Merge patch series "Fix for huge faults regression"

Amir Goldstein <amir73il@gmail.com> says:

The two Fix patches have been tested by Alex together and each one
independently.

I also verified that they pass the LTP inoityf/fanotify tests.

* patches from https://lore.kernel.org/r/20250203223205.861346-1-amir73il@gmail.com:
  fsnotify: disable pre-content and permission events by default
  fsnotify: disable notification by default for all pseudo files
  fsnotify: use accessor to set FMODE_NONOTIFY_*

Link: https://lore.kernel.org/r/20250203223205.861346-1-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: brauner

drivers/tty/pty.c

@@ -798,7 +798,7 @@ static int ptmx_open(struct inode *inode, struct file *filp)
 	nonseekable_open(inode, filp);
 
 	/* We refuse fsnotify events on ptmx, since it's a shared resource */
-	filp->f_mode |= FMODE_NONOTIFY;
+	file_set_fsnotify_mode(filp, FMODE_NONOTIFY);
 
 	retval = tty_alloc_file(filp);
 	if (retval)

fs/file_table.c

@@ -194,6 +194,11 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 	 * refcount bumps we should reinitialize the reused file first.
 	 */
 	file_ref_init(&f->f_ref, 1);
+	/*
+	 * Disable permission and pre-content events for all files by default.
+	 * They may be enabled later by file_set_fsnotify_mode_from_watchers().
+	 */
+	file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
 	return 0;
 }
 
@@ -375,7 +380,13 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 	if (IS_ERR(file)) {
 		ihold(inode);
 		path_put(&path);
+		return file;
 	}
+	/*
+	 * Disable all fsnotify events for pseudo files by default.
+	 * They may be enabled by caller with file_set_fsnotify_mode().
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY);
 	return file;
 }
 EXPORT_SYMBOL(alloc_file_pseudo);
@@ -400,6 +411,11 @@ struct file *alloc_file_pseudo_noaccount(struct inode *inode,
 		return file;
 	}
 	file_init_path(file, &path, fops);
+	/*
+	 * Disable all fsnotify events for pseudo files by default.
+	 * They may be enabled by caller with file_set_fsnotify_mode().
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY);
 	return file;
 }
 EXPORT_SYMBOL_GPL(alloc_file_pseudo_noaccount);

fs/notify/fsnotify.c

@@ -648,7 +648,7 @@ EXPORT_SYMBOL_GPL(fsnotify);
  * Later, fsnotify permission hooks do not check if there are permission event
  * watches, but that there were permission event watches at open time.
  */
-void file_set_fsnotify_mode(struct file *file)
+void file_set_fsnotify_mode_from_watchers(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry, *parent;
 	struct super_block *sb = dentry->d_sb;
@@ -665,7 +665,7 @@ void file_set_fsnotify_mode(struct file *file)
 	 */
 	if (likely(!fsnotify_sb_has_priority_watchers(sb,
 						FSNOTIFY_PRIO_CONTENT))) {
-		file->f_mode |= FMODE_NONOTIFY_PERM;
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
 		return;
 	}
 
@@ -676,7 +676,7 @@ void file_set_fsnotify_mode(struct file *file)
 	if ((!d_is_dir(dentry) && !d_is_reg(dentry)) ||
 	    likely(!fsnotify_sb_has_priority_watchers(sb,
 						FSNOTIFY_PRIO_PRE_CONTENT))) {
-		file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
 		return;
 	}
 
@@ -686,19 +686,25 @@ void file_set_fsnotify_mode(struct file *file)
 	 */
 	mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
 	if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask,
-				     FSNOTIFY_PRE_CONTENT_EVENTS)))
+				     FSNOTIFY_PRE_CONTENT_EVENTS))) {
+		/* Enable pre-content events */
+		file_set_fsnotify_mode(file, 0);
 		return;
+	}
 
 	/* Is parent watching for pre-content events on this file? */
 	if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
 		parent = dget_parent(dentry);
 		p_mask = fsnotify_inode_watches_children(d_inode(parent));
 		dput(parent);
-		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)
+		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) {
+			/* Enable pre-content events */
+			file_set_fsnotify_mode(file, 0);
 			return;
+		}
 	}
 	/* Nobody watching for pre-content events from this file */
-	file->f_mode |= FMODE_NONOTIFY | FMODE_NONOTIFY_PERM;
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
 }
 #endif
 

fs/open.c

@@ -905,7 +905,8 @@ static int do_dentry_open(struct file *f,
 	f->f_sb_err = file_sample_sb_err(f);
 
 	if (unlikely(f->f_flags & O_PATH)) {
-		f->f_mode = FMODE_PATH | FMODE_OPENED | FMODE_NONOTIFY;
+		f->f_mode = FMODE_PATH | FMODE_OPENED;
+		file_set_fsnotify_mode(f, FMODE_NONOTIFY);
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -935,10 +936,10 @@ static int do_dentry_open(struct file *f,
 
 	/*
 	 * Set FMODE_NONOTIFY_* bits according to existing permission watches.
-	 * If FMODE_NONOTIFY was already set for an fanotify fd, this doesn't
-	 * change anything.
+	 * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a
+	 * pseudo file, this call will not change the mode.
 	 */
-	file_set_fsnotify_mode(f);
+	file_set_fsnotify_mode_from_watchers(f);
 	error = fsnotify_open_perm(f);
 	if (error)
 		goto cleanup_all;
@@ -1122,7 +1123,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags,
 	if (!IS_ERR(f)) {
 		int error;
 
-		f->f_mode |= FMODE_NONOTIFY;
+		file_set_fsnotify_mode(f, FMODE_NONOTIFY);
 		error = vfs_open(path, f);
 		if (error) {
 			fput(f);

fs/pipe.c

@@ -960,6 +960,12 @@ int create_pipe_files(struct file **res, int flags)
 	res[1] = f;
 	stream_open(inode, res[0]);
 	stream_open(inode, res[1]);
+	/*
+	 * Disable permission and pre-content events, but enable legacy
+	 * inotify events for legacy users.
+	 */
+	file_set_fsnotify_mode(res[0], FMODE_NONOTIFY_PERM);
+	file_set_fsnotify_mode(res[1], FMODE_NONOTIFY_PERM);
 	return 0;
 }
 

include/linux/fs.h

@@ -222,7 +222,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_FSNOTIFY_HSM(mode)	0
 #endif
 
-
 /*
  * Attribute flags.  These should be or-ed together to figure out what
  * has been changed!
@@ -3140,6 +3139,12 @@ static inline void exe_file_allow_write_access(struct file *exe_file)
 	allow_write_access(exe_file);
 }
 
+static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode)
+{
+	file->f_mode &= ~FMODE_FSNOTIFY_MASK;
+	file->f_mode |= mode;
+}
+
 static inline bool inode_is_open_for_write(const struct inode *inode)
 {
 	return atomic_read(&inode->i_writecount) > 0;

include/linux/fsnotify.h

@@ -129,7 +129,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 
-void file_set_fsnotify_mode(struct file *file);
+void file_set_fsnotify_mode_from_watchers(struct file *file);
 
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
@@ -213,7 +213,7 @@ static inline int fsnotify_open_perm(struct file *file)
 }
 
 #else
-static inline void file_set_fsnotify_mode(struct file *file)
+static inline void file_set_fsnotify_mode_from_watchers(struct file *file)
 {
 }
 

net/socket.c

@@ -479,6 +479,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 	sock->file = file;
 	file->private_data = sock;
 	stream_open(SOCK_INODE(sock), file);
+	/*
+	 * Disable permission and pre-content events, but enable legacy
+	 * inotify events for legacy users.
+	 */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
 	return file;
 }
 EXPORT_SYMBOL(sock_alloc_file);