perf PMU support for Haswell: Extended functionality v1

perf PMU support for Haswell: Extended functionality v1

[Andi Kleen]

This is based on v7 of the earlier combined Haswell PMU patchkit.
The basic functionality has moved into a separate patchkit.
These patches implement more advanced functionality. Most
of the functionality is related to TSX.

This applies on top of the basic hsw/pmu4-basics patchkit posted
separately.

Some of this touches similar areas as Stephane's patchkit, with
some shared patches too.

Available at 
git://git.kernel.org/pub/scm/linux/kernel/ak/linux-misc.git hsw/pmu4

High level overview:

- Easy high level TSX measurement in perf stat -T
- Transaction events and attributes implemented with sysfs enumeration
- Export arch perfmon events in sysfs 
- Generic weightend profiling for memory latency and transaction abort costs.
- Support for address profiling
- KVM support to do basic TSX profiling from guests
- Support for filtering/displaying transaction abort types based on 
PEBS information

For more details on the Haswell PMU please see the SDM. For more details on TSX
please see http://halobates.de/adding-lock-elision-to-linux.pdf

Some of the added features could be added to older CPUs too. I plan
to do this, but in separate patches.

Open:
- Weight sorting does not work (see thread), not a show stopper.

-Andi

[PATCH 01/18] perf, tools: Support sorting by intx, abort branch flags v2

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Extend the perf branch sorting code to support sorting by intx
or abort qualifiers. Also print out those qualifiers.

This also fixes up some of the existing sort key documentation.

We do not support notx here, because it's simply not showing
the intx flag.

v2: Readd flags to man pages
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/util/sort.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index b7a4100..7896250 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -537,6 +537,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
+	DIM(SORT_ABORT, "abort", sort_abort),
+	DIM(SORT_INTX, "intx", sort_intx)
 };
 
 #undef DIM
-- 
1.7.7.6

[PATCH 02/18] perf, kvm: Support the intx/intx_cp modifiers in KVM arch perfmon emulation v5

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

This is not arch perfmon, but older CPUs will just ignore it. This makes
it possible to do at least some TSX measurements from a KVM guest

Cc: gleb@redhat.com
v2: Various fixes to address review feedback
v3: Ignore the bits when no CPUID. No #GP. Force raw events with TSX bits.
v4: Use reserved bits for #GP
v5: Remove obsolete argument
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/include/asm/kvm_host.h |    1 +
 arch/x86/kvm/pmu.c              |   25 ++++++++++++++++++++-----
 2 files changed, 21 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index dc87b65..703a1f8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -320,6 +320,7 @@ struct kvm_pmu {
 	u64 global_ovf_ctrl;
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
+	u64 reserved_bits;
 	u8 version;
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index cfc258a..9317c43 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
 
 static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		unsigned config, bool exclude_user, bool exclude_kernel,
-		bool intr)
+		bool intr, bool intx, bool intx_cp)
 {
 	struct perf_event *event;
 	struct perf_event_attr attr = {
@@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
 		.exclude_kernel = exclude_kernel,
 		.config = config,
 	};
+	if (intx)
+		attr.config |= HSW_INTX;
+	if (intx_cp)
+		attr.config |= HSW_INTX_CHECKPOINTED;
 
 	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
 
@@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 
 	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
 				ARCH_PERFMON_EVENTSEL_INV |
-				ARCH_PERFMON_EVENTSEL_CMASK))) {
+				ARCH_PERFMON_EVENTSEL_CMASK |
+				HSW_INTX |
+				HSW_INTX_CHECKPOINTED))) {
 		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
 				unit_mask);
 		if (config != PERF_COUNT_HW_MAX)
@@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	reprogram_counter(pmc, type, config,
 			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
 			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
-			eventsel & ARCH_PERFMON_EVENTSEL_INT);
+			eventsel & ARCH_PERFMON_EVENTSEL_INT,
+			(eventsel & HSW_INTX),
+			(eventsel & HSW_INTX_CHECKPOINTED));
 }
 
 static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
@@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
 			arch_events[fixed_pmc_events[idx]].event_type,
 			!(en & 0x2), /* exclude user */
 			!(en & 0x1), /* exclude kernel */
-			pmi);
+			pmi, false, false);
 }
 
 static inline u8 fixed_en_pmi(u64 ctrl, int idx)
@@ -400,7 +408,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
 			if (data == pmc->eventsel)
 				return 0;
-			if (!(data & 0xffffffff00200000ull)) {
+			if (!(data & pmu->reserved_bits)) {
 				reprogram_gp_counter(pmc, data);
 				return 0;
 			}
@@ -442,6 +450,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_GP] = 0;
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->version = 0;
+	pmu->reserved_bits = 0xffffffff00200000ull;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -470,6 +479,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
 		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
 	pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+	if (entry &&
+	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+		pmu->reserved_bits ^= HSW_INTX|HSW_INTX_CHECKPOINTED;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
-- 
1.7.7.6

Re: [PATCH 02/18] perf, kvm: Support the intx/intx_cp modifiers in KVM arch perfmon emulation v5

[Gleb Natapov]

On Fri, Jan 25, 2013 at 02:32:56PM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
> 
> This is not arch perfmon, but older CPUs will just ignore it. This makes
> it possible to do at least some TSX measurements from a KVM guest
> 
> Cc: gleb@redhat.com
> v2: Various fixes to address review feedback
> v3: Ignore the bits when no CPUID. No #GP. Force raw events with TSX bits.
> v4: Use reserved bits for #GP
> v5: Remove obsolete argument
> Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Gleb Natapov <gleb@redhat.com>

I suppose it will go through tip tree with all the other patches this one
depends on.

> ---
>  arch/x86/include/asm/kvm_host.h |    1 +
>  arch/x86/kvm/pmu.c              |   25 ++++++++++++++++++++-----
>  2 files changed, 21 insertions(+), 5 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index dc87b65..703a1f8 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -320,6 +320,7 @@ struct kvm_pmu {
>  	u64 global_ovf_ctrl;
>  	u64 counter_bitmask[2];
>  	u64 global_ctrl_mask;
> +	u64 reserved_bits;
>  	u8 version;
>  	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
>  	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
> diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
> index cfc258a..9317c43 100644
> --- a/arch/x86/kvm/pmu.c
> +++ b/arch/x86/kvm/pmu.c
> @@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
>  
>  static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
>  		unsigned config, bool exclude_user, bool exclude_kernel,
> -		bool intr)
> +		bool intr, bool intx, bool intx_cp)
>  {
>  	struct perf_event *event;
>  	struct perf_event_attr attr = {
> @@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
>  		.exclude_kernel = exclude_kernel,
>  		.config = config,
>  	};
> +	if (intx)
> +		attr.config |= HSW_INTX;
> +	if (intx_cp)
> +		attr.config |= HSW_INTX_CHECKPOINTED;
>  
>  	attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
>  
> @@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
>  
>  	if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
>  				ARCH_PERFMON_EVENTSEL_INV |
> -				ARCH_PERFMON_EVENTSEL_CMASK))) {
> +				ARCH_PERFMON_EVENTSEL_CMASK |
> +				HSW_INTX |
> +				HSW_INTX_CHECKPOINTED))) {
>  		config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
>  				unit_mask);
>  		if (config != PERF_COUNT_HW_MAX)
> @@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
>  	reprogram_counter(pmc, type, config,
>  			!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
>  			!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
> -			eventsel & ARCH_PERFMON_EVENTSEL_INT);
> +			eventsel & ARCH_PERFMON_EVENTSEL_INT,
> +			(eventsel & HSW_INTX),
> +			(eventsel & HSW_INTX_CHECKPOINTED));
>  }
>  
>  static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
> @@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
>  			arch_events[fixed_pmc_events[idx]].event_type,
>  			!(en & 0x2), /* exclude user */
>  			!(en & 0x1), /* exclude kernel */
> -			pmi);
> +			pmi, false, false);
>  }
>  
>  static inline u8 fixed_en_pmi(u64 ctrl, int idx)
> @@ -400,7 +408,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
>  		} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
>  			if (data == pmc->eventsel)
>  				return 0;
> -			if (!(data & 0xffffffff00200000ull)) {
> +			if (!(data & pmu->reserved_bits)) {
>  				reprogram_gp_counter(pmc, data);
>  				return 0;
>  			}
> @@ -442,6 +450,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
>  	pmu->counter_bitmask[KVM_PMC_GP] = 0;
>  	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
>  	pmu->version = 0;
> +	pmu->reserved_bits = 0xffffffff00200000ull;
>  
>  	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
>  	if (!entry)
> @@ -470,6 +479,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
>  	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
>  		(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
>  	pmu->global_ctrl_mask = ~pmu->global_ctrl;
> +
> +	entry = kvm_find_cpuid_entry(vcpu, 7, 0);
> +	if (entry &&
> +	    (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
> +	    (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
> +		pmu->reserved_bits ^= HSW_INTX|HSW_INTX_CHECKPOINTED;
>  }
>  
>  void kvm_pmu_init(struct kvm_vcpu *vcpu)
> -- 
> 1.7.7.6

--
			Gleb.

[PATCH 03/18] perf, x86: Support PERF_SAMPLE_ADDR on Haswell

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Haswell supplies the address for every PEBS memory event, so always fill it in
when the user requested it.  It will be 0 when not useful (no memory access)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 16d7c58..aa0f5fa 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -630,6 +630,10 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	else
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 
+	if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
+		x86_pmu.intel_cap.pebs_format >= 2)
+		data.addr = ((struct pebs_record_v2 *)pebs)->nhm.dla;
+
 	if (has_branch_stack(event))
 		data.br_stack = &cpuc->lbr_stack;
 
-- 
1.7.7.6

[PATCH 04/18] perf, core: Add a concept of a weightened sample v2

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

For some events it's useful to weight sample with a hardware
provided number. This expresses how expensive the action the
sample represent was.  This allows the profiler to scale
the samples to be more informative to the programmer.

There is already the period which is used similarly, but it means
something different, so I chose to not overload it. Instead
a new sample type for WEIGHT is added.

Can be used for multiple things. Initially it is used for TSX abort costs
and profiling by memory latencies (so to make expensive load appear higher
up in the histograms)  The concept is quite generic and can be extended
to many other kinds of events or architectures, as long as the hardware
provides suitable auxillary values. In principle it could be also
used for software tracpoints.

This adds the generic glue. A new optional sample format for a 64bit
weight value.

v2: Move weight format to the end. Remove *_FORMAT_WEIGHT
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 include/linux/perf_event.h      |    2 ++
 include/uapi/linux/perf_event.h |    6 +++++-
 kernel/events/core.c            |    6 ++++++
 3 files changed, 13 insertions(+), 1 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 91052e1..c9686c8 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -588,6 +588,7 @@ struct perf_sample_data {
 	struct perf_branch_stack	*br_stack;
 	struct perf_regs_user		regs_user;
 	u64				stack_user_size;
+	u64				weight;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -601,6 +602,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
+	data->weight = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 41b25f0..309968a 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -132,8 +132,10 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_BRANCH_STACK		= 1U << 11,
 	PERF_SAMPLE_REGS_USER			= 1U << 12,
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
+	PERF_SAMPLE_WEIGHT			= 1U << 14,
+
+	PERF_SAMPLE_MAX = 1U << 15,		/* non-ABI */
 
-	PERF_SAMPLE_MAX = 1U << 14,		/* non-ABI */
 };
 
 /*
@@ -591,6 +593,8 @@ enum perf_event_type {
 	 * 	{ u64			size;
 	 * 	  char			data[size];
 	 * 	  u64			dyn_size; } && PERF_SAMPLE_STACK_USER
+	 *
+	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 301079d..749bdf4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -952,6 +952,9 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_PERIOD)
 		size += sizeof(data->period);
 
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		size += sizeof(data->weight);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
 
@@ -4169,6 +4172,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 		perf_output_sample_ustack(handle,
 					  data->stack_user_size,
 					  data->regs_user.regs);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		perf_output_put(handle, data->weight);
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
-- 
1.7.7.6

[PATCH 05/18] perf, x86: Support weight samples for PEBS

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

When a weighted sample is requested, first try to report the TSX abort cost
on Haswell. If that is not available report the memory latency. This
allows profiling both by abort cost and by memory latencies.

Memory latencies requires enabling a different PEBS mode (LL).
When both address and weight is requested address wins.

The LL mode only works for memory related PEBS events, so add a
separate event constraint table for those.

I only did this for Haswell for now, but it could be added
for several other Intel CPUs too by just adding the right
table for them.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.h          |    4 ++
 arch/x86/kernel/cpu/perf_event_intel.c    |    4 ++
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   47 +++++++++++++++++++++++++++-
 3 files changed, 53 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ce2a863..d55e502 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -168,6 +168,7 @@ struct cpu_hw_events {
 	u64				perf_ctr_virt_mask;
 
 	void				*kfree_on_online;
+	u8				*memory_latency_events;
 };
 
 #define __EVENT_CONSTRAINT(c, n, m, w, o) {\
@@ -390,6 +391,7 @@ struct x86_pmu {
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
 	int 		max_pebs_events;
+	struct event_constraint *memory_lat_events;
 
 	/*
 	 * Intel LBR
@@ -599,6 +601,8 @@ extern struct event_constraint intel_ivb_pebs_event_constraints[];
 
 extern struct event_constraint intel_hsw_pebs_event_constraints[];
 
+extern struct event_constraint intel_hsw_memory_latency_events[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_enable(struct perf_event *event);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6899f57..d8acedd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1619,6 +1619,9 @@ static int hsw_hw_config(struct perf_event *event)
 
 	if (ret)
 		return ret;
+	/* PEBS cannot capture both */
+	if (event->attr.sample_type & PERF_SAMPLE_ADDR)
+		event->attr.sample_type &= ~PERF_SAMPLE_WEIGHT;
 	if (!boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has(X86_FEATURE_HLE))
 		return 0;
 	event->hw.config |= event->attr.config & (HSW_INTX|HSW_INTX_CHECKPOINTED);
@@ -2225,6 +2228,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
 		x86_pmu.format_attrs = intel_hsw_formats_attr;
+		x86_pmu.memory_lat_events = intel_hsw_memory_latency_events;
 		pr_cont("Haswell events, ");
 		break;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index aa0f5fa..3094caa 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -456,6 +456,17 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+/* Subset of PEBS events supporting memory latency. Not used for scheduling */
+
+struct event_constraint intel_hsw_memory_latency_events[] = {
+	INTEL_EVENT_CONSTRAINT(0xcd, 0), /* MEM_TRANS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0), /* MEM_UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0), /* MEM_LOAD_UOPS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd3, 0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -473,6 +484,21 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
+static bool is_memory_lat_event(struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	if (x86_pmu.intel_cap.pebs_format < 1)
+		return false;
+	if (!x86_pmu.memory_lat_events)
+		return false;
+	for_each_event_constraint(c, x86_pmu.memory_lat_events) {
+		if ((event->hw.config & c->cmask) == c->code)
+			return true;
+	}
+	return false;
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -480,7 +506,12 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
-	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+	/* When weight is requested enable LL instead of normal PEBS */
+	if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) &&
+		is_memory_lat_event(event))
+		cpuc->pebs_enabled |= 1ULL << (32 + hwc->idx);
+	else
+		cpuc->pebs_enabled |= 1ULL << hwc->idx;
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -488,7 +519,11 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+	if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) &&
+		is_memory_lat_event(event))
+		cpuc->pebs_enabled &= ~(1ULL << (32 + hwc->idx));
+	else
+		cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -634,6 +669,14 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		x86_pmu.intel_cap.pebs_format >= 2)
 		data.addr = ((struct pebs_record_v2 *)pebs)->nhm.dla;
 
+	if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) &&
+	    x86_pmu.intel_cap.pebs_format >= 2) {
+		data.weight = ((struct pebs_record_v2 *)pebs)->tsx_tuning &
+				0xffffffff;
+		if (!data.weight)
+			data.weight = ((struct pebs_record_v2 *)pebs)->nhm.lat;
+	}
+
 	if (has_branch_stack(event))
 		data.br_stack = &cpuc->lbr_stack;
 
-- 
1.7.7.6

[PATCH 06/18] perf, tools: Add support for weight v8

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

perf record has a new option -W that enables weightened sampling.

Add sorting support in top/report for the average weight per sample and the
total weight sum. This allows to both compare relative cost per event
and the total cost over the measurement period.

Add the necessary glue to perf report, record and the library.

v2: Merge with new hist refactoring.
v3: Fix manpage. Remove value check.
Rename global_weight to weight and weight to local_weight.
v4: Readd sort keys to manpage
v5: Move weight to end
v6: Move weight to template
v7: Rename weight key
v8: Port to latest tree
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-record.txt |    6 ++++
 tools/perf/Documentation/perf-report.txt |    3 ++
 tools/perf/Documentation/perf-top.txt    |    2 +-
 tools/perf/builtin-annotate.c            |    2 +-
 tools/perf/builtin-diff.c                |    7 ++--
 tools/perf/builtin-record.c              |    2 +
 tools/perf/builtin-report.c              |    8 +++--
 tools/perf/builtin-top.c                 |    5 ++-
 tools/perf/perf.h                        |    1 +
 tools/perf/tests/hists_link.c            |    4 +-
 tools/perf/util/event.h                  |    1 +
 tools/perf/util/evsel.c                  |   10 ++++++
 tools/perf/util/hist.c                   |   23 ++++++++++----
 tools/perf/util/hist.h                   |    8 ++++-
 tools/perf/util/session.c                |    3 ++
 tools/perf/util/sort.c                   |   47 ++++++++++++++++++++++++++++-
 tools/perf/util/sort.h                   |    3 ++
 17 files changed, 112 insertions(+), 23 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index f7d74b2..6f3405e 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -185,6 +185,12 @@ is enabled for all the sampling events. The sampled branch type is the same for
 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
 Note that this feature may not be available on all processors.
 
+-W::
+--weight::
+Enable weightened sampling. An additional weight is recorded per sample and can be
+displayed with the weight and local_weight sort keys.  This currently works for TSX
+abort events and some memory events in precise mode on modern Intel CPUs.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index eaf23ab..5a8b3cc 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -72,6 +72,9 @@ OPTIONS
 	- cpu: cpu number the task ran at the time of sample
 	- srcline: filename and line number executed at the time of sample.  The
 	DWARF debugging info must be provided.
+	- weight: Event specific weight, e.g. memory latency or transaction
+	abort cost. This is the global weight.
+	- local_weight: Local weight version of the weight above.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 93970b7..f7ded9d 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -114,7 +114,7 @@ Default is to monitor all CPUS.
 --sort::
 	Sort by key(s): pid, comm, dso, symbol, parent, srcline,
         dso_from, dso_to, symbol_to, symbol_from, mispredict,
-        abort, intx
+        abort, intx,  local_weight, weight
 
 -n::
 --show-nr-samples::
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index dc870cf..1bacb7d 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -62,7 +62,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, 1);
+	he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1);
 	if (he == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 4af0b58..8f29306 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -231,9 +231,10 @@ int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
 }
 
 static int hists__add_entry(struct hists *self,
-			    struct addr_location *al, u64 period)
+			    struct addr_location *al, u64 period,
+			    u64 weight)
 {
-	if (__hists__add_entry(self, al, NULL, period) != NULL)
+	if (__hists__add_entry(self, al, NULL, period, weight) != NULL)
 		return 0;
 	return -ENOMEM;
 }
@@ -255,7 +256,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (al.filtered)
 		return 0;
 
-	if (hists__add_entry(&evsel->hists, &al, sample->period)) {
+	if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4bcfccd..653a7b7 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -951,6 +951,8 @@ const struct option record_options[] = {
 	OPT_CALLBACK('j', "branch-filter", &record.opts.branch_stack,
 		     "branch filter mask", "branch stack filter modes",
 		     parse_branch_stack),
+	OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
+		    "sample by weight (on special events only)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d51a66d..13c980e 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -88,7 +88,7 @@ static int perf_report__add_branch_hist_entry(struct perf_tool *tool,
 		 * and not events sampled. Thus we use a pseudo period of 1.
 		 */
 		he = __hists__add_branch_entry(&evsel->hists, al, parent,
-				&bi[i], 1);
+				&bi[i], 1, 1);
 		if (he) {
 			struct annotation *notes;
 			err = -ENOMEM;
@@ -146,7 +146,8 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 			return err;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, parent, sample->period);
+	he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
+					sample->weight);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -596,7 +597,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		    "Use the stdio interface"),
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
-		   " dso_to, dso_from, symbol_to, symbol_from, mispredict, abort, intx"),
+		   " dso_to, dso_from, symbol_to, symbol_from, mispredict, "
+		   " abort, intx, weight, local_weight"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 9e08cec..1c165cf 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -249,7 +249,8 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 {
 	struct hist_entry *he;
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, sample->period);
+	he = __hists__add_entry(&evsel->hists, al, NULL, sample->period,
+				sample->weight);
 	if (he == NULL)
 		return NULL;
 
@@ -1080,7 +1081,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
 		   " dso_from, symbol_to, symbol_from, mispredict, srcline,"
-		   " abort, intx"),
+		   " abort, intx, weight, local_weight"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
 	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index eb049df..d888563 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -234,6 +234,7 @@ struct perf_record_opts {
 	bool	     pipe_output;
 	bool	     raw_samples;
 	bool	     sample_address;
+	bool	     sample_weight;
 	bool	     sample_time;
 	bool	     period;
 	unsigned int freq;
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index 0afd922..d65abaa 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -223,7 +223,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample, 0) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL, 1);
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 0);
 			if (he == NULL)
 				goto out;
 
@@ -247,7 +247,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample, 0) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL, 1);
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 0);
 			if (he == NULL)
 				goto out;
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 0d573ff..a97fbbe 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -88,6 +88,7 @@ struct perf_sample {
 	u64 id;
 	u64 stream_id;
 	u64 period;
+	u64 weight;
 	u32 cpu;
 	u32 raw_size;
 	void *raw_data;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e45332d..42e1e34 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -538,6 +538,9 @@ void perf_evsel__config(struct perf_evsel *evsel,
 		attr->branch_sample_type = opts->branch_stack;
 	}
 
+	if (opts->sample_weight)
+		attr->sample_type	|= PERF_SAMPLE_WEIGHT;
+
 	attr->mmap = track;
 	attr->comm = track;
 
@@ -956,6 +959,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 	data->period = 1;
+	data->weight = 0;
 
 	if (event->header.type != PERF_RECORD_SAMPLE) {
 		if (!evsel->attr.sample_id_all)
@@ -1106,6 +1110,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		}
 	}
 
+	data->weight = 0;
+	if (type & PERF_SAMPLE_WEIGHT) {
+		data->weight = *array;
+		array++;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 8170a3d..d3e0fcf 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -154,9 +154,11 @@ static void hist_entry__add_cpumode_period(struct hist_entry *he,
 	}
 }
 
-static void he_stat__add_period(struct he_stat *he_stat, u64 period)
+static void he_stat__add_period(struct he_stat *he_stat, u64 period,
+				u64 weight)
 {
 	he_stat->period		+= period;
+	he_stat->weight		+= weight;
 	he_stat->nr_events	+= 1;
 }
 
@@ -168,12 +170,14 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
+	dest->weight		+= src->weight;
 }
 
 static void hist_entry__decay(struct hist_entry *he)
 {
 	he->stat.period = (he->stat.period * 7) / 8;
 	he->stat.nr_events = (he->stat.nr_events * 7) / 8;
+	/* XXX need decay for weight too? */
 }
 
 static bool hists__decay_entry(struct hists *hists, struct hist_entry *he)
@@ -281,7 +285,8 @@ static u8 symbol__parent_filter(const struct symbol *parent)
 static struct hist_entry *add_hist_entry(struct hists *hists,
 				      struct hist_entry *entry,
 				      struct addr_location *al,
-				      u64 period)
+				      u64 period,
+				      u64 weight)
 {
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -305,7 +310,7 @@ static struct hist_entry *add_hist_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 
 		if (!cmp) {
-			he_stat__add_period(&he->stat, period);
+			he_stat__add_period(&he->stat, period, weight);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
@@ -344,7 +349,8 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self,
 					     struct addr_location *al,
 					     struct symbol *sym_parent,
 					     struct branch_info *bi,
-					     u64 period)
+					     u64 period,
+					     u64 weight)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -358,6 +364,7 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self,
 		.stat = {
 			.period	= period,
 			.nr_events = 1,
+			.weight = weight,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent),
@@ -365,12 +372,13 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self,
 		.hists	= self,
 	};
 
-	return add_hist_entry(self, &entry, al, period);
+	return add_hist_entry(self, &entry, al, period, weight);
 }
 
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
-				      struct symbol *sym_parent, u64 period)
+				      struct symbol *sym_parent, u64 period,
+				      u64 weight)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -384,13 +392,14 @@ struct hist_entry *__hists__add_entry(struct hists *self,
 		.stat = {
 			.period	= period,
 			.nr_events = 1,
+			.weight = weight,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent),
 		.hists	= self,
 	};
 
-	return add_hist_entry(self, &entry, al, period);
+	return add_hist_entry(self, &entry, al, period, weight);
 }
 
 int64_t
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 36a8565..42b075f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -51,6 +51,8 @@ enum hist_column {
 	HISTC_DSO_FROM,
 	HISTC_DSO_TO,
 	HISTC_SRCLINE,
+	HISTC_LOCAL_WEIGHT,
+	HISTC_GLOBAL_WEIGHT,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -75,7 +77,8 @@ struct hists {
 
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
-				      struct symbol *parent, u64 period);
+				      struct symbol *parent, u64 period,
+				      u64 weight);
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
 int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size,
@@ -86,7 +89,8 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self,
 					     struct addr_location *al,
 					     struct symbol *sym_parent,
 					     struct branch_info *bi,
-					     u64 period);
+					     u64 period,
+					     u64 weight);
 
 void hists__output_resort(struct hists *self);
 void hists__output_resort_threaded(struct hists *hists);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index bd85280b..12ffceb 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -800,6 +800,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT)
+		printf("... weight: %" PRIu64 "\n", sample->weight);
 }
 
 static struct machine *
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 7896250..5e9c842 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -521,6 +521,49 @@ struct sort_entry sort_intx = {
 	.se_width_idx	= HISTC_INTX,
 };
 
+static u64 he_weight(struct hist_entry *he)
+{
+	return he->stat.nr_events ? he->stat.weight / he->stat.nr_events : 0;
+}
+
+static int64_t
+sort__local_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return he_weight(left) - he_weight(right);
+}
+
+static int hist_entry__local_weight_snprintf(struct hist_entry *self, char *bf,
+				    size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*llu", width, he_weight(self));
+}
+
+struct sort_entry sort_local_weight = {
+	.se_header	= "Local Weight",
+	.se_cmp		= sort__local_weight_cmp,
+	.se_snprintf	= hist_entry__local_weight_snprintf,
+	.se_width_idx	= HISTC_LOCAL_WEIGHT,
+};
+
+static int64_t
+sort__global_weight_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->stat.weight - right->stat.weight;
+}
+
+static int hist_entry__global_weight_snprintf(struct hist_entry *self, char *bf,
+					      size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*llu", width, self->stat.weight);
+}
+
+struct sort_entry sort_global_weight = {
+	.se_header	= "Weight",
+	.se_cmp		= sort__global_weight_cmp,
+	.se_snprintf	= hist_entry__global_weight_snprintf,
+	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
+};
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
@@ -537,8 +580,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_PARENT, "parent", sort_parent),
 	DIM(SORT_CPU, "cpu", sort_cpu),
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
-	DIM(SORT_ABORT, "abort", sort_abort),
-	DIM(SORT_INTX, "intx", sort_intx)
+	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
+	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 6755d28..6ba3020 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -49,6 +49,7 @@ struct he_stat {
 	u64			period_us;
 	u64			period_guest_sys;
 	u64			period_guest_us;
+	u64			weight;
 	u32			nr_events;
 };
 
@@ -130,6 +131,8 @@ enum sort_type {
 	SORT_PARENT,
 	SORT_CPU,
 	SORT_SRCLINE,
+	SORT_LOCAL_WEIGHT,
+	SORT_GLOBAL_WEIGHT,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
-- 
1.7.7.6

[PATCH 07/18] perf, core: Add generic transaction flags v3

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add a generic qualifier for transaction events, as a new sample
type that returns a flag word. This is particularly useful
for qualifying aborts: to distinguish aborts which happen
due to asynchronous events (like conflicts caused by another
CPU) versus instructions that lead to an abort.

The tuning strategies are very different for those cases,
so it's important to distinguish them easily and early.

Since it's inconvenient and inflexible to filter for this
in the kernel we report all the events out and allow
some post processing in user space.

The flags are based on the Intel TSX events, but should be fairly
generic and mostly applicable to other architectures too. In addition
to various flag words there's also reserved space to report an
program supplied abort code. For TSX this is used to distinguish specific
classes of aborts, like a lock busy abort when doing lock elision.

This adds the perf core glue needed for reporting the new flag word out.

v2: Add MEM/MISC
v3: Move transaction to the end
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 include/linux/perf_event.h      |    2 ++
 include/uapi/linux/perf_event.h |   26 ++++++++++++++++++++++++--
 kernel/events/core.c            |    6 ++++++
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c9686c8..c32fba3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -589,6 +589,7 @@ struct perf_sample_data {
 	struct perf_regs_user		regs_user;
 	u64				stack_user_size;
 	u64				weight;
+	u64				transaction;
 };
 
 static inline void perf_sample_data_init(struct perf_sample_data *data,
@@ -603,6 +604,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->regs_user.regs = NULL;
 	data->stack_user_size = 0;
 	data->weight = 0;
+	data->transaction = 0;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 309968a..6b47798 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -133,9 +133,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_REGS_USER			= 1U << 12,
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
+	PERF_SAMPLE_TRANSACTION			= 1U << 15,
 
-	PERF_SAMPLE_MAX = 1U << 15,		/* non-ABI */
-
+	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
 };
 
 /*
@@ -179,6 +179,28 @@ enum perf_sample_regs_abi {
 };
 
 /*
+ * Values for the transaction event qualifier, mostly for abort events.
+ */
+enum {
+	PERF_SAMPLE_TXN_ELISION     = (1 << 0), /* From elision */
+	PERF_SAMPLE_TXN_TRANSACTION = (1 << 1), /* From transaction */
+	PERF_SAMPLE_TXN_SYNC        = (1 << 2), /* Instruction is related */
+	PERF_SAMPLE_TXN_ASYNC       = (1 << 3), /* Instruction not related */
+	PERF_SAMPLE_TXN_RETRY       = (1 << 4), /* Retry possible */
+	PERF_SAMPLE_TXN_CONFLICT    = (1 << 5), /* Conflict abort */
+	PERF_SAMPLE_TXN_CAPACITY    = (1 << 6), /* Capacity abort */
+	PERF_SAMPLE_TXN_MEMORY      = (1 << 7), /* Memory related abort */
+	PERF_SAMPLE_TXN_MISC        = (1 << 8), /* Misc aborts */
+
+	PERF_SAMPLE_TXN_MAX	    = (1 << 9),  /* non-ABI */
+
+	/* bits 24..31 are reserved for the abort code */
+
+	PERF_SAMPLE_TXN_ABORT_MASK  = 0xff000000,
+	PERF_SAMPLE_TXN_ABORT_SHIFT = 24,
+};
+
+/*
  * The format of the data returned by read() on a perf event fd,
  * as specified by attr.read_format:
  *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 749bdf4..b4078a0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -955,6 +955,9 @@ static void perf_event__header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_WEIGHT)
 		size += sizeof(data->weight);
 
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		size += sizeof(data->transaction);
+
 	if (sample_type & PERF_SAMPLE_READ)
 		size += event->read_size;
 
@@ -4175,6 +4178,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_WEIGHT)
 		perf_output_put(handle, data->weight);
+
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		perf_output_put(handle, data->transaction);
 }
 
 void perf_prepare_sample(struct perf_event_header *header,
-- 
1.7.7.6

[PATCH 08/18] perf, x86: Add Haswell specific transaction flag reporting

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

In the PEBS handler report the transaction flags using the new
generic transaction flags facility. Most of them come from
the "tsx_tuning" field in PEBSv2, but the abort code is derived
from the RAX register reported in the PEBS record.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c |    9 +++++++++
 1 files changed, 9 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3094caa..4b657c2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -677,6 +677,15 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 			data.weight = ((struct pebs_record_v2 *)pebs)->nhm.lat;
 	}
 
+	if ((event->attr.sample_type & PERF_SAMPLE_TRANSACTION) &&
+	    x86_pmu.intel_cap.pebs_format >= 2) {
+		data.transaction =
+		     ((struct pebs_record_v2 *)pebs)->tsx_tuning >> 32;
+		if ((data.transaction & PERF_SAMPLE_TXN_TRANSACTION) &&
+		    (pebs->ax & 1))
+			data.transaction |= pebs->ax & 0xff000000;
+	}
+
 	if (has_branch_stack(event))
 		data.br_stack = &cpuc->lbr_stack;
 
-- 
1.7.7.6

[PATCH 09/18] perf, tools: Add support for record transaction flags v3

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add the glue in the user tools to record transaction flags with
--transaction (-T was already taken) and dump them.

Followon patches will use them.

v2: Fix manpage
v3: Move transaction to the end
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-record.txt |    4 +++-
 tools/perf/builtin-record.c              |    2 ++
 tools/perf/perf.h                        |    1 +
 tools/perf/util/event.h                  |    1 +
 tools/perf/util/evsel.c                  |    9 +++++++++
 tools/perf/util/session.c                |    3 +++
 6 files changed, 19 insertions(+), 1 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 6f3405e..c73dd25 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -185,12 +185,14 @@ is enabled for all the sampling events. The sampled branch type is the same for
 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
 Note that this feature may not be available on all processors.
 
--W::
 --weight::
 Enable weightened sampling. An additional weight is recorded per sample and can be
 displayed with the weight and local_weight sort keys.  This currently works for TSX
 abort events and some memory events in precise mode on modern Intel CPUs.
 
+--transaction::
+Record transaction flags for transaction related events.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 653a7b7..5aa0e25 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -953,6 +953,8 @@ const struct option record_options[] = {
 		     parse_branch_stack),
 	OPT_BOOLEAN('W', "weight", &record.opts.sample_weight,
 		    "sample by weight (on special events only)"),
+	OPT_BOOLEAN(0, "transaction", &record.opts.sample_transaction,
+		    "sample transaction flags (special events only)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d888563..5671d31 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -244,6 +244,7 @@ struct perf_record_opts {
 	u64	     default_interval;
 	u64	     user_interval;
 	u16	     stack_dump_size;
+	bool	     sample_transaction;
 };
 
 #endif
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index a97fbbe..84b070d 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -89,6 +89,7 @@ struct perf_sample {
 	u64 stream_id;
 	u64 period;
 	u64 weight;
+	u64 transaction;
 	u32 cpu;
 	u32 raw_size;
 	void *raw_data;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 42e1e34..1fc510c 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -541,6 +541,9 @@ void perf_evsel__config(struct perf_evsel *evsel,
 	if (opts->sample_weight)
 		attr->sample_type	|= PERF_SAMPLE_WEIGHT;
 
+	if (opts->sample_transaction)
+		attr->sample_type	|= PERF_SAMPLE_TRANSACTION;
+
 	attr->mmap = track;
 	attr->comm = track;
 
@@ -1116,6 +1119,12 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->transaction = 0;
+	if (type & PERF_SAMPLE_TRANSACTION) {
+		data->transaction = *array;
+		array++;
+	}
+
 	return 0;
 }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 12ffceb..860e6a4 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -803,6 +803,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 
 	if (sample_type & PERF_SAMPLE_WEIGHT)
 		printf("... weight: %" PRIu64 "\n", sample->weight);
+
+	if (sample_type & PERF_SAMPLE_TRANSACTION)
+		printf("... transaction: %" PRIx64 "\n", sample->transaction);
 }
 
 static struct machine *
-- 
1.7.7.6

[PATCH 10/18] perf, tools: Add browser support for transaction flags v6

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add histogram support for the transaction flags. Each flags instance becomes
a separate histogram. Support sorting and displaying the flags in report
and top.

The patch is fairly large, but it's really mostly just plumbing to pass the
flags around.

v2: Increase column. Fix flags decoding. Use longer strings for flags
to be more user friendly.
v3: Fix WERROR=1 build. Tidy display
v4: Readd sort keys to manpage
v5: Reimplement transaction flags display code
v6: Port to latest tree
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-report.txt |    1 +
 tools/perf/Documentation/perf-top.txt    |    2 +-
 tools/perf/builtin-annotate.c            |    2 +-
 tools/perf/builtin-diff.c                |    8 ++-
 tools/perf/builtin-report.c              |    4 +-
 tools/perf/builtin-top.c                 |    4 +-
 tools/perf/tests/hists_link.c            |    4 +-
 tools/perf/util/hist.c                   |    7 +++-
 tools/perf/util/hist.h                   |    4 +-
 tools/perf/util/sort.c                   |   73 ++++++++++++++++++++++++++++++
 tools/perf/util/sort.h                   |    2 +
 11 files changed, 98 insertions(+), 13 deletions(-)

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 5a8b3cc..1e5ba01 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -75,6 +75,7 @@ OPTIONS
 	- weight: Event specific weight, e.g. memory latency or transaction
 	abort cost. This is the global weight.
 	- local_weight: Local weight version of the weight above.
+	- transaction: Transaction abort flags.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index f7ded9d..8c6bf2a 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -114,7 +114,7 @@ Default is to monitor all CPUS.
 --sort::
 	Sort by key(s): pid, comm, dso, symbol, parent, srcline,
         dso_from, dso_to, symbol_to, symbol_from, mispredict,
-        abort, intx,  local_weight, weight
+        abort, intx,  local_weight, weight, transaction
 
 -n::
 --show-nr-samples::
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 1bacb7d..cb8fa96 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -62,7 +62,7 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 		return 0;
 	}
 
-	he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1);
+	he = __hists__add_entry(&evsel->hists, al, NULL, 1, 1, 0);
 	if (he == NULL)
 		return -ENOMEM;
 
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 8f29306..ee54390 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -232,9 +232,10 @@ int perf_diff__formula(struct hist_entry *he, struct hist_entry *pair,
 
 static int hists__add_entry(struct hists *self,
 			    struct addr_location *al, u64 period,
-			    u64 weight)
+			    u64 weight, u64 transaction)
 {
-	if (__hists__add_entry(self, al, NULL, period, weight) != NULL)
+	if (__hists__add_entry(self, al, NULL, period, weight, transaction)
+	    != NULL)
 		return 0;
 	return -ENOMEM;
 }
@@ -256,7 +257,8 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (al.filtered)
 		return 0;
 
-	if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight)) {
+	if (hists__add_entry(&evsel->hists, &al, sample->period, sample->weight,
+			     sample->transaction)) {
 		pr_warning("problem incrementing symbol period, skipping event\n");
 		return -1;
 	}
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 13c980e..7b46793 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -147,7 +147,7 @@ static int perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	}
 
 	he = __hists__add_entry(&evsel->hists, al, parent, sample->period,
-					sample->weight);
+				sample->weight, sample->transaction);
 	if (he == NULL)
 		return -ENOMEM;
 
@@ -598,7 +598,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, cpu, srcline,"
 		   " dso_to, dso_from, symbol_to, symbol_from, mispredict, "
-		   " abort, intx, weight, local_weight"),
+		   " abort, intx, weight, local_weight, transaction"),
 	OPT_BOOLEAN(0, "showcpuutilization", &symbol_conf.show_cpu_utilization,
 		    "Show sample percentage for different cpu modes"),
 	OPT_STRING('p', "parent", &parent_pattern, "regex",
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1c165cf..faa1fa8 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -250,7 +250,7 @@ static struct hist_entry *perf_evsel__add_hist_entry(struct perf_evsel *evsel,
 	struct hist_entry *he;
 
 	he = __hists__add_entry(&evsel->hists, al, NULL, sample->period,
-				sample->weight);
+				sample->weight, sample->transaction);
 	if (he == NULL)
 		return NULL;
 
@@ -1081,7 +1081,7 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_STRING('s', "sort", &sort_order, "key[,key2...]",
 		   "sort by key(s): pid, comm, dso, symbol, parent, dso_to,"
 		   " dso_from, symbol_to, symbol_from, mispredict, srcline,"
-		   " abort, intx, weight, local_weight"),
+		   " abort, intx, weight, local_weight, transaction"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
 		    "Show a column with the number of samples"),
 	OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c
index d65abaa..8929de1 100644
--- a/tools/perf/tests/hists_link.c
+++ b/tools/perf/tests/hists_link.c
@@ -223,7 +223,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample, 0) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 0);
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 0, 0);
 			if (he == NULL)
 				goto out;
 
@@ -247,7 +247,7 @@ static int add_hist_entries(struct perf_evlist *evlist, struct machine *machine)
 							  &sample, 0) < 0)
 				goto out;
 
-			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 0);
+			he = __hists__add_entry(&evsel->hists, &al, NULL, 1, 0, 0);
 			if (he == NULL)
 				goto out;
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index d3e0fcf..2d2e7d4 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -115,6 +115,10 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 			hists__set_unres_dso_col_len(hists, HISTC_DSO_TO);
 		}
 	}
+
+	if (h->transaction)
+		hists__new_col_len(hists, HISTC_TRANSACTION, 
+				   hist_entry__transaction_len());
 }
 
 void hists__output_recalc_col_len(struct hists *hists, int max_rows)
@@ -378,7 +382,7 @@ struct hist_entry *__hists__add_branch_entry(struct hists *self,
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
 				      struct symbol *sym_parent, u64 period,
-				      u64 weight)
+				      u64 weight, u64 transaction)
 {
 	struct hist_entry entry = {
 		.thread	= al->thread,
@@ -397,6 +401,7 @@ struct hist_entry *__hists__add_entry(struct hists *self,
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent),
 		.hists	= self,
+		.transaction = transaction,
 	};
 
 	return add_hist_entry(self, &entry, al, period, weight);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 42b075f..f8fafae 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -53,6 +53,7 @@ enum hist_column {
 	HISTC_SRCLINE,
 	HISTC_LOCAL_WEIGHT,
 	HISTC_GLOBAL_WEIGHT,
+	HISTC_TRANSACTION,
 	HISTC_NR_COLS, /* Last entry */
 };
 
@@ -78,9 +79,10 @@ struct hists {
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
 				      struct symbol *parent, u64 period,
-				      u64 weight);
+				      u64 weight, u64 transaction);
 int64_t hist_entry__cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t hist_entry__collapse(struct hist_entry *left, struct hist_entry *right);
+int hist_entry__transaction_len(void);
 int hist_entry__sort_snprintf(struct hist_entry *self, char *bf, size_t size,
 			      struct hists *hists);
 void hist_entry__free(struct hist_entry *);
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 5e9c842..fe3b56c 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -564,6 +564,78 @@ struct sort_entry sort_global_weight = {
 	.se_width_idx	= HISTC_GLOBAL_WEIGHT,
 };
 
+static int64_t
+sort__transaction_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->transaction - right->transaction;
+}
+
+static inline char *add_str(char *p, const char *str)
+{
+	strcpy(p, str);
+	return p + strlen(str);
+}
+
+static struct txbit {
+	unsigned flag;
+	const char *name;
+	int skip_for_len;
+} txbits[] = {
+	{ PERF_SAMPLE_TXN_ELISION,     "EL ", 0 },
+	{ PERF_SAMPLE_TXN_TRANSACTION, "TX ", 1 },
+	{ PERF_SAMPLE_TXN_SYNC,        "SYNC ", 1 },
+	{ PERF_SAMPLE_TXN_ASYNC,       "ASYNC ", 0 },
+	{ PERF_SAMPLE_TXN_RETRY,       "RETRY ", 0 },
+	{ PERF_SAMPLE_TXN_CONFLICT,    "CON ", 0 },
+	{ PERF_SAMPLE_TXN_CAPACITY,    "CAP ", 1 },
+	{ PERF_SAMPLE_TXN_MEMORY,      "MEM ", 0 },
+	{ PERF_SAMPLE_TXN_MISC,        "MISC ", 0 },
+	{ 0, NULL, 0 }
+};
+
+int hist_entry__transaction_len(void)
+{
+	int i;
+	int len = 0;
+
+	for (i = 0; txbits[i].name; i++) {
+		if (!txbits[i].skip_for_len)
+			len += strlen(txbits[i].name);
+	}
+	len += 4; /* :XX<space> */
+	return len;
+}
+
+static int hist_entry__transaction_snprintf(struct hist_entry *self, char *bf,
+	 			    	    size_t size, unsigned int width)
+{
+	u64 t = self->transaction;
+	char buf[128];
+	char *p = buf;
+	int i;
+
+	for (i = 0; txbits[i].name; i++)
+		if (txbits[i].flag & t)
+			p = add_str(p, txbits[i].name);
+	if (t && !(t & (PERF_SAMPLE_TXN_SYNC|PERF_SAMPLE_TXN_ASYNC)))
+		p = add_str(p, "NEITHER ");
+	if (t & PERF_SAMPLE_TXN_ABORT_MASK) {
+		sprintf(p, ":%" PRIx64,
+			(t & PERF_SAMPLE_TXN_ABORT_MASK) >>
+			PERF_SAMPLE_TXN_ABORT_SHIFT);
+		p += strlen(p);
+	}
+
+	return repsep_snprintf(bf, size, "%-*s", width, buf);
+}
+
+struct sort_entry sort_transaction = {
+	.se_header	= "Transaction                ",
+	.se_cmp		= sort__transaction_cmp,
+	.se_snprintf	= hist_entry__transaction_snprintf,
+	.se_width_idx	= HISTC_TRANSACTION,
+};
+
 struct sort_dimension {
 	const char		*name;
 	struct sort_entry	*entry;
@@ -582,6 +654,7 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_SRCLINE, "srcline", sort_srcline),
 	DIM(SORT_LOCAL_WEIGHT, "local_weight", sort_local_weight),
 	DIM(SORT_GLOBAL_WEIGHT, "weight", sort_global_weight),
+	DIM(SORT_TRANSACTION, "transaction", sort_transaction),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 6ba3020..7b7dfde 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -83,6 +83,7 @@ struct hist_entry {
 	struct map_symbol	ms;
 	struct thread		*thread;
 	u64			ip;
+	u64			transaction;
 	s32			cpu;
 
 	struct hist_entry_diff	diff;
@@ -133,6 +134,7 @@ enum sort_type {
 	SORT_SRCLINE,
 	SORT_LOCAL_WEIGHT,
 	SORT_GLOBAL_WEIGHT,
+	SORT_TRANSACTION,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
-- 
1.7.7.6

[PATCH 11/18] tools, perf: Add a precise event qualifier v2

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add a precise qualifier, like cpu/event=0x3c,precise=1/

This is needed so that the kernel can request enabling PEBS
for TSX events. The parser bails out on any sysfs parse errors,
so this is needed in any case to handle any event on the TSX
perf kernel.

v2: Allow 3 as value
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/util/parse-events.c |    6 ++++++
 tools/perf/util/parse-events.h |    1 +
 tools/perf/util/parse-events.l |    1 +
 3 files changed, 8 insertions(+), 0 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 02f6421..f6f6aaa 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -568,6 +568,12 @@ do {								\
 	case PARSE_EVENTS__TERM_TYPE_NAME:
 		CHECK_TYPE_VAL(STR);
 		break;
+	case PARSE_EVENTS__TERM_TYPE_PRECISE:
+		CHECK_TYPE_VAL(NUM);
+		if ((unsigned)term->val.num > 3)
+			return -EINVAL;
+		attr->precise_ip = term->val.num;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 2cd2c42..9d526cf 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -48,6 +48,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_NAME,
 	PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD,
 	PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE,
+	PARSE_EVENTS__TERM_TYPE_PRECISE,
 };
 
 struct parse_events_term {
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index e9d1134..32a9000 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -169,6 +169,7 @@ period			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD); }
 branch_type		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_BRANCH_SAMPLE_TYPE); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
+precise			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PRECISE); }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
 }
 
-- 
1.7.7.6

[PATCH 12/18] perf, x86: improve sysfs event mapping with event string

[Andi Kleen]

From: Stephane Eranian <eranian@google.com>

This patch extends Jiri's changes to make generic
events mapping visible via sysfs. The patch extends
the mechanism to non-generic events by allowing
the mappings to be hardcoded in strings.

This mechanism will be used by the PEBS-LL patch
later on.

[AK: Make events_sysfs_show unstatic again to fix compilation]
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.c |   28 +++++++++++++---------------
 arch/x86/kernel/cpu/perf_event.h |   26 ++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index c95290a..fa14db6 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1310,20 +1310,22 @@ 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)
 {
+	struct device_attribute *d;
+	struct perf_pmu_events_attr *pmu_attr;
 	int i, j;
 
 	for (i = 0; attrs[i]; i++) {
+		d = (struct device_attribute *)attrs[i];
+		pmu_attr = container_of(d, struct perf_pmu_events_attr, attr);
+		/* str trumps id */
+		if (pmu_attr->event_str)
+			continue;
 		if (x86_pmu.event_map(i))
 			continue;
 
@@ -1335,24 +1337,20 @@ static void __init filter_events(struct attribute **attrs)
 	}
 }
 
-static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+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
+	/* string trumps id */
+	if (pmu_attr->event_str)
+		return sprintf(page, "%s", pmu_attr->event_str);
 
-#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,				\
-};
+	return x86_pmu.events_sysfs_show(page, config);
+}
 
 EVENT_ATTR(cpu-cycles,			CPU_CYCLES		);
 EVENT_ATTR(instructions,		INSTRUCTIONS		);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index d55e502..8253b73 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -425,6 +425,29 @@ do {									\
 #define ERF_NO_HT_SHARING	1
 #define ERF_HAS_RSP_1		2
 
+#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_str = NULL,					\
+};
+
+#define EVENT_ATTR_STR(_name, v, str)				  \
+static struct perf_pmu_events_attr event_attr_##v = {		  \
+	.attr      = __ATTR(_name, 0444, events_sysfs_show, NULL),\
+	.id        =  0,					  \
+	.event_str =  str,					  \
+};
+
+struct perf_pmu_events_attr {
+	struct device_attribute attr;
+	u64 id;
+	const char *event_str;
+};
+
 extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events);
@@ -643,6 +666,9 @@ int p6_pmu_init(void);
 
 int knc_pmu_init(void);
 
+ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
+			  char *page);
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)
-- 
1.7.7.6

[PATCH 13/18] perf, x86: Support CPU specific sysfs events

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add a way for the CPU initialization code to register additional events,
and merge them into the events attribute directory. Used in the next
patch.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event.c |   29 +++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/perf_event.h |    1 +
 2 files changed, 30 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index fa14db6..375498a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1337,6 +1337,30 @@ static void __init filter_events(struct attribute **attrs)
 	}
 }
 
+/* Merge two pointer arrays */
+static __init struct attribute **merge_attr(struct attribute **a,
+					    struct attribute **b)
+{
+	struct attribute **new;
+	int j, i;
+
+	for (j = 0; a[j]; j++)
+		;
+	for (i = 0; b[i]; i++)
+		j++;
+	j++;
+	new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL);
+	if (!new)
+		return a;
+	j = 0;
+	for (i = 0; a[i]; i++)
+		new[j++] = a[i];
+	for (i = 0; b[i]; i++)
+		new[j++] = b[i];
+	new[j] = NULL;
+	return new;
+}
+
 ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
 			  char *page)
 {
@@ -1474,6 +1498,11 @@ static int __init init_hw_perf_events(void)
 	else
 		filter_events(x86_pmu_events_group.attrs);
 
+	if (x86_pmu.cpu_events)
+		x86_pmu_events_group.attrs =
+			merge_attr(x86_pmu_events_group.attrs,
+				   x86_pmu.cpu_events);
+
 	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);
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8253b73..ba5d043 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -360,6 +360,7 @@ struct x86_pmu {
 	struct attribute **format_attrs;
 
 	ssize_t		(*events_sysfs_show)(char *page, u64 config);
+	struct attribute **cpu_events;
 
 	/*
 	 * CPU Hotplug hooks
-- 
1.7.7.6

[PATCH 14/18] perf, x86: Add Haswell TSX event aliases v2

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add infrastructure to generate event aliases in /sys/devices/cpu/events/

And use this to set up user friendly aliases for the common TSX events.
TSX tuning relies heavily on the PMU, so it's important to be user friendly.

This replaces the generic transaction events in an earlier version
of this patchkit.

tx-start/commit/abort  to count RTM transactions
el-start/commit/abort  to count HLE ("elision") transactions
tx-conflict/overflow   to count conflict/overflow for both combined.

The general abort events exist in precise and non precise variants
Since the common case is sampling plain "tx-aborts" in precise.

This is very important because abort sampling only really works
with PEBS enabled, otherwise it would report the IP after the abort,
not the abort point. But counting with PEBS has more overhead,
so also have tx/el-abort-count aliases that do not enable PEBS
for perf stat.

It would be nice to switch automatically between those two, like in the
previous version, but that would need more new infrastructure for sysfs
first.

There is an tx-abort<->tx-aborts alias too, because I found myself
using both variants.

Also added friendly aliases for cpu/cycles,intx=1/ and
cpu/cycles,intx=1,intx_cp=1/ and the same for instructions.
These will be used by perf stat -T, and are also useful for users directly.

So for example to get transactional cycles can use "perf stat -e cycles-t"

v2: Move to new sysfs infrastructure
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c |   47 ++++++++++++++++++++++++++++++++
 1 files changed, 47 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index d8acedd..022246a 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2004,6 +2004,52 @@ static __init void intel_nehalem_quirk(void)
 	}
 }
 
+/* Haswell special events */
+EVENT_ATTR_STR(tx-start,       tx_start,       "event=0xc9,umask=0x1");
+EVENT_ATTR_STR(tx-commit,      tx_commit,      "event=0xc9,umask=0x2");
+EVENT_ATTR_STR(tx-abort,       tx_abort,       "event=0xc9,umask=0x4,precise=2");
+EVENT_ATTR_STR(tx-abort-count, tx_abort_count, "event=0xc9,umask=0x4");
+/* alias */
+EVENT_ATTR_STR(tx-aborts,      tx_aborts,      "event=0xc9,umask=0x4,precise=2");
+EVENT_ATTR_STR(tx-capacity,    tx_capacity,    "event=0x54,umask=0x2");
+EVENT_ATTR_STR(tx-conflict,    tx_conflict,    "event=0x54,umask=0x1");
+EVENT_ATTR_STR(el-start,       el_start,       "event=0xc8,umask=0x1");
+EVENT_ATTR_STR(el-commit,      el_commit,      "event=0xc8,umask=0x2");
+EVENT_ATTR_STR(el-abort,       el_abort,       "event=0xc8,umask=0x4,precise=2");
+EVENT_ATTR_STR(el-abort-count, el_abort_count, "event=0xc8,umask=0x4");
+/* alias */
+EVENT_ATTR_STR(el-aborts,      el_aborts,      "event=0xc8,umask=0x4,precise=2");
+/* shared with tx-* */
+EVENT_ATTR_STR(el-capacity,    el_capacity,    "event=0x54,umask=0x2");
+/* shared with tx-* */
+EVENT_ATTR_STR(el-conflict,    el_conflict,    "event=0x54,umask=0x1");
+EVENT_ATTR_STR(cycles-t,       cycles_t,       "event=0x3c,intx=1");
+EVENT_ATTR_STR(cycles-ct,      cycles_ct,      "event=0x3c,intx=1,intx_cp=1");
+EVENT_ATTR_STR(instructions-t, instructions_t, "event=0xc0,intx=1");
+EVENT_ATTR_STR(instructions-ct,instructions_ct,"event=0xc0,intx=1,intx_cp=1");
+
+static struct attribute *hsw_events_attrs[] = {
+	EVENT_PTR(tx_start),
+	EVENT_PTR(tx_commit),
+	EVENT_PTR(tx_abort),
+	EVENT_PTR(tx_aborts),
+	EVENT_PTR(tx_abort_count),
+	EVENT_PTR(tx_capacity),
+	EVENT_PTR(tx_conflict),
+	EVENT_PTR(el_start),
+	EVENT_PTR(el_commit),
+	EVENT_PTR(el_abort),
+	EVENT_PTR(el_aborts),
+	EVENT_PTR(el_abort_count),
+	EVENT_PTR(el_capacity),
+	EVENT_PTR(el_conflict),
+	EVENT_PTR(cycles_t),
+	EVENT_PTR(cycles_ct),
+	EVENT_PTR(instructions_t),
+	EVENT_PTR(instructions_ct),
+	NULL
+};
+
 __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -2229,6 +2275,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
 		x86_pmu.format_attrs = intel_hsw_formats_attr;
 		x86_pmu.memory_lat_events = intel_hsw_memory_latency_events;
+		x86_pmu.cpu_events = hsw_events_attrs;
 		pr_cont("Haswell events, ");
 		break;
 
-- 
1.7.7.6

[PATCH 15/18] perf, tools: Add perf stat --transaction v3

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add support to perf stat to print the basic transactional execution statistics:
Total cycles, Cycles in Transaction, Cycles in aborted transsactions
using the intx and intx_checkpoint qualifiers.
Transaction Starts and Elision Starts, to compute the average transaction length.

This is a reasonable overview over the success of the transactions.

Enable with a new --transaction / -T option.

This requires measuring these events in a group, since they depend on each
other.

This is implemented by using TM sysfs events exported by the kernel

v2: Only print the extended statistics when the option is enabled.
This avoids negative output when the user specifies the -T events
in separate groups.
v3: Port to latest tree
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-stat.txt |    4 +
 tools/perf/builtin-stat.c              |  101 +++++++++++++++++++++++++++++++-
 tools/perf/util/evsel.h                |    6 ++
 3 files changed, 108 insertions(+), 3 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index cf0c310..0d5b8cb 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -114,6 +114,10 @@ with it.  --append may be used here.  Examples:
 
 perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
 
+-T::
+--transaction::
+
+Print statistics of transactional execution if supported.
 
 EXAMPLES
 --------
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 1c2ac14..50691b4 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -65,6 +65,29 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
+static const char *transaction_attrs[] = {
+	"task-clock",
+	"{"
+	"instructions,"
+	"cycles,"
+	"cpu/cycles-t/,"
+	"cpu/cycles-ct/,"
+	"cpu/tx-start/,"
+	"cpu/el-start/"
+	"}"
+};
+
+/* must match the transaction_attrs above */
+enum {
+	T_TASK_CLOCK,
+	T_INSTRUCTIONS,
+	T_CYCLES,
+	T_CYCLES_INTX,
+	T_CYCLES_INTX_CP,
+	T_TRANSACTION_START,
+	T_ELISION_START
+};
+
 static struct perf_evlist	*evsel_list;
 
 static struct perf_target	target = {
@@ -78,6 +101,7 @@ static bool			no_aggr				= false;
 static pid_t			child_pid			= -1;
 static bool			null_run			=  false;
 static int			detailed_run			=  0;
+static bool			transaction_run			=  false;
 static bool			big_num				=  true;
 static int			big_num_opt			=  -1;
 static const char		*csv_sep			= NULL;
@@ -127,7 +151,11 @@ static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
 static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
 static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
 static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_intx_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_intxcp_stats[MAX_NR_CPUS];
 static struct stats walltime_nsecs_stats;
+static struct stats runtime_transaction_stats[MAX_NR_CPUS];
+static struct stats runtime_elision_stats[MAX_NR_CPUS];
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
 {
@@ -163,6 +191,18 @@ static inline int nsec_counter(struct perf_evsel *evsel)
 	return 0;
 }
 
+static struct perf_evsel *nth_evsel(int n)
+{
+	struct perf_evsel *ev;
+	int j;
+
+	j = 0;
+	list_for_each_entry (ev, &evsel_list->entries, node)
+		if (j++ == n)
+			return ev;
+	return NULL;
+}
+
 /*
  * Update various tracking values we maintain to print
  * more semantic information such as miss/hit ratios,
@@ -174,8 +214,14 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
 		update_stats(&runtime_nsecs_stats[0], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[0], count[0]);
-	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
-		update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
+	else if (perf_evsel__cmp(counter, nth_evsel(T_CYCLES_INTX)))
+		update_stats(&runtime_cycles_intx_stats[0], count[0]);
+	else if (perf_evsel__cmp(counter, nth_evsel(T_CYCLES_INTX_CP)))
+		update_stats(&runtime_cycles_intxcp_stats[0], count[0]);
+	else if (perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
+		update_stats(&runtime_transaction_stats[0], count[0]);
+	else if (perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
+		update_stats(&runtime_elision_stats[0], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
 		update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
 	else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
@@ -631,7 +677,7 @@ static void print_ll_cache_misses(int cpu,
 
 static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
-	double total, ratio = 0.0;
+	double total, ratio = 0.0, total2;
 	char cpustr[16] = { '\0', };
 	const char *fmt;
 
@@ -731,6 +777,41 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 			ratio = 1.0 * avg / total;
 
 		fprintf(output, " # %8.3f GHz                    ", ratio);
+	} else if (perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_INTX)) &&
+		   transaction_run) {
+		total = avg_stats(&runtime_cycles_stats[cpu]);
+		if (total)
+			fprintf(output,
+				" #   %5.2f%% transactional cycles   ",
+				100.0 * (avg / total));
+	} else if (perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_INTX_CP)) &&
+		   transaction_run) {
+		total = avg_stats(&runtime_cycles_stats[cpu]);
+		total2 = avg_stats(&runtime_cycles_intx_stats[cpu]);
+		if (total)
+			fprintf(output,
+				" #   %5.2f%% aborted cycles         ",
+				100.0 * ((total2-avg) / total));
+	} else if (perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) &&
+		   avg > 0 &&
+		   runtime_cycles_intx_stats[cpu].n != 0 &&
+		   transaction_run) {
+		total = avg_stats(&runtime_cycles_intx_stats[cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(output, " # %8.0f cycles / transaction ", ratio);
+	} else if (perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) &&
+		   avg > 0 &&
+		   runtime_cycles_intx_stats[cpu].n != 0 &&
+		   transaction_run) {
+		total = avg_stats(&runtime_cycles_intx_stats[cpu]);
+
+		if (total)
+			ratio = total / avg;
+
+		fprintf(output, " # %8.0f cycles / elision     ", ratio);
 	} else if (runtime_nsecs_stats[cpu].n != 0) {
 		char unit = 'M';
 
@@ -1037,6 +1118,18 @@ static int add_default_attributes(void)
 	if (null_run)
 		return 0;
 
+	if (transaction_run) {
+		unsigned i;
+
+		for (i = 0; i < ARRAY_SIZE(transaction_attrs); i++) {
+			if (parse_events(evsel_list, transaction_attrs[i])) {
+				fprintf(stderr, "Cannot set up transaction events\n");
+				return -1;
+			}
+		}
+		return 0;
+	}
+
 	if (!evsel_list->nr_entries) {
 		if (perf_evlist__add_default_attrs(evsel_list, default_attrs) < 0)
 			return -1;
@@ -1115,6 +1208,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 			"command to run prior to the measured command"),
 	OPT_STRING(0, "post", &post_cmd, "command",
 			"command to run after to the measured command"),
+	OPT_BOOLEAN('T', "transaction", &transaction_run,
+		    "hardware transaction statistics"),
 	OPT_END()
 	};
 	const char * const stat_usage[] = {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index c68d1b8..70f10e1 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -171,6 +171,12 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	       (e1->attr.config == e2->attr.config);
 }
 
+#define perf_evsel__cmp(a, b)			\
+	((a) &&					\
+	 (b) &&					\
+	 (a)->attr.type == (b)->attr.type &&	\
+	 (a)->attr.config == (b)->attr.config)
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
 
-- 
1.7.7.6

[PATCH 16/18] perf, x86: Add a Haswell precise instructions event v2

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

Add a instructions-p event alias that uses the PDIR randomized instruction
retirement event. This is useful to avoid some systematic sampling shadow
problems. Normally PEBS sampling has a systematic shadow. With PDIR
enabled the hardware adds some randomization that statistically avoids
this problem. In this sense, it's more precise over a whole sampling
interval, but an individual sample can be less precise. But since we
sample overall it's a more precise event.

This could be used before using the explicit event code syntax, but it's easier
and more user friendly to use with an "instructions-p" alias. I expect
this will eventually become a common use case.

Right now for Haswell, will add to Ivy Bridge later too.

v2: Use new sysfs infrastructure
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 arch/x86/kernel/cpu/perf_event_intel.c |    2 ++
 1 files changed, 2 insertions(+), 0 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 022246a..fa20a19 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2027,6 +2027,7 @@ EVENT_ATTR_STR(cycles-t,       cycles_t,       "event=0x3c,intx=1");
 EVENT_ATTR_STR(cycles-ct,      cycles_ct,      "event=0x3c,intx=1,intx_cp=1");
 EVENT_ATTR_STR(instructions-t, instructions_t, "event=0xc0,intx=1");
 EVENT_ATTR_STR(instructions-ct,instructions_ct,"event=0xc0,intx=1,intx_cp=1");
+EVENT_ATTR_STR(instructions-p, instructions_p, "event=0xc0,umask=0x01,precise=2");
 
 static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(tx_start),
@@ -2047,6 +2048,7 @@ static struct attribute *hsw_events_attrs[] = {
 	EVENT_PTR(cycles_ct),
 	EVENT_PTR(instructions_t),
 	EVENT_PTR(instructions_ct),
+	EVENT_PTR(instructions_p),
 	NULL
 };
 
-- 
1.7.7.6

[PATCH 17/18] perf, tools: Default to cpu// for events v5

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

When an event fails to parse and it's not in a new style format,
try to parse it again as a cpu event.

This allows to use sysfs exported events directly without //, so I can use

perf record -e tx-aborts ...

instead of

perf record -e cpu/tx-aborts/

v2: Handle multiple events
v3: Move to separate function
v4: Move library function to util/string.c
v5: Handle unhandleable errors
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/util/include/linux/string.h |    1 +
 tools/perf/util/parse-events.c         |   32 ++++++++++++++++++++++++++++++--
 tools/perf/util/string.c               |   25 +++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/include/linux/string.h b/tools/perf/util/include/linux/string.h
index 6f19c54..97a8007 100644
--- a/tools/perf/util/include/linux/string.h
+++ b/tools/perf/util/include/linux/string.h
@@ -1,3 +1,4 @@
 #include <string.h>
 
 void *memdup(const void *src, size_t len);
+int str_append(char **s, int *len, const char *a);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index f6f6aaa..7c1250f 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -6,7 +6,7 @@
 #include "parse-options.h"
 #include "parse-events.h"
 #include "exec_cmd.h"
-#include "string.h"
+#include "linux/string.h"
 #include "symbol.h"
 #include "cache.h"
 #include "header.h"
@@ -834,6 +834,32 @@ int parse_events_name(struct list_head *list, char *name)
 	return 0;
 }
 
+static int parse_events__scanner(const char *str, void *data, int start_token);
+
+static int parse_events_fixup(int ret, const char *str, void *data,
+			      int start_token)
+{
+	char *o = strdup(str);
+	char *s = NULL;
+	char *t = o;
+	char *p;
+	int len = 0;
+
+	if (!o)
+		return ret;
+	while ((p = strsep(&t, ",")) != NULL) {
+		if (s)
+			str_append(&s, &len, ",");
+		str_append(&s, &len, "cpu/");
+		str_append(&s, &len, p);
+		str_append(&s, &len, "/");
+	}
+	free(o);
+	if (!s)
+		return -ENOMEM;
+	return parse_events__scanner(s, data, start_token);
+}
+
 static int parse_events__scanner(const char *str, void *data, int start_token)
 {
 	YY_BUFFER_STATE buffer;
@@ -854,7 +880,9 @@ static int parse_events__scanner(const char *str, void *data, int start_token)
 	parse_events__flush_buffer(buffer, scanner);
 	parse_events__delete_buffer(buffer, scanner);
 	parse_events_lex_destroy(scanner);
-	return ret;
+	if (ret && !strchr(str, '/'))
+		ret = parse_events_fixup(ret, str, data, start_token);
+ 	return ret;
 }
 
 /*
diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c
index 29c7b2c..fce558b 100644
--- a/tools/perf/util/string.c
+++ b/tools/perf/util/string.c
@@ -387,3 +387,28 @@ void *memdup(const void *src, size_t len)
 
 	return p;
 }
+
+/**
+ * str_append - reallocate string and append another
+ * @s: pointer to string pointer
+ * @len: pointer to len (initialized)
+ * @a: string to append.
+ * Also allow the caller to mishandle unhandleable errors.
+ */
+int str_append(char **s, int *len, const char *a)
+{
+	int olen = *s ? strlen(*s) : 0;
+	int nlen = olen + strlen(a) + 1;
+	if (*len < nlen) {
+		*len = *len * 2;
+		if (*len < nlen)
+			*len = nlen;
+		*s = realloc(*s, *len);
+		if (!*s)
+			return -ENOMEM;
+		if (olen == 0)
+			**s = 0;
+	}
+	strcat(*s, a);
+	return 0;
+}
-- 
1.7.7.6

[PATCH 18/18] perf, tools: List kernel supplied event aliases in perf list v3

[Andi Kleen]

From: Andi Kleen <ak@linux.intel.com>

List the kernel supplied pmu event aliases in perf list

It's better when the users can actually see them.

v2: Fix pattern matching
v3: perf_pmu__alias -> perf_pmu_alias
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
 tools/perf/Documentation/perf-list.txt |    4 +-
 tools/perf/builtin-list.c              |    3 +
 tools/perf/util/parse-events.c         |    5 ++-
 tools/perf/util/pmu.c                  |   73 ++++++++++++++++++++++++++++++++
 tools/perf/util/pmu.h                  |    3 +
 5 files changed, 86 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index d1e39dc..826f3d6 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -8,7 +8,7 @@ perf-list - List all symbolic event types
 SYNOPSIS
 --------
 [verse]
-'perf list' [hw|sw|cache|tracepoint|event_glob]
+'perf list' [hw|sw|cache|tracepoint|pmu|event_glob]
 
 DESCRIPTION
 -----------
@@ -104,6 +104,8 @@ To limit the list use:
   'subsys_glob:event_glob' to filter by tracepoint subsystems such as sched,
   block, etc.
 
+. 'pmu' to print the kernel supplied PMU events.
+
 . If none of the above is matched, it will apply the supplied glob to all
   events, printing the ones that match.
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 1948ece..e79f423 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -13,6 +13,7 @@
 
 #include "util/parse-events.h"
 #include "util/cache.h"
+#include "util/pmu.h"
 
 int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 {
@@ -37,6 +38,8 @@ int cmd_list(int argc, const char **argv, const char *prefix __maybe_unused)
 			else if (strcmp(argv[i], "cache") == 0 ||
 				 strcmp(argv[i], "hwcache") == 0)
 				print_hwcache_events(NULL, false);
+			else if (strcmp(argv[i], "pmu") == 0)
+				print_pmu_events(NULL, false);
 			else if (strcmp(argv[i], "--raw-dump") == 0)
 				print_events(NULL, true);
 			else {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 7c1250f..700a3a5 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1119,6 +1119,8 @@ int print_hwcache_events(const char *event_glob, bool name_only)
 		}
 	}
 
+	if (printed)
+		printf("\n");
 	return printed;
 }
 
@@ -1173,11 +1175,12 @@ void print_events(const char *event_glob, bool name_only)
 
 	print_hwcache_events(event_glob, name_only);
 
+	print_pmu_events(event_glob, name_only);
+
 	if (event_glob != NULL)
 		return;
 
 	if (!name_only) {
-		printf("\n");
 		printf("  %-50s [%s]\n",
 		       "rNNN",
 		       event_type_descriptors[PERF_TYPE_RAW]);
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 4c6f9c4..8945726 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -564,3 +564,76 @@ void perf_pmu__set_format(unsigned long *bits, long from, long to)
 	for (b = from; b <= to; b++)
 		set_bit(b, bits);
 }
+
+static char *format_alias(char *buf, int len, struct perf_pmu *pmu,
+			  struct perf_pmu_alias *alias)
+{
+	snprintf(buf, len, "%s/%s/", pmu->name, alias->name);
+	return buf;
+}
+
+static char *format_alias_or(char *buf, int len, struct perf_pmu *pmu,
+			     struct perf_pmu_alias *alias)
+{
+	snprintf(buf, len, "%s OR %s/%s/", alias->name, pmu->name, alias->name);
+	return buf;
+}
+
+static int cmp_string(const void *a, const void *b)
+{
+	const char * const *as = a;
+	const char * const *bs = b;
+	return strcmp(*as, *bs);
+}
+
+void print_pmu_events(const char *event_glob, bool name_only)
+{
+	struct perf_pmu *pmu;
+	struct perf_pmu_alias *alias;
+	char buf[1024];
+	int printed = 0;
+	int len, j;
+	char **aliases;
+
+	pmu = NULL;
+	len = 0;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+		list_for_each_entry (alias, &pmu->aliases, list)
+			len++;
+	aliases = malloc(sizeof(char *) * len);
+	if (!aliases)
+		return;
+	pmu = NULL;
+	j = 0;
+	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+		list_for_each_entry (alias, &pmu->aliases, list) {
+			char *name = format_alias(buf, sizeof buf, pmu, alias);
+			bool is_cpu = !strcmp(pmu->name, "cpu");
+
+			if (event_glob != NULL &&
+			    !(strglobmatch(name, event_glob) ||
+			      (!is_cpu && strglobmatch(alias->name, event_glob))))
+				continue;
+			aliases[j] = name;
+			if (is_cpu && !name_only)
+				aliases[j] = format_alias_or(buf, sizeof buf,
+							      pmu, alias);
+			aliases[j] = strdup(aliases[j]);
+			j++;
+		}
+	len = j;
+	qsort(aliases, len, sizeof(char *), cmp_string);
+	for (j = 0; j < len; j++) {
+		if (name_only) {
+			printf("%s ", aliases[j]);
+			continue;
+		}
+		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
+		free(aliases[j]);
+		printed++;
+	}
+	if (printed)
+		printf("\n");
+	free(aliases);
+}
+
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index 32fe55b..20d7494 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -3,6 +3,7 @@
 
 #include <linux/bitops.h>
 #include <linux/perf_event.h>
+#include <stdbool.h>
 
 enum {
 	PERF_PMU_FORMAT_VALUE_CONFIG,
@@ -40,5 +41,7 @@ int perf_pmu__format_parse(char *dir, struct list_head *head);
 
 struct perf_pmu *perf_pmu__scan(struct perf_pmu *pmu);
 
+void print_pmu_events(const char *event_glob, bool name_only);
+
 int perf_pmu__test(void);
 #endif /* __PMU_H */
-- 
1.7.7.6