perf intel-pt: Add LBR information to synthesized PEBS sample

Add LBR information from PEBS data in the Intel PT trace to the
synthesized PEBS sample.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190610072803.10456-10-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index f83dd10..db00c13 100644 (file)
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1628,6 +1628,58 @@ static void intel_pt_add_xmm(struct regs_dump *intr_regs, u64 *pos,
        }
 }
 
+#define LBR_INFO_MISPRED       (1ULL << 63)
+#define LBR_INFO_IN_TX         (1ULL << 62)
+#define LBR_INFO_ABORT         (1ULL << 61)
+#define LBR_INFO_CYCLES                0xffff
+
+/* Refer kernel's intel_pmu_store_pebs_lbrs() */
+static u64 intel_pt_lbr_flags(u64 info)
+{
+       union {
+               struct branch_flags flags;
+               u64 result;
+       } u = {
+               .flags = {
+                       .mispred        = !!(info & LBR_INFO_MISPRED),
+                       .predicted      = !(info & LBR_INFO_MISPRED),
+                       .in_tx          = !!(info & LBR_INFO_IN_TX),
+                       .abort          = !!(info & LBR_INFO_ABORT),
+                       .cycles         = info & LBR_INFO_CYCLES,
+               }
+       };
+
+       return u.result;
+}
+
+static void intel_pt_add_lbrs(struct branch_stack *br_stack,
+                             const struct intel_pt_blk_items *items)
+{
+       u64 *to;
+       int i;
+
+       br_stack->nr = 0;
+
+       to = &br_stack->entries[0].from;
+
+       for (i = INTEL_PT_LBR_0_POS; i <= INTEL_PT_LBR_2_POS; i++) {
+               u32 mask = items->mask[i];
+               const u64 *from = items->val[i];
+
+               for (; mask; mask >>= 3, from += 3) {
+                       if ((mask & 7) == 7) {
+                               *to++ = from[0];
+                               *to++ = from[1];
+                               *to++ = intel_pt_lbr_flags(from[2]);
+                               br_stack->nr += 1;
+                       }
+               }
+       }
+}
+
+/* INTEL_PT_LBR_0, INTEL_PT_LBR_1 and INTEL_PT_LBR_2 */
+#define LBRS_MAX (INTEL_PT_BLK_ITEM_ID_CNT * 3)
+
 static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
 {
        const struct intel_pt_blk_items *items = &ptq->state->items;
@@ -1694,6 +1746,26 @@ static int intel_pt_synth_pebs_sample(struct intel_pt_queue *ptq)
                intel_pt_add_xmm(&sample.intr_regs, pos, items, regs_mask);
        }
 
+       if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+               struct {
+                       struct branch_stack br_stack;
+                       struct branch_entry entries[LBRS_MAX];
+               } br;
+
+               if (items->mask[INTEL_PT_LBR_0_POS] ||
+                   items->mask[INTEL_PT_LBR_1_POS] ||
+                   items->mask[INTEL_PT_LBR_2_POS]) {
+                       intel_pt_add_lbrs(&br.br_stack, items);
+                       sample.branch_stack = &br.br_stack;
+               } else if (pt->synth_opts.last_branch) {
+                       intel_pt_copy_last_branch_rb(ptq);
+                       sample.branch_stack = ptq->last_branch;
+               } else {
+                       br.br_stack.nr = 0;
+                       sample.branch_stack = &br.br_stack;
+               }
+       }
+
        return intel_pt_deliver_synth_event(pt, ptq, event, &sample, sample_type);
 }