From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file

---
 kernel/fs/namei.c |  111 ++++++++++++++++++++++++++++++++++++++++++-------------
 1 files changed, 85 insertions(+), 26 deletions(-)

diff --git a/kernel/fs/namei.c b/kernel/fs/namei.c
index e02fcec..83ef3d7 100644
--- a/kernel/fs/namei.c
+++ b/kernel/fs/namei.c
@@ -1616,7 +1616,7 @@
 {
 	struct dentry *dentry, *old;
 	struct inode *inode = dir->d_inode;
-	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	/* Don't go there if it's already dead */
 	if (unlikely(IS_DEADDIR(inode)))
@@ -2724,7 +2724,7 @@
 	dput(path->dentry);
 	path->dentry = parent;
 	child = d_hash_and_lookup(parent, &this);
-	if (!child)
+	if (IS_ERR_OR_NULL(child))
 		return -ENOENT;
 
 	path->dentry = child;
@@ -2866,8 +2866,8 @@
 		return p;
 	}
 
-	inode_lock_nested(p1->d_inode, I_MUTEX_PARENT);
-	inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2);
+	lock_two_inodes(p1->d_inode, p2->d_inode,
+			I_MUTEX_PARENT, I_MUTEX_PARENT2);
 	return NULL;
 }
 EXPORT_SYMBOL(lock_rename);
@@ -2882,6 +2882,63 @@
 }
 EXPORT_SYMBOL(unlock_rename);
 
+/**
+ * mode_strip_umask - handle vfs umask stripping
+ * @dir:	parent directory of the new inode
+ * @mode:	mode of the new inode to be created in @dir
+ *
+ * Umask stripping depends on whether or not the filesystem supports POSIX
+ * ACLs. If the filesystem doesn't support it umask stripping is done directly
+ * in here. If the filesystem does support POSIX ACLs umask stripping is
+ * deferred until the filesystem calls posix_acl_create().
+ *
+ * Returns: mode
+ */
+static inline umode_t mode_strip_umask(const struct inode *dir, umode_t mode)
+{
+	if (!IS_POSIXACL(dir))
+		mode &= ~current_umask();
+	return mode;
+}
+
+/**
+ * vfs_prepare_mode - prepare the mode to be used for a new inode
+ * @dir:	parent directory of the new inode
+ * @mode:	mode of the new inode
+ * @mask_perms:	allowed permission by the vfs
+ * @type:	type of file to be created
+ *
+ * This helper consolidates and enforces vfs restrictions on the @mode of a new
+ * object to be created.
+ *
+ * Umask stripping depends on whether the filesystem supports POSIX ACLs (see
+ * the kernel documentation for mode_strip_umask()). Moving umask stripping
+ * after setgid stripping allows the same ordering for both non-POSIX ACL and
+ * POSIX ACL supporting filesystems.
+ *
+ * Note that it's currently valid for @type to be 0 if a directory is created.
+ * Filesystems raise that flag individually and we need to check whether each
+ * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a
+ * non-zero type.
+ *
+ * Returns: mode to be passed to the filesystem
+ */
+static inline umode_t vfs_prepare_mode(const struct inode *dir, umode_t mode,
+				       umode_t mask_perms, umode_t type)
+{
+	mode = mode_strip_sgid(dir, mode);
+	mode = mode_strip_umask(dir, mode);
+
+	/*
+	 * Apply the vfs mandated allowed permission mask and set the type of
+	 * file to be created before we call into the filesystem.
+	 */
+	mode &= (mask_perms & ~S_IFMT);
+	mode |= (type & S_IFMT);
+
+	return mode;
+}
+
 int vfs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 		bool want_excl)
 {
@@ -2891,8 +2948,8 @@
 
 	if (!dir->i_op->create)
 		return -EACCES;	/* shouldn't it be ENOSYS? */
-	mode &= S_IALLUGO;
-	mode |= S_IFREG;
+
+	mode = vfs_prepare_mode(dir, mode, S_IALLUGO, S_IFREG);
 	error = security_inode_create(dir, dentry, mode);
 	if (error)
 		return error;
@@ -3112,7 +3169,7 @@
 	struct dentry *dentry;
 	int error, create_error = 0;
 	umode_t mode = op->mode;
-	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	if (unlikely(IS_DEADDIR(dir_inode)))
 		return ERR_PTR(-ENOENT);
@@ -3156,8 +3213,7 @@
 	if (open_flag & O_CREAT) {
 		if (open_flag & O_EXCL)
 			open_flag &= ~O_TRUNC;
-		if (!IS_POSIXACL(dir->d_inode))
-			mode &= ~current_umask();
+		mode = vfs_prepare_mode(dir->d_inode, mode, mode, mode);
 		if (likely(got_write))
 			create_error = may_o_create(&nd->path, dentry, mode);
 		else
@@ -3370,8 +3426,7 @@
 	child = d_alloc(dentry, &slash_name);
 	if (unlikely(!child))
 		goto out_err;
-	if (!IS_POSIXACL(dir))
-		mode &= ~current_umask();
+	mode = vfs_prepare_mode(dir, mode, mode, mode);
 	error = dir->i_op->tmpfile(dir, child, mode);
 	if (error)
 		goto out_err;
@@ -3632,6 +3687,7 @@
 	if (!dir->i_op->mknod)
 		return -EPERM;
 
+	mode = vfs_prepare_mode(dir, mode, mode, mode);
 	error = devcgroup_inode_mknod(mode, dev);
 	if (error)
 		return error;
@@ -3680,9 +3736,8 @@
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (!IS_POSIXACL(path.dentry->d_inode))
-		mode &= ~current_umask();
-	error = security_path_mknod(&path, dentry, mode, dev);
+	error = security_path_mknod(&path, dentry,
+			mode_strip_umask(path.dentry->d_inode, mode), dev);
 	if (error)
 		goto out;
 	switch (mode & S_IFMT) {
@@ -3730,7 +3785,7 @@
 	if (!dir->i_op->mkdir)
 		return -EPERM;
 
-	mode &= (S_IRWXUGO|S_ISVTX);
+	mode = vfs_prepare_mode(dir, mode, S_IRWXUGO | S_ISVTX, 0);
 	error = security_inode_mkdir(dir, dentry, mode);
 	if (error)
 		return error;
@@ -3757,9 +3812,8 @@
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (!IS_POSIXACL(path.dentry->d_inode))
-		mode &= ~current_umask();
-	error = security_path_mkdir(&path, dentry, mode);
+	error = security_path_mkdir(&path, dentry,
+			mode_strip_umask(path.dentry->d_inode, mode));
 	if (!error)
 		error = vfs_mkdir(path.dentry->d_inode, dentry, mode);
 	done_path_create(&path, dentry);
@@ -4294,7 +4348,7 @@
  *	   sb->s_vfs_rename_mutex. We might be more accurate, but that's another
  *	   story.
  *	c) we have to lock _four_ objects - parents and victim (if it exists),
- *	   and source (if it is not a directory).
+ *	   and source.
  *	   And that - after we got ->i_mutex on parents (until then we don't know
  *	   whether the target exists).  Solution: try to be smart with locking
  *	   order for inodes.  We rely on the fact that tree topology may change
@@ -4371,10 +4425,16 @@
 
 	take_dentry_name_snapshot(&old_name, old_dentry);
 	dget(new_dentry);
-	if (!is_dir || (flags & RENAME_EXCHANGE))
-		lock_two_nondirectories(source, target);
-	else if (target)
-		inode_lock(target);
+	/*
+	 * Lock all moved children. Moved directories may need to change parent
+	 * pointer so they need the lock to prevent against concurrent
+	 * directory changes moving parent pointer. For regular files we've
+	 * historically always done this. The lockdep locking subclasses are
+	 * somewhat arbitrary but RENAME_EXCHANGE in particular can swap
+	 * regular files and directories so it's difficult to tell which
+	 * subclasses to use.
+	 */
+	lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2);
 
 	error = -EBUSY;
 	if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry))
@@ -4418,9 +4478,8 @@
 			d_exchange(old_dentry, new_dentry);
 	}
 out:
-	if (!is_dir || (flags & RENAME_EXCHANGE))
-		unlock_two_nondirectories(source, target);
-	else if (target)
+	inode_unlock(source);
+	if (target)
 		inode_unlock(target);
 	dput(new_dentry);
 	if (!error) {

--
Gitblit v1.6.2