perf annotate: Compute IPC and basic block cycles

Compute the IPC and the basic block cycles for the annotate display.

IPC is computed by counting the instructions, and then dividing the
accounted cycles by that count.

The actual IPC computation can only be done at annotate time, because we
need to parse the objdump output first to know the number of
instructions in the basic block.

The cycles/IPC are also put into the perf function annotation so that
the display code can show them.

Again basic block overlaps are not handled, with the longest winning,
but there are some heuristics to hide the IPC when the longest is not
the most common.

v2: Compute IPC correctly.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1437233094-12844-6-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 72 insertions, 1 deletions

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 5995a8bd7c69..6ec179547f72 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -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);