vfs: Introduce fs_context, switch vfs_kern_mount() to it.

Introduce a filesystem context concept to be used during superblock
creation for mount and superblock reconfiguration for remount.  This is
allocated at the beginning of the mount procedure and into it is placed:

 (1) Filesystem type.

 (2) Namespaces.

 (3) Source/Device names (there may be multiple).

 (4) Superblock flags (SB_*).

 (5) Security details.

 (6) Filesystem-specific data, as set by the mount options.

Accessor functions are then provided to set up a context, parameterise it
from monolithic mount data (the data page passed to mount(2)) and tear it
down again.

A legacy wrapper is provided that implements what will be the basic
operations, wrapping access to filesystems that aren't yet aware of the
fs_context.

Finally, vfs_kern_mount() is changed to make use of the fs_context and
mount_fs() is replaced by vfs_get_tree(), called from vfs_kern_mount().
[AV -- add missing kstrdup()]
[AV -- put_cred() can be unconditional - fc->cred can't be NULL]
[AV -- take legacy_validate() contents into legacy_parse_monolithic()]
[AV -- merge KERNEL_MOUNT and USER_MOUNT]
[AV -- don't unlock superblock on success return from vfs_get_tree()]
[AV -- kill 'reference' argument of init_fs_context()]

Signed-off-by: David Howells <dhowells@redhat.com>
Co-developed-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 32 insertions, 14 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index f0b8a8ca08dfb..3f2fd7a34733d 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -27,6 +27,7 @@
 #include <linux/task_work.h>
 #include <linux/sched/task.h>
 #include <uapi/linux/mount.h>
+#include <linux/fs_context.h>
 
 #include "pnode.h"
 #include "internal.h"
@@ -940,36 +941,53 @@ 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 vfsmount *vfs_kern_mount(struct file_system_type *type,
+				int flags, const char *name,
+				void *data)
 {
+	struct fs_context *fc;
 	struct mount *mnt;
-	struct dentry *root;
+	int ret = 0;
 
 	if (!type)
 		return ERR_PTR(-ENODEV);
 
+	fc = fs_context_for_mount(type, flags);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	if (name) {
+		fc->source = kstrdup(name, GFP_KERNEL);
+		if (!fc->source)
+			ret = -ENOMEM;
+	}
+	if (!ret)
+		ret = parse_monolithic_mount_data(fc, data);
+	if (!ret)
+		ret = vfs_get_tree(fc);
+	if (ret) {
+		put_fs_context(fc);
+		return ERR_PTR(ret);
+	}
+	up_write(&fc->root->d_sb->s_umount);
 	mnt = alloc_vfsmnt(name);
-	if (!mnt)
+	if (!mnt) {
+		put_fs_context(fc);
 		return ERR_PTR(-ENOMEM);
+	}
 
 	if (flags & SB_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;
+	atomic_inc(&fc->root->d_sb->s_active);
+	mnt->mnt.mnt_root = dget(fc->root);
+	mnt->mnt.mnt_sb = fc->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);
+	list_add_tail(&mnt->mnt_instance, &fc->root->d_sb->s_mounts);
 	unlock_mount_hash();
+	put_fs_context(fc);
 	return &mnt->mnt;
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);