rcu/x86: Provide early rcu_cpu_starting() callback

The x86/mtrr code does horrific things because hardware. It uses
stop_machine_from_inactive_cpu(), which does a wakeup (of the stopper
thread on another CPU), which uses RCU, all before the CPU is onlined.

RCU complains about this, because wakeups use RCU and RCU does
(rightfully) not consider offline CPUs for grace-periods.

Fix this by initializing RCU way early in the MTRR case.

Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Add !SMP support, per 0day Test Robot report. ]

arch/x86/kernel/cpu/mtrr/main.c

@@ -46,6 +46,7 @@
 #include <linux/pci.h>
 #include <linux/smp.h>
 #include <linux/syscore_ops.h>
+#include <linux/rcupdate.h>
 
 #include <asm/cpufeature.h>
 #include <asm/e820/api.h>
@@ -793,6 +794,9 @@ void mtrr_ap_init(void)
 
 	if (!use_intel() || mtrr_aps_delayed_init)
 		return;
+
+	rcu_cpu_starting(smp_processor_id());
+
 	/*
 	 * Ideally we should hold mtrr_mutex here to avoid mtrr entries
 	 * changed, but this routine will be called in cpu boot time,

include/linux/rcupdate.h

@@ -108,7 +108,6 @@ void rcu_sched_qs(void);
 void rcu_bh_qs(void);
 void rcu_check_callbacks(int user);
 void rcu_report_dead(unsigned int cpu);
-void rcu_cpu_starting(unsigned int cpu);
 void rcutree_migrate_callbacks(int cpu);
 
 #ifdef CONFIG_RCU_STALL_COMMON

include/linux/rcutiny.h

@@ -132,5 +132,6 @@ static inline void rcu_all_qs(void) { barrier(); }
 #define rcutree_offline_cpu      NULL
 #define rcutree_dead_cpu         NULL
 #define rcutree_dying_cpu        NULL
+static inline void rcu_cpu_starting(unsigned int cpu) { }
 
 #endif /* __LINUX_RCUTINY_H */

include/linux/rcutree.h

@@ -101,5 +101,6 @@ int rcutree_online_cpu(unsigned int cpu);
 int rcutree_offline_cpu(unsigned int cpu);
 int rcutree_dead_cpu(unsigned int cpu);
 int rcutree_dying_cpu(unsigned int cpu);
+void rcu_cpu_starting(unsigned int cpu);
 
 #endif /* __LINUX_RCUTREE_H */

kernel/rcu/tree.c

@@ -3665,6 +3665,8 @@ int rcutree_dead_cpu(unsigned int cpu)
 	return 0;
 }
 
+static DEFINE_PER_CPU(int, rcu_cpu_started);
+
 /*
  * Mark the specified CPU as being online so that subsequent grace periods
  * (both expedited and normal) will wait on it.  Note that this means that
@@ -3686,6 +3688,11 @@ void rcu_cpu_starting(unsigned int cpu)
 	struct rcu_node *rnp;
 	struct rcu_state *rsp;
 
+	if (per_cpu(rcu_cpu_started, cpu))
+		return;
+
+	per_cpu(rcu_cpu_started, cpu) = 1;
+
 	for_each_rcu_flavor(rsp) {
 		rdp = per_cpu_ptr(rsp->rda, cpu);
 		rnp = rdp->mynode;
@@ -3742,6 +3749,8 @@ void rcu_report_dead(unsigned int cpu)
 	preempt_enable();
 	for_each_rcu_flavor(rsp)
 		rcu_cleanup_dying_idle_cpu(cpu, rsp);
+
+	per_cpu(rcu_cpu_started, cpu) = 0;
 }
 
 /* Migrate the dead CPU's callbacks to the current CPU. */