1 files changed, 41 insertions, 21 deletions

diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 375b33ecafa2..935bc6562fa4 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -27,6 +27,7 @@
 #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>
@@ -146,31 +147,43 @@ static int register_stop_handler(void)
 
 static void native_stop_other_cpus(int wait)
 {
-	unsigned long flags;
-	unsigned long timeout;
+	unsigned int cpu = smp_processor_id();
+	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 */
+	if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1)
+		return;
 
 	/*
-	 * 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;
+	cpumask_copy(&cpus_stop_mask, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &cpus_stop_mask);
 
+	if (!cpumask_empty(&cpus_stop_mask)) {
 		/* sync above data before sending IRQ */
 		wmb();
 
@@ -183,12 +196,12 @@ 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
@@ -200,7 +213,8 @@ static void native_stop_other_cpus(int wait)
 
 			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 +222,7 @@ 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 +230,12 @@ 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);
 }
 
 /*