Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (146 commits)
  tools, perf: Documentation for the power events API
  perf: Add calls to suspend trace point
  perf script: Make some lists static
  perf script: Use the default lost event handler
  perf session: Warn about errors when processing pipe events too
  perf tools: Fix perf_event.h header usage
  perf test: Clarify some error reports in the open syscall test
  x86, NMI: Add touch_nmi_watchdog to io_check_error delay
  x86: Avoid calling arch_trigger_all_cpu_backtrace() at the same time
  x86: Only call smp_processor_id in non-preempt cases
  perf timechart: Adjust perf timechart to the new power events
  perf: Clean up power events by introducing new, more generic ones
  perf: Do not export power_frequency, but power_start event
  perf test: Add test for counting open syscalls
  perf evsel: Auto allocate resources needed for some methods
  perf evsel: Use {cpu,thread}_map to shorten list of parameters
  perf tools: Refactor all_tids to hold nr and the map
  perf tools: Refactor cpumap to hold nr and the map
  perf evsel: Introduce per cpu and per thread open helpers
  perf evsel: Steal the counter reading routines from stat
  ...

38 files changed, 444 insertions, 1547 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 76561d20ea2..4a2adaa9aef 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -180,8 +180,15 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * On the local CPU you need to be protected again NMI or MCE handlers seeing an
  * inconsistent instruction while you patch.
  */
+struct text_poke_param {
+	void *addr;
+	const void *opcode;
+	size_t len;
+};
+
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
+extern void text_poke_smp_batch(struct text_poke_param *params, int n);
 
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 #define IDEAL_NOP_SIZE_5 5
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 13b0ebaa512..ba870bb6dd8 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -15,10 +15,6 @@ static inline int irq_canonicalize(int irq)
 	return ((irq == 2) ? 9 : irq);
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG
-#endif
-
 #ifdef CONFIG_X86_32
 extern void irq_ctx_init(int cpu);
 #else
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 5bdfca86581..f23eb252846 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -28,7 +28,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_registers(struct pt_regs *regs);
 extern void show_trace(struct task_struct *t, struct pt_regs *regs,
-		       unsigned long *sp, unsigned long bp);
+		       unsigned long *sp);
 extern void __show_regs(struct pt_regs *regs, int all);
 extern void show_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6b89f5e8602..86030f63ba0 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -123,6 +123,10 @@
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
 
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL		0xc0010200
+#define MSR_F15H_PERF_CTR		0xc0010201
+
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
 #define FAM10H_MMIO_CONF_ENABLE		(1<<0)
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 932f0f86b4b..c4021b95351 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -5,41 +5,15 @@
 #include <asm/irq.h>
 #include <asm/io.h>
 
-#ifdef ARCH_HAS_NMI_WATCHDOG
-
-/**
- * do_nmi_callback
- *
- * Check to see if a callback exists and execute it.  Return 1
- * if the handler exists and was handled successfully.
- */
-int do_nmi_callback(struct pt_regs *regs, int cpu);
+#ifdef CONFIG_X86_LOCAL_APIC
 
 extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
-extern int check_nmi_watchdog(void);
-#if !defined(CONFIG_LOCKUP_DETECTOR)
-extern int nmi_watchdog_enabled;
-#endif
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
 extern void release_perfctr_nmi(unsigned int);
 extern int reserve_evntsel_nmi(unsigned int);
 extern void release_evntsel_nmi(unsigned int);
 
-extern void setup_apic_nmi_watchdog(void *);
-extern void stop_apic_nmi_watchdog(void *);
-extern void disable_timer_nmi_watchdog(void);
-extern void enable_timer_nmi_watchdog(void);
-extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
-extern void cpu_nmi_set_wd_enabled(void);
-
-extern atomic_t nmi_active;
-extern unsigned int nmi_watchdog;
-#define NMI_NONE	0
-#define NMI_IO_APIC	1
-#define NMI_LOCAL_APIC	2
-#define NMI_INVALID	3
-
 struct ctl_table;
 extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
@@ -47,33 +21,8 @@ extern int unknown_nmi_panic;
 
 void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
-
-static inline void localise_nmi_watchdog(void)
-{
-	if (nmi_watchdog == NMI_IO_APIC)
-		nmi_watchdog = NMI_LOCAL_APIC;
-}
-
-/* check if nmi_watchdog is active (ie was specified at boot) */
-static inline int nmi_watchdog_active(void)
-{
-	/*
-	 * actually it should be:
-	 * 	return (nmi_watchdog == NMI_LOCAL_APIC ||
-	 * 		nmi_watchdog == NMI_IO_APIC)
-	 * but since they are power of two we could use a
-	 * cheaper way --cvg
-	 */
-	return nmi_watchdog & (NMI_LOCAL_APIC | NMI_IO_APIC);
-}
 #endif
 
-void lapic_watchdog_stop(void);
-int lapic_watchdog_init(unsigned nmi_hz);
-int lapic_wd_event(unsigned nmi_hz);
-unsigned lapic_adjust_nmi_hz(unsigned hz);
-void disable_lapic_nmi_watchdog(void);
-void enable_lapic_nmi_watchdog(void);
 void stop_nmi(void);
 void restart_nmi(void);
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 550e26b1dbb..d9d4dae305f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -125,7 +125,6 @@ union cpuid10_edx {
 #define IBS_OP_MAX_CNT_EXT	0x007FFFFFULL	/* not a register bit mask */
 
 #ifdef CONFIG_PERF_EVENTS
-extern void init_hw_perf_events(void);
 extern void perf_events_lapic_init(void);
 
 #define PERF_EVENT_INDEX_OFFSET			0
@@ -156,7 +155,6 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 }
 
 #else
-static inline void init_hw_perf_events(void)		{ }
 static inline void perf_events_lapic_init(void)	{ }
 #endif
 
diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index a70cd216be5..295e2ff18a6 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -744,14 +744,6 @@ enum P4_ESCR_EMASKS {
 };
 
 /*
- * P4 PEBS specifics (Replay Event only)
- *
- * Format (bits):
- *   0-6: metric from P4_PEBS_METRIC enum
- *    7 : reserved
- *    8 : reserved
- * 9-11 : reserved
- *
  * Note we have UOP and PEBS bits reserved for now
  * just in case if we will need them once
  */
@@ -788,5 +780,60 @@ enum P4_PEBS_METRIC {
 	P4_PEBS_METRIC__max
 };
 
+/*
+ * Notes on internal configuration of ESCR+CCCR tuples
+ *
+ * Since P4 has quite the different architecture of
+ * performance registers in compare with "architectural"
+ * once and we have on 64 bits to keep configuration
+ * of performance event, the following trick is used.
+ *
+ * 1) Since both ESCR and CCCR registers have only low
+ *    32 bits valuable, we pack them into a single 64 bit
+ *    configuration. Low 32 bits of such config correspond
+ *    to low 32 bits of CCCR register and high 32 bits
+ *    correspond to low 32 bits of ESCR register.
+ *
+ * 2) The meaning of every bit of such config field can
+ *    be found in Intel SDM but it should be noted that
+ *    we "borrow" some reserved bits for own usage and
+ *    clean them or set to a proper value when we do
+ *    a real write to hardware registers.
+ *
+ * 3) The format of bits of config is the following
+ *    and should be either 0 or set to some predefined
+ *    values:
+ *
+ *    Low 32 bits
+ *    -----------
+ *      0-6: P4_PEBS_METRIC enum
+ *     7-11:                    reserved
+ *       12:                    reserved (Enable)
+ *    13-15:                    reserved (ESCR select)
+ *    16-17: Active Thread
+ *       18: Compare
+ *       19: Complement
+ *    20-23: Threshold
+ *       24: Edge
+ *       25:                    reserved (FORCE_OVF)
+ *       26:                    reserved (OVF_PMI_T0)
+ *       27:                    reserved (OVF_PMI_T1)
+ *    28-29:                    reserved
+ *       30:                    reserved (Cascade)
+ *       31:                    reserved (OVF)
+ *
+ *    High 32 bits
+ *    ------------
+ *        0:                    reserved (T1_USR)
+ *        1:                    reserved (T1_OS)
+ *        2:                    reserved (T0_USR)
+ *        3:                    reserved (T0_OS)
+ *        4: Tag Enable
+ *      5-8: Tag Value
+ *     9-24: Event Mask (may use P4_ESCR_EMASK_BIT helper)
+ *    25-30: enum P4_EVENTS
+ *       31:                    reserved (HT thread)
+ */
+
 #endif /* PERF_EVENT_P4_H */
 
diff --git a/arch/x86/include/asm/smpboot_hooks.h b/arch/x86/include/asm/smpboot_hooks.h
index 1def6011490..6c22bf353f2 100644
--- a/arch/x86/include/asm/smpboot_hooks.h
+++ b/arch/x86/include/asm/smpboot_hooks.h
@@ -48,7 +48,6 @@ static inline void __init smpboot_setup_io_apic(void)
 		setup_IO_APIC();
 	else {
 		nr_ioapics = 0;
-		localise_nmi_watchdog();
 	}
 #endif
 }
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index 2b16a2ad23d..52b5c7ed360 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -7,6 +7,7 @@
 #define _ASM_X86_STACKTRACE_H
 
 #include <linux/uaccess.h>
+#include <linux/ptrace.h>
 
 extern int kstack_depth_to_print;
 
@@ -46,7 +47,7 @@ struct stacktrace_ops {
 };
 
 void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
+		unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data);
 
 #ifdef CONFIG_X86_32
@@ -57,13 +58,39 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
+#ifdef CONFIG_FRAME_POINTER
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+	unsigned long bp;
+
+	if (regs)
+		return regs->bp;
+
+	if (task == current) {
+		/* Grab bp right from our regs */
+		get_bp(bp);
+		return bp;
+	}
+
+	/* bp is the last reg pushed by switch_to */
+	return *(unsigned long *)task->thread.sp;
+}
+#else
+static inline unsigned long
+stack_frame(struct task_struct *task, struct pt_regs *regs)
+{
+	return 0;
+}
+#endif
+
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl);
+		   unsigned long *stack, char *log_lvl);
 
 extern void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *sp, unsigned long bp, char *log_lvl);
+		   unsigned long *sp, char *log_lvl);
 
 extern unsigned int code_bytes;
 
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 5469630b27f..fa7b9176b76 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -10,12 +10,6 @@
 unsigned long long native_sched_clock(void);
 extern int recalibrate_cpu_khz(void);
 
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
-extern int timer_ack;
-#else
-# define timer_ack (0)
-#endif
-
 extern int no_timer_check;
 
 /* Accelerators for sched_clock()
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5079f24c955..553d0b0d639 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -591,17 +591,21 @@ static atomic_t stop_machine_first;
 static int wrote_text;
 
 struct text_poke_params {
-	void *addr;
-	const void *opcode;
-	size_t len;
+	struct text_poke_param *params;
+	int nparams;
 };
 
 static int __kprobes stop_machine_text_poke(void *data)
 {
 	struct text_poke_params *tpp = data;
+	struct text_poke_param *p;
+	int i;
 
 	if (atomic_dec_and_test(&stop_machine_first)) {
-		text_poke(tpp->addr, tpp->opcode, tpp->len);
+		for (i = 0; i < tpp->nparams; i++) {
+			p = &tpp->params[i];
+			text_poke(p->addr, p->opcode, p->len);
+		}
 		smp_wmb();	/* Make sure other cpus see that this has run */
 		wrote_text = 1;
 	} else {
@@ -610,8 +614,12 @@ static int __kprobes stop_machine_text_poke(void *data)
 		smp_mb();	/* Load wrote_text before following execution */
 	}
 
-	flush_icache_range((unsigned long)tpp->addr,
-			   (unsigned long)tpp->addr + tpp->len);
+	for (i = 0; i < tpp->nparams; i++) {
+		p = &tpp->params[i];
+		flush_icache_range((unsigned long)p->addr,
+				   (unsigned long)p->addr + p->len);
+	}
+
 	return 0;
 }
 
@@ -631,10 +639,13 @@ static int __kprobes stop_machine_text_poke(void *data)
 void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 {
 	struct text_poke_params tpp;
+	struct text_poke_param p;
 
-	tpp.addr = addr;
-	tpp.opcode = opcode;
-	tpp.len = len;
+	p.addr = addr;
+	p.opcode = opcode;
+	p.len = len;
+	tpp.params = &p;
+	tpp.nparams = 1;
 	atomic_set(&stop_machine_first, 1);
 	wrote_text = 0;
 	/* Use __stop_machine() because the caller already got online_cpus. */
@@ -642,6 +653,26 @@ void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
 	return addr;
 }
 
+/**
+ * text_poke_smp_batch - Update instructions on a live kernel on SMP
+ * @params: an array of text_poke parameters
+ * @n: the number of elements in params.
+ *
+ * Modify multi-byte instruction by using stop_machine() on SMP. Since the
+ * stop_machine() is heavy task, it is better to aggregate text_poke requests
+ * and do it once if possible.
+ *
+ * Note: Must be called under get_online_cpus() and text_mutex.
+ */
+void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+{
+	struct text_poke_params tpp = {.params = params, .nparams = n};
+
+	atomic_set(&stop_machine_first, 1);
+	wrote_text = 0;
+	stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+}
+
 #if defined(CONFIG_DYNAMIC_FTRACE) || defined(HAVE_JUMP_LABEL)
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 910f20b457c..3966b564ea4 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -3,10 +3,7 @@
 #
 
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o probe_$(BITS).o ipi.o
-ifneq ($(CONFIG_HARDLOCKUP_DETECTOR),y)
-obj-$(CONFIG_X86_LOCAL_APIC)	+= nmi.o
-endif
-obj-$(CONFIG_HARDLOCKUP_DETECTOR)	+= hw_nmi.o
+obj-y				+= hw_nmi.o
 
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_SMP)		+= ipi.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 78218135b48..fb7657822aa 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -31,7 +31,6 @@
 #include <linux/init.h>
 #include <linux/cpu.h>
 #include <linux/dmi.h>
-#include <linux/nmi.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
 
@@ -799,11 +798,7 @@ void __init setup_boot_APIC_clock(void)
 	 * PIT/HPET going.  Otherwise register lapic as a dummy
 	 * device.
 	 */
-	if (nmi_watchdog != NMI_IO_APIC)
-		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-	else
-		pr_warning("APIC timer registered as dummy,"
-			" due to nmi_watchdog=%d!\n", nmi_watchdog);
+	lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 
 	/* Setup the lapic or request the broadcast */
 	setup_APIC_timer();
@@ -1387,7 +1382,6 @@ void __cpuinit end_local_APIC_setup(void)
 	}
 #endif
 
-	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
 
 	/*
@@ -1758,17 +1752,10 @@ int __init APIC_init_uniprocessor(void)
 		setup_IO_APIC();
 	else {
 		nr_ioapics = 0;
-		localise_nmi_watchdog();
 	}
-#else
-	localise_nmi_watchdog();
 #endif
 
 	x86_init.timers.setup_percpu_clockev();
-#ifdef CONFIG_X86_64
-	check_nmi_watchdog();
-#endif
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 62f6e1e55b9..72ec29e1ae0 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,20 +17,31 @@
 #include <linux/nmi.h>
 #include <linux/module.h>
 
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
 u64 hw_nmi_get_sample_period(void)
 {
 	return (u64)(cpu_khz) * 1000 * 60;
 }
+#endif
 
-#ifdef ARCH_HAS_NMI_WATCHDOG
-
+#ifdef arch_trigger_all_cpu_backtrace
 /* For reliability, we're prepared to waste bits here. */
 static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
 
+/* "in progress" flag of arch_trigger_all_cpu_backtrace */
+static unsigned long backtrace_flag;
+
 void arch_trigger_all_cpu_backtrace(void)
 {
 	int i;
 
+	if (test_and_set_bit(0, &backtrace_flag))
+		/*
+		 * If there is already a trigger_all_cpu_backtrace() in progress
+		 * (backtrace_flag == 1), don't output double cpu dump infos.
+		 */
+		return;
+
 	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
 
 	printk(KERN_INFO "sending NMI to all CPUs:\n");
@@ -42,6 +53,9 @@ void arch_trigger_all_cpu_backtrace(void)
 			break;
 		mdelay(1);
 	}
+
+	clear_bit(0, &backtrace_flag);
+	smp_mb__after_clear_bit();
 }
 
 static int __kprobes
@@ -50,7 +64,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 {
 	struct die_args *args = __args;
 	struct pt_regs *regs;
-	int cpu = smp_processor_id();
+	int cpu;
 
 	switch (cmd) {
 	case DIE_NMI:
@@ -62,6 +76,7 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 	}
 
 	regs = args->regs;
+	cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
 		static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
@@ -91,18 +106,3 @@ static int __init register_trigger_all_cpu_backtrace(void)
 }
 early_initcall(register_trigger_all_cpu_backtrace);
 #endif
-
-/* STUB calls to mimic old nmi_watchdog behaviour */
-#if defined(CONFIG_X86_LOCAL_APIC)
-unsigned int nmi_watchdog = NMI_NONE;
-EXPORT_SYMBOL(nmi_watchdog);
-void acpi_nmi_enable(void) { return; }
-void acpi_nmi_disable(void) { return; }
-#endif
-atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
-EXPORT_SYMBOL(nmi_active);
-int unknown_nmi_panic;
-void cpu_nmi_set_wd_enabled(void) { return; }
-void stop_apic_nmi_watchdog(void *unused) { return; }
-void setup_apic_nmi_watchdog(void *unused) { return; }
-int __init check_nmi_watchdog(void) { return 0; }
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fadcd743a74..16c2db8750a 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -54,7 +54,6 @@
 #include <asm/dma.h>
 #include <asm/timer.h>
 #include <asm/i8259.h>
-#include <asm/nmi.h>
 #include <asm/msidef.h>
 #include <asm/hypertransport.h>
 #include <asm/setup.h>
@@ -2642,24 +2641,6 @@ static void lapic_register_intr(int irq)
 				      "edge");
 }
 
-static void __init setup_nmi(void)
-{
-	/*
-	 * Dirty trick to enable the NMI watchdog ...
-	 * We put the 8259A master into AEOI mode and
-	 * unmask on all local APICs LVT0 as NMI.
-	 *
-	 * The idea to use the 8259A in AEOI mode ('8259A Virtual Wire')
-	 * is from Maciej W. Rozycki - so we do not have to EOI from
-	 * the NMI handler or the timer interrupt.
-	 */
-	apic_printk(APIC_VERBOSE, KERN_INFO "activating NMI Watchdog ...");
-
-	enable_NMI_through_LVT0();
-
-	apic_printk(APIC_VERBOSE, " done.\n");
-}
-
 /*
  * This looks a bit hackish but it's about the only one way of sending
  * a few INTA cycles to 8259As and any associated glue logic.  ICR does
@@ -2765,15 +2746,6 @@ static inline void __init check_timer(void)
 	 */
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
 	legacy_pic->init(1);
-#ifdef CONFIG_X86_32
-	{
-		unsigned int ver;
-
-		ver = apic_read(APIC_LVR);
-		ver = GET_APIC_VERSION(ver);
-		timer_ack = (nmi_watchdog == NMI_IO_APIC && !APIC_INTEGRATED(ver));
-	}
-#endif
 
 	pin1  = find_isa_irq_pin(0, mp_INT);
 	apic1 = find_isa_irq_apic(0, mp_INT);
@@ -2821,10 +2793,6 @@ static inline void __init check_timer(void)
 				unmask_ioapic(cfg);
 		}
 		if (timer_irq_works()) {
-			if (nmi_watchdog == NMI_IO_APIC) {
-				setup_nmi();
-				legacy_pic->unmask(0);
-			}
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
 			goto out;
@@ -2850,11 +2818,6 @@ static inline void __init check_timer(void)
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
 			timer_through_8259 = 1;
-			if (nmi_watchdog == NMI_IO_APIC) {
-				legacy_pic->mask(0);
-				setup_nmi();
-				legacy_pic->unmask(0);
-			}
 			goto out;
 		}
 		/*
@@ -2866,15 +2829,6 @@ static inline void __init check_timer(void)
 		apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
 	}
 
-	if (nmi_watchdog == NMI_IO_APIC) {
-		apic_printk(APIC_QUIET, KERN_WARNING "timer doesn't work "
-			    "through the IO-APIC - disabling NMI Watchdog!\n");
-		nmi_watchdog = NMI_NONE;
-	}
-#ifdef CONFIG_X86_32
-	timer_ack = 0;
-#endif
-
 	apic_printk(APIC_QUIET, KERN_INFO
 		    "...trying to set up timer as Virtual Wire IRQ...\n");
 
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
deleted file mode 100644
index c90041ccb74..00000000000
--- a/arch/x86/kernel/apic/nmi.c
+++ /dev/null
@@ -1,567 +0,0 @@
-/*
- *  NMI watchdog support on APIC systems
- *
- *  Started by Ingo Molnar <mingo@redhat.com>
- *
- *  Fixes:
- *  Mikael Pettersson	: AMD K7 support for local APIC NMI watchdog.
- *  Mikael Pettersson	: Power Management for local APIC NMI watchdog.
- *  Mikael Pettersson	: Pentium 4 support for local APIC NMI watchdog.
- *  Pavel Machek and
- *  Mikael Pettersson	: PM converted to driver model. Disable/enable API.
- */
-
-#include <asm/apic.h>
-
-#include <linux/nmi.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/sysdev.h>
-#include <linux/sysctl.h>
-#include <linux/percpu.h>
-#include <linux/kprobes.h>
-#include <linux/cpumask.h>
-#include <linux/kernel_stat.h>
-#include <linux/kdebug.h>
-#include <linux/smp.h>
-
-#include <asm/i8259.h>
-#include <asm/io_apic.h>
-#include <asm/proto.h>
-#include <asm/timer.h>
-
-#include <asm/mce.h>
-
-#include <asm/mach_traps.h>
-
-int unknown_nmi_panic;
-int nmi_watchdog_enabled;
-
-/* For reliability, we're prepared to waste bits here. */
-static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
-
-/* nmi_active:
- * >0: the lapic NMI watchdog is active, but can be disabled
- * <0: the lapic NMI watchdog has not been set up, and cannot
- *     be enabled
- *  0: the lapic NMI watchdog is disabled, but can be enabled
- */
-atomic_t nmi_active = ATOMIC_INIT(0);		/* oprofile uses this */
-EXPORT_SYMBOL(nmi_active);
-
-unsigned int nmi_watchdog = NMI_NONE;
-EXPORT_SYMBOL(nmi_watchdog);
-
-static int panic_on_timeout;
-
-static unsigned int nmi_hz = HZ;
-static DEFINE_PER_CPU(short, wd_enabled);
-static int endflag __initdata;
-
-static inline unsigned int get_nmi_count(int cpu)
-{
-	return per_cpu(irq_stat, cpu).__nmi_count;
-}
-
-static inline int mce_in_progress(void)
-{
-#if defined(CONFIG_X86_MCE)
-	return atomic_read(&mce_entry) > 0;
-#endif
-	return 0;
-}
-
-/*
- * Take the local apic timer and PIT/HPET into account. We don't
- * know which one is active, when we have highres/dyntick on
- */
-static inline unsigned int get_timer_irqs(int cpu)
-{
-	return per_cpu(irq_stat, cpu).apic_timer_irqs +
-		per_cpu(irq_stat, cpu).irq0_irqs;
-}
-
-#ifdef CONFIG_SMP
-/*
- * The performance counters used by NMI_LOCAL_APIC don't trigger when
- * the CPU is idle. To make sure the NMI watchdog really ticks on all
- * CPUs during the test make them busy.
- */
-static __init void nmi_cpu_busy(void *data)
-{
-	local_irq_enable_in_hardirq();
-	/*
-	 * Intentionally don't use cpu_relax here. This is
-	 * to make sure that the performance counter really ticks,
-	 * even if there is a simulator or similar that catches the
-	 * pause instruction. On a real HT machine this is fine because
-	 * all other CPUs are busy with "useless" delay loops and don't
-	 * care if they get somewhat less cycles.
-	 */
-	while (endflag == 0)
-		mb();
-}
-#endif
-
-static void report_broken_nmi(int cpu, unsigned int *prev_nmi_count)
-{
-	printk(KERN_CONT "\n");
-
-	printk(KERN_WARNING
-		"WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n",
-			cpu, prev_nmi_count[cpu], get_nmi_count(cpu));
-
-	printk(KERN_WARNING
-		"Please report this to bugzilla.kernel.org,\n");
-	printk(KERN_WARNING
-		"and attach the output of the 'dmesg' command.\n");
-
-	per_cpu(wd_enabled, cpu) = 0;
-	atomic_dec(&nmi_active);
-}
-
-static void __acpi_nmi_disable(void *__unused)
-{
-	apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
-}
-
-int __init check_nmi_watchdog(void)
-{
-	unsigned int *prev_nmi_count;
-	int cpu;
-
-	if (!nmi_watchdog_active() || !atomic_read(&nmi_active))
-		return 0;
-
-	prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(int), GFP_KERNEL);
-	if (!prev_nmi_count)
-		goto error;
-
-	printk(KERN_INFO "Testing NMI watchdog ... ");
-
-#ifdef CONFIG_SMP
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		smp_call_function(nmi_cpu_busy, (void *)&endflag, 0);
-#endif
-
-	for_each_possible_cpu(cpu)
-		prev_nmi_count[cpu] = get_nmi_count(cpu);
-	local_irq_enable();
-	mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
-
-	for_each_online_cpu(cpu) {
-		if (!per_cpu(wd_enabled, cpu))
-			continue;
-		if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
-			report_broken_nmi(cpu, prev_nmi_count);
-	}
-	endflag = 1;
-	if (!atomic_read(&nmi_active)) {
-		kfree(prev_nmi_count);
-		atomic_set(&nmi_active, -1);
-		goto error;
-	}
-	printk("OK.\n");
-
-	/*
-	 * now that we know it works we can reduce NMI frequency to
-	 * something more reasonable; makes a difference in some configs
-	 */
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		nmi_hz = lapic_adjust_nmi_hz(1);
-
-	kfree(prev_nmi_count);
-	return 0;
-error:
-	if (nmi_watchdog == NMI_IO_APIC) {
-		if (!timer_through_8259)
-			legacy_pic->mask(0);
-		on_each_cpu(__acpi_nmi_disable, NULL, 1);
-	}
-
-#ifdef CONFIG_X86_32
-	timer_ack = 0;
-#endif
-	return -1;
-}
-
-static int __init setup_nmi_watchdog(char *str)
-{
-	unsigned int nmi;
-
-	if (!strncmp(str, "panic", 5)) {
-		panic_on_timeout = 1;
-		str = strchr(str, ',');
-		if (!str)
-			return 1;
-		++str;
-	}
-
-	if (!strncmp(str, "lapic", 5))
-		nmi_watchdog = NMI_LOCAL_APIC;
-	else if (!strncmp(str, "ioapic", 6))
-		nmi_watchdog = NMI_IO_APIC;
-	else {
-		get_option(&str, &nmi);
-		if (nmi >= NMI_INVALID)
-			return 0;
-		nmi_watchdog = nmi;
-	}
-
-	return 1;
-}
-__setup("nmi_watchdog=", setup_nmi_watchdog);
-
-/*
- * Suspend/resume support
- */
-#ifdef CONFIG_PM
-
-static int nmi_pm_active; /* nmi_active before suspend */
-
-static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
-{
-	/* only CPU0 goes here, other CPUs should be offline */
-	nmi_pm_active = atomic_read(&nmi_active);
-	stop_apic_nmi_watchdog(NULL);
-	BUG_ON(atomic_read(&nmi_active) != 0);
-	return 0;
-}
-
-static int lapic_nmi_resume(struct sys_device *dev)
-{
-	/* only CPU0 goes here, other CPUs should be offline */
-	if (nmi_pm_active > 0) {
-		setup_apic_nmi_watchdog(NULL);
-		touch_nmi_watchdog();
-	}
-	return 0;
-}
-
-static struct sysdev_class nmi_sysclass = {
-	.name		= "lapic_nmi",
-	.resume		= lapic_nmi_resume,
-	.suspend	= lapic_nmi_suspend,
-};
-
-static struct sys_device device_lapic_nmi = {
-	.id	= 0,
-	.cls	= &nmi_sysclass,
-};
-
-static int __init init_lapic_nmi_sysfs(void)
-{
-	int error;
-
-	/*
-	 * should really be a BUG_ON but b/c this is an
-	 * init call, it just doesn't work.  -dcz
-	 */
-	if (nmi_watchdog != NMI_LOCAL_APIC)
-		return 0;
-
-	if (atomic_read(&nmi_active) < 0)
-		return 0;
-
-	error = sysdev_class_register(&nmi_sysclass);
-	if (!error)
-		error = sysdev_register(&device_lapic_nmi);
-	return error;
-}
-
-/* must come after the local APIC's device_initcall() */
-late_initcall(init_lapic_nmi_sysfs);
-
-#endif	/* CONFIG_PM */
-
-static void __acpi_nmi_enable(void *__unused)
-{
-	apic_write(APIC_LVT0, APIC_DM_NMI);
-}
-
-/*
- * Enable timer based NMIs on all CPUs:
- */
-void acpi_nmi_enable(void)
-{
-	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-		on_each_cpu(__acpi_nmi_enable, NULL, 1);
-}
-
-/*
- * Disable timer based NMIs on all CPUs:
- */
-void acpi_nmi_disable(void)
-{
-	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
-		on_each_cpu(__acpi_nmi_disable, NULL, 1);
-}
-
-/*
- * This function is called as soon the LAPIC NMI watchdog driver has everything
- * in place and it's ready to check if the NMIs belong to the NMI watchdog
- */
-void cpu_nmi_set_wd_enabled(void)
-{
-	__get_cpu_var(wd_enabled) = 1;
-}
-
-void setup_apic_nmi_watchdog(void *unused)
-{
-	if (__get_cpu_var(wd_enabled))
-		return;
-
-	/* cheap hack to support suspend/resume */
-	/* if cpu0 is not active neither should the other cpus */
-	if (smp_processor_id() != 0 && atomic_read(&nmi_active) <= 0)
-		return;
-
-	switch (nmi_watchdog) {
-	case NMI_LOCAL_APIC:
-		if (lapic_watchdog_init(nmi_hz) < 0) {
-			__get_cpu_var(wd_enabled) = 0;
-			return;
-		}
-		/* FALL THROUGH */
-	case NMI_IO_APIC:
-		__get_cpu_var(wd_enabled) = 1;
-		atomic_inc(&nmi_active);
-	}
-}
-
-void stop_apic_nmi_watchdog(void *unused)
-{
-	/* only support LOCAL and IO APICs for now */
-	if (!nmi_watchdog_active())
-		return;
-	if (__get_cpu_var(wd_enabled) == 0)
-		return;
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		lapic_watchdog_stop();
-	else
-		__acpi_nmi_disable(NULL);
-	__get_cpu_var(wd_enabled) = 0;
-	atomic_dec(&nmi_active);
-}
-
-/*
- * the best way to detect whether a CPU has a 'hard lockup' problem
- * is to check it's local APIC timer IRQ counts. If they are not
- * changing then that CPU has some problem.
- *
- * as these watchdog NMI IRQs are generated on every CPU, we only
- * have to check the current processor.
- *
- * since NMIs don't listen to _any_ locks, we have to be extremely
- * careful not to rely on unsafe variables. The printk might lock
- * up though, so we have to break up any console locks first ...
- * [when there will be more tty-related locks, break them up here too!]
- */
-
-static DEFINE_PER_CPU(unsigned, last_irq_sum);
-static DEFINE_PER_CPU(long, alert_counter);
-static DEFINE_PER_CPU(int, nmi_touch);
-
-void touch_nmi_watchdog(void)
-{
-	if (nmi_watchdog_active()) {
-		unsigned cpu;
-
-		/*
-		 * Tell other CPUs to reset their alert counters. We cannot
-		 * do it ourselves because the alert count increase is not
-		 * atomic.
-		 */
-		for_each_present_cpu(cpu) {
-			if (per_cpu(nmi_touch, cpu) != 1)
-				per_cpu(nmi_touch, cpu) = 1;
-		}
-	}
-
-	/*
-	 * Tickle the softlockup detector too:
-	 */
-	touch_softlockup_watchdog();
-}
-EXPORT_SYMBOL(touch_nmi_watchdog);
-
-notrace __kprobes int
-nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
-{
-	/*
-	 * Since current_thread_info()-> is always on the stack, and we
-	 * always switch the stack NMI-atomically, it's safe to use
-	 * smp_processor_id().
-	 */
-	unsigned int sum;
-	int touched = 0;
-	int cpu = smp_processor_id();
-	int rc = 0;
-
-	sum = get_timer_irqs(cpu);
-
-	if (__get_cpu_var(nmi_touch)) {
-		__get_cpu_var(nmi_touch) = 0;
-		touched = 1;
-	}
-
-	/* We can be called before check_nmi_watchdog, hence NULL check. */
-	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		static DEFINE_RAW_SPINLOCK(lock); /* Serialise the printks */
-
-		raw_spin_lock(&lock);
-		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
-		show_regs(regs);
-		dump_stack();
-		raw_spin_unlock(&lock);
-		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
-
-		rc = 1;
-	}
-
-	/* Could check oops_in_progress here too, but it's safer not to */
-	if (mce_in_progress())
-		touched = 1;
-
-	/* if the none of the timers isn't firing, this cpu isn't doing much */
-	if (!touched && __get_cpu_var(last_irq_sum) == sum) {
-		/*
-		 * Ayiee, looks like this CPU is stuck ...
-		 * wait a few IRQs (5 seconds) before doing the oops ...
-		 */
-		__this_cpu_inc(alert_counter);
-		if (__this_cpu_read(alert_counter) == 5 * nmi_hz)
-			/*
-			 * die_nmi will return ONLY if NOTIFY_STOP happens..
-			 */
-			die_nmi("BUG: NMI Watchdog detected LOCKUP",
-				regs, panic_on_timeout);
-	} else {
-		__get_cpu_var(last_irq_sum) = sum;
-		__this_cpu_write(alert_counter, 0);
-	}
-
-	/* see if the nmi watchdog went off */
-	if (!__get_cpu_var(wd_enabled))
-		return rc;
-	switch (nmi_watchdog) {
-	case NMI_LOCAL_APIC:
-		rc |= lapic_wd_event(nmi_hz);
-		break;
-	case NMI_IO_APIC:
-		/*
-		 * don't know how to accurately check for this.
-		 * just assume it was a watchdog timer interrupt
-		 * This matches the old behaviour.
-		 */
-		rc = 1;
-		break;
-	}
-	return rc;
-}
-
-#ifdef CONFIG_SYSCTL
-
-static void enable_ioapic_nmi_watchdog_single(void *unused)
-{
-	__get_cpu_var(wd_enabled) = 1;
-	atomic_inc(&nmi_active);
-	__acpi_nmi_enable(NULL);
-}
-
-static void enable_ioapic_nmi_watchdog(void)
-{
-	on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
-	touch_nmi_watchdog();
-}
-
-static void disable_ioapic_nmi_watchdog(void)
-{
-	on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
-}
-
-static int __init setup_unknown_nmi_panic(char *str)
-{
-	unknown_nmi_panic = 1;
-	return 1;
-}
-__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-
-static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
-{
-	unsigned char reason = get_nmi_reason();
-	char buf[64];
-
-	sprintf(buf, "NMI received for unknown reason %02x\n", reason);
-	die_nmi(buf, regs, 1); /* Always panic here */
-	return 0;
-}
-
-/*
- * proc handler for /proc/sys/kernel/nmi
- */
-int proc_nmi_enabled(struct ctl_table *table, int write,
-			void __user *buffer, size_t *length, loff_t *ppos)
-{
-	int old_state;
-
-	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
-	old_state = nmi_watchdog_enabled;
-	proc_dointvec(table, write, buffer, length, ppos);
-	if (!!old_state == !!nmi_watchdog_enabled)
-		return 0;
-
-	if (atomic_read(&nmi_active) < 0 || !nmi_watchdog_active()) {
-		printk(KERN_WARNING
-			"NMI watchdog is permanently disabled\n");
-		return -EIO;
-	}
-
-	if (nmi_watchdog == NMI_LOCAL_APIC) {
-		if (nmi_watchdog_enabled)
-			enable_lapic_nmi_watchdog();
-		else
-			disable_lapic_nmi_watchdog();
-	} else if (nmi_watchdog == NMI_IO_APIC) {
-		if (nmi_watchdog_enabled)
-			enable_ioapic_nmi_watchdog();
-		else
-			disable_ioapic_nmi_watchdog();
-	} else {
-		printk(KERN_WARNING
-			"NMI watchdog doesn't know what hardware to touch\n");
-		return -EIO;
-	}
-	return 0;
-}
-
-#endif /* CONFIG_SYSCTL */
-
-int do_nmi_callback(struct pt_regs *regs, int cpu)
-{
-#ifdef CONFIG_SYSCTL
-	if (unknown_nmi_panic)
-		return unknown_nmi_panic_callback(regs, cpu);
-#endif
-	return 0;
-}
-
-void arch_trigger_all_cpu_backtrace(void)
-{
-	int i;
-
-	cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
-
-	printk(KERN_INFO "sending NMI to all CPUs:\n");
-	apic->send_IPI_all(NMI_VECTOR);
-
-	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
-	for (i = 0; i < 10 * 1000; i++) {
-		if (cpumask_empty(to_cpumask(backtrace_mask)))
-			break;
-		mdelay(1);
-	}
-}
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/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6d75b9145b1..0a360d14659 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
@@ -384,15 +375,53 @@ static void release_pmc_hardware(void) {}
 static bool check_hw_exists(void)
 {
 	u64 val, val_new = 0;
-	int ret = 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 = checking_wrmsrl(x86_pmu.perfctr, val);
 	ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
 	if (ret || val != val_new)
-		return false;
+		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);
@@ -451,7 +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);
@@ -1362,7 +1391,7 @@ 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;
@@ -1377,20 +1406,18 @@ 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()) {
-		pr_cont("Broken PMU hardware detected, software events only.\n");
-		return;
-	}
+	if (!check_hw_exists())
+		return 0;
 
 	pr_cont("%s PMU driver.\n", x86_pmu.name);
 
@@ -1438,9 +1465,12 @@ 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)
 {
@@ -1686,7 +1716,7 @@ 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 e421b8cd694..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]
@@ -275,7 +273,7 @@ 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;
@@ -285,7 +283,7 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	if (!nb)
 		return NULL;
 
-	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..24e390e40f2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -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/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;
-}
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 6e8752c1bd5..8474c998cbd 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -175,21 +175,21 @@ static const struct stacktrace_ops print_trace_ops = {
 
 void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl)
+		unsigned long *stack, char *log_lvl)
 {
 	printk("%sCall Trace:\n", log_lvl);
-	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+	dump_trace(task, regs, stack, &print_trace_ops, log_lvl);
 }
 
 void show_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp)
+		unsigned long *stack)
 {
-	show_trace_log_lvl(task, regs, stack, bp, "");
+	show_trace_log_lvl(task, regs, stack, "");
 }
 
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
-	show_stack_log_lvl(task, NULL, sp, 0, "");
+	show_stack_log_lvl(task, NULL, sp, "");
 }
 
 /*
@@ -210,7 +210,7 @@ void dump_stack(void)
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
-	show_trace(NULL, NULL, &stack, bp);
+	show_trace(NULL, NULL, &stack);
 }
 EXPORT_SYMBOL(dump_stack);
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 1bc7f75a5bd..74cc1eda384 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,11 +17,12 @@
 #include <asm/stacktrace.h>
 
 
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
+void dump_trace(struct task_struct *task,
+		struct pt_regs *regs, unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data)
 {
 	int graph = 0;
+	unsigned long bp;
 
 	if (!task)
 		task = current;
@@ -34,18 +35,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			stack = (unsigned long *)task->thread.sp;
 	}
 
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp) {
-		if (task == current) {
-			/* Grab bp right from our regs */
-			get_bp(bp);
-		} else {
-			/* bp is the last reg pushed by switch_to */
-			bp = *(unsigned long *) task->thread.sp;
-		}
-	}
-#endif
-
+	bp = stack_frame(task, regs);
 	for (;;) {
 		struct thread_info *context;
 
@@ -65,7 +55,7 @@ EXPORT_SYMBOL(dump_trace);
 
 void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *sp, unsigned long bp, char *log_lvl)
+		   unsigned long *sp, char *log_lvl)
 {
 	unsigned long *stack;
 	int i;
@@ -87,7 +77,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		touch_nmi_watchdog();
 	}
 	printk(KERN_CONT "\n");
-	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+	show_trace_log_lvl(task, regs, sp, log_lvl);
 }
 
 
@@ -112,8 +102,7 @@ void show_registers(struct pt_regs *regs)
 		u8 *ip;
 
 		printk(KERN_EMERG "Stack:\n");
-		show_stack_log_lvl(NULL, regs, &regs->sp,
-				0, KERN_EMERG);
+		show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
 
 		printk(KERN_EMERG "Code: ");
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6a340485249..64101335de1 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -139,8 +139,8 @@ fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-void dump_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
+void dump_trace(struct task_struct *task,
+		struct pt_regs *regs, unsigned long *stack,
 		const struct stacktrace_ops *ops, void *data)
 {
 	const unsigned cpu = get_cpu();
@@ -149,6 +149,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	unsigned used = 0;
 	struct thread_info *tinfo;
 	int graph = 0;
+	unsigned long bp;
 
 	if (!task)
 		task = current;
@@ -160,18 +161,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			stack = (unsigned long *)task->thread.sp;
 	}
 
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp) {
-		if (task == current) {
-			/* Grab bp right from our regs */
-			get_bp(bp);
-		} else {
-			/* bp is the last reg pushed by switch_to */
-			bp = *(unsigned long *) task->thread.sp;
-		}
-	}
-#endif
-
+	bp = stack_frame(task, regs);
 	/*
 	 * Print function call entries in all stacks, starting at the
 	 * current stack address. If the stacks consist of nested
@@ -235,7 +225,7 @@ EXPORT_SYMBOL(dump_trace);
 
 void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		   unsigned long *sp, unsigned long bp, char *log_lvl)
+		   unsigned long *sp, char *log_lvl)
 {
 	unsigned long *irq_stack_end;
 	unsigned long *irq_stack;
@@ -279,7 +269,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	preempt_enable();
 
 	printk(KERN_CONT "\n");
-	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
+	show_trace_log_lvl(task, regs, sp, log_lvl);
 }
 
 void show_registers(struct pt_regs *regs)
@@ -308,7 +298,7 @@ void show_registers(struct pt_regs *regs)
 
 		printk(KERN_EMERG "Stack:\n");
 		show_stack_log_lvl(NULL, regs, (unsigned long *)sp,
-				regs->bp, KERN_EMERG);
+				   KERN_EMERG);
 
 		printk(KERN_EMERG "Code: ");
 
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 1cbd54c0df9..5940282bd2f 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -1184,6 +1184,10 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op,
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
+	/* This is possible if op is under delayed unoptimizing */
+	if (kprobe_disabled(&op->kp))
+		return;
+
 	preempt_disable();
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(&op->kp);
@@ -1401,10 +1405,16 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
 	return 0;
 }
 
-/* Replace a breakpoint (int3) with a relative jump.  */
-int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
+#define MAX_OPTIMIZE_PROBES 256
+static struct text_poke_param *jump_poke_params;
+static struct jump_poke_buffer {
+	u8 buf[RELATIVEJUMP_SIZE];
+} *jump_poke_bufs;
+
+static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
+					    u8 *insn_buf,
+					    struct optimized_kprobe *op)
 {
-	unsigned char jmp_code[RELATIVEJUMP_SIZE];
 	s32 rel = (s32)((long)op->optinsn.insn -
 			((long)op->kp.addr + RELATIVEJUMP_SIZE));
 
@@ -1412,16 +1422,79 @@ int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
 	memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
 	       RELATIVE_ADDR_SIZE);
 
-	jmp_code[0] = RELATIVEJUMP_OPCODE;
-	*(s32 *)(&jmp_code[1]) = rel;
+	insn_buf[0] = RELATIVEJUMP_OPCODE;
+	*(s32 *)(&insn_buf[1]) = rel;
+
+	tprm->addr = op->kp.addr;
+	tprm->opcode = insn_buf;
+	tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Replace breakpoints (int3) with relative jumps.
+ * Caller must call with locking kprobe_mutex and text_mutex.
+ */
+void __kprobes arch_optimize_kprobes(struct list_head *oplist)
+{
+	struct optimized_kprobe *op, *tmp;
+	int c = 0;
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
+		WARN_ON(kprobe_disabled(&op->kp));
+		/* Setup param */
+		setup_optimize_kprobe(&jump_poke_params[c],
+				      jump_poke_bufs[c].buf, op);
+		list_del_init(&op->list);
+		if (++c >= MAX_OPTIMIZE_PROBES)
+			break;
+	}
 
 	/*
 	 * text_poke_smp doesn't support NMI/MCE code modifying.
 	 * However, since kprobes itself also doesn't support NMI/MCE
 	 * code probing, it's not a problem.
 	 */
-	text_poke_smp(op->kp.addr, jmp_code, RELATIVEJUMP_SIZE);
-	return 0;
+	text_poke_smp_batch(jump_poke_params, c);
+}
+
+static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
+					      u8 *insn_buf,
+					      struct optimized_kprobe *op)
+{
+	/* Set int3 to first byte for kprobes */
+	insn_buf[0] = BREAKPOINT_INSTRUCTION;
+	memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+	tprm->addr = op->kp.addr;
+	tprm->opcode = insn_buf;
+	tprm->len = RELATIVEJUMP_SIZE;
+}
+
+/*
+ * Recover original instructions and breakpoints from relative jumps.
+ * Caller must call with locking kprobe_mutex.
+ */
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+				    struct list_head *done_list)
+{
+	struct optimized_kprobe *op, *tmp;
+	int c = 0;
+
+	list_for_each_entry_safe(op, tmp, oplist, list) {
+		/* Setup param */
+		setup_unoptimize_kprobe(&jump_poke_params[c],
+					jump_poke_bufs[c].buf, op);
+		list_move(&op->list, done_list);
+		if (++c >= MAX_OPTIMIZE_PROBES)
+			break;
+	}
+
+	/*
+	 * text_poke_smp doesn't support NMI/MCE code modifying.
+	 * However, since kprobes itself also doesn't support NMI/MCE
+	 * code probing, it's not a problem.
+	 */
+	text_poke_smp_batch(jump_poke_params, c);
 }
 
 /* Replace a relative jump with a breakpoint (int3).  */
@@ -1453,11 +1526,35 @@ static int  __kprobes setup_detour_execution(struct kprobe *p,
 	}
 	return 0;
 }
+
+static int __kprobes init_poke_params(void)
+{
+	/* Allocate code buffer and parameter array */
+	jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
+				 MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+	if (!jump_poke_bufs)
+		return -ENOMEM;
+
+	jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
+				   MAX_OPTIMIZE_PROBES, GFP_KERNEL);
+	if (!jump_poke_params) {
+		kfree(jump_poke_bufs);
+		jump_poke_bufs = NULL;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+#else	/* !CONFIG_OPTPROBES */
+static int __kprobes init_poke_params(void)
+{
+	return 0;
+}
 #endif
 
 int __init arch_init_kprobes(void)
 {
-	return 0;
+	return init_poke_params();
 }
 
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 57d1868a86a..c852041bfc3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -91,8 +91,7 @@ void exit_thread(void)
 void show_regs(struct pt_regs *regs)
 {
 	show_registers(regs);
-	show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs),
-		   regs->bp);
+	show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
 }
 
 void show_regs_common(void)
@@ -374,6 +373,7 @@ void default_idle(void)
 {
 	if (hlt_use_halt()) {
 		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
+		trace_cpu_idle(1, smp_processor_id());
 		current_thread_info()->status &= ~TS_POLLING;
 		/*
 		 * TS_POLLING-cleared state must be visible before we
@@ -444,6 +444,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
 	trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id());
+	trace_cpu_idle((ax>>4)+1, smp_processor_id());
 	if (!need_resched()) {
 		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
@@ -460,6 +461,7 @@ static void mwait_idle(void)
 {
 	if (!need_resched()) {
 		trace_power_start(POWER_CSTATE, 1, smp_processor_id());
+		trace_cpu_idle(1, smp_processor_id());
 		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
@@ -481,10 +483,12 @@ static void mwait_idle(void)
 static void poll_idle(void)
 {
 	trace_power_start(POWER_CSTATE, 0, smp_processor_id());
+	trace_cpu_idle(0, smp_processor_id());
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
-	trace_power_end(0);
+	trace_power_end(smp_processor_id());
+	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 96586c3cbbb..4b9befa0e34 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -113,8 +113,8 @@ void cpu_idle(void)
 			stop_critical_timings();
 			pm_idle();
 			start_critical_timings();
-
 			trace_power_end(smp_processor_id());
+			trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 		}
 		tick_nohz_restart_sched_tick();
 		preempt_enable_no_resched();
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index b3d7a3a04f3..4c818a73839 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -142,6 +142,8 @@ void cpu_idle(void)
 			start_critical_timings();
 
 			trace_power_end(smp_processor_id());
+			trace_cpu_idle(PWR_EVENT_EXIT,
+				       smp_processor_id());
 
 			/* In many cases the interrupt that ended idle
 			   has already called exit_idle. But some idle
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 083e99d1b7d..68f61ac632e 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -281,6 +281,13 @@ static void __cpuinit smp_callin(void)
 	 */
 	smp_store_cpu_info(cpuid);
 
+	/*
+	 * This must be done before setting cpu_online_mask
+	 * or calling notify_cpu_starting.
+	 */
+	set_cpu_sibling_map(raw_smp_processor_id());
+	wmb();
+
 	notify_cpu_starting(cpuid);
 
 	/*
@@ -316,16 +323,6 @@ notrace static void __cpuinit start_secondary(void *unused)
 	 */
 	check_tsc_sync_target();
 
-	if (nmi_watchdog == NMI_IO_APIC) {
-		legacy_pic->mask(0);
-		enable_NMI_through_LVT0();
-		legacy_pic->unmask(0);
-	}
-
-	/* This must be done before setting cpu_online_mask */
-	set_cpu_sibling_map(raw_smp_processor_id());
-	wmb();
-
 	/*
 	 * We need to hold call_lock, so there is no inconsistency
 	 * between the time smp_call_function() determines number of
@@ -1061,8 +1058,6 @@ static int __init smp_sanity_check(unsigned max_cpus)
 		printk(KERN_INFO "SMP mode deactivated.\n");
 		smpboot_clear_io_apic();
 
-		localise_nmi_watchdog();
-
 		connect_bsp_APIC();
 		setup_local_APIC();
 		end_local_APIC_setup();
@@ -1196,7 +1191,6 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 #ifdef CONFIG_X86_IO_APIC
 	setup_ioapic_dest();
 #endif
-	check_nmi_watchdog();
 	mtrr_aps_init();
 }
 
@@ -1341,8 +1335,6 @@ int native_cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
-	if (nmi_watchdog == NMI_LOCAL_APIC)
-		stop_apic_nmi_watchdog(NULL);
 	clear_local_APIC();
 
 	cpu_disable_common();
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index b53c525368a..938c8e10a19 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -73,22 +73,22 @@ static const struct stacktrace_ops save_stack_ops_nosched = {
  */
 void save_stack_trace(struct stack_trace *trace)
 {
-	dump_trace(current, NULL, NULL, 0, &save_stack_ops, trace);
+	dump_trace(current, NULL, NULL, &save_stack_ops, trace);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
-void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp)
+void save_stack_trace_regs(struct stack_trace *trace, struct pt_regs *regs)
 {
-	dump_trace(current, NULL, NULL, bp, &save_stack_ops, trace);
+	dump_trace(current, regs, NULL, &save_stack_ops, trace);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	dump_trace(tsk, NULL, NULL, 0, &save_stack_ops_nosched, trace);
+	dump_trace(tsk, NULL, NULL, &save_stack_ops_nosched, trace);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index fb5cc5e14cf..25a28a24593 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -22,10 +22,6 @@
 #include <asm/hpet.h>
 #include <asm/time.h>
 
-#if defined(CONFIG_X86_32) && defined(CONFIG_X86_IO_APIC)
-int timer_ack;
-#endif
-
 #ifdef CONFIG_X86_64
 volatile unsigned long __jiffies __section_jiffies = INITIAL_JIFFIES;
 #endif
@@ -63,20 +59,6 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 	/* Keep nmi watchdog up to date */
 	inc_irq_stat(irq0_irqs);
 
-	/* Optimized out for !IO_APIC and x86_64 */
-	if (timer_ack) {
-		/*
-		 * Subtle, when I/O APICs are used we have to ack timer IRQ
-		 * manually to deassert NMI lines for the watchdog if run
-		 * on an 82489DX-based system.
-		 */
-		raw_spin_lock(&i8259A_lock);
-		outb(0x0c, PIC_MASTER_OCW3);
-		/* Ack the IRQ; AEOI will end it automatically. */
-		inb(PIC_MASTER_POLL);
-		raw_spin_unlock(&i8259A_lock);
-	}
-
 	global_clock_event->event_handler(global_clock_event);
 
 	/* MCA bus quirk: Acknowledge irq0 by setting bit 7 in port 0x61 */
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index cb838ca42c9..c76aaca5694 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -83,6 +83,8 @@ EXPORT_SYMBOL_GPL(used_vectors);
 
 static int ignore_nmis;
 
+int unknown_nmi_panic;
+
 static inline void conditional_sti(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
@@ -300,6 +302,13 @@ gp_in_kernel:
 	die("general protection fault", regs, error_code);
 }
 
+static int __init setup_unknown_nmi_panic(char *str)
+{
+	unknown_nmi_panic = 1;
+	return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
+
 static notrace __kprobes void
 mem_parity_error(unsigned char reason, struct pt_regs *regs)
 {
@@ -342,9 +351,11 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 	reason = (reason & 0xf) | 8;
 	outb(reason, 0x61);
 
-	i = 2000;
-	while (--i)
-		udelay(1000);
+	i = 20000;
+	while (--i) {
+		touch_nmi_watchdog();
+		udelay(100);
+	}
 
 	reason &= ~8;
 	outb(reason, 0x61);
@@ -371,7 +382,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 			reason, smp_processor_id());
 
 	printk(KERN_EMERG "Do you have a strange power saving mode enabled?\n");
-	if (panic_on_unrecovered_nmi)
+	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
 		panic("NMI: Not continuing");
 
 	printk(KERN_EMERG "Dazed and confused, but trying to continue\n");
@@ -397,20 +408,8 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 		if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
 							== NOTIFY_STOP)
 			return;
-
-#ifndef CONFIG_LOCKUP_DETECTOR
-		/*
-		 * Ok, so this is none of the documented NMI sources,
-		 * so it must be the NMI watchdog.
-		 */
-		if (nmi_watchdog_tick(regs, reason))
-			return;
-		if (!do_nmi_callback(regs, cpu))
-#endif /* !CONFIG_LOCKUP_DETECTOR */
-			unknown_nmi_error(reason, regs);
-#else
-		unknown_nmi_error(reason, regs);
 #endif
+		unknown_nmi_error(reason, regs);
 
 		return;
 	}
@@ -446,14 +445,12 @@ do_nmi(struct pt_regs *regs, long error_code)
 
 void stop_nmi(void)
 {
-	acpi_nmi_disable();
 	ignore_nmis++;
 }
 
 void restart_nmi(void)
 {
 	ignore_nmis--;
-	acpi_nmi_enable();
 }
 
 /* May run on IST stack. */
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
index af3b6c8a436..704a37ceddd 100644
--- a/arch/x86/mm/kmemcheck/error.c
+++ b/arch/x86/mm/kmemcheck/error.c
@@ -185,7 +185,7 @@ void kmemcheck_error_save(enum kmemcheck_shadow state,
 	e->trace.entries = e->trace_entries;
 	e->trace.max_entries = ARRAY_SIZE(e->trace_entries);
 	e->trace.skip = 0;
-	save_stack_trace_bp(&e->trace, regs->bp);
+	save_stack_trace_regs(&e->trace, regs);
 
 	/* Round address down to nearest 16 bytes */
 	shadow_copy = kmemcheck_shadow_lookup(address
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index 2d49d4e19a3..72cbec14d78 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -126,7 +126,7 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 	if (!user_mode_vm(regs)) {
 		unsigned long stack = kernel_stack_pointer(regs);
 		if (depth)
-			dump_trace(NULL, regs, (unsigned long *)stack, 0,
+			dump_trace(NULL, regs, (unsigned long *)stack,
 				   &backtrace_ops, &depth);
 		return;
 	}
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 4e8baad36d3..358c8b9c96a 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -732,6 +732,9 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 		case 0x14:
 			cpu_type = "x86-64/family14h";
 			break;
+		case 0x15:
+			cpu_type = "x86-64/family15h";
+			break;
 		default:
 			return -ENODEV;
 		}
diff --git a/arch/x86/oprofile/nmi_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index e3ecb71b579..0636dd93cef 100644
--- a/arch/x86/oprofile/nmi_timer_int.c
+++ b/arch/x86/oprofile/nmi_timer_int.c
@@ -58,9 +58,6 @@ static void timer_stop(void)
 
 int __init op_nmi_timer_init(struct oprofile_operations *ops)
 {
-	if ((nmi_watchdog != NMI_IO_APIC) || (atomic_read(&nmi_active) <= 0))
-		return -ENODEV;
-
 	ops->start = timer_start;
 	ops->stop = timer_stop;
 	ops->cpu_type = "timer";
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 7d90d47655b..51104b33fd5 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -29,11 +29,12 @@
 #include "op_x86_model.h"
 #include "op_counter.h"
 
-#define NUM_COUNTERS 4
+#define NUM_COUNTERS		4
+#define NUM_COUNTERS_F15H	6
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
-#define NUM_VIRT_COUNTERS 32
+#define NUM_VIRT_COUNTERS	32
 #else
-#define NUM_VIRT_COUNTERS NUM_COUNTERS
+#define NUM_VIRT_COUNTERS	0
 #endif
 
 #define OP_EVENT_MASK			0x0FFF
@@ -41,7 +42,8 @@
 
 #define MSR_AMD_EVENTSEL_RESERVED	((0xFFFFFCF0ULL<<32)|(1ULL<<21))
 
-static unsigned long reset_value[NUM_VIRT_COUNTERS];
+static int num_counters;
+static unsigned long reset_value[OP_MAX_COUNTER];
 
 #define IBS_FETCH_SIZE			6
 #define IBS_OP_SIZE			12
@@ -387,7 +389,7 @@ static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
 	int i;
 
 	/* enable active counters */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		int virt = op_x86_phys_to_virt(i);
 		if (!reset_value[virt])
 			continue;
@@ -406,7 +408,7 @@ static void op_amd_shutdown(struct op_msrs const * const msrs)
 {
 	int i;
 
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		if (!msrs->counters[i].addr)
 			continue;
 		release_perfctr_nmi(MSR_K7_PERFCTR0 + i);
@@ -418,7 +420,7 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
 {
 	int i;
 
-	for (i = 0; i < NUM_COUNTERS; i++) {
+	for (i = 0; i < num_counters; i++) {
 		if (!reserve_perfctr_nmi(MSR_K7_PERFCTR0 + i))
 			goto fail;
 		if (!reserve_evntsel_nmi(MSR_K7_EVNTSEL0 + i)) {
@@ -426,8 +428,13 @@ static int op_amd_fill_in_addresses(struct op_msrs * const msrs)
 			goto fail;
 		}
 		/* both registers must be reserved */
-		msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
-		msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
+		if (num_counters == NUM_COUNTERS_F15H) {
+			msrs->counters[i].addr = MSR_F15H_PERF_CTR + (i << 1);
+			msrs->controls[i].addr = MSR_F15H_PERF_CTL + (i << 1);
+		} else {
+			msrs->controls[i].addr = MSR_K7_EVNTSEL0 + i;
+			msrs->counters[i].addr = MSR_K7_PERFCTR0 + i;
+		}
 		continue;
 	fail:
 		if (!counter_config[i].enabled)
@@ -447,7 +454,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
 	int i;
 
 	/* setup reset_value */
-	for (i = 0; i < NUM_VIRT_COUNTERS; ++i) {
+	for (i = 0; i < OP_MAX_COUNTER; ++i) {
 		if (counter_config[i].enabled
 		    && msrs->counters[op_x86_virt_to_phys(i)].addr)
 			reset_value[i] = counter_config[i].count;
@@ -456,7 +463,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
 	}
 
 	/* clear all counters */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		if (!msrs->controls[i].addr)
 			continue;
 		rdmsrl(msrs->controls[i].addr, val);
@@ -472,7 +479,7 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
 	}
 
 	/* enable active counters */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		int virt = op_x86_phys_to_virt(i);
 		if (!reset_value[virt])
 			continue;
@@ -503,7 +510,7 @@ static int op_amd_check_ctrs(struct pt_regs * const regs,
 	u64 val;
 	int i;
 
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		int virt = op_x86_phys_to_virt(i);
 		if (!reset_value[virt])
 			continue;
@@ -526,7 +533,7 @@ static void op_amd_start(struct op_msrs const * const msrs)
 	u64 val;
 	int i;
 
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[op_x86_phys_to_virt(i)])
 			continue;
 		rdmsrl(msrs->controls[i].addr, val);
@@ -546,7 +553,7 @@ static void op_amd_stop(struct op_msrs const * const msrs)
 	 * Subtle: stop on all counters to avoid race with setting our
 	 * pm callback
 	 */
-	for (i = 0; i < NUM_COUNTERS; ++i) {
+	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[op_x86_phys_to_virt(i)])
 			continue;
 		rdmsrl(msrs->controls[i].addr, val);
@@ -706,18 +713,29 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
 	return 0;
 }
 
+struct op_x86_model_spec op_amd_spec;
+
 static int op_amd_init(struct oprofile_operations *ops)
 {
 	init_ibs();
 	create_arch_files = ops->create_files;
 	ops->create_files = setup_ibs_files;
+
+	if (boot_cpu_data.x86 == 0x15) {
+		num_counters = NUM_COUNTERS_F15H;
+	} else {
+		num_counters = NUM_COUNTERS;
+	}
+
+	op_amd_spec.num_counters = num_counters;
+	op_amd_spec.num_controls = num_counters;
+	op_amd_spec.num_virt_counters = max(num_counters, NUM_VIRT_COUNTERS);
+
 	return 0;
 }
 
 struct op_x86_model_spec op_amd_spec = {
-	.num_counters		= NUM_COUNTERS,
-	.num_controls		= NUM_COUNTERS,
-	.num_virt_counters	= NUM_VIRT_COUNTERS,
+	/* num_counters/num_controls filled in at runtime */
 	.reserved		= MSR_AMD_EVENTSEL_RESERVED,
 	.event_mask		= OP_EVENT_MASK,
 	.init			= op_amd_init,
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 182558dd551..9fadec07414 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -11,7 +11,7 @@
 #include <linux/oprofile.h>
 #include <linux/smp.h>
 #include <linux/ptrace.h>
-#include <linux/nmi.h>
+#include <asm/nmi.h>
 #include <asm/msr.h>
 #include <asm/fixmap.h>
 #include <asm/apic.h>