[PATCH v4 0/6] perf: add ability to sample interrupted machine state

[PATCH v4 0/6] perf: add ability to sample interrupted machine state

[Stephane Eranian]

This short patch series add the ability to sample the interrupted
machine state for each hardware sample. This is useful to analyze
the state after certain events, for instance for function value
profiling after a call instruction.

The patch extends the interface with a new PERF_SAMPLE_REGS_INTR 
smaple_type flag. The register to sample can be named in the
sample_regs_intr bitmask for each event. The name and bit
position for each register is architecture dependent and
provided, just like for PERF_SAMPLE_REGS_USER by asm/perf_regs.h.

The support is similar to PERF_SAMPLE_REGS_USER.

On Intel x86, the series includes support for capturing the
PEBS state as well. When precise sampling is used, the interrupted
state is collect from the PEBS records, at least partially.
The PEBS machine state is a subset of the machine state.

The series provides access to this new feature in perf record
with the -I option. It is possible to display the sampled
register values using perf report -D.

This patch series is the fundation for a future series adding
function value profiling.

In V2, we address the issues raised during reviews:
 - add sample parsing test
 - shorten perf record option to --intr-regs
 - added man page for perf record -I/--intr-regs option
 - refactor register printf code between user and intr regs
 - rebase to v3.16-rc3

In V3, we rebase to 3.16.0+ and made the modifications suggested
by PeterZ. We also integrated his patch to improve the layout
of perf_sample_data.

In V4, we rebase to 3.17-rc3 and we fix the ABI change issue 
reported by Namhyung Kim.

Peter Zijlstra (1):
  perf: improve perf_sample_data struct layout

Stephane Eranian (5):
  perf: add ability to sample machine state on interrupt
  perf/x86: add support for sampling PEBS machine state registers
  perf tools: add core support for sampling intr machine state regs
  perf/tests: add interrupted state sample parsing test
  perf record: add new -I option to sample interrupted machine state

 arch/x86/kernel/cpu/perf_event_intel_ds.c |   17 +++++++++
 include/linux/perf_event.h                |   37 ++++++++++---------
 include/uapi/linux/perf_event.h           |   15 +++++++-
 kernel/events/core.c                      |   49 +++++++++++++++++++++++--
 tools/perf/Documentation/perf-record.txt  |    6 ++++
 tools/perf/builtin-record.c               |    2 ++
 tools/perf/perf.h                         |    1 +
 tools/perf/tests/sample-parsing.c         |   55 +++++++++++++++++++++--------
 tools/perf/util/event.h                   |    1 +
 tools/perf/util/evsel.c                   |   46 +++++++++++++++++++++++-
 tools/perf/util/header.c                  |    1 +
 tools/perf/util/session.c                 |   44 ++++++++++++++++++++---
 12 files changed, 232 insertions(+), 42 deletions(-)

-- 
1.7.9.5

[PATCH v4 1/6] perf: add ability to sample machine state on interrupt

[Stephane Eranian]

Enable capture of interrupted machine state for each
sample.

Registers to sample are passed per event in the
sample_regs_intr bitmask.

To sample interrupt machine state, the
PERF_SAMPLE_INTR_REGS must be passed in
sample_type.

The list of available registers is arch
dependent and provided by asm/perf_regs.h

Registers are laid out as u64 in the order
of the bit order of sample_intr_regs.

This patch also adds a new ABI version
PERF_ATTR_SIZE_VER4 because we extend
the perf_event_attr struct with a new u64
field.

Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Stephane Eranian <eranian@google.com>
---
 include/linux/perf_event.h      |    7 +++++--
 include/uapi/linux/perf_event.h |   15 ++++++++++++-
 kernel/events/core.c            |   44 +++++++++++++++++++++++++++++++++++++--
 3 files changed, 61 insertions(+), 5 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 893a0d0..68d46d5 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,7 +79,7 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs_user {
+struct perf_regs {
 	__u64		abi;
 	struct pt_regs	*regs;
 };
@@ -600,7 +600,8 @@ struct perf_sample_data {
 	struct perf_callchain_entry	*callchain;
 	struct perf_raw_record		*raw;
 	struct perf_branch_stack	*br_stack;
-	struct perf_regs_user		regs_user;
+	struct perf_regs		regs_user;
+	struct perf_regs		regs_intr;
 	u64				stack_user_size;
 	u64				weight;
 	/*
@@ -630,6 +631,8 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
+	data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE;
+	data->regs_intr.regs = NULL;
 }
 
 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 9269de2..f70f345 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 
-	PERF_SAMPLE_MAX = 1U << 18,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
 };
 
 /*
@@ -238,6 +239,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
 #define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
 					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -334,6 +336,15 @@ struct perf_event_attr {
 
 	/* Align to u64. */
 	__u32	__reserved_2;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
 };
 
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))
@@ -686,6 +697,8 @@ enum perf_event_type {
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 * 	{ u64			abi; # enum perf_sample_regs_abi
+	 * 	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 01bd42e..7459b02 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4421,7 +4421,7 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 	}
 }
 
-static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+static void perf_sample_regs_user(struct perf_regs *regs_user,
 				  struct pt_regs *regs)
 {
 	if (!user_mode(regs)) {
@@ -4437,6 +4437,14 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
 	}
 }
 
+static void perf_sample_regs_intr(struct perf_regs *regs_intr,
+				  struct pt_regs *regs)
+{
+	regs_intr->regs = regs;
+	regs_intr->abi  = perf_reg_abi(current);
+}
+
+
 /*
  * Get remaining task size from user stack pointer.
  *
@@ -4818,6 +4826,22 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		perf_output_put(handle, data->txn);
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		u64 abi = data->regs_intr.abi;
+		/*
+		 * If there are no regs to dump, notice it through
+		 * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+		 */
+		perf_output_put(handle, abi);
+
+		if (abi) {
+			u64 mask = event->attr.sample_regs_intr;
+			perf_output_sample_regs(handle,
+						data->regs_intr.regs,
+						mask);
+		}
+	}
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
@@ -4904,7 +4928,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.
 		 */
-		struct perf_regs_user *uregs = &data->regs_user;
+		struct perf_regs *uregs = &data->regs_user;
 		u16 stack_size = event->attr.sample_stack_user;
 		u16 size = sizeof(u64);
 
@@ -4925,6 +4949,20 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->stack_user_size = stack_size;
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		/* regs dump ABI info */
+		int size = sizeof(u64);
+
+		perf_sample_regs_intr(&data->regs_intr, regs);
+
+		if (data->regs_intr.regs) {
+			u64 mask = event->attr.sample_regs_intr;
+			size += hweight64(mask) * sizeof(u64);
+		}
+
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -7125,6 +7163,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			ret = -EINVAL;
 	}
 
+	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
+		ret = perf_reg_validate(attr->sample_regs_intr);
 out:
 	return ret;
 
-- 
1.7.9.5

[PATCH v4 2/6] perf/x86: add support for sampling PEBS machine state registers

[Stephane Eranian]

PEBS can capture machine state regs at retiremnt of the sampled
instructions. When precise sampling is enabled on an event, PEBS
is used, so substitute the interrupted state with the PEBS state.
Note that not all registers are captured by PEBS. Those missing
are replaced by the interrupt state counter-parts.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c |   17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 9dc4199..139a8a5 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -886,6 +886,23 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	regs.bp = pebs->bp;
 	regs.sp = pebs->sp;
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		regs.ax = pebs->ax;
+		regs.bx = pebs->bx;
+		regs.cx = pebs->cx;
+		regs.si = pebs->si;
+		regs.di = pebs->di;
+
+		regs.r8 = pebs->r8;
+		regs.r9 = pebs->r9;
+		regs.r10 = pebs->r10;
+		regs.r11 = pebs->r11;
+		regs.r12 = pebs->r12;
+		regs.r13 = pebs->r13;
+		regs.r14 = pebs->r14;
+		regs.r14 = pebs->r15;
+	}
+
 	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
 		regs.ip = pebs->real_ip;
 		regs.flags |= PERF_EFLAGS_EXACT;
-- 
1.7.9.5

Re: [PATCH v4 2/6] perf/x86: add support for sampling PEBS machine state registers

[Chuck Ebbert]

On Wed,  3 Sep 2014 16:59:07 +0200
Stephane Eranian <eranian@google.com> wrote:

> PEBS can capture machine state regs at retiremnt of the sampled
> instructions. When precise sampling is enabled on an event, PEBS
> is used, so substitute the interrupted state with the PEBS state.
> Note that not all registers are captured by PEBS. Those missing
> are replaced by the interrupt state counter-parts.
> 
> Signed-off-by: Stephane Eranian <eranian@google.com>
> ---
>  arch/x86/kernel/cpu/perf_event_intel_ds.c |   17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 
> diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c
> b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 9dc4199..139a8a5
> 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> @@ -886,6 +886,23 @@ static void __intel_pmu_pebs_event(struct
> perf_event *event, regs.bp = pebs->bp;
>  	regs.sp = pebs->sp;
>  
> +	if (sample_type & PERF_SAMPLE_REGS_INTR) {
> +		regs.ax = pebs->ax;
> +		regs.bx = pebs->bx;
> +		regs.cx = pebs->cx;
> +		regs.si = pebs->si;
> +		regs.di = pebs->di;
> +
> +		regs.r8 = pebs->r8;
> +		regs.r9 = pebs->r9;
> +		regs.r10 = pebs->r10;
> +		regs.r11 = pebs->r11;
> +		regs.r12 = pebs->r12;
> +		regs.r13 = pebs->r13;
> +		regs.r14 = pebs->r14;
> +		regs.r14 = pebs->r15;
   		     ^^^
   		     r15 ???

> +	}
> +
>  	if (event->attr.precise_ip > 1 &&
> x86_pmu.intel_cap.pebs_format >= 2) { regs.ip = pebs->real_ip;
>  		regs.flags |= PERF_EFLAGS_EXACT;

Re: [PATCH v4 2/6] perf/x86: add support for sampling PEBS machine state registers

[Stephane Eranian]

On Fri, Sep 5, 2014 at 4:16 AM, Chuck Ebbert <cebbert.lkml@gmail.com> wrote:
> On Wed,  3 Sep 2014 16:59:07 +0200
> Stephane Eranian <eranian@google.com> wrote:
>
>> PEBS can capture machine state regs at retiremnt of the sampled
>> instructions. When precise sampling is enabled on an event, PEBS
>> is used, so substitute the interrupted state with the PEBS state.
>> Note that not all registers are captured by PEBS. Those missing
>> are replaced by the interrupt state counter-parts.
>>
>> Signed-off-by: Stephane Eranian <eranian@google.com>
>> ---
>>  arch/x86/kernel/cpu/perf_event_intel_ds.c |   17 +++++++++++++++++
>>  1 file changed, 17 insertions(+)
>>
>> diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c
>> b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 9dc4199..139a8a5
>> 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
>> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
>> @@ -886,6 +886,23 @@ static void __intel_pmu_pebs_event(struct
>> perf_event *event, regs.bp = pebs->bp;
>>       regs.sp = pebs->sp;
>>
>> +     if (sample_type & PERF_SAMPLE_REGS_INTR) {
>> +             regs.ax = pebs->ax;
>> +             regs.bx = pebs->bx;
>> +             regs.cx = pebs->cx;
>> +             regs.si = pebs->si;
>> +             regs.di = pebs->di;
>> +
>> +             regs.r8 = pebs->r8;
>> +             regs.r9 = pebs->r9;
>> +             regs.r10 = pebs->r10;
>> +             regs.r11 = pebs->r11;
>> +             regs.r12 = pebs->r12;
>> +             regs.r13 = pebs->r13;
>> +             regs.r14 = pebs->r14;
>> +             regs.r14 = pebs->r15;
>                      ^^^
>                      r15 ???
>
Oops, good catch. I will fix in v5.
Thanks.

>> +     }
>> +
>>       if (event->attr.precise_ip > 1 &&
>> x86_pmu.intel_cap.pebs_format >= 2) { regs.ip = pebs->real_ip;
>>               regs.flags |= PERF_EFLAGS_EXACT;
>

Re: [PATCH v4 2/6] perf/x86: add support for sampling PEBS machine state registers

[Ingo Molnar]

* Stephane Eranian <eranian@google.com> wrote:

> PEBS can capture machine state regs at retiremnt of the sampled
> instructions. When precise sampling is enabled on an event, PEBS
> is used, so substitute the interrupted state with the PEBS state.
> Note that not all registers are captured by PEBS. Those missing
> are replaced by the interrupt state counter-parts.
> 
> Signed-off-by: Stephane Eranian <eranian@google.com>
> ---
>  arch/x86/kernel/cpu/perf_event_intel_ds.c |   17 +++++++++++++++++
>  1 file changed, 17 insertions(+)
> 
> diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> index 9dc4199..139a8a5 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> @@ -886,6 +886,23 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
>  	regs.bp = pebs->bp;
>  	regs.sp = pebs->sp;
>  
> +	if (sample_type & PERF_SAMPLE_REGS_INTR) {
> +		regs.ax = pebs->ax;
> +		regs.bx = pebs->bx;
> +		regs.cx = pebs->cx;
> +		regs.si = pebs->si;
> +		regs.di = pebs->di;
> +
> +		regs.r8 = pebs->r8;
> +		regs.r9 = pebs->r9;
> +		regs.r10 = pebs->r10;
> +		regs.r11 = pebs->r11;
> +		regs.r12 = pebs->r12;
> +		regs.r13 = pebs->r13;
> +		regs.r14 = pebs->r14;
> +		regs.r14 = pebs->r15;

Beyond regs.r15, is pebs->dx left out on purpose? It's part of 
pebs_record_hsw so presumably the hardware fills it in.

Thanks,

	Ingo

Re: [PATCH v4 2/6] perf/x86: add support for sampling PEBS machine state registers

[Stephane Eranian]

On Fri, Sep 5, 2014 at 12:35 PM, Ingo Molnar <mingo@kernel.org> wrote:
>
> * Stephane Eranian <eranian@google.com> wrote:
>
>> PEBS can capture machine state regs at retiremnt of the sampled
>> instructions. When precise sampling is enabled on an event, PEBS
>> is used, so substitute the interrupted state with the PEBS state.
>> Note that not all registers are captured by PEBS. Those missing
>> are replaced by the interrupt state counter-parts.
>>
>> Signed-off-by: Stephane Eranian <eranian@google.com>
>> ---
>>  arch/x86/kernel/cpu/perf_event_intel_ds.c |   17 +++++++++++++++++
>>  1 file changed, 17 insertions(+)
>>
>> diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
>> index 9dc4199..139a8a5 100644
>> --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
>> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
>> @@ -886,6 +886,23 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
>>       regs.bp = pebs->bp;
>>       regs.sp = pebs->sp;
>>
>> +     if (sample_type & PERF_SAMPLE_REGS_INTR) {
>> +             regs.ax = pebs->ax;
>> +             regs.bx = pebs->bx;
>> +             regs.cx = pebs->cx;
>> +             regs.si = pebs->si;
>> +             regs.di = pebs->di;
>> +
>> +             regs.r8 = pebs->r8;
>> +             regs.r9 = pebs->r9;
>> +             regs.r10 = pebs->r10;
>> +             regs.r11 = pebs->r11;
>> +             regs.r12 = pebs->r12;
>> +             regs.r13 = pebs->r13;
>> +             regs.r14 = pebs->r14;
>> +             regs.r14 = pebs->r15;
>
> Beyond regs.r15, is pebs->dx left out on purpose? It's part of
> pebs_record_hsw so presumably the hardware fills it in.
>
Yep, will fix that one too in v5.

[PATCH v4 3/6] perf tools: add core support for sampling intr machine state regs

[Stephane Eranian]

Add the infrastructure to setup, collect and report the interrupt
machine state regs which can be captured by the kernel.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 tools/perf/perf.h         |    1 +
 tools/perf/util/event.h   |    1 +
 tools/perf/util/evsel.c   |   46 ++++++++++++++++++++++++++++++++++++++++++++-
 tools/perf/util/header.c  |    1 +
 tools/perf/util/session.c |   44 ++++++++++++++++++++++++++++++++++++++-----
 5 files changed, 87 insertions(+), 6 deletions(-)

diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 510c65f..309d956 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -54,6 +54,7 @@ struct record_opts {
 	bool	     sample_weight;
 	bool	     sample_time;
 	bool	     period;
+	bool	     sample_intr_regs;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 7eb7107..d6e79f3 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -162,6 +162,7 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
 	struct regs_dump  user_regs;
+	struct regs_dump  intr_regs;
 	struct stack_dump user_stack;
 	struct sample_read read;
 };
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index b38de58..5c2e784 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -628,6 +628,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 	if (opts->call_graph_enabled && !evsel->no_aux_samples)
 		perf_evsel__config_callgraph(evsel, opts);
 
+	if (opts->sample_intr_regs) {
+		attr->sample_regs_intr = PERF_REGS_MASK;
+		perf_evsel__set_sample_bit(evsel, REGS_INTR);
+	}
+
 	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
 
@@ -1005,6 +1010,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 	ret += PRINT_ATTR_X64(branch_sample_type);
 	ret += PRINT_ATTR_X64(sample_regs_user);
 	ret += PRINT_ATTR_U32(sample_stack_user);
+	ret += PRINT_ATTR_X64(sample_regs_intr);
 
 	ret += fprintf(fp, "%.60s\n", graph_dotted_line);
 
@@ -1504,6 +1510,23 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		OVERFLOW_CHECK_u64(array);
+		data->intr_regs.abi = *array;
+		array++;
+
+		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
+			u64 mask = evsel->attr.sample_regs_intr;
+
+			sz = hweight_long(mask) * sizeof(u64);
+			OVERFLOW_CHECK(array, sz, max_size);
+			data->intr_regs.mask = mask;
+			data->intr_regs.regs = (u64 *)array;
+			array = (void *)array + sz;
+		}
+	}
+
 	return 0;
 }
 
@@ -1599,6 +1622,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_TRANSACTION)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
 	return result;
 }
 
@@ -1777,6 +1810,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			*array++ = sample->intr_regs.abi;
+			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			memcpy(array, sample->intr_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
 	return 0;
 }
 
@@ -1906,7 +1950,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
 		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
-		bit_name(IDENTIFIER),
+		bit_name(IDENTIFIER), bit_name(REGS_INTR),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 158c787..62514a7 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2458,6 +2458,7 @@ static const int attr_file_abi_sizes[] = {
 	[1] = PERF_ATTR_SIZE_VER1,
 	[2] = PERF_ATTR_SIZE_VER2,
 	[3] = PERF_ATTR_SIZE_VER3,
+	[4] = PERF_ATTR_SIZE_VER4,
 	0,
 };
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6d2d50d..4eb8ca6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -581,15 +581,46 @@ static void regs_dump__printf(u64 mask, u64 *regs)
 	}
 }
 
+static const char *regs_abi[]= {
+ [PERF_SAMPLE_REGS_ABI_NONE] = "none",
+ [PERF_SAMPLE_REGS_ABI_32] = "32-bit",
+ [PERF_SAMPLE_REGS_ABI_64] = "64-bit",
+};
+
+static inline const char *regs_dump_abi(struct regs_dump *d)
+{
+	if (d->abi > PERF_SAMPLE_REGS_ABI_64)
+		return "unknown";
+
+	return regs_abi[d->abi];
+}
+
+static void regs__printf(const char *type, struct regs_dump *regs)
+{
+	u64 mask = regs->mask;
+
+	printf("... %s regs: mask 0x%" PRIx64 " ABI %s\n",
+	       type,
+	       mask,
+	       regs_dump_abi(regs));
+
+	regs_dump__printf(mask, regs->regs);
+}
+
 static void regs_user__printf(struct perf_sample *sample)
 {
 	struct regs_dump *user_regs = &sample->user_regs;
 
-	if (user_regs->regs) {
-		u64 mask = user_regs->mask;
-		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
-		regs_dump__printf(mask, user_regs->regs);
-	}
+	if (user_regs->regs)
+		regs__printf("user", user_regs);
+}
+
+static void regs_intr__printf(struct perf_sample *sample)
+{
+	struct regs_dump *intr_regs = &sample->intr_regs;
+
+	if (intr_regs->regs)
+		regs__printf("intr", intr_regs);
 }
 
 static void stack_user__printf(struct stack_dump *dump)
@@ -688,6 +719,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample);
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR)
+		regs_intr__printf(sample);
+
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
 
-- 
1.7.9.5

[PATCH v4 4/6] perf/tests: add interrupted state sample parsing test

[Stephane Eranian]

This patch updates the sample parsing test with support
for the sampling of machine interrupted state.

The patch modifies the do_test() code to sahred the sample
regts bitmask between user and intr regs.

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 tools/perf/tests/sample-parsing.c |   55 +++++++++++++++++++++++++++----------
 1 file changed, 40 insertions(+), 15 deletions(-)

diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index ca292f9..4908c64 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -126,16 +126,28 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_TRANSACTION)
 		COMP(transaction);
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64);
+
+		COMP(intr_regs.mask);
+		COMP(intr_regs.abi);
+		if (s1->intr_regs.abi &&
+		    (!s1->intr_regs.regs || !s2->intr_regs.regs ||
+		     memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) {
+			pr_debug("Samples differ at 'intr_regs'\n");
+			return false;
+		}
+	}
+
 	return true;
 }
 
-static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 {
 	struct perf_evsel evsel = {
 		.needs_swap = false,
 		.attr = {
 			.sample_type = sample_type,
-			.sample_regs_user = sample_regs_user,
 			.read_format = read_format,
 		},
 	};
@@ -154,7 +166,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		/* 1 branch_entry */
 		.data = {1, 211, 212, 213},
 	};
-	u64 user_regs[64];
+	u64 regs[64];
 	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
 	const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
 	struct perf_sample sample = {
@@ -176,8 +188,8 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		.branch_stack	= &branch_stack.branch_stack,
 		.user_regs	= {
 			.abi	= PERF_SAMPLE_REGS_ABI_64,
-			.mask	= sample_regs_user,
-			.regs	= user_regs,
+			.mask	= sample_regs,
+			.regs	= regs,
 		},
 		.user_stack	= {
 			.size	= sizeof(data),
@@ -187,14 +199,25 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 			.time_enabled = 0x030a59d664fca7deULL,
 			.time_running = 0x011b6ae553eb98edULL,
 		},
+		.intr_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs,
+			.regs	= regs,
+		},
 	};
 	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
 	struct perf_sample sample_out;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
 
-	for (i = 0; i < sizeof(user_regs); i++)
-		*(i + (u8 *)user_regs) = i & 0xfe;
+	if (sample_type & PERF_SAMPLE_REGS_USER)
+		evsel.attr.sample_regs_user = sample_regs;
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR)
+		evsel.attr.sample_regs_intr = sample_regs;
+
+	for (i = 0; i < sizeof(regs); i++)
+		*(i + (u8 *)regs) = i & 0xfe;
 
 	if (read_format & PERF_FORMAT_GROUP) {
 		sample.read.group.nr     = 4;
@@ -271,7 +294,7 @@ int test__sample_parsing(void)
 {
 	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
 	u64 sample_type;
-	u64 sample_regs_user;
+	u64 sample_regs;
 	size_t i;
 	int err;
 
@@ -280,7 +303,7 @@ int test__sample_parsing(void)
 	 * were added.  Please actually update the test rather than just change
 	 * the condition below.
 	 */
-	if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}
@@ -297,22 +320,24 @@ int test__sample_parsing(void)
 			}
 			continue;
 		}
+		sample_regs = 0;
 
 		if (sample_type == PERF_SAMPLE_REGS_USER)
-			sample_regs_user = 0x3fff;
-		else
-			sample_regs_user = 0;
+			sample_regs = 0x3fff;
+
+		if (sample_type == PERF_SAMPLE_REGS_INTR)
+			sample_regs = 0xff0fff;
 
-		err = do_test(sample_type, sample_regs_user, 0);
+		err = do_test(sample_type, sample_regs, 0);
 		if (err)
 			return err;
 	}
 
 	/* Test all sample format bits together */
 	sample_type = PERF_SAMPLE_MAX - 1;
-	sample_regs_user = 0x3fff;
+	sample_regs = 0x3fff; /* shared yb intr and user regs */
 	for (i = 0; i < ARRAY_SIZE(rf); i++) {
-		err = do_test(sample_type, sample_regs_user, rf[i]);
+		err = do_test(sample_type, sample_regs, rf[i]);
 		if (err)
 			return err;
 	}
-- 
1.7.9.5

[PATCH v4 5/6] perf record: add new -I option to sample interrupted machine state

[Stephane Eranian]

Add -I/--intr-regs option to capture machine state registers at
interrupt.

Add the corresponding man page description

Signed-off-by: Stephane Eranian <eranian@google.com>
---
 tools/perf/Documentation/perf-record.txt |    6 ++++++
 tools/perf/builtin-record.c              |    2 ++
 2 files changed, 8 insertions(+)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d460049..1a36259 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -214,6 +214,12 @@ if combined with -a or -C options.
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
+-I::
+--intr-regs::
+Capture machine state (registers) at interrupt, i.e., on counter overflows for
+each sample. List of captured registers depends on the architecture. This option
+is off by default.
+
 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 87e28a4..27378d5 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -883,6 +883,8 @@ const struct option record_options[] = {
 		    "sample transaction flags (special events only)"),
 	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
 		    "use per-thread mmaps"),
+	OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
+		    "Sample machine registers on interrupt"),
 	OPT_END()
 };
 
-- 
1.7.9.5

[PATCH v4 6/6] perf: improve perf_sample_data struct layout

[Stephane Eranian]

From: Peter Zijlstra <peterz@infradead.org>

This patch reorders fields in the perf_sample_data
struct in order to minimize the number of cachelines
touched in perf_sample_data_init(). It also removes
some intializations which are redundant with the
code in kernel/events/core.c

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
---
 include/linux/perf_event.h |   34 +++++++++++++++++-----------------
 kernel/events/core.c       |    5 ++++-
 2 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 68d46d5..486e84c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -580,35 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event,
 
 
 struct perf_sample_data {
-	u64				type;
+	/*
+	 * Fields set by perf_sample_data_init(), group so as to
+	 * minimize the cachelines touched.
+	 */
+	u64				addr;
+	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
+	u64				period;
+	u64				weight;
+	u64				txn;
+	union  perf_mem_data_src	data_src;
 
+	/*
+	 * The other fields, optionally {set,used} by
+	 * perf_{prepare,output}_sample().
+	 */
+	u64				type;
 	u64				ip;
 	struct {
 		u32	pid;
 		u32	tid;
 	}				tid_entry;
 	u64				time;
-	u64				addr;
 	u64				id;
 	u64				stream_id;
 	struct {
 		u32	cpu;
 		u32	reserved;
 	}				cpu_entry;
-	u64				period;
-	union  perf_mem_data_src	data_src;
 	struct perf_callchain_entry	*callchain;
-	struct perf_raw_record		*raw;
-	struct perf_branch_stack	*br_stack;
 	struct perf_regs		regs_user;
 	struct perf_regs		regs_intr;
 	u64				stack_user_size;
-	u64				weight;
-	/*
-	 * Transaction flags for abort events:
-	 */
-	u64				txn;
-};
+} ____cacheline_aligned;
 
 /* default value for data source */
 #define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
@@ -625,14 +630,9 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->raw  = NULL;
 	data->br_stack = NULL;
 	data->period = period;
-	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_user.regs = NULL;
-	data->stack_user_size = 0;
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
-	data->regs_intr.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_intr.regs = NULL;
 }
 
 extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7459b02..575869d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4432,8 +4432,11 @@ static void perf_sample_regs_user(struct perf_regs *regs_user,
 	}
 
 	if (regs) {
-		regs_user->regs = regs;
 		regs_user->abi  = perf_reg_abi(current);
+		regs_user->regs = regs;
+	} else {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
 	}
 }
 
-- 
1.7.9.5