sched/isolation: Convert housekeeping cpumasks to rcu pointers

HK_TYPE_DOMAIN's cpumask will soon be made modifiable by cpuset.
A synchronization mechanism is then needed to synchronize the updates
with the housekeeping cpumask readers.

Turn the housekeeping cpumasks into RCU pointers. Once a housekeeping
cpumask will be modified, the update side will wait for an RCU grace
period and propagate the change to interested subsystem when deemed
necessary.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Marco Crivellari <marco.crivellari@suse.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Waiman Long <longman@redhat.com>

2 files changed, 38 insertions, 23 deletions

diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 11a623fa6320..6f77289c14c3 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -21,7 +21,7 @@ DEFINE_STATIC_KEY_FALSE(housekeeping_overridden);
 EXPORT_SYMBOL_GPL(housekeeping_overridden);
 
 struct housekeeping {
-	cpumask_var_t cpumasks[HK_TYPE_MAX];
+	struct cpumask __rcu *cpumasks[HK_TYPE_MAX];
 	unsigned long flags;
 };
 
@@ -33,17 +33,28 @@ bool housekeeping_enabled(enum hk_type type)
 }
 EXPORT_SYMBOL_GPL(housekeeping_enabled);
 
+const struct cpumask *housekeeping_cpumask(enum hk_type type)
+{
+	if (static_branch_unlikely(&housekeeping_overridden)) {
+		if (housekeeping.flags & BIT(type)) {
+			return rcu_dereference_check(housekeeping.cpumasks[type], 1);
+		}
+	}
+	return cpu_possible_mask;
+}
+EXPORT_SYMBOL_GPL(housekeeping_cpumask);
+
 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.cpumasks[type], smp_processor_id());
+			cpu = sched_numa_find_closest(housekeeping_cpumask(type), smp_processor_id());
 			if (cpu < nr_cpu_ids)
 				return cpu;
 
-			cpu = cpumask_any_and_distribute(housekeeping.cpumasks[type], cpu_online_mask);
+			cpu = cpumask_any_and_distribute(housekeeping_cpumask(type), cpu_online_mask);
 			if (likely(cpu < nr_cpu_ids))
 				return cpu;
 			/*
@@ -59,28 +70,18 @@ int housekeeping_any_cpu(enum hk_type type)
 }
 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.cpumasks[type];
-	return cpu_possible_mask;
-}
-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.cpumasks[type]);
+			set_cpus_allowed_ptr(t, housekeeping_cpumask(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.cpumasks[type]);
+	if (static_branch_unlikely(&housekeeping_overridden) && housekeeping.flags & BIT(type))
+		return cpumask_test_cpu(cpu, housekeeping_cpumask(type));
 	return true;
 }
 EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
@@ -96,20 +97,33 @@ void __init housekeeping_init(void)
 
 	if (housekeeping.flags & HK_FLAG_KERNEL_NOISE)
 		sched_tick_offload_init();
-
+	/*
+	 * Realloc with a proper allocator so that any cpumask update
+	 * can indifferently free the old version with kfree().
+	 */
 	for_each_set_bit(type, &housekeeping.flags, HK_TYPE_MAX) {
+		struct cpumask *omask, *nmask = kmalloc(cpumask_size(), GFP_KERNEL);
+
+		if (WARN_ON_ONCE(!nmask))
+			return;
+
+		omask = rcu_dereference(housekeeping.cpumasks[type]);
+
 		/* We need at least one CPU to handle housekeeping work */
-		WARN_ON_ONCE(cpumask_empty(housekeeping.cpumasks[type]));
+		WARN_ON_ONCE(cpumask_empty(omask));
+		cpumask_copy(nmask, omask);
+		RCU_INIT_POINTER(housekeeping.cpumasks[type], nmask);
+		memblock_free(omask, cpumask_size());
 	}
 }
 
 static void __init housekeeping_setup_type(enum hk_type type,
 					   cpumask_var_t housekeeping_staging)
 {
+	struct cpumask *mask = memblock_alloc_or_panic(cpumask_size(), SMP_CACHE_BYTES);
 
-	alloc_bootmem_cpumask_var(&housekeeping.cpumasks[type]);
-	cpumask_copy(housekeeping.cpumasks[type],
-		     housekeeping_staging);
+	cpumask_copy(mask, housekeeping_staging);
+	RCU_INIT_POINTER(housekeeping.cpumasks[type], mask);
 }
 
 static int __init housekeeping_setup(char *str, unsigned long flags)
@@ -162,7 +176,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 
 		for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) {
 			if (!cpumask_equal(housekeeping_staging,
-					   housekeeping.cpumasks[type])) {
+					   housekeeping_cpumask(type))) {
 				pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
 				goto free_housekeeping_staging;
 			}
@@ -183,7 +197,7 @@ static int __init housekeeping_setup(char *str, unsigned long flags)
 		iter_flags = flags & (HK_FLAG_KERNEL_NOISE | HK_FLAG_DOMAIN);
 		first_cpu = (type == HK_TYPE_MAX || !iter_flags) ? 0 :
 			    cpumask_first_and_and(cpu_present_mask,
-				    housekeeping_staging, housekeeping.cpumasks[type]);
+						  housekeeping_staging, housekeeping_cpumask(type));
 		if (first_cpu >= min(nr_cpu_ids, setup_max_cpus)) {
 			pr_warn("Housekeeping: must include one present CPU "
 				"neither in nohz_full= nor in isolcpus=domain, "
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index d30cca6870f5..475bdab3b8db 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -42,6 +42,7 @@
 #include <linux/ktime_api.h>
 #include <linux/lockdep_api.h>
 #include <linux/lockdep.h>
+#include <linux/memblock.h>
 #include <linux/minmax.h>
 #include <linux/mm.h>
 #include <linux/module.h>