x86, clockevents: add C1E aware idle function

C1E on AMD machines is like C3 but without control from the OS. Up to
now we disabled the local apic timer for those machines as it stops
when the CPU goes into C1E. This excludes those machines from high
resolution timers / dynamic ticks, which hurts especially X2 based
laptops.

The current boot time C1E detection has another, more serious flaw
as well: some BIOSes do not enable C1E until the ACPI processor module
is loaded. This causes systems to stop working after that point.

To work nicely with C1E enabled machines we use a separate idle
function, which checks on idle entry whether C1E was enabled in the
Interrupt Pending Message MSR. This allows us to do timer broadcasting
for C1E and covers the late enablement of C1E as well.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 69 insertions, 83 deletions

diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c
index 4b99b1bdeb6..c44206e731d 100644
--- a/arch/x86/kernel/apic_32.c
+++ b/arch/x86/kernel/apic_32.c
@@ -64,9 +64,8 @@ static int enable_local_apic __initdata;
 
 /* Local APIC timer verification ok */
 static int local_apic_timer_verify_ok;
-/* Disable local APIC timer from the kernel commandline or via dmi quirk
-   or using CPU MSR check */
-int local_apic_timer_disabled;
+/* Disable local APIC timer from the kernel commandline or via dmi quirk */
+static int local_apic_timer_disabled;
 /* Local APIC timer works in C2 */
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 0633cfd0dc2..a5cc8447cf4 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -43,7 +43,7 @@
 #include <mach_ipi.h>
 #include <mach_apic.h>
 
-int disable_apic_timer __cpuinitdata;
+static int disable_apic_timer __cpuinitdata;
 static int apic_calibrate_pmtmr __initdata;
 int disable_apic;
 
@@ -422,32 +422,8 @@ void __init setup_boot_APIC_clock(void)
 	setup_APIC_timer();
 }
 
-/*
- * AMD C1E enabled CPUs have a real nasty problem: Some BIOSes set the
- * C1E flag only in the secondary CPU, so when we detect the wreckage
- * we already have enabled the boot CPU local apic timer. Check, if
- * disable_apic_timer is set and the DUMMY flag is cleared. If yes,
- * set the DUMMY flag again and force the broadcast mode in the
- * clockevents layer.
- */
-static void __cpuinit check_boot_apic_timer_broadcast(void)
-{
-	if (!disable_apic_timer ||
-	    (lapic_clockevent.features & CLOCK_EVT_FEAT_DUMMY))
-		return;
-
-	printk(KERN_INFO "AMD C1E detected late. Force timer broadcast.\n");
-	lapic_clockevent.features |= CLOCK_EVT_FEAT_DUMMY;
-
-	local_irq_enable();
-	clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
-			   &boot_cpu_physical_apicid);
-	local_irq_disable();
-}
-
 void __cpuinit setup_secondary_APIC_clock(void)
 {
-	check_boot_apic_timer_broadcast();
 	setup_APIC_timer();
 }
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e76b49e7a91..acc891ae590 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -24,31 +24,6 @@
 extern void vide(void);
 __asm__(".align 4\nvide: ret");
 
-#ifdef CONFIG_X86_LOCAL_APIC
-
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-
-	if (c->x86 < 0x0F)
-		return 0;
-
-	/* Family 0x0f models < rev F do not have this MSR */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
-
-	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-		if (smp_processor_id() != boot_cpu_physical_apicid)
-			printk(KERN_INFO "AMD C1E detected late. "
-			       "Force timer broadcast.\n");
-		return 1;
-	}
-	return 0;
-}
-#endif
-
 int force_mwait __cpuinitdata;
 
 static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
@@ -285,11 +260,6 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			num_cache_leaves = 3;
 	}
 
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (amd_apic_timer_broken(c))
-		local_apic_timer_disabled = 1;
-#endif
-
 	/* K6s reports MCEs but don't actually have all the MSRs */
 	if (c->x86 < 6)
 		clear_cpu_cap(c, X86_FEATURE_MCE);
diff --git a/arch/x86/kernel/cpu/amd_64.c b/arch/x86/kernel/cpu/amd_64.c
index f5fc161d8f2..f8d20588bde 100644
--- a/arch/x86/kernel/cpu/amd_64.c
+++ b/arch/x86/kernel/cpu/amd_64.c
@@ -110,28 +110,6 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
 #endif
 }
 
-/* AMD systems with C1E don't have a working lAPIC timer. Check for that. */
-static __cpuinit int amd_apic_timer_broken(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-
-	if (c->x86 < 0x0F)
-		return 0;
-
-	/* Family 0x0f models < rev F do not have this MSR */
-	if (c->x86 == 0x0f && c->x86_model < 0x40)
-		return 0;
-
-	rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
-	if (lo & K8_INTP_C1E_ACTIVE_MASK) {
-		if (smp_processor_id() != boot_cpu_physical_apicid)
-			printk(KERN_INFO "AMD C1E detected late. "
-			       "Force timer broadcast.\n");
-		return 1;
-	}
-	return 0;
-}
-
 void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 {
 	early_init_amd_mc(c);
@@ -212,9 +190,6 @@ void __cpuinit init_amd(struct cpuinfo_x86 *c)
 	if (c->x86 == 0x10)
 		amd_enable_pci_ext_cfg(c);
 
-	if (amd_apic_timer_broken(c))
-		disable_apic_timer = 1;
-
 	if (c == &boot_cpu_data && c->x86 >= 0xf && c->x86 <= 0x11) {
 		unsigned long long tseg;
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9fea14607df..68ad3539b14 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/pm.h>
+#include <linux/clockchips.h>
 
 struct kmem_cache *task_xstate_cachep;
 
@@ -219,6 +220,68 @@ static int __cpuinit mwait_usable(const struct cpuinfo_x86 *c)
 	return (edx & MWAIT_EDX_C1);
 }
 
+/*
+ * Check for AMD CPUs, which have potentially C1E support
+ */
+static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
+{
+	if (c->x86_vendor != X86_VENDOR_AMD)
+		return 0;
+
+	if (c->x86 < 0x0F)
+		return 0;
+
+	/* Family 0x0f models < rev F do not have C1E */
+	if (c->x86 == 0x0f && c->x86_model < 0x40)
+		return 0;
+
+	return 1;
+}
+
+/*
+ * C1E aware idle routine. We check for C1E active in the interrupt
+ * pending message MSR. If we detect C1E, then we handle it the same
+ * way as C3 power states (local apic timer and TSC stop)
+ */
+static void c1e_idle(void)
+{
+	static cpumask_t c1e_mask = CPU_MASK_NONE;
+	static int c1e_detected;
+
+	if (need_resched())
+		return;
+
+	if (!c1e_detected) {
+		u32 lo, hi;
+
+		rdmsr(MSR_K8_INT_PENDING_MSG, lo, hi);
+		if (lo & K8_INTP_C1E_ACTIVE_MASK) {
+			c1e_detected = 1;
+			mark_tsc_unstable("TSC halt in C1E");
+			printk(KERN_INFO "System has C1E enabled\n");
+		}
+	}
+
+	if (c1e_detected) {
+		int cpu = smp_processor_id();
+
+		if (!cpu_isset(cpu, c1e_mask)) {
+			cpu_set(cpu, c1e_mask);
+			/* Force broadcast so ACPI can not interfere */
+			clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_FORCE,
+					   &cpu);
+			printk(KERN_INFO "Switch to broadcast mode on CPU%d\n",
+			       cpu);
+		}
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
+		default_idle();
+		local_irq_disable();
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+		local_irq_enable();
+	} else
+		default_idle();
+}
+
 void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_SMP
@@ -236,6 +299,9 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		 */
 		printk(KERN_INFO "using mwait in idle threads.\n");
 		pm_idle = mwait_idle;
+	} else if (check_c1e_idle(c)) {
+		printk(KERN_INFO "using C1E aware idle routine\n");
+		pm_idle = c1e_idle;
 	} else
 		pm_idle = default_idle;
 }