[PATCH] i386: Handle missing local APIC timer interrupts on C3 state

Whenever we see that a CPU is capable of C3 (during ACPI cstate init), we
disable local APIC timer and switch to using a broadcast from external timer
interrupt (IRQ 0). This is needed because Intel CPUs stop the local
APIC timer in C3.  This is currently only enabled for Intel CPUs.

Patch below adds the code for i386 and also the ACPI hunk.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

4 files changed, 102 insertions, 2 deletions

diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 2d8c6ce1ecda..acd3f1e34ca6 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -26,6 +26,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
 #include <linux/cpu.h>
+#include <linux/module.h>
 
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -37,10 +38,17 @@
 #include <asm/i8253.h>
 
 #include <mach_apic.h>
+#include <mach_ipi.h>
 
 #include "io_ports.h"
 
 /*
+ * cpu_mask that denotes the CPUs that needs timer interrupt coming in as
+ * IPIs in place of local APIC timers
+ */
+static cpumask_t timer_bcast_ipi;
+
+/*
  * Knob to control our willingness to enable the local APIC.
  */
 int enable_local_apic __initdata = 0; /* -1=force-disable, +1=force-enable */
@@ -931,11 +939,16 @@ void (*wait_timer_tick)(void) __devinitdata = wait_8254_wraparound;
 static void __setup_APIC_LVTT(unsigned int clocks)
 {
 	unsigned int lvtt_value, tmp_value, ver;
+	int cpu = smp_processor_id();
 
 	ver = GET_APIC_VERSION(apic_read(APIC_LVR));
 	lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR;
 	if (!APIC_INTEGRATED(ver))
 		lvtt_value |= SET_APIC_TIMER_BASE(APIC_TIMER_BASE_DIV);
+
+	if (cpu_isset(cpu, timer_bcast_ipi))
+		lvtt_value |= APIC_LVT_MASKED;
+
 	apic_write_around(APIC_LVTT, lvtt_value);
 
 	/*
@@ -1068,7 +1081,7 @@ void __devinit setup_secondary_APIC_clock(void)
 	setup_APIC_timer(calibration_result);
 }
 
-void __devinit disable_APIC_timer(void)
+void disable_APIC_timer(void)
 {
 	if (using_apic_timer) {
 		unsigned long v;
@@ -1080,7 +1093,10 @@ void __devinit disable_APIC_timer(void)
 
 void enable_APIC_timer(void)
 {
-	if (using_apic_timer) {
+	int cpu = smp_processor_id();
+
+	if (using_apic_timer &&
+	    !cpu_isset(cpu, timer_bcast_ipi)) {
 		unsigned long v;
 
 		v = apic_read(APIC_LVTT);
@@ -1088,6 +1104,32 @@ void enable_APIC_timer(void)
 	}
 }
 
+void switch_APIC_timer_to_ipi(void *cpumask)
+{
+	cpumask_t mask = *(cpumask_t *)cpumask;
+	int cpu = smp_processor_id();
+
+	if (cpu_isset(cpu, mask) &&
+	    !cpu_isset(cpu, timer_bcast_ipi)) {
+		disable_APIC_timer();
+		cpu_set(cpu, timer_bcast_ipi);
+	}
+}
+EXPORT_SYMBOL(switch_APIC_timer_to_ipi);
+
+void switch_ipi_to_APIC_timer(void *cpumask)
+{
+	cpumask_t mask = *(cpumask_t *)cpumask;
+	int cpu = smp_processor_id();
+
+	if (cpu_isset(cpu, mask) &&
+	    cpu_isset(cpu, timer_bcast_ipi)) {
+		cpu_clear(cpu, timer_bcast_ipi);
+		enable_APIC_timer();
+	}
+}
+EXPORT_SYMBOL(switch_ipi_to_APIC_timer);
+
 #undef APIC_DIVISOR
 
 /*
@@ -1152,6 +1194,38 @@ fastcall void smp_apic_timer_interrupt(struct pt_regs *regs)
 	irq_exit();
 }
 
+#ifndef CONFIG_SMP
+static void up_apic_timer_interrupt_call(struct pt_regs *regs)
+{
+	int cpu = smp_processor_id();
+
+	/*
+	 * the NMI deadlock-detector uses this.
+	 */
+	per_cpu(irq_stat, cpu).apic_timer_irqs++;
+
+	smp_local_timer_interrupt(regs);
+}
+#endif
+
+void smp_send_timer_broadcast_ipi(struct pt_regs *regs)
+{
+	cpumask_t mask;
+
+	cpus_and(mask, cpu_online_map, timer_bcast_ipi);
+	if (!cpus_empty(mask)) {
+#ifdef CONFIG_SMP
+		send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
+#else
+		/*
+		 * We can directly call the apic timer interrupt handler
+		 * in UP case. Minus all irq related functions
+		 */
+		up_apic_timer_interrupt_call(regs);
+#endif
+	}
+}
+
 int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index 41c5b2dc6200..a14d594bfbeb 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -302,6 +302,12 @@ irqreturn_t timer_interrupt(int irq, void *dev_id, struct pt_regs *regs)
 	do_timer_interrupt(irq, regs);
 
 	write_sequnlock(&xtime_lock);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	if (using_apic_timer)
+		smp_send_timer_broadcast_ipi(regs);
+#endif
+
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 807b0df308f1..cc049338e418 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -843,6 +843,15 @@ static int acpi_processor_power_verify(struct acpi_processor *pr)
 	unsigned int i;
 	unsigned int working = 0;
 
+#ifdef ARCH_APICTIMER_STOPS_ON_C3
+	struct cpuinfo_x86 *c = cpu_data + pr->id;
+	cpumask_t mask = cpumask_of_cpu(pr->id);
+
+	if (c->x86_vendor == X86_VENDOR_INTEL) {
+		on_each_cpu(switch_ipi_to_APIC_timer, &mask, 1, 1);
+	}
+#endif
+
 	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
 		struct acpi_processor_cx *cx = &pr->power.states[i];
 
@@ -857,6 +866,12 @@ static int acpi_processor_power_verify(struct acpi_processor *pr)
 
 		case ACPI_STATE_C3:
 			acpi_processor_power_verify_c3(pr, cx);
+#ifdef ARCH_APICTIMER_STOPS_ON_C3
+			if (c->x86_vendor == X86_VENDOR_INTEL) {
+				on_each_cpu(switch_APIC_timer_to_ipi,
+						&mask, 1, 1);
+			}
+#endif
 			break;
 		}
 
diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h
index 8c454aa58ac6..d30b8571573f 100644
--- a/include/asm-i386/apic.h
+++ b/include/asm-i386/apic.h
@@ -132,6 +132,11 @@ extern unsigned int nmi_watchdog;
 
 extern int disable_timer_pin_1;
 
+void smp_send_timer_broadcast_ipi(struct pt_regs *regs);
+void switch_APIC_timer_to_ipi(void *cpumask);
+void switch_ipi_to_APIC_timer(void *cpumask);
+#define ARCH_APICTIMER_STOPS_ON_C3	1
+
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }