Merge branch 'linus' into x86/cleanups

Merge reason: We were on an older pre-rc1 base, move to almost-rc2.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

17 files changed, 575 insertions, 564 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index e5b27d8f1b47..28e5f5956042 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -258,13 +258,15 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_HT
 	unsigned bits;
+	int cpu = smp_processor_id();
 
 	bits = c->x86_coreid_bits;
-
 	/* Low order bits define the core id (index of core in socket) */
 	c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
 	/* Convert the initial APIC ID into the socket ID */
 	c->phys_proc_id = c->initial_apicid >> bits;
+	/* use socket ID also for last level cache */
+	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9fa33886c0d7..f1961c07af9a 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -108,7 +108,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
 	/* data */
 	[GDT_ENTRY_APMBIOS_BASE+2]	= { { { 0x0000ffff, 0x00409200 } } },
 
-	[GDT_ENTRY_ESPFIX_SS]		= { { { 0x00000000, 0x00c09200 } } },
+	[GDT_ENTRY_ESPFIX_SS]		= { { { 0x0000ffff, 0x00cf9200 } } },
 	[GDT_ENTRY_PERCPU]		= { { { 0x0000ffff, 0x00cf9200 } } },
 	GDT_STACK_CANARY_INIT
 #endif
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index 45004faf67ea..188a1ca5ad2b 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -1,11 +1,12 @@
-obj-y				=  mce.o therm_throt.o
+obj-y				=  mce.o
 
 obj-$(CONFIG_X86_NEW_MCE)	+= mce-severity.o
 obj-$(CONFIG_X86_OLD_MCE)	+= k7.o p4.o p6.o
 obj-$(CONFIG_X86_ANCIENT_MCE)	+= winchip.o p5.o
-obj-$(CONFIG_X86_MCE_P4THERMAL)	+= mce_intel.o
-obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel_64.o mce_intel.o
-obj-$(CONFIG_X86_MCE_AMD)	+= mce_amd_64.o
+obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel.o
+obj-$(CONFIG_X86_MCE_AMD)	+= mce_amd.o
 obj-$(CONFIG_X86_MCE_NONFATAL)	+= non-fatal.o
 obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
 obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
+
+obj-$(CONFIG_X86_THERMAL_VECTOR) += therm_throt.o
diff --git a/arch/x86/kernel/cpu/mcheck/k7.c b/arch/x86/kernel/cpu/mcheck/k7.c
index 89e510424152..b945d5dbc609 100644
--- a/arch/x86/kernel/cpu/mcheck/k7.c
+++ b/arch/x86/kernel/cpu/mcheck/k7.c
@@ -10,10 +10,9 @@
 
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 
-#include "mce.h"
-
 /* Machine Check Handler For AMD Athlon/Duron: */
 static void k7_machine_check(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index fabba15e4558..af425b83202b 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -44,7 +44,6 @@
 #include <asm/msr.h>
 
 #include "mce-internal.h"
-#include "mce.h"
 
 /* Handle unconfigured int18 (should never happen) */
 static void unexpected_machine_check(struct pt_regs *regs, long error_code)
@@ -57,7 +56,7 @@ static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 void (*machine_check_vector)(struct pt_regs *, long error_code) =
 						unexpected_machine_check;
 
-int				mce_disabled;
+int mce_disabled __read_mostly;
 
 #ifdef CONFIG_X86_NEW_MCE
 
@@ -76,21 +75,22 @@ DEFINE_PER_CPU(unsigned, mce_exception_count);
  *   2: SIGBUS or log uncorrected errors (if possible), log corrected errors
  *   3: never panic or SIGBUS, log all errors (for testing only)
  */
-static int			tolerant = 1;
-static int			banks;
-static u64			*bank;
-static unsigned long		notify_user;
-static int			rip_msr;
-static int			mce_bootlog = -1;
-static int			monarch_timeout = -1;
-static int			mce_panic_timeout;
-static int			mce_dont_log_ce;
-int				mce_cmci_disabled;
-int				mce_ignore_ce;
-int				mce_ser;
-
-static char			trigger[128];
-static char			*trigger_argv[2] = { trigger, NULL };
+static int			tolerant		__read_mostly = 1;
+static int			banks			__read_mostly;
+static u64			*bank			__read_mostly;
+static int			rip_msr			__read_mostly;
+static int			mce_bootlog		__read_mostly = -1;
+static int			monarch_timeout		__read_mostly = -1;
+static int			mce_panic_timeout	__read_mostly;
+static int			mce_dont_log_ce		__read_mostly;
+int				mce_cmci_disabled	__read_mostly;
+int				mce_ignore_ce		__read_mostly;
+int				mce_ser			__read_mostly;
+
+/* User mode helper program triggered by machine check event */
+static unsigned long		mce_need_notify;
+static char			mce_helper[128];
+static char			*mce_helper_argv[2] = { mce_helper, NULL };
 
 static unsigned long		dont_init_banks;
 
@@ -180,7 +180,7 @@ void mce_log(struct mce *mce)
 	wmb();
 
 	mce->finished = 1;
-	set_bit(0, &notify_user);
+	set_bit(0, &mce_need_notify);
 }
 
 static void print_mce(struct mce *m)
@@ -691,18 +691,21 @@ static atomic_t global_nwo;
  * in the entry order.
  * TBD double check parallel CPU hotunplug
  */
-static int mce_start(int no_way_out, int *order)
+static int mce_start(int *no_way_out)
 {
-	int nwo;
+	int order;
 	int cpus = num_online_cpus();
 	u64 timeout = (u64)monarch_timeout * NSEC_PER_USEC;
 
-	if (!timeout) {
-		*order = -1;
-		return no_way_out;
-	}
+	if (!timeout)
+		return -1;
 
-	atomic_add(no_way_out, &global_nwo);
+	atomic_add(*no_way_out, &global_nwo);
+	/*
+	 * global_nwo should be updated before mce_callin
+	 */
+	smp_wmb();
+	order = atomic_add_return(1, &mce_callin);
 
 	/*
 	 * Wait for everyone.
@@ -710,40 +713,43 @@ static int mce_start(int no_way_out, int *order)
 	while (atomic_read(&mce_callin) != cpus) {
 		if (mce_timed_out(&timeout)) {
 			atomic_set(&global_nwo, 0);
-			*order = -1;
-			return no_way_out;
+			return -1;
 		}
 		ndelay(SPINUNIT);
 	}
 
 	/*
-	 * Cache the global no_way_out state.
+	 * mce_callin should be read before global_nwo
 	 */
-	nwo = atomic_read(&global_nwo);
+	smp_rmb();
 
-	/*
-	 * Monarch starts executing now, the others wait.
-	 */
-	if (*order == 1) {
+	if (order == 1) {
+		/*
+		 * Monarch: Starts executing now, the others wait.
+		 */
 		atomic_set(&mce_executing, 1);
-		return nwo;
+	} else {
+		/*
+		 * Subject: Now start the scanning loop one by one in
+		 * the original callin order.
+		 * This way when there are any shared banks it will be
+		 * only seen by one CPU before cleared, avoiding duplicates.
+		 */
+		while (atomic_read(&mce_executing) < order) {
+			if (mce_timed_out(&timeout)) {
+				atomic_set(&global_nwo, 0);
+				return -1;
+			}
+			ndelay(SPINUNIT);
+		}
 	}
 
 	/*
-	 * Now start the scanning loop one by one
-	 * in the original callin order.
-	 * This way when there are any shared banks it will
-	 * be only seen by one CPU before cleared, avoiding duplicates.
+	 * Cache the global no_way_out state.
 	 */
-	while (atomic_read(&mce_executing) < *order) {
-		if (mce_timed_out(&timeout)) {
-			atomic_set(&global_nwo, 0);
-			*order = -1;
-			return no_way_out;
-		}
-		ndelay(SPINUNIT);
-	}
-	return nwo;
+	*no_way_out = atomic_read(&global_nwo);
+
+	return order;
 }
 
 /*
@@ -863,7 +869,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * check handler.
 	 */
 	int order;
-
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If tolerant is cranked up, we'll try anyway.
@@ -887,7 +892,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	if (!banks)
 		goto out;
 
-	order = atomic_add_return(1, &mce_callin);
 	mce_setup(&m);
 
 	m.mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
@@ -909,7 +913,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	 * This way we don't report duplicated events on shared banks
 	 * because the first one to see it will clear it.
 	 */
-	no_way_out = mce_start(no_way_out, &order);
+	order = mce_start(&no_way_out);
 	for (i = 0; i < banks; i++) {
 		__clear_bit(i, toclear);
 		if (!bank[i])
@@ -1113,12 +1117,12 @@ static void mcheck_timer(unsigned long data)
 		*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
 
 	t->expires = jiffies + *n;
-	add_timer(t);
+	add_timer_on(t, smp_processor_id());
 }
 
 static void mce_do_trigger(struct work_struct *work)
 {
-	call_usermodehelper(trigger, trigger_argv, NULL, UMH_NO_WAIT);
+	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
 }
 
 static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
@@ -1135,7 +1139,7 @@ int mce_notify_irq(void)
 
 	clear_thread_flag(TIF_MCE_NOTIFY);
 
-	if (test_and_clear_bit(0, &notify_user)) {
+	if (test_and_clear_bit(0, &mce_need_notify)) {
 		wake_up_interruptible(&mce_wait);
 
 		/*
@@ -1143,7 +1147,7 @@ int mce_notify_irq(void)
 		 * work_pending is always cleared before the function is
 		 * executed.
 		 */
-		if (trigger[0] && !work_pending(&mce_trigger_work))
+		if (mce_helper[0] && !work_pending(&mce_trigger_work))
 			schedule_work(&mce_trigger_work);
 
 		if (__ratelimit(&ratelimit))
@@ -1245,7 +1249,7 @@ static void mce_cpu_quirks(struct cpuinfo_x86 *c)
 		 * Various K7s with broken bank 0 around. Always disable
 		 * by default.
 		 */
-		 if (c->x86 == 6)
+		 if (c->x86 == 6 && banks > 0)
 			bank[0] = 0;
 	}
 
@@ -1282,8 +1286,7 @@ static void __cpuinit mce_ancient_init(struct cpuinfo_x86 *c)
 		return;
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
-		if (mce_p5_enabled())
-			intel_p5_mcheck_init(c);
+		intel_p5_mcheck_init(c);
 		break;
 	case X86_VENDOR_CENTAUR:
 		winchip_mcheck_init(c);
@@ -1318,7 +1321,7 @@ static void mce_init_timer(void)
 		return;
 	setup_timer(t, mcheck_timer, smp_processor_id());
 	t->expires = round_jiffies(jiffies + *n);
-	add_timer(t);
+	add_timer_on(t, smp_processor_id());
 }
 
 /*
@@ -1609,8 +1612,9 @@ static int mce_resume(struct sys_device *dev)
 static void mce_cpu_restart(void *data)
 {
 	del_timer_sync(&__get_cpu_var(mce_timer));
-	if (mce_available(&current_cpu_data))
-		mce_init();
+	if (!mce_available(&current_cpu_data))
+		return;
+	mce_init();
 	mce_init_timer();
 }
 
@@ -1620,6 +1624,26 @@ static void mce_restart(void)
 	on_each_cpu(mce_cpu_restart, NULL, 1);
 }
 
+/* Toggle features for corrected errors */
+static void mce_disable_ce(void *all)
+{
+	if (!mce_available(&current_cpu_data))
+		return;
+	if (all)
+		del_timer_sync(&__get_cpu_var(mce_timer));
+	cmci_clear();
+}
+
+static void mce_enable_ce(void *all)
+{
+	if (!mce_available(&current_cpu_data))
+		return;
+	cmci_reenable();
+	cmci_recheck();
+	if (all)
+		mce_init_timer();
+}
+
 static struct sysdev_class mce_sysclass = {
 	.suspend	= mce_suspend,
 	.shutdown	= mce_shutdown,
@@ -1659,9 +1683,9 @@ static ssize_t set_bank(struct sys_device *s, struct sysdev_attribute *attr,
 static ssize_t
 show_trigger(struct sys_device *s, struct sysdev_attribute *attr, char *buf)
 {
-	strcpy(buf, trigger);
+	strcpy(buf, mce_helper);
 	strcat(buf, "\n");
-	return strlen(trigger) + 1;
+	return strlen(mce_helper) + 1;
 }
 
 static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
@@ -1670,10 +1694,10 @@ static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
 	char *p;
 	int len;
 
-	strncpy(trigger, buf, sizeof(trigger));
-	trigger[sizeof(trigger)-1] = 0;
-	len = strlen(trigger);
-	p = strchr(trigger, '\n');
+	strncpy(mce_helper, buf, sizeof(mce_helper));
+	mce_helper[sizeof(mce_helper)-1] = 0;
+	len = strlen(mce_helper);
+	p = strchr(mce_helper, '\n');
 
 	if (*p)
 		*p = 0;
@@ -1681,6 +1705,52 @@ static ssize_t set_trigger(struct sys_device *s, struct sysdev_attribute *attr,
 	return len;
 }
 
+static ssize_t set_ignore_ce(struct sys_device *s,
+			     struct sysdev_attribute *attr,
+			     const char *buf, size_t size)
+{
+	u64 new;
+
+	if (strict_strtoull(buf, 0, &new) < 0)
+		return -EINVAL;
+
+	if (mce_ignore_ce ^ !!new) {
+		if (new) {
+			/* disable ce features */
+			on_each_cpu(mce_disable_ce, (void *)1, 1);
+			mce_ignore_ce = 1;
+		} else {
+			/* enable ce features */
+			mce_ignore_ce = 0;
+			on_each_cpu(mce_enable_ce, (void *)1, 1);
+		}
+	}
+	return size;
+}
+
+static ssize_t set_cmci_disabled(struct sys_device *s,
+				 struct sysdev_attribute *attr,
+				 const char *buf, size_t size)
+{
+	u64 new;
+
+	if (strict_strtoull(buf, 0, &new) < 0)
+		return -EINVAL;
+
+	if (mce_cmci_disabled ^ !!new) {
+		if (new) {
+			/* disable cmci */
+			on_each_cpu(mce_disable_ce, NULL, 1);
+			mce_cmci_disabled = 1;
+		} else {
+			/* enable cmci */
+			mce_cmci_disabled = 0;
+			on_each_cpu(mce_enable_ce, NULL, 1);
+		}
+	}
+	return size;
+}
+
 static ssize_t store_int_with_restart(struct sys_device *s,
 				      struct sysdev_attribute *attr,
 				      const char *buf, size_t size)
@@ -1693,6 +1763,7 @@ static ssize_t store_int_with_restart(struct sys_device *s,
 static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
 static SYSDEV_INT_ATTR(tolerant, 0644, tolerant);
 static SYSDEV_INT_ATTR(monarch_timeout, 0644, monarch_timeout);
+static SYSDEV_INT_ATTR(dont_log_ce, 0644, mce_dont_log_ce);
 
 static struct sysdev_ext_attribute attr_check_interval = {
 	_SYSDEV_ATTR(check_interval, 0644, sysdev_show_int,
@@ -1700,9 +1771,24 @@ static struct sysdev_ext_attribute attr_check_interval = {
 	&check_interval
 };
 
+static struct sysdev_ext_attribute attr_ignore_ce = {
+	_SYSDEV_ATTR(ignore_ce, 0644, sysdev_show_int, set_ignore_ce),
+	&mce_ignore_ce
+};
+
+static struct sysdev_ext_attribute attr_cmci_disabled = {
+	_SYSDEV_ATTR(cmci_disabled, 0644, sysdev_show_int, set_cmci_disabled),
+	&mce_cmci_disabled
+};
+
 static struct sysdev_attribute *mce_attrs[] = {
-	&attr_tolerant.attr, &attr_check_interval.attr, &attr_trigger,
+	&attr_tolerant.attr,
+	&attr_check_interval.attr,
+	&attr_trigger,
 	&attr_monarch_timeout.attr,
+	&attr_dont_log_ce.attr,
+	&attr_ignore_ce.attr,
+	&attr_cmci_disabled.attr,
 	NULL
 };
 
@@ -1712,7 +1798,7 @@ static cpumask_var_t mce_dev_initialized;
 static __cpuinit int mce_create_device(unsigned int cpu)
 {
 	int err;
-	int i;
+	int i, j;
 
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
@@ -1730,9 +1816,9 @@ static __cpuinit int mce_create_device(unsigned int cpu)
 		if (err)
 			goto error;
 	}
-	for (i = 0; i < banks; i++) {
+	for (j = 0; j < banks; j++) {
 		err = sysdev_create_file(&per_cpu(mce_dev, cpu),
-					&bank_attrs[i]);
+					&bank_attrs[j]);
 		if (err)
 			goto error2;
 	}
@@ -1740,8 +1826,8 @@ static __cpuinit int mce_create_device(unsigned int cpu)
 
 	return 0;
 error2:
-	while (--i >= 0)
-		sysdev_remove_file(&per_cpu(mce_dev, cpu), &bank_attrs[i]);
+	while (--j >= 0)
+		sysdev_remove_file(&per_cpu(mce_dev, cpu), &bank_attrs[j]);
 error:
 	while (--i >= 0)
 		sysdev_remove_file(&per_cpu(mce_dev, cpu), mce_attrs[i]);
@@ -1883,7 +1969,7 @@ static __init int mce_init_device(void)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
-	alloc_cpumask_var(&mce_dev_initialized, GFP_KERNEL);
+	zalloc_cpumask_var(&mce_dev_initialized, GFP_KERNEL);
 
 	err = mce_init_banks();
 	if (err)
@@ -1915,7 +2001,7 @@ EXPORT_SYMBOL_GPL(nr_mce_banks);	/* non-fatal.o */
 /* This has to be run for each processor */
 void mcheck_init(struct cpuinfo_x86 *c)
 {
-	if (mce_disabled == 1)
+	if (mce_disabled)
 		return;
 
 	switch (c->x86_vendor) {
@@ -1945,10 +2031,9 @@ void mcheck_init(struct cpuinfo_x86 *c)
 
 static int __init mcheck_enable(char *str)
 {
-	mce_disabled = -1;
+	mce_p5_enabled = 1;
 	return 1;
 }
-
 __setup("mce", mcheck_enable);
 
 #endif /* CONFIG_X86_OLD_MCE */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.h b/arch/x86/kernel/cpu/mcheck/mce.h
deleted file mode 100644
index 84a552b458c8..000000000000
--- a/arch/x86/kernel/cpu/mcheck/mce.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#include <linux/init.h>
-#include <asm/mce.h>
-
-#ifdef CONFIG_X86_OLD_MCE
-void amd_mcheck_init(struct cpuinfo_x86 *c);
-void intel_p4_mcheck_init(struct cpuinfo_x86 *c);
-void intel_p6_mcheck_init(struct cpuinfo_x86 *c);
-#endif
-
-#ifdef CONFIG_X86_ANCIENT_MCE
-void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
-void winchip_mcheck_init(struct cpuinfo_x86 *c);
-extern int mce_p5_enable;
-static inline int mce_p5_enabled(void) { return mce_p5_enable; }
-static inline void enable_p5_mce(void) { mce_p5_enable = 1; }
-#else
-static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {}
-static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
-static inline int mce_p5_enabled(void) { return 0; }
-static inline void enable_p5_mce(void) { }
-#endif
-
-/* Call the installed machine check handler for this CPU setup. */
-extern void (*machine_check_vector)(struct pt_regs *, long error_code);
-
-#ifdef CONFIG_X86_OLD_MCE
-
-extern int nr_mce_banks;
-
-void intel_set_thermal_handler(void);
-
-#else
-
-static inline void intel_set_thermal_handler(void) { }
-
-#endif
-
-void intel_init_thermal(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ddae21620bda..ddae21620bda 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 2b011d2d8579..e1acec0f7a32 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -1,74 +1,226 @@
 /*
- * Common code for Intel machine checks
+ * Intel specific MCE features.
+ * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca>
+ * Copyright (C) 2008, 2009 Intel Corporation
+ * Author: Andi Kleen
  */
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/smp.h>
 
-#include <asm/therm_throt.h>
-#include <asm/processor.h>
-#include <asm/system.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
 #include <asm/apic.h>
+#include <asm/processor.h>
 #include <asm/msr.h>
+#include <asm/mce.h>
+
+/*
+ * Support for Intel Correct Machine Check Interrupts. This allows
+ * the CPU to raise an interrupt when a corrected machine check happened.
+ * Normally we pick those up using a regular polling timer.
+ * Also supports reliable discovery of shared banks.
+ */
 
-#include "mce.h"
+static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
 
-void intel_init_thermal(struct cpuinfo_x86 *c)
+/*
+ * cmci_discover_lock protects against parallel discovery attempts
+ * which could race against each other.
+ */
+static DEFINE_SPINLOCK(cmci_discover_lock);
+
+#define CMCI_THRESHOLD 1
+
+static int cmci_supported(int *banks)
 {
-	unsigned int cpu = smp_processor_id();
-	int tm2 = 0;
-	u32 l, h;
+	u64 cap;
 
-	/* Thermal monitoring depends on ACPI and clock modulation*/
-	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
-		return;
+	if (mce_cmci_disabled || mce_ignore_ce)
+		return 0;
 
 	/*
-	 * First check if its enabled already, in which case there might
-	 * be some SMM goo which handles it, so we can't even put a handler
-	 * since it might be delivered via SMI already:
+	 * Vendor check is not strictly needed, but the initial
+	 * initialization is vendor keyed and this
+	 * makes sure none of the backdoors are entered otherwise.
 	 */
-	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
-	h = apic_read(APIC_LVTTHMR);
-	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
-		printk(KERN_DEBUG
-		       "CPU%d: Thermal monitoring handled by SMI\n", cpu);
-		return;
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return 0;
+	if (!cpu_has_apic || lapic_get_maxlvt() < 6)
+		return 0;
+	rdmsrl(MSR_IA32_MCG_CAP, cap);
+	*banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff);
+	return !!(cap & MCG_CMCI_P);
+}
+
+/*
+ * The interrupt handler. This is called on every event.
+ * Just call the poller directly to log any events.
+ * This could in theory increase the threshold under high load,
+ * but doesn't for now.
+ */
+static void intel_threshold_interrupt(void)
+{
+	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	mce_notify_irq();
+}
+
+static void print_update(char *type, int *hdr, int num)
+{
+	if (*hdr == 0)
+		printk(KERN_INFO "CPU %d MCA banks", smp_processor_id());
+	*hdr = 1;
+	printk(KERN_CONT " %s:%d", type, num);
+}
+
+/*
+ * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
+ * on this CPU. Use the algorithm recommended in the SDM to discover shared
+ * banks.
+ */
+static void cmci_discover(int banks, int boot)
+{
+	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
+	unsigned long flags;
+	int hdr = 0;
+	int i;
+
+	spin_lock_irqsave(&cmci_discover_lock, flags);
+	for (i = 0; i < banks; i++) {
+		u64 val;
+
+		if (test_bit(i, owned))
+			continue;
+
+		rdmsrl(MSR_IA32_MC0_CTL2 + i, val);
+
+		/* Already owned by someone else? */
+		if (val & CMCI_EN) {
+			if (test_and_clear_bit(i, owned) || boot)
+				print_update("SHD", &hdr, i);
+			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+			continue;
+		}
+
+		val |= CMCI_EN | CMCI_THRESHOLD;
+		wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
+		rdmsrl(MSR_IA32_MC0_CTL2 + i, val);
+
+		/* Did the enable bit stick? -- the bank supports CMCI */
+		if (val & CMCI_EN) {
+			if (!test_and_set_bit(i, owned) || boot)
+				print_update("CMCI", &hdr, i);
+			__clear_bit(i, __get_cpu_var(mce_poll_banks));
+		} else {
+			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
+		}
 	}
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
+	if (hdr)
+		printk(KERN_CONT "\n");
+}
+
+/*
+ * Just in case we missed an event during initialization check
+ * all the CMCI owned banks.
+ */
+void cmci_recheck(void)
+{
+	unsigned long flags;
+	int banks;
+
+	if (!mce_available(&current_cpu_data) || !cmci_supported(&banks))
+		return;
+	local_irq_save(flags);
+	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
+	local_irq_restore(flags);
+}
 
-	if (cpu_has(c, X86_FEATURE_TM2) && (l & MSR_IA32_MISC_ENABLE_TM2))
-		tm2 = 1;
+/*
+ * Disable CMCI on this CPU for all banks it owns when it goes down.
+ * This allows other CPUs to claim the banks on rediscovery.
+ */
+void cmci_clear(void)
+{
+	unsigned long flags;
+	int i;
+	int banks;
+	u64 val;
 
-	/* Check whether a vector already exists */
-	if (h & APIC_VECTOR_MASK) {
-		printk(KERN_DEBUG
-		       "CPU%d: Thermal LVT vector (%#x) already installed\n",
-		       cpu, (h & APIC_VECTOR_MASK));
+	if (!cmci_supported(&banks))
 		return;
+	spin_lock_irqsave(&cmci_discover_lock, flags);
+	for (i = 0; i < banks; i++) {
+		if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
+			continue;
+		/* Disable CMCI */
+		rdmsrl(MSR_IA32_MC0_CTL2 + i, val);
+		val &= ~(CMCI_EN|CMCI_THRESHOLD_MASK);
+		wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
+		__clear_bit(i, __get_cpu_var(mce_banks_owned));
 	}
+	spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
+/*
+ * After a CPU went down cycle through all the others and rediscover
+ * Must run in process context.
+ */
+void cmci_rediscover(int dying)
+{
+	int banks;
+	int cpu;
+	cpumask_var_t old;
+
+	if (!cmci_supported(&banks))
+		return;
+	if (!alloc_cpumask_var(&old, GFP_KERNEL))
+		return;
+	cpumask_copy(old, &current->cpus_allowed);
 
-	/* We'll mask the thermal vector in the lapic till we're ready: */
-	h = THERMAL_APIC_VECTOR | APIC_DM_FIXED | APIC_LVT_MASKED;
-	apic_write(APIC_LVTTHMR, h);
+	for_each_online_cpu(cpu) {
+		if (cpu == dying)
+			continue;
+		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
+			continue;
+		/* Recheck banks in case CPUs don't all have the same */
+		if (cmci_supported(&banks))
+			cmci_discover(banks, 0);
+	}
 
-	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
-	wrmsr(MSR_IA32_THERM_INTERRUPT,
-		l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h);
+	set_cpus_allowed_ptr(current, old);
+	free_cpumask_var(old);
+}
 
-	intel_set_thermal_handler();
+/*
+ * Reenable CMCI on this CPU in case a CPU down failed.
+ */
+void cmci_reenable(void)
+{
+	int banks;
+	if (cmci_supported(&banks))
+		cmci_discover(banks, 0);
+}
 
-	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
-	wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
+static void intel_init_cmci(void)
+{
+	int banks;
 
-	/* Unmask the thermal vector: */
-	l = apic_read(APIC_LVTTHMR);
-	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+	if (!cmci_supported(&banks))
+		return;
 
-	printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n",
-	       cpu, tm2 ? "TM2" : "TM1");
+	mce_threshold_vector = intel_threshold_interrupt;
+	cmci_discover(banks, 1);
+	/*
+	 * For CPU #0 this runs with still disabled APIC, but that's
+	 * ok because only the vector is set up. We still do another
+	 * check for the banks later for CPU #0 just to make sure
+	 * to not miss any events.
+	 */
+	apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED);
+	cmci_recheck();
+}
 
-	/* enable thermal throttle processing */
-	atomic_set(&therm_throt_en, 1);
+void mce_intel_feature_init(struct cpuinfo_x86 *c)
+{
+	intel_init_thermal(c);
+	intel_init_cmci();
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
deleted file mode 100644
index f2ef6952c400..000000000000
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ /dev/null
@@ -1,248 +0,0 @@
-/*
- * Intel specific MCE features.
- * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca>
- * Copyright (C) 2008, 2009 Intel Corporation
- * Author: Andi Kleen
- */
-
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/percpu.h>
-#include <asm/processor.h>
-#include <asm/apic.h>
-#include <asm/msr.h>
-#include <asm/mce.h>
-#include <asm/hw_irq.h>
-#include <asm/idle.h>
-#include <asm/therm_throt.h>
-
-#include "mce.h"
-
-asmlinkage void smp_thermal_interrupt(void)
-{
-	__u64 msr_val;
-
-	ack_APIC_irq();
-
-	exit_idle();
-	irq_enter();
-
-	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
-	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT))
-		mce_log_therm_throt_event(msr_val);
-
-	inc_irq_stat(irq_thermal_count);
-	irq_exit();
-}
-
-/*
- * Support for Intel Correct Machine Check Interrupts. This allows
- * the CPU to raise an interrupt when a corrected machine check happened.
- * Normally we pick those up using a regular polling timer.
- * Also supports reliable discovery of shared banks.
- */
-
-static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
-
-/*
- * cmci_discover_lock protects against parallel discovery attempts
- * which could race against each other.
- */
-static DEFINE_SPINLOCK(cmci_discover_lock);
-
-#define CMCI_THRESHOLD 1
-
-static int cmci_supported(int *banks)
-{
-	u64 cap;
-
-	if (mce_cmci_disabled || mce_ignore_ce)
-		return 0;
-
-	/*
-	 * Vendor check is not strictly needed, but the initial
-	 * initialization is vendor keyed and this
-	 * makes sure none of the backdoors are entered otherwise.
-	 */
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
-		return 0;
-	if (!cpu_has_apic || lapic_get_maxlvt() < 6)
-		return 0;
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
-	*banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff);
-	return !!(cap & MCG_CMCI_P);
-}
-
-/*
- * The interrupt handler. This is called on every event.
- * Just call the poller directly to log any events.
- * This could in theory increase the threshold under high load,
- * but doesn't for now.
- */
-static void intel_threshold_interrupt(void)
-{
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
-	mce_notify_irq();
-}
-
-static void print_update(char *type, int *hdr, int num)
-{
-	if (*hdr == 0)
-		printk(KERN_INFO "CPU %d MCA banks", smp_processor_id());
-	*hdr = 1;
-	printk(KERN_CONT " %s:%d", type, num);
-}
-
-/*
- * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks
- * on this CPU. Use the algorithm recommended in the SDM to discover shared
- * banks.
- */
-static void cmci_discover(int banks, int boot)
-{
-	unsigned long *owned = (void *)&__get_cpu_var(mce_banks_owned);
-	unsigned long flags;
-	int hdr = 0;
-	int i;
-
-	spin_lock_irqsave(&cmci_discover_lock, flags);
-	for (i = 0; i < banks; i++) {
-		u64 val;
-
-		if (test_bit(i, owned))
-			continue;
-
-		rdmsrl(MSR_IA32_MC0_CTL2 + i, val);
-
-		/* Already owned by someone else? */
-		if (val & CMCI_EN) {
-			if (test_and_clear_bit(i, owned) || boot)
-				print_update("SHD", &hdr, i);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
-			continue;
-		}
-
-		val |= CMCI_EN | CMCI_THRESHOLD;
-		wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
-		rdmsrl(MSR_IA32_MC0_CTL2 + i, val);
-
-		/* Did the enable bit stick? -- the bank supports CMCI */
-		if (val & CMCI_EN) {
-			if (!test_and_set_bit(i, owned) || boot)
-				print_update("CMCI", &hdr, i);
-			__clear_bit(i, __get_cpu_var(mce_poll_banks));
-		} else {
-			WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
-		}
-	}
-	spin_unlock_irqrestore(&cmci_discover_lock, flags);
-	if (hdr)
-		printk(KERN_CONT "\n");
-}
-
-/*
- * Just in case we missed an event during initialization check
- * all the CMCI owned banks.
- */
-void cmci_recheck(void)
-{
-	unsigned long flags;
-	int banks;
-
-	if (!mce_available(&current_cpu_data) || !cmci_supported(&banks))
-		return;
-	local_irq_save(flags);
-	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
-	local_irq_restore(flags);
-}
-
-/*
- * Disable CMCI on this CPU for all banks it owns when it goes down.
- * This allows other CPUs to claim the banks on rediscovery.
- */
-void cmci_clear(void)
-{
-	unsigned long flags;
-	int i;
-	int banks;
-	u64 val;
-
-	if (!cmci_supported(&banks))
-		return;
-	spin_lock_irqsave(&cmci_discover_lock, flags);
-	for (i = 0; i < banks; i++) {
-		if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
-			continue;
-		/* Disable CMCI */
-		rdmsrl(MSR_IA32_MC0_CTL2 + i, val);
-		val &= ~(CMCI_EN|CMCI_THRESHOLD_MASK);
-		wrmsrl(MSR_IA32_MC0_CTL2 + i, val);
-		__clear_bit(i, __get_cpu_var(mce_banks_owned));
-	}
-	spin_unlock_irqrestore(&cmci_discover_lock, flags);
-}
-
-/*
- * After a CPU went down cycle through all the others and rediscover
- * Must run in process context.
- */
-void cmci_rediscover(int dying)
-{
-	int banks;
-	int cpu;
-	cpumask_var_t old;
-
-	if (!cmci_supported(&banks))
-		return;
-	if (!alloc_cpumask_var(&old, GFP_KERNEL))
-		return;
-	cpumask_copy(old, &current->cpus_allowed);
-
-	for_each_online_cpu(cpu) {
-		if (cpu == dying)
-			continue;
-		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
-			continue;
-		/* Recheck banks in case CPUs don't all have the same */
-		if (cmci_supported(&banks))
-			cmci_discover(banks, 0);
-	}
-
-	set_cpus_allowed_ptr(current, old);
-	free_cpumask_var(old);
-}
-
-/*
- * Reenable CMCI on this CPU in case a CPU down failed.
- */
-void cmci_reenable(void)
-{
-	int banks;
-	if (cmci_supported(&banks))
-		cmci_discover(banks, 0);
-}
-
-static void intel_init_cmci(void)
-{
-	int banks;
-
-	if (!cmci_supported(&banks))
-		return;
-
-	mce_threshold_vector = intel_threshold_interrupt;
-	cmci_discover(banks, 1);
-	/*
-	 * For CPU #0 this runs with still disabled APIC, but that's
-	 * ok because only the vector is set up. We still do another
-	 * check for the banks later for CPU #0 just to make sure
-	 * to not miss any events.
-	 */
-	apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED);
-	cmci_recheck();
-}
-
-void mce_intel_feature_init(struct cpuinfo_x86 *c)
-{
-	intel_init_thermal(c);
-	intel_init_cmci();
-}
diff --git a/arch/x86/kernel/cpu/mcheck/non-fatal.c b/arch/x86/kernel/cpu/mcheck/non-fatal.c
index 70b710420f74..f5f2d6f71fb6 100644
--- a/arch/x86/kernel/cpu/mcheck/non-fatal.c
+++ b/arch/x86/kernel/cpu/mcheck/non-fatal.c
@@ -17,10 +17,9 @@
 
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 
-#include "mce.h"
-
 static int		firstbank;
 
 #define MCE_RATE	(15*HZ)	/* timer rate is 15s */
diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index 82cee108a2d3..4482aea9aa2e 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -1,21 +1,15 @@
 /*
  * P4 specific Machine Check Exception Reporting
  */
-
-#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/smp.h>
 
-#include <asm/therm_throt.h>
 #include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/apic.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 
-#include "mce.h"
-
 /* as supported by the P4/Xeon family */
 struct intel_mce_extended_msrs {
 	u32 eax;
@@ -33,46 +27,6 @@ struct intel_mce_extended_msrs {
 
 static int mce_num_extended_msrs;
 
-
-#ifdef CONFIG_X86_MCE_P4THERMAL
-
-static void unexpected_thermal_interrupt(struct pt_regs *regs)
-{
-	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
-			smp_processor_id());
-	add_taint(TAINT_MACHINE_CHECK);
-}
-
-/* P4/Xeon Thermal transition interrupt handler: */
-static void intel_thermal_interrupt(struct pt_regs *regs)
-{
-	__u64 msr_val;
-
-	ack_APIC_irq();
-
-	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
-	therm_throt_process(msr_val & THERM_STATUS_PROCHOT);
-}
-
-/* Thermal interrupt handler for this CPU setup: */
-static void (*vendor_thermal_interrupt)(struct pt_regs *regs) =
-						unexpected_thermal_interrupt;
-
-void smp_thermal_interrupt(struct pt_regs *regs)
-{
-	irq_enter();
-	vendor_thermal_interrupt(regs);
-	__get_cpu_var(irq_stat).irq_thermal_count++;
-	irq_exit();
-}
-
-void intel_set_thermal_handler(void)
-{
-	vendor_thermal_interrupt = intel_thermal_interrupt;
-}
-
-#endif /* CONFIG_X86_MCE_P4THERMAL */
-
 /* P4/Xeon Extended MCE MSR retrieval, return 0 if unsupported */
 static void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 {
diff --git a/arch/x86/kernel/cpu/mcheck/p5.c b/arch/x86/kernel/cpu/mcheck/p5.c
index 015f481ab1b0..5c0e6533d9bc 100644
--- a/arch/x86/kernel/cpu/mcheck/p5.c
+++ b/arch/x86/kernel/cpu/mcheck/p5.c
@@ -10,12 +10,11 @@
 
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 
-#include "mce.h"
-
 /* By default disabled */
-int		mce_p5_enable;
+int mce_p5_enabled __read_mostly;
 
 /* Machine check handler for Pentium class Intel CPUs: */
 static void pentium_machine_check(struct pt_regs *regs, long error_code)
@@ -43,15 +42,13 @@ void intel_p5_mcheck_init(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 
-	/* Check for MCE support: */
-	if (!cpu_has(c, X86_FEATURE_MCE))
+	/* Default P5 to off as its often misconnected: */
+	if (!mce_p5_enabled)
 		return;
 
-#ifdef CONFIG_X86_OLD_MCE
-	/* Default P5 to off as its often misconnected: */
-	if (mce_disabled != -1)
+	/* Check for MCE support: */
+	if (!cpu_has(c, X86_FEATURE_MCE))
 		return;
-#endif
 
 	machine_check_vector = pentium_machine_check;
 	/* Make sure the vector pointer is visible before we enable MCEs: */
diff --git a/arch/x86/kernel/cpu/mcheck/p6.c b/arch/x86/kernel/cpu/mcheck/p6.c
index 43c24e667457..01e4f8178183 100644
--- a/arch/x86/kernel/cpu/mcheck/p6.c
+++ b/arch/x86/kernel/cpu/mcheck/p6.c
@@ -10,10 +10,9 @@
 
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 
-#include "mce.h"
-
 /* Machine Check Handler For PII/PIII */
 static void intel_machine_check(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 7b1ae2e20ba5..bff8dd191dd5 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -13,13 +13,23 @@
  * Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c.
  *          Inspired by Ross Biro's and Al Borchers' counter code.
  */
+#include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/jiffies.h>
+#include <linux/kernel.h>
 #include <linux/percpu.h>
 #include <linux/sysdev.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/smp.h>
 #include <linux/cpu.h>
 
-#include <asm/therm_throt.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/apic.h>
+#include <asm/idle.h>
+#include <asm/mce.h>
+#include <asm/msr.h>
 
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL		(300 * HZ)
@@ -27,7 +37,7 @@
 static DEFINE_PER_CPU(__u64, next_check) = INITIAL_JIFFIES;
 static DEFINE_PER_CPU(unsigned long, thermal_throttle_count);
 
-atomic_t therm_throt_en		= ATOMIC_INIT(0);
+static atomic_t therm_throt_en		= ATOMIC_INIT(0);
 
 #ifdef CONFIG_SYSFS
 #define define_therm_throt_sysdev_one_ro(_name)				\
@@ -82,7 +92,7 @@ static struct attribute_group thermal_throttle_attr_group = {
  *          1 : Event should be logged further, and a message has been
  *              printed to the syslog.
  */
-int therm_throt_process(int curr)
+static int therm_throt_process(int curr)
 {
 	unsigned int cpu = smp_processor_id();
 	__u64 tmp_jiffs = get_jiffies_64();
@@ -186,6 +196,94 @@ static __init int thermal_throttle_init_device(void)
 
 	return 0;
 }
-
 device_initcall(thermal_throttle_init_device);
+
 #endif /* CONFIG_SYSFS */
+
+/* Thermal transition interrupt handler */
+static void intel_thermal_interrupt(void)
+{
+	__u64 msr_val;
+
+	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
+	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT))
+		mce_log_therm_throt_event(msr_val);
+}
+
+static void unexpected_thermal_interrupt(void)
+{
+	printk(KERN_ERR "CPU%d: Unexpected LVT TMR interrupt!\n",
+			smp_processor_id());
+	add_taint(TAINT_MACHINE_CHECK);
+}
+
+static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt;
+
+asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
+{
+	exit_idle();
+	irq_enter();
+	inc_irq_stat(irq_thermal_count);
+	smp_thermal_vector();
+	irq_exit();
+	/* Ack only at the end to avoid potential reentry */
+	ack_APIC_irq();
+}
+
+void intel_init_thermal(struct cpuinfo_x86 *c)
+{
+	unsigned int cpu = smp_processor_id();
+	int tm2 = 0;
+	u32 l, h;
+
+	/* Thermal monitoring depends on ACPI and clock modulation*/
+	if (!cpu_has(c, X86_FEATURE_ACPI) || !cpu_has(c, X86_FEATURE_ACC))
+		return;
+
+	/*
+	 * First check if its enabled already, in which case there might
+	 * be some SMM goo which handles it, so we can't even put a handler
+	 * since it might be delivered via SMI already:
+	 */
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+	h = apic_read(APIC_LVTTHMR);
+	if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
+		printk(KERN_DEBUG
+		       "CPU%d: Thermal monitoring handled by SMI\n", cpu);
+		return;
+	}
+
+	if (cpu_has(c, X86_FEATURE_TM2) && (l & MSR_IA32_MISC_ENABLE_TM2))
+		tm2 = 1;
+
+	/* Check whether a vector already exists */
+	if (h & APIC_VECTOR_MASK) {
+		printk(KERN_DEBUG
+		       "CPU%d: Thermal LVT vector (%#x) already installed\n",
+		       cpu, (h & APIC_VECTOR_MASK));
+		return;
+	}
+
+	/* We'll mask the thermal vector in the lapic till we're ready: */
+	h = THERMAL_APIC_VECTOR | APIC_DM_FIXED | APIC_LVT_MASKED;
+	apic_write(APIC_LVTTHMR, h);
+
+	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
+	wrmsr(MSR_IA32_THERM_INTERRUPT,
+		l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h);
+
+	smp_thermal_vector = intel_thermal_interrupt;
+
+	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+	wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
+
+	/* Unmask the thermal vector: */
+	l = apic_read(APIC_LVTTHMR);
+	apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+
+	printk(KERN_INFO "CPU%d: Thermal monitoring enabled (%s)\n",
+	       cpu, tm2 ? "TM2" : "TM1");
+
+	/* enable thermal throttle processing */
+	atomic_set(&therm_throt_en, 1);
+}
diff --git a/arch/x86/kernel/cpu/mcheck/winchip.c b/arch/x86/kernel/cpu/mcheck/winchip.c
index 81b02487090b..54060f565974 100644
--- a/arch/x86/kernel/cpu/mcheck/winchip.c
+++ b/arch/x86/kernel/cpu/mcheck/winchip.c
@@ -9,10 +9,9 @@
 
 #include <asm/processor.h>
 #include <asm/system.h>
+#include <asm/mce.h>
 #include <asm/msr.h>
 
-#include "mce.h"
-
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kernel/cpu/perf_counter.c b/arch/x86/kernel/cpu/perf_counter.c
index 275bc142cd5d..d4cf4ce19aac 100644
--- a/arch/x86/kernel/cpu/perf_counter.c
+++ b/arch/x86/kernel/cpu/perf_counter.c
@@ -19,6 +19,7 @@
 #include <linux/kdebug.h>
 #include <linux/sched.h>
 #include <linux/uaccess.h>
+#include <linux/highmem.h>
 
 #include <asm/apic.h>
 #include <asm/stacktrace.h>
@@ -389,23 +390,23 @@ static u64 intel_pmu_raw_event(u64 event)
 	return event & CORE_EVNTSEL_MASK;
 }
 
-static const u64 amd_0f_hw_cache_event_ids
+static const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
 {
  [ C(L1D) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
+		[ C(RESULT_MISS)   ] = 0x0041, /* Data Cache Misses          */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */
 		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0267, /* Data Prefetcher :attempts  */
+		[ C(RESULT_MISS)   ] = 0x0167, /* Data Prefetcher :cancelled */
 	},
  },
  [ C(L1I ) ] = {
@@ -418,17 +419,17 @@ static const u64 amd_0f_hw_cache_event_ids
 		[ C(RESULT_MISS)   ] = -1,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x014B, /* Prefetch Instructions :Load */
 		[ C(RESULT_MISS)   ] = 0,
 	},
  },
  [ C(LL  ) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x037D, /* Requests to L2 Cache :IC+DC */
+		[ C(RESULT_MISS)   ] = 0x037E, /* L2 Cache Misses : IC+DC     */
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x017F, /* L2 Fill/Writeback           */
 		[ C(RESULT_MISS)   ] = 0,
 	},
 	[ C(OP_PREFETCH) ] = {
@@ -438,8 +439,8 @@ static const u64 amd_0f_hw_cache_event_ids
  },
  [ C(DTLB) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = 0,
-		[ C(RESULT_MISS)   ] = 0,
+		[ C(RESULT_ACCESS) ] = 0x0040, /* Data Cache Accesses        */
+		[ C(RESULT_MISS)   ] = 0x0046, /* L1 DTLB and L2 DLTB Miss   */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0,
@@ -911,6 +912,8 @@ x86_perf_counter_set_period(struct perf_counter *counter,
 	err = checking_wrmsrl(hwc->counter_base + idx,
 			     (u64)(-left) & x86_pmu.counter_mask);
 
+	perf_counter_update_userpage(counter);
+
 	return ret;
 }
 
@@ -968,13 +971,6 @@ fixed_mode_idx(struct perf_counter *counter, struct hw_perf_counter *hwc)
 	if (!x86_pmu.num_counters_fixed)
 		return -1;
 
-	/*
-	 * Quirk, IA32_FIXED_CTRs do not work on current Atom processors:
-	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-					boot_cpu_data.x86_model == 28)
-		return -1;
-
 	event = hwc->config & ARCH_PERFMON_EVENT_MASK;
 
 	if (unlikely(event == x86_pmu.event_map(PERF_COUNT_HW_INSTRUCTIONS)))
@@ -1040,6 +1036,8 @@ try_generic:
 	x86_perf_counter_set_period(counter, hwc, idx);
 	x86_pmu.enable(hwc, idx);
 
+	perf_counter_update_userpage(counter);
+
 	return 0;
 }
 
@@ -1132,6 +1130,8 @@ static void x86_pmu_disable(struct perf_counter *counter)
 	x86_perf_counter_update(counter, hwc, idx);
 	cpuc->counters[idx] = NULL;
 	clear_bit(idx, cpuc->used_mask);
+
+	perf_counter_update_userpage(counter);
 }
 
 /*
@@ -1223,6 +1223,8 @@ again:
 		if (!intel_pmu_save_and_restart(counter))
 			continue;
 
+		data.period = counter->hw.last_period;
+
 		if (perf_counter_overflow(counter, 1, &data))
 			intel_pmu_disable_counter(&counter->hw, bit);
 	}
@@ -1425,8 +1427,6 @@ static int intel_pmu_init(void)
 	 */
 	x86_pmu.num_counters_fixed	= max((int)edx.split.num_counters_fixed, 3);
 
-	rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
-
 	/*
 	 * Install the hw-cache-events table:
 	 */
@@ -1459,18 +1459,16 @@ static int intel_pmu_init(void)
 
 static int amd_pmu_init(void)
 {
+	/* Performance-monitoring supported from K7 and later: */
+	if (boot_cpu_data.x86 < 6)
+		return -ENODEV;
+
 	x86_pmu = amd_pmu;
 
-	switch (boot_cpu_data.x86) {
-	case 0x0f:
-	case 0x10:
-	case 0x11:
-		memcpy(hw_cache_event_ids, amd_0f_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
+	/* Events are common for all AMDs */
+	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
+	       sizeof(hw_cache_event_ids));
 
-		pr_cont("AMD Family 0f/10/11 events, ");
-		break;
-	}
 	return 0;
 }
 
@@ -1498,21 +1496,22 @@ void __init init_hw_perf_counters(void)
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
 	if (x86_pmu.num_counters > X86_PMC_MAX_GENERIC) {
-		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 		WARN(1, KERN_ERR "hw perf counters %d > max(%d), clipping!",
 		     x86_pmu.num_counters, X86_PMC_MAX_GENERIC);
+		x86_pmu.num_counters = X86_PMC_MAX_GENERIC;
 	}
 	perf_counter_mask = (1 << x86_pmu.num_counters) - 1;
 	perf_max_counters = x86_pmu.num_counters;
 
 	if (x86_pmu.num_counters_fixed > X86_PMC_MAX_FIXED) {
-		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
 		WARN(1, KERN_ERR "hw perf counters fixed %d > max(%d), clipping!",
 		     x86_pmu.num_counters_fixed, X86_PMC_MAX_FIXED);
+		x86_pmu.num_counters_fixed = X86_PMC_MAX_FIXED;
 	}
 
 	perf_counter_mask |=
 		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
+	x86_pmu.intel_ctrl = perf_counter_mask;
 
 	perf_counters_lapic_init();
 	register_die_notifier(&perf_counter_nmi_notifier);
@@ -1554,9 +1553,9 @@ const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
  */
 
 static inline
-void callchain_store(struct perf_callchain_entry *entry, unsigned long ip)
+void callchain_store(struct perf_callchain_entry *entry, u64 ip)
 {
-	if (entry->nr < MAX_STACK_DEPTH)
+	if (entry->nr < PERF_MAX_STACK_DEPTH)
 		entry->ip[entry->nr++] = ip;
 }
 
@@ -1577,8 +1576,8 @@ static void backtrace_warning(void *data, char *msg)
 
 static int backtrace_stack(void *data, char *name)
 {
-	/* Don't bother with IRQ stacks for now */
-	return -1;
+	/* Process all stacks: */
+	return 0;
 }
 
 static void backtrace_address(void *data, unsigned long addr, int reliable)
@@ -1596,47 +1595,59 @@ static const struct stacktrace_ops backtrace_ops = {
 	.address		= backtrace_address,
 };
 
+#include "../dumpstack.h"
+
 static void
 perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
-	unsigned long bp;
-	char *stack;
-	int nr = entry->nr;
+	callchain_store(entry, PERF_CONTEXT_KERNEL);
+	callchain_store(entry, regs->ip);
 
-	callchain_store(entry, instruction_pointer(regs));
+	dump_trace(NULL, regs, NULL, 0, &backtrace_ops, entry);
+}
 
-	stack = ((char *)regs + sizeof(struct pt_regs));
-#ifdef CONFIG_FRAME_POINTER
-	bp = frame_pointer(regs);
-#else
-	bp = 0;
-#endif
+/*
+ * best effort, GUP based copy_from_user() that assumes IRQ or NMI context
+ */
+static unsigned long
+copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
+{
+	unsigned long offset, addr = (unsigned long)from;
+	int type = in_nmi() ? KM_NMI : KM_IRQ0;
+	unsigned long size, len = 0;
+	struct page *page;
+	void *map;
+	int ret;
 
-	dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, entry);
+	do {
+		ret = __get_user_pages_fast(addr, 1, 0, &page);
+		if (!ret)
+			break;
 
-	entry->kernel = entry->nr - nr;
-}
+		offset = addr & (PAGE_SIZE - 1);
+		size = min(PAGE_SIZE - offset, n - len);
 
+		map = kmap_atomic(page, type);
+		memcpy(to, map+offset, size);
+		kunmap_atomic(map, type);
+		put_page(page);
 
-struct stack_frame {
-	const void __user	*next_fp;
-	unsigned long		return_address;
-};
+		len  += size;
+		to   += size;
+		addr += size;
+
+	} while (len < n);
+
+	return len;
+}
 
 static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
 {
-	int ret;
-
-	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
-		return 0;
+	unsigned long bytes;
 
-	ret = 1;
-	pagefault_disable();
-	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
-		ret = 0;
-	pagefault_enable();
+	bytes = copy_from_user_nmi(frame, fp, sizeof(*frame));
 
-	return ret;
+	return bytes == sizeof(*frame);
 }
 
 static void
@@ -1644,28 +1655,28 @@ perf_callchain_user(struct pt_regs *regs, struct perf_callchain_entry *entry)
 {
 	struct stack_frame frame;
 	const void __user *fp;
-	int nr = entry->nr;
 
-	regs = (struct pt_regs *)current->thread.sp0 - 1;
-	fp   = (void __user *)regs->bp;
+	if (!user_mode(regs))
+		regs = task_pt_regs(current);
+
+	fp = (void __user *)regs->bp;
 
+	callchain_store(entry, PERF_CONTEXT_USER);
 	callchain_store(entry, regs->ip);
 
-	while (entry->nr < MAX_STACK_DEPTH) {
-		frame.next_fp	     = NULL;
+	while (entry->nr < PERF_MAX_STACK_DEPTH) {
+		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
 		if (!copy_stack_frame(fp, &frame))
 			break;
 
-		if ((unsigned long)fp < user_stack_pointer(regs))
+		if ((unsigned long)fp < regs->sp)
 			break;
 
 		callchain_store(entry, frame.return_address);
-		fp = frame.next_fp;
+		fp = frame.next_frame;
 	}
-
-	entry->user = entry->nr - nr;
 }
 
 static void
@@ -1701,9 +1712,6 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 		entry = &__get_cpu_var(irq_entry);
 
 	entry->nr = 0;
-	entry->hv = 0;
-	entry->kernel = 0;
-	entry->user = 0;
 
 	perf_do_callchain(regs, entry);
 
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d6f5b9fbde32..5c481f6205bf 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -716,11 +716,15 @@ static void probe_nmi_watchdog(void)
 		wd_ops = &k7_wd_ops;
 		break;
 	case X86_VENDOR_INTEL:
-		/*
-		 * Work around Core Duo (Yonah) errata AE49 where perfctr1
-		 * doesn't have a working enable bit.
+		/* Work around where perfctr1 doesn't have a working enable
+		 * bit as described in the following errata:
+		 * AE49 Core Duo and Intel Core Solo 65 nm
+		 * AN49 Intel Pentium Dual-Core
+		 * AF49 Dual-Core Intel Xeon Processor LV
 		 */
-		if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) {
+		if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 14) ||
+		    ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 15 &&
+		     boot_cpu_data.x86_mask == 4))) {
 			intel_arch_wd_ops.perfctr = MSR_ARCH_PERFMON_PERFCTR0;
 			intel_arch_wd_ops.evntsel = MSR_ARCH_PERFMON_EVENTSEL0;
 		}