[PATCH 1/2] fs: move SB_I_USERNS_VISIBLE to FS_USERNS_MOUNT_RESTRICTED

[Christian Brauner]

Whether a filesystem's mounts need to undergo a visibility check in user
namespaces is a static property of the filesystem type, not a runtime
property of each superblock instance. Both proc and sysfs always set
SB_I_USERNS_VISIBLE on their superblocks unconditionally (sysfs does so
on first creation, and subsequent mounts reuse the same superblock).

Move this flag from sb->s_iflags (SB_I_USERNS_VISIBLE) to
file_system_type->fs_flags (FS_USERNS_MOUNT_RESTRICTED) so the intent
is expressed at the filesystem type level where it belongs.

All check sites are updated to test sb->s_type->fs_flags instead of
sb->s_iflags. The SB_I_NOEXEC and SB_I_NODEV flags remain on the
superblock as they are runtime properties set during fill_super.

Signed-off-by: Christian Brauner <brauner@xxxxxxxxxx>
---
 fs/namespace.c                 | 4 ++--
 fs/proc/root.c                 | 4 ++--
 fs/sysfs/mount.c               | 4 +---
 include/linux/fs.h             | 1 +
 include/linux/fs/super_types.h | 1 -
 kernel/acct.c                  | 2 +-
 6 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index fe919abd2f01..a60ddfe71c7a 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -6405,10 +6405,10 @@ static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags
 		return false;
 
 	/* Can this filesystem be too revealing? */
-	s_iflags = sb->s_iflags;
-	if (!(s_iflags & SB_I_USERNS_VISIBLE))
+	if (!(sb->s_type->fs_flags & FS_USERNS_MOUNT_RESTRICTED))
 		return false;
 
+	s_iflags = sb->s_iflags;
 	if ((s_iflags & required_iflags) != required_iflags) {
 		WARN_ONCE(1, "Expected s_iflags to contain 0x%lx\n",
 			  required_iflags);
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 0f9100559471..b65053f9f046 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -257,7 +257,7 @@ static int proc_fill_super(struct super_block *s, struct fs_context *fc)
 	proc_apply_options(fs_info, fc, current_user_ns());
 
 	/* User space would break if executables or devices appear on proc */
-	s->s_iflags |= SB_I_USERNS_VISIBLE | SB_I_NOEXEC | SB_I_NODEV;
+	s->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
 	s->s_flags |= SB_NODIRATIME | SB_NOSUID | SB_NOEXEC;
 	s->s_blocksize = 1024;
 	s->s_blocksize_bits = 10;
@@ -359,7 +359,7 @@ static struct file_system_type proc_fs_type = {
 	.init_fs_context	= proc_init_fs_context,
 	.parameters		= proc_fs_parameters,
 	.kill_sb		= proc_kill_sb,
-	.fs_flags		= FS_USERNS_MOUNT | FS_DISALLOW_NOTIFY_PERM,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED | FS_DISALLOW_NOTIFY_PERM,
 };
 
 void __init proc_root_init(void)
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index b199e8ff79b1..b45ea5d511e7 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -32,8 +32,6 @@ static int sysfs_get_tree(struct fs_context *fc)
 	if (ret)
 		return ret;
 
-	if (kfc->new_sb_created)
-		fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
 	return 0;
 }
 
@@ -93,7 +91,7 @@ static struct file_system_type sysfs_fs_type = {
 	.name			= "sysfs",
 	.init_fs_context	= sysfs_init_fs_context,
 	.kill_sb		= sysfs_kill_sb,
-	.fs_flags		= FS_USERNS_MOUNT,
+	.fs_flags		= FS_USERNS_MOUNT | FS_USERNS_MOUNT_RESTRICTED,
 };
 
 int __init sysfs_init(void)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b5b01bb22d12..17a6baefb7d3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2280,6 +2280,7 @@ struct file_system_type {
 #define FS_MGTIME		64	/* FS uses multigrain timestamps */
 #define FS_LBS			128	/* FS supports LBS */
 #define FS_POWER_FREEZE		256	/* Always freeze on suspend/hibernate */
+#define FS_USERNS_MOUNT_RESTRICTED 512	/* Restrict mount in userns if not already visible */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
index 383050e7fdf5..182efbeb9520 100644
--- a/include/linux/fs/super_types.h
+++ b/include/linux/fs/super_types.h
@@ -326,7 +326,6 @@ struct super_block {
 #define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
 
 /* sb->s_iflags to limit user namespace mounts */
-#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
 #define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
 #define SB_I_UNTRUSTED_MOUNTER		0x00000040
 #define SB_I_EVM_HMAC_UNSUPPORTED	0x00000080
diff --git a/kernel/acct.c b/kernel/acct.c
index cbbf79d718cf..c440d43479ca 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -249,7 +249,7 @@ static int acct_on(const char __user *name)
 		return -EINVAL;
 
 	/* Exclude procfs and sysfs. */
-	if (file_inode(file)->i_sb->s_iflags & SB_I_USERNS_VISIBLE)
+	if (file_inode(file)->i_sb->s_type->fs_flags & FS_USERNS_MOUNT_RESTRICTED)
 		return -EINVAL;
 
 	if (!(file->f_mode & FMODE_CAN_WRITE))
-- 
2.47.3


--nfsjwfyis4t5hlj3
Content-Type: text/x-diff; charset=utf-8
Content-Disposition: attachment;
	filename="0002-sysfs-remove-trivial-sysfs_get_tree-wrapper.patch"