Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.32 as permitted sender) client-ip=23.128.96.32;
Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 216.228.117.161 as permitted sender) receiver=protection.outlook.com;
 client-ip=216.228.117.161; helo=mail.nvidia.com; pr=C
From:   Besar Wicaksono <bwicaksono@nvidia.com>
To:     <james.clark@arm.com>, <mike.leach@linaro.org>,
        <suzuki.poulose@arm.com>
CC:     <linux-arm-kernel@lists.infradead.org>,
        <linux-kernel@vger.kernel.org>, <coresight@lists.linaro.org>,
        <linux-tegra@vger.kernel.org>, <treding@nvidia.com>,
        <jonathanh@nvidia.com>, <vsethi@nvidia.com>, <rwiley@nvidia.com>,
        <ywan@nvidia.com>, Besar Wicaksono <bwicaksono@nvidia.com>
Subject: [PATCH] perf cs-etm: Fix missing decoder for per-process trace
Date:   Tue, 19 Sep 2023 17:45:53 -0500
Message-ID: <20230919224553.1658-1-bwicaksono@nvidia.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 19 Sep 2023 22:47:18.1600
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: c75578e1-4b71-4fcd-6374-08dbb96260b0
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[216.228.117.161];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: MWH0EPF000971E3.namprd02.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM6PR12MB4388
X-Spam-Status: No, score=-0.9 required=5.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED,
	DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,
	MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS autolearn=unavailable
	autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on agentk.vger.email
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (agentk.vger.email [0.0.0.0]); Tue, 19 Sep 2023 15:47:34 -0700 (PDT)

The decoder creation for raw trace uses metadata from the first CPU.
On per-process/per-thread traces, the first CPU is CPU0. If CPU0 trace
is not enabled, its metadata will be marked unused and the decoder is
not created. Perf report dump skips the decoding part because the
decoder is missing.

To fix this, use metadata of the CPU associated with sample object.

Signed-off-by: Besar Wicaksono <bwicaksono@nvidia.com>
---
 tools/perf/util/cs-etm.c | 130 +++++++++++++++++++++++----------------
 1 file changed, 77 insertions(+), 53 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 9729d006550d..3c3179a5eac6 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -640,71 +640,94 @@ static void cs_etm__packet_dump(const char *pkt_string)
 	fflush(stdout);
 }
 
-static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int idx,
-					  u32 etmidr)
+static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_param,
+					  u64 *metadata, u32 etmidr)
 {
-	u64 **metadata = etm->metadata;
-
-	t_params[idx].protocol = cs_etm__get_v7_protocol_version(etmidr);
-	t_params[idx].etmv3.reg_ctrl = metadata[idx][CS_ETM_ETMCR];
-	t_params[idx].etmv3.reg_trc_id = metadata[idx][CS_ETM_ETMTRACEIDR];
+	t_param->protocol = cs_etm__get_v7_protocol_version(etmidr);
+	t_param->etmv3.reg_ctrl = metadata[CS_ETM_ETMCR];
+	t_param->etmv3.reg_trc_id = metadata[CS_ETM_ETMTRACEIDR];
 }
 
-static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int idx)
+static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_param,
+					  u64 *metadata)
 {
-	u64 **metadata = etm->metadata;
+	t_param->protocol = CS_ETM_PROTO_ETMV4i;
+	t_param->etmv4.reg_idr0 = metadata[CS_ETMV4_TRCIDR0];
+	t_param->etmv4.reg_idr1 = metadata[CS_ETMV4_TRCIDR1];
+	t_param->etmv4.reg_idr2 = metadata[CS_ETMV4_TRCIDR2];
+	t_param->etmv4.reg_idr8 = metadata[CS_ETMV4_TRCIDR8];
+	t_param->etmv4.reg_configr = metadata[CS_ETMV4_TRCCONFIGR];
+	t_param->etmv4.reg_traceidr = metadata[CS_ETMV4_TRCTRACEIDR];
+}
 
-	t_params[idx].protocol = CS_ETM_PROTO_ETMV4i;
-	t_params[idx].etmv4.reg_idr0 = metadata[idx][CS_ETMV4_TRCIDR0];
-	t_params[idx].etmv4.reg_idr1 = metadata[idx][CS_ETMV4_TRCIDR1];
-	t_params[idx].etmv4.reg_idr2 = metadata[idx][CS_ETMV4_TRCIDR2];
-	t_params[idx].etmv4.reg_idr8 = metadata[idx][CS_ETMV4_TRCIDR8];
-	t_params[idx].etmv4.reg_configr = metadata[idx][CS_ETMV4_TRCCONFIGR];
-	t_params[idx].etmv4.reg_traceidr = metadata[idx][CS_ETMV4_TRCTRACEIDR];
+static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_param,
+					u64 *metadata)
+{
+	t_param->protocol = CS_ETM_PROTO_ETE;
+	t_param->ete.reg_idr0 = metadata[CS_ETE_TRCIDR0];
+	t_param->ete.reg_idr1 = metadata[CS_ETE_TRCIDR1];
+	t_param->ete.reg_idr2 = metadata[CS_ETE_TRCIDR2];
+	t_param->ete.reg_idr8 = metadata[CS_ETE_TRCIDR8];
+	t_param->ete.reg_configr = metadata[CS_ETE_TRCCONFIGR];
+	t_param->ete.reg_traceidr = metadata[CS_ETE_TRCTRACEIDR];
+	t_param->ete.reg_devarch = metadata[CS_ETE_TRCDEVARCH];
 }
 
-static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_params,
-					  struct cs_etm_auxtrace *etm, int idx)
+static int cs_etm__set_trace_param(struct cs_etm_trace_params *t_param,
+				   u64 *metadata)
 {
-	u64 **metadata = etm->metadata;
+	u32 etmidr;
+	u64 architecture = metadata[CS_ETM_MAGIC];
+
+	switch (architecture) {
+	case __perf_cs_etmv3_magic:
+		etmidr = metadata[CS_ETM_ETMIDR];
+		cs_etm__set_trace_param_etmv3(t_param, metadata, etmidr);
+		break;
+	case __perf_cs_etmv4_magic:
+		cs_etm__set_trace_param_etmv4(t_param, metadata);
+		break;
+	case __perf_cs_ete_magic:
+		cs_etm__set_trace_param_ete(t_param, metadata);
+		break;
+	default:
+		return -EINVAL;
+	}
 
-	t_params[idx].protocol = CS_ETM_PROTO_ETE;
-	t_params[idx].ete.reg_idr0 = metadata[idx][CS_ETE_TRCIDR0];
-	t_params[idx].ete.reg_idr1 = metadata[idx][CS_ETE_TRCIDR1];
-	t_params[idx].ete.reg_idr2 = metadata[idx][CS_ETE_TRCIDR2];
-	t_params[idx].ete.reg_idr8 = metadata[idx][CS_ETE_TRCIDR8];
-	t_params[idx].ete.reg_configr = metadata[idx][CS_ETE_TRCCONFIGR];
-	t_params[idx].ete.reg_traceidr = metadata[idx][CS_ETE_TRCTRACEIDR];
-	t_params[idx].ete.reg_devarch = metadata[idx][CS_ETE_TRCDEVARCH];
+	return 0;
 }
 
 static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params,
 				     struct cs_etm_auxtrace *etm,
+				     bool formatted,
+				     int sample_cpu,
 				     int decoders)
 {
-	int i;
-	u32 etmidr;
-	u64 architecture;
-
-	for (i = 0; i < decoders; i++) {
-		architecture = etm->metadata[i][CS_ETM_MAGIC];
+	int i, ret;
+	struct cs_etm_trace_params *t_param;
+	u64 *metadata;
 
-		switch (architecture) {
-		case __perf_cs_etmv3_magic:
-			etmidr = etm->metadata[i][CS_ETM_ETMIDR];
-			cs_etm__set_trace_param_etmv3(t_params, etm, i, etmidr);
-			break;
-		case __perf_cs_etmv4_magic:
-			cs_etm__set_trace_param_etmv4(t_params, etm, i);
-			break;
-		case __perf_cs_ete_magic:
-			cs_etm__set_trace_param_ete(t_params, etm, i);
-			break;
-		default:
+	if (!formatted) {
+		/*
+		 * There is only one decoder when unformatted. Use metadata of
+		 * sample AUX cpu.
+		 */
+		t_param = t_params;
+		metadata = get_cpu_data(etm, sample_cpu);
+		if (!metadata) {
+			pr_err("CS_ETM: invalid sample CPU: %d\n", sample_cpu);
 			return -EINVAL;
 		}
+
+		return cs_etm__set_trace_param(t_param, metadata);
+	}
+
+	for (i = 0; i < decoders; i++) {
+		t_param = &t_params[i];
+		metadata = etm->metadata[i];
+		ret = cs_etm__set_trace_param(t_param, metadata);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -1016,7 +1039,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
 }
 
 static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
-						bool formatted)
+						bool formatted, int sample_cpu)
 {
 	struct cs_etm_decoder_params d_params;
 	struct cs_etm_trace_params  *t_params = NULL;
@@ -1041,7 +1064,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 	if (!t_params)
 		goto out_free;
 
-	if (cs_etm__init_trace_params(t_params, etm, decoders))
+	if (cs_etm__init_trace_params(t_params, etm, formatted, sample_cpu, decoders))
 		goto out_free;
 
 	/* Set decoder parameters to decode trace packets */
@@ -1081,14 +1104,15 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm,
 			       struct auxtrace_queue *queue,
 			       unsigned int queue_nr,
-			       bool formatted)
+			       bool formatted,
+			       int sample_cpu)
 {
 	struct cs_etm_queue *etmq = queue->priv;
 
 	if (list_empty(&queue->head) || etmq)
 		return 0;
 
-	etmq = cs_etm__alloc_queue(etm, formatted);
+	etmq = cs_etm__alloc_queue(etm, formatted, sample_cpu);
 
 	if (!etmq)
 		return -ENOMEM;
@@ -2816,7 +2840,7 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session,
 		 * formatted in piped mode (true).
 		 */
 		err = cs_etm__setup_queue(etm, &etm->queues.queue_array[idx],
-					  idx, true);
+					  idx, true, -1);
 		if (err)
 			return err;
 
@@ -3022,7 +3046,7 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o
 		idx = auxtrace_event->idx;
 		formatted = !(aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW);
 		return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx],
-					   idx, formatted);
+					   idx, formatted, sample->cpu);
 	}
 
 	/* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */
-- 
2.34.1