[PATCH 01/52] perf c2c: Introduce c2c_decode_stats function

From: Arnaldo Carvalho de Melo
Date: Thu Oct 20 2016 - 11:04:54 EST


From: Jiri Olsa <jolsa@xxxxxxxxxx>

Introducing c2c_decode_stats function, which decodes
data_src data into new struct c2c_stats.

Signed-off-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Original-patch-by: Dick Fowles <rfowles@xxxxxxxxxx>
Original-patch-by: Don Zickus <dzickus@xxxxxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Don Zickus <dzickus@xxxxxxxxxx>
Cc: Joe Mario <jmario@xxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Link: http://lkml.kernel.org/r/1474558645-19956-3-git-send-email-jolsa@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/util/mem-events.c | 98 ++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/mem-events.h | 36 ++++++++++++++++
2 files changed, 134 insertions(+)

diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index bbc368e7d1e4..502fcee91973 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -9,6 +9,7 @@
#include "mem-events.h"
#include "debug.h"
#include "symbol.h"
+#include "sort.h"

unsigned int perf_mem_events__loads_ldlat = 30;

@@ -268,3 +269,100 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in

return i;
}
+
+int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
+{
+ union perf_mem_data_src *data_src = &mi->data_src;
+ u64 daddr = mi->daddr.addr;
+ u64 op = data_src->mem_op;
+ u64 lvl = data_src->mem_lvl;
+ u64 snoop = data_src->mem_snoop;
+ u64 lock = data_src->mem_lock;
+ int err = 0;
+
+#define P(a, b) PERF_MEM_##a##_##b
+
+ stats->nr_entries++;
+
+ if (lock & P(LOCK, LOCKED)) stats->locks++;
+
+ if (op & P(OP, LOAD)) {
+ /* load */
+ stats->load++;
+
+ if (!daddr) {
+ stats->ld_noadrs++;
+ return -1;
+ }
+
+ if (lvl & P(LVL, HIT)) {
+ if (lvl & P(LVL, UNC)) stats->ld_uncache++;
+ if (lvl & P(LVL, IO)) stats->ld_io++;
+ if (lvl & P(LVL, LFB)) stats->ld_fbhit++;
+ if (lvl & P(LVL, L1 )) stats->ld_l1hit++;
+ if (lvl & P(LVL, L2 )) stats->ld_l2hit++;
+ if (lvl & P(LVL, L3 )) {
+ if (snoop & P(SNOOP, HITM))
+ stats->lcl_hitm++;
+ else
+ stats->ld_llchit++;
+ }
+
+ if (lvl & P(LVL, LOC_RAM)) {
+ stats->lcl_dram++;
+ if (snoop & P(SNOOP, HIT))
+ stats->ld_shared++;
+ else
+ stats->ld_excl++;
+ }
+
+ if ((lvl & P(LVL, REM_RAM1)) ||
+ (lvl & P(LVL, REM_RAM2))) {
+ stats->rmt_dram++;
+ if (snoop & P(SNOOP, HIT))
+ stats->ld_shared++;
+ else
+ stats->ld_excl++;
+ }
+ }
+
+ if ((lvl & P(LVL, REM_CCE1)) ||
+ (lvl & P(LVL, REM_CCE2))) {
+ if (snoop & P(SNOOP, HIT))
+ stats->rmt_hit++;
+ else if (snoop & P(SNOOP, HITM))
+ stats->rmt_hitm++;
+ }
+
+ if ((lvl & P(LVL, MISS)))
+ stats->ld_miss++;
+
+ } else if (op & P(OP, STORE)) {
+ /* store */
+ stats->store++;
+
+ if (!daddr) {
+ stats->st_noadrs++;
+ return -1;
+ }
+
+ if (lvl & P(LVL, HIT)) {
+ if (lvl & P(LVL, UNC)) stats->st_uncache++;
+ if (lvl & P(LVL, L1 )) stats->st_l1hit++;
+ }
+ if (lvl & P(LVL, MISS))
+ if (lvl & P(LVL, L1)) stats->st_l1miss++;
+ } else {
+ /* unparsable data_src? */
+ stats->noparse++;
+ return -1;
+ }
+
+ if (!mi->daddr.map || !mi->iaddr.map) {
+ stats->nomap++;
+ return -1;
+ }
+
+#undef P
+ return err;
+}
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 7f69bf9d789d..e111a2a2b18f 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -2,6 +2,10 @@
#define __PERF_MEM_EVENTS_H

#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <linux/types.h>
+#include "stat.h"

struct perf_mem_event {
bool record;
@@ -33,4 +37,36 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info);

int perf_script__meminfo_scnprintf(char *bf, size_t size, struct mem_info *mem_info);

+struct c2c_stats {
+ u32 nr_entries;
+
+ u32 locks; /* count of 'lock' transactions */
+ u32 store; /* count of all stores in trace */
+ u32 st_uncache; /* stores to uncacheable address */
+ u32 st_noadrs; /* cacheable store with no address */
+ u32 st_l1hit; /* count of stores that hit L1D */
+ u32 st_l1miss; /* count of stores that miss L1D */
+ u32 load; /* count of all loads in trace */
+ u32 ld_excl; /* exclusive loads, rmt/lcl DRAM - snp none/miss */
+ u32 ld_shared; /* shared loads, rmt/lcl DRAM - snp hit */
+ u32 ld_uncache; /* loads to uncacheable address */
+ u32 ld_io; /* loads to io address */
+ u32 ld_miss; /* loads miss */
+ u32 ld_noadrs; /* cacheable load with no address */
+ u32 ld_fbhit; /* count of loads hitting Fill Buffer */
+ u32 ld_l1hit; /* count of loads that hit L1D */
+ u32 ld_l2hit; /* count of loads that hit L2D */
+ u32 ld_llchit; /* count of loads that hit LLC */
+ u32 lcl_hitm; /* count of loads with local HITM */
+ u32 rmt_hitm; /* count of loads with remote HITM */
+ u32 rmt_hit; /* count of loads with remote hit clean; */
+ u32 lcl_dram; /* count of loads miss to local DRAM */
+ u32 rmt_dram; /* count of loads miss to remote DRAM */
+ u32 nomap; /* count of load/stores with no phys adrs */
+ u32 noparse; /* count of unparsable data sources */
+};
+
+struct hist_entry;
+int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi);
+
#endif /* __PERF_MEM_EVENTS_H */
--
2.7.4