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

Pull perf updates from Ingo Molnar:
 "Lots of activity:

   211 files changed, 8328 insertions(+), 4116 deletions(-)

  most of it on the tooling side.

  Main changes:

   * ftrace enhancements and fixes from Steve Rostedt.

   * uprobes fixes, cleanups and preparation for the ARM port from Oleg
     Nesterov.

   * UAPI fixes, from David Howels - prepares the arch/x86 UAPI
     transition

   * Separate perf tests into multiple objects, one per test, from Jiri
     Olsa.

   * Make hardware event translations available in sysfs, from Jiri
     Olsa.

   * Fixes to /proc/pid/maps parsing, preparatory to supporting data
     maps, from Namhyung Kim

   * Implement ui_progress for GTK, from Namhyung Kim

   * Add framework for automated perf_event_attr tests, where tools with
     different command line options will be run from a 'perf test', via
     python glue, and the perf syscall will be intercepted to verify
     that the perf_event_attr fields set by the tool are those expected,
     from Jiri Olsa

   * Add a 'link' method for hists, so that we can have the leader with
     buckets for all the entries in all the hists.  This new method is
     now used in the default 'diff' output, making the sum of the
     'baseline' column be 100%, eliminating blind spots.

   * libtraceevent fixes for compiler warnings trying to make perf it
     build on some distros, like fedora 14, 32-bit, some of the warnings
     really pointed to real bugs.

   * Add a browser for 'perf script' and make it available from the
     report and annotate browsers.  It does filtering to find the
     scripts that handle events found in the perf.data file used.  From
     Feng Tang

   * perf inject changes to allow showing where a task sleeps, from
     Andrew Vagin.

   * Makefile improvements from Namhyung Kim.

   * Add --pre and --post command hooks in 'stat', from Peter Zijlstra.

   * Don't stop synthesizing threads when one vanishes, this is for the
     existing threads when we start a tool like trace.

   * Use sched:sched_stat_runtime to provide a thread summary, this
     produces the same output as the 'trace summary' subcommand of
     tglx's original "trace" tool.

   * Support interrupted syscalls in 'trace'

   * Add an event duration column and filter in 'trace'.

   * There are references to the man pages in some tools, so try to
     build Documentation when installing, warning the user if that is
     not possible, from Borislav Petkov.

   * Give user better message if precise is not supported, from David
     Ahern.

   * Try to find cross-built objdump path by using the session
     environment information in the perf.data file header, from Irina
     Tirdea, original patch and idea by Namhyung Kim.

   * Diplays more output on features check for make V=1, so that one can
     figure out what is happening by looking at gcc output, etc.  From
     Jiri Olsa.

   * Add on_exit implementation for systems without one, e.g.  Android,
     from Bernhard Rosenkraenzer.

   * Only process events for vcpus of interest, helps handling large
     number of events, from David Ahern.

   * Cross compilation fixes for Android, from Irina Tirdea.

   * Add documentation on compiling for Android, from Irina Tirdea.

   * perf diff improvements from Jiri Olsa.

   * Target (task/user/cpu/syswide) handling improvements, from Namhyung
     Kim.

   * Add support in 'trace' for tracing workload given by command line,
     from Namhyung Kim.

   * ... and much more."

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (194 commits)
  uprobes: Use percpu_rw_semaphore to fix register/unregister vs dup_mmap() race
  perf evsel: Introduce is_group_member method
  perf powerpc: Use uapi/unistd.h to fix build error
  tools: Pass the target in descend
  tools: Honour the O= flag when tool build called from a higher Makefile
  tools: Define a Makefile function to do subdir processing
  perf ui: Always compile browser setup code
  perf ui: Add ui_progress__finish()
  perf ui gtk: Implement ui_progress functions
  perf ui: Introduce generic ui_progress helper
  perf ui tui: Move progress.c under ui/tui directory
  perf tools: Add basic event modifier sanity check
  perf tools: Omit group members from perf_evlist__disable/enable
  perf tools: Ensure single disable call per event in record comand
  perf tools: Fix 'disabled' attribute config for record command
  perf tools: Fix attributes for '{}' defined event groups
  perf tools: Use sscanf for parsing /proc/pid/maps
  perf tools: Add gtk.<command> config option for launching GTK browser
  perf tools: Fix compile error on NO_NEWT=1 build
  perf hists: Initialize all of he->stat with zeroes
  ...

11 files changed, 213 insertions, 42 deletions

diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h
new file mode 100644
index 0000000..beab86c
--- /dev/null
+++ b/arch/x86/include/asm/trace_clock.h
@@ -0,0 +1,20 @@
+#ifndef _ASM_X86_TRACE_CLOCK_H
+#define _ASM_X86_TRACE_CLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_X86_TSC
+
+extern u64 notrace trace_clock_x86_tsc(void);
+
+# define ARCH_TRACE_CLOCKS \
+	{ trace_clock_x86_tsc,	"x86-tsc",	.in_ns = 0 },
+
+#else /* !CONFIG_X86_TSC */
+
+#define ARCH_TRACE_CLOCKS
+
+#endif
+
+#endif  /* _ASM_X86_TRACE_CLOCK_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 91ce48f..34e923a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -9,7 +9,6 @@ CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
 ifdef CONFIG_FUNCTION_TRACER
 # Do not profile debug and lowlevel utilities
 CFLAGS_REMOVE_tsc.o = -pg
-CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_pvclock.o = -pg
 CFLAGS_REMOVE_kvmclock.o = -pg
@@ -62,6 +61,7 @@ obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
+obj-$(CONFIG_X86_TSC)		+= trace_clock.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 4a3374e..4428fd1 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1316,6 +1316,121 @@ static struct attribute_group x86_pmu_format_group = {
 	.attrs = NULL,
 };
 
+struct perf_pmu_events_attr {
+	struct device_attribute attr;
+	u64 id;
+};
+
+/*
+ * Remove all undefined events (x86_pmu.event_map(id) == 0)
+ * out of events_attr attributes.
+ */
+static void __init filter_events(struct attribute **attrs)
+{
+	int i, j;
+
+	for (i = 0; attrs[i]; i++) {
+		if (x86_pmu.event_map(i))
+			continue;
+
+		for (j = i; attrs[j]; j++)
+			attrs[j] = attrs[j + 1];
+
+		/* Check the shifted attr. */
+		i--;
+	}
+}
+
+static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr = \
+		container_of(attr, struct perf_pmu_events_attr, attr);
+
+	u64 config = x86_pmu.event_map(pmu_attr->id);
+	return x86_pmu.events_sysfs_show(page, config);
+}
+
+#define EVENT_VAR(_id)  event_attr_##_id
+#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
+
+#define EVENT_ATTR(_name, _id)					\
+static struct perf_pmu_events_attr EVENT_VAR(_id) = {		\
+	.attr = __ATTR(_name, 0444, events_sysfs_show, NULL),	\
+	.id   =  PERF_COUNT_HW_##_id,				\
+};
+
+EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
+EVENT_ATTR(instructions,		INSTRUCTIONS		);
+EVENT_ATTR(cache-references,		CACHE_REFERENCES	);
+EVENT_ATTR(cache-misses, 		CACHE_MISSES		);
+EVENT_ATTR(branch-instructions,		BRANCH_INSTRUCTIONS	);
+EVENT_ATTR(branch-misses,		BRANCH_MISSES		);
+EVENT_ATTR(bus-cycles,			BUS_CYCLES		);
+EVENT_ATTR(stalled-cycles-frontend,	STALLED_CYCLES_FRONTEND	);
+EVENT_ATTR(stalled-cycles-backend,	STALLED_CYCLES_BACKEND	);
+EVENT_ATTR(ref-cycles,			REF_CPU_CYCLES		);
+
+static struct attribute *empty_attrs;
+
+static struct attribute *events_attr[] = {
+	EVENT_PTR(CPU_CYCLES),
+	EVENT_PTR(INSTRUCTIONS),
+	EVENT_PTR(CACHE_REFERENCES),
+	EVENT_PTR(CACHE_MISSES),
+	EVENT_PTR(BRANCH_INSTRUCTIONS),
+	EVENT_PTR(BRANCH_MISSES),
+	EVENT_PTR(BUS_CYCLES),
+	EVENT_PTR(STALLED_CYCLES_FRONTEND),
+	EVENT_PTR(STALLED_CYCLES_BACKEND),
+	EVENT_PTR(REF_CPU_CYCLES),
+	NULL,
+};
+
+static struct attribute_group x86_pmu_events_group = {
+	.name = "events",
+	.attrs = events_attr,
+};
+
+ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event)
+{
+	u64 umask  = (config & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
+	u64 cmask  = (config & ARCH_PERFMON_EVENTSEL_CMASK) >> 24;
+	bool edge  = (config & ARCH_PERFMON_EVENTSEL_EDGE);
+	bool pc    = (config & ARCH_PERFMON_EVENTSEL_PIN_CONTROL);
+	bool any   = (config & ARCH_PERFMON_EVENTSEL_ANY);
+	bool inv   = (config & ARCH_PERFMON_EVENTSEL_INV);
+	ssize_t ret;
+
+	/*
+	* We have whole page size to spend and just little data
+	* to write, so we can safely use sprintf.
+	*/
+	ret = sprintf(page, "event=0x%02llx", event);
+
+	if (umask)
+		ret += sprintf(page + ret, ",umask=0x%02llx", umask);
+
+	if (edge)
+		ret += sprintf(page + ret, ",edge");
+
+	if (pc)
+		ret += sprintf(page + ret, ",pc");
+
+	if (any)
+		ret += sprintf(page + ret, ",any");
+
+	if (inv)
+		ret += sprintf(page + ret, ",inv");
+
+	if (cmask)
+		ret += sprintf(page + ret, ",cmask=0x%02llx", cmask);
+
+	ret += sprintf(page + ret, "\n");
+
+	return ret;
+}
+
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -1362,6 +1477,11 @@ static int __init init_hw_perf_events(void)
 	x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */
 	x86_pmu_format_group.attrs = x86_pmu.format_attrs;
 
+	if (!x86_pmu.events_sysfs_show)
+		x86_pmu_events_group.attrs = &empty_attrs;
+	else
+		filter_events(x86_pmu_events_group.attrs);
+
 	pr_info("... version:                %d\n",     x86_pmu.version);
 	pr_info("... bit width:              %d\n",     x86_pmu.cntval_bits);
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
@@ -1651,6 +1771,7 @@ static struct attribute_group x86_pmu_attr_group = {
 static const struct attribute_group *x86_pmu_attr_groups[] = {
 	&x86_pmu_attr_group,
 	&x86_pmu_format_group,
+	&x86_pmu_events_group,
 	NULL,
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 271d257..115c1ea 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -354,6 +354,8 @@ struct x86_pmu {
 	int		attr_rdpmc;
 	struct attribute **format_attrs;
 
+	ssize_t		(*events_sysfs_show)(char *page, u64 config);
+
 	/*
 	 * CPU Hotplug hooks
 	 */
@@ -536,6 +538,9 @@ static inline void set_linear_ip(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 
+ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event);
+ssize_t intel_event_sysfs_show(char *page, u64 config);
+
 #ifdef CONFIG_CPU_SUP_AMD
 
 int amd_pmu_init(void);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 4528ae7..c93bc4e 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -568,6 +568,14 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev
 	}
 }
 
+static ssize_t amd_event_sysfs_show(char *page, u64 config)
+{
+	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT) |
+		    (config & AMD64_EVENTSEL_EVENT) >> 24;
+
+	return x86_event_sysfs_show(page, config, event);
+}
+
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -591,6 +599,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.put_event_constraints	= amd_put_event_constraints,
 
 	.format_attrs		= amd_format_attr,
+	.events_sysfs_show	= amd_event_sysfs_show,
 
 	.cpu_prepare		= amd_pmu_cpu_prepare,
 	.cpu_starting		= amd_pmu_cpu_starting,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 324bb52..93b9e11 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1603,6 +1603,13 @@ static struct attribute *intel_arch_formats_attr[] = {
 	NULL,
 };
 
+ssize_t intel_event_sysfs_show(char *page, u64 config)
+{
+	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT);
+
+	return x86_event_sysfs_show(page, config, event);
+}
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -1628,6 +1635,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.event_constraints	= intel_core_event_constraints,
 	.guest_get_msrs		= core_guest_get_msrs,
 	.format_attrs		= intel_arch_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
 };
 
 struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1766,6 +1774,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.pebs_aliases		= intel_pebs_aliases_core2,
 
 	.format_attrs		= intel_arch3_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
 
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c
index 7d0270b..f2af39f 100644
--- a/arch/x86/kernel/cpu/perf_event_p6.c
+++ b/arch/x86/kernel/cpu/perf_event_p6.c
@@ -227,6 +227,8 @@ static __initconst const struct x86_pmu p6_pmu = {
 	.event_constraints	= p6_event_constraints,
 
 	.format_attrs		= intel_p6_formats_attr,
+	.events_sysfs_show	= intel_event_sysfs_show,
+
 };
 
 __init int p6_pmu_init(void)
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 4929c1b..801602b 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -195,12 +195,6 @@ void read_persistent_clock(struct timespec *ts)
 	ts->tv_nsec = 0;
 }
 
-unsigned long long native_read_tsc(void)
-{
-	return __native_read_tsc();
-}
-EXPORT_SYMBOL(native_read_tsc);
-
 
 static struct resource rtc_resources[] = {
 	[0] = {
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
new file mode 100644
index 0000000..25b9937
--- /dev/null
+++ b/arch/x86/kernel/trace_clock.c
@@ -0,0 +1,21 @@
+/*
+ * X86 trace clocks
+ */
+#include <asm/trace_clock.h>
+#include <asm/barrier.h>
+#include <asm/msr.h>
+
+/*
+ * trace_clock_x86_tsc(): A clock that is just the cycle counter.
+ *
+ * Unlike the other clocks, this is not in nanoseconds.
+ */
+u64 notrace trace_clock_x86_tsc(void)
+{
+	u64 ret;
+
+	rdtsc_barrier();
+	rdtscll(ret);
+
+	return ret;
+}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index cfa5d4f..06ccb50 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -77,6 +77,12 @@ unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
 #endif
 
+unsigned long long native_read_tsc(void)
+{
+	return __native_read_tsc();
+}
+EXPORT_SYMBOL(native_read_tsc);
+
 int check_tsc_unstable(void)
 {
 	return tsc_unstable;
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index aafa555..c71025b 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -478,6 +478,11 @@ int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	regs->ip = current->utask->xol_vaddr;
 	pre_xol_rip_insn(auprobe, regs, autask);
 
+	autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
+	regs->flags |= X86_EFLAGS_TF;
+	if (test_tsk_thread_flag(current, TIF_BLOCKSTEP))
+		set_task_blockstep(current, false);
+
 	return 0;
 }
 
@@ -603,6 +608,16 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	if (auprobe->fixups & UPROBE_FIX_CALL)
 		result = adjust_ret_addr(regs->sp, correction);
 
+	/*
+	 * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP
+	 * so we can get an extra SIGTRAP if we do not clear TF. We need
+	 * to examine the opcode to make it right.
+	 */
+	if (utask->autask.saved_tf)
+		send_sig(SIGTRAP, current, 0);
+	else if (!(auprobe->fixups & UPROBE_FIX_SETF))
+		regs->flags &= ~X86_EFLAGS_TF;
+
 	return result;
 }
 
@@ -647,6 +662,10 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	current->thread.trap_nr = utask->autask.saved_trap_nr;
 	handle_riprel_post_xol(auprobe, regs, NULL);
 	instruction_pointer_set(regs, utask->vaddr);
+
+	/* clear TF if it was set by us in arch_uprobe_pre_xol() */
+	if (!utask->autask.saved_tf)
+		regs->flags &= ~X86_EFLAGS_TF;
 }
 
 /*
@@ -676,38 +695,3 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 		send_sig(SIGTRAP, current, 0);
 	return ret;
 }
-
-void arch_uprobe_enable_step(struct arch_uprobe *auprobe)
-{
-	struct task_struct *task = current;
-	struct arch_uprobe_task	*autask	= &task->utask->autask;
-	struct pt_regs *regs = task_pt_regs(task);
-
-	autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF);
-
-	regs->flags |= X86_EFLAGS_TF;
-	if (test_tsk_thread_flag(task, TIF_BLOCKSTEP))
-		set_task_blockstep(task, false);
-}
-
-void arch_uprobe_disable_step(struct arch_uprobe *auprobe)
-{
-	struct task_struct *task = current;
-	struct arch_uprobe_task	*autask	= &task->utask->autask;
-	bool trapped = (task->utask->state == UTASK_SSTEP_TRAPPED);
-	struct pt_regs *regs = task_pt_regs(task);
-	/*
-	 * The state of TIF_BLOCKSTEP was not saved so we can get an extra
-	 * SIGTRAP if we do not clear TF. We need to examine the opcode to
-	 * make it right.
-	 */
-	if (unlikely(trapped)) {
-		if (!autask->saved_tf)
-			regs->flags &= ~X86_EFLAGS_TF;
-	} else {
-		if (autask->saved_tf)
-			send_sig(SIGTRAP, task, 0);
-		else if (!(auprobe->fixups & UPROBE_FIX_SETF))
-			regs->flags &= ~X86_EFLAGS_TF;
-	}
-}