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

Pull perf updates from Ingo Molnar:
 "This tree includes some late late perf items that missed the first
  round:

  tools:

   - Bash auto completion improvements, now we can auto complete the
     tools long options, tracepoint event names, etc, from Namhyung Kim.

   - Look up thread using tid instead of pid in 'perf sched'.

   - Move global variables into a perf_kvm struct, from David Ahern.

   - Hists refactorings, preparatory for improved 'diff' command, from
     Jiri Olsa.

   - Hists refactorings, preparatory for event group viewieng work, from
     Namhyung Kim.

   - Remove double negation on optional feature macro definitions, from
     Namhyung Kim.

   - Remove several cases of needless global variables, on most
     builtins.

   - misc fixes

  kernel:

   - sysfs support for IBS on AMD CPUs, from Robert Richter.

   - Support for an upcoming Intel CPU, the Xeon-Phi / Knights Corner
     HPC blade PMU, from Vince Weaver.

   - misc fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  perf: Fix perf_cgroup_switch for sw-events
  perf: Clarify perf_cpu_context::active_pmu usage by renaming it to ::unique_pmu
  perf/AMD/IBS: Add sysfs support
  perf hists: Add more helpers for hist entry stat
  perf hists: Move he->stat.nr_events initialization to a template
  perf hists: Introduce struct he_stat
  perf diff: Removing the total_period argument from output code
  perf tool: Add hpp interface to enable/disable hpp column
  perf tools: Removing hists pair argument from output path
  perf hists: Separate overhead and baseline columns
  perf diff: Refactor diff displacement possition info
  perf hists: Add struct hists pointer to struct hist_entry
  perf tools: Complete tracepoint event names
  perf/x86: Add support for Intel Xeon-Phi Knights Corner PMU
  perf evlist: Remove some unused methods
  perf evlist: Introduce add_newtp method
  perf kvm: Move global variables into a perf_kvm struct
  perf tools: Convert to BACKTRACE_SUPPORT
  perf tools: Long option completion support for each subcommands
  perf tools: Complete long option names of perf command
  ...

55 files changed, 1517 insertions, 1198 deletions

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index fbee9714d9a..7f0edceb756 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -121,6 +121,11 @@
 #define MSR_P6_EVNTSEL0			0x00000186
 #define MSR_P6_EVNTSEL1			0x00000187
 
+#define MSR_KNC_PERFCTR0               0x00000020
+#define MSR_KNC_PERFCTR1               0x00000021
+#define MSR_KNC_EVNTSEL0               0x00000028
+#define MSR_KNC_EVNTSEL1               0x00000029
+
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index d30a6a9a012..a0e067d3d96 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,7 +32,7 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_event.o
 
 ifdef CONFIG_PERF_EVENTS
 obj-$(CONFIG_CPU_SUP_AMD)		+= perf_event_amd.o
-obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_p4.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_p6.o perf_event_knc.o perf_event_p4.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= perf_event_intel_uncore.o
 endif
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8b6defe7eef..271d2570029 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -626,6 +626,8 @@ int p4_pmu_init(void);
 
 int p6_pmu_init(void);
 
+int knc_pmu_init(void);
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index eebd5ffe1bb..6336bcbd061 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -41,17 +41,22 @@ struct cpu_perf_ibs {
 };
 
 struct perf_ibs {
-	struct pmu	pmu;
-	unsigned int	msr;
-	u64		config_mask;
-	u64		cnt_mask;
-	u64		enable_mask;
-	u64		valid_mask;
-	u64		max_period;
-	unsigned long	offset_mask[1];
-	int		offset_max;
-	struct cpu_perf_ibs __percpu *pcpu;
-	u64		(*get_count)(u64 config);
+	struct pmu			pmu;
+	unsigned int			msr;
+	u64				config_mask;
+	u64				cnt_mask;
+	u64				enable_mask;
+	u64				valid_mask;
+	u64				max_period;
+	unsigned long			offset_mask[1];
+	int				offset_max;
+	struct cpu_perf_ibs __percpu	*pcpu;
+
+	struct attribute		**format_attrs;
+	struct attribute_group		format_group;
+	const struct attribute_group	*attr_groups[2];
+
+	u64				(*get_count)(u64 config);
 };
 
 struct perf_ibs_data {
@@ -446,6 +451,19 @@ static void perf_ibs_del(struct perf_event *event, int flags)
 
 static void perf_ibs_read(struct perf_event *event) { }
 
+PMU_FORMAT_ATTR(rand_en,	"config:57");
+PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
+
+static struct attribute *ibs_fetch_format_attrs[] = {
+	&format_attr_rand_en.attr,
+	NULL,
+};
+
+static struct attribute *ibs_op_format_attrs[] = {
+	NULL,	/* &format_attr_cnt_ctl.attr if IBS_CAPS_OPCNT */
+	NULL,
+};
+
 static struct perf_ibs perf_ibs_fetch = {
 	.pmu = {
 		.task_ctx_nr	= perf_invalid_context,
@@ -465,6 +483,7 @@ static struct perf_ibs perf_ibs_fetch = {
 	.max_period		= IBS_FETCH_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSFETCH_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSFETCH_REG_COUNT,
+	.format_attrs		= ibs_fetch_format_attrs,
 
 	.get_count		= get_ibs_fetch_count,
 };
@@ -488,6 +507,7 @@ static struct perf_ibs perf_ibs_op = {
 	.max_period		= IBS_OP_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSOP_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSOP_REG_COUNT,
+	.format_attrs		= ibs_op_format_attrs,
 
 	.get_count		= get_ibs_op_count,
 };
@@ -597,6 +617,17 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 
 	perf_ibs->pcpu = pcpu;
 
+	/* register attributes */
+	if (perf_ibs->format_attrs[0]) {
+		memset(&perf_ibs->format_group, 0, sizeof(perf_ibs->format_group));
+		perf_ibs->format_group.name	= "format";
+		perf_ibs->format_group.attrs	= perf_ibs->format_attrs;
+
+		memset(&perf_ibs->attr_groups, 0, sizeof(perf_ibs->attr_groups));
+		perf_ibs->attr_groups[0]	= &perf_ibs->format_group;
+		perf_ibs->pmu.attr_groups	= perf_ibs->attr_groups;
+	}
+
 	ret = perf_pmu_register(&perf_ibs->pmu, name, -1);
 	if (ret) {
 		perf_ibs->pcpu = NULL;
@@ -608,13 +639,19 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 
 static __init int perf_event_ibs_init(void)
 {
+	struct attribute **attr = ibs_op_format_attrs;
+
 	if (!ibs_caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
 	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
-	if (ibs_caps & IBS_CAPS_OPCNT)
+
+	if (ibs_caps & IBS_CAPS_OPCNT) {
 		perf_ibs_op.config_mask |= IBS_OP_CNT_CTL;
+		*attr++ = &format_attr_cnt_ctl.attr;
+	}
 	perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
+
 	register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
 	printk(KERN_INFO "perf: AMD IBS detected (0x%08x)\n", ibs_caps);
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6bca492b854..324bb523d9d 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1906,6 +1906,8 @@ __init int intel_pmu_init(void)
 		switch (boot_cpu_data.x86) {
 		case 0x6:
 			return p6_pmu_init();
+		case 0xb:
+			return knc_pmu_init();
 		case 0xf:
 			return p4_pmu_init();
 		}
diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c
new file mode 100644
index 00000000000..7c46bfdbc37
--- /dev/null
+++ b/arch/x86/kernel/cpu/perf_event_knc.c
@@ -0,0 +1,248 @@
+/* Driver for Intel Xeon Phi "Knights Corner" PMU */
+
+#include <linux/perf_event.h>
+#include <linux/types.h>
+
+#include "perf_event.h"
+
+static const u64 knc_perfmon_event_map[] =
+{
+  [PERF_COUNT_HW_CPU_CYCLES]		= 0x002a,
+  [PERF_COUNT_HW_INSTRUCTIONS]		= 0x0016,
+  [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0028,
+  [PERF_COUNT_HW_CACHE_MISSES]		= 0x0029,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x0012,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x002b,
+};
+
+static __initconst u64 knc_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		/* On Xeon Phi event "0" is a valid DATA_READ          */
+		/*   (L1 Data Cache Reads) Instruction.                */
+		/* We code this as ARCH_PERFMON_EVENTSEL_INT as this   */
+		/* bit will always be set in x86_pmu_hw_config().      */
+		[ C(RESULT_ACCESS) ] = ARCH_PERFMON_EVENTSEL_INT,
+						/* DATA_READ           */
+		[ C(RESULT_MISS)   ] = 0x0003,	/* DATA_READ_MISS      */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0001,	/* DATA_WRITE          */
+		[ C(RESULT_MISS)   ] = 0x0004,	/* DATA_WRITE_MISS     */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0011,	/* L1_DATA_PF1         */
+		[ C(RESULT_MISS)   ] = 0x001c,	/* L1_DATA_PF1_MISS    */
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x000c,	/* CODE_READ          */
+		[ C(RESULT_MISS)   ] = 0x000e,	/* CODE_CACHE_MISS    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0x10cb,	/* L2_READ_MISS */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x10cc,	/* L2_WRITE_HIT */
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x10fc,	/* L2_DATA_PF2      */
+		[ C(RESULT_MISS)   ] = 0x10fe,	/* L2_DATA_PF2_MISS */
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = ARCH_PERFMON_EVENTSEL_INT,
+						/* DATA_READ */
+						/* see note on L1 OP_READ */
+		[ C(RESULT_MISS)   ] = 0x0002,	/* DATA_PAGE_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0001,	/* DATA_WRITE */
+		[ C(RESULT_MISS)   ] = 0x0002,	/* DATA_PAGE_WALK */
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0,
+		[ C(RESULT_MISS)   ] = 0x0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x000c,	/* CODE_READ */
+		[ C(RESULT_MISS)   ] = 0x000d,	/* CODE_PAGE_WALK */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0012,	/* BRANCHES */
+		[ C(RESULT_MISS)   ] = 0x002b,	/* BRANCHES_MISPREDICTED */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
+
+static u64 knc_pmu_event_map(int hw_event)
+{
+	return knc_perfmon_event_map[hw_event];
+}
+
+static struct event_constraint knc_event_constraints[] =
+{
+	INTEL_EVENT_CONSTRAINT(0xc3, 0x1),	/* HWP_L2HIT */
+	INTEL_EVENT_CONSTRAINT(0xc4, 0x1),	/* HWP_L2MISS */
+	INTEL_EVENT_CONSTRAINT(0xc8, 0x1),	/* L2_READ_HIT_E */
+	INTEL_EVENT_CONSTRAINT(0xc9, 0x1),	/* L2_READ_HIT_M */
+	INTEL_EVENT_CONSTRAINT(0xca, 0x1),	/* L2_READ_HIT_S */
+	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),	/* L2_READ_MISS */
+	INTEL_EVENT_CONSTRAINT(0xcc, 0x1),	/* L2_WRITE_HIT */
+	INTEL_EVENT_CONSTRAINT(0xce, 0x1),	/* L2_STRONGLY_ORDERED_STREAMING_VSTORES_MISS */
+	INTEL_EVENT_CONSTRAINT(0xcf, 0x1),	/* L2_WEAKLY_ORDERED_STREAMING_VSTORE_MISS */
+	INTEL_EVENT_CONSTRAINT(0xd7, 0x1),	/* L2_VICTIM_REQ_WITH_DATA */
+	INTEL_EVENT_CONSTRAINT(0xe3, 0x1),	/* SNP_HITM_BUNIT */
+	INTEL_EVENT_CONSTRAINT(0xe6, 0x1),	/* SNP_HIT_L2 */
+	INTEL_EVENT_CONSTRAINT(0xe7, 0x1),	/* SNP_HITM_L2 */
+	INTEL_EVENT_CONSTRAINT(0xf1, 0x1),	/* L2_DATA_READ_MISS_CACHE_FILL */
+	INTEL_EVENT_CONSTRAINT(0xf2, 0x1),	/* L2_DATA_WRITE_MISS_CACHE_FILL */
+	INTEL_EVENT_CONSTRAINT(0xf6, 0x1),	/* L2_DATA_READ_MISS_MEM_FILL */
+	INTEL_EVENT_CONSTRAINT(0xf7, 0x1),	/* L2_DATA_WRITE_MISS_MEM_FILL */
+	INTEL_EVENT_CONSTRAINT(0xfc, 0x1),	/* L2_DATA_PF2 */
+	INTEL_EVENT_CONSTRAINT(0xfd, 0x1),	/* L2_DATA_PF2_DROP */
+	INTEL_EVENT_CONSTRAINT(0xfe, 0x1),	/* L2_DATA_PF2_MISS */
+	INTEL_EVENT_CONSTRAINT(0xff, 0x1),	/* L2_DATA_HIT_INFLIGHT_PF2 */
+	EVENT_CONSTRAINT_END
+};
+
+#define MSR_KNC_IA32_PERF_GLOBAL_STATUS		0x0000002d
+#define MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL	0x0000002e
+#define MSR_KNC_IA32_PERF_GLOBAL_CTRL		0x0000002f
+
+#define KNC_ENABLE_COUNTER0			0x00000001
+#define KNC_ENABLE_COUNTER1			0x00000002
+
+static void knc_pmu_disable_all(void)
+{
+	u64 val;
+
+	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+	val &= ~(KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
+	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+}
+
+static void knc_pmu_enable_all(int added)
+{
+	u64 val;
+
+	rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+	val |= (KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
+	wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+}
+
+static inline void
+knc_pmu_disable_event(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 val;
+
+	val = hwc->config;
+	if (cpuc->enabled)
+		val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+
+	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+}
+
+static void knc_pmu_enable_event(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 val;
+
+	val = hwc->config;
+	if (cpuc->enabled)
+		val |= ARCH_PERFMON_EVENTSEL_ENABLE;
+
+	(void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+}
+
+PMU_FORMAT_ATTR(event,	"config:0-7"	);
+PMU_FORMAT_ATTR(umask,	"config:8-15"	);
+PMU_FORMAT_ATTR(edge,	"config:18"	);
+PMU_FORMAT_ATTR(inv,	"config:23"	);
+PMU_FORMAT_ATTR(cmask,	"config:24-31"	);
+
+static struct attribute *intel_knc_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
+static __initconst struct x86_pmu knc_pmu = {
+	.name			= "knc",
+	.handle_irq		= x86_pmu_handle_irq,
+	.disable_all		= knc_pmu_disable_all,
+	.enable_all		= knc_pmu_enable_all,
+	.enable			= knc_pmu_enable_event,
+	.disable		= knc_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_KNC_EVNTSEL0,
+	.perfctr		= MSR_KNC_PERFCTR0,
+	.event_map		= knc_pmu_event_map,
+	.max_events             = ARRAY_SIZE(knc_perfmon_event_map),
+	.apic			= 1,
+	.max_period		= (1ULL << 31) - 1,
+	.version		= 0,
+	.num_counters		= 2,
+	/* in theory 40 bits, early silicon is buggy though */
+	.cntval_bits		= 32,
+	.cntval_mask		= (1ULL << 32) - 1,
+	.get_event_constraints	= x86_get_event_constraints,
+	.event_constraints	= knc_event_constraints,
+	.format_attrs		= intel_knc_formats_attr,
+};
+
+__init int knc_pmu_init(void)
+{
+	x86_pmu = knc_pmu;
+
+	memcpy(hw_cache_event_ids, knc_hw_cache_event_ids, 
+		sizeof(hw_cache_event_ids));
+
+	return 0;
+}
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 966512b2cac..2e8caf03f59 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -56,6 +56,8 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		switch (boot_cpu_data.x86) {
 		case 6:
 			return msr - MSR_P6_PERFCTR0;
+		case 11:
+			return msr - MSR_KNC_PERFCTR0;
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
@@ -82,6 +84,8 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		switch (boot_cpu_data.x86) {
 		case 6:
 			return msr - MSR_P6_EVNTSEL0;
+		case 11:
+			return msr - MSR_KNC_EVNTSEL0;
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 599afc4bb67..b4166cdfa7a 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1110,7 +1110,7 @@ struct perf_cpu_context {
 	int				exclusive;
 	struct list_head		rotation_list;
 	int				jiffies_interval;
-	struct pmu			*active_pmu;
+	struct pmu			*unique_pmu;
 	struct perf_cgroup		*cgrp;
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cda3ebd49e8..dbccf83c134 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -372,6 +372,8 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->unique_pmu != pmu)
+			continue; /* ensure we process each cpuctx once */
 
 		/*
 		 * perf_cgroup_events says at least one
@@ -395,9 +397,10 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
 
 			if (mode & PERF_CGROUP_SWIN) {
 				WARN_ON_ONCE(cpuctx->cgrp);
-				/* set cgrp before ctxsw in to
-				 * allow event_filter_match() to not
-				 * have to pass task around
+				/*
+				 * set cgrp before ctxsw in to allow
+				 * event_filter_match() to not have to pass
+				 * task around
 				 */
 				cpuctx->cgrp = perf_cgroup_from_task(task);
 				cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
@@ -4412,7 +4415,7 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->active_pmu != pmu)
+		if (cpuctx->unique_pmu != pmu)
 			goto next;
 		perf_event_task_ctx(&cpuctx->ctx, task_event);
 
@@ -4558,7 +4561,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->active_pmu != pmu)
+		if (cpuctx->unique_pmu != pmu)
 			goto next;
 		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
@@ -4754,7 +4757,7 @@ got_name:
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
-		if (cpuctx->active_pmu != pmu)
+		if (cpuctx->unique_pmu != pmu)
 			goto next;
 		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
 					vma->vm_flags & VM_EXEC);
@@ -5855,8 +5858,8 @@ static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
 
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 
-		if (cpuctx->active_pmu == old_pmu)
-			cpuctx->active_pmu = pmu;
+		if (cpuctx->unique_pmu == old_pmu)
+			cpuctx->unique_pmu = pmu;
 	}
 }
 
@@ -5991,7 +5994,7 @@ skip_type:
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
 		INIT_LIST_HEAD(&cpuctx->rotation_list);
-		cpuctx->active_pmu = pmu;
+		cpuctx->unique_pmu = pmu;
 	}
 
 got_cpu_context:
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 9546ff58f02..247264502fb 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -45,6 +45,8 @@ include config/utilities.mak
 #
 # Define NO_LIBUNWIND if you do not want libunwind dependency for dwarf
 # backtrace post unwind.
+#
+# Define NO_BACKTRACE if you do not want stack backtrace debug feature
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -185,7 +187,7 @@ strip-libs = $(filter-out -l%,$(1))
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py
 
-$(OUTPUT)python/perf.so: $(PYRF_OBJS) $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
+$(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 	$(QUIET_GEN)CFLAGS='$(BASIC_CFLAGS)' $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
@@ -447,20 +449,6 @@ BUILTIN_OBJS += $(OUTPUT)builtin-inject.o
 
 PERFLIBS = $(LIB_FILE) $(LIBTRACEEVENT)
 
-# Files needed for the python binding, perf.so
-# pyrf is just an internal name needed for all those wrappers.
-# This has to be in sync with what is in the 'sources' variable in
-# tools/perf/util/setup.py
-
-PYRF_OBJS += $(OUTPUT)util/cpumap.o
-PYRF_OBJS += $(OUTPUT)util/ctype.o
-PYRF_OBJS += $(OUTPUT)util/evlist.o
-PYRF_OBJS += $(OUTPUT)util/evsel.o
-PYRF_OBJS += $(OUTPUT)util/python.o
-PYRF_OBJS += $(OUTPUT)util/thread_map.o
-PYRF_OBJS += $(OUTPUT)util/util.o
-PYRF_OBJS += $(OUTPUT)util/xyarray.o
-
 #
 # Platform specific tweaks
 #
@@ -487,7 +475,13 @@ ifneq ($(call try-cc,$(SOURCE_LIBELF),$(FLAGS_LIBELF)),y)
 		NO_DWARF := 1
 		NO_DEMANGLE := 1
 	endif
-endif
+else
+	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
+	endif # Dwarf support
+endif # SOURCE_LIBELF
 endif # NO_LIBELF
 
 ifndef NO_LIBUNWIND
@@ -512,8 +506,6 @@ ifneq ($(OUTPUT),)
 endif
 
 ifdef NO_LIBELF
-BASIC_CFLAGS += -DNO_LIBELF_SUPPORT
-
 EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
 
 # Remove ELF/DWARF dependent codes
@@ -528,17 +520,12 @@ BUILTIN