perf report: Support instruction latency

The instruction latency information can be recorded on some platforms,
e.g., the Intel Sapphire Rapids server. With both memory latency
(weight) and the new instruction latency information, users can easily
locate the expensive load instructions, and also understand the time
spent in different stages. The users can optimize their applications in
different pipeline stages.

The 'weight' field is shared among different architectures. Reusing the
'weight' field may impacts other architectures. Add a new field to store
the instruction latency.

Like the 'weight' support, introduce a 'ins_lat' for the global
instruction latency, and a 'local_ins_lat' for the local instruction
latency version.

Add new sort functions, INSTR Latency and Local INSTR Latency,
accordingly.

Add local_ins_lat to the default_mem_sort_order[].

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-7-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 9 insertions, 3 deletions

diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 4038b086cb80..c82f5fc26af8 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -209,6 +209,8 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
+	hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
+	hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
 	if (symbol_conf.nanosecs)
 		hists__new_col_len(hists, HISTC_TIME, 16);
 	else
@@ -287,12 +289,13 @@ static long hist_time(unsigned long htime)
 }
 
 static void he_stat__add_period(struct he_stat *he_stat, u64 period,
-				u64 weight)
+				u64 weight, u64 ins_lat)
 {
 
 	he_stat->period		+= period;
 	he_stat->weight		+= weight;
 	he_stat->nr_events	+= 1;
+	he_stat->ins_lat	+= ins_lat;
 }
 
 static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
@@ -304,6 +307,7 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_guest_us	+= src->period_guest_us;
 	dest->nr_events		+= src->nr_events;
 	dest->weight		+= src->weight;
+	dest->ins_lat		+= src->ins_lat;
 }
 
 static void he_stat__decay(struct he_stat *he_stat)
@@ -592,6 +596,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 	int64_t cmp;
 	u64 period = entry->stat.period;
 	u64 weight = entry->stat.weight;
+	u64 ins_lat = entry->stat.ins_lat;
 	bool leftmost = true;
 
 	p = &hists->entries_in->rb_root.rb_node;
@@ -610,11 +615,11 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period, weight);
+				he_stat__add_period(&he->stat, period, weight, ins_lat);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
-				he_stat__add_period(he->stat_acc, period, weight);
+				he_stat__add_period(he->stat_acc, period, weight, ins_lat);
 
 			/*
 			 * This mem info was allocated from sample__resolve_mem
@@ -725,6 +730,7 @@ __hists__add_entry(struct hists *hists,
 			.nr_events = 1,
 			.period	= sample->period,
 			.weight = sample->weight,
+			.ins_lat = sample->ins_lat,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,