cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset

Until now, HK_TYPE_DOMAIN used to only include boot defined isolated
CPUs passed through isolcpus= boot option. Users interested in also
knowing the runtime defined isolated CPUs through cpuset must use
different APIs: cpuset_cpu_is_isolated(), cpu_is_isolated(), etc...

There are many drawbacks to that approach:

1) Most interested subsystems want to know about all isolated CPUs, not
  just those defined on boot time.

2) cpuset_cpu_is_isolated() / cpu_is_isolated() are not synchronized with
  concurrent cpuset changes.

3) Further cpuset modifications are not propagated to subsystems

Solve 1) and 2) and centralize all isolated CPUs within the
HK_TYPE_DOMAIN housekeeping cpumask.

Subsystems can rely on RCU to synchronize against concurrent changes.

The propagation mentioned in 3) will be handled in further patches.

[Chen Ridong: Fix cpu_hotplug_lock deadlock and use correct static
branch API]

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Waiman Long <longman@redhat.com>
Reviewed-by: Chen Ridong <chenridong@huawei.com>
Signed-off-by: Chen Ridong <chenridong@huawei.com>
Cc: "Michal Koutný" <mkoutny@suse.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
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>
Cc: cgroups@vger.kernel.org

3 files changed, 73 insertions, 8 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 5e2e3514c22e..e146e1f34bf9 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1482,14 +1482,15 @@ static void update_isolation_cpumasks(void)
 	if (!isolated_cpus_updating)
 		return;
 
-	lockdep_assert_cpus_held();
-
 	ret = workqueue_unbound_exclude_cpumask(isolated_cpus);
 	WARN_ON_ONCE(ret < 0);
 
 	ret = tmigr_isolated_exclude_cpumask(isolated_cpus);
 	WARN_ON_ONCE(ret < 0);
 
+	ret = housekeeping_update(isolated_cpus);
+	WARN_ON_ONCE(ret < 0);
+
 	isolated_cpus_updating = false;
 }
 
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 6f77289c14c3..674a02891b38 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -29,18 +29,48 @@ static struct housekeeping housekeeping;
 
 bool housekeeping_enabled(enum hk_type type)
 {
-	return !!(housekeeping.flags & BIT(type));
+	return !!(READ_ONCE(housekeeping.flags) & BIT(type));
 }
 EXPORT_SYMBOL_GPL(housekeeping_enabled);
 
+static bool housekeeping_dereference_check(enum hk_type type)
+{
+	if (IS_ENABLED(CONFIG_LOCKDEP) && type == HK_TYPE_DOMAIN) {
+		/* Cpuset isn't even writable yet? */
+		if (system_state <= SYSTEM_SCHEDULING)
+			return true;
+
+		/* CPU hotplug write locked, so cpuset partition can't be overwritten */
+		if (IS_ENABLED(CONFIG_HOTPLUG_CPU) && lockdep_is_cpus_write_held())
+			return true;
+
+		/* Cpuset lock held, partitions not writable */
+		if (IS_ENABLED(CONFIG_CPUSETS) && lockdep_is_cpuset_held())
+			return true;
+
+		return false;
+	}
+
+	return true;
+}
+
+static inline struct cpumask *housekeeping_cpumask_dereference(enum hk_type type)
+{
+	return rcu_dereference_all_check(housekeeping.cpumasks[type],
+					 housekeeping_dereference_check(type));
+}
+
 const struct cpumask *housekeeping_cpumask(enum hk_type type)
 {
+	const struct cpumask *mask = NULL;
+
 	if (static_branch_unlikely(&housekeeping_overridden)) {
-		if (housekeeping.flags & BIT(type)) {
-			return rcu_dereference_check(housekeeping.cpumasks[type], 1);
-		}
+		if (READ_ONCE(housekeeping.flags) & BIT(type))
+			mask = housekeeping_cpumask_dereference(type);
 	}
-	return cpu_possible_mask;
+	if (!mask)
+		mask = cpu_possible_mask;
+	return mask;
 }
 EXPORT_SYMBOL_GPL(housekeeping_cpumask);
 
@@ -80,12 +110,45 @@ EXPORT_SYMBOL_GPL(housekeeping_affine);
 
 bool housekeeping_test_cpu(int cpu, enum hk_type type)
 {
-	if (static_branch_unlikely(&housekeeping_overridden) && housekeeping.flags & BIT(type))
+	if (static_branch_unlikely(&housekeeping_overridden) &&
+	    READ_ONCE(housekeeping.flags) & BIT(type))
 		return cpumask_test_cpu(cpu, housekeeping_cpumask(type));
 	return true;
 }
 EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
 
+int housekeeping_update(struct cpumask *isol_mask)
+{
+	struct cpumask *trial, *old = NULL;
+
+	lockdep_assert_cpus_held();
+
+	trial = kmalloc(cpumask_size(), GFP_KERNEL);
+	if (!trial)
+		return -ENOMEM;
+
+	cpumask_andnot(trial, housekeeping_cpumask(HK_TYPE_DOMAIN_BOOT), isol_mask);
+	if (!cpumask_intersects(trial, cpu_online_mask)) {
+		kfree(trial);
+		return -EINVAL;
+	}
+
+	if (!housekeeping.flags)
+		static_branch_enable_cpuslocked(&housekeeping_overridden);
+
+	if (housekeeping.flags & HK_FLAG_DOMAIN)
+		old = housekeeping_cpumask_dereference(HK_TYPE_DOMAIN);
+	else
+		WRITE_ONCE(housekeeping.flags, housekeeping.flags | HK_FLAG_DOMAIN);
+	rcu_assign_pointer(housekeeping.cpumasks[HK_TYPE_DOMAIN], trial);
+
+	synchronize_rcu();
+
+	kfree(old);
+
+	return 0;
+}
+
 void __init housekeeping_init(void)
 {
 	enum hk_type type;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 475bdab3b8db..653e898a996a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -30,6 +30,7 @@
 #include <linux/context_tracking.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask_api.h>
+#include <linux/cpuset.h>
 #include <linux/ctype.h>
 #include <linux/file.h>
 #include <linux/fs_api.h>