kernfs, sysfs, cgroup, intel_rdt: Support fs_context

Make kernfs support superblock creation/mount/remount with fs_context.

This requires that sysfs, cgroup and intel_rdt, which are built on kernfs,
be made to support fs_context also.

Notes:

 (1) A kernfs_fs_context struct is created to wrap fs_context and the
     kernfs mount parameters are moved in here (or are in fs_context).

 (2) kernfs_mount{,_ns}() are made into kernfs_get_tree().  The extra
     namespace tag parameter is passed in the context if desired

 (3) kernfs_free_fs_context() is provided as a destructor for the
     kernfs_fs_context struct, but for the moment it does nothing except
     get called in the right places.

 (4) sysfs doesn't wrap kernfs_fs_context since it has no parameters to
     pass, but possibly this should be done anyway in case someone wants to
     add a parameter in future.

 (5) A cgroup_fs_context struct is created to wrap kernfs_fs_context and
     the cgroup v1 and v2 mount parameters are all moved there.

 (6) cgroup1 parameter parsing error messages are now handled by invalf(),
     which allows userspace to collect them directly.

 (7) cgroup1 parameter cleanup is now done in the context destructor rather
     than in the mount/get_tree and remount functions.

Weirdies:

 (*) cgroup_do_get_tree() calls cset_cgroup_from_root() with locks held,
     but then uses the resulting pointer after dropping the locks.  I'm
     told this is okay and needs commenting.

 (*) The cgroup refcount web.  This really needs documenting.

 (*) cgroup2 only has one root?

Add a suggestion from Thomas Gleixner in which the RDT enablement code is
placed into its own function.

[folded a leak fix from Andrey Vagin]

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
cc: Tejun Heo <tj@kernel.org>
cc: Li Zefan <lizefan@huawei.com>
cc: Johannes Weiner <hannes@cmpxchg.org>
cc: cgroups@vger.kernel.org
cc: fenghua.yu@intel.com
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 92 insertions, 71 deletions

diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 3d83b114bb08..379e3a9eb1ec 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -17,6 +17,7 @@
 #include <linux/xattr.h>
 
 #include <linux/kernfs.h>
+#include <linux/fs_context.h>
 
 struct kernfs_iattrs {
 	struct iattr		ia_iattr;
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index 4d303047a4f8..36376cc5c9c2 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -22,16 +22,6 @@
 
 struct kmem_cache *kernfs_node_cache;
 
-static int kernfs_sop_remount_fs(struct super_block *sb, int *flags, char *data)
-{
-	struct kernfs_root *root = kernfs_info(sb)->root;
-	struct kernfs_syscall_ops *scops = root->syscall_ops;
-
-	if (scops && scops->remount_fs)
-		return scops->remount_fs(root, flags, data);
-	return 0;
-}
-
 static int kernfs_sop_show_options(struct seq_file *sf, struct dentry *dentry)
 {
 	struct kernfs_root *root = kernfs_root(kernfs_dentry_node(dentry));
@@ -60,7 +50,6 @@ const struct super_operations kernfs_sops = {
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= kernfs_evict_inode,
 
-	.remount_fs	= kernfs_sop_remount_fs,
 	.show_options	= kernfs_sop_show_options,
 	.show_path	= kernfs_sop_show_path,
 };
@@ -222,7 +211,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 	} while (true);
 }
 
-static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
+static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *kfc)
 {
 	struct kernfs_super_info *info = kernfs_info(sb);
 	struct inode *inode;
@@ -233,7 +222,7 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 	sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV;
 	sb->s_blocksize = PAGE_SIZE;
 	sb->s_blocksize_bits = PAGE_SHIFT;
-	sb->s_magic = magic;
+	sb->s_magic = kfc->magic;
 	sb->s_op = &kernfs_sops;
 	sb->s_xattr = kernfs_xattr_handlers;
 	if (info->root->flags & KERNFS_ROOT_SUPPORT_EXPORTOP)
@@ -263,21 +252,20 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 	return 0;
 }
 
-static int kernfs_test_super(struct super_block *sb, void *data)
+static int kernfs_test_super(struct super_block *sb, struct fs_context *fc)
 {
 	struct kernfs_super_info *sb_info = kernfs_info(sb);
-	struct kernfs_super_info *info = data;
+	struct kernfs_super_info *info = fc->s_fs_info;
 
 	return sb_info->root == info->root && sb_info->ns == info->ns;
 }
 
-static int kernfs_set_super(struct super_block *sb, void *data)
+static int kernfs_set_super(struct super_block *sb, struct fs_context *fc)
 {
-	int error;
-	error = set_anon_super(sb, data);
-	if (!error)
-		sb->s_fs_info = data;
-	return error;
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	kfc->ns_tag = NULL;
+	return set_anon_super_fc(sb, fc);
 }
 
 /**
@@ -294,63 +282,60 @@ const void *kernfs_super_ns(struct super_block *sb)
 }
 
 /**
- * kernfs_mount_ns - kernfs mount helper
- * @fs_type: file_system_type of the fs being mounted
- * @flags: mount flags specified for the mount
- * @root: kernfs_root of the hierarchy being mounted
- * @magic: file system specific magic number
- * @new_sb_created: tell the caller if we allocated a new superblock
- * @ns: optional namespace tag of the mount
+ * kernfs_get_tree - kernfs filesystem access/retrieval helper
+ * @fc: The filesystem context.
  *
- * This is to be called from each kernfs user's file_system_type->mount()
- * implementation, which should pass through the specified @fs_type and
- * @flags, and specify the hierarchy and namespace tag to mount via @root
- * and @ns, respectively.
- *
- * The return value can be passed to the vfs layer verbatim.
+ * This is to be called from each kernfs user's fs_context->ops->get_tree()
+ * implementation, which should set the specified ->@fs_type and ->@flags, and
+ * specify the hierarchy and namespace tag to mount via ->@root and ->@ns,
+ * respectively.
  */
-struct dentry *kernfs_mount_ns(struct file_system_type *fs_type, int flags,
-				struct kernfs_root *root, unsigned long magic,
-				bool *new_sb_created, const void *ns)
+int kernfs_get_tree(struct fs_context *fc)
 {
+	struct kernfs_fs_context *kfc = fc->fs_private;
 	struct super_block *sb;
 	struct kernfs_super_info *info;
 	int error;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
-	info->root = root;
-	info->ns = ns;
+	info->root = kfc->root;
+	info->ns = kfc->ns_tag;
 	INIT_LIST_HEAD(&info->node);
 
-	sb = sget_userns(fs_type, kernfs_test_super, kernfs_set_super, flags,
-			 &init_user_ns, info);
-	if (IS_ERR(sb) || sb->s_fs_info != info)
-		kfree(info);
+	fc->s_fs_info = info;
+	sb = sget_fc(fc, kernfs_test_super, kernfs_set_super);
 	if (IS_ERR(sb))
-		return ERR_CAST(sb);
-
-	if (new_sb_created)
-		*new_sb_created = !sb->s_root;
+		return PTR_ERR(sb);
 
 	if (!sb->s_root) {
 		struct kernfs_super_info *info = kernfs_info(sb);
 
-		error = kernfs_fill_super(sb, magic);
+		kfc->new_sb_created = true;
+
+		error = kernfs_fill_super(sb, kfc);
 		if (error) {
 			deactivate_locked_super(sb);
-			return ERR_PTR(error);
+			return error;
 		}
 		sb->s_flags |= SB_ACTIVE;
 
 		mutex_lock(&kernfs_mutex);
-		list_add(&info->node, &root->supers);
+		list_add(&info->node, &info->root->supers);
 		mutex_unlock(&kernfs_mutex);
 	}
 
-	return dget(sb->s_root);
+	fc->root = dget(sb->s_root);
+	return 0;
+}
+
+void kernfs_free_fs_context(struct fs_context *fc)
+{
+	/* Note that we don't deal with kfc->ns_tag here. */
+	kfree(fc->s_fs_info);
+	fc->s_fs_info = NULL;
 }
 
 /**
diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
index 92682fcc41f6..4cb21b558a85 100644
--- a/fs/sysfs/mount.c
+++ b/fs/sysfs/mount.c
@@ -13,34 +13,69 @@
 #include <linux/magic.h>
 #include <linux/mount.h>
 #include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/user_namespace.h>
+#include <linux/fs_context.h>
+#include <net/net_namespace.h>
 
 #include "sysfs.h"
 
 static struct kernfs_root *sysfs_root;
 struct kernfs_node *sysfs_root_kn;
 
-static struct dentry *sysfs_mount(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data)
+static int sysfs_get_tree(struct fs_context *fc)
 {
-	struct dentry *root;
-	void *ns;
-	bool new_sb = false;
+	struct kernfs_fs_context *kfc = fc->fs_private;
+	int ret;
 
-	if (!(flags & SB_KERNMOUNT)) {
+	ret = kernfs_get_tree(fc);
+	if (ret)
+		return ret;
+
+	if (kfc->new_sb_created)
+		fc->root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
+	return 0;
+}
+
+static void sysfs_fs_context_free(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	if (kfc->ns_tag)
+		kobj_ns_drop(KOBJ_NS_TYPE_NET, kfc->ns_tag);
+	kernfs_free_fs_context(fc);
+	kfree(kfc);
+}
+
+static const struct fs_context_operations sysfs_fs_context_ops = {
+	.free		= sysfs_fs_context_free,
+	.get_tree	= sysfs_get_tree,
+};
+
+static int sysfs_init_fs_context(struct fs_context *fc)
+{
+	struct kernfs_fs_context *kfc;
+	struct net *netns;
+
+	if (!(fc->sb_flags & SB_KERNMOUNT)) {
 		if (!kobj_ns_current_may_mount(KOBJ_NS_TYPE_NET))
-			return ERR_PTR(-EPERM);
+			return -EPERM;
 	}
 
-	ns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
-	root = kernfs_mount_ns(fs_type, flags, sysfs_root,
-				SYSFS_MAGIC, &new_sb, ns);
-	if (!new_sb)
-		kobj_ns_drop(KOBJ_NS_TYPE_NET, ns);
-	else if (!IS_ERR(root))
-		root->d_sb->s_iflags |= SB_I_USERNS_VISIBLE;
+	kfc = kzalloc(sizeof(struct kernfs_fs_context), GFP_KERNEL);
+	if (!kfc)
+		return -ENOMEM;
 
-	return root;
+	kfc->ns_tag = netns = kobj_ns_grab_current(KOBJ_NS_TYPE_NET);
+	kfc->root = sysfs_root;
+	kfc->magic = SYSFS_MAGIC;
+	fc->fs_private = kfc;
+	fc->ops = &sysfs_fs_context_ops;
+	if (fc->user_ns)
+		put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(netns->user_ns);
+	fc->global = true;
+	return 0;
 }
 
 static void sysfs_kill_sb(struct super_block *sb)
@@ -52,10 +87,10 @@ static void sysfs_kill_sb(struct super_block *sb)
 }
 
 static struct file_system_type sysfs_fs_type = {
-	.name		= "sysfs",
-	.mount		= sysfs_mount,
-	.kill_sb	= sysfs_kill_sb,
-	.fs_flags	= FS_USERNS_MOUNT,
+	.name			= "sysfs",
+	.init_fs_context	= sysfs_init_fs_context,
+	.kill_sb		= sysfs_kill_sb,
+	.fs_flags		= FS_USERNS_MOUNT,
 };
 
 int __init sysfs_init(void)