summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorRavi Bangoria <ravi.bangoria@amd.com>2021-09-11 07:38:53 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2021-09-18 23:43:05 +0300
commit7efbcc8c075c5e9ef69b2379b75b58a699f23eb3 (patch)
treefb979ff35cf8170b4b631c9ea19ab88c4a9d60a4
parent93ff9f13be91c5f36bb3e5d23237702155deae74 (diff)
downloadlinux-7efbcc8c075c5e9ef69b2379b75b58a699f23eb3.tar.xz
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>
-rw-r--r--tools/perf/ui/browser.c33
-rw-r--r--tools/perf/ui/browser.h2
-rw-r--r--tools/perf/ui/browsers/annotate.c24
3 files changed, 42 insertions, 17 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);
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 3678eb88f119..510ce4554050 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -51,7 +51,7 @@ 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);
+ unsigned int row, int diff, 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 ef4da4295bf7..e81c2493efdf 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -125,13 +125,20 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
ab->selection = al;
}
-static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
+static int is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
{
struct disasm_line *pos = list_prev_entry(cursor, al.node);
const char *name;
+ int diff = 1;
+
+ while (pos && pos->al.offset == -1) {
+ pos = list_prev_entry(pos, al.node);
+ if (!ab->opts->hide_src_code)
+ diff++;
+ }
if (!pos)
- return false;
+ return 0;
if (ins__is_lock(&pos->ins))
name = pos->ops.locked.ins.name;
@@ -139,9 +146,11 @@ static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
name = pos->ins.name;
if (!name || !cursor->ins.name)
- return false;
+ return 0;
- return ins__is_fused(ab->arch, name, cursor->ins.name);
+ if (ins__is_fused(ab->arch, name, cursor->ins.name))
+ return diff;
+ return 0;
}
static void annotate_browser__draw_current_jump(struct ui_browser *browser)
@@ -155,6 +164,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
struct annotation *notes = symbol__annotation(sym);
u8 pcnt_width = annotation__pcnt_width(notes);
int width;
+ int diff = 0;
/* PLT symbols contain external offsets */
if (strstr(sym->name, "@plt"))
@@ -205,11 +215,11 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
pcnt_width + 2 + notes->widths.addr + width,
from, to);
- if (is_fused(ab, cursor)) {
+ diff = is_fused(ab, cursor);
+ if (diff > 0) {
ui_browser__mark_fused(browser,
pcnt_width + 3 + notes->widths.addr + width,
- from - 1,
- to > from);
+ from - diff, diff, to > from);
}
}