118 files changed, 2008 insertions, 2283 deletions
diff --git a/CREDITS b/CREDITS
index 41d8e63d5165..494b6e4746d7 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2365,8 +2365,6 @@ E: acme@redhat.com
 W: http://oops.ghostprotocols.net:81/blog/
 P: 1024D/9224DF01 D5DF E3BB E3C8 BCBB F8AD  841A B6AB 4681 9224 DF01
 D: IPX, LLC, DCCP, cyc2x, wl3501_cs, net/ hacks
-S: R. Brasílio Itiberê, 4270/1010 - Água Verde
-S: 80240-060 - Curitiba - Paraná
 S: Brazil
 N: Karsten Merker
diff --git a/MAINTAINERS b/MAINTAINERS
index 1a1c27b9c557..ed192f11ad23 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4612,7 +4612,7 @@ PERFORMANCE EVENTS SUBSYSTEM
 M:      Peter Zijlstra <a.p.zijlstra@chello.nl>
 M:      Paul Mackerras <paulus@samba.org>
 M:      Ingo Molnar <mingo@elte.hu>
-M:      Arnaldo Carvalho de Melo <acme@redhat.com>
+M:      Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
 S:      Supported
 F:      kernel/perf_event*.c
 F:      include/linux/perf_event.h
diff --git a/arch/alpha/include/asm/perf_event.h b/arch/alpha/include/asm/perf_event.h
index fe792ca818f6..5996e7a6757e 100644
--- a/arch/alpha/include/asm/perf_event.h
+++ b/arch/alpha/include/asm/perf_event.h
@@ -1,10 +1,4 @@
 #ifndef __ASM_ALPHA_PERF_EVENT_H
 #define __ASM_ALPHA_PERF_EVENT_H
-#ifdef CONFIG_PERF_EVENTS
-extern void init_hw_perf_events(void);
-#else
-static inline void init_hw_perf_events(void)    { }
-#endif
 #endif /* __ASM_ALPHA_PERF_EVENT_H */
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index 5f77afb88e89..4c8bb374eb0a 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -112,8 +112,6 @@ init_IRQ(void)
        wrent(entInt, 0);
        alpha_mv.init_irq();
-        init_hw_perf_events();
 }
 /*
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 1cc49683fb69..3283059b6e85 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/kdebug.h>
 #include <linux/mutex.h>
+#include <linux/init.h>
 #include <asm/hwrpb.h>
 #include <asm/atomic.h>
@@ -863,13 +864,13 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 /*
 * Init call to initialise performance events at kernel startup.
 */
-void __init init_hw_perf_events(void)
+int __init init_hw_perf_events(void)
 {
        pr_info("Performance events: ");
        if (!supported_cpu()) {
                pr_cont("No support for your CPU.\n");
-                return;
+                return 0;
        }
        pr_cont("Supported CPU type!\n");
@@ -882,5 +883,7 @@ void __init init_hw_perf_events(void)
        alpha_pmu = &ev67_pmu;
        perf_pmu_register(&pmu);
-}
+        return 0;
+}
+early_initcall(init_hw_perf_events);
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 07a50357492a..d45f70e5f2ee 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -3038,7 +3038,7 @@ init_hw_perf_events(void)
        return 0;
 }
-arch_initcall(init_hw_perf_events);
+early_initcall(init_hw_perf_events);
 /*
 * Callchain handling code.
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 5c7c6fc07565..183e0d226669 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1047,6 +1047,6 @@ init_hw_perf_events(void)
        return 0;
 }
-arch_initcall(init_hw_perf_events);
+early_initcall(init_hw_perf_events);
 #endif /* defined(CONFIG_CPU_MIPS32)... */
diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c
index 7c07de0d8943..b150b510510f 100644
--- a/arch/powerpc/kernel/e500-pmu.c
+++ b/arch/powerpc/kernel/e500-pmu.c
@@ -126,4 +126,4 @@ static int init_e500_pmu(void)
        return register_fsl_emb_pmu(&e500_pmu);
 }
-arch_initcall(init_e500_pmu);
+early_initcall(init_e500_pmu);
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
index 09d72028f317..2cc5e0301d0b 100644
--- a/arch/powerpc/kernel/mpc7450-pmu.c
+++ b/arch/powerpc/kernel/mpc7450-pmu.c
@@ -414,4 +414,4 @@ static int init_mpc7450_pmu(void)
        return register_power_pmu(&mpc7450_pmu);
 }
-arch_initcall(init_mpc7450_pmu);
+early_initcall(init_mpc7450_pmu);
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c
index 2a361cdda635..ead8b3c2649e 100644
--- a/arch/powerpc/kernel/power4-pmu.c
+++ b/arch/powerpc/kernel/power4-pmu.c
@@ -613,4 +613,4 @@ static int init_power4_pmu(void)
        return register_power_pmu(&power4_pmu);
 }
-arch_initcall(init_power4_pmu);
+early_initcall(init_power4_pmu);
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
index 199de527d411..eca0ac595cb6 100644
--- a/arch/powerpc/kernel/power5+-pmu.c
+++ b/arch/powerpc/kernel/power5+-pmu.c
@@ -682,4 +682,4 @@ static int init_power5p_pmu(void)
        return register_power_pmu(&power5p_pmu);
 }
-arch_initcall(init_power5p_pmu);
+early_initcall(init_power5p_pmu);
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
index 98b6a729a9dd..d5ff0f64a5e6 100644
--- a/arch/powerpc/kernel/power5-pmu.c
+++ b/arch/powerpc/kernel/power5-pmu.c
@@ -621,4 +621,4 @@ static int init_power5_pmu(void)
        return register_power_pmu(&power5_pmu);
 }
-arch_initcall(init_power5_pmu);
+early_initcall(init_power5_pmu);
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
index 84a607bda8fb..31603927e376 100644
--- a/arch/powerpc/kernel/power6-pmu.c
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -544,4 +544,4 @@ static int init_power6_pmu(void)
        return register_power_pmu(&power6_pmu);
 }
-arch_initcall(init_power6_pmu);
+early_initcall(init_power6_pmu);
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
index 852f7b7f6b40..593740fcb799 100644
--- a/arch/powerpc/kernel/power7-pmu.c
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -369,4 +369,4 @@ static int init_power7_pmu(void)
        return register_power_pmu(&power7_pmu);
 }
-arch_initcall(init_power7_pmu);
+early_initcall(init_power7_pmu);
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
index 3fee685de4df..9a6e093858fe 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -494,4 +494,4 @@ static int init_ppc970_pmu(void)
        return register_power_pmu(&ppc970_pmu);
 }
-arch_initcall(init_ppc970_pmu);
+early_initcall(init_ppc970_pmu);
diff --git a/arch/sh/kernel/cpu/sh4/perf_event.c b/arch/sh/kernel/cpu/sh4/perf_event.c
index dbf3b4bb71fe..748955df018d 100644
--- a/arch/sh/kernel/cpu/sh4/perf_event.c
+++ b/arch/sh/kernel/cpu/sh4/perf_event.c
@@ -250,4 +250,4 @@ static int __init sh7750_pmu_init(void)
        return register_sh_pmu(&sh7750_pmu);
 }
-arch_initcall(sh7750_pmu_init);
+early_initcall(sh7750_pmu_init);
diff --git a/arch/sh/kernel/cpu/sh4a/perf_event.c b/arch/sh/kernel/cpu/sh4a/perf_event.c
index 580276525731..17e6bebfede0 100644
--- a/arch/sh/kernel/cpu/sh4a/perf_event.c
+++ b/arch/sh/kernel/cpu/sh4a/perf_event.c
@@ -284,4 +284,4 @@ static int __init sh4a_pmu_init(void)
        return register_sh_pmu(&sh4a_pmu);
 }
-arch_initcall(sh4a_pmu_init);
+early_initcall(sh4a_pmu_init);
diff --git a/arch/sparc/include/asm/perf_event.h b/arch/sparc/include/asm/perf_event.h
index 6e8bfa1786da..4d3dbe3703e9 100644
--- a/arch/sparc/include/asm/perf_event.h
+++ b/arch/sparc/include/asm/perf_event.h
@@ -4,8 +4,6 @@
 #ifdef CONFIG_PERF_EVENTS
 #include <asm/ptrace.h>
-extern void init_hw_perf_events(void);
 #define perf_arch_fetch_caller_regs(regs, ip)           \
 do {                                                    \
        unsigned long _pstate, _asi, _pil, _i7, _fp;    \
@@ -26,8 +24,6 @@ do {							\
        (regs)->u_regs[UREG_I6] = _fp;                  \
        (regs)->u_regs[UREG_I7] = _i7;                  \
 } while (0)
-#else
-static inline void init_hw_perf_events(void)    { }
 #endif
 #endif
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index a4bd7ba74c89..300f810142f5 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -270,8 +270,6 @@ int __init nmi_init(void)
                        atomic_set(&nmi_active, -1);
                }
        }
-        if (!err)
-                init_hw_perf_events();
        return err;
 }
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 0d6deb55a2ae..75c5b1263970 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1307,20 +1307,23 @@ static bool __init supported_pmu(void)
        return false;
 }
-void __init init_hw_perf_events(void)
+int __init init_hw_perf_events(void)
 {
        pr_info("Performance events: ");
        if (!supported_pmu()) {
                pr_cont("No support for PMU type '%s'\n", sparc_pmu_type);
-                return;
+                return 0;
        }
        pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type);
        perf_pmu_register(&pmu);
        register_die_notifier(&perf_event_nmi_notifier);
+        return 0;
 }
+early_initcall(init_hw_perf_event);
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
                           struct pt_regs *regs)
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 76561d20ea2f..4a2adaa9aefc 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/kdebug.h b/arch/x86/include/asm/kdebug.h
index 5bdfca86581b..f23eb2528464 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/nmi.h b/arch/x86/include/asm/nmi.h
index 932f0f86b4b7..3545838cddeb 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -7,39 +7,13 @@
 #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);
 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 550e26b1dbb3..d9d4dae305f6 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 a70cd216be5d..295e2ff18a6a 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 1def60114906..6c22bf353f26 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 2b16a2ad23dc..52b5c7ed3608 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 5469630b27f5..fa7b9176b76c 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 5079f24c955a..553d0b0d639b 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;
+        struct text_poke_param *params;
-        const void *opcode;
+        int nparams;
-        size_t len;
 };
 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,
+        for (i = 0; i < tpp->nparams; i++) {
-                           (unsigned long)tpp->addr + tpp->len);
+                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;
+        p.addr = addr;
-        tpp.opcode = opcode;
+        p.opcode = opcode;
-        tpp.len = len;
+        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 910f20b457c4..3966b564ea47 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 ($(CONFIG_HARDLOCKUP_DETECTOR),y)
+obj-y                           += hw_nmi.o
-obj-$(CONFIG_X86_LOCAL_APIC)    += nmi.o
-endif
-obj-$(CONFIG_HARDLOCKUP_DETECTOR)       += hw_nmi.o
 obj-$(CONFIG_X86_IO_APIC)       += io_apic.o
 obj-$(CONFIG_SMP)               += ipi.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3f838d537392..e9e2a93783f9 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;
-                lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
-        else
-                pr_warning("APIC timer registered as dummy,"
-                        " due to nmi_watchdog=%d!\n", nmi_watchdog);
        /* 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();
 }
@@ -1750,17 +1744,10 @@ 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 62f6e1e55b90..a0e71cb4fa9c 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -17,16 +17,18 @@
 #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
 /* For reliability, we're prepared to waste bits here. */
 static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
+#ifdef arch_trigger_all_cpu_backtrace
 void arch_trigger_all_cpu_backtrace(void)
 {
        int i;
@@ -93,16 +95,4 @@ 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 7cc0a721f628..e4a040c28de1 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>
@@ -2643,24 +2642,6 @@ 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
@@ -2766,15 +2747,6 @@ 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);
@@ -2822,10 +2794,6 @@ 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;
@@ -2851,11 +2819,6 @@ 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;
                }
                /*
@@ -2867,15 +2830,6 @@ 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 c90041ccb742..000000000000
--- 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 4b68bda30938..1d59834396bd 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 6d75b9145b13..817d2b195e8e 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
@@ -451,7 +442,7 @@ 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 +1353,7 @@ 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;
@@ -1377,11 +1368,11 @@ 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();
@@ -1389,7 +1380,7 @@ void __init init_hw_perf_events(void)
        /* sanity check that the hardware exists or is emulated */
        if (!check_hw_exists()) {
                pr_cont("Broken PMU hardware detected, software events only.\n");
-                return;
+                return 0;
        }
        pr_cont("%s PMU driver.\n", x86_pmu.name);
@@ -1440,7 +1431,10 @@ void __init init_hw_perf_events(void)
        perf_pmu_register(&pmu);
        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 +1680,7 @@ 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/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index d9f4ff8fcd69..14d45928c282 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -22,26 +22,6 @@
 #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 6e8752c1bd52..8474c998cbd4 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 1bc7f75a5bda..74cc1eda384b 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,
+void dump_trace(struct task_struct *task,
-                unsigned long *stack, unsigned long bp,
+                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
+        bp = stack_frame(task, regs);
-        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
        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,
+                show_stack_log_lvl(NULL, regs, &regs->sp, KERN_EMERG);
-                                0, KERN_EMERG);
                printk(KERN_EMERG "Code: ");
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 6a340485249a..64101335de19 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,
+void dump_trace(struct task_struct *task,
-                unsigned long *stack, unsigned long bp,
+                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
+        bp = stack_frame(task, regs);
-        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
        /*
         * 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 1cbd54c0df99..5940282bd2f9 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.  */
+#define MAX_OPTIMIZE_PROBES 256
-int __kprobes arch_optimize_kprobe(struct optimized_kprobe *op)
+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;
+        insn_buf[0] = RELATIVEJUMP_OPCODE;
-        *(s32 *)(&jmp_code[1]) = rel;
+        *(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);
+        text_poke_smp_batch(jump_poke_params, c);
-        return 0;
+}
+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 57d1868a86aa..96ed1aac543a 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),
+        show_trace(NULL, regs, (unsigned long *)kernel_stack_pointer(regs));
-                   regs->bp);
 }
 void show_regs_common(void)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 083e99d1b7df..68f61ac632e1 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 b53c525368a7..938c8e10a19a 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 fb5cc5e14cfa..25a28a245937 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 cb838ca42c96..f02c179c2552 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -398,15 +398,6 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
                                                        == 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);
@@ -446,14 +437,12 @@ 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 af3b6c8a436f..704a37cedddb 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 2d49d4e19a36..72cbec14d783 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_timer_int.c b/arch/x86/oprofile/nmi_timer_int.c
index e3ecb71b5790..0636dd93cef8 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/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 660a2728908d..0cac7ec0d2ec 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -577,9 +577,7 @@ acpi_ns_init_one_device(acpi_handle obj_handle,
         * as possible (without an NMI being received in the middle of
         * this) - so disable NMIs and initialize the device:
         */
-        acpi_nmi_disable();
        status = acpi_ns_evaluate(info);
-        acpi_nmi_enable();
        if (ACPI_SUCCESS(status)) {
                walk_info->num_INI++;
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 3d77116e4634..c19f4a20794a 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -649,12 +649,7 @@ static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev)
         * If nmi_watchdog is turned off then we can turn on
         * our nmi decoding capability.
         */
-        if (!nmi_watchdog_active())
+        hpwdt_nmi_decoding = 1;
-                hpwdt_nmi_decoding = 1;
-        else
-                dev_warn(&dev->dev, "NMI decoding is disabled. To enable this "
-                        "functionality you must reboot with nmi_watchdog=0 "
-                        "and load the hpwdt driver with priority=1.\n");
 }
 #else
 static void __devinit hpwdt_check_nmi_decoding(struct pci_dev *dev)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 8beabb958f61..725bf6bd39f7 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -154,12 +154,14 @@ enum {
        TRACE_EVENT_FL_ENABLED_BIT,
        TRACE_EVENT_FL_FILTERED_BIT,
        TRACE_EVENT_FL_RECORDED_CMD_BIT,
+        TRACE_EVENT_FL_CAP_ANY_BIT,
 };
 enum {
        TRACE_EVENT_FL_ENABLED          = (1 << TRACE_EVENT_FL_ENABLED_BIT),
        TRACE_EVENT_FL_FILTERED         = (1 << TRACE_EVENT_FL_FILTERED_BIT),
        TRACE_EVENT_FL_RECORDED_CMD     = (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
+        TRACE_EVENT_FL_CAP_ANY          = (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
 };
 struct ftrace_event_call {
@@ -196,6 +198,14 @@ struct ftrace_event_call {
 #endif
 };
+#define __TRACE_EVENT_FLAGS(name, value)                                \
+        static int __init trace_init_flags_##name(void)                 \
+        {                                                               \
+                event_##name.flags = value;                             \
+                return 0;                                               \
+        }                                                               \
+        early_initcall(trace_init_flags_##name);
 #define PERF_MAX_TRACE_SIZE     2048
 #define MAX_FILTER_PRED         32
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index e7d1b2e0070d..b78edb58ee66 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -275,7 +275,9 @@ extern int arch_prepared_optinsn(struct arch_optimized_insn *optinsn);
 extern int arch_check_optimized_kprobe(struct optimized_kprobe *op);
 extern int arch_prepare_optimized_kprobe(struct optimized_kprobe *op);
 extern void arch_remove_optimized_kprobe(struct optimized_kprobe *op);
-extern int  arch_optimize_kprobe(struct optimized_kprobe *op);
+extern void arch_optimize_kprobes(struct list_head *oplist);
+extern void arch_unoptimize_kprobes(struct list_head *oplist,
+                                    struct list_head *done_list);
 extern void arch_unoptimize_kprobe(struct optimized_kprobe *op);
 extern kprobe_opcode_t *get_optinsn_slot(void);
 extern void free_optinsn_slot(kprobe_opcode_t *slot, int dirty);
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 06aab5eee134..1c451e6ecc17 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -16,10 +16,7 @@
 */
 #ifdef ARCH_HAS_NMI_WATCHDOG
 #include <asm/nmi.h>
-extern void touch_nmi_watchdog(void);
+#endif
-extern void acpi_nmi_disable(void);
-extern void acpi_nmi_enable(void);
-#else
 #ifndef CONFIG_HARDLOCKUP_DETECTOR
 static inline void touch_nmi_watchdog(void)
 {
@@ -28,9 +25,6 @@ static inline void touch_nmi_watchdog(void)
 #else
 extern void touch_nmi_watchdog(void);
 #endif
-static inline void acpi_nmi_disable(void) { }
-static inline void acpi_nmi_enable(void) { }
-#endif
 /*
 * Create trigger_all_cpu_backtrace() out of the arch-provided
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index de2c41758e29..adf6d9931643 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -758,6 +758,8 @@ struct perf_event {
        u64                             shadow_ctx_time;
        struct perf_event_attr          attr;
+        u16                             header_size;
+        u16                             read_size;
        struct hw_perf_event            hw;
        struct perf_event_context       *ctx;
@@ -969,6 +971,11 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
                                 struct perf_sample_data *data,
                                 struct pt_regs *regs);
+static inline bool is_sampling_event(struct perf_event *event)
+{
+        return event->attr.sample_period != 0;
+}
 /*
 * Return 1 for a software event, 0 for a hardware event
 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2c79e921a68b..d2e63d1e725c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -316,6 +316,7 @@ extern int proc_dowatchdog_thresh(struct ctl_table *table, int write,
                                  size_t *lenp, loff_t *ppos);
 extern unsigned int  softlockup_panic;
 extern int softlockup_thresh;
+void lockup_detector_init(void);
 #else
 static inline void touch_softlockup_watchdog(void)
 {
@@ -326,6 +327,9 @@ static inline void touch_softlockup_watchdog_sync(void)
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
+static inline void lockup_detector_init(void)
+{
+}
 #endif
 #ifdef CONFIG_DETECT_HUNG_TASK
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 51efbef38fb0..25310f1d7f37 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -2,6 +2,7 @@
 #define __LINUX_STACKTRACE_H
 struct task_struct;
+struct pt_regs;
 #ifdef CONFIG_STACKTRACE
 struct task_struct;
@@ -13,7 +14,8 @@ struct stack_trace {
 };
 extern void save_stack_trace(struct stack_trace *trace);
-extern void save_stack_trace_bp(struct stack_trace *trace, unsigned long bp);
+extern void save_stack_trace_regs(struct stack_trace *trace,
+                                  struct pt_regs *regs);
 extern void save_stack_trace_tsk(struct task_struct *tsk,
                                struct stack_trace *trace);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index cacc27a0e285..18cd0684fc4e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -127,8 +127,6 @@ extern struct trace_event_functions exit_syscall_print_funcs;
 #define SYSCALL_TRACE_ENTER_EVENT(sname)                                \
        static struct syscall_metadata                                  \
        __attribute__((__aligned__(4))) __syscall_meta_##sname;         \
-        static struct ftrace_event_call                                 \
-        __attribute__((__aligned__(4))) event_enter_##sname;            \
        static struct ftrace_event_call __used                          \
          __attribute__((__aligned__(4)))                               \
          __attribute__((section("_ftrace_events")))                    \
@@ -137,13 +135,12 @@ extern struct trace_event_functions exit_syscall_print_funcs;
                .class                  = &event_class_syscall_enter,   \
                .event.funcs            = &enter_syscall_print_funcs,   \
                .data                   = (void *)&__syscall_meta_##sname,\
-        }
+        };                                                              \
+        __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
 #define SYSCALL_TRACE_EXIT_EVENT(sname)                                 \
        static struct syscall_metadata                                  \
        __attribute__((__aligned__(4))) __syscall_meta_##sname;         \
-        static struct ftrace_event_call                                 \
-        __attribute__((__aligned__(4))) event_exit_##sname;             \
        static struct ftrace_event_call __used                          \
          __attribute__((__aligned__(4)))                               \
          __attribute__((section("_ftrace_events")))                    \
@@ -152,7 +149,8 @@ extern struct trace_event_functions exit_syscall_print_funcs;
                .class                  = &event_class_syscall_exit,    \
                .event.funcs            = &exit_syscall_print_funcs,    \
                .data                   = (void *)&__syscall_meta_##sname,\
-        }
+        };                                                              \
+        __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
 #define SYSCALL_METADATA(sname, nb)                             \
        SYSCALL_TRACE_ENTER_EVENT(sname);                       \
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index a4a90b6726ce..5a6074fcd81d 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -234,6 +234,8 @@ do_trace:								\
                                PARAMS(void *__data, proto),            \
                                PARAMS(__data, args))
+#define TRACE_EVENT_FLAGS(event, flag)
 #endif /* DECLARE_TRACE */
 #ifndef TRACE_EVENT
@@ -354,4 +356,6 @@ do_trace:								\
                assign, print, reg, unreg)                      \
        DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#define TRACE_EVENT_FLAGS(event, flag)
 #endif /* ifdef TRACE_EVENT (see note above) */
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index fb726ac7caee..5a4c04a75b3d 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -40,6 +40,8 @@ TRACE_EVENT_FN(sys_enter,
        syscall_regfunc, syscall_unregfunc
 );
+TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)
 TRACE_EVENT_FN(sys_exit,
        TP_PROTO(struct pt_regs *regs, long ret),
@@ -62,6 +64,8 @@ TRACE_EVENT_FN(sys_exit,
        syscall_regfunc, syscall_unregfunc
 );
+TRACE_EVENT_FLAGS(sys_exit, TRACE_EVENT_FL_CAP_ANY)
 #endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
 #endif /* _TRACE_EVENTS_SYSCALLS_H */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index a9377c0083ad..e718a917d897 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -82,6 +82,10 @@
        TRACE_EVENT(name, PARAMS(proto), PARAMS(args),                  \
                PARAMS(tstruct), PARAMS(assign), PARAMS(print))         \
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(name, value)                                  \
+        __TRACE_EVENT_FLAGS(name, value)
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
@@ -129,6 +133,9 @@
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)  \
        DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(event, flag)
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 /*
diff --git a/init/main.c b/init/main.c
index 8646401f7a0e..261ad7b3fe0b 100644
--- a/init/main.c
+++ b/init/main.c
@@ -882,6 +882,7 @@ static int __init kernel_init(void * unused)
        smp_prepare_cpus(setup_max_cpus);
        do_pre_smp_initcalls();
+        lockup_detector_init();
        smp_init();
        sched_init_smp();
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9737a76e106f..7663e5df0e6f 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -354,13 +354,20 @@ static inline int kprobe_aggrprobe(struct kprobe *p)
        return p->pre_handler == aggr_pre_handler;
 }
+/* Return true(!0) if the kprobe is unused */
+static inline int kprobe_unused(struct kprobe *p)
+{
+        return kprobe_aggrprobe(p) && kprobe_disabled(p) &&
+               list_empty(&p->list);
+}
 /*
 * Keep all fields in the kprobe consistent
 */
-static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+static inline void copy_kprobe(struct kprobe *ap, struct kprobe *p)
 {
-        memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
+        memcpy(&p->opcode, &ap->opcode, sizeof(kprobe_opcode_t));
-        memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+        memcpy(&p->ainsn, &ap->ainsn, sizeof(struct arch_specific_insn));
 }
 #ifdef CONFIG_OPTPROBES
@@ -384,6 +391,17 @@ void __kprobes opt_pre_handler(struct kprobe *p, struct pt_regs *regs)
        }
 }
+/* Free optimized instructions and optimized_kprobe */
+static __kprobes void free_aggr_kprobe(struct kprobe *p)
+{
+        struct optimized_kprobe *op;
+        op = container_of(p, struct optimized_kprobe, kp);
+        arch_remove_optimized_kprobe(op);
+        arch_remove_kprobe(p);
+        kfree(op);
+}
 /* Return true(!0) if the kprobe is ready for optimization. */
 static inline int kprobe_optready(struct kprobe *p)
 {
@@ -397,6 +415,33 @@ static inline int kprobe_optready(struct kprobe *p)
        return 0;
 }
+/* Return true(!0) if the kprobe is disarmed. Note: p must be on hash list */
+static inline int kprobe_disarmed(struct kprobe *p)
+{
+        struct optimized_kprobe *op;
+        /* If kprobe is not aggr/opt probe, just return kprobe is disabled */
+        if (!kprobe_aggrprobe(p))
+                return kprobe_disabled(p);
+        op = container_of(p, struct optimized_kprobe, kp);
+        return kprobe_disabled(p) && list_empty(&op->list);
+}
+/* Return true(!0) if the probe is queued on (un)optimizing lists */
+static int __kprobes kprobe_queued(struct kprobe *p)
+{
+        struct optimized_kprobe *op;
+        if (kprobe_aggrprobe(p)) {
+                op = container_of(p, struct optimized_kprobe, kp);
+                if (!list_empty(&op->list))
+                        return 1;
+        }
+        return 0;
+}
 /*
 * Return an optimized kprobe whose optimizing code replaces
 * instructions including addr (exclude breakpoint).
@@ -422,30 +467,23 @@ static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
 /* Optimization staging list, protected by kprobe_mutex */
 static LIST_HEAD(optimizing_list);
+static LIST_HEAD(unoptimizing_list);
 static void kprobe_optimizer(struct work_struct *work);
 static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
+static DECLARE_COMPLETION(optimizer_comp);
 #define OPTIMIZE_DELAY 5
-/* Kprobe jump optimizer */
+/*
-static __kprobes void kprobe_optimizer(struct work_struct *work)
+ * Optimize (replace a breakpoint with a jump) kprobes listed on
+ * optimizing_list.
+ */
+static __kprobes void do_optimize_kprobes(void)
 {
-        struct optimized_kprobe *op, *tmp;
+        /* Optimization never be done when disarmed */
+        if (kprobes_all_disarmed || !kprobes_allow_optimization ||
-        /* Lock modules while optimizing kprobes */
+            list_empty(&optimizing_list))
-        mutex_lock(&module_mutex);
+                return;
-        mutex_lock(&kprobe_mutex);
-        if (kprobes_all_disarmed || !kprobes_allow_optimization)
-                goto end;
-        /*
-         * Wait for quiesence period to ensure all running interrupts
-         * are done. Because optprobe may modify multiple instructions
-         * there is a chance that Nth instruction is interrupted. In that
-         * case, running interrupt can return to 2nd-Nth byte of jump
-         * instruction. This wait is for avoiding it.
-         */
-        synchronize_sched();
        /*
         * The optimization/unoptimization refers online_cpus via
@@ -459,17 +497,111 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
         */
        get_online_cpus();
        mutex_lock(&text_mutex);
-        list_for_each_entry_safe(op, tmp, &optimizing_list, list) {
+        arch_optimize_kprobes(&optimizing_list);
-                WARN_ON(kprobe_disabled(&op->kp));
+        mutex_unlock(&text_mutex);
-                if (arch_optimize_kprobe(op) < 0)
+        put_online_cpus();
-                        op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+}
-                list_del_init(&op->list);
+/*
+ * Unoptimize (replace a jump with a breakpoint and remove the breakpoint
+ * if need) kprobes listed on unoptimizing_list.
+ */
+static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
+{
+        struct optimized_kprobe *op, *tmp;
+        /* Unoptimization must be done anytime */
+        if (list_empty(&unoptimizing_list))
+                return;
+        /* Ditto to do_optimize_kprobes */
+        get_online_cpus();
+        mutex_lock(&text_mutex);
+        arch_unoptimize_kprobes(&unoptimizing_list, free_list);
+        /* Loop free_list for disarming */
+        list_for_each_entry_safe(op, tmp, free_list, list) {
+                /* Disarm probes if marked disabled */
+                if (kprobe_disabled(&op->kp))
+                        arch_disarm_kprobe(&op->kp);
+                if (kprobe_unused(&op->kp)) {
+                        /*
+                         * Remove unused probes from hash list. After waiting
+                         * for synchronization, these probes are reclaimed.
+                         * (reclaiming is done by do_free_cleaned_kprobes.)
+                         */
+                        hlist_del_rcu(&op->kp.hlist);
+                } else
+                        list_del_init(&op->list);
        }
        mutex_unlock(&text_mutex);
        put_online_cpus();
-end:
+}
+/* Reclaim all kprobes on the free_list */
+static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list)
+{
+        struct optimized_kprobe *op, *tmp;
+        list_for_each_entry_safe(op, tmp, free_list, list) {
+                BUG_ON(!kprobe_unused(&op->kp));
+                list_del_init(&op->list);
+                free_aggr_kprobe(&op->kp);
+        }
+}
+/* Start optimizer after OPTIMIZE_DELAY passed */
+static __kprobes void kick_kprobe_optimizer(void)
+{
+        if (!delayed_work_pending(&optimizing_work))
+                schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+}
+/* Kprobe jump optimizer */
+static __kprobes void kprobe_optimizer(struct work_struct *work)
+{
+        LIST_HEAD(free_list);
+        /* Lock modules while optimizing kprobes */
+        mutex_lock(&module_mutex);
+        mutex_lock(&kprobe_mutex);
+        /*
+         * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
+         * kprobes before waiting for quiesence period.
+         */
+        do_unoptimize_kprobes(&free_list);
+        /*
+         * Step 2: Wait for quiesence period to ensure all running interrupts
+         * are done. Because optprobe may modify multiple instructions
+         * there is a chance that Nth instruction is interrupted. In that
+         * case, running interrupt can return to 2nd-Nth byte of jump
+         * instruction. This wait is for avoiding it.
+         */
+        synchronize_sched();
+        /* Step 3: Optimize kprobes after quiesence period */
+        do_optimize_kprobes();
+        /* Step 4: Free cleaned kprobes after quiesence period */
+        do_free_cleaned_kprobes(&free_list);
        mutex_unlock(&kprobe_mutex);
        mutex_unlock(&module_mutex);
+        /* Step 5: Kick optimizer again if needed */
+        if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list))
+                kick_kprobe_optimizer();
+        else
+                /* Wake up all waiters */
+                complete_all(&optimizer_comp);
+}
+/* Wait for completing optimization and unoptimization */
+static __kprobes void wait_for_kprobe_optimizer(void)
+{
+        if (delayed_work_pending(&optimizing_work))
+                wait_for_completion(&optimizer_comp);
 }
 /* Optimize kprobe if p is ready to be optimized */
@@ -495,42 +627,99 @@ static __kprobes void optimize_kprobe(struct kprobe *p)
        /* Check if it is already optimized. */
        if (op->kp.flags & KPROBE_FLAG_OPTIMIZED)
                return;
        op->kp.flags |= KPROBE_FLAG_OPTIMIZED;
-        list_add(&op->list, &optimizing_list);
-        if (!delayed_work_pending(&optimizing_work))
+        if (!list_empty(&op->list))
-                schedule_delayed_work(&optimizing_work, OPTIMIZE_DELAY);
+                /* This is under unoptimizing. Just dequeue the probe */
+                list_del_init(&op->list);
+        else {
+                list_add(&op->list, &optimizing_list);
+                kick_kprobe_optimizer();
+        }
+}
+/* Short cut to direct unoptimizing */
+static __kprobes void force_unoptimize_kprobe(struct optimized_kprobe *op)
+{
+        get_online_cpus();
+        arch_unoptimize_kprobe(op);
+        put_online_cpus();
+        if (kprobe_disabled(&op->kp))
+                arch_disarm_kprobe(&op->kp);
 }
 /* Unoptimize a kprobe if p is optimized */
-static __kprobes void unoptimize_kprobe(struct kprobe *p)
+static __kprobes void unoptimize_kprobe(struct kprobe *p, bool force)
 {
        struct optimized_kprobe *op;
-        if ((p->flags & KPROBE_FLAG_OPTIMIZED) && kprobe_aggrprobe(p)) {
+        if (!kprobe_aggrprobe(p) || kprobe_disarmed(p))
-                op = container_of(p, struct optimized_kprobe, kp);
+                return; /* This is not an optprobe nor optimized */
-                if (!list_empty(&op->list))
-                        /* Dequeue from the optimization queue */
+        op = container_of(p, struct optimized_kprobe, kp);
+        if (!kprobe_optimized(p)) {
+                /* Unoptimized or unoptimizing case */
+                if (force && !list_empty(&op->list)) {
+                        /*
+                         * Only if this is unoptimizing kprobe and forced,
+                         * forcibly unoptimize it. (No need to unoptimize
+                         * unoptimized kprobe again :)
+                         */
                        list_del_init(&op->list);
-                else
+                        force_unoptimize_kprobe(op);
-                        /* Replace jump with break */
+                }
-                        arch_unoptimize_kprobe(op);
+                return;
-                op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+        }
+        op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+        if (!list_empty(&op->list)) {
+                /* Dequeue from the optimization queue */
+                list_del_init(&op->list);
+                return;
+        }
+        /* Optimized kprobe case */
+        if (force)
+                /* Forcibly update the code: this is a special case */
+                force_unoptimize_kprobe(op);
+        else {
+                list_add(&op->list, &unoptimizing_list);
+                kick_kprobe_optimizer();
        }
 }
+/* Cancel unoptimizing for reusing */
+static void reuse_unused_kprobe(struct kprobe *ap)
+{
+        struct optimized_kprobe *op;
+        BUG_ON(!kprobe_unused(ap));
+        /*
+         * Unused kprobe MUST be on the way of delayed unoptimizing (means
+         * there is still a relative jump) and disabled.
+         */
+        op = container_of(ap, struct optimized_kprobe, kp);
+        if (unlikely(list_empty(&op->list)))
+                printk(KERN_WARNING "Warning: found a stray unused "
+                        "aggrprobe@%p\n", ap->addr);
+        /* Enable the probe again */
+        ap->flags &= ~KPROBE_FLAG_DISABLED;
+        /* Optimize it again (remove from op->list) */
+        BUG_ON(!kprobe_optready(ap));
+        optimize_kprobe(ap);
+}
 /* Remove optimized instructions */
 static void __kprobes kill_optimized_kprobe(struct kprobe *p)
 {
        struct optimized_kprobe *op;
        op = container_of(p, struct optimized_kprobe, kp);
-        if (!list_empty(&op->list)) {
+        if (!list_empty(&op->list))
-                /* Dequeue from the optimization queue */
+                /* Dequeue from the (un)optimization queue */
                list_del_init(&op->list);
-                op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
-        }
+        op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
-        /* Don't unoptimize, because the target code will be freed. */
+        /* Don't touch the code, because it is already freed. */
        arch_remove_optimized_kprobe(op);
 }
@@ -543,16 +732,6 @@ static __kprobes void prepare_optimized_kprobe(struct kprobe *p)
        arch_prepare_optimized_kprobe(op);
 }
-/* Free optimized instructions and optimized_kprobe */
-static __kprobes void free_aggr_kprobe(struct kprobe *p)
-{
-        struct optimized_kprobe *op;
-        op = container_of(p, struct optimized_kprobe, kp);
-        arch_remove_optimized_kprobe(op);
-        kfree(op);
-}
 /* Allocate new optimized_kprobe and try to prepare optimized instructions */
 static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 {
@@ -587,7 +766,8 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p)
        op = container_of(ap, struct optimized_kprobe, kp);
        if (!arch_prepared_optinsn(&op->optinsn)) {
                /* If failed to setup optimizing, fallback to kprobe */
-                free_aggr_kprobe(ap);
+                arch_remove_optimized_kprobe(op);
+                kfree(op);
                return;
        }
@@ -631,21 +811,16 @@ static void __kprobes unoptimize_all_kprobes(void)
                return;
        kprobes_allow_optimization = false;
-        printk(KERN_INFO "Kprobes globally unoptimized\n");
-        get_online_cpus();      /* For avoiding text_mutex deadlock */
-        mutex_lock(&text_mutex);
        for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
                head = &kprobe_table[i];
                hlist_for_each_entry_rcu(p, node, head, hlist) {
                        if (!kprobe_disabled(p))
-                                unoptimize_kprobe(p);
+                                unoptimize_kprobe(p, false);
                }
        }
+        /* Wait for unoptimizing completion */
-        mutex_unlock(&text_mutex);
+        wait_for_kprobe_optimizer();
-        put_online_cpus();
+        printk(KERN_INFO "Kprobes globally unoptimized\n");
-        /* Allow all currently running kprobes to complete */
-        synchronize_sched();
 }
 int sysctl_kprobes_optimization;
@@ -669,44 +844,60 @@ int proc_kprobes_optimization_handler(struct ctl_table *table, int write,
 }
 #endif /* CONFIG_SYSCTL */
+/* Put a breakpoint for a probe. Must be called with text_mutex locked */
 static void __kprobes __arm_kprobe(struct kprobe *p)
 {
-        struct kprobe *old_p;
+        struct kprobe *_p;
        /* Check collision with other optimized kprobes */
-        old_p = get_optimized_kprobe((unsigned long)p->addr);
+        _p = get_optimized_kprobe((unsigned long)p->addr);
-        if (unlikely(old_p))
+        if (unlikely(_p))
-                unoptimize_kprobe(old_p); /* Fallback to unoptimized kprobe */
+                /* Fallback to unoptimized kprobe */
+                unoptimize_kprobe(_p, true);
        arch_arm_kprobe(p);
        optimize_kprobe(p);     /* Try to optimize (add kprobe to a list) */
 }
-static void __kprobes __disarm_kprobe(struct kprobe *p)
+/* Remove the breakpoint of a probe. Must be called with text_mutex locked */
+static void __kprobes __disarm_kprobe(struct kprobe *p, bool reopt)
 {
-        struct kprobe *old_p;
+        struct kprobe *_p;
-        unoptimize_kprobe(p);   /* Try to unoptimize */
+        unoptimize_kprobe(p, false);    /* Try to unoptimize */
-        arch_disarm_kprobe(p);
-        /* If another kprobe was blocked, optimize it. */
+        if (!kprobe_queued(p)) {
-        old_p = get_optimized_kprobe((unsigned long)p->addr);
+                arch_disarm_kprobe(p);
-        if (unlikely(old_p))
+                /* If another kprobe was blocked, optimize it. */
-                optimize_kprobe(old_p);
+                _p = get_optimized_kprobe((unsigned long)p->addr);
+                if (unlikely(_p) && reopt)
+                        optimize_kprobe(_p);
+        }
+        /* TODO: reoptimize others after unoptimized this probe */
 }
 #else /* !CONFIG_OPTPROBES */
 #define optimize_kprobe(p)                      do {} while (0)
-#define unoptimize_kprobe(p)                    do {} while (0)
+#define unoptimize_kprobe(p, f)                 do {} while (0)
 #define kill_optimized_kprobe(p)                do {} while (0)
 #define prepare_optimized_kprobe(p)             do {} while (0)
 #define try_to_optimize_kprobe(p)               do {} while (0)
 #define __arm_kprobe(p)                         arch_arm_kprobe(p)
-#define __disarm_kprobe(p)                      arch_disarm_kprobe(p)
+#define __disarm_kprobe(p, o)                   arch_disarm_kprobe(p)
+#define kprobe_disarmed(p)                      kprobe_disabled(p)
+#define wait_for_kprobe_optimizer()             do {} while (0)
+/* There should be no unused kprobes can be reused without optimization */
+static void reuse_unused_kprobe(struct kprobe *ap)
+{
+        printk(KERN_ERR "Error: There should be no unused kprobe here.\n");
+        BUG_ON(kprobe_unused(ap));
+}
 static __kprobes void free_aggr_kprobe(struct kprobe *p)
 {
+        arch_remove_kprobe(p);
        kfree(p);
 }
@@ -732,11 +923,10 @@ static void __kprobes arm_kprobe(struct kprobe *kp)
 /* Disarm a kprobe with text_mutex */
 static void __kprobes disarm_kprobe(struct kprobe *kp)
 {
-        get_online_cpus();      /* For avoiding text_mutex deadlock */
+        /* Ditto */
        mutex_lock(&text_mutex);
-        __disarm_kprobe(kp);
+        __disarm_kprobe(kp, true);
        mutex_unlock(&text_mutex);
-        put_online_cpus();
 }
 /*
@@ -942,7 +1132,7 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p)
        BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
        if (p->break_handler || p->post_handler)
-                unoptimize_kprobe(ap);  /* Fall back to normal kprobe */
+                unoptimize_kprobe(ap, true);    /* Fall back to normal kprobe */
        if (p->break_handler) {
                if (ap->break_handler)
@@ -993,19 +1183,21 @@ static void __kprobes init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 * This is the second or subsequent kprobe at the address - handle
 * the intricacies
 */
-static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
+static int __kprobes register_aggr_kprobe(struct kprobe *orig_p,
                                          struct kprobe *p)
 {
        int ret = 0;
-        struct kprobe *ap = old_p;
+        struct kprobe *ap = orig_p;
-        if (!kprobe_aggrprobe(old_p)) {
+        if (!kprobe_aggrprobe(orig_p)) {
-                /* If old_p is not an aggr_kprobe, create new aggr_kprobe. */
+                /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */
-                ap = alloc_aggr_kprobe(old_p);
+                ap = alloc_aggr_kprobe(orig_p);
                if (!ap)
                        return -ENOMEM;
-                init_aggr_kprobe(ap, old_p);
+                init_aggr_kprobe(ap, orig_p);
-        }
+        } else if (kprobe_unused(ap))
+                /* This probe is going to die. Rescue it */
+                reuse_unused_kprobe(ap);
        if (kprobe_gone(ap)) {
                /*
@@ -1039,23 +1231,6 @@ static int __kprobes register_aggr_kprobe(struct kprobe *old_p,
        return add_new_kprobe(ap, p);
 }
-/* Try to disable aggr_kprobe, and return 1 if succeeded.*/
-static int __kprobes try_to_disable_aggr_kprobe(struct kprobe *p)
-{
-        struct kprobe *kp;
-        list_for_each_entry_rcu(kp, &p->list, list) {
-                if (!kprobe_disabled(kp))
-                        /*
-                         * There is an active probe on the list.
-                         * We can't disable aggr_kprobe.
-                         */
-                        return 0;
-        }
-        p->flags |= KPROBE_FLAG_DISABLED;
-        return 1;
-}
 static int __kprobes in_kprobes_functions(unsigned long addr)
 {
        struct kprobe_blackpoint *kb;
@@ -1098,34 +1273,33 @@ static kprobe_opcode_t __kprobes *kprobe_addr(struct kprobe *p)
 /* Check passed kprobe is valid and return kprobe in kprobe_table. */
 static struct kprobe * __kprobes __get_valid_kprobe(struct kprobe *p)
 {
-        struct kprobe *old_p, *list_p;
+        struct kprobe *ap, *list_p;
-        old_p = get_kprobe(p->addr);
+        ap = get_kprobe(p->addr);
-        if (unlikely(!old_p))
+        if (unlikely(!ap))
                return NULL;
-        if (p != old_p) {
+        if (p != ap) {
-                list_for_each_entry_rcu(list_p, &old_p->list, list)
+                list_for_each_entry_rcu(list_p, &ap->list, list)
                        if (list_p == p)
                        /* kprobe p is a valid probe */
                                goto valid;
                return NULL;
        }
 valid:
-        return old_p;
+        return ap;
 }
 /* Return error if the kprobe is being re-registered */
 static inline int check_kprobe_rereg(struct kprobe *p)
 {
        int ret = 0;
-        struct kprobe *old_p;
        mutex_lock(&kprobe_mutex);
-        old_p = __get_valid_kprobe(p);
+        if (__get_valid_kprobe(p))
-        if (old_p)
                ret = -EINVAL;
        mutex_unlock(&kprobe_mutex);
        return ret;
 }
@@ -1229,67 +1403,121 @@ fail_with_jump_label:
 }
 EXPORT_SYMBOL_GPL(register_kprobe);
+/* Check if all probes on the aggrprobe are disabled */
+static int __kprobes aggr_kprobe_disabled(struct kprobe *ap)
+{
+        struct kprobe *kp;
+        list_for_each_entry_rcu(kp, &ap->list, list)
+                if (!kprobe_disabled(kp))
+                        /*
+                         * There is an active probe on the list.
+                         * We can't disable this ap.
+                         */
+                        return 0;
+        return 1;
+}
+/* Disable one kprobe: Make sure called under kprobe_mutex is locked */
+static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p)
+{
+        struct kprobe *orig_p;
+        /* Get an original kprobe for return */
+        orig_p = __get_valid_kprobe(p);
+        if (unlikely(orig_p == NULL))
+                return NULL;
+        if (!kprobe_disabled(p)) {
+                /* Disable probe if it is a child probe */
+                if (p != orig_p)
+                        p->flags |= KPROBE_FLAG_DISABLED;
+                /* Try to disarm and disable this/parent probe */
+                if (p == orig_p || aggr_kprobe_disabled(orig_p)) {
+                        disarm_kprobe(orig_p);
+                        orig_p->flags |= KPROBE_FLAG_DISABLED;
+                }
+        }
+        return orig_p;
+}
 /*
 * Unregister a kprobe without a scheduler synchronization.
 */
 static int __kprobes __unregister_kprobe_top(struct kprobe *p)
 {
-        struct kprobe *old_p, *list_p;
+        struct kprobe *ap, *list_p;
-        old_p = __get_valid_kprobe(p);
+        /* Disable kprobe. This will disarm it if needed. */
-        if (old_p == NULL)
+        ap = __disable_kprobe(p);
+        if (ap == NULL)
                return -EINVAL;
-        if (old_p == p ||
+        if (ap == p)
-            (kprobe_aggrprobe(old_p) &&
-             list_is_singular(&old_p->list))) {
                /*
-                 * Only probe on the hash list. Disarm only if kprobes are
+                 * This probe is an independent(and non-optimized) kprobe
-                 * enabled and not gone - otherwise, the breakpoint would
+                 * (not an aggrprobe). Remove from the hash list.
-                 * already have been removed. We save on flushing icache.
                 */
-                if (!kprobes_all_disarmed && !kprobe_disabled(old_p))
+                goto disarmed;
-                        disarm_kprobe(old_p);
-                hlist_del_rcu(&old_p->hlist);
+        /* Following process expects this probe is an aggrprobe */
-        } else {
+        WARN_ON(!kprobe_aggrprobe(ap));
+        if (list_is_singular(&ap->list) && kprobe_disarmed(ap))
+                /*
+                 * !disarmed could be happen if the probe is under delayed
+                 * unoptimizing.
+                 */
+                goto disarmed;
+        else {
+                /* If disabling probe has special handlers, update aggrprobe */
                if (p->break_handler && !kprobe_gone(p))
-                        old_p->break_handler = NULL;
+                        ap->break_handler = NULL;
                if (p->post_handler && !kprobe_gone(p)) {
-                        list_for_each_entry_rcu(list_p, &old_p->list, list) {
+                        list_for_each_entry_rcu(list_p, &ap->list, list) {
                                if ((list_p != p) && (list_p->post_handler))
                                        goto noclean;
                        }
-                        old_p->post_handler = NULL;
+                        ap->post_handler = NULL;
                }
 noclean:
+                /*
+                 * Remove from the aggrprobe: this path will do nothing in
+                 * __unregister_kprobe_bottom().
+                 */
                list_del_rcu(&p->list);
-                if (!kprobe_disabled(old_p)) {
+                if (!kprobe_disabled(ap) && !kprobes_all_disarmed)
-                        try_to_disable_aggr_kprobe(old_p);
+                        /*
-                        if (!kprobes_all_disarmed) {
+                         * Try to optimize this probe again, because post
-                                if (kprobe_disabled(old_p))
+                         * handler may have been changed.
-                                        disarm_kprobe(old_p);
+                         */
-                                else
+                        optimize_kprobe(ap);
-                                        /* Try to optimize this probe again */
-                                        optimize_kprobe(old_p);
-                        }
-                }
        }
        return 0;
+disarmed:
+        BUG_ON(!kprobe_disarmed(ap));
+        hlist_del_rcu(&ap->hlist);
+        return 0;
 }
 static void __kprobes __unregister_kprobe_bottom(struct kprobe *p)
 {
-        struct kprobe *old_p;
+        struct kprobe *ap;
        if (list_empty(&p->list))
+                /* This is an independent kprobe */
                arch_remove_kprobe(p);
        else if (list_is_singular(&p->list)) {
-                /* "p" is the last child of an aggr_kprobe */
+                /* This is the last child of an aggrprobe */
-                old_p = list_entry(p->list.next, struct kprobe, list);
+                ap = list_entry(p->list.next, struct kprobe, list);
                list_del(&p->list);
-                arch_remove_kprobe(old_p);
+                free_aggr_kprobe(ap);
-                free_aggr_kprobe(old_p);
        }
+        /* Otherwise, do nothing. */
 }
 int __kprobes register_kprobes(struct kprobe **kps, int num)
@@ -1607,29 +1835,13 @@ static void __kprobes kill_kprobe(struct kprobe *p)
 int __kprobes disable_kprobe(struct kprobe *kp)
 {
        int ret = 0;
-        struct kprobe *p;
        mutex_lock(&kprobe_mutex);
-        /* Check whether specified probe is valid. */
+        /* Disable this kprobe */
-        p = __get_valid_kprobe(kp);
+        if (__disable_kprobe(kp) == NULL)
-        if (unlikely(p == NULL)) {
                ret = -EINVAL;
-                goto out;
-        }
-        /* If the probe is already disabled (or gone), just return */
-        if (kprobe_disabled(kp))
-                goto out;
-        kp->flags |= KPROBE_FLAG_DISABLED;
-        if (p != kp)
-                /* When kp != p, p is always enabled. */
-                try_to_disable_aggr_kprobe(p);
-        if (!kprobes_all_disarmed && kprobe_disabled(p))
-                disarm_kprobe(p);
-out:
        mutex_unlock(&kprobe_mutex);
        return ret;
 }
@@ -1927,36 +2139,27 @@ static void __kprobes disarm_all_kprobes(void)
        mutex_lock(&kprobe_mutex);
        /* If kprobes are already disarmed, just return */
-        if (kprobes_all_disarmed)
+        if (kprobes_all_disarmed) {
-                goto already_disabled;
+                mutex_unlock(&kprobe_mutex);
+                return;
+        }
        kprobes_all_disarmed = true;
        printk(KERN_INFO "Kprobes globally disabled\n");
-        /*
-         * Here we call get_online_cpus() for avoiding text_mutex deadlock,
-         * because disarming may also unoptimize kprobes.
-         */
-        get_online_cpus();
        mutex_lock(&text_mutex);
        for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
                head = &kprobe_table[i];
                hlist_for_each_entry_rcu(p, node, head, hlist) {
                        if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p))
-                                __disarm_kprobe(p);
+                                __disarm_kprobe(p, false);
                }
        }
        mutex_unlock(&text_mutex);
-        put_online_cpus();
        mutex_unlock(&kprobe_mutex);
-        /* Allow all currently running kprobes to complete */
-        synchronize_sched();
-        return;
-already_disabled:
+        /* Wait for disarming all kprobes by optimizer */
-        mutex_unlock(&kprobe_mutex);
+        wait_for_kprobe_optimizer();
-        return;
 }
 /*
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index eac7e3364335..aede71245e9f 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -312,9 +312,75 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
                ctx->nr_stat++;
 }
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__read_size(struct perf_event *event)
+{
+        int entry = sizeof(u64); /* value */
+        int size = 0;
+        int nr = 1;
+        if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
+                size += sizeof(u64);
+        if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
+                size += sizeof(u64);
+        if (event->attr.read_format & PERF_FORMAT_ID)
+                entry += sizeof(u64);
+        if (event->attr.read_format & PERF_FORMAT_GROUP) {
+                nr += event->group_leader->nr_siblings;
+                size += sizeof(u64);
+        }
+        size += entry * nr;
+        event->read_size = size;
+}
+static void perf_event__header_size(struct perf_event *event)
+{
+        struct perf_sample_data *data;
+        u64 sample_type = event->attr.sample_type;
+        u16 size = 0;
+        perf_event__read_size(event);
+        if (sample_type & PERF_SAMPLE_IP)
+                size += sizeof(data->ip);
+        if (sample_type & PERF_SAMPLE_TID)
+                size += sizeof(data->tid_entry);
+        if (sample_type & PERF_SAMPLE_TIME)
+                size += sizeof(data->time);
+        if (sample_type & PERF_SAMPLE_ADDR)
+                size += sizeof(data->addr);
+        if (sample_type & PERF_SAMPLE_ID)
+                size += sizeof(data->id);
+        if (sample_type & PERF_SAMPLE_STREAM_ID)
+                size += sizeof(data->stream_id);
+        if (sample_type & PERF_SAMPLE_CPU)
+                size += sizeof(data->cpu_entry);
+        if (sample_type & PERF_SAMPLE_PERIOD)
+                size += sizeof(data->period);
+        if (sample_type & PERF_SAMPLE_READ)
+                size += event->read_size;
+        event->header_size = size;
+}
 static void perf_group_attach(struct perf_event *event)
 {
-        struct perf_event *group_leader = event->group_leader;
+        struct perf_event *group_leader = event->group_leader, *pos;
        /*
         * We can have double attach due to group movement in perf_event_open.
@@ -333,6 +399,11 @@ static void perf_group_attach(struct perf_event *event)
        list_add_tail(&event->group_entry, &group_leader->sibling_list);
        group_leader->nr_siblings++;
+        perf_event__header_size(group_leader);
+        list_for_each_entry(pos, &group_leader->sibling_list, group_entry)
+                perf_event__header_size(pos);
 }
 /*
@@ -391,7 +462,7 @@ static void perf_group_detach(struct perf_event *event)
        if (event->group_leader != event) {
                list_del_init(&event->group_entry);
                event->group_leader->nr_siblings--;
-                return;
+                goto out;
        }
        if (!list_empty(&event->group_entry))
@@ -410,6 +481,12 @@ static void perf_group_detach(struct perf_event *event)
                /* Inherit group flags from the previous leader */
                sibling->group_flags = event->group_flags;
        }
+out:
+        perf_event__header_size(event->group_leader);
+        list_for_each_entry(tmp, &event->group_leader->sibling_list, group_entry)
+                perf_event__header_size(tmp);
 }
 static inline int
@@ -1073,7 +1150,7 @@ static int perf_event_refresh(struct perf_event *event, int refresh)
        /*
         * not supported on inherited events
         */
-        if (event->attr.inherit)
+        if (event->attr.inherit || !is_sampling_event(event))
                return -EINVAL;
        atomic_add(refresh, &event->event_limit);
@@ -2289,31 +2366,6 @@ static int perf_release(struct inode *inode, struct file *file)
        return perf_event_release_kernel(event);
 }
-static int perf_event_read_size(struct perf_event *event)
-{
-        int entry = sizeof(u64); /* value */
-        int size = 0;
-        int nr = 1;
-        if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
-                size += sizeof(u64);
-        if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING)
-                size += sizeof(u64);
-        if (event->attr.read_format & PERF_FORMAT_ID)
-                entry += sizeof(u64);
-        if (event->attr.read_format & PERF_FORMAT_GROUP) {
-                nr += event->group_leader->nr_siblings;
-                size += sizeof(u64);
-        }
-        size += entry * nr;
-        return size;
-}
 u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running)
 {
        struct perf_event *child;
@@ -2428,7 +2480,7 @@ perf_read_hw(struct perf_event *event, char __user *buf, size_t count)
        if (event->state == PERF_EVENT_STATE_ERROR)
                return 0;
-        if (count < perf_event_read_size(event))
+        if (count < event->read_size)
                return -ENOSPC;
        WARN_ON_ONCE(event->ctx->parent_ctx);
@@ -2514,7 +2566,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg)
        int ret = 0;
        u64 value;
-        if (!event->attr.sample_period)
+        if (!is_sampling_event(event))
                return -EINVAL;
        if (copy_from_user(&value, arg, sizeof(value)))
@@ -3606,59 +3658,34 @@ void perf_prepare_sample(struct perf_event_header *header,
        data->type = sample_type;
        header->type = PERF_RECORD_SAMPLE;
-        header->size = sizeof(*header);
+        header->size = sizeof(*header) + event->header_size;
        header->misc = 0;
        header->misc |= perf_misc_flags(regs);
-        if (sample_type & PERF_SAMPLE_IP) {
+        if (sample_type & PERF_SAMPLE_IP)
                data->ip = perf_instruction_pointer(regs);
-                header->size += sizeof(data->ip);
-        }
        if (sample_type & PERF_SAMPLE_TID) {
                /* namespace issues */
                data->tid_entry.pid = perf_event_pid(event, current);
                data->tid_entry.tid = perf_event_tid(event, current);
-                header->size += sizeof(data->tid_entry);
        }
-        if (sample_type & PERF_SAMPLE_TIME) {
+        if (sample_type & PERF_SAMPLE_TIME)
                data->time = perf_clock();
-                header->size += sizeof(data->time);
+        if (sample_type & PERF_SAMPLE_ID)
-        }
-        if (sample_type & PERF_SAMPLE_ADDR)
-                header->size += sizeof(data->addr);
-        if (sample_type & PERF_SAMPLE_ID) {
                data->id = primary_event_id(event);
-                header->size += sizeof(data->id);
+        if (sample_type & PERF_SAMPLE_STREAM_ID)
-        }
-        if (sample_type & PERF_SAMPLE_STREAM_ID) {
                data->stream_id = event->id;
-                header->size += sizeof(data->stream_id);
-        }
        if (sample_type & PERF_SAMPLE_CPU) {
                data->cpu_entry.cpu             = raw_smp_processor_id();
                data->cpu_entry.reserved        = 0;
-                header->size += sizeof(data->cpu_entry);
        }
-        if (sample_type & PERF_SAMPLE_PERIOD)
-                header->size += sizeof(data->period);
-        if (sample_type & PERF_SAMPLE_READ)
-                header->size += perf_event_read_size(event);
        if (sample_type & PERF_SAMPLE_CALLCHAIN) {
                int size = 1;
@@ -3726,7 +3753,7 @@ perf_event_read_event(struct perf_event *event,
                .header = {
                        .type = PERF_RECORD_READ,
                        .misc = 0,
-                        .size = sizeof(read_event) + perf_event_read_size(event),
+                        .size = sizeof(read_event) + event->read_size,
                },
                .pid = perf_event_pid(event, task),
                .tid = perf_event_tid(event, task),
@@ -4240,6 +4267,13 @@ static int __perf_event_overflow(struct perf_event *event, int nmi,
        struct hw_perf_event *hwc = &event->hw;
        int ret = 0;
+        /*
+         * Non-sampling counters might still use the PMI to fold short
+         * hardware counters, ignore those.
+         */
+        if (unlikely(!is_sampling_event(event)))
+                return 0;
        if (!throttle) {
                hwc->interrupts++;
        } else {
@@ -4385,7 +4419,7 @@ static void perf_swevent_event(struct perf_event *event, u64 nr,
        if (!regs)
                return;
-        if (!hwc->sample_period)
+        if (!is_sampling_event(event))
                return;
        if (nr == 1 && hwc->sample_period == 1 && !event->attr.freq)
@@ -4548,7 +4582,7 @@ static int perf_swevent_add(struct perf_event *event, int flags)
        struct hw_perf_event *hwc = &event->hw;
        struct hlist_head *head;
-        if (hwc->sample_period) {
+        if (is_sampling_event(event)) {
                hwc->last_period = hwc->sample_period;
                perf_swevent_set_period(event);
        }
@@ -4805,15 +4839,6 @@ static int perf_tp_event_init(struct perf_event *event)
        if (event->attr.type != PERF_TYPE_TRACEPOINT)
                return -ENOENT;
-        /*
-         * Raw tracepoint data is a severe data leak, only allow root to
-         * have these.
-         */
-        if ((event->attr.sample_type & PERF_SAMPLE_RAW) &&
-                        perf_paranoid_tracepoint_raw() &&
-                        !capable(CAP_SYS_ADMIN))
-                return -EPERM;
        err = perf_trace_init(event);
        if (err)
                return err;
@@ -4926,31 +4951,33 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
 static void perf_swevent_start_hrtimer(struct perf_event *event)
 {
        struct hw_perf_event *hwc = &event->hw;
+        s64 period;
+        if (!is_sampling_event(event))
+                return;
        hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
        hwc->hrtimer.function = perf_swevent_hrtimer;
-        if (hwc->sample_period) {
-                s64 period = local64_read(&hwc->period_left);
-                if (period) {
+        period = local64_read(&hwc->period_left);
-                        if (period < 0)
+        if (period) {
-                                period = 10000;
+                if (period < 0)
+                        period = 10000;
-                        local64_set(&hwc->period_left, 0);
+                local64_set(&hwc->period_left, 0);
-                } else {
+        } else {
-                        period = max_t(u64, 10000, hwc->sample_period);
+                period = max_t(u64, 10000, hwc->sample_period);
-                }
+        }
-                __hrtimer_start_range_ns(&hwc->hrtimer,
+        __hrtimer_start_range_ns(&hwc->hrtimer,
                                ns_to_ktime(period), 0,
                                HRTIMER_MODE_REL_PINNED, 0);
-        }
 }
 static void perf_swevent_cancel_hrtimer(struct perf_event *event)
 {
        struct hw_perf_event *hwc = &event->hw;
-        if (hwc->sample_period) {
+        if (is_sampling_event(event)) {
                ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
                local64_set(&hwc->period_left, ktime_to_ns(remaining));
@@ -5715,6 +5742,11 @@ SYSCALL_DEFINE5(perf_event_open,
        mutex_unlock(&current->perf_event_mutex);
        /*
+         * Precalculate sample_data sizes
+         */
+        perf_event__header_size(event);
+        /*
         * Drop the reference on the group_event after placing the
         * new event on the sibling_list. This ensures destruction
         * of the group leader will find the pointer to itself in
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 5abfa1518554..cbd97da7a613 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -746,22 +746,6 @@ static struct ctl_table kern_table[] = {
                .extra2         = &one,
        },
 #endif
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR)
-        {
-                .procname       = "unknown_nmi_panic",
-                .data           = &unknown_nmi_panic,
-                .maxlen         = sizeof (int),
-                .mode           = 0644,
-                .proc_handler   = proc_dointvec,
-        },
-        {
-                .procname       = "nmi_watchdog",
-                .data           = &nmi_watchdog_enabled,
-                .maxlen         = sizeof (int),
-                .mode           = 0644,
-                .proc_handler   = proc_nmi_enabled,
-        },
-#endif
 #if defined(CONFIG_X86)
        {
                .procname       = "panic_on_unrecovered_nmi",
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 39c059ca670e..19a359d5e6d5 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
 /* Count the events in use (per event id, not per instance) */
 static int      total_ref_count;
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+                                 struct perf_event *p_event)
+{
+        /* No tracing, just counting, so no obvious leak */
+        if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+                return 0;
+        /* Some events are ok to be traced by non-root users... */
+        if (p_event->attach_state == PERF_ATTACH_TASK) {
+                if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+                        return 0;
+        }
+        /*
+         * ...otherwise raw tracepoint data can be a severe data leak,
+         * only allow root to have these.
+         */
+        if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+                return -EPERM;
+        return 0;
+}
 static int perf_trace_event_init(struct ftrace_event_call *tp_event,
                                 struct perf_event *p_event)
 {
        struct hlist_head __percpu *list;
-        int ret = -ENOMEM;
+        int ret;
        int cpu;
+        ret = perf_trace_event_perm(tp_event, p_event);
+        if (ret)
+                return ret;
        p_event->tp_event = tp_event;
        if (tp_event->perf_refcount++ > 0)
                return 0;
+        ret = -ENOMEM;
        list = alloc_percpu(struct hlist_head);
        if (!list)
                goto fail;
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 6e3c41a4024c..cad4e42060a9 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -547,13 +547,13 @@ static struct notifier_block __cpuinitdata cpu_nfb = {
        .notifier_call = cpu_callback
 };
-static int __init spawn_watchdog_task(void)
+void __init lockup_detector_init(void)
 {
        void *cpu = (void *)(long)smp_processor_id();
        int err;
        if (no_watchdog)
-                return 0;
+                return;
        err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
        WARN_ON(notifier_to_errno(err));
@@ -561,6 +561,5 @@ static int __init spawn_watchdog_task(void)
        cpu_callback(&cpu_nfb, CPU_ONLINE, cpu);
        register_cpu_notifier(&cpu_nfb);
-        return 0;
+        return;
 }
-early_initcall(spawn_watchdog_task);
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 8509bb512935..bbbe584d4494 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -125,7 +125,9 @@ exuberant()
        -I DEFINE_TRACE,EXPORT_TRACEPOINT_SYMBOL,EXPORT_TRACEPOINT_SYMBOL_GPL \
        --extra=+f --c-kinds=-px                                \
        --regex-asm='/^ENTRY\(([^)]*)\).*/\1/'                  \
-        --regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/'
+        --regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
+        --regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'               \
+        --regex-c++='/^DEFINE_EVENT\(([^,)]*).*/trace_\1/'
        all_kconfigs | xargs $1 -a                              \
        --langdef=kconfig --language-force=kconfig              \
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index b2c63309a651..6f5a498608b2 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -24,12 +24,47 @@ OPTIONS
 --input=::
        Input file name. (default: perf.data)
+-d::
+--dsos=<dso[,dso...]>::
+        Only consider symbols in these dsos.
+-s::
+--symbol=<symbol>::
+        Symbol to annotate.
+-f::
+--force::
+        Don't complain, do it.
+-v::
+--verbose::
+        Be more verbose. (Show symbol address, etc)
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+-k::
+--vmlinux=<file>::
+        vmlinux pathname.
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel.
+-l::
+--print-line::
+        Print matching source lines (may be slow).
+-P::
+--full-paths::
+        Don't shorten the displayed pathnames.
 --stdio:: Use the stdio interface.
 --tui:: Use the TUI interface Use of --tui requires a tty, if one is not
        present, as when piping to other commands, the stdio interface is
        used. This interfaces starts by centering on the line with more
-        samples, TAB/UNTAB cycles thru the lines with more samples.
+        samples, TAB/UNTAB cycles through the lines with more samples.
 SEE ALSO
 --------
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 01b642c0bf8f..5eaac6f26d51 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -18,6 +18,9 @@ perf report.
 OPTIONS
 -------
+-H::
+--with-hits::
+        Show only DSOs with hits.
 -i::
 --input=::
        Input file name. (default: perf.data)
diff --git a/tools/perf/Documentation/perf-diff.txt b/tools/perf/Documentation/perf-diff.txt
index 20d97d84ea1c..6a9ec2b35310 100644
--- a/tools/perf/Documentation/perf-diff.txt
+++ b/tools/perf/Documentation/perf-diff.txt
@@ -19,6 +19,18 @@ If no parameters are passed it will assume perf.data.old and perf.data.
 OPTIONS
 -------
+-M::
+--displacement::
+        Show position displacement relative to baseline.
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
+-m::
+--modules::
+        Load module symbols. WARNING: use only with -k and LIVE kernel
 -d::
 --dsos=::
        Only consider symbols in these dsos. CSV that understands
@@ -42,7 +54,7 @@ OPTIONS
 --field-separator=::
        Use a special separator character and don't pad with spaces, replacing
-        all occurances of this separator in symbol names (and other output)
+        all occurrences of this separator in symbol names (and other output)
        with a '.' character, that thus it's the only non valid separator.
 -v::
@@ -50,6 +62,11 @@ OPTIONS
        Be verbose, for instance, show the raw counts in addition to the
        diff.
+-f::
+--force::
+       Don't complain, do it.
 SEE ALSO
 --------
 linkperf:perf-record[1]
diff --git a/tools/perf/Documentation/perf-kvm.txt b/tools/perf/Documentation/perf-kvm.txt
index d004e19fe6d6..dd84cb2f0a88 100644
--- a/tools/perf/Documentation/perf-kvm.txt
+++ b/tools/perf/Documentation/perf-kvm.txt
@@ -22,7 +22,7 @@ There are a couple of variants of perf kvm:
  a performance counter profile of guest os in realtime
  of an arbitrary workload.
-  'perf kvm record <command>' to record the performance couinter profile
+  'perf kvm record <command>' to record the performance counter profile
  of an arbitrary workload and save it into a perf data file. If both
  --host and --guest are input, the perf data file name is perf.data.kvm.
  If there is  no --host but --guest, the file name is perf.data.guest.
@@ -40,6 +40,12 @@ There are a couple of variants of perf kvm:
 OPTIONS
 -------
+-i::
+--input=::
+        Input file name.
+-o::
+--output::
+        Output file name.
 --host=::
        Collect host side performance profile.
 --guest=::
diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt
index b317102138c8..921de259ea10 100644
--- a/tools/perf/Documentation/perf-lock.txt
+++ b/tools/perf/Documentation/perf-lock.txt
@@ -24,6 +24,21 @@ and statistics with this 'perf lock' command.
  'perf lock report' reports statistical data.
+OPTIONS
+-------
+-i::
+--input=<file>::
+        Input file name.
+-v::
+--verbose::
+        Be more verbose (show symbol address, etc).
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index 62de1b7f4e76..4e2323276984 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -115,7 +115,7 @@ Each probe argument follows below syntax.
 LINE SYNTAX
 -----------
-Line range is descripted by following syntax.
+Line range is described by following syntax.
 "FUNC[:RLN[+NUM|-RLN2]]|SRC:ALN[+NUM|-ALN2]"
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index a91f9f9e6e5c..0ad1bc75ab49 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -39,15 +39,24 @@ OPTIONS
          be passed as follows: '\mem:addr[:[r][w][x]]'.
          If you want to profile read-write accesses in 0x1000, just set
          'mem:0x1000:rw'.
+--filter=<filter>::
+        Event filter.
 -a::
-        System-wide collection.
+--all-cpus::
+        System-wide collection from all CPUs.
 -l::
        Scale counter values.
 -p::
 --pid=::
-        Record events on existing pid.
+        Record events on existing process ID.
+-t::
+--tid=::
+        Record events on existing thread ID.
 -r::
 --realtime=::
@@ -109,8 +118,8 @@ Collect raw sample records from all opened counters (default for tracepoint coun
 -C::
 --cpu::
-Collect samples only on the list of cpus provided. Multiple CPUs can be provided as a
+Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 In per-thread mode with inheritance mode on (default), samples are captured only when
 the thread executes on the designated CPUs. Default is to monitor all CPUs.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 12052c9ed0ba..59a1f57f2bb7 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -20,6 +20,11 @@ OPTIONS
 -i::
 --input=::
        Input file name. (default: perf.data)
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
 -d::
 --dsos=::
        Only consider symbols in these dsos. CSV that understands
@@ -27,6 +32,10 @@ OPTIONS
 -n::
 --show-nr-samples::
        Show the number of samples for each symbol
+--showcpuutilization::
+        Show sample percentage for different cpu modes.
 -T::
 --threads::
        Show per-thread event counters
@@ -39,12 +48,24 @@ OPTIONS
        Only consider these symbols. CSV that understands
        file://filename entries.
+-U::
+--hide-unresolved::
+        Only display entries resolved to a symbol.
 -s::
 --sort=::
        Sort by key(s): pid, comm, dso, symbol, parent.
+-p::
+--parent=<regex>::
+        regex filter to identify parent, see: '--sort parent'
+-x::
+--exclude-other::
+        Only display entries with parent-match.
 -w::
--field-width=::
+--column-widths=<width[,width...]>::
        Force each column width to the provided list, for large terminal
        readability.
@@ -52,19 +73,26 @@ OPTIONS
 --field-separator=::
        Use a special separator character and don't pad with spaces, replacing
-        all occurances of this separator in symbol names (and other output)
+        all occurrences of this separator in symbol names (and other output)
        with a '.' character, that thus it's the only non valid separator.
+-D::
+--dump-raw-trace::
+        Dump raw trace in ASCII.
 -g [type,min]::
 --call-graph::
-        Display callchains using type and min percent threshold.
+        Display call chains using type and min percent threshold.
        type can be either:
-        - flat: single column, linear exposure of callchains.
+        - flat: single column, linear exposure of call chains.
        - graph: use a graph tree, displaying absolute overhead rates.
        - fractal: like graph, but displays relative rates. Each branch of
                 the tree is considered as a new profiled object. +
        Default: fractal,0.5.
+--pretty=<key>::
+        Pretty printing style.  key: normal, raw
 --stdio:: Use the stdio interface.
 --tui:: Use the TUI interface, that is integrated with annotate and allows
@@ -72,6 +100,19 @@ OPTIONS
        requires a tty, if one is not present, as when piping to other
        commands, the stdio interface is used.
+-k::
+--vmlinux=<file>::
+        vmlinux pathname
+-m::
+--modules::
+        Load module symbols. WARNING: This should only be used with -k and
+        a LIVE kernel.
+-f::
+--force::
+        Don't complain, do it.
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 8417644a6166..46822d5fde1c 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,11 +8,11 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|replay|trace}
+'perf sched' {record|latency|map|replay|trace}
 DESCRIPTION
 -----------
-There are four variants of perf sched:
+There are five variants of perf sched:
  'perf sched record <command>' to record the scheduling events
  of an arbitrary workload.
@@ -30,8 +30,22 @@ There are four variants of perf sched:
  of the workload as it occurred when it was recorded - and can repeat
  it a number of times, measuring its performance.)
+  'perf sched map' to print a textual context-switching outline of
+  workload captured via perf sched record.  Columns stand for
+  individual CPUs, and the two-letter shortcuts stand for tasks that
+  are running on a CPU. A '*' denotes the CPU that had the event, and
+  a dot signals an idle CPU.
 OPTIONS
 -------
+-i::
+--input=<file>::
+        Input file name. (default: perf.data)
+-v::
+--verbose::
+        Be more verbose. (show symbol address, etc)
 -D::
 --dump-raw-trace=::
        Display verbose dump of the sched data.
diff --git a/tools/perf/Documentation/perf-trace-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index ee6525ee6d69..5bb41e55a3ac 100644
--- a/tools/perf/Documentation/perf-trace-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -1,19 +1,19 @@
-perf-trace-perl(1)
+perf-script-perl(1)
 ==================
 NAME
 ----
-perf-trace-perl - Process trace data with a Perl script
+perf-script-perl - Process trace data with a Perl script
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [Perl]:script[.pl] ]
+'perf script' [-s [Perl]:script[.pl] ]
 DESCRIPTION
 -----------
-This perf trace option is used to process perf trace data using perf's
+This perf script option is used to process perf script data using perf's
 built-in Perl interpreter.  It reads and processes the input file and
 displays the results of the trace analysis implemented in the given
 Perl script, if any.
@@ -21,7 +21,7 @@ Perl script, if any.
 STARTER SCRIPTS
 ---------------
-You can avoid reading the rest of this document by running 'perf trace
+You can avoid reading the rest of this document by running 'perf script
 -g perl' in the same directory as an existing perf.data trace file.
 That will generate a starter script containing a handler for each of
 the event types in the trace file; it simply prints every available
@@ -30,13 +30,13 @@ field for each event in the trace file.
 You can also look at the existing scripts in
 ~/libexec/perf-core/scripts/perl for typical examples showing how to
 do basic things like aggregate event data, print results, etc.  Also,
-the check-perf-trace.pl script, while not interesting for its results,
+the check-perf-script.pl script, while not interesting for its results,
 attempts to exercise all of the main scripting features.
 EVENT HANDLERS
 --------------
-When perf trace is invoked using a trace script, a user-defined
+When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
 ignored (or passed to a 'trace_handled' function, see below) and the
@@ -112,13 +112,13 @@ write a useful trace script.  The sections below cover the rest.
 SCRIPT LAYOUT
 -------------
-Every perf trace Perl script should start by setting up a Perl module
+Every perf script Perl script should start by setting up a Perl module
 search path and 'use'ing a few support modules (see module
 descriptions below):
 ----
- use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/Perf-Trace-Util/lib";
+ use lib "$ENV{'PERF_EXEC_PATH'}/scripts/perl/perf-script-Util/lib";
- use lib "./Perf-Trace-Util/lib";
+ use lib "./perf-script-Util/lib";
 use Perf::Trace::Core;
 use Perf::Trace::Context;
 use Perf::Trace::Util;
@@ -162,7 +162,7 @@ sub trace_unhandled
 ----
 The remaining sections provide descriptions of each of the available
-built-in perf trace Perl modules and their associated functions.
+built-in perf script Perl modules and their associated functions.
 AVAILABLE MODULES AND FUNCTIONS
 -------------------------------
@@ -170,7 +170,7 @@ AVAILABLE MODULES AND FUNCTIONS
 The following sections describe the functions and variables available
 via the various Perf::Trace::* Perl modules.  To use the functions and
 variables from the given module, add the corresponding 'use
-Perf::Trace::XXX' line to your perf trace script.
+Perf::Trace::XXX' line to your perf script script.
 Perf::Trace::Core Module
 ~~~~~~~~~~~~~~~~~~~~~~~~
@@ -204,7 +204,7 @@ argument.
 Perf::Trace::Util Module
 ~~~~~~~~~~~~~~~~~~~~~~~~
-Various utility functions for use with perf trace:
+Various utility functions for use with perf script:
  nsecs($secs, $nsecs) - returns total nsecs given secs/nsecs pair
  nsecs_secs($nsecs) - returns whole secs portion given nsecs
@@ -214,4 +214,4 @@ Various utility functions for use with perf trace:
 SEE ALSO
 --------
-linkperf:perf-trace[1]
+linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf-trace-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 693be804dd3d..36b38277422c 100644
--- a/tools/perf/Documentation/perf-trace-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -1,19 +1,19 @@
-perf-trace-python(1)
+perf-script-python(1)
 ====================
 NAME
 ----
-perf-trace-python - Process trace data with a Python script
+perf-script-python - Process trace data with a Python script
 SYNOPSIS
 --------
 [verse]
-'perf trace' [-s [Python]:script[.py] ]
+'perf script' [-s [Python]:script[.py] ]
 DESCRIPTION
 -----------
-This perf trace option is used to process perf trace data using perf's
+This perf script option is used to process perf script data using perf's
 built-in Python interpreter.  It reads and processes the input file and
 displays the results of the trace analysis implemented in the given
 Python script, if any.
@@ -23,15 +23,15 @@ A QUICK EXAMPLE
 This section shows the process, start to finish, of creating a working
 Python script that aggregates and extracts useful information from a
-raw perf trace stream.  You can avoid reading the rest of this
+raw perf script stream.  You can avoid reading the rest of this
 document if an example is enough for you; the rest of the document
 provides more details on each step and lists the library functions
 available to script writers.
 This example actually details the steps that were used to create the
-'syscall-counts' script you see when you list the available perf trace
+'syscall-counts' script you see when you list the available perf script
-scripts via 'perf trace -l'.  As such, this script also shows how to
+scripts via 'perf script -l'.  As such, this script also shows how to
-integrate your script into the list of general-purpose 'perf trace'
+integrate your script into the list of general-purpose 'perf script'
 scripts listed by that command.
 The syscall-counts script is a simple script, but demonstrates all the
@@ -105,31 +105,31 @@ That single stream will be recorded in a file in the current directory
 called perf.data.
 Once we have a perf.data file containing our data, we can use the -g
-'perf trace' option to generate a Python script that will contain a
+'perf script' option to generate a Python script that will contain a
 callback handler for each event type found in the perf.data trace
 stream (for more details, see the STARTER SCRIPTS section).
 ----
-# perf trace -g python
+# perf script -g python
-generated Python script: perf-trace.py
+generated Python script: perf-script.py
 The output file created also in the current directory is named
-perf-trace.py.  Here's the file in its entirety:
+perf-script.py.  Here's the file in its entirety:
-# perf trace event handlers, generated by perf trace -g python
+# perf script event handlers, generated by perf script -g python
 # Licensed under the terms of the GNU GPL License version 2
 # The common_* event handler fields are the most useful fields common to
 # all events.  They don't necessarily correspond to the 'common_*' fields
 # in the format files.  Those fields not available as handler params can
 # be retrieved using Python functions of the form common_*(context).
-# See the perf-trace-python Documentation for the list of available functions.
+# See the perf-script-python Documentation for the list of available functions.
 import os
 import sys
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+        '/scripts/python/perf-script-Util/lib/Perf/Trace')
 from perf_trace_context import *
 from Core import *
@@ -160,7 +160,7 @@ def print_header(event_name, cpu, secs, nsecs, pid, comm):
 ----
 At the top is a comment block followed by some import statements and a
-path append which every perf trace script should include.
+path append which every perf script script should include.
 Following that are a couple generated functions, trace_begin() and
 trace_end(), which are called at the beginning and the end of the
@@ -189,8 +189,8 @@ simply a utility function used for that purpose.  Let's rename the
 script and run it to see the default output:
 ----
-# mv perf-trace.py syscall-counts.py
+# mv perf-script.py syscall-counts.py
-# perf trace -s syscall-counts.py
+# perf script -s syscall-counts.py
 raw_syscalls__sys_enter     1 00840.847582083     7506 perf                  id=1, args=
 raw_syscalls__sys_enter     1 00840.847595764     7506 perf                  id=1, args=
@@ -216,7 +216,7 @@ import os
 import sys
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+        '/scripts/python/perf-script-Util/lib/Perf/Trace')
 from perf_trace_context import *
 from Core import *
@@ -279,7 +279,7 @@ import os
 import sys
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-        '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+        '/scripts/python/perf-script-Util/lib/Perf/Trace')
 from perf_trace_context import *
 from Core import *
@@ -315,7 +315,7 @@ def print_syscall_totals():
 The script can be run just as before:
-  # perf trace -s syscall-counts.py
+  # perf script -s syscall-counts.py
 So those are the essential steps in writing and running a script.  The
 process can be generalized to any tracepoint or set of tracepoints
@@ -324,17 +324,17 @@ interested in by looking at the list of available events shown by
 'perf list' and/or look in /sys/kernel/debug/tracing events for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
-generate a skeleton script using 'perf trace -g python' and modify the
+generate a skeleton script using 'perf script -g python' and modify the
 code to aggregate and display it for your particular needs.
 After you've done that you may end up with a general-purpose script
 that you want to keep around and have available for future use.  By
 writing a couple of very simple shell scripts and putting them in the
 right place, you can have your script listed alongside the other
-scripts listed by the 'perf trace -l' command e.g.:
+scripts listed by the 'perf script -l' command e.g.:
 ----
-root@tropicana:~# perf trace -l
+root@tropicana:~# perf script -l
 List of available trace scripts:
  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
  wakeup-latency                       system-wide min/max/avg wakeup latency
@@ -365,14 +365,14 @@ perf record -a -e raw_syscalls:sys_enter
 The 'report' script is also a shell script with the same base name as
 your script, but with -report appended.  It should also be located in
 the perf/scripts/python/bin directory.  In that script, you write the
-'perf trace -s' command-line needed for running your script:
+'perf script -s' command-line needed for running your script:
 ----
 # cat kernel-source/tools/perf/scripts/python/bin/syscall-counts-report
 #!/bin/bash
 # description: system-wide syscall counts
-perf trace -s ~/libexec/perf-core/scripts/python/syscall-counts.py
+perf script -s ~/libexec/perf-core/scripts/python/syscall-counts.py
 ----
 Note that the location of the Python script given in the shell script
@@ -390,17 +390,17 @@ total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
 drwxr-xr-x 2 trz trz 4096 2010-01-26 22:29 bin
-rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-trace.py
+-rw-r--r-- 1 trz trz 2548 2010-01-26 22:29 check-perf-script.py
-drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 Perf-Trace-Util
+drwxr-xr-x 3 trz trz 4096 2010-01-26 22:49 perf-script-Util
 -rw-r--r-- 1 trz trz 1462 2010-01-26 22:30 syscall-counts.py
 ----
 Once you've done that (don't forget to do a new 'make install',
-otherwise your script won't show up at run-time), 'perf trace -l'
+otherwise your script won't show up at run-time), 'perf script -l'
 should show a new entry for your script:
 ----
-root@tropicana:~# perf trace -l
+root@tropicana:~# perf script -l
 List of available trace scripts:
  workqueue-stats                      workqueue stats (ins/exe/create/destroy)
  wakeup-latency                       system-wide min/max/avg wakeup latency
@@ -409,19 +409,19 @@ List of available trace scripts:
  syscall-counts                       system-wide syscall counts
 ----
-You can now perform the record step via 'perf trace record':
+You can now perform the record step via 'perf script record':
-  # perf trace record syscall-counts
+  # perf script record syscall-counts
-and display the output using 'perf trace report':
+and display the output using 'perf script report':
-  # perf trace report syscall-counts
+  # perf script report syscall-counts
 STARTER SCRIPTS
 ---------------
 You can quickly get started writing a script for a particular set of
-trace data by generating a skeleton script using 'perf trace -g
+trace data by generating a skeleton script using 'perf script -g
 python' in the same directory as an existing perf.data trace file.
 That will generate a starter script containing a handler for each of
 the event types in the trace file; it simply prints every available
@@ -430,13 +430,13 @@ field for each event in the trace file.
 You can also look at the existing scripts in
 ~/libexec/perf-core/scripts/python for typical examples showing how to
 do basic things like aggregate event data, print results, etc.  Also,
-the check-perf-trace.py script, while not interesting for its results,
+the check-perf-script.py script, while not interesting for its results,
 attempts to exercise all of the main scripting features.
 EVENT HANDLERS
 --------------
-When perf trace is invoked using a trace script, a user-defined
+When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
 ignored (or passed to a 'trace_handled' function, see below) and the
@@ -510,7 +510,7 @@ write a useful trace script.  The sections below cover the rest.
 SCRIPT LAYOUT
 -------------
-Every perf trace Python script should start by setting up a Python
+Every perf script Python script should start by setting up a Python
 module search path and 'import'ing a few support modules (see module
 descriptions below):
@@ -519,7 +519,7 @@ descriptions below):
 import sys
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
-              '/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+              '/scripts/python/perf-script-Util/lib/Perf/Trace')
 from perf_trace_context import *
 from Core import *
@@ -559,15 +559,15 @@ def trace_unhandled(event_name, context, common_cpu, common_secs,
 ----
 The remaining sections provide descriptions of each of the available
-built-in perf trace Python modules and their associated functions.
+built-in perf script Python modules and their associated functions.
 AVAILABLE MODULES AND FUNCTIONS
 -------------------------------
 The following sections describe the functions and variables available
-via the various perf trace Python modules.  To use the functions and
+via the various perf script Python modules.  To use the functions and
 variables from the given module, add the corresponding 'from XXXX
-import' line to your perf trace script.
+import' line to your perf script script.
 Core.py Module
 ~~~~~~~~~~~~~~
@@ -610,7 +610,7 @@ argument.
 Util.py Module
 ~~~~~~~~~~~~~~
-Various utility functions for use with perf trace:
+Various utility functions for use with perf script:
  nsecs(secs, nsecs) - returns total nsecs given secs/nsecs pair
  nsecs_secs(nsecs) - returns whole secs portion given nsecs
@@ -620,4 +620,4 @@ Various utility functions for use with perf trace:
 SEE ALSO
 --------
-linkperf:perf-trace[1]
+linkperf:perf-script[1]
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-script.txt
index 26aff6bf9e50..29ad94293cd2 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -1,71 +1,71 @@
-perf-trace(1)
+perf-script(1)
 =============
 NAME
 ----
-perf-trace - Read perf.data (created by perf record) and display trace output
+perf-script - Read perf.data (created by perf record) and display trace output
 SYNOPSIS
 --------
 [verse]
-'perf trace' [<options>]
+'perf script' [<options>]
-'perf trace' [<options>] record <script> [<record-options>] <command>
+'perf script' [<options>] record <script> [<record-options>] <command>
-'perf trace' [<options>] report <script> [script-args]
+'perf script' [<options>] report <script> [script-args]
-'perf trace' [<options>] <script> <required-script-args> [<record-options>] <command>
+'perf script' [<options>] <script> <required-script-args> [<record-options>] <command>
-'perf trace' [<options>] <top-script> [script-args]
+'perf script' [<options>] <top-script> [script-args]
 DESCRIPTION
 -----------
 This command reads the input file and displays the trace recorded.
-There are several variants of perf trace:
+There are several variants of perf script:
-  'perf trace' to see a detailed trace of the workload that was
+  'perf script' to see a detailed trace of the workload that was
  recorded.
  You can also run a set of pre-canned scripts that aggregate and
  summarize the raw trace data in various ways (the list of scripts is
-  available via 'perf trace -l').  The following variants allow you to
+  available via 'perf script -l').  The following variants allow you to
  record and run those scripts:
-  'perf trace record <script> <command>' to record the events required
+  'perf script record <script> <command>' to record the events required
-  for 'perf trace report'.  <script> is the name displayed in the
+  for 'perf script report'.  <script> is the name displayed in the
-  output of 'perf trace --list' i.e. the actual script name minus any
+  output of 'perf script --list' i.e. the actual script name minus any
  language extension.  If <command> is not specified, the events are
  recorded using the -a (system-wide) 'perf record' option.
-  'perf trace report <script> [args]' to run and display the results
+  'perf script report <script> [args]' to run and display the results
  of <script>.  <script> is the name displayed in the output of 'perf
  trace --list' i.e. the actual script name minus any language
-  extension.  The perf.data output from a previous run of 'perf trace
+  extension.  The perf.data output from a previous run of 'perf script
  record <script>' is used and should be present for this command to
  succeed.  [args] refers to the (mainly optional) args expected by
  the script.
-  'perf trace <script> <required-script-args> <command>' to both
+  'perf script <script> <required-script-args> <command>' to both
  record the events required for <script> and to run the <script>
  using 'live-mode' i.e. without writing anything to disk.  <script>
-  is the name displayed in the output of 'perf trace --list' i.e. the
+  is the name displayed in the output of 'perf script --list' i.e. the
  actual script name minus any language extension.  If <command> is
  not specified, the events are recorded using the -a (system-wide)
  'perf record' option.  If <script> has any required args, they
  should be specified before <command>.  This mode doesn't allow for
  optional script args to be specified; if optional script args are
-  desired, they can be specified using separate 'perf trace record'
+  desired, they can be specified using separate 'perf script record'
-  and 'perf trace report' commands, with the stdout of the record step
+  and 'perf script report' commands, with the stdout of the record step
  piped to the stdin of the report script, using the '-o -' and '-i -'
  options of the corresponding commands.
-  'perf trace <top-script>' to both record the events required for
+  'perf script <top-script>' to both record the events required for
  <top-script> and to run the <top-script> using 'live-mode'
  i.e. without writing anything to disk.  <top-script> is the name
-  displayed in the output of 'perf trace --list' i.e. the actual
+  displayed in the output of 'perf script --list' i.e. the actual
  script name minus any language extension; a <top-script> is defined
  as any script name ending with the string 'top'.
-  [<record-options>] can be passed to the record steps of 'perf trace
+  [<record-options>] can be passed to the record steps of 'perf script
  record' and 'live-mode' variants; this isn't possible however for
-  <top-script> 'live-mode' or 'perf trace report' variants.
+  <top-script> 'live-mode' or 'perf script report' variants.
  See the 'SEE ALSO' section for links to language-specific
  information on how to write and run your own trace scripts.
@@ -76,7 +76,7 @@ OPTIONS
        Any command you can specify in a shell.
 -D::
--dump-raw-trace=::
+--dump-raw-script=::
        Display verbose dump of the trace data.
 -L::
@@ -95,7 +95,7 @@ OPTIONS
 -g::
 --gen-script=::
-        Generate perf-trace.[ext] starter script for given language,
+        Generate perf-script.[ext] starter script for given language,
        using current perf.data.
 -a::
@@ -104,8 +104,15 @@ OPTIONS
        normally don't - this option allows the latter to be run in
        system-wide mode.
+-i::
+--input=::
+        Input file name.
+-d::
+--debug-mode::
+        Do various checks like samples ordering and lost events.
 SEE ALSO
 --------
-linkperf:perf-record[1], linkperf:perf-trace-perl[1],
+linkperf:perf-record[1], linkperf:perf-script-perl[1],
-linkperf:perf-trace-python[1]
+linkperf:perf-script-python[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4b3a2d46b437..b6da7affbbee 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -8,8 +8,8 @@ perf-stat - Run a command and gather performance counter statistics
 SYNOPSIS
 --------
 [verse]
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] <command>
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
-'perf stat' [-e <EVENT> | --event=EVENT] [-S] [-a] -- <command> [<options>]
+'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
 DESCRIPTION
 -----------
@@ -35,24 +35,54 @@ OPTIONS
        child tasks do not inherit counters
 -p::
 --pid=<pid>::
-        stat events on existing pid
+        stat events on existing process id
+-t::
+--tid=<tid>::
+        stat events on existing thread id
 -a::
-        system-wide collection
+--all-cpus::
+        system-wide collection from all CPUs
 -c::
-        scale counter values
+--scale::
+        scale/normalize counter values
+-r::
+--repeat=<n>::
+        repeat command and print average + stddev (max: 100)
 -B::
+--big-num::
        print large numbers with thousands' separators according to locale
 -C::
 --cpu=::
-Count only on the list of cpus provided. Multiple CPUs can be provided as a
+Count only on the list of CPUs provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 In per-thread mode, this option is ignored. The -a option is still necessary
 to activate system-wide monitoring. Default is to count on all CPUs.
+-A::
+--no-aggr::
+Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
+This option is only valid in system-wide mode.
+-n::
+--null::
+        null run - don't start any counters
+-v::
+--verbose::
+        be more verbose (show counter open errors, etc)
+-x SEP::
+--field-separator SEP::
+print counts using a CSV-style output to make it easy to import directly into
+spreadsheets. Columns are separated by the string specified in SEP.
 EXAMPLES
 --------
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 1c4b5f5b7f71..2c3b462f64b0 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 DESCRIPTION
 -----------
-This command does assorted sanity tests, initially thru linked routines but
+This command does assorted sanity tests, initially through linked routines but
 also will look for a directory with more tests in the form of scripts.
 OPTIONS
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 1f9687663f2a..f6eb1cdafb77 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -12,7 +12,7 @@ SYNOPSIS
 DESCRIPTION
 -----------
-This command generates and displays a performance counter profile in realtime.
+This command generates and displays a performance counter profile in real time.
 OPTIONS
@@ -27,8 +27,8 @@ OPTIONS
 -C <cpu-list>::
 --cpu=<cpu>::
-Monitor only on the list of cpus provided. Multiple CPUs can be provided as a
+Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
-comma-sperated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
+comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 Default is to monitor all CPUS.
 -d <seconds>::
@@ -50,6 +50,10 @@ Default is to monitor all CPUS.
 --count-filter=<count>::
        Only display functions with more events than this.
+-g::
+--group::
+        Put the counters into a counter group.
 -F <freq>::
 --freq=<freq>::
        Profile at this frequency.
@@ -68,7 +72,11 @@ Default is to monitor all CPUS.
 -p <pid>::
 --pid=<pid>::
-        Profile events on existing pid.
+        Profile events on existing Process ID.
+-t <tid>::
+--tid=<tid>::
+        Profile events on existing thread ID.
 -r <priority>::
 --realtime=<priority>::
@@ -78,6 +86,18 @@ Default is to monitor all CPUS.
 --sym-annotate=<symbol>::
        Annotate this symbol.
+-K::
+--hide_kernel_symbols::
+        Hide kernel symbols.
+-U::
+--hide_user_symbols::
+        Hide user symbols.
+-D::
+--dump-symtab::
+        Dump the symbol table used for profiling.
 -v::
 --verbose::
        Be more verbose (show counter open errors, etc).
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 8c7fc0c8f0b8..c12659d8cb26 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -7,6 +7,7 @@ include/linux/stringify.h
 lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
+arch/*/lib/memcpy*.S
 include/linux/poison.h
 include/linux/magic.h
 include/linux/hw_breakpoint.h
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index d1db0f676a4b..d88137a4356e 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -185,7 +185,10 @@ ifeq ($(ARCH),i386)
        ARCH := x86
 endif
 ifeq ($(ARCH),x86_64)
+        RAW_ARCH := x86_64
        ARCH := x86
+        ARCH_CFLAGS := -DARCH_X86_64
+        ARCH_INCLUDE = ../../arch/x86/lib/memcpy_64.S
 endif
 # CFLAGS and LDFLAGS are for the users to override from the command line.
@@ -375,6 +378,7 @@ LIB_H += util/include/linux/prefetch.h
 LIB_H += util/include/linux/rbtree.h
 LIB_H += util/include/linux/string.h
 LIB_H += util/include/linux/types.h
+LIB_H += util/include/linux/linkage.h
 LIB_H += util/include/asm/asm-offsets.h
 LIB_H += util/include/asm/bug.h
 LIB_H += util/include/asm/byteorder.h
@@ -383,6 +387,8 @@ LIB_H += util/include/asm/swab.h
 LIB_H += util/include/asm/system.h
 LIB_H += util/include/asm/uaccess.h
 LIB_H += util/include/dwarf-regs.h
+LIB_H += util/include/asm/dwarf2.h
+LIB_H += util/include/asm/cpufeature.h
 LIB_H += perf.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
@@ -417,6 +423,7 @@ LIB_H += util/probe-finder.h
 LIB_H += util/probe-event.h
 LIB_H += util/pstack.h
 LIB_H += util/cpumap.h
+LIB_H += $(ARCH_INCLUDE)
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -472,6 +479,9 @@ BUILTIN_OBJS += $(OUTPUT)builtin-bench.o
 # Benchmark modules
 BUILTIN_OBJS += $(OUTPUT)bench/sched-messaging.o
 BUILTIN_OBJS += $(OUTPUT)bench/sched-pipe.o
+ifeq ($(RAW_ARCH),x86_64)
+BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy-x86-64-asm.o
+endif
 BUILTIN_OBJS += $(OUTPUT)bench/mem-memcpy.o
 BUILTIN_OBJS += $(OUTPUT)builtin-diff.o
@@ -485,7 +495,7 @@ BUILTIN_OBJS += $(OUTPUT)builtin-report.o
 BUILTIN_OBJS += $(OUTPUT)builtin-stat.o
 BUILTIN_OBJS += $(OUTPUT)builtin-timechart.o
 BUILTIN_OBJS += $(OUTPUT)builtin-top.o
-BUILTIN_OBJS += $(OUTPUT)builtin-trace.o
+BUILTIN_OBJS += $(OUTPUT)builtin-script.o
 BUILTIN_OBJS += $(OUTPUT)builtin-probe.o
 BUILTIN_OBJS += $(OUTPUT)builtin-kmem.o
 BUILTIN_OBJS += $(OUTPUT)builtin-lock.o
@@ -507,7 +517,7 @@ PERFLIBS = $(LIB_FILE)
 -include config.mak
 ifndef NO_DWARF
-FLAGS_DWARF=$(ALL_CFLAGS) -I/usr/include/elfutils -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
+FLAGS_DWARF=$(ALL_CFLAGS) -ldw -lelf $(ALL_LDFLAGS) $(EXTLIBS)
 ifneq ($(call try-cc,$(SOURCE_DWARF),$(FLAGS_DWARF)),y)
        msg := $(warning No libdw.h found or old libdw.h found or elfutils is older than 0.138, disables dwarf support. Please install new elfutils-devel/libdw-dev);
        NO_DWARF := 1
@@ -554,7 +564,7 @@ ifndef NO_DWARF
 ifeq ($(origin PERF_HAVE_DWARF_REGS), undefined)
        msg := $(warning DWARF register mappings have not been defined for architecture $(ARCH), DWARF support disabled);
 else
-        BASIC_CFLAGS += -I/usr/include/elfutils -DDWARF_SUPPORT
+        BASIC_CFLAGS += -DDWARF_SUPPORT
        EXTLIBS += -lelf -ldw
        LIB_OBJS += $(OUTPUT)util/probe-finder.o
 endif # PERF_HAVE_DWARF_REGS
@@ -898,6 +908,7 @@ BASIC_CFLAGS += -DSHA1_HEADER='$(SHA1_HEADER_SQ)' \
 LIB_OBJS += $(COMPAT_OBJS)
 ALL_CFLAGS += $(BASIC_CFLAGS)
+ALL_CFLAGS += $(ARCH_CFLAGS)
 ALL_LDFLAGS += $(BASIC_LDFLAGS)
 export TAR INSTALL DESTDIR SHELL_PATH
diff --git a/tools/perf/bench/mem-memcpy-arch.h b/tools/perf/bench/mem-memcpy-arch.h
new file mode 100644
index 000000000000..a72e36cb5394
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-arch.h
@@ -0,0 +1,12 @@
+#ifdef ARCH_X86_64
+#define MEMCPY_FN(fn, name, desc)               \
+        extern void *fn(void *, const void *, size_t);
+#include "mem-memcpy-x86-64-asm-def.h"
+#undef MEMCPY_FN
+#endif
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm-def.h b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
new file mode 100644
index 000000000000..d588b87696fc
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm-def.h
@@ -0,0 +1,4 @@
+MEMCPY_FN(__memcpy,
+        "x86-64-unrolled",
+        "unrolled memcpy() in arch/x86/lib/memcpy_64.S")
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
new file mode 100644
index 000000000000..a57b66e853c2
--- /dev/null
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -0,0 +1,2 @@
+#include "../../../arch/x86/lib/memcpy_64.S"
diff --git a/tools/perf/bench/mem-memcpy.c b/tools/perf/bench/mem-memcpy.c
index 38dae7465142..db82021f4b91 100644
--- a/tools/perf/bench/mem-memcpy.c
+++ b/tools/perf/bench/mem-memcpy.c
@@ -12,6 +12,7 @@
 #include "../util/parse-options.h"
 #include "../util/header.h"
 #include "bench.h"
+#include "mem-memcpy-arch.h"
 #include <stdio.h>
 #include <stdlib.h>
@@ -23,8 +24,10 @@
 static const char       *length_str     = "1MB";
 static const char       *routine        = "default";
-static bool             use_clock       = false;
+static bool             use_clock;
 static int              clock_fd;
+static bool             only_prefault;
+static bool             no_prefault;
 static const struct option options[] = {
        OPT_STRING('l', "length", &length_str, "1MB",
@@ -34,19 +37,33 @@ static const struct option options[] = {
                    "Specify routine to copy"),
        OPT_BOOLEAN('c', "clock", &use_clock,
                    "Use CPU clock for measuring"),
+        OPT_BOOLEAN('o', "only-prefault", &only_prefault,
+                    "Show only the result with page faults before memcpy()"),
+        OPT_BOOLEAN('n', "no-prefault", &no_prefault,
+                    "Show only the result without page faults before memcpy()"),
        OPT_END()
 };
+typedef void *(*memcpy_t)(void *, const void *, size_t);
 struct routine {
        const char *name;
        const char *desc;
-        void * (*fn)(void *dst, const void *src, size_t len);
+        memcpy_t fn;
 };
 struct routine routines[] = {
        { "default",
          "Default memcpy() provided by glibc",
          memcpy },
+#ifdef ARCH_X86_64
+#define MEMCPY_FN(fn, name, desc) { name, desc, fn },
+#include "mem-memcpy-x86-64-asm-def.h"
+#undef MEMCPY_FN
+#endif
        { NULL,
          NULL,
          NULL   }
@@ -89,29 +106,98 @@ static double timeval2double(struct timeval *ts)
                (double)ts->tv_usec / (double)1000000;
 }
+static void alloc_mem(void **dst, void **src, size_t length)
+{
+        *dst = zalloc(length);
+        if (!dst)
+                die("memory allocation failed - maybe length is too large?\n");
+        *src = zalloc(length);
+        if (!src)
+                die("memory allocation failed - maybe length is too large?\n");
+}
+static u64 do_memcpy_clock(memcpy_t fn, size_t len, bool prefault)
+{
+        u64 clock_start = 0ULL, clock_end = 0ULL;
+        void *src = NULL, *dst = NULL;
+        alloc_mem(&src, &dst, len);
+        if (prefault)
+                fn(dst, src, len);
+        clock_start = get_clock();
+        fn(dst, src, len);
+        clock_end = get_clock();
+        free(src);
+        free(dst);
+        return clock_end - clock_start;
+}
+static double do_memcpy_gettimeofday(memcpy_t fn, size_t len, bool prefault)
+{
+        struct timeval tv_start, tv_end, tv_diff;
+        void *src = NULL, *dst = NULL;
+        alloc_mem(&src, &dst, len);
+        if (prefault)
+                fn(dst, src, len);
+        BUG_ON(gettimeofday(&tv_start, NULL));
+        fn(dst, src, len);
+        BUG_ON(gettimeofday(&tv_end, NULL));
+        timersub(&tv_end, &tv_start, &tv_diff);
+        free(src);
+        free(dst);
+        return (double)((double)len / timeval2double(&tv_diff));
+}
+#define pf (no_prefault ? 0 : 1)
+#define print_bps(x) do {                                       \
+                if (x < K)                                      \
+                        printf(" %14lf B/Sec", x);              \
+                else if (x < K * K)                             \
+                        printf(" %14lfd KB/Sec", x / K);        \
+                else if (x < K * K * K)                         \
+                        printf(" %14lf MB/Sec", x / K / K);     \
+                else                                            \
+                        printf(" %14lf GB/Sec", x / K / K / K); \
+        } while (0)
 int bench_mem_memcpy(int argc, const char **argv,
                     const char *prefix __used)
 {
        int i;
-        void *dst, *src;
+        size_t len;
-        size_t length;
+        double result_bps[2];
-        double bps = 0.0;
+        u64 result_clock[2];
-        struct timeval tv_start, tv_end, tv_diff;
-        u64 clock_start, clock_end, clock_diff;
-        clock_start = clock_end = clock_diff = 0ULL;
        argc = parse_options(argc, argv, options,
                             bench_mem_memcpy_usage, 0);
-        tv_diff.tv_sec = 0;
+        if (use_clock)
-        tv_diff.tv_usec = 0;
+                init_clock();
-        length = (size_t)perf_atoll((char *)length_str);
+        len = (size_t)perf_atoll((char *)length_str);
-        if ((s64)length <= 0) {
+        result_clock[0] = result_clock[1] = 0ULL;
+        result_bps[0] = result_bps[1] = 0.0;
+        if ((s64)len <= 0) {
                fprintf(stderr, "Invalid length:%s\n", length_str);
                return 1;
        }
+        /* same to without specifying either of prefault and no-prefault */
+        if (only_prefault && no_prefault)
+                only_prefault = no_prefault = false;
        for (i = 0; routines[i].name; i++) {
                if (!strcmp(routines[i].name, routine))
                        break;
@@ -126,61 +212,80 @@ int bench_mem_memcpy(int argc, const char **argv,
                return 1;
        }
-        dst = zalloc(length);
+        if (bench_format == BENCH_FORMAT_DEFAULT)
-        if (!dst)
+                printf("# Copying %s Bytes ...\n\n", length_str);
-                die("memory allocation failed - maybe length is too large?\n");
-        src = zalloc(length);
-        if (!src)
-                die("memory allocation failed - maybe length is too large?\n");
-        if (bench_format == BENCH_FORMAT_DEFAULT) {
-                printf("# Copying %s Bytes from %p to %p ...\n\n",
-                       length_str, src, dst);
-        }
-        if (use_clock) {
-                init_clock();
-                clock_start = get_clock();
-        } else {
-                BUG_ON(gettimeofday(&tv_start, NULL));
-        }
-        routines[i].fn(dst, src, length);
-        if (use_clock) {
+        if (!only_prefault && !no_prefault) {
-                clock_end = get_clock();
+                /* show both of results */
-                clock_diff = clock_end - clock_start;
+                if (use_clock) {
+                        result_clock[0] =
+                                do_memcpy_clock(routines[i].fn, len, false);
+                        result_clock[1] =
+                                do_memcpy_clock(routines[i].fn, len, true);
+                } else {
+                        result_bps[0] =
+                                do_memcpy_gettimeofday(routines[i].fn,
+                                                len, false);
+                        result_bps[1] =
+                                do_memcpy_gettimeofday(routines[i].fn,
+                                                len, true);
+                }
        } else {
-                BUG_ON(gettimeofday(&tv_end, NULL));
+                if (use_clock) {
-                timersub(&tv_end, &tv_start, &tv_diff);
+                        result_clock[pf] =
-                bps = (double)((double)length / timeval2double(&tv_diff));
+                                do_memcpy_clock(routines[i].fn,
+                                                len, only_prefault);
+                } else {
+                        result_bps[pf] =
+                                do_memcpy_gettimeofday(routines[i].fn,
+                                                len, only_prefault);
+                }
        }
        switch (bench_format) {
        case BENCH_FORMAT_DEFAULT:
-                if (use_clock) {
+                if (!only_prefault && !no_prefault) {
-                        printf(" %14lf Clock/Byte\n",
+                        if (use_clock) {
-                               (double)clock_diff / (double)length);
+                                printf(" %14lf Clock/Byte\n",
-                } else {
+                                        (double)result_clock[0]
-                        if (bps < K)
+                                        / (double)len);
-                                printf(" %14lf B/Sec\n", bps);
+                                printf(" %14lf Clock/Byte (with prefault)\n",
-                        else if (bps < K * K)
+                                        (double)result_clock[1]
-                                printf(" %14lfd KB/Sec\n", bps / 1024);
+                                        / (double)len);
-                        else if (bps < K * K * K)
+                        } else {
-                                printf(" %14lf MB/Sec\n", bps / 1024 / 1024);
+                                print_bps(result_bps[0]);
-                        else {
+                                printf("\n");
-                                printf(" %14lf GB/Sec\n",
+                                print_bps(result_bps[1]);
-                                       bps / 1024 / 1024 / 1024);
+                                printf(" (with prefault)\n");
                        }
+                } else {
+                        if (use_clock) {
+                                printf(" %14lf Clock/Byte",
+                                        (double)result_clock[pf]
+                                        / (double)len);
+                        } else
+                                print_bps(result_bps[pf]);
+                        printf("%s\n", only_prefault ? " (with prefault)" : "");
                }
                break;
        case BENCH_FORMAT_SIMPLE:
-                if (use_clock) {
+                if (!only_prefault && !no_prefault) {
-                        printf("%14lf\n",
+                        if (use_clock) {
-                               (double)clock_diff / (double)length);
+                                printf("%lf %lf\n",
-                } else
+                                        (double)result_clock[0] / (double)len,
-                        printf("%lf\n", bps);
+                                        (double)result_clock[1] / (double)len);
+                        } else {
+                                printf("%lf %lf\n",
+                                        result_bps[0], result_bps[1]);
+                        }
+                } else {
+                        if (use_clock) {
+                                printf("%lf\n", (double)result_clock[pf]
+                                        / (double)len);
+                        } else
+                                printf("%lf\n", result_bps[pf]);
+                }
                break;
        default:
                /* reaching this means there's some disaster: */
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index fca1d4402910..221b823bc26f 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -173,7 +173,7 @@ static const char * const diff_usage[] = {
 static const struct option options[] = {
        OPT_INCR('v', "verbose", &verbose,
                    "be more verbose (show symbol address, etc)"),
-        OPT_BOOLEAN('m', "displacement", &show_displacement,
+        OPT_BOOLEAN('M', "displacement", &show_displacement,
                    "Show position displacement relative to baseline"),
        OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
                    "dump raw trace in ASCII"),
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 821c1586a22b..8452a2ae2191 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -982,9 +982,9 @@ int cmd_lock(int argc, const char **argv, const char *prefix __used)
                                usage_with_options(report_usage, report_options);
                }
                __cmd_report();
-        } else if (!strcmp(argv[0], "trace")) {
+        } else if (!strcmp(argv[0], "script")) {
-                /* Aliased to 'perf trace' */
+                /* Aliased to 'perf script' */
-                return cmd_trace(argc, argv, prefix);
+                return cmd_script(argc, argv, prefix);
        } else if (!strcmp(argv[0], "info")) {
                if (argc) {
                        argc = parse_options(argc, argv,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index e2c2de201eec..024e1441d76b 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -61,6 +61,7 @@ static bool			inherit_stat			=  false;
 static bool                     no_samples                      =  false;
 static bool                     sample_address                  =  false;
 static bool                     no_buildid                      =  false;
+static bool                     no_buildid_cache                =  false;
 static long                     samples                         =      0;
 static u64                      bytes_written                   =      0;
@@ -326,7 +327,7 @@ try_again:
                                goto try_again;
                        }
                        printf("\n");
-                        error("perfcounter syscall returned with %d (%s)\n",
+                        error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
                                        fd[nr_cpu][counter][thread_index], strerror(err));
 #if defined(__i386__) || defined(__x86_64__)
@@ -437,7 +438,8 @@ static void atexit_header(void)
        if (!pipe_output) {
                session->header.data_size += bytes_written;
-                process_buildids();
+                if (!no_buildid)
+                        process_buildids();
                perf_header__write(&session->header, output, true);
                perf_session__delete(session);
                symbol__exit();
@@ -557,6 +559,9 @@ static int __cmd_record(int argc, const char **argv)
                return -1;
        }
+        if (!no_buildid)
+                perf_header__set_feat(&session->header, HEADER_BUILD_ID);
        if (!file_new) {
                err = perf_header__read(session, output);
                if (err < 0)
@@ -831,8 +836,10 @@ const struct option record_options[] = {
                    "Sample addresses"),
        OPT_BOOLEAN('n', "no-samples", &no_samples,
                    "don't sample"),
-        OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid,
+        OPT_BOOLEAN('N', "no-buildid-cache", &no_buildid_cache,
                    "do not update the buildid cache"),
+        OPT_BOOLEAN('B', "no-buildid", &no_buildid,
+                    "do not collect buildids in perf.data"),
        OPT_END()
 };
@@ -857,7 +864,8 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
        }
        symbol__init();
-        if (no_buildid)
+        if (no_buildid_cache || no_buildid)
                disable_buildid_cache();
        if (!nr_counters) {
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 55f3b5dcc731..26523c939791 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -1888,10 +1888,10 @@ int cmd_sched(int argc, const char **argv, const char *prefix __used)
                usage_with_options(sched_usage, sched_options);
        /*
-         * Aliased to 'perf trace' for now:
+         * Aliased to 'perf script' for now:
         */
-        if (!strcmp(argv[0], "trace"))
+        if (!strcmp(argv[0], "script"))
-                return cmd_trace(argc, argv, prefix);
+                return cmd_script(argc, argv, prefix);
        symbol__init();
        if (!strncmp(argv[0], "rec", 3)) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-script.c
index 86cfe3800e6b..4539551ab40e 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-script.c
@@ -56,7 +56,7 @@ static void setup_scripting(void)
 static int cleanup_scripting(void)
 {
-        pr_debug("\nperf trace script stopped\n");
+        pr_debug("\nperf script stopped\n");
        return scripting_ops->stop_script();
 }
@@ -137,7 +137,7 @@ static void sig_handler(int sig __unused)
        session_done = 1;
 }
-static int __cmd_trace(struct perf_session *session)
+static int __cmd_script(struct perf_session *session)
 {
        int ret;
@@ -247,7 +247,7 @@ static void list_available_languages(void)
        fprintf(stderr, "\n");
        fprintf(stderr, "Scripting language extensions (used in "
-                "perf trace -s [spec:]script.[spec]):\n\n");
+                "perf script -s [spec:]script.[spec]):\n\n");
        list_for_each_entry(s, &script_specs, node)
                fprintf(stderr, "  %-42s [%s]\n", s->spec, s->ops->name);
@@ -301,17 +301,34 @@ static int parse_scriptname(const struct option *opt __used,
        return 0;
 }
-#define for_each_lang(scripts_dir, lang_dirent, lang_next)              \
+/* Helper function for filesystems that return a dent->d_type DT_UNKNOWN */
+static int is_directory(const char *base_path, const struct dirent *dent)
+{
+        char path[PATH_MAX];
+        struct stat st;
+        sprintf(path, "%s/%s", base_path, dent->d_name);
+        if (stat(path, &st))
+                return 0;
+        return S_ISDIR(st.st_mode);
+}
+#define for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next)\
        while (!readdir_r(scripts_dir, &lang_dirent, &lang_next) &&     \
               lang_next)                                               \
-                if (lang_dirent.d_type == DT_DIR &&                     \
+                if ((lang_dirent.d_type == DT_DIR ||                    \
+                     (lang_dirent.d_type == DT_UNKNOWN &&               \
+                      is_directory(scripts_path, &lang_dirent))) &&     \
                    (strcmp(lang_dirent.d_name, ".")) &&                \
                    (strcmp(lang_dirent.d_name, "..")))
-#define for_each_script(lang_dir, script_dirent, script_next)           \
+#define for_each_script(lang_path, lang_dir, script_dirent, script_next)\
        while (!readdir_r(lang_dir, &script_dirent, &script_next) &&    \
               script_next)                                             \
-                if (script_dirent.d_type != DT_DIR)
+                if (script_dirent.d_type != DT_DIR &&                   \
+                    (script_dirent.d_type != DT_UNKNOWN ||              \
+                     !is_directory(lang_path, &script_dirent)))
 #define RECORD_SUFFIX                   "-record"
@@ -466,14 +483,14 @@ static int list_available_scripts(const struct option *opt __used,
        if (!scripts_dir)
                return -1;
-        for_each_lang(scripts_dir, lang_dirent, lang_next) {
+        for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
                snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
                         lang_dirent.d_name);
                lang_dir = opendir(lang_path);
                if (!lang_dir)
                        continue;
-                for_each_script(lang_dir, script_dirent, script_next) {
+                for_each_script(lang_path, lang_dir, script_dirent, script_next) {
                        script_root = strdup(script_dirent.d_name);
                        str = ends_with(script_root, REPORT_SUFFIX);
                        if (str) {
@@ -514,14 +531,14 @@ static char *get_script_path(const char *script_root, const char *suffix)
        if (!scripts_dir)
                return NULL;
-        for_each_lang(scripts_dir, lang_dirent, lang_next) {
+        for_each_lang(scripts_path, scripts_dir, lang_dirent, lang_next) {
                snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
                         lang_dirent.d_name);
                lang_dir = opendir(lang_path);
                if (!lang_dir)
                        continue;
-                for_each_script(lang_dir, script_dirent, script_next) {
+                for_each_script(lang_path, lang_dir, script_dirent, script_next) {
                        __script_root = strdup(script_dirent.d_name);
                        str = ends_with(__script_root, suffix);
                        if (str) {
@@ -569,12 +586,12 @@ out:
        return n_args;
 }
-static const char * const trace_usage[] = {
+static const char * const script_usage[] = {
-        "perf trace [<options>]",
+        "perf script [<options>]",
-        "perf trace [<options>] record <script> [<record-options>] <command>",
+        "perf script [<options>] record <script> [<record-options>] <command>",
-        "perf trace [<options>] report <script> [script-args]",
+        "perf script [<options>] report <script> [script-args]",
-        "perf trace [<options>] <script> [<record-options>] <command>",
+        "perf script [<options>] <script> [<record-options>] <command>",
-        "perf trace [<options>] <top-script> [script-args]",
+        "perf script [<options>] <top-script> [script-args]",
        NULL
 };
@@ -591,7 +608,7 @@ static const struct option options[] = {
                     "script file name (lang:script name, script name, or *)",
                     parse_scriptname),
        OPT_STRING('g', "gen-script", &generate_script_lang, "lang",
-                   "generate perf-trace.xx script in specified language"),
+                   "generate perf-script.xx script in specified language"),
        OPT_STRING('i', "input", &input_name, "file",
                    "input file name"),
        OPT_BOOLEAN('d', "debug-mode", &debug_mode,
@@ -614,7 +631,7 @@ static bool have_cmd(int argc, const char **argv)
        return argc != 0;
 }
-int cmd_trace(int argc, const char **argv, const char *prefix __used)
+int cmd_script(int argc, const char **argv, const char *prefix __used)
 {
        char *rec_script_path = NULL;
        char *rep_script_path = NULL;
@@ -626,7 +643,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
        setup_scripting();
-        argc = parse_options(argc, argv, options, trace_usage,
+        argc = parse_options(argc, argv, options, script_usage,
                             PARSE_OPT_STOP_AT_NON_OPTION);
        if (argc > 1 && !strncmp(argv[0], "rec", strlen("rec"))) {
@@ -640,7 +657,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                if (!rep_script_path) {
                        fprintf(stderr,
                                "Please specify a valid report script"
-                                "(see 'perf trace -l' for listing)\n");
+                                "(see 'perf script -l' for listing)\n");
                        return -1;
                }
        }
@@ -658,8 +675,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                if (!rec_script_path && !rep_script_path) {
                        fprintf(stderr, " Couldn't find script %s\n\n See perf"
-                                " trace -l for available scripts.\n", argv[0]);
+                                " script -l for available scripts.\n", argv[0]);
-                        usage_with_options(trace_usage, options);
+                        usage_with_options(script_usage, options);
                }
                if (is_top_script(argv[0])) {
@@ -671,9 +688,9 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                        rec_args = (argc - 1) - rep_args;
                        if (rec_args < 0) {
                                fprintf(stderr, " %s script requires options."
-                                        "\n\n See perf trace -l for available "
+                                        "\n\n See perf script -l for available "
                                        "scripts and options.\n", argv[0]);
-                                usage_with_options(trace_usage, options);
+                                usage_with_options(script_usage, options);
                        }
                }
@@ -806,7 +823,7 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                        return -1;
                }
-                err = scripting_ops->generate_script("perf-trace");
+                err = scripting_ops->generate_script("perf-script");
                goto out;
        }
@@ -814,10 +831,10 @@ int cmd_trace(int argc, const char **argv, const char *prefix __used)
                err = scripting_ops->start_script(script_name, argc, argv);
                if (err)
                        goto out;
-                pr_debug("perf trace started with script %s\n\n", script_name);
+                pr_debug("perf script started with script %s\n\n", script_name);
        }
-        err = __cmd_trace(session);
+        err = __cmd_script(session);
        perf_session__delete(session);
        cleanup_scripting();
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a6b4d44f9502..7ff746da7e6c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -52,6 +52,8 @@
 #include <math.h>
 #include <locale.h>
+#define DEFAULT_SEPARATOR       " "
 static struct perf_event_attr default_attrs[] = {
  { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK              },
@@ -75,20 +77,30 @@ static int			run_idx				=  0;
 static int                      run_count                       =  1;
 static bool                     no_inherit                      = false;
 static bool                     scale                           =  true;
+static bool                     no_aggr                         = false;
 static pid_t                    target_pid                      = -1;
 static pid_t                    target_tid                      = -1;
 static pid_t                    *all_tids                       =  NULL;
 static int                      thread_num                      =  0;
 static pid_t                    child_pid                       = -1;
 static bool                     null_run                        =  false;
-static bool                     big_num                         =  false;
+static bool                     big_num                         =  true;
+static int                      big_num_opt                     =  -1;
 static const char               *cpu_list;
+static const char               *csv_sep                        = NULL;
+static bool                     csv_output                      = false;
 static int                      *fd[MAX_NR_CPUS][MAX_COUNTERS];
 static int                      event_scaled[MAX_COUNTERS];
+static struct {
+        u64 val;
+        u64 ena;
+        u64 run;
+} cpu_counts[MAX_NR_CPUS][MAX_COUNTERS];
 static volatile int done = 0;
 struct stats
@@ -136,19 +148,19 @@ static double stddev_stats(struct stats *stats)
 }
 struct stats                    event_res_stats[MAX_COUNTERS][3];
-struct stats                    runtime_nsecs_stats;
+struct stats                    runtime_nsecs_stats[MAX_NR_CPUS];
+struct stats                    runtime_cycles_stats[MAX_NR_CPUS];
+struct stats                    runtime_branches_stats[MAX_NR_CPUS];
 struct stats                    walltime_nsecs_stats;
-struct stats                    runtime_cycles_stats;
-struct stats                    runtime_branches_stats;
 #define MATCH_EVENT(t, c, counter)                      \
        (attrs[counter].type == PERF_TYPE_##t &&        \
         attrs[counter].config == PERF_COUNT_##c)
 #define ERR_PERF_OPEN \
-"Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
+"counter %d, sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information."
-static int create_perf_stat_counter(int counter)
+static int create_perf_stat_counter(int counter, bool *perm_err)
 {
        struct perf_event_attr *attr = attrs + counter;
        int thread;
@@ -164,11 +176,14 @@ static int create_perf_stat_counter(int counter)
                for (cpu = 0; cpu < nr_cpus; cpu++) {
                        fd[cpu][counter][0] = sys_perf_event_open(attr,
                                        -1, cpumap[cpu], -1, 0);
-                        if (fd[cpu][counter][0] < 0)
+                        if (fd[cpu][counter][0] < 0) {
-                                pr_debug(ERR_PERF_OPEN, counter,
+                                if (errno == EPERM || errno == EACCES)
+                                        *perm_err = true;
+                                error(ERR_PERF_OPEN, counter,
                                         fd[cpu][counter][0], strerror(errno));
-                        else
+                        } else {
                                ++ncreated;
+                        }
                }
        } else {
                attr->inherit = !no_inherit;
@@ -179,12 +194,15 @@ static int create_perf_stat_counter(int counter)
                for (thread = 0; thread < thread_num; thread++) {
                        fd[0][counter][thread] = sys_perf_event_open(attr,
                                all_tids[thread], -1, -1, 0);
-                        if (fd[0][counter][thread] < 0)
+                        if (fd[0][counter][thread] < 0) {
-                                pr_debug(ERR_PERF_OPEN, counter,
+                                if (errno == EPERM || errno == EACCES)
+                                        *perm_err = true;
+                                error(ERR_PERF_OPEN, counter,
                                         fd[0][counter][thread],
                                         strerror(errno));
-                        else
+                        } else {
                                ++ncreated;
+                        }
                }
        }
@@ -205,8 +223,9 @@ static inline int nsec_counter(int counter)
 /*
 * Read out the results of a single counter:
+ * aggregate counts across CPUs in system-wide mode
 */
-static void read_counter(int counter)
+static void read_counter_aggr(int counter)
 {
        u64 count[3], single_count[3];
        int cpu;
@@ -264,11 +283,58 @@ static void read_counter(int counter)
         * Save the full runtime - to allow normalization during printout:
         */
        if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
-                update_stats(&runtime_nsecs_stats, count[0]);
+                update_stats(&runtime_nsecs_stats[0], count[0]);
        if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter))
-                update_stats(&runtime_cycles_stats, count[0]);
+                update_stats(&runtime_cycles_stats[0], count[0]);
        if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter))
-                update_stats(&runtime_branches_stats, count[0]);
+                update_stats(&runtime_branches_stats[0], count[0]);
+}
+/*
+ * Read out the results of a single counter:
+ * do not aggregate counts across CPUs in system-wide mode
+ */
+static void read_counter(int counter)
+{
+        u64 count[3];
+        int cpu;
+        size_t res, nv;
+        count[0] = count[1] = count[2] = 0;
+        nv = scale ? 3 : 1;
+        for (cpu = 0; cpu < nr_cpus; cpu++) {
+                if (fd[cpu][counter][0] < 0)
+                        continue;
+                res = read(fd[cpu][counter][0], count, nv * sizeof(u64));
+                assert(res == nv * sizeof(u64));
+                close(fd[cpu][counter][0]);
+                fd[cpu][counter][0] = -1;
+                if (scale) {
+                        if (count[2] == 0) {
+                                count[0] = 0;
+                        } else if (count[2] < count[1]) {
+                                count[0] = (unsigned long long)
+                                ((double)count[0] * count[1] / count[2] + 0.5);
+                        }
+                }
+                cpu_counts[cpu][counter].val = count[0]; /* scaled count */
+                cpu_counts[cpu][counter].ena = count[1];
+                cpu_counts[cpu][counter].run = count[2];
+                if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter))
+                        update_stats(&runtime_nsecs_stats[cpu], count[0]);
+                if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter))
+                        update_stats(&runtime_cycles_stats[cpu], count[0]);
+                if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter))
+                        update_stats(&runtime_branches_stats[cpu], count[0]);
+        }
 }
 static int run_perf_stat(int argc __used, const char **argv)
@@ -277,6 +343,7 @@ static int run_perf_stat(int argc __used, const char **argv)
        int status = 0;
        int counter, ncreated = 0;
        int child_ready_pipe[2], go_pipe[2];
+        bool perm_err = false;
        const bool forks = (argc > 0);
        char buf;
@@ -335,12 +402,15 @@ static int run_perf_stat(int argc __used, const char **argv)
        }
        for (counter = 0; counter < nr_counters; counter++)
-                ncreated += create_perf_stat_counter(counter);
+                ncreated += create_perf_stat_counter(counter, &perm_err);
-        if (ncreated == 0) {
+        if (ncreated < nr_counters) {
-                pr_err("No permission to collect %sstats.\n"
+                if (perm_err)
-                       "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
+                        error("You may not have permission to collect %sstats.\n"
-                       system_wide ? "system-wide " : "");
+                              "\t Consider tweaking"
+                              " /proc/sys/kernel/perf_event_paranoid or running as root.",
+                              system_wide ? "system-wide " : "");
+                die("Not all events could be opened.\n");
                if (child_pid != -1)
                        kill(child_pid, SIGTERM);
                return -1;
@@ -362,9 +432,13 @@ static int run_perf_stat(int argc __used, const char **argv)
        update_stats(&walltime_nsecs_stats, t1 - t0);
-        for (counter = 0; counter < nr_counters; counter++)
+        if (no_aggr) {
-                read_counter(counter);
+                for (counter = 0; counter < nr_counters; counter++)
+                        read_counter(counter);
+        } else {
+                for (counter = 0; counter < nr_counters; counter++)
+                        read_counter_aggr(counter);
+        }
        return WEXITSTATUS(status);
 }
@@ -377,11 +451,21 @@ static void print_noise(int counter, double avg)
                        100 * stddev_stats(&event_res_stats[counter][0]) / avg);
 }
-static void nsec_printout(int counter, double avg)
+static void nsec_printout(int cpu, int counter, double avg)
 {
        double msecs = avg / 1e6;
+        char cpustr[16] = { '\0', };
+        const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-24s";
+        if (no_aggr)
+                sprintf(cpustr, "CPU%*d%s",
+                        csv_output ? 0 : -4,
+                        cpumap[cpu], csv_sep);
-        fprintf(stderr, " %18.6f  %-24s", msecs, event_name(counter));
+        fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(counter));
+        if (csv_output)
+                return;
        if (MATCH_EVENT(SOFTWARE, SW_TASK_CLOCK, counter)) {
                fprintf(stderr, " # %10.3f CPUs ",
@@ -389,33 +473,49 @@ static void nsec_printout(int counter, double avg)
        }
 }
-static void abs_printout(int counter, double avg)
+static void abs_printout(int cpu, int counter, double avg)
 {
        double total, ratio = 0.0;
+        char cpustr[16] = { '\0', };
+        const char *fmt;
+        if (csv_output)
+                fmt = "%s%.0f%s%s";
+        else if (big_num)
+                fmt = "%s%'18.0f%s%-24s";
+        else
+                fmt = "%s%18.0f%s%-24s";
-        if (big_num)
+        if (no_aggr)
-                fprintf(stderr, " %'18.0f  %-24s", avg, event_name(counter));
+                sprintf(cpustr, "CPU%*d%s",
+                        csv_output ? 0 : -4,
+                        cpumap[cpu], csv_sep);
        else
-                fprintf(stderr, " %18.0f  %-24s", avg, event_name(counter));
+                cpu = 0;
+        fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(counter));
+        if (csv_output)
+                return;
        if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
-                total = avg_stats(&runtime_cycles_stats);
+                total = avg_stats(&runtime_cycles_stats[cpu]);
                if (total)
                        ratio = avg / total;
                fprintf(stderr, " # %10.3f IPC  ", ratio);
        } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) &&
-                        runtime_branches_stats.n != 0) {
+                        runtime_branches_stats[cpu].n != 0) {
-                total = avg_stats(&runtime_branches_stats);
+                total = avg_stats(&runtime_branches_stats[cpu]);
                if (total)
                        ratio = avg * 100 / total;
                fprintf(stderr, " # %10.3f %%    ", ratio);
-        } else if (runtime_nsecs_stats.n != 0) {
+        } else if (runtime_nsecs_stats[cpu].n != 0) {
-                total = avg_stats(&runtime_nsecs_stats);
+                total = avg_stats(&runtime_nsecs_stats[cpu]);
                if (total)
                        ratio = 1000.0 * avg / total;
@@ -426,22 +526,29 @@ static void abs_printout(int counter, double avg)
 /*
 * Print out the results of a single counter:
+ * aggregated counts in system-wide mode
 */
-static void print_counter(int counter)
+static void print_counter_aggr(int counter)
 {
        double avg = avg_stats(&event_res_stats[counter][0]);
        int scaled = event_scaled[counter];
        if (scaled == -1) {
-                fprintf(stderr, " %18s  %-24s\n",
+                fprintf(stderr, "%*s%s%-24s\n",
-                        "<not counted>", event_name(counter));
+                        csv_output ? 0 : 18,
+                        "<not counted>", csv_sep, event_name(counter));
                return;
        }
        if (nsec_counter(counter))
-                nsec_printout(counter, avg);
+                nsec_printout(-1, counter, avg);
        else
-                abs_printout(counter, avg);
+                abs_printout(-1, counter, avg);
+        if (csv_output) {
+                fputc('\n', stderr);
+                return;
+        }
        print_noise(counter, avg);
@@ -458,40 +565,91 @@ static void print_counter(int counter)
        fprintf(stderr, "\n");
 }
+/*
+ * Print out the results of a single counter:
+ * does not use aggregated count in system-wide
+ */
+static void print_counter(int counter)
+{
+        u64 ena, run, val;
+        int cpu;
+        for (cpu = 0; cpu < nr_cpus; cpu++) {
+                val = cpu_counts[cpu][counter].val;
+                ena = cpu_counts[cpu][counter].ena;
+                run = cpu_counts[cpu][counter].run;
+                if (run == 0 || ena == 0) {
+                        fprintf(stderr, "CPU%*d%s%*s%s%-24s",
+                                csv_output ? 0 : -4,
+                                cpumap[cpu], csv_sep,
+                                csv_output ? 0 : 18,
+                                "<not counted>", csv_sep,
+                                event_name(counter));
+                        fprintf(stderr, "\n");
+                        continue;
+                }
+                if (nsec_counter(counter))
+                        nsec_printout(cpu, counter, val);
+                else
+                        abs_printout(cpu, counter, val);
+                if (!csv_output) {
+                        print_noise(counter, 1.0);
+                        if (run != ena) {
+                                fprintf(stderr, "  (scaled from %.2f%%)",
+                                        100.0 * run / ena);
+                        }
+                }
+                fprintf(stderr, "\n");
+        }
+}
 static void print_stat(int argc, const char **argv)
 {
        int i, counter;
        fflush(stdout);
-        fprintf(stderr, "\n");
+        if (!csv_output) {
-        fprintf(stderr, " Performance counter stats for ");
+                fprintf(stderr, "\n");
-        if(target_pid == -1 && target_tid == -1) {
+                fprintf(stderr, " Performance counter stats for ");
-                fprintf(stderr, "\'%s", argv[0]);
+                if(target_pid == -1 && target_tid == -1) {
-                for (i = 1; i < argc; i++)
+                        fprintf(stderr, "\'%s", argv[0]);
-                        fprintf(stderr, " %s", argv[i]);
+                        for (i = 1; i < argc; i++)
-        } else if (target_pid != -1)
+                                fprintf(stderr, " %s", argv[i]);
-                fprintf(stderr, "process id \'%d", target_pid);
+                } else if (target_pid != -1)
-        else
+                        fprintf(stderr, "process id \'%d", target_pid);
-                fprintf(stderr, "thread id \'%d", target_tid);
+                else
+                        fprintf(stderr, "thread id \'%d", target_tid);
-        fprintf(stderr, "\'");
-        if (run_count > 1)
+                fprintf(stderr, "\'");
-                fprintf(stderr, " (%d runs)", run_count);
+                if (run_count > 1)
-        fprintf(stderr, ":\n\n");
+                        fprintf(stderr, " (%d runs)", run_count);
+                fprintf(stderr, ":\n\n");
+        }
-        for (counter = 0; counter < nr_counters; counter++)
+        if (no_aggr) {
-                print_counter(counter);
+                for (counter = 0; counter < nr_counters; counter++)
+                        print_counter(counter);
+        } else {
+                for (counter = 0; counter < nr_counters; counter++)
+                        print_counter_aggr(counter);
+        }
-        fprintf(stderr, "\n");
+        if (!csv_output) {
-        fprintf(stderr, " %18.9f  seconds time elapsed",
+                fprintf(stderr, "\n");
-                        avg_stats(&walltime_nsecs_stats)/1e9);
+                fprintf(stderr, " %18.9f  seconds time elapsed",
-        if (run_count > 1) {
+                                avg_stats(&walltime_nsecs_stats)/1e9);
-                fprintf(stderr, "   ( +- %7.3f%% )",
+                if (run_count > 1) {
+                        fprintf(stderr, "   ( +- %7.3f%% )",
                                100*stddev_stats(&walltime_nsecs_stats) /
                                avg_stats(&walltime_nsecs_stats));
+                }
+                fprintf(stderr, "\n\n");
        }
-        fprintf(stderr, "\n\n");
 }
 static volatile int signr = -1;
@@ -521,6 +679,13 @@ static const char * const stat_usage[] = {
        NULL
 };
+static int stat__set_big_num(const struct option *opt __used,
+                             const char *s __used, int unset)
+{
+        big_num_opt = unset ? 0 : 1;
+        return 0;
+}
 static const struct option options[] = {
        OPT_CALLBACK('e', "event", NULL, "event",
                     "event selector. use 'perf list' to list available events",
@@ -541,10 +706,15 @@ static const struct option options[] = {
                    "repeat command and print average + stddev (max: 100)"),
        OPT_BOOLEAN('n', "null", &null_run,
                    "null run - dont start any counters"),
-        OPT_BOOLEAN('B', "big-num", &big_num,
+        OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, 
-                    "print large numbers with thousands\' separators"),
+                           "print large numbers with thousands\' separators",
+                           stat__set_big_num),
        OPT_STRING('C', "cpu", &cpu_list, "cpu",
                    "list of cpus to monitor in system-wide"),
+        OPT_BOOLEAN('A', "no-aggr", &no_aggr,
+                    "disable CPU count aggregation"),
+        OPT_STRING('x', "field-separator", &csv_sep, "separator",
+                   "print counts with custom separator"),
        OPT_END()
 };
@@ -557,11 +727,34 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
        argc = parse_options(argc, argv, options, stat_usage,
                PARSE_OPT_STOP_AT_NON_OPTION);
+        if (csv_sep)
+                csv_output = true;
+        else
+                csv_sep = DEFAULT_SEPARATOR;
+        /*
+         * let the spreadsheet do the pretty-printing
+         */
+        if (csv_output) {
+                /* User explicitely passed -B? */
+                if (big_num_opt == 1) {
+                        fprintf(stderr, "-B option not supported with -x\n");
+                        usage_with_options(stat_usage, options);
+                } else /* Nope, so disable big number formatting */
+                        big_num = false;
+        } else if (big_num_opt == 0) /* User passed --no-big-num */
+                big_num = false;
        if (!argc && target_pid == -1 && target_tid == -1)
                usage_with_options(stat_usage, options);
        if (run_count <= 0)
                usage_with_options(stat_usage, options);
+        /* no_aggr is for system-wide only */
+        if (no_aggr && !system_wide)
+                usage_with_options(stat_usage, options);
        /* Set attrs and nr_counters if no event is selected and !null_run */
        if (!null_run && !nr_counters) {
                memcpy(attrs, default_attrs, sizeof(default_attrs));
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index dd625808c2a5..3d2b47d5121a 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1214,7 +1214,9 @@ try_again:
                        int err = errno;
                        if (err == EPERM || err == EACCES)
-                                die("No permission - are you root?\n");
+                                die("Permission error - are you root?\n"
+                                        "\t Consider tweaking"
+                                        " /proc/sys/kernel/perf_event_paranoid.\n");
                        /*
                         * If it's cycles then fall back to hrtimer
                         * based cpu-clock-tick sw counter, which
@@ -1231,7 +1233,7 @@ try_again:
                                goto try_again;
                        }
                        printf("\n");
-                        error("perfcounter syscall returned with %d (%s)\n",
+                        error("sys_perf_event_open() syscall returned with %d (%s).  /bin/dmesg may provide additional information.\n",
                                        fd[i][counter][thread_index], strerror(err));
                        die("No CONFIG_PERF_EVENTS=y kernel support configured?\n");
                        exit(-1);
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index 921245b28583..c7798c7f24ed 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -27,7 +27,7 @@ extern int cmd_report(int argc, const char **argv, const char *prefix);
 extern int cmd_stat(int argc, const char **argv, const char *prefix);
 extern int cmd_timechart(int argc, const char **argv, const char *prefix);
 extern int cmd_top(int argc, const char **argv, const char *prefix);
-extern int cmd_trace(int argc, const char **argv, const char *prefix);
+extern int cmd_script(int argc, const char **argv, const char *prefix);
 extern int cmd_version(int argc, const char **argv, const char *prefix);
 extern int cmd_probe(int argc, const char **argv, const char *prefix);
 extern int cmd_kmem(int argc, const char **argv, const char *prefix);
diff --git a/tools/perf/command-list.txt b/tools/perf/command-list.txt
index 949d77fc0b97..16b5088cf8f4 100644
--- a/tools/perf/command-list.txt
+++ b/tools/perf/command-list.txt
@@ -16,7 +16,7 @@ perf-report			mainporcelain common
 perf-stat                       mainporcelain common
 perf-timechart                  mainporcelain common
 perf-top                        mainporcelain common
-perf-trace                      mainporcelain common
+perf-script                     mainporcelain common
 perf-probe                      mainporcelain common
 perf-kmem                       mainporcelain common
 perf-lock                       mainporcelain common
diff --git a/tools/perf/feature-tests.mak b/tools/perf/feature-tests.mak
index b253db634f04..b041ca67a2cb 100644
--- a/tools/perf/feature-tests.mak
+++ b/tools/perf/feature-tests.mak
@@ -9,8 +9,8 @@ endef
 ifndef NO_DWARF
 define SOURCE_DWARF
 #include <dwarf.h>
-#include <libdw.h>
+#include <elfutils/libdw.h>
-#include <version.h>
+#include <elfutils/version.h>
 #ifndef _ELFUTILS_PREREQ
 #error
 #endif
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index cdd6c03f1e14..595d0f4a7103 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -323,7 +323,7 @@ static void handle_internal_command(int argc, const char **argv)
                { "top",        cmd_top,        0 },
                { "annotate",   cmd_annotate,   0 },
                { "version",    cmd_version,    0 },
-                { "trace",      cmd_trace,      0 },
+                { "script",     cmd_script,     0 },
                { "sched",      cmd_sched,      0 },
                { "probe",      cmd_probe,      0 },
                { "kmem",       cmd_kmem,       0 },
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index 957085dd5d8d..315067b8f552 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -1,5 +1,5 @@
 /*
- * Context.c.  Python interfaces for perf trace.
+ * Context.c.  Python interfaces for perf script.
 *
 * Copyright (C) 2010 Tom Zanussi <tzanussi@gmail.com>
 *
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c8d81b00089d..01bbe8ecec3f 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -46,20 +46,16 @@ int dump_printf(const char *fmt, ...)
        return ret;
 }
-static int dump_printf_color(const char *fmt, const char *color, ...)
+#ifdef NO_NEWT_SUPPORT
+void ui__warning(const char *format, ...)
 {
        va_list args;
-        int ret = 0;
-        if (dump_trace) {
+        va_start(args, format);
-                va_start(args, color);
+        vfprintf(stderr, format, args);
-                ret = color_vfprintf(stdout, color, fmt, args);
+        va_end(args);
-                va_end(args);
-        }
-        return ret;
 }
+#endif
 void trace_event(event_t *event)
 {
@@ -70,29 +66,29 @@ void trace_event(event_t *event)
        if (!dump_trace)
                return;
-        dump_printf(".");
+        printf(".");
-        dump_printf_color("\n. ... raw event: size %d bytes\n", color,
+        color_fprintf(stdout, color, "\n. ... raw event: size %d bytes\n",
-                          event->header.size);
+                      event->header.size);
        for (i = 0; i < event->header.size; i++) {
                if ((i & 15) == 0) {
-                        dump_printf(".");
+                        printf(".");
-                        dump_printf_color("  %04x: ", color, i);
+                        color_fprintf(stdout, color, "  %04x: ", i);
                }
-                dump_printf_color(" %02x", color, raw_event[i]);
+                color_fprintf(stdout, color, " %02x", raw_event[i]);
                if (((i & 15) == 15) || i == event->header.size-1) {
-                        dump_printf_color("  ", color);
+                        color_fprintf(stdout, color, "  ");
                        for (j = 0; j < 15-(i & 15); j++)
-                                dump_printf_color("   ", color);
+                                color_fprintf(stdout, color, "   ");
                        for (j = i & ~15; j <= i; j++) {
-                                dump_printf_color("%c", color,
+                                color_fprintf(stdout, color, "%c",
-                                                isprint(raw_event[j]) ?
+                                              isprint(raw_event[j]) ?
-                                                raw_event[j] : '.');
+                                              raw_event[j] : '.');
                        }
-                        dump_printf_color("\n", color);
+                        color_fprintf(stdout, color, "\n");
                }
        }
-        dump_printf(".\n");
+        printf(".\n");
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 7b514082bbaf..ca35fd66b5df 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -35,4 +35,6 @@ int ui_helpline__show_help(const char *format, va_list ap);
 #include "ui/progress.h"
 #endif
+void ui__warning(const char *format, ...) __attribute__((format(printf, 1, 2)));
 #endif  /* __PERF_DEBUG_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index dab9e754a281..7260db75b93d 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -392,7 +392,7 @@ static void event_set_kernel_mmap_len(struct map **maps, event_t *self)
         * a zero sized synthesized MMAP event for the kernel.
         */
        if (maps[MAP__FUNCTION]->end == 0)
-                maps[MAP__FUNCTION]->end = ~0UL;
+                maps[MAP__FUNCTION]->end = ~0ULL;
 }
 static int event__process_kernel_mmap(event_t *self,
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d7e67b167ea3..f65d7dc127b6 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -152,6 +152,11 @@ void perf_header__set_feat(struct perf_header *self, int feat)
        set_bit(feat, self->adds_features);
 }
+void perf_header__clear_feat(struct perf_header *self, int feat)
+{
+        clear_bit(feat, self->adds_features);
+}
 bool perf_header__has_feat(const struct perf_header *self, int feat)
 {
        return test_bit(feat, self->adds_features);
@@ -431,8 +436,10 @@ static int perf_header__adds_write(struct perf_header *self, int fd)
        int idx = 0, err;
        session = container_of(self, struct perf_session, header);
-        if (perf_session__read_build_ids(session, true))
-                perf_header__set_feat(self, HEADER_BUILD_ID);
+        if (perf_header__has_feat(self, HEADER_BUILD_ID &&
+            !perf_session__read_build_ids(session, true)))
+                perf_header__clear_feat(self, HEADER_BUILD_ID);
        nr_sections = bitmap_weight(self->adds_features, HEADER_FEAT_BITS);
        if (!nr_sections)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 402ac2454cf8..ed550bffd655 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -84,6 +84,7 @@ u64 perf_header__sample_type(struct perf_header *header);
 struct perf_event_attr *
 perf_header__find_attr(u64 id, struct perf_header *header);
 void perf_header__set_feat(struct perf_header *self, int feat);
+void perf_header__clear_feat(struct perf_header *self, int feat);
 bool perf_header__has_feat(const struct perf_header *self, int feat);
 int perf_header__process_sections(struct perf_header *self, int fd,
diff --git a/tools/perf/util/include/asm/cpufeature.h b/tools/perf/util/include/asm/cpufeature.h
new file mode 100644
index 000000000000..acffd5e4d1d4
--- /dev/null
+++ b/tools/perf/util/include/asm/cpufeature.h
@@ -0,0 +1,9 @@
+#ifndef PERF_CPUFEATURE_H
+#define PERF_CPUFEATURE_H
+/* cpufeature.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+#define X86_FEATURE_REP_GOOD 0
+#endif  /* PERF_CPUFEATURE_H */
diff --git a/tools/perf/util/include/asm/dwarf2.h b/tools/perf/util/include/asm/dwarf2.h
new file mode 100644
index 000000000000..bb4198e7837a
--- /dev/null
+++ b/tools/perf/util/include/asm/dwarf2.h
@@ -0,0 +1,11 @@
+#ifndef PERF_DWARF2_H
+#define PERF_DWARF2_H
+/* dwarf2.h ... dummy header file for including arch/x86/lib/memcpy_64.S */
+#define CFI_STARTPROC
+#define CFI_ENDPROC
+#endif  /* PERF_DWARF2_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index bb4ac2e05385..8be0b968ca0b 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -13,6 +13,11 @@ static inline void set_bit(int nr, unsigned long *addr)
        addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
 }
+static inline void clear_bit(int nr, unsigned long *addr)
+{
+        addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
+}
 static __always_inline int test_bit(unsigned int nr, const unsigned long *addr)
 {
        return ((1UL << (nr % BITS_PER_LONG)) &
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
new file mode 100644
index 000000000000..06387cffe125
--- /dev/null
+++ b/tools/perf/util/include/linux/linkage.h
@@ -0,0 +1,13 @@
+#ifndef PERF_LINUX_LINKAGE_H_
+#define PERF_LINUX_LINKAGE_H_
+/* linkage.h ... for including arch/x86/lib/memcpy_64.S */
+#define ENTRY(name)                             \
+        .globl name;                            \
+        name:
+#define ENDPROC(name)
+#endif  /* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 4af5bd59cfd1..c305305a3884 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -434,7 +434,7 @@ parse_single_tracepoint_event(char *sys_name,
        id = atoll(id_buf);
        attr->config = id;
        attr->type = PERF_TYPE_TRACEPOINT;
-        *strp = evt_name + evt_length;
+        *strp += strlen(sys_name) + evt_length + 1; /* + 1 for the ':' */
        attr->sample_type |= PERF_SAMPLE_RAW;
        attr->sample_type |= PERF_SAMPLE_TIME;
@@ -495,7 +495,7 @@ static enum event_result parse_tracepoint_event(const char **strp,
                                    struct perf_event_attr *attr)
 {
        const char *evt_name;
-        char *flags;
+        char *flags = NULL, *comma_loc;
        char sys_name[MAX_EVENT_LENGTH];
        unsigned int sys_length, evt_length;
@@ -514,6 +514,11 @@ static enum event_result parse_tracepoint_event(const char **strp,
        sys_name[sys_length] = '\0';
        evt_name = evt_name + 1;
+        comma_loc = strchr(evt_name, ',');
+        if (comma_loc) {
+                /* take the event name up to the comma */
+                evt_name = strndup(evt_name, comma_loc - evt_name);
+        }
        flags = strchr(evt_name, ':');
        if (flags) {
                /* split it out: */
@@ -524,9 +529,8 @@ static enum event_result parse_tracepoint_event(const char **strp,
        evt_length = strlen(evt_name);
        if (evt_length >= MAX_EVENT_LENGTH)
                return EVT_FAILED;
        if (strpbrk(evt_name, "*?")) {
-                *strp = evt_name + evt_length;
+                *strp += strlen(sys_name) + evt_length;
                return parse_multiple_tracepoint_event(sys_name, evt_name,
                                                       flags);
        } else
diff --git a/tools/perf/util/probe-finder.h b/tools/perf/util/probe-finder.h
index bba69d455699..beaefc3c1223 100644
--- a/tools/perf/util/probe-finder.h
+++ b/tools/perf/util/probe-finder.h
@@ -34,9 +34,9 @@ extern int find_available_vars_at(int fd, struct perf_probe_event *pev,
                                  bool externs);
 #include <dwarf.h>
-#include <libdw.h>
+#include <elfutils/libdw.h>
-#include <libdwfl.h>
+#include <elfutils/libdwfl.h>
-#include <version.h>
+#include <elfutils/version.h>
 struct probe_finder {
        struct perf_probe_event *pev;           /* Target probe event */
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index b059dc50cc2d..93680818e244 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -1,5 +1,5 @@
 /*
- * trace-event-perl.  Feed perf trace events to an embedded Perl interpreter.
+ * trace-event-perl.  Feed perf script events to an embedded Perl interpreter.
 *
 * Copyright (C) 2009 Tom Zanussi <tzanussi@gmail.com>
 *
@@ -411,8 +411,8 @@ static int perl_generate_script(const char *outfile)
                return -1;
        }
-        fprintf(ofp, "# perf trace event handlers, "
+        fprintf(ofp, "# perf script event handlers, "
-                "generated by perf trace -g perl\n");
+                "generated by perf script -g perl\n");
        fprintf(ofp, "# Licensed under the terms of the GNU GPL"
                " License version 2\n\n");
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 33a632523743..c6d99334bdfa 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -442,8 +442,8 @@ static int python_generate_script(const char *outfile)
                fprintf(stderr, "couldn't open %s\n", fname);
                return -1;
        }
-        fprintf(ofp, "# perf trace event handlers, "
+        fprintf(ofp, "# perf script event handlers, "
-                "generated by perf trace -g python\n");
+                "generated by perf script -g python\n");
        fprintf(ofp, "# Licensed under the terms of the GNU GPL"
                " License version 2\n\n");
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index fa9d652c2dc3..52672dad1fe9 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -101,10 +101,20 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
        INIT_LIST_HEAD(&self->dead_threads);
        self->hists_tree = RB_ROOT;
        self->last_match = NULL;
-        self->mmap_window = 32;
+        /*
+         * On 64bit we can mmap the data file in one go. No need for tiny mmap
+         * slices. On 32bit we use 32MB.
+         */
+#if BITS_PER_LONG == 64
+        self->mmap_window = ULLONG_MAX;
+#else
+        self->mmap_window = 32 * 1024 * 1024ULL;
+#endif
        self->machines = RB_ROOT;
        self->repipe = repipe;
-        INIT_LIST_HEAD(&self->ordered_samples.samples_head);
+        INIT_LIST_HEAD(&self->ordered_samples.samples);
+        INIT_LIST_HEAD(&self->ordered_samples.sample_cache);
+        INIT_LIST_HEAD(&self->ordered_samples.to_free);
        machine__init(&self->host_machine, "", HOST_KERNEL_ID);
        if (mode == O_RDONLY) {
@@ -262,7 +272,7 @@ static void perf_event_ops__fill_defaults(struct perf_event_ops *handler)
        if (handler->exit == NULL)
                handler->exit = process_event_stub;
        if (handler->lost == NULL)
-                handler->lost = process_event_stub;
+                handler->lost = event__process_lost;
        if (handler->read == NULL)
                handler->read = process_event_stub;
        if (handler->throttle == NULL)
@@ -386,33 +396,51 @@ static event__swap_op event__swap_ops[] = {
 struct sample_queue {
        u64                     timestamp;
-        struct sample_event     *event;
+        event_t                 *event;
        struct list_head        list;
 };
+static void perf_session_free_sample_buffers(struct perf_session *session)
+{
+        struct ordered_samples *os = &session->ordered_samples;
+        while (!list_empty(&os->to_free)) {
+                struct sample_queue *sq;
+                sq = list_entry(os->to_free.next, struct sample_queue, list);
+                list_del(&sq->list);
+                free(sq);
+        }
+}
 static void flush_sample_queue(struct perf_session *s,
                               struct perf_event_ops *ops)
 {
-        struct list_head *head = &s->ordered_samples.samples_head;
+        struct ordered_samples *os = &s->ordered_samples;
-        u64 limit = s->ordered_samples.next_flush;
+        struct list_head *head = &os->samples;
        struct sample_queue *tmp, *iter;
+        u64 limit = os->next_flush;
+        u64 last_ts = os->last_sample ? os->last_sample->timestamp : 0ULL;
        if (!ops->ordered_samples || !limit)
                return;
        list_for_each_entry_safe(iter, tmp, head, list) {
                if (iter->timestamp > limit)
-                        return;
+                        break;
-                if (iter == s->ordered_samples.last_inserted)
-                        s->ordered_samples.last_inserted = NULL;
-                ops->sample((event_t *)iter->event, s);
+                ops->sample(iter->event, s);
-                s->ordered_samples.last_flush = iter->timestamp;
+                os->last_flush = iter->timestamp;
                list_del(&iter->list);
-                free(iter->event);
+                list_add(&iter->list, &os->sample_cache);
-                free(iter);
+        }
+        if (list_empty(head)) {
+                os->last_sample = NULL;
+        } else if (last_ts <= limit) {
+                os->last_sample =
+                        list_entry(head->prev, struct sample_queue, list);
        }
 }
@@ -465,104 +493,87 @@ static int process_finished_round(event_t *event __used,
        return 0;
 }
-static void __queue_sample_end(struct sample_queue *new, struct list_head *head)
-{
-        struct sample_queue *iter;
-        list_for_each_entry_reverse(iter, head, list) {
-                if (iter->timestamp < new->timestamp) {
-                        list_add(&new->list, &iter->list);
-                        return;
-                }
-        }
-        list_add(&new->list, head);
-}
-static void __queue_sample_before(struct sample_queue *new,
-                                  struct sample_queue *iter,
-                                  struct list_head *head)
-{
-        list_for_each_entry_continue_reverse(iter, head, list) {
-                if (iter->timestamp < new->timestamp) {
-                        list_add(&new->list, &iter->list);
-                        return;
-                }
-        }
-        list_add(&new->list, head);
-}
-static void __queue_sample_after(struct sample_queue *new,
-                                 struct sample_queue *iter,
-                                 struct list_head *head)
-{
-        list_for_each_entry_continue(iter, head, list) {
-                if (iter->timestamp > new->timestamp) {
-                        list_add_tail(&new->list, &iter->list);
-                        return;
-                }
-        }
-        list_add_tail(&new->list, head);
-}
 /* The queue is ordered by time */
 static void __queue_sample_event(struct sample_queue *new,
                                 struct perf_session *s)
 {
-        struct sample_queue *last_inserted = s->ordered_samples.last_inserted;
+        struct ordered_samples *os = &s->ordered_samples;
-        struct list_head *head = &s->ordered_samples.samples_head;
+        struct sample_queue *sample = os->last_sample;
+        u64 timestamp = new->timestamp;
+        struct list_head *p;
+        os->last_sample = new;
-        if (!last_inserted) {
+        if (!sample) {
-                __queue_sample_end(new, head);
+                list_add(&new->list, &os->samples);
+                os->max_timestamp = timestamp;
                return;
        }
        /*
-         * Most of the time the current event has a timestamp
+         * last_sample might point to some random place in the list as it's
-         * very close to the last event inserted, unless we just switched
+         * the last queued event. We expect that the new event is close to
-         * to another event buffer. Having a sorting based on a list and
+         * this.
-         * on the last inserted event that is close to the current one is
-         * probably more efficient than an rbtree based sorting.
         */
-        if (last_inserted->timestamp >= new->timestamp)
+        if (sample->timestamp <= timestamp) {
-                __queue_sample_before(new, last_inserted, head);
+                while (sample->timestamp <= timestamp) {
-        else
+                        p = sample->list.next;
-                __queue_sample_after(new, last_inserted, head);
+                        if (p == &os->samples) {
+                                list_add_tail(&new->list, &os->samples);
+                                os->max_timestamp = timestamp;
+                                return;
+                        }
+                        sample = list_entry(p, struct sample_queue, list);
+                }
+                list_add_tail(&new->list, &sample->list);
+        } else {
+                while (sample->timestamp > timestamp) {
+                        p = sample->list.prev;
+                        if (p == &os->samples) {
+                                list_add(&new->list, &os->samples);
+                                return;
+                        }
+                        sample = list_entry(p, struct sample_queue, list);
+                }
+                list_add(&new->list, &sample->list);
+        }
 }
+#define MAX_SAMPLE_BUFFER       (64 * 1024 / sizeof(struct sample_queue))
 static int queue_sample_event(event_t *event, struct sample_data *data,
                              struct perf_session *s)
 {
+        struct ordered_samples *os = &s->ordered_samples;
+        struct list_head *sc = &os->sample_cache;
        u64 timestamp = data->time;
        struct sample_queue *new;
        if (timestamp < s->ordered_samples.last_flush) {
                printf("Warning: Timestamp below last timeslice flush\n");
                return -EINVAL;
        }
-        new = malloc(sizeof(*new));
+        if (!list_empty(sc)) {
-        if (!new)
+                new = list_entry(sc->next, struct sample_queue, list);
-                return -ENOMEM;
+                list_del(&new->list);
+        } else if (os->sample_buffer) {
-        new->timestamp = timestamp;
+                new = os->sample_buffer + os->sample_buffer_idx;
+                if (++os->sample_buffer_idx == MAX_SAMPLE_BUFFER)
-        new->event = malloc(event->header.size);
+                        os->sample_buffer = NULL;
-        if (!new->event) {
+        } else {
-                free(new);
+                os->sample_buffer = malloc(MAX_SAMPLE_BUFFER * sizeof(*new));
-                return -ENOMEM;
+                if (!os->sample_buffer)
+                        return -ENOMEM;
+                list_add(&os->sample_buffer->list, &os->to_free);
+                os->sample_buffer_idx = 2;
+                new = os->sample_buffer + 1;
        }
-        memcpy(new->event, event, event->header.size);
+        new->timestamp = timestamp;
+        new->event = event;
        __queue_sample_event(new, s);
-        s->ordered_samples.last_inserted = new;
-        if (new->timestamp > s->ordered_samples.max_timestamp)
-                s->ordered_samples.max_timestamp = new->timestamp;
        return 0;
 }
@@ -586,13 +597,13 @@ static int perf_session__process_sample(event_t *event, struct perf_session *s,
 static int perf_session__process_event(struct perf_session *self,
                                       event_t *event,
                                       struct perf_event_ops *ops,
-                                       u64 offset, u64 head)
+                                       u64 file_offset)
 {
        trace_event(event);
        if (event->header.type < PERF_RECORD_HEADER_MAX) {
                dump_printf("%#Lx [%#x]: PERF_RECORD_%s",
-                            offset + head, event->header.size,
+                            file_offset, event->header.size,
                            event__name[event->header.type]);
                hists__inc_nr_events(&self->hists, event->header.type);
        }
@@ -625,7 +636,7 @@ static int perf_session__process_event(struct perf_session *self,
                return ops->event_type(event, self);
        case PERF_RECORD_HEADER_TRACING_DATA:
                /* setup for reading amidst mmap */
-                lseek(self->fd, offset + head, SEEK_SET);
+                lseek(self->fd, file_offset, SEEK_SET);
                return ops->tracing_data(event, self);
        case PERF_RECORD_HEADER_BUILD_ID:
                return ops->build_id(event, self);
@@ -724,8 +735,7 @@ more:
        }
        if (size == 0 ||
-            (skip = perf_session__process_event(self, &event, ops,
+            (skip = perf_session__process_event(self, &event, ops, head)) < 0) {
-                                                0, head)) < 0) {
                dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
                            head, event.header.size, event.header.type);
                /*
@@ -751,82 +761,93 @@ more:
 done:
        err = 0;
 out_err:
+        perf_session_free_sample_buffers(self);
        return err;
 }
-int __perf_session__process_events(struct perf_session *self,
+int __perf_session__process_events(struct perf_session *session,
                                   u64 data_offset, u64 data_size,
                                   u64 file_size, struct perf_event_ops *ops)
 {
-        int err, mmap_prot, mmap_flags;
+        u64 head, page_offset, file_offset, file_pos, progress_next;
-        u64 head, shift;
+        int err, mmap_prot, mmap_flags, map_idx = 0;
-        u64 offset = 0;
+        struct ui_progress *progress;
-        size_t  page_size;
+        size_t  page_size, mmap_size;
+        char *buf, *mmaps[8];
        event_t *event;
        uint32_t size;
-        char *buf;
-        struct ui_progress *progress = ui_progress__new("Processing events...",
-                                                        self->size);
-        if (progress == NULL)
-                return -1;
        perf_event_ops__fill_defaults(ops);
        page_size = sysconf(_SC_PAGESIZE);
-        head = data_offset;
+        page_offset = page_size * (data_offset / page_size);
-        shift = page_size * (head / page_size);
+        file_offset = page_offset;
-        offset += shift;
+        head = data_offset - page_offset;
-        head -= shift;
+        if (data_offset + data_size < file_size)
+                file_size = data_offset + data_size;
+        progress_next = file_size / 16;
+        progress = ui_progress__new("Processing events...", file_size);
+        if (progress == NULL)
+                return -1;
+        mmap_size = session->mmap_window;
+        if (mmap_size > file_size)
+                mmap_size = file_size;
+        memset(mmaps, 0, sizeof(mmaps));
        mmap_prot  = PROT_READ;
        mmap_flags = MAP_SHARED;
-        if (self->header.needs_swap) {
+        if (session->header.needs_swap) {
                mmap_prot  |= PROT_WRITE;
                mmap_flags = MAP_PRIVATE;
        }
 remap:
-        buf = mmap(NULL, page_size * self->mmap_window, mmap_prot,
+        buf = mmap(NULL, mmap_size, mmap_prot, mmap_flags, session->fd,
-                   mmap_flags, self->fd, offset);
+                   file_offset);
        if (buf == MAP_FAILED) {
                pr_err("failed to mmap file\n");
                err = -errno;
                goto out_err;
        }
+        mmaps[map_idx] = buf;
+        map_idx = (map_idx + 1) & (ARRAY_SIZE(mmaps) - 1);
+        file_pos = file_offset + head;
 more:
        event = (event_t *)(buf + head);
-        ui_progress__update(progress, offset);
-        if (self->header.needs_swap)
+        if (session->header.needs_swap)
                perf_event_header__bswap(&event->header);
        size = event->header.size;
        if (size == 0)
                size = 8;
-        if (head + event->header.size >= page_size * self->mmap_window) {
+        if (head + event->header.size >= mmap_size) {
-                int munmap_ret;
+                if (mmaps[map_idx]) {
+                        munmap(mmaps[map_idx], mmap_size);
-                shift = page_size * (head / page_size);
+                        mmaps[map_idx] = NULL;
+                }
-                munmap_ret = munmap(buf, page_size * self->mmap_window);
-                assert(munmap_ret == 0);
-                offset += shift;
+                page_offset = page_size * (head / page_size);
-                head -= shift;
+                file_offset += page_offset;
+                head -= page_offset;
                goto remap;
        }
        size = event->header.size;
        dump_printf("\n%#Lx [%#x]: event: %d\n",
-                    offset + head, event->header.size, event->header.type);
+                    file_pos, event->header.size, event->header.type);
        if (size == 0 ||
-            perf_session__process_event(self, event, ops, offset, head) < 0) {
+            perf_session__process_event(session, event, ops, file_pos) < 0) {
                dump_printf("%#Lx [%#x]: skipping unknown header type: %d\n",
-                            offset + head, event->header.size,
+                            file_offset + head, event->header.size,
                            event->header.type);
                /*
                 * assume we lost track of the stream, check alignment, and
@@ -839,19 +860,41 @@ more:
        }
        head += size;
+        file_pos += size;
-        if (offset + head >= data_offset + data_size)
+        if (file_pos >= progress_next) {
-                goto done;
+                progress_next += file_size / 16;
+                ui_progress__update(progress, file_pos);
+        }
-        if (offset + head < file_size)
+        if (file_pos < file_size)
                goto more;
-done:
        err = 0;
        /* do the final flush for ordered samples */
-        self->ordered_samples.next_flush = ULLONG_MAX;
+        session->ordered_samples.next_flush = ULLONG_MAX;
-        flush_sample_queue(self, ops);
+        flush_sample_queue(session, ops);
 out_err:
        ui_progress__delete(progress);
+        if (ops->lost == event__process_lost &&
+            session->hists.stats.total_lost != 0) {
+                ui__warning("Processed %Lu events and LOST %Lu!\n\n"
+                            "Check IO/CPU overload!\n\n",
+                            session->hists.stats.total_period,
+                            session->hists.stats.total_lost);
+        }
+        if (session->hists.stats.nr_unknown_events != 0) {
+                ui__warning("Found %u unknown events!\n\n"
+                            "Is this an older tool processing a perf.data "
+                            "file generated by a more recent tool?\n\n"
+                            "If that is not the case, consider "
+                            "reporting to linux-kernel@vger.kernel.org.\n\n",
+                            session->hists.stats.nr_unknown_events);
+        }
+        perf_session_free_sample_buffers(session);
        return err;
 }
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 9fa0fc2a863f..5bf6efa3788a 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -17,8 +17,12 @@ struct ordered_samples {
        u64                     last_flush;
        u64                     next_flush;
        u64                     max_timestamp;
-        struct list_head        samples_head;
+        struct list_head        samples;
-        struct sample_queue     *last_inserted;
+        struct list_head        sample_cache;
+        struct list_head        to_free;
+        struct sample_queue     *sample_buffer;
+        struct sample_queue     *last_sample;
+        int                     sample_buffer_idx;
 };
 struct perf_session {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 0500895a45af..a348906b587d 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -121,7 +121,7 @@ static void __map_groups__fixup_end(struct map_groups *self, enum map_type type)
         * We still haven't the actual symbols, so guess the
         * last map final address.
         */
-        curr->end = ~0UL;
+        curr->end = ~0ULL;
 }
 static void map_groups__fixup_end(struct map_groups *self)
diff --git a/tools/perf/util/ui/util.c b/tools/perf/util/ui/util.c
index 056c69521a38..7b5a8926624e 100644
--- a/tools/perf/util/ui/util.c
+++ b/tools/perf/util/ui/util.c
@@ -104,10 +104,24 @@ out_destroy_form:
        return rc;
 }
-static const char yes[] = "Yes", no[] = "No";
+static const char yes[] = "Yes", no[] = "No",
+                  warning_str[] = "Warning!", ok[] = "Ok";
 bool ui__dialog_yesno(const char *msg)
 {
        /* newtWinChoice should really be accepting const char pointers... */
        return newtWinChoice(NULL, (char *)yes, (char *)no, (char *)msg) == 1;
 }
+void ui__warning(const char *format, ...)
+{
+        va_list args;
+        va_start(args, format);
+        if (use_browser > 0)
+                newtWinMessagev((char *)warning_str, (char *)ok,
+                                (char *)format, args);
+        else
+                vfprintf(stderr, format, args);
+        va_end(args);
+}