[GIT pull] smp/core for v6.2-rc1

[Thomas Gleixner]

Linus,

please pull the latest smp/core branch from:

   git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git smp-core-2022-12-10

up to:  6f855b39e460: cpu/hotplug: Do not bail-out in DYING/STARTING sections

A small set of updates for CPU hotplug:

  - Prevent stale CPU hotplug state in the cpu_down() path which
    was detected by stress testing the sysfs interface

  - Ensure that the target CPU hotplug state for the boot CPU is
    CPUHP_ONLINE instead of the compile time init value CPUHP_OFFLINE.

  - Switch back to the original behaviour of warning when a CPU hotplug
    callback in the DYING/STARTING section returns an error code. Otherwise
    a buggy callback can leave the CPUs in an non recoverable state.

Thanks,

	tglx

------------------>
Phil Auld (2):
      cpu/hotplug: Make target_store() a nop when target == state
      cpu/hotplug: Set cpuhp target for boot cpu

Vincent Donnefort (1):
      cpu/hotplug: Do not bail-out in DYING/STARTING sections


 kernel/cpu.c | 61 +++++++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 44 insertions(+), 17 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index bbad5e375d3b..6c0a92ca6bb5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -663,21 +663,51 @@ static bool cpuhp_next_state(bool bringup,
 	return true;
 }
 
-static int cpuhp_invoke_callback_range(bool bringup,
-				       unsigned int cpu,
-				       struct cpuhp_cpu_state *st,
-				       enum cpuhp_state target)
+static int __cpuhp_invoke_callback_range(bool bringup,
+					 unsigned int cpu,
+					 struct cpuhp_cpu_state *st,
+					 enum cpuhp_state target,
+					 bool nofail)
 {
 	enum cpuhp_state state;
-	int err = 0;
+	int ret = 0;
 
 	while (cpuhp_next_state(bringup, &state, st, target)) {
+		int err;
+
 		err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL);
-		if (err)
+		if (!err)
+			continue;
+
+		if (nofail) {
+			pr_warn("CPU %u %s state %s (%d) failed (%d)\n",
+				cpu, bringup ? "UP" : "DOWN",
+				cpuhp_get_step(st->state)->name,
+				st->state, err);
+			ret = -1;
+		} else {
+			ret = err;
 			break;
+		}
 	}
 
-	return err;
+	return ret;
+}
+
+static inline int cpuhp_invoke_callback_range(bool bringup,
+					      unsigned int cpu,
+					      struct cpuhp_cpu_state *st,
+					      enum cpuhp_state target)
+{
+	return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false);
+}
+
+static inline void cpuhp_invoke_callback_range_nofail(bool bringup,
+						      unsigned int cpu,
+						      struct cpuhp_cpu_state *st,
+						      enum cpuhp_state target)
+{
+	__cpuhp_invoke_callback_range(bringup, cpu, st, target, true);
 }
 
 static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
@@ -999,7 +1029,6 @@ static int take_cpu_down(void *_param)
 	struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
 	enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
 	int err, cpu = smp_processor_id();
-	int ret;
 
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
@@ -1012,13 +1041,10 @@ static int take_cpu_down(void *_param)
 	 */
 	WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1));
 
-	/* Invoke the former CPU_DYING callbacks */
-	ret = cpuhp_invoke_callback_range(false, cpu, st, target);
-
 	/*
-	 * DYING must not fail!
+	 * Invoke the former CPU_DYING callbacks. DYING must not fail!
 	 */
-	WARN_ON_ONCE(ret);
+	cpuhp_invoke_callback_range_nofail(false, cpu, st, target);
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
@@ -1296,16 +1322,14 @@ void notify_cpu_starting(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
-	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
 	cpumask_set_cpu(cpu, &cpus_booted_once_mask);
-	ret = cpuhp_invoke_callback_range(true, cpu, st, target);
 
 	/*
 	 * STARTING must not fail!
 	 */
-	WARN_ON_ONCE(ret);
+	cpuhp_invoke_callback_range_nofail(true, cpu, st, target);
 }
 
 /*
@@ -2326,8 +2350,10 @@ static ssize_t target_store(struct device *dev, struct device_attribute *attr,
 
 	if (st->state < target)
 		ret = cpu_up(dev->id, target);
-	else
+	else if (st->state > target)
 		ret = cpu_down(dev->id, target);
+	else if (WARN_ON(st->target != target))
+		st->target = target;
 out:
 	unlock_device_hotplug();
 	return ret ? ret : count;
@@ -2688,6 +2714,7 @@ void __init boot_cpu_hotplug_init(void)
 	cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask);
 #endif
 	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
+	this_cpu_write(cpuhp_state.target, CPUHP_ONLINE);
 }
 
 /*