perf report: Support Retire Latency

The Retire Latency field is added in the var3_w of the
PERF_SAMPLE_WEIGHT_STRUCT. The Retire Latency reports pipeline stall of
this instruction compared to the previous instruction in cycles.  That's
quite useful to display the information with perf mem report.

The p_stage_cyc for Power is also from the var3_w. Union the p_stage_cyc
and retire_lat to share the code.

Implement X86 specific codes to display the X86 specific header.

Add a new sort key retire_lat for the Retire Latency.

Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20230104201349.1451191-8-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

5 files changed, 30 insertions, 1 deletions

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 9b0c0dbf9a77..c242e8da6b1a 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -115,6 +115,8 @@ OPTIONS
 	- p_stage_cyc: On powerpc, this presents the number of cycles spent in a
 	  pipeline stage. And currently supported only on powerpc.
 	- addr: (Full) virtual address of the sampled instruction
+	- retire_lat: On X86, this reports pipeline stall of this instruction compared
+	  to the previous instruction in cycles. And currently supported only on X86
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index a3acefe6d0c6..37b3feb53e8d 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -89,6 +89,7 @@ void arch_perf_parse_sample_weight(struct perf_sample *data,
 	else {
 		data->weight = weight.var1_dw;
 		data->ins_lat = weight.var2_w;
+		data->retire_lat = weight.var3_w;
 	}
 }
 
@@ -102,3 +103,22 @@ void arch_perf_synthesize_sample_weight(const struct perf_sample *data,
 		*array |= ((u64)data->ins_lat << 32);
 	}
 }
+
+const char *arch_perf_header_entry(const char *se_header)
+{
+	if (!strcmp(se_header, "Local Pipeline Stage Cycle"))
+		return "Local Retire Latency";
+	else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+		return "Retire Latency";
+
+	return se_header;
+}
+
+int arch_support_sort_key(const char *sort_key)
+{
+	if (!strcmp(sort_key, "p_stage_cyc"))
+		return 1;
+	if (!strcmp(sort_key, "local_p_stage_cyc"))
+		return 1;
+	return 0;
+}
diff --git a/tools/perf/util/sample.h b/tools/perf/util/sample.h
index 60ec79d4eea4..33b08e0ac746 100644
--- a/tools/perf/util/sample.h
+++ b/tools/perf/util/sample.h
@@ -92,7 +92,10 @@ struct perf_sample {
 	u8  cpumode;
 	u16 misc;
 	u16 ins_lat;
-	u16 p_stage_cyc;
+	union {
+		u16 p_stage_cyc;
+		u16 retire_lat;
+	};
 	bool no_hw_idx;		/* No hw_idx collected in branch_stack */
 	char insn[MAX_INSN];
 	void *raw_data;
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d7d0f997873a..4a648231fe72 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2133,6 +2133,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
 	DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
 	DIM(SORT_ADDR, "addr", sort_addr),
+	DIM(SORT_LOCAL_RETIRE_LAT, "local_retire_lat", sort_local_p_stage_cyc),
+	DIM(SORT_GLOBAL_RETIRE_LAT, "retire_lat", sort_global_p_stage_cyc),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 921715e6aec4..9a91d0df2833 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -237,6 +237,8 @@ enum sort_type {
 	SORT_LOCAL_PIPELINE_STAGE_CYC,
 	SORT_GLOBAL_PIPELINE_STAGE_CYC,
 	SORT_ADDR,
+	SORT_LOCAL_RETIRE_LAT,
+	SORT_GLOBAL_RETIRE_LAT,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,