2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* linux/fs/namei.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Some corrections by tytso.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname
|
|
|
|
* lookup logic.
|
|
|
|
*/
|
|
|
|
/* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/namei.h>
|
|
|
|
#include <linux/quotaops.h>
|
|
|
|
#include <linux/pagemap.h>
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:06:03 +07:00
|
|
|
#include <linux/fsnotify.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <linux/personality.h>
|
|
|
|
#include <linux/security.h>
|
|
|
|
#include <linux/syscalls.h>
|
|
|
|
#include <linux/mount.h>
|
|
|
|
#include <linux/audit.h>
|
2006-01-12 03:17:46 +07:00
|
|
|
#include <linux/capability.h>
|
2005-10-19 04:20:16 +07:00
|
|
|
#include <linux/file.h>
|
2006-01-19 08:43:53 +07:00
|
|
|
#include <linux/fcntl.h>
|
|
|
|
#include <linux/namei.h>
|
2005-04-17 05:20:36 +07:00
|
|
|
#include <asm/namei.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
|
|
|
#define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
|
|
|
|
|
|
|
|
/* [Feb-1997 T. Schoebel-Theuer]
|
|
|
|
* Fundamental changes in the pathname lookup mechanisms (namei)
|
|
|
|
* were necessary because of omirr. The reason is that omirr needs
|
|
|
|
* to know the _real_ pathname, not the user-supplied one, in case
|
|
|
|
* of symlinks (and also when transname replacements occur).
|
|
|
|
*
|
|
|
|
* The new code replaces the old recursive symlink resolution with
|
|
|
|
* an iterative one (in case of non-nested symlink chains). It does
|
|
|
|
* this with calls to <fs>_follow_link().
|
|
|
|
* As a side effect, dir_namei(), _namei() and follow_link() are now
|
|
|
|
* replaced with a single function lookup_dentry() that can handle all
|
|
|
|
* the special cases of the former code.
|
|
|
|
*
|
|
|
|
* With the new dcache, the pathname is stored at each inode, at least as
|
|
|
|
* long as the refcount of the inode is positive. As a side effect, the
|
|
|
|
* size of the dcache depends on the inode cache and thus is dynamic.
|
|
|
|
*
|
|
|
|
* [29-Apr-1998 C. Scott Ananian] Updated above description of symlink
|
|
|
|
* resolution to correspond with current state of the code.
|
|
|
|
*
|
|
|
|
* Note that the symlink resolution is not *completely* iterative.
|
|
|
|
* There is still a significant amount of tail- and mid- recursion in
|
|
|
|
* the algorithm. Also, note that <fs>_readlink() is not used in
|
|
|
|
* lookup_dentry(): lookup_dentry() on the result of <fs>_readlink()
|
|
|
|
* may return different results than <fs>_follow_link(). Many virtual
|
|
|
|
* filesystems (including /proc) exhibit this behavior.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation:
|
|
|
|
* New symlink semantics: when open() is called with flags O_CREAT | O_EXCL
|
|
|
|
* and the name already exists in form of a symlink, try to create the new
|
|
|
|
* name indicated by the symlink. The old code always complained that the
|
|
|
|
* name already exists, due to not following the symlink even if its target
|
|
|
|
* is nonexistent. The new semantics affects also mknod() and link() when
|
|
|
|
* the name is a symlink pointing to a non-existant name.
|
|
|
|
*
|
|
|
|
* I don't know which semantics is the right one, since I have no access
|
|
|
|
* to standards. But I found by trial that HP-UX 9.0 has the full "new"
|
|
|
|
* semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the
|
|
|
|
* "old" one. Personally, I think the new semantics is much more logical.
|
|
|
|
* Note that "ln old new" where "new" is a symlink pointing to a non-existing
|
|
|
|
* file does succeed in both HP-UX and SunOs, but not in Solaris
|
|
|
|
* and in the old Linux semantics.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink
|
|
|
|
* semantics. See the comments in "open_namei" and "do_link" below.
|
|
|
|
*
|
|
|
|
* [10-Sep-98 Alan Modra] Another symlink change.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks:
|
|
|
|
* inside the path - always follow.
|
|
|
|
* in the last component in creation/removal/renaming - never follow.
|
|
|
|
* if LOOKUP_FOLLOW passed - follow.
|
|
|
|
* if the pathname has trailing slashes - follow.
|
|
|
|
* otherwise - don't follow.
|
|
|
|
* (applied in that order).
|
|
|
|
*
|
|
|
|
* [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT
|
|
|
|
* restored for 2.4. This is the last surviving part of old 4.2BSD bug.
|
|
|
|
* During the 2.4 we need to fix the userland stuff depending on it -
|
|
|
|
* hopefully we will be able to get rid of that wart in 2.5. So far only
|
|
|
|
* XEmacs seems to be relying on it...
|
|
|
|
*/
|
|
|
|
/*
|
|
|
|
* [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland)
|
2006-03-23 18:00:33 +07:00
|
|
|
* implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives
|
2005-04-17 05:20:36 +07:00
|
|
|
* any extra contention...
|
|
|
|
*/
|
|
|
|
|
2007-07-19 15:48:22 +07:00
|
|
|
static int fastcall link_path_walk(const char *name, struct nameidata *nd);
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/* 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.
|
|
|
|
*/
|
2006-01-15 04:20:43 +07:00
|
|
|
static int do_getname(const char __user *filename, char *page)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int retval;
|
|
|
|
unsigned long len = PATH_MAX;
|
|
|
|
|
|
|
|
if (!segment_eq(get_fs(), KERNEL_DS)) {
|
|
|
|
if ((unsigned long) filename >= TASK_SIZE)
|
|
|
|
return -EFAULT;
|
|
|
|
if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
|
|
|
|
len = TASK_SIZE - (unsigned long) filename;
|
|
|
|
}
|
|
|
|
|
|
|
|
retval = strncpy_from_user(page, filename, len);
|
|
|
|
if (retval > 0) {
|
|
|
|
if (retval < len)
|
|
|
|
return 0;
|
|
|
|
return -ENAMETOOLONG;
|
|
|
|
} else if (!retval)
|
|
|
|
retval = -ENOENT;
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
char * getname(const char __user * filename)
|
|
|
|
{
|
|
|
|
char *tmp, *result;
|
|
|
|
|
|
|
|
result = ERR_PTR(-ENOMEM);
|
|
|
|
tmp = __getname();
|
|
|
|
if (tmp) {
|
|
|
|
int retval = do_getname(filename, tmp);
|
|
|
|
|
|
|
|
result = tmp;
|
|
|
|
if (retval < 0) {
|
|
|
|
__putname(tmp);
|
|
|
|
result = ERR_PTR(retval);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
audit_getname(result);
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_AUDITSYSCALL
|
|
|
|
void putname(const char *name)
|
|
|
|
{
|
2006-07-16 17:38:45 +07:00
|
|
|
if (unlikely(!audit_dummy_context()))
|
2005-04-17 05:20:36 +07:00
|
|
|
audit_putname(name);
|
|
|
|
else
|
|
|
|
__putname(name);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(putname);
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
* generic_permission - check for access rights on a Posix-like filesystem
|
|
|
|
* @inode: inode to check access rights for
|
|
|
|
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
|
|
|
|
* @check_acl: optional callback to check for Posix ACLs
|
|
|
|
*
|
|
|
|
* 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..
|
|
|
|
*/
|
|
|
|
int generic_permission(struct inode *inode, int mask,
|
|
|
|
int (*check_acl)(struct inode *inode, int mask))
|
|
|
|
{
|
|
|
|
umode_t mode = inode->i_mode;
|
|
|
|
|
|
|
|
if (current->fsuid == inode->i_uid)
|
|
|
|
mode >>= 6;
|
|
|
|
else {
|
|
|
|
if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) {
|
|
|
|
int error = check_acl(inode, mask);
|
|
|
|
if (error == -EACCES)
|
|
|
|
goto check_capabilities;
|
|
|
|
else 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 (((mode & mask & (MAY_READ|MAY_WRITE|MAY_EXEC)) == mask))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
check_capabilities:
|
|
|
|
/*
|
|
|
|
* Read/write DACs are always overridable.
|
|
|
|
* Executable DACs are overridable if at least one exec bit is set.
|
|
|
|
*/
|
|
|
|
if (!(mask & MAY_EXEC) ||
|
|
|
|
(inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
|
|
|
|
if (capable(CAP_DAC_OVERRIDE))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Searching includes executable on directories, else just read.
|
|
|
|
*/
|
|
|
|
if (mask == MAY_READ || (S_ISDIR(inode->i_mode) && !(mask & MAY_WRITE)))
|
|
|
|
if (capable(CAP_DAC_READ_SEARCH))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
return -EACCES;
|
|
|
|
}
|
|
|
|
|
|
|
|
int permission(struct inode *inode, int mask, struct nameidata *nd)
|
|
|
|
{
|
2006-08-23 07:06:03 +07:00
|
|
|
umode_t mode = inode->i_mode;
|
2005-04-17 05:20:36 +07:00
|
|
|
int retval, submask;
|
|
|
|
|
|
|
|
if (mask & MAY_WRITE) {
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Nobody gets write access to a read-only fs.
|
|
|
|
*/
|
|
|
|
if (IS_RDONLY(inode) &&
|
|
|
|
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)))
|
|
|
|
return -EROFS;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Nobody gets write access to an immutable file.
|
|
|
|
*/
|
|
|
|
if (IS_IMMUTABLE(inode))
|
|
|
|
return -EACCES;
|
|
|
|
}
|
|
|
|
|
|
|
|
|
2006-08-23 07:06:03 +07:00
|
|
|
/*
|
|
|
|
* MAY_EXEC on regular files requires special handling: We override
|
2006-12-07 11:35:25 +07:00
|
|
|
* filesystem execute permissions if the mode bits aren't set or
|
|
|
|
* the fs is mounted with the "noexec" flag.
|
2006-08-23 07:06:03 +07:00
|
|
|
*/
|
2006-12-07 11:35:25 +07:00
|
|
|
if ((mask & MAY_EXEC) && S_ISREG(mode) && (!(mode & S_IXUGO) ||
|
|
|
|
(nd && nd->mnt && (nd->mnt->mnt_flags & MNT_NOEXEC))))
|
2006-08-23 07:06:03 +07:00
|
|
|
return -EACCES;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/* Ordinary permission routines do not understand MAY_APPEND. */
|
|
|
|
submask = mask & ~MAY_APPEND;
|
|
|
|
if (inode->i_op && inode->i_op->permission)
|
|
|
|
retval = inode->i_op->permission(inode, submask, nd);
|
|
|
|
else
|
|
|
|
retval = generic_permission(inode, submask, NULL);
|
|
|
|
if (retval)
|
|
|
|
return retval;
|
|
|
|
|
|
|
|
return security_inode_permission(inode, mask, nd);
|
|
|
|
}
|
|
|
|
|
2005-11-09 12:35:04 +07:00
|
|
|
/**
|
|
|
|
* vfs_permission - check for access rights to a given path
|
|
|
|
* @nd: lookup result that describes the path
|
|
|
|
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
|
|
|
|
*
|
|
|
|
* Used to check for read/write/execute permissions on a path.
|
|
|
|
* We use "fsuid" for this, letting us set arbitrary permissions
|
|
|
|
* for filesystem access without changing the "normal" uids which
|
|
|
|
* are used for other things.
|
|
|
|
*/
|
|
|
|
int vfs_permission(struct nameidata *nd, int mask)
|
|
|
|
{
|
|
|
|
return permission(nd->dentry->d_inode, mask, nd);
|
|
|
|
}
|
|
|
|
|
2005-11-09 12:35:04 +07:00
|
|
|
/**
|
|
|
|
* file_permission - check for additional access rights to a given file
|
|
|
|
* @file: file to check access rights for
|
|
|
|
* @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC)
|
|
|
|
*
|
|
|
|
* Used to check for read/write/execute permissions on an already opened
|
|
|
|
* file.
|
|
|
|
*
|
|
|
|
* Note:
|
|
|
|
* Do not use this function in new code. All access checks should
|
|
|
|
* be done using vfs_permission().
|
|
|
|
*/
|
|
|
|
int file_permission(struct file *file, int mask)
|
|
|
|
{
|
2006-12-08 17:36:35 +07:00
|
|
|
return permission(file->f_path.dentry->d_inode, mask, NULL);
|
2005-11-09 12:35:04 +07:00
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* get_write_access() gets write permission for a file.
|
|
|
|
* put_write_access() releases this write permission.
|
|
|
|
* This is used for regular files.
|
|
|
|
* We cannot support write (and maybe mmap read-write shared) accesses and
|
|
|
|
* MAP_DENYWRITE mmappings simultaneously. The i_writecount field of an inode
|
|
|
|
* can have the following values:
|
|
|
|
* 0: no writers, no VM_DENYWRITE mappings
|
|
|
|
* < 0: (-i_writecount) vm_area_structs with VM_DENYWRITE set exist
|
|
|
|
* > 0: (i_writecount) users are writing to the file.
|
|
|
|
*
|
|
|
|
* Normally we operate on that counter with atomic_{inc,dec} and it's safe
|
|
|
|
* except for the cases where we don't hold i_writecount yet. Then we need to
|
|
|
|
* use {get,deny}_write_access() - these functions check the sign and refuse
|
|
|
|
* to do the change if sign is wrong. Exclusion between them is provided by
|
|
|
|
* the inode->i_lock spinlock.
|
|
|
|
*/
|
|
|
|
|
|
|
|
int get_write_access(struct inode * inode)
|
|
|
|
{
|
|
|
|
spin_lock(&inode->i_lock);
|
|
|
|
if (atomic_read(&inode->i_writecount) < 0) {
|
|
|
|
spin_unlock(&inode->i_lock);
|
|
|
|
return -ETXTBSY;
|
|
|
|
}
|
|
|
|
atomic_inc(&inode->i_writecount);
|
|
|
|
spin_unlock(&inode->i_lock);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
int deny_write_access(struct file * file)
|
|
|
|
{
|
2006-12-08 17:36:35 +07:00
|
|
|
struct inode *inode = file->f_path.dentry->d_inode;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
spin_lock(&inode->i_lock);
|
|
|
|
if (atomic_read(&inode->i_writecount) > 0) {
|
|
|
|
spin_unlock(&inode->i_lock);
|
|
|
|
return -ETXTBSY;
|
|
|
|
}
|
|
|
|
atomic_dec(&inode->i_writecount);
|
|
|
|
spin_unlock(&inode->i_lock);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void path_release(struct nameidata *nd)
|
|
|
|
{
|
|
|
|
dput(nd->dentry);
|
|
|
|
mntput(nd->mnt);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* umount() mustn't call path_release()/mntput() as that would clear
|
|
|
|
* mnt_expiry_mark
|
|
|
|
*/
|
|
|
|
void path_release_on_umount(struct nameidata *nd)
|
|
|
|
{
|
|
|
|
dput(nd->dentry);
|
2005-07-08 07:57:30 +07:00
|
|
|
mntput_no_expire(nd->mnt);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
2005-10-19 04:20:16 +07:00
|
|
|
/**
|
|
|
|
* release_open_intent - free up open intent resources
|
|
|
|
* @nd: pointer to nameidata
|
|
|
|
*/
|
|
|
|
void release_open_intent(struct nameidata *nd)
|
|
|
|
{
|
2006-12-08 17:36:35 +07:00
|
|
|
if (nd->intent.open.file->f_path.dentry == NULL)
|
2005-10-19 04:20:16 +07:00
|
|
|
put_filp(nd->intent.open.file);
|
|
|
|
else
|
|
|
|
fput(nd->intent.open.file);
|
|
|
|
}
|
|
|
|
|
2006-09-27 15:50:44 +07:00
|
|
|
static inline struct dentry *
|
|
|
|
do_revalidate(struct dentry *dentry, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
int status = dentry->d_op->d_revalidate(dentry, nd);
|
|
|
|
if (unlikely(status <= 0)) {
|
|
|
|
/*
|
|
|
|
* The dentry failed validation.
|
|
|
|
* If d_revalidate returned 0 attempt to invalidate
|
|
|
|
* the dentry otherwise d_revalidate is asking us
|
|
|
|
* to return a fail status.
|
|
|
|
*/
|
|
|
|
if (!status) {
|
|
|
|
if (!d_invalidate(dentry)) {
|
|
|
|
dput(dentry);
|
|
|
|
dentry = NULL;
|
|
|
|
}
|
|
|
|
} else {
|
|
|
|
dput(dentry);
|
|
|
|
dentry = ERR_PTR(status);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return dentry;
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* Internal lookup() using the new generic dcache.
|
|
|
|
* SMP-safe
|
|
|
|
*/
|
|
|
|
static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
struct dentry * dentry = __d_lookup(parent, name);
|
|
|
|
|
|
|
|
/* lockess __d_lookup may fail due to concurrent d_move()
|
|
|
|
* in some unrelated directory, so try with d_lookup
|
|
|
|
*/
|
|
|
|
if (!dentry)
|
|
|
|
dentry = d_lookup(parent, name);
|
|
|
|
|
2006-09-27 15:50:44 +07:00
|
|
|
if (dentry && dentry->d_op && dentry->d_op->d_revalidate)
|
|
|
|
dentry = do_revalidate(dentry, nd);
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
return dentry;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Short-cut version of permission(), for calling by
|
|
|
|
* path_walk(), when dcache lock is held. Combines parts
|
|
|
|
* of permission() and generic_permission(), and tests ONLY for
|
|
|
|
* MAY_EXEC permission.
|
|
|
|
*
|
|
|
|
* If appropriate, check DAC only. If not appropriate, or
|
|
|
|
* short-cut DAC fails, then call permission() to do more
|
|
|
|
* complete permission check.
|
|
|
|
*/
|
2006-01-15 04:20:43 +07:00
|
|
|
static int exec_permission_lite(struct inode *inode,
|
2005-04-17 05:20:36 +07:00
|
|
|
struct nameidata *nd)
|
|
|
|
{
|
|
|
|
umode_t mode = inode->i_mode;
|
|
|
|
|
|
|
|
if (inode->i_op && inode->i_op->permission)
|
|
|
|
return -EAGAIN;
|
|
|
|
|
|
|
|
if (current->fsuid == inode->i_uid)
|
|
|
|
mode >>= 6;
|
|
|
|
else if (in_group_p(inode->i_gid))
|
|
|
|
mode >>= 3;
|
|
|
|
|
|
|
|
if (mode & MAY_EXEC)
|
|
|
|
goto ok;
|
|
|
|
|
|
|
|
if ((inode->i_mode & S_IXUGO) && capable(CAP_DAC_OVERRIDE))
|
|
|
|
goto ok;
|
|
|
|
|
|
|
|
if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_OVERRIDE))
|
|
|
|
goto ok;
|
|
|
|
|
|
|
|
if (S_ISDIR(inode->i_mode) && capable(CAP_DAC_READ_SEARCH))
|
|
|
|
goto ok;
|
|
|
|
|
|
|
|
return -EACCES;
|
|
|
|
ok:
|
|
|
|
return security_inode_permission(inode, MAY_EXEC, nd);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is called when everything else fails, and we actually have
|
|
|
|
* to go to the low-level filesystem to find out what we should do..
|
|
|
|
*
|
|
|
|
* We get the directory semaphore, and after getting that we also
|
|
|
|
* make sure that nobody added the entry to the dcache in the meantime..
|
|
|
|
* SMP-safe
|
|
|
|
*/
|
|
|
|
static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
struct dentry * result;
|
|
|
|
struct inode *dir = parent->d_inode;
|
|
|
|
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&dir->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* First re-do the cached lookup just in case it was created
|
|
|
|
* while we waited for the directory semaphore..
|
|
|
|
*
|
|
|
|
* FIXME! This could use version numbering or similar to
|
|
|
|
* avoid unnecessary cache lookups.
|
|
|
|
*
|
|
|
|
* The "dcache_lock" is purely to protect the RCU list walker
|
|
|
|
* from concurrent renames at this point (we mustn't get false
|
|
|
|
* negatives from the RCU list walk here, unlike the optimistic
|
|
|
|
* fast walk).
|
|
|
|
*
|
|
|
|
* so doing d_lookup() (with seqlock), instead of lockfree __d_lookup
|
|
|
|
*/
|
|
|
|
result = d_lookup(parent, name);
|
|
|
|
if (!result) {
|
|
|
|
struct dentry * dentry = d_alloc(parent, name);
|
|
|
|
result = ERR_PTR(-ENOMEM);
|
|
|
|
if (dentry) {
|
|
|
|
result = dir->i_op->lookup(dir, dentry, nd);
|
|
|
|
if (result)
|
|
|
|
dput(dentry);
|
|
|
|
else
|
|
|
|
result = dentry;
|
|
|
|
}
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&dir->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Uhhuh! Nasty case: the cache was re-populated while
|
|
|
|
* we waited on the semaphore. Need to revalidate.
|
|
|
|
*/
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&dir->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (result->d_op && result->d_op->d_revalidate) {
|
2006-09-27 15:50:44 +07:00
|
|
|
result = do_revalidate(result, nd);
|
|
|
|
if (!result)
|
2005-04-17 05:20:36 +07:00
|
|
|
result = ERR_PTR(-ENOENT);
|
|
|
|
}
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __emul_lookup_dentry(const char *, struct nameidata *);
|
|
|
|
|
|
|
|
/* SMP-safe */
|
2006-01-15 04:21:31 +07:00
|
|
|
static __always_inline int
|
2005-04-17 05:20:36 +07:00
|
|
|
walk_init_root(const char *name, struct nameidata *nd)
|
|
|
|
{
|
2006-09-29 16:01:22 +07:00
|
|
|
struct fs_struct *fs = current->fs;
|
|
|
|
|
|
|
|
read_lock(&fs->lock);
|
|
|
|
if (fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
|
|
|
|
nd->mnt = mntget(fs->altrootmnt);
|
|
|
|
nd->dentry = dget(fs->altroot);
|
|
|
|
read_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (__emul_lookup_dentry(name,nd))
|
|
|
|
return 0;
|
2006-09-29 16:01:22 +07:00
|
|
|
read_lock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2006-09-29 16:01:22 +07:00
|
|
|
nd->mnt = mntget(fs->rootmnt);
|
|
|
|
nd->dentry = dget(fs->root);
|
|
|
|
read_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2006-01-15 04:21:31 +07:00
|
|
|
static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int res = 0;
|
|
|
|
char *name;
|
|
|
|
if (IS_ERR(link))
|
|
|
|
goto fail;
|
|
|
|
|
|
|
|
if (*link == '/') {
|
|
|
|
path_release(nd);
|
|
|
|
if (!walk_init_root(link, nd))
|
|
|
|
/* weird __emul_prefix() stuff did it */
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
res = link_path_walk(link, nd);
|
|
|
|
out:
|
|
|
|
if (nd->depth || res || nd->last_type!=LAST_NORM)
|
|
|
|
return res;
|
|
|
|
/*
|
|
|
|
* If it is an iterative symlinks resolution in open_namei() we
|
|
|
|
* have to copy the last component. And all that crap because of
|
|
|
|
* bloody create() on broken symlinks. Furrfu...
|
|
|
|
*/
|
|
|
|
name = __getname();
|
|
|
|
if (unlikely(!name)) {
|
|
|
|
path_release(nd);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
strcpy(name, nd->last.name);
|
|
|
|
nd->last.name = name;
|
|
|
|
return 0;
|
|
|
|
fail:
|
|
|
|
path_release(nd);
|
|
|
|
return PTR_ERR(link);
|
|
|
|
}
|
|
|
|
|
2006-03-27 16:14:53 +07:00
|
|
|
static inline void dput_path(struct path *path, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
dput(path->dentry);
|
|
|
|
if (path->mnt != nd->mnt)
|
|
|
|
mntput(path->mnt);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void path_to_nameidata(struct path *path, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
dput(nd->dentry);
|
|
|
|
if (nd->mnt != path->mnt)
|
|
|
|
mntput(nd->mnt);
|
|
|
|
nd->mnt = path->mnt;
|
|
|
|
nd->dentry = path->dentry;
|
|
|
|
}
|
|
|
|
|
2006-01-15 04:21:31 +07:00
|
|
|
static __always_inline int __do_follow_link(struct path *path, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error;
|
2005-08-20 08:02:56 +07:00
|
|
|
void *cookie;
|
2005-06-07 03:36:03 +07:00
|
|
|
struct dentry *dentry = path->dentry;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2005-06-07 03:36:14 +07:00
|
|
|
touch_atime(path->mnt, dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
nd_set_link(nd, NULL);
|
2005-06-07 03:36:03 +07:00
|
|
|
|
2006-03-27 16:14:53 +07:00
|
|
|
if (path->mnt != nd->mnt) {
|
|
|
|
path_to_nameidata(path, nd);
|
|
|
|
dget(dentry);
|
|
|
|
}
|
|
|
|
mntget(path->mnt);
|
2005-08-20 08:02:56 +07:00
|
|
|
cookie = dentry->d_inode->i_op->follow_link(dentry, nd);
|
|
|
|
error = PTR_ERR(cookie);
|
|
|
|
if (!IS_ERR(cookie)) {
|
2005-04-17 05:20:36 +07:00
|
|
|
char *s = nd_get_link(nd);
|
2005-08-20 08:02:56 +07:00
|
|
|
error = 0;
|
2005-04-17 05:20:36 +07:00
|
|
|
if (s)
|
|
|
|
error = __vfs_follow_link(nd, s);
|
|
|
|
if (dentry->d_inode->i_op->put_link)
|
2005-08-20 08:02:56 +07:00
|
|
|
dentry->d_inode->i_op->put_link(dentry, nd, cookie);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2005-06-07 03:36:03 +07:00
|
|
|
dput(dentry);
|
|
|
|
mntput(path->mnt);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This limits recursive symlink follows to 8, while
|
|
|
|
* limiting consecutive symlinks to 40.
|
|
|
|
*
|
|
|
|
* Without that kind of total limit, nasty chains of consecutive
|
|
|
|
* symlinks can cause almost arbitrarily long lookups.
|
|
|
|
*/
|
2005-06-07 03:35:58 +07:00
|
|
|
static inline int do_follow_link(struct path *path, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int err = -ELOOP;
|
|
|
|
if (current->link_count >= MAX_NESTED_LINKS)
|
|
|
|
goto loop;
|
|
|
|
if (current->total_link_count >= 40)
|
|
|
|
goto loop;
|
|
|
|
BUG_ON(nd->depth >= MAX_NESTED_LINKS);
|
|
|
|
cond_resched();
|
2005-06-07 03:35:58 +07:00
|
|
|
err = security_inode_follow_link(path->dentry, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err)
|
|
|
|
goto loop;
|
|
|
|
current->link_count++;
|
|
|
|
current->total_link_count++;
|
|
|
|
nd->depth++;
|
2005-06-07 03:36:03 +07:00
|
|
|
err = __do_follow_link(path, nd);
|
2005-06-07 03:36:02 +07:00
|
|
|
current->link_count--;
|
|
|
|
nd->depth--;
|
2005-04-17 05:20:36 +07:00
|
|
|
return err;
|
|
|
|
loop:
|
2005-09-07 05:18:21 +07:00
|
|
|
dput_path(path, nd);
|
2005-06-07 03:36:02 +07:00
|
|
|
path_release(nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
int follow_up(struct vfsmount **mnt, struct dentry **dentry)
|
|
|
|
{
|
|
|
|
struct vfsmount *parent;
|
|
|
|
struct dentry *mountpoint;
|
|
|
|
spin_lock(&vfsmount_lock);
|
|
|
|
parent=(*mnt)->mnt_parent;
|
|
|
|
if (parent == *mnt) {
|
|
|
|
spin_unlock(&vfsmount_lock);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
mntget(parent);
|
|
|
|
mountpoint=dget((*mnt)->mnt_mountpoint);
|
|
|
|
spin_unlock(&vfsmount_lock);
|
|
|
|
dput(*dentry);
|
|
|
|
*dentry = mountpoint;
|
|
|
|
mntput(*mnt);
|
|
|
|
*mnt = parent;
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* no need for dcache_lock, as serialization is taken care in
|
|
|
|
* namespace.c
|
|
|
|
*/
|
2005-06-07 03:36:05 +07:00
|
|
|
static int __follow_mount(struct path *path)
|
|
|
|
{
|
|
|
|
int res = 0;
|
|
|
|
while (d_mountpoint(path->dentry)) {
|
|
|
|
struct vfsmount *mounted = lookup_mnt(path->mnt, path->dentry);
|
|
|
|
if (!mounted)
|
|
|
|
break;
|
|
|
|
dput(path->dentry);
|
|
|
|
if (res)
|
|
|
|
mntput(path->mnt);
|
|
|
|
path->mnt = mounted;
|
|
|
|
path->dentry = dget(mounted->mnt_root);
|
|
|
|
res = 1;
|
|
|
|
}
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
2005-06-07 03:36:13 +07:00
|
|
|
static void follow_mount(struct vfsmount **mnt, struct dentry **dentry)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
while (d_mountpoint(*dentry)) {
|
|
|
|
struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
|
|
|
|
if (!mounted)
|
|
|
|
break;
|
2005-06-07 03:36:13 +07:00
|
|
|
dput(*dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
mntput(*mnt);
|
|
|
|
*mnt = mounted;
|
|
|
|
*dentry = dget(mounted->mnt_root);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* no need for dcache_lock, as serialization is taken care in
|
|
|
|
* namespace.c
|
|
|
|
*/
|
2005-06-07 03:36:06 +07:00
|
|
|
int follow_down(struct vfsmount **mnt, struct dentry **dentry)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
struct vfsmount *mounted;
|
|
|
|
|
|
|
|
mounted = lookup_mnt(*mnt, *dentry);
|
|
|
|
if (mounted) {
|
2005-06-07 03:36:06 +07:00
|
|
|
dput(*dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
mntput(*mnt);
|
|
|
|
*mnt = mounted;
|
|
|
|
*dentry = dget(mounted->mnt_root);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-01-15 04:21:31 +07:00
|
|
|
static __always_inline void follow_dotdot(struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2006-09-29 16:01:22 +07:00
|
|
|
struct fs_struct *fs = current->fs;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
while(1) {
|
|
|
|
struct vfsmount *parent;
|
2005-06-07 03:36:13 +07:00
|
|
|
struct dentry *old = nd->dentry;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2006-09-29 16:01:22 +07:00
|
|
|
read_lock(&fs->lock);
|
|
|
|
if (nd->dentry == fs->root &&
|
|
|
|
nd->mnt == fs->rootmnt) {
|
|
|
|
read_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
break;
|
|
|
|
}
|
2006-09-29 16:01:22 +07:00
|
|
|
read_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
spin_lock(&dcache_lock);
|
2005-06-07 03:36:13 +07:00
|
|
|
if (nd->dentry != nd->mnt->mnt_root) {
|
|
|
|
nd->dentry = dget(nd->dentry->d_parent);
|
2005-04-17 05:20:36 +07:00
|
|
|
spin_unlock(&dcache_lock);
|
|
|
|
dput(old);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
spin_unlock(&dcache_lock);
|
|
|
|
spin_lock(&vfsmount_lock);
|
2005-06-07 03:36:13 +07:00
|
|
|
parent = nd->mnt->mnt_parent;
|
|
|
|
if (parent == nd->mnt) {
|
2005-04-17 05:20:36 +07:00
|
|
|
spin_unlock(&vfsmount_lock);
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
mntget(parent);
|
2005-06-07 03:36:13 +07:00
|
|
|
nd->dentry = dget(nd->mnt->mnt_mountpoint);
|
2005-04-17 05:20:36 +07:00
|
|
|
spin_unlock(&vfsmount_lock);
|
|
|
|
dput(old);
|
2005-06-07 03:36:13 +07:00
|
|
|
mntput(nd->mnt);
|
|
|
|
nd->mnt = parent;
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2005-06-07 03:36:13 +07:00
|
|
|
follow_mount(&nd->mnt, &nd->dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* It's more convoluted than I'd like it to be, but... it's still fairly
|
|
|
|
* small and for now I'd prefer to have fast path as straight as possible.
|
|
|
|
* It _is_ time-critical.
|
|
|
|
*/
|
|
|
|
static int do_lookup(struct nameidata *nd, struct qstr *name,
|
|
|
|
struct path *path)
|
|
|
|
{
|
|
|
|
struct vfsmount *mnt = nd->mnt;
|
|
|
|
struct dentry *dentry = __d_lookup(nd->dentry, name);
|
|
|
|
|
|
|
|
if (!dentry)
|
|
|
|
goto need_lookup;
|
|
|
|
if (dentry->d_op && dentry->d_op->d_revalidate)
|
|
|
|
goto need_revalidate;
|
|
|
|
done:
|
|
|
|
path->mnt = mnt;
|
|
|
|
path->dentry = dentry;
|
2005-06-07 03:36:13 +07:00
|
|
|
__follow_mount(path);
|
2005-04-17 05:20:36 +07:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
need_lookup:
|
|
|
|
dentry = real_lookup(nd->dentry, name, nd);
|
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto fail;
|
|
|
|
goto done;
|
|
|
|
|
|
|
|
need_revalidate:
|
2006-09-27 15:50:44 +07:00
|
|
|
dentry = do_revalidate(dentry, nd);
|
|
|
|
if (!dentry)
|
|
|
|
goto need_lookup;
|
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto fail;
|
|
|
|
goto done;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
fail:
|
|
|
|
return PTR_ERR(dentry);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Name resolution.
|
2005-04-29 22:00:17 +07:00
|
|
|
* This is the basic name resolution function, turning a pathname into
|
|
|
|
* the final dentry. We expect 'base' to be positive and a directory.
|
2005-04-17 05:20:36 +07:00
|
|
|
*
|
2005-04-29 22:00:17 +07:00
|
|
|
* Returns 0 and nd will have valid dentry and mnt on success.
|
|
|
|
* Returns error and drops reference to input namei data on failure.
|
2005-04-17 05:20:36 +07:00
|
|
|
*/
|
|
|
|
static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
struct path next;
|
|
|
|
struct inode *inode;
|
|
|
|
int err;
|
|
|
|
unsigned int lookup_flags = nd->flags;
|
|
|
|
|
|
|
|
while (*name=='/')
|
|
|
|
name++;
|
|
|
|
if (!*name)
|
|
|
|
goto return_reval;
|
|
|
|
|
|
|
|
inode = nd->dentry->d_inode;
|
|
|
|
if (nd->depth)
|
2006-02-05 14:28:01 +07:00
|
|
|
lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
/* At this point we know we have a real path component. */
|
|
|
|
for(;;) {
|
|
|
|
unsigned long hash;
|
|
|
|
struct qstr this;
|
|
|
|
unsigned int c;
|
|
|
|
|
2005-10-19 04:20:18 +07:00
|
|
|
nd->flags |= LOOKUP_CONTINUE;
|
2005-04-17 05:20:36 +07:00
|
|
|
err = exec_permission_lite(inode, nd);
|
2005-11-09 12:35:04 +07:00
|
|
|
if (err == -EAGAIN)
|
|
|
|
err = vfs_permission(nd, MAY_EXEC);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
|
|
|
|
this.name = name;
|
|
|
|
c = *(const unsigned char *)name;
|
|
|
|
|
|
|
|
hash = init_name_hash();
|
|
|
|
do {
|
|
|
|
name++;
|
|
|
|
hash = partial_name_hash(c, hash);
|
|
|
|
c = *(const unsigned char *)name;
|
|
|
|
} while (c && (c != '/'));
|
|
|
|
this.len = name - (const char *) this.name;
|
|
|
|
this.hash = end_name_hash(hash);
|
|
|
|
|
|
|
|
/* remove trailing slashes? */
|
|
|
|
if (!c)
|
|
|
|
goto last_component;
|
|
|
|
while (*++name == '/');
|
|
|
|
if (!*name)
|
|
|
|
goto last_with_slashes;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* "." and ".." are special - ".." especially so because it has
|
|
|
|
* to be able to know about the current root directory and
|
|
|
|
* parent relationships.
|
|
|
|
*/
|
|
|
|
if (this.name[0] == '.') switch (this.len) {
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
case 2:
|
|
|
|
if (this.name[1] != '.')
|
|
|
|
break;
|
2005-06-07 03:36:13 +07:00
|
|
|
follow_dotdot(nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
inode = nd->dentry->d_inode;
|
|
|
|
/* fallthrough */
|
|
|
|
case 1:
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
/*
|
|
|
|
* See if the low-level filesystem might want
|
|
|
|
* to use its own hash..
|
|
|
|
*/
|
|
|
|
if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
|
|
|
|
err = nd->dentry->d_op->d_hash(nd->dentry, &this);
|
|
|
|
if (err < 0)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
/* This does the actual lookups.. */
|
|
|
|
err = do_lookup(nd, &this, &next);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
|
|
|
|
err = -ENOENT;
|
|
|
|
inode = next.dentry->d_inode;
|
|
|
|
if (!inode)
|
|
|
|
goto out_dput;
|
|
|
|
err = -ENOTDIR;
|
|
|
|
if (!inode->i_op)
|
|
|
|
goto out_dput;
|
|
|
|
|
|
|
|
if (inode->i_op->follow_link) {
|
2005-06-07 03:35:58 +07:00
|
|
|
err = do_follow_link(&next, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err)
|
|
|
|
goto return_err;
|
|
|
|
err = -ENOENT;
|
|
|
|
inode = nd->dentry->d_inode;
|
|
|
|
if (!inode)
|
|
|
|
break;
|
|
|
|
err = -ENOTDIR;
|
|
|
|
if (!inode->i_op)
|
|
|
|
break;
|
2005-09-07 05:18:21 +07:00
|
|
|
} else
|
|
|
|
path_to_nameidata(&next, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
err = -ENOTDIR;
|
|
|
|
if (!inode->i_op->lookup)
|
|
|
|
break;
|
|
|
|
continue;
|
|
|
|
/* here ends the main loop */
|
|
|
|
|
|
|
|
last_with_slashes:
|
|
|
|
lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY;
|
|
|
|
last_component:
|
2006-02-05 14:28:01 +07:00
|
|
|
/* Clear LOOKUP_CONTINUE iff it was previously unset */
|
|
|
|
nd->flags &= lookup_flags | ~LOOKUP_CONTINUE;
|
2005-04-17 05:20:36 +07:00
|
|
|
if (lookup_flags & LOOKUP_PARENT)
|
|
|
|
goto lookup_parent;
|
|
|
|
if (this.name[0] == '.') switch (this.len) {
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
case 2:
|
|
|
|
if (this.name[1] != '.')
|
|
|
|
break;
|
2005-06-07 03:36:13 +07:00
|
|
|
follow_dotdot(nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
inode = nd->dentry->d_inode;
|
|
|
|
/* fallthrough */
|
|
|
|
case 1:
|
|
|
|
goto return_reval;
|
|
|
|
}
|
|
|
|
if (nd->dentry->d_op && nd->dentry->d_op->d_hash) {
|
|
|
|
err = nd->dentry->d_op->d_hash(nd->dentry, &this);
|
|
|
|
if (err < 0)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
err = do_lookup(nd, &this, &next);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
inode = next.dentry->d_inode;
|
|
|
|
if ((lookup_flags & LOOKUP_FOLLOW)
|
|
|
|
&& inode && inode->i_op && inode->i_op->follow_link) {
|
2005-06-07 03:35:58 +07:00
|
|
|
err = do_follow_link(&next, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err)
|
|
|
|
goto return_err;
|
|
|
|
inode = nd->dentry->d_inode;
|
2005-09-07 05:18:21 +07:00
|
|
|
} else
|
|
|
|
path_to_nameidata(&next, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
err = -ENOENT;
|
|
|
|
if (!inode)
|
|
|
|
break;
|
|
|
|
if (lookup_flags & LOOKUP_DIRECTORY) {
|
|
|
|
err = -ENOTDIR;
|
|
|
|
if (!inode->i_op || !inode->i_op->lookup)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
goto return_base;
|
|
|
|
lookup_parent:
|
|
|
|
nd->last = this;
|
|
|
|
nd->last_type = LAST_NORM;
|
|
|
|
if (this.name[0] != '.')
|
|
|
|
goto return_base;
|
|
|
|
if (this.len == 1)
|
|
|
|
nd->last_type = LAST_DOT;
|
|
|
|
else if (this.len == 2 && this.name[1] == '.')
|
|
|
|
nd->last_type = LAST_DOTDOT;
|
|
|
|
else
|
|
|
|
goto return_base;
|
|
|
|
return_reval:
|
|
|
|
/*
|
|
|
|
* We bypassed the ordinary revalidation routines.
|
|
|
|
* We may need to check the cached dentry for staleness.
|
|
|
|
*/
|
|
|
|
if (nd->dentry && nd->dentry->d_sb &&
|
|
|
|
(nd->dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) {
|
|
|
|
err = -ESTALE;
|
|
|
|
/* Note: we do not d_invalidate() */
|
|
|
|
if (!nd->dentry->d_op->d_revalidate(nd->dentry, nd))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return_base:
|
|
|
|
return 0;
|
|
|
|
out_dput:
|
2005-09-07 05:18:21 +07:00
|
|
|
dput_path(&next, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
path_release(nd);
|
|
|
|
return_err:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Wrapper to retry pathname resolution whenever the underlying
|
|
|
|
* file system returns an ESTALE.
|
|
|
|
*
|
|
|
|
* Retry the whole path once, forcing real lookup requests
|
|
|
|
* instead of relying on the dcache.
|
|
|
|
*/
|
2007-07-19 15:48:22 +07:00
|
|
|
static int fastcall link_path_walk(const char *name, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
struct nameidata save = *nd;
|
|
|
|
int result;
|
|
|
|
|
|
|
|
/* make sure the stuff we saved doesn't go away */
|
|
|
|
dget(save.dentry);
|
|
|
|
mntget(save.mnt);
|
|
|
|
|
|
|
|
result = __link_path_walk(name, nd);
|
|
|
|
if (result == -ESTALE) {
|
|
|
|
*nd = save;
|
|
|
|
dget(nd->dentry);
|
|
|
|
mntget(nd->mnt);
|
|
|
|
nd->flags |= LOOKUP_REVAL;
|
|
|
|
result = __link_path_walk(name, nd);
|
|
|
|
}
|
|
|
|
|
|
|
|
dput(save.dentry);
|
|
|
|
mntput(save.mnt);
|
|
|
|
|
|
|
|
return result;
|
|
|
|
}
|
|
|
|
|
2007-07-19 15:48:22 +07:00
|
|
|
static int fastcall path_walk(const char * name, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
current->total_link_count = 0;
|
|
|
|
return link_path_walk(name, nd);
|
|
|
|
}
|
|
|
|
|
2005-04-29 22:00:17 +07:00
|
|
|
/*
|
|
|
|
* SMP-safe: Returns 1 and nd will have valid dentry and mnt, if
|
|
|
|
* everything is done. Returns 0 and drops input nd, if lookup failed;
|
|
|
|
*/
|
2005-04-17 05:20:36 +07:00
|
|
|
static int __emul_lookup_dentry(const char *name, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
if (path_walk(name, nd))
|
|
|
|
return 0; /* something went wrong... */
|
|
|
|
|
|
|
|
if (!nd->dentry->d_inode || S_ISDIR(nd->dentry->d_inode->i_mode)) {
|
|
|
|
struct dentry *old_dentry = nd->dentry;
|
|
|
|
struct vfsmount *old_mnt = nd->mnt;
|
|
|
|
struct qstr last = nd->last;
|
|
|
|
int last_type = nd->last_type;
|
2006-09-29 16:01:22 +07:00
|
|
|
struct fs_struct *fs = current->fs;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
2006-09-29 16:01:22 +07:00
|
|
|
* NAME was not found in alternate root or it's a directory.
|
|
|
|
* Try to find it in the normal root:
|
2005-04-17 05:20:36 +07:00
|
|
|
*/
|
|
|
|
nd->last_type = LAST_ROOT;
|
2006-09-29 16:01:22 +07:00
|
|
|
read_lock(&fs->lock);
|
|
|
|
nd->mnt = mntget(fs->rootmnt);
|
|
|
|
nd->dentry = dget(fs->root);
|
|
|
|
read_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (path_walk(name, nd) == 0) {
|
|
|
|
if (nd->dentry->d_inode) {
|
|
|
|
dput(old_dentry);
|
|
|
|
mntput(old_mnt);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
path_release(nd);
|
|
|
|
}
|
|
|
|
nd->dentry = old_dentry;
|
|
|
|
nd->mnt = old_mnt;
|
|
|
|
nd->last = last;
|
|
|
|
nd->last_type = last_type;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
void set_fs_altroot(void)
|
|
|
|
{
|
|
|
|
char *emul = __emul_prefix();
|
|
|
|
struct nameidata nd;
|
|
|
|
struct vfsmount *mnt = NULL, *oldmnt;
|
|
|
|
struct dentry *dentry = NULL, *olddentry;
|
|
|
|
int err;
|
2006-09-29 16:01:22 +07:00
|
|
|
struct fs_struct *fs = current->fs;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
if (!emul)
|
|
|
|
goto set_it;
|
|
|
|
err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd);
|
|
|
|
if (!err) {
|
|
|
|
mnt = nd.mnt;
|
|
|
|
dentry = nd.dentry;
|
|
|
|
}
|
|
|
|
set_it:
|
2006-09-29 16:01:22 +07:00
|
|
|
write_lock(&fs->lock);
|
|
|
|
oldmnt = fs->altrootmnt;
|
|
|
|
olddentry = fs->altroot;
|
|
|
|
fs->altrootmnt = mnt;
|
|
|
|
fs->altroot = dentry;
|
|
|
|
write_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (olddentry) {
|
|
|
|
dput(olddentry);
|
|
|
|
mntput(oldmnt);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2005-04-29 22:00:17 +07:00
|
|
|
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
|
2006-01-19 08:43:53 +07:00
|
|
|
static int fastcall do_path_lookup(int dfd, const char *name,
|
|
|
|
unsigned int flags, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2005-04-29 22:00:17 +07:00
|
|
|
int retval = 0;
|
2006-02-05 14:28:02 +07:00
|
|
|
int fput_needed;
|
|
|
|
struct file *file;
|
2006-09-29 16:01:22 +07:00
|
|
|
struct fs_struct *fs = current->fs;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
nd->last_type = LAST_ROOT; /* if there are only slashes... */
|
|
|
|
nd->flags = flags;
|
|
|
|
nd->depth = 0;
|
|
|
|
|
|
|
|
if (*name=='/') {
|
2006-09-29 16:01:22 +07:00
|
|
|
read_lock(&fs->lock);
|
|
|
|
if (fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
|
|
|
|
nd->mnt = mntget(fs->altrootmnt);
|
|
|
|
nd->dentry = dget(fs->altroot);
|
|
|
|
read_unlock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (__emul_lookup_dentry(name,nd))
|
2005-04-29 22:00:17 +07:00
|
|
|
goto out; /* found in altroot */
|
2006-09-29 16:01:22 +07:00
|
|
|
read_lock(&fs->lock);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2006-09-29 16:01:22 +07:00
|
|
|
nd->mnt = mntget(fs->rootmnt);
|
|
|
|
nd->dentry = dget(fs->root);
|
|
|
|
read_unlock(&fs->lock);
|
2006-01-19 08:43:53 +07:00
|
|
|
} else if (dfd == AT_FDCWD) {
|
2006-09-29 16:01:22 +07:00
|
|
|
read_lock(&fs->lock);
|
|
|
|
nd->mnt = mntget(fs->pwdmnt);
|
|
|
|
nd->dentry = dget(fs->pwd);
|
|
|
|
read_unlock(&fs->lock);
|
2006-01-19 08:43:53 +07:00
|
|
|
} else {
|
|
|
|
struct dentry *dentry;
|
|
|
|
|
|
|
|
file = fget_light(dfd, &fput_needed);
|
2006-02-05 14:28:02 +07:00
|
|
|
retval = -EBADF;
|
|
|
|
if (!file)
|
2006-06-04 16:51:37 +07:00
|
|
|
goto out_fail;
|
2006-01-19 08:43:53 +07:00
|
|
|
|
2006-12-08 17:36:35 +07:00
|
|
|
dentry = file->f_path.dentry;
|
2006-01-19 08:43:53 +07:00
|
|
|
|
2006-02-05 14:28:02 +07:00
|
|
|
retval = -ENOTDIR;
|
|
|
|
if (!S_ISDIR(dentry->d_inode->i_mode))
|
2006-06-04 16:51:37 +07:00
|
|
|
goto fput_fail;
|
2006-01-19 08:43:53 +07:00
|
|
|
|
|
|
|
retval = file_permission(file, MAY_EXEC);
|
2006-02-05 14:28:02 +07:00
|
|
|
if (retval)
|
2006-06-04 16:51:37 +07:00
|
|
|
goto fput_fail;
|
2006-01-19 08:43:53 +07:00
|
|
|
|
2006-12-08 17:36:35 +07:00
|
|
|
nd->mnt = mntget(file->f_path.mnt);
|
2006-01-19 08:43:53 +07:00
|
|
|
nd->dentry = dget(dentry);
|
|
|
|
|
|
|
|
fput_light(file, fput_needed);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2007-05-09 16:33:41 +07:00
|
|
|
|
|
|
|
retval = path_walk(name, nd);
|
2005-04-29 22:00:17 +07:00
|
|
|
out:
|
2007-05-09 16:33:41 +07:00
|
|
|
if (unlikely(!retval && !audit_dummy_context() && nd->dentry &&
|
2006-02-08 03:58:36 +07:00
|
|
|
nd->dentry->d_inode))
|
2006-06-09 10:19:31 +07:00
|
|
|
audit_inode(name, nd->dentry->d_inode);
|
2006-06-04 16:51:37 +07:00
|
|
|
out_fail:
|
2006-02-05 14:28:02 +07:00
|
|
|
return retval;
|
|
|
|
|
2006-06-04 16:51:37 +07:00
|
|
|
fput_fail:
|
2006-02-05 14:28:02 +07:00
|
|
|
fput_light(file, fput_needed);
|
2006-06-04 16:51:37 +07:00
|
|
|
goto out_fail;
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
int fastcall path_lookup(const char *name, unsigned int flags,
|
|
|
|
struct nameidata *nd)
|
|
|
|
{
|
|
|
|
return do_path_lookup(AT_FDCWD, name, flags, nd);
|
|
|
|
}
|
|
|
|
|
fs: introduce vfs_path_lookup
Stackable file systems, among others, frequently need to lookup paths or
path components starting from an arbitrary point in the namespace
(identified by a dentry and a vfsmount). Currently, such file systems use
lookup_one_len, which is frowned upon [1] as it does not pass the lookup
intent along; not passing a lookup intent, for example, can trigger BUG_ON's
when stacking on top of NFSv4.
The first patch introduces a new lookup function to allow lookup starting
from an arbitrary point in the namespace. This approach has been suggested
by Christoph Hellwig [2].
The second patch changes sunrpc to use vfs_path_lookup.
The third patch changes nfsctl.c to use vfs_path_lookup.
The fourth patch marks link_path_walk static.
The fifth, and last patch, unexports path_walk because it is no longer
unnecessary to call it directly, and using the new vfs_path_lookup is
cleaner.
For example, the following snippet of code, looks up "some/path/component"
in a directory pointed to by parent_{dentry,vfsmnt}:
err = vfs_path_lookup(parent_dentry, parent_vfsmnt,
"some/path/component", 0, &nd);
if (!err) {
/* exits */
...
/* once done, release the references */
path_release(&nd);
} else if (err == -ENOENT) {
/* doesn't exist */
} else {
/* other error */
}
VFS functions such as lookup_create can be used on the nameidata structure
to pass the create intent to the file system.
Signed-off-by: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Christoph Hellwig <hch@lst.de>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Neil Brown <neilb@suse.de>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:48:18 +07:00
|
|
|
/**
|
|
|
|
* vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
|
|
|
|
* @dentry: pointer to dentry of the base directory
|
|
|
|
* @mnt: pointer to vfs mount of the base directory
|
|
|
|
* @name: pointer to file name
|
|
|
|
* @flags: lookup flags
|
|
|
|
* @nd: pointer to nameidata
|
|
|
|
*/
|
|
|
|
int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
|
|
|
|
const char *name, unsigned int flags,
|
|
|
|
struct nameidata *nd)
|
|
|
|
{
|
|
|
|
int retval;
|
|
|
|
|
|
|
|
/* same as do_path_lookup */
|
|
|
|
nd->last_type = LAST_ROOT;
|
|
|
|
nd->flags = flags;
|
|
|
|
nd->depth = 0;
|
|
|
|
|
|
|
|
nd->mnt = mntget(mnt);
|
|
|
|
nd->dentry = dget(dentry);
|
|
|
|
|
|
|
|
retval = path_walk(name, nd);
|
|
|
|
if (unlikely(!retval && !audit_dummy_context() && nd->dentry &&
|
|
|
|
nd->dentry->d_inode))
|
|
|
|
audit_inode(name, nd->dentry->d_inode);
|
|
|
|
|
|
|
|
return retval;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
static int __path_lookup_intent_open(int dfd, const char *name,
|
|
|
|
unsigned int lookup_flags, struct nameidata *nd,
|
|
|
|
int open_flags, int create_mode)
|
2005-10-19 04:20:16 +07:00
|
|
|
{
|
|
|
|
struct file *filp = get_empty_filp();
|
|
|
|
int err;
|
|
|
|
|
|
|
|
if (filp == NULL)
|
|
|
|
return -ENFILE;
|
|
|
|
nd->intent.open.file = filp;
|
|
|
|
nd->intent.open.flags = open_flags;
|
|
|
|
nd->intent.open.create_mode = create_mode;
|
2006-01-19 08:43:53 +07:00
|
|
|
err = do_path_lookup(dfd, name, lookup_flags|LOOKUP_OPEN, nd);
|
2005-10-19 04:20:16 +07:00
|
|
|
if (IS_ERR(nd->intent.open.file)) {
|
|
|
|
if (err == 0) {
|
|
|
|
err = PTR_ERR(nd->intent.open.file);
|
|
|
|
path_release(nd);
|
|
|
|
}
|
|
|
|
} else if (err != 0)
|
|
|
|
release_open_intent(nd);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* path_lookup_open - lookup a file path with open intent
|
2006-02-01 18:06:57 +07:00
|
|
|
* @dfd: the directory to use as base, or AT_FDCWD
|
2005-10-19 04:20:16 +07:00
|
|
|
* @name: pointer to file name
|
|
|
|
* @lookup_flags: lookup intent flags
|
|
|
|
* @nd: pointer to nameidata
|
|
|
|
* @open_flags: open intent flags
|
|
|
|
*/
|
2006-01-19 08:43:53 +07:00
|
|
|
int path_lookup_open(int dfd, const char *name, unsigned int lookup_flags,
|
2005-10-19 04:20:16 +07:00
|
|
|
struct nameidata *nd, int open_flags)
|
|
|
|
{
|
2006-01-19 08:43:53 +07:00
|
|
|
return __path_lookup_intent_open(dfd, name, lookup_flags, nd,
|
2005-10-19 04:20:16 +07:00
|
|
|
open_flags, 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* path_lookup_create - lookup a file path with open + create intent
|
2006-02-01 18:06:57 +07:00
|
|
|
* @dfd: the directory to use as base, or AT_FDCWD
|
2005-10-19 04:20:16 +07:00
|
|
|
* @name: pointer to file name
|
|
|
|
* @lookup_flags: lookup intent flags
|
|
|
|
* @nd: pointer to nameidata
|
|
|
|
* @open_flags: open intent flags
|
|
|
|
* @create_mode: create intent flags
|
|
|
|
*/
|
2006-01-19 08:43:53 +07:00
|
|
|
static int path_lookup_create(int dfd, const char *name,
|
|
|
|
unsigned int lookup_flags, struct nameidata *nd,
|
|
|
|
int open_flags, int create_mode)
|
2005-10-19 04:20:16 +07:00
|
|
|
{
|
2006-01-19 08:43:53 +07:00
|
|
|
return __path_lookup_intent_open(dfd, name, lookup_flags|LOOKUP_CREATE,
|
|
|
|
nd, open_flags, create_mode);
|
2005-10-19 04:20:16 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags,
|
|
|
|
struct nameidata *nd, int open_flags)
|
|
|
|
{
|
|
|
|
char *tmp = getname(name);
|
|
|
|
int err = PTR_ERR(tmp);
|
|
|
|
|
|
|
|
if (!IS_ERR(tmp)) {
|
2006-01-19 08:43:53 +07:00
|
|
|
err = __path_lookup_intent_open(AT_FDCWD, tmp, lookup_flags, nd, open_flags, 0);
|
2005-10-19 04:20:16 +07:00
|
|
|
putname(tmp);
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2007-04-26 14:12:05 +07:00
|
|
|
static inline struct dentry *__lookup_hash_kern(struct qstr *name, struct dentry *base, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2007-04-26 14:12:05 +07:00
|
|
|
struct dentry *dentry;
|
2005-04-17 05:20:36 +07:00
|
|
|
struct inode *inode;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
inode = base->d_inode;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* See if the low-level filesystem might want
|
|
|
|
* to use its own hash..
|
|
|
|
*/
|
|
|
|
if (base->d_op && base->d_op->d_hash) {
|
|
|
|
err = base->d_op->d_hash(base, name);
|
|
|
|
dentry = ERR_PTR(err);
|
|
|
|
if (err < 0)
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
dentry = cached_lookup(base, name, nd);
|
|
|
|
if (!dentry) {
|
|
|
|
struct dentry *new = d_alloc(base, name);
|
|
|
|
dentry = ERR_PTR(-ENOMEM);
|
|
|
|
if (!new)
|
|
|
|
goto out;
|
|
|
|
dentry = inode->i_op->lookup(inode, new, nd);
|
|
|
|
if (!dentry)
|
|
|
|
dentry = new;
|
|
|
|
else
|
|
|
|
dput(new);
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
return dentry;
|
|
|
|
}
|
|
|
|
|
2007-04-26 14:12:05 +07:00
|
|
|
/*
|
|
|
|
* Restricted form of lookup. Doesn't follow links, single-component only,
|
|
|
|
* needs parent already locked. Doesn't follow mounts.
|
|
|
|
* SMP-safe.
|
|
|
|
*/
|
|
|
|
static inline struct dentry * __lookup_hash(struct qstr *name, struct dentry *base, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
struct dentry *dentry;
|
|
|
|
struct inode *inode;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
inode = base->d_inode;
|
|
|
|
|
|
|
|
err = permission(inode, MAY_EXEC, nd);
|
|
|
|
dentry = ERR_PTR(err);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
dentry = __lookup_hash_kern(name, base, nd);
|
|
|
|
out:
|
|
|
|
return dentry;
|
|
|
|
}
|
|
|
|
|
2006-03-31 17:32:11 +07:00
|
|
|
static struct dentry *lookup_hash(struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2005-11-09 12:35:06 +07:00
|
|
|
return __lookup_hash(&nd->last, nd->dentry, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/* SMP-safe */
|
2007-04-26 14:12:05 +07:00
|
|
|
static inline int __lookup_one_len(const char *name, struct qstr *this, struct dentry *base, int len)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
unsigned long hash;
|
|
|
|
unsigned int c;
|
|
|
|
|
2007-04-26 14:12:05 +07:00
|
|
|
this->name = name;
|
|
|
|
this->len = len;
|
2005-04-17 05:20:36 +07:00
|
|
|
if (!len)
|
2007-04-26 14:12:05 +07:00
|
|
|
return -EACCES;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
hash = init_name_hash();
|
|
|
|
while (len--) {
|
|
|
|
c = *(const unsigned char *)name++;
|
|
|
|
if (c == '/' || c == '\0')
|
2007-04-26 14:12:05 +07:00
|
|
|
return -EACCES;
|
2005-04-17 05:20:36 +07:00
|
|
|
hash = partial_name_hash(c, hash);
|
|
|
|
}
|
2007-04-26 14:12:05 +07:00
|
|
|
this->hash = end_name_hash(hash);
|
|
|
|
return 0;
|
|
|
|
}
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2007-04-26 14:12:05 +07:00
|
|
|
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct qstr this;
|
|
|
|
|
|
|
|
err = __lookup_one_len(name, &this, base, len);
|
|
|
|
if (err)
|
|
|
|
return ERR_PTR(err);
|
2005-11-09 12:35:06 +07:00
|
|
|
return __lookup_hash(&this, base, NULL);
|
2007-04-26 14:12:05 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
struct dentry *lookup_one_len_kern(const char *name, struct dentry *base, int len)
|
|
|
|
{
|
|
|
|
int err;
|
|
|
|
struct qstr this;
|
|
|
|
|
|
|
|
err = __lookup_one_len(name, &this, base, len);
|
|
|
|
if (err)
|
|
|
|
return ERR_PTR(err);
|
|
|
|
return __lookup_hash_kern(&this, base, NULL);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
int fastcall __user_walk_fd(int dfd, const char __user *name, unsigned flags,
|
|
|
|
struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
char *tmp = getname(name);
|
|
|
|
int err = PTR_ERR(tmp);
|
|
|
|
|
|
|
|
if (!IS_ERR(tmp)) {
|
2006-01-19 08:43:53 +07:00
|
|
|
err = do_path_lookup(dfd, tmp, flags, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
putname(tmp);
|
|
|
|
}
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
|
|
|
|
{
|
|
|
|
return __user_walk_fd(AT_FDCWD, name, flags, nd);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* It's inline, so penalty for filesystems that don't use sticky bit is
|
|
|
|
* minimal.
|
|
|
|
*/
|
|
|
|
static inline int check_sticky(struct inode *dir, struct inode *inode)
|
|
|
|
{
|
|
|
|
if (!(dir->i_mode & S_ISVTX))
|
|
|
|
return 0;
|
|
|
|
if (inode->i_uid == current->fsuid)
|
|
|
|
return 0;
|
|
|
|
if (dir->i_uid == current->fsuid)
|
|
|
|
return 0;
|
|
|
|
return !capable(CAP_FOWNER);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Check whether we can remove a link victim from directory dir, check
|
|
|
|
* whether the type of victim is right.
|
|
|
|
* 1. We can't do it if dir is read-only (done in permission())
|
|
|
|
* 2. We should have write and exec permissions on dir
|
|
|
|
* 3. We can't remove anything from append-only dir
|
|
|
|
* 4. We can't do anything with immutable dir (done in permission())
|
|
|
|
* 5. If the sticky bit on dir is set we should either
|
|
|
|
* a. be owner of dir, or
|
|
|
|
* b. be owner of victim, or
|
|
|
|
* c. have CAP_FOWNER capability
|
|
|
|
* 6. If the victim is append-only or immutable we can't do antyhing with
|
|
|
|
* links pointing to it.
|
|
|
|
* 7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
|
|
|
|
* 8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
|
|
|
|
* 9. We can't remove a root or mountpoint.
|
|
|
|
* 10. We don't allow removal of NFS sillyrenamed files; it's handled by
|
|
|
|
* nfs_async_unlink().
|
|
|
|
*/
|
2006-01-15 04:20:43 +07:00
|
|
|
static int may_delete(struct inode *dir,struct dentry *victim,int isdir)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error;
|
|
|
|
|
|
|
|
if (!victim->d_inode)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
BUG_ON(victim->d_parent->d_inode != dir);
|
2006-07-14 00:16:39 +07:00
|
|
|
audit_inode_child(victim->d_name.name, victim->d_inode, dir);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
error = permission(dir,MAY_WRITE | MAY_EXEC, NULL);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
if (IS_APPEND(dir))
|
|
|
|
return -EPERM;
|
|
|
|
if (check_sticky(dir, victim->d_inode)||IS_APPEND(victim->d_inode)||
|
|
|
|
IS_IMMUTABLE(victim->d_inode))
|
|
|
|
return -EPERM;
|
|
|
|
if (isdir) {
|
|
|
|
if (!S_ISDIR(victim->d_inode->i_mode))
|
|
|
|
return -ENOTDIR;
|
|
|
|
if (IS_ROOT(victim))
|
|
|
|
return -EBUSY;
|
|
|
|
} else if (S_ISDIR(victim->d_inode->i_mode))
|
|
|
|
return -EISDIR;
|
|
|
|
if (IS_DEADDIR(dir))
|
|
|
|
return -ENOENT;
|
|
|
|
if (victim->d_flags & DCACHE_NFSFS_RENAMED)
|
|
|
|
return -EBUSY;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Check whether we can create an object with dentry child in directory
|
|
|
|
* dir.
|
|
|
|
* 1. We can't do it if child already exists (open has special treatment for
|
|
|
|
* this case, but since we are inlined it's OK)
|
|
|
|
* 2. We can't do it if dir is read-only (done in permission())
|
|
|
|
* 3. We should have write and exec permissions on dir
|
|
|
|
* 4. We can't do it if dir is immutable (done in permission())
|
|
|
|
*/
|
|
|
|
static inline int may_create(struct inode *dir, struct dentry *child,
|
|
|
|
struct nameidata *nd)
|
|
|
|
{
|
|
|
|
if (child->d_inode)
|
|
|
|
return -EEXIST;
|
|
|
|
if (IS_DEADDIR(dir))
|
|
|
|
return -ENOENT;
|
|
|
|
return permission(dir,MAY_WRITE | MAY_EXEC, nd);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* O_DIRECTORY translates into forcing a directory lookup.
|
|
|
|
*/
|
|
|
|
static inline int lookup_flags(unsigned int f)
|
|
|
|
{
|
|
|
|
unsigned long retval = LOOKUP_FOLLOW;
|
|
|
|
|
|
|
|
if (f & O_NOFOLLOW)
|
|
|
|
retval &= ~LOOKUP_FOLLOW;
|
|
|
|
|
|
|
|
if (f & O_DIRECTORY)
|
|
|
|
retval |= LOOKUP_DIRECTORY;
|
|
|
|
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* 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) {
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
|
2005-04-17 05:20:36 +07:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2006-03-23 18:00:33 +07:00
|
|
|
mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
for (p = p1; p->d_parent != p; p = p->d_parent) {
|
|
|
|
if (p->d_parent == p2) {
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
|
|
|
|
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
|
2005-04-17 05:20:36 +07:00
|
|
|
return p;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
for (p = p2; p->d_parent != p; p = p->d_parent) {
|
|
|
|
if (p->d_parent == p1) {
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
|
|
|
|
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
|
2005-04-17 05:20:36 +07:00
|
|
|
return p;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
|
|
|
|
mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
|
2005-04-17 05:20:36 +07:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
void unlock_rename(struct dentry *p1, struct dentry *p2)
|
|
|
|
{
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&p1->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (p1 != p2) {
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&p2->d_inode->i_mutex);
|
2006-03-23 18:00:33 +07:00
|
|
|
mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
int vfs_create(struct inode *dir, struct dentry *dentry, int mode,
|
|
|
|
struct nameidata *nd)
|
|
|
|
{
|
|
|
|
int error = may_create(dir, dentry, nd);
|
|
|
|
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!dir->i_op || !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;
|
|
|
|
DQUOT_INIT(dir);
|
|
|
|
error = dir->i_op->create(dir, dentry, mode, nd);
|
2005-09-10 03:01:44 +07:00
|
|
|
if (!error)
|
2005-11-03 22:57:06 +07:00
|
|
|
fsnotify_create(dir, dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
int may_open(struct nameidata *nd, int acc_mode, int flag)
|
|
|
|
{
|
|
|
|
struct dentry *dentry = nd->dentry;
|
|
|
|
struct inode *inode = dentry->d_inode;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
if (!inode)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
if (S_ISLNK(inode->i_mode))
|
|
|
|
return -ELOOP;
|
|
|
|
|
|
|
|
if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE))
|
|
|
|
return -EISDIR;
|
|
|
|
|
2005-11-09 12:35:04 +07:00
|
|
|
error = vfs_permission(nd, acc_mode);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* FIFO's, sockets and device files are special: they don't
|
|
|
|
* actually live on the filesystem itself, and as such you
|
|
|
|
* can write to them even if the filesystem is read-only.
|
|
|
|
*/
|
|
|
|
if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
|
|
|
|
flag &= ~O_TRUNC;
|
|
|
|
} else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) {
|
|
|
|
if (nd->mnt->mnt_flags & MNT_NODEV)
|
|
|
|
return -EACCES;
|
|
|
|
|
|
|
|
flag &= ~O_TRUNC;
|
|
|
|
} else if (IS_RDONLY(inode) && (flag & FMODE_WRITE))
|
|
|
|
return -EROFS;
|
|
|
|
/*
|
|
|
|
* An append-only file must be opened in append mode for writing.
|
|
|
|
*/
|
|
|
|
if (IS_APPEND(inode)) {
|
|
|
|
if ((flag & FMODE_WRITE) && !(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)
|
2007-07-17 16:30:08 +07:00
|
|
|
if (!is_owner_or_cap(inode))
|
2005-04-17 05:20:36 +07:00
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Ensure there are no outstanding leases on the file.
|
|
|
|
*/
|
|
|
|
error = break_lease(inode, flag);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (flag & O_TRUNC) {
|
|
|
|
error = get_write_access(inode);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Refuse to truncate files with mandatory locks held on them.
|
|
|
|
*/
|
|
|
|
error = locks_verify_locked(inode);
|
|
|
|
if (!error) {
|
|
|
|
DQUOT_INIT(inode);
|
|
|
|
|
2006-01-08 16:02:39 +07:00
|
|
|
error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
put_write_access(inode);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
} else
|
|
|
|
if (flag & FMODE_WRITE)
|
|
|
|
DQUOT_INIT(inode);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-10-01 13:29:02 +07:00
|
|
|
static int open_namei_create(struct nameidata *nd, struct path *path,
|
|
|
|
int flag, int mode)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
struct dentry *dir = nd->dentry;
|
|
|
|
|
|
|
|
if (!IS_POSIXACL(dir->d_inode))
|
|
|
|
mode &= ~current->fs->umask;
|
|
|
|
error = vfs_create(dir->d_inode, path->dentry, mode, nd);
|
|
|
|
mutex_unlock(&dir->d_inode->i_mutex);
|
|
|
|
dput(nd->dentry);
|
|
|
|
nd->dentry = path->dentry;
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
/* Don't check for write permission, don't truncate */
|
|
|
|
return may_open(nd, 0, flag & ~O_TRUNC);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* open_namei()
|
|
|
|
*
|
|
|
|
* namei for open - this is in fact almost the whole open-routine.
|
|
|
|
*
|
|
|
|
* Note that the low bits of "flag" aren't the same as in the open
|
|
|
|
* system call - they are 00 - no permissions needed
|
|
|
|
* 01 - read permission needed
|
|
|
|
* 10 - write permission needed
|
|
|
|
* 11 - read/write permissions needed
|
|
|
|
* which is a lot more logical, and also allows the "no perm" needed
|
|
|
|
* for symlinks (where the permissions are checked later).
|
|
|
|
* SMP-safe
|
|
|
|
*/
|
2006-01-19 08:43:53 +07:00
|
|
|
int open_namei(int dfd, const char *pathname, int flag,
|
|
|
|
int mode, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2005-10-19 04:20:16 +07:00
|
|
|
int acc_mode, error;
|
2005-06-07 03:36:00 +07:00
|
|
|
struct path path;
|
2005-04-17 05:20:36 +07:00
|
|
|
struct dentry *dir;
|
|
|
|
int count = 0;
|
|
|
|
|
|
|
|
acc_mode = ACC_MODE(flag);
|
|
|
|
|
2005-10-19 04:20:16 +07:00
|
|
|
/* O_TRUNC implies we need access checks for write permissions */
|
|
|
|
if (flag & O_TRUNC)
|
|
|
|
acc_mode |= MAY_WRITE;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/* Allow the LSM permission hook to distinguish append
|
|
|
|
access from general write access. */
|
|
|
|
if (flag & O_APPEND)
|
|
|
|
acc_mode |= MAY_APPEND;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The simplest case - just a plain lookup.
|
|
|
|
*/
|
|
|
|
if (!(flag & O_CREAT)) {
|
2006-01-19 08:43:53 +07:00
|
|
|
error = path_lookup_open(dfd, pathname, lookup_flags(flag),
|
|
|
|
nd, flag);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
goto ok;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Create - we need to know the parent.
|
|
|
|
*/
|
2006-01-19 08:43:53 +07:00
|
|
|
error = path_lookup_create(dfd,pathname,LOOKUP_PARENT,nd,flag,mode);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We have the parent and last component. First of all, check
|
|
|
|
* that we are not asked to creat(2) an obvious directory - that
|
|
|
|
* will not do.
|
|
|
|
*/
|
|
|
|
error = -EISDIR;
|
|
|
|
if (nd->last_type != LAST_NORM || nd->last.name[nd->last.len])
|
|
|
|
goto exit;
|
|
|
|
|
|
|
|
dir = nd->dentry;
|
|
|
|
nd->flags &= ~LOOKUP_PARENT;
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&dir->d_inode->i_mutex);
|
2005-11-09 12:35:06 +07:00
|
|
|
path.dentry = lookup_hash(nd);
|
2005-06-07 03:36:01 +07:00
|
|
|
path.mnt = nd->mnt;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
do_last:
|
2005-06-07 03:36:00 +07:00
|
|
|
error = PTR_ERR(path.dentry);
|
|
|
|
if (IS_ERR(path.dentry)) {
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&dir->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
|
[PATCH] Missed error checking for intent's filp in open_namei().
It seems there is error check missing in open_namei for errors returned
through intent.open.file (from lookup_instantiate_filp).
If there is plain open performed, then such a check done inside
__path_lookup_intent_open called from path_lookup_open(), but when the open
is performed with O_CREAT flag set, then __path_lookup_intent_open is only
called with LOOKUP_PARENT set where no file opening can occur yet.
Later on lookup_hash is called where exact opening might take place and
intent.open.file may be filled. If it is filled with error value of some
sort, then we get kernel attempting to dereference this error value as
address (and corresponding oops) in nameidata_to_filp() called from
filp_open().
While this is relatively simple to workaround in ->lookup() method by just
checking lookup_instantiate_filp() return value and returning error as
needed, this is not so easy in ->d_revalidate(), where we can only return
"yes, dentry is valid" or "no, dentry is invalid, perform full lookup
again", and just returning 0 on error would cause extra lookup (with
potential extra costly RPCs).
So in short, I believe that there should be no difference in error handling
for opening a file and creating a file in open_namei() and propose this
simple patch as a solution.
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-03-25 18:06:54 +07:00
|
|
|
if (IS_ERR(nd->intent.open.file)) {
|
|
|
|
mutex_unlock(&dir->d_inode->i_mutex);
|
|
|
|
error = PTR_ERR(nd->intent.open.file);
|
|
|
|
goto exit_dput;
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/* Negative dentry, just create the file */
|
2005-06-07 03:36:00 +07:00
|
|
|
if (!path.dentry->d_inode) {
|
2006-10-01 13:29:02 +07:00
|
|
|
error = open_namei_create(nd, &path, flag, mode);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit;
|
2006-10-01 13:29:02 +07:00
|
|
|
return 0;
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* It already exists.
|
|
|
|
*/
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&dir->d_inode->i_mutex);
|
2007-02-14 02:15:01 +07:00
|
|
|
audit_inode(pathname, path.dentry->d_inode);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
error = -EEXIST;
|
|
|
|
if (flag & O_EXCL)
|
|
|
|
goto exit_dput;
|
|
|
|
|
2005-06-07 03:36:06 +07:00
|
|
|
if (__follow_mount(&path)) {
|
2005-04-17 05:20:36 +07:00
|
|
|
error = -ELOOP;
|
2005-06-07 03:36:08 +07:00
|
|
|
if (flag & O_NOFOLLOW)
|
|
|
|
goto exit_dput;
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2006-07-14 00:16:02 +07:00
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
error = -ENOENT;
|
2005-06-07 03:36:00 +07:00
|
|
|
if (!path.dentry->d_inode)
|
2005-04-17 05:20:36 +07:00
|
|
|
goto exit_dput;
|
2005-06-07 03:36:00 +07:00
|
|
|
if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link)
|
2005-04-17 05:20:36 +07:00
|
|
|
goto do_link;
|
|
|
|
|
2005-09-07 05:18:21 +07:00
|
|
|
path_to_nameidata(&path, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
error = -EISDIR;
|
2005-06-07 03:36:00 +07:00
|
|
|
if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode))
|
2005-04-17 05:20:36 +07:00
|
|
|
goto exit;
|
|
|
|
ok:
|
|
|
|
error = may_open(nd, acc_mode, flag);
|
|
|
|
if (error)
|
|
|
|
goto exit;
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
exit_dput:
|
2005-09-07 05:18:21 +07:00
|
|
|
dput_path(&path, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
exit:
|
2005-10-19 04:20:16 +07:00
|
|
|
if (!IS_ERR(nd->intent.open.file))
|
|
|
|
release_open_intent(nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
path_release(nd);
|
|
|
|
return error;
|
|
|
|
|
|
|
|
do_link:
|
|
|
|
error = -ELOOP;
|
|
|
|
if (flag & O_NOFOLLOW)
|
|
|
|
goto exit_dput;
|
|
|
|
/*
|
|
|
|
* This is subtle. Instead of calling do_follow_link() we do the
|
|
|
|
* thing by hands. The reason is that this way we have zero link_count
|
|
|
|
* and path_walk() (called from ->follow_link) honoring LOOKUP_PARENT.
|
|
|
|
* After that we have the parent and last component, i.e.
|
|
|
|
* we are in the same situation as after the first path_walk().
|
|
|
|
* Well, almost - if the last component is normal we get its copy
|
|
|
|
* stored in nd->last.name and we will have to putname() it when we
|
|
|
|
* are done. Procfs-like symlinks just set LAST_BIND.
|
|
|
|
*/
|
|
|
|
nd->flags |= LOOKUP_PARENT;
|
2005-06-07 03:36:00 +07:00
|
|
|
error = security_inode_follow_link(path.dentry, nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit_dput;
|
2005-06-07 03:36:03 +07:00
|
|
|
error = __do_follow_link(&path, nd);
|
2006-07-14 14:23:49 +07:00
|
|
|
if (error) {
|
|
|
|
/* Does someone understand code flow here? Or it is only
|
|
|
|
* me so stupid? Anathema to whoever designed this non-sense
|
|
|
|
* with "intent.open".
|
|
|
|
*/
|
|
|
|
release_open_intent(nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
2006-07-14 14:23:49 +07:00
|
|
|
}
|
2005-04-17 05:20:36 +07:00
|
|
|
nd->flags &= ~LOOKUP_PARENT;
|
2005-06-07 03:36:04 +07:00
|
|
|
if (nd->last_type == LAST_BIND)
|
2005-04-17 05:20:36 +07:00
|
|
|
goto ok;
|
|
|
|
error = -EISDIR;
|
|
|
|
if (nd->last_type != LAST_NORM)
|
|
|
|
goto exit;
|
|
|
|
if (nd->last.name[nd->last.len]) {
|
2005-10-07 11:54:21 +07:00
|
|
|
__putname(nd->last.name);
|
2005-04-17 05:20:36 +07:00
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
error = -ELOOP;
|
|
|
|
if (count++==32) {
|
2005-10-07 11:54:21 +07:00
|
|
|
__putname(nd->last.name);
|
2005-04-17 05:20:36 +07:00
|
|
|
goto exit;
|
|
|
|
}
|
|
|
|
dir = nd->dentry;
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&dir->d_inode->i_mutex);
|
2005-11-09 12:35:06 +07:00
|
|
|
path.dentry = lookup_hash(nd);
|
2005-06-07 03:36:04 +07:00
|
|
|
path.mnt = nd->mnt;
|
2005-10-07 11:54:21 +07:00
|
|
|
__putname(nd->last.name);
|
2005-04-17 05:20:36 +07:00
|
|
|
goto do_last;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* lookup_create - lookup a dentry, creating it if it doesn't exist
|
|
|
|
* @nd: nameidata info
|
|
|
|
* @is_dir: directory flag
|
|
|
|
*
|
|
|
|
* Simple function to lookup and return a dentry and create it
|
|
|
|
* if it doesn't exist. Is SMP-safe.
|
2005-06-23 14:09:49 +07:00
|
|
|
*
|
2006-01-10 06:59:24 +07:00
|
|
|
* Returns with nd->dentry->d_inode->i_mutex locked.
|
2005-04-17 05:20:36 +07:00
|
|
|
*/
|
|
|
|
struct dentry *lookup_create(struct nameidata *nd, int is_dir)
|
|
|
|
{
|
2005-06-23 14:09:49 +07:00
|
|
|
struct dentry *dentry = ERR_PTR(-EEXIST);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&nd->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
|
2005-06-23 14:09:49 +07:00
|
|
|
/*
|
|
|
|
* Yucky last component or no last component at all?
|
|
|
|
* (foo/., foo/.., /////)
|
|
|
|
*/
|
2005-04-17 05:20:36 +07:00
|
|
|
if (nd->last_type != LAST_NORM)
|
|
|
|
goto fail;
|
|
|
|
nd->flags &= ~LOOKUP_PARENT;
|
2006-08-23 07:06:02 +07:00
|
|
|
nd->flags |= LOOKUP_CREATE;
|
|
|
|
nd->intent.open.flags = O_EXCL;
|
2005-06-23 14:09:49 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Do the final lookup.
|
|
|
|
*/
|
2005-11-09 12:35:06 +07:00
|
|
|
dentry = lookup_hash(nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto fail;
|
2005-06-23 14:09:49 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Special case - lookup gave negative, but... we had foo/bar/
|
|
|
|
* From the vfs_mknod() POV we just have a negative dentry -
|
|
|
|
* all is fine. Let's be bastards - you had / on the end, you've
|
|
|
|
* been asking for (non-existent) directory. -ENOENT for you.
|
|
|
|
*/
|
2005-04-17 05:20:36 +07:00
|
|
|
if (!is_dir && nd->last.name[nd->last.len] && !dentry->d_inode)
|
|
|
|
goto enoent;
|
|
|
|
return dentry;
|
|
|
|
enoent:
|
|
|
|
dput(dentry);
|
|
|
|
dentry = ERR_PTR(-ENOENT);
|
|
|
|
fail:
|
|
|
|
return dentry;
|
|
|
|
}
|
2005-05-20 02:26:43 +07:00
|
|
|
EXPORT_SYMBOL_GPL(lookup_create);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
|
|
|
|
{
|
|
|
|
int error = may_create(dir, dentry, NULL);
|
|
|
|
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
if (!dir->i_op || !dir->i_op->mknod)
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
error = security_inode_mknod(dir, dentry, mode, dev);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
DQUOT_INIT(dir);
|
|
|
|
error = dir->i_op->mknod(dir, dentry, mode, dev);
|
2005-09-10 03:01:44 +07:00
|
|
|
if (!error)
|
2005-11-03 22:57:06 +07:00
|
|
|
fsnotify_create(dir, dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
|
|
|
|
unsigned dev)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
char * tmp;
|
|
|
|
struct dentry * dentry;
|
|
|
|
struct nameidata nd;
|
|
|
|
|
|
|
|
if (S_ISDIR(mode))
|
|
|
|
return -EPERM;
|
|
|
|
tmp = getname(filename);
|
|
|
|
if (IS_ERR(tmp))
|
|
|
|
return PTR_ERR(tmp);
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto out;
|
|
|
|
dentry = lookup_create(&nd, 0);
|
|
|
|
error = PTR_ERR(dentry);
|
|
|
|
|
|
|
|
if (!IS_POSIXACL(nd.dentry->d_inode))
|
|
|
|
mode &= ~current->fs->umask;
|
|
|
|
if (!IS_ERR(dentry)) {
|
|
|
|
switch (mode & S_IFMT) {
|
|
|
|
case 0: case S_IFREG:
|
|
|
|
error = vfs_create(nd.dentry->d_inode,dentry,mode,&nd);
|
|
|
|
break;
|
|
|
|
case S_IFCHR: case S_IFBLK:
|
|
|
|
error = vfs_mknod(nd.dentry->d_inode,dentry,mode,
|
|
|
|
new_decode_dev(dev));
|
|
|
|
break;
|
|
|
|
case S_IFIFO: case S_IFSOCK:
|
|
|
|
error = vfs_mknod(nd.dentry->d_inode,dentry,mode,0);
|
|
|
|
break;
|
|
|
|
case S_IFDIR:
|
|
|
|
error = -EPERM;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
error = -EINVAL;
|
|
|
|
}
|
|
|
|
dput(dentry);
|
|
|
|
}
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&nd.dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
path_release(&nd);
|
|
|
|
out:
|
|
|
|
putname(tmp);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_mknod(const char __user *filename, int mode, unsigned dev)
|
|
|
|
{
|
|
|
|
return sys_mknodat(AT_FDCWD, filename, mode, dev);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
|
|
|
|
{
|
|
|
|
int error = may_create(dir, dentry, NULL);
|
|
|
|
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!dir->i_op || !dir->i_op->mkdir)
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
mode &= (S_IRWXUGO|S_ISVTX);
|
|
|
|
error = security_inode_mkdir(dir, dentry, mode);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
DQUOT_INIT(dir);
|
|
|
|
error = dir->i_op->mkdir(dir, dentry, mode);
|
2005-09-10 03:01:44 +07:00
|
|
|
if (!error)
|
2005-11-03 22:57:06 +07:00
|
|
|
fsnotify_mkdir(dir, dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
char * tmp;
|
2006-10-01 13:29:01 +07:00
|
|
|
struct dentry *dentry;
|
|
|
|
struct nameidata nd;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
tmp = getname(pathname);
|
|
|
|
error = PTR_ERR(tmp);
|
2006-10-01 13:29:01 +07:00
|
|
|
if (IS_ERR(tmp))
|
|
|
|
goto out_err;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2006-10-01 13:29:01 +07:00
|
|
|
error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd);
|
|
|
|
if (error)
|
|
|
|
goto out;
|
|
|
|
dentry = lookup_create(&nd, 1);
|
|
|
|
error = PTR_ERR(dentry);
|
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto out_unlock;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2006-10-01 13:29:01 +07:00
|
|
|
if (!IS_POSIXACL(nd.dentry->d_inode))
|
|
|
|
mode &= ~current->fs->umask;
|
|
|
|
error = vfs_mkdir(nd.dentry->d_inode, dentry, mode);
|
|
|
|
dput(dentry);
|
|
|
|
out_unlock:
|
|
|
|
mutex_unlock(&nd.dentry->d_inode->i_mutex);
|
|
|
|
path_release(&nd);
|
|
|
|
out:
|
|
|
|
putname(tmp);
|
|
|
|
out_err:
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_mkdir(const char __user *pathname, int mode)
|
|
|
|
{
|
|
|
|
return sys_mkdirat(AT_FDCWD, pathname, mode);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* We try to drop the dentry early: we should have
|
|
|
|
* a usage count of 2 if we're the only user of this
|
|
|
|
* dentry, and if that is true (possibly after pruning
|
|
|
|
* the dcache), then we drop the dentry now.
|
|
|
|
*
|
|
|
|
* A low-level filesystem can, if it choses, legally
|
|
|
|
* do a
|
|
|
|
*
|
|
|
|
* if (!d_unhashed(dentry))
|
|
|
|
* return -EBUSY;
|
|
|
|
*
|
|
|
|
* if it cannot handle the case of removing a directory
|
|
|
|
* that is still in use by something else..
|
|
|
|
*/
|
|
|
|
void dentry_unhash(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
dget(dentry);
|
2006-12-07 11:37:07 +07:00
|
|
|
shrink_dcache_parent(dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
spin_lock(&dcache_lock);
|
|
|
|
spin_lock(&dentry->d_lock);
|
|
|
|
if (atomic_read(&dentry->d_count) == 2)
|
|
|
|
__d_drop(dentry);
|
|
|
|
spin_unlock(&dentry->d_lock);
|
|
|
|
spin_unlock(&dcache_lock);
|
|
|
|
}
|
|
|
|
|
|
|
|
int vfs_rmdir(struct inode *dir, struct dentry *dentry)
|
|
|
|
{
|
|
|
|
int error = may_delete(dir, dentry, 1);
|
|
|
|
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!dir->i_op || !dir->i_op->rmdir)
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
DQUOT_INIT(dir);
|
|
|
|
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
dentry_unhash(dentry);
|
|
|
|
if (d_mountpoint(dentry))
|
|
|
|
error = -EBUSY;
|
|
|
|
else {
|
|
|
|
error = security_inode_rmdir(dir, dentry);
|
|
|
|
if (!error) {
|
|
|
|
error = dir->i_op->rmdir(dir, dentry);
|
|
|
|
if (!error)
|
|
|
|
dentry->d_inode->i_flags |= S_DEAD;
|
|
|
|
}
|
|
|
|
}
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (!error) {
|
|
|
|
d_delete(dentry);
|
|
|
|
}
|
|
|
|
dput(dentry);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
static long do_rmdir(int dfd, const char __user *pathname)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
char * name;
|
|
|
|
struct dentry *dentry;
|
|
|
|
struct nameidata nd;
|
|
|
|
|
|
|
|
name = getname(pathname);
|
|
|
|
if(IS_ERR(name))
|
|
|
|
return PTR_ERR(name);
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_path_lookup(dfd, name, LOOKUP_PARENT, &nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit;
|
|
|
|
|
|
|
|
switch(nd.last_type) {
|
|
|
|
case LAST_DOTDOT:
|
|
|
|
error = -ENOTEMPTY;
|
|
|
|
goto exit1;
|
|
|
|
case LAST_DOT:
|
|
|
|
error = -EINVAL;
|
|
|
|
goto exit1;
|
|
|
|
case LAST_ROOT:
|
|
|
|
error = -EBUSY;
|
|
|
|
goto exit1;
|
|
|
|
}
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
|
2005-11-09 12:35:06 +07:00
|
|
|
dentry = lookup_hash(&nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
error = PTR_ERR(dentry);
|
2006-10-01 13:29:01 +07:00
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto exit2;
|
|
|
|
error = vfs_rmdir(nd.dentry->d_inode, dentry);
|
|
|
|
dput(dentry);
|
|
|
|
exit2:
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&nd.dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
exit1:
|
|
|
|
path_release(&nd);
|
|
|
|
exit:
|
|
|
|
putname(name);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_rmdir(const char __user *pathname)
|
|
|
|
{
|
|
|
|
return do_rmdir(AT_FDCWD, pathname);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
int vfs_unlink(struct inode *dir, struct dentry *dentry)
|
|
|
|
{
|
|
|
|
int error = may_delete(dir, dentry, 0);
|
|
|
|
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!dir->i_op || !dir->i_op->unlink)
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
DQUOT_INIT(dir);
|
|
|
|
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (d_mountpoint(dentry))
|
|
|
|
error = -EBUSY;
|
|
|
|
else {
|
|
|
|
error = security_inode_unlink(dir, dentry);
|
|
|
|
if (!error)
|
|
|
|
error = dir->i_op->unlink(dir, dentry);
|
|
|
|
}
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
/* We don't d_delete() NFS sillyrenamed files--they still exist. */
|
|
|
|
if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
|
2005-08-05 03:07:08 +07:00
|
|
|
d_delete(dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:06:03 +07:00
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Make sure that the actual truncation of the file will occur outside its
|
2006-01-10 06:59:24 +07:00
|
|
|
* directory's i_mutex. Truncate can take a long time if there is a lot of
|
2005-04-17 05:20:36 +07:00
|
|
|
* writeout happening, and we don't want to prevent access to the directory
|
|
|
|
* while waiting on the I/O.
|
|
|
|
*/
|
2006-01-19 08:43:53 +07:00
|
|
|
static long do_unlinkat(int dfd, const char __user *pathname)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
char * name;
|
|
|
|
struct dentry *dentry;
|
|
|
|
struct nameidata nd;
|
|
|
|
struct inode *inode = NULL;
|
|
|
|
|
|
|
|
name = getname(pathname);
|
|
|
|
if(IS_ERR(name))
|
|
|
|
return PTR_ERR(name);
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_path_lookup(dfd, name, LOOKUP_PARENT, &nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit;
|
|
|
|
error = -EISDIR;
|
|
|
|
if (nd.last_type != LAST_NORM)
|
|
|
|
goto exit1;
|
2006-07-03 14:25:05 +07:00
|
|
|
mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
|
2005-11-09 12:35:06 +07:00
|
|
|
dentry = lookup_hash(&nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
error = PTR_ERR(dentry);
|
|
|
|
if (!IS_ERR(dentry)) {
|
|
|
|
/* Why not before? Because we want correct error value */
|
|
|
|
if (nd.last.name[nd.last.len])
|
|
|
|
goto slashes;
|
|
|
|
inode = dentry->d_inode;
|
|
|
|
if (inode)
|
|
|
|
atomic_inc(&inode->i_count);
|
|
|
|
error = vfs_unlink(nd.dentry->d_inode, dentry);
|
|
|
|
exit2:
|
|
|
|
dput(dentry);
|
|
|
|
}
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&nd.dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (inode)
|
|
|
|
iput(inode); /* truncate the inode here */
|
|
|
|
exit1:
|
|
|
|
path_release(&nd);
|
|
|
|
exit:
|
|
|
|
putname(name);
|
|
|
|
return error;
|
|
|
|
|
|
|
|
slashes:
|
|
|
|
error = !dentry->d_inode ? -ENOENT :
|
|
|
|
S_ISDIR(dentry->d_inode->i_mode) ? -EISDIR : -ENOTDIR;
|
|
|
|
goto exit2;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_unlinkat(int dfd, const char __user *pathname, int flag)
|
|
|
|
{
|
|
|
|
if ((flag & ~AT_REMOVEDIR) != 0)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (flag & AT_REMOVEDIR)
|
|
|
|
return do_rmdir(dfd, pathname);
|
|
|
|
|
|
|
|
return do_unlinkat(dfd, pathname);
|
|
|
|
}
|
|
|
|
|
|
|
|
asmlinkage long sys_unlink(const char __user *pathname)
|
|
|
|
{
|
|
|
|
return do_unlinkat(AT_FDCWD, pathname);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, int mode)
|
|
|
|
{
|
|
|
|
int error = may_create(dir, dentry, NULL);
|
|
|
|
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!dir->i_op || !dir->i_op->symlink)
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
error = security_inode_symlink(dir, dentry, oldname);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
DQUOT_INIT(dir);
|
|
|
|
error = dir->i_op->symlink(dir, dentry, oldname);
|
2005-09-10 03:01:44 +07:00
|
|
|
if (!error)
|
2005-11-03 22:57:06 +07:00
|
|
|
fsnotify_create(dir, dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_symlinkat(const char __user *oldname,
|
|
|
|
int newdfd, const char __user *newname)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
char * from;
|
|
|
|
char * to;
|
2006-10-01 13:29:01 +07:00
|
|
|
struct dentry *dentry;
|
|
|
|
struct nameidata nd;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
from = getname(oldname);
|
|
|
|
if(IS_ERR(from))
|
|
|
|
return PTR_ERR(from);
|
|
|
|
to = getname(newname);
|
|
|
|
error = PTR_ERR(to);
|
2006-10-01 13:29:01 +07:00
|
|
|
if (IS_ERR(to))
|
|
|
|
goto out_putname;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
2006-10-01 13:29:01 +07:00
|
|
|
error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd);
|
|
|
|
if (error)
|
|
|
|
goto out;
|
|
|
|
dentry = lookup_create(&nd, 0);
|
|
|
|
error = PTR_ERR(dentry);
|
|
|
|
if (IS_ERR(dentry))
|
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO);
|
|
|
|
dput(dentry);
|
|
|
|
out_unlock:
|
|
|
|
mutex_unlock(&nd.dentry->d_inode->i_mutex);
|
|
|
|
path_release(&nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
out:
|
2006-10-01 13:29:01 +07:00
|
|
|
putname(to);
|
|
|
|
out_putname:
|
2005-04-17 05:20:36 +07:00
|
|
|
putname(from);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_symlink(const char __user *oldname, const char __user *newname)
|
|
|
|
{
|
|
|
|
return sys_symlinkat(oldname, AT_FDCWD, newname);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry)
|
|
|
|
{
|
|
|
|
struct inode *inode = old_dentry->d_inode;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
if (!inode)
|
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
error = may_create(dir, new_dentry, NULL);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (dir->i_sb != inode->i_sb)
|
|
|
|
return -EXDEV;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A link to an append-only or immutable file cannot be created.
|
|
|
|
*/
|
|
|
|
if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
|
|
|
|
return -EPERM;
|
|
|
|
if (!dir->i_op || !dir->i_op->link)
|
|
|
|
return -EPERM;
|
|
|
|
if (S_ISDIR(old_dentry->d_inode->i_mode))
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
error = security_inode_link(old_dentry, dir, new_dentry);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&old_dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
DQUOT_INIT(dir);
|
|
|
|
error = dir->i_op->link(old_dentry, dir, new_dentry);
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&old_dentry->d_inode->i_mutex);
|
2005-09-10 03:01:45 +07:00
|
|
|
if (!error)
|
2005-11-03 22:57:06 +07:00
|
|
|
fsnotify_create(dir, new_dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Hardlinks are often used in delicate situations. We avoid
|
|
|
|
* security-related surprises by not following symlinks on the
|
|
|
|
* newname. --KAB
|
|
|
|
*
|
|
|
|
* We don't follow them on the oldname either to be compatible
|
|
|
|
* with linux 2.0, and to avoid hard-linking to directories
|
|
|
|
* and other special files. --ADM
|
|
|
|
*/
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
|
2006-02-25 04:04:21 +07:00
|
|
|
int newdfd, const char __user *newname,
|
|
|
|
int flags)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
struct dentry *new_dentry;
|
|
|
|
struct nameidata nd, old_nd;
|
|
|
|
int error;
|
|
|
|
char * to;
|
|
|
|
|
2006-06-25 19:49:11 +07:00
|
|
|
if ((flags & ~AT_SYMLINK_FOLLOW) != 0)
|
2006-02-25 04:04:21 +07:00
|
|
|
return -EINVAL;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
to = getname(newname);
|
|
|
|
if (IS_ERR(to))
|
|
|
|
return PTR_ERR(to);
|
|
|
|
|
2006-06-25 19:49:11 +07:00
|
|
|
error = __user_walk_fd(olddfd, oldname,
|
|
|
|
flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0,
|
|
|
|
&old_nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit;
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto out;
|
|
|
|
error = -EXDEV;
|
|
|
|
if (old_nd.mnt != nd.mnt)
|
|
|
|
goto out_release;
|
|
|
|
new_dentry = lookup_create(&nd, 0);
|
|
|
|
error = PTR_ERR(new_dentry);
|
2006-10-01 13:29:01 +07:00
|
|
|
if (IS_ERR(new_dentry))
|
|
|
|
goto out_unlock;
|
|
|
|
error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry);
|
|
|
|
dput(new_dentry);
|
|
|
|
out_unlock:
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&nd.dentry->d_inode->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
out_release:
|
|
|
|
path_release(&nd);
|
|
|
|
out:
|
|
|
|
path_release(&old_nd);
|
|
|
|
exit:
|
|
|
|
putname(to);
|
|
|
|
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_link(const char __user *oldname, const char __user *newname)
|
|
|
|
{
|
2006-02-25 04:04:21 +07:00
|
|
|
return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
|
2006-01-19 08:43:53 +07:00
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* The worst of all namespace operations - renaming directory. "Perverted"
|
|
|
|
* doesn't even start to describe it. Somebody in UCB had a heck of a trip...
|
|
|
|
* Problems:
|
|
|
|
* a) we can get into loop creation. Check is done in is_subdir().
|
|
|
|
* b) race potential - two innocent renames can create a loop together.
|
|
|
|
* That's where 4.4 screws up. Current fix: serialization on
|
2006-03-23 18:00:33 +07:00
|
|
|
* sb->s_vfs_rename_mutex. We might be more accurate, but that's another
|
2005-04-17 05:20:36 +07:00
|
|
|
* story.
|
|
|
|
* c) we have to lock _three_ objects - parents and victim (if it exists).
|
2006-01-10 06:59:24 +07:00
|
|
|
* And that - after we got ->i_mutex on parents (until then we don't know
|
2005-04-17 05:20:36 +07:00
|
|
|
* whether the target exists). Solution: try to be smart with locking
|
|
|
|
* order for inodes. We rely on the fact that tree topology may change
|
2006-03-23 18:00:33 +07:00
|
|
|
* only under ->s_vfs_rename_mutex _and_ that parent of the object we
|
2005-04-17 05:20:36 +07:00
|
|
|
* move will be locked. Thus we can rank directories by the tree
|
|
|
|
* (ancestors first) and rank all non-directories after them.
|
|
|
|
* That works since everybody except rename does "lock parent, lookup,
|
2006-03-23 18:00:33 +07:00
|
|
|
* lock child" and rename is under ->s_vfs_rename_mutex.
|
2005-04-17 05:20:36 +07:00
|
|
|
* HOWEVER, it relies on the assumption that any object with ->lookup()
|
|
|
|
* has no more than 1 dentry. If "hybrid" objects will ever appear,
|
|
|
|
* we'd better make sure that there's no link(2) for them.
|
|
|
|
* d) some filesystems don't support opened-but-unlinked directories,
|
|
|
|
* either because of layout or because they are not ready to deal with
|
|
|
|
* all cases correctly. The latter will be fixed (taking this sort of
|
|
|
|
* stuff into VFS), but the former is not going away. Solution: the same
|
|
|
|
* trick as in rmdir().
|
|
|
|
* e) conversion from fhandle to dentry may come in the wrong moment - when
|
2006-01-10 06:59:24 +07:00
|
|
|
* we are removing the target. Solution: we will have to grab ->i_mutex
|
2005-04-17 05:20:36 +07:00
|
|
|
* in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
|
2006-01-10 06:59:24 +07:00
|
|
|
* ->i_mutex on parents, which works but leads to some truely excessive
|
2005-04-17 05:20:36 +07:00
|
|
|
* locking].
|
|
|
|
*/
|
2005-05-06 06:16:09 +07:00
|
|
|
static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
|
|
|
|
struct inode *new_dir, struct dentry *new_dentry)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
struct inode *target;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If we are going to change the parent - check write permissions,
|
|
|
|
* we'll need to flip '..'.
|
|
|
|
*/
|
|
|
|
if (new_dir != old_dir) {
|
|
|
|
error = permission(old_dentry->d_inode, MAY_WRITE, NULL);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
target = new_dentry->d_inode;
|
|
|
|
if (target) {
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&target->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
dentry_unhash(new_dentry);
|
|
|
|
}
|
|
|
|
if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
|
|
|
|
error = -EBUSY;
|
|
|
|
else
|
|
|
|
error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
|
|
|
|
if (target) {
|
|
|
|
if (!error)
|
|
|
|
target->i_flags |= S_DEAD;
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&target->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (d_unhashed(new_dentry))
|
|
|
|
d_rehash(new_dentry);
|
|
|
|
dput(new_dentry);
|
|
|
|
}
|
2005-09-10 03:01:45 +07:00
|
|
|
if (!error)
|
2006-09-09 04:22:21 +07:00
|
|
|
if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
|
|
|
|
d_move(old_dentry,new_dentry);
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2005-05-06 06:16:09 +07:00
|
|
|
static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
|
|
|
|
struct inode *new_dir, struct dentry *new_dentry)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
struct inode *target;
|
|
|
|
int error;
|
|
|
|
|
|
|
|
error = security_inode_rename(old_dir, old_dentry, new_dir, new_dentry);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
dget(new_dentry);
|
|
|
|
target = new_dentry->d_inode;
|
|
|
|
if (target)
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_lock(&target->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
|
|
|
|
error = -EBUSY;
|
|
|
|
else
|
|
|
|
error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry);
|
|
|
|
if (!error) {
|
2006-09-09 04:22:21 +07:00
|
|
|
if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE))
|
2005-04-17 05:20:36 +07:00
|
|
|
d_move(old_dentry, new_dentry);
|
|
|
|
}
|
|
|
|
if (target)
|
2006-01-10 06:59:24 +07:00
|
|
|
mutex_unlock(&target->i_mutex);
|
2005-04-17 05:20:36 +07:00
|
|
|
dput(new_dentry);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
|
|
|
|
struct inode *new_dir, struct dentry *new_dentry)
|
|
|
|
{
|
|
|
|
int error;
|
|
|
|
int is_dir = S_ISDIR(old_dentry->d_inode->i_mode);
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:06:03 +07:00
|
|
|
const char *old_name;
|
2005-04-17 05:20:36 +07:00
|
|
|
|
|
|
|
if (old_dentry->d_inode == new_dentry->d_inode)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
error = may_delete(old_dir, old_dentry, is_dir);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!new_dentry->d_inode)
|
|
|
|
error = may_create(new_dir, new_dentry, NULL);
|
|
|
|
else
|
|
|
|
error = may_delete(new_dir, new_dentry, is_dir);
|
|
|
|
if (error)
|
|
|
|
return error;
|
|
|
|
|
|
|
|
if (!old_dir->i_op || !old_dir->i_op->rename)
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
DQUOT_INIT(old_dir);
|
|
|
|
DQUOT_INIT(new_dir);
|
|
|
|
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:06:03 +07:00
|
|
|
old_name = fsnotify_oldname_init(old_dentry->d_name.name);
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
if (is_dir)
|
|
|
|
error = vfs_rename_dir(old_dir,old_dentry,new_dir,new_dentry);
|
|
|
|
else
|
|
|
|
error = vfs_rename_other(old_dir,old_dentry,new_dir,new_dentry);
|
|
|
|
if (!error) {
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:06:03 +07:00
|
|
|
const char *new_name = old_dentry->d_name.name;
|
2005-08-15 23:13:28 +07:00
|
|
|
fsnotify_move(old_dir, new_dir, old_name, new_name, is_dir,
|
|
|
|
new_dentry->d_inode, old_dentry->d_inode);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
[PATCH] inotify
inotify is intended to correct the deficiencies of dnotify, particularly
its inability to scale and its terrible user interface:
* dnotify requires the opening of one fd per each directory
that you intend to watch. This quickly results in too many
open files and pins removable media, preventing unmount.
* dnotify is directory-based. You only learn about changes to
directories. Sure, a change to a file in a directory affects
the directory, but you are then forced to keep a cache of
stat structures.
* dnotify's interface to user-space is awful. Signals?
inotify provides a more usable, simple, powerful solution to file change
notification:
* inotify's interface is a system call that returns a fd, not SIGIO.
You get a single fd, which is select()-able.
* inotify has an event that says "the filesystem that the item
you were watching is on was unmounted."
* inotify can watch directories or files.
Inotify is currently used by Beagle (a desktop search infrastructure),
Gamin (a FAM replacement), and other projects.
See Documentation/filesystems/inotify.txt.
Signed-off-by: Robert Love <rml@novell.com>
Cc: John McCutchan <ttb@tentacle.dhs.org>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-07-13 04:06:03 +07:00
|
|
|
fsnotify_oldname_free(old_name);
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
static int do_rename(int olddfd, const char *oldname,
|
|
|
|
int newdfd, const char *newname)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error = 0;
|
|
|
|
struct dentry * old_dir, * new_dir;
|
|
|
|
struct dentry * old_dentry, *new_dentry;
|
|
|
|
struct dentry * trap;
|
|
|
|
struct nameidata oldnd, newnd;
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_path_lookup(olddfd, oldname, LOOKUP_PARENT, &oldnd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit;
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_path_lookup(newdfd, newname, LOOKUP_PARENT, &newnd);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (error)
|
|
|
|
goto exit1;
|
|
|
|
|
|
|
|
error = -EXDEV;
|
|
|
|
if (oldnd.mnt != newnd.mnt)
|
|
|
|
goto exit2;
|
|
|
|
|
|
|
|
old_dir = oldnd.dentry;
|
|
|
|
error = -EBUSY;
|
|
|
|
if (oldnd.last_type != LAST_NORM)
|
|
|
|
goto exit2;
|
|
|
|
|
|
|
|
new_dir = newnd.dentry;
|
|
|
|
if (newnd.last_type != LAST_NORM)
|
|
|
|
goto exit2;
|
|
|
|
|
|
|
|
trap = lock_rename(new_dir, old_dir);
|
|
|
|
|
2005-11-09 12:35:06 +07:00
|
|
|
old_dentry = lookup_hash(&oldnd);
|
2005-04-17 05:20:36 +07:00
|
|
|
error = PTR_ERR(old_dentry);
|
|
|
|
if (IS_ERR(old_dentry))
|
|
|
|
goto exit3;
|
|
|
|
/* source must exist */
|
|
|
|
error = -ENOENT;
|
|
|
|
if (!old_dentry->d_inode)
|
|
|
|
goto exit4;
|
|
|
|
/* unless the source is a directory trailing slashes give -ENOTDIR */
|
|
|
|
if (!S_ISDIR(old_dentry->d_inode->i_mode)) {
|
|
|
|
error = -ENOTDIR;
|
|
|
|
if (oldnd.last.name[oldnd.last.len])
|
|
|
|
goto exit4;
|
|
|
|
if (newnd.last.name[newnd.last.len])
|
|
|
|
goto exit4;
|
|
|
|
}
|
|
|
|
/* source should not be ancestor of target */
|
|
|
|
error = -EINVAL;
|
|
|
|
if (old_dentry == trap)
|
|
|
|
goto exit4;
|
2005-11-09 12:35:06 +07:00
|
|
|
new_dentry = lookup_hash(&newnd);
|
2005-04-17 05:20:36 +07:00
|
|
|
error = PTR_ERR(new_dentry);
|
|
|
|
if (IS_ERR(new_dentry))
|
|
|
|
goto exit4;
|
|
|
|
/* target should not be an ancestor of source */
|
|
|
|
error = -ENOTEMPTY;
|
|
|
|
if (new_dentry == trap)
|
|
|
|
goto exit5;
|
|
|
|
|
|
|
|
error = vfs_rename(old_dir->d_inode, old_dentry,
|
|
|
|
new_dir->d_inode, new_dentry);
|
|
|
|
exit5:
|
|
|
|
dput(new_dentry);
|
|
|
|
exit4:
|
|
|
|
dput(old_dentry);
|
|
|
|
exit3:
|
|
|
|
unlock_rename(new_dir, old_dir);
|
|
|
|
exit2:
|
|
|
|
path_release(&newnd);
|
|
|
|
exit1:
|
|
|
|
path_release(&oldnd);
|
|
|
|
exit:
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_renameat(int olddfd, const char __user *oldname,
|
|
|
|
int newdfd, const char __user *newname)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
int error;
|
|
|
|
char * from;
|
|
|
|
char * to;
|
|
|
|
|
|
|
|
from = getname(oldname);
|
|
|
|
if(IS_ERR(from))
|
|
|
|
return PTR_ERR(from);
|
|
|
|
to = getname(newname);
|
|
|
|
error = PTR_ERR(to);
|
|
|
|
if (!IS_ERR(to)) {
|
2006-01-19 08:43:53 +07:00
|
|
|
error = do_rename(olddfd, from, newdfd, to);
|
2005-04-17 05:20:36 +07:00
|
|
|
putname(to);
|
|
|
|
}
|
|
|
|
putname(from);
|
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
2006-01-19 08:43:53 +07:00
|
|
|
asmlinkage long sys_rename(const char __user *oldname, const char __user *newname)
|
|
|
|
{
|
|
|
|
return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname);
|
|
|
|
}
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link)
|
|
|
|
{
|
|
|
|
int len;
|
|
|
|
|
|
|
|
len = PTR_ERR(link);
|
|
|
|
if (IS_ERR(link))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
len = strlen(link);
|
|
|
|
if (len > (unsigned) buflen)
|
|
|
|
len = buflen;
|
|
|
|
if (copy_to_user(buffer, link, len))
|
|
|
|
len = -EFAULT;
|
|
|
|
out:
|
|
|
|
return len;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* A helper for ->readlink(). This should be used *ONLY* for symlinks that
|
|
|
|
* have ->follow_link() touching nd only in nd_set_link(). Using (or not
|
|
|
|
* using) it for any given inode is up to filesystem.
|
|
|
|
*/
|
|
|
|
int generic_readlink(struct dentry *dentry, char __user *buffer, int buflen)
|
|
|
|
{
|
|
|
|
struct nameidata nd;
|
2005-08-20 08:02:56 +07:00
|
|
|
void *cookie;
|
|
|
|
|
2005-04-17 05:20:36 +07:00
|
|
|
nd.depth = 0;
|
2005-08-20 08:02:56 +07:00
|
|
|
cookie = dentry->d_inode->i_op->follow_link(dentry, &nd);
|
|
|
|
if (!IS_ERR(cookie)) {
|
|
|
|
int res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
|
2005-04-17 05:20:36 +07:00
|
|
|
if (dentry->d_inode->i_op->put_link)
|
2005-08-20 08:02:56 +07:00
|
|
|
dentry->d_inode->i_op->put_link(dentry, &nd, cookie);
|
|
|
|
cookie = ERR_PTR(res);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
2005-08-20 08:02:56 +07:00
|
|
|
return PTR_ERR(cookie);
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
int vfs_follow_link(struct nameidata *nd, const char *link)
|
|
|
|
{
|
|
|
|
return __vfs_follow_link(nd, link);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* get the link contents into pagecache */
|
|
|
|
static char *page_getlink(struct dentry * dentry, struct page **ppage)
|
|
|
|
{
|
|
|
|
struct page * page;
|
|
|
|
struct address_space *mapping = dentry->d_inode->i_mapping;
|
2006-06-23 16:05:08 +07:00
|
|
|
page = read_mapping_page(mapping, 0, NULL);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (IS_ERR(page))
|
2007-05-07 04:49:04 +07:00
|
|
|
return (char*)page;
|
2005-04-17 05:20:36 +07:00
|
|
|
*ppage = page;
|
|
|
|
return kmap(page);
|
|
|
|
}
|
|
|
|
|
|
|
|
int page_readlink(struct dentry *dentry, char __user *buffer, int buflen)
|
|
|
|
{
|
|
|
|
struct page *page = NULL;
|
|
|
|
char *s = page_getlink(dentry, &page);
|
|
|
|
int res = vfs_readlink(dentry,buffer,buflen,s);
|
|
|
|
if (page) {
|
|
|
|
kunmap(page);
|
|
|
|
page_cache_release(page);
|
|
|
|
}
|
|
|
|
return res;
|
|
|
|
}
|
|
|
|
|
2005-08-20 08:02:56 +07:00
|
|
|
void *page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2005-08-20 08:02:56 +07:00
|
|
|
struct page *page = NULL;
|
2005-04-17 05:20:36 +07:00
|
|
|
nd_set_link(nd, page_getlink(dentry, &page));
|
2005-08-20 08:02:56 +07:00
|
|
|
return page;
|
2005-04-17 05:20:36 +07:00
|
|
|
}
|
|
|
|
|
2005-08-20 08:02:56 +07:00
|
|
|
void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
2005-08-20 08:02:56 +07:00
|
|
|
struct page *page = cookie;
|
|
|
|
|
|
|
|
if (page) {
|
2005-04-17 05:20:36 +07:00
|
|
|
kunmap(page);
|
|
|
|
page_cache_release(page);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2006-03-11 18:27:13 +07:00
|
|
|
int __page_symlink(struct inode *inode, const char *symname, int len,
|
|
|
|
gfp_t gfp_mask)
|
2005-04-17 05:20:36 +07:00
|
|
|
{
|
|
|
|
struct address_space *mapping = inode->i_mapping;
|
2006-03-11 18:27:13 +07:00
|
|
|
struct page *page;
|
2007-02-16 16:27:18 +07:00
|
|
|
int err;
|
2005-04-17 05:20:36 +07:00
|
|
|
char *kaddr;
|
|
|
|
|
2006-03-25 18:07:57 +07:00
|
|
|
retry:
|
2007-02-16 16:27:18 +07:00
|
|
|
err = -ENOMEM;
|
2006-03-11 18:27:13 +07:00
|
|
|
page = find_or_create_page(mapping, 0, gfp_mask);
|
2005-04-17 05:20:36 +07:00
|
|
|
if (!page)
|
|
|
|
goto fail;
|
|
|
|
err = mapping->a_ops->prepare_write(NULL, page, 0, len-1);
|
2006-03-25 18:07:57 +07:00
|
|
|
if (err == AOP_TRUNCATED_PAGE) {
|
|
|
|
page_cache_release(page);
|
|
|
|
goto retry;
|
|
|
|
}
|
2005-04-17 05:20:36 +07:00
|
|
|
if (err)
|
|
|
|
goto fail_map;
|
|
|
|
kaddr = kmap_atomic(page, KM_USER0);
|
|
|
|
memcpy(kaddr, symname, len-1);
|
|
|
|
kunmap_atomic(kaddr, KM_USER0);
|
2006-03-25 18:07:57 +07:00
|
|
|
err = mapping->a_ops->commit_write(NULL, page, 0, len-1);
|
|
|
|
if (err == AOP_TRUNCATED_PAGE) {
|
|
|
|
page_cache_release(page);
|
|
|
|
goto retry;
|
|
|
|
}
|
|
|
|
if (err)
|
|
|
|
goto fail_map;
|
2005-04-17 05:20:36 +07:00
|
|
|
/*
|
|
|
|
* Notice that we are _not_ going to block here - end of page is
|
|
|
|
* unmapped, so this will only try to map the rest of page, see
|
|
|
|
* that it is unmapped (typically even will not look into inode -
|
|
|
|
* ->i_size will be enough for everything) and zero it out.
|
|
|
|
* OTOH it's obviously correct and should make the page up-to-date.
|
|
|
|
*/
|
|
|
|
if (!PageUptodate(page)) {
|
|
|
|
err = mapping->a_ops->readpage(NULL, page);
|
2006-03-25 18:07:57 +07:00
|
|
|
if (err != AOP_TRUNCATED_PAGE)
|
|
|
|
wait_on_page_locked(page);
|
2005-04-17 05:20:36 +07:00
|
|
|
} else {
|
|
|
|
unlock_page(page);
|
|
|
|
}
|
|
|
|
page_cache_release(page);
|
|
|
|
if (err < 0)
|
|
|
|
goto fail;
|
|
|
|
mark_inode_dirty(inode);
|
|
|
|
return 0;
|
|
|
|
fail_map:
|
|
|
|
unlock_page(page);
|
|
|
|
page_cache_release(page);
|
|
|
|
fail:
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2006-03-11 18:27:13 +07:00
|
|
|
int page_symlink(struct inode *inode, const char *symname, int len)
|
|
|
|
{
|
|
|
|
return __page_symlink(inode, symname, len,
|
|
|
|
mapping_gfp_mask(inode->i_mapping));
|
|
|
|
}
|
|
|
|
|
2007-02-12 15:55:39 +07:00
|
|
|
const struct inode_operations page_symlink_inode_operations = {
|
2005-04-17 05:20:36 +07:00
|
|
|
.readlink = generic_readlink,
|
|
|
|
.follow_link = page_follow_link_light,
|
|
|
|
.put_link = page_put_link,
|
|
|
|
};
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(__user_walk);
|
2006-01-19 08:43:53 +07:00
|
|
|
EXPORT_SYMBOL(__user_walk_fd);
|
2005-04-17 05:20:36 +07:00
|
|
|
EXPORT_SYMBOL(follow_down);
|
|
|
|
EXPORT_SYMBOL(follow_up);
|
|
|
|
EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
|
|
|
|
EXPORT_SYMBOL(getname);
|
|
|
|
EXPORT_SYMBOL(lock_rename);
|
|
|
|
EXPORT_SYMBOL(lookup_one_len);
|
|
|
|
EXPORT_SYMBOL(page_follow_link_light);
|
|
|
|
EXPORT_SYMBOL(page_put_link);
|
|
|
|
EXPORT_SYMBOL(page_readlink);
|
2006-03-11 18:27:13 +07:00
|
|
|
EXPORT_SYMBOL(__page_symlink);
|
2005-04-17 05:20:36 +07:00
|
|
|
EXPORT_SYMBOL(page_symlink);
|
|
|
|
EXPORT_SYMBOL(page_symlink_inode_operations);
|
|
|
|
EXPORT_SYMBOL(path_lookup);
|
fs: introduce vfs_path_lookup
Stackable file systems, among others, frequently need to lookup paths or
path components starting from an arbitrary point in the namespace
(identified by a dentry and a vfsmount). Currently, such file systems use
lookup_one_len, which is frowned upon [1] as it does not pass the lookup
intent along; not passing a lookup intent, for example, can trigger BUG_ON's
when stacking on top of NFSv4.
The first patch introduces a new lookup function to allow lookup starting
from an arbitrary point in the namespace. This approach has been suggested
by Christoph Hellwig [2].
The second patch changes sunrpc to use vfs_path_lookup.
The third patch changes nfsctl.c to use vfs_path_lookup.
The fourth patch marks link_path_walk static.
The fifth, and last patch, unexports path_walk because it is no longer
unnecessary to call it directly, and using the new vfs_path_lookup is
cleaner.
For example, the following snippet of code, looks up "some/path/component"
in a directory pointed to by parent_{dentry,vfsmnt}:
err = vfs_path_lookup(parent_dentry, parent_vfsmnt,
"some/path/component", 0, &nd);
if (!err) {
/* exits */
...
/* once done, release the references */
path_release(&nd);
} else if (err == -ENOENT) {
/* doesn't exist */
} else {
/* other error */
}
VFS functions such as lookup_create can be used on the nameidata structure
to pass the create intent to the file system.
Signed-off-by: Josef 'Jeff' Sipek <jsipek@cs.sunysb.edu>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Acked-by: Christoph Hellwig <hch@lst.de>
Cc: Trond Myklebust <trond.myklebust@fys.uio.no>
Cc: Neil Brown <neilb@suse.de>
Cc: Michael Halcrow <mhalcrow@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-19 15:48:18 +07:00
|
|
|
EXPORT_SYMBOL(vfs_path_lookup);
|
2005-04-17 05:20:36 +07:00
|
|
|
EXPORT_SYMBOL(path_release);
|
|
|
|
EXPORT_SYMBOL(permission);
|
2005-11-09 12:35:04 +07:00
|
|
|
EXPORT_SYMBOL(vfs_permission);
|
2005-11-09 12:35:04 +07:00
|
|
|
EXPORT_SYMBOL(file_permission);
|
2005-04-17 05:20:36 +07:00
|
|
|
EXPORT_SYMBOL(unlock_rename);
|
|
|
|
EXPORT_SYMBOL(vfs_create);
|
|
|
|
EXPORT_SYMBOL(vfs_follow_link);
|
|
|
|
EXPORT_SYMBOL(vfs_link);
|
|
|
|
EXPORT_SYMBOL(vfs_mkdir);
|
|
|
|
EXPORT_SYMBOL(vfs_mknod);
|
|
|
|
EXPORT_SYMBOL(generic_permission);
|
|
|
|
EXPORT_SYMBOL(vfs_readlink);
|
|
|
|
EXPORT_SYMBOL(vfs_rename);
|
|
|
|
EXPORT_SYMBOL(vfs_rmdir);
|
|
|
|
EXPORT_SYMBOL(vfs_symlink);
|
|
|
|
EXPORT_SYMBOL(vfs_unlink);
|
|
|
|
EXPORT_SYMBOL(dentry_unhash);
|
|
|
|
EXPORT_SYMBOL(generic_readlink);
|