#include <linux/smp_lock.h>
#include <linux/personality.h>
#include <linux/security.h>
+#include <linux/syscalls.h>
#include <linux/mount.h>
#include <linux/audit.h>
+#include <linux/proc_fs.h>
+#include <linux/vserver/inode.h>
+#include <linux/vserver/debug.h>
#include <asm/namei.h>
#include <asm/uaccess.h>
int retval;
unsigned long len = PATH_MAX;
- if ((unsigned long) filename >= TASK_SIZE) {
- if (!segment_eq(get_fs(), KERNEL_DS))
+ if (!segment_eq(get_fs(), KERNEL_DS)) {
+ if ((unsigned long) filename >= TASK_SIZE)
return -EFAULT;
- } else if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
- len = TASK_SIZE - (unsigned long) filename;
+ if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
+ len = TASK_SIZE - (unsigned long) filename;
+ }
- retval = strncpy_from_user((char *)page, filename, len);
+ retval = strncpy_from_user(page, filename, len);
if (retval > 0) {
if (retval < len)
return 0;
result = ERR_PTR(retval);
}
}
- if (unlikely(current->audit_context) && !IS_ERR(result) && result)
- audit_getname(result);
+ audit_getname(result);
return result;
}
-/*
- * vfs_permission()
+#ifdef CONFIG_AUDITSYSCALL
+void putname(const char *name)
+{
+ if (unlikely(current->audit_context))
+ 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
*
- * is used to check for read/write/execute permissions on a file.
+ * 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 vfs_permission(struct inode * inode, int mask)
+int generic_permission(struct inode *inode, int mask,
+ int (*check_acl)(struct inode *inode, int mask))
{
umode_t mode = inode->i_mode;
- 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;
- }
-
if (current->fsuid == inode->i_uid)
mode >>= 6;
- else if (in_group_p(inode->i_gid))
- mode >>= 3;
+ 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.
return -EACCES;
}
-int permission(struct inode * inode,int mask, struct nameidata *nd)
+static inline int xid_permission(struct inode *inode, int mask, struct nameidata *nd)
{
- int retval;
- int submask;
+ if (IS_BARRIER(inode) && !vx_check(0, VX_ADMIN)) {
+ vxwprintk(1, "xid=%d did hit the barrier.",
+ vx_current_xid());
+ return -EACCES;
+ }
+ if (inode->i_xid == 0)
+ return 0;
+ if (vx_check(inode->i_xid, VX_ADMIN|VX_WATCH|VX_IDENT))
+ return 0;
+
+ vxwprintk(1, "xid=%d denied access to %p[#%d,%lu] »%s«.",
+ vx_current_xid(), inode, inode->i_xid, inode->i_ino,
+ vxd_path(nd->dentry, nd->mnt));
+ return -EACCES;
+}
+
+int permission(struct inode *inode, int mask, struct nameidata *nd)
+{
+ int retval, submask;
+
+ if (mask & MAY_WRITE) {
+ umode_t mode = inode->i_mode;
+
+ /*
+ * 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;
+ }
+
/* Ordinary permission routines do not understand MAY_APPEND. */
submask = mask & ~MAY_APPEND;
-
+ if ((retval = xid_permission(inode, mask, nd)))
+ return retval;
if (inode->i_op && inode->i_op->permission)
retval = inode->i_op->permission(inode, submask, nd);
else
- retval = vfs_permission(inode, submask);
+ retval = generic_permission(inode, submask, NULL);
if (retval)
return retval;
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);
+ _mntput(nd->mnt);
+}
+
/*
* Internal lookup() using the new generic dcache.
* SMP-safe
/*
* Short-cut version of permission(), for calling by
* path_walk(), when dcache lock is held. Combines parts
- * of permission() and vfs_permission(), and tests ONLY for
+ * of permission() and generic_permission(), and tests ONLY for
* MAY_EXEC permission.
*
* If appropriate, check DAC only. If not appropriate, or
{
umode_t mode = inode->i_mode;
- if ((inode->i_op && inode->i_op->permission))
+ if (inode->i_op && inode->i_op->permission)
return -EAGAIN;
if (current->fsuid == inode->i_uid)
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 result;
}
+static int __emul_lookup_dentry(const char *, struct nameidata *);
+
+/* SMP-safe */
+static inline int
+walk_init_root(const char *name, struct nameidata *nd)
+{
+ read_lock(¤t->fs->lock);
+ if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
+ nd->mnt = mntget(current->fs->altrootmnt);
+ nd->dentry = dget(current->fs->altroot);
+ read_unlock(¤t->fs->lock);
+ if (__emul_lookup_dentry(name,nd))
+ return 0;
+ read_lock(¤t->fs->lock);
+ }
+ nd->mnt = mntget(current->fs->rootmnt);
+ nd->dentry = dget(current->fs->root);
+ read_unlock(¤t->fs->lock);
+ return 1;
+}
+
+static inline int __vfs_follow_link(struct nameidata *nd, const char *link)
+{
+ 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);
+}
+
+struct path {
+ struct vfsmount *mnt;
+ struct dentry *dentry;
+};
+
+static inline int __do_follow_link(struct path *path, struct nameidata *nd)
+{
+ int error;
+ struct dentry *dentry = path->dentry;
+
+ touch_atime(path->mnt, dentry);
+ nd_set_link(nd, NULL);
+
+ if (path->mnt == nd->mnt)
+ mntget(path->mnt);
+ error = dentry->d_inode->i_op->follow_link(dentry, nd);
+ if (!error) {
+ char *s = nd_get_link(nd);
+ if (s)
+ error = __vfs_follow_link(nd, s);
+ if (dentry->d_inode->i_op->put_link)
+ dentry->d_inode->i_op->put_link(dentry, nd);
+ }
+ dput(dentry);
+ mntput(path->mnt);
+
+ 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.
*/
-static inline int do_follow_link(struct dentry *dentry, struct nameidata *nd)
+static inline int do_follow_link(struct path *path, struct nameidata *nd)
{
int err = -ELOOP;
- if (current->link_count >= 5)
+ 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();
- err = security_inode_follow_link(dentry, nd);
+ err = security_inode_follow_link(path->dentry, nd);
if (err)
goto loop;
current->link_count++;
current->total_link_count++;
- touch_atime(nd->mnt, dentry);
- err = dentry->d_inode->i_op->follow_link(dentry, nd);
+ nd->depth++;
+ err = __do_follow_link(path, nd);
current->link_count--;
+ nd->depth--;
return err;
loop:
+ dput(path->dentry);
+ if (path->mnt != nd->mnt)
+ mntput(path->mnt);
path_release(nd);
return err;
}
/* no need for dcache_lock, as serialization is taken care in
* namespace.c
*/
-static int follow_mount(struct vfsmount **mnt, struct dentry **dentry)
+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;
+}
+
+static void follow_mount(struct vfsmount **mnt, struct dentry **dentry)
+{
while (d_mountpoint(*dentry)) {
struct vfsmount *mounted = lookup_mnt(*mnt, *dentry);
if (!mounted)
break;
+ dput(*dentry);
mntput(*mnt);
*mnt = mounted;
- dput(*dentry);
*dentry = dget(mounted->mnt_root);
- res = 1;
}
- return res;
}
/* no need for dcache_lock, as serialization is taken care in
* namespace.c
*/
-static inline int __follow_down(struct vfsmount **mnt, struct dentry **dentry)
+int follow_down(struct vfsmount **mnt, struct dentry **dentry)
{
struct vfsmount *mounted;
mounted = lookup_mnt(*mnt, *dentry);
if (mounted) {
+ dput(*dentry);
mntput(*mnt);
*mnt = mounted;
- dput(*dentry);
*dentry = dget(mounted->mnt_root);
return 1;
}
return 0;
}
-int follow_down(struct vfsmount **mnt, struct dentry **dentry)
-{
- return __follow_down(mnt,dentry);
-}
-
-static inline void follow_dotdot(struct vfsmount **mnt, struct dentry **dentry)
+static inline void follow_dotdot(struct nameidata *nd)
{
while(1) {
struct vfsmount *parent;
- struct dentry *old = *dentry;
+ struct dentry *old = nd->dentry;
read_lock(¤t->fs->lock);
- if (*dentry == current->fs->root &&
- *mnt == current->fs->rootmnt) {
+ if (nd->dentry == current->fs->root &&
+ nd->mnt == current->fs->rootmnt) {
read_unlock(¤t->fs->lock);
- break;
+ /* for sane '/' avoid follow_mount() */
+ return;
}
read_unlock(¤t->fs->lock);
spin_lock(&dcache_lock);
- if (*dentry != (*mnt)->mnt_root) {
- *dentry = dget((*dentry)->d_parent);
+ if (nd->dentry != nd->mnt->mnt_root) {
+ nd->dentry = dget(nd->dentry->d_parent);
spin_unlock(&dcache_lock);
dput(old);
break;
}
spin_unlock(&dcache_lock);
spin_lock(&vfsmount_lock);
- parent = (*mnt)->mnt_parent;
- if (parent == *mnt) {
+ parent = nd->mnt->mnt_parent;
+ if (parent == nd->mnt) {
spin_unlock(&vfsmount_lock);
break;
}
mntget(parent);
- *dentry = dget((*mnt)->mnt_mountpoint);
+ nd->dentry = dget(nd->mnt->mnt_mountpoint);
spin_unlock(&vfsmount_lock);
dput(old);
- mntput(*mnt);
- *mnt = parent;
+ mntput(nd->mnt);
+ nd->mnt = parent;
}
- follow_mount(mnt, dentry);
+ follow_mount(&nd->mnt, &nd->dentry);
}
-struct path {
- struct vfsmount *mnt;
- struct dentry *dentry;
-};
-
/*
* 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.
{
struct vfsmount *mnt = nd->mnt;
struct dentry *dentry = __d_lookup(nd->dentry, name);
+ struct inode *inode;
if (!dentry)
goto need_lookup;
if (dentry->d_op && dentry->d_op->d_revalidate)
goto need_revalidate;
+ inode = dentry->d_inode;
+ if (!inode)
+ goto done;
+ if (!vx_check(inode->i_xid, VX_WATCH|VX_ADMIN|VX_HOSTID|VX_IDENT))
+ goto hidden;
+ if (inode->i_sb->s_magic == PROC_SUPER_MAGIC) {
+ struct proc_dir_entry *de = PDE(inode);
+
+ if (de && !vx_hide_check(0, de->vx_flags))
+ goto hidden;
+ }
done:
path->mnt = mnt;
path->dentry = dentry;
+ __follow_mount(path);
return 0;
+hidden:
+ vxwprintk(1, "xid=%d did lookup hidden %p[#%d,%lu] »%s«.",
+ vx_current_xid(), inode, inode->i_xid, inode->i_ino,
+ vxd_path(dentry, mnt));
+ dput(dentry);
+ return -ENOENT;
need_lookup:
dentry = real_lookup(nd->dentry, name, nd);
/*
* Name resolution.
+ * This is the basic name resolution function, turning a pathname into
+ * the final dentry. We expect 'base' to be positive and a directory.
*
- * This is the basic name resolution function, turning a pathname
- * into the final dentry.
- *
- * We expect 'base' to be positive and a directory.
+ * Returns 0 and nd will have valid dentry and mnt on success.
+ * Returns error and drops reference to input namei data on failure.
*/
-int fastcall link_path_walk(const char * name, struct nameidata *nd)
+static fastcall int __link_path_walk(const char * name, struct nameidata *nd)
{
struct path next;
struct inode *inode;
goto return_reval;
inode = nd->dentry->d_inode;
- if (current->link_count)
+ if (nd->depth)
lookup_flags = LOOKUP_FOLLOW;
/* At this point we know we have a real path component. */
case 2:
if (this.name[1] != '.')
break;
- follow_dotdot(&nd->mnt, &nd->dentry);
+ follow_dotdot(nd);
inode = nd->dentry->d_inode;
/* fallthrough */
case 1:
err = do_lookup(nd, &this, &next);
if (err)
break;
- /* Check mountpoints.. */
- follow_mount(&next.mnt, &next.dentry);
err = -ENOENT;
inode = next.dentry->d_inode;
goto out_dput;
if (inode->i_op->follow_link) {
- mntget(next.mnt);
- err = do_follow_link(next.dentry, nd);
- dput(next.dentry);
- mntput(next.mnt);
+ err = do_follow_link(&next, nd);
if (err)
goto return_err;
err = -ENOENT;
break;
} else {
dput(nd->dentry);
+ if (nd->mnt != next.mnt)
+ mntput(nd->mnt);
nd->mnt = next.mnt;
nd->dentry = next.dentry;
}
case 2:
if (this.name[1] != '.')
break;
- follow_dotdot(&nd->mnt, &nd->dentry);
+ follow_dotdot(nd);
inode = nd->dentry->d_inode;
/* fallthrough */
case 1:
err = do_lookup(nd, &this, &next);
if (err)
break;
- follow_mount(&next.mnt, &next.dentry);
inode = next.dentry->d_inode;
if ((lookup_flags & LOOKUP_FOLLOW)
&& inode && inode->i_op && inode->i_op->follow_link) {
- mntget(next.mnt);
- err = do_follow_link(next.dentry, nd);
- dput(next.dentry);
- mntput(next.mnt);
+ err = do_follow_link(&next, nd);
if (err)
goto return_err;
inode = nd->dentry->d_inode;
} else {
dput(nd->dentry);
+ if (nd->mnt != next.mnt)
+ mntput(nd->mnt);
nd->mnt = next.mnt;
nd->dentry = next.dentry;
}
return 0;
out_dput:
dput(next.dentry);
+ if (nd->mnt != next.mnt)
+ mntput(next.mnt);
break;
}
path_release(nd);
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)
{
current->total_link_count = 0;
return link_path_walk(name, nd);
}
-/* SMP-safe */
-/* returns 1 if everything is done */
+/*
+ * 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;
+ */
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 nameidata nd_root;
+ struct dentry *old_dentry = nd->dentry;
+ struct vfsmount *old_mnt = nd->mnt;
+ struct qstr last = nd->last;
+ int last_type = nd->last_type;
/*
* NAME was not found in alternate root or it's a directory. Try to find
* it in the normal root:
*/
- nd_root.last_type = LAST_ROOT;
- nd_root.flags = nd->flags;
- memcpy(&nd_root.intent, &nd->intent, sizeof(nd_root.intent));
+ nd->last_type = LAST_ROOT;
read_lock(¤t->fs->lock);
- nd_root.mnt = mntget(current->fs->rootmnt);
- nd_root.dentry = dget(current->fs->root);
+ nd->mnt = mntget(current->fs->rootmnt);
+ nd->dentry = dget(current->fs->root);
read_unlock(¤t->fs->lock);
- if (path_walk(name, &nd_root))
- return 1;
- if (nd_root.dentry->d_inode) {
+ if (path_walk(name, nd) == 0) {
+ if (nd->dentry->d_inode) {
+ dput(old_dentry);
+ mntput(old_mnt);
+ return 1;
+ }
path_release(nd);
- nd->dentry = nd_root.dentry;
- nd->mnt = nd_root.mnt;
- nd->last = nd_root.last;
- return 1;
}
- path_release(&nd_root);
+ nd->dentry = old_dentry;
+ nd->mnt = old_mnt;
+ nd->last = last;
+ nd->last_type = last_type;
}
return 1;
}
}
}
-/* SMP-safe */
-static inline int
-walk_init_root(const char *name, struct nameidata *nd)
-{
- read_lock(¤t->fs->lock);
- if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) {
- nd->mnt = mntget(current->fs->altrootmnt);
- nd->dentry = dget(current->fs->altroot);
- read_unlock(¤t->fs->lock);
- if (__emul_lookup_dentry(name,nd))
- return 0;
- read_lock(¤t->fs->lock);
- }
- nd->mnt = mntget(current->fs->rootmnt);
- nd->dentry = dget(current->fs->root);
- read_unlock(¤t->fs->lock);
- return 1;
-}
-
+/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata *nd)
{
- int retval;
+ int retval = 0;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags;
+ nd->depth = 0;
read_lock(¤t->fs->lock);
if (*name=='/') {
nd->dentry = dget(current->fs->altroot);
read_unlock(¤t->fs->lock);
if (__emul_lookup_dentry(name,nd))
- return 0;
+ goto out; /* found in altroot */
read_lock(¤t->fs->lock);
}
nd->mnt = mntget(current->fs->rootmnt);
nd->dentry = dget(current->fs->root);
- }
- else{
+ } else {
nd->mnt = mntget(current->fs->pwdmnt);
nd->dentry = dget(current->fs->pwd);
}
read_unlock(¤t->fs->lock);
current->total_link_count = 0;
retval = link_path_walk(name, nd);
+out:
if (unlikely(current->audit_context
&& nd && nd->dentry && nd->dentry->d_inode))
- audit_inode(name,
- nd->dentry->d_inode->i_ino,
- nd->dentry->d_inode->i_rdev);
+ audit_inode(name, nd->dentry->d_inode);
return retval;
}
static inline int may_delete(struct inode *dir,struct dentry *victim,int isdir)
{
int error;
- if (!victim->d_inode || victim->d_parent->d_inode != dir)
+
+ if (!victim->d_inode)
return -ENOENT;
+
+ BUG_ON(victim->d_parent->d_inode != dir);
+
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))
+ IS_IXORUNLINK(victim->d_inode))
return -EPERM;
if (isdir) {
if (!S_ISDIR(victim->d_inode->i_mode))
return -EPERM;
}
+ /* O_NOATIME can only be set by the owner or superuser */
+ if (flag & O_NOATIME)
+ if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
+ return -EPERM;
+
/*
* Ensure there are no outstanding leases on the file.
*/
int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd)
{
int acc_mode, error = 0;
- struct dentry *dentry;
+ struct path path;
struct dentry *dir;
int count = 0;
dir = nd->dentry;
nd->flags &= ~LOOKUP_PARENT;
down(&dir->d_inode->i_sem);
- dentry = __lookup_hash(&nd->last, nd->dentry, nd);
+ path.dentry = __lookup_hash(&nd->last, nd->dentry, nd);
+ path.mnt = nd->mnt;
do_last:
- error = PTR_ERR(dentry);
- if (IS_ERR(dentry)) {
+ error = PTR_ERR(path.dentry);
+ if (IS_ERR(path.dentry)) {
up(&dir->d_inode->i_sem);
goto exit;
}
/* Negative dentry, just create the file */
- if (!dentry->d_inode) {
+ if (!path.dentry->d_inode) {
if (!IS_POSIXACL(dir->d_inode))
mode &= ~current->fs->umask;
- error = vfs_create(dir->d_inode, dentry, mode, nd);
+ error = vfs_create(dir->d_inode, path.dentry, mode, nd);
up(&dir->d_inode->i_sem);
dput(nd->dentry);
- nd->dentry = dentry;
+ nd->dentry = path.dentry;
if (error)
goto exit;
/* Don't check for write permission, don't truncate */
if (flag & O_EXCL)
goto exit_dput;
- if (d_mountpoint(dentry)) {
+ if (__follow_mount(&path)) {
error = -ELOOP;
if (flag & O_NOFOLLOW)
goto exit_dput;
- while (__follow_down(&nd->mnt,&dentry) && d_mountpoint(dentry));
}
error = -ENOENT;
- if (!dentry->d_inode)
+ if (!path.dentry->d_inode)
goto exit_dput;
- if (dentry->d_inode->i_op && dentry->d_inode->i_op->follow_link)
+ if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link)
goto do_link;
dput(nd->dentry);
- nd->dentry = dentry;
+ nd->dentry = path.dentry;
+ if (nd->mnt != path.mnt)
+ mntput(nd->mnt);
+ nd->mnt = path.mnt;
error = -EISDIR;
- if (dentry->d_inode && S_ISDIR(dentry->d_inode->i_mode))
+ if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode))
goto exit;
ok:
error = may_open(nd, acc_mode, flag);
return 0;
exit_dput:
- dput(dentry);
+ dput(path.dentry);
+ if (nd->mnt != path.mnt)
+ mntput(path.mnt);
exit:
path_release(nd);
return error;
* are done. Procfs-like symlinks just set LAST_BIND.
*/
nd->flags |= LOOKUP_PARENT;
- error = security_inode_follow_link(dentry, nd);
+ error = security_inode_follow_link(path.dentry, nd);
if (error)
goto exit_dput;
- touch_atime(nd->mnt, dentry);
- error = dentry->d_inode->i_op->follow_link(dentry, nd);
- dput(dentry);
+ error = __do_follow_link(&path, nd);
if (error)
return error;
nd->flags &= ~LOOKUP_PARENT;
- if (nd->last_type == LAST_BIND) {
- dentry = nd->dentry;
+ if (nd->last_type == LAST_BIND)
goto ok;
- }
error = -EISDIR;
if (nd->last_type != LAST_NORM)
goto exit;
}
dir = nd->dentry;
down(&dir->d_inode->i_sem);
- dentry = __lookup_hash(&nd->last, nd->dentry, nd);
+ path.dentry = __lookup_hash(&nd->last, nd->dentry, nd);
+ path.mnt = nd->mnt;
putname(nd->last.name);
goto do_last;
}
fail:
return dentry;
}
+EXPORT_SYMBOL_GPL(lookup_create);
int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
* if it cannot handle the case of removing a directory
* that is still in use by something else..
*/
-static void d_unhash(struct dentry *dentry)
+void dentry_unhash(struct dentry *dentry)
{
dget(dentry);
- spin_lock(&dcache_lock);
- switch (atomic_read(&dentry->d_count)) {
- default:
- spin_unlock(&dcache_lock);
+ if (atomic_read(&dentry->d_count))
shrink_dcache_parent(dentry);
- spin_lock(&dcache_lock);
- if (atomic_read(&dentry->d_count) != 2)
- break;
- case 2:
+ 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);
}
DQUOT_INIT(dir);
down(&dentry->d_inode->i_sem);
- d_unhash(dentry);
+ dentry_unhash(dentry);
if (d_mountpoint(dentry))
error = -EBUSY;
else {
dput(dentry);
}
up(&nd.dentry->d_inode->i_sem);
+ if (inode)
+ iput(inode); /* truncate the inode here */
exit1:
path_release(&nd);
exit:
putname(name);
-
- if (inode)
- iput(inode); /* truncate the inode here */
return error;
slashes:
goto exit2;
}
-int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname)
+int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, int mode)
{
int error = may_create(dir, dentry, NULL);
dentry = lookup_create(&nd, 0);
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
- error = vfs_symlink(nd.dentry->d_inode, dentry, from);
+ error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO);
dput(dentry);
}
up(&nd.dentry->d_inode->i_sem);
/*
* A link to an append-only or immutable file cannot be created.
*/
- if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+ if (IS_APPEND(inode) || IS_IXORUNLINK(inode))
return -EPERM;
if (!dir->i_op || !dir->i_op->link)
return -EPERM;
* ->i_sem on parents, which works but leads to some truely excessive
* locking].
*/
-int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
{
int error = 0;
struct inode *target;
target = new_dentry->d_inode;
if (target) {
down(&target->i_sem);
- d_unhash(new_dentry);
+ dentry_unhash(new_dentry);
}
if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry))
error = -EBUSY;
return error;
}
-int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry)
{
struct inode *target;
int error;
return len;
}
-static inline int
-__vfs_follow_link(struct nameidata *nd, const char *link)
+/*
+ * 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)
{
- 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 (current->link_count || 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;
+ struct nameidata nd;
+ int res;
+ nd.depth = 0;
+ res = dentry->d_inode->i_op->follow_link(dentry, &nd);
+ if (!res) {
+ res = vfs_readlink(dentry, buffer, buflen, nd_get_link(&nd));
+ if (dentry->d_inode->i_op->put_link)
+ dentry->d_inode->i_op->put_link(dentry, &nd);
}
- strcpy(name, nd->last.name);
- nd->last.name = name;
- return 0;
-fail:
- path_release(nd);
- return PTR_ERR(link);
+ return res;
}
int vfs_follow_link(struct nameidata *nd, const char *link)
return res;
}
-int page_follow_link(struct dentry *dentry, struct nameidata *nd)
+int page_follow_link_light(struct dentry *dentry, struct nameidata *nd)
{
- struct page *page = NULL;
- char *s = page_getlink(dentry, &page);
- int res = __vfs_follow_link(nd, s);
- if (page) {
+ struct page *page;
+ nd_set_link(nd, page_getlink(dentry, &page));
+ return 0;
+}
+
+void page_put_link(struct dentry *dentry, struct nameidata *nd)
+{
+ if (!IS_ERR(nd_get_link(nd))) {
+ struct page *page;
+ page = find_get_page(dentry->d_inode->i_mapping, 0);
+ if (!page)
+ BUG();
kunmap(page);
page_cache_release(page);
+ page_cache_release(page);
}
- return res;
}
int page_symlink(struct inode *inode, const char *symname, int len)
}
struct inode_operations page_symlink_inode_operations = {
- .readlink = page_readlink,
- .follow_link = page_follow_link,
+ .readlink = generic_readlink,
+ .follow_link = page_follow_link_light,
+ .put_link = page_put_link,
};
EXPORT_SYMBOL(__user_walk);
EXPORT_SYMBOL(get_write_access); /* binfmt_aout */
EXPORT_SYMBOL(getname);
EXPORT_SYMBOL(lock_rename);
-EXPORT_SYMBOL(lookup_create);
EXPORT_SYMBOL(lookup_hash);
EXPORT_SYMBOL(lookup_one_len);
-EXPORT_SYMBOL(page_follow_link);
+EXPORT_SYMBOL(page_follow_link_light);
+EXPORT_SYMBOL(page_put_link);
EXPORT_SYMBOL(page_readlink);
EXPORT_SYMBOL(page_symlink);
EXPORT_SYMBOL(page_symlink_inode_operations);
EXPORT_SYMBOL(vfs_link);
EXPORT_SYMBOL(vfs_mkdir);
EXPORT_SYMBOL(vfs_mknod);
-EXPORT_SYMBOL(vfs_permission);
+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);