patches/kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch

From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 4 Apr 2017 12:50:16 +0200
Subject: [PATCH] kernel: sched: Provide a pointer to the valid CPU mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In commit 4b53a3412d66 ("sched/core: Remove the tsk_nr_cpus_allowed()
wrapper") the tsk_nr_cpus_allowed() wrapper was removed. There was not
much difference in !RT but in RT we used this to implement
migrate_disable(). Within a migrate_disable() section the CPU mask is
restricted to single CPU while the "normal" CPU mask remains untouched.

As an alternative implementation Ingo suggested to use
	struct task_struct {
		const cpumask_t		*cpus_ptr;
		cpumask_t		cpus_mask;
        };
with
	t->cpus_allowed_ptr = &t->cpus_allowed;

In -RT we then can switch the cpus_ptr to
	t->cpus_allowed_ptr = &cpumask_of(task_cpu(p));

in a migration disabled region. The rules are simple:
- Code that 'uses' ->cpus_allowed would use the pointer.
- Code that 'modifies' ->cpus_allowed would use the direct mask.

While converting the existing users I tried to stick with the rules
above however… well mostly CPUFREQ tries to temporary switch the CPU
mask to do something on a certain CPU and then switches the mask back it
its original value. So in theory `cpus_ptr' could or should be used.
However if this is invoked in a migration disabled region (which is not
the case because it would require something like preempt_disable() and
set_cpus_allowed_ptr() might sleep so it can't be) then the "restore"
part would restore the wrong mask. So it only looks strange and I go for
the pointer…

Some drivers copy the cpumask without cpumask_copy() and others use
cpumask_copy but without alloc_cpumask_var(). I did not fix those as
part of this, could do this as a follow up…

So is this the way we want it?
Is the usage of `cpus_ptr' vs `cpus_mask' for the set + restore part
(see cpufreq users) what we want? At some point it looks like they
should use a different interface for their doing. I am not sure why
switching to certain CPU is important but maybe it could be done via a
workqueue from the CPUFREQ core (so we have a comment desribing why are
doing this and a get_online_cpus() to ensure that the CPU does not go
offline too early).

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
 arch/ia64/kernel/mca.c                     |    2 -
 arch/mips/include/asm/switch_to.h          |    4 +-
 arch/mips/kernel/mips-mt-fpaff.c           |    2 -
 arch/mips/kernel/traps.c                   |    6 ++--
 arch/powerpc/platforms/cell/spufs/sched.c  |    2 -
 arch/tile/include/asm/setup.h              |    2 -
 arch/tile/kernel/hardwall.c                |   10 +++---
 drivers/infiniband/hw/hfi1/affinity.c      |    6 ++--
 drivers/infiniband/hw/hfi1/sdma.c          |    3 --
 drivers/infiniband/hw/qib/qib_file_ops.c   |    7 ++--
 fs/proc/array.c                            |    4 +-
 include/linux/sched.h                      |    5 ++-
 init/init_task.c                           |    3 +-
 kernel/cgroup/cpuset.c                     |    2 -
 kernel/fork.c                              |    3 +-
 kernel/sched/core.c                        |   42 ++++++++++++++---------------
 kernel/sched/cpudeadline.c                 |    4 +-
 kernel/sched/cpupri.c                      |    4 +-
 kernel/sched/deadline.c                    |    6 ++--
 kernel/sched/fair.c                        |   32 +++++++++++-----------
 kernel/sched/rt.c                          |    4 +-
 kernel/trace/trace_hwlat.c                 |    2 -
 lib/smp_processor_id.c                     |    2 -
 samples/trace_events/trace-events-sample.c |    2 -
 24 files changed, 80 insertions(+), 79 deletions(-)

--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1824,7 +1824,7 @@ format_mca_init_stack(void *mca_data, un
 	ti->cpu = cpu;
 	p->stack = ti;
 	p->state = TASK_UNINTERRUPTIBLE;
-	cpumask_set_cpu(cpu, &p->cpus_allowed);
+	cpumask_set_cpu(cpu, &p->cpus_mask);
 	INIT_LIST_HEAD(&p->tasks);
 	p->parent = p->real_parent = p->group_leader = p;
 	INIT_LIST_HEAD(&p->children);
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -42,7 +42,7 @@ extern struct task_struct *ll_task;
  * inline to try to keep the overhead down. If we have been forced to run on
  * a "CPU" with an FPU because of a previous high level of FP computation,
  * but did not actually use the FPU during the most recent time-slice (CU1
- * isn't set), we undo the restriction on cpus_allowed.
+ * isn't set), we undo the restriction on cpus_mask.
  *
  * We're not calling set_cpus_allowed() here, because we have no need to
  * force prompt migration - we're already switching the current CPU to a
@@ -57,7 +57,7 @@ do {									\
 	    test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) &&		\
 	    (!(KSTK_STATUS(prev) & ST0_CU1))) {				\
 		clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND);		\
-		prev->cpus_allowed = prev->thread.user_cpus_allowed;	\
+		prev->cpus_mask = prev->thread.user_cpus_allowed;	\
 	}								\
 	next->thread.emulated_fp = 0;					\
 } while(0)
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffi
 	if (retval)
 		goto out_unlock;
 
-	cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+	cpumask_or(&allowed, &p->thread.user_cpus_allowed, p->cpus_ptr);
 	cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1199,12 +1199,12 @@ static void mt_ase_fp_affinity(void)
 		 * restricted the allowed set to exclude any CPUs with FPUs,
 		 * we'll skip the procedure.
 		 */
-		if (cpumask_intersects(&current->cpus_allowed, &mt_fpu_cpumask)) {
+		if (cpumask_intersects(&current->cpus_mask, &mt_fpu_cpumask)) {
 			cpumask_t tmask;
 
 			current->thread.user_cpus_allowed
-				= current->cpus_allowed;
-			cpumask_and(&tmask, &current->cpus_allowed,
+				= current->cpus_mask;
+			cpumask_and(&tmask, &current->cpus_mask,
 				    &mt_fpu_cpumask);
 			set_cpus_allowed_ptr(current, &tmask);
 			set_thread_flag(TIF_FPUBOUND);
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_
 	 * runqueue. The context will be rescheduled on the proper node
 	 * if it is timesliced or preempted.
 	 */
-	cpumask_copy(&ctx->cpus_allowed, &current->cpus_allowed);
+	cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr);
 
 	/* Save the current cpu id for spu interrupt routing. */
 	ctx->last_ran = raw_smp_processor_id();
--- a/arch/tile/include/asm/setup.h
+++ b/arch/tile/include/asm/setup.h
@@ -49,7 +49,7 @@ int hardwall_ipi_valid(int cpu);
 
 /* Hook hardwall code into changes in affinity. */
 #define arch_set_cpus_allowed(p, new_mask) do { \
-	if (!cpumask_equal(&p->cpus_allowed, new_mask)) \
+	if (!cpumask_equal(p->cpus_ptr, new_mask)) \
 		hardwall_deactivate_all(p); \
 } while (0)
 #endif
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -590,12 +590,12 @@ static int hardwall_activate(struct hard
 	 * Get our affinity; if we're not bound to this tile uniquely,
 	 * we can't access the network registers.
 	 */
-	if (cpumask_weight(&p->cpus_allowed) != 1)
+	if (p->nr_cpus_allowed != 1)
 		return -EPERM;
 
 	/* Make sure we are bound to a cpu assigned to this resource. */
 	cpu = smp_processor_id();
-	BUG_ON(cpumask_first(&p->cpus_allowed) != cpu);
+	BUG_ON(cpumask_first(p->cpus_ptr) != cpu);
 	if (!cpumask_test_cpu(cpu, &info->cpumask))
 		return -EINVAL;
 
@@ -621,17 +621,17 @@ static int hardwall_activate(struct hard
  * Deactivate a task's hardwall.  Must hold lock for hardwall_type.
  * This method may be called from exit_thread(), so we don't want to
  * rely on too many fields of struct task_struct still being valid.
- * We assume the cpus_allowed, pid, and comm fields are still valid.
+ * We assume the nr_cpus_allowed, pid, and comm fields are still valid.
  */
 static void _hardwall_deactivate(struct hardwall_type *hwt,
 				 struct task_struct *task)
 {
 	struct thread_struct *ts = &task->thread;
 
-	if (cpumask_weight(&task->cpus_allowed) != 1) {
+	if (task->nr_cpus_allowed != 1) {
 		pr_err("pid %d (%s) releasing %s hardwall with an affinity mask containing %d cpus!\n",
 		       task->pid, task->comm, hwt->name,
-		       cpumask_weight(&task->cpus_allowed));
+		       task->nr_cpus_allowed);
 		BUG();
 	}
 
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -576,7 +576,7 @@ int hfi1_get_proc_affinity(int node)
 	struct hfi1_affinity_node *entry;
 	cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask;
 	const struct cpumask *node_mask,
-		*proc_mask = &current->cpus_allowed;
+		*proc_mask = current->cpus_ptr;
 	struct hfi1_affinity_node_list *affinity = &node_affinity;
 	struct cpu_mask_set *set = &affinity->proc;
 
@@ -584,7 +584,7 @@ int hfi1_get_proc_affinity(int node)
 	 * check whether process/context affinity has already
 	 * been set
 	 */
-	if (cpumask_weight(proc_mask) == 1) {
+	if (current->nr_cpus_allowed == 1) {
 		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl",
 			  current->pid, current->comm,
 			  cpumask_pr_args(proc_mask));
@@ -595,7 +595,7 @@ int hfi1_get_proc_affinity(int node)
 		cpu = cpumask_first(proc_mask);
 		cpumask_set_cpu(cpu, &set->used);
 		goto done;
-	} else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) {
+	} else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) {
 		hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
 			  current->pid, current->comm,
 			  cpumask_pr_args(proc_mask));
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -855,14 +855,13 @@ struct sdma_engine *sdma_select_user_eng
 {
 	struct sdma_rht_node *rht_node;
 	struct sdma_engine *sde = NULL;
-	const struct cpumask *current_mask = &current->cpus_allowed;
 	unsigned long cpu_id;
 
 	/*
 	 * To ensure that always the same sdma engine(s) will be
 	 * selected make sure the process is pinned to this CPU only.
 	 */
-	if (cpumask_weight(current_mask) != 1)
+	if (current->nr_cpus_allowed != 1)
 		goto out;
 
 	cpu_id = smp_processor_id();
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -1138,7 +1138,7 @@ static __poll_t qib_poll(struct file *fp
 static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd)
 {
 	struct qib_filedata *fd = fp->private_data;
-	const unsigned int weight = cpumask_weight(&current->cpus_allowed);
+	const unsigned int weight = current->nr_cpus_allowed;
 	const struct cpumask *local_mask = cpumask_of_pcibus(dd->pcidev->bus);
 	int local_cpu;
 
@@ -1619,9 +1619,8 @@ static int qib_assign_ctxt(struct file *
 		ret = find_free_ctxt(i_minor - 1, fp, uinfo);
 	else {
 		int unit;
-		const unsigned int cpu = cpumask_first(&current->cpus_allowed);
-		const unsigned int weight =
-			cpumask_weight(&current->cpus_allowed);
+		const unsigned int cpu = cpumask_first(current->cpus_ptr);
+		const unsigned int weight = current->nr_cpus_allowed;
 
 		if (weight == 1 && !test_bit(cpu, qib_cpulist))
 			if (!find_hca(cpu, &unit) && unit >= 0)
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -386,9 +386,9 @@ static inline void task_context_switch_c
 static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 {
 	seq_printf(m, "Cpus_allowed:\t%*pb\n",
-		   cpumask_pr_args(&task->cpus_allowed));
+		   cpumask_pr_args(task->cpus_ptr));
 	seq_printf(m, "Cpus_allowed_list:\t%*pbl\n",
-		   cpumask_pr_args(&task->cpus_allowed));
+		   cpumask_pr_args(task->cpus_ptr));
 }
 
 static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -590,7 +590,8 @@ struct task_struct {
 
 	unsigned int			policy;
 	int				nr_cpus_allowed;
-	cpumask_t			cpus_allowed;
+	const cpumask_t			*cpus_ptr;
+	cpumask_t			cpus_mask;
 
 #ifdef CONFIG_PREEMPT_RCU
 	int				rcu_read_lock_nesting;
@@ -1316,7 +1317,7 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
-#define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
+#define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MUTEX_TESTER		0x20000000	/* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP		0x40000000	/* Freezer should not count it as freezable */
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -63,7 +63,8 @@ struct task_struct init_task
 	.static_prio	= MAX_PRIO - 20,
 	.normal_prio	= MAX_PRIO - 20,
 	.policy		= SCHED_NORMAL,
-	.cpus_allowed	= CPU_MASK_ALL,
+	.cpus_ptr	= &init_task.cpus_mask,
+	.cpus_mask	= CPU_MASK_ALL,
 	.nr_cpus_allowed= NR_CPUS,
 	.mm		= NULL,
 	.active_mm	= &init_mm,
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -2089,7 +2089,7 @@ static void cpuset_fork(struct task_stru
 	if (task_css_is_root(task, cpuset_cgrp_id))
 		return;
 
-	set_cpus_allowed_ptr(task, &current->cpus_allowed);
+	set_cpus_allowed_ptr(task, current->cpus_ptr);
 	task->mems_allowed = current->mems_allowed;
 }
 
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -813,7 +813,8 @@ static struct task_struct *dup_task_stru
 #ifdef CONFIG_CC_STACKPROTECTOR
 	tsk->stack_canary = get_random_canary();
 #endif
-
+	if (orig->cpus_ptr == &orig->cpus_mask)
+		tsk->cpus_ptr = &tsk->cpus_mask;
 	/*
 	 * One for us, one for whoever does the "release_task()" (usually
 	 * parent)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -971,7 +971,7 @@ static struct rq *__migrate_task(struct
 	}
 
 	/* Affinity changed (again). */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+	if (!cpumask_test_cpu(dest_cpu, p->cpus_ptr))
 		return rq;
 
 	update_rq_clock(rq);
@@ -999,7 +999,7 @@ static int migration_cpu_stop(void *data
 	local_irq_disable();
 	/*
 	 * We need to explicitly wake pending tasks before running
-	 * __migrate_task() such that we will not miss enforcing cpus_allowed
+	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
 	sched_ttwu_pending();
@@ -1030,7 +1030,7 @@ static int migration_cpu_stop(void *data
  */
 void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
 {
-	cpumask_copy(&p->cpus_allowed, new_mask);
+	cpumask_copy(&p->cpus_mask, new_mask);
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
@@ -1100,7 +1100,7 @@ static int __set_cpus_allowed_ptr(struct
 		goto out;
 	}
 
-	if (cpumask_equal(&p->cpus_allowed, new_mask))
+	if (cpumask_equal(p->cpus_ptr, new_mask))
 		goto out;
 
 	if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
@@ -1261,10 +1261,10 @@ static int migrate_swap_stop(void *data)
 	if (task_cpu(arg->src_task) != arg->src_cpu)
 		goto unlock;
 
-	if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr))
 		goto unlock;
 
-	if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr))
 		goto unlock;
 
 	__migrate_swap_task(arg->src_task, arg->dst_cpu);
@@ -1305,10 +1305,10 @@ int migrate_swap(struct task_struct *cur
 	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
 		goto out;
 
-	if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr))
 		goto out;
 
-	if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr))
 		goto out;
 
 	trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
@@ -1452,7 +1452,7 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 
 /*
- * ->cpus_allowed is protected by both rq->lock and p->pi_lock
+ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
  *
  * A few notes on cpu_active vs cpu_online:
  *
@@ -1492,14 +1492,14 @@ static int select_fallback_rq(int cpu, s
 		for_each_cpu(dest_cpu, nodemask) {
 			if (!cpu_active(dest_cpu))
 				continue;
-			if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+			if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
 				return dest_cpu;
 		}
 	}
 
 	for (;;) {
 		/* Any allowed, online CPU? */
-		for_each_cpu(dest_cpu, &p->cpus_allowed) {
+		for_each_cpu(dest_cpu, p->cpus_ptr) {
 			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
 				continue;
 			if (!cpu_online(dest_cpu))
@@ -1544,7 +1544,7 @@ static int select_fallback_rq(int cpu, s
 }
 
 /*
- * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
  */
 static inline
 int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
@@ -1554,11 +1554,11 @@ int select_task_rq(struct task_struct *p
 	if (p->nr_cpus_allowed > 1)
 		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 	else
-		cpu = cpumask_any(&p->cpus_allowed);
+		cpu = cpumask_any(p->cpus_ptr);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
-	 * to rely on ttwu() to place the task on a valid ->cpus_allowed
+	 * to rely on ttwu() to place the task on a valid ->cpus_ptr
 	 * CPU.
 	 *
 	 * Since this is common to all placement strategies, this lives here.
@@ -1566,7 +1566,7 @@ int select_task_rq(struct task_struct *p
 	 * [ this allows ->select_task() to simply return task_cpu(p) and
 	 *   not worry about this generic constraint ]
 	 */
-	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
+	if (unlikely(!cpumask_test_cpu(cpu, p->cpus_ptr) ||
 		     !cpu_online(cpu)))
 		cpu = select_fallback_rq(task_cpu(p), p);
 
@@ -2456,7 +2456,7 @@ void wake_up_new_task(struct task_struct
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
-	 *  - cpus_allowed can change in the fork path
+	 *  - cpus_ptr can change in the fork path
 	 *  - any previously selected CPU might disappear through hotplug
 	 *
 	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
@@ -4240,7 +4240,7 @@ static int __sched_setscheduler(struct t
 			 * the entire root_domain to become SCHED_DEADLINE. We
 			 * will also fail if there's no bandwidth available.
 			 */
-			if (!cpumask_subset(span, &p->cpus_allowed) ||
+			if (!cpumask_subset(span, p->cpus_ptr) ||
 			    rq->rd->dl_bw.bw == 0) {
 				task_rq_unlock(rq, p, &rf);
 				return -EPERM;
@@ -4839,7 +4839,7 @@ long sched_getaffinity(pid_t pid, struct
 		goto out_unlock;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
+	cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
@@ -5429,7 +5429,7 @@ int task_can_attach(struct task_struct *
 	 * allowed nodes is unnecessary.  Thus, cpusets are not
 	 * applicable for such threads.  This prevents checking for
 	 * success of set_cpus_allowed_ptr() on all attached tasks
-	 * before cpus_allowed may be changed.
+	 * before cpus_mask may be changed.
 	 */
 	if (p->flags & PF_NO_SETAFFINITY) {
 		ret = -EINVAL;
@@ -5456,7 +5456,7 @@ int migrate_task_to(struct task_struct *
 	if (curr_cpu == target_cpu)
 		return 0;
 
-	if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed))
+	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
 	/* TODO: This is not properly updating schedstats */
@@ -5593,7 +5593,7 @@ static void migrate_tasks(struct rq *dea
 		put_prev_task(rq, next);
 
 		/*
-		 * Rules for changing task_struct::cpus_allowed are holding
+		 * Rules for changing task_struct::cpus_mask are holding
 		 * both pi_lock and rq->lock, such that holding either
 		 * stabilizes the mask.
 		 *
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -127,13 +127,13 @@ int cpudl_find(struct cpudl *cp, struct
 	const struct sched_dl_entity *dl_se = &p->dl;
 
 	if (later_mask &&
-	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
+	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
 		return 1;
 	} else {
 		int best_cpu = cpudl_maximum(cp);
 		WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
-		if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) &&
+		if (cpumask_test_cpu(best_cpu, p->cpus_ptr) &&
 		    dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
 			if (later_mask)
 				cpumask_set_cpu(best_cpu, later_mask);
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -103,11 +103,11 @@ int cpupri_find(struct cpupri *cp, struc
 		if (skip)
 			continue;
 
-		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
+		if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
 			continue;
 
 		if (lowest_mask) {
-			cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+			cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
 
 			/*
 			 * We have to ensure that we have at least one bit
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -541,7 +541,7 @@ static struct rq *dl_task_offline_migrat
 		 * If we cannot preempt any rq, fall back to pick any
 		 * online cpu.
 		 */
-		cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
+		cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr);
 		if (cpu >= nr_cpu_ids) {
 			/*
 			 * Fail to find any suitable cpu.
@@ -1816,7 +1816,7 @@ static void set_curr_task_dl(struct rq *
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, &p->cpus_allowed))
+	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 	return 0;
 }
@@ -1966,7 +1966,7 @@ static struct rq *find_lock_later_rq(str
 		/* Retry if something changed. */
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) ||
+				     !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
 				     task_running(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1588,7 +1588,7 @@ static void task_numa_compare(struct tas
 	 */
 	if (cur) {
 		/* Skip this swap candidate if cannot move to the source cpu */
-		if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+		if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
 			goto unlock;
 
 		/*
@@ -1698,7 +1698,7 @@ static void task_numa_find_cpu(struct ta
 
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
-		if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
+		if (!cpumask_test_cpu(cpu, env->p->cpus_ptr))
 			continue;
 
 		env->dst_cpu = cpu;
@@ -5811,7 +5811,7 @@ find_idlest_group(struct sched_domain *s
 
 		/* Skip over this group if it has no CPUs allowed */
 		if (!cpumask_intersects(sched_group_span(group),
-					&p->cpus_allowed))
+					p->cpus_ptr))
 			continue;
 
 		local_group = cpumask_test_cpu(this_cpu,
@@ -5931,7 +5931,7 @@ find_idlest_group_cpu(struct sched_group
 		return cpumask_first(sched_group_span(group));
 
 	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
+	for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
 		if (idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5971,7 +5971,7 @@ static inline int find_idlest_cpu(struct
 {
 	int new_cpu = cpu;
 
-	if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
+	if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr))
 		return prev_cpu;
 
 	while (sd) {
@@ -6080,7 +6080,7 @@ static int select_idle_core(struct task_
 	if (!test_idle_cores(target, false))
 		return -1;
 
-	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
+	cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
 
 	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
@@ -6114,7 +6114,7 @@ static int select_idle_smt(struct task_s
 		return -1;
 
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
-		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 			continue;
 		if (idle_cpu(cpu))
 			return cpu;
@@ -6177,7 +6177,7 @@ static int select_idle_cpu(struct task_s
 	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
 		if (!--nr)
 			return -1;
-		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 			continue;
 		if (idle_cpu(cpu))
 			break;
@@ -6214,7 +6214,7 @@ static int select_idle_sibling(struct ta
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
 	    idle_cpu(recent_used_cpu) &&
-	    cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
+	    cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
 		 * candidate for the next wake.
@@ -6347,7 +6347,7 @@ select_task_rq_fair(struct task_struct *
 	if (sd_flag & SD_BALANCE_WAKE) {
 		record_wakee(p);
 		want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
-			      && cpumask_test_cpu(cpu, &p->cpus_allowed);
+			      && cpumask_test_cpu(cpu, p->cpus_ptr);
 	}
 
 	rcu_read_lock();
@@ -7095,14 +7095,14 @@ int can_migrate_task(struct task_struct
 	/*
 	 * We do not migrate tasks that are:
 	 * 1) throttled_lb_pair, or
-	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
+	 * 2) cannot be migrated to this CPU due to cpus_ptr, or
 	 * 3) running (obviously), or
 	 * 4) are cache-hot on their current CPU.
 	 */
 	if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
 		return 0;
 
-	if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) {
+	if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
 		int cpu;
 
 		schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
@@ -7122,7 +7122,7 @@ int can_migrate_task(struct task_struct
 
 		/* Prevent to re-select dst_cpu via env's cpus */
 		for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
-			if (cpumask_test_cpu(cpu, &p->cpus_allowed)) {
+			if (cpumask_test_cpu(cpu, p->cpus_ptr)) {
 				env->flags |= LBF_DST_PINNED;
 				env->new_dst_cpu = cpu;
 				break;
@@ -7692,7 +7692,7 @@ check_cpu_capacity(struct rq *rq, struct
 
 /*
  * Group imbalance indicates (and tries to solve) the problem where balancing
- * groups is inadequate due to ->cpus_allowed constraints.
+ * groups is inadequate due to ->cpus_ptr constraints.
  *
  * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a
  * cpumask covering 1 cpu of the first group and 3 cpus of the second group.
@@ -8268,7 +8268,7 @@ static struct sched_group *find_busiest_
 	/*
 	 * If the busiest group is imbalanced the below checks don't
 	 * work because they assume all things are equal, which typically
-	 * isn't true due to cpus_allowed constraints and the like.
+	 * isn't true due to cpus_ptr constraints and the like.
 	 */
 	if (busiest->group_type == group_imbalanced)
 		goto force_balance;
@@ -8663,7 +8663,7 @@ static int load_balance(int this_cpu, st
 			 * if the curr task on busiest cpu can't be
 			 * moved to this_cpu
 			 */
-			if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+			if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
 				raw_spin_unlock_irqrestore(&busiest->lock,
 							    flags);
 				env.flags |= LBF_ALL_PINNED;
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1594,7 +1594,7 @@ static void put_prev_task_rt(struct rq *
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, &p->cpus_allowed))
+	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 	return 0;
 }
@@ -1729,7 +1729,7 @@ static struct rq *find_lock_lowest_rq(st
 			 * Also make sure that it wasn't scheduled on its rq.
 			 */
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) ||
+				     !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
 				     task_running(rq, task) ||
 				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -279,7 +279,7 @@ static void move_to_next_cpu(void)
 	 * of this thread, than stop migrating for the duration
 	 * of the current test.
 	 */
-	if (!cpumask_equal(current_mask, &current->cpus_allowed))
+	if (!cpumask_equal(current_mask, current->cpus_ptr))
 		goto disable;
 
 	get_online_cpus();
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -22,7 +22,7 @@ notrace static unsigned int check_preemp
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
+	if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu)))
 		goto out;
 
 	/*
--- a/samples/trace_events/trace-events-sample.c
+++ b/samples/trace_events/trace-events-sample.c
@@ -33,7 +33,7 @@ static void simple_thread_func(int cnt)
 
 	/* Silly tracepoints */
 	trace_foo_bar("hello", cnt, array, random_strings[len],
-		      &current->cpus_allowed);
+		      current->cpus_ptr);
 
 	trace_foo_with_template_simple("HELLO", cnt);