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;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   K Prateek Nayak <kprateek.nayak@amd.com>
To:     <linux-perf-users@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <acme@kernel.org>, <peterz@infradead.org>, <mingo@redhat.com>,
        <mark.rutland@arm.com>, <alexander.shishkin@linux.intel.com>,
        <jolsa@kernel.org>, <namhyung@kernel.org>
CC:     <ravi.bangoria@amd.com>, <sandipan.das@amd.com>,
        <ananth.narayan@amd.com>, <gautham.shenoy@amd.com>,
        <eranian@google.com>
Subject: [RFC PATCH 3/4] perf: Extract building cache level for a CPU into separate function
Date:   Fri, 31 Mar 2023 10:21:16 +0530
Message-ID: <20230331045117.1266-4-kprateek.nayak@amd.com>
In-Reply-To: <20230331045117.1266-1-kprateek.nayak@amd.com>
References: <20230331045117.1266-1-kprateek.nayak@amd.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 31 Mar 2023 04:53:21.5270
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: f4ee7163-413b-4d29-a018-08db31a3da70
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: CO1NAM11FT107.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SN7PR12MB7834
X-Spam-Status: No, score=-0.2 required=5.0 tests=DKIM_SIGNED,DKIM_VALID,
        DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,RCVD_IN_DNSWL_NONE,
        RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE autolearn=unavailable
        autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

build_caches() builds the complete cache topology of the system by
iterating over all CPU, building and comparing cache levels of each CPU,
keeping only the unique ones at the end.

Extract the function that build the cache levels for a single CPU into
a separate function. Expose this function to be used elsewhere in perf
too.

Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
---
 tools/perf/util/header.c | 62 +++++++++++++++++++++++++---------------
 tools/perf/util/header.h |  4 +++
 2 files changed, 43 insertions(+), 23 deletions(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 50d66092c82b..770b0f624d7c 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1220,38 +1220,54 @@ static void cpu_cache_level__fprintf(FILE *out, struct cpu_cache_level *c)
 	fprintf(out, "L%d %-15s %8s [%s]\n", c->level, c->type, c->size, c->map);
 }
 
-#define MAX_CACHE_LVL 4
-
-static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
+/*
+ * Build caches levels for a particular CPU from the data in
+ * /sys/devices/system/cpu/cpu<cpu>/cache/
+ * The cache level data is stored in caches[] from index at
+ * *cntp.
+ */
+int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp)
 {
-	u32 i, cnt = 0;
-	u32 nr, cpu;
 	u16 level;
 
-	nr = cpu__max_cpu().cpu;
+	for (level = 0; level < MAX_CACHE_LVL; level++) {
+		struct cpu_cache_level c;
+		int err;
+		u32 i;
 
-	for (cpu = 0; cpu < nr; cpu++) {
-		for (level = 0; level < MAX_CACHE_LVL; level++) {
-			struct cpu_cache_level c;
-			int err;
+		err = cpu_cache_level__read(&c, cpu, level);
+		if (err < 0)
+			return err;
 
-			err = cpu_cache_level__read(&c, cpu, level);
-			if (err < 0)
-				return err;
+		if (err == 1)
+			break;
 
-			if (err == 1)
+		for (i = 0; i < *cntp; i++) {
+			if (cpu_cache_level__cmp(&c, &caches[i]))
 				break;
+		}
 
-			for (i = 0; i < cnt; i++) {
-				if (cpu_cache_level__cmp(&c, &caches[i]))
-					break;
-			}
+		if (i == *cntp) {
+			caches[*cntp] = c;
+			*cntp = *cntp + 1;
+		} else
+			cpu_cache_level__free(&c);
+	}
 
-			if (i == cnt)
-				caches[cnt++] = c;
-			else
-				cpu_cache_level__free(&c);
-		}
+	return 0;
+}
+
+static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
+{
+	u32 nr, cpu, cnt = 0;
+
+	nr = cpu__max_cpu().cpu;
+
+	for (cpu = 0; cpu < nr; cpu++) {
+		int ret = build_caches_for_cpu(cpu, caches, &cnt);
+
+		if (ret)
+			return ret;
 	}
 	*cntp = cnt;
 	return 0;
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index e3861ae62172..94cf2ffb6e60 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -177,7 +177,11 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size);
 int write_padded(struct feat_fd *fd, const void *bf,
 		 size_t count, size_t count_aligned);
 
+#define MAX_CACHE_LVL 4
+
 int is_cpu_online(unsigned int cpu);
+int build_caches_for_cpu(u32 cpu, struct cpu_cache_level caches[], u32 *cntp);
+
 /*
  * arch specific callback
  */
-- 
2.34.1