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

7 files changed, 246 insertions, 128 deletions

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 980b76a1237e..d629094fac6e 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -71,8 +71,10 @@ extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
 extern void cpuset_wait_for_hotplug(void);
-extern void cpuset_read_lock(void);
-extern void cpuset_read_unlock(void);
+extern void inc_dl_tasks_cs(struct task_struct *task);
+extern void dec_dl_tasks_cs(struct task_struct *task);
+extern void cpuset_lock(void);
+extern void cpuset_unlock(void);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
@@ -189,8 +191,10 @@ static inline void cpuset_update_active_cpus(void)
 
 static inline void cpuset_wait_for_hotplug(void) { }
 
-static inline void cpuset_read_lock(void) { }
-static inline void cpuset_read_unlock(void) { }
+static inline void inc_dl_tasks_cs(struct task_struct *task) { }
+static inline void dec_dl_tasks_cs(struct task_struct *task) { }
+static inline void cpuset_lock(void) { }
+static inline void cpuset_unlock(void) { }
 
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index eed5d65b8d1f..2553918f0b61 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1852,7 +1852,9 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)
 }
 
 extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_effective_cpus);
+extern int task_can_attach(struct task_struct *p);
+extern int dl_bw_alloc(int cpu, u64 dl_bw);
+extern void dl_bw_free(int cpu, u64 dl_bw);
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index b26ae200abef..306385a7234b 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -57,6 +57,7 @@
 #include <linux/file.h>
 #include <linux/fs_parser.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/deadline.h>
 #include <linux/psi.h>
 #include <net/sock.h>
 
@@ -6695,6 +6696,9 @@ void cgroup_exit(struct task_struct *tsk)
 	list_add_tail(&tsk->cg_list, &cset->dying_tasks);
 	cset->nr_tasks--;
 
+	if (dl_task(tsk))
+		dec_dl_tasks_cs(tsk);
+
 	WARN_ON_ONCE(cgroup_task_frozen(tsk));
 	if (unlikely(!(tsk->flags & PF_KTHREAD) &&
 		     test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags)))
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index e4ca2dd2b764..2c76fcd9f0bc 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -193,6 +193,14 @@ struct cpuset {
 	int use_parent_ecpus;
 	int child_ecpus_count;
 
+	/*
+	 * number of SCHED_DEADLINE tasks attached to this cpuset, so that we
+	 * know when to rebuild associated root domain bandwidth information.
+	 */
+	int nr_deadline_tasks;
+	int nr_migrate_dl_tasks;
+	u64 sum_migrate_dl_bw;
+
 	/* Invalid partition error code, not lock protected */
 	enum prs_errcode prs_err;
 
@@ -245,6 +253,20 @@ static inline struct cpuset *parent_cs(struct cpuset *cs)
 	return css_cs(cs->css.parent);
 }
 
+void inc_dl_tasks_cs(struct task_struct *p)
+{
+	struct cpuset *cs = task_cs(p);
+
+	cs->nr_deadline_tasks++;
+}
+
+void dec_dl_tasks_cs(struct task_struct *p)
+{
+	struct cpuset *cs = task_cs(p);
+
+	cs->nr_deadline_tasks--;
+}
+
 /* bits in struct cpuset flags field */
 typedef enum {
 	CS_ONLINE,
@@ -366,22 +388,23 @@ static struct cpuset top_cpuset = {
 		if (is_cpuset_online(((des_cs) = css_cs((pos_css)))))
 
 /*
- * There are two global locks guarding cpuset structures - cpuset_rwsem and
+ * There are two global locks guarding cpuset structures - cpuset_mutex and
  * callback_lock. We also require taking task_lock() when dereferencing a
  * task's cpuset pointer. See "The task_lock() exception", at the end of this
- * comment.  The cpuset code uses only cpuset_rwsem write lock.  Other
- * kernel subsystems can use cpuset_read_lock()/cpuset_read_unlock() to
- * prevent change to cpuset structures.
+ * comment.  The cpuset code uses only cpuset_mutex. Other kernel subsystems
+ * can use cpuset_lock()/cpuset_unlock() to prevent change to cpuset
+ * structures. Note that cpuset_mutex needs to be a mutex as it is used in
+ * paths that rely on priority inheritance (e.g. scheduler - on RT) for
+ * correctness.
  *
  * A task must hold both locks to modify cpusets.  If a task holds
- * cpuset_rwsem, it blocks others wanting that rwsem, ensuring that it
- * is the only task able to also acquire callback_lock and be able to
- * modify cpusets.  It can perform various checks on the cpuset structure
- * first, knowing nothing will change.  It can also allocate memory while
- * just holding cpuset_rwsem.  While it is performing these checks, various
- * callback routines can briefly acquire callback_lock to query cpusets.
- * Once it is ready to make the changes, it takes callback_lock, blocking
- * everyone else.
+ * cpuset_mutex, it blocks others, ensuring that it is the only task able to
+ * also acquire callback_lock and be able to modify cpusets.  It can perform
+ * various checks on the cpuset structure first, knowing nothing will change.
+ * It can also allocate memory while just holding cpuset_mutex.  While it is
+ * performing these checks, various callback routines can briefly acquire
+ * callback_lock to query cpusets.  Once it is ready to make the changes, it
+ * takes callback_lock, blocking everyone else.
  *
  * Calls to the kernel memory allocator can not be made while holding
  * callback_lock, as that would risk double tripping on callback_lock
@@ -403,16 +426,16 @@ static struct cpuset top_cpuset = {
  * guidelines for accessing subsystem state in kernel/cgroup.c
  */
 
-DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem);
+static DEFINE_MUTEX(cpuset_mutex);
 
-void cpuset_read_lock(void)
+void cpuset_lock(void)
 {
-	percpu_down_read(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 }
 
-void cpuset_read_unlock(void)
+void cpuset_unlock(void)
 {
-	percpu_up_read(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 }
 
 static DEFINE_SPINLOCK(callback_lock);
@@ -496,7 +519,7 @@ static inline bool partition_is_populated(struct cpuset *cs,
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
  *
- * Call with callback_lock or cpuset_rwsem held.
+ * Call with callback_lock or cpuset_mutex held.
  */
 static void guarantee_online_cpus(struct task_struct *tsk,
 				  struct cpumask *pmask)
@@ -538,7 +561,7 @@ out_unlock:
  * One way or another, we guarantee to return some non-empty subset
  * of node_states[N_MEMORY].
  *
- * Call with callback_lock or cpuset_rwsem held.
+ * Call with callback_lock or cpuset_mutex held.
  */
 static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
 {
@@ -550,7 +573,7 @@ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask)
 /*
  * update task's spread flag if cpuset's page/slab spread flag is set
  *
- * Call with callback_lock or cpuset_rwsem held. The check can be skipped
+ * Call with callback_lock or cpuset_mutex held. The check can be skipped
  * if on default hierarchy.
  */
 static void cpuset_update_task_spread_flags(struct cpuset *cs,
@@ -575,7 +598,7 @@ static void cpuset_update_task_spread_flags(struct cpuset *cs,
  *
  * One cpuset is a subset of another if all its allowed CPUs and
  * Memory Nodes are a subset of the other, and its exclusive flags
- * are only set if the other's are set.  Call holding cpuset_rwsem.
+ * are only set if the other's are set.  Call holding cpuset_mutex.
  */
 
 static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q)
@@ -713,7 +736,7 @@ out:
  * If we replaced the flag and mask values of the current cpuset
  * (cur) with those values in the trial cpuset (trial), would
  * our various subset and exclusive rules still be valid?  Presumes
- * cpuset_rwsem held.
+ * cpuset_mutex held.
  *
  * 'cur' is the address of an actual, in-use cpuset.  Operations
  * such as list traversal that depend on the actual address of the
@@ -829,7 +852,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
 	rcu_read_unlock();
 }
 
-/* Must be called with cpuset_rwsem held.  */
+/* Must be called with cpuset_mutex held.  */
 static inline int nr_cpusets(void)
 {
 	/* jump label reference count + the top-level cpuset */
@@ -855,7 +878,7 @@ static inline int nr_cpusets(void)
  * domains when operating in the severe memory shortage situations
  * that could cause allocation failures below.
  *
- * Must be called with cpuset_rwsem held.
+ * Must be called with cpuset_mutex held.
  *
  * The three key local variables below are:
  *    cp - cpuset pointer, used (together with pos_css) to perform a
@@ -1066,11 +1089,14 @@ done:
 	return ndoms;
 }
 
-static void update_tasks_root_domain(struct cpuset *cs)
+static void dl_update_tasks_root_domain(struct cpuset *cs)
 {
 	struct css_task_iter it;
 	struct task_struct *task;
 
+	if (cs->nr_deadline_tasks == 0)
+		return;
+
 	css_task_iter_start(&cs->css, 0, &it);
 
 	while ((task = css_task_iter_next(&it)))
@@ -1079,12 +1105,12 @@ static void update_tasks_root_domain(struct cpuset *cs)
 	css_task_iter_end(&it);
 }
 
-static void rebuild_root_domains(void)
+static void dl_rebuild_rd_accounting(void)
 {
 	struct cpuset *cs = NULL;
 	struct cgroup_subsys_state *pos_css;
 
-	percpu_rwsem_assert_held(&cpuset_rwsem);
+	lockdep_assert_held(&cpuset_mutex);
 	lockdep_assert_cpus_held();
 	lockdep_assert_held(&sched_domains_mutex);
 
@@ -1107,7 +1133,7 @@ static void rebuild_root_domains(void)
 
 		rcu_read_unlock();
 
-		update_tasks_root_domain(cs);
+		dl_update_tasks_root_domain(cs);
 
 		rcu_read_lock();
 		css_put(&cs->css);
@@ -1121,7 +1147,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 {
 	mutex_lock(&sched_domains_mutex);
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
-	rebuild_root_domains();
+	dl_rebuild_rd_accounting();
 	mutex_unlock(&sched_domains_mutex);
 }
 
@@ -1134,7 +1160,7 @@ partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
  * 'cpus' is removed, then call this routine to rebuild the
  * scheduler's dynamic sched domains.
  *
- * Call with cpuset_rwsem held.  Takes cpus_read_lock().
+ * Call with cpuset_mutex held.  Takes cpus_read_lock().
  */
 static void rebuild_sched_domains_locked(void)
 {
@@ -1145,7 +1171,7 @@ static void rebuild_sched_domains_locked(void)
 	int ndoms;
 
 	lockdep_assert_cpus_held();
-	percpu_rwsem_assert_held(&cpuset_rwsem);
+	lockdep_assert_held(&cpuset_mutex);
 
 	/*
 	 * If we have raced with CPU hotplug, return early to avoid
@@ -1196,9 +1222,9 @@ static void rebuild_sched_domains_locked(void)
 void rebuild_sched_domains(void)
 {
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	rebuild_sched_domains_locked();
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 }
 
@@ -1208,7 +1234,7 @@ void rebuild_sched_domains(void)
  * @new_cpus: the temp variable for the new effective_cpus mask
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
- * effective cpuset's.  As this function is called with cpuset_rwsem held,
+ * effective cpuset's.  As this function is called with cpuset_mutex held,
  * cpuset membership stays stable. For top_cpuset, task_cpu_possible_mask()
  * is used instead of effective_cpus to make sure all offline CPUs are also
  * included as hotplug code won't update cpumasks for tasks in top_cpuset.
@@ -1322,7 +1348,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
 	int old_prs, new_prs;
 	int part_error = PERR_NONE;	/* Partition error? */
 
-	percpu_rwsem_assert_held(&cpuset_rwsem);
+	lockdep_assert_held(&cpuset_mutex);
 
 	/*
 	 * The parent must be a partition root.
@@ -1545,7 +1571,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
  *
  * On legacy hierarchy, effective_cpus will be the same with cpu_allowed.
  *
- * Called with cpuset_rwsem held
+ * Called with cpuset_mutex held
  */
 static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
 				 bool force)
@@ -1705,7 +1731,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
 	struct cpuset *sibling;
 	struct cgroup_subsys_state *pos_css;
 
-	percpu_rwsem_assert_held(&cpuset_rwsem);
+	lockdep_assert_held(&cpuset_mutex);
 
 	/*
 	 * Check all its siblings and call update_cpumasks_hier()
@@ -1955,12 +1981,12 @@ static void *cpuset_being_rebound;
  * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
  *
  * Iterate through each task of @cs updating its mems_allowed to the
- * effective cpuset's.  As this function is called with cpuset_rwsem held,
+ * effective cpuset's.  As this function is called with cpuset_mutex held,
  * cpuset membership stays stable.
  */
 static void update_tasks_nodemask(struct cpuset *cs)
 {
-	static nodemask_t newmems;	/* protected by cpuset_rwsem */
+	static nodemask_t newmems;	/* protected by cpuset_mutex */
 	struct css_task_iter it;
 	struct task_struct *task;
 
@@ -1973,7 +1999,7 @@ static void update_tasks_nodemask(struct cpuset *cs)
 	 * take while holding tasklist_lock.  Forks can happen - the
 	 * mpol_dup() cpuset_being_rebound check will catch such forks,
 	 * and rebind their vma mempolicies too.  Because we still hold
-	 * the global cpuset_rwsem, we know that no other rebind effort
+	 * the global cpuset_mutex, we know that no other rebind effort
 	 * will be contending for the global variable cpuset_being_rebound.
 	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
 	 * is idempotent.  Also migrate pages in each mm to new nodes.
@@ -2019,7 +2045,7 @@ static void update_tasks_nodemask(struct cpuset *cs)
  *
  * On legacy hierarchy, effective_mems will be the same with mems_allowed.
  *
- * Called with cpuset_rwsem held
+ * Called with cpuset_mutex held
  */
 static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 {
@@ -2072,7 +2098,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
  * mempolicies and if the cpuset is marked 'memory_migrate',
  * migrate the tasks pages to the new memory.
  *
- * Call with cpuset_rwsem held. May take callback_lock during call.
+ * Call with cpuset_mutex held. May take callback_lock during call.
  * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
  * lock each such tasks mm->mmap_lock, scan its vma's and rebind
  * their mempolicies to the cpusets new mems_allowed.
@@ -2164,7 +2190,7 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val)
  * @cs: the cpuset in which each task's spread flags needs to be changed
  *
  * Iterate through each task of @cs updating its spread flags.  As this
- * function is called with cpuset_rwsem held, cpuset membership stays
+ * function is called with cpuset_mutex held, cpuset membership stays
  * stable.
  */
 static void update_tasks_flags(struct cpuset *cs)
@@ -2184,7 +2210,7 @@ static void update_tasks_flags(struct cpuset *cs)
  * cs:		the cpuset to update
  * turning_on: 	whether the flag is being set or cleared
  *
- * Call with cpuset_rwsem held.
+ * Call with cpuset_mutex held.
  */
 
 static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
@@ -2234,7 +2260,7 @@ out:
  * @new_prs: new partition root state
  * Return: 0 if successful, != 0 if error
  *
- * Call with cpuset_rwsem held.
+ * Call with cpuset_mutex held.
  */
 static int update_prstate(struct cpuset *cs, int new_prs)
 {
@@ -2472,19 +2498,26 @@ static int cpuset_can_attach_check(struct cpuset *cs)
 	return 0;
 }
 
-/* Called by cgroups to determine if a cpuset is usable; cpuset_rwsem held */
+static void reset_migrate_dl_data(struct cpuset *cs)
+{
+	cs->nr_migrate_dl_tasks = 0;
+	cs->sum_migrate_dl_bw = 0;
+}
+
+/* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */
 static int cpuset_can_attach(struct cgroup_taskset *tset)
 {
 	struct cgroup_subsys_state *css;
-	struct cpuset *cs;
+	struct cpuset *cs, *oldcs;
 	struct task_struct *task;
 	int ret;
 
 	/* used later by cpuset_attach() */
 	cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css));
+	oldcs = cpuset_attach_old_cs;
 	cs = css_cs(css);
 
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 
 	/* Check to see if task is allowed in the cpuset */
 	ret = cpuset_can_attach_check(cs);
@@ -2492,21 +2525,46 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
 		goto out_unlock;
 
 	cgroup_taskset_for_each(task, css, tset) {
-		ret = task_can_attach(task, cs->effective_cpus);
+		ret = task_can_attach(task);
 		if (ret)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
 		if (ret)
 			goto out_unlock;
+
+		if (dl_task(task)) {
+			cs->nr_migrate_dl_tasks++;
+			cs->sum_migrate_dl_bw += task->dl.dl_bw;
+		}
 	}
 
+	if (!cs->nr_migrate_dl_tasks)
+		goto out_success;
+
+	if (!cpumask_intersects(oldcs->effective_cpus, cs->effective_cpus)) {
+		int cpu = cpumask_any_and(cpu_active_mask, cs->effective_cpus);
+
+		if (unlikely(cpu >= nr_cpu_ids)) {
+			reset_migrate_dl_data(cs);
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		ret = dl_bw_alloc(cpu, cs->sum_migrate_dl_bw);
+		if (ret) {
+			reset_migrate_dl_data(cs);
+			goto out_unlock;
+		}
+	}
+
+out_success:
 	/*
 	 * Mark attach is in progress.  This makes validate_change() fail
 	 * changes which zero cpus/mems_allowed.
 	 */
 	cs->attach_in_progress++;
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	return ret;
 }
 
@@ -2518,15 +2576,23 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
 	cgroup_taskset_first(tset, &css);
 	cs = css_cs(css);
 
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	cs->attach_in_progress--;
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
-	percpu_up_write(&cpuset_rwsem);
+
+	if (cs->nr_migrate_dl_tasks) {
+		int cpu = cpumask_any(cs->effective_cpus);
+
+		dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+		reset_migrate_dl_data(cs);
+	}
+
+	mutex_unlock(&cpuset_mutex);
 }
 
 /*
- * Protected by cpuset_rwsem. cpus_attach is used only by cpuset_attach_task()
+ * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach_task()
  * but we can't allocate it dynamically there.  Define it global and
  * allocate from cpuset_init().
  */
@@ -2535,7 +2601,7 @@ static nodemask_t cpuset_attach_nodemask_to;
 
 static void cpuset_attach_task(struct cpuset *cs, struct task_struct *task)
 {
-	percpu_rwsem_assert_held(&cpuset_rwsem);
+	lockdep_assert_held(&cpuset_mutex);
 
 	if (cs != &top_cpuset)
 		guarantee_online_cpus(task, cpus_attach);
@@ -2565,7 +2631,7 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 	cs = css_cs(css);
 
 	lockdep_assert_cpus_held();	/* see cgroup_attach_lock() */
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	cpus_updated = !cpumask_equal(cs->effective_cpus,
 				      oldcs->effective_cpus);
 	mems_updated = !nodes_equal(cs->effective_mems, oldcs->effective_mems);
@@ -2622,11 +2688,17 @@ static void cpuset_attach(struct cgroup_taskset *tset)
 out:
 	cs->old_mems_allowed = cpuset_attach_nodemask_to;
 
+	if (cs->nr_migrate_dl_tasks) {
+		cs->nr_deadline_tasks += cs->nr_migrate_dl_tasks;
+		oldcs->nr_deadline_tasks -= cs->nr_migrate_dl_tasks;
+		reset_migrate_dl_data(cs);
+	}
+
 	cs->attach_in_progress--;
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
 
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -2658,7 +2730,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 	int retval = 0;
 
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs)) {
 		retval = -ENODEV;
 		goto out_unlock;
@@ -2694,7 +2766,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft,
 		break;
 	}
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	return retval;
 }
@@ -2707,7 +2779,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 	int retval = -ENODEV;
 
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 
@@ -2720,7 +2792,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft,
 		break;
 	}
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	return retval;
 }
@@ -2753,7 +2825,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	 * operation like this one can lead to a deadlock through kernfs
 	 * active_ref protection.  Let's break the protection.  Losing the
 	 * protection is okay as we check whether @cs is online after
-	 * grabbing cpuset_rwsem anyway.  This only happens on the legacy
+	 * grabbing cpuset_mutex anyway.  This only happens on the legacy
 	 * hierarchies.
 	 */
 	css_get(&cs->css);
@@ -2761,7 +2833,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	flush_work(&cpuset_hotplug_work);
 
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 
@@ -2785,7 +2857,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 
 	free_cpuset(trialcs);
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	kernfs_unbreak_active_protection(of->kn);
 	css_put(&cs->css);
@@ -2933,13 +3005,13 @@ static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf,
 
 	css_get(&cs->css);
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	if (!is_cpuset_online(cs))
 		goto out_unlock;
 
 	retval = update_prstate(cs, val);
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	css_put(&cs->css);
 	return retval ?: nbytes;
@@ -3156,7 +3228,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 		return 0;
 
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 
 	set_bit(CS_ONLINE, &cs->flags);
 	if (is_spread_page(parent))
@@ -3207,7 +3279,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
 	spin_unlock_irq(&callback_lock);
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 	return 0;
 }
@@ -3228,7 +3300,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	struct cpuset *cs = css_cs(css);
 
 	cpus_read_lock();
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 
 	if (is_partition_valid(cs))
 		update_prstate(cs, 0);
@@ -3247,7 +3319,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css)
 	cpuset_dec();
 	clear_bit(CS_ONLINE, &cs->flags);
 
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	cpus_read_unlock();
 }
 
@@ -3260,7 +3332,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 
 static void cpuset_bind(struct cgroup_subsys_state *root_css)
 {
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	spin_lock_irq(&callback_lock);
 
 	if (is_in_v2_mode()) {
@@ -3273,7 +3345,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 	}
 
 	spin_unlock_irq(&callback_lock);
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 }
 
 /*
@@ -3294,14 +3366,14 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset)
 		return 0;
 
 	lockdep_assert_held(&cgroup_mutex);
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 
 	/* Check to see if task is allowed in the cpuset */
 	ret = cpuset_can_attach_check(cs);
 	if (ret)
 		goto out_unlock;
 
-	ret = task_can_attach(task, cs->effective_cpus);
+	ret = task_can_attach(task);
 	if (ret)
 		goto out_unlock;
 
@@ -3315,7 +3387,7 @@ static int cpuset_can_fork(struct task_struct *task, struct css_set *cset)
 	 */
 	cs->attach_in_progress++;
 out_unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 	return ret;
 }
 
@@ -3331,11 +3403,11 @@ static void cpuset_cancel_fork(struct task_struct *task, struct css_set *cset)
 	if (same_cs)
 		return;
 
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	cs->attach_in_progress--;
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 }
 
 /*
@@ -3363,7 +3435,7 @@ static void cpuset_fork(struct task_struct *task)
 	}
 
 	/* CLONE_INTO_CGROUP */
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 	guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
 	cpuset_attach_task(cs, task);
 
@@ -3371,7 +3443,7 @@ static void cpuset_fork(struct task_struct *task)
 	if (!cs->attach_in_progress)
 		wake_up(&cpuset_attach_wq);
 
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 }
 
 struct cgroup_subsys cpuset_cgrp_subsys = {
@@ -3472,7 +3544,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	is_empty = cpumask_empty(cs->cpus_allowed) ||
 		   nodes_empty(cs->mems_allowed);
 
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 
 	/*
 	 * Move tasks to the nearest ancestor with execution resources,
@@ -3482,7 +3554,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 	if (is_empty)
 		remove_tasks_in_empty_cpuset(cs);
 
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 }
 
 static void
@@ -3533,14 +3605,14 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp)
 retry:
 	wait_event(cpuset_attach_wq, cs->attach_in_progress == 0);
 
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 
 	/*
 	 * We have raced with task attaching. We wait until attaching
 	 * is finished, so we won't attach a task to an empty cpuset.
 	 */
 	if (cs->attach_in_progress) {
-		percpu_up_write(&cpuset_rwsem);
+		mutex_unlock(&cpuset_mutex);
 		goto retry;
 	}
 
@@ -3637,7 +3709,7 @@ update_tasks:
 					    cpus_updated, mems_updated);
 
 unlock:
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 }
 
 /**
@@ -3667,7 +3739,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 	if (on_dfl && !alloc_cpumasks(NULL, &tmp))
 		ptmp = &tmp;
 
-	percpu_down_write(&cpuset_rwsem);
+	mutex_lock(&cpuset_mutex);
 
 	/* fetch the available cpus/mems and find out which changed how */
 	cpumask_copy(&new_cpus, cpu_active_mask);
@@ -3724,7 +3796,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 		update_tasks_nodemask(&top_cpuset);
 	}
 
-	percpu_up_write(&cpuset_rwsem);
+	mutex_unlock(&cpuset_mutex);
 
 	/* if cpus or mems changed, we need to propagate to descendants */
 	if (cpus_updated || mems_updated) {
@@ -4155,7 +4227,7 @@ void __cpuset_memory_pressure_bump(void)
  *  - Used for /proc/<pid>/cpuset.
  *  - No need to task_lock(tsk) on this tsk->cpuset reference, as it
  *    doesn't really matter if tsk->cpuset changes after we read it,
- *    and we take cpuset_rwsem, keeping cpuset_attach() from changing it
+ *    and we take cpuset_mutex, keeping cpuset_attach() from changing it
  *    anyway.
  */
 int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a68d1276bab0..90005760003f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7590,6 +7590,7 @@ static int __sched_setscheduler(struct task_struct *p,
 	int reset_on_fork;
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
+	bool cpuset_locked = false;
 
 	/* The pi code expects interrupts enabled */
 	BUG_ON(pi && in_interrupt());
@@ -7639,8 +7640,14 @@ recheck:
 			return retval;
 	}
 
-	if (pi)
-		cpuset_read_lock();
+	/*
+	 * SCHED_DEADLINE bandwidth accounting relies on stable cpusets
+	 * information.
+	 */
+	if (dl_policy(policy) || dl_policy(p->policy)) {
+		cpuset_locked = true;
+		cpuset_lock();
+	}
 
 	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
@@ -7716,8 +7723,8 @@ change:
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
 		task_rq_unlock(rq, p, &rf);
-		if (pi)
-			cpuset_read_unlock();
+		if (cpuset_locked)
+			cpuset_unlock();
 		goto recheck;
 	}
 
@@ -7784,7 +7791,8 @@ change:
 	task_rq_unlock(rq, p, &rf);
 
 	if (pi) {
-		cpuset_read_unlock();
+		if (cpuset_locked)
+			cpuset_unlock();
 		rt_mutex_adjust_pi(p);
 	}
 
@@ -7796,8 +7804,8 @@ change:
 
 unlock:
 	task_rq_unlock(rq, p, &rf);
-	if (pi)
-		cpuset_read_unlock();
+	if (cpuset_locked)
+		cpuset_unlock();
 	return retval;
 }
 
@@ -9286,8 +9294,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-int task_can_attach(struct task_struct *p,
-		    const struct cpumask *cs_effective_cpus)
+int task_can_attach(struct task_struct *p)
 {
 	int ret = 0;
 
@@ -9300,21 +9307,9 @@ int task_can_attach(struct task_struct *p,
 	 * success of set_cpus_allowed_ptr() on all attached tasks
 	 * before cpus_mask may be changed.
 	 */
-	if (p->flags & PF_NO_SETAFFINITY) {
+	if (p->flags & PF_NO_SETAFFINITY)
 		ret = -EINVAL;
-		goto out;
-	}
 
-	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_effective_cpus)) {
-		int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus);
-
-		if (unlikely(cpu >= nr_cpu_ids))
-			return -EINVAL;
-		ret = dl_cpu_busy(cpu, p);
-	}
-
-out:
 	return ret;
 }
 
@@ -9596,7 +9591,7 @@ static void cpuset_cpu_active(void)
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		int ret = dl_cpu_busy(cpu, NULL);
+		int ret = dl_bw_check_overflow(cpu);
 
 		if (ret)
 			return ret;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 5a9a4b81c972..166c3e6eae61 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,8 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 
+#include <linux/cpuset.h>
+
 /*
  * Default limits for DL period; on the top end we guard against small util
  * tasks still getting ridiculously long effective runtimes, on the bottom end we
@@ -2596,6 +2598,12 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
 		task_non_contending(p);
 
+	/*
+	 * In case a task is setscheduled out from SCHED_DEADLINE we need to
+	 * keep track of that on its cpuset (for correct bandwidth tracking).
+	 */
+	dec_dl_tasks_cs(p);
+
 	if (!task_on_rq_queued(p)) {
 		/*
 		 * Inactive timer is armed. However, p is leaving DEADLINE and
@@ -2636,6 +2644,12 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
 		put_task_struct(p);
 
+	/*
+	 * In case a task is setscheduled to SCHED_DEADLINE we need to keep
+	 * track of that on its cpuset (for correct bandwidth tracking).
+	 */
+	inc_dl_tasks_cs(p);
+
 	/* If p is not queued we will update its parameters at next wakeup. */
 	if (!task_on_rq_queued(p)) {
 		add_rq_bw(&p->dl, &rq->dl);
@@ -3044,26 +3058,38 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 	return ret;
 }
 
-int dl_cpu_busy(int cpu, struct task_struct *p)
+enum dl_bw_request {
+	dl_bw_req_check_overflow = 0,
+	dl_bw_req_alloc,
+	dl_bw_req_free
+};
+
+static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 {
-	unsigned long flags, cap;
+	unsigned long flags;
 	struct dl_bw *dl_b;
-	bool overflow;
+	bool overflow = 0;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cap = dl_bw_capacity(cpu);
-	overflow = __dl_overflow(dl_b, cap, 0, p ? p->dl.dl_bw : 0);
 
-	if (!overflow && p) {
-		/*
-		 * We reserve space for this task in the destination
-		 * root_domain, as we can't fail after this point.
-		 * We will free resources in the source root_domain
-		 * later on (see set_cpus_allowed_dl()).
-		 */
-		__dl_add(dl_b, p->dl.dl_bw, dl_bw_cpus(cpu));
+	if (req == dl_bw_req_free) {
+		__dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
+	} else {
+		unsigned long cap = dl_bw_capacity(cpu);
+
+		overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
+
+		if (req == dl_bw_req_alloc && !overflow) {
+			/*
+			 * We reserve space in the destination
+			 * root_domain, as we can't fail after this point.
+			 * We will free resources in the source root_domain
+			 * later on (see set_cpus_allowed_dl()).
+			 */
+			__dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
+		}
 	}
 
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
@@ -3071,6 +3097,21 @@ int dl_cpu_busy(int cpu, struct task_struct *p)
 
 	return overflow ? -EBUSY : 0;
 }
+
+int dl_bw_check_overflow(int cpu)
+{
+	return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0);
+}
+
+int dl_bw_alloc(int cpu, u64 dl_bw)
+{
+	return dl_bw_manage(dl_bw_req_alloc, cpu, dl_bw);
+}
+
+void dl_bw_free(int cpu, u64 dl_bw)
+{
+	dl_bw_manage(dl_bw_req_free, cpu, dl_bw);
+}
 #endif
 
 #ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 678446251c35..1704763897d0 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -330,7 +330,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int  dl_cpu_busy(int cpu, struct task_struct *p);
+extern int  dl_bw_check_overflow(int cpu);
 
 #ifdef CONFIG_CGROUP_SCHED