blob: 6571a5f5112ed82894fdbec1c9b6dfaf557d93b1 [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/export.h>
#include <linux/kernel.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 <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(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) {
struct filename *tmp;
tmp = kmalloc(sizeof(*tmp), 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)
{
BUG_ON(name->refcnt <= 0);
if (--name->refcnt > 0)
return;
if (name->name != name->iname) {
__putname(name->name);
kfree(name);
} else
__putname(name);
}
static int check_acl(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(inode, acl, mask & ~MAY_NOT_BLOCK);
}
acl = get_acl(inode, ACL_TYPE_ACCESS);
if (IS_ERR(acl))
return PTR_ERR(acl);
if (acl) {
int error = posix_acl_permission(inode, acl, mask);
posix_acl_release(acl);
return error;
}
#endif
return -EAGAIN;
}
/*
* This does the basic permission checking
*/
static int acl_permission_check(struct inode *inode, int mask)
{
unsigned int mode = inode->i_mode;
if (likely(uid_eq(current_fsuid(), inode->i_uid)))
mode >>= 6;
else {
if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
int error = check_acl(inode, mask);
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 & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 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, ...)
*
* 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)
{
int ret;
/*
* Do the basic permission checks.
*/
ret = acl_permission_check(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(inode,
CAP_DAC_READ_SEARCH))
return 0;
if (capable_wrt_inode_uidgid(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(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(inode, CAP_DAC_OVERRIDE))
return 0;
return -EACCES;
}
EXPORT_SYMBOL(generic_permission);
/*
* 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 inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
if (likely(inode->i_op->permission))
return inode->i_op->permission(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(inode, mask);
}
/**
* __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)
*
* Check for read/write/execute permissions on an inode.
*
* When checking for MAY_APPEND, MAY_WRITE must also be set in @mask.
*
* This does not check for a read-only file system. You probably want
* inode_permission().
*/
int __inode_permission(struct inode *inode, int mask)
{
int 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(inode))
return -EACCES;
}
retval = do_inode_permission(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);
/**
* 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->s_flags & MS_RDONLY) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
return -EROFS;
}
return 0;
}
/**
* 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)
*
* 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 inode *inode, int mask)
{
int retval;
retval = sb_permission(inode->i_sb, inode, mask);
if (retval)
return retval;
return __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;
unsigned seq, m_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;
struct inode *link_inode;
unsigned root_seq;
int dfd;
};
static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
{
struct nameidata *old = current->nameidata;
p->stack = p->internal;
p->dfd = dfd;
p->name = name;
p->total_link_count = old ? old->total_link_count : 0;
p->saved = old;
current->nameidata = p;
}
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 int __nd_alloc_stack(struct nameidata *nd)
{
struct saved *p;
if (nd->flags & LOOKUP_RCU) {
p= kmalloc(MAXSYMLINKS * sizeof(struct saved),
GFP_ATOMIC);
if (unlikely(!p))
return -ECHILD;
} else {
p= kmalloc(MAXSYMLINKS * sizeof(struct saved),
GFP_KERNEL);
if (unlikely(!p))
return -ENOMEM;
}
memcpy(p, nd->internal, sizeof(nd->internal));
nd->stack = p;
return 0;
}
/**
* path_connected - Verify that a path->dentry is below path->mnt.mnt_root
* @path: nameidate to verify
*
* 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(const struct path *path)
{
struct vfsmount *mnt = path->mnt;
/* Only bind mounts can have disconnected paths */
if (mnt->mnt_root == mnt->mnt_sb->s_root)
return true;
return is_subdir(path->dentry, mnt->mnt_root);
}
static inline int nd_alloc_stack(struct nameidata *nd)
{
if (likely(nd->depth != EMBEDDED_LEVELS))
return 0;
if (likely(nd->stack != nd->internal))
return 0;
return __nd_alloc_stack(nd);
}
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 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->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
path_put(&nd->root);
nd->root.mnt = NULL;
}
} else {
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
}
nd->depth = 0;
}
/* path_put is needed afterwards regardless of success or failure */
static bool legitimize_path(struct nameidata *nd,
struct path *path, unsigned seq)
{
int res = __legitimize_mnt(path->mnt, nd->m_seq);
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 bool legitimize_links(struct nameidata *nd)
{
int i;
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;
}
/*
* 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.
*/
/**
* unlazy_walk - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* Returns: 0 on success, -ECHILD on failure
*
* unlazy_walk 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 unlazy_walk() failure and
* terminate_walk().
*/
static int unlazy_walk(struct nameidata *nd)
{
struct dentry *parent = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
nd->flags &= ~LOOKUP_RCU;
if (unlikely(!legitimize_links(nd)))
goto out2;
if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
goto out1;
if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
goto out;
}
rcu_read_unlock();
BUG_ON(nd->inode != parent->d_inode);
return 0;
out2:
nd->path.mnt = NULL;
nd->path.dentry = NULL;
out1:
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
out:
rcu_read_unlock();
return -ECHILD;
}
/**
* unlazy_child - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
* @dentry: child of nd->path.dentry
* @seq: seq number to check dentry against
* Returns: 0 on success, -ECHILD on failure
*
* unlazy_child attempts to legitimize the current nd->path, nd->root and dentry
* for ref-walk mode. @dentry must be a path found by a do_lookup call on
* @nd. Must be called from rcu-walk context.
* Nothing should touch nameidata between unlazy_child() failure and
* terminate_walk().
*/
static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq)
{
BUG_ON(!(nd->flags & LOOKUP_RCU));
nd->flags &= ~LOOKUP_RCU;
if (unlikely(!legitimize_links(nd)))
goto out2;
if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
goto out2;
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 (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) {
rcu_read_unlock();
dput(dentry);
goto drop_root_mnt;
}
/*
* Sequence counts matched. Now make sure that the root is
* still valid and get it if required.
*/
if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq))) {
rcu_read_unlock();
dput(dentry);
return -ECHILD;
}
}
rcu_read_unlock();
return 0;
out2:
nd->path.mnt = NULL;
out1:
nd->path.dentry = NULL;
out:
rcu_read_unlock();
drop_root_mnt:
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
return -ECHILD;
}
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) {
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
if (unlikely(unlazy_walk(nd)))
return -ECHILD;
}
if (likely(!(nd->flags & LOOKUP_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 void set_root(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
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);
}
}
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 int nd_jump_root(struct nameidata *nd)
{
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 (unlikely(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->flags |= LOOKUP_JUMPED;
return 0;
}
/*
* Helper to directly jump to a known parsed path from ->get_link,
* caller must have taken a reference to path beforehand.
*/
void nd_jump_link(struct path *path)
{
struct nameidata *nd = current->nameidata;
path_put(&nd->path);
nd->path = *path;
nd->inode = nd->path.dentry->d_inode;
nd->flags |= LOOKUP_JUMPED;
}
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);
}
int sysctl_protected_symlinks __read_mostly = 0;
int sysctl_protected_hardlinks __read_mostly = 0;
/**
* 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;
const struct inode *parent;
kuid_t puid;
if (!sysctl_protected_symlinks)
return 0;
/* Allowed if owner and follower match. */
inode = nd->link_inode;
if (uid_eq(current_cred()->fsuid, inode->i_uid))
return 0;
/* Allowed if parent directory not sticky and world-writable. */
parent = nd->inode;
if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
return 0;
/* Allowed if parent directory and link owner match. */
puid = parent->i_uid;
if (uid_valid(puid) && uid_eq(puid, inode->i_uid))
return 0;
if (nd->flags & LOOKUP_RCU)
return -ECHILD;
audit_log_link_denied("follow_link", &nd->stack[0].link);
return -EACCES;
}
/**
* safe_hardlink_source - Check for safe hardlink conditions
* @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 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(inode, MAY_READ | MAY_WRITE))
return false;
return true;
}
/**
* may_linkat - Check permissions for creating a hardlink
* @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
*
* Returns 0 if successful, -ve on error.
*/
static int may_linkat(struct path *link)
{
struct inode *inode;
if (!sysctl_protected_hardlinks)
return 0;
inode = link->dentry->d_inode;
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
if (inode_owner_or_capable(inode) || safe_hardlink_source(inode))
return 0;
audit_log_link_denied("linkat", link);
return -EPERM;
}
static __always_inline
const char *get_link(struct nameidata *nd)
{
struct saved *last = nd->stack + nd->depth - 1;
struct dentry *dentry = last->link.dentry;
struct inode *inode = nd->link_inode;
int error;
const char *res;
if (!(nd->flags & LOOKUP_RCU)) {
touch_atime(&last->link);
cond_resched();
} else if (atime_needs_update_rcu(&last->link, inode)) {
if (unlikely(unlazy_walk(nd)))
return ERR_PTR(-ECHILD);
touch_atime(&last->link);
}
error = security_inode_follow_link(dentry, inode,
nd->flags & LOOKUP_RCU);
if (unlikely(error))
return ERR_PTR(error);
nd->last_type = LAST_BIND;
res = 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)) {
if (unlikely(unlazy_walk(nd)))
return ERR_PTR(-ECHILD);
res = get(dentry, inode, &last->done);
}
} else {
res = get(dentry, inode, &last->done);
}
if (IS_ERR_OR_NULL(res))
return res;
}
if (*res == '/') {
if (!nd->root.mnt)
set_root(nd);
if (unlikely(nd_jump_root(nd)))
return ERR_PTR(-ECHILD);
while (unlikely(*++res == '/'))
;
}
if (!*res)
res = NULL;
return res;
}
/*
* 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);
/*
* 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, struct nameidata *nd,
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'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 (!(nd->flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
path->dentry->d_inode)
return -EISDIR;
if (path->dentry->d_sb->s_user_ns != &init_user_ns)
return -EACCES;
nd->total_link_count++;
if (nd->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 && (nd->flags & LOOKUP_PARENT))
return -EREMOTE;
return PTR_ERR(mnt);
}
if (!mnt) /* mount collision */
return 0;
if (!*need_mntput) {
/* lock_mount() may release path->mnt on error */
mntget(path->mnt);
*need_mntput = true;
}
err = finish_automount(mnt, path);
switch (err) {
case -EBUSY:
/* Someone else made a mount here whilst we were busy */
return 0;
case 0:
path_put(path);
path->mnt = mnt;
path->dentry = dget(mnt->mnt_root);
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, struct nameidata *nd)
{
struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
unsigned managed;
bool need_mntput = false;
int ret = 0;
/* 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, false);
if (ret < 0)
break;
}
/* 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 lookup_mnt() could
* get it */
}
/* Handle an automount point */
if (managed & DCACHE_NEED_AUTOMOUNT) {
ret = follow_automount(path, nd, &need_mntput);
if (ret < 0)
break;
continue;
}
/* We didn't change the current path point */
break;
}
if (need_mntput && path->mnt == mnt)
mntput(path->mnt);
if (ret == -EISDIR || !ret)
ret = 1;
if (need_mntput)
nd->flags |= LOOKUP_JUMPED;
if (unlikely(ret < 0))
path_put_conditional(path, nd);
return ret;
}
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);
static inline int managed_dentry_rcu(const struct path *path)
{
return (path->dentry->d_flags & DCACHE_MANAGE_TRANSIT) ?
path->dentry->d_op->d_manage(path, true) : 0;
}
/*
* 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 inode **inode, unsigned *seqp)
{
for (;;) {
struct mount *mounted;
/*
* Don't forget we might have a non-mountpoint managed dentry
* that wants to block transit.
*/
switch (managed_dentry_rcu(path)) {
case -ECHILD:
default:
return false;
case -EISDIR:
return true;
case 0:
break;
}
if (!d_mountpoint(path->dentry))
return !(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT);
mounted = __lookup_mnt(path->mnt, path->dentry);
if (!mounted)
break;
path->mnt = &mounted->mnt;
path->dentry = mounted->mnt.mnt_root;
nd->flags |= LOOKUP_JUMPED;
*seqp = read_seqcount_begin(&path->dentry->d_seq);
/*
* Update the inode too. We don't need to re-check the
* dentry sequence number here after this d_inode read,
* because a mount-point is always pinned.
*/
*inode = path->dentry->d_inode;
}
return !read_seqretry(&mount_lock, nd->m_seq) &&
!(path->dentry->d_flags & DCACHE_NEED_AUTOMOUNT);
}
static int follow_dotdot_rcu(struct nameidata *nd)
{
struct inode *inode = nd->inode;
while (1) {
if (path_equal(&nd->path, &nd->root))
break;
if (nd->path.dentry != nd->path.mnt->mnt_root) {
struct dentry *old = nd->path.dentry;
struct dentry *parent = old->d_parent;
unsigned seq;
inode = parent->d_inode;
seq = read_seqcount_begin(&parent->d_seq);
if (unlikely(read_seqcount_retry(&old->d_seq, nd->seq)))
return -ECHILD;
nd->path.dentry = parent;
nd->seq = seq;
if (unlikely(!path_connected(&nd->path)))
return -ENOENT;
break;
} else {
struct mount *mnt = real_mount(nd->path.mnt);
struct mount *mparent = mnt->mnt_parent;
struct dentry *mountpoint = mnt->mnt_mountpoint;
struct inode *inode2 = mountpoint->d_inode;
unsigned seq = read_seqcount_begin(&mountpoint->d_seq);
if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
return -ECHILD;
if (&mparent->mnt == nd->path.mnt)
break;
/* we know that mountpoint was pinned */
nd->path.dentry = mountpoint;
nd->path.mnt = &mparent->mnt;
inode = inode2;
nd->seq = seq;
}
}
while (unlikely(d_mountpoint(nd->path.dentry))) {
struct mount *mounted;
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
if (unlikely(read_seqretry(&mount_lock, nd->m_seq)))
return -ECHILD;
if (!mounted)
break;
nd->path.mnt = &mounted->mnt;
nd->path.dentry = mounted->mnt.mnt_root;
inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
}
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.
*/
int follow_down(struct path *path)
{
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, 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;
}
EXPORT_SYMBOL(follow_down);
/*
* 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 int path_parent_directory(struct path *path)
{
struct dentry *old = path->dentry;
/* rare case of legitimate dget_parent()... */
path->dentry = dget_parent(path->dentry);
dput(old);
if (unlikely(!path_connected(path)))
return -ENOENT;
return 0;
}
static int follow_dotdot(struct nameidata *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) {
int ret = path_parent_directory(&nd->path);
if (ret)
return ret;
break;
}
if (!follow_up(&nd->path))
break;
}
follow_mount(&nd->path);
nd->inode = nd->path.dentry->d_inode;
return 0;
}
/*
* 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;
}
/*
* Call i_op->lookup on the dentry. The dentry must be negative and
* unhashed.
*
* dir->d_inode->i_mutex must be held
*/
static struct dentry *lookup_real(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
struct dentry *old;
/* Don't create child dentry for a dead directory. */
if (unlikely(IS_DEADDIR(dir))) {
dput(dentry);
return ERR_PTR(-ENOENT);
}
old = dir->i_op->lookup(dir, dentry, flags);
if (unlikely(old)) {
dput(dentry);
dentry = old;
}
return dentry;
}
static struct dentry *__lookup_hash(const struct qstr *name,
struct dentry *base, unsigned int flags)
{
struct dentry *dentry = lookup_dcache(name, base, flags);
if (dentry)
return dentry;
dentry = d_alloc(base, name);
if (unlikely(!dentry))
return ERR_PTR(-ENOMEM);
return lookup_real(base->d_inode, dentry, flags);
}
static int lookup_fast(struct nameidata *nd,
struct path *path, struct inode **inode,
unsigned *seqp)
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
int status = 1;
int err;
/*
* 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) {
unsigned seq;
bool negative;
dentry = __d_lookup_rcu(parent, &nd->last, &seq);
if (unlikely(!dentry)) {
if (unlazy_walk(nd))
return -ECHILD;
return 0;
}
/*
* This sequence count validates that the inode matches
* the dentry name information from lookup.
*/
*inode = d_backing_inode(dentry);
negative = d_is_negative(dentry);
if (unlikely(read_seqcount_retry(&dentry->d_seq, seq)))
return -ECHILD;
/*
* This sequence count validates that the parent had no
* changes while we did the lookup of the dentry above.
*
* The memory barrier in read_seqcount_begin of child is
* enough, we can use __read_seqcount_retry here.
*/
if (unlikely(__read_seqcount_retry(&parent->d_seq, nd->seq)))
return -ECHILD;
*seqp = seq;
status = d_revalidate(dentry, nd->flags);
if (likely(status > 0)) {
/*
* Note: do negative dentry check after revalidation in
* case that drops it.
*/
if (unlikely(negative))
return -ENOENT;
path->mnt = mnt;
path->dentry = dentry;
if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
return 1;
}
if (unlazy_child(nd, dentry, seq))
return -ECHILD;
if (unlikely(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 0;
status = d_revalidate(dentry, nd->flags);
}
if (unlikely(status <= 0)) {
if (!status)
d_invalidate(dentry);
dput(dentry);
return status;
}
if (unlikely(d_is_negative(dentry))) {
dput(dentry);
return -ENOENT;
}
path->mnt = mnt;
path->dentry = dentry;
err = follow_managed(path, nd);
if (likely(err > 0))
*inode = d_backing_inode(path->dentry);
return err;
}
/* 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 = ERR_PTR(-ENOENT), *old;
struct inode *inode = dir->d_inode;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
inode_lock_shared(inode);
/* Don't go there if it's already dead */
if (unlikely(IS_DEADDIR(inode)))
goto out;
again:
dentry = d_alloc_parallel(dir, name, &wq);
if (IS_ERR(dentry))
goto out;
if (unlikely(!d_in_lookup(dentry))) {
if (!(flags & LOOKUP_NO_REVAL)) {
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;
}
}
out:
inode_unlock_shared(inode);
return dentry;
}
static inline int may_lookup(struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD)
return err;
if (unlazy_walk(nd))
return -ECHILD;
}
return inode_permission(nd->inode, MAY_EXEC);
}
static inline int handle_dots(struct nameidata *nd, int type)
{
if (type == LAST_DOTDOT) {
if (!nd->root.mnt)
set_root(nd);
if (nd->flags & LOOKUP_RCU) {
return follow_dotdot_rcu(nd);
} else
return follow_dotdot(nd);
}
return 0;
}
static int pick_link(struct nameidata *nd, struct path *link,
struct inode *inode, unsigned seq)
{
int error;
struct saved *last;
if (unlikely(nd->total_link_count++ >= MAXSYMLINKS)) {
path_to_nameidata(link, nd);
return -ELOOP;
}
if (!(nd->flags & LOOKUP_RCU)) {
if (link->mnt == nd->path.mnt)
mntget(link->mnt);
}
error = nd_alloc_stack(nd);
if (unlikely(error)) {
if (error == -ECHILD) {
if (unlikely(!legitimize_path(nd, link, seq))) {
drop_links(nd);
nd->depth = 0;
nd->flags &= ~LOOKUP_RCU;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
} else if (likely(unlazy_walk(nd)) == 0)
error = nd_alloc_stack(nd);
}
if (error) {
path_put(link);
return error;
}
}
last = nd->stack + nd->depth++;
last->link = *link;
clear_delayed_call(&last->done);
nd->link_inode = inode;
last->seq = seq;
return 1;
}
enum {WALK_FOLLOW = 1, WALK_MORE = 2};
/*
* 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.
*/
static inline int step_into(struct nameidata *nd, struct path *path,
int flags, struct inode *inode, unsigned seq)
{
if (!(flags & WALK_MORE) && nd->depth)
put_link(nd);
if (likely(!d_is_symlink(path->dentry)) ||
!(flags & WALK_FOLLOW || nd->flags & LOOKUP_FOLLOW)) {
/* not a symlink or should not follow */
path_to_nameidata(path, nd);
nd->inode = inode;
nd->seq = seq;
return 0;
}
/* make sure that d_is_symlink above matches inode */
if (nd->flags & LOOKUP_RCU) {
if (read_seqcount_retry(&path->dentry->d_seq, seq))
return -ECHILD;
}
return pick_link(nd, path, inode, seq);
}
static int walk_component(struct nameidata *nd, int flags)
{
struct path path;
struct inode *inode;
unsigned seq;
int err;
/*
* "." 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)) {
err = handle_dots(nd, nd->last_type);
if (!(flags & WALK_MORE) && nd->depth)
put_link(nd);
return err;
}
err = lookup_fast(nd, &path, &inode, &seq);
if (unlikely(err <= 0)) {
if (err < 0)
return err;
path.dentry = lookup_slow(&nd->last, nd->path.dentry,
nd->flags);
if (IS_ERR(path.dentry))
return PTR_ERR(path.dentry);
path.mnt = nd->path.mnt;
err = follow_managed(&path, nd);
if (unlikely(err < 0))
return err;
if (unlikely(d_is_negative(path.dentry))) {
path_to_nameidata(&path, nd);
return -ENOENT;
}
seq = 0; /* we are already out of RCU mode */
inode = d_backing_inode(path.dentry);
}
return step_into(nd, &path, flags, inode, seq);
}
/*
* 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 err;
while (*name=='/')
name++;
if (!*name)
return 0;
/* At this point we know we have a real path component. */
for(;;) {
u64 hash_len;
int type;
err = may_lookup(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->flags |= LOOKUP_JUMPED;
}
break;
case 1:
type = LAST_DOT;
}
if (likely(type == LAST_NORM)) {
struct dentry *parent = nd->path.dentry;
nd->flags &= ~LOOKUP_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 body, done */
if (!nd->depth)
return 0;
name = nd->stack[nd->depth - 1].name;
/* trailing symlink, done */
if (!name)
return 0;
/* last component of nested symlink */
err = walk_component(nd, WALK_FOLLOW);
} else {
/* not the last component */
err = walk_component(nd, WALK_FOLLOW | WALK_MORE);
}
if (err < 0)
return err;
if (err) {
const char *s = get_link(nd);
if (IS_ERR(s))
return PTR_ERR(s);
err = 0;
if (unlikely(!s)) {
/* jumped */
put_link(nd);
} else {
nd->stack[nd->depth - 1].name = name;
name = s;
continue;
}
}
if (unlikely(!d_can_lookup(nd->path.dentry))) {
if (nd->flags & LOOKUP_RCU) {
if (unlazy_walk(nd))
return -ECHILD;
}
return -ENOTDIR;
}
}
}
static const char *path_init(struct nameidata *nd, unsigned flags)
{
const char *s = nd->name->name;
if (!*s)
flags &= ~LOOKUP_RCU;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->depth = 0;
if (flags & LOOKUP_ROOT) {
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) {
rcu_read_lock();
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
nd->root_seq = nd->seq;
nd->m_seq = read_seqbegin(&mount_lock);
} else {
path_get(&nd->path);
}
return s;
}
nd->root.mnt = NULL;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
nd->m_seq = read_seqbegin(&mount_lock);
if (*s == '/') {
if (flags & LOOKUP_RCU)
rcu_read_lock();
set_root(nd);
if (likely(!nd_jump_root(nd)))
return s;
nd->root.mnt = NULL;
rcu_read_unlock();
return ERR_PTR(-ECHILD);
} else if (nd->dfd == AT_FDCWD) {
if (flags & LOOKUP_RCU) {
struct fs_struct *fs = current->fs;
unsigned seq;
rcu_read_lock();
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;
}
return s;
} 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) {
if (!d_can_lookup(dentry)) {
fdput(f);
return ERR_PTR(-ENOTDIR);
}
}
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
rcu_read_lock();
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);
return s;
}
}
static const char *trailing_symlink(struct nameidata *nd)
{
const char *s;
int error = may_follow_link(nd);
if (unlikely(error))
return ERR_PTR(error);
nd->flags |= LOOKUP_PARENT;
nd->stack[0].name = NULL;
s = get_link(nd);
return s ? s : "";
}
static inline int lookup_last(struct nameidata *nd)
{
if (nd->last_type == LAST_NORM && nd->last.name[nd->last.len])
nd->flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
nd->flags &= ~LOOKUP_PARENT;
return walk_component(nd, 0);
}
static int handle_lookup_down(struct nameidata *nd)
{
struct path path = nd->path;
struct inode *inode = nd->inode;
unsigned seq = nd->seq;
int err;
if (nd->flags & LOOKUP_RCU) {
/*
* don't bother with unlazy_walk on failure - we are
* at the very beginning of walk, so we lose nothing
* if we simply redo everything in non-RCU mode
*/
if (unlikely(!__follow_mount_rcu(nd, &path, &inode, &seq)))
return -ECHILD;
} else {
dget(path.dentry);
err = follow_managed(&path, nd);
if (unlikely(err < 0))
return err;
inode = d_backing_inode(path.dentry);
seq = 0;
}
path_to_nameidata(&path, nd);
nd->inode = inode;
nd->seq = seq;
return 0;
}
/* 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 (IS_ERR(s))
return PTR_ERR(s);
if (unlikely(flags & LOOKUP_DOWN)) {
err = handle_lookup_down(nd);
if (unlikely(err < 0)) {
terminate_walk(nd);
return err;
}
}
while (!(err = link_path_walk(s, nd))
&& ((err = lookup_last(nd)) > 0)) {
s = trailing_symlink(nd);
if (IS_ERR(s)) {
err = PTR_ERR(s);
break;
}
}
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;
}
static 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);
if (unlikely(root)) {
nd.root = *root;
flags |= LOOKUP_ROOT;
}
set_nameidata(&nd, dfd, name);
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_PARENT);
restore_nameidata();
putname(name);
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;
if (IS_ERR(s))
return PTR_ERR(s);
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;
}
static struct filename *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 name;
set_nameidata(&nd, dfd, name);
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, LOOKUP_PARENT);
} else {
putname(name);
name = ERR_PTR(retval);
}
restore_nameidata();
return name;
}
/* does lookup, returns the object with parent locked */
struct dentry *kern_path_locked(const char *name, struct path *path)
{
struct filename *filename;
struct dentry *d;
struct qstr last;
int type;
filename = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
&last, &type);
if (IS_ERR(filename))
return ERR_CAST(filename);
if (unlikely(type != LAST_NORM)) {
path_put(path);
putname(filename);
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);
}
putname(filename);
return d;
}
int kern_path(const char *name, unsigned int flags, struct path *path)
{
return filename_lookup(AT_FDCWD, getname_kernel(name),
flags, path, NULL);
}
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 path root = {.mnt = mnt, .dentry = dentry};
/* the first argument of filename_lookup() is ignored with root */
return filename_lookup(AT_FDCWD, getname_kernel(name),
flags , path, &root);
}
EXPORT_SYMBOL(vfs_path_lookup);
/**
* 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 qstr this;
unsigned int c;
int err;
WARN_ON_ONCE(!inode_is_locked(base->d_inode));
this.name = name;
this.len = len;
this.hash = full_name_hash(base, name, len);
if (!len)
return ERR_PTR(-EACCES);
if (unlikely(name[0] == '.')) {
if (len < 2 || (len == 2 && name[1] == '.'))
return ERR_PTR(-EACCES);
}
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
return ERR_PTR(-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_PTR(err);
}
err = inode_permission(base->d_inode, MAY_EXEC);
if (err)
return ERR_PTR(err);
return __lookup_hash(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one_len);
/**
* 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)
{
struct qstr this;
unsigned int c;
int err;
struct dentry *ret;
this.name = name;
this.len = len;
this.hash = full_name_hash(base, name, len);
if (!len)
return ERR_PTR(-EACCES);
if (unlikely(name[0] == '.')) {
if (len < 2 || (len == 2 && name[1] == '.'))
return ERR_PTR(-EACCES);
}
while (len--) {
c = *(const unsigned char *)name++;
if (c == '/' || c == '\0')
return ERR_PTR(-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_PTR(err);
}
err = inode_permission(base->d_inode, MAY_EXEC);
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_len_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 *child, *parent;
struct qstr this;
int ret;
ret = path_parent_directory(path);
if (ret)
return ret;
parent = path->dentry;
this.name = "pts";
this.len = 3;
child = d_hash_and_lookup(parent, &this);
if (!child)
return -ENOENT;
path->dentry = child;
dput(parent);
follow_mount(path);
return 0;
}
#endif
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
struct path *path, int *empty)
{
return filename_lookup(dfd, getname_flags(name, flags, empty),
flags, path, NULL);
}
EXPORT_SYMBOL(user_path_at_empty);
/**
* mountpoint_last - look up last component for umount
* @nd: pathwalk nameidata - currently pointing at parent directory of "last"
*
* This is a special lookup_last function just for umount. In this case, we
* need to resolve the path without doing any revalidation.
*
* The nameidata should be the result of doing a LOOKUP_PARENT pathwalk. Since
* mountpoints are always pinned in the dcache, their ancestors are too. Thus,
* in almost all cases, this lookup will be served out of the dcache. The only
* cases where it won't are if nd->last refers to a symlink or the path is
* bogus and it doesn't exist.
*
* Returns:
* -error: if there was an error during lookup. This includes -ENOENT if the
* lookup found a negative dentry.
*
* 0: if we successfully resolved nd->last and found it to not to be a
* symlink that needs to be followed.
*
* 1: if we successfully resolved nd->last and found it to be a symlink
* that needs to be followed.
*/
static int
mountpoint_last(struct nameidata *nd)
{
int error = 0;
struct dentry *dir = nd->path.dentry;
struct path path;
/* If we're in rcuwalk, drop out of it to handle last component */
if (nd->flags & LOOKUP_RCU) {
if (unlazy_walk(nd))
return -ECHILD;
}
nd->flags &= ~LOOKUP_PARENT;
if (unlikely(nd->last_type != LAST_NORM)) {
error = handle_dots(nd, nd->last_type);
if (error)
return error;
path.dentry = dget(nd->path.dentry);
} else {
path.dentry = d_lookup(dir, &nd->last);
if (!path.dentry) {
/*
* No cached dentry. Mounted dentries are pinned in the
* cache, so that means that this dentry is probably
* a symlink or the path doesn't actually point
* to a mounted dentry.
*/
path.dentry = lookup_slow(&nd->last, dir,
nd->flags | LOOKUP_NO_REVAL);
if (IS_ERR(path.dentry))
return PTR_ERR(path.dentry);
}
}
if (d_is_negative(path.dentry)) {
dput(path.dentry);
return -ENOENT;
}
path.mnt = nd->path.mnt;
return step_into(nd, &path, 0, d_backing_inode(path.dentry), 0);
}
/**
* path_mountpoint - look up a path to be umounted
* @nd: lookup context
* @flags: lookup flags
* @path: pointer to container for result
*
* Look up the given name, but don't attempt to revalidate the last component.
* Returns 0 and "path" will be valid on success; Returns error otherwise.
*/
static int
path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
{
const char *s = path_init(nd, flags);
int err;
if (IS_ERR(s))
return PTR_ERR(s);
while (!(err = link_path_walk(s, nd)) &&
(err = mountpoint_last(nd)) > 0) {
s = trailing_symlink(nd);
if (IS_ERR(s)) {
err = PTR_ERR(s);
break;
}
}
if (!err) {
*path = nd->path;
nd->path.mnt = NULL;
nd->path.dentry = NULL;
follow_mount(path);
}
terminate_walk(nd);
return err;
}
static int
filename_mountpoint(int dfd, struct filename *name, struct path *path,
unsigned int flags)
{
struct nameidata nd;
int error;
if (IS_ERR(name))
return PTR_ERR(name);
set_nameidata(&nd, dfd, name);
error = path_mountpoint(&nd, flags | LOOKUP_RCU, path);
if (unlikely(error == -ECHILD))
error = path_mountpoint(&nd, flags, path);
if (unlikely(error == -ESTALE))
error = path_mountpoint(&nd, flags | LOOKUP_REVAL, path);
if (likely(!error))
audit_inode(name, path->dentry, 0);
restore_nameidata();
putname(name);
return error;
}
/**
* user_path_mountpoint_at - lookup a path from userland in order to umount it
* @dfd: directory file descriptor
* @name: pathname from userland
* @flags: lookup flags
* @path: pointer to container to hold result
*
* A umount is a special case for path walking. We're not actually interested
* in the inode in this situation, and ESTALE errors can be a problem. We
* simply want track down the dentry and vfsmount attached at the mountpoint
* and avoid revalidating the last component.
*
* Returns 0 and populates "path" on success.
*/
int
user_path_mountpoint_at(int dfd, const char __user *name, unsigned int flags,
struct path *path)
{
return filename_mountpoint(dfd, getname(name), path, flags);
}
int
kern_path_mountpoint(int dfd, const char *name, struct path *path,
unsigned int flags)
{
return filename_mountpoint(dfd, getname_kernel(name), path, flags);
}
EXPORT_SYMBOL(kern_path_mountpoint);
int __check_sticky(struct inode *dir, struct inode *inode)
{
kuid_t fsuid = current_fsuid();
if (uid_eq(inode->i_uid, fsuid))
return 0;
if (uid_eq(dir->i_uid, fsuid))
return 0;
return !capable_wrt_inode_uidgid(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 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);
audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);
error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
if (error)
return error;
if (IS_APPEND(dir))
return -EPERM;
if (check_sticky(dir, inode) || IS_APPEND(inode) ||
IS_IMMUTABLE(inode) || IS_SWAPFILE(inode) || HAS_UNMAPPED_ID(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 inode *dir, struct dentry *child)
{
struct user_namespace *s_user_ns;
audit_inode_child(dir, child, AUDIT_TYPE_CHILD_CREATE);
if (child->d_inode)
return -EEXIST;
if (IS_DEADDIR(dir))
return -ENOENT;
s_user_ns = dir->i_sb->s_user_ns;
if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
!kgid_has_mapping(s_user_ns, current_fsgid()))
return -EOVERFLOW;
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) {
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);
int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool want_excl)
{
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, want_excl);
if (!error)
fsnotify_create(dir, dentry);
return error;
}
EXPORT_SYMBOL(vfs_create);
bool may_open_dev(const struct path *path)
{
return !(path->mnt->mnt_flags & MNT_NODEV) &&
!(path->mnt->mnt_sb->s_iflags & SB_I_NODEV);
}
static int may_open(const 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 (!may_open_dev(path))
return -EACCES;
/*FALLTHRU*/
case S_IFIFO:
case S_IFSOCK:
flag &= ~O_TRUNC;
break;
}
error = inode_permission(inode, MAY_OPEN | 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 && !inode_owner_or_capable(inode))
return -EPERM;
return 0;
}
static int handle_truncate(struct file *filp)
{
const 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(filp);
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;
}
static inline int open_to_namei_flags(int flag)
{
if ((flag & O_ACCMODE) == 3)
flag--;
return flag;
}
static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode)
{
struct user_namespace *s_user_ns;
int error = security_path_mknod(dir, dentry, mode, 0);
if (error)
return error;
s_user_ns = dir->dentry->d_sb->s_user_ns;
if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
!kgid_has_mapping(s_user_ns, current_fsgid()))
return -EOVERFLOW;
error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
return security_inode_create(dir->dentry->d_inode, dentry, mode);
}
/*
* Attempt to atomically look up, create and open a file from a negative
* dentry.
*
* Returns 0 if successful. The file will have been created and attached to
* @file by the filesystem calling finish_open().
*
* Returns 1 if the file was looked up only or didn't need creating. The
* caller will need to perform the open themselves. @path will have been
* updated to point to the new dentry. This may be negative.
*
* Returns an error code otherwise.
*/
static int atomic_open(struct nameidata *nd, struct dentry *dentry,
struct path *path, struct file *file,
const struct open_flags *op,
int open_flag, umode_t mode,
int *opened)
{
struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
struct inode *dir = nd->path.dentry->d_inode;
int error;
if (!(~open_flag & (O_EXCL | O_CREAT))) /* both O_EXCL and O_CREAT */
open_flag &= ~O_TRUNC;
if (nd->flags & LOOKUP_DIRECTORY)
open_flag |= O_DIRECTORY;
file->f_path.dentry = DENTRY_NOT_SET;
file->f_path.mnt = nd->path.mnt;
error = dir->i_op->atomic_open(dir, dentry, file,
open_to_namei_flags(open_flag),
mode, opened);
d_lookup_done(dentry);
if (!error) {
/*
* We didn't have the inode before the open, so check open
* permission here.
*/
int acc_mode = op->acc_mode;
if (*opened & FILE_CREATED) {
WARN_ON(!(open_flag & O_CREAT));
fsnotify_create(dir, dentry);
acc_mode = 0;
}
error = may_open(&file->f_path, acc_mode, open_flag);
if (WARN_ON(error > 0))
error = -EINVAL;
} else if (error > 0) {
if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
error = -EIO;
} else {
if (file->f_path.dentry) {
dput(dentry);
dentry = file->f_path.dentry;
}
if (*opened & FILE_CREATED)
fsnotify_create(dir, dentry);
if (unlikely(d_is_negative(dentry))) {
error = -ENOENT;
} else {
path->dentry = dentry;
path->mnt = nd->path.mnt;
return 1;
}
}
}
dput(dentry);
return error;
}
/*
* Look up and maybe create and open the last component.
*
* Must be called with i_mutex held on parent.
*
* Returns 0 if the file was successfully atomically created (if necessary) and
* opened. In this case the file will be returned attached to @file.
*
* Returns 1 if the file was not completely opened at this time, though lookups
* and creations will have been performed and the dentry returned in @path will
* be positive upon return if O_CREAT was specified. If O_CREAT wasn't
* specified then a negative dentry may be returned.
*
* An error code is returned otherwise.
*
* FILE_CREATE will be set in @*opened if the dentry was created and will be
* cleared otherwise prior to returning.
*/