1 files changed, 193 insertions, 176 deletions

diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 8f75893a646..be8e1bde07a 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -1,8 +1,8 @@
 /*
  *	Intel SMP support routines.
  *
- *	(c) 1995 Alan Cox, Building #3 <alan@redhat.com>
- *	(c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
+ *	(c) 1995 Alan Cox, Building #3 <alan@lxorguk.ukuu.org.uk>
+ *	(c) 1998-99, 2000, 2009 Ingo Molnar <mingo@redhat.com>
  *      (c) 2002,2003 Andi Kleen, SuSE Labs.
  *
  *	i386 and x86_64 integration by Glauber Costa <gcosta@redhat.com>
@@ -16,18 +16,21 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/spinlock.h>
+#include <linux/export.h>
 #include <linux/kernel_stat.h>
 #include <linux/mc146818rtc.h>
 #include <linux/cache.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/gfp.h>
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
-#include <mach_ipi.h>
-#include <mach_apic.h>
+#include <asm/apic.h>
+#include <asm/nmi.h>
+#include <asm/trace/irq_vectors.h>
 /*
  *	Some notes on x86 processor bugs affecting SMP operation:
  *
@@ -107,6 +110,9 @@
  *	about nothing of note with C stepping upwards.
  */
 
+static atomic_t stopping_cpu = ATOMIC_INIT(-1);
+static bool smp_no_nmi_ipi = false;
+
 /*
  * this function sends a 'reschedule' IPI to another CPU.
  * it goes straight through and wastes no time serializing
@@ -118,226 +124,237 @@ static void native_smp_send_reschedule(int cpu)
 		WARN_ON(1);
 		return;
 	}
-	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
+	apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR);
 }
 
-/*
- * Structure and data for smp_call_function(). This is designed to minimise
- * static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	atomic_t started;
-	atomic_t finished;
-	int wait;
-};
-
-void lock_ipi_call_lock(void)
+void native_send_call_func_single_ipi(int cpu)
 {
-	spin_lock_irq(&call_lock);
+	apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR);
 }
 
-void unlock_ipi_call_lock(void)
+void native_send_call_func_ipi(const struct cpumask *mask)
 {
-	spin_unlock_irq(&call_lock);
-}
+	cpumask_var_t allbutself;
 
-static struct call_data_struct *call_data;
-
-static void __smp_call_function(void (*func) (void *info), void *info,
-				int nonatomic, int wait)
-{
-	struct call_data_struct data;
-	int cpus = num_online_cpus() - 1;
-
-	if (!cpus)
+	if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
+		apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
 		return;
-
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	mb();
-
-	/* Send a message to all other CPUs and wait for them to respond */
-	send_IPI_allbutself(CALL_FUNCTION_VECTOR);
-
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-}
-
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.  Must not include the current cpu.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
-  * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-static int
-native_smp_call_function_mask(cpumask_t mask,
-			      void (*func)(void *), void *info,
-			      int wait)
-{
-	struct call_data_struct data;
-	cpumask_t allbutself;
-	int cpus;
-
-	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
-
-	/* Holding any lock stops cpus from going down. */
-	spin_lock(&call_lock);
-
-	allbutself = cpu_online_map;
-	cpu_clear(smp_processor_id(), allbutself);
-
-	cpus_and(mask, mask, allbutself);
-	cpus = cpus_weight(mask);
-
-	if (!cpus) {
-		spin_unlock(&call_lock);
-		return 0;
 	}
 
-	data.func = func;
-	data.info = info;
-	atomic_set(&data.started, 0);
-	data.wait = wait;
-	if (wait)
-		atomic_set(&data.finished, 0);
-
-	call_data = &data;
-	wmb();
+	cpumask_copy(allbutself, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), allbutself);
 
-	/* Send a message to other CPUs */
-	if (cpus_equal(mask, allbutself))
-		send_IPI_allbutself(CALL_FUNCTION_VECTOR);
+	if (cpumask_equal(mask, allbutself) &&
+	    cpumask_equal(cpu_online_mask, cpu_callout_mask))
+		apic->send_IPI_allbutself(CALL_FUNCTION_VECTOR);
 	else
-		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+		apic->send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
 
-	/* Wait for response */
-	while (atomic_read(&data.started) != cpus)
-		cpu_relax();
-
-	if (wait)
-		while (atomic_read(&data.finished) != cpus)
-			cpu_relax();
-	spin_unlock(&call_lock);
-
-	return 0;
+	free_cpumask_var(allbutself);
 }
 
-static void stop_this_cpu(void *dummy)
+static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
 {
-	local_irq_disable();
-	/*
-	 * Remove this CPU:
-	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
-	disable_local_APIC();
-	if (hlt_works(smp_processor_id()))
-		for (;;) halt();
-	for (;;);
+	/* 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.
  */
 
-static void native_smp_send_stop(void)
+asmlinkage __visible void smp_reboot_interrupt(void)
+{
+	ack_APIC_irq();
+	irq_enter();
+	stop_this_cpu(NULL);
+	irq_exit();
+}
+
+static void native_stop_other_cpus(int wait)
 {
-	int nolock;
 	unsigned long flags;
+	unsigned long timeout;
 
 	if (reboot_force)
 		return;
 
-	/* Don't deadlock on the call lock in panic */
-	nolock = !spin_trylock(&call_lock);
+	/*
+	 * Use an own vector here because smp_call_function
+	 * does lots of things not suitable in a panic situation.
+	 */
+
+	/*
+	 * 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);
+
+		/*
+		 * Don't wait longer than a second if the caller
+		 * didn't ask us to wait.
+		 */
+		timeout = USEC_PER_SEC;
+		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) && (!smp_no_nmi_ipi))  {
+		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);
-	__smp_call_function(stop_this_cpu, NULL, 0, 0);
-	if (!nolock)
-		spin_unlock(&call_lock);
 	disable_local_APIC();
 	local_irq_restore(flags);
 }
 
 /*
- * Reschedule call back. Nothing to do,
- * all the work is done automatically when
- * we return from the interrupt.
+ * Reschedule call back.
  */
-void smp_reschedule_interrupt(struct pt_regs *regs)
+static inline void __smp_reschedule_interrupt(void)
 {
-	ack_APIC_irq();
-#ifdef CONFIG_X86_32
-	__get_cpu_var(irq_stat).irq_resched_count++;
-#else
-	add_pda(irq_resched_count, 1);
-#endif
+	inc_irq_stat(irq_resched_count);
+	scheduler_ipi();
 }
 
-void smp_call_function_interrupt(struct pt_regs *regs)
+__visible void smp_reschedule_interrupt(struct pt_regs *regs)
 {
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
+	ack_APIC_irq();
+	__smp_reschedule_interrupt();
+	/*
+	 * KVM uses this interrupt to force a cpu out of guest mode
+	 */
+}
 
+static inline void smp_entering_irq(void)
+{
 	ack_APIC_irq();
+	irq_enter();
+}
+
+__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+{
 	/*
-	 * Notify initiating CPU that I've grabbed the data and am
-	 * about to execute the function
+	 * Need to call irq_enter() before calling the trace point.
+	 * __smp_reschedule_interrupt() calls irq_enter/exit() too (in
+	 * scheduler_ipi(). This is OK, since those functions are allowed
+	 * to nest.
 	 */
-	mb();
-	atomic_inc(&call_data->started);
+	smp_entering_irq();
+	trace_reschedule_entry(RESCHEDULE_VECTOR);
+	__smp_reschedule_interrupt();
+	trace_reschedule_exit(RESCHEDULE_VECTOR);
+	exiting_irq();
 	/*
-	 * At this point the info structure may be out of scope unless wait==1
+	 * KVM uses this interrupt to force a cpu out of guest mode
 	 */
-	irq_enter();
-	(*func)(info);
-#ifdef CONFIG_X86_32
-	__get_cpu_var(irq_stat).irq_call_count++;
-#else
-	add_pda(irq_call_count, 1);
-#endif
-	irq_exit();
+}
 
-	if (wait) {
-		mb();
-		atomic_inc(&call_data->finished);
-	}
+static inline void __smp_call_function_interrupt(void)
+{
+	generic_smp_call_function_interrupt();
+	inc_irq_stat(irq_call_count);
 }
 
+__visible void smp_call_function_interrupt(struct pt_regs *regs)
+{
+	smp_entering_irq();
+	__smp_call_function_interrupt();
+	exiting_irq();
+}
+
+__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
+{
+	smp_entering_irq();
+	trace_call_function_entry(CALL_FUNCTION_VECTOR);
+	__smp_call_function_interrupt();
+	trace_call_function_exit(CALL_FUNCTION_VECTOR);
+	exiting_irq();
+}
+
+static inline void __smp_call_function_single_interrupt(void)
+{
+	generic_smp_call_function_single_interrupt();
+	inc_irq_stat(irq_call_count);
+}
+
+__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
+{
+	smp_entering_irq();
+	__smp_call_function_single_interrupt();
+	exiting_irq();
+}
+
+__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+{
+	smp_entering_irq();
+	trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
+	__smp_call_function_single_interrupt();
+	trace_call_function_single_exit(CALL_FUNCTION_SINGLE_VECTOR);
+	exiting_irq();
+}
+
+static int __init nonmi_ipi_setup(char *str)
+{
+	smp_no_nmi_ipi = true;
+	return 1;
+}
+
+__setup("nonmi_ipi", nonmi_ipi_setup);
+
 struct smp_ops smp_ops = {
-	.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
-	.smp_prepare_cpus = native_smp_prepare_cpus,
-	.cpu_up = native_cpu_up,
-	.smp_cpus_done = native_smp_cpus_done,
-
-	.smp_send_stop = native_smp_send_stop,
-	.smp_send_reschedule = native_smp_send_reschedule,
-	.smp_call_function_mask = native_smp_call_function_mask,
+	.smp_prepare_boot_cpu	= native_smp_prepare_boot_cpu,
+	.smp_prepare_cpus	= native_smp_prepare_cpus,
+	.smp_cpus_done		= native_smp_cpus_done,
+
+	.stop_other_cpus	= native_stop_other_cpus,
+	.smp_send_reschedule	= native_smp_send_reschedule,
+
+	.cpu_up			= native_cpu_up,
+	.cpu_die		= native_cpu_die,
+	.cpu_disable		= native_cpu_disable,
+	.play_dead		= native_play_dead,
+
+	.send_call_func_ipi	= native_send_call_func_ipi,
+	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);
-