Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Sender: Namhyung Kim <namhyung@gmail.com>
From:   Namhyung Kim <namhyung@kernel.org>
To:     Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>
Cc:     Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>,
        Jiri Olsa <jolsa@kernel.org>,
        LKML <linux-kernel@vger.kernel.org>, Song Liu <song@kernel.org>,
        bpf@vger.kernel.org, x86@kernel.org
Subject: [PATCH 2/8] perf/core: Add perf_sample_save_callchain() helper
Date:   Tue, 17 Jan 2023 22:05:53 -0800
Message-Id: <20230118060559.615653-3-namhyung@kernel.org>
In-Reply-To: <20230118060559.615653-1-namhyung@kernel.org>
References: <20230118060559.615653-1-namhyung@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

When it saves the callchain to the perf sample data, it needs to update
the sample flags and the dynamic size.  To make sure this, add the
perf_sample_save_callchain() helper and convert all call sites.

Cc: x86@kernel.org
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Tested-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 arch/x86/events/amd/ibs.c  |  6 ++----
 arch/x86/events/intel/ds.c | 12 ++++--------
 include/linux/perf_event.h | 16 +++++++++++++++-
 kernel/events/core.c       | 12 ++----------
 4 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index da3f5ebac4e1..417c80bd3274 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1122,10 +1122,8 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 	 * recorded as part of interrupt regs. Thus we need to use rip from
 	 * interrupt regs while unwinding call stack.
 	 */
-	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) {
-		data.callchain = perf_callchain(event, iregs);
-		data.sample_flags |= PERF_SAMPLE_CALLCHAIN;
-	}
+	if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(&data, event, iregs);
 
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 6ec326b47e2e..158cf845fc80 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1617,10 +1617,8 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	 * previous PMI context or an (I)RET happened between the record and
 	 * PMI.
 	 */
-	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		data->callchain = perf_callchain(event, iregs);
-		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
-	}
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(data, event, iregs);
 
 	/*
 	 * We use the interrupt regs as a base because the PEBS record does not
@@ -1795,10 +1793,8 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	 * previous PMI context or an (I)RET happened between the record and
 	 * PMI.
 	 */
-	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		data->callchain = perf_callchain(event, iregs);
-		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
-	}
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(data, event, iregs);
 
 	*regs = *iregs;
 	/* The ip in basic is EventingIP */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 16b980014449..a9419608402b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1095,6 +1095,8 @@ int perf_event_read_local(struct perf_event *event, u64 *value,
 extern u64 perf_event_read_value(struct perf_event *event,
 				 u64 *enabled, u64 *running);
 
+extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
+
 
 struct perf_sample_data {
 	/*
@@ -1167,6 +1169,19 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	}
 }
 
+static inline void perf_sample_save_callchain(struct perf_sample_data *data,
+					      struct perf_event *event,
+					      struct pt_regs *regs)
+{
+	int size = 1;
+
+	data->callchain = perf_callchain(event, regs);
+	size += data->callchain->nr;
+
+	data->dyn_size += size * sizeof(u64);
+	data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
+}
+
 /*
  * Clear all bitfields in the perf_branch_entry.
  * The to and from fields are not cleared because they are
@@ -1408,7 +1423,6 @@ extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark);
-extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8c8de26f04ab..0fba98b9cd65 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7585,16 +7585,8 @@ void perf_prepare_sample(struct perf_event_header *header,
 	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
 		data->ip = perf_instruction_pointer(regs);
 
-	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
-		int size = 1;
-
-		if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)
-			data->callchain = perf_callchain(event, regs);
-
-		size += data->callchain->nr;
-
-		data->dyn_size += size * sizeof(u64);
-	}
+	if (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)
+		perf_sample_save_callchain(data, event, regs);
 
 	if (sample_type & PERF_SAMPLE_RAW) {
 		struct perf_raw_record *raw = data->raw;
-- 
2.39.0.314.g84b9a713c41-goog