cgroup: introduce sane_behavior mount option

It's a sad fact that at this point various cgroup controllers are
carrying so many idiosyncrasies and pure insanities that it simply
isn't possible to reach any sort of sane consistent behavior while
maintaining staying fully compatible with what already has been
exposed to userland.

As we can't break exposed userland interface, transitioning to sane
behaviors can only be done in steps while maintaining backwards
compatibility.  This patch introduces a new mount option -
__DEVEL__sane_behavior - which disables crazy features and enforces
consistent behaviors in cgroup core proper and various controllers.
As exactly which behaviors it changes are still being determined, the
mount option, at this point, is useful only for development of the new
behaviors.  As such, the mount option is prefixed with __DEVEL__ and
generates a warning message when used.

Eventually, once we get to the point where all controller's behaviors
are consistent enough to implement unified hierarchy, the __DEVEL__
prefix will be dropped, and more importantly, unified-hierarchy will
enforce sane_behavior by default.  Maybe we'll able to completely drop
the crazy stuff after a while, maybe not, but we at least have a
strategy to move on to saner behaviors.

This patch introduces the mount option and changes the following
behaviors in cgroup core.

* Mount options "noprefix" and "clone_children" are disallowed.  Also,
  cgroupfs file cgroup.clone_children is not created.

* When mounting an existing superblock, mount options should match.
  This is currently pretty crazy.  If one mounts a cgroup, creates a
  subdirectory, unmounts it and then mount it again with different
  option, it looks like the new options are applied but they aren't.

* Remount is disallowed.

The behaviors changes are documented in the comment above
CGRP_ROOT_SANE_BEHAVIOR enum and will be expanded as different
controllers are converted and planned improvements progress.

v2: Dropped unnecessary explicit file permission setting sane_behavior
    cftype entry as suggested by Li Zefan.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Serge E. Hallyn <serge.hallyn@ubuntu.com>
Acked-by: Li Zefan <lizefan@huawei.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vivek Goyal <vgoyal@redhat.com>

1 files changed, 48 insertions, 0 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8b8eb7c168f..67804590d4b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1080,6 +1080,8 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry)
 	mutex_lock(&cgroup_root_mutex);
 	for_each_subsys(root, ss)
 		seq_printf(seq, ",%s", ss->name);
+	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR)
+		seq_puts(seq, ",sane_behavior");
 	if (root->flags & CGRP_ROOT_NOPREFIX)
 		seq_puts(seq, ",noprefix");
 	if (root->flags & CGRP_ROOT_XATTR)
@@ -1144,6 +1146,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 			all_ss = true;
 			continue;
 		}
+		if (!strcmp(token, "__DEVEL__sane_behavior")) {
+			opts->flags |= CGRP_ROOT_SANE_BEHAVIOR;
+			continue;
+		}
 		if (!strcmp(token, "noprefix")) {
 			opts->flags |= CGRP_ROOT_NOPREFIX;
 			continue;
@@ -1231,6 +1237,20 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 
 	/* Consistency checks */
 
+	if (opts->flags & CGRP_ROOT_SANE_BEHAVIOR) {
+		pr_warning("cgroup: sane_behavior: this is still under development and its behaviors will change, proceed at your own risk\n");
+
+		if (opts->flags & CGRP_ROOT_NOPREFIX) {
+			pr_err("cgroup: sane_behavior: noprefix is not allowed\n");
+			return -EINVAL;
+		}
+
+		if (opts->cpuset_clone_children) {
+			pr_err("cgroup: sane_behavior: clone_children is not allowed\n");
+			return -EINVAL;
+		}
+	}
+
 	/*
 	 * Option noprefix was introduced just for backward compatibility
 	 * with the old cpuset, so we allow noprefix only if mounting just
@@ -1307,6 +1327,11 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	struct cgroup_sb_opts opts;
 	unsigned long added_mask, removed_mask;
 
+	if (root->flags & CGRP_ROOT_SANE_BEHAVIOR) {
+		pr_err("cgroup: sane_behavior: remount is not allowed\n");
+		return -EINVAL;
+	}
+
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 	mutex_lock(&cgroup_root_mutex);
@@ -1657,6 +1682,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		 * any) is not needed
 		 */
 		cgroup_drop_root(opts.new_root);
+
+		if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) &&
+		    root->flags != opts.flags) {
+			pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n");
+			ret = -EINVAL;
+			goto drop_new_super;
+		}
+
 		/* no subsys rebinding, so refcounts don't change */
 		drop_parsed_module_refcounts(opts.subsys_mask);
 	}
@@ -2200,6 +2233,13 @@ static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
 	return 0;
 }
 
+static int cgroup_sane_behavior_show(struct cgroup *cgrp, struct cftype *cft,
+				     struct seq_file *seq)
+{
+	seq_printf(seq, "%d\n", cgroup_sane_behavior(cgrp));
+	return 0;
+}
+
 /* A buffer size big enough for numbers or short strings */
 #define CGROUP_LOCAL_BUFFER_SIZE 64
 
@@ -2681,6 +2721,8 @@ static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 
 	for (cft = cfts; cft->name[0] != '\0'; cft++) {
 		/* does cft->flags tell us to skip this file on @cgrp? */
+		if ((cft->flags & CFTYPE_INSANE) && cgroup_sane_behavior(cgrp))
+			continue;
 		if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent)
 			continue;
 		if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgrp->parent)
@@ -3918,10 +3960,16 @@ static struct cftype files[] = {
 	},
 	{
 		.name = "cgroup.clone_children",
+		.flags = CFTYPE_INSANE,
 		.read_u64 = cgroup_clone_children_read,
 		.write_u64 = cgroup_clone_children_write,
 	},
 	{
+		.name = "cgroup.sane_behavior",
+		.flags = CFTYPE_ONLY_ON_ROOT,
+		.read_seq_string = cgroup_sane_behavior_show,
+	},
+	{
 		.name = "release_agent",
 		.flags = CFTYPE_ONLY_ON_ROOT,
 		.read_seq_string = cgroup_release_agent_show,