diff mbox series

[RFC,1/8] rcu/nocb: Pass a cpumask instead of a single CPU to offload/deoffload

Message ID 20240117163511.88173-2-longman@redhat.com
State New
Headers show
Series cgroup/cpuset: Support RCU_NOCB on isolated partitions | expand

Commit Message

Waiman Long Jan. 17, 2024, 4:35 p.m. UTC 
From: Frederic Weisbecker <frederic@kernel.org>

Currently the interface to toggle callbacks offloading state only takes
a single CPU per call. Now driving RCU NOCB through cpusets requires
to be able to change the offloading state of a whole set of CPUs.

To make it easier, extend the (de-)offloading interface to support a
cpumask.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Phil Auld <pauld@redhat.com>
Cc: Nicolas Saenz Julienne <nsaenz@kernel.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Waiman Long <longman@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
---
 include/linux/rcupdate.h |   9 ++--
 kernel/rcu/rcutorture.c  |   4 +-
 kernel/rcu/tree_nocb.h   | 102 ++++++++++++++++++++++++++-------------
 3 files changed, 76 insertions(+), 39 deletions(-)
diff mbox series

Patch

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 0746b1b0b663..b649344075d2 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -142,13 +142,14 @@  static inline void rcu_irq_work_resched(void) { }
 
 #ifdef CONFIG_RCU_NOCB_CPU
 void rcu_init_nohz(void);
-int rcu_nocb_cpu_offload(int cpu);
-int rcu_nocb_cpu_deoffload(int cpu);
+int rcu_nocb_cpumask_update(const struct cpumask *cpumask, bool offload);
 void rcu_nocb_flush_deferred_wakeup(void);
 #else /* #ifdef CONFIG_RCU_NOCB_CPU */
 static inline void rcu_init_nohz(void) { }
-static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; }
-static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; }
+static inline int rcu_nocb_cpumask_update(const struct cpumask *cpumask, bool offload)
+{
+	return -EINVAL;
+}
 static inline void rcu_nocb_flush_deferred_wakeup(void) { }
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 7567ca8e743c..228a5488eb5e 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -2140,10 +2140,10 @@  static int rcu_nocb_toggle(void *arg)
 		r = torture_random(&rand);
 		cpu = (r >> 1) % (maxcpu + 1);
 		if (r & 0x1) {
-			rcu_nocb_cpu_offload(cpu);
+			rcu_nocb_cpumask_update(cpumask_of(cpu), true);
 			atomic_long_inc(&n_nocb_offload);
 		} else {
-			rcu_nocb_cpu_deoffload(cpu);
+			rcu_nocb_cpumask_update(cpumask_of(cpu), false);
 			atomic_long_inc(&n_nocb_deoffload);
 		}
 		toggle_delay = torture_random(&rand) % toggle_fuzz + toggle_interval;
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index 4efbf7333d4e..60b0a15ed6e2 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -1203,29 +1203,23 @@  static long rcu_nocb_rdp_deoffload(void *arg)
 	return 0;
 }
 
-int rcu_nocb_cpu_deoffload(int cpu)
+static int rcu_nocb_cpu_deoffload(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
 	int ret = 0;
 
-	cpus_read_lock();
-	mutex_lock(&rcu_state.barrier_mutex);
-	if (rcu_rdp_is_offloaded(rdp)) {
-		if (cpu_online(cpu)) {
-			ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp);
-			if (!ret)
-				cpumask_clear_cpu(cpu, rcu_nocb_mask);
-		} else {
-			pr_info("NOCB: Cannot CB-deoffload offline CPU %d\n", rdp->cpu);
-			ret = -EINVAL;
-		}
-	}
-	mutex_unlock(&rcu_state.barrier_mutex);
-	cpus_read_unlock();
+	if (cpu_is_offline(cpu))
+		return -EINVAL;
+
+	if (!rcu_rdp_is_offloaded(rdp))
+		return 0;
+
+	ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp);
+	if (!ret)
+		cpumask_clear_cpu(cpu, rcu_nocb_mask);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(rcu_nocb_cpu_deoffload);
 
 static long rcu_nocb_rdp_offload(void *arg)
 {
@@ -1236,12 +1230,6 @@  static long rcu_nocb_rdp_offload(void *arg)
 	struct rcu_data *rdp_gp = rdp->nocb_gp_rdp;
 
 	WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id());
-	/*
-	 * For now we only support re-offload, ie: the rdp must have been
-	 * offloaded on boot first.
-	 */
-	if (!rdp->nocb_gp_rdp)
-		return -EINVAL;
 
 	if (WARN_ON_ONCE(!rdp_gp->nocb_gp_kthread))
 		return -EINVAL;
@@ -1288,29 +1276,77 @@  static long rcu_nocb_rdp_offload(void *arg)
 	return 0;
 }
 
-int rcu_nocb_cpu_offload(int cpu)
+static int rcu_nocb_cpu_offload(int cpu)
 {
 	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-	int ret = 0;
+	int ret;
+
+	if (cpu_is_offline(cpu))
+		return -EINVAL;
+
+	if (rcu_rdp_is_offloaded(rdp))
+		return 0;
+
+	ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp);
+	if (!ret)
+		cpumask_set_cpu(cpu, rcu_nocb_mask);
+
+	return ret;
+}
+
+int rcu_nocb_cpumask_update(const struct cpumask *cpumask, bool offload)
+{
+	int cpu;
+	int err = 0;
+	int err_cpu;
+	cpumask_var_t saved_nocb_mask;
+
+	if (!alloc_cpumask_var(&saved_nocb_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	cpumask_copy(saved_nocb_mask, rcu_nocb_mask);
 
 	cpus_read_lock();
 	mutex_lock(&rcu_state.barrier_mutex);
-	if (!rcu_rdp_is_offloaded(rdp)) {
-		if (cpu_online(cpu)) {
-			ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp);
-			if (!ret)
-				cpumask_set_cpu(cpu, rcu_nocb_mask);
+	for_each_cpu(cpu, cpumask) {
+		if (offload) {
+			err = rcu_nocb_cpu_offload(cpu);
+			if (err < 0) {
+				err_cpu = cpu;
+				pr_err("NOCB: offload cpu %d failed (%d)\n", cpu, err);
+				break;
+			}
 		} else {
-			pr_info("NOCB: Cannot CB-offload offline CPU %d\n", rdp->cpu);
-			ret = -EINVAL;
+			err = rcu_nocb_cpu_deoffload(cpu);
+			if (err < 0) {
+				err_cpu = cpu;
+				pr_err("NOCB: deoffload cpu %d failed (%d)\n", cpu, err);
+				break;
+			}
+		}
+	}
+
+	/* Rollback in case of error */
+	if (err < 0) {
+		err_cpu = cpu;
+		for_each_cpu(cpu, cpumask) {
+			if (err_cpu == cpu)
+				break;
+			if (cpumask_test_cpu(cpu, saved_nocb_mask))
+				WARN_ON_ONCE(rcu_nocb_cpu_offload(cpu));
+			else
+				WARN_ON_ONCE(rcu_nocb_cpu_deoffload(cpu));
 		}
 	}
+
 	mutex_unlock(&rcu_state.barrier_mutex);
 	cpus_read_unlock();
 
-	return ret;
+	free_cpumask_var(saved_nocb_mask);
+
+	return err;
 }
-EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload);
+EXPORT_SYMBOL_GPL(rcu_nocb_cpumask_update);
 
 #ifdef CONFIG_RCU_LAZY
 static unsigned long