Cycles annotation support for perf tools v3

index c53f363..ec175ca 100644
@@ -134,7 +134,8 @@ struct branch_flags {
 	u64 predicted:1;
 	u64 in_tx:1;
 	u64 abort:1;
-	u64 reserved:60;
+	u64 cycles:16;
+	u64 reserved:44;
 };
 
 struct branch_entry {

index 6f28d53..54fc003 100644
@@ -618,7 +618,8 @@ iter_add_next_branch_entry(struct hist_entry_iter *iter, struct addr_location *a
 	 * and not events sampled. Thus we use a pseudo period of 1.
 	 */
 	he = __hists__add_entry(hists, al, iter->parent, &bi[i], NULL,
-				1, 1, 0, true);
+				1, bi->flags.cycles ? bi->flags.cycles : 1,
+				0, true);
 	if (he == NULL)
 		return -ENOMEM;
 

index 5ed8d9c..3881d98 100644
@@ -47,6 +47,7 @@ enum hist_column {
 	HISTC_MEM_SNOOP,
 	HISTC_MEM_DCACHELINE,
 	HISTC_TRANSACTION,
+	HISTC_CYCLES,
 	HISTC_NR_COLS, /* Last entry */
 };
 

index ed9dc25..e495127c 100644
@@ -766,10 +766,18 @@ static void branch_stack__printf(struct perf_sample *sample)
 
 	printf("... branch stack: nr:%" PRIu64 "\n", sample->branch_stack->nr);
 
-	for (i = 0; i < sample->branch_stack->nr; i++)
-		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 "\n",
-			i, sample->branch_stack->entries[i].from,
-			sample->branch_stack->entries[i].to);
+	for (i = 0; i < sample->branch_stack->nr; i++) {
+		struct branch_entry *e = &sample->branch_stack->entries[i];
+
+		printf("..... %2"PRIu64": %016" PRIx64 " -> %016" PRIx64 " %hu cycles %s%s%s%s %x\n",
+			i, e->from, e->to,
+			e->flags.cycles,
+			e->flags.mispred ? "M" : " ",
+			e->flags.predicted ? "P" : " ",
+			e->flags.abort ? "A" : " ",
+			e->flags.in_tx ? "T" : " ",
+			(unsigned)e->flags.reserved);
+	}
 }
 
 static void regs_dump__printf(u64 mask, u64 *regs)

index 4c65a14..5b7a50c 100644
@@ -526,6 +526,29 @@ static int hist_entry__mispredict_snprintf(struct hist_entry *he, char *bf,
 	return repsep_snprintf(bf, size, "%-*.*s", width, width, out);
 }
 
+static int64_t
+sort__cycles_cmp(struct hist_entry *left, struct hist_entry *right)
+{
+	return left->branch_info->flags.cycles -
+		right->branch_info->flags.cycles;
+}
+
+static int hist_entry__cycles_snprintf(struct hist_entry *he, char *bf,
+				    size_t size, unsigned int width)
+{
+	if (he->branch_info->flags.cycles == 0)
+		return repsep_snprintf(bf, size, "%-*s", width, "-");
+	return repsep_snprintf(bf, size, "%-*hd", width,
+			       he->branch_info->flags.cycles);
+}
+
+struct sort_entry sort_cycles = {
+	.se_header	= "Basic Block Cycles",
+	.se_cmp		= sort__cycles_cmp,
+	.se_snprintf	= hist_entry__cycles_snprintf,
+	.se_width_idx	= HISTC_CYCLES,
+};
+
 /* --sort daddr_sym */
 static int64_t
 sort__daddr_cmp(struct hist_entry *left, struct hist_entry *right)

@@ -1190,6 +1213,7 @@ static struct sort_dimension bstack_sort_dimensions[] = {
 	DIM(SORT_MISPREDICT, "mispredict", sort_mispredict),
 	DIM(SORT_IN_TX, "in_tx", sort_in_tx),
 	DIM(SORT_ABORT, "abort", sort_abort),
+	DIM(SORT_CYCLES, "cycles", sort_cycles),
 };
 
 #undef DIM

index e97cd47..bc6c87a 100644
@@ -185,6 +185,7 @@ enum sort_type {
 	SORT_MISPREDICT,
 	SORT_ABORT,
 	SORT_IN_TX,
+	SORT_CYCLES,
 
 	/* memory mode specific sort keys */
 	__SORT_MEMORY_MODE,

index 95a4771..3ba0e97 100644
@@ -53,6 +53,7 @@ struct report {
 	bool			mem_mode;
 	bool			header;
 	bool			header_only;
+	bool			nonany_branch_mode;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;

@@ -258,6 +259,12 @@ static int report__setup_sample_type(struct report *rep)
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;
 	}
+
+	/* ??? handle more cases than just ANY? */
+	if (!(perf_evlist__combined_branch_type(session->evlist) &
+				PERF_SAMPLE_BRANCH_ANY))
+		rep->nonany_branch_mode = true;
+
 	return 0;
 }
 

index f7d9c77..cba8069 100644
@@ -1255,6 +1255,16 @@ u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist)
 	return __perf_evlist__combined_sample_type(evlist);
 }
 
+u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+	u64 branch_type = 0;
+
+	evlist__for_each(evlist, evsel)
+		branch_type |= evsel->attr.branch_sample_type;
+	return branch_type;
+}
+
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist)
 {
 	struct perf_evsel *first = perf_evlist__first(evlist), *pos = first;

index 037633c..c1cdb86 100644
@@ -169,6 +169,7 @@ void perf_evlist__set_leader(struct perf_evlist *evlist);
 u64 perf_evlist__read_format(struct perf_evlist *evlist);
 u64 __perf_evlist__combined_sample_type(struct perf_evlist *evlist);
 u64 perf_evlist__combined_sample_type(struct perf_evlist *evlist);
+u64 perf_evlist__combined_branch_type(struct perf_evlist *evlist);
 bool perf_evlist__sample_id_all(struct perf_evlist *evlist);
 u16 perf_evlist__id_hdr_size(struct perf_evlist *evlist);
 

index 2c1bec3..467a23b 100644
@@ -187,6 +187,7 @@ find_next:
 			 * symbol, free he->ms.sym->src to signal we already
 			 * processed this symbol.
 			 */
+			zfree(&notes->src->cycles_hist);
 			zfree(&notes->src);
 		}
 	}

166 lines not on this page · raw message

index 7e78e6c..a06518d 100644
@@ -79,6 +79,17 @@ struct sym_hist {
 	u64		addr[0];
 };
 
+struct cyc_hist {
+	u64	start;
+	u64	cycles;
+	u64	cycles_aggr;
+	u32	num;
+	u32	num_aggr;
+	u8	have_start;
+	/* 1 byte padding */
+	u16	reset;
+};
+
 struct source_line_samples {
 	double		percent;
 	double		percent_sum;

@@ -97,6 +108,7 @@ struct source_line {
  * @histogram: Array of addr hit histograms per event being monitored
  * @lines: If 'print_lines' is specified, per source code line percentages
  * @source: source parsed from a disassembler like objdump -dS
+ * @cyc_hist: Average cycles per basic block
  *
  * lines is allocated, percentages calculated and all sorted by percentage
  * when the annotation is about to be presented, so the percentages are for

@@ -109,6 +121,7 @@ struct annotated_source {
 	struct source_line *lines;
 	int    		   nr_histograms;
 	int    		   sizeof_sym_hist;
+	struct cyc_hist	   *cycles_hist;
 	struct sym_hist	   histograms[0];
 };
 

@@ -130,6 +143,10 @@ static inline struct annotation *symbol__annotation(struct symbol *sym)
 
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, int evidx);
 
+int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
+				    struct addr_map_symbol *start,
+				    unsigned cycles);
+
 int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 
 int symbol__alloc_hist(struct symbol *sym);

index 3ba0e97..3a9d1b6 100644
@@ -103,6 +103,9 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	if (!ui__has_annotation())
 		return 0;
 
+	hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
+			     rep->nonany_branch_mode);
+
 	if (sort__mode == SORT_MODE__BRANCH) {
 		bi = he->branch_info;
 		err = addr_map_symbol__inc_samples(&bi->from, evsel->idx);

index 54fc003..a6e9ddd 100644
@@ -1415,6 +1415,39 @@ int hists__link(struct hists *leader, struct hists *other)
 	return 0;
 }
 
+void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
+			  struct perf_sample *sample, bool nonany_branch_mode)
+{
+	struct branch_info *bi;
+
+	/* If we have branch cycles always annotate them. */
+	if (bs && bs->nr && bs->entries[0].flags.cycles) {
+		int i;
+
+		bi = sample__resolve_bstack(sample, al);
+		if (bi) {
+			struct addr_map_symbol *prev = NULL;
+
+			/*
+			 * Ignore errors, still want to process the
+			 * other entries.
+			 *
+			 * For non standard branch modes always
+			 * force no IPC (prev == NULL)
+			 *
+			 * Note that perf stores branches reversed from
+			 * program order!
+			 */
+			for (i = bs->nr - 1; i >= 0; i--) {
+				addr_map_symbol__account_cycles(&bi[i].from,
+					nonany_branch_mode ? NULL : prev,
+					bi[i].flags.cycles);
+				prev = &bi[i].to;
+			}
+			free(bi);
+		}
+	}
+}
 
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp)
 {

index 3881d98..e2f712f 100644
@@ -350,6 +350,9 @@ static inline int script_browse(const char *script_opt __maybe_unused)
 
 unsigned int hists__sort_list_width(struct hists *hists);
 
+void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
+			  struct perf_sample *sample, bool nonany_branch_mode);
+
 struct option;
 int parse_filter_percentage(const struct option *opt __maybe_unused,
 			    const char *arg, int unset __maybe_unused);

index 5995a8b..6ec1795 100644
@@ -53,6 +53,7 @@ struct annotate_browser {
 	int		    max_jump_sources;
 	int		    nr_jumps;
 	bool		    searching_backwards;
+	bool		    have_cycles;
 	u8		    addr_width;
 	u8		    jumps_width;
 	u8		    target_width;

@@ -390,7 +391,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 				max_percent = bpos->samples[i].percent;
 		}
 
-		if (max_percent < 0.01) {
+		if (max_percent < 0.01 && pos->ipc == 0) {
 			RB_CLEAR_NODE(&bpos->rb_node);
 			continue;
 		}

@@ -869,6 +870,75 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
 
+
+static unsigned count_insn(struct annotate_browser *browser, u64 start, u64 end)
+{
+	unsigned n_insn = 0;
+	u64 offset;
+
+	for (offset = start; offset <= end; offset++) {
+		if (browser->offsets[offset])
+			n_insn++;
+	}
+	return n_insn;
+}
+
+static void count_and_fill(struct annotate_browser *browser, u64 start, u64 end,
+			   struct cyc_hist *ch)
+{
+	unsigned n_insn;
+	u64 offset;
+
+	n_insn = count_insn(browser, start, end);
+	if (n_insn && ch->num && ch->cycles) {
+		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
+
+		/* Hide data when there are too many overlaps. */
+		if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2)
+			return;
+
+		for (offset = start; offset <= end; offset++) {
+			struct disasm_line *dl = browser->offsets[offset];
+
+			if (dl)
+				dl->ipc = ipc;
+		}
+	}
+}
+
+/*
+ * This should probably be in util/annotate.c to share with the tty
+ * annotate, but right now we need the per byte offsets arrays,
+ * which are only here.
+ */
+static void annotate__compute_ipc(struct annotate_browser *browser, size_t size,
+			   struct symbol *sym)
+{
+	u64 offset;
+	struct annotation *notes = symbol__annotation(sym);
+
+	if (!notes->src || !notes->src->cycles_hist)
+		return;
+
+	pthread_mutex_lock(&notes->lock);
+	for (offset = 0; offset < size; ++offset) {
+		struct cyc_hist *ch;
+
+		ch = &notes->src->cycles_hist[offset];
+		if (ch && ch->cycles) {
+			struct disasm_line *dl;
+
+			if (ch->have_start)
+				count_and_fill(browser, ch->start, offset, ch);
+			dl = browser->offsets[offset];
+			if (dl && ch->num_aggr)
+				dl->cycles = ch->cycles_aggr / ch->num_aggr;
+			browser->have_cycles = true;
+		}
+	}
+	pthread_mutex_unlock(&notes->lock);
+}
+
 static void annotate_browser__mark_jump_targets(struct annotate_browser *browser,
 						size_t size)
 {

@@ -991,6 +1061,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	}
 
 	annotate_browser__mark_jump_targets(&browser, size);
+	annotate__compute_ipc(&browser, size, sym);
 
 	browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size);
 	browser.max_addr_width = hex_width(sym->end);

index a06518d..e999609 100644
@@ -59,6 +59,8 @@ struct disasm_line {
 	char		    *name;
 	struct ins	    *ins;
 	int		    line_nr;
+	float		    ipc;
+	u64		    cycles;
 	struct ins_operands ops;
 };
 

index 6ec1795..b5fc847 100644
@@ -16,6 +16,9 @@ struct disasm_line_samples {
 	u64		nr;
 };
 
+#define IPC_WIDTH 6
+#define CYCLES_WIDTH 6
+
 struct browser_disasm_line {
 	struct rb_node			rb_node;
 	u32				idx;

@@ -97,6 +100,15 @@ static int annotate_browser__set_jumps_percent_color(struct annotate_browser *br
 	 return ui_browser__set_color(&browser->b, color);
 }
 
+static int annotate_browser__pcnt_width(struct annotate_browser *ab)
+{
+	int w = 7 * ab->nr_events;
+
+	if (ab->have_cycles)
+		w += IPC_WIDTH + CYCLES_WIDTH;
+	return w;
+}
+
 static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);

@@ -107,7 +119,7 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 			     (!current_entry || (browser->use_navkeypressed &&
 					         !browser->navkeypressed)));
 	int width = browser->width, printed;
-	int i, pcnt_width = 7 * ab->nr_events;
+	int i, pcnt_width = annotate_browser__pcnt_width(ab);
 	double percent_max = 0.0;
 	char bf[256];
 

@@ -117,19 +129,34 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	}
 
 	if (dl->offset != -1 && percent_max != 0.0) {
-		for (i = 0; i < ab->nr_events; i++) {
-			ui_browser__set_percent_color(browser,
-						      bdl->samples[i].percent,
-						      current_entry);
-			if (annotate_browser__opts.show_total_period)
-				slsmg_printf("%6" PRIu64 " ",
-					     bdl->samples[i].nr);
-			else
-				slsmg_printf("%6.2f ", bdl->samples[i].percent);
+		if (percent_max != 0.0) {
+			for (i = 0; i < ab->nr_events; i++) {
+				ui_browser__set_percent_color(browser,
+							bdl->samples[i].percent,
+							current_entry);
+				if (annotate_browser__opts.show_total_period)
+					slsmg_printf("%6" PRIu64 " ",
+						     bdl->samples[i].nr);
+				else
+					slsmg_printf("%6.2f ", bdl->samples[i].percent);
+			}
+		} else {
+			slsmg_write_nstring(" ", 7 * ab->nr_events);
 		}
 	} else {
 		ui_browser__set_percent_color(browser, 0, current_entry);
-		slsmg_write_nstring(" ", pcnt_width);
+		slsmg_write_nstring(" ", 7 * ab->nr_events);
+	}
+	if (ab->have_cycles) {
+		if (dl->ipc)
+			slsmg_printf("%*.2f ", IPC_WIDTH - 1, dl->ipc);
+		else
+			slsmg_write_nstring(" ", IPC_WIDTH);
+		if (dl->cycles)
+			slsmg_printf("%*" PRIu64 " ",
+				     CYCLES_WIDTH - 1, dl->cycles);
+		else
+			slsmg_write_nstring(" ", CYCLES_WIDTH);
 	}
 
 	SLsmg_write_char(' ');

@@ -232,7 +259,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	unsigned int from, to;
 	struct map_symbol *ms = ab->b.priv;
 	struct symbol *sym = ms->sym;
-	u8 pcnt_width = 7;
+	u8 pcnt_width = annotate_browser__pcnt_width(ab);
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))

@@ -256,8 +283,6 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 		to = (u64)btarget->idx;
 	}
 
-	pcnt_width *= ab->nr_events;
-
 	ui_browser__set_color(browser, HE_COLORSET_CODE);
 	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
 				 from, to);

@@ -267,9 +292,7 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	int ret = ui_browser__list_head_refresh(browser);
-	int pcnt_width;
-
-	pcnt_width = 7 * ab->nr_events;
+	int pcnt_width = annotate_browser__pcnt_width(ab);
 
 	if (annotate_browser__opts.jump_arrows)
 		annotate_browser__draw_current_jump(browser);

index ecf3197..f0a5240 100644
@@ -40,6 +40,7 @@
 #include "util/xyarray.h"
 #include "util/sort.h"
 #include "util/intlist.h"
+#include "util/parse-branch-options.h"
 #include "arch/common.h"
 
 #include "util/debug.h"

@@ -695,6 +696,8 @@ static int hist_iter__top_callback(struct hist_entry_iter *iter,
 		perf_top__record_precise_ip(top, he, evsel->idx, ip);
 	}
 
+	hist__account_cycles(iter->sample->branch_stack, al, iter->sample,
+		     !(top->record_opts.branch_stack & PERF_SAMPLE_BRANCH_ANY));
 	return 0;
 }
 

@@ -932,7 +935,6 @@ static int perf_top__setup_sample_type(struct perf_top *top __maybe_unused)
 			return -EINVAL;
 		}
 	}
-
 	return 0;
 }
 

@@ -1171,6 +1173,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "don't try to adjust column width, use these fixed values"),
 	OPT_UINTEGER(0, "proc-map-timeout", &opts->proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_CALLBACK_NOOPT('b', "branch-any", &opts->branch_stack,
+		     "branch any", "sample any taken branches",
+		     parse_branch_stack),
+	OPT_CALLBACK('j', "branch-filter", &opts->branch_stack,
+		     "branch filter mask", "branch stack filter modes",
+		     parse_branch_stack),
 	OPT_END()
 	};
 	const char * const top_usage[] = {

index 5b7a50c..5177088 100644
@@ -9,7 +9,7 @@ regex_t		parent_regex;
 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,dso_to,symbol_to";
+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";
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";

index a6e9ddd..8a4bf84 100644
@@ -1421,7 +1421,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al,
 	struct branch_info *bi;
 
 	/* If we have branch cycles always annotate them. */
-	if (bs && bs->nr && bs->entries[0].flags.cycles) {
+	if (bs && bs->nr /* && bs->entries[0].flags.cycles */) {
 		int i;
 
 		bi = sample__resolve_bstack(sample, al);

index 7ff6827..1351f19 100644
@@ -1597,6 +1597,8 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
 		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
 		bi[i].flags = bs->entries[i].flags;
+		if (bi[i].flags.cycles == 0)
+			bi[i].flags.cycles = 123;
 	}
 	return bi;
 }