gid_valid(i_gid_into_mnt(mnt_userns, inode)))
return -EOVERFLOW;
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
error = inode_permission(mnt_userns, dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
return -EPERM;
if (check_sticky(mnt_userns, dir, inode) || IS_APPEND(inode) ||
IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) ||
HAS_UNMAPPED_ID(mnt_userns, inode))
return -EPERM;
if (isdir) {
if (!d_is_dir(victim))
return -ENOTDIR;
if (IS_ROOT(victim))
return -EBUSY;
} else if (d_is_dir(victim))
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 can't do it if the fs can't represent the fsuid or fsgid.
* 4. We should have write and exec permissions on dir
* 5. We can't do it if dir is immutable (done in permission())
*/
static inline int may_create(struct user_namespace *mnt_userns,
struct inode *dir, struct dentry *child)
{
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
if (!fsuidgid_has_mapping(dir->i_sb, mnt_userns))
return -EOVERFLOW;
return inode_permission(mnt_userns, 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) {
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
return NULL;
}
mutex_lock(&p1->d_sb->s_vfs_rename_mutex);
p = d_ancestor(p2, p1);
if (p) {
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
inode_lock_nested(p1->d_inode, I_MUTEX_CHILD);
return p;
}
p = d_ancestor(p1, p2);
if (p) {
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
inode_lock_nested(p2->d_inode, I_MUTEX_CHILD);
return p;
}
inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
return NULL;
}
EXPORT_SYMBOL(lock_rename);
void unlock_rename(struct dentry *p1, struct dentry *p2)
{
inode_unlock(p1->d_inode);
if (p1 != p2) {
inode_unlock(p2->d_inode);
mutex_unlock(&p1->d_sb->s_vfs_rename_mutex);
}
}
EXPORT_SYMBOL(unlock_rename);
/**
* mode_strip_umask - handle vfs umask stripping
* @dir: parent directory of the new inode
* @mode: mode of the new inode to be created in @dir
*
* Umask stripping depends on whether or not the filesystem supports POSIX
* ACLs. If the filesystem doesn't support it umask stripping is done directly
* in here. If the filesystem does support POSIX ACLs umask stripping is
* deferred until the filesystem calls posix_acl_create().
*
* Returns: mode
*/
static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode)
{
if (!IS_POSIXACL(dir))
mode &= ~current_umask();
return mode;
}
/**
* vfs_prepare_mode - prepare the mode to be used for a new inode
* @mnt_userns: user namespace of the mount the inode was found from
* @dir: parent directory of the new inode
* @mode: mode of the new inode
* @mask_perms: allowed permission by the vfs
* @type: type of file to be created
*
* This helper consolidates and enforces vfs restrictions on the @mode of a new
* object to be created.
*
* Umask stripping depends on whether the filesystem supports POSIX ACLs (see
* the kernel documentation for mode_strip_umask()). Moving umask stripping
* after setgid stripping allows the same ordering for both non-POSIX ACL and
* POSIX ACL supporting filesystems.
*
* Note that it's currently valid for @type to be 0 if a directory is created.
* Filesystems raise that flag individually and we need to check whether each
* filesystem can deal with receiving S_IFDIR from the vfs before we enforce a
* non-zero type.
*
* Returns: mode to be passed to the filesystem
*/
static inline umode_t vfs_prepare_mode(struct user_namespace *mnt_userns,
const struct inode *dir, umode_t mode,
umode_t mask_perms, umode_t type)
{
mode = mode_strip_sgid(mnt_userns, dir, mode);
mode = mode_strip_umask(dir, mode);
/*
* Apply the vfs mandated allowed permission mask and set the type of
* file to be created before we call into the filesystem.
*/
mode &= (mask_perms & ~S_IFMT);
mode |= (type & S_IFMT);
return mode;
}
/**
* vfs_create - create new file
* @mnt_userns: user namespace of the mount the inode was found from
* @dir: inode of @dentry
* @dentry: pointer to dentry of the base directory
* @mode: mode of the new file
* @want_excl: whether the file must not yet exist
*
* Create a new file.
*
* If the inode has been found through an idmapped mount the user namespace of
* the vfsmount must be passed through @mnt_userns. This function will then take
* care to map the inode according to @mnt_userns before checking permissions.
* On non-idmapped mounts or if permission checking is to be performed on the
* raw inode simply passs init_user_ns.
*/
int vfs_create(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, bool want_excl<