cgroup: pass around cgroup_subsys_state instead of cgroup in subsystem methods

cgroup is currently in the process of transitioning to using struct
cgroup_subsys_state * as the primary handle instead of struct cgroup *
in subsystem implementations for the following reasons.

* With unified hierarchy, subsystems will be dynamically bound and
  unbound from cgroups and thus css's (cgroup_subsys_state) may be
  created and destroyed dynamically over the lifetime of a cgroup,
  which is different from the current state where all css's are
  allocated and destroyed together with the associated cgroup.  This
  in turn means that cgroup_css() should be synchronized and may
  return NULL, making it more cumbersome to use.

* Differing levels of per-subsystem granularity in the unified
  hierarchy means that the task and descendant iterators should behave
  differently depending on the specific subsystem the iteration is
  being performed for.

* In majority of the cases, subsystems only care about its part in the
  cgroup hierarchy - ie. the hierarchy of css's.  Subsystem methods
  often obtain the matching css pointer from the cgroup and don't
  bother with the cgroup pointer itself.  Passing around css fits
  much better.

This patch converts all cgroup_subsys methods to take @css instead of
@cgroup.  The conversions are mostly straight-forward.  A few
noteworthy changes are

* ->css_alloc() now takes css of the parent cgroup rather than the
  pointer to the new cgroup as the css for the new cgroup doesn't
  exist yet.  Knowing the parent css is enough for all the existing
  subsystems.

* In kernel/cgroup.c::offline_css(), unnecessary open coded css
  dereference is replaced with local variable access.

This patch shouldn't cause any behavior differences.

v2: Unnecessary explicit cgrp->subsys[] deref in css_online() replaced
    with local variable @css as suggested by Li Zefan.

    Rebased on top of new for-3.12 which includes for-3.11-fixes so
    that ->css_free() invocation added by da0a12caff ("cgroup: fix a
    leak when percpu_ref_init() fails") is converted too.  Suggested
    by Li Zefan.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Li Zefan <lizefan@huawei.com>
Acked-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Aristeu Rozanski <aris@redhat.com>
Acked-by: Daniel Wagner <daniel.wagner@bmw-carit.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: Matt Helsley <matthltc@us.ibm.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 34 insertions, 23 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 4234428f1014..271d9a5cde5f 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -853,8 +853,11 @@ static void cgroup_free_fn(struct work_struct *work)
 	/*
 	 * Release the subsystem state objects.
 	 */
-	for_each_root_subsys(cgrp->root, ss)
-		ss->css_free(cgrp);
+	for_each_root_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
+		ss->css_free(css);
+	}
 
 	cgrp->root->number_of_cgroups--;
 	mutex_unlock(&cgroup_mutex);
@@ -1056,7 +1059,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			list_move(&ss->sibling, &root->subsys_list);
 			ss->root = root;
 			if (ss->bind)
-				ss->bind(cgrp);
+				ss->bind(cgrp->subsys[i]);
 
 			/* refcount was already taken, and we're keeping it */
 			root->subsys_mask |= bit;
@@ -1066,7 +1069,7 @@ static int rebind_subsystems(struct cgroupfs_root *root,
 			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
 
 			if (ss->bind)
-				ss->bind(cgroup_dummy_top);
+				ss->bind(cgroup_dummy_top->subsys[i]);
 			cgroup_dummy_top->subsys[i]->cgroup = cgroup_dummy_top;
 			cgrp->subsys[i] = NULL;
 			cgroup_subsys[i]->root = &cgroup_dummy_root;
@@ -2049,8 +2052,10 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 	 * step 1: check that we can legitimately attach to the cgroup.
 	 */
 	for_each_root_subsys(root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
 		if (ss->can_attach) {
-			retval = ss->can_attach(cgrp, &tset);
+			retval = ss->can_attach(css, &tset);
 			if (retval) {
 				failed_ss = ss;
 				goto out_cancel_attach;
@@ -2089,8 +2094,10 @@ static int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk,
 	 * step 4: do subsystem attach callbacks.
 	 */
 	for_each_root_subsys(root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
 		if (ss->attach)
-			ss->attach(cgrp, &tset);
+			ss->attach(css, &tset);
 	}
 
 	/*
@@ -2109,10 +2116,12 @@ out_put_css_set_refs:
 out_cancel_attach:
 	if (retval) {
 		for_each_root_subsys(root, ss) {
+			struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+
 			if (ss == failed_ss)
 				break;
 			if (ss->cancel_attach)
-				ss->cancel_attach(cgrp, &tset);
+				ss->cancel_attach(css, &tset);
 		}
 	}
 out_free_group_list:
@@ -4206,14 +4215,15 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 /* invoke ->css_online() on a new CSS and mark it online if successful */
 static int online_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 {
+	struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
 	int ret = 0;
 
 	lockdep_assert_held(&cgroup_mutex);
 
 	if (ss->css_online)
-		ret = ss->css_online(cgrp);
+		ret = ss->css_online(css);
 	if (!ret)
-		cgrp->subsys[ss->subsys_id]->flags |= CSS_ONLINE;
+		css->flags |= CSS_ONLINE;
 	return ret;
 }
 
@@ -4228,9 +4238,9 @@ static void offline_css(struct cgroup_subsys *ss, struct cgroup *cgrp)
 		return;
 
 	if (ss->css_offline)
-		ss->css_offline(cgrp);
+		ss->css_offline(css);
 
-	cgrp->subsys[ss->subsys_id]->flags &= ~CSS_ONLINE;
+	css->flags &= ~CSS_ONLINE;
 }
 
 /*
@@ -4305,7 +4315,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	for_each_root_subsys(root, ss) {
 		struct cgroup_subsys_state *css;
 
-		css = ss->css_alloc(cgrp);
+		css = ss->css_alloc(parent->subsys[ss->subsys_id]);
 		if (IS_ERR(css)) {
 			err = PTR_ERR(css);
 			goto err_free_all;
@@ -4313,7 +4323,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 		err = percpu_ref_init(&css->refcnt, css_release);
 		if (err) {
-			ss->css_free(cgrp);
+			ss->css_free(css);
 			goto err_free_all;
 		}
 
@@ -4386,7 +4396,7 @@ err_free_all:
 
 		if (css) {
 			percpu_ref_cancel_init(&css->refcnt);
-			ss->css_free(cgrp);
+			ss->css_free(css);
 		}
 	}
 	mutex_unlock(&cgroup_mutex);
@@ -4641,7 +4651,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 	/* Create the top cgroup state for this subsystem */
 	list_add(&ss->sibling, &cgroup_dummy_root.subsys_list);
 	ss->root = &cgroup_dummy_root;
-	css = ss->css_alloc(cgroup_dummy_top);
+	css = ss->css_alloc(cgroup_dummy_top->subsys[ss->subsys_id]);
 	/* We don't handle early failures gracefully */
 	BUG_ON(IS_ERR(css));
 	init_cgroup_css(css, ss, cgroup_dummy_top);
@@ -4720,7 +4730,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss)
 	 * struct, so this can happen first (i.e. before the dummy root
 	 * attachment).
 	 */
-	css = ss->css_alloc(cgroup_dummy_top);
+	css = ss->css_alloc(cgroup_dummy_top->subsys[ss->subsys_id]);
 	if (IS_ERR(css)) {
 		/* failure case - need to deassign the cgroup_subsys[] slot. */
 		cgroup_subsys[ss->subsys_id] = NULL;
@@ -4836,7 +4846,7 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss)
 	 * the cgrp->subsys pointer to find their state. note that this
 	 * also takes care of freeing the css_id.
 	 */
-	ss->css_free(cgroup_dummy_top);
+	ss->css_free(cgroup_dummy_top->subsys[ss->subsys_id]);
 	cgroup_dummy_top->subsys[ss->subsys_id] = NULL;
 
 	mutex_unlock(&cgroup_mutex);
@@ -5192,10 +5202,10 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks)
 		 */
 		for_each_builtin_subsys(ss, i) {
 			if (ss->exit) {
-				struct cgroup *old_cgrp = cset->subsys[i]->cgroup;
-				struct cgroup *cgrp = task_cgroup(tsk, i);
+				struct cgroup_subsys_state *old_css = cset->subsys[i];
+				struct cgroup_subsys_state *css = task_css(tsk, i);
 
-				ss->exit(cgrp, old_cgrp, tsk);
+				ss->exit(css, old_css, tsk);
 			}
 		}
 	}
@@ -5529,7 +5539,8 @@ struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
 }
 
 #ifdef CONFIG_CGROUP_DEBUG
-static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cgrp)
+static struct cgroup_subsys_state *
+debug_css_alloc(struct cgroup_subsys_state *parent_css)
 {
 	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);
 
@@ -5539,9 +5550,9 @@ static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cgrp)
 	return css;
 }
 
-static void debug_css_free(struct cgroup *cgrp)
+static void debug_css_free(struct cgroup_subsys_state *css)
 {
-	kfree(cgrp->subsys[debug_subsys_id]);
+	kfree(css);
 }
 
 static u64 debug_taskcount_read(struct cgroup *cgrp, struct cftype *cft)