Merge remote branch 'tip/auto-latest'

13 files changed, 247 insertions, 63 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index acda512da2e2..4877a8c8ee16 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -151,4 +151,11 @@ config HAVE_MIXED_BREAKPOINTS_REGS
 config HAVE_USER_RETURN_NOTIFIER
 	bool
 
+config HAVE_PERF_EVENTS_NMI
+	bool
+	help
+	  System hardware can generate an NMI using the perf event
+	  subsystem.  Also has support for calculating CPU cycle events
+	  to determine how many clock cycles in a given period.
+
 source "kernel/gcov/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 981bdf2dd1af..fc847b4ba274 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -55,6 +55,7 @@ config X86
 	select HAVE_HW_BREAKPOINT
 	select HAVE_MIXED_BREAKPOINTS_REGS
 	select PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI
 	select ANON_INODES
 	select HAVE_ARCH_KMEMCHECK
 	select HAVE_USER_RETURN_NOTIFIER
diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index c74a2eebe570..a69b1ac9eaf8 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -55,7 +55,6 @@ extern unsigned long apbt_quick_calibrate(void);
 extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu);
 extern void apbt_setup_secondary_clock(void);
 extern unsigned int boot_cpu_id;
-extern int disable_apbt_percpu;
 
 extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint);
 extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr);
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 451d30e7f62d..16350740edf6 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -13,6 +13,32 @@
 extern int pci_mrst_init(void);
 int __init sfi_parse_mrtc(struct sfi_table_header *table);
 
+/*
+ * Medfield is the follow-up of Moorestown, it combines two chip solution into
+ * one. Other than that it also added always-on and constant tsc and lapic
+ * timers. Medfield is the platform name, and the chip name is called Penwell
+ * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be
+ * identified via MSRs.
+ */
+enum mrst_cpu_type {
+	MRST_CPU_CHIP_LINCROFT = 1,
+	MRST_CPU_CHIP_PENWELL,
+};
+
+extern enum mrst_cpu_type __mrst_cpu_chip;
+static enum mrst_cpu_type mrst_identify_cpu(void)
+{
+	return __mrst_cpu_chip;
+}
+
+enum mrst_timer_options {
+	MRST_TIMER_DEFAULT,
+	MRST_TIMER_APBT_ONLY,
+	MRST_TIMER_LAPIC_APBT,
+};
+
+extern enum mrst_timer_options mrst_timer_options;
+
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX	8
 
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 93da9c3f3341..932f0f86b4b7 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu);
 
 extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
 extern int check_nmi_watchdog(void);
+#if !defined(CONFIG_LOCKUP_DETECTOR)
 extern int nmi_watchdog_enabled;
+#endif
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index a35347501d36..8dd77800ff5d 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -43,10 +43,11 @@
 
 #include <asm/fixmap.h>
 #include <asm/apb_timer.h>
+#include <asm/mrst.h>
 
 #define APBT_MASK			CLOCKSOURCE_MASK(32)
 #define APBT_SHIFT			22
-#define APBT_CLOCKEVENT_RATING		150
+#define APBT_CLOCKEVENT_RATING		110
 #define APBT_CLOCKSOURCE_RATING		250
 #define APBT_MIN_DELTA_USEC		200
 
@@ -83,8 +84,6 @@ struct apbt_dev {
 	char name[10];
 };
 
-int disable_apbt_percpu __cpuinitdata;
-
 static DEFINE_PER_CPU(struct apbt_dev, cpu_apbt_dev);
 
 #ifdef CONFIG_SMP
@@ -195,29 +194,6 @@ static struct clock_event_device apbt_clockevent = {
 };
 
 /*
- * if user does not want to use per CPU apb timer, just give it a lower rating
- * than local apic timer and skip the late per cpu timer init.
- */
-static inline int __init setup_x86_mrst_timer(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	if (strcmp("apbt_only", arg) == 0)
-		disable_apbt_percpu = 0;
-	else if (strcmp("lapic_and_apbt", arg) == 0)
-		disable_apbt_percpu = 1;
-	else {
-		pr_warning("X86 MRST timer option %s not recognised"
-			   " use x86_mrst_timer=apbt_only or lapic_and_apbt\n",
-			   arg);
-		return -EINVAL;
-	}
-	return 0;
-}
-__setup("x86_mrst_timer=", setup_x86_mrst_timer);
-
-/*
  * start count down from 0xffff_ffff. this is done by toggling the enable bit
  * then load initial load count to ~0.
  */
@@ -335,7 +311,7 @@ static int __init apbt_clockevent_register(void)
 	adev->num = smp_processor_id();
 	memcpy(&adev->evt, &apbt_clockevent, sizeof(struct clock_event_device));
 
-	if (disable_apbt_percpu) {
+	if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
 		apbt_clockevent.rating = APBT_CLOCKEVENT_RATING - 100;
 		global_clock_event = &adev->evt;
 		printk(KERN_DEBUG "%s clockevent registered as global\n",
@@ -429,7 +405,8 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
 static __init int apbt_late_init(void)
 {
-	if (disable_apbt_percpu || !apb_timer_block_enabled)
+	if (mrst_timer_options == MRST_TIMER_LAPIC_APBT ||
+		!apb_timer_block_enabled)
 		return 0;
 	/* This notifier should be called after workqueue is ready */
 	hotcpu_notifier(apbt_cpuhp_notify, -20);
@@ -450,6 +427,8 @@ static void apbt_set_mode(enum clock_event_mode mode,
 	int timer_num;
 	struct apbt_dev *adev = EVT_TO_APBT_DEV(evt);
 
+	BUG_ON(!apbt_virt_address);
+
 	timer_num = adev->num;
 	pr_debug("%s CPU %d timer %d mode=%d\n",
 		 __func__, first_cpu(*evt->cpumask), timer_num, mode);
@@ -676,7 +655,7 @@ void __init apbt_time_init(void)
 	}
 #ifdef CONFIG_SMP
 	/* kernel cmdline disable apb timer, so we will use lapic timers */
-	if (disable_apbt_percpu) {
+	if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
 		printk(KERN_INFO "apbt: disabled per cpu timer\n");
 		return;
 	}
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 565c1bfc507d..910f20b457c4 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -2,7 +2,12 @@
 # Makefile for local APIC drivers and for the IO-APIC code
 #
 
-obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o nmi.o
+obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o
+ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y)
+obj-$(CONFIG_X86_LOCAL_APIC)	+= nmi.o
+endif
+obj-$(CONFIG_HARDLOCKUP_DETECTOR)	+= hw_nmi.o
+
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_SMP)		+= ipi.o
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
new file mode 100644
index 000000000000..cefd6942f0e9
--- /dev/null
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -0,0 +1,107 @@
+/*
+ *  HW NMI watchdog support
+ *
+ *  started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
+ *
+ *  Arch specific calls to support NMI watchdog
+ *
+ *  Bits copied from original nmi.c file
+ *
+ */
+#include <asm/apic.h>
+
+#include <linux/cpumask.h>
+#include <linux/kdebug.h>
+#include <linux/notifier.h>
+#include <linux/kprobes.h>
+#include <linux/nmi.h>
+#include <linux/module.h>
+
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+
+u64 hw_nmi_get_sample_period(void)
+{
+	return (u64)(cpu_khz) * 1000 * 60;
+}
+
+#ifdef ARCH_HAS_NMI_WATCHDOG
+void arch_trigger_all_cpu_backtrace(void)
+{
+	int i;
+
+	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
+
+	printk(KERN_INFO "sending NMI to all CPUs:\n");
+	apic->send_IPI_all(NMI_VECTOR);
+
+	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
+	for (i = 0; i < 10 * 1000; i++) {
+		if (cpumask_empty(to_cpumask(backtrace_mask)))
+			break;
+		mdelay(1);
+	}
+}
+
+static int __kprobes
+arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
+			 unsigned long cmd, void *__args)
+{
+	struct die_args *args = __args;
+	struct pt_regs *regs;
+	int cpu = smp_processor_id();
+
+	switch (cmd) {
+	case DIE_NMI:
+	case DIE_NMI_IPI:
+		break;
+
+	default:
+		return NOTIFY_DONE;
+	}
+
+	regs = args->regs;
+
+	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
+		static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
+
+		arch_spin_lock(&lock);
+		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
+		show_regs(regs);
+		dump_stack();
+		arch_spin_unlock(&lock);
+		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
+		return NOTIFY_STOP;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static __read_mostly struct notifier_block backtrace_notifier = {
+	.notifier_call          = arch_trigger_all_cpu_backtrace_handler,
+	.next                   = NULL,
+	.priority               = 1
+};
+
+static int __init register_trigger_all_cpu_backtrace(void)
+{
+	register_die_notifier(&backtrace_notifier);
+	return 0;
+}
+early_initcall(register_trigger_all_cpu_backtrace);
+#endif
+
+/* STUB calls to mimic old nmi_watchdog behaviour */
+#if defined(CONFIG_X86_LOCAL_APIC)
+unsigned int nmi_watchdog = NMI_NONE;
+EXPORT_SYMBOL(nmi_watchdog);
+void acpi_nmi_enable(void) { return; }
+void acpi_nmi_disable(void) { return; }
+#endif
+atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
+int unknown_nmi_panic;
+void cpu_nmi_set_wd_enabled(void) { return; }
+void stop_apic_nmi_watchdog(void *unused) { return; }
+void setup_apic_nmi_watchdog(void *unused) { return; }
+int __init check_nmi_watchdog(void) { return 0; }
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index 1edaf15c0b8e..a43f71cb30f8 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -401,13 +401,6 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 	int cpu = smp_processor_id();
 	int rc = 0;
 
-	/* check for other users first */
-	if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
-			== NOTIFY_STOP) {
-		rc = 1;
-		touched = 1;
-	}
-
 	sum = get_timer_irqs(cpu);
 
 	if (__get_cpu_var(nmi_touch)) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 68e4a6f2211e..c4c864ab5c86 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -576,6 +576,7 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c)
 	if (c->extended_cpuid_level >= 0x80000007)
 		c->x86_power = cpuid_edx(0x80000007);
 
+	init_scattered_cpuid_features(c);
 }
 
 static void __cpuinit identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -731,7 +732,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
 
 	get_model_name(c); /* Default name */
 
-	init_scattered_cpuid_features(c);
 	detect_nopl(c);
 }
 
diff --git a/arch/x86/kernel/mrst.c b/arch/x86/kernel/mrst.c
index e796448f0eb5..7ee4ed901baf 100644
--- a/arch/x86/kernel/mrst.c
+++ b/arch/x86/kernel/mrst.c
@@ -25,8 +25,34 @@
 #include <asm/i8259.h>
 #include <asm/apb_timer.h>
 
+/*
+ * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
+ * cmdline option x86_mrst_timer can be used to override the configuration
+ * to prefer one or the other.
+ * at runtime, there are basically three timer configurations:
+ * 1. per cpu apbt clock only
+ * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only
+ * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast.
+ *
+ * by default (without cmdline option), platform code first detects cpu type
+ * to see if we are on lincroft or penwell, then set up both lapic or apbt
+ * clocks accordingly.
+ * i.e. by default, medfield uses configuration #2, moorestown uses #1.
+ * config #3 is supported but not recommended on medfield.
+ *
+ * rating and feature summary:
+ * lapic (with C3STOP) --------- 100
+ * apbt (always-on) ------------ 110
+ * lapic (always-on,ARAT) ------ 150
+ */
+
+__cpuinitdata enum mrst_timer_options mrst_timer_options;
+
 static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM];
 static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM];
+enum mrst_cpu_type __mrst_cpu_chip;
+EXPORT_SYMBOL_GPL(__mrst_cpu_chip);
+
 int sfi_mtimer_num;
 
 struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
@@ -167,18 +193,6 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 	return 0;
 }
 
-/*
- * the secondary clock in Moorestown can be APBT or LAPIC clock, default to
- * APBT but cmdline option can also override it.
- */
-static void __cpuinit mrst_setup_secondary_clock(void)
-{
-	/* restore default lapic clock if disabled by cmdline */
-	if (disable_apbt_percpu)
-		return setup_secondary_APIC_clock();
-	apbt_setup_secondary_clock();
-}
-
 static unsigned long __init mrst_calibrate_tsc(void)
 {
 	unsigned long flags, fast_calibrate;
@@ -195,6 +209,21 @@ static unsigned long __init mrst_calibrate_tsc(void)
 
 void __init mrst_time_init(void)
 {
+	switch (mrst_timer_options) {
+	case MRST_TIMER_APBT_ONLY:
+		break;
+	case MRST_TIMER_LAPIC_APBT:
+		x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+		x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
+		break;
+	default:
+		if (!boot_cpu_has(X86_FEATURE_ARAT))
+			break;
+		x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+		x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
+		return;
+	}
+	/* we need at least one APB timer */
 	sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
 	pre_init_apic_IRQ0();
 	apbt_time_init();
@@ -205,16 +234,21 @@ void __init mrst_rtc_init(void)
 	sfi_table_parse(SFI_SIG_MRTC, NULL, NULL, sfi_parse_mrtc);
 }
 
-/*
- * if we use per cpu apb timer, the bootclock already setup. if we use lapic
- * timer and one apbt timer for broadcast, we need to set up lapic boot clock.
- */
-static void __init mrst_setup_boot_clock(void)
+void __cpuinit mrst_arch_setup(void)
 {
-	pr_info("%s: per cpu apbt flag %d \n", __func__, disable_apbt_percpu);
-	if (disable_apbt_percpu)
-		setup_boot_APIC_clock();
-};
+	if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
+		__mrst_cpu_chip = MRST_CPU_CHIP_PENWELL;
+	else if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x26)
+		__mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT;
+	else {
+		pr_err("Unknown Moorestown CPU (%d:%d), default to Lincroft\n",
+			boot_cpu_data.x86, boot_cpu_data.x86_model);
+		__mrst_cpu_chip = MRST_CPU_CHIP_LINCROFT;
+	}
+	pr_debug("Moorestown CPU %s identified\n",
+		(__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT) ?
+		"Lincroft" : "Penwell");
+}
 
 /*
  * Moorestown specific x86_init function overrides and early setup
@@ -226,11 +260,13 @@ void __init x86_mrst_early_setup(void)
 	x86_init.resources.reserve_resources = x86_init_noop;
 
 	x86_init.timers.timer_init = mrst_time_init;
-	x86_init.timers.setup_percpu_clockev = mrst_setup_boot_clock;
+	x86_init.timers.setup_percpu_clockev = x86_init_noop;
 
 	x86_init.irqs.pre_vector_init = x86_init_noop;
 
-	x86_cpuinit.setup_percpu_clockev = mrst_setup_secondary_clock;
+	x86_init.oem.arch_setup = mrst_arch_setup;
+
+	x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
 
 	x86_platform.calibrate_tsc = mrst_calibrate_tsc;
 	x86_init.pci.init = pci_mrst_init;
@@ -243,3 +279,26 @@ void __init x86_mrst_early_setup(void)
 	x86_init.mpparse.get_smp_config = x86_init_uint_noop;
 
 }
+
+/*
+ * if user does not want to use per CPU apb timer, just give it a lower rating
+ * than local apic timer and skip the late per cpu timer init.
+ */
+static inline int __init setup_x86_mrst_timer(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (strcmp("apbt_only", arg) == 0)
+		mrst_timer_options = MRST_TIMER_APBT_ONLY;
+	else if (strcmp("lapic_and_apbt", arg) == 0)
+		mrst_timer_options = MRST_TIMER_LAPIC_APBT;
+	else {
+		pr_warning("X86 MRST timer option %s not recognised"
+			   " use x86_mrst_timer=apbt_only or lapic_and_apbt\n",
+			   arg);
+		return -EINVAL;
+	}
+	return 0;
+}
+__setup("x86_mrst_timer=", setup_x86_mrst_timer);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e7e35219b32f..b460db8195fa 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -43,7 +43,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	}
 	return 0;
 }
-
 void free_thread_xstate(struct task_struct *tsk)
 {
 	fpu_free(&tsk->thread.fpu);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 142d70c74b02..c7d0ba79cc83 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -392,7 +392,13 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 		if (notify_die(DIE_NMI_IPI, "nmi_ipi", regs, reason, 2, SIGINT)
 								== NOTIFY_STOP)
 			return;
+
 #ifdef CONFIG_X86_LOCAL_APIC
+		if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
+							== NOTIFY_STOP)
+			return;
+
+#ifndef CONFIG_LOCKUP_DETECTOR
 		/*
 		 * Ok, so this is none of the documented NMI sources,
 		 * so it must be the NMI watchdog.
@@ -400,6 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 		if (nmi_watchdog_tick(regs, reason))
 			return;
 		if (!do_nmi_callback(regs, cpu))
+#endif /* !CONFIG_LOCKUP_DETECTOR */
 			unknown_nmi_error(reason, regs);
 #else
 		unknown_nmi_error(reason, regs);