fs: get rid of __FMODE_NONOTIFY kludge

All it takes to get rid of the __FMODE_NONOTIFY kludge is switching
fanotify from anon_inode_getfd() to anon_inode_getfile_fmode() and adding
a dentry_open_nonotify() helper to be used by fanotify on the other path.
That's it - no more weird shit in OPEN_FMODE(), etc.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/linux-fsdevel/20241113043003.GH3387508@ZenIV/
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/d1231137e7b661a382459e79a764259509a4115d.1731684329.git.josef@toxicpanda.com

fs/fcntl.c

@@ -1158,10 +1158,10 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+	BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ !=
 		HWEIGHT32(
 			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
-			__FMODE_EXEC | __FMODE_NONOTIFY));
+			__FMODE_EXEC));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
 					 sizeof(struct fasync_struct), 0,

fs/notify/fanotify/fanotify_user.c

@@ -100,8 +100,7 @@ static void __init fanotify_sysctls_init(void)
  *
  * Internal and external open flags are stored together in field f_flags of
  * struct file. Only external open flags shall be allowed in event_f_flags.
- * Internal flags like FMODE_NONOTIFY, FMODE_EXEC, FMODE_NOCMTIME shall be
+ * Internal flags like FMODE_EXEC shall be excluded.
- * excluded.
  */
 #define	FANOTIFY_INIT_ALL_EVENT_F_BITS				( \
 		O_ACCMODE	| O_APPEND	| O_NONBLOCK	| \
@@ -258,12 +257,11 @@ static int create_fd(struct fsnotify_group *group, const struct path *path,
 		return client_fd;
 
 	/*
-	 * we need a new file handle for the userspace program so it can read even if it was
+	 * We provide an fd for the userspace program, so it could access the
-	 * originally opened O_WRONLY.
+	 * file without generating fanotify events itself.
 	 */
-	new_file = dentry_open(path,
+	new_file = dentry_open_nonotify(path, group->fanotify_data.f_flags,
-			       group->fanotify_data.f_flags | __FMODE_NONOTIFY,
+					current_cred());
-			       current_cred());
 	if (IS_ERR(new_file)) {
 		put_unused_fd(client_fd);
 		client_fd = PTR_ERR(new_file);
@@ -1409,6 +1407,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	unsigned int fid_mode = flags & FANOTIFY_FID_BITS;
 	unsigned int class = flags & FANOTIFY_CLASS_BITS;
 	unsigned int internal_flags = 0;
+	struct file *file;
 
 	pr_debug("%s: flags=%x event_f_flags=%x\n",
 		 __func__, flags, event_f_flags);
@@ -1477,7 +1476,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	    (!(fid_mode & FAN_REPORT_NAME) || !(fid_mode & FAN_REPORT_FID)))
 		return -EINVAL;
 
-	f_flags = O_RDWR | __FMODE_NONOTIFY;
+	f_flags = O_RDWR;
 	if (flags & FAN_CLOEXEC)
 		f_flags |= O_CLOEXEC;
 	if (flags & FAN_NONBLOCK)
@@ -1555,10 +1554,18 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 			goto out_destroy_group;
 	}
 
-	fd = anon_inode_getfd("[fanotify]", &fanotify_fops, group, f_flags);
+	fd = get_unused_fd_flags(f_flags);
 	if (fd < 0)
 		goto out_destroy_group;
 
+	file = anon_inode_getfile_fmode("[fanotify]", &fanotify_fops, group,
+					f_flags, FMODE_NONOTIFY);
+	if (IS_ERR(file)) {
+		fd = PTR_ERR(file);
+		put_unused_fd(fd);
+		goto out_destroy_group;
+	}
+	fd_install(fd, file);
 	return fd;
 
 out_destroy_group:

fs/open.c

@@ -1105,6 +1105,23 @@ struct file *dentry_open(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(dentry_open);
 
+struct file *dentry_open_nonotify(const struct path *path, int flags,
+				  const struct cred *cred)
+{
+	struct file *f = alloc_empty_file(flags, cred);
+	if (!IS_ERR(f)) {
+		int error;
+
+		f->f_mode |= FMODE_NONOTIFY;
+		error = vfs_open(path, f);
+		if (error) {
+			fput(f);
+			f = ERR_PTR(error);
+		}
+	}
+	return f;
+}
+
 /**
  * dentry_create - Create and open a file
  * @path: path to create
@@ -1202,7 +1219,7 @@ inline struct open_how build_open_how(int flags, umode_t mode)
 inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 {
 	u64 flags = how->flags;
-	u64 strip = __FMODE_NONOTIFY | O_CLOEXEC;
+	u64 strip = O_CLOEXEC;
 	int lookup_flags = 0;
 	int acc_mode = ACC_MODE(flags);
 
@@ -1210,9 +1227,7 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op)
 			 "struct open_flags doesn't yet handle flags > 32 bits");
 
 	/*
-	 * Strip flags that either shouldn't be set by userspace like
+	 * Strip flags that aren't relevant in determining struct open_flags.
-	 * FMODE_NONOTIFY or that aren't relevant in determining struct
-	 * open_flags like O_CLOEXEC.
 	 */
 	flags &= ~strip;
 

include/linux/fs.h

@@ -2751,6 +2751,8 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
 }
 struct file *dentry_open(const struct path *path, int flags,
 			 const struct cred *creds);
+struct file *dentry_open_nonotify(const struct path *path, int flags,
+				  const struct cred *cred);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
 struct path *backing_file_user_path(struct file *f);
@@ -3707,11 +3709,9 @@ struct ctl_table;
 int __init list_bdev_fs_names(char *buf, size_t size);
 
 #define __FMODE_EXEC		((__force int) FMODE_EXEC)
-#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)
 
 #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
-#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
+#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE))
-					    (flag & __FMODE_NONOTIFY)))
 
 static inline bool is_sxid(umode_t mode)
 {

include/uapi/asm-generic/fcntl.h

@@ -6,7 +6,6 @@
 
 /*
  * FMODE_EXEC is 0x20
- * FMODE_NONOTIFY is 0x4000000
  * These cannot be used by userspace O_* until internal and external open
  * flags are split.
  * -Eric Paris