perf tools: Add support for cycles, weight branch_info field

cycles is a new branch_info field available on some CPUs that indicates
the time deltas between branches in the LBR.

Add a sort key and output code for the cycles to allow to display the
basic block cycles individually in perf report.

We also pass in the cycles for weight when LBRs are processed, which
allows to get global and local weight, to get an estimate of the total
cost.

And also print the cycles information for perf report -D.  I also added
printing for the previously missing LBR flags (mispredict etc.)

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/1437233094-12844-2-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

7 files changed, 43 insertions, 6 deletions

diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index c33b69f3374f..960da203ec11 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -109,6 +109,7 @@ OPTIONS
         - mispredict: "N" for predicted branch, "Y" for mispredicted branch
         - in_tx: branch in TSX transaction
         - abort: TSX transaction abort.
+        - cycles: Cycles in basic block
 
         And default sort keys are changed to comm, dso_from, symbol_from, dso_to
         and symbol_to, see '--branch-stack'.
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 4bb2ae894c78..f729df5e25e6 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -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 {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6f28d53d4e46..54fc0033dd6a 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -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;
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 5ed8d9c22981..3881d9815309 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -47,6 +47,7 @@ enum hist_column {
         HISTC_MEM_SNOOP,
         HISTC_MEM_DCACHELINE,
         HISTC_TRANSACTION,
+        HISTC_CYCLES,
         HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index f51eb54aeeb3..18722e774a69 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -784,10 +784,18 @@ 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)
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 4c65a143a34c..5b7a50c04e45 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -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
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index e97cd476d336..bc6c87a76d16 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -185,6 +185,7 @@ enum sort_type {
         SORT_MISPREDICT,
         SORT_ABORT,
         SORT_IN_TX,
+        SORT_CYCLES,
 
         /* memory mode specific sort keys */
         __SORT_MEMORY_MODE,