perf annotate: Fix fused instr logic for assembly functions

Some x86 microarchitectures fuse a subset of cmp/test/ALU instructions
with branch instructions, and thus perf annotate highlight such valid
pairs as fused.

When annotated with source, perf uses struct disasm_line to contain
either source or instruction line from objdump output. Usually, a C
statement generates multiple instructions which include such
cmp/test/ALU + branch instruction pairs. But in case of assembly
function, each individual assembly source line generate one
instruction.

The 'perf annotate' instruction fusion logic assumes the previous
disasm_line as the previous instruction line, which is wrong because,
for assembly function, previous disasm_line contains source line.  And
thus perf fails to highlight valid fused instruction pairs for assembly
functions.

Fix it by searching backward until we find an instruction line and
consider that disasm_line as fused with current branch instruction.

Before:
         │    cmpq    %rcx, RIP+8(%rsp)
    0.00 │      cmp    %rcx,0x88(%rsp)
         │    je      .Lerror_bad_iret      <--- Source line
    0.14 │   ┌──je     b4                   <--- Instruction line
         │   │movl    %ecx, %eax

After:
         │    cmpq    %rcx, RIP+8(%rsp)
    0.00 │   ┌──cmp    %rcx,0x88(%rsp)
         │   │je      .Lerror_bad_iret
    0.14 │   ├──je     b4
         │   │movl    %ecx, %eax

Reviewed-by: Jin Yao <yao.jin@linux.intel.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https //lore.kernel.org/r/20210911043854.8373-1-ravi.bangoria@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 24 insertions, 9 deletions

diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 781afe42e90e..fa5bd5c20e96 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -757,25 +757,40 @@ void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
 }
 
 void ui_browser__mark_fused(struct ui_browser *browser, unsigned int column,
-			    unsigned int row, bool arrow_down)
+			    unsigned int row, int diff, bool arrow_down)
 {
-	unsigned int end_row;
+	int end_row;
 
-	if (row >= browser->top_idx)
-		end_row = row - browser->top_idx;
-	else
+	if (diff <= 0)
 		return;
 
 	SLsmg_set_char_set(1);
 
 	if (arrow_down) {
+		if (row + diff <= browser->top_idx)
+			return;
+
+		end_row = row + diff - browser->top_idx;
 		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);
+
+		while (--end_row >= 0 && end_row > (int)(row - browser->top_idx)) {
+			ui_browser__gotorc(browser, end_row, column - 1);
+			SLsmg_draw_vline(1);
+		}
+
+		end_row = (int)(row - browser->top_idx);
+		if (end_row >= 0) {
+			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);
+		}
 	} else {
+		if (row < browser->top_idx)
+			return;
+
+		end_row = row - browser->top_idx;
 		ui_browser__gotorc(browser, end_row, column - 1);
 		SLsmg_write_char(SLSMG_LTEE_CHAR);
 		ui_browser__gotorc(browser, end_row, column);