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>

2 files changed, 18 insertions, 18 deletions

diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 37cf709b7a0e..30e39f3932ad 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -41,6 +41,7 @@ extern void __init enable_debug_cgroup(void);
  * The cgroup filesystem superblock creation/mount context.
  */
 struct cgroup_fs_context {
+	struct kernfs_fs_context kfc;
 	struct cgroup_root	*root;
 	struct cgroup_namespace	*ns;
 	unsigned int	flags;			/* CGRP_ROOT_* flags */
@@ -56,7 +57,9 @@ struct cgroup_fs_context {
 
 static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc)
 {
-	return fc->fs_private;
+	struct kernfs_fs_context *kfc = fc->fs_private;
+
+	return container_of(kfc, struct cgroup_fs_context, kfc);
 }
 
 /*
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 0c6bef234a7c..747e5b17f9da 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2039,18 +2039,14 @@ out:
 int cgroup_do_get_tree(struct fs_context *fc)
 {
 	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
-	bool new_sb = false;
-	unsigned long magic;
-	int ret = 0;
+	int ret;
 
+	ctx->kfc.root = ctx->root->kf_root;
 	if (fc->fs_type == &cgroup2_fs_type)
-		magic = CGROUP2_SUPER_MAGIC;
+		ctx->kfc.magic = CGROUP2_SUPER_MAGIC;
 	else
-		magic = CGROUP_SUPER_MAGIC;
-	fc->root = kernfs_mount(fc->fs_type, fc->sb_flags, ctx->root->kf_root,
-				magic, &new_sb);
-	if (IS_ERR(fc->root))
-		ret = PTR_ERR(fc->root);
+		ctx->kfc.magic = CGROUP_SUPER_MAGIC;
+	ret = kernfs_get_tree(fc);
 
 	/*
 	 * In non-init cgroup namespace, instead of root cgroup's dentry,
@@ -2078,7 +2074,7 @@ int cgroup_do_get_tree(struct fs_context *fc)
 		}
 	}
 
-	if (!new_sb)
+	if (!ctx->kfc.new_sb_created)
 		cgroup_put(&ctx->root->cgrp);
 
 	return ret;
@@ -2094,19 +2090,15 @@ static void cgroup_fs_context_free(struct fs_context *fc)
 	kfree(ctx->name);
 	kfree(ctx->release_agent);
 	put_cgroup_ns(ctx->ns);
+	kernfs_free_fs_context(fc);
 	kfree(ctx);
 }
 
 static int cgroup_get_tree(struct fs_context *fc)
 {
-	struct cgroup_namespace *ns = current->nsproxy->cgroup_ns;
 	struct cgroup_fs_context *ctx = cgroup_fc2context(fc);
 	int ret;
 
-	/* Check if the caller has permission to mount. */
-	if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
-		return -EPERM;
-
 	cgrp_dfl_visible = true;
 	cgroup_get_live(&cgrp_dfl_root.cgrp);
 	ctx->root = &cgrp_dfl_root;
@@ -2132,7 +2124,8 @@ static const struct fs_context_operations cgroup1_fs_context_ops = {
 };
 
 /*
- * Initialise the cgroup filesystem creation/reconfiguration context.
+ * Initialise the cgroup filesystem creation/reconfiguration context.  Notably,
+ * we select the namespace we're going to use.
  */
 static int cgroup_init_fs_context(struct fs_context *fc)
 {
@@ -2151,11 +2144,15 @@ static int cgroup_init_fs_context(struct fs_context *fc)
 
 	ctx->ns = current->nsproxy->cgroup_ns;
 	get_cgroup_ns(ctx->ns);
-	fc->fs_private = ctx;
+	fc->fs_private = &ctx->kfc;
 	if (fc->fs_type == &cgroup2_fs_type)
 		fc->ops = &cgroup_fs_context_ops;
 	else
 		fc->ops = &cgroup1_fs_context_ops;
+	if (fc->user_ns)
+		put_user_ns(fc->user_ns);
+	fc->user_ns = get_user_ns(ctx->ns->user_ns);
+	fc->global = true;
 	return 0;
 }