#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/vs_base.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;
return result;
}
-/*
- * vfs_permission()
+/**
+ * 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 (IS_BARRIER(inode) && !vx_check(0, VX_ADMIN|VX_WATCH))
- return -EACCES;
-
- 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;
}
-static inline int xid_permission(struct inode *inode)
+static inline int xid_permission(struct inode *inode, int mask, struct nameidata *nd)
{
+ 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 permission(struct inode *inode, int mask, struct nameidata *nd)
{
- int retval;
- int submask;
+ 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)))
+ 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);
+}
+
+static inline int __do_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ int error;
+
+ touch_atime(nd->mnt, dentry);
+ nd_set_link(nd, NULL);
+ 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);
+ }
+
+ return error;
+}
+
/*
* This limits recursive symlink follows to 8, while
* limiting consecutive symlinks to 40.
static inline int do_follow_link(struct dentry *dentry, 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);
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(dentry, nd);
current->link_count--;
+ nd->depth--;
return err;
loop:
path_release(nd);
if (*dentry == current->fs->root &&
*mnt == current->fs->rootmnt) {
read_unlock(¤t->fs->lock);
- break;
+ return;
}
read_unlock(¤t->fs->lock);
spin_lock(&dcache_lock);
{
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;
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);
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. */
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;
-}
-
int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata *nd)
{
int retval;
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags;
+ nd->depth = 0;
read_lock(¤t->fs->lock);
if (*name=='/') {
}
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);
}
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;
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.
*/
error = security_inode_follow_link(dentry, nd);
if (error)
goto exit_dput;
- touch_atime(nd->mnt, dentry);
- error = dentry->d_inode->i_op->follow_link(dentry, nd);
+ error = __do_follow_link(dentry, nd);
dput(dentry);
if (error)
return error;
* 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);
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:
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 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);