---

yaml
---
r: 305491
b: refs/heads/master
c: 7d007d2
h: refs/heads/master
i:
  305489: 4d7ac54
  305487: c72f232
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 5d2b86d90f7cc4a41316cef3d41560da6141f45c
+refs/heads/master: 7d007d21e539dbecb6942c5734e6649f720982cf

trunk/arch/x86/kernel/smp.c

@@ -29,6 +29,7 @@
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
  *
@@ -108,6 +109,8 @@
  *	about nothing of note with C stepping upwards.
  */
 
+static atomic_t stopping_cpu = ATOMIC_INIT(-1);
+
 /*
  * this function sends a 'reschedule' IPI to another CPU.
  * it goes straight through and wastes no time serializing
@@ -148,6 +151,17 @@ void native_send_call_func_ipi(const struct cpumask *mask)
 	free_cpumask_var(allbutself);
 }
 
+static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
+{
+	/* We are registered on stopping cpu too, avoid spurious NMI */
+	if (raw_smp_processor_id() == atomic_read(&stopping_cpu))
+		return NMI_HANDLED;
+
+	stop_this_cpu(NULL);
+
+	return NMI_HANDLED;
+}
+
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
  */
@@ -171,13 +185,25 @@ static void native_stop_other_cpus(int wait)
 	/*
 	 * Use an own vector here because smp_call_function
 	 * does lots of things not suitable in a panic situation.
-	 * On most systems we could also use an NMI here,
-	 * but there are a few systems around where NMI
-	 * is problematic so stay with an non NMI for now
-	 * (this implies we cannot stop CPUs spinning with irq off
-	 * currently)
+	 */
+
+	/*
+	 * 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.
 	 */
 	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();
+
 		apic->send_IPI_allbutself(REBOOT_VECTOR);
 
 		/*
@@ -188,7 +214,32 @@ static void native_stop_other_cpus(int wait)
 		while (num_online_cpus() > 1 && (wait || timeout--))
 			udelay(1);
 	}
+
+	/* if the REBOOT_VECTOR didn't work, try with the NMI */
+	if ((num_online_cpus() > 1))  {
+		if (register_nmi_handler(NMI_LOCAL, smp_stop_nmi_callback,
+					 NMI_FLAG_FIRST, "smp_stop"))
+			/* Note: we ignore failures here */
+			/* Hope the REBOOT_IRQ is good enough */
+			goto finish;
+
+		/* sync above data before sending IRQ */
+		wmb();
+
+		pr_emerg("Shutting down cpus with NMI\n");
+
+		apic->send_IPI_allbutself(NMI_VECTOR);
+
+		/*
+		 * Don't wait longer than a 10 ms if the caller
+		 * didn't ask us to wait.
+		 */
+		timeout = USEC_PER_MSEC * 10;
+		while (num_online_cpus() > 1 && (wait || timeout--))
+			udelay(1);
+	}
 
+finish:
 	local_irq_save(flags);
 	disable_local_APIC();
 	local_irq_restore(flags);