From: Kan Liang <kan.liang@linux.intel.com>

When a machine supports PEBS v6, perf unconditionally searches the
cpuc->event_list[] for every event and check if the late setup is
required, which is unnecessary.

The late setup is only required for special events, e.g., events support
counters snapshotting feature. Add n_late_setup to track the num of
events that needs the late setup.

Other features, e.g., auto counter reload feature, require the late
setup as well. Add a wrapper, intel_pmu_pebs_late_setup, for the events
that support counters snapshotting feature.

Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---
 arch/x86/events/intel/core.c | 14 ++++++++++++++
 arch/x86/events/intel/ds.c   |  3 +--
 arch/x86/events/perf_event.h |  5 +++++
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 2a3f802e3ab9..66c42f856636 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2603,6 +2603,8 @@ static void intel_pmu_del_event(struct perf_event *event)
 		intel_pmu_lbr_del(event);
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_del(event);
+	if (is_pebs_counter_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
 }
 
 static int icl_set_topdown_event_period(struct perf_event *event)
@@ -2914,12 +2916,24 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	}
 }
 
+void intel_pmu_late_setup(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!cpuc->n_late_setup)
+		return;
+
+	intel_pmu_pebs_late_setup(cpuc);
+}
+
 static void intel_pmu_add_event(struct perf_event *event)
 {
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_add(event);
 	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_add(event);
+	if (is_pebs_counter_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup++;
 }
 
 /*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1f7e1a692a7a..486881fe162e 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1355,9 +1355,8 @@ static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
 }
 
 
-static void intel_pmu_late_setup(void)
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	u64 pebs_data_cfg = 0;
 	int i;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index d6d56568e11f..84943243b05d 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -261,6 +261,7 @@ struct cpu_hw_events {
 	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
 
 	int			n_excl; /* the number of exclusive events */
+	int			n_late_setup; /* the num of events needs late setup */
 
 	unsigned int		txn_flags;
 	int			is_fake;
@@ -1598,6 +1599,8 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
+void intel_pmu_late_setup(void);
+
 u64 grt_latency_data(struct perf_event *event, u64 status);
 
 u64 cmt_latency_data(struct perf_event *event, u64 status);
@@ -1654,6 +1657,8 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc);
+
 void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
-- 
2.38.1

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

Commit-ID:     0a6557938d8f189024a03aca77e58763930840ee
Gitweb:        https://git.kernel.org/tip/0a6557938d8f189024a03aca77e58763930840ee
Author:        Kan Liang <kan.liang@linux.intel.com>
AuthorDate:    Thu, 27 Mar 2025 12:52:14 -07:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 08 Apr 2025 20:55:48 +02:00

perf/x86/intel: Track the num of events needs late setup

When a machine supports PEBS v6, perf unconditionally searches the
cpuc->event_list[] for every event and check if the late setup is
required, which is unnecessary.

The late setup is only required for special events, e.g., events support
counters snapshotting feature. Add n_late_setup to track the num of
events that needs the late setup.

Other features, e.g., auto counter reload feature, require the late
setup as well. Add a wrapper, intel_pmu_pebs_late_setup, for the events
that support counters snapshotting feature.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
Link: https://lkml.kernel.org/r/20250327195217.2683619-3-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 14 ++++++++++++++
 arch/x86/events/intel/ds.c   |  3 +--
 arch/x86/events/perf_event.h |  5 +++++
 3 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 9724928..6105024 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2603,6 +2603,8 @@ static void intel_pmu_del_event(struct perf_event *event)
 		intel_pmu_lbr_del(event);
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_del(event);
+	if (is_pebs_counter_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
 }
 
 static int icl_set_topdown_event_period(struct perf_event *event)
@@ -2914,12 +2916,24 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	}
 }
 
+void intel_pmu_late_setup(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!cpuc->n_late_setup)
+		return;
+
+	intel_pmu_pebs_late_setup(cpuc);
+}
+
 static void intel_pmu_add_event(struct perf_event *event)
 {
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_add(event);
 	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_add(event);
+	if (is_pebs_counter_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup++;
 }
 
 /*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 1f7e1a6..486881f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1355,9 +1355,8 @@ static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
 }
 
 
-static void intel_pmu_late_setup(void)
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	u64 pebs_data_cfg = 0;
 	int i;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f5ba165..4410cf0 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -261,6 +261,7 @@ struct cpu_hw_events {
 	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
 
 	int			n_excl; /* the number of exclusive events */
+	int			n_late_setup; /* the num of events needs late setup */
 
 	unsigned int		txn_flags;
 	int			is_fake;
@@ -1581,6 +1582,8 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
+void intel_pmu_late_setup(void);
+
 u64 grt_latency_data(struct perf_event *event, u64 status);
 
 u64 cmt_latency_data(struct perf_event *event, u64 status);
@@ -1637,6 +1640,8 @@ void intel_pmu_pebs_disable_all(void);
 
 void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
 
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc);
+
 void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);