Received-SPF: pass (google.com: domain of linux-kernel+bounces-180321-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Wed, 15 May 2024 12:36:09 -0700
In-Reply-To: <20240515193610.2350456-1-yabinc@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240515193610.2350456-1-yabinc@google.com>
Message-ID: <20240515193610.2350456-4-yabinc@google.com>
Subject: [PATCH v5 3/3] perf/core: Check sample_type in perf_sample_save_brstack
From: Yabin Cui <yabinc@google.com>
To: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>, 
	Arnaldo Carvalho de Melo <acme@kernel.org>, Namhyung Kim <namhyung@kernel.org>, 
	Mark Rutland <mark.rutland@arm.com>, 
	Alexander Shishkin <alexander.shishkin@linux.intel.com>, Jiri Olsa <jolsa@kernel.org>, 
	Ian Rogers <irogers@google.com>, Adrian Hunter <adrian.hunter@intel.com>
Cc: linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, 
	bpf@vger.kernel.org, Yabin Cui <yabinc@google.com>
Content-Type: text/plain; charset="UTF-8"

Check sample_type in perf_sample_save_brstack() to prevent
saving branch stack data when it isn't required.

Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Yabin Cui <yabinc@google.com>
---
 arch/x86/events/amd/core.c |  3 +--
 arch/x86/events/core.c     |  3 +--
 arch/x86/events/intel/ds.c |  3 +--
 include/linux/perf_event.h | 15 ++++++++++-----
 4 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 1fc4ce44e743..f71a9ef932c5 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -998,8 +998,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (has_branch_stack(event))
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
+		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5b0dd07b1ef1..ff5577315938 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1702,8 +1702,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 
 		perf_sample_data_init(&data, 0, event->hw.last_period);
 
-		if (has_branch_stack(event))
-			perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
+		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
 		if (perf_event_overflow(event, &data, regs))
 			x86_pmu_stop(event, 0);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c2b5585aa6d1..f25236ffa28f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1754,8 +1754,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	if (x86_pmu.intel_cap.pebs_format >= 3)
 		setup_pebs_time(event, data, pebs->tsc);
 
-	if (has_branch_stack(event))
-		perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
+	perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL);
 }
 
 static void adaptive_pebs_save_regs(struct pt_regs *regs,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index bda066c33120..f6637f3cbe84 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1276,6 +1276,11 @@ static inline void perf_sample_save_raw_data(struct perf_sample_data *data,
 	data->sample_flags |= PERF_SAMPLE_RAW;
 }
 
+static inline bool has_branch_stack(struct perf_event *event)
+{
+	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
+}
+
 static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 					    struct perf_event *event,
 					    struct perf_branch_stack *brs,
@@ -1283,6 +1288,11 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 {
 	int size = sizeof(u64); /* nr */
 
+	if (!has_branch_stack(event))
+		return;
+	if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK))
+		return;
+
 	if (branch_sample_hw_index(event))
 		size += sizeof(u64);
 	size += brs->nr * sizeof(struct perf_branch_entry);
@@ -1658,11 +1668,6 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 # define perf_arch_bpf_user_pt_regs(regs) regs
 #endif
 
-static inline bool has_branch_stack(struct perf_event *event)
-{
-	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
-}
-
 static inline bool needs_branch_stack(struct perf_event *event)
 {
 	return event->attr.branch_sample_type != 0;
-- 
2.45.0.rc1.225.g2a3ae87e7f-goog