blob: 86fad2befb71e74ce0b0af35e92055013f0fe378 [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 <asm/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.
*/
void final_putname(struct filename *name)
{
if (name->separate) {
__putname(name->name);
kfree(name);
} else {
__putname(name);
}
}
#define EMBEDDED_NAME_MAX (PATH_MAX - sizeof(struct filename))
static struct filename *
getname_flags(const char __user *filename, int flags, int *empty)
{
struct filename *result, *err;
int len;
long max;
char *kname;
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 + sizeof(*result);
result->name = kname;
result->separate = false;
max = EMBEDDED_NAME_MAX;
recopy:
len = strncpy_from_user(kname, filename, max);
if (unlikely(len < 0)) {
err = ERR_PTR(len);
goto error;
}
/*
* 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 (len == EMBEDDED_NAME_MAX && max == EMBEDDED_NAME_MAX) {
kname = (char *)result;
result = kzalloc(sizeof(*result), GFP_KERNEL);
if (!result) {
err = ERR_PTR(-ENOMEM);
result = (struct filename *)kname;
goto error;
}
result->name = kname;
result->separate = true;
max = PATH_MAX;
goto recopy;
}
/* The empty path is special. */
if (unlikely(!len)) {
if (empty)
*empty = 1;
err = ERR_PTR(-ENOENT);
if (!(flags & LOOKUP_EMPTY))
goto error;
}
err = ERR_PTR(-ENAMETOOLONG);
if (unlikely(len >= PATH_MAX))
goto error;
result->uptr = filename;
result->aname = NULL;
audit_getname(result);
return result;
error:
final_putname(result);
return err;
}
struct filename *
getname(const char __user * filename)
{
return getname_flags(filename, 0, NULL);
}
/*
* The "getname_kernel()" interface doesn't do pathnames longer
* than EMBEDDED_NAME_MAX. Deal with it - you're a kernel user.
*/
struct filename *
getname_kernel(const char * filename)
{
struct filename *result;
char *kname;
int len;
len = strlen(filename);
if (len >= EMBEDDED_NAME_MAX)
return ERR_PTR(-ENAMETOOLONG);
result = __getname();
if (unlikely(!result))
return ERR_PTR(-ENOMEM);
kname = (char *)result + sizeof(*result);
result->name = kname;
result->uptr = NULL;
result->aname = NULL;
result->separate = false;
strlcpy(kname, filename, EMBEDDED_NAME_MAX);
return result;
}
#ifdef CONFIG_AUDITSYSCALL
void putname(struct filename *name)
{
if (unlikely(!audit_dummy_context()))
return audit_putname(name);
final_putname(name);
}
#endif
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 (acl == ACL_NOT_CACHED)
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 (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
return 0;
if (!(mask & MAY_WRITE))
if (capable_wrt_inode_uidgid(inode,
CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
}
/*
* 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;
/*
* 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;
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 vfsmount *mnt, struct inode *inode, int mask)
{
if (unlikely(!(inode->i_opflags & IOP_FASTPERM))) {
if (likely(mnt && inode->i_op->permission2))
return inode->i_op->permission2(mnt, inode, mask);
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_permission2(struct vfsmount *mnt, 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 -EACCES;
}
retval = do_inode_permission(mnt, inode, mask);
if (retval)
return retval;
retval = devcgroup_inode_permission(inode, mask);
if (retval)
return retval;
retval = security_inode_permission(inode, mask);
return retval;
}
EXPORT_SYMBOL(__inode_permission2);
int __inode_permission(struct inode *inode, int mask)
{
return __inode_permission2(NULL, 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_permission2(struct vfsmount *mnt, struct inode *inode, int mask)
{
int retval;
retval = sb_permission(inode->i_sb, inode, mask);
if (retval)
return retval;
return __inode_permission2(mnt, inode, mask);
}
EXPORT_SYMBOL(inode_permission2);
int inode_permission(struct inode *inode, int mask)
{
return inode_permission2(NULL, 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);
/**
* 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);
}
/*
* 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 rcu-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
* @dentry: child of nd->path.dentry or NULL
* Returns: 0 on success, -ECHILD on failure
*
* unlazy_walk 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 or NULL. Must be called from rcu-walk context.
*/
static int unlazy_walk(struct nameidata *nd, struct dentry *dentry)
{
struct fs_struct *fs = current->fs;
struct dentry *parent = nd->path.dentry;
BUG_ON(!(nd->flags & LOOKUP_RCU));
/*
* After legitimizing the bastards, terminate_walk()
* will do the right thing for non-RCU mode, and all our
* subsequent exit cases should rcu_read_unlock()
* before returning. Do vfsmount first; if dentry
* can't be legitimized, just set nd->path.dentry to NULL
* and rely on dput(NULL) being a no-op.
*/
if (!legitimize_mnt(nd->path.mnt, nd->m_seq))
return -ECHILD;
nd->flags &= ~LOOKUP_RCU;
if (!lockref_get_not_dead(&parent->d_lockref)) {
nd->path.dentry = NULL;
goto out;
}
/*
* For a negative lookup, the lookup sequence point is the parents
* sequence point, and it only needs to revalidate the parent dentry.
*
* For a positive lookup, 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 still valid.
*/
if (!dentry) {
if (read_seqcount_retry(&parent->d_seq, nd->seq))
goto out;
BUG_ON(nd->inode != parent->d_inode);
} else {
if (!lockref_get_not_dead(&dentry->d_lockref))
goto out;
if (read_seqcount_retry(&dentry->d_seq, nd->seq))
goto drop_dentry;
}
/*
* 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)) {
spin_lock(&fs->lock);
if (nd->root.mnt != fs->root.mnt || nd->root.dentry != fs->root.dentry)
goto unlock_and_drop_dentry;
path_get(&nd->root);
spin_unlock(&fs->lock);
}
rcu_read_unlock();
return 0;
unlock_and_drop_dentry:
spin_unlock(&fs->lock);
drop_dentry:
rcu_read_unlock();
dput(dentry);
goto drop_root_mnt;
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)
{
return dentry->d_op->d_revalidate(dentry, flags);
}
/**
* 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) {
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
if (!legitimize_mnt(nd->path.mnt, nd->m_seq)) {
rcu_read_unlock();
return -ECHILD;
}
if (unlikely(!lockref_get_not_dead(&dentry->d_lockref))) {
rcu_read_unlock();
mntput(nd->path.mnt);
return -ECHILD;
}
if (read_seqcount_retry(&dentry->d_seq, nd->seq)) {
rcu_read_unlock();
dput(dentry);
mntput(nd->path.mnt);
return -ECHILD;
}
rcu_read_unlock();
}
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;
path_put(&nd->path);
return status;
}
static __always_inline void set_root(struct nameidata *nd)
{
get_fs_root(current->fs, &nd->root);
}
static int link_path_walk(const char *, struct nameidata *);
static __always_inline unsigned set_root_rcu(struct nameidata *nd)
{
struct fs_struct *fs = current->fs;
unsigned seq, res;
do {
seq = read_seqcount_begin(&fs->seq);
nd->root = fs->root;
res = __read_seqcount_begin(&nd->root.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
return res;
}
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;
}
/*
* Helper to directly jump to a known parsed path from ->follow_link,
* caller must have taken a reference to path beforehand.
*/
void nd_jump_link(struct nameidata *nd, struct path *path)
{
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 path *link, void *cookie)
{
struct inode *inode = link->dentry->d_inode;
if (inode->i_op->put_link)
inode->i_op->put_link(link->dentry, nd, cookie);
path_put(link);
}
int sysctl_protected_symlinks __read_mostly = 0;
int sysctl_protected_hardlinks __read_mostly = 0;
/**
* may_follow_link - Check symlink following for unsafe situations
* @link: The path of the symlink
* @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 path *link, struct nameidata *nd)
{
const struct inode *inode;
const struct inode *parent;
if (!sysctl_protected_symlinks)
return 0;
/* Allowed if owner and follower match. */
inode = link->dentry->d_inode;
if (uid_eq(current_cred()->fsuid, inode->i_uid))
return 0;
/* Allowed if parent directory not sticky and world-writable. */
parent = nd->path.dentry->d_inode;
if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
return 0;
/* Allowed if parent directory and link owner match. */
if (uid_eq(parent->i_uid, inode->i_uid))
return 0;
audit_log_link_denied("follow_link", link);
path_put_conditional(link, nd);
path_put(&nd->path);
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
*
* Returns 0 if successful, -ve on error.
*/
static int may_linkat(struct path *link)
{
const struct cred *cred;
struct inode *inode;
if (!sysctl_protected_hardlinks)
return 0;
cred = current_cred();
inode = link->dentry->d_inode;
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
if (uid_eq(cred->fsuid, inode->i_uid) || safe_hardlink_source(inode) ||
capable(CAP_FOWNER))
return 0;
audit_log_link_denied("linkat", link);
return -EPERM;
}
static __always_inline int
follow_link(struct path *link, struct nameidata *nd, void **p)
{
struct dentry *dentry = link->dentry;
int error;
char *s;
BUG_ON(nd->flags & LOOKUP_RCU);
if (link->mnt == nd->path.mnt)
mntget(link->mnt);
error = -ELOOP;
if (unlikely(current->total_link_count >= 40))
goto out_put_nd_path;
cond_resched();
current->total_link_count++;
touch_atime(link);
nd_set_link(nd, NULL);
error = security_inode_follow_link(link->dentry, nd);
if (error)
goto out_put_nd_path;
nd->last_type = LAST_BIND;
*p = dentry->d_inode->i_op->follow_link(dentry, nd);
error = PTR_ERR(*p);
if (IS_ERR(*p))
goto out_put_nd_path;
error = 0;
s = nd_get_link(nd);
if (s) {
if (unlikely(IS_ERR(s))) {
path_put(&nd->path);
put_link(nd, link, *p);
return PTR_ERR(s);
}
if (*s == '/') {
if (!nd->root.mnt)
set_root(nd);
path_put(&nd->path);
nd->path = nd->root;
path_get(&nd->root);
nd->flags |= LOOKUP_JUMPED;
}
nd->inode = nd->path.dentry->d_inode;
error = link_path_walk(s, nd);
if (unlikely(error))
put_link(nd, link, *p);
}
return error;
out_put_nd_path:
*p = NULL;
path_put(&nd->path);
path_put(link);
return error;
}
static int follow_up_rcu(struct path *path)
{
struct mount *mnt = real_mount(path->mnt);
struct mount *parent;
struct dentry *mountpoint;
parent = mnt->mnt_parent;
if (&parent->mnt == path->mnt)
return 0;
mountpoint = mnt->mnt_mountpoint;
path->dentry = mountpoint;
path->mnt = &parent->mnt;
return 1;
}
/*
* 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, unsigned flags,
bool *need_mntput)
{
struct vfsmount *mnt;
int err;
if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
return -EREMOTE;
/* We don't want to mount if someone'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 (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
path->dentry->d_inode)
return -EISDIR;
current->total_link_count++;
if (current->total_link_count >= 40)
return -ELOOP;
mnt = path->dentry->d_op->d_automount(path);
if (IS_ERR(mnt)) {
/*
* The filesystem is allowed to return -EISDIR here to indicate
* it doesn't want to automount. For instance, autofs would do
* this so that its userspace daemon can mount on this dentry.
*
* However, we can only permit this if it's a terminal point in
* the path being looked up; if it wasn't then the remainder of
* the path is inaccessible and we should say so.
*/
if (PTR_ERR(mnt) == -EISDIR && (flags & LOOKUP_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, unsigned flags)
{
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->dentry, 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, flags, &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 = 0;
return ret < 0 ? ret : need_mntput;
}
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(struct dentry *dentry)
{
return (dentry->d_flags & DCACHE_MANAGE_TRANSIT) ?
dentry->d_op->d_manage(dentry, 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)
{
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->dentry)) {
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;
nd->seq = 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;
if (!nd->root.mnt)
set_root_rcu(nd);
while (1) {
if (nd->path.dentry == nd->root.dentry &&
nd->path.mnt == nd->root.mnt) {
break;
}
if (nd->path.dentry != nd->path.mnt->mnt_root) {
struct dentry *old = nd->path.dentry;
struct dentry *parent = old->d_parent;
unsigned seq;
inode = parent->d_inode;
seq = read_seqcount_begin(&parent->d_seq);
if (read_seqcount_retry(&old->d_seq, nd->seq))
goto failed;
nd->path.dentry = parent;
nd->seq = seq;
if (unlikely(!path_connected(&nd->path)))
goto failed;
break;
}
if (!follow_up_rcu(&nd->path))
break;
inode = nd->path.dentry->d_inode;
nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
}
while (d_mountpoint(nd->path.dentry)) {
struct mount *mounted;
mounted = __lookup_mnt(nd->path.mnt, nd->path.dentry);
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);
if (read_seqretry(&mount_lock, nd->m_seq))
goto failed;
}
nd->inode = inode;
return 0;
failed:
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
return -ECHILD;
}
/*
* 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->dentry, 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 follow_dotdot(struct nameidata *nd)
{
if (!nd->root.mnt)
set_root(nd);
while(1) {
struct dentry *old = nd->path.dentry;
if (nd->path.dentry == nd->root.dentry &&
nd->path.mnt == nd->root.mnt) {
break;
}
if (nd->path.dentry != nd->path.mnt->mnt_root) {
/* rare case of legitimate dget_parent()... */
nd->path.dentry = dget_parent(nd->path.dentry);
dput(old);
if (unlikely(!path_connected(&nd->path))) {
path_put(&nd->path);
return -ENOENT;
}
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, possibly revalidates the old dentry and
* allocates a new one if not found or not valid. In the need_lookup argument
* returns whether i_op->lookup is necessary.
*
* dir->d_inode->i_mutex must be held
*/
static struct dentry *lookup_dcache(struct qstr *name, struct dentry *dir,
unsigned int flags, bool *need_lookup)
{
struct dentry *dentry;
int error;
*need_lookup = false;
dentry = d_lookup(dir, name);
if (dentry) {
if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
if (error < 0) {
dput(dentry);
return ERR_PTR(error);
} else {
d_invalidate(dentry);
dput(dentry);
dentry = NULL;
}
}
}
}
if (!dentry) {
dentry = d_alloc(dir, name);
if (unlikely(!dentry))
return ERR_PTR(-ENOMEM);
*need_lookup = true;
}
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(struct qstr *name,
struct dentry *base, unsigned int flags)
{
bool need_lookup;
struct dentry *dentry;
dentry = lookup_dcache(name, base, flags, &need_lookup);
if (!need_lookup)
return dentry;
return lookup_real(base->d_inode, dentry, flags);
}
/*
* It's more convoluted than I'd like it to be, but... it's still fairly
* small and for now I'd prefer to have fast path as straight as possible.
* It _is_ time-critical.
*/
static int lookup_fast(struct nameidata *nd,
struct path *path, struct inode **inode)
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
int need_reval = 1;
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, we're going to
* do the non-racy lookup, below.
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
dentry = __d_lookup_rcu(parent, &nd->last, &seq);
if (!dentry)
goto unlazy;
/*
* This sequence count validates that the inode matches
* the dentry name information from lookup.
*/
*inode = dentry->d_inode;
if (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 (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
nd->seq = seq;
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE)) {
status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
if (status != -ECHILD)
need_reval = 0;
goto unlazy;
}
}
path->mnt = mnt;
path->dentry = dentry;
if (likely(__follow_mount_rcu(nd, path, inode)))
return 0;
unlazy:
if (unlazy_walk(nd, dentry))
return -ECHILD;
} else {
dentry = __d_lookup(parent, &nd->last);
}
if (unlikely(!dentry))
goto need_lookup;
if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE) && need_reval)
status = d_revalidate(dentry, nd->flags);
if (unlikely(status <= 0)) {
if (status < 0) {
dput(dentry);
return status;
}
d_invalidate(dentry);
dput(dentry);
goto need_lookup;
}
path->mnt = mnt;
path->dentry = dentry;
err = follow_managed(path, nd->flags);
if (unlikely(err < 0)) {
path_put_conditional(path, nd);
return err;
}
if (err)
nd->flags |= LOOKUP_JUMPED;
*inode = path->dentry->d_inode;
return 0;
need_lookup:
return 1;
}
/* Fast lookup failed, do it the slow way */
static int lookup_slow(struct nameidata *nd, struct path *path)
{
struct dentry *dentry, *parent;
int err;
parent = nd->path.dentry;
BUG_ON(nd->inode != parent->d_inode);
mutex_lock(&parent->d_inode->i_mutex);
dentry = __lookup_hash(&nd->last, parent, nd->flags);
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
path->mnt = nd->path.mnt;
path->dentry = dentry;
err = follow_managed(path, nd->flags);
if (unlikely(err < 0)) {
path_put_conditional(path, nd);
return err;
}
if (err)
nd->flags |= LOOKUP_JUMPED;
return 0;
}
static inline int may_lookup(struct nameidata *nd)
{
if (nd->flags & LOOKUP_RCU) {
int err = inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD)
return err;
if (unlazy_walk(nd, NULL))
return -ECHILD;
}
return inode_permission2(nd->path.mnt, nd->inode, MAY_EXEC);
}
static inline int handle_dots(struct nameidata *nd, int type)
{
if (type == LAST_DOTDOT) {
if (nd->flags & LOOKUP_RCU) {
if (follow_dotdot_rcu(nd))
return -ECHILD;
} else
return follow_dotdot(nd);
}
return 0;
}
static void terminate_walk(struct nameidata *nd)
{
if (!(nd->flags & LOOKUP_RCU)) {
path_put(&nd->path);
} else {
nd->flags &= ~LOOKUP_RCU;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
}
}
/*
* 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 should_follow_link(struct dentry *dentry, int follow)
{
return unlikely(d_is_symlink(dentry)) ? follow : 0;
}
static inline int walk_component(struct nameidata *nd, struct path *path,
int follow)
{
struct inode *inode;
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))
return handle_dots(nd, nd->last_type);
err = lookup_fast(nd, path, &inode);
if (unlikely(err)) {
if (err < 0)
goto out_err;
err = lookup_slow(nd, path);
if (err < 0)
goto out_err;
inode = path->dentry->d_inode;
}
err = -ENOENT;
if (!inode || d_is_negative(path->dentry))
goto out_path_put;
if (should_follow_link(path->dentry, follow)) {
if (nd->flags & LOOKUP_RCU) {
if (unlikely(nd->path.mnt != path->mnt ||
unlazy_walk(nd, path->dentry))) {
err = -ECHILD;
goto out_err;
}
}
BUG_ON(inode != path->dentry->d_inode);
return 1;
}
path_to_nameidata(path, nd);
nd->inode = inode;
return 0;
out_path_put:
path_to_nameidata(path, nd);
out_err:
terminate_walk(nd);
return err;
}
/*
* This limits recursive symlink follows to 8, while
* limiting consecutive symlinks to 40.
*
* Without that kind of total limit, nasty chains of consecutive
* symlinks can cause almost arbitrarily long lookups.
*/
static inline int nested_symlink(struct path *path, struct nameidata *nd)
{
int res;
if (unlikely(current->link_count >= MAX_NESTED_LINKS)) {
path_put_conditional(path, nd);
path_put(&nd->path);
return -ELOOP;
}
BUG_ON(nd->depth >= MAX_NESTED_LINKS);
nd->depth++;
current->link_count++;
do {
struct path link = *path;
void *cookie;
res = follow_link(&link, nd, &cookie);
if (res)
break;
res = walk_component(nd, path, LOOKUP_FOLLOW);
put_link(nd, &link, cookie);
} while (res > 0);
current->link_count--;
nd->depth--;
return res;
}
/*
* 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 CONFIG_64BIT
static inline unsigned int fold_hash(unsigned long hash)
{
return hash_64(hash, 32);
}
#else /* 32-bit case */
#define fold_hash(x) (x)
#endif
unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
unsigned long a, mask;
unsigned long hash = 0;
for (;;) {
a = load_unaligned_zeropad(name);
if (len < sizeof(unsigned long))
break;
hash += a;
hash *= 9;
name += sizeof(unsigned long);
len -= sizeof(unsigned long);
if (!len)
goto done;
}
mask = bytemask_from_count(len);
hash += mask & a;
done:
return fold_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);
/*
* Calculate the length and hash of the path component, and
* return the "hash_len" as the result.
*/
static inline u64 hash_name(const char *name)
{
unsigned long a, b, adata, bdata, mask, hash, len;
const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
hash = a = 0;
len = -sizeof(unsigned long);
do {
hash = (hash + a) * 9;
len += sizeof(unsigned long);
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);
hash += a & zero_bytemask(mask);
len += find_zero(mask);
return hashlen_create(fold_hash(hash), len);
}
#else
unsigned int full_name_hash(const unsigned char *name, unsigned int len)
{
unsigned long hash = init_name_hash();
while (len--)
hash = partial_name_hash(*name++, hash);
return end_name_hash(hash);
}
EXPORT_SYMBOL(full_name_hash);
/*
* We know there's a real path component here of at least
* one character.
*/
static inline u64 hash_name(const char *name)
{
unsigned long hash = init_name_hash();
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)
{
struct path next;
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)
break;
hash_len = hash_name(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)
break;
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)
return 0;
/*
* If it wasn't NUL, we know it was '/'. Skip that
* slash, and continue until no more slashes.
*/
do {
name++;
} while (unlikely(*name == '/'));
if (!*name)
return 0;
err = walk_component(nd, &next, LOOKUP_FOLLOW);
if (err < 0)
return err;
if (err) {
err = nested_symlink(&next, nd);
if (err)
return err;
}
if (!d_can_lookup(nd->path.dentry)) {
err = -ENOTDIR;
break;
}
}
terminate_walk(nd);
return err;
}
static int path_init(int dfd, const char *name, unsigned int flags,
struct nameidata *nd, struct file **fp)
{
int retval = 0;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED;
nd->depth = 0;
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
struct vfsmount *mnt = nd->root.mnt;
struct inode *inode = root->d_inode;
if (*name) {
if (!d_can_lookup(root))
return -ENOTDIR;
retval = inode_permission2(mnt, inode, MAY_EXEC);
if (retval)
return retval;
}
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->m_seq = read_seqbegin(&mount_lock);
} else {
path_get(&nd->path);
}
return 0;
}
nd->root.mnt = NULL;
nd->m_seq = read_seqbegin(&mount_lock);
if (*name=='/') {
if (flags & LOOKUP_RCU) {
rcu_read_lock();
nd->seq = set_root_rcu(nd);
} else {
set_root(nd);
path_get(&nd->root);
}
nd->path = nd->root;
} else if (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->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
} while (read_seqcount_retry(&fs->seq, seq));
} else {
get_fs_pwd(current->fs, &nd->path);
}
} else {
/* Caller must check execute permissions on the starting path component */
struct fd f = fdget_raw(dfd);
struct dentry *dentry;
if (!f.file)
return -EBADF;
dentry = f.file->f_path.dentry;
if (*name) {
if (!d_can_lookup(dentry)) {
fdput(f);
return -ENOTDIR;
}
}
nd->path = f.file->f_path;
if (flags & LOOKUP_RCU) {
if (f.flags & FDPUT_FPUT)
*fp = f.file;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
rcu_read_lock();
} else {
path_get(&nd->path);
fdput(f);
}
}
nd->inode = nd->path.dentry->d_inode;
if (!(flags & LOOKUP_RCU))
return 0;
if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
return 0;
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
return -ECHILD;
}
static inline int lookup_last(struct nameidata *nd, struct path *path)
{
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, path, nd->flags & LOOKUP_FOLLOW);
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(int dfd, const char *name,
unsigned int flags, struct nameidata *nd)
{
struct file *base = NULL;
struct path path;
int err;
/*
* Path walking is largely split up into 2 different synchronisation
* schemes, rcu-walk and ref-walk (explained in
* Documentation/filesystems/path-lookup.txt). These share much of the
* path walk code, but some things particularly setup, cleanup, and
* following mounts are sufficiently divergent that functions are
* duplicated. Typically there is a function foo(), and its RCU
* analogue, foo_rcu().
*
* -ECHILD is the error number of choice (just to avoid clashes) that
* is returned if some aspect of an rcu-walk fails. Such an error must
* be handled by restarting a traditional ref-walk (which will always
* be able to complete).
*/
err = path_init(dfd, name, flags | LOOKUP_PARENT, nd, &base);
if (unlikely(err))
goto out;
current->total_link_count = 0;
err = link_path_walk(name, nd);
if (!err && !(flags & LOOKUP_PARENT)) {
err = lookup_last(nd, &path);
while (err > 0) {
void *cookie;
struct path link = path;
err = may_follow_link(&link, nd);
if (unlikely(err))
break;
nd->flags |= LOOKUP_PARENT;
err = follow_link(&link, nd, &cookie);
if (err)
break;
err = lookup_last(nd, &path);
put_link(nd, &link, cookie);
}
}
if (!err)
err = complete_walk(nd);
if (!err && nd->flags & LOOKUP_DIRECTORY) {
if (!d_can_lookup(nd->path.dentry)) {
path_put(&nd->path);
err = -ENOTDIR;
}
}
out:
if (base)
fput(base);
if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
path_put(&nd->root);
nd->root.mnt = NULL;
}
return err;
}
static int filename_lookup(int dfd, struct filename *name,
unsigned int flags, struct nameidata *nd)
{
int retval = path_lookupat(dfd, name->name, flags | LOOKUP_RCU, nd);
if (unlikely(retval == -ECHILD))
retval = path_lookupat(dfd, name->name, flags, nd);
if (unlikely(retval == -ESTALE))
retval = path_lookupat(dfd, name->name,
flags | LOOKUP_REVAL, nd);
if (likely(!retval))
audit_inode(name, nd->path.dentry, flags & LOOKUP_PARENT);
return retval;
}
static int do_path_lookup(int dfd, const char *name,
unsigned int flags, struct nameidata *nd)
{
struct filename filename = { .name = name };
return filename_lookup(dfd, &filename, flags, nd);
}
/* does lookup, returns the object with parent locked */
struct dentry *kern_path_locked(const char *name, struct path *path)
{
struct nameidata nd;
struct dentry *d;
int err = do_path_lookup(AT_FDCWD, name, LOOKUP_PARENT, &nd);
if (err)
return ERR_PTR(err);
if (nd.last_type != LAST_NORM) {
path_put(&nd.path);
return ERR_PTR(-EINVAL);
}
mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
d = __lookup_hash(&nd.last, nd.path.dentry, 0);
if (IS_ERR(d)) {
mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
path_put(&nd.path);
return d;
}
*path = nd.path;
return d;
}
int kern_path(const char *name, unsigned int flags, struct path *path)
{
struct nameidata nd;
int res = do_path_lookup(AT_FDCWD, name, flags, &nd);
if (!res)
*path = nd.path;
return res;
}
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 nameidata nd;
int err;
nd.root.dentry = dentry;
nd.root.mnt = mnt;
BUG_ON(flags & LOOKUP_PARENT);
/* the first argument of do_path_lookup() is ignored with LOOKUP_ROOT */
err = do_path_lookup(AT_FDCWD, name, flags | LOOKUP_ROOT, &nd);
if (!err)
*path = nd.path;
return err;
}
EXPORT_SYMBOL(vfs_path_lookup);
/*
* Restricted form of lookup. Doesn't follow links, single-component only,
* needs parent already locked. Doesn't follow mounts.
* SMP-safe.
*/
static struct dentry *lookup_hash(struct nameidata *nd)
{
return __lookup_hash(&nd->last, nd->path.dentry, nd->flags);
}
/**
* lookup_one_len - filesystem helper to lookup single pathname component
* @name: pathname component to lookup
* @mnt: mount we are looking up on
* @base: base directory to lookup from
* @len: maximum length @len should be interpreted to
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code. Also note that by using this function the
* nameidata argument is passed to the filesystem methods and a filesystem
* using this helper needs to be prepared for that.
*/
struct dentry *lookup_one_len2(const char *name, struct vfsmount *mnt, struct dentry *base, int len)
{
struct qstr this;
unsigned int c;
int err;
WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
this.name = name;
this.len = len;
this.hash = full_name_hash(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_permission2(mnt, base->d_inode, MAY_EXEC);
if (err)
return ERR_PTR(err);
return __lookup_hash(&this, base, 0);
}
EXPORT_SYMBOL(lookup_one_len2);
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
return lookup_one_len2(name, NULL, base, len);
}
EXPORT_SYMBOL(lookup_one_len);
int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
struct path *path, int *empty)
{
struct nameidata nd;
struct filename *tmp = getname_flags(name, flags, empty);
int err = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
BUG_ON(flags & LOOKUP_PARENT);
err = filename_lookup(dfd, tmp, flags, &nd);
putname(tmp);
if (!err)
*path = nd.path;
}
return err;
}
int user_path_at(int dfd, const char __user *name, unsigned flags,
struct path *path)
{
return user_path_at_empty(dfd, name, flags, path, NULL);
}
EXPORT_SYMBOL(user_path_at);
/*
* NB: most callers don't do anything directly with the reference to the
* to struct filename, but the nd->last pointer points into the name string
* allocated by getname. So we must hold the reference to it until all
* path-walking is complete.
*/
static struct filename *
user_path_parent(int dfd, const char __user *path, struct nameidata *nd,
unsigned int flags)
{
struct filename *s = getname(path);
int error;
/* only LOOKUP_REVAL is allowed in extra flags */
flags &= LOOKUP_REVAL;
if (IS_ERR(s))
return s;
error = filename_lookup(dfd, s, flags | LOOKUP_PARENT, nd);
if (error) {
putname(s);
return ERR_PTR(error);
}
return s;
}
/**
* mountpoint_last - look up last component for umount
* @nd: pathwalk nameidata - currently pointing at parent directory of "last"
* @path: pointer to container for result
*
* 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. The nd->path reference will also be
* put in this case.
*
* 0: if we successfully resolved nd->path and found it to not to be a
* symlink that needs to be followed. "path" will also be populated.
* The nd->path reference will also be put.
*
* 1: if we successfully resolved nd->last and found it to be a symlink
* that needs to be followed. "path" will be populated with the path
* to the link, and nd->path will *not* be put.
*/
static int
mountpoint_last(struct nameidata *nd, struct path *path)
{
int error = 0;
struct dentry *dentry;
struct dentry *dir = nd->path.dentry;
/* If we're in rcuwalk, drop out of it to handle last component */
if (nd->flags & LOOKUP_RCU) {
if (unlazy_walk(nd, NULL)) {
error = -ECHILD;
goto out;
}
}
nd->flags &= ~LOOKUP_PARENT;
if (unlikely(nd->last_type != LAST_NORM)) {
error = handle_dots(nd, nd->last_type);
if (error)
return error;
dentry = dget(nd->path.dentry);
goto done;
}
mutex_lock(&dir->d_inode->i_mutex);
dentry = d_lookup(dir, &nd->last);
if (!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.
*/
dentry = d_alloc(dir, &nd->last);
if (!dentry) {
error = -ENOMEM;
mutex_unlock(&dir->d_inode->i_mutex);
goto out;
}
dentry = lookup_real(dir->d_inode, dentry, nd->flags);
error = PTR_ERR(dentry);
if (IS_ERR(dentry)) {
mutex_unlock(&dir->d_inode->i_mutex);
goto out;
}
}
mutex_unlock(&dir->d_inode->i_mutex);
done:
if (!dentry->d_inode || d_is_negative(dentry)) {
error = -ENOENT;
dput(dentry);
goto out;
}
path->dentry = dentry;
path->mnt = nd->path.mnt;
if (should_follow_link(dentry, nd->flags & LOOKUP_FOLLOW))
return 1;
mntget(path->mnt);
follow_mount(path);
error = 0;
out:
terminate_walk(nd);
return error;
}
/**
* path_mountpoint - look up a path to be umounted
* @dfd: directory file descriptor to start walk from
* @name: full pathname to walk
* @path: pointer to container for result
* @flags: lookup flags
*
* 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(int dfd, const char *name, struct path *path, unsigned int flags)
{
struct file *base = NULL;
struct nameidata nd;
int err;
err = path_init(dfd, name, flags | LOOKUP_PARENT, &nd, &base);
if (unlikely(err))
goto out;
current->total_link_count = 0;
err = link_path_walk(name, &nd);
if (err)
goto out;
err = mountpoint_last(&nd, path);
while (err > 0) {
void *cookie;
struct path link = *path;
err = may_follow_link(&link, &nd);
if (unlikely(err))
break;
nd.flags |= LOOKUP_PARENT;
err = follow_link(&link, &nd, &cookie);
if (err)
break;
err = mountpoint_last(&nd, path);
put_link(&nd, &link, cookie);
}
out:
if (base)
fput(base);
if (nd.root.mnt && !(nd.flags & LOOKUP_ROOT))
path_put(&nd.root);
return err;
}
static int
filename_mountpoint(int dfd, struct filename *s, struct path *path,
unsigned int flags)
{
int error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_RCU);
if (unlikely(error == -ECHILD))
error = path_mountpoint(dfd, s->name, path, flags);
if (unlikely(error == -ESTALE))
error = path_mountpoint(dfd, s->name, path, flags | LOOKUP_REVAL);
if (likely(!error))
audit_inode(s, path->dentry, 0);
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)
{
struct filename *s = getname(name);
int error;
if (IS_ERR(s))
return PTR_ERR(s);
error = filename_mountpoint(dfd, s, path, flags);
putname(s);
return error;
}
int
kern_path_mountpoint(int dfd, const char *name, struct path *path,
unsigned int flags)
{
struct filename s = {.name = name};
return filename_mountpoint(dfd, &s, 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 we were asked to remove a directory and victim isn't one - ENOTDIR.
* 8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
* 9. We can't remove a root or mountpoint.
* 10. We don't allow removal of NFS sillyrenamed files; it's handled by
* nfs_async_unlink().
*/
static int may_delete(struct vfsmount *mnt, struct inode *dir, struct dentry *victim, bool isdir)
{
struct inode *inode = victim->d_inode;
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_permission2(mnt, 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))
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 should have write and exec permissions on dir
* 4. We can't do it if dir is immutable (done in permission())
*/
static inline int may_create(struct vfsmount *mnt, 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;
return inode_permission2(mnt, dir, MAY_WRITE | MAY_EXEC);
}
/*
* p1 and p2 should be directories on the same fs.
*/
struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
{
struct dentry *p;
if (p1 == p2) {
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
return NULL;
}
mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
p = d_ancestor(p2, p1);
if (p) {
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
return p;
}
p = d_ancestor(p1, p2);
if (p) {
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
return p;
}
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
return NULL;
}
EXPORT_SYMBOL(lock_rename);
void unlock_rename(struct dentry *p1, struct dentry *p2)
{
mutex_unlock(&p1->d_inode->i_mutex);
if (p1 != p2) {
mutex_unlock(&p2->d_inode->i_mutex);
mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
}
}
EXPORT_SYMBOL(unlock_rename);
int vfs_create2(struct vfsmount *mnt, struct inode *dir, struct dentry *dentry,
umode_t mode, bool want_excl)
{
int error = may_create(mnt, 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_create2);
int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool want_excl)
{
return vfs_create2(NULL, dir, dentry, mode, want_excl);
}
EXPORT_SYMBOL(vfs_create);
static int may_open(struct path *path, int acc_mode, int flag)
{
struct dentry *dentry = path->dentry;
struct vfsmount *mnt = path->mnt;
struct inode *inode = dentry->d_inode;
int error;
/* O_PATH? */
if (!acc_mode)
return 0;
if (!inode)
return -ENOENT;
switch (inode->i_mode & S_IFMT) {
case S_IFLNK:
return -ELOOP;
case S_IFDIR:
if (acc_mode & MAY_WRITE)
return -EISDIR;
break;
case S_IFBLK:
case S_IFCHR:
if (path->mnt->mnt_flags & MNT_NODEV)
return -EACCES;
/*FALLTHRU*/
case S_IFIFO:
case S_IFSOCK:
flag &= ~O_TRUNC;
break;
}
error = inode_permission2(mnt, inode, acc_mode);
if (error)
return error;
/*
* An append-only file must be opened in append mode for writing.
*/
if (IS_APPEND(inode)) {
if ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
return -EPERM;
if (flag & O_TRUNC)
return -EPERM;
}
/* O_NOATIME can only be set by the owner or superuser */
if (flag & O_NOATIME && !inode_owner_or_capable(inode))
return -EPERM;
return 0;
}
static int handle_truncate(struct file *filp)
{
struct path *path = &filp->f_path;
struct inode *inode = path->dentry->d_inode;
int error = get_write_access(inode);
if (error)
return error;
/*
* Refuse to truncate files with mandatory locks held on them.
*/
error = locks_verify_locked(filp);
if (!error)
error = security_path_truncate(path);
if (!error) {
error = do_truncate2(path->mnt, 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(struct path *dir, struct dentry *dentry, umode_t mode)
{
int error = security_path_mknod(dir, dentry, mode, 0);
if (error)
return error;
error = inode_permission2(dir->mnt, 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,
bool got_write, bool need_lookup,
int *opened)
{
struct inode *dir = nd->path.dentry->d_inode;
unsigned open_flag = open_to_namei_flags(op->open_flag);
umode_t mode;
int error;
int acc_mode;
int create_error = 0;
struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
bool excl;
BUG_ON(dentry->d_inode);
/* Don't create child dentry for a dead directory. */
if (unlikely(IS_DEADDIR(dir))) {
error = -ENOENT;
goto out;
}
mode = op->mode;
if ((open_flag & O_CREAT) && !IS_POSIXACL(dir))
mode &= ~current_umask();
excl = (open_flag & (O_EXCL | O_CREAT)) == (O_EXCL | O_CREAT);
if (excl)
open_flag &= ~O_TRUNC;
/*
* Checking write permission is tricky, bacuse we don't know if we are
* going to actually need it: O_CREAT opens should work as long as the
* file exists. But checking existence breaks atomicity. The trick is
* to check access and if not granted clear O_CREAT from the flags.
*
* Another problem is returing the "right" error value (e.g. for an
* O_EXCL open we want to return EEXIST not EROFS).
*/
if (((open_flag & (O_CREAT | O_TRUNC)) ||
(open_flag & O_ACCMODE) != O_RDONLY) && unlikely(!got_write)) {
if (!(open_flag & O_CREAT)) {
/*
* No O_CREATE -> atomicity not a requirement -> fall
* back to lookup + open
*/
goto no_open;
} else if (open_flag & (O_EXCL | O_TRUNC)) {
/* Fall back and fail with the right error */
create_error = -EROFS;
goto no_open;
} else {
/* No side effects, safe to clear O_CREAT */
create_error = -EROFS;
open_flag &= ~O_CREAT;
}
}
if (open_flag & O_CREAT) {
error = may_o_create(&nd->path, dentry, mode);
if (error) {
create_error = error;
if (open_flag & O_EXCL)
goto no_open;
open_flag &= ~O_CREAT;
}
}
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_flag, mode,
opened);
if (error < 0) {
if (create_error && error == -ENOENT)
error = create_error;
goto out;
}
if (error) { /* returned 1, that is */
if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
error = -EIO;
goto out;
}
if (file->f_path.dentry) {
dput(dentry);
dentry = file->f_path.dentry;
}
if (*opened & FILE_CREATED)
fsnotify_create(dir, dentry);
if (!dentry->d_inode) {
WARN_ON(*opened & FILE_CREATED);
if (create_error) {
error = create_error;
goto out;
}
} else {
if (excl && !(*opened & FILE_CREATED)) {
error = -EEXIST;
goto out;
}
}
goto looked_up;
}
/*
* We didn't have the inode before the open, so check open permission
* here.
*/
acc_mode = op->acc_mode;
if (*opened & FILE_CREATE