[RFC,v2,3/4] perf: Extract building cache level for a CPU into separate function

Message ID 20230405170906.2510-4-kprateek.nayak@amd.com
State New
Headers
Series perf stat: Add option to aggregate data based on the cache topology |

Commit Message

K Prateek Nayak April 5, 2023, 5:09 p.m. UTC
  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(-)
  

Patch

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 2daaee5065ef..357879dd8333 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1227,38 +1227,54 @@  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
  */