perf sort: Include global and local variants for p_stage_cyc sort key

Sort key 'p_stage_cyc' is used to present the latency cycles spent in
pipeline stages.

perf has local 'p_stage_cyc' sort key to display this info. There is no
global variant available for this sort key. The local variant shows
latency in a single sample, whereas the global value will be useful to
present the total latency (sum of latencies) in the hist entry. It
represents the latency number multiplied by the number of samples.

Add global ('p_stage_cyc') and local variant ('local_p_stage_cyc') for
this sort key. Use 'local_p_stage_cyc' as default option for "mem" sort
mode.

Also add this to the list of dynamic sort keys and made the
"dynamic_headers" and "arch_specific_sort_keys" as static.
Reported-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Athira Jajeev <atrajeev@linux.vnet.ibm.com>
Tested-by: Nageswara R Sastry <rnsastry@linux.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/r/20211203022038.48240-1-atrajeev@linux.vnet.ibm.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/hist.c

@@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	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);
-	hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13);
+	hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
+	hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
+
 	if (symbol_conf.nanosecs)
 		hists__new_col_len(hists, HISTC_TIME, 16);
 	else

tools/perf/util/hist.h

@@ -75,7 +75,8 @@ enum hist_column {
 	HISTC_MEM_BLOCKED,
 	HISTC_LOCAL_INS_LAT,
 	HISTC_GLOBAL_INS_LAT,
-	HISTC_P_STAGE_CYC,
+	HISTC_LOCAL_P_STAGE_CYC,
+	HISTC_GLOBAL_P_STAGE_CYC,
 	HISTC_NR_COLS, /* Last entry */
 };
 

tools/perf/util/sort.c

@@ -37,7 +37,7 @@ const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char	*parent_pattern = default_parent_pattern;
 const char	*default_sort_order = "comm,dso,symbol";
 const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
-const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc";
+const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc";
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";
 const char	default_tracepoint_sort_order[] = "trace";
@@ -46,8 +46,8 @@ const char	*field_order;
 regex_t		ignore_callees_regex;
 int		have_ignore_callees = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
-const char	*dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"};
-const char	*arch_specific_sort_keys[] = {"p_stage_cyc"};
+static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"};
+static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"};
 
 /*
  * Replaces all occurrences of a char used with the:
@@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = {
 };
 
 static int64_t
-sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	return left->p_stage_cyc - right->p_stage_cyc;
 }
 
+static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*u", width,
+			he->p_stage_cyc * he->stat.nr_events);
+}
+
+
 static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
 	return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
 }
 
-struct sort_entry sort_p_stage_cyc = {
-	.se_header      = "Pipeline Stage Cycle",
-	.se_cmp         = sort__global_p_stage_cyc_cmp,
+struct sort_entry sort_local_p_stage_cyc = {
+	.se_header      = "Local Pipeline Stage Cycle",
+	.se_cmp         = sort__p_stage_cyc_cmp,
 	.se_snprintf	= hist_entry__p_stage_cyc_snprintf,
-	.se_width_idx	= HISTC_P_STAGE_CYC,
+	.se_width_idx	= HISTC_LOCAL_P_STAGE_CYC,
+};
+
+struct sort_entry sort_global_p_stage_cyc = {
+	.se_header      = "Pipeline Stage Cycle",
+	.se_cmp         = sort__p_stage_cyc_cmp,
+	.se_snprintf    = hist_entry__global_p_stage_cyc_snprintf,
+	.se_width_idx   = HISTC_GLOBAL_P_STAGE_CYC,
 };
 
 struct sort_entry sort_mem_daddr_sym = {
@@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
 	DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
 	DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
-	DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc),
+	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),
 };
 
 #undef DIM

tools/perf/util/sort.h

@@ -235,7 +235,8 @@ enum sort_type {
 	SORT_CODE_PAGE_SIZE,
 	SORT_LOCAL_INS_LAT,
 	SORT_GLOBAL_INS_LAT,
-	SORT_PIPELINE_STAGE_CYC,
+	SORT_LOCAL_PIPELINE_STAGE_CYC,
+	SORT_GLOBAL_PIPELINE_STAGE_CYC,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,