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>
Cc:     Ingo Molnar <mingo@kernel.org>,
        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 <songliubraving@fb.com>,
        Ravi Bangoria <ravi.bangoria@amd.com>,
        Stephane Eranian <eranian@google.com>,
        Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH 2/2] perf: Use sample_flags for raw_data
Date:   Wed, 21 Sep 2022 15:00:32 -0700
Message-Id: <20220921220032.2858517-2-namhyung@kernel.org>
In-Reply-To: <20220921220032.2858517-1-namhyung@kernel.org>
References: <20220921220032.2858517-1-namhyung@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Use the new sample_flags to indicate whether the raw data field is
filled by the PMU driver.  Although it could check with the NULL,
follow the same rule with other fields.

Remove the raw field from the perf_sample_data_init() to minimize
the number of cache lines touched.

Cc: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 arch/s390/kernel/perf_cpum_cf.c    | 1 +
 arch/s390/kernel/perf_pai_crypto.c | 1 +
 arch/x86/events/amd/ibs.c          | 1 +
 include/linux/perf_event.h         | 5 ++---
 kernel/events/core.c               | 3 ++-
 5 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index f7dd3c849e68..f043a7ff220b 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -664,6 +664,7 @@ static int cfdiag_push_sample(struct perf_event *event,
 		raw.frag.data = cpuhw->stop;
 		raw.size = raw.frag.size;
 		data.raw = &raw;
+		data.sample_flags |= PERF_SAMPLE_RAW;
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index b38b4ae01589..6826e2a69a21 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -366,6 +366,7 @@ static int paicrypt_push_sample(void)
 		raw.frag.data = cpump->save;
 		raw.size = raw.frag.size;
 		data.raw = &raw;
+		data.sample_flags |= PERF_SAMPLE_RAW;
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index ce5720bfb350..c29a006954c7 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -781,6 +781,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 			},
 		};
 		data.raw = &raw;
+		data.sample_flags |= PERF_SAMPLE_RAW;
 	}
 
 	/*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f4a13579b0e8..e9b151cde491 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1028,7 +1028,6 @@ struct perf_sample_data {
 	 * minimize the cachelines touched.
 	 */
 	u64				sample_flags;
-	struct perf_raw_record		*raw;
 	u64				period;
 
 	/*
@@ -1040,6 +1039,7 @@ struct perf_sample_data {
 	union  perf_mem_data_src	data_src;
 	u64				txn;
 	u64				addr;
+	struct perf_raw_record		*raw;
 
 	u64				type;
 	u64				ip;
@@ -1078,8 +1078,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 					 u64 addr, u64 period)
 {
 	/* remaining struct members initialized in perf_prepare_sample() */
-	data->sample_flags = 0;
-	data->raw  = NULL;
+	data->sample_flags = PERF_SAMPLE_PERIOD;
 	data->period = period;
 
 	if (addr) {
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a91f74db9fe9..04e19a857d4b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7332,7 +7332,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 		struct perf_raw_record *raw = data->raw;
 		int size;
 
-		if (raw) {
+		if (raw && (data->sample_flags & PERF_SAMPLE_RAW)) {
 			struct perf_raw_frag *frag = &raw->frag;
 			u32 sum = 0;
 
@@ -7348,6 +7348,7 @@ void perf_prepare_sample(struct perf_event_header *header,
 			frag->pad = raw->size - sum;
 		} else {
 			size = sizeof(u64);
+			data->raw = NULL;
 		}
 
 		header->size += size;
-- 
2.37.3.968.ga6b4b080e4-goog