Merge tag 'v4.5-rc1' into x86/asm, to refresh the branch before merging new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 166 insertions, 104 deletions

diff --git a/fs/namei.c b/fs/namei.c
index 3c909aebef70..f624d132e01e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -534,10 +534,8 @@ static void restore_nameidata(void)
 	current->nameidata = old;
 	if (old)
 		old->total_link_count = now->total_link_count;
-	if (now->stack != now->internal) {
+	if (now->stack != now->internal)
 		kfree(now->stack);
-		now->stack = now->internal;
-	}
 }
 
 static int __nd_alloc_stack(struct nameidata *nd)
@@ -654,7 +652,7 @@ static bool legitimize_links(struct nameidata *nd)
  * Path walking has 2 modes, rcu-walk and ref-walk (see
  * Documentation/filesystems/path-lookup.txt).  In situations when we can't
  * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab
- * normal reference counts on dentries and vfsmounts to transition to rcu-walk
+ * normal reference counts on dentries and vfsmounts to transition to ref-walk
  * mode.  Refcounts are grabbed at the last known good point before rcu-walk
  * got stuck, so ref-walk may continue from there. If this is not successful
  * (eg. a seqcount has changed), then failure is returned and it's up to caller
@@ -804,19 +802,19 @@ static int complete_walk(struct nameidata *nd)
 
 static void set_root(struct nameidata *nd)
 {
-	get_fs_root(current->fs, &nd->root);
-}
-
-static void set_root_rcu(struct nameidata *nd)
-{
 	struct fs_struct *fs = current->fs;
-	unsigned seq;
 
-	do {
-		seq = read_seqcount_begin(&fs->seq);
-		nd->root = fs->root;
-		nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
-	} while (read_seqcount_retry(&fs->seq, seq));
+	if (nd->flags & LOOKUP_RCU) {
+		unsigned seq;
+
+		do {
+			seq = read_seqcount_begin(&fs->seq);
+			nd->root = fs->root;
+			nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
+		} while (read_seqcount_retry(&fs->seq, seq));
+	} else {
+		get_fs_root(fs, &nd->root);
+	}
 }
 
 static void path_put_conditional(struct path *path, struct nameidata *nd)
@@ -838,6 +836,26 @@ static inline void path_to_nameidata(const struct path *path,
 	nd->path.dentry = path->dentry;
 }
 
+static int nd_jump_root(struct nameidata *nd)
+{
+	if (nd->flags & LOOKUP_RCU) {
+		struct dentry *d;
+		nd->path = nd->root;
+		d = nd->path.dentry;
+		nd->inode = d->d_inode;
+		nd->seq = nd->root_seq;
+		if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
+			return -ECHILD;
+	} else {
+		path_put(&nd->path);
+		nd->path = nd->root;
+		path_get(&nd->path);
+		nd->inode = nd->path.dentry->d_inode;
+	}
+	nd->flags |= LOOKUP_JUMPED;
+	return 0;
+}
+
 /*
  * Helper to directly jump to a known parsed path from ->get_link,
  * caller must have taken a reference to path beforehand.
@@ -1016,25 +1034,10 @@ const char *get_link(struct nameidata *nd)
 			return res;
 	}
 	if (*res == '/') {
-		if (nd->flags & LOOKUP_RCU) {
-			struct dentry *d;
-			if (!nd->root.mnt)
-				set_root_rcu(nd);
-			nd->path = nd->root;
-			d = nd->path.dentry;
-			nd->inode = d->d_inode;
-			nd->seq = nd->root_seq;
-			if (unlikely(read_seqcount_retry(&d->d_seq, nd->seq)))
-				return ERR_PTR(-ECHILD);
-		} else {
-			if (!nd->root.mnt)
-				set_root(nd);
-			path_put(&nd->path);
-			nd->path = nd->root;
-			path_get(&nd->root);
-			nd->inode = nd->path.dentry->d_inode;
-		}
-		nd->flags |= LOOKUP_JUMPED;
+		if (!nd->root.mnt)
+			set_root(nd);
+		if (unlikely(nd_jump_root(nd)))
+			return ERR_PTR(-ECHILD);
 		while (unlikely(*++res == '/'))
 			;
 	}
@@ -1295,8 +1298,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 static int follow_dotdot_rcu(struct nameidata *nd)
 {
 	struct inode *inode = nd->inode;
-	if (!nd->root.mnt)
-		set_root_rcu(nd);
 
 	while (1) {
 		if (path_equal(&nd->path, &nd->root))
@@ -1416,9 +1417,6 @@ static void follow_mount(struct path *path)
 
 static int follow_dotdot(struct nameidata *nd)
 {
-	if (!nd->root.mnt)
-		set_root(nd);
-
 	while(1) {
 		struct dentry *old = nd->path.dentry;
 
@@ -1631,9 +1629,9 @@ static int lookup_slow(struct nameidata *nd, struct path *path)
 	parent = nd->path.dentry;
 	BUG_ON(nd->inode != parent->d_inode);
 
-	mutex_lock(&parent->d_inode->i_mutex);
+	inode_lock(parent->d_inode);
 	dentry = __lookup_hash(&nd->last, parent, nd->flags);
-	mutex_unlock(&parent->d_inode->i_mutex);
+	inode_unlock(parent->d_inode);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 	path->mnt = nd->path.mnt;
@@ -1656,6 +1654,8 @@ static inline int may_lookup(struct nameidata *nd)
 static inline int handle_dots(struct nameidata *nd, int type)
 {
 	if (type == LAST_DOTDOT) {
+		if (!nd->root.mnt)
+			set_root(nd);
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
@@ -2021,18 +2021,19 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 	}
 
 	nd->root.mnt = NULL;
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU) {
+		if (flags & LOOKUP_RCU)
 			rcu_read_lock();
-			set_root_rcu(nd);
-			nd->seq = nd->root_seq;
-		} else {
-			set_root(nd);
-			path_get(&nd->root);
-		}
-		nd->path = nd->root;
+		set_root(nd);
+		if (likely(!nd_jump_root(nd)))
+			return s;
+		nd->root.mnt = NULL;
+		rcu_read_unlock();
+		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
@@ -2043,11 +2044,14 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
+				nd->inode = nd->path.dentry->d_inode;
 				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			} while (read_seqcount_retry(&fs->seq, seq));
 		} else {
 			get_fs_pwd(current->fs, &nd->path);
+			nd->inode = nd->path.dentry->d_inode;
 		}
+		return s;
 	} else {
 		/* Caller must check execute permissions on the starting path component */
 		struct fd f = fdget_raw(nd->dfd);
@@ -2077,16 +2081,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		fdput(f);
 		return s;
 	}
-
-	nd->inode = nd->path.dentry->d_inode;
-	if (!(flags & LOOKUP_RCU))
-		return s;
-	if (likely(!read_seqcount_retry(&nd->path.dentry->d_seq, nd->seq)))
-		return s;
-	if (!(nd->flags & LOOKUP_ROOT))
-		nd->root.mnt = NULL;
-	rcu_read_unlock();
-	return ERR_PTR(-ECHILD);
 }
 
 static const char *trailing_symlink(struct nameidata *nd)
@@ -2235,10 +2229,10 @@ struct dentry *kern_path_locked(const char *name, struct path *path)
 		putname(filename);
 		return ERR_PTR(-EINVAL);
 	}
-	mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
 	d = __lookup_hash(&last, path->dentry, 0);
 	if (IS_ERR(d)) {
-		mutex_unlock(&path->dentry->d_inode->i_mutex);
+		inode_unlock(path->dentry->d_inode);
 		path_put(path);
 	}
 	putname(filename);
@@ -2279,6 +2273,8 @@ EXPORT_SYMBOL(vfs_path_lookup);
  *
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.
+ *
+ * The caller must hold base->i_mutex.
  */
 struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
@@ -2286,7 +2282,7 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 	unsigned int c;
 	int err;
 
-	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
+	WARN_ON_ONCE(!inode_is_locked(base->d_inode));
 
 	this.name = name;
 	this.len = len;
@@ -2322,6 +2318,75 @@ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 }
 EXPORT_SYMBOL(lookup_one_len);
 
+/**
+ * lookup_one_len_unlocked - 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.
+ *
+ * Unlike lookup_one_len, it should be called without the parent
+ * i_mutex held, and will take the i_mutex itself if necessary.
+ */
+struct dentry *lookup_one_len_unlocked(const char *name,
+				       struct dentry *base, int len)
+{
+	struct qstr this;
+	unsigned int c;
+	int err;
+	struct dentry *ret;
+
+	this.name = name;
+	this.len = len;
+	this.hash = full_name_hash(name, len);
+	if (!len)
+		return ERR_PTR(-EACCES);
+
+	if (unlikely(name[0] == '.')) {
+		if (len < 2 || (len == 2 && name[1] == '.'))
+			return ERR_PTR(-EACCES);
+	}
+
+	while (len--) {
+		c = *(const unsigned char *)name++;
+		if (c == '/' || c == '\0')
+			return ERR_PTR(-EACCES);
+	}
+	/*
+	 * See if the low-level filesystem might want
+	 * to use its own hash..
+	 */
+	if (base->d_flags & DCACHE_OP_HASH) {
+		int err = base->d_op->d_hash(base, &this);
+		if (err < 0)
+			return ERR_PTR(err);
+	}
+
+	err = inode_permission(base->d_inode, MAY_EXEC);
+	if (err)
+		return ERR_PTR(err);
+
+	/*
+	 * __d_lookup() is used to try to get a quick answer and avoid the
+	 * mutex.  A false-negative does no harm.
+	 */
+	ret = __d_lookup(base, &this);
+	if (ret && unlikely(ret->d_flags & DCACHE_OP_REVALIDATE)) {
+		dput(ret);
+		ret = NULL;
+	}
+	if (ret)
+		return ret;
+
+	inode_lock(base->d_inode);
+	ret =  __lookup_hash(&this, base, 0);
+	inode_unlock(base->d_inode);
+	return ret;
+}
+EXPORT_SYMBOL(lookup_one_len_unlocked);
+
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
@@ -2398,7 +2463,7 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 		goto done;
 	}
 
-	mutex_lock(&dir->d_inode->i_mutex);
+	inode_lock(dir->d_inode);
 	dentry = d_lookup(dir, &nd->last);
 	if (!dentry) {
 		/*
@@ -2408,16 +2473,16 @@ mountpoint_last(struct nameidata *nd, struct path *path)
 		 */
 		dentry = d_alloc(dir, &nd->last);
 		if (!dentry) {
-			mutex_unlock(&dir->d_inode->i_mutex);
+			inode_unlock(dir->d_inode);
 			return -ENOMEM;
 		}
 		dentry = lookup_real(dir->d_inode, dentry, nd->flags);
 		if (IS_ERR(dentry)) {
-			mutex_unlock(&dir->d_inode->i_mutex);
+			inode_unlock(dir->d_inode);
 			return PTR_ERR(dentry);
 		}
 	}
-	mutex_unlock(&dir->d_inode->i_mutex);
+	inode_unlock(dir->d_inode);
 
 done:
 	if (d_is_negative(dentry)) {
@@ -2607,7 +2672,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 	struct dentry *p;
 
 	if (p1 == p2) {
-		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
 		return NULL;
 	}
 
@@ -2615,29 +2680,29 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 
 	p = d_ancestor(p2, p1);
 	if (p) {
-		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
+		inode_lock_nested(p2->d_inode, I_MUTEX_PARENT);
+		inode_lock_nested(p1->d_inode, I_MUTEX_CHILD);
 		return p;
 	}
 
 	p = d_ancestor(p1, p2);
 	if (p) {
-		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
+		inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+		inode_lock_nested(p2->d_inode, I_MUTEX_CHILD);
 		return p;
 	}
 
-	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-	mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT2);
+	inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
+	inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
 	return NULL;
 }
 EXPORT_SYMBOL(lock_rename);
 
 void unlock_rename(struct dentry *p1, struct dentry *p2)
 {
-	mutex_unlock(&p1->d_inode->i_mutex);
+	inode_unlock(p1->d_inode);
 	if (p1 != p2) {
-		mutex_unlock(&p2->d_inode->i_mutex);
+		inode_unlock(p2->d_inode);
 		mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
 	}
 }
@@ -2670,10 +2735,6 @@ static int may_open(struct path *path, int acc_mode, int flag)
 	struct inode *inode = dentry->d_inode;
 	int error;
 
-	/* O_PATH? */
-	if (!acc_mode)
-		return 0;
-
 	if (!inode)
 		return -ENOENT;
 
@@ -2695,7 +2756,7 @@ static int may_open(struct path *path, int acc_mode, int flag)
 		break;
 	}
 
-	error = inode_permission(inode, acc_mode);
+	error = inode_permission(inode, MAY_OPEN | acc_mode);
 	if (error)
 		return error;
 
@@ -2887,7 +2948,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	if (*opened & FILE_CREATED) {
 		WARN_ON(!(open_flag & O_CREAT));
 		fsnotify_create(dir, dentry);
-		acc_mode = MAY_OPEN;
+		acc_mode = 0;
 	}
 	error = may_open(&file->f_path, acc_mode, open_flag);
 	if (error)
@@ -3080,9 +3141,9 @@ retry_lookup:
 		 * dropping this one anyway.
 		 */
 	}
-	mutex_lock(&dir->d_inode->i_mutex);
+	inode_lock(dir->d_inode);
 	error = lookup_open(nd, &path, file, op, got_write, opened);
-	mutex_unlock(&dir->d_inode->i_mutex);
+	inode_unlock(dir->d_inode);
 
 	if (error <= 0) {
 		if (error)
@@ -3100,7 +3161,7 @@ retry_lookup:
 		/* Don't check for write permission, don't truncate */
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
-		acc_mode = MAY_OPEN;
+		acc_mode = 0;
 		path_to_nameidata(&path, nd);
 		goto finish_open_created;
 	}
@@ -3184,10 +3245,11 @@ finish_open:
 		got_write = true;
 	}
 finish_open_created:
-	error = may_open(&nd->path, acc_mode, open_flag);
-	if (error)
-		goto out;
-
+	if (likely(!(open_flag & O_PATH))) {
+		error = may_open(&nd->path, acc_mode, open_flag);
+		if (error)
+			goto out;
+	}
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 	error = vfs_open(&nd->path, file, current_cred());
 	if (!error) {
@@ -3274,7 +3336,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
-	error = may_open(&path, MAY_OPEN, op->open_flag);
+	error = may_open(&path, 0, op->open_flag);
 	if (error)
 		goto out2;
 	file->f_path.mnt = path.mnt;
@@ -3427,7 +3489,7 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 * Do the final lookup.
 	 */
 	lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL;
-	mutex_lock_nested(&path->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
 	dentry = __lookup_hash(&last, path->dentry, lookup_flags);
 	if (IS_ERR(dentry))
 		goto unlock;
@@ -3456,7 +3518,7 @@ fail:
 	dput(dentry);
 	dentry = ERR_PTR(error);
 unlock:
-	mutex_unlock(&path->dentry->d_inode->i_mutex);
+	inode_unlock(path->dentry->d_inode);
 	if (!err2)
 		mnt_drop_write(path->mnt);
 out:
@@ -3476,7 +3538,7 @@ EXPORT_SYMBOL(kern_path_create);
 void done_path_create(struct path *path, struct dentry *dentry)
 {
 	dput(dentry);
-	mutex_unlock(&path->dentry->d_inode->i_mutex);
+	inode_unlock(path->dentry->d_inode);
 	mnt_drop_write(path->mnt);
 	path_put(path);
 }
@@ -3673,7 +3735,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return -EPERM;
 
 	dget(dentry);
-	mutex_lock(&dentry->d_inode->i_mutex);
+	inode_lock(dentry->d_inode);
 
 	error = -EBUSY;
 	if (is_local_mountpoint(dentry))
@@ -3693,7 +3755,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry)
 	detach_mounts(dentry);
 
 out:
-	mutex_unlock(&dentry->d_inode->i_mutex);
+	inode_unlock(dentry->d_inode);
 	dput(dentry);
 	if (!error)
 		d_delete(dentry);
@@ -3732,7 +3794,7 @@ retry:
 	if (error)
 		goto exit1;
 
-	mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
 	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
@@ -3748,7 +3810,7 @@ retry:
 exit3:
 	dput(dentry);
 exit2:
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	inode_unlock(path.dentry->d_inode);
 	mnt_drop_write(path.mnt);
 exit1:
 	path_put(&path);
@@ -3794,7 +3856,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 	if (!dir->i_op->unlink)
 		return -EPERM;
 
-	mutex_lock(&target->i_mutex);
+	inode_lock(target);
 	if (is_local_mountpoint(dentry))
 		error = -EBUSY;
 	else {
@@ -3811,7 +3873,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate
 		}
 	}
 out:
-	mutex_unlock(&target->i_mutex);
+	inode_unlock(target);
 
 	/* We don't d_delete() NFS sillyrenamed files--they still exist. */
 	if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) {
@@ -3854,7 +3916,7 @@ retry:
 	if (error)
 		goto exit1;
 retry_deleg:
-	mutex_lock_nested(&path.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
+	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
 	dentry = __lookup_hash(&last, path.dentry, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
@@ -3872,7 +3934,7 @@ retry_deleg:
 exit2:
 		dput(dentry);
 	}
-	mutex_unlock(&path.dentry->d_inode->i_mutex);
+	inode_unlock(path.dentry->d_inode);
 	if (inode)
 		iput(inode);	/* truncate the inode here */
 	inode = NULL;
@@ -4024,7 +4086,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 	if (error)
 		return error;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	/* Make sure we don't allow creating hardlink to an unlinked file */
 	if (inode->i_nlink == 0 && !(inode->i_state & I_LINKABLE))
 		error =  -ENOENT;
@@ -4041,7 +4103,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de
 		inode->i_state &= ~I_LINKABLE;
 		spin_unlock(&inode->i_lock);
 	}
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	if (!error)
 		fsnotify_link(dir, inode, new_dentry);
 	return error;
@@ -4241,7 +4303,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (!is_dir || (flags & RENAME_EXCHANGE))
 		lock_two_nondirectories(source, target);
 	else if (target)
-		mutex_lock(&target->i_mutex);
+		inode_lock(target);
 
 	error = -EBUSY;
 	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
@@ -4294,7 +4356,7 @@ out:
 	if (!is_dir || (flags & RENAME_EXCHANGE))
 		unlock_two_nondirectories(source, target);
 	else if (target)
-		mutex_unlock(&target->i_mutex);
+		inode_unlock(target);
 	dput(new_dentry);
 	if (!error) {
 		fsnotify_move(old_dir, new_dir, old_name, is_dir,