Merge branch 'work.namei' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs name lookup updates from Al Viro:
 "Small namei.c patch series, mostly to simplify the rules for nameidata
  state. It's actually from the previous cycle - but I didn't post it
  for review in time...

  Changes visible outside of fs/namei.c: file_open_root() calling
  conventions change, some freed bits in LOOKUP_... space"

* 'work.namei' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  namei: make sure nd->depth is always valid
  teach set_nameidata() to handle setting the root as well
  take LOOKUP_{ROOT,ROOT_GRABBED,JUMPED} out of LOOKUP_... space
  switch file_open_root() to struct path

Documentation/filesystems/path-lookup.rst

@@ -1297,18 +1297,18 @@ to lookup: RCU-walk, REF-walk, and REF-walk with forced revalidation.
 yet.  This is primarily used to tell the audit subsystem the full
 context of a particular access being audited.
 
-``LOOKUP_ROOT`` indicates that the ``root`` field in the ``nameidata`` was
+``ND_ROOT_PRESET`` indicates that the ``root`` field in the ``nameidata`` was
 provided by the caller, so it shouldn't be released when it is no
 longer needed.
 
-``LOOKUP_JUMPED`` means that the current dentry was chosen not because
+``ND_JUMPED`` means that the current dentry was chosen not because
 it had the right name but for some other reason.  This happens when
 following "``..``", following a symlink to ``/``, crossing a mount point
 or accessing a "``/proc/$PID/fd/$FD``" symlink (also known as a "magic
 link"). In this case the filesystem has not been asked to revalidate the
 name (with ``d_revalidate()``).  In such cases the inode may still need
 to be revalidated, so ``d_op->d_weak_revalidate()`` is called if
-``LOOKUP_JUMPED`` is set when the look completes - which may be at the
+``ND_JUMPED`` is set when the look completes - which may be at the
 final component or, when creating, unlinking, or renaming, at the penultimate component.
 
 Resolution-restriction flags

Documentation/filesystems/porting.rst

@@ -899,3 +899,12 @@ iov_iter_copy_from_user_atomic() is gone; use copy_page_from_iter_atomic().
 The difference is copy_page_from_iter_atomic() advances the iterator and
 you don't need iov_iter_advance() after it.  However, if you decide to use
 only a part of obtained data, you should do iov_iter_revert().
+
+---
+
+**mandatory**
+
+Calling conventions for file_open_root() changed; now it takes struct path *
+instead of passing mount and dentry separately.  For callers that used to
+pass <mnt, mnt->mnt_root> pair (i.e. the root of given mount), a new helper
+is provided - file_open_root_mnt().  In-tree users adjusted.

arch/um/drivers/mconsole_kern.c

@@ -141,7 +141,7 @@ void mconsole_proc(struct mc_request *req)
 		mconsole_reply(req, "Proc not available", 1, 0);
 		goto out;
 	}
-	file = file_open_root(mnt->mnt_root, mnt, ptr, O_RDONLY, 0);
+	file = file_open_root_mnt(mnt, ptr, O_RDONLY, 0);
 	if (IS_ERR(file)) {
 		mconsole_reply(req, "Failed to open file", 1, 0);
 		printk(KERN_ERR "open /proc/%s: %ld\n", ptr, PTR_ERR(file));

fs/coredump.c

@@ -755,8 +755,8 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 			task_lock(&init_task);
 			get_fs_root(init_task.fs, &root);
 			task_unlock(&init_task);
-			cprm.file = file_open_root(root.dentry, root.mnt,
-				cn.corename, open_flags, 0600);
+			cprm.file = file_open_root(&root, cn.corename,
+						   open_flags, 0600);
 			path_put(&root);
 		} else {
 			cprm.file = filp_open(cn.corename, open_flags, 0600);

fs/fhandle.c

@@ -229,7 +229,7 @@ static long do_handle_open(int mountdirfd, struct file_handle __user *ufh,
 		path_put(&path);
 		return fd;
 	}
-	file = file_open_root(path.dentry, path.mnt, "", open_flag, 0);
+	file = file_open_root(&path, "", open_flag, 0);
 	if (IS_ERR(file)) {
 		put_unused_fd(fd);
 		retval =  PTR_ERR(file);

fs/internal.h

@@ -129,7 +129,7 @@ struct open_flags {
 };
 extern struct file *do_filp_open(int dfd, struct filename *pathname,
 		const struct open_flags *op);
-extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
+extern struct file *do_file_open_root(const struct path *,
 		const char *, const struct open_flags *);
 extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);

fs/kernel_read_file.c

@@ -160,7 +160,7 @@ int kernel_read_file_from_path_initns(const char *path, loff_t offset,
 	get_fs_root(init_task.fs, &root);
 	task_unlock(&init_task);
 
-	file = file_open_root(root.dentry, root.mnt, path, O_RDONLY, 0);
+	file = file_open_root(&root, path, O_RDONLY, 0);
 	path_put(&root);
 	if (IS_ERR(file))
 		return PTR_ERR(file);

fs/namei.c

@@ -554,7 +554,7 @@ struct nameidata {
 	struct qstr	last;
 	struct path	root;
 	struct inode	*inode; /* path.dentry.d_inode */
-	unsigned int	flags;
+	unsigned int	flags, state;
 	unsigned	seq, m_seq, r_seq;
 	int		last_type;
 	unsigned	depth;
@@ -573,10 +573,15 @@ struct nameidata {
 	umode_t		dir_mode;
 } __randomize_layout;
 
-static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
+#define ND_ROOT_PRESET 1
+#define ND_ROOT_GRABBED 2
+#define ND_JUMPED 4
+
+static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 {
 	struct nameidata *old = current->nameidata;
 	p->stack = p->internal;
+	p->depth = 0;
 	p->dfd = dfd;
 	p->name = name;
 	p->path.mnt = NULL;
@@ -586,6 +591,17 @@ static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 	current->nameidata = p;
 }
 
+static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name,
+			  const struct path *root)
+{
+	__set_nameidata(p, dfd, name);
+	p->state = 0;
+	if (unlikely(root)) {
+		p->state = ND_ROOT_PRESET;
+		p->root = *root;
+	}
+}
+
 static void restore_nameidata(void)
 {
 	struct nameidata *now = current->nameidata, *old = now->saved;
@@ -645,9 +661,9 @@ static void terminate_walk(struct nameidata *nd)
 		path_put(&nd->path);
 		for (i = 0; i < nd->depth; i++)
 			path_put(&nd->stack[i].link);
-		if (nd->flags & LOOKUP_ROOT_GRABBED) {
+		if (nd->state & ND_ROOT_GRABBED) {
 			path_put(&nd->root);
-			nd->flags &= ~LOOKUP_ROOT_GRABBED;
+			nd->state &= ~ND_ROOT_GRABBED;
 		}
 	} else {
 		nd->flags &= ~LOOKUP_RCU;
@@ -710,9 +726,9 @@ static bool legitimize_root(struct nameidata *nd)
 	if (!nd->root.mnt && (nd->flags & LOOKUP_IS_SCOPED))
 		return false;
 	/* Nothing to do if nd->root is zero or is managed by the VFS user. */
-	if (!nd->root.mnt || (nd->flags & LOOKUP_ROOT))
+	if (!nd->root.mnt || (nd->state & ND_ROOT_PRESET))
 		return true;
-	nd->flags |= LOOKUP_ROOT_GRABBED;
+	nd->state |= ND_ROOT_GRABBED;
 	return legitimize_path(nd, &nd->root, nd->root_seq);
 }
 
@@ -849,8 +865,9 @@ static int complete_walk(struct nameidata *nd)
 		 * We don't want to zero nd->root for scoped-lookups or
 		 * externally-managed nd->root.
 		 */
-		if (!(nd->flags & (LOOKUP_ROOT | LOOKUP_IS_SCOPED)))
-			nd->root.mnt = NULL;
+		if (!(nd->state & ND_ROOT_PRESET))
+			if (!(nd->flags & LOOKUP_IS_SCOPED))
+				nd->root.mnt = NULL;
 		nd->flags &= ~LOOKUP_CACHED;
 		if (!try_to_unlazy(nd))
 			return -ECHILD;
@@ -877,7 +894,7 @@ static int complete_walk(struct nameidata *nd)
 			return -EXDEV;
 	}
 
-	if (likely(!(nd->flags & LOOKUP_JUMPED)))
+	if (likely(!(nd->state & ND_JUMPED)))
 		return 0;
 
 	if (likely(!(dentry->d_flags & DCACHE_OP_WEAK_REVALIDATE)))
@@ -915,7 +932,7 @@ static int set_root(struct nameidata *nd)
 		} while (read_seqcount_retry(&fs->seq, seq));
 	} else {
 		get_fs_root(fs, &nd->root);
-		nd->flags |= LOOKUP_ROOT_GRABBED;
+		nd->state |= ND_ROOT_GRABBED;
 	}
 	return 0;
 }
@@ -948,7 +965,7 @@ static int nd_jump_root(struct nameidata *nd)
 		path_get(&nd->path);
 		nd->inode = nd->path.dentry->d_inode;
 	}
-	nd->flags |= LOOKUP_JUMPED;
+	nd->state |= ND_JUMPED;
 	return 0;
 }
 
@@ -976,7 +993,7 @@ int nd_jump_link(struct path *path)
 	path_put(&nd->path);
 	nd->path = *path;
 	nd->inode = nd->path.dentry->d_inode;
-	nd->flags |= LOOKUP_JUMPED;
+	nd->state |= ND_JUMPED;
 	return 0;
 
 err:
@@ -1423,7 +1440,7 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 			if (mounted) {
 				path->mnt = &mounted->mnt;
 				dentry = path->dentry = mounted->mnt.mnt_root;
-				nd->flags |= LOOKUP_JUMPED;
+				nd->state |= ND_JUMPED;
 				*seqp = read_seqcount_begin(&dentry->d_seq);
 				*inode = dentry->d_inode;
 				/*
@@ -1468,7 +1485,7 @@ static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry,
 		if (unlikely(nd->flags & LOOKUP_NO_XDEV))
 			ret = -EXDEV;
 		else
-			nd->flags |= LOOKUP_JUMPED;
+			nd->state |= ND_JUMPED;
 	}
 	if (unlikely(ret)) {
 		dput(path->dentry);
@@ -2219,7 +2236,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			case 2:
 				if (name[1] == '.') {
 					type = LAST_DOTDOT;
-					nd->flags |= LOOKUP_JUMPED;
+					nd->state |= ND_JUMPED;
 				}
 				break;
 			case 1:
@@ -2227,7 +2244,7 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 		}
 		if (likely(type == LAST_NORM)) {
 			struct dentry *parent = nd->path.dentry;
-			nd->flags &= ~LOOKUP_JUMPED;
+			nd->state &= ~ND_JUMPED;
 			if (unlikely(parent->d_flags & DCACHE_OP_HASH)) {
 				struct qstr this = { { .hash_len = hash_len }, .name = name };
 				err = parent->d_op->d_hash(parent, &this);
@@ -2301,14 +2318,14 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	if (flags & LOOKUP_RCU)
 		rcu_read_lock();
 
-	nd->flags = flags | LOOKUP_JUMPED;
-	nd->depth = 0;
+	nd->flags = flags;
+	nd->state |= ND_JUMPED;
 
 	nd->m_seq = __read_seqcount_begin(&mount_lock.seqcount);
 	nd->r_seq = __read_seqcount_begin(&rename_lock.seqcount);
 	smp_rmb();
 
-	if (flags & LOOKUP_ROOT) {
+	if (nd->state & ND_ROOT_PRESET) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
 		if (*s && unlikely(!d_can_lookup(root)))
@@ -2383,7 +2400,7 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			nd->root_seq = nd->seq;
 		} else {
 			path_get(&nd->root);
-			nd->flags |= LOOKUP_ROOT_GRABBED;
+			nd->state |= ND_ROOT_GRABBED;
 		}
 	}
 	return s;
@@ -2422,7 +2439,7 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 		;
 	if (!err && unlikely(nd->flags & LOOKUP_MOUNTPOINT)) {
 		err = handle_lookup_down(nd);
-		nd->flags &= ~LOOKUP_JUMPED; // no d_weak_revalidate(), please...
+		nd->state &= ~ND_JUMPED; // no d_weak_revalidate(), please...
 	}
 	if (!err)
 		err = complete_walk(nd);
@@ -2446,11 +2463,7 @@ int filename_lookup(int dfd, struct filename *name, unsigned flags,
 	struct nameidata nd;
 	if (IS_ERR(name))
 		return PTR_ERR(name);
-	if (unlikely(root)) {
-		nd.root = *root;
-		flags |= LOOKUP_ROOT;
-	}
-	set_nameidata(&nd, dfd, name);
+	set_nameidata(&nd, dfd, name, root);
 	retval = path_lookupat(&nd, flags | LOOKUP_RCU, path);
 	if (unlikely(retval == -ECHILD))
 		retval = path_lookupat(&nd, flags, path);
@@ -2491,7 +2504,7 @@ static struct filename *filename_parentat(int dfd, struct filename *name,
 
 	if (IS_ERR(name))
 		return name;
-	set_nameidata(&nd, dfd, name);
+	set_nameidata(&nd, dfd, name, NULL);
 	retval = path_parentat(&nd, flags | LOOKUP_RCU, parent);
 	if (unlikely(retval == -ECHILD))
 		retval = path_parentat(&nd, flags, parent);
@@ -3517,7 +3530,7 @@ struct file *do_filp_open(int dfd, struct filename *pathname,
 	int flags = op->lookup_flags;
 	struct file *filp;
 
-	set_nameidata(&nd, dfd, pathname);
+	set_nameidata(&nd, dfd, pathname, NULL);
 	filp = path_openat(&nd, op, flags | LOOKUP_RCU);
 	if (unlikely(filp == ERR_PTR(-ECHILD)))
 		filp = path_openat(&nd, op, flags);
@@ -3527,25 +3540,22 @@ struct file *do_filp_open(int dfd, struct filename *pathname,
 	return filp;
 }
 
-struct file *do_file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+struct file *do_file_open_root(const struct path *root,
 		const char *name, const struct open_flags *op)
 {
 	struct nameidata nd;
 	struct file *file;
 	struct filename *filename;
-	int flags = op->lookup_flags | LOOKUP_ROOT;
-
-	nd.root.mnt = mnt;
-	nd.root.dentry = dentry;
+	int flags = op->lookup_flags;
 
-	if (d_is_symlink(dentry) && op->intent & LOOKUP_OPEN)
+	if (d_is_symlink(root->dentry) && op->intent & LOOKUP_OPEN)
 		return ERR_PTR(-ELOOP);
 
 	filename = getname_kernel(name);
 	if (IS_ERR(filename))
 		return ERR_CAST(filename);
 
-	set_nameidata(&nd, -1, filename);
+	set_nameidata(&nd, -1, filename, root);
 	file = path_openat(&nd, op, flags | LOOKUP_RCU);
 	if (unlikely(file == ERR_PTR(-ECHILD)))
 		file = path_openat(&nd, op, flags);

fs/nfs/nfstrace.h

@@ -280,8 +280,6 @@ TRACE_DEFINE_ENUM(LOOKUP_OPEN);
 TRACE_DEFINE_ENUM(LOOKUP_CREATE);
 TRACE_DEFINE_ENUM(LOOKUP_EXCL);
 TRACE_DEFINE_ENUM(LOOKUP_RENAME_TARGET);
-TRACE_DEFINE_ENUM(LOOKUP_JUMPED);
-TRACE_DEFINE_ENUM(LOOKUP_ROOT);
 TRACE_DEFINE_ENUM(LOOKUP_EMPTY);
 TRACE_DEFINE_ENUM(LOOKUP_DOWN);
 
@@ -297,8 +295,6 @@ TRACE_DEFINE_ENUM(LOOKUP_DOWN);
 			{ LOOKUP_CREATE, "CREATE" }, \
 			{ LOOKUP_EXCL, "EXCL" }, \
 			{ LOOKUP_RENAME_TARGET, "RENAME_TARGET" }, \
-			{ LOOKUP_JUMPED, "JUMPED" }, \
-			{ LOOKUP_ROOT, "ROOT" }, \
 			{ LOOKUP_EMPTY, "EMPTY" }, \
 			{ LOOKUP_DOWN, "DOWN" })
 

fs/open.c

@@ -1173,7 +1173,7 @@ struct file *filp_open(const char *filename, int flags, umode_t mode)
 }
 EXPORT_SYMBOL(filp_open);
 
-struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
+struct file *file_open_root(const struct path *root,
 			    const char *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
@@ -1181,7 +1181,7 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 	int err = build_open_flags(&how, &op);
 	if (err)
 		return ERR_PTR(err);
-	return do_file_open_root(dentry, mnt, filename, &op);
+	return do_file_open_root(root, filename, &op);
 }
 EXPORT_SYMBOL(file_open_root);
 

fs/proc/proc_sysctl.c

@@ -1807,7 +1807,7 @@ static int process_sysctl_arg(char *param, char *val,
 		panic("%s: Failed to allocate path for %s\n", __func__, param);
 	strreplace(path, '.', '/');
 
-	file = file_open_root((*proc_mnt)->mnt_root, *proc_mnt, path, O_WRONLY, 0);
+	file = file_open_root_mnt(*proc_mnt, path, O_WRONLY, 0);
 	if (IS_ERR(file)) {
 		err = PTR_ERR(file);
 		if (err == -ENOENT)

include/linux/fs.h

@@ -2768,8 +2768,14 @@ extern long do_sys_open(int dfd, const char __user *filename, int flags,
 			umode_t mode);
 extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
-extern struct file *file_open_root(struct dentry *, struct vfsmount *,
+extern struct file *file_open_root(const struct path *,
 				   const char *, int, umode_t);
+static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
+				   const char *name, int flags, umode_t mode)
+{
+	return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root},
+			      name, flags, mode);
+}
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
 extern struct file * open_with_fake_path(const struct path *, int,
 					 struct inode*, const struct cred *);

include/linux/namei.h

@@ -36,9 +36,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT};
 
 /* internal use only */
 #define LOOKUP_PARENT		0x0010
-#define LOOKUP_JUMPED		0x1000
-#define LOOKUP_ROOT		0x2000
-#define LOOKUP_ROOT_GRABBED	0x0008
 
 /* Scoping flags for lookup. */
 #define LOOKUP_NO_SYMLINKS	0x010000 /* No symlink crossing. */

kernel/usermode_driver.c

@@ -26,7 +26,7 @@ static struct vfsmount *blob_to_mnt(const void *data, size_t len, const char *na
 	if (IS_ERR(mnt))
 		return mnt;
 
-	file = file_open_root(mnt->mnt_root, mnt, name, O_CREAT | O_WRONLY, 0700);
+	file = file_open_root_mnt(mnt, name, O_CREAT | O_WRONLY, 0700);
 	if (IS_ERR(file)) {
 		mntput(mnt);
 		return ERR_CAST(file);