Merge branch 'devicetree/for-x86' of git://git.secretlab.ca/git/linux-2.6 into x86/platform

Reason: x86 devicetree support for ce4100 depends on those device tree
	changes scheduled for .39.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

14 files changed, 329 insertions, 867 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9e093f8fe78..7c7bedb83c5 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -668,7 +668,7 @@ EXPORT_SYMBOL_GPL(amd_erratum_383);
 
 bool cpu_has_amd_erratum(const int *erratum)
 {
-	struct cpuinfo_x86 *cpu = &current_cpu_data;
+	struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info);
 	int osvw_id = *erratum++;
 	u32 range;
 	u32 ms;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 4b68bda3093..1d59834396b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -894,7 +894,6 @@ void __init identify_boot_cpu(void)
 #else
 	vgetcpu_set_mode();
 #endif
-	init_hw_perf_events();
 }
 
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 491977baf6c..35c7e65e59b 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -521,7 +521,7 @@ static void check_supported_cpu(void *_rc)
 
 	*rc = -ENODEV;
 
-	if (current_cpu_data.x86_vendor != X86_VENDOR_AMD)
+	if (__this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_AMD)
 		return;
 
 	eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
@@ -1377,7 +1377,7 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
 static void query_values_on_cpu(void *_err)
 {
 	int *err = _err;
-	struct powernow_k8_data *data = __get_cpu_var(powernow_data);
+	struct powernow_k8_data *data = __this_cpu_read(powernow_data);
 
 	*err = query_current_values_with_pending_wait(data);
 }
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 17ad0336621..ec2c19a7b8e 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -45,6 +45,7 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
 	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
+	{ 0x0e, LVL_1_DATA, 24 },	/* 6-way set assoc, 64 byte line size */
 	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x23, LVL_3,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -66,6 +67,7 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x45, LVL_2,      MB(2) },	/* 4-way set assoc, 32 byte line size */
 	{ 0x46, LVL_3,      MB(4) },	/* 4-way set assoc, 64 byte line size */
 	{ 0x47, LVL_3,      MB(8) },	/* 8-way set assoc, 64 byte line size */
+	{ 0x48, LVL_2,      MB(3) },	/* 12-way set assoc, 64 byte line size */
 	{ 0x49, LVL_3,      MB(4) },	/* 16-way set assoc, 64 byte line size */
 	{ 0x4a, LVL_3,      MB(6) },	/* 12-way set assoc, 64 byte line size */
 	{ 0x4b, LVL_3,      MB(8) },	/* 16-way set assoc, 64 byte line size */
@@ -87,6 +89,7 @@ static const struct _cache_table __cpuinitconst cache_table[] =
 	{ 0x7c, LVL_2,      MB(1) },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x7d, LVL_2,      MB(2) },	/* 8-way set assoc, 64 byte line size */
 	{ 0x7f, LVL_2,      512 },	/* 2-way set assoc, 64 byte line size */
+	{ 0x80, LVL_2,      512 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x82, LVL_2,      256 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x83, LVL_2,      512 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x84, LVL_2,      MB(1) },	/* 8-way set assoc, 32 byte line size */
@@ -149,8 +152,7 @@ union _cpuid4_leaf_ecx {
 };
 
 struct amd_l3_cache {
-	struct	 pci_dev *dev;
-	bool	 can_disable;
+	struct	 amd_northbridge *nb;
 	unsigned indices;
 	u8	 subcaches[4];
 };
@@ -266,7 +268,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 		line_size = l2.line_size;
 		lines_per_tag = l2.lines_per_tag;
 		/* cpu_data has errata corrections for K7 applied */
-		size_in_kb = current_cpu_data.x86_cache_size;
+		size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
 		break;
 	case 3:
 		if (!l3.val)
@@ -288,7 +290,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
 	eax->split.num_threads_sharing = 0;
-	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
+	eax->split.num_cores_on_die = __this_cpu_read(cpu_info.x86_max_cores) - 1;
 
 
 	if (assoc == 0xffff)
@@ -311,14 +313,12 @@ struct _cache_attr {
 /*
  * L3 cache descriptors
  */
-static struct amd_l3_cache **__cpuinitdata l3_caches;
-
 static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 {
 	unsigned int sc0, sc1, sc2, sc3;
 	u32 val = 0;
 
-	pci_read_config_dword(l3->dev, 0x1C4, &val);
+	pci_read_config_dword(l3->nb->misc, 0x1C4, &val);
 
 	/* calculate subcache sizes */
 	l3->subcaches[0] = sc0 = !(val & BIT(0));
@@ -330,47 +330,14 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
 	l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
 }
 
-static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
-{
-	struct amd_l3_cache *l3;
-	struct pci_dev *dev = node_to_k8_nb_misc(node);
-
-	l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC);
-	if (!l3) {
-		printk(KERN_WARNING "Error allocating L3 struct\n");
-		return NULL;
-	}
-
-	l3->dev = dev;
-
-	amd_calc_l3_indices(l3);
-
-	return l3;
-}
-
-static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
-					   int index)
+static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
+					int index)
 {
+	static struct amd_l3_cache *__cpuinitdata l3_caches;
 	int node;
 
-	if (boot_cpu_data.x86 != 0x10)
-		return;
-
-	if (index < 3)
-		return;
-
-	/* see errata #382 and #388 */
-	if (boot_cpu_data.x86_model < 0x8)
-		return;
-
-	if ((boot_cpu_data.x86_model == 0x8 ||
-	     boot_cpu_data.x86_model == 0x9)
-		&&
-	     boot_cpu_data.x86_mask < 0x1)
-			return;
-
-	/* not in virtualized environments */
-	if (k8_northbridges.num == 0)
+	/* only for L3, and not in virtualized environments */
+	if (index < 3 || amd_nb_num() == 0)
 		return;
 
 	/*
@@ -378,7 +345,7 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 	 * never freed but this is done only on shutdown so it doesn't matter.
 	 */
 	if (!l3_caches) {
-		int size = k8_northbridges.num * sizeof(struct amd_l3_cache *);
+		int size = amd_nb_num() * sizeof(struct amd_l3_cache);
 
 		l3_caches = kzalloc(size, GFP_ATOMIC);
 		if (!l3_caches)
@@ -387,14 +354,12 @@ static void __cpuinit amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf,
 
 	node = amd_get_nb_id(smp_processor_id());
 
-	if (!l3_caches[node]) {
-		l3_caches[node] = amd_init_l3_cache(node);
-		l3_caches[node]->can_disable = true;
+	if (!l3_caches[node].nb) {
+		l3_caches[node].nb = node_to_amd_nb(node);
+		amd_calc_l3_indices(&l3_caches[node]);
 	}
 
-	WARN_ON(!l3_caches[node]);
-
-	this_leaf->l3 = l3_caches[node];
+	this_leaf->l3 = &l3_caches[node];
 }
 
 /*
@@ -408,7 +373,7 @@ int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
 {
 	unsigned int reg = 0;
 
-	pci_read_config_dword(l3->dev, 0x1BC + slot * 4, &reg);
+	pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, &reg);
 
 	/* check whether this slot is activated already */
 	if (reg & (3UL << 30))
@@ -422,7 +387,8 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
 {
 	int index;
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	if (!this_leaf->l3 ||
+	    !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
 	index = amd_get_l3_disable_slot(this_leaf->l3, slot);
@@ -457,7 +423,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 		if (!l3->subcaches[i])
 			continue;
 
-		pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+		pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 
 		/*
 		 * We need to WBINVD on a core on the node containing the L3
@@ -467,7 +433,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
 		wbinvd_on_cpu(cpu);
 
 		reg |= BIT(31);
-		pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+		pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
 	}
 }
 
@@ -524,7 +490,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!this_leaf->l3 || !this_leaf->l3->can_disable)
+	if (!this_leaf->l3 ||
+	    !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
 		return -EINVAL;
 
 	cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
@@ -545,7 +512,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 #define STORE_CACHE_DISABLE(slot)					\
 static ssize_t								\
 store_cache_disable_##slot(struct _cpuid4_info *this_leaf,		\
-			    const char *buf, size_t count)		\
+			   const char *buf, size_t count)		\
 {									\
 	return store_cache_disable(this_leaf, buf, count, slot);	\
 }
@@ -558,10 +525,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
 		show_cache_disable_1, store_cache_disable_1);
 
 #else	/* CONFIG_AMD_NB */
-static void __cpuinit
-amd_check_l3_disable(struct _cpuid4_info_regs *this_leaf, int index)
-{
-};
+#define amd_init_l3_cache(x, y)
 #endif /* CONFIG_AMD_NB */
 
 static int
@@ -575,7 +539,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 
 	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
 		amd_cpuid4(index, &eax, &ebx, &ecx);
-		amd_check_l3_disable(this_leaf, index);
+		amd_init_l3_cache(this_leaf, index);
 	} else {
 		cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
 	}
@@ -983,30 +947,48 @@ define_one_ro(size);
 define_one_ro(shared_cpu_map);
 define_one_ro(shared_cpu_list);
 
-#define DEFAULT_SYSFS_CACHE_ATTRS	\
-	&type.attr,			\
-	&level.attr,			\
-	&coherency_line_size.attr,	\
-	&physical_line_partition.attr,	\
-	&ways_of_associativity.attr,	\
-	&number_of_sets.attr,		\
-	&size.attr,			\
-	&shared_cpu_map.attr,		\
-	&shared_cpu_list.attr
-
 static struct attribute *default_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
+	&type.attr,
+	&level.attr,
+	&coherency_line_size.attr,
+	&physical_line_partition.attr,
+	&ways_of_associativity.attr,
+	&number_of_sets.attr,
+	&size.attr,
+	&shared_cpu_map.attr,
+	&shared_cpu_list.attr,
 	NULL
 };
 
-static struct attribute *default_l3_attrs[] = {
-	DEFAULT_SYSFS_CACHE_ATTRS,
 #ifdef CONFIG_AMD_NB
-	&cache_disable_0.attr,
-	&cache_disable_1.attr,
+static struct attribute ** __cpuinit amd_l3_attrs(void)
+{
+	static struct attribute **attrs;
+	int n;
+
+	if (attrs)
+		return attrs;
+
+	n = sizeof (default_attrs) / sizeof (struct attribute *);
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+		n += 2;
+
+	attrs = kzalloc(n * sizeof (struct attribute *), GFP_KERNEL);
+	if (attrs == NULL)
+		return attrs = default_attrs;
+
+	for (n = 0; default_attrs[n]; n++)
+		attrs[n] = default_attrs[n];
+
+	if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+		attrs[n++] = &cache_disable_0.attr;
+		attrs[n++] = &cache_disable_1.attr;
+	}
+
+	return attrs;
+}
 #endif
-	NULL
-};
 
 static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf)
 {
@@ -1117,11 +1099,11 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
 
 		this_leaf = CPUID4_INFO_IDX(cpu, i);
 
-		if (this_leaf->l3 && this_leaf->l3->can_disable)
-			ktype_cache.default_attrs = default_l3_attrs;
-		else
-			ktype_cache.default_attrs = default_attrs;
-
+		ktype_cache.default_attrs = default_attrs;
+#ifdef CONFIG_AMD_NB
+		if (this_leaf->l3)
+			ktype_cache.default_attrs = amd_l3_attrs();
+#endif
 		retval = kobject_init_and_add(&(this_object->kobj),
 					      &ktype_cache,
 					      per_cpu(ici_cache_kobject, cpu),
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index e7dbde7bfed..a7797197956 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -25,6 +25,7 @@
 #include <linux/gfp.h>
 #include <asm/mce.h>
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 /* Update fake mce registers on current CPU. */
 static void inject_mce(struct mce *m)
@@ -83,7 +84,7 @@ static int mce_raise_notify(struct notifier_block *self,
 	struct die_args *args = (struct die_args *)data;
 	int cpu = smp_processor_id();
 	struct mce *m = &__get_cpu_var(injectm);
-	if (val != DIE_NMI_IPI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
+	if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
 		return NOTIFY_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
 	if (m->inject_flags & MCJ_EXCEPTION)
@@ -95,7 +96,7 @@ static int mce_raise_notify(struct notifier_block *self,
 
 static struct notifier_block mce_raise_nb = {
 	.notifier_call = mce_raise_notify,
-	.priority = 1000,
+	.priority = NMI_LOCAL_NORMAL_PRIOR,
 };
 
 /* Inject mce on current CPU */
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7a35b72d7c0..d916183b7f9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -326,7 +326,7 @@ static void mce_panic(char *msg, struct mce *final, char *exp)
 
 static int msr_to_offset(u32 msr)
 {
-	unsigned bank = __get_cpu_var(injectm.bank);
+	unsigned bank = __this_cpu_read(injectm.bank);
 
 	if (msr == rip_msr)
 		return offsetof(struct mce, ip);
@@ -346,7 +346,7 @@ static u64 mce_rdmsrl(u32 msr)
 {
 	u64 v;
 
-	if (__get_cpu_var(injectm).finished) {
+	if (__this_cpu_read(injectm.finished)) {
 		int offset = msr_to_offset(msr);
 
 		if (offset < 0)
@@ -369,7 +369,7 @@ static u64 mce_rdmsrl(u32 msr)
 
 static void mce_wrmsrl(u32 msr, u64 v)
 {
-	if (__get_cpu_var(injectm).finished) {
+	if (__this_cpu_read(injectm.finished)) {
 		int offset = msr_to_offset(msr);
 
 		if (offset >= 0)
@@ -1159,7 +1159,7 @@ static void mce_start_timer(unsigned long data)
 
 	WARN_ON(smp_processor_id() != data);
 
-	if (mce_available(&current_cpu_data)) {
+	if (mce_available(__this_cpu_ptr(&cpu_info))) {
 		machine_check_poll(MCP_TIMESTAMP,
 				&__get_cpu_var(mce_poll_banks));
 	}
@@ -1767,7 +1767,7 @@ static int mce_shutdown(struct sys_device *dev)
 static int mce_resume(struct sys_device *dev)
 {
 	__mcheck_cpu_init_generic();
-	__mcheck_cpu_init_vendor(&current_cpu_data);
+	__mcheck_cpu_init_vendor(__this_cpu_ptr(&cpu_info));
 
 	return 0;
 }
@@ -1775,7 +1775,7 @@ 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))
+	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_timer();
@@ -1790,7 +1790,7 @@ static void mce_restart(void)
 /* Toggle features for corrected errors */
 static void mce_disable_ce(void *all)
 {
-	if (!mce_available(&current_cpu_data))
+	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 	if (all)
 		del_timer_sync(&__get_cpu_var(mce_timer));
@@ -1799,7 +1799,7 @@ static void mce_disable_ce(void *all)
 
 static void mce_enable_ce(void *all)
 {
-	if (!mce_available(&current_cpu_data))
+	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 	cmci_reenable();
 	cmci_recheck();
@@ -2022,7 +2022,7 @@ static void __cpuinit mce_disable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(&current_cpu_data))
+	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
@@ -2040,7 +2040,7 @@ static void __cpuinit mce_reenable_cpu(void *h)
 	unsigned long action = *(unsigned long *)h;
 	int i;
 
-	if (!mce_available(&current_cpu_data))
+	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 
 	if (!(action & CPU_TASKS_FROZEN))
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 80c482382d5..5bf2fac52ac 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -31,8 +31,6 @@
 #include <asm/mce.h>
 #include <asm/msr.h>
 
-#define PFX               "mce_threshold: "
-#define VERSION           "version 1.1.1"
 #define NR_BANKS          6
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -59,12 +57,6 @@ struct threshold_block {
 	struct list_head	miscj;
 };
 
-/* defaults used early on boot */
-static struct threshold_block threshold_defaults = {
-	.interrupt_enable	= 0,
-	.threshold_limit	= THRESHOLD_MAX,
-};
-
 struct threshold_bank {
 	struct kobject		*kobj;
 	struct threshold_block	*blocks;
@@ -89,50 +81,101 @@ static void amd_threshold_interrupt(void);
 struct thresh_restart {
 	struct threshold_block	*b;
 	int			reset;
+	int			set_lvt_off;
+	int			lvt_off;
 	u16			old_limit;
 };
 
+static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi)
+{
+	int msr = (hi & MASK_LVTOFF_HI) >> 20;
+
+	if (apic < 0) {
+		pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt "
+		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu,
+		       b->bank, b->block, b->address, hi, lo);
+		return 0;
+	}
+
+	if (apic != msr) {
+		pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d "
+		       "for bank %d, block %d (MSR%08X=0x%x%08x)\n",
+		       b->cpu, apic, b->bank, b->block, b->address, hi, lo);
+		return 0;
+	}
+
+	return 1;
+};
+
 /* must be called with correct cpu affinity */
 /* Called via smp_call_function_single() */
 static void threshold_restart_bank(void *_tr)
 {
 	struct thresh_restart *tr = _tr;
-	u32 mci_misc_hi, mci_misc_lo;
+	u32 hi, lo;
 
-	rdmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+	rdmsr(tr->b->address, lo, hi);
 
-	if (tr->b->threshold_limit < (mci_misc_hi & THRESHOLD_MAX))
+	if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
 		tr->reset = 1;	/* limit cannot be lower than err count */
 
 	if (tr->reset) {		/* reset err count and overflow bit */
-		mci_misc_hi =
-		    (mci_misc_hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
+		hi =
+		    (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
 		    (THRESHOLD_MAX - tr->b->threshold_limit);
 	} else if (tr->old_limit) {	/* change limit w/o reset */
-		int new_count = (mci_misc_hi & THRESHOLD_MAX) +
+		int new_count = (hi & THRESHOLD_MAX) +
 		    (tr->old_limit - tr->b->threshold_limit);
 
-		mci_misc_hi = (mci_misc_hi & ~MASK_ERR_COUNT_HI) |
+		hi = (hi & ~MASK_ERR_COUNT_HI) |
 		    (new_count & THRESHOLD_MAX);
 	}
 
+	if (tr->set_lvt_off) {
+		if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) {
+			/* set new lvt offset */
+			hi &= ~MASK_LVTOFF_HI;
+			hi |= tr->lvt_off << 20;
+		}
+	}
+
 	tr->b->interrupt_enable ?
-	    (mci_misc_hi = (mci_misc_hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
-	    (mci_misc_hi &= ~MASK_INT_TYPE_HI);
+	    (hi = (hi & ~MASK_INT_TYPE_HI) | INT_TYPE_APIC) :
+	    (hi &= ~MASK_INT_TYPE_HI);
 
-	mci_misc_hi |= MASK_COUNT_EN_HI;
-	wrmsr(tr->b->address, mci_misc_lo, mci_misc_hi);
+	hi |= MASK_COUNT_EN_HI;
+	wrmsr(tr->b->address, lo, hi);
+}
+
+static void mce_threshold_block_init(struct threshold_block *b, int offset)
+{
+	struct thresh_restart tr = {
+		.b			= b,
+		.set_lvt_off		= 1,
+		.lvt_off		= offset,
+	};
+
+	b->threshold_limit		= THRESHOLD_MAX;
+	threshold_restart_bank(&tr);
+};
+
+static int setup_APIC_mce(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
+	struct threshold_block b;
 	unsigned int cpu = smp_processor_id();
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
-	struct thresh_restart tr;
-	int lvt_off = -1;
-	u8 offset;
+	int offset = -1;
 
 	for (bank = 0; bank < NR_BANKS; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
@@ -163,39 +206,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
 #endif
-			offset = (high & MASK_LVTOFF_HI) >> 20;
-			if (lvt_off < 0) {
-				if (setup_APIC_eilvt(offset,
-						     THRESHOLD_APIC_VECTOR,
-						     APIC_EILVT_MSG_FIX, 0)) {
-					pr_err(FW_BUG "cpu %d, failed to "
-					       "setup threshold interrupt "
-					       "for bank %d, block %d "
-					       "(MSR%08X=0x%x%08x)",
-					       smp_processor_id(), bank, block,
-					       address, high, low);
-					continue;
-				}
-				lvt_off = offset;
-			} else if (lvt_off != offset) {
-				pr_err(FW_BUG "cpu %d, invalid threshold "
-				       "interrupt offset %d for bank %d,"
-				       "block %d (MSR%08X=0x%x%08x)",
-				       smp_processor_id(), lvt_off, bank,
-				       block, address, high, low);
-				continue;
-			}
-
-			high &= ~MASK_LVTOFF_HI;
-			high |= lvt_off << 20;
-			wrmsr(address, low, high);
+			offset = setup_APIC_mce(offset,
+						(high & MASK_LVTOFF_HI) >> 20);
 
-			threshold_defaults.address = address;
-			tr.b = &threshold_defaults;
-			tr.reset = 0;
-			tr.old_limit = 0;
-			threshold_restart_bank(&tr);
+			memset(&b, 0, sizeof(b));
+			b.cpu		= cpu;
+			b.bank		= bank;
+			b.block		= block;
+			b.address	= address;
 
+			mce_threshold_block_init(&b, offset);
 			mce_threshold_vector = amd_threshold_interrupt;
 		}
 	}
@@ -298,9 +318,8 @@ store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size)
 
 	b->interrupt_enable = !!new;
 
+	memset(&tr, 0, sizeof(tr));
 	tr.b		= b;
-	tr.reset	= 0;
-	tr.old_limit	= 0;
 
 	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -321,10 +340,10 @@ store_threshold_limit(struct threshold_block *b, const char *buf, size_t size)
 	if (new < 1)
 		new = 1;
 
+	memset(&tr, 0, sizeof(tr));
 	tr.old_limit = b->threshold_limit;
 	b->threshold_limit = new;
 	tr.b = b;
-	tr.reset = 0;
 
 	smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1);
 
@@ -603,9 +622,9 @@ static __cpuinit int threshold_create_device(unsigned int cpu)
 			continue;
 		err = threshold_create_bank(cpu, bank);
 		if (err)
-			goto out;
+			return err;
 	}
-out:
+
 	return err;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 6fcd0936194..8694ef56459 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -130,7 +130,7 @@ void cmci_recheck(void)
 	unsigned long flags;
 	int banks;
 
-	if (!mce_available(&current_cpu_data) || !cmci_supported(&banks))
+	if (!mce_available(__this_cpu_ptr(&cpu_info)) || !cmci_supported(&banks))
 		return;
 	local_irq_save(flags);
 	machine_check_poll(MCP_TIMESTAMP, &__get_cpu_var(mce_banks_owned));
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 4b683267eca..6f8c5e9da97 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -53,8 +53,14 @@ struct thermal_state {
 	struct _thermal_state core_power_limit;
 	struct _thermal_state package_throttle;
 	struct _thermal_state package_power_limit;
+	struct _thermal_state core_thresh0;
+	struct _thermal_state core_thresh1;
 };
 
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+EXPORT_SYMBOL(platform_thermal_notify);
+
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
@@ -200,6 +206,22 @@ static int therm_throt_process(bool new_event, int event, int level)
 	return 0;
 }
 
+static int thresh_event_valid(int event)
+{
+	struct _thermal_state *state;
+	unsigned int this_cpu = smp_processor_id();
+	struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
+	u64 now = get_jiffies_64();
+
+	state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+
+	if (time_before64(now, state->next_check))
+		return 0;
+
+	state->next_check = now + CHECK_INTERVAL;
+	return 1;
+}
+
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +335,22 @@ device_initcall(thermal_throttle_init_device);
 #define PACKAGE_THROTTLED	((__u64)2 << 62)
 #define PACKAGE_POWER_LIMIT	((__u64)3 << 62)
 
+static void notify_thresholds(__u64 msr_val)
+{
+	/* check whether the interrupt handler is defined;
+	 * otherwise simply return
+	 */
+	if (!platform_thermal_notify)
+		return;
+
+	/* lower threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD0) &&	thresh_event_valid(0))
+		platform_thermal_notify(msr_val);
+	/* higher threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+		platform_thermal_notify(msr_val);
+}
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
@@ -321,6 +359,9 @@ static void intel_thermal_interrupt(void)
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
+	/* Check for violation of core thermal thresholds*/
+	notify_thresholds(msr_val);
+
 	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
 				THERMAL_THROTTLING_EVENT,
 				CORE_LEVEL) != 0)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index ed6310183ef..9d977a2ea69 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -330,9 +330,6 @@ static bool reserve_pmc_hardware(void)
 {
 	int i;
 
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		disable_lapic_nmi_watchdog();
-
 	for (i = 0; i < x86_pmu.num_counters; i++) {
 		if (!reserve_perfctr_nmi(x86_pmu.perfctr + i))
 			goto perfctr_fail;
@@ -355,9 +352,6 @@ perfctr_fail:
 	for (i--; i >= 0; i--)
 		release_perfctr_nmi(x86_pmu.perfctr + i);
 
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		enable_lapic_nmi_watchdog();
-
 	return false;
 }
 
@@ -369,9 +363,6 @@ static void release_pmc_hardware(void)
 		release_perfctr_nmi(x86_pmu.perfctr + i);
 		release_evntsel_nmi(x86_pmu.eventsel + i);
 	}
-
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		enable_lapic_nmi_watchdog();
 }
 
 #else
@@ -381,6 +372,58 @@ static void release_pmc_hardware(void) {}
 
 #endif
 
+static bool check_hw_exists(void)
+{
+	u64 val, val_new = 0;
+	int i, reg, ret = 0;
+
+	/*
+	 * Check to see if the BIOS enabled any of the counters, if so
+	 * complain and bail.
+	 */
+	for (i = 0; i < x86_pmu.num_counters; i++) {
+		reg = x86_pmu.eventsel + i;
+		ret = rdmsrl_safe(reg, &val);
+		if (ret)
+			goto msr_fail;
+		if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
+			goto bios_fail;
+	}
+
+	if (x86_pmu.num_counters_fixed) {
+		reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+		ret = rdmsrl_safe(reg, &val);
+		if (ret)
+			goto msr_fail;
+		for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+			if (val & (0x03 << i*4))
+				goto bios_fail;
+		}
+	}
+
+	/*
+	 * Now write a value and read it back to see if it matches,
+	 * this is needed to detect certain hardware emulators (qemu/kvm)
+	 * that don't trap on the MSR access and always return 0s.
+	 */
+	val = 0xabcdUL;
+	ret = checking_wrmsrl(x86_pmu.perfctr, val);
+	ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
+	if (ret || val != val_new)
+		goto msr_fail;
+
+	return true;
+
+bios_fail:
+	printk(KERN_CONT "Broken BIOS detected, using software events only.\n");
+	printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val);
+	return false;
+
+msr_fail:
+	printk(KERN_CONT "Broken PMU hardware detected, using software events only.\n");
+	return false;
+}
+
 static void reserve_ds_buffers(void);
 static void release_ds_buffers(void);
 
@@ -437,7 +480,7 @@ static int x86_setup_perfctr(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	u64 config;
 
-	if (!hwc->sample_period) {
+	if (!is_sampling_event(event)) {
 		hwc->sample_period = x86_pmu.max_period;
 		hwc->last_period = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
@@ -954,8 +997,7 @@ x86_perf_event_set_period(struct perf_event *event)
 
 static void x86_pmu_enable_event(struct perf_event *event)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-	if (cpuc->enabled)
+	if (__this_cpu_read(cpu_hw_events.enabled))
 		__x86_pmu_enable_event(&event->hw,
 				       ARCH_PERFMON_EVENTSEL_ENABLE);
 }
@@ -1225,11 +1267,10 @@ perf_event_nmi_handler(struct notifier_block *self,
 
 	switch (cmd) {
 	case DIE_NMI:
-	case DIE_NMI_IPI:
 		break;
 	case DIE_NMIUNKNOWN:
 		this_nmi = percpu_read(irq_stat.__nmi_count);
-		if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+		if (this_nmi != __this_cpu_read(pmu_nmi.marked))
 			/* let the kernel handle the unknown nmi */
 			return NOTIFY_DONE;
 		/*
@@ -1253,8 +1294,8 @@ perf_event_nmi_handler(struct notifier_block *self,
 	this_nmi = percpu_read(irq_stat.__nmi_count);
 	if ((handled > 1) ||
 		/* the next nmi could be a back-to-back nmi */
-	    ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
-	     (__get_cpu_var(pmu_nmi).handled > 1))) {
+	    ((__this_cpu_read(pmu_nmi.marked) == this_nmi) &&
+	     (__this_cpu_read(pmu_nmi.handled) > 1))) {
 		/*
 		 * We could have two subsequent back-to-back nmis: The
 		 * first handles more than one counter, the 2nd
@@ -1265,8 +1306,8 @@ perf_event_nmi_handler(struct notifier_block *self,
 		 * handling more than one counter. We will mark the
 		 * next (3rd) and then drop it if unhandled.
 		 */
-		__get_cpu_var(pmu_nmi).marked	= this_nmi + 1;
-		__get_cpu_var(pmu_nmi).handled	= handled;
+		__this_cpu_write(pmu_nmi.marked, this_nmi + 1);
+		__this_cpu_write(pmu_nmi.handled, handled);
 	}
 
 	return NOTIFY_STOP;
@@ -1275,7 +1316,7 @@ perf_event_nmi_handler(struct notifier_block *self,
 static __read_mostly struct notifier_block perf_event_nmi_notifier = {
 	.notifier_call		= perf_event_nmi_handler,
 	.next			= NULL,
-	.priority		= 1
+	.priority		= NMI_LOCAL_LOW_PRIOR,
 };
 
 static struct event_constraint unconstrained;
@@ -1348,7 +1389,7 @@ static void __init pmu_check_apic(void)
 	pr_info("no hardware sampling interrupt available.\n");
 }
 
-void __init init_hw_perf_events(void)
+int __init init_hw_perf_events(void)
 {
 	struct event_constraint *c;
 	int err;
@@ -1363,15 +1404,19 @@ void __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		break;
 	default:
-		return;
+		return 0;
 	}
 	if (err != 0) {
 		pr_cont("no PMU driver, software events only.\n");
-		return;
+		return 0;
 	}
 
 	pmu_check_apic();
 
+	/* sanity check that the hardware exists or is emulated */
+	if (!check_hw_exists())
+		return 0;
+
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
 	if (x86_pmu.quirks)
@@ -1418,9 +1463,12 @@ void __init init_hw_perf_events(void)
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
-	perf_pmu_register(&pmu);
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	perf_cpu_notifier(x86_pmu_notifier);
+
+	return 0;
 }
+early_initcall(init_hw_perf_events);
 
 static inline void x86_pmu_read(struct perf_event *event)
 {
@@ -1434,11 +1482,9 @@ static inline void x86_pmu_read(struct perf_event *event)
  */
 static void x86_pmu_start_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
 	perf_pmu_disable(pmu);
-	cpuc->group_flag |= PERF_EVENT_TXN;
-	cpuc->n_txn = 0;
+	__this_cpu_or(cpu_hw_events.group_flag, PERF_EVENT_TXN);
+	__this_cpu_write(cpu_hw_events.n_txn, 0);
 }
 
 /*
@@ -1448,14 +1494,12 @@ static void x86_pmu_start_txn(struct pmu *pmu)
  */
 static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
-	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-
-	cpuc->group_flag &= ~PERF_EVENT_TXN;
+	__this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
 	/*
 	 * Truncate the collected events.
 	 */
-	cpuc->n_added -= cpuc->n_txn;
-	cpuc->n_events -= cpuc->n_txn;
+	__this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
+	__this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
 	perf_pmu_enable(pmu);
 }
 
@@ -1666,7 +1710,7 @@ perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 
 	perf_callchain_store(entry, regs->ip);
 
-	dump_trace(NULL, regs, NULL, regs->bp, &backtrace_ops, entry);
+	dump_trace(NULL, regs, NULL, &backtrace_ops, entry);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 46d58448c3a..67e2202a603 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,7 +1,5 @@
 #ifdef CONFIG_CPU_SUP_AMD
 
-static DEFINE_RAW_SPINLOCK(amd_nb_lock);
-
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -275,17 +273,17 @@ done:
 	return &emptyconstraint;
 }
 
-static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
+static struct amd_nb *amd_alloc_nb(int cpu)
 {
 	struct amd_nb *nb;
 	int i;
 
-	nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+	nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
+			  cpu_to_node(cpu));
 	if (!nb)
 		return NULL;
 
-	memset(nb, 0, sizeof(*nb));
-	nb->nb_id = nb_id;
+	nb->nb_id = -1;
 
 	/*
 	 * initialize all possible NB constraints
@@ -306,7 +304,7 @@ static int amd_pmu_cpu_prepare(int cpu)
 	if (boot_cpu_data.x86_max_cores < 2)
 		return NOTIFY_OK;
 
-	cpuc->amd_nb = amd_alloc_nb(cpu, -1);
+	cpuc->amd_nb = amd_alloc_nb(cpu);
 	if (!cpuc->amd_nb)
 		return NOTIFY_BAD;
 
@@ -325,8 +323,6 @@ static void amd_pmu_cpu_starting(int cpu)
 	nb_id = amd_get_nb_id(cpu);
 	WARN_ON_ONCE(nb_id == BAD_APICID);
 
-	raw_spin_lock(&amd_nb_lock);
-
 	for_each_online_cpu(i) {
 		nb = per_cpu(cpu_hw_events, i).amd_nb;
 		if (WARN_ON_ONCE(!nb))
@@ -341,8 +337,6 @@ static void amd_pmu_cpu_starting(int cpu)
 
 	cpuc->amd_nb->nb_id = nb_id;
 	cpuc->amd_nb->refcnt++;
-
-	raw_spin_unlock(&amd_nb_lock);
 }
 
 static void amd_pmu_cpu_dead(int cpu)
@@ -354,8 +348,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
 	cpuhw = &per_cpu(cpu_hw_events, cpu);
 
-	raw_spin_lock(&amd_nb_lock);
-
 	if (cpuhw->amd_nb) {
 		struct amd_nb *nb = cpuhw->amd_nb;
 
@@ -364,8 +356,6 @@ static void amd_pmu_cpu_dead(int cpu)
 
 		cpuhw->amd_nb = NULL;
 	}
-
-	raw_spin_unlock(&amd_nb_lock);
 }
 
 static __initconst const struct x86_pmu amd_pmu = {
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index c8f5c088cad..008835c1d79 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -649,7 +649,7 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 
 	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
-		if (!__get_cpu_var(cpu_hw_events).enabled)
+		if (!__this_cpu_read(cpu_hw_events.enabled))
 			return;
 
 		intel_pmu_enable_bts(hwc->config);
@@ -679,7 +679,7 @@ static int intel_pmu_save_and_restart(struct perf_event *event)
 
 static void intel_pmu_reset(void)
 {
-	struct debug_store *ds = __get_cpu_var(cpu_hw_events).ds;
+	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
 	unsigned long flags;
 	int idx;
 
@@ -816,6 +816,32 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.precise_ip &&
+	    (event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) {
+		/*
+		 * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P
+		 * (0x003c) so that we can use it with PEBS.
+		 *
+		 * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't
+		 * PEBS capable. However we can use INST_RETIRED.ANY_P
+		 * (0x00c0), which is a PEBS capable event, to get the same
+		 * count.
+		 *
+		 * INST_RETIRED.ANY_P counts the number of cycles that retires
+		 * CNTMASK instructions. By setting CNTMASK to a value (16)
+		 * larger than the maximum number of instructions that can be
+		 * retired per cycle (4) and then inverting the condition, we
+		 * count all cycles that retire 16 or less instructions, which
+		 * is every cycle.
+		 *
+		 * Thereby we gain a PEBS capable cycle counter.
+		 */
+		u64 alt_config = 0x108000c0; /* INST_RETIRED.TOTAL_CYCLES */
+
+		alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK);
+		event->hw.config = alt_config;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 81400b93e69..e56b9bfbabd 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -753,19 +753,21 @@ out:
 
 static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
 {
-	int overflow = 0;
-	u32 low, high;
+	u64 v;
 
-	rdmsr(hwc->config_base + hwc->idx, low, high);
-
-	/* we need to check high bit for unflagged overflows */
-	if ((low & P4_CCCR_OVF) || !(high & (1 << 31))) {
-		overflow = 1;
-		(void)checking_wrmsrl(hwc->config_base + hwc->idx,
-			((u64)low) & ~P4_CCCR_OVF);
+	/* an official way for overflow indication */
+	rdmsrl(hwc->config_base + hwc->idx, v);
+	if (v & P4_CCCR_OVF) {
+		wrmsrl(hwc->config_base + hwc->idx, v & ~P4_CCCR_OVF);
+		return 1;
 	}
 
-	return overflow;
+	/* it might be unflagged overflow */
+	rdmsrl(hwc->event_base + hwc->idx, v);
+	if (!(v & ARCH_P4_CNTRVAL_MASK))
+		return 1;
+
+	return 0;
 }
 
 static void p4_pmu_disable_pebs(void)
@@ -1152,9 +1154,9 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 */
 	.num_counters		= ARCH_P4_MAX_CCCR,
 	.apic			= 1,
-	.cntval_bits		= 40,
-	.cntval_mask		= (1ULL << 40) - 1,
-	.max_period		= (1ULL << 39) - 1,
+	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
+	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
+	.max_period		= (1ULL << (ARCH_P4_CNTRVAL_BITS - 1)) - 1,
 	.hw_config		= p4_hw_config,
 	.schedule_events	= p4_pmu_schedule_events,
 	/*
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d9f4ff8fcd6..d5a23661550 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -16,32 +16,12 @@
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
+#include <asm/nmi.h>
 #include <linux/kprobes.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
 
-struct nmi_watchdog_ctlblk {
-	unsigned int cccr_msr;
-	unsigned int perfctr_msr;  /* the MSR to reset in NMI handler */
-	unsigned int evntsel_msr;  /* the MSR to select the events to handle */
-};
-
-/* Interface defining a CPU specific perfctr watchdog */
-struct wd_ops {
-	int (*reserve)(void);
-	void (*unreserve)(void);
-	int (*setup)(unsigned nmi_hz);
-	void (*rearm)(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz);
-	void (*stop)(void);
-	unsigned perfctr;
-	unsigned evntsel;
-	u64 checkbit;
-};
-
-static const struct wd_ops *wd_ops;
-
 /*
  * this number is calculated from Intel's MSR_P4_CRU_ESCR5 register and it's
  * offset from MSR_P4_BSU_ESCR0.
@@ -60,8 +40,6 @@ static const struct wd_ops *wd_ops;
 static DECLARE_BITMAP(perfctr_nmi_owner, NMI_MAX_COUNTER_BITS);
 static DECLARE_BITMAP(evntsel_nmi_owner, NMI_MAX_COUNTER_BITS);
 
-static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
-
 /* converts an msr to an appropriate reservation bit */
 static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 {
@@ -172,623 +150,3 @@ void release_evntsel_nmi(unsigned int msr)
 	clear_bit(counter, evntsel_nmi_owner);
 }
 EXPORT_SYMBOL(release_evntsel_nmi);
-
-void disable_lapic_nmi_watchdog(void)
-{
-	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
-	if (atomic_read(&nmi_active) <= 0)
-		return;
-
-	on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
-
-	if (wd_ops)
-		wd_ops->unreserve();
-
-	BUG_ON(atomic_read(&nmi_active) != 0);
-}
-
-void enable_lapic_nmi_watchdog(void)
-{
-	BUG_ON(nmi_watchdog != NMI_LOCAL_APIC);
-
-	/* are we already enabled */
-	if (atomic_read(&nmi_active) != 0)
-		return;
-
-	/* are we lapic aware */
-	if (!wd_ops)
-		return;
-	if (!wd_ops->reserve()) {
-		printk(KERN_ERR "NMI watchdog: cannot reserve perfctrs\n");
-		return;
-	}
-
-	on_each_cpu(setup_apic_nmi_watchdog, NULL, 1);
-	touch_nmi_watchdog();
-}
-
-/*
- * Activate the NMI watchdog via the local APIC.
- */
-
-static unsigned int adjust_for_32bit_ctr(unsigned int hz)
-{
-	u64 counter_val;
-	unsigned int retval = hz;
-
-	/*
-	 * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
-	 * are writable, with higher bits sign extending from bit 31.
-	 * So, we can only program the counter with 31 bit values and
-	 * 32nd bit should be 1, for 33.. to be 1.
-	 * Find the appropriate nmi_hz
-	 */
-	counter_val = (u64)cpu_khz * 1000;
-	do_div(counter_val, retval);
-	if (counter_val > 0x7fffffffULL) {
-		u64 count = (u64)cpu_khz * 1000;
-		do_div(count, 0x7fffffffUL);
-		retval = count + 1;
-	}
-	return retval;
-}
-
-static void write_watchdog_counter(unsigned int perfctr_msr,
-				const char *descr, unsigned nmi_hz)
-{
-	u64 count = (u64)cpu_khz * 1000;
-
-	do_div(count, nmi_hz);
-	if (descr)
-		pr_debug("setting %s to -0x%08Lx\n", descr, count);
-	wrmsrl(perfctr_msr, 0 - count);
-}
-
-static void write_watchdog_counter32(unsigned int perfctr_msr,
-				const char *descr, unsigned nmi_hz)
-{
-	u64 count = (u64)cpu_khz * 1000;
-
-	do_div(count, nmi_hz);
-	if (descr)
-		pr_debug("setting %s to -0x%08Lx\n", descr, count);
-	wrmsr(perfctr_msr, (u32)(-count), 0);
-}
-
-/*
- * AMD K7/K8/Family10h/Family11h support.
- * AMD keeps this interface nicely stable so there is not much variety
- */
-#define K7_EVNTSEL_ENABLE	(1 << 22)
-#define K7_EVNTSEL_INT		(1 << 20)
-#define K7_EVNTSEL_OS		(1 << 17)
-#define K7_EVNTSEL_USR		(1 << 16)
-#define K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING	0x76
-#define K7_NMI_EVENT		K7_EVENT_CYCLES_PROCESSOR_IS_RUNNING
-
-static int setup_k7_watchdog(unsigned nmi_hz)
-{
-	unsigned int perfctr_msr, evntsel_msr;
-	unsigned int evntsel;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	perfctr_msr = wd_ops->perfctr;
-	evntsel_msr = wd_ops->evntsel;
-
-	wrmsrl(perfctr_msr, 0UL);
-
-	evntsel = K7_EVNTSEL_INT
-		| K7_EVNTSEL_OS
-		| K7_EVNTSEL_USR
-		| K7_NMI_EVENT;
-
-	/* setup the timer */
-	wrmsr(evntsel_msr, evntsel, 0);
-	write_watchdog_counter(perfctr_msr, "K7_PERFCTR0", nmi_hz);
-
-	/* initialize the wd struct before enabling */
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  /* unused */
-
-	/* ok, everything is initialized, announce that we're set */
-	cpu_nmi_set_wd_enabled();
-
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= K7_EVNTSEL_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
-
-	return 1;
-}
-
-static void single_msr_stop_watchdog(void)
-{
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	wrmsr(wd->evntsel_msr, 0, 0);
-}
-
-static int single_msr_reserve(void)
-{
-	if (!reserve_perfctr_nmi(wd_ops->perfctr))
-		return 0;
-
-	if (!reserve_evntsel_nmi(wd_ops->evntsel)) {
-		release_perfctr_nmi(wd_ops->perfctr);
-		return 0;
-	}
-	return 1;
-}
-
-static void single_msr_unreserve(void)
-{
-	release_evntsel_nmi(wd_ops->evntsel);
-	release_perfctr_nmi(wd_ops->perfctr);
-}
-
-static void __kprobes
-single_msr_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
-	/* start the cycle over again */
-	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops k7_wd_ops = {
-	.reserve	= single_msr_reserve,
-	.unreserve	= single_msr_unreserve,
-	.setup		= setup_k7_watchdog,
-	.rearm		= single_msr_rearm,
-	.stop		= single_msr_stop_watchdog,
-	.perfctr	= MSR_K7_PERFCTR0,
-	.evntsel	= MSR_K7_EVNTSEL0,
-	.checkbit	= 1ULL << 47,
-};
-
-/*
- * Intel Model 6 (PPro+,P2,P3,P-M,Core1)
- */
-#define P6_EVNTSEL0_ENABLE	(1 << 22)
-#define P6_EVNTSEL_INT		(1 << 20)
-#define P6_EVNTSEL_OS		(1 << 17)
-#define P6_EVNTSEL_USR		(1 << 16)
-#define P6_EVENT_CPU_CLOCKS_NOT_HALTED	0x79
-#define P6_NMI_EVENT		P6_EVENT_CPU_CLOCKS_NOT_HALTED
-
-static int setup_p6_watchdog(unsigned nmi_hz)
-{
-	unsigned int perfctr_msr, evntsel_msr;
-	unsigned int evntsel;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	perfctr_msr = wd_ops->perfctr;
-	evntsel_msr = wd_ops->evntsel;
-
-	/* KVM doesn't implement this MSR */
-	if (wrmsr_safe(perfctr_msr, 0, 0) < 0)
-		return 0;
-
-	evntsel = P6_EVNTSEL_INT
-		| P6_EVNTSEL_OS
-		| P6_EVNTSEL_USR
-		| P6_NMI_EVENT;
-
-	/* setup the timer */
-	wrmsr(evntsel_msr, evntsel, 0);
-	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-	write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0", nmi_hz);
-
-	/* initialize the wd struct before enabling */
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  /* unused */
-
-	/* ok, everything is initialized, announce that we're set */
-	cpu_nmi_set_wd_enabled();
-
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= P6_EVNTSEL0_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
-
-	return 1;
-}
-
-static void __kprobes p6_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
-	/*
-	 * P6 based Pentium M need to re-unmask
-	 * the apic vector but it doesn't hurt
-	 * other P6 variant.
-	 * ArchPerfom/Core Duo also needs this
-	 */
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-
-	/* P6/ARCH_PERFMON has 32 bit counter write */
-	write_watchdog_counter32(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops p6_wd_ops = {
-	.reserve	= single_msr_reserve,
-	.unreserve	= single_msr_unreserve,
-	.setup		= setup_p6_watchdog,
-	.rearm		= p6_rearm,
-	.stop		= single_msr_stop_watchdog,
-	.perfctr	= MSR_P6_PERFCTR0,
-	.evntsel	= MSR_P6_EVNTSEL0,
-	.checkbit	= 1ULL << 39,
-};
-
-/*
- * Intel P4 performance counters.
- * By far the most complicated of all.
- */
-#define MSR_P4_MISC_ENABLE_PERF_AVAIL	(1 << 7)
-#define P4_ESCR_EVENT_SELECT(N)	((N) << 25)
-#define P4_ESCR_OS		(1 << 3)
-#define P4_ESCR_USR		(1 << 2)
-#define P4_CCCR_OVF_PMI0	(1 << 26)
-#define P4_CCCR_OVF_PMI1	(1 << 27)
-#define P4_CCCR_THRESHOLD(N)	((N) << 20)
-#define P4_CCCR_COMPLEMENT	(1 << 19)
-#define P4_CCCR_COMPARE		(1 << 18)
-#define P4_CCCR_REQUIRED	(3 << 16)
-#define P4_CCCR_ESCR_SELECT(N)	((N) << 13)
-#define P4_CCCR_ENABLE		(1 << 12)
-#define P4_CCCR_OVF 		(1 << 31)
-
-#define P4_CONTROLS 18
-static unsigned int p4_controls[18] = {
-	MSR_P4_BPU_CCCR0,
-	MSR_P4_BPU_CCCR1,
-	MSR_P4_BPU_CCCR2,
-	MSR_P4_BPU_CCCR3,
-	MSR_P4_MS_CCCR0,
-	MSR_P4_MS_CCCR1,
-	MSR_P4_MS_CCCR2,
-	MSR_P4_MS_CCCR3,
-	MSR_P4_FLAME_CCCR0,
-	MSR_P4_FLAME_CCCR1,
-	MSR_P4_FLAME_CCCR2,
-	MSR_P4_FLAME_CCCR3,
-	MSR_P4_IQ_CCCR0,
-	MSR_P4_IQ_CCCR1,
-	MSR_P4_IQ_CCCR2,
-	MSR_P4_IQ_CCCR3,
-	MSR_P4_IQ_CCCR4,
-	MSR_P4_IQ_CCCR5,
-};
-/*
- * Set up IQ_COUNTER0 to behave like a clock, by having IQ_CCCR0 filter
- * CRU_ESCR0 (with any non-null event selector) through a complemented
- * max threshold. [IA32-Vol3, Section 14.9.9]
- */
-static int setup_p4_watchdog(unsigned nmi_hz)
-{
-	unsigned int perfctr_msr, evntsel_msr, cccr_msr;
-	unsigned int evntsel, cccr_val;
-	unsigned int misc_enable, dummy;
-	unsigned int ht_num;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	rdmsr(MSR_IA32_MISC_ENABLE, misc_enable, dummy);
-	if (!(misc_enable & MSR_P4_MISC_ENABLE_PERF_AVAIL))
-		return 0;
-
-#ifdef CONFIG_SMP
-	/* detect which hyperthread we are on */
-	if (smp_num_siblings == 2) {
-		unsigned int ebx, apicid;
-
-		ebx = cpuid_ebx(1);
-		apicid = (ebx >> 24) & 0xff;
-		ht_num = apicid & 1;
-	} else
-#endif
-		ht_num = 0;
-
-	/*
-	 * performance counters are shared resources
-	 * assign each hyperthread its own set
-	 * (re-use the ESCR0 register, seems safe
-	 * and keeps the cccr_val the same)
-	 */
-	if (!ht_num) {
-		/* logical cpu 0 */
-		perfctr_msr = MSR_P4_IQ_PERFCTR0;
-		evntsel_msr = MSR_P4_CRU_ESCR0;
-		cccr_msr = MSR_P4_IQ_CCCR0;
-		cccr_val = P4_CCCR_OVF_PMI0 | P4_CCCR_ESCR_SELECT(4);
-
-		/*
-		 * If we're on the kdump kernel or other situation, we may
-		 * still have other performance counter registers set to
-		 * interrupt and they'll keep interrupting forever because
-		 * of the P4_CCCR_OVF quirk. So we need to ACK all the
-		 * pending interrupts and disable all the registers here,
-		 * before reenabling the NMI delivery. Refer to p4_rearm()
-		 * about the P4_CCCR_OVF quirk.
-		 */
-		if (reset_devices) {
-			unsigned int low, high;
-			int i;
-
-			for (i = 0; i < P4_CONTROLS; i++) {
-				rdmsr(p4_controls[i], low, high);
-				low &= ~(P4_CCCR_ENABLE | P4_CCCR_OVF);
-				wrmsr(p4_controls[i], low, high);
-			}
-		}
-	} else {
-		/* logical cpu 1 */
-		perfctr_msr = MSR_P4_IQ_PERFCTR1;
-		evntsel_msr = MSR_P4_CRU_ESCR0;
-		cccr_msr = MSR_P4_IQ_CCCR1;
-
-		/* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */
-		if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4)
-			cccr_val = P4_CCCR_OVF_PMI0;
-		else
-			cccr_val = P4_CCCR_OVF_PMI1;
-		cccr_val |= P4_CCCR_ESCR_SELECT(4);
-	}
-
-	evntsel = P4_ESCR_EVENT_SELECT(0x3F)
-		| P4_ESCR_OS
-		| P4_ESCR_USR;
-
-	cccr_val |= P4_CCCR_THRESHOLD(15)
-		 | P4_CCCR_COMPLEMENT
-		 | P4_CCCR_COMPARE
-		 | P4_CCCR_REQUIRED;
-
-	wrmsr(evntsel_msr, evntsel, 0);
-	wrmsr(cccr_msr, cccr_val, 0);
-	write_watchdog_counter(perfctr_msr, "P4_IQ_COUNTER0", nmi_hz);
-
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = cccr_msr;
-
-	/* ok, everything is initialized, announce that we're set */
-	cpu_nmi_set_wd_enabled();
-
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	cccr_val |= P4_CCCR_ENABLE;
-	wrmsr(cccr_msr, cccr_val, 0);
-	return 1;
-}
-
-static void stop_p4_watchdog(void)
-{
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-	wrmsr(wd->cccr_msr, 0, 0);
-	wrmsr(wd->evntsel_msr, 0, 0);
-}
-
-static int p4_reserve(void)
-{
-	if (!reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR0))
-		return 0;
-#ifdef CONFIG_SMP
-	if (smp_num_siblings > 1 && !reserve_perfctr_nmi(MSR_P4_IQ_PERFCTR1))
-		goto fail1;
-#endif
-	if (!reserve_evntsel_nmi(MSR_P4_CRU_ESCR0))
-		goto fail2;
-	/* RED-PEN why is ESCR1 not reserved here? */
-	return 1;
- fail2:
-#ifdef CONFIG_SMP
-	if (smp_num_siblings > 1)
-		release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
- fail1:
-#endif
-	release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
-	return 0;
-}
-
-static void p4_unreserve(void)
-{
-#ifdef CONFIG_SMP
-	if (smp_num_siblings > 1)
-		release_perfctr_nmi(MSR_P4_IQ_PERFCTR1);
-#endif
-	release_evntsel_nmi(MSR_P4_CRU_ESCR0);
-	release_perfctr_nmi(MSR_P4_IQ_PERFCTR0);
-}
-
-static void __kprobes p4_rearm(struct nmi_watchdog_ctlblk *wd, unsigned nmi_hz)
-{
-	unsigned dummy;
-	/*
-	 * P4 quirks:
-	 * - An overflown perfctr will assert its interrupt
-	 *   until the OVF flag in its CCCR is cleared.
-	 * - LVTPC is masked on interrupt and must be
-	 *   unmasked by the LVTPC handler.
-	 */
-	rdmsrl(wd->cccr_msr, dummy);
-	dummy &= ~P4_CCCR_OVF;
-	wrmsrl(wd->cccr_msr, dummy);
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	/* start the cycle over again */
-	write_watchdog_counter(wd->perfctr_msr, NULL, nmi_hz);
-}
-
-static const struct wd_ops p4_wd_ops = {
-	.reserve	= p4_reserve,
-	.unreserve	= p4_unreserve,
-	.setup		= setup_p4_watchdog,
-	.rearm		= p4_rearm,
-	.stop		= stop_p4_watchdog,
-	/* RED-PEN this is wrong for the other sibling */
-	.perfctr	= MSR_P4_BPU_PERFCTR0,
-	.evntsel	= MSR_P4_BSU_ESCR0,
-	.checkbit	= 1ULL << 39,
-};
-
-/*
- * Watchdog using the Intel architected PerfMon.
- * Used for Core2 and hopefully all future Intel CPUs.
- */
-#define ARCH_PERFMON_NMI_EVENT_SEL	ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
-#define ARCH_PERFMON_NMI_EVENT_UMASK	ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
-
-static struct wd_ops intel_arch_wd_ops;
-
-static int setup_intel_arch_watchdog(unsigned nmi_hz)
-{
-	unsigned int ebx;
-	union cpuid10_eax eax;
-	unsigned int unused;
-	unsigned int perfctr_msr, evntsel_msr;
-	unsigned int evntsel;
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-
-	/*
-	 * Check whether the Architectural PerfMon supports
-	 * Unhalted Core Cycles Event or not.
-	 * NOTE: Corresponding bit = 0 in ebx indicates event present.
-	 */
-	cpuid(10, &(eax.full), &ebx, &unused, &unused);
-	if ((eax.split.mask_length <
-			(ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
-	    (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
-		return 0;
-
-	perfctr_msr = wd_ops->perfctr;
-	evntsel_msr = wd_ops->evntsel;
-
-	wrmsrl(perfctr_msr, 0UL);
-
-	evntsel = ARCH_PERFMON_EVENTSEL_INT
-		| ARCH_PERFMON_EVENTSEL_OS
-		| ARCH_PERFMON_EVENTSEL_USR
-		| ARCH_PERFMON_NMI_EVENT_SEL
-		| ARCH_PERFMON_NMI_EVENT_UMASK;
-
-	/* setup the timer */
-	wrmsr(evntsel_msr, evntsel, 0);
-	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
-	write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0", nmi_hz);
-
-	wd->perfctr_msr = perfctr_msr;
-	wd->evntsel_msr = evntsel_msr;
-	wd->cccr_msr = 0;  /* unused */
-
-	/* ok, everything is initialized, announce that we're set */
-	cpu_nmi_set_wd_enabled();
-
-	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	evntsel |= ARCH_PERFMON_EVENTSEL_ENABLE;
-	wrmsr(evntsel_msr, evntsel, 0);
-	intel_arch_wd_ops.checkbit = 1ULL << (eax.split.bit_width - 1);
-	return 1;
-}
-
-static struct wd_ops intel_arch_wd_ops __read_mostly = {
-	.reserve	= single_msr_reserve,
-	.unreserve	= single_msr_unreserve,
-	.setup		= setup_intel_arch_watchdog,
-	.rearm		= p6_rearm,
-	.stop		= single_msr_stop_watchdog,
-	.perfctr	= MSR_ARCH_PERFMON_PERFCTR1,
-	.evntsel	= MSR_ARCH_PERFMON_EVENTSEL1,
-};
-
-static void probe_nmi_watchdog(void)
-{
-	switch (boot_cpu_data.x86_vendor) {
-	case X86_VENDOR_AMD:
-		if (boot_cpu_data.x86 == 6 ||
-		    (boot_cpu_data.x86 >= 0xf && boot_cpu_data.x86 <= 0x15))
-			wd_ops = &k7_wd_ops;
-		return;
-	case X86_VENDOR_INTEL:
-		/* 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) ||
-		    ((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;
-		}
-		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
-			wd_ops = &intel_arch_wd_ops;
-			break;
-		}
-		switch (boot_cpu_data.x86) {
-		case 6:
-			if (boot_cpu_data.x86_model > 13)
-				return;
-
-			wd_ops = &p6_wd_ops;
-			break;
-		case 15:
-			wd_ops = &p4_wd_ops;
-			break;
-		default:
-			return;
-		}
-		break;
-	}
-}
-
-/* Interface to nmi.c */
-
-int lapic_watchdog_init(unsigned nmi_hz)
-{
-	if (!wd_ops) {
-		probe_nmi_watchdog();
-		if (!wd_ops) {
-			printk(KERN_INFO "NMI watchdog: CPU not supported\n");
-			return -1;
-		}
-
-		if (!wd_ops->reserve()) {
-			printk(KERN_ERR
-				"NMI watchdog: cannot reserve perfctrs\n");
-			return -1;
-		}
-	}
-
-	if (!(wd_ops->setup(nmi_hz))) {
-		printk(KERN_ERR "Cannot setup NMI watchdog on CPU %d\n",
-		       raw_smp_processor_id());
-		return -1;
-	}
-
-	return 0;
-}
-
-void lapic_watchdog_stop(void)
-{
-	if (wd_ops)
-		wd_ops->stop();
-}
-
-unsigned lapic_adjust_nmi_hz(unsigned hz)
-{
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-	if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
-	    wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR1)
-		hz = adjust_for_32bit_ctr(hz);
-	return hz;
-}
-
-int __kprobes lapic_wd_event(unsigned nmi_hz)
-{
-	struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
-	u64 ctr;
-
-	rdmsrl(wd->perfctr_msr, ctr);
-	if (ctr & wd_ops->checkbit) /* perfctr still running? */
-		return 0;
-
-	wd_ops->rearm(wd, nmi_hz);
-	return 1;
-}