#include <linux/capability.h>
#include <linux/file.h>
#include <linux/fcntl.h>
-#include <linux/namei.h>
#include <asm/namei.h>
#include <asm/uaccess.h>
* any extra contention...
*/
+static int __link_path_walk(const char *name, struct nameidata *nd);
+
/* 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..
int permission(struct inode *inode, int mask, struct nameidata *nd)
{
- umode_t mode = inode->i_mode;
int retval, submask;
+ struct vfsmount *mnt = NULL;
+
+ if (nd)
+ mnt = nd->path.mnt;
if (mask & MAY_WRITE) {
+ umode_t mode = inode->i_mode;
/*
* Nobody gets write access to a read-only fs.
return -EACCES;
}
-
- /*
- * MAY_EXEC on regular files requires special handling: We override
- * filesystem execute permissions if the mode bits aren't set or
- * the fs is mounted with the "noexec" flag.
- */
- if ((mask & MAY_EXEC) && S_ISREG(mode) && (!(mode & S_IXUGO) ||
- (nd && nd->mnt && (nd->mnt->mnt_flags & MNT_NOEXEC))))
- return -EACCES;
+ if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) {
+ /*
+ * MAY_EXEC on regular files is denied if the fs is mounted
+ * with the "noexec" flag.
+ */
+ if (mnt && (mnt->mnt_flags & MNT_NOEXEC))
+ return -EACCES;
+ }
/* Ordinary permission routines do not understand MAY_APPEND. */
submask = mask & ~MAY_APPEND;
- if (inode->i_op && inode->i_op->permission)
+ if (inode->i_op && inode->i_op->permission) {
retval = inode->i_op->permission(inode, submask, nd);
- else
+ if (!retval) {
+ /*
+ * Exec permission on a regular file is denied if none
+ * of the execute bits are set.
+ *
+ * This check should be done by the ->permission()
+ * method.
+ */
+ if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode) &&
+ !(inode->i_mode & S_IXUGO))
+ return -EACCES;
+ }
+ } else {
retval = generic_permission(inode, submask, NULL);
+ }
if (retval)
return retval;
*/
int vfs_permission(struct nameidata *nd, int mask)
{
- return permission(nd->dentry->d_inode, mask, nd);
+ return permission(nd->path.dentry->d_inode, mask, nd);
}
/**
return 0;
}
-void path_release(struct nameidata *nd)
+/**
+ * path_get - get a reference to a path
+ * @path: path to get the reference to
+ *
+ * Given a path increment the reference count to the dentry and the vfsmount.
+ */
+void path_get(struct path *path)
{
- dput(nd->dentry);
- mntput(nd->mnt);
+ mntget(path->mnt);
+ dget(path->dentry);
}
+EXPORT_SYMBOL(path_get);
-/*
- * umount() mustn't call path_release()/mntput() as that would clear
- * mnt_expiry_mark
+/**
+ * path_put - put a reference to a path
+ * @path: path to put the reference to
+ *
+ * Given a path decrement the reference count to the dentry and the vfsmount.
*/
-void path_release_on_umount(struct nameidata *nd)
+void path_put(struct path *path)
{
- dput(nd->dentry);
- mntput_no_expire(nd->mnt);
+ dput(path->dentry);
+ mntput(path->mnt);
}
+EXPORT_SYMBOL(path_put);
/**
* release_open_intent - free up open intent resources
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);
+ if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) {
+ nd->path = fs->altroot;
+ path_get(&fs->altroot);
read_unlock(&fs->lock);
if (__emul_lookup_dentry(name,nd))
return 0;
read_lock(&fs->lock);
}
- nd->mnt = mntget(fs->rootmnt);
- nd->dentry = dget(fs->root);
+ nd->path = fs->root;
+ path_get(&fs->root);
read_unlock(&fs->lock);
return 1;
}
+/*
+ * 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.
+ */
+static __always_inline int link_path_walk(const char *name, struct nameidata *nd)
+{
+ struct path save = nd->path;
+ 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->path had been dropped */
+ nd->path = save;
+ dget(nd->path.dentry);
+ mntget(nd->path.mnt);
+ nd->flags |= LOOKUP_REVAL;
+ result = __link_path_walk(name, nd);
+ }
+
+ path_put(&save);
+
+ return result;
+}
+
static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link)
{
int res = 0;
goto fail;
if (*link == '/') {
- path_release(nd);
+ path_put(&nd->path);
if (!walk_init_root(link, nd))
/* weird __emul_prefix() stuff did it */
goto out;
*/
name = __getname();
if (unlikely(!name)) {
- path_release(nd);
+ path_put(&nd->path);
return -ENOMEM;
}
strcpy(name, nd->last.name);
nd->last.name = name;
return 0;
fail:
- path_release(nd);
+ path_put(&nd->path);
return PTR_ERR(link);
}
-static inline void dput_path(struct path *path, struct nameidata *nd)
+static void path_put_conditional(struct path *path, struct nameidata *nd)
{
dput(path->dentry);
- if (path->mnt != nd->mnt)
+ if (path->mnt != nd->path.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;
+ dput(nd->path.dentry);
+ if (nd->path.mnt != path->mnt)
+ mntput(nd->path.mnt);
+ nd->path.mnt = path->mnt;
+ nd->path.dentry = path->dentry;
}
static __always_inline int __do_follow_link(struct path *path, struct nameidata *nd)
touch_atime(path->mnt, dentry);
nd_set_link(nd, NULL);
- if (path->mnt != nd->mnt) {
+ if (path->mnt != nd->path.mnt) {
path_to_nameidata(path, nd);
dget(dentry);
}
if (dentry->d_inode->i_op->put_link)
dentry->d_inode->i_op->put_link(dentry, nd, cookie);
}
- dput(dentry);
- mntput(path->mnt);
+ path_put(path);
return error;
}
nd->depth--;
return err;
loop:
- dput_path(path, nd);
- path_release(nd);
+ path_put_conditional(path, nd);
+ path_put(&nd->path);
return err;
}
while(1) {
struct vfsmount *parent;
- struct dentry *old = nd->dentry;
+ struct dentry *old = nd->path.dentry;
read_lock(&fs->lock);
- if (nd->dentry == fs->root &&
- nd->mnt == fs->rootmnt) {
+ if (nd->path.dentry == fs->root.dentry &&
+ nd->path.mnt == fs->root.mnt) {
read_unlock(&fs->lock);
break;
}
read_unlock(&fs->lock);
spin_lock(&dcache_lock);
- if (nd->dentry != nd->mnt->mnt_root) {
- nd->dentry = dget(nd->dentry->d_parent);
+ if (nd->path.dentry != nd->path.mnt->mnt_root) {
+ nd->path.dentry = dget(nd->path.dentry->d_parent);
spin_unlock(&dcache_lock);
dput(old);
break;
}
spin_unlock(&dcache_lock);
spin_lock(&vfsmount_lock);
- parent = nd->mnt->mnt_parent;
- if (parent == nd->mnt) {
+ parent = nd->path.mnt->mnt_parent;
+ if (parent == nd->path.mnt) {
spin_unlock(&vfsmount_lock);
break;
}
mntget(parent);
- nd->dentry = dget(nd->mnt->mnt_mountpoint);
+ nd->path.dentry = dget(nd->path.mnt->mnt_mountpoint);
spin_unlock(&vfsmount_lock);
dput(old);
- mntput(nd->mnt);
- nd->mnt = parent;
+ mntput(nd->path.mnt);
+ nd->path.mnt = parent;
}
- follow_mount(&nd->mnt, &nd->dentry);
+ follow_mount(&nd->path.mnt, &nd->path.dentry);
}
/*
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);
+ struct vfsmount *mnt = nd->path.mnt;
+ struct dentry *dentry = __d_lookup(nd->path.dentry, name);
if (!dentry)
goto need_lookup;
return 0;
need_lookup:
- dentry = real_lookup(nd->dentry, name, nd);
+ dentry = real_lookup(nd->path.dentry, name, nd);
if (IS_ERR(dentry))
goto fail;
goto done;
* Returns 0 and nd will have valid dentry and mnt on success.
* Returns error and drops reference to input namei data on failure.
*/
-static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
+static int __link_path_walk(const char *name, struct nameidata *nd)
{
struct path next;
struct inode *inode;
if (!*name)
goto return_reval;
- inode = nd->dentry->d_inode;
+ inode = nd->path.dentry->d_inode;
if (nd->depth)
lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE);
if (this.name[1] != '.')
break;
follow_dotdot(nd);
- inode = nd->dentry->d_inode;
+ inode = nd->path.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 (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) {
+ err = nd->path.dentry->d_op->d_hash(nd->path.dentry,
+ &this);
if (err < 0)
break;
}
if (err)
goto return_err;
err = -ENOENT;
- inode = nd->dentry->d_inode;
+ inode = nd->path.dentry->d_inode;
if (!inode)
break;
err = -ENOTDIR;
if (this.name[1] != '.')
break;
follow_dotdot(nd);
- inode = nd->dentry->d_inode;
+ inode = nd->path.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 (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) {
+ err = nd->path.dentry->d_op->d_hash(nd->path.dentry,
+ &this);
if (err < 0)
break;
}
err = do_follow_link(&next, nd);
if (err)
goto return_err;
- inode = nd->dentry->d_inode;
+ inode = nd->path.dentry->d_inode;
} else
path_to_nameidata(&next, nd);
err = -ENOENT;
* 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)) {
+ if (nd->path.dentry && nd->path.dentry->d_sb &&
+ (nd->path.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))
+ if (!nd->path.dentry->d_op->d_revalidate(
+ nd->path.dentry, nd))
break;
}
return_base:
return 0;
out_dput:
- dput_path(&next, nd);
+ path_put_conditional(&next, nd);
break;
}
- path_release(nd);
+ path_put(&nd->path);
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.
- */
-int fastcall link_path_walk(const char *name, struct nameidata *nd)
-{
- 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;
-}
-
-int fastcall path_walk(const char * name, struct nameidata *nd)
+static int path_walk(const char *name, struct nameidata *nd)
{
current->total_link_count = 0;
return link_path_walk(name, 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;
+ if (!nd->path.dentry->d_inode ||
+ S_ISDIR(nd->path.dentry->d_inode->i_mode)) {
+ struct path old_path = nd->path;
struct qstr last = nd->last;
int last_type = nd->last_type;
struct fs_struct *fs = current->fs;
*/
nd->last_type = LAST_ROOT;
read_lock(&fs->lock);
- nd->mnt = mntget(fs->rootmnt);
- nd->dentry = dget(fs->root);
+ nd->path = fs->root;
+ path_get(&fs->root);
read_unlock(&fs->lock);
if (path_walk(name, nd) == 0) {
- if (nd->dentry->d_inode) {
- dput(old_dentry);
- mntput(old_mnt);
+ if (nd->path.dentry->d_inode) {
+ path_put(&old_path);
return 1;
}
- path_release(nd);
+ path_put(&nd->path);
}
- nd->dentry = old_dentry;
- nd->mnt = old_mnt;
+ nd->path = old_path;
nd->last = last;
nd->last_type = last_type;
}
{
char *emul = __emul_prefix();
struct nameidata nd;
- struct vfsmount *mnt = NULL, *oldmnt;
- struct dentry *dentry = NULL, *olddentry;
+ struct path path = {}, old_path;
int err;
struct fs_struct *fs = current->fs;
if (!emul)
goto set_it;
err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd);
- if (!err) {
- mnt = nd.mnt;
- dentry = nd.dentry;
- }
+ if (!err)
+ path = nd.path;
set_it:
write_lock(&fs->lock);
- oldmnt = fs->altrootmnt;
- olddentry = fs->altroot;
- fs->altrootmnt = mnt;
- fs->altroot = dentry;
+ old_path = fs->altroot;
+ fs->altroot = path;
write_unlock(&fs->lock);
- if (olddentry) {
- dput(olddentry);
- mntput(oldmnt);
- }
+ if (old_path.dentry)
+ path_put(&old_path);
}
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
-static int fastcall do_path_lookup(int dfd, const char *name,
+static int do_path_lookup(int dfd, const char *name,
unsigned int flags, struct nameidata *nd)
{
int retval = 0;
if (*name=='/') {
read_lock(&fs->lock);
- if (fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
- nd->mnt = mntget(fs->altrootmnt);
- nd->dentry = dget(fs->altroot);
+ if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) {
+ nd->path = fs->altroot;
+ path_get(&fs->altroot);
read_unlock(&fs->lock);
if (__emul_lookup_dentry(name,nd))
goto out; /* found in altroot */
read_lock(&fs->lock);
}
- nd->mnt = mntget(fs->rootmnt);
- nd->dentry = dget(fs->root);
+ nd->path = fs->root;
+ path_get(&fs->root);
read_unlock(&fs->lock);
} else if (dfd == AT_FDCWD) {
read_lock(&fs->lock);
- nd->mnt = mntget(fs->pwdmnt);
- nd->dentry = dget(fs->pwd);
+ nd->path = fs->pwd;
+ path_get(&fs->pwd);
read_unlock(&fs->lock);
} else {
struct dentry *dentry;
if (retval)
goto fput_fail;
- nd->mnt = mntget(file->f_path.mnt);
- nd->dentry = dget(dentry);
+ nd->path = file->f_path;
+ path_get(&file->f_path);
fput_light(file, fput_needed);
}
- current->total_link_count = 0;
- retval = link_path_walk(name, nd);
+
+ retval = path_walk(name, nd);
out:
- if (likely(retval == 0)) {
- if (unlikely(!audit_dummy_context() && nd && nd->dentry &&
- nd->dentry->d_inode))
- audit_inode(name, nd->dentry->d_inode);
- }
+ if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
+ nd->path.dentry->d_inode))
+ audit_inode(name, nd->path.dentry);
out_fail:
return retval;
goto out_fail;
}
-int fastcall path_lookup(const char *name, unsigned int flags,
+int path_lookup(const char *name, unsigned int flags,
struct nameidata *nd)
{
return do_path_lookup(AT_FDCWD, name, flags, nd);
}
+/**
+ * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
+ * @dentry: pointer to dentry of the base directory
+ * @mnt: pointer to vfs mount of the base directory
+ * @name: pointer to file name
+ * @flags: lookup flags
+ * @nd: pointer to nameidata
+ */
+int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
+ const char *name, unsigned int flags,
+ struct nameidata *nd)
+{
+ int retval;
+
+ /* same as do_path_lookup */
+ nd->last_type = LAST_ROOT;
+ nd->flags = flags;
+ nd->depth = 0;
+
+ nd->path.mnt = mntget(mnt);
+ nd->path.dentry = dget(dentry);
+
+ retval = path_walk(name, nd);
+ if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry &&
+ nd->path.dentry->d_inode))
+ audit_inode(name, nd->path.dentry);
+
+ return retval;
+
+}
+
static int __path_lookup_intent_open(int dfd, const char *name,
unsigned int lookup_flags, struct nameidata *nd,
int open_flags, int create_mode)
if (IS_ERR(nd->intent.open.file)) {
if (err == 0) {
err = PTR_ERR(nd->intent.open.file);
- path_release(nd);
+ path_put(&nd->path);
}
} else if (err != 0)
release_open_intent(nd);
return err;
}
-static inline struct dentry *__lookup_hash_kern(struct qstr *name, struct dentry *base, struct nameidata *nd)
+static struct dentry *__lookup_hash(struct qstr *name,
+ struct dentry *base, struct nameidata *nd)
{
struct dentry *dentry;
struct inode *inode;
* 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)
+static struct dentry *lookup_hash(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);
+ err = permission(nd->path.dentry->d_inode, MAY_EXEC, nd);
if (err)
- goto out;
-
- dentry = __lookup_hash_kern(name, base, nd);
-out:
- return dentry;
-}
-
-static struct dentry *lookup_hash(struct nameidata *nd)
-{
- return __lookup_hash(&nd->last, nd->dentry, nd);
+ return ERR_PTR(err);
+ return __lookup_hash(&nd->last, nd->path.dentry, nd);
}
-/* SMP-safe */
-static inline int __lookup_one_len(const char *name, struct qstr *this, struct dentry *base, int len)
+static int __lookup_one_len(const char *name, struct qstr *this,
+ struct dentry *base, int len)
{
unsigned long hash;
unsigned int c;
return 0;
}
+/**
+ * lookup_one_len - filesystem helper to lookup single pathname component
+ * @name: pathname component to lookup
+ * @base: base directory to lookup from
+ * @len: maximum length @len should be interpreted to
+ *
+ * Note that this routine is purely a helper for filesystem usage and should
+ * not be called by generic code. Also note that by using this function the
+ * nameidata argument is passed to the filesystem methods and a filesystem
+ * using this helper needs to be prepared for that.
+ */
struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
{
int err;
err = __lookup_one_len(name, &this, base, len);
if (err)
return ERR_PTR(err);
+
+ err = permission(base->d_inode, MAY_EXEC, NULL);
+ if (err)
+ return ERR_PTR(err);
return __lookup_hash(&this, base, NULL);
}
-struct dentry *lookup_one_len_kern(const char *name, struct dentry *base, int len)
+/**
+ * lookup_one_noperm - bad hack for sysfs
+ * @name: pathname component to lookup
+ * @base: base directory to lookup from
+ *
+ * This is a variant of lookup_one_len that doesn't perform any permission
+ * checks. It's a horrible hack to work around the braindead sysfs
+ * architecture and should not be used anywhere else.
+ *
+ * DON'T USE THIS FUNCTION EVER, thanks.
+ */
+struct dentry *lookup_one_noperm(const char *name, struct dentry *base)
{
int err;
struct qstr this;
- err = __lookup_one_len(name, &this, base, len);
+ err = __lookup_one_len(name, &this, base, strlen(name));
if (err)
return ERR_PTR(err);
- return __lookup_hash_kern(&this, base, NULL);
+ return __lookup_hash(&this, base, NULL);
}
-int fastcall __user_walk_fd(int dfd, const char __user *name, unsigned flags,
+int __user_walk_fd(int dfd, const char __user *name, unsigned flags,
struct nameidata *nd)
{
char *tmp = getname(name);
return err;
}
-int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
+int __user_walk(const char __user *name, unsigned flags, struct nameidata *nd)
{
return __user_walk_fd(AT_FDCWD, name, flags, nd);
}
return -ENOENT;
BUG_ON(victim->d_parent->d_inode != dir);
- audit_inode_child(victim->d_name.name, victim->d_inode, dir);
+ audit_inode_child(victim->d_name.name, victim, dir);
error = permission(dir,MAY_WRITE | MAY_EXEC, NULL);
if (error)
int may_open(struct nameidata *nd, int acc_mode, int flag)
{
- struct dentry *dentry = nd->dentry;
+ struct dentry *dentry = nd->path.dentry;
struct inode *inode = dentry->d_inode;
int error;
if (S_ISLNK(inode->i_mode))
return -ELOOP;
- if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE))
+ if (S_ISDIR(inode->i_mode) && (acc_mode & MAY_WRITE))
return -EISDIR;
- error = vfs_permission(nd, acc_mode);
- 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
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)
+ if (nd->path.mnt->mnt_flags & MNT_NODEV)
return -EACCES;
flag &= ~O_TRUNC;
- } else if (IS_RDONLY(inode) && (flag & FMODE_WRITE))
- return -EROFS;
+ }
+
+ error = vfs_permission(nd, acc_mode);
+ if (error)
+ return error;
/*
* An append-only file must be opened in append mode for writing.
*/
/* O_NOATIME can only be set by the owner or superuser */
if (flag & O_NOATIME)
- if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
+ if (!is_owner_or_cap(inode))
return -EPERM;
/*
error = locks_verify_locked(inode);
if (!error) {
DQUOT_INIT(inode);
-
- error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL);
+
+ error = do_truncate(dentry, 0,
+ ATTR_MTIME|ATTR_CTIME|ATTR_OPEN,
+ NULL);
}
put_write_access(inode);
if (error)
return 0;
}
-static int open_namei_create(struct nameidata *nd, struct path *path,
+/*
+ * Be careful about ever adding any more callers of this
+ * function. Its flags must be in the namei format, not
+ * what get passed to sys_open().
+ */
+static int __open_namei_create(struct nameidata *nd, struct path *path,
int flag, int mode)
{
int error;
- struct dentry *dir = nd->dentry;
+ struct dentry *dir = nd->path.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;
+ dput(nd->path.dentry);
+ nd->path.dentry = path->dentry;
if (error)
return error;
/* Don't check for write permission, don't truncate */
}
/*
- * open_namei()
- *
- * namei for open - this is in fact almost the whole open-routine.
+ * Note that while the flag value (low two bits) for sys_open means:
+ * 00 - read-only
+ * 01 - write-only
+ * 10 - read-write
+ * 11 - special
+ * it is changed into
+ * 00 - no permissions needed
+ * 01 - read-permission
+ * 10 - write-permission
+ * 11 - read-write
+ * for the internal routines (ie open_namei()/follow_link() etc)
+ * This is more logical, and also allows the 00 "no perm needed"
+ * to be used for symlinks (where the permissions are checked
+ * later).
*
- * 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
+*/
+static inline int open_to_namei_flags(int flag)
+{
+ if ((flag+1) & O_ACCMODE)
+ flag++;
+ return flag;
+}
+
+static int open_will_write_to_fs(int flag, struct inode *inode)
+{
+ /*
+ * We'll never write to the fs underlying
+ * a device file.
+ */
+ if (special_file(inode->i_mode))
+ return 0;
+ return (flag & O_TRUNC);
+}
+
+/*
+ * Note that the low bits of the passed in "open_flag"
+ * are not the same as in the local variable "flag". See
+ * open_to_namei_flags() for more details.
*/
-int open_namei(int dfd, const char *pathname, int flag,
- int mode, struct nameidata *nd)
+struct file *do_filp_open(int dfd, const char *pathname,
+ int open_flag, int mode)
{
+ struct file *filp;
+ struct nameidata nd;
int acc_mode, error;
struct path path;
struct dentry *dir;
int count = 0;
+ int will_write;
+ int flag = open_to_namei_flags(open_flag);
acc_mode = ACC_MODE(flag);
*/
if (!(flag & O_CREAT)) {
error = path_lookup_open(dfd, pathname, lookup_flags(flag),
- nd, flag);
+ &nd, flag);
if (error)
- return error;
+ return ERR_PTR(error);
goto ok;
}
/*
* Create - we need to know the parent.
*/
- error = path_lookup_create(dfd,pathname,LOOKUP_PARENT,nd,flag,mode);
+ error = path_lookup_create(dfd, pathname, LOOKUP_PARENT,
+ &nd, flag, mode);
if (error)
- return error;
+ return ERR_PTR(error);
/*
* We have the parent and last component. First of all, check
* will not do.
*/
error = -EISDIR;
- if (nd->last_type != LAST_NORM || nd->last.name[nd->last.len])
+ if (nd.last_type != LAST_NORM || nd.last.name[nd.last.len])
goto exit;
- dir = nd->dentry;
- nd->flags &= ~LOOKUP_PARENT;
+ dir = nd.path.dentry;
+ nd.flags &= ~LOOKUP_PARENT;
mutex_lock(&dir->d_inode->i_mutex);
- path.dentry = lookup_hash(nd);
- path.mnt = nd->mnt;
+ path.dentry = lookup_hash(&nd);
+ path.mnt = nd.path.mnt;
do_last:
error = PTR_ERR(path.dentry);
goto exit;
}
- if (IS_ERR(nd->intent.open.file)) {
- mutex_unlock(&dir->d_inode->i_mutex);
- error = PTR_ERR(nd->intent.open.file);
- goto exit_dput;
+ if (IS_ERR(nd.intent.open.file)) {
+ error = PTR_ERR(nd.intent.open.file);
+ goto exit_mutex_unlock;
}
/* Negative dentry, just create the file */
if (!path.dentry->d_inode) {
- error = open_namei_create(nd, &path, flag, mode);
+ /*
+ * This write is needed to ensure that a
+ * ro->rw transition does not occur between
+ * the time when the file is created and when
+ * a permanent write count is taken through
+ * the 'struct file' in nameidata_to_filp().
+ */
+ error = mnt_want_write(nd.path.mnt);
if (error)
+ goto exit_mutex_unlock;
+ error = __open_namei_create(&nd, &path, flag, mode);
+ if (error) {
+ mnt_drop_write(nd.path.mnt);
goto exit;
- return 0;
+ }
+ filp = nameidata_to_filp(&nd, open_flag);
+ mnt_drop_write(nd.path.mnt);
+ return filp;
}
/*
* It already exists.
*/
mutex_unlock(&dir->d_inode->i_mutex);
- audit_inode_update(path.dentry->d_inode);
+ audit_inode(pathname, path.dentry);
error = -EEXIST;
if (flag & O_EXCL)
if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link)
goto do_link;
- path_to_nameidata(&path, nd);
+ path_to_nameidata(&path, &nd);
error = -EISDIR;
if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode))
goto exit;
ok:
- error = may_open(nd, acc_mode, flag);
- if (error)
+ /*
+ * Consider:
+ * 1. may_open() truncates a file
+ * 2. a rw->ro mount transition occurs
+ * 3. nameidata_to_filp() fails due to
+ * the ro mount.
+ * That would be inconsistent, and should
+ * be avoided. Taking this mnt write here
+ * ensures that (2) can not occur.
+ */
+ will_write = open_will_write_to_fs(flag, nd.path.dentry->d_inode);
+ if (will_write) {
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto exit;
+ }
+ error = may_open(&nd, acc_mode, flag);
+ if (error) {
+ if (will_write)
+ mnt_drop_write(nd.path.mnt);
goto exit;
- return 0;
+ }
+ filp = nameidata_to_filp(&nd, open_flag);
+ /*
+ * It is now safe to drop the mnt write
+ * because the filp has had a write taken
+ * on its behalf.
+ */
+ if (will_write)
+ mnt_drop_write(nd.path.mnt);
+ return filp;
+exit_mutex_unlock:
+ mutex_unlock(&dir->d_inode->i_mutex);
exit_dput:
- dput_path(&path, nd);
+ path_put_conditional(&path, &nd);
exit:
- if (!IS_ERR(nd->intent.open.file))
- release_open_intent(nd);
- path_release(nd);
- return error;
+ if (!IS_ERR(nd.intent.open.file))
+ release_open_intent(&nd);
+ path_put(&nd.path);
+ return ERR_PTR(error);
do_link:
error = -ELOOP;
* stored in nd->last.name and we will have to putname() it when we
* are done. Procfs-like symlinks just set LAST_BIND.
*/
- nd->flags |= LOOKUP_PARENT;
- error = security_inode_follow_link(path.dentry, nd);
+ nd.flags |= LOOKUP_PARENT;
+ error = security_inode_follow_link(path.dentry, &nd);
if (error)
goto exit_dput;
- error = __do_follow_link(&path, nd);
+ error = __do_follow_link(&path, &nd);
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);
- return error;
+ release_open_intent(&nd);
+ return ERR_PTR(error);
}
- nd->flags &= ~LOOKUP_PARENT;
- if (nd->last_type == LAST_BIND)
+ nd.flags &= ~LOOKUP_PARENT;
+ if (nd.last_type == LAST_BIND)
goto ok;
error = -EISDIR;
- if (nd->last_type != LAST_NORM)
+ if (nd.last_type != LAST_NORM)
goto exit;
- if (nd->last.name[nd->last.len]) {
- __putname(nd->last.name);
+ if (nd.last.name[nd.last.len]) {
+ __putname(nd.last.name);
goto exit;
}
error = -ELOOP;
if (count++==32) {
- __putname(nd->last.name);
+ __putname(nd.last.name);
goto exit;
}
- dir = nd->dentry;
+ dir = nd.path.dentry;
mutex_lock(&dir->d_inode->i_mutex);
- path.dentry = lookup_hash(nd);
- path.mnt = nd->mnt;
- __putname(nd->last.name);
+ path.dentry = lookup_hash(&nd);
+ path.mnt = nd.path.mnt;
+ __putname(nd.last.name);
goto do_last;
}
/**
+ * filp_open - open file and return file pointer
+ *
+ * @filename: path to open
+ * @flags: open flags as per the open(2) second argument
+ * @mode: mode for the new file if O_CREAT is set, else ignored
+ *
+ * This is the helper to open a file from kernelspace if you really
+ * have to. But in generally you should not do this, so please move
+ * along, nothing to see here..
+ */
+struct file *filp_open(const char *filename, int flags, int mode)
+{
+ return do_filp_open(AT_FDCWD, filename, flags, mode);
+}
+EXPORT_SYMBOL(filp_open);
+
+/**
* lookup_create - lookup a dentry, creating it if it doesn't exist
* @nd: nameidata info
* @is_dir: directory flag
* Simple function to lookup and return a dentry and create it
* if it doesn't exist. Is SMP-safe.
*
- * Returns with nd->dentry->d_inode->i_mutex locked.
+ * Returns with nd->path.dentry->d_inode->i_mutex locked.
*/
struct dentry *lookup_create(struct nameidata *nd, int is_dir)
{
struct dentry *dentry = ERR_PTR(-EEXIST);
- mutex_lock_nested(&nd->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&nd->path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
/*
* Yucky last component or no last component at all?
* (foo/., foo/.., /////)
return error;
}
+static int may_mknod(mode_t mode)
+{
+ switch (mode & S_IFMT) {
+ case S_IFREG:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFIFO:
+ case S_IFSOCK:
+ case 0: /* zero mode translates to S_IFREG */
+ return 0;
+ case S_IFDIR:
+ return -EPERM;
+ default:
+ return -EINVAL;
+ }
+}
+
asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode,
unsigned dev)
{
if (error)
goto out;
dentry = lookup_create(&nd, 0);
- error = PTR_ERR(dentry);
-
- if (!IS_POSIXACL(nd.dentry->d_inode))
+ if (IS_ERR(dentry)) {
+ error = PTR_ERR(dentry);
+ goto out_unlock;
+ }
+ if (!IS_POSIXACL(nd.path.dentry->d_inode))
mode &= ~current->fs->umask;
- if (!IS_ERR(dentry)) {
- switch (mode & S_IFMT) {
+ error = may_mknod(mode);
+ if (error)
+ goto out_dput;
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_dput;
+ switch (mode & S_IFMT) {
case 0: case S_IFREG:
- error = vfs_create(nd.dentry->d_inode,dentry,mode,&nd);
+ error = vfs_create(nd.path.dentry->d_inode,dentry,mode,&nd);
break;
case S_IFCHR: case S_IFBLK:
- error = vfs_mknod(nd.dentry->d_inode,dentry,mode,
+ error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,
new_decode_dev(dev));
break;
case S_IFIFO: case S_IFSOCK:
- error = vfs_mknod(nd.dentry->d_inode,dentry,mode,0);
+ error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,0);
break;
- case S_IFDIR:
- error = -EPERM;
- break;
- default:
- error = -EINVAL;
- }
- dput(dentry);
}
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
- path_release(&nd);
+ mnt_drop_write(nd.path.mnt);
+out_dput:
+ dput(dentry);
+out_unlock:
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
out:
putname(tmp);
if (IS_ERR(dentry))
goto out_unlock;
- if (!IS_POSIXACL(nd.dentry->d_inode))
+ if (!IS_POSIXACL(nd.path.dentry->d_inode))
mode &= ~current->fs->umask;
- error = vfs_mkdir(nd.dentry->d_inode, dentry, mode);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_dput;
+ error = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode);
+ mnt_drop_write(nd.path.mnt);
+out_dput:
dput(dentry);
out_unlock:
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
- path_release(&nd);
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
out:
putname(tmp);
out_err:
error = -EBUSY;
goto exit1;
}
- mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
error = PTR_ERR(dentry);
if (IS_ERR(dentry))
goto exit2;
- error = vfs_rmdir(nd.dentry->d_inode, dentry);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto exit3;
+ error = vfs_rmdir(nd.path.dentry->d_inode, dentry);
+ mnt_drop_write(nd.path.mnt);
+exit3:
dput(dentry);
exit2:
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
exit1:
- path_release(&nd);
+ path_put(&nd.path);
exit:
putname(name);
return error;
/* We don't d_delete() NFS sillyrenamed files--they still exist. */
if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
+ fsnotify_link_count(dentry->d_inode);
d_delete(dentry);
}
error = -EISDIR;
if (nd.last_type != LAST_NORM)
goto exit1;
- mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
inode = dentry->d_inode;
if (inode)
atomic_inc(&inode->i_count);
- error = vfs_unlink(nd.dentry->d_inode, dentry);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto exit2;
+ error = vfs_unlink(nd.path.dentry->d_inode, dentry);
+ mnt_drop_write(nd.path.mnt);
exit2:
dput(dentry);
}
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
if (inode)
iput(inode); /* truncate the inode here */
exit1:
- path_release(&nd);
+ path_put(&nd.path);
exit:
putname(name);
return error;
if (IS_ERR(dentry))
goto out_unlock;
- error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_dput;
+ error = vfs_symlink(nd.path.dentry->d_inode, dentry, from, S_IALLUGO);
+ mnt_drop_write(nd.path.mnt);
+out_dput:
dput(dentry);
out_unlock:
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
- path_release(&nd);
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
+ path_put(&nd.path);
out:
putname(to);
out_putname:
error = dir->i_op->link(old_dentry, dir, new_dentry);
mutex_unlock(&old_dentry->d_inode->i_mutex);
if (!error)
- fsnotify_create(dir, new_dentry);
+ fsnotify_link(dir, old_dentry->d_inode, new_dentry);
return error;
}
if (error)
goto out;
error = -EXDEV;
- if (old_nd.mnt != nd.mnt)
+ if (old_nd.path.mnt != nd.path.mnt)
goto out_release;
new_dentry = lookup_create(&nd, 0);
error = PTR_ERR(new_dentry);
if (IS_ERR(new_dentry))
goto out_unlock;
- error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_dput;
+ error = vfs_link(old_nd.path.dentry, nd.path.dentry->d_inode, new_dentry);
+ mnt_drop_write(nd.path.mnt);
+out_dput:
dput(new_dentry);
out_unlock:
- mutex_unlock(&nd.dentry->d_inode->i_mutex);
+ mutex_unlock(&nd.path.dentry->d_inode->i_mutex);
out_release:
- path_release(&nd);
+ path_put(&nd.path);
out:
- path_release(&old_nd);
+ path_put(&old_nd.path);
exit:
putname(to);
if (!error) {
const char *new_name = old_dentry->d_name.name;
fsnotify_move(old_dir, new_dir, old_name, new_name, is_dir,
- new_dentry->d_inode, old_dentry->d_inode);
+ new_dentry->d_inode, old_dentry);
}
fsnotify_oldname_free(old_name);
goto exit1;
error = -EXDEV;
- if (oldnd.mnt != newnd.mnt)
+ if (oldnd.path.mnt != newnd.path.mnt)
goto exit2;
- old_dir = oldnd.dentry;
+ old_dir = oldnd.path.dentry;
error = -EBUSY;
if (oldnd.last_type != LAST_NORM)
goto exit2;
- new_dir = newnd.dentry;
+ new_dir = newnd.path.dentry;
if (newnd.last_type != LAST_NORM)
goto exit2;
if (new_dentry == trap)
goto exit5;
+ error = mnt_want_write(oldnd.path.mnt);
+ if (error)
+ goto exit5;
error = vfs_rename(old_dir->d_inode, old_dentry,
new_dir->d_inode, new_dentry);
+ mnt_drop_write(oldnd.path.mnt);
exit5:
dput(new_dentry);
exit4:
exit3:
unlock_rename(new_dir, old_dir);
exit2:
- path_release(&newnd);
+ path_put(&newnd.path);
exit1:
- path_release(&oldnd);
+ path_put(&oldnd.path);
exit:
return error;
}
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
+ void *fsdata;
int err;
char *kaddr;
retry:
- err = -ENOMEM;
- page = find_or_create_page(mapping, 0, gfp_mask);
- if (!page)
- goto fail;
- err = mapping->a_ops->prepare_write(NULL, page, 0, len-1);
- if (err == AOP_TRUNCATED_PAGE) {
- page_cache_release(page);
- goto retry;
- }
+ err = pagecache_write_begin(NULL, mapping, 0, len-1,
+ AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
if (err)
- goto fail_map;
+ goto fail;
+
kaddr = kmap_atomic(page, KM_USER0);
memcpy(kaddr, symname, len-1);
kunmap_atomic(kaddr, KM_USER0);
- 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;
- /*
- * 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);
- if (err != AOP_TRUNCATED_PAGE)
- wait_on_page_locked(page);
- } else {
- unlock_page(page);
- }
- page_cache_release(page);
+
+ err = pagecache_write_end(NULL, mapping, 0, len-1, len-1,
+ page, fsdata);
if (err < 0)
goto fail;
+ if (err < len-1)
+ goto retry;
+
mark_inode_dirty(inode);
return 0;
-fail_map:
- unlock_page(page);
- page_cache_release(page);
fail:
return err;
}
EXPORT_SYMBOL(page_symlink);
EXPORT_SYMBOL(page_symlink_inode_operations);
EXPORT_SYMBOL(path_lookup);
-EXPORT_SYMBOL(path_release);
-EXPORT_SYMBOL(path_walk);
+EXPORT_SYMBOL(vfs_path_lookup);
EXPORT_SYMBOL(permission);
EXPORT_SYMBOL(vfs_permission);
EXPORT_SYMBOL(file_permission);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff