[PATCH v3 2/2] perf report: Implement visual marker for macro fusion in annotate

[Jin Yao]

For marking the fused instructions clearly, This patch adds a
line before the first instruction of pair and joins it with the
arrow of the jump.

For example, when je is selected in annotate view, the line
before cmpl is displayed and joins the arrow of je.

       â   âââcmpl   $0x0,argp_program_version_hook
 81.93 â   âââje     20
       â   â  lock   cmpxchg %esi,0x38a9a4(%rip)
       â   ââ jne    29
       â   ââ jmp    43
 11.47 â20:âââcmpxch %esi,0x38a999(%rip)

That means the cmpl+je is fused instruction pair and they should
be considered together.

Change-log:
-----------
v3: Use Arnaldo's fix to let the display be better.
    To get the evsel->evlist->env->cpuid, save the evsel in
    annotate_browser.

v2: No more changes, just uses a new function "ins__is_fused"
    to check if the instructions are fused.

v1: Initial post

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
 tools/perf/ui/browser.c           | 29 +++++++++++++++++++++++++++++
 tools/perf/ui/browser.h           |  2 ++
 tools/perf/ui/browsers/annotate.c | 32 ++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.c        |  5 +++++
 tools/perf/util/annotate.h        |  1 +
 5 files changed, 69 insertions(+)

diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index a4d3762..9ef7677 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -738,6 +738,35 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
 		__ui_browser__line_arrow_down(browser, column, start, end);
 }
 
+void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
+			    unsigned int row, bool arrow_down)
+{
+	unsigned int end_row;
+
+	if (row >= browser->top_idx)
+		end_row = row - browser->top_idx;
+	else
+		return;
+
+	SLsmg_set_char_set(1);
+
+	if (arrow_down) {
+		ui_browser__gotorc(browser, end_row, column - 1);
+		SLsmg_write_char(SLSMG_ULCORN_CHAR);
+		ui_browser__gotorc(browser, end_row, column);
+		SLsmg_draw_hline(2);
+		ui_browser__gotorc(browser, end_row + 1, column - 1);
+		SLsmg_write_char(SLSMG_LTEE_CHAR);
+	} else {
+		ui_browser__gotorc(browser, end_row, column - 1);
+		SLsmg_write_char(SLSMG_LTEE_CHAR);
+		ui_browser__gotorc(browser, end_row, column);
+		SLsmg_draw_hline(2);
+	}
+
+	SLsmg_set_char_set(0);
+}
+
 void ui_browser__init(void)
 {
 	int i = 0;
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index be3b70e..a12eff7 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -43,6 +43,8 @@ void ui_browser__printf(struct ui_browser *browser, const char *fmt, ...);
 void ui_browser__write_graph(struct ui_browser *browser, int graph);
 void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
 			      u64 start, u64 end);
+void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
+			    unsigned int row, bool arrow_down);
 void __ui_browser__show_title(struct ui_browser *browser, const char *title);
 void ui_browser__show_title(struct ui_browser *browser, const char *title);
 int ui_browser__show(struct ui_browser *browser, const char *title,
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 27f41f2..d3c7109 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -9,6 +9,7 @@
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include "../../util/config.h"
+#include "../../util/evlist.h"
 #include <inttypes.h>
 #include <pthread.h>
 #include <linux/kernel.h>
@@ -55,6 +56,7 @@ struct annotate_browser {
 	struct disasm_line  *selection;
 	struct disasm_line  **offsets;
 	struct arch	    *arch;
+	struct perf_evsel   *evsel;
 	int		    nr_events;
 	u64		    start;
 	int		    nr_asm_entries;
@@ -272,6 +274,28 @@ static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sy
 	return true;
 }
 
+static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
+{
+	struct disasm_line *pos = list_prev_entry(cursor, node);
+	struct perf_evsel *evsel = ab->evsel;
+	const char *name;
+
+	if (!pos || !evsel || !evsel->evlist || !evsel->evlist->env ||
+	    !evsel->evlist->env->cpuid)
+		return false;
+
+	if (ins__is_lock(&pos->ins))
+		name = pos->ops.locked.ins.name;
+	else
+		name = pos->ins.name;
+
+	if (!name || !cursor->ins.name)
+		return false;
+
+	return ins__is_fused(ab->arch, evsel->evlist->env->cpuid, name,
+			     cursor->ins.name);
+}
+
 static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
@@ -307,6 +331,13 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
 	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
 				 from, to);
+
+	if (is_fused(ab, cursor)) {
+		ui_browser__mark_fused(browser,
+				       pcnt_width + 3 + ab->addr_width,
+				       from - 1,
+				       to > from ? true : false);
+	}
 }
 
 static unsigned int annotate_browser__refresh(struct ui_browser *browser)
@@ -1120,6 +1151,7 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	browser.b.nr_entries = browser.nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
+	browser.evsel = evsel;
 
 	if (annotate_browser__opts.hide_src_code)
 		annotate_browser__init_asm_mode(&browser);
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 8cf6025..0688837 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -514,6 +514,11 @@ bool ins__is_ret(const struct ins *ins)
 	return ins->ops == &ret_ops;
 }
 
+bool ins__is_lock(const struct ins *ins)
+{
+	return ins->ops == &lock_ops;
+}
+
 static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 35cb7b5..2f5735e 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -52,6 +52,7 @@ struct ins_ops {
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 bool ins__is_ret(const struct ins *ins);
+bool ins__is_lock(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 bool ins__is_fused(struct arch *arch, char *cpuid, const char *ins1,
 		   const char *ins2);
-- 
2.7.4