1 files changed, 82 insertions, 36 deletions

diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 06db901fabe8..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -21,18 +21,20 @@
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
 #include <linux/gfp.h>
+#include <linux/kexec.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 #include <asm/apic.h>
+#include <asm/cpu.h>
 #include <asm/idtentry.h>
 #include <asm/nmi.h>
 #include <asm/mce.h>
 #include <asm/trace/irq_vectors.h>
 #include <asm/kexec.h>
-#include <asm/virtext.h>
+#include <asm/reboot.h>
 
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
@@ -122,7 +124,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
 		return NMI_HANDLED;
 
-	cpu_emergency_vmxoff();
+	cpu_emergency_disable_virtualization();
 	stop_this_cpu(NULL);
 
 	return NMI_HANDLED;
@@ -133,8 +135,8 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
  */
 DEFINE_IDTENTRY_SYSVEC(sysvec_reboot)
 {
-	ack_APIC_irq();
-	cpu_emergency_vmxoff();
+	apic_eoi();
+	cpu_emergency_disable_virtualization();
 	stop_this_cpu(NULL);
 }
 
@@ -146,34 +148,49 @@ static int register_stop_handler(void)
 
 static void native_stop_other_cpus(int wait)
 {
-	unsigned long flags;
-	unsigned long timeout;
+	unsigned int old_cpu, this_cpu;
+	unsigned long flags, timeout;
 
 	if (reboot_force)
 		return;
 
-	/*
-	 * Use an own vector here because smp_call_function
-	 * does lots of things not suitable in a panic situation.
-	 */
+	/* Only proceed if this is the first CPU to reach this code */
+	old_cpu = -1;
+	this_cpu = smp_processor_id();
+	if (!atomic_try_cmpxchg(&stopping_cpu, &old_cpu, this_cpu))
+		return;
+
+	/* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */
+	if (kexec_in_progress)
+		smp_kick_mwait_play_dead();
 
 	/*
-	 * We start by using the REBOOT_VECTOR irq.
-	 * The irq is treated as a sync point to allow critical
-	 * regions of code on other cpus to release their spin locks
-	 * and re-enable irqs.  Jumping straight to an NMI might
-	 * accidentally cause deadlocks with further shutdown/panic
-	 * code.  By syncing, we give the cpus up to one second to
-	 * finish their work before we force them off with the NMI.
+	 * 1) Send an IPI on the reboot vector to all other CPUs.
+	 *
+	 *    The other CPUs should react on it after leaving critical
+	 *    sections and re-enabling interrupts. They might still hold
+	 *    locks, but there is nothing which can be done about that.
+	 *
+	 * 2) Wait for all other CPUs to report that they reached the
+	 *    HLT loop in stop_this_cpu()
+	 *
+	 * 3) If #2 timed out send an NMI to the CPUs which did not
+	 *    yet report
+	 *
+	 * 4) Wait for all other CPUs to report that they reached the
+	 *    HLT loop in stop_this_cpu()
+	 *
+	 * #3 can obviously race against a CPU reaching the HLT loop late.
+	 * That CPU will have reported already and the "have all CPUs
+	 * reached HLT" condition will be true despite the fact that the
+	 * other CPU is still handling the NMI. Again, there is no
+	 * protection against that as "disabled" APICs still respond to
+	 * NMIs.
 	 */
-	if (num_online_cpus() > 1) {
-		/* did someone beat us here? */
-		if (atomic_cmpxchg(&stopping_cpu, -1, safe_smp_processor_id()) != -1)
-			return;
-
-		/* sync above data before sending IRQ */
-		wmb();
+	cpumask_copy(&cpus_stop_mask, cpu_online_mask);
+	cpumask_clear_cpu(this_cpu, &cpus_stop_mask);
 
+	if (!cpumask_empty(&cpus_stop_mask)) {
 		apic_send_IPI_allbutself(REBOOT_VECTOR);
 
 		/*
@@ -183,24 +200,24 @@ static void native_stop_other_cpus(int wait)
 		 * CPUs reach shutdown state.
 		 */
 		timeout = USEC_PER_SEC;
-		while (num_online_cpus() > 1 && timeout--)
+		while (!cpumask_empty(&cpus_stop_mask) && timeout--)
 			udelay(1);
 	}
 
 	/* if the REBOOT_VECTOR didn't work, try with the NMI */
-	if (num_online_cpus() > 1) {
+	if (!cpumask_empty(&cpus_stop_mask)) {
 		/*
 		 * If NMI IPI is enabled, try to register the stop handler
 		 * and send the IPI. In any case try to wait for the other
 		 * CPUs to stop.
 		 */
 		if (!smp_no_nmi_ipi && !register_stop_handler()) {
-			/* Sync above data before sending IRQ */
-			wmb();
+			unsigned int cpu;
 
 			pr_emerg("Shutting down cpus with NMI\n");
 
-			apic_send_IPI_allbutself(NMI_VECTOR);
+			for_each_cpu(cpu, &cpus_stop_mask)
+				__apic_send_IPI(cpu, NMI_VECTOR);
 		}
 		/*
 		 * Don't wait longer than 10 ms if the caller didn't
@@ -208,7 +225,7 @@ static void native_stop_other_cpus(int wait)
 		 * one or more CPUs do not reach shutdown state.
 		 */
 		timeout = USEC_PER_MSEC * 10;
-		while (num_online_cpus() > 1 && (wait || timeout--))
+		while (!cpumask_empty(&cpus_stop_mask) && (wait || timeout--))
 			udelay(1);
 	}
 
@@ -216,6 +233,12 @@ static void native_stop_other_cpus(int wait)
 	disable_local_APIC();
 	mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
 	local_irq_restore(flags);
+
+	/*
+	 * Ensure that the cpus_stop_mask cache lines are invalidated on
+	 * the other CPUs. See comment vs. SME in stop_this_cpu().
+	 */
+	cpumask_clear(&cpus_stop_mask);
 }
 
 /*
@@ -224,7 +247,7 @@ static void native_stop_other_cpus(int wait)
  */
 DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_reschedule_ipi)
 {
-	ack_APIC_irq();
+	apic_eoi();
 	trace_reschedule_entry(RESCHEDULE_VECTOR);
 	inc_irq_stat(irq_resched_count);
 	scheduler_ipi();
@@ -233,7 +256,7 @@ DEFINE_IDTENTRY_SYSVEC_SIMPLE(sysvec_reschedule_ipi)
 
 DEFINE_IDTENTRY_SYSVEC(sysvec_call_function)
 {
-	ack_APIC_irq();
+	apic_eoi();
 	trace_call_function_entry(CALL_FUNCTION_VECTOR);
 	inc_irq_stat(irq_call_count);
 	generic_smp_call_function_interrupt();
@@ -242,7 +265,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_call_function)
 
 DEFINE_IDTENTRY_SYSVEC(sysvec_call_function_single)
 {
-	ack_APIC_irq();
+	apic_eoi();
 	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
 	inc_irq_stat(irq_call_count);
 	generic_smp_call_function_single_interrupt();
@@ -263,13 +286,12 @@ struct smp_ops smp_ops = {
 	.smp_cpus_done		= native_smp_cpus_done,
 
 	.stop_other_cpus	= native_stop_other_cpus,
-#if defined(CONFIG_KEXEC_CORE)
+#if defined(CONFIG_CRASH_DUMP)
 	.crash_stop_other_cpus	= kdump_nmi_shootdown_cpus,
 #endif
 	.smp_send_reschedule	= native_smp_send_reschedule,
 
-	.cpu_up			= native_cpu_up,
-	.cpu_die		= native_cpu_die,
+	.kick_ap_alive		= native_kick_ap,
 	.cpu_disable		= native_cpu_disable,
 	.play_dead		= native_play_dead,
 
@@ -277,3 +299,27 @@ struct smp_ops smp_ops = {
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+	enum cpuhp_smt_control old = cpu_smt_control;
+	int ret;
+
+	/*
+	 * If SMT has been disabled and SMT siblings are in HLT, bring them back
+	 * online and offline them again so that they end up in MWAIT proper.
+	 *
+	 * Called with hotplug enabled.
+	 */
+	if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+		return 0;
+
+	ret = cpuhp_smt_enable();
+	if (ret)
+		return ret;
+
+	ret = cpuhp_smt_disable(old);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);