[PATCH 0/8] sched/isolation: Split housekeeping cpumask v2

[PATCH 0/8] sched/isolation: Split housekeeping cpumask v2

[Frederic Weisbecker]

This is the v2 of https://lore.kernel.org/lkml/20220104144944.1278663-1-frederic@kernel.org/

No change in this v2. Only acks and reviewed-by tags added.

git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
	isolation/split-v2

HEAD: 31b398242699300304defda3f388cc15b314c1b0

Thanks,
	Frederic
---

Frederic Weisbecker (8):
      pci: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch
      workqueue: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch
      net: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch
      sched/isolation: Use single feature type while referring to housekeeping cpumask
      sched/isolation: Consolidate check for housekeeping minimum service
      sched/isolation: Consolidate error handling
      sched/isolation: Fix housekeeping_mask memory leak
      sched/isolation: Split housekeeping cpumask per isolation features


 arch/x86/kernel/cpu/aperfmperf.c |   6 +-
 arch/x86/kvm/x86.c               |   2 +-
 drivers/base/cpu.c               |   2 +-
 drivers/pci/pci-driver.c         |  21 +++--
 include/linux/sched/isolation.h  |  43 ++++++-----
 kernel/cgroup/cpuset.c           |   6 +-
 kernel/cpu.c                     |   4 +-
 kernel/irq/cpuhotplug.c          |   4 +-
 kernel/irq/manage.c              |   4 +-
 kernel/kthread.c                 |   4 +-
 kernel/rcu/tasks.h               |   2 +-
 kernel/rcu/tree_plugin.h         |   2 +-
 kernel/sched/core.c              |  12 +--
 kernel/sched/fair.c              |  10 +--
 kernel/sched/isolation.c         | 162 +++++++++++++++++++++++++--------------
 kernel/sched/topology.c          |   8 +-
 kernel/watchdog.c                |   2 +-
 kernel/workqueue.c               |   4 +-
 net/core/net-sysfs.c             |   6 +-
 19 files changed, 180 insertions(+), 124 deletions(-)

[PATCH 1/8] pci: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch

[Frederic Weisbecker]

To prepare for supporting each feature of the housekeeping cpumask
toward cpuset, prepare each of the HK_FLAG_* entries to move to their
own cpumask with enforcing to fetch them individually. The new
constraint is that multiple HK_FLAG_* entries can't be mixed together
anymore in a single call to housekeeping cpumask().

This will later allow, for example, to runtime modify the cpulist passed
through "isolcpus=", "nohz_full=" and "rcu_nocbs=" kernel boot
parameters.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 drivers/pci/pci-driver.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 588588cfda48..4a5792c82d08 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -350,7 +350,6 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 			  const struct pci_device_id *id)
 {
 	int error, node, cpu;
-	int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
 	struct drv_dev_and_id ddi = { drv, dev, id };
 
 	/*
@@ -368,17 +367,29 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	 * device is probed from work_on_cpu() of the Physical device.
 	 */
 	if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
-	    pci_physfn_is_probed(dev))
+	    pci_physfn_is_probed(dev)) {
 		cpu = nr_cpu_ids;
-	else
+	} else {
+		cpumask_var_t wq_domain_mask;
+
+		if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) {
+			error = -ENOMEM;
+			goto out;
+		}
+		cpumask_and(wq_domain_mask,
+			    housekeeping_cpumask(HK_FLAG_WQ),
+			    housekeeping_cpumask(HK_FLAG_DOMAIN));
+
 		cpu = cpumask_any_and(cpumask_of_node(node),
-				      housekeeping_cpumask(hk_flags));
+				      wq_domain_mask);
+		free_cpumask_var(wq_domain_mask);
+	}
 
 	if (cpu < nr_cpu_ids)
 		error = work_on_cpu(cpu, local_pci_probe, &ddi);
 	else
 		error = local_pci_probe(&ddi);
-
+out:
 	dev->is_probed = 0;
 	cpu_hotplug_enable();
 	return error;
-- 
2.25.1

[PATCH 2/8] workqueue: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch

[Frederic Weisbecker]

To prepare for supporting each feature of the housekeeping cpumask
toward cpuset, prepare each of the HK_FLAG_* entries to move to their
own cpumask with enforcing to fetch them individually. The new
constraint is that multiple HK_FLAG_* entries can't be mixed together
anymore in a single call to housekeeping cpumask().

This will later allow, for example, to runtime modify the cpulist passed
through "isolcpus=", "nohz_full=" and "rcu_nocbs=" kernel boot
parameters.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 kernel/workqueue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 33f1106b4f99..61ed310621ea 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6006,13 +6006,13 @@ static void __init wq_numa_init(void)
 void __init workqueue_init_early(void)
 {
 	int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL };
-	int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
 	int i, cpu;
 
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
-	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(hk_flags));
+	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_WQ));
+	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_DOMAIN));
 
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
-- 
2.25.1

[PATCH 3/8] net: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch

[Frederic Weisbecker]

To prepare for supporting each feature of the housekeeping cpumask
toward cpuset, prepare each of the HK_FLAG_* entries to move to their
own cpumask with enforcing to fetch them individually. The new
constraint is that multiple HK_FLAG_* entries can't be mixed together
anymore in a single call to housekeeping cpumask().

This will later allow, for example, to runtime modify the cpulist passed
through "isolcpus=", "nohz_full=" and "rcu_nocbs=" kernel boot
parameters.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 net/core/net-sysfs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 53ea262ecafd..ed8da7b8d35b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -823,7 +823,7 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 {
 	struct rps_map *old_map, *map;
 	cpumask_var_t mask;
-	int err, cpu, i, hk_flags;
+	int err, cpu, i;
 	static DEFINE_MUTEX(rps_map_mutex);
 
 	if (!capable(CAP_NET_ADMIN))
@@ -839,8 +839,8 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	}
 
 	if (!cpumask_empty(mask)) {
-		hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
-		cpumask_and(mask, mask, housekeeping_cpumask(hk_flags));
+		cpumask_and(mask, mask, housekeeping_cpumask(HK_FLAG_DOMAIN));
+		cpumask_and(mask, mask, housekeeping_cpumask(HK_FLAG_WQ));
 		if (cpumask_empty(mask)) {
 			free_cpumask_var(mask);
 			return -EINVAL;
-- 
2.25.1

[PATCH 4/8] sched/isolation: Use single feature type while referring to housekeeping cpumask

[Frederic Weisbecker]

Refer to housekeeping APIs using single feature types instead of flags.
This prevents from passing multiple isolation features at once to
housekeeping interfaces, which soon won't be possible anymore as each
isolation features will have their own cpumask.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 arch/x86/kernel/cpu/aperfmperf.c |  6 ++---
 arch/x86/kvm/x86.c               |  2 +-
 drivers/base/cpu.c               |  2 +-
 drivers/pci/pci-driver.c         |  4 +--
 include/linux/sched/isolation.h  | 43 ++++++++++++++++----------------
 kernel/cgroup/cpuset.c           |  6 ++---
 kernel/cpu.c                     |  4 +--
 kernel/irq/cpuhotplug.c          |  4 +--
 kernel/irq/manage.c              |  4 +--
 kernel/kthread.c                 |  4 +--
 kernel/rcu/tasks.h               |  2 +-
 kernel/rcu/tree_plugin.h         |  2 +-
 kernel/sched/core.c              | 12 ++++-----
 kernel/sched/fair.c              | 10 ++++----
 kernel/sched/isolation.c         | 32 ++++++++++++++++--------
 kernel/sched/topology.c          |  8 +++---
 kernel/watchdog.c                |  2 +-
 kernel/workqueue.c               |  4 +--
 net/core/net-sysfs.c             |  4 +--
 19 files changed, 84 insertions(+), 71 deletions(-)

diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 22911deacb6e..9ca008f9e9b1 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -91,7 +91,7 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	if (rcu_is_idle_cpu(cpu))
@@ -114,7 +114,7 @@ void arch_freq_prepare_all(void)
 		return;
 
 	for_each_online_cpu(cpu) {
-		if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 			continue;
 		if (rcu_is_idle_cpu(cpu))
 			continue; /* Idle CPUs are completely uninteresting. */
@@ -136,7 +136,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 74b53a16f38a..c91cb0623a4b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8838,7 +8838,7 @@ int kvm_arch_init(void *opaque)
 	}
 
 	if (pi_inject_timer == -1)
-		pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER);
+		pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
 
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 5fc258073bc7..2ef23fce0860 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -275,7 +275,7 @@ static ssize_t print_cpus_isolated(struct device *dev,
 		return -ENOMEM;
 
 	cpumask_andnot(isolated, cpu_possible_mask,
-		       housekeeping_cpumask(HK_FLAG_DOMAIN));
+		       housekeeping_cpumask(HK_TYPE_DOMAIN));
 	len = sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(isolated));
 
 	free_cpumask_var(isolated);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 4a5792c82d08..f61c40a47891 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -377,8 +377,8 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 			goto out;
 		}
 		cpumask_and(wq_domain_mask,
-			    housekeeping_cpumask(HK_FLAG_WQ),
-			    housekeeping_cpumask(HK_FLAG_DOMAIN));
+			    housekeeping_cpumask(HK_TYPE_WQ),
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 		cpu = cpumask_any_and(cpumask_of_node(node),
 				      wq_domain_mask);
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index cc9f393e2a70..8c15abd67aed 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -5,54 +5,55 @@
 #include <linux/init.h>
 #include <linux/tick.h>
 
-enum hk_flags {
-	HK_FLAG_TIMER		= 1,
-	HK_FLAG_RCU		= (1 << 1),
-	HK_FLAG_MISC		= (1 << 2),
-	HK_FLAG_SCHED		= (1 << 3),
-	HK_FLAG_TICK		= (1 << 4),
-	HK_FLAG_DOMAIN		= (1 << 5),
-	HK_FLAG_WQ		= (1 << 6),
-	HK_FLAG_MANAGED_IRQ	= (1 << 7),
-	HK_FLAG_KTHREAD		= (1 << 8),
+enum hk_type {
+	HK_TYPE_TIMER,
+	HK_TYPE_RCU,
+	HK_TYPE_MISC,
+	HK_TYPE_SCHED,
+	HK_TYPE_TICK,
+	HK_TYPE_DOMAIN,
+	HK_TYPE_WQ,
+	HK_TYPE_MANAGED_IRQ,
+	HK_TYPE_KTHREAD,
+	HK_TYPE_MAX
 };
 
 #ifdef CONFIG_CPU_ISOLATION
 DECLARE_STATIC_KEY_FALSE(housekeeping_overridden);
-extern int housekeeping_any_cpu(enum hk_flags flags);
-extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
-extern bool housekeeping_enabled(enum hk_flags flags);
-extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
-extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
+extern int housekeeping_any_cpu(enum hk_type type);
+extern const struct cpumask *housekeeping_cpumask(enum hk_type type);
+extern bool housekeeping_enabled(enum hk_type type);
+extern void housekeeping_affine(struct task_struct *t, enum hk_type type);
+extern bool housekeeping_test_cpu(int cpu, enum hk_type type);
 extern void __init housekeeping_init(void);
 
 #else
 
-static inline int housekeeping_any_cpu(enum hk_flags flags)
+static inline int housekeeping_any_cpu(enum hk_type type)
 {
 	return smp_processor_id();
 }
 
-static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+static inline const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	return cpu_possible_mask;
 }
 
-static inline bool housekeeping_enabled(enum hk_flags flags)
+static inline bool housekeeping_enabled(enum hk_type type)
 {
 	return false;
 }
 
 static inline void housekeeping_affine(struct task_struct *t,
-				       enum hk_flags flags) { }
+				       enum hk_type type) { }
 static inline void housekeeping_init(void) { }
 #endif /* CONFIG_CPU_ISOLATION */
 
-static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
+static inline bool housekeeping_cpu(int cpu, enum hk_type type)
 {
 #ifdef CONFIG_CPU_ISOLATION
 	if (static_branch_unlikely(&housekeeping_overridden))
-		return housekeeping_test_cpu(cpu, flags);
+		return housekeeping_test_cpu(cpu, type);
 #endif
 	return true;
 }
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index dc653ab26e50..e4e18a2cb404 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -803,7 +803,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 			update_domain_attr_tree(dattr, &top_cpuset);
 		}
 		cpumask_and(doms[0], top_cpuset.effective_cpus,
-			    housekeeping_cpumask(HK_FLAG_DOMAIN));
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 		goto done;
 	}
@@ -833,7 +833,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		if (!cpumask_empty(cp->cpus_allowed) &&
 		    !(is_sched_load_balance(cp) &&
 		      cpumask_intersects(cp->cpus_allowed,
-					 housekeeping_cpumask(HK_FLAG_DOMAIN))))
+					 housekeeping_cpumask(HK_TYPE_DOMAIN))))
 			continue;
 
 		if (root_load_balance &&
@@ -922,7 +922,7 @@ static int generate_sched_domains(cpumask_var_t **domains,
 
 			if (apn == b->pn) {
 				cpumask_or(dp, dp, b->effective_cpus);
-				cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN));
+				cpumask_and(dp, dp, housekeeping_cpumask(HK_TYPE_DOMAIN));
 				if (dattr)
 					update_domain_attr_tree(dattr + nslot, b);
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 407a2568f35e..f39eb0b52dfe 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1488,8 +1488,8 @@ int freeze_secondary_cpus(int primary)
 	cpu_maps_update_begin();
 	if (primary == -1) {
 		primary = cpumask_first(cpu_online_mask);
-		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
-			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+		if (!housekeeping_cpu(primary, HK_TYPE_TIMER))
+			primary = housekeeping_any_cpu(HK_TYPE_TIMER);
 	} else {
 		if (!cpu_online(primary))
 			primary = cpumask_first(cpu_online_mask);
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 39a41c56ad4f..1ed2b1739363 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -176,10 +176,10 @@ static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
 {
 	const struct cpumask *hk_mask;
 
-	if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
+	if (!housekeeping_enabled(HK_TYPE_MANAGED_IRQ))
 		return false;
 
-	hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+	hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
 	if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
 		return false;
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f23ffd30385b..c03f71d5ec10 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -247,13 +247,13 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	 * online.
 	 */
 	if (irqd_affinity_is_managed(data) &&
-	    housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) {
+	    housekeeping_enabled(HK_TYPE_MANAGED_IRQ)) {
 		const struct cpumask *hk_mask, *prog_mask;
 
 		static DEFINE_RAW_SPINLOCK(tmp_mask_lock);
 		static struct cpumask tmp_mask;
 
-		hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+		hk_mask = housekeeping_cpumask(HK_TYPE_MANAGED_IRQ);
 
 		raw_spin_lock(&tmp_mask_lock);
 		cpumask_and(&tmp_mask, mask, hk_mask);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 38c6dd822da8..d100d5a15b38 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -356,7 +356,7 @@ static int kthread(void *_create)
 	 * back to default in case they have been changed.
 	 */
 	sched_setscheduler_nocheck(current, SCHED_NORMAL, &param);
-	set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_KTHREAD));
+	set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_KTHREAD));
 
 	/* OK, tell user we're spawned, wait for stop or wakeup */
 	__set_current_state(TASK_UNINTERRUPTIBLE);
@@ -722,7 +722,7 @@ int kthreadd(void *unused)
 	/* Setup a clean context for our children to inherit. */
 	set_task_comm(tsk, "kthreadd");
 	ignore_signals(tsk);
-	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD));
+	set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD));
 	set_mems_allowed(node_states[N_MEMORY]);
 
 	current->flags |= PF_NOFREEZE;
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index d64f0b1d8cd3..2c8d2fda55a8 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -496,7 +496,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	struct rcu_tasks *rtp = arg;
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
-	housekeeping_affine(current, HK_FLAG_RCU);
+	housekeeping_affine(current, HK_TYPE_RCU);
 	WRITE_ONCE(rtp->kthread_ptr, current); // Let GPs start!
 
 	/*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c5b45c2f68a1..e91efaa3e8e5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1291,7 +1291,7 @@ static void rcu_bind_gp_kthread(void)
 {
 	if (!tick_nohz_full_enabled())
 		return;
-	housekeeping_affine(current, HK_FLAG_RCU);
+	housekeeping_affine(current, HK_TYPE_RCU);
 }
 
 /* Record the current task on dyntick-idle entry. */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 848eaa0efe0e..ed67c2b56064 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1024,13 +1024,13 @@ int get_nohz_timer_target(void)
 	struct sched_domain *sd;
 	const struct cpumask *hk_mask;
 
-	if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) {
+	if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
 		if (!idle_cpu(cpu))
 			return cpu;
 		default_cpu = cpu;
 	}
 
-	hk_mask = housekeeping_cpumask(HK_FLAG_TIMER);
+	hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
@@ -1046,7 +1046,7 @@ int get_nohz_timer_target(void)
 	}
 
 	if (default_cpu == -1)
-		default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+		default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
 	cpu = default_cpu;
 unlock:
 	rcu_read_unlock();
@@ -5370,7 +5370,7 @@ static void sched_tick_start(int cpu)
 	int os;
 	struct tick_work *twork;
 
-	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
 		return;
 
 	WARN_ON_ONCE(!tick_work_cpu);
@@ -5391,7 +5391,7 @@ static void sched_tick_stop(int cpu)
 	struct tick_work *twork;
 	int os;
 
-	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+	if (housekeeping_cpu(cpu, HK_TYPE_TICK))
 		return;
 
 	WARN_ON_ONCE(!tick_work_cpu);
@@ -9240,7 +9240,7 @@ void __init sched_init_smp(void)
 	mutex_unlock(&sched_domains_mutex);
 
 	/* Move init over to a non-isolated CPU */
-	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
+	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
 		BUG();
 	current->flags &= ~PF_NO_SETAFFINITY;
 	sched_init_granularity();
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5146163bfabb..0c842a5ad9df 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10351,7 +10351,7 @@ static inline int on_null_domain(struct rq *rq)
  * - When one of the busy CPUs notice that there may be an idle rebalancing
  *   needed, they will kick the idle load balancer, which then does idle
  *   load balancing for all the idle CPUs.
- * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set
  *   anywhere yet.
  */
 
@@ -10360,7 +10360,7 @@ static inline int find_new_ilb(void)
 	int ilb;
 	const struct cpumask *hk_mask;
 
-	hk_mask = housekeeping_cpumask(HK_FLAG_MISC);
+	hk_mask = housekeeping_cpumask(HK_TYPE_MISC);
 
 	for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) {
 
@@ -10376,7 +10376,7 @@ static inline int find_new_ilb(void)
 
 /*
  * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
- * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
+ * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one).
  */
 static void kick_ilb(unsigned int flags)
 {
@@ -10589,7 +10589,7 @@ void nohz_balance_enter_idle(int cpu)
 		return;
 
 	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
-	if (!housekeeping_cpu(cpu, HK_FLAG_SCHED))
+	if (!housekeeping_cpu(cpu, HK_TYPE_SCHED))
 		return;
 
 	/*
@@ -10805,7 +10805,7 @@ static void nohz_newidle_balance(struct rq *this_rq)
 	 * This CPU doesn't want to be disturbed by scheduler
 	 * housekeeping
 	 */
-	if (!housekeeping_cpu(this_cpu, HK_FLAG_SCHED))
+	if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED))
 		return;
 
 	/* Will wake up very soon. No time for doing anything else*/
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 7f06eaf12818..a735d9e229dd 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -9,23 +9,35 @@
  */
 #include "sched.h"
 
+enum hk_flags {
+	HK_FLAG_TIMER		= BIT(HK_TYPE_TIMER),
+	HK_FLAG_RCU		= BIT(HK_TYPE_RCU),
+	HK_FLAG_MISC		= BIT(HK_TYPE_MISC),
+	HK_FLAG_SCHED		= BIT(HK_TYPE_SCHED),
+	HK_FLAG_TICK		= BIT(HK_TYPE_TICK),
+	HK_FLAG_DOMAIN		= BIT(HK_TYPE_DOMAIN),
+	HK_FLAG_WQ		= BIT(HK_TYPE_WQ),
+	HK_FLAG_MANAGED_IRQ	= BIT(HK_TYPE_MANAGED_IRQ),
+	HK_FLAG_KTHREAD		= BIT(HK_TYPE_KTHREAD),
+};
+
 DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
 EXPORT_SYMBOL_GPL(housekeeping_overridden);
 static cpumask_var_t housekeeping_mask;
 static unsigned int housekeeping_flags;
 
-bool housekeeping_enabled(enum hk_flags flags)
+bool housekeeping_enabled(enum hk_type type)
 {
-	return !!(housekeeping_flags & flags);
+	return !!(housekeeping_flags & BIT(type));
 }
 EXPORT_SYMBOL_GPL(housekeeping_enabled);
 
-int housekeeping_any_cpu(enum hk_flags flags)
+int housekeeping_any_cpu(enum hk_type type)
 {
 	int cpu;
 
 	if (static_branch_unlikely(&housekeeping_overridden)) {
-		if (housekeeping_flags & flags) {
+		if (housekeeping_flags & BIT(type)) {
 			cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id());
 			if (cpu < nr_cpu_ids)
 				return cpu;
@@ -37,27 +49,27 @@ int housekeeping_any_cpu(enum hk_flags flags)
 }
 EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
 
-const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
+const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & flags)
+		if (housekeeping_flags & BIT(type))
 			return housekeeping_mask;
 	return cpu_possible_mask;
 }
 EXPORT_SYMBOL_GPL(housekeeping_cpumask);
 
-void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
+void housekeeping_affine(struct task_struct *t, enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & flags)
+		if (housekeeping_flags & BIT(type))
 			set_cpus_allowed_ptr(t, housekeeping_mask);
 }
 EXPORT_SYMBOL_GPL(housekeeping_affine);
 
-bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
+bool housekeeping_test_cpu(int cpu, enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & flags)
+		if (housekeeping_flags & BIT(type))
 			return cpumask_test_cpu(cpu, housekeeping_mask);
 	return true;
 }
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index d201a7052a29..5318940b0b76 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1366,7 +1366,7 @@ static void asym_cpu_capacity_scan(void)
 	list_for_each_entry(entry, &asym_cap_list, link)
 		cpumask_clear(cpu_capacity_span(entry));
 
-	for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_FLAG_DOMAIN))
+	for_each_cpu_and(cpu, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN))
 		asym_cpu_capacity_update_data(cpu);
 
 	list_for_each_entry_safe(entry, next, &asym_cap_list, link) {
@@ -2351,7 +2351,7 @@ int sched_init_domains(const struct cpumask *cpu_map)
 	doms_cur = alloc_sched_domains(ndoms_cur);
 	if (!doms_cur)
 		doms_cur = &fallback_doms;
-	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_FLAG_DOMAIN));
+	cpumask_and(doms_cur[0], cpu_map, housekeeping_cpumask(HK_TYPE_DOMAIN));
 	err = build_sched_domains(doms_cur[0], NULL);
 
 	return err;
@@ -2440,7 +2440,7 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 		if (doms_new) {
 			n = 1;
 			cpumask_and(doms_new[0], cpu_active_mask,
-				    housekeeping_cpumask(HK_FLAG_DOMAIN));
+				    housekeeping_cpumask(HK_TYPE_DOMAIN));
 		}
 	} else {
 		n = ndoms_new;
@@ -2475,7 +2475,7 @@ void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[],
 		n = 0;
 		doms_new = &fallback_doms;
 		cpumask_and(doms_new[0], cpu_active_mask,
-			    housekeeping_cpumask(HK_FLAG_DOMAIN));
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
 	}
 
 	/* Build new domains: */
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 99afb88d2e85..9166220457bc 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -848,7 +848,7 @@ void __init lockup_detector_init(void)
 		pr_info("Disabling watchdog on nohz_full cores by default\n");
 
 	cpumask_copy(&watchdog_cpumask,
-		     housekeeping_cpumask(HK_FLAG_TIMER));
+		     housekeeping_cpumask(HK_TYPE_TIMER));
 
 	if (!watchdog_nmi_probe())
 		nmi_watchdog_available = true;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61ed310621ea..52e9abbb7759 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6011,8 +6011,8 @@ void __init workqueue_init_early(void)
 	BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long));
 
 	BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL));
-	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_WQ));
-	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_FLAG_DOMAIN));
+	cpumask_copy(wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_WQ));
+	cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, housekeeping_cpumask(HK_TYPE_DOMAIN));
 
 	pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ed8da7b8d35b..7ceb3460161b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -839,8 +839,8 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	}
 
 	if (!cpumask_empty(mask)) {
-		cpumask_and(mask, mask, housekeeping_cpumask(HK_FLAG_DOMAIN));
-		cpumask_and(mask, mask, housekeeping_cpumask(HK_FLAG_WQ));
+		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_DOMAIN));
+		cpumask_and(mask, mask, housekeeping_cpumask(HK_TYPE_WQ));
 		if (cpumask_empty(mask)) {
 			free_cpumask_var(mask);
 			return -EINVAL;
-- 
2.25.1

[PATCH 5/8] sched/isolation: Consolidate check for housekeeping minimum service

[Frederic Weisbecker]

There can be two subsequent calls to housekeeping_setup() due to
"nohz_full=" and "isolcpus=" that can mix up.  The two passes each have
their own way to deal with an empty housekeeping set of CPUs.
Consolidate this part and remove the awful "tmp" based naming.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 kernel/sched/isolation.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index a735d9e229dd..23085e665faa 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -91,8 +91,7 @@ void __init housekeeping_init(void)
 
 static int __init housekeeping_setup(char *str, enum hk_flags flags)
 {
-	cpumask_var_t non_housekeeping_mask;
-	cpumask_var_t tmp;
+	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
 
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
 	if (cpulist_parse(str, non_housekeeping_mask) < 0) {
@@ -101,32 +100,32 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 		return 0;
 	}
 
-	alloc_bootmem_cpumask_var(&tmp);
-	if (!housekeeping_flags) {
-		alloc_bootmem_cpumask_var(&housekeeping_mask);
-		cpumask_andnot(housekeeping_mask,
-			       cpu_possible_mask, non_housekeeping_mask);
+	alloc_bootmem_cpumask_var(&housekeeping_staging);
+	cpumask_andnot(housekeeping_staging,
+		       cpu_possible_mask, non_housekeeping_mask);
 
-		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
-		if (cpumask_empty(tmp)) {
+	if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
+		__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
+		__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+		if (!housekeeping_flags) {
 			pr_warn("Housekeeping: must include one present CPU, "
 				"using boot CPU:%d\n", smp_processor_id());
-			__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
-			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
 		}
+	}
+
+	if (!housekeeping_flags) {
+		alloc_bootmem_cpumask_var(&housekeeping_mask);
+		cpumask_copy(housekeeping_mask, housekeeping_staging);
 	} else {
-		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
-		if (cpumask_empty(tmp))
-			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
-		cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
-		if (!cpumask_equal(tmp, housekeeping_mask)) {
+		if (!cpumask_equal(housekeeping_staging, housekeeping_mask)) {
 			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
-			free_bootmem_cpumask_var(tmp);
+			free_bootmem_cpumask_var(housekeeping_staging);
 			free_bootmem_cpumask_var(non_housekeeping_mask);
 			return 0;
 		}
 	}
-	free_bootmem_cpumask_var(tmp);
+
+	free_bootmem_cpumask_var(housekeeping_staging);
 
 	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
 		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
-- 
2.25.1

[PATCH 6/8] sched/isolation: Consolidate error handling

[Frederic Weisbecker]

Centralize the mask freeing and return value for the error path. This
makes potential leaks more visible.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 kernel/sched/isolation.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 23085e665faa..828dacec483e 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -92,12 +92,12 @@ void __init housekeeping_init(void)
 static int __init housekeeping_setup(char *str, enum hk_flags flags)
 {
 	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
+	int err = 0;
 
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
 	if (cpulist_parse(str, non_housekeeping_mask) < 0) {
 		pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n");
-		free_bootmem_cpumask_var(non_housekeeping_mask);
-		return 0;
+		goto free_non_housekeeping_mask;
 	}
 
 	alloc_bootmem_cpumask_var(&housekeeping_staging);
@@ -119,30 +119,29 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 	} else {
 		if (!cpumask_equal(housekeeping_staging, housekeeping_mask)) {
 			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
-			free_bootmem_cpumask_var(housekeeping_staging);
-			free_bootmem_cpumask_var(non_housekeeping_mask);
-			return 0;
+			goto free_housekeeping_staging;
 		}
 	}
 
-	free_bootmem_cpumask_var(housekeeping_staging);
-
 	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
 		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
 			tick_nohz_full_setup(non_housekeeping_mask);
 		} else {
 			pr_warn("Housekeeping: nohz unsupported."
 				" Build with CONFIG_NO_HZ_FULL\n");
-			free_bootmem_cpumask_var(non_housekeeping_mask);
-			return 0;
+			goto free_housekeeping_staging;
 		}
 	}
 
 	housekeeping_flags |= flags;
+	err = 1;
 
+free_housekeeping_staging:
+	free_bootmem_cpumask_var(housekeeping_staging);
+free_non_housekeeping_mask:
 	free_bootmem_cpumask_var(non_housekeeping_mask);
 
-	return 1;
+	return err;
 }
 
 static int __init housekeeping_nohz_full_setup(char *str)
-- 
2.25.1

[PATCH 7/8] sched/isolation: Fix housekeeping_mask memory leak

[Frederic Weisbecker]

If "nohz_full=" or "isolcpus=nohz" are called with CONFIG_NO_HZ_FULL=n,
housekeeping_mask doesn't get freed despite it being unused if
housekeeping_setup() is called for the first time.

Check this scenario first to fix this, so that no useless allocation
is performed.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
---
 kernel/sched/isolation.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 828dacec483e..883eee9fae22 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -94,6 +94,14 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
 	int err = 0;
 
+	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
+		if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) {
+			pr_warn("Housekeeping: nohz unsupported."
+				" Build with CONFIG_NO_HZ_FULL\n");
+			return 0;
+		}
+	}
+
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
 	if (cpulist_parse(str, non_housekeeping_mask) < 0) {
 		pr_warn("Housekeeping: nohz_full= or isolcpus= incorrect CPU range\n");
@@ -123,15 +131,8 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 		}
 	}
 
-	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
-		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
-			tick_nohz_full_setup(non_housekeeping_mask);
-		} else {
-			pr_warn("Housekeeping: nohz unsupported."
-				" Build with CONFIG_NO_HZ_FULL\n");
-			goto free_housekeeping_staging;
-		}
-	}
+	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK))
+		tick_nohz_full_setup(non_housekeeping_mask);
 
 	housekeeping_flags |= flags;
 	err = 1;
-- 
2.25.1

[PATCH 8/8] sched/isolation: Split housekeeping cpumask per isolation features

[Frederic Weisbecker]

To prepare for supporting each housekeeping feature toward cpuset, split
the global housekeeping cpumask per HK_TYPE_* entry.

This will later allow, for example, to runtime modify the cpulist passed
through "isolcpus=", "nohz_full=" and "rcu_nocbs=" kernel boot
parameters.

Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Nitesh Lal <nilal@redhat.com>
Cc: Nicolas Saenz <nsaenzju@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Christoph Lameter <cl@gentwo.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Alex Belits <abelits@marvell.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Paul E. McKenney  <paulmck@kernel.org>
---
 kernel/sched/isolation.c | 91 +++++++++++++++++++++++++++-------------
 1 file changed, 62 insertions(+), 29 deletions(-)

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 883eee9fae22..b4d10815c45a 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -23,12 +23,17 @@ enum hk_flags {
 
 DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
 EXPORT_SYMBOL_GPL(housekeeping_overridden);
-static cpumask_var_t housekeeping_mask;
-static unsigned int housekeeping_flags;
+
+struct housekeeping {
+	cpumask_var_t cpumasks[HK_TYPE_MAX];
+	unsigned long flags;
+};
+
+static struct housekeeping housekeeping;
 
 bool housekeeping_enabled(enum hk_type type)
 {
-	return !!(housekeeping_flags & BIT(type));
+	return !!(housekeeping.flags & BIT(type));
 }
 EXPORT_SYMBOL_GPL(housekeeping_enabled);
 
@@ -37,12 +42,12 @@ int housekeeping_any_cpu(enum hk_type type)
 	int cpu;
 
 	if (static_branch_unlikely(&housekeeping_overridden)) {
-		if (housekeeping_flags & BIT(type)) {
-			cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id());
+		if (housekeeping.flags & BIT(type)) {
+			cpu = sched_numa_find_closest(housekeeping.cpumasks[type], smp_processor_id());
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			return cpumask_any_and(housekeeping_mask, cpu_online_mask);
+			return cpumask_any_and(housekeeping.cpumasks[type], cpu_online_mask);
 		}
 	}
 	return smp_processor_id();
@@ -52,8 +57,8 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
 const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & BIT(type))
-			return housekeeping_mask;
+		if (housekeeping.flags & BIT(type))
+			return housekeeping.cpumasks[type];
 	return cpu_possible_mask;
 }
 EXPORT_SYMBOL_GPL(housekeeping_cpumask);
@@ -61,40 +66,53 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask);
 void housekeeping_affine(struct task_struct *t, enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & BIT(type))
-			set_cpus_allowed_ptr(t, housekeeping_mask);
+		if (housekeeping.flags & BIT(type))
+			set_cpus_allowed_ptr(t, housekeeping.cpumasks[type]);
 }
 EXPORT_SYMBOL_GPL(housekeeping_affine);
 
 bool housekeeping_test_cpu(int cpu, enum hk_type type)
 {
 	if (static_branch_unlikely(&housekeeping_overridden))
-		if (housekeeping_flags & BIT(type))
-			return cpumask_test_cpu(cpu, housekeeping_mask);
+		if (housekeeping.flags & BIT(type))
+			return cpumask_test_cpu(cpu, housekeeping.cpumasks[type]);
 	return true;
 }
 EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
 
 void __init housekeeping_init(void)
 {
-	if (!housekeeping_flags)
+	enum hk_type type;
+
+	if (!housekeeping.flags)
 		return;
 
 	static_branch_enable(&housekeeping_overridden);
 
-	if (housekeeping_flags & HK_FLAG_TICK)
+	if (housekeeping.flags & HK_FLAG_TICK)
 		sched_tick_offload_init();
 
-	/* We need at least one CPU to handle housekeeping work */
-	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
+	for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
+		/* We need at least one CPU to handle housekeeping work */
+		WARN_ON_ONCE(cpumask_empty(housekeeping.cpumasks[type]));
+	}
 }
 
-static int __init housekeeping_setup(char *str, enum hk_flags flags)
+static void __init housekeeping_setup_type(enum hk_type type,
+					   cpumask_var_t housekeeping_staging)
+{
+
+	alloc_bootmem_cpumask_var(&housekeeping.cpumasks[type]);
+	cpumask_copy(housekeeping.cpumasks[type],
+		     housekeeping_staging);
+}
+
+static int __init housekeeping_setup(char *str, unsigned long flags)
 {
 	cpumask_var_t non_housekeeping_mask, housekeeping_staging;
 	int err = 0;
 
-	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
+	if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK)) {
 		if (!IS_ENABLED(CONFIG_NO_HZ_FULL)) {
 			pr_warn("Housekeeping: nohz unsupported."
 				" Build with CONFIG_NO_HZ_FULL\n");
@@ -115,26 +133,41 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 	if (!cpumask_intersects(cpu_present_mask, housekeeping_staging)) {
 		__cpumask_set_cpu(smp_processor_id(), housekeeping_staging);
 		__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
-		if (!housekeeping_flags) {
+		if (!housekeeping.flags) {
 			pr_warn("Housekeeping: must include one present CPU, "
 				"using boot CPU:%d\n", smp_processor_id());
 		}
 	}
 
-	if (!housekeeping_flags) {
-		alloc_bootmem_cpumask_var(&housekeeping_mask);
-		cpumask_copy(housekeeping_mask, housekeeping_staging);
+	if (!housekeeping.flags) {
+		/* First setup call ("nohz_full=" or "isolcpus=") */
+		enum hk_type type;
+
+		for_each_set_bit(type, &flags, HK_TYPE_MAX)
+			housekeeping_setup_type(type, housekeeping_staging);
 	} else {
-		if (!cpumask_equal(housekeeping_staging, housekeeping_mask)) {
-			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
-			goto free_housekeeping_staging;
+		/* Second setup call ("nohz_full=" after "isolcpus=" or the reverse) */
+		enum hk_type type;
+		unsigned long iter_flags = flags & housekeeping.flags;
+
+		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) {
+			if (!cpumask_equal(housekeeping_staging,
+					   housekeeping.cpumasks[type])) {
+				pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
+				goto free_housekeeping_staging;
+			}
 		}
+
+		iter_flags = flags & ~housekeeping.flags;
+
+		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX)
+			housekeeping_setup_type(type, housekeeping_staging);
 	}
 
-	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK))
+	if ((flags & HK_FLAG_TICK) && !(housekeeping.flags & HK_FLAG_TICK))
 		tick_nohz_full_setup(non_housekeeping_mask);
 
-	housekeeping_flags |= flags;
+	housekeeping.flags |= flags;
 	err = 1;
 
 free_housekeeping_staging:
@@ -147,7 +180,7 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 
 static int __init housekeeping_nohz_full_setup(char *str)
 {
-	unsigned int flags;
+	unsigned long flags;
 
 	flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU |
 		HK_FLAG_MISC | HK_FLAG_KTHREAD;
@@ -158,7 +191,7 @@ __setup("nohz_full=", housekeeping_nohz_full_setup);
 
 static int __init housekeeping_isolcpus_setup(char *str)
 {
-	unsigned int flags = 0;
+	unsigned long flags = 0;
 	bool illegal = false;
 	char *par;
 	int len;
-- 
2.25.1