Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/tip/linux-2.6-tip

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

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

Documentation/kernel-parameters.txt

@@ -1579,20 +1579,12 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nmi_watchdog=	[KNL,BUGS=X86] Debugging features for SMP kernels
 			Format: [panic,][num]
-			Valid num: 0,1,2
+			Valid num: 0
 			0 - turn nmi_watchdog off
-			1 - use the IO-APIC timer for the NMI watchdog
-			2 - use the local APIC for the NMI watchdog using
-			a performance counter. Note: This will use one
-			performance counter and the local APIC's performance
-			vector.
 			When panic is specified, panic when an NMI watchdog
 			timeout occurs.
 			This is useful when you use a panic=... timeout and
 			need the box quickly up again.
-			Instead of 1 and 2 it is possible to use the following
-			symbolic names: lapic and ioapic
-			Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
 
 	netpoll.carrier_timeout=
 			[NET] Specifies amount of time (in seconds) that

Documentation/trace/events-power.txt

@@ -0,0 +1,90 @@
+
+			Subsystem Trace Points: power
+
+The power tracing system captures events related to power transitions
+within the kernel. Broadly speaking there are three major subheadings:
+
+  o Power state switch which reports events related to suspend (S-states),
+     cpuidle (C-states) and cpufreq (P-states)
+  o System clock related changes
+  o Power domains related changes and transitions
+
+This document describes what each of the tracepoints is and why they
+might be useful.
+
+Cf. include/trace/events/power.h for the events definitions.
+
+1. Power state switch events
+============================
+
+1.1 New trace API
+-----------------
+
+A 'cpu' event class gathers the CPU-related events: cpuidle and
+cpufreq.
+
+cpu_idle		"state=%lu cpu_id=%lu"
+cpu_frequency		"state=%lu cpu_id=%lu"
+
+A suspend event is used to indicate the system going in and out of the
+suspend mode:
+
+machine_suspend		"state=%lu"
+
+
+Note: the value of '-1' or '4294967295' for state means an exit from the current state,
+i.e. trace_cpu_idle(4, smp_processor_id()) means that the system
+enters the idle state 4, while trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id())
+means that the system exits the previous idle state.
+
+The event which has 'state=4294967295' in the trace is very important to the user
+space tools which are using it to detect the end of the current state, and so to
+correctly draw the states diagrams and to calculate accurate statistics etc.
+
+1.2 DEPRECATED trace API
+------------------------
+
+A new Kconfig option CONFIG_EVENT_POWER_TRACING_DEPRECATED with the default value of
+'y' has been created. This allows the legacy trace power API to be used conjointly
+with the new trace API.
+The Kconfig option, the old trace API (in include/trace/events/power.h) and the
+old trace points will disappear in a future release (namely 2.6.41).
+
+power_start		"type=%lu state=%lu cpu_id=%lu"
+power_frequency		"type=%lu state=%lu cpu_id=%lu"
+power_end		"cpu_id=%lu"
+
+The 'type' parameter takes one of those macros:
+ . POWER_NONE	= 0,
+ . POWER_CSTATE	= 1,	/* C-State */
+ . POWER_PSTATE	= 2,	/* Fequency change or DVFS */
+
+The 'state' parameter is set depending on the type:
+ . Target C-state for type=POWER_CSTATE,
+ . Target frequency for type=POWER_PSTATE,
+
+power_end is used to indicate the exit of a state, corresponding to the latest
+power_start event.
+
+2. Clocks events
+================
+The clock events are used for clock enable/disable and for
+clock rate change.
+
+clock_enable		"%s state=%lu cpu_id=%lu"
+clock_disable		"%s state=%lu cpu_id=%lu"
+clock_set_rate		"%s state=%lu cpu_id=%lu"
+
+The first parameter gives the clock name (e.g. "gpio1_iclk").
+The second parameter is '1' for enable, '0' for disable, the target
+clock rate for set_rate.
+
+3. Power domains events
+=======================
+The power domain events are used for power domains transitions
+
+power_domain_target	"%s state=%lu cpu_id=%lu"
+
+The first parameter gives the power domain name (e.g. "mpu_pwrdm").
+The second parameter is the power domain target state.
+

MAINTAINERS

@@ -4627,7 +4627,7 @@ 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

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 */

arch/alpha/kernel/irq_alpha.c

@@ -112,8 +112,6 @@ init_IRQ(void)
 	wrent(entInt, 0);
 
 	alpha_mv.init_irq();
-
-	init_hw_perf_events();
 }
 
 /*

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");
@@ -881,6 +882,8 @@ void __init init_hw_perf_events(void)
 	/* And set up PMU specification */
 	alpha_pmu = &ev67_pmu;
 
-	perf_pmu_register(&pmu);
-}
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 
+	return 0;
+}
+early_initcall(init_hw_perf_events);

arch/arm/kernel/perf_event.c

@@ -3034,11 +3034,11 @@ init_hw_perf_events(void)
 		pr_info("no hardware support available\n");
 	}
 
-	perf_pmu_register(&pmu);
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 
 	return 0;
 }
-arch_initcall(init_hw_perf_events);
+early_initcall(init_hw_perf_events);
 
 /*
  * Callchain handling code.

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)... */

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);

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);

arch/powerpc/kernel/perf_event.c

@@ -1379,7 +1379,7 @@ int register_power_pmu(struct power_pmu *pmu)
 		freeze_events_kernel = MMCR0_FCHV;
 #endif /* CONFIG_PPC64 */
 
-	perf_pmu_register(&power_pmu);
+	perf_pmu_register(&power_pmu, "cpu", PERF_TYPE_RAW);
 	perf_cpu_notifier(power_pmu_notifier);
 
 	return 0;

arch/powerpc/kernel/perf_event_fsl_emb.c

@@ -681,7 +681,7 @@ int register_fsl_emb_pmu(struct fsl_emb_pmu *pmu)
 	pr_info("%s performance monitor hardware support registered\n",
 		pmu->name);
 
-	perf_pmu_register(&fsl_emb_pmu);
+	perf_pmu_register(&fsl_emb_pmu, "cpu", PERF_TYPE_RAW);
 
 	return 0;
 }

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);

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);

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);

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);

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);

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);

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);

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);

arch/sh/kernel/perf_event.c

@@ -389,7 +389,7 @@ int __cpuinit register_sh_pmu(struct sh_pmu *_pmu)
 
 	WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
-	perf_pmu_register(&pmu);
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	perf_cpu_notifier(sh_pmu_notifier);
 	return 0;
 }

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

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;
 }

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);
+	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
 	register_die_notifier(&perf_event_nmi_notifier);
+
+	return 0;
 }
+early_initcall(init_hw_perf_events);
 
 void perf_callchain_kernel(struct perf_callchain_entry *entry,
 			   struct pt_regs *regs)

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

arch/x86/include/asm/irq.h

@@ -15,10 +15,6 @@ static inline int irq_canonicalize(int irq)
 	return ((irq == 2) ? 9 : irq);
 }
 
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG
-#endif
-
 #ifdef CONFIG_X86_32
 extern void irq_ctx_init(int cpu);
 #else

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);

arch/x86/include/asm/msr-index.h

@@ -123,6 +123,10 @@
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
 
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL		0xc0010200
+#define MSR_F15H_PERF_CTR		0xc0010201
+
 /* Fam 10h MSRs */
 #define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
 #define FAM10H_MMIO_CONF_ENABLE		(1<<0)