diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5bcdfc10c23a..5a37188b559f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q)
  * of the main cic data structures.  For now we allow a task to change
  * its cgroup only if it's the only owner of its ioc.
  */
-static int blkcg_can_attach(struct cgroup_subsys_state *css,
-			    struct cgroup_taskset *tset)
+static int blkcg_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 	struct io_context *ioc;
 	int ret = 0;
 
 	/* task_lock() is needed to avoid races with exit_io_context() */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
 		task_lock(task);
 		ioc = task->io_context;
 		if (ioc && atomic_read(&ioc->nr_tasks) > 1)
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 869fd4a3d28e..06b77f9dd3f2 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -422,12 +422,9 @@ struct cgroup_subsys {
 	void (*css_reset)(struct cgroup_subsys_state *css);
 	void (*css_e_css_changed)(struct cgroup_subsys_state *css);
 
-	int (*can_attach)(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset);
-	void (*cancel_attach)(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset);
-	void (*attach)(struct cgroup_subsys_state *css,
-		       struct cgroup_taskset *tset);
+	int (*can_attach)(struct cgroup_taskset *tset);
+	void (*cancel_attach)(struct cgroup_taskset *tset);
+	void (*attach)(struct cgroup_taskset *tset);
 	int (*can_fork)(struct task_struct *task, void **priv_p);
 	void (*cancel_fork)(struct task_struct *task, void *priv);
 	void (*fork)(struct task_struct *task, void *priv);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f64083030ad5..cb91b44f5f78 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -120,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state
 struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
 						     struct cgroup_subsys_state *css);
 
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset);
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset);
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+					 struct cgroup_subsys_state **dst_cssp);
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+					struct cgroup_subsys_state **dst_cssp);
 
 void css_task_iter_start(struct cgroup_subsys_state *css,
 			 struct css_task_iter *it);
@@ -236,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it);
 /**
  * cgroup_taskset_for_each - iterate cgroup_taskset
  * @task: the loop cursor
+ * @dst_css: the destination css
  * @tset: taskset to iterate
  *
  * @tset may contain multiple tasks and they may belong to multiple
- * processes.  When there are multiple tasks in @tset, if a task of a
- * process is in @tset, all tasks of the process are in @tset.  Also, all
- * are guaranteed to share the same source and destination csses.
+ * processes.
+ *
+ * On the v2 hierarchy, there may be tasks from multiple processes and they
+ * may not share the source or destination csses.
+ *
+ * On traditional hierarchies, when there are multiple tasks in @tset, if a
+ * task of a process is in @tset, all tasks of the process are in @tset.
+ * Also, all are guaranteed to share the same source and destination csses.
  *
  * Iteration is not in any specific order.
  */
-#define cgroup_taskset_for_each(task, tset)				\
-	for ((task) = cgroup_taskset_first((tset)); (task);		\
-	     (task) = cgroup_taskset_next((tset)))
+#define cgroup_taskset_for_each(task, dst_css, tset)			\
+	for ((task) = cgroup_taskset_first((tset), &(dst_css));		\
+	     (task);							\
+	     (task) = cgroup_taskset_next((tset), &(dst_css)))
 
 /**
  * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
  * @leader: the loop cursor
+ * @dst_css: the destination css
  * @tset: takset to iterate
  *
  * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
  * may not contain any.
  */
-#define cgroup_taskset_for_each_leader(leader, tset)			\
-	for ((leader) = cgroup_taskset_first((tset)); (leader);		\
-	     (leader) = cgroup_taskset_next((tset)))			\
+#define cgroup_taskset_for_each_leader(leader, dst_css, tset)		\
+	for ((leader) = cgroup_taskset_first((tset), &(dst_css));	\
+	     (leader);							\
+	     (leader) = cgroup_taskset_next((tset), &(dst_css)))	\
 		if ((leader) != (leader)->group_leader)			\
 			;						\
 		else
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5cea63fe4095..470f6536b9e8 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2237,6 +2237,9 @@ struct cgroup_taskset {
 	struct list_head	src_csets;
 	struct list_head	dst_csets;
 
+	/* the subsys currently being processed */
+	int			ssid;
+
 	/*
 	 * Fields for cgroup_taskset_*() iteration.
 	 *
@@ -2299,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task,
 /**
  * cgroup_taskset_first - reset taskset and return the first task
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * @tset iteration is initialized and the first task is returned.
  */
-struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
+					 struct cgroup_subsys_state **dst_cssp)
 {
 	tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node);
 	tset->cur_task = NULL;
 
-	return cgroup_taskset_next(tset);
+	return cgroup_taskset_next(tset, dst_cssp);
 }
 
 /**
  * cgroup_taskset_next - iterate to the next task in taskset
  * @tset: taskset of interest
+ * @dst_cssp: output variable for the destination css
  *
  * Return the next task in @tset.  Iteration must have been initialized
  * with cgroup_taskset_first().
  */
-struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
+struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
+					struct cgroup_subsys_state **dst_cssp)
 {
 	struct css_set *cset = tset->cur_cset;
 	struct task_struct *task = tset->cur_task;
@@ -2332,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset)
 		if (&task->cg_list != &cset->mg_tasks) {
 			tset->cur_cset = cset;
 			tset->cur_task = task;
+
+			/*
+			 * This function may be called both before and
+			 * after cgroup_taskset_migrate().  The two cases
+			 * can be distinguished by looking at whether @cset
+			 * has its ->mg_dst_cset set.
+			 */
+			if (cset->mg_dst_cset)
+				*dst_cssp = cset->mg_dst_cset->subsys[tset->ssid];
+			else
+				*dst_cssp = cset->subsys[tset->ssid];
+
 			return task;
 		}
 
@@ -2367,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	/* check that we can legitimately attach to the cgroup */
 	for_each_e_css(css, i, dst_cgrp) {
 		if (css->ss->can_attach) {
-			ret = css->ss->can_attach(css, tset);
+			tset->ssid = i;
+			ret = css->ss->can_attach(tset);
 			if (ret) {
 				failed_css = css;
 				goto out_cancel_attach;
@@ -2400,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset,
 	 */
 	tset->csets = &tset->dst_csets;
 
-	for_each_e_css(css, i, dst_cgrp)
-		if (css->ss->attach)
-			css->ss->attach(css, tset);
+	for_each_e_css(css, i, dst_cgrp) {
+		if (css->ss->attach) {
+			tset->ssid = i;
+			css->ss->attach(tset);
+		}
+	}
 
 	ret = 0;
 	goto out_release_tset;
@@ -2411,8 +2434,10 @@ out_cancel_attach:
 	for_each_e_css(css, i, dst_cgrp) {
 		if (css == failed_css)
 			break;
-		if (css->ss->cancel_attach)
-			css->ss->cancel_attach(css, tset);
+		if (css->ss->cancel_attach) {
+			tset->ssid = i;
+			css->ss->cancel_attach(tset);
+		}
 	}
 out_release_tset:
 	spin_lock_bh(&css_set_lock);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ff02a8e51bb3..2d3df82c54f2 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -155,10 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css)
  * @freezer->lock.  freezer_attach() makes the new tasks conform to the
  * current state and all following state changes can see the new tasks.
  */
-static void freezer_attach(struct cgroup_subsys_state *new_css,
-			   struct cgroup_taskset *tset)
+static void freezer_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *new_css;
 
 	mutex_lock(&freezer_mutex);
 
@@ -172,7 +172,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css,
 	 * current state before executing the following - !frozen tasks may
 	 * be visible in a FROZEN cgroup and frozen tasks in a THAWED one.
 	 */
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, new_css, tset) {
 		struct freezer *freezer = css_freezer(new_css);
 
 		if (!(freezer->state & CGROUP_FREEZING)) {
diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c
index de3359a48dbb..8e27fc5dbb20 100644
--- a/kernel/cgroup_pids.c
+++ b/kernel/cgroup_pids.c
@@ -162,13 +162,13 @@ revert:
 	return -EAGAIN;
 }
 
-static int pids_can_attach(struct cgroup_subsys_state *css,
-			   struct cgroup_taskset *tset)
+static int pids_can_attach(struct cgroup_taskset *tset)
 {
-	struct pids_cgroup *pids = css_pids(css);
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
 		struct cgroup_subsys_state *old_css;
 		struct pids_cgroup *old_pids;
 
@@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void pids_cancel_attach(struct cgroup_subsys_state *css,
-			       struct cgroup_taskset *tset)
+static void pids_cancel_attach(struct cgroup_taskset *tset)
 {
-	struct pids_cgroup *pids = css_pids(css);
 	struct task_struct *task;
+	struct cgroup_subsys_state *dst_css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, dst_css, tset) {
+		struct pids_cgroup *pids = css_pids(dst_css);
 		struct cgroup_subsys_state *old_css;
 		struct pids_cgroup *old_pids;
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 10ae73611d80..02a8ea5c9963 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp)
 static struct cpuset *cpuset_attach_old_cs;
 
 /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys_state *css,
-			     struct cgroup_taskset *tset)
+static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct task_struct *task;
 	int ret;
 
 	/* used later by cpuset_attach() */
-	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset));
+	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+	cs = css_cs(css);
 
 	mutex_lock(&cpuset_mutex);
 
@@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css,
 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
 		goto out_unlock;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		ret = task_can_attach(task, cs->cpus_allowed);
 		if (ret)
 			goto out_unlock;
@@ -1467,9 +1468,14 @@ out_unlock:
 	return ret;
 }
 
-static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 {
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
+
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 	css_cs(css)->attach_in_progress--;
 	mutex_unlock(&cpuset_mutex);
@@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css,
  */
 static cpumask_var_t cpus_attach;
 
-static void cpuset_attach(struct cgroup_subsys_state *css,
-			  struct cgroup_taskset *tset)
+static void cpuset_attach(struct cgroup_taskset *tset)
 {
 	/* static buf protected by cpuset_mutex */
 	static nodemask_t cpuset_attach_nodemask_to;
 	struct task_struct *task;
 	struct task_struct *leader;
-	struct cpuset *cs = css_cs(css);
+	struct cgroup_subsys_state *css;
+	struct cpuset *cs;
 	struct cpuset *oldcs = cpuset_attach_old_cs;
 
+	cgroup_taskset_first(tset, &css);
+	cs = css_cs(css);
+
 	mutex_lock(&cpuset_mutex);
 
 	/* prepare for attach */
@@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 		/*
 		 * can_attach beforehand should guarantee that this doesn't
 		 * fail.  TODO: have a better way to handle failure here
@@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css,
 	 * sleep and should be moved outside migration path proper.
 	 */
 	cpuset_attach_nodemask_to = cs->effective_mems;
-	cgroup_taskset_for_each_leader(leader, tset) {
+	cgroup_taskset_for_each_leader(leader, css, tset) {
 		struct mm_struct *mm = get_task_mm(leader);
 
 		if (mm) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 36babfd20648..026305dfe523 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9456,12 +9456,12 @@ static int __perf_cgroup_move(void *info)
 	return 0;
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys_state *css,
-			       struct cgroup_taskset *tset)
+static void perf_cgroup_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset)
+	cgroup_taskset_for_each(task, css, tset)
 		task_function_call(task, __perf_cgroup_move, task);
 }
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac9319e..a9db4819e586 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8217,12 +8217,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private)
 	sched_move_task(task);
 }
 
-static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
-				 struct cgroup_taskset *tset)
+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset) {
+	cgroup_taskset_for_each(task, css, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
@@ -8235,12 +8235,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css,
 	return 0;
 }
 
-static void cpu_cgroup_attach(struct cgroup_subsys_state *css,
-			      struct cgroup_taskset *tset)
+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
+	struct cgroup_subsys_state *css;
 
-	cgroup_taskset_for_each(task, tset)
+	cgroup_taskset_for_each(task, css, tset)
 		sched_move_task(task);
 }
 
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
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 6441f47b1a8f..81cb3c72efe8 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -67,14 +67,15 @@ static int update_classid(const void *v, struct file *file, unsigned n)
 	return 0;
 }
 
-static void cgrp_attach(struct cgroup_subsys_state *css,
-			struct cgroup_taskset *tset)
+static void cgrp_attach(struct cgroup_taskset *tset)
 {
-	struct cgroup_cls_state *cs = css_cls_state(css);
-	void *v = (void *)(unsigned long)cs->classid;
 	struct task_struct *p;
+	struct cgroup_subsys_state *css;
+
+	cgroup_taskset_for_each(p, css, tset) {
+		struct cgroup_cls_state *cs = css_cls_state(css);
+		void *v = (void *)(unsigned long)cs->classid;
 
-	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_classid, v);
 		task_unlock(p);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index cbd0a199bf52..40fd09fe06ae 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n)
 	return 0;
 }
 
-static void net_prio_attach(struct cgroup_subsys_state *css,
-			    struct cgroup_taskset *tset)
+static void net_prio_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
-	void *v = (void *)(unsigned long)css->cgroup->id;
+	struct cgroup_subsys_state *css;
+
+	cgroup_taskset_for_each(p, css, tset) {
+		void *v = (void *)(unsigned long)css->cgroup->id;
 
-	cgroup_taskset_for_each(p, tset) {
 		task_lock(p);
 		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);