3 files changed, 28 insertions, 2 deletions

diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 881d7c5e5e2a..d404bed7003a 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -113,6 +113,7 @@ struct intel_pt_decoder {
         bool have_cyc;
         bool fixup_last_mtc;
         bool have_last_ip;
+        enum intel_pt_param_flags flags;
         uint64_t pos;
         uint64_t last_ip;
         uint64_t ip;
@@ -226,6 +227,8 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
         decoder->return_compression = params->return_compression;
         decoder->branch_enable      = params->branch_enable;
 
+        decoder->flags              = params->flags;
+
         decoder->period             = params->period;
         decoder->period_type        = params->period_type;
 
@@ -1097,6 +1100,15 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
         return ret;
 }
 
+static inline bool intel_pt_fup_with_nlip(struct intel_pt_decoder *decoder,
+                                          struct intel_pt_insn *intel_pt_insn,
+                                          uint64_t ip, int err)
+{
+        return decoder->flags & INTEL_PT_FUP_WITH_NLIP && !err &&
+               intel_pt_insn->branch == INTEL_PT_BR_INDIRECT &&
+               ip == decoder->ip + intel_pt_insn->length;
+}
+
 static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 {
         struct intel_pt_insn intel_pt_insn;
@@ -1109,10 +1121,11 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
                 err = intel_pt_walk_insn(decoder, &intel_pt_insn, ip);
                 if (err == INTEL_PT_RETURN)
                         return 0;
-                if (err == -EAGAIN) {
+                if (err == -EAGAIN ||
+                    intel_pt_fup_with_nlip(decoder, &intel_pt_insn, ip, err)) {
                         if (intel_pt_fup_event(decoder))
                                 return 0;
-                        return err;
+                        return -EAGAIN;
                 }
                 decoder->set_fup_tx_flags = false;
                 if (err)
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index fc1752d50019..51c18d67f4ca 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -60,6 +60,14 @@ enum {
         INTEL_PT_ERR_MAX,
 };
 
+enum intel_pt_param_flags {
+        /*
+         * FUP packet can contain next linear instruction pointer instead of
+         * current linear instruction pointer.
+         */
+        INTEL_PT_FUP_WITH_NLIP  = 1 << 0,
+};
+
 struct intel_pt_state {
         enum intel_pt_sample_type type;
         int err;
@@ -106,6 +114,7 @@ struct intel_pt_params {
         unsigned int mtc_period;
         uint32_t tsc_ctc_ratio_n;
         uint32_t tsc_ctc_ratio_d;
+        enum intel_pt_param_flags flags;
 };
 
 struct intel_pt_decoder;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 3db7f0ee52a8..aec68908d604 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -749,6 +749,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
                                                    unsigned int queue_nr)
 {
         struct intel_pt_params params = { .get_trace = 0, };
+        struct perf_env *env = pt->machine->env;
         struct intel_pt_queue *ptq;
 
         ptq = zalloc(sizeof(struct intel_pt_queue));
@@ -830,6 +831,9 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
                 }
         }
 
+        if (env->cpuid && !strncmp(env->cpuid, "GenuineIntel,6,92,", 18))
+                params.flags |= INTEL_PT_FUP_WITH_NLIP;
+
         ptq->decoder = intel_pt_decoder_new(&params);
         if (!ptq->decoder)
                 goto out_free;