tools headers UAPI: Add new macros for mem_hops field to perf_event.h

Add new macros for mem_hops field which can be used to represent
remote-node, socket and board level details.

Currently the code had macro for HOPS_0 which, corresponds to data
coming from another core but same node.  Add new macros for HOPS_1 to
HOPS_3 to represent remote-node, socket and board level data.

Also add corresponding strings in the mem_hops array to represent
mem_hop field data in perf_mem__lvl_scnprintf function

Incase mem_hops field is used, PERF_MEM_LVLNUM field also need to be set
inorder to represent the data source. Hence printing data source via
PERF_MEM_LVL field can be skip in that scenario.

For ex: Encodings for mem_hops fields with L2 cache:

  L2                      - local L2
  L2 | REMOTE | HOPS_0    - remote core, same node L2
  L2 | REMOTE | HOPS_1    - remote node, same socket L2
  L2 | REMOTE | HOPS_2    - remote socket, same board L2
  L2 | REMOTE | HOPS_3    - remote board L2
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lore.kernel.org/lkml/20211206091749.87585-3-kjain@linux.ibm.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/include/uapi/linux/perf_event.h

@@ -1332,7 +1332,10 @@ union perf_mem_data_src {
 
 /* hop level */
 #define PERF_MEM_HOPS_0		0x01 /* remote core, same node */
-/* 2-7 available */
+#define PERF_MEM_HOPS_1         0x02 /* remote node, same socket */
+#define PERF_MEM_HOPS_2         0x03 /* remote socket, same board */
+#define PERF_MEM_HOPS_3         0x04 /* remote board */
+/* 5-7 available */
 #define PERF_MEM_HOPS_SHIFT	43
 
 #define PERF_MEM_S(a, s) \

tools/perf/util/mem-events.c

@@ -309,6 +309,9 @@ static const char * const mem_hops[] = {
 	 * to be set with mem_hops field.
 	 */
 	"core, same node",
+	"node, same socket",
+	"socket, same board",
+	"board",
 };
 
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
@@ -316,7 +319,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	size_t i, l = 0;
 	u64 m =  PERF_MEM_LVL_NA;
 	u64 hit, miss;
-	int printed;
+	int printed = 0;
 
 	if (mem_info)
 		m  = mem_info->data_src.mem_lvl;
@@ -335,18 +338,22 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 		l += 7;
 	}
 
-	if (mem_info && mem_info->data_src.mem_hops)
+	/*
+	 * Incase mem_hops field is set, we can skip printing data source via
+	 * PERF_MEM_LVL namespace.
+	 */
+	if (mem_info && mem_info->data_src.mem_hops) {
 		l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]);
-
-	printed = 0;
-	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (printed++) {
-			strcat(out, " or ");
-			l += 4;
+	} else {
+		for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+			if (!(m & 0x1))
+				continue;
+			if (printed++) {
+				strcat(out, " or ");
+				l += 4;
+			}
+			l += scnprintf(out + l, sz - l, mem_lvl[i]);
 		}
-		l += scnprintf(out + l, sz - l, mem_lvl[i]);
 	}
 
 	if (mem_info && mem_info->data_src.mem_lvl_num) {