1 files changed, 157 insertions, 105 deletions

diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index c37a78677955..f8b6ae557d8b 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -23,6 +23,8 @@
 #include "util/time-utils.h"
 #include "util/annotate.h"
 #include "util/map.h"
+#include "util/spark.h"
+#include "util/block-info.h"
 #include <linux/err.h>
 #include <linux/zalloc.h>
 #include <subcmd/pager.h>
@@ -53,6 +55,7 @@ enum {
 	PERF_HPP_DIFF__FORMULA,
 	PERF_HPP_DIFF__DELTA_ABS,
 	PERF_HPP_DIFF__CYCLES,
+	PERF_HPP_DIFF__CYCLES_HIST,
 
 	PERF_HPP_DIFF__MAX_INDEX
 };
@@ -87,6 +90,7 @@ static bool force;
 static bool show_period;
 static bool show_formula;
 static bool show_baseline_only;
+static bool cycles_hist;
 static unsigned int sort_compute = 1;
 
 static s64 compute_wdiff_w1;
@@ -95,8 +99,6 @@ static s64 compute_wdiff_w2;
 static const char		*cpu_list;
 static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
 
-static struct addr_location dummy_al;
-
 enum {
 	COMPUTE_DELTA,
 	COMPUTE_RATIO,
@@ -164,6 +166,10 @@ static struct header_column {
 	[PERF_HPP_DIFF__CYCLES] = {
 		.name  = "[Program Block Range] Cycles Diff",
 		.width = 70,
+	},
+	[PERF_HPP_DIFF__CYCLES_HIST] = {
+		.name  = "stddev/Hist",
+		.width = NUM_SPARKS + 9,
 	}
 };
 
@@ -420,7 +426,8 @@ static int diff__process_sample_event(struct perf_tool *tool,
 			goto out_put;
 		}
 
-		hist__account_cycles(sample->branch_stack, &al, sample, false);
+		hist__account_cycles(sample->branch_stack, &al, sample, false,
+				     NULL);
 	}
 
 	/*
@@ -530,41 +537,6 @@ static void hists__baseline_only(struct hists *hists)
 	}
 }
 
-static int64_t block_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
-			 struct hist_entry *left, struct hist_entry *right)
-{
-	struct block_info *bi_l = left->block_info;
-	struct block_info *bi_r = right->block_info;
-	int cmp;
-
-	if (!bi_l->sym || !bi_r->sym) {
-		if (!bi_l->sym && !bi_r->sym)
-			return 0;
-		else if (!bi_l->sym)
-			return -1;
-		else
-			return 1;
-	}
-
-	if (bi_l->sym == bi_r->sym) {
-		if (bi_l->start == bi_r->start) {
-			if (bi_l->end == bi_r->end)
-				return 0;
-			else
-				return (int64_t)(bi_r->end - bi_l->end);
-		} else
-			return (int64_t)(bi_r->start - bi_l->start);
-	} else {
-		cmp = strcmp(bi_l->sym->name, bi_r->sym->name);
-		return cmp;
-	}
-
-	if (bi_l->sym->start != bi_r->sym->start)
-		return (int64_t)(bi_r->sym->start - bi_l->sym->start);
-
-	return (int64_t)(bi_r->sym->end - bi_l->sym->end);
-}
-
 static int64_t block_cycles_diff_cmp(struct hist_entry *left,
 				     struct hist_entry *right)
 {
@@ -575,8 +547,8 @@ static int64_t block_cycles_diff_cmp(struct hist_entry *left,
 	if (!pairs_left && !pairs_right)
 		return 0;
 
-	l = labs(left->diff.cycles);
-	r = labs(right->diff.cycles);
+	l = llabs(left->diff.cycles);
+	r = llabs(right->diff.cycles);
 	return r - l;
 }
 
@@ -593,64 +565,13 @@ static void init_block_hist(struct block_hist *bh)
 
 	INIT_LIST_HEAD(&bh->block_fmt.list);
 	INIT_LIST_HEAD(&bh->block_fmt.sort_list);
-	bh->block_fmt.cmp = block_cmp;
+	bh->block_fmt.cmp = block_info__cmp;
 	bh->block_fmt.sort = block_sort;
 	perf_hpp_list__register_sort_field(&bh->block_list,
 					   &bh->block_fmt);
 	bh->valid = true;
 }
 
-static void init_block_info(struct block_info *bi, struct symbol *sym,
-			    struct cyc_hist *ch, int offset)
-{
-	bi->sym = sym;
-	bi->start = ch->start;
-	bi->end = offset;
-	bi->cycles = ch->cycles;
-	bi->cycles_aggr = ch->cycles_aggr;
-	bi->num = ch->num;
-	bi->num_aggr = ch->num_aggr;
-}
-
-static int process_block_per_sym(struct hist_entry *he)
-{
-	struct annotation *notes;
-	struct cyc_hist *ch;
-	struct block_hist *bh;
-
-	if (!he->ms.map || !he->ms.sym)
-		return 0;
-
-	notes = symbol__annotation(he->ms.sym);
-	if (!notes || !notes->src || !notes->src->cycles_hist)
-		return 0;
-
-	bh = container_of(he, struct block_hist, he);
-	init_block_hist(bh);
-
-	ch = notes->src->cycles_hist;
-	for (unsigned int i = 0; i < symbol__size(he->ms.sym); i++) {
-		if (ch[i].num_aggr) {
-			struct block_info *bi;
-			struct hist_entry *he_block;
-
-			bi = block_info__new();
-			if (!bi)
-				return -1;
-
-			init_block_info(bi, he->ms.sym, &ch[i], i);
-			he_block = hists__add_entry_block(&bh->block_hists,
-							  &dummy_al, bi);
-			if (!he_block) {
-				block_info__put(bi);
-				return -1;
-			}
-		}
-	}
-
-	return 0;
-}
-
 static int block_pair_cmp(struct hist_entry *a, struct hist_entry *b)
 {
 	struct block_info *bi_a = a->block_info;
@@ -689,6 +610,21 @@ static struct hist_entry *get_block_pair(struct hist_entry *he,
 	return NULL;
 }
 
+static void init_spark_values(unsigned long *svals, int num)
+{
+	for (int i = 0; i < num; i++)
+		svals[i] = 0;
+}
+
+static void update_spark_value(unsigned long *svals, int num,
+			       struct stats *stats, u64 val)
+{
+	int n = stats->n;
+
+	if (n < num)
+		svals[n] = val;
+}
+
 static void compute_cycles_diff(struct hist_entry *he,
 				struct hist_entry *pair)
 {
@@ -697,6 +633,26 @@ static void compute_cycles_diff(struct hist_entry *he,
 		pair->diff.cycles =
 			pair->block_info->cycles_aggr / pair->block_info->num_aggr -
 			he->block_info->cycles_aggr / he->block_info->num_aggr;
+
+		if (!cycles_hist)
+			return;
+
+		init_stats(&pair->diff.stats);
+		init_spark_values(pair->diff.svals, NUM_SPARKS);
+
+		for (int i = 0; i < pair->block_info->num; i++) {
+			u64 val;
+
+			if (i >= he->block_info->num || i >= NUM_SPARKS)
+				break;
+
+			val = llabs(pair->block_info->cycles_spark[i] -
+				     he->block_info->cycles_spark[i]);
+
+			update_spark_value(pair->diff.svals, NUM_SPARKS,
+					   &pair->diff.stats, val);
+			update_stats(&pair->diff.stats, val);
+		}
 	}
 }
 
@@ -720,13 +676,6 @@ static void block_hists_match(struct hists *hists_base,
 	}
 }
 
-static int filter_cb(struct hist_entry *he, void *arg __maybe_unused)
-{
-	/* Skip the calculation of column length in output_resort */
-	he->filtered = true;
-	return 0;
-}
-
 static void hists__precompute(struct hists *hists)
 {
 	struct rb_root_cached *root;
@@ -747,8 +696,11 @@ static void hists__precompute(struct hists *hists)
 		he   = rb_entry(next, struct hist_entry, rb_node_in);
 		next = rb_next(&he->rb_node_in);
 
-		if (compute == COMPUTE_CYCLES)
-			process_block_per_sym(he);
+		if (compute == COMPUTE_CYCLES) {
+			bh = container_of(he, struct block_hist, he);
+			init_block_hist(bh);
+			block_info__process_sym(he, bh, NULL, 0);
+		}
 
 		data__for_each_file_new(i, d) {
 			pair = get_pair_data(he, d);
@@ -767,16 +719,18 @@ static void hists__precompute(struct hists *hists)
 				compute_wdiff(he, pair);
 				break;
 			case COMPUTE_CYCLES:
-				process_block_per_sym(pair);
-				bh = container_of(he, struct block_hist, he);
 				pair_bh = container_of(pair, struct block_hist,
 						       he);
+				init_block_hist(pair_bh);
+				block_info__process_sym(pair, pair_bh, NULL, 0);
+
+				bh = container_of(he, struct block_hist, he);
 
 				if (bh->valid && pair_bh->valid) {
 					block_hists_match(&bh->block_hists,
 							  &pair_bh->block_hists);
-					hists__output_resort_cb(&pair_bh->block_hists,
-								NULL, filter_cb);
+					hists__output_resort(&pair_bh->block_hists,
+							     NULL);
 				}
 				break;
 			default:
@@ -1255,6 +1209,9 @@ static const struct option options[] = {
 		    "Show period values."),
 	OPT_BOOLEAN('F', "formula", &show_formula,
 		    "Show formula."),
+	OPT_BOOLEAN(0, "cycles-hist", &cycles_hist,
+		    "Show cycles histogram and standard deviation "
+		    "- WARNING: use only with -c cycles."),
 	OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace,
 		    "dump raw trace in ASCII"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
@@ -1462,6 +1419,90 @@ static int hpp__color_cycles(struct perf_hpp_fmt *fmt,
 	return __hpp__color_compare(fmt, hpp, he, COMPUTE_CYCLES);
 }
 
+static int all_zero(unsigned long *vals, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		if (vals[i] != 0)
+			return 0;
+	return 1;
+}
+
+static int print_cycles_spark(char *bf, int size, unsigned long *svals, u64 n)
+{
+	int printed;
+
+	if (n <= 1)
+		return 0;
+
+	if (n > NUM_SPARKS)
+		n = NUM_SPARKS;
+	if (all_zero(svals, n))
+		return 0;
+
+	printed = print_spark(bf, size, svals, n);
+	printed += scnprintf(bf + printed, size - printed, " ");
+	return printed;
+}
+
+static int hpp__color_cycles_hist(struct perf_hpp_fmt *fmt,
+			    struct perf_hpp *hpp, struct hist_entry *he)
+{
+	struct diff_hpp_fmt *dfmt =
+		container_of(fmt, struct diff_hpp_fmt, fmt);
+	struct hist_entry *pair = get_pair_fmt(he, dfmt);
+	struct block_hist *bh = container_of(he, struct block_hist, he);
+	struct block_hist *bh_pair;
+	struct hist_entry *block_he;
+	char spark[32], buf[128];
+	double r;
+	int ret, pad;
+
+	if (!pair) {
+		if (bh->block_idx)
+			hpp->skip = true;
+
+		goto no_print;
+	}
+
+	bh_pair = container_of(pair, struct block_hist, he);
+
+	block_he = hists__get_entry(&bh_pair->block_hists, bh->block_idx);
+	if (!block_he) {
+		hpp->skip = true;
+		goto no_print;
+	}
+
+	ret = print_cycles_spark(spark, sizeof(spark), block_he->diff.svals,
+				 block_he->diff.stats.n);
+
+	r = rel_stddev_stats(stddev_stats(&block_he->diff.stats),
+			     avg_stats(&block_he->diff.stats));
+
+	if (ret) {
+		/*
+		 * Padding spaces if number of sparks less than NUM_SPARKS
+		 * otherwise the output is not aligned.
+		 */
+		pad = NUM_SPARKS - ((ret - 1) / 3);
+		scnprintf(buf, sizeof(buf), "%s%5.1f%% %s", "\u00B1", r, spark);
+		ret = scnprintf(hpp->buf, hpp->size, "%*s",
+				dfmt->header_width, buf);
+
+		if (pad) {
+			ret += scnprintf(hpp->buf + ret, hpp->size - ret,
+					 "%-*s", pad, " ");
+		}
+
+		return ret;
+	}
+
+no_print:
+	return scnprintf(hpp->buf, hpp->size, "%*s",
+			dfmt->header_width, " ");
+}
+
 static void
 hpp__entry_unpair(struct hist_entry *he, int idx, char *buf, size_t size)
 {
@@ -1667,6 +1708,10 @@ static void data__hpp_register(struct data__file *d, int idx)
 		fmt->color = hpp__color_cycles;
 		fmt->sort  = hist_entry__cmp_nop;
 		break;
+	case PERF_HPP_DIFF__CYCLES_HIST:
+		fmt->color = hpp__color_cycles_hist;
+		fmt->sort  = hist_entry__cmp_nop;
+		break;
 	default:
 		fmt->sort  = hist_entry__cmp_nop;
 		break;
@@ -1692,10 +1737,14 @@ static int ui_init(void)
 		 *   PERF_HPP_DIFF__DELTA
 		 *   PERF_HPP_DIFF__RATIO
 		 *   PERF_HPP_DIFF__WEIGHTED_DIFF
+		 *   PERF_HPP_DIFF__CYCLES
 		 */
 		data__hpp_register(d, i ? compute_2_hpp[compute] :
 					  PERF_HPP_DIFF__BASELINE);
 
+		if (cycles_hist && i)
+			data__hpp_register(d, PERF_HPP_DIFF__CYCLES_HIST);
+
 		/*
 		 * And the rest:
 		 *
@@ -1850,6 +1899,9 @@ int cmd_diff(int argc, const char **argv)
 	if (quiet)
 		perf_quiet_option();
 
+	if (cycles_hist && (compute != COMPUTE_CYCLES))
+		usage_with_options(diff_usage, options);
+
 	symbol__annotation_init();
 
 	if (symbol__init(NULL) < 0)