[PATCH 09/23] VFS: Implement a superblock configuration context [ver #4]

From: David Howells
Date: Mon May 22 2017 - 11:59:14 EST

Implement a superblock configuration context concept to be used during
superblock creation for mount and superblock reconfiguration for remount.

The mounting procedure then becomes:

(1) Allocate new sb_config context.

(2) Configure the context.

(3) Create superblock.

(4) Mount the superblock any number of times.

(5) Destroy the context.

Rather than calling fs_type->mount(), an sb_config struct is created and
fs_type->init_sb_config() is called to set it up. fs_type->sb_config_size
says how much space should be allocated for the config context. The
sb_config struct is placed at the beginning and any extra space is for the
filesystem's use.

A set of operations has to be set by ->init_sb_config() to provide freeing,
duplication, option parsing, binary data parsing, validation, mounting and
superblock filling.

Legacy filesystems are supported by the provision of a set of legacy
sb_config operations that build up a list of mount options and then invoke
fs_type->mount() from within the sb_config ->get_tree() operation. This
allows all filesystems to be accessed using sb_config.

It should be noted that, whilst this patch adds a lot of lines of code,
there is quite a bit of duplication with existing code that can be
eliminated should all filesystems be converted over.

Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
---

fs/Makefile | 3
fs/internal.h | 2
fs/libfs.c | 17 +
fs/namespace.c | 389 ++++++++++++++++++++++++++--------
fs/sb_config.c | 512 +++++++++++++++++++++++++++++++++++++++++++++
fs/super.c | 57 +++++
include/linux/fs.h | 14 +
include/linux/mount.h | 4
include/linux/sb_config.h | 13 +
9 files changed, 907 insertions(+), 104 deletions(-)
create mode 100644 fs/sb_config.c

diff --git a/fs/Makefile b/fs/Makefile
index 7bbaca9c67b1..8f5142525866 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -11,7 +11,8 @@ obj-y := open.o read_write.o file_table.o super.o \
attr.o bad_inode.o file.o filesystems.o namespace.o \
seq_file.o xattr.o libfs.o fs-writeback.o \
pnode.o splice.o sync.o utimes.o \
- stack.o fs_struct.o statfs.o fs_pin.o nsfs.o
+ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
+ sb_config.o

ifeq ($(CONFIG_BLOCK),y)
obj-y += buffer.o block_dev.o direct-io.o mpage.o
diff --git a/fs/internal.h b/fs/internal.h
index 9676fe11c093..39121a99d930 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -87,7 +87,7 @@ extern struct file *get_empty_filp(void);
/*
* super.c
*/
-extern int do_remount_sb(struct super_block *, int, void *, int);
+extern int do_remount_sb(struct super_block *, int, void *, int, struct sb_config *);
extern bool trylock_super(struct super_block *sb);
extern struct dentry *mount_fs(struct file_system_type *,
int, const char *, void *);
diff --git a/fs/libfs.c b/fs/libfs.c
index a04395334bb1..e8787adf0363 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -9,6 +9,7 @@
#include <linux/slab.h>
#include <linux/cred.h>
#include <linux/mount.h>
+#include <linux/sb_config.h>
#include <linux/vfs.h>
#include <linux/quotaops.h>
#include <linux/mutex.h>
@@ -574,13 +575,27 @@ static DEFINE_SPINLOCK(pin_fs_lock);

int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
{
+ struct sb_config *sc;
struct vfsmount *mnt = NULL;
+ int ret;
+
spin_lock(&pin_fs_lock);
if (unlikely(!*mount)) {
spin_unlock(&pin_fs_lock);
- mnt = vfs_kern_mount(type, MS_KERNMOUNT, type->name, NULL);
+
+ sc = __vfs_new_sb_config(type, NULL, MS_KERNMOUNT, SB_CONFIG_FOR_NEW);
+ if (IS_ERR(sc))
+ return PTR_ERR(sc);
+
+ ret = vfs_get_tree(sc);
+ if (ret < 0)
+ return ret;
+
+ mnt = vfs_kern_mount_sc(sc);
+ put_sb_config(sc);
if (IS_ERR(mnt))
return PTR_ERR(mnt);
+
spin_lock(&pin_fs_lock);
if (!*mount)
*mount = mnt;
diff --git a/fs/namespace.c b/fs/namespace.c
index c076787871e7..e92bc48accb5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -25,7 +25,9 @@
#include <linux/magic.h>
#include <linux/bootmem.h>
#include <linux/task_work.h>
+#include <linux/file.h>
#include <linux/sched/task.h>
+#include <linux/sb_config.h>

#include "pnode.h"
#include "internal.h"
@@ -957,55 +959,6 @@ static struct mount *skip_mnt_tree(struct mount *p)
return p;
}

-struct vfsmount *
-vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
-{
- struct mount *mnt;
- struct dentry *root;
-
- if (!type)
- return ERR_PTR(-ENODEV);
-
- mnt = alloc_vfsmnt(name);
- if (!mnt)
- return ERR_PTR(-ENOMEM);
-
- if (flags & MS_KERNMOUNT)
- mnt->mnt.mnt_flags = MNT_INTERNAL;
-
- root = mount_fs(type, flags, name, data);
- if (IS_ERR(root)) {
- mnt_free_id(mnt);
- free_vfsmnt(mnt);
- return ERR_CAST(root);
- }
-
- mnt->mnt.mnt_root = root;
- mnt->mnt.mnt_sb = root->d_sb;
- mnt->mnt_mountpoint = mnt->mnt.mnt_root;
- mnt->mnt_parent = mnt;
- lock_mount_hash();
- list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts);
- unlock_mount_hash();
- return &mnt->mnt;
-}
-EXPORT_SYMBOL_GPL(vfs_kern_mount);
-
-struct vfsmount *
-vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
- const char *name, void *data)
-{
- /* Until it is worked out how to pass the user namespace
- * through from the parent mount to the submount don't support
- * unprivileged mounts with submounts.
- */
- if (mountpoint->d_sb->s_user_ns != &init_user_ns)
- return ERR_PTR(-EPERM);
-
- return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
-}
-EXPORT_SYMBOL_GPL(vfs_submount);
-
static struct mount *clone_mnt(struct mount *old, struct dentry *root,
int flag)
{
@@ -1593,7 +1546,7 @@ static int do_umount(struct mount *mnt, int flags)
return -EPERM;
down_write(&sb->s_umount);
if (!(sb->s_flags & MS_RDONLY))
- retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
+ retval = do_remount_sb(sb, MS_RDONLY, NULL, 0, NULL);
up_write(&sb->s_umount);
return retval;
}
@@ -2276,6 +2229,20 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
}

/*
+ * Parse the monolithic page of mount data given to sys_mount().
+ */
+static int parse_monolithic_mount_data(struct sb_config *sc, void *data)
+{
+ int (*monolithic_mount_data)(struct sb_config *, void *);
+
+ monolithic_mount_data = sc->ops->monolithic_mount_data;
+ if (!monolithic_mount_data)
+ monolithic_mount_data = generic_monolithic_mount_data;
+
+ return monolithic_mount_data(sc, data);
+}
+
+/*
* change filesystem flags. dir should be a physical root of filesystem.
* If you've mounted a non-root directory somewhere and want to do remount
* on it - tough luck.
@@ -2283,9 +2250,11 @@ static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
static int do_remount(struct path *path, int flags, int mnt_flags,
void *data)
{
+ struct sb_config *sc = NULL;
int err;
struct super_block *sb = path->mnt->mnt_sb;
struct mount *mnt = real_mount(path->mnt);
+ struct file_system_type *type = sb->s_type;

if (!check_mnt(mnt))
return -EINVAL;
@@ -2320,9 +2289,19 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
return -EPERM;
}

- err = security_sb_remount(sb, data);
- if (err)
- return err;
+ if (type->init_sb_config) {
+ sc = vfs_sb_reconfig(path->mnt, flags);
+ if (IS_ERR(sc))
+ return PTR_ERR(sc);
+
+ err = parse_monolithic_mount_data(sc, data);
+ if (err < 0)
+ goto err_sc;
+ } else {
+ err = security_sb_remount(sb, data);
+ if (err)
+ return err;
+ }

down_write(&sb->s_umount);
if (flags & MS_BIND)
@@ -2330,7 +2309,7 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
else if (!capable(CAP_SYS_ADMIN))
err = -EPERM;
else
- err = do_remount_sb(sb, flags, data, 0);
+ err = do_remount_sb(sb, flags, data, 0, sc);
if (!err) {
lock_mount_hash();
mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
@@ -2339,6 +2318,9 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
unlock_mount_hash();
}
up_write(&sb->s_umount);
+err_sc:
+ if (sc)
+ put_sb_config(sc);
return err;
}

@@ -2422,29 +2404,6 @@ static int do_move_mount(struct path *path, const char *old_name)
return err;
}

-static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
-{
- int err;
- const char *subtype = strchr(fstype, '.');
- if (subtype) {
- subtype++;
- err = -EINVAL;
- if (!subtype[0])
- goto err;
- } else
- subtype = "";
-
- mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
- err = -ENOMEM;
- if (!mnt->mnt_sb->s_subtype)
- goto err;
- return mnt;
-
- err:
- mntput(mnt);
- return ERR_PTR(err);
-}
-
/*
* add a mount into a namespace's mount tree
*/
@@ -2492,40 +2451,80 @@ static int do_add_mount(struct mount *newmnt, struct path *path, int mnt_flags)
static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags);

/*
+ * Create a new mount using a superblock configuration and request it
+ * be added to the namespace tree.
+ */
+static int do_new_mount_sc(struct sb_config *sc, struct path *mountpoint,
+ unsigned int mnt_flags)
+{
+ struct vfsmount *mnt;
+ int ret;
+
+ mnt = vfs_kern_mount_sc(sc);
+ if (IS_ERR(mnt))
+ return PTR_ERR(mnt);
+
+ ret = -EPERM;
+ if (mount_too_revealing(mnt, &mnt_flags)) {
+ errorf("VFS: Mount too revealing");
+ goto err_mnt;
+ }
+
+ ret = do_add_mount(real_mount(mnt), mountpoint, mnt_flags);
+ if (ret < 0) {
+ errorf("VFS: Failed to add mount");
+ goto err_mnt;
+ }
+ return ret;
+
+err_mnt:
+ mntput(mnt);
+ return ret;
+}
+
+/*
* create a new mount for userspace and request it to be added into the
* namespace's tree
*/
-static int do_new_mount(struct path *path, const char *fstype, int flags,
+static int do_new_mount(struct path *mountpoint, const char *fstype, int flags,
int mnt_flags, const char *name, void *data)
{
- struct file_system_type *type;
- struct vfsmount *mnt;
+ struct sb_config *sc;
int err;

if (!fstype)
return -EINVAL;

- type = get_fs_type(fstype);
- if (!type)
- return -ENODEV;
+ sc = vfs_new_sb_config(fstype);
+ if (IS_ERR(sc)) {
+ err = PTR_ERR(sc);
+ goto err;
+ }
+ sc->ms_flags = flags;

- mnt = vfs_kern_mount(type, flags, name, data);
- if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
- !mnt->mnt_sb->s_subtype)
- mnt = fs_set_subtype(mnt, fstype);
+ err = -ENOMEM;
+ sc->device = kstrdup(name, GFP_KERNEL);
+ if (!sc->device)
+ goto err_sc;

- put_filesystem(type);
- if (IS_ERR(mnt))
- return PTR_ERR(mnt);
+ err = parse_monolithic_mount_data(sc, data);
+ if (err < 0)
+ goto err_sc;

- if (mount_too_revealing(mnt, &mnt_flags)) {
- mntput(mnt);
- return -EPERM;
- }
+ err = vfs_get_tree(sc);
+ if (err < 0)
+ goto err_sc;

- err = do_add_mount(real_mount(mnt), path, mnt_flags);
+ err = do_new_mount_sc(sc, mountpoint, mnt_flags);
if (err)
- mntput(mnt);
+ goto err_sc;
+
+ put_sb_config(sc);
+ return 0;
+
+err_sc:
+ put_sb_config(sc);
+err:
return err;
}

@@ -3058,6 +3057,187 @@ SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
return ret;
}

+/**
+ * vfs_get_tree - Get the mountable root
+ * @sc: The superblock configuration context.
+ *
+ * The filesystem is invoked to get or create a superblock which can then later
+ * be used for mounting. The filesystem places a pointer to the root to be
+ * used for mounting in @sc->root.
+ */
+int vfs_get_tree(struct sb_config *sc)
+{
+ struct super_block *sb;
+ int ret;
+
+ if (sc->root)
+ return -EBUSY;
+
+ if (sc->ops->validate) {
+ ret = sc->ops->validate(sc);
+ if (ret < 0)
+ return ret;
+ }
+
+ /* The filesystem may transfer preallocated resources from the
+ * configuration context to the superblock, thereby rendering the
+ * config unusable for another attempt at creation if this one fails.
+ */
+ if (sc->degraded)
+ return invalf("VFS: The config is degraded");
+
+ /* Get the mountable root in sc->root, with a ref on the root and a ref
+ * on the superblock.
+ */
+ ret = sc->ops->get_tree(sc);
+ if (ret < 0)
+ return ret;
+
+ BUG_ON(!sc->root);
+ sb = sc->root->d_sb;
+ WARN_ON(!sb->s_bdi);
+
+ ret = security_sb_get_tree(sc);
+ if (ret < 0)
+ goto err_sb;
+
+ ret = -ENOMEM;
+ if (sc->subtype && !sb->s_subtype) {
+ sb->s_subtype = kstrdup(sc->subtype, GFP_KERNEL);
+ if (!sb->s_subtype)
+ goto err_sb;
+ }
+
+ sb->s_flags |= MS_BORN;
+
+ /* Filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
+ * but s_maxbytes was an unsigned long long for many releases. Throw
+ * this warning for a little while to try and catch filesystems that
+ * violate this rule.
+ */
+ WARN(sb->s_maxbytes < 0,
+ "%s set sb->s_maxbytes to negative value (%lld)\n",
+ sc->fs_type->name, sb->s_maxbytes);
+
+ up_write(&sb->s_umount);
+ return 0;
+
+err_sb:
+ dput(sc->root);
+ sc->root = NULL;
+ deactivate_locked_super(sb);
+ return ret;
+}
+EXPORT_SYMBOL(vfs_get_tree);
+
+/**
+ * vfs_kern_mount_sc - Create a mount for a configured superblock
+ * sc: The configuration context with the superblock attached
+ *
+ * Create a mount to an already configured superblock. If necessary, the
+ * caller should invoke vfs_create_super() before calling this.
+ */
+struct vfsmount *vfs_kern_mount_sc(struct sb_config *sc)
+{
+ struct mount *mnt;
+
+ if (!sc->root)
+ return ERR_PTR(invalf("VFS: Root must be obtained before mount"));
+
+ mnt = alloc_vfsmnt(sc->device ?: "none");
+ if (!mnt)
+ return ERR_PTR(-ENOMEM);
+
+ if (sc->ms_flags & MS_KERNMOUNT)
+ mnt->mnt.mnt_flags = MNT_INTERNAL;
+
+ atomic_inc(&sc->root->d_sb->s_active);
+ mnt->mnt.mnt_sb = sc->root->d_sb;
+ mnt->mnt.mnt_root = dget(sc->root);
+ mnt->mnt_mountpoint = mnt->mnt.mnt_root;
+ mnt->mnt_parent = mnt;
+
+ lock_mount_hash();
+ list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts);
+ unlock_mount_hash();
+ return &mnt->mnt;
+}
+EXPORT_SYMBOL_GPL(vfs_kern_mount_sc);
+
+struct vfsmount *vfs_kern_mount(struct file_system_type *type,
+ int flags, const char *name, void *data)
+{
+ struct sb_config *sc;
+ struct vfsmount *mnt;
+ int ret;
+
+ if (!type)
+ return ERR_PTR(-EINVAL);
+
+ sc = __vfs_new_sb_config(type, NULL, flags, SB_CONFIG_FOR_NEW);
+ if (IS_ERR(sc))
+ return ERR_CAST(sc);
+
+ if (name) {
+ ret = -ENOMEM;
+ sc->device = kstrdup(name, GFP_KERNEL);
+ if (!sc->device)
+ goto err_sc;
+ }
+
+ ret = parse_monolithic_mount_data(sc, data);
+ if (ret < 0)
+ goto err_sc;
+
+ ret = vfs_get_tree(sc);
+ if (ret < 0)
+ goto err_sc;
+
+ mnt = vfs_kern_mount_sc(sc);
+ if (IS_ERR(mnt)) {
+ ret = PTR_ERR(mnt);
+ goto err_sc;
+ }
+
+ put_sb_config(sc);
+ return mnt;
+
+err_sc:
+ put_sb_config(sc);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(vfs_kern_mount);
+
+struct vfsmount *
+vfs_submount_sc(const struct dentry *mountpoint, struct sb_config *sc)
+{
+ /* Until it is worked out how to pass the user namespace
+ * through from the parent mount to the submount don't support
+ * unprivileged mounts with submounts.
+ */
+ if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+ return ERR_PTR(-EPERM);
+
+ sc->ms_flags = MS_SUBMOUNT;
+ return vfs_kern_mount_sc(sc);
+}
+EXPORT_SYMBOL_GPL(vfs_submount_sc);
+
+struct vfsmount *
+vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
+ const char *name, void *data)
+{
+ /* Until it is worked out how to pass the user namespace
+ * through from the parent mount to the submount don't support
+ * unprivileged mounts with submounts.
+ */
+ if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+ return ERR_PTR(-EPERM);
+
+ return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+}
+EXPORT_SYMBOL_GPL(vfs_submount);
+
/*
* Return true if path is reachable from root
*
@@ -3299,6 +3479,23 @@ struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
}
EXPORT_SYMBOL_GPL(kern_mount_data);

+struct vfsmount *kern_mount_data_sc(struct sb_config *sc)
+{
+ struct vfsmount *mnt;
+
+ sc->ms_flags = MS_KERNMOUNT;
+ mnt = vfs_kern_mount_sc(sc);
+ if (!IS_ERR(mnt)) {
+ /*
+ * it is a longterm mount, don't release mnt until
+ * we unmount before file sys is unregistered
+ */
+ real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
+ }
+ return mnt;
+}
+EXPORT_SYMBOL_GPL(kern_mount_data_sc);
+
void kern_unmount(struct vfsmount *mnt)
{
/* release long term mount so mount point can be released */
diff --git a/fs/sb_config.c b/fs/sb_config.c
new file mode 100644
index 000000000000..4d9bfb982d41
--- /dev/null
+++ b/fs/sb_config.c
@@ -0,0 +1,512 @@
+/* Provide a way to create a superblock configuration context within the kernel
+ * that allows a superblock to be set up prior to mounting.
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@xxxxxxxxxx)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/sb_config.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/nsproxy.h>
+#include <linux/slab.h>
+#include <linux/magic.h>
+#include <linux/security.h>
+#include <linux/parser.h>
+#include <linux/mnt_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include <net/net_namespace.h>
+#include "mount.h"
+
+struct legacy_sb_config {
+ struct sb_config sc;
+ char *legacy_data; /* Data page for legacy filesystems */
+ char *secdata;
+ unsigned int data_usage;
+};
+
+static const struct sb_config_operations legacy_sb_config_ops;
+
+static const match_table_t common_set_mount_options = {
+ { MS_DIRSYNC, "dirsync" },
+ { MS_I_VERSION, "iversion" },
+ { MS_LAZYTIME, "lazytime" },
+ { MS_MANDLOCK, "mand" },
+ { MS_POSIXACL, "posixacl" },
+ { MS_RDONLY, "ro" },
+ { MS_REC, "rec" },
+ { MS_SYNCHRONOUS, "sync" },
+ { MS_VERBOSE, "verbose" },
+ { },
+};
+
+static const match_table_t common_clear_mount_options = {
+ { MS_LAZYTIME, "nolazytime" },
+ { MS_MANDLOCK, "nomand" },
+ { MS_RDONLY, "rw" },
+ { MS_SILENT, "silent" },
+ { MS_SYNCHRONOUS, "async" },
+ { },
+};
+
+static const match_table_t forbidden_mount_options = {
+ { MS_BIND, "bind" },
+ { MS_MOVE, "move" },
+ { MS_PRIVATE, "private" },
+ { MS_REMOUNT, "remount" },
+ { MS_SHARED, "shared" },
+ { MS_SLAVE, "slave" },
+ { MS_UNBINDABLE, "unbindable" },
+ { MS_NOATIME, "noatime" },
+ { MS_RELATIME, "relatime" },
+ { MS_RELATIME, "norelatime" },
+ { MS_STRICTATIME, "strictatime" },
+ { MS_STRICTATIME, "nostrictatime" },
+ { MS_NODIRATIME, "nodiratime" },
+ { MS_NODEV, "dev" },
+ { MS_NODEV, "nodev" },
+ { MS_NOEXEC, "exec" },
+ { MS_NOEXEC, "noexec" },
+ { MS_NOSUID, "suid" },
+ { MS_NOSUID, "nosuid" },
+ { },
+};
+
+/*
+ * Check for a common mount option.
+ */
+static int vfs_parse_ms_mount_option(struct sb_config *sc, char *data)
+{
+ substring_t args[MAX_OPT_ARGS];
+ unsigned int token;
+
+ token = match_token(data, common_set_mount_options, args);
+ if (token) {
+ sc->ms_flags |= token;
+ return 1;
+ }
+
+ token = match_token(data, common_clear_mount_options, args);
+ if (token) {
+ sc->ms_flags &= ~token;
+ return 1;
+ }
+
+ token = match_token(data, forbidden_mount_options, args);
+ if (token)
+ return invalf("VFS: Mount option, not superblock option");
+
+ return 0;
+}
+
+/**
+ * vfs_parse_mount_option - Add a single mount option to a superblock config
+ * @mc: The superblock configuration to modify
+ * @p: The option to apply.
+ *
+ * A single mount option in string form is applied to the superblock
+ * configuration being set up. Certain standard options (for example "ro") are
+ * translated into flag bits without going to the filesystem. The active
+ * security module is allowed to observe and poach options. Any other options
+ * are passed over to the filesystem to parse.
+ *
+ * This may be called multiple times for a context.
+ *
+ * Returns 0 on success and a negative error code on failure. In the event of
+ * failure, sc->error may have been set to a non-allocated string that gives
+ * more information.
+ */
+int vfs_parse_mount_option(struct sb_config *sc, char *p)
+{
+ int ret;
+
+ ret = vfs_parse_ms_mount_option(sc, p);
+ if (ret < 0)
+ return ret;
+ if (ret == 1)
+ return 0;
+
+ ret = security_sb_config_parse_option(sc, p);
+ if (ret < 0)
+ return ret;
+ if (ret == 1)
+ return 0;
+
+ if (sc->ops->parse_option)
+ return sc->ops->parse_option(sc, p);
+
+ return invalf("VFS: FS takes no options");
+}
+EXPORT_SYMBOL(vfs_parse_mount_option);
+
+/**
+ * generic_monolithic_mount_data - Parse key[=val][,key[=val]]* mount data
+ * @mc: The superblock configuration to fill in.
+ * @data: The data to parse
+ *
+ * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be
+ * called from the ->monolithic_mount_data() sb_config operation.
+ *
+ * Returns 0 on success or the error returned by the ->parse_option() sb_config
+ * operation on failure.
+ */
+int generic_monolithic_mount_data(struct sb_config *ctx, void *data)
+{
+ char *options = data, *p;
+ int ret;
+
+ if (!options)
+ return 0;
+
+ while ((p = strsep(&options, ",")) != NULL) {
+ if (*p) {
+ ret = vfs_parse_mount_option(ctx, p);
+ if (ret < 0)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(generic_monolithic_mount_data);
+
+/**
+ * __vfs_new_sb_config - Create a superblock config.
+ * @fs_type: The filesystem type.
+ * @src_sb: A superblock from which this one derives (or NULL)
+ * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
+ * @purpose: The purpose that this configuration shall be used for.
+ *
+ * Open a filesystem and create a mount context. The mount context is
+ * initialised with the supplied flags and, if a submount/automount from
+ * another superblock (@src_sb), may have parameters such as namespaces copied
+ * across from that superblock.
+ */
+struct sb_config *__vfs_new_sb_config(struct file_system_type *fs_type,
+ struct super_block *src_sb,
+ unsigned int ms_flags,
+ enum sb_config_purpose purpose)
+{
+ struct sb_config *sc;
+ size_t sc_size = fs_type->sb_config_size;
+ int ret;
+
+ BUG_ON(fs_type->init_sb_config && sc_size < sizeof(*sc));
+
+ if (!fs_type->init_sb_config)
+ sc_size = sizeof(struct legacy_sb_config);
+
+ sc = kzalloc(sc_size, GFP_KERNEL);
+ if (!sc)
+ return ERR_PTR(-ENOMEM);
+
+ sc->purpose = purpose;
+ sc->ms_flags = ms_flags;
+ sc->fs_type = get_filesystem(fs_type);
+ sc->net_ns = get_net(current->nsproxy->net_ns);
+ sc->user_ns = get_user_ns(current_user_ns());
+ sc->cred = get_current_cred();
+
+ /* TODO: Make all filesystems support this unconditionally */
+ if (sc->fs_type->init_sb_config) {
+ ret = sc->fs_type->init_sb_config(sc, src_sb);
+ if (ret < 0)
+ goto err_sc;
+ } else {
+ sc->ops = &legacy_sb_config_ops;
+ }
+
+ /* Do the security check last because ->init_sb_config may change the
+ * namespace subscriptions.
+ */
+ ret = security_sb_config_alloc(sc, src_sb);
+ if (ret < 0)
+ goto err_sc;
+
+ return sc;
+
+err_sc:
+ put_sb_config(sc);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(__vfs_new_sb_config);
+
+/**
+ * vfs_new_sb_config - Create a superblock config for a new mount.
+ * @fs_name: The name of the filesystem
+ *
+ * Open a filesystem and create a superblock config context for a new mount
+ * that will hold the mount options, device name, security details, etc.. Note
+ * that the caller should check the ->ops pointer in the returned context to
+ * determine whether the filesystem actually supports the superblock context
+ * itself.
+ */
+struct sb_config *vfs_new_sb_config(const char *fs_name)
+{
+ struct file_system_type *fs_type;
+ struct sb_config *sc;
+
+ fs_type = get_fs_type(fs_name);
+ if (!fs_type)
+ return ERR_PTR(-ENODEV);
+
+ sc = __vfs_new_sb_config(fs_type, NULL, 0, SB_CONFIG_FOR_NEW);
+ put_filesystem(fs_type);
+ return sc;
+}
+EXPORT_SYMBOL(vfs_new_sb_config);
+
+/**
+ * vfs_sb_reconfig - Create a superblock config for remount/reconfiguration
+ * @mnt: The mountpoint to open
+ * @ms_flags: Superblock flags and op flags (such as MS_REMOUNT)
+ *
+ * Open a mounted filesystem and create a mount context such that a remount can
+ * be effected.
+ */
+struct sb_config *vfs_sb_reconfig(struct vfsmount *mnt,
+ unsigned int ms_flags)
+{
+ return __vfs_new_sb_config(mnt->mnt_sb->s_type, mnt->mnt_sb,
+ ms_flags, SB_CONFIG_FOR_REMOUNT);
+}
+
+/**
+ * vfs_dup_sc_config: Duplicate a superblock configuration context.
+ * @src_sc: The context to copy.
+ */
+struct sb_config *vfs_dup_sb_config(struct sb_config *src_sc)
+{
+ struct sb_config *sc;
+ size_t sc_size;
+ int ret;
+
+ if (!src_sc->ops->dup)
+ return ERR_PTR(-ENOTSUPP);
+
+ sc_size = src_sc->fs_type->sb_config_size;
+ if (!src_sc->fs_type->init_sb_config)
+ sc_size = sizeof(struct legacy_sb_config);
+
+ sc = kmemdup(src_sc, src_sc->fs_type->sb_config_size, GFP_KERNEL);
+ if (!sc)
+ return ERR_PTR(-ENOMEM);
+
+ sc->device = NULL;
+ sc->security = NULL;
+ get_filesystem(sc->fs_type);
+ get_net(sc->net_ns);
+ get_user_ns(sc->user_ns);
+ get_cred(sc->cred);
+
+ /* Can't call put until we've called ->dup */
+ ret = sc->ops->dup(sc, src_sc);
+ if (ret < 0)
+ goto err_sc;
+
+ ret = security_sb_config_dup(sc, src_sc);
+ if (ret < 0)
+ goto err_sc;
+ return sc;
+
+err_sc:
+ put_sb_config(sc);
+ return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(vfs_dup_sb_config);
+
+/**
+ * put_sb_config - Dispose of a superblock configuration context.
+ * @sc: The context to dispose of.
+ */
+void put_sb_config(struct sb_config *sc)
+{
+ struct super_block *sb;
+
+ if (sc->root) {
+ sb = sc->root->d_sb;
+ dput(sc->root);
+ sc->root = NULL;
+ deactivate_super(sb);
+ }
+
+ if (sc->ops && sc->ops->free)
+ sc->ops->free(sc);
+
+ security_sb_config_free(sc);
+ if (sc->net_ns)
+ put_net(sc->net_ns);
+ put_user_ns(sc->user_ns);
+ if (sc->cred)
+ put_cred(sc->cred);
+ kfree(sc->subtype);
+ put_filesystem(sc->fs_type);
+ kfree(sc->device);
+ kfree(sc);
+}
+EXPORT_SYMBOL(put_sb_config);
+
+/*
+ * Free the config for a filesystem that doesn't support sb_config.
+ */
+static void legacy_sb_config_free(struct sb_config *sc)
+{
+ struct legacy_sb_config *cfg = container_of(sc, struct legacy_sb_config, sc);
+
+ free_secdata(cfg->secdata);
+ kfree(cfg->legacy_data);
+}
+
+/*
+ * Duplicate a legacy config.
+ */
+static int legacy_sb_config_dup(struct sb_config *sc, struct sb_config *src_sc)
+{
+ struct legacy_sb_config *cfg = container_of(sc, struct legacy_sb_config, sc);
+ struct legacy_sb_config *src_cfg = container_of(src_sc, struct legacy_sb_config, sc);
+
+ cfg->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!cfg->legacy_data)
+ return -ENOMEM;
+ memcpy(cfg->legacy_data, src_cfg->legacy_data, sizeof(PAGE_SIZE));
+ return 0;
+}
+
+/*
+ * Add an option to a legacy config. We build up a comma-separated list of
+ * options.
+ */
+static int legacy_parse_option(struct sb_config *sc, char *p)
+{
+ struct legacy_sb_config *cfg = container_of(sc, struct legacy_sb_config, sc);
+ unsigned int usage = cfg->data_usage;
+ size_t len = strlen(p);
+
+ if (len > PAGE_SIZE - 2 - usage)
+ return invalf("VFS: Insufficient data buffer space");
+ if (memchr(p, ',', len) != NULL)
+ return invalf("VFS: Options cannot contain commas");
+ if (!cfg->legacy_data) {
+ cfg->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!cfg->legacy_data)
+ return -ENOMEM;
+ }
+
+ cfg->legacy_data[usage++] = ',';
+ memcpy(cfg->legacy_data + usage, p, len);
+ usage += len;
+ cfg->legacy_data[usage] = '\0';
+ cfg->data_usage = usage;
+ return 0;
+}
+
+/*
+ * Add monolithic mount data.
+ */
+static int legacy_monolithic_mount_data(struct sb_config *sc, void *data)
+{
+ struct legacy_sb_config *cfg = container_of(sc, struct legacy_sb_config, sc);
+
+ if (cfg->data_usage != 0)
+ return invalf("VFS: Can't mix monolithic and individual options");
+ if (!data)
+ return 0;
+ if (!cfg->legacy_data) {
+ cfg->legacy_data = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!cfg->legacy_data)
+ return -ENOMEM;
+ }
+
+ memcpy(cfg->legacy_data, data, PAGE_SIZE);
+ cfg->data_usage = PAGE_SIZE;
+ return 0;
+}
+
+/*
+ * Use the legacy mount validation step to strip out and process security
+ * config options.
+ */
+static int legacy_validate(struct sb_config *sc)
+{
+ struct legacy_sb_config *cfg = container_of(sc, struct legacy_sb_config, sc);
+
+ if (!cfg->legacy_data || cfg->sc.fs_type->fs_flags & FS_BINARY_MOUNTDATA)
+ return 0;
+
+ cfg->secdata = alloc_secdata();
+ if (!cfg->secdata)
+ return -ENOMEM;
+
+ return security_sb_copy_data(cfg->legacy_data, cfg->secdata);
+}
+
+/*
+ * Determine the superblock subtype.
+ */
+static int legacy_set_subtype(struct sb_config *sc)
+{
+ const char *subtype = strchr(sc->fs_type->name, '.');
+
+ if (subtype) {
+ subtype++;
+ if (!subtype[0])
+ return -EINVAL;
+ } else {
+ subtype = "";
+ }
+
+ sc->subtype = kstrdup(subtype, GFP_KERNEL);
+ if (!sc->subtype)
+ return -ENOMEM;
+ return 0;
+}
+
+/*
+ * Get a mountable root with the legacy mount command.
+ */
+static int legacy_get_tree(struct sb_config *sc)
+{
+ struct legacy_sb_config *cfg = container_of(sc, struct legacy_sb_config, sc);
+ struct super_block *sb;
+ struct dentry *root;
+ int ret;
+
+ root = cfg->sc.fs_type->mount(cfg->sc.fs_type, cfg->sc.ms_flags,
+ cfg->sc.device, cfg->legacy_data);
+ if (IS_ERR(root))
+ return PTR_ERR(root);
+
+ sb = root->d_sb;
+ BUG_ON(!sb);
+
+ if ((cfg->sc.fs_type->fs_flags & FS_HAS_SUBTYPE) &&
+ !sc->subtype) {
+ ret = legacy_set_subtype(sc);
+ if (ret < 0)
+ goto err_sb;
+ }
+
+ cfg->sc.root = root;
+ return 0;
+
+err_sb:
+ dput(root);
+ deactivate_locked_super(sb);
+ return ret;
+}
+
+static const struct sb_config_operations legacy_sb_config_ops = {
+ .free = legacy_sb_config_free,
+ .dup = legacy_sb_config_dup,
+ .parse_option = legacy_parse_option,
+ .monolithic_mount_data = legacy_monolithic_mount_data,
+ .validate = legacy_validate,
+ .get_tree = legacy_get_tree,
+};
diff --git a/fs/super.c b/fs/super.c
index adb0c0de428c..e4b47d481679 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -34,6 +34,7 @@
#include <linux/fsnotify.h>
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
+#include <linux/sb_config.h>
#include "internal.h"


@@ -805,10 +806,13 @@ struct super_block *user_get_super(dev_t dev)
* @flags: numeric part of options
* @data: the rest of options
* @force: whether or not to force the change
+ * @sc: the superblock config for filesystems that support it
+ * (NULL if called from emergency or umount)
*
* Alters the mount options of a mounted file system.
*/
-int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
+int do_remount_sb(struct super_block *sb, int flags, void *data, int force,
+ struct sb_config *sc)
{
int retval;
int remount_ro;
@@ -850,8 +854,14 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
}
}

- if (sb->s_op->remount_fs) {
- retval = sb->s_op->remount_fs(sb, &flags, data);
+ if (sb->s_op->remount_fs_sc ||
+ sb->s_op->remount_fs) {
+ if (sb->s_op->remount_fs_sc) {
+ retval = sb->s_op->remount_fs_sc(sb, sc);
+ flags = sc->ms_flags;
+ } else {
+ retval = sb->s_op->remount_fs(sb, &flags, data);
+ }
if (retval) {
if (!force)
goto cancel_readonly;
@@ -898,7 +908,7 @@ static void do_emergency_remount(struct work_struct *work)
/*
* What lock protects sb->s_flags??
*/
- do_remount_sb(sb, MS_RDONLY, NULL, 1);
+ do_remount_sb(sb, MS_RDONLY, NULL, 1, NULL);
}
up_write(&sb->s_umount);
spin_lock(&sb_lock);
@@ -1048,6 +1058,43 @@ struct dentry *mount_ns(struct file_system_type *fs_type,

EXPORT_SYMBOL(mount_ns);

+int mount_ns_sc(struct sb_config *sc,
+ int (*fill_super)(struct super_block *sb, struct sb_config *sc),
+ void *ns)
+{
+ struct super_block *sb;
+
+ /* Don't allow mounting unless the caller has CAP_SYS_ADMIN
+ * over the namespace.
+ */
+ if (!(sc->ms_flags & MS_KERNMOUNT) &&
+ !ns_capable(sc->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ sb = sget_userns(sc->fs_type, ns_test_super, ns_set_super,
+ sc->ms_flags, sc->user_ns, ns);
+ if (IS_ERR(sb))
+ return PTR_ERR(sb);
+
+ if (!sb->s_root) {
+ int err;
+ err = fill_super(sb, sc);
+ if (err) {
+ deactivate_locked_super(sb);
+ return err;
+ }
+
+ sb->s_flags |= MS_ACTIVE;
+ }
+
+ if (!sc->root) {
+ sc->root = sb->s_root;
+ dget(sb->s_root);
+ }
+ return 0;
+}
+EXPORT_SYMBOL(mount_ns_sc);
+
#ifdef CONFIG_BLOCK
static int set_bdev_super(struct super_block *s, void *data)
{
@@ -1196,7 +1243,7 @@ struct dentry *mount_single(struct file_system_type *fs_type,
}
s->s_flags |= MS_ACTIVE;
} else {
- do_remount_sb(s, flags, data, 0);
+ do_remount_sb(s, flags, data, 0, NULL);
}
return dget(s->s_root);
}
diff --git a/include/linux/fs.h b/include/linux/fs.h
index bc0c054894b9..1acb76f400c4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -54,6 +54,7 @@ struct workqueue_struct;
struct iov_iter;
struct fscrypt_info;
struct fscrypt_operations;
+struct sb_config;

extern void __init inode_init(void);
extern void __init inode_init_early(void);
@@ -701,6 +702,11 @@ static inline void inode_unlock(struct inode *inode)
up_write(&inode->i_rwsem);
}

+static inline int inode_lock_killable(struct inode *inode)
+{
+ return down_write_killable(&inode->i_rwsem);
+}
+
static inline void inode_lock_shared(struct inode *inode)
{
down_read(&inode->i_rwsem);
@@ -1787,6 +1793,7 @@ struct super_operations {
int (*unfreeze_fs) (struct super_block *);
int (*statfs) (struct dentry *, struct kstatfs *);
int (*remount_fs) (struct super_block *, int *, char *);
+ int (*remount_fs_sc) (struct super_block *, struct sb_config *);
void (*umount_begin) (struct super_block *);

int (*show_options)(struct seq_file *, struct dentry *);
@@ -2021,8 +2028,10 @@ struct file_system_type {
#define FS_HAS_SUBTYPE 4
#define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */
#define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */
+ unsigned short sb_config_size; /* Size of superblock config context to allocate */
struct dentry *(*mount) (struct file_system_type *, int,
const char *, void *);
+ int (*init_sb_config)(struct sb_config *, struct super_block *);
void (*kill_sb) (struct super_block *);
struct module *owner;
struct file_system_type * next;
@@ -2040,6 +2049,10 @@ struct file_system_type {

#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)

+extern int mount_ns_sc(struct sb_config *mc,
+ int (*fill_super)(struct super_block *sb,
+ struct sb_config *sc),
+ void *ns);
extern struct dentry *mount_ns(struct file_system_type *fs_type,
int flags, void *data, void *ns, struct user_namespace *user_ns,
int (*fill_super)(struct super_block *, void *, int));
@@ -2106,6 +2119,7 @@ extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
#define kern_mount(type) kern_mount_data(type, NULL)
+extern struct vfsmount *kern_mount_data_sc(struct sb_config *);
extern void kern_unmount(struct vfsmount *mnt);
extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 8e0352af06b7..a5dca6abc4d5 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -20,6 +20,7 @@ struct super_block;
struct vfsmount;
struct dentry;
struct mnt_namespace;
+struct sb_config;

#define MNT_NOSUID 0x01
#define MNT_NODEV 0x02
@@ -90,9 +91,12 @@ struct file_system_type;
extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
int flags, const char *name,
void *data);
+extern struct vfsmount *vfs_kern_mount_sc(struct sb_config *sc);
extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
struct file_system_type *type,
const char *name, void *data);
+extern struct vfsmount *vfs_submount_sc(const struct dentry *mountpoint,
+ struct sb_config *sc);

extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
extern void mark_mounts_for_expiry(struct list_head *mounts);
diff --git a/include/linux/sb_config.h b/include/linux/sb_config.h
index d2af7342a082..0da92dd99d60 100644
--- a/include/linux/sb_config.h
+++ b/include/linux/sb_config.h
@@ -69,4 +69,17 @@ struct sb_config_operations {
int (*get_tree)(struct sb_config *sc);
};

+extern struct sb_config *vfs_new_sb_config(const char *fs_name);
+extern struct sb_config *__vfs_new_sb_config(struct file_system_type *fs_type,
+ struct super_block *src_sb,
+ unsigned int ms_flags,
+ enum sb_config_purpose purpose);
+extern struct sb_config *vfs_sb_reconfig(struct vfsmount *mnt,
+ unsigned int ms_flags);
+extern struct sb_config *vfs_dup_sb_config(struct sb_config *src);
+extern int vfs_parse_mount_option(struct sb_config *sc, char *data);
+extern int generic_monolithic_mount_data(struct sb_config *sc, void *data);
+extern int vfs_get_tree(struct sb_config *sc);
+extern void put_sb_config(struct sb_config *sc);
+
#endif /* _LINUX_SB_CONFIG_H */