linux-kernel - [PATCH 4/6] perf: Use sample

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 31 Aug 2022 07:55:12 -0700
From:   kan.liang@...ux.intel.com
To:     peterz@...radead.org, acme@...nel.org, mingo@...hat.com,
        eranian@...gle.com, mpe@...erman.id.au,
        linux-kernel@...r.kernel.org
Cc:     ak@...ux.intel.com, andreas.kogler.0x@...il.com,
        atrajeev@...ux.vnet.ibm.com, Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH 4/6] perf: Use sample_flags for weight

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

Use the new sample_flags to indicate whether the weight field is filled
by the PMU driver.

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

Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
 arch/powerpc/perf/core-book3s.c |  5 +++--
 arch/x86/events/intel/ds.c      | 10 +++++++---
 include/linux/perf_event.h      |  3 +--
 kernel/events/core.c            |  3 +++
 4 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 1ad1efdb33f9..a5c95a2006ea 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2305,9 +2305,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			ppmu->get_mem_data_src(&data.data_src, ppmu->flags, regs);
 
 		if (event->attr.sample_type & PERF_SAMPLE_WEIGHT_TYPE &&
-						ppmu->get_mem_weight)
+						ppmu->get_mem_weight) {
 			ppmu->get_mem_weight(&data.weight.full, event->attr.sample_type);
-
+			data.sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+		}
 		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);
 	} else if (period) {
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index d5f3007af59d..e80632a575d1 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1532,8 +1532,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
-	if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE))
+	if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) {
 		data->weight.full = pebs->lat;
+		data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+	}
 
 	/*
 	 * data.data_src encodes the data source
@@ -1625,9 +1627,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
-		if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll)
+		if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) {
 			data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning);
-
+			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+		}
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
 			data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
 							      pebs->ax);
@@ -1769,6 +1772,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 				data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?:
 					intel_get_tsx_weight(meminfo->tsx_tuning);
 			}
+			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
 
 		if (sample_type & PERF_SAMPLE_DATA_SRC)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 2aec1765b3d5..c030d1d1c675 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1011,7 +1011,6 @@ struct perf_sample_data {
 	u64				addr;
 	struct perf_raw_record		*raw;
 	u64				period;
-	union perf_sample_weight	weight;
 	u64				txn;
 	union  perf_mem_data_src	data_src;
 
@@ -1020,6 +1019,7 @@ struct perf_sample_data {
 	 * perf_{prepare,output}_sample().
 	 */
 	struct perf_branch_stack	*br_stack;
+	union perf_sample_weight	weight;
 
 	u64				type;
 	u64				ip;
@@ -1062,7 +1062,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->addr = addr;
 	data->raw  = NULL;
 	data->period = period;
-	data->weight.full = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 104c0c9f4e6f..f0af45db02b3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7408,6 +7408,9 @@ void perf_prepare_sample(struct perf_event_header *header,
 		header->size += size;
 	}
 
+	if (filtered_sample_type & PERF_SAMPLE_WEIGHT_TYPE)
+		data->weight.full = 0;
+
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
-- 
2.35.1