[PATCH v6 0/7] perf, intel: Add support for PEBS output to Intel PT

[PATCH v6 0/7] perf, intel: Add support for PEBS output to Intel PT

[Alexander Shishkin]

Hi Peter,

Seventh attempt at the PEBS-via-PT feature. The previous ones were [1], [2],
[3], [4], [5], [6]. This one finalizes the 'aux_output' naming in the code.

The PEBS feature: output to Intel PT stream instead of the DS area. It's
theoretically useful in virtualized environments, where DS area can't be
used. It's also good for those who are interested in instruction trace for
context of the PEBS events. As PEBS goes, it can provide LBR context with
all the branch-related information that PT doesn't provide at the moment.

PEBS records are packetized in the PT stream, so instead of extracting
them in the PMI, we leave it to the perf tool, because real time PT
decoding is not practical.

[1] https://marc.info/?l=linux-kernel&m=155679423430002
[2] https://marc.info/?l=linux-kernel&m=156225605132606
[3] https://marc.info/?l=linux-kernel&m=156458152126310
[4] https://marc.info/?l=linux-kernel&m=156458348626999
[5] https://marc.info/?l=linux-kernel&m=156498939722450
[6] https://marc.info/?l=linux-kernel&m=156507654612681

Adrian Hunter (5):
  perf tools: Add aux_output attribute flag
  perf tools: Add itrace option 'o' to synthesize aux-output events
  perf intel-pt: Process options for PEBS event synthesis
  perf tools: Add aux-output config term
  perf intel-pt: Add brief documentation for PEBS via Intel PT

Alexander Shishkin (2):
  perf: Allow normal events to output AUX data
  perf/x86/intel: Support PEBS output to PT

 arch/x86/events/core.c                   | 34 +++++++++
 arch/x86/events/intel/core.c             | 18 +++++
 arch/x86/events/intel/ds.c               | 51 ++++++++++++-
 arch/x86/events/intel/pt.c               |  5 ++
 arch/x86/events/perf_event.h             | 17 +++++
 arch/x86/include/asm/intel_pt.h          |  2 +
 arch/x86/include/asm/msr-index.h         |  4 +
 include/linux/perf_event.h               | 14 ++++
 include/uapi/linux/perf_event.h          |  3 +-
 kernel/events/core.c                     | 93 ++++++++++++++++++++++++
 tools/include/uapi/linux/perf_event.h    |  3 +-
 tools/perf/Documentation/intel-pt.txt    | 15 ++++
 tools/perf/Documentation/itrace.txt      |  2 +
 tools/perf/Documentation/perf-record.txt |  2 +
 tools/perf/arch/x86/util/intel-pt.c      | 23 ++++++
 tools/perf/util/auxtrace.c               |  4 +
 tools/perf/util/auxtrace.h               |  3 +
 tools/perf/util/evsel.c                  |  4 +
 tools/perf/util/evsel.h                  |  2 +
 tools/perf/util/intel-pt.c               | 18 +++++
 tools/perf/util/parse-events.c           |  8 ++
 tools/perf/util/parse-events.h           |  1 +
 tools/perf/util/parse-events.l           |  1 +
 23 files changed, 324 insertions(+), 3 deletions(-)

-- 
2.20.1

[PATCH v6 1/7] perf: Allow normal events to output AUX data

[Alexander Shishkin]

In some cases, ordinary (non-AUX) events can generate data for AUX events.
For example, PEBS events can come out as records in the Intel PT stream
instead of their usual DS records, if configured to do so.

One requirement for such events is to consistently schedule together, to
ensure that the data from the "AUX output" events isn't lost while their
corresponding AUX event is not scheduled. We use grouping to provide this
guarantee: an "AUX output" event can be added to a group where an AUX event
is a group leader, and provided that the former supports writing to the
latter.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 include/linux/perf_event.h      | 14 +++++
 include/uapi/linux/perf_event.h |  3 +-
 kernel/events/core.c            | 93 +++++++++++++++++++++++++++++++++
 3 files changed, 109 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e8ad3c590a23..61448c19a132 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -246,6 +246,7 @@ struct perf_event;
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
 #define PERF_PMU_CAP_NO_EXCLUDE			0x80
+#define PERF_PMU_CAP_AUX_OUTPUT			0x100
 
 /**
  * struct pmu - generic performance monitoring unit
@@ -446,6 +447,16 @@ struct pmu {
 	void (*addr_filters_sync)	(struct perf_event *event);
 					/* optional */
 
+	/*
+	 * Check if event can be used for aux_output purposes for
+	 * events of this PMU.
+	 *
+	 * Runs from perf_event_open(). Should return 0 for "no match"
+	 * or non-zero for "match".
+	 */
+	int (*aux_output_match)		(struct perf_event *event);
+					/* optional */
+
 	/*
 	 * Filter events for PMU-specific reasons.
 	 */
@@ -681,6 +692,9 @@ struct perf_event {
 	struct perf_addr_filter_range	*addr_filter_ranges;
 	unsigned long			addr_filters_gen;
 
+	/* for aux_output events */
+	struct perf_event		*aux_event;
+
 	void (*destroy)(struct perf_event *);
 	struct rcu_head			rcu_head;
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7198ddd0c6b1..bb7b271397a6 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -374,7 +374,8 @@ struct perf_event_attr {
 				namespaces     :  1, /* include namespaces data */
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
-				__reserved_1   : 33;
+				aux_output     :  1, /* generate AUX records instead of events */
+				__reserved_1   : 32;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c1f52a749db2..1c414b8866b4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1887,6 +1887,89 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	ctx->generation++;
 }
 
+static int
+perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
+{
+	if (!has_aux(aux_event))
+		return 0;
+
+	if (!event->pmu->aux_output_match)
+		return 0;
+
+	return event->pmu->aux_output_match(aux_event);
+}
+
+static void put_event(struct perf_event *event);
+static void event_sched_out(struct perf_event *event,
+			    struct perf_cpu_context *cpuctx,
+			    struct perf_event_context *ctx);
+
+static void perf_put_aux_event(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct perf_event *iter;
+
+	/*
+	 * If event uses aux_event tear down the link
+	 */
+	if (event->aux_event) {
+		iter = event->aux_event;
+		event->aux_event = NULL;
+		put_event(iter);
+		return;
+	}
+
+	/*
+	 * If the event is an aux_event, tear down all links to
+	 * it from other events.
+	 */
+	for_each_sibling_event(iter, event->group_leader) {
+		if (iter->aux_event != event)
+			continue;
+
+		iter->aux_event = NULL;
+		put_event(event);
+
+		/*
+		 * If it's ACTIVE, schedule it out and put it into ERROR
+		 * state so that we don't try to schedule it again. Note
+		 * that perf_event_enable() will clear the ERROR status.
+		 */
+		event_sched_out(iter, cpuctx, ctx);
+		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+	}
+}
+
+static int perf_get_aux_event(struct perf_event *event,
+			      struct perf_event *group_leader)
+{
+	/*
+	 * Our group leader must be an aux event if we want to be
+	 * an aux_output. This way, the aux event will precede its
+	 * aux_output events in the group, and therefore will always
+	 * schedule first.
+	 */
+	if (!group_leader)
+		return 0;
+
+	if (!perf_aux_output_match(event, group_leader))
+		return 0;
+
+	if (!atomic_long_inc_not_zero(&group_leader->refcount))
+		return 0;
+
+	/*
+	 * Link aux_outputs to their aux event; this is undone in
+	 * perf_group_detach() by perf_put_aux_event(). When the
+	 * group in torn down, the aux_output events loose their
+	 * link to the aux_event and can't schedule any more.
+	 */
+	event->aux_event = group_leader;
+
+	return 1;
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *sibling, *tmp;
@@ -1902,6 +1985,8 @@ static void perf_group_detach(struct perf_event *event)
 
 	event->attach_state &= ~PERF_ATTACH_GROUP;
 
+	perf_put_aux_event(event);
+
 	/*
 	 * If this is a sibling, remove it from its group.
 	 */
@@ -10423,6 +10508,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_ns;
 	}
 
+	if (event->attr.aux_output &&
+	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+		err = -EOPNOTSUPP;
+		goto err_pmu;
+	}
+
 	err = exclusive_event_init(event);
 	if (err)
 		goto err_pmu;
@@ -11079,6 +11170,8 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (event->attr.aux_output && !perf_get_aux_event(event, group_leader))
+		goto err_locked;
 
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),
-- 
2.20.1

[PATCH v6 2/7] perf/x86/intel: Support PEBS output to PT

[Alexander Shishkin]

If PEBS declares ability to output its data to Intel PT stream, use the
aux_output attribute bit to enable PEBS data output to PT. This requires
a PT event to be present and scheduled in the same context. Unlike the
DS area, the kernel does not extract PEBS records from the PT stream to
generate corresponding records in the perf stream, because that would
require real time in-kernel PT decoding, which is not feasible. The PMI,
however, can still be used.

The output setting is per-CPU, so all PEBS events must be either writing
to PT or to the DS area, therefore, in case of conflict, the conflicting
event will fail to schedule, allowing the rotation logic to alternate
between the PEBS->PT and PEBS->DS events.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 arch/x86/events/core.c           | 34 +++++++++++++++++++++
 arch/x86/events/intel/core.c     | 18 +++++++++++
 arch/x86/events/intel/ds.c       | 51 +++++++++++++++++++++++++++++++-
 arch/x86/events/intel/pt.c       |  5 ++++
 arch/x86/events/perf_event.h     | 17 +++++++++++
 arch/x86/include/asm/intel_pt.h  |  2 ++
 arch/x86/include/asm/msr-index.h |  4 +++
 7 files changed, 130 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index cfe256ca76df..ab7846780385 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1005,6 +1005,27 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
+	if (!cpuc->n_events)
+		cpuc->pebs_output = 0;
+
+	if (!cpuc->is_fake && leader->attr.precise_ip) {
+		/*
+		 * For PEBS->PT, if !aux_event, the group leader (PT) went
+		 * away, the group was broken down and this singleton event
+		 * can't schedule any more.
+		 */
+		if (is_pebs_pt(leader) && !leader->aux_event)
+			return -EINVAL;
+
+		/*
+		 * pebs_output: 0: no PEBS so far, 1: PT, 2: DS
+		 */
+		if (cpuc->pebs_output &&
+		    cpuc->pebs_output != is_pebs_pt(leader) + 1)
+			return -EINVAL;
+
+		cpuc->pebs_output = is_pebs_pt(leader) + 1;
+	}
 
 	if (is_x86_event(leader)) {
 		if (n >= max_count)
@@ -2241,6 +2262,17 @@ static int x86_pmu_check_period(struct perf_event *event, u64 value)
 	return 0;
 }
 
+static int x86_pmu_aux_output_match(struct perf_event *event)
+{
+	if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT))
+		return 0;
+
+	if (x86_pmu.aux_output_match)
+		return x86_pmu.aux_output_match(event);
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2266,6 +2298,8 @@ static struct pmu pmu = {
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 	.check_period		= x86_pmu_check_period,
+
+	.aux_output_match	= x86_pmu_aux_output_match,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 648260b5f367..28459f4b795a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -18,6 +18,7 @@
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
 #include <asm/intel-family.h>
+#include <asm/intel_pt.h>
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
 
@@ -3298,6 +3299,13 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 	}
 
+	if (event->attr.aux_output) {
+		if (!event->attr.precise_ip)
+			return -EINVAL;
+
+		event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
@@ -3811,6 +3819,14 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value)
 	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
 }
 
+static int intel_pmu_aux_output_match(struct perf_event *event)
+{
+	if (!x86_pmu.intel_cap.pebs_output_pt_available)
+		return 0;
+
+	return is_intel_pt_event(event);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3935,6 +3951,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.sched_task		= intel_pmu_sched_task,
 
 	.check_period		= intel_pmu_check_period,
+
+	.aux_output_match	= intel_pmu_aux_output_match,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f1269e804e9b..ce83950036c5 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -902,6 +902,9 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
  */
 static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
 {
+	if (cpuc->n_pebs == cpuc->n_pebs_via_pt)
+		return false;
+
 	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
 }
 
@@ -919,6 +922,9 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 	u64 threshold;
 	int reserved;
 
+	if (cpuc->n_pebs_via_pt)
+		return;
+
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
 		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
 	else
@@ -1059,10 +1065,40 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	cpuc->n_pebs++;
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
+	if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT)
+		cpuc->n_pebs_via_pt++;
 
 	pebs_update_state(needed_cb, cpuc, event, true);
 }
 
+static void intel_pmu_pebs_via_pt_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!is_pebs_pt(event))
+		return;
+
+	if (!(cpuc->pebs_enabled & ~PEBS_VIA_PT_MASK))
+		cpuc->pebs_enabled &= ~PEBS_VIA_PT_MASK;
+}
+
+static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
+
+	if (!is_pebs_pt(event))
+		return;
+
+	if (!(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
+		cpuc->pebs_enabled |= PEBS_PMI_AFTER_EACH_RECORD;
+
+	cpuc->pebs_enabled |= PEBS_OUTPUT_PT;
+
+	wrmsrl(MSR_RELOAD_PMC0 + hwc->idx, ds->pebs_event_reset[hwc->idx]);
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1100,6 +1136,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
 	}
+
+	intel_pmu_pebs_via_pt_enable(event);
 }
 
 void intel_pmu_pebs_del(struct perf_event *event)
@@ -1111,6 +1149,8 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	cpuc->n_pebs--;
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
+	if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT)
+		cpuc->n_pebs_via_pt--;
 
 	pebs_update_state(needed_cb, cpuc, event, false);
 }
@@ -1120,7 +1160,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (cpuc->n_pebs == cpuc->n_large_pebs)
+	if (cpuc->n_pebs == cpuc->n_large_pebs &&
+	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
 		intel_pmu_drain_pebs_buffer();
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -1131,6 +1172,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
+	intel_pmu_pebs_via_pt_disable(event);
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -2031,6 +2074,12 @@ void __init intel_ds_init(void)
 					  PERF_SAMPLE_REGS_INTR);
 			}
 			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+
+			if (x86_pmu.intel_cap.pebs_output_pt_available) {
+				pr_cont("PEBS-via-PT, ");
+				x86_get_pmu()->capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+			}
+
 			break;
 
 		default:
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index d3dc2274ddd4..d58124d93e5f 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1481,6 +1481,11 @@ void cpu_emergency_stop_pt(void)
 		pt_event_stop(pt->handle.event, PERF_EF_UPDATE);
 }
 
+int is_intel_pt_event(struct perf_event *event)
+{
+	return event->pmu == &pt_pmu.pmu;
+}
+
 static __init int pt_init(void)
 {
 	int ret, cpu, prior_warn = 0;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8751008fc170..ecacfbf4ebc1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -76,6 +76,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
+#define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -85,6 +86,11 @@ struct amd_nb {
 };
 
 #define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
+#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60)
+#define PEBS_OUTPUT_OFFSET	61
+#define PEBS_OUTPUT_MASK	(3ull << PEBS_OUTPUT_OFFSET)
+#define PEBS_OUTPUT_PT		(1ull << PEBS_OUTPUT_OFFSET)
+#define PEBS_VIA_PT_MASK	(PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD)
 
 /*
  * Flags PEBS can handle without an PMI.
@@ -211,6 +217,8 @@ struct cpu_hw_events {
 	u64			pebs_enabled;
 	int			n_pebs;
 	int			n_large_pebs;
+	int			n_pebs_via_pt;
+	int			pebs_output;
 
 	/* Current super set of events hardware configuration */
 	u64			pebs_data_cfg;
@@ -510,6 +518,8 @@ union perf_capabilities {
 		 */
 		u64	full_width_write:1;
 		u64     pebs_baseline:1;
+		u64	pebs_metrics_available:1;
+		u64	pebs_output_pt_available:1;
 	};
 	u64	capabilities;
 };
@@ -692,6 +702,8 @@ struct x86_pmu {
 	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
 	 */
 	int (*check_period) (struct perf_event *event, u64 period);
+
+	int (*aux_output_match) (struct perf_event *event);
 };
 
 struct x86_perf_task_context {
@@ -901,6 +913,11 @@ static inline int amd_pmu_init(void)
 
 #endif /* CONFIG_CPU_SUP_AMD */
 
+static inline int is_pebs_pt(struct perf_event *event)
+{
+	return !!(event->hw.flags & PERF_X86_EVENT_PEBS_VIA_PT);
+}
+
 #ifdef CONFIG_CPU_SUP_INTEL
 
 static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
index 634f99b1dc22..423b788f495e 100644
--- a/arch/x86/include/asm/intel_pt.h
+++ b/arch/x86/include/asm/intel_pt.h
@@ -28,10 +28,12 @@ enum pt_capabilities {
 void cpu_emergency_stop_pt(void);
 extern u32 intel_pt_validate_hw_cap(enum pt_capabilities cap);
 extern u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities cap);
+extern int is_intel_pt_event(struct perf_event *event);
 #else
 static inline void cpu_emergency_stop_pt(void) {}
 static inline u32 intel_pt_validate_hw_cap(enum pt_capabilities cap) { return 0; }
 static inline u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability) { return 0; }
+static inline int is_intel_pt_event(struct perf_event *event) { return 0; }
 #endif
 
 #endif /* _ASM_X86_INTEL_PT_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 6b4fc2788078..03c42f08f063 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -375,6 +375,10 @@
 /* Alternative perfctr range with full access. */
 #define MSR_IA32_PMC0			0x000004c1
 
+/* Auto-reload via MSR instead of DS area */
+#define MSR_RELOAD_PMC0			0x000014c1
+#define MSR_RELOAD_FIXED_CTR0		0x00001309
+
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
 
-- 
2.20.1

[PATCH v6 3/7] perf tools: Add aux_output attribute flag

[Alexander Shishkin]

From: Adrian Hunter <adrian.hunter@intel.com>

Add aux_output attribute flag to match the kernel's perf_event.h file.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 tools/include/uapi/linux/perf_event.h | 3 ++-
 tools/perf/util/evsel.c               | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 7198ddd0c6b1..bb7b271397a6 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -374,7 +374,8 @@ struct perf_event_attr {
 				namespaces     :  1, /* include namespaces data */
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
-				__reserved_1   : 33;
+				aux_output     :  1, /* generate AUX records instead of events */
+				__reserved_1   : 32;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 52459dd5ad0c..9ec8782d3226 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1684,6 +1684,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(namespaces, p_unsigned);
 	PRINT_ATTRf(ksymbol, p_unsigned);
 	PRINT_ATTRf(bpf_event, p_unsigned);
+	PRINT_ATTRf(aux_output, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);
-- 
2.20.1

[PATCH v6 4/7] perf tools: Add itrace option 'o' to synthesize aux-output events

[Alexander Shishkin]

From: Adrian Hunter <adrian.hunter@intel.com>

Add itrace option 'o' to synthesize events recorded in the AUX area due to
the use of perf record's aux-output config term.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 tools/perf/Documentation/itrace.txt | 2 ++
 tools/perf/util/auxtrace.c          | 4 ++++
 tools/perf/util/auxtrace.h          | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index c2182cbabde3..82ff7dad40c2 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -5,6 +5,8 @@
 		x	synthesize transactions events
 		w	synthesize ptwrite events
 		p	synthesize power events
+		o	synthesize other events recorded due to the use
+			of aux-output (refer to perf record)
 		e	synthesize error events
 		d	create a debug log
 		g	synthesize a call chain (use with i or x)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index ec0af36697c4..cd763f9e7400 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -964,6 +964,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
+	synth_opts->other_events = true;
 	synth_opts->errors = true;
 	if (no_sample) {
 		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
@@ -1061,6 +1062,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'p':
 			synth_opts->pwr_events = true;
 			break;
+		case 'o':
+			synth_opts->other_events = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index e9b4c5edf78b..d2001fc2625b 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -60,6 +60,8 @@ enum itrace_period_type {
  * @transactions: whether to synthesize events for transactions
  * @ptwrites: whether to synthesize events for ptwrites
  * @pwr_events: whether to synthesize power events
+ * @other_events: whether to synthesize other events recorded due to the use of
+ *                aux_output
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log
@@ -86,6 +88,7 @@ struct itrace_synth_opts {
 	bool			transactions;
 	bool			ptwrites;
 	bool			pwr_events;
+	bool			other_events;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;
-- 
2.20.1

[PATCH v6 5/7] perf intel-pt: Process options for PEBS event synthesis

[Alexander Shishkin]

From: Adrian Hunter <adrian.hunter@intel.com>

Process synth_opts.other_events and attr.aux_output to set up for
synthesizing PEBs via Intel PT events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 tools/perf/arch/x86/util/intel-pt.c | 23 +++++++++++++++++++++++
 tools/perf/util/intel-pt.c          | 18 ++++++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 609088c01e3a..9a66e1575dd3 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -548,6 +548,26 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
 					evsel->attr.config);
 }
 
+/*
+ * Currently, there is not enough information to disambiguate different PEBS
+ * events, so only allow one.
+ */
+static bool intel_pt_too_many_aux_output(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	int aux_output_cnt = 0;
+
+	evlist__for_each_entry(evlist, evsel)
+		aux_output_cnt += !!evsel->attr.aux_output;
+
+	if (aux_output_cnt > 1) {
+		pr_err(INTEL_PT_PMU_NAME " supports at most one event with aux-output\n");
+		return true;
+	}
+
+	return false;
+}
+
 static int intel_pt_recording_options(struct auxtrace_record *itr,
 				      struct perf_evlist *evlist,
 				      struct record_opts *opts)
@@ -588,6 +608,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		return -EINVAL;
 	}
 
+	if (intel_pt_too_many_aux_output(evlist))
+		return -EINVAL;
+
 	if (!opts->full_auxtrace)
 		return 0;
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index df061599fef4..04ce74a66fee 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2894,6 +2894,22 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 	return 0;
 }
 
+static void intel_pt_setup_pebs_events(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+
+	if (!pt->synth_opts.other_events)
+		return;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (evsel->attr.aux_output && evsel->id) {
+			pt->sample_pebs = true;
+			pt->pebs_evsel = evsel;
+			return;
+		}
+	}
+}
+
 static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
@@ -3263,6 +3279,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (err)
 		goto err_delete_thread;
 
+	intel_pt_setup_pebs_events(pt);
+
 	err = auxtrace_queues__process_index(&pt->queues, session);
 	if (err)
 		goto err_delete_thread;
-- 
2.20.1

[PATCH v6 6/7] perf tools: Add aux-output config term

[Alexander Shishkin]

From: Adrian Hunter <adrian.hunter@intel.com>

Expose the aux_output attribute flag to the user to configure, by adding a
config term 'aux-output'. For events that support it, selection of
'aux-output' causes the generation of AUX records instead of event records.
This requires that an AUX area event is also provided.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 tools/perf/Documentation/perf-record.txt | 2 ++
 tools/perf/util/evsel.c                  | 3 +++
 tools/perf/util/evsel.h                  | 2 ++
 tools/perf/util/parse-events.c           | 8 ++++++++
 tools/perf/util/parse-events.h           | 1 +
 tools/perf/util/parse-events.l           | 1 +
 6 files changed, 17 insertions(+)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 15e0fa87241b..566050066c77 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -60,6 +60,8 @@ OPTIONS
 	  - 'name' : User defined event name. Single quotes (') may be used to
 		    escape symbols in the name from parsing by shell and tool
 		    like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'.
+	  - 'aux-output': Generate AUX records instead of events. This requires
+			  that an AUX area event is also provided.
 
           See the linkperf:perf-list[1] man page for more parameters.
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 9ec8782d3226..b872089f3974 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -832,6 +832,9 @@ static void apply_config_terms(struct perf_evsel *evsel,
 			break;
 		case PERF_EVSEL__CONFIG_TERM_PERCORE:
 			break;
+		case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT:
+			attr->aux_output = term->val.aux_output ? 1 : 0;
+			break;
 		default:
 			break;
 		}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index cad54e8ba522..e7b2f506e939 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -51,6 +51,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
 	PERF_EVSEL__CONFIG_TERM_PERCORE,
+	PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT,
 };
 
 struct perf_evsel_config_term {
@@ -69,6 +70,7 @@ struct perf_evsel_config_term {
 		char	*branch;
 		unsigned long max_events;
 		bool	percore;
+		bool	aux_output;
 	} val;
 	bool weak;
 };
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 371ff3aee769..78af7f4dd782 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -952,6 +952,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
 	[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
+	[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
 };
 
 static bool config_term_shrinked;
@@ -1072,6 +1073,9 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1122,6 +1126,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1214,6 +1219,9 @@ do {								\
 			ADD_CONFIG_TERM(PERCORE, percore,
 					term->val.num ? true : false);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+			ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0);
+			break;
 		default:
 			break;
 		}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index f7139e1a2fd3..b09eeb498fbc 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -76,6 +76,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
 	PARSE_EVENTS__TERM_TYPE_PERCORE,
+	PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index ca6098874fe2..7469497cd28e 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -284,6 +284,7 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
 no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
+aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }
-- 
2.20.1

[PATCH v6 7/7] perf intel-pt: Add brief documentation for PEBS via Intel PT

[Alexander Shishkin]

From: Adrian Hunter <adrian.hunter@intel.com>

Document how to select PEBS via Intel PT and how to display synthesized
PEBS samples.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
---
 tools/perf/Documentation/intel-pt.txt | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 50c5b60101bd..8dc513b6607b 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -919,3 +919,18 @@ amended to take the number of elements as a parameter.
 
 Note there is currently no advantage to using Intel PT instead of LBR, but
 that may change in the future if greater use is made of the data.
+
+
+PEBS via Intel PT
+=================
+
+Some hardware has the feature to redirect PEBS records to the Intel PT trace.
+Recording is selected by using the aux-output config term e.g.
+
+	perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
+
+Note that currently, software only supports redirecting at most one PEBS event.
+
+To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
+
+	perf script --itrace=oe
-- 
2.20.1

Re: [PATCH v6 0/7] perf, intel: Add support for PEBS output to Intel PT

[Peter Zijlstra]

On Tue, Aug 06, 2019 at 11:45:59AM +0300, Alexander Shishkin wrote:

> Seventh attempt at the PEBS-via-PT feature. The previous ones were [1], [2],
> [3], [4], [5], [6]. This one finalizes the 'aux_output' naming in the code.

> Alexander Shishkin (2):
>   perf: Allow normal events to output AUX data
>   perf/x86/intel: Support PEBS output to PT

Thanks Alexander!, I've picked up the above two patches.

> Adrian Hunter (5):
>   perf tools: Add aux_output attribute flag
>   perf tools: Add itrace option 'o' to synthesize aux-output events
>   perf intel-pt: Process options for PEBS event synthesis
>   perf tools: Add aux-output config term
>   perf intel-pt: Add brief documentation for PEBS via Intel PT

Arnaldo, can you either ack (in which case I'll pick them up) or
otherwise take care of these?

Re: [PATCH v6 0/7] perf, intel: Add support for PEBS output to Intel PT

[Arnaldo Carvalho de Melo]

Em Tue, Aug 06, 2019 at 04:30:32PM +0200, Peter Zijlstra escreveu:
> On Tue, Aug 06, 2019 at 11:45:59AM +0300, Alexander Shishkin wrote:
> 
> > Seventh attempt at the PEBS-via-PT feature. The previous ones were [1], [2],
> > [3], [4], [5], [6]. This one finalizes the 'aux_output' naming in the code.
> 
> > Alexander Shishkin (2):
> >   perf: Allow normal events to output AUX data
> >   perf/x86/intel: Support PEBS output to PT
> 
> Thanks Alexander!, I've picked up the above two patches.
> 
> > Adrian Hunter (5):
> >   perf tools: Add aux_output attribute flag
> >   perf tools: Add itrace option 'o' to synthesize aux-output events
> >   perf intel-pt: Process options for PEBS event synthesis
> >   perf tools: Add aux-output config term
> >   perf intel-pt: Add brief documentation for PEBS via Intel PT
> 
> Arnaldo, can you either ack (in which case I'll pick them up) or
> otherwise take care of these?

Lemme pick those, so that it goes thru the container build tests, etc.

- Arnaldo

Re: [PATCH v6 7/7] perf intel-pt: Add brief documentation for PEBS via Intel PT

[Arnaldo Carvalho de Melo]

Em Tue, Aug 06, 2019 at 11:46:06AM +0300, Alexander Shishkin escreveu:
> From: Adrian Hunter <adrian.hunter@intel.com>
> 
> Document how to select PEBS via Intel PT and how to display synthesized
> PEBS samples.
> 
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> ---
>  tools/perf/Documentation/intel-pt.txt | 15 +++++++++++++++
>  1 file changed, 15 insertions(+)
> 
> diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
> index 50c5b60101bd..8dc513b6607b 100644
> --- a/tools/perf/Documentation/intel-pt.txt
> +++ b/tools/perf/Documentation/intel-pt.txt
> @@ -919,3 +919,18 @@ amended to take the number of elements as a parameter.
>  
>  Note there is currently no advantage to using Intel PT instead of LBR, but
>  that may change in the future if greater use is made of the data.
> +
> +
> +PEBS via Intel PT
> +=================
> +
> +Some hardware has the feature to redirect PEBS records to the Intel PT trace.
> +Recording is selected by using the aux-output config term e.g.
> +
> +	perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
> +
> +Note that currently, software only supports redirecting at most one PEBS event.

So, with these patches, but not the kernel ones I end up getting:

[root@quaco ~]# perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument)
for event (cycles/aux-output/ppp).
/bin/dmesg | grep -i perf may provide additional information.

[root@quaco ~]#

I'll check if I can make it spew a more helpful message, then build a
kernel with the kernel patches and try with it as well.

PeterZ has the kernel ones landed on tip? I guess not, as perf/core I
have should be in sync...

- Arnaldo

> +To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
> +
> +	perf script --itrace=oe
> -- 
> 2.20.1

Re: [PATCH v6 7/7] perf intel-pt: Add brief documentation for PEBS via Intel PT

[Alexander Shishkin]

Arnaldo Carvalho de Melo <acme@redhat.com> writes:

> Em Tue, Aug 06, 2019 at 11:46:06AM +0300, Alexander Shishkin escreveu:
>> From: Adrian Hunter <adrian.hunter@intel.com>
>> 
>> Document how to select PEBS via Intel PT and how to display synthesized
>> PEBS samples.
>> 
>> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
>> Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
>> ---
>>  tools/perf/Documentation/intel-pt.txt | 15 +++++++++++++++
>>  1 file changed, 15 insertions(+)
>> 
>> diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
>> index 50c5b60101bd..8dc513b6607b 100644
>> --- a/tools/perf/Documentation/intel-pt.txt
>> +++ b/tools/perf/Documentation/intel-pt.txt
>> @@ -919,3 +919,18 @@ amended to take the number of elements as a parameter.
>>  
>>  Note there is currently no advantage to using Intel PT instead of LBR, but
>>  that may change in the future if greater use is made of the data.
>> +
>> +
>> +PEBS via Intel PT
>> +=================
>> +
>> +Some hardware has the feature to redirect PEBS records to the Intel PT trace.
>> +Recording is selected by using the aux-output config term e.g.
>> +
>> +	perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
>> +
>> +Note that currently, software only supports redirecting at most one PEBS event.
>
> So, with these patches, but not the kernel ones I end up getting:
>
> [root@quaco ~]# perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname

FWIW, the correct command line for that would have the two events
grouped and intel_pt be the group leader.

Regards,
--
Alex

Re: [PATCH v6 7/7] perf intel-pt: Add brief documentation for PEBS via Intel PT

[Arnaldo Carvalho de Melo]

Em Tue, Aug 13, 2019 at 05:05:46PM +0300, Alexander Shishkin escreveu:
> Arnaldo Carvalho de Melo <acme@redhat.com> writes:
> 
> > Em Tue, Aug 06, 2019 at 11:46:06AM +0300, Alexander Shishkin escreveu:
> >> From: Adrian Hunter <adrian.hunter@intel.com>
> >> 
> >> Document how to select PEBS via Intel PT and how to display synthesized
> >> PEBS samples.
> >> 
> >> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
> >> Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
> >> ---
> >>  tools/perf/Documentation/intel-pt.txt | 15 +++++++++++++++
> >>  1 file changed, 15 insertions(+)
> >> 
> >> diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
> >> index 50c5b60101bd..8dc513b6607b 100644
> >> --- a/tools/perf/Documentation/intel-pt.txt
> >> +++ b/tools/perf/Documentation/intel-pt.txt
> >> @@ -919,3 +919,18 @@ amended to take the number of elements as a parameter.
> >>  
> >>  Note there is currently no advantage to using Intel PT instead of LBR, but
> >>  that may change in the future if greater use is made of the data.
> >> +
> >> +
> >> +PEBS via Intel PT
> >> +=================
> >> +
> >> +Some hardware has the feature to redirect PEBS records to the Intel PT trace.
> >> +Recording is selected by using the aux-output config term e.g.
> >> +
> >> +	perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
> >> +
> >> +Note that currently, software only supports redirecting at most one PEBS event.
> >
> > So, with these patches, but not the kernel ones I end up getting:
> >
> > [root@quaco ~]# perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
> 
> FWIW, the correct command line for that would have the two events
> grouped and intel_pt be the group leader.

I've just blindly followed the provided documentation :)

So you say I should have tried this instead:

  # perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
  Error:
  The 'aux_output' feature is not supported, update the kernel.
  #

Or with leader sampling?

  # perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}:S' uname
  Error:
  The 'aux_output' feature is not supported, update the kernel.
  # 

This is with the patch at the end of this message and without the kernel counterpart.

- Arnaldo

commit 58c5a9772d88f5dead1e561f6323f9f355625caa
Author: Arnaldo Carvalho de Melo <acme@redhat.com>
Date:   Tue Aug 13 11:06:38 2019 -0300

    perf evsel: Provide meaningful warning when trying to use 'aux_output' on older kernels
    
    Just like we do with the 'write_backwards' feature:
    
    Before:
    
      # perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
      Error:
      The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles/aux-output/ppp).
      /bin/dmesg | grep -i perf may provide additional information.
    
      #
    
    After:
    
      # perf record  -c 10000 -e cycles/aux-output/ppp -e intel_pt/branch=0/ uname
      Error:
      The 'aux_output' feature is not supported, update the kernel.
      #
    
    Cc: Adrian Hunter <adrian.hunter@intel.com>
    Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
    Cc: Jiri Olsa <jolsa@kernel.org>
    Cc: Kan Liang <kan.liang@linux.intel.com>
    Cc: Namhyung Kim <namhyung@kernel.org>
    Cc: Peter Zijlstra <peterz@infradead.org>
    Link: https://lkml.kernel.org/n/tip-wgjsjroe1e150c0metgwmqwd@git.kernel.org
    Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 6f08aea4f108..0b3b5af33954 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1738,7 +1738,8 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 	int pid = -1, err;
 	enum { NO_CHANGE, SET_TO_MAX, INCREASED_MAX } set_rlimit = NO_CHANGE;
 
-	if (perf_missing_features.write_backward && evsel->core.attr.write_backward)
+	if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) ||
+	    (perf_missing_features.aux_output     && evsel->core.attr.aux_output))
 		return -EINVAL;
 
 	if (cpus == NULL) {
@@ -1912,7 +1913,11 @@ int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 	 * Must probe features in the order they were added to the
 	 * perf_event_attr interface.
 	 */
-	if (!perf_missing_features.bpf_event && evsel->core.attr.bpf_event) {
+	if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) {
+		perf_missing_features.aux_output = true;
+		pr_debug2("Kernel has no attr.aux_output support, bailing out\n");
+		goto out_close;
+	} else if (!perf_missing_features.bpf_event && evsel->core.attr.bpf_event) {
 		perf_missing_features.bpf_event = true;
 		pr_debug2("switching off bpf_event\n");
 		goto fallback_missing_features;
@@ -2926,6 +2931,8 @@ int perf_evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size, "clockid feature not supported.");
 		if (perf_missing_features.clockid_wrong)
 			return scnprintf(msg, size, "wrong clockid (%d).", clockid);
+		if (perf_missing_features.aux_output)
+			return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
 		break;
 	default:
 		break;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 8a316dd54cd0..9cd6e3ae479a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -184,6 +184,7 @@ struct perf_missing_features {
 	bool group_read;
 	bool ksymbol;
 	bool bpf_event;
+	bool aux_output;
 };
 
 extern struct perf_missing_features perf_missing_features;

Re: [PATCH v6 7/7] perf intel-pt: Add brief documentation for PEBS via Intel PT

[Alexander Shishkin]

Arnaldo Carvalho de Melo <acme@redhat.com> writes:

> I've just blindly followed the provided documentation :)

Yes, I should have checked it also before I sent it out. :)

> So you say I should have tried this instead:
>
>   # perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname

Right. For the purposes of illustrating the error condition, you can
probably drop the '-c ...' and 'branch=0' also, but either way is fine.

>   Error:
>   The 'aux_output' feature is not supported, update the kernel.

Or it's not supported by the hardware. I don't think we make a
distinction at the moment. You can tell if it's available from dmesg,
but not otherwise.

>   #
>
> Or with leader sampling?
>
>   # perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}:S' uname

Not sure if we should even allow this. Maybe Adrian can chime in.

Thanks,
--
Alex

[tip:perf/core] perf tools: Add aux_output attribute flag

[tip-bot for Adrian Hunter]

Commit-ID:  5a4b58e5d64ac7ebca175ffd8d74ca1b5cb0a01f
Gitweb:     https://git.kernel.org/tip/5a4b58e5d64ac7ebca175ffd8d74ca1b5cb0a01f
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 6 Aug 2019 11:46:02 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 14 Aug 2019 10:59:59 -0300

perf tools: Add aux_output attribute flag

Add aux_output attribute flag to match the kernel's perf_event.h file.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190806084606.4021-4-alexander.shishkin@linux.intel.com
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 3 ++-
 tools/perf/util/evsel.c               | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 7198ddd0c6b1..bb7b271397a6 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -374,7 +374,8 @@ struct perf_event_attr {
 				namespaces     :  1, /* include namespaces data */
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
-				__reserved_1   : 33;
+				aux_output     :  1, /* generate AUX records instead of events */
+				__reserved_1   : 32;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 64bc32ed6dfa..897a97af2d81 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1587,6 +1587,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 	PRINT_ATTRf(namespaces, p_unsigned);
 	PRINT_ATTRf(ksymbol, p_unsigned);
 	PRINT_ATTRf(bpf_event, p_unsigned);
+	PRINT_ATTRf(aux_output, p_unsigned);
 
 	PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsigned);
 	PRINT_ATTRf(bp_type, p_unsigned);

[tip:perf/core] perf tools: Add itrace option 'o' to synthesize aux-output events

[tip-bot for Adrian Hunter]

Commit-ID:  181ebb5e23a5e480f6d6aa2816a9c4aaa65afa59
Gitweb:     https://git.kernel.org/tip/181ebb5e23a5e480f6d6aa2816a9c4aaa65afa59
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 6 Aug 2019 11:46:03 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 14 Aug 2019 10:59:59 -0300

perf tools: Add itrace option 'o' to synthesize aux-output events

Add itrace option 'o' to synthesize events recorded in the AUX area due
to the use of perf record's aux-output config term.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190806084606.4021-5-alexander.shishkin@linux.intel.com
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/itrace.txt | 2 ++
 tools/perf/util/auxtrace.c          | 4 ++++
 tools/perf/util/auxtrace.h          | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index c2182cbabde3..82ff7dad40c2 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -5,6 +5,8 @@
 		x	synthesize transactions events
 		w	synthesize ptwrite events
 		p	synthesize power events
+		o	synthesize other events recorded due to the use
+			of aux-output (refer to perf record)
 		e	synthesize error events
 		d	create a debug log
 		g	synthesize a call chain (use with i or x)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 72ce4c5e7c78..60428576426e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -974,6 +974,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->transactions = true;
 	synth_opts->ptwrites = true;
 	synth_opts->pwr_events = true;
+	synth_opts->other_events = true;
 	synth_opts->errors = true;
 	if (no_sample) {
 		synth_opts->period_type = PERF_ITRACE_PERIOD_INSTRUCTIONS;
@@ -1071,6 +1072,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'p':
 			synth_opts->pwr_events = true;
 			break;
+		case 'o':
+			synth_opts->other_events = true;
+			break;
 		case 'e':
 			synth_opts->errors = true;
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 8ccabacd0b11..8e637ac3918e 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -60,6 +60,8 @@ enum itrace_period_type {
  * @transactions: whether to synthesize events for transactions
  * @ptwrites: whether to synthesize events for ptwrites
  * @pwr_events: whether to synthesize power events
+ * @other_events: whether to synthesize other events recorded due to the use of
+ *                aux_output
  * @errors: whether to synthesize decoder error events
  * @dont_decode: whether to skip decoding entirely
  * @log: write a decoding log
@@ -86,6 +88,7 @@ struct itrace_synth_opts {
 	bool			transactions;
 	bool			ptwrites;
 	bool			pwr_events;
+	bool			other_events;
 	bool			errors;
 	bool			dont_decode;
 	bool			log;

[tip:perf/core] perf intel-pt: Process options for PEBS event synthesis

[tip-bot for Adrian Hunter]

Commit-ID:  9e64cefe4335b0f2799956d3f3cca8bb652d950f
Gitweb:     https://git.kernel.org/tip/9e64cefe4335b0f2799956d3f3cca8bb652d950f
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 6 Aug 2019 11:46:04 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 14 Aug 2019 10:59:59 -0300

perf intel-pt: Process options for PEBS event synthesis

Process synth_opts.other_events and attr.aux_output to set up for
synthesizing PEBs via Intel PT events.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190806084606.4021-6-alexander.shishkin@linux.intel.com
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
[ Fixed up libbperf clashes, i.e. some places using perf_evsel (now in libperf)
  need to use instead 'evsel' (a tools/perf only abstraction) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/util/intel-pt.c | 23 +++++++++++++++++++++++
 tools/perf/util/intel-pt.c          | 18 ++++++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index 218a4e694618..a8e633aa278a 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -548,6 +548,26 @@ static int intel_pt_validate_config(struct perf_pmu *intel_pt_pmu,
 					evsel->core.attr.config);
 }
 
+/*
+ * Currently, there is not enough information to disambiguate different PEBS
+ * events, so only allow one.
+ */
+static bool intel_pt_too_many_aux_output(struct evlist *evlist)
+{
+	struct evsel *evsel;
+	int aux_output_cnt = 0;
+
+	evlist__for_each_entry(evlist, evsel)
+		aux_output_cnt += !!evsel->core.attr.aux_output;
+
+	if (aux_output_cnt > 1) {
+		pr_err(INTEL_PT_PMU_NAME " supports at most one event with aux-output\n");
+		return true;
+	}
+
+	return false;
+}
+
 static int intel_pt_recording_options(struct auxtrace_record *itr,
 				      struct evlist *evlist,
 				      struct record_opts *opts)
@@ -588,6 +608,9 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		return -EINVAL;
 	}
 
+	if (intel_pt_too_many_aux_output(evlist))
+		return -EINVAL;
+
 	if (!opts->full_auxtrace)
 		return 0;
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 4c52204868d8..ea504fa9b623 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -2894,6 +2894,22 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 	return 0;
 }
 
+static void intel_pt_setup_pebs_events(struct intel_pt *pt)
+{
+	struct evsel *evsel;
+
+	if (!pt->synth_opts.other_events)
+		return;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (evsel->core.attr.aux_output && evsel->id) {
+			pt->sample_pebs = true;
+			pt->pebs_evsel = evsel;
+			return;
+		}
+	}
+}
+
 static struct evsel *intel_pt_find_sched_switch(struct evlist *evlist)
 {
 	struct evsel *evsel;
@@ -3263,6 +3279,8 @@ int intel_pt_process_auxtrace_info(union perf_event *event,
 	if (err)
 		goto err_delete_thread;
 
+	intel_pt_setup_pebs_events(pt);
+
 	err = auxtrace_queues__process_index(&pt->queues, session);
 	if (err)
 		goto err_delete_thread;

[tip:perf/core] perf tools: Add aux-output config term

[tip-bot for Adrian Hunter]

Commit-ID:  1b9921546a9641aefc4a52c1c635b96b67142993
Gitweb:     https://git.kernel.org/tip/1b9921546a9641aefc4a52c1c635b96b67142993
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 6 Aug 2019 11:46:05 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 14 Aug 2019 10:59:59 -0300

perf tools: Add aux-output config term

Expose the aux_output attribute flag to the user to configure, by adding a
config term 'aux-output'. For events that support it, selection of
'aux-output' causes the generation of AUX records instead of event records.
This requires that an AUX area event is also provided.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190806084606.4021-7-alexander.shishkin@linux.intel.com
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-record.txt | 2 ++
 tools/perf/util/evsel.c                  | 3 +++
 tools/perf/util/evsel.h                  | 2 ++
 tools/perf/util/parse-events.c           | 8 ++++++++
 tools/perf/util/parse-events.h           | 1 +
 tools/perf/util/parse-events.l           | 1 +
 6 files changed, 17 insertions(+)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index d5e58e0a2bca..c6f9f31b6039 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -60,6 +60,8 @@ OPTIONS
 	  - 'name' : User defined event name. Single quotes (') may be used to
 		    escape symbols in the name from parsing by shell and tool
 		    like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'.
+	  - 'aux-output': Generate AUX records instead of events. This requires
+			  that an AUX area event is also provided.
 
           See the linkperf:perf-list[1] man page for more parameters.
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 897a97af2d81..5da40511546b 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -833,6 +833,9 @@ static void apply_config_terms(struct evsel *evsel,
 			break;
 		case PERF_EVSEL__CONFIG_TERM_PERCORE:
 			break;
+		case PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT:
+			attr->aux_output = term->val.aux_output ? 1 : 0;
+			break;
 		default:
 			break;
 		}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 3cf35aa782b9..8a316dd54cd0 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -52,6 +52,7 @@ enum term_type {
 	PERF_EVSEL__CONFIG_TERM_DRV_CFG,
 	PERF_EVSEL__CONFIG_TERM_BRANCH,
 	PERF_EVSEL__CONFIG_TERM_PERCORE,
+	PERF_EVSEL__CONFIG_TERM_AUX_OUTPUT,
 };
 
 struct perf_evsel_config_term {
@@ -70,6 +71,7 @@ struct perf_evsel_config_term {
 		char	*branch;
 		unsigned long max_events;
 		bool	percore;
+		bool	aux_output;
 	} val;
 	bool weak;
 };
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2cfec3b7a982..9101568946d2 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -963,6 +963,7 @@ static const char *config_term_names[__PARSE_EVENTS__TERM_TYPE_NR] = {
 	[PARSE_EVENTS__TERM_TYPE_NOOVERWRITE]		= "no-overwrite",
 	[PARSE_EVENTS__TERM_TYPE_DRV_CFG]		= "driver-config",
 	[PARSE_EVENTS__TERM_TYPE_PERCORE]		= "percore",
+	[PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT]		= "aux-output",
 };
 
 static bool config_term_shrinked;
@@ -1083,6 +1084,9 @@ do {									   \
 			return -EINVAL;
 		}
 		break;
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+		CHECK_TYPE_VAL(NUM);
+		break;
 	default:
 		err->str = strdup("unknown term");
 		err->idx = term->err_term;
@@ -1133,6 +1137,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 	case PARSE_EVENTS__TERM_TYPE_MAX_EVENTS:
 	case PARSE_EVENTS__TERM_TYPE_OVERWRITE:
 	case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE:
+	case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
 		return config_term_common(attr, term, err);
 	default:
 		if (err) {
@@ -1225,6 +1230,9 @@ do {								\
 			ADD_CONFIG_TERM(PERCORE, percore,
 					term->val.num ? true : false);
 			break;
+		case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT:
+			ADD_CONFIG_TERM(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0);
+			break;
 		default:
 			break;
 		}
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 48111b8fc232..616ca1eda0eb 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -76,6 +76,7 @@ enum {
 	PARSE_EVENTS__TERM_TYPE_OVERWRITE,
 	PARSE_EVENTS__TERM_TYPE_DRV_CFG,
 	PARSE_EVENTS__TERM_TYPE_PERCORE,
+	PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT,
 	__PARSE_EVENTS__TERM_TYPE_NR,
 };
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index ca6098874fe2..7469497cd28e 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -284,6 +284,7 @@ no-inherit		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOINHERIT); }
 overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_OVERWRITE); }
 no-overwrite		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE); }
 percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
+aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 ,			{ return ','; }
 "/"			{ BEGIN(INITIAL); return '/'; }
 {name_minus}		{ return str(yyscanner, PE_NAME); }

[tip:perf/core] perf intel-pt: Add brief documentation for PEBS via Intel PT

[tip-bot for Adrian Hunter]

Commit-ID:  243384dd25c8ea721c5c82a229eaf33cbd1bfd52
Gitweb:     https://git.kernel.org/tip/243384dd25c8ea721c5c82a229eaf33cbd1bfd52
Author:     Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Tue, 6 Aug 2019 11:46:06 +0300
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 14 Aug 2019 10:59:59 -0300

perf intel-pt: Add brief documentation for PEBS via Intel PT

Document how to select PEBS via Intel PT and how to display synthesized
PEBS samples.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190806084606.4021-8-alexander.shishkin@linux.intel.com
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
[ Update the example to use a group with intel_pt// as the group leader, as per Alex comment ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/intel-pt.txt | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 50c5b60101bd..e0d9e7dd4f17 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -919,3 +919,18 @@ amended to take the number of elements as a parameter.
 
 Note there is currently no advantage to using Intel PT instead of LBR, but
 that may change in the future if greater use is made of the data.
+
+
+PEBS via Intel PT
+=================
+
+Some hardware has the feature to redirect PEBS records to the Intel PT trace.
+Recording is selected by using the aux-output config term e.g.
+
+	perf record -c 10000 -e '{intel_pt/branch=0/,cycles/aux-output/ppp}' uname
+
+Note that currently, software only supports redirecting at most one PEBS event.
+
+To display PEBS events from the Intel PT trace, use the itrace 'o' option e.g.
+
+	perf script --itrace=oe

[tip: perf/core] perf: Allow normal events to output AUX data

[tip-bot2 for Alexander Shishkin]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     ab43762ef010967e4ccd53627f70a2eecbeafefb
Gitweb:        https://git.kernel.org/tip/ab43762ef010967e4ccd53627f70a2eecbeafefb
Author:        Alexander Shishkin <alexander.shishkin@linux.intel.com>
AuthorDate:    Tue, 06 Aug 2019 11:46:00 +03:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 28 Aug 2019 11:29:38 +02:00

perf: Allow normal events to output AUX data

In some cases, ordinary (non-AUX) events can generate data for AUX events.
For example, PEBS events can come out as records in the Intel PT stream
instead of their usual DS records, if configured to do so.

One requirement for such events is to consistently schedule together, to
ensure that the data from the "AUX output" events isn't lost while their
corresponding AUX event is not scheduled. We use grouping to provide this
guarantee: an "AUX output" event can be added to a group where an AUX event
is a group leader, and provided that the former supports writing to the
latter.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: kan.liang@linux.intel.com
Link: https://lkml.kernel.org/r/20190806084606.4021-2-alexander.shishkin@linux.intel.com
---
 include/linux/perf_event.h      | 14 +++++-
 include/uapi/linux/perf_event.h |  3 +-
 kernel/events/core.c            | 93 ++++++++++++++++++++++++++++++++-
 3 files changed, 109 insertions(+), 1 deletion(-)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e8ad3c5..61448c1 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -246,6 +246,7 @@ struct perf_event;
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
 #define PERF_PMU_CAP_NO_EXCLUDE			0x80
+#define PERF_PMU_CAP_AUX_OUTPUT			0x100
 
 /**
  * struct pmu - generic performance monitoring unit
@@ -447,6 +448,16 @@ struct pmu {
 					/* optional */
 
 	/*
+	 * Check if event can be used for aux_output purposes for
+	 * events of this PMU.
+	 *
+	 * Runs from perf_event_open(). Should return 0 for "no match"
+	 * or non-zero for "match".
+	 */
+	int (*aux_output_match)		(struct perf_event *event);
+					/* optional */
+
+	/*
 	 * Filter events for PMU-specific reasons.
 	 */
 	int (*filter_match)		(struct perf_event *event); /* optional */
@@ -681,6 +692,9 @@ struct perf_event {
 	struct perf_addr_filter_range	*addr_filter_ranges;
 	unsigned long			addr_filters_gen;
 
+	/* for aux_output events */
+	struct perf_event		*aux_event;
+
 	void (*destroy)(struct perf_event *);
 	struct rcu_head			rcu_head;
 
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7198ddd..bb7b271 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -374,7 +374,8 @@ struct perf_event_attr {
 				namespaces     :  1, /* include namespaces data */
 				ksymbol        :  1, /* include ksymbol events */
 				bpf_event      :  1, /* include bpf events */
-				__reserved_1   : 33;
+				aux_output     :  1, /* generate AUX records instead of events */
+				__reserved_1   : 32;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0463c11..2aad959 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1887,6 +1887,89 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 	ctx->generation++;
 }
 
+static int
+perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
+{
+	if (!has_aux(aux_event))
+		return 0;
+
+	if (!event->pmu->aux_output_match)
+		return 0;
+
+	return event->pmu->aux_output_match(aux_event);
+}
+
+static void put_event(struct perf_event *event);
+static void event_sched_out(struct perf_event *event,
+			    struct perf_cpu_context *cpuctx,
+			    struct perf_event_context *ctx);
+
+static void perf_put_aux_event(struct perf_event *event)
+{
+	struct perf_event_context *ctx = event->ctx;
+	struct perf_cpu_context *cpuctx = __get_cpu_context(ctx);
+	struct perf_event *iter;
+
+	/*
+	 * If event uses aux_event tear down the link
+	 */
+	if (event->aux_event) {
+		iter = event->aux_event;
+		event->aux_event = NULL;
+		put_event(iter);
+		return;
+	}
+
+	/*
+	 * If the event is an aux_event, tear down all links to
+	 * it from other events.
+	 */
+	for_each_sibling_event(iter, event->group_leader) {
+		if (iter->aux_event != event)
+			continue;
+
+		iter->aux_event = NULL;
+		put_event(event);
+
+		/*
+		 * If it's ACTIVE, schedule it out and put it into ERROR
+		 * state so that we don't try to schedule it again. Note
+		 * that perf_event_enable() will clear the ERROR status.
+		 */
+		event_sched_out(iter, cpuctx, ctx);
+		perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+	}
+}
+
+static int perf_get_aux_event(struct perf_event *event,
+			      struct perf_event *group_leader)
+{
+	/*
+	 * Our group leader must be an aux event if we want to be
+	 * an aux_output. This way, the aux event will precede its
+	 * aux_output events in the group, and therefore will always
+	 * schedule first.
+	 */
+	if (!group_leader)
+		return 0;
+
+	if (!perf_aux_output_match(event, group_leader))
+		return 0;
+
+	if (!atomic_long_inc_not_zero(&group_leader->refcount))
+		return 0;
+
+	/*
+	 * Link aux_outputs to their aux event; this is undone in
+	 * perf_group_detach() by perf_put_aux_event(). When the
+	 * group in torn down, the aux_output events loose their
+	 * link to the aux_event and can't schedule any more.
+	 */
+	event->aux_event = group_leader;
+
+	return 1;
+}
+
 static void perf_group_detach(struct perf_event *event)
 {
 	struct perf_event *sibling, *tmp;
@@ -1902,6 +1985,8 @@ static void perf_group_detach(struct perf_event *event)
 
 	event->attach_state &= ~PERF_ATTACH_GROUP;
 
+	perf_put_aux_event(event);
+
 	/*
 	 * If this is a sibling, remove it from its group.
 	 */
@@ -10426,6 +10511,12 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 		goto err_ns;
 	}
 
+	if (event->attr.aux_output &&
+	    !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) {
+		err = -EOPNOTSUPP;
+		goto err_pmu;
+	}
+
 	err = exclusive_event_init(event);
 	if (err)
 		goto err_pmu;
@@ -11082,6 +11173,8 @@ SYSCALL_DEFINE5(perf_event_open,
 		}
 	}
 
+	if (event->attr.aux_output && !perf_get_aux_event(event, group_leader))
+		goto err_locked;
 
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),

[tip: perf/core] perf/x86/intel: Support PEBS output to PT

[tip-bot2 for Alexander Shishkin]

The following commit has been merged into the perf/core branch of tip:

Commit-ID:     42880f726c66f13ae1d9ac9ce4c43abe64ecac84
Gitweb:        https://git.kernel.org/tip/42880f726c66f13ae1d9ac9ce4c43abe64ecac84
Author:        Alexander Shishkin <alexander.shishkin@linux.intel.com>
AuthorDate:    Tue, 06 Aug 2019 11:46:01 +03:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 28 Aug 2019 11:29:39 +02:00

perf/x86/intel: Support PEBS output to PT

If PEBS declares ability to output its data to Intel PT stream, use the
aux_output attribute bit to enable PEBS data output to PT. This requires
a PT event to be present and scheduled in the same context. Unlike the
DS area, the kernel does not extract PEBS records from the PT stream to
generate corresponding records in the perf stream, because that would
require real time in-kernel PT decoding, which is not feasible. The PMI,
however, can still be used.

The output setting is per-CPU, so all PEBS events must be either writing
to PT or to the DS area, therefore, in case of conflict, the conflicting
event will fail to schedule, allowing the rotation logic to alternate
between the PEBS->PT and PEBS->DS events.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: kan.liang@linux.intel.com
Link: https://lkml.kernel.org/r/20190806084606.4021-3-alexander.shishkin@linux.intel.com
---
 arch/x86/events/core.c           | 34 +++++++++++++++++++++-
 arch/x86/events/intel/core.c     | 18 +++++++++++-
 arch/x86/events/intel/ds.c       | 51 ++++++++++++++++++++++++++++++-
 arch/x86/events/intel/pt.c       |  5 +++-
 arch/x86/events/perf_event.h     | 17 ++++++++++-
 arch/x86/include/asm/intel_pt.h  |  2 +-
 arch/x86/include/asm/msr-index.h |  4 ++-
 7 files changed, 130 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 325959d..15b90b1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1005,6 +1005,27 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 
 	/* current number of events already accepted */
 	n = cpuc->n_events;
+	if (!cpuc->n_events)
+		cpuc->pebs_output = 0;
+
+	if (!cpuc->is_fake && leader->attr.precise_ip) {
+		/*
+		 * For PEBS->PT, if !aux_event, the group leader (PT) went
+		 * away, the group was broken down and this singleton event
+		 * can't schedule any more.
+		 */
+		if (is_pebs_pt(leader) && !leader->aux_event)
+			return -EINVAL;
+
+		/*
+		 * pebs_output: 0: no PEBS so far, 1: PT, 2: DS
+		 */
+		if (cpuc->pebs_output &&
+		    cpuc->pebs_output != is_pebs_pt(leader) + 1)
+			return -EINVAL;
+
+		cpuc->pebs_output = is_pebs_pt(leader) + 1;
+	}
 
 	if (is_x86_event(leader)) {
 		if (n >= max_count)
@@ -2241,6 +2262,17 @@ static int x86_pmu_check_period(struct perf_event *event, u64 value)
 	return 0;
 }
 
+static int x86_pmu_aux_output_match(struct perf_event *event)
+{
+	if (!(pmu.capabilities & PERF_PMU_CAP_AUX_OUTPUT))
+		return 0;
+
+	if (x86_pmu.aux_output_match)
+		return x86_pmu.aux_output_match(event);
+
+	return 0;
+}
+
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
 	.pmu_disable		= x86_pmu_disable,
@@ -2266,6 +2298,8 @@ static struct pmu pmu = {
 	.sched_task		= x86_pmu_sched_task,
 	.task_ctx_size          = sizeof(struct x86_perf_task_context),
 	.check_period		= x86_pmu_check_period,
+
+	.aux_output_match	= x86_pmu_aux_output_match,
 };
 
 void arch_perf_update_userpage(struct perf_event *event,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 648260b..28459f4 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -18,6 +18,7 @@
 #include <asm/cpufeature.h>
 #include <asm/hardirq.h>
 #include <asm/intel-family.h>
+#include <asm/intel_pt.h>
 #include <asm/apic.h>
 #include <asm/cpu_device_id.h>
 
@@ -3298,6 +3299,13 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		}
 	}
 
+	if (event->attr.aux_output) {
+		if (!event->attr.precise_ip)
+			return -EINVAL;
+
+		event->hw.flags |= PERF_X86_EVENT_PEBS_VIA_PT;
+	}
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
@@ -3811,6 +3819,14 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value)
 	return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0;
 }
 
+static int intel_pmu_aux_output_match(struct perf_event *event)
+{
+	if (!x86_pmu.intel_cap.pebs_output_pt_available)
+		return 0;
+
+	return is_intel_pt_event(event);
+}
+
 PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
@@ -3935,6 +3951,8 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.sched_task		= intel_pmu_sched_task,
 
 	.check_period		= intel_pmu_check_period,
+
+	.aux_output_match	= intel_pmu_aux_output_match,
 };
 
 static __init void intel_clovertown_quirk(void)
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index f1269e8..ce83950 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -902,6 +902,9 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
  */
 static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
 {
+	if (cpuc->n_pebs == cpuc->n_pebs_via_pt)
+		return false;
+
 	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
 }
 
@@ -919,6 +922,9 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 	u64 threshold;
 	int reserved;
 
+	if (cpuc->n_pebs_via_pt)
+		return;
+
 	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
 		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
 	else
@@ -1059,10 +1065,40 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	cpuc->n_pebs++;
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
+	if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT)
+		cpuc->n_pebs_via_pt++;
 
 	pebs_update_state(needed_cb, cpuc, event, true);
 }
 
+static void intel_pmu_pebs_via_pt_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!is_pebs_pt(event))
+		return;
+
+	if (!(cpuc->pebs_enabled & ~PEBS_VIA_PT_MASK))
+		cpuc->pebs_enabled &= ~PEBS_VIA_PT_MASK;
+}
+
+static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	struct debug_store *ds = cpuc->ds;
+
+	if (!is_pebs_pt(event))
+		return;
+
+	if (!(event->hw.flags & PERF_X86_EVENT_LARGE_PEBS))
+		cpuc->pebs_enabled |= PEBS_PMI_AFTER_EACH_RECORD;
+
+	cpuc->pebs_enabled |= PEBS_OUTPUT_PT;
+
+	wrmsrl(MSR_RELOAD_PMC0 + hwc->idx, ds->pebs_event_reset[hwc->idx]);
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1100,6 +1136,8 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
 	}
+
+	intel_pmu_pebs_via_pt_enable(event);
 }
 
 void intel_pmu_pebs_del(struct perf_event *event)
@@ -1111,6 +1149,8 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	cpuc->n_pebs--;
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
+	if (hwc->flags & PERF_X86_EVENT_PEBS_VIA_PT)
+		cpuc->n_pebs_via_pt--;
 
 	pebs_update_state(needed_cb, cpuc, event, false);
 }
@@ -1120,7 +1160,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (cpuc->n_pebs == cpuc->n_large_pebs)
+	if (cpuc->n_pebs == cpuc->n_large_pebs &&
+	    cpuc->n_pebs != cpuc->n_pebs_via_pt)
 		intel_pmu_drain_pebs_buffer();
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -1131,6 +1172,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
+	intel_pmu_pebs_via_pt_disable(event);
+
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -2031,6 +2074,12 @@ void __init intel_ds_init(void)
 					  PERF_SAMPLE_REGS_INTR);
 			}
 			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+
+			if (x86_pmu.intel_cap.pebs_output_pt_available) {
+				pr_cont("PEBS-via-PT, ");
+				x86_get_pmu()->capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+			}
+
 			break;
 
 		default:
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fa43d90..b1bb4d2 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1564,6 +1564,11 @@ void cpu_emergency_stop_pt(void)
 		pt_event_stop(pt->handle.event, PERF_EF_UPDATE);
 }
 
+int is_intel_pt_event(struct perf_event *event)
+{
+	return event->pmu == &pt_pmu.pmu;
+}
+
 static __init int pt_init(void)
 {
 	int ret, cpu, prior_warn = 0;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 8751008..ecacfbf 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -76,6 +76,7 @@ static inline bool constraint_match(struct event_constraint *c, u64 ecode)
 #define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
 #define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
 #define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
+#define PERF_X86_EVENT_PEBS_VIA_PT	0x0800 /* use PT buffer for PEBS */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -85,6 +86,11 @@ struct amd_nb {
 };
 
 #define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
+#define PEBS_PMI_AFTER_EACH_RECORD BIT_ULL(60)
+#define PEBS_OUTPUT_OFFSET	61
+#define PEBS_OUTPUT_MASK	(3ull << PEBS_OUTPUT_OFFSET)
+#define PEBS_OUTPUT_PT		(1ull << PEBS_OUTPUT_OFFSET)
+#define PEBS_VIA_PT_MASK	(PEBS_OUTPUT_PT | PEBS_PMI_AFTER_EACH_RECORD)
 
 /*
  * Flags PEBS can handle without an PMI.
@@ -211,6 +217,8 @@ struct cpu_hw_events {
 	u64			pebs_enabled;
 	int			n_pebs;
 	int			n_large_pebs;
+	int			n_pebs_via_pt;
+	int			pebs_output;
 
 	/* Current super set of events hardware configuration */
 	u64			pebs_data_cfg;
@@ -510,6 +518,8 @@ union perf_capabilities {
 		 */
 		u64	full_width_write:1;
 		u64     pebs_baseline:1;
+		u64	pebs_metrics_available:1;
+		u64	pebs_output_pt_available:1;
 	};
 	u64	capabilities;
 };
@@ -692,6 +702,8 @@ struct x86_pmu {
 	 * Check period value for PERF_EVENT_IOC_PERIOD ioctl.
 	 */
 	int (*check_period) (struct perf_event *event, u64 period);
+
+	int (*aux_output_match) (struct perf_event *event);
 };
 
 struct x86_perf_task_context {
@@ -901,6 +913,11 @@ static inline int amd_pmu_init(void)
 
 #endif /* CONFIG_CPU_SUP_AMD */
 
+static inline int is_pebs_pt(struct perf_event *event)
+{
+	return !!(event->hw.flags & PERF_X86_EVENT_PEBS_VIA_PT);
+}
+
 #ifdef CONFIG_CPU_SUP_INTEL
 
 static inline bool intel_pmu_has_bts_period(struct perf_event *event, u64 period)
diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h
index 634f99b..423b788 100644
--- a/arch/x86/include/asm/intel_pt.h
+++ b/arch/x86/include/asm/intel_pt.h
@@ -28,10 +28,12 @@ enum pt_capabilities {
 void cpu_emergency_stop_pt(void);
 extern u32 intel_pt_validate_hw_cap(enum pt_capabilities cap);
 extern u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities cap);
+extern int is_intel_pt_event(struct perf_event *event);
 #else
 static inline void cpu_emergency_stop_pt(void) {}
 static inline u32 intel_pt_validate_hw_cap(enum pt_capabilities cap) { return 0; }
 static inline u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability) { return 0; }
+static inline int is_intel_pt_event(struct perf_event *event) { return 0; }
 #endif
 
 #endif /* _ASM_X86_INTEL_PT_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 271d837..de75320 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -375,6 +375,10 @@
 /* Alternative perfctr range with full access. */
 #define MSR_IA32_PMC0			0x000004c1
 
+/* Auto-reload via MSR instead of DS area */
+#define MSR_RELOAD_PMC0			0x000014c1
+#define MSR_RELOAD_FIXED_CTR0		0x00001309
+
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */