Merge branch 'for-4.4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup

Pull cgroup fixes from Tejun Heo:
 "More change than I'd have liked at this stage.  The pids controller
  and the changes made to cgroup core to support it introduced and
  revealed several important issues.

   - Assigning membership to a newly created task and migrating it can
     race leading to incorrect accounting.  Oleg fixed it by widening
     threadgroup synchronization.  It looks like we'll be able to merge
     it with a different percpu rwsem which is used in fork path making
     things simpler and cheaper.

   - The recent change to extend cgroup membership to zombies (so that
     pid accounting can extend till the pid is actually released) missed
     pinning the underlying data structures leading to use-after-free.
     Fixed.

   - v2 hierarchy was calling subsystem callbacks with the wrong target
     cgroup_subsys_state based on the incorrect assumption that they
     share the same target.  pids is the first controller affected by
     this.  Subsys callbacks updated so that they can deal with
     multi-target migrations"

* 'for-4.4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  cgroup_pids: don't account for the root cgroup
  cgroup: fix handling of multi-destination migration from subtree_control enabling
  cgroup_freezer: simplify propagation of CGROUP_FROZEN clearing in freezer_attach()
  cgroup: pids: kill pids_fork(), simplify pids_can_fork() and pids_cancel_fork()
  cgroup: pids: fix race between cgroup_post_fork() and cgroup_migrate()
  cgroup: make css_set pin its css's to avoid use-afer-free
  cgroup: fix cftype->file_offset handling

1 files changed, 23 insertions, 22 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9acfb165eb52..c92a65b2b4ab 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void)
 	spin_unlock(&mc.lock);
 }
 
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 {
-	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *memcg;
 	struct mem_cgroup *from;
 	struct task_struct *leader, *p;
 	struct mm_struct *mm;
 	unsigned long move_flags;
 	int ret = 0;
 
-	/*
-	 * We are now commited to this value whatever it is. Changes in this
-	 * tunable will only affect upcoming migrations, not the current one.
-	 * So we need to save it, and keep it going.
-	 */
-	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
-	if (!move_flags)
+	/* charge immigration isn't supported on the default hierarchy */
+	if (cgroup_subsys_on_dfl(memory_cgrp_subsys))
 		return 0;
 
 	/*
@@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	 * multiple.
 	 */
 	p = NULL;
-	cgroup_taskset_for_each_leader(leader, tset) {
+	cgroup_taskset_for_each_leader(leader, css, tset) {
 		WARN_ON_ONCE(p);
 		p = leader;
+		memcg = mem_cgroup_from_css(css);
 	}
 	if (!p)
 		return 0;
 
+	/*
+	 * We are now commited to this value whatever it is. Changes in this
+	 * tunable will only affect upcoming migrations, not the current one.
+	 * So we need to save it, and keep it going.
+	 */
+	move_flags = READ_ONCE(memcg->move_charge_at_immigrate);
+	if (!move_flags)
+		return 0;
+
 	from = mem_cgroup_from_task(p);
 
 	VM_BUG_ON(from == memcg);
@@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
 	return ret;
 }
 
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
-				     struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 	if (mc.to)
 		mem_cgroup_clear_mc();
@@ -4985,10 +4989,10 @@ retry:
 	atomic_dec(&mc.from->moving_account);
 }
 
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
 {
-	struct task_struct *p = cgroup_taskset_first(tset);
+	struct cgroup_subsys_state *css;
+	struct task_struct *p = cgroup_taskset_first(tset, &css);
 	struct mm_struct *mm = get_task_mm(p);
 
 	if (mm) {
@@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
 		mem_cgroup_clear_mc();
 }
 #else	/* !CONFIG_MMU */
-static int mem_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	return 0;
 }
-static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css,
-				     struct cgroup_taskset *tset)
+static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset)
 {
 }
-static void mem_cgroup_move_task(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void mem_cgroup_move_task(struct cgroup_taskset *tset)
 {
 }
 #endif