5 files changed, 36 insertions, 5 deletions

diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 00c98c968cb1..505c13bf7e30 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -352,6 +352,8 @@ int __kmod_path__parse(struct kmod_path *m, const char *path,
 		if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
 		    (strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
 		    (strncmp(name, "[vdso]", 6) == 0) ||
+		    (strncmp(name, "[vdso32]", 8) == 0) ||
+		    (strncmp(name, "[vdsox32]", 9) == 0) ||
 		    (strncmp(name, "[vsyscall]", 10) == 0)) {
 			m->kmod = false;
 
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 f9157aed1289..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)
@@ -1376,7 +1389,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 {
 	intel_pt_log("ERROR: Buffer overflow\n");
 	intel_pt_clear_tx_flags(decoder);
-	decoder->have_tma = false;
 	decoder->cbr = 0;
 	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
@@ -1604,7 +1616,6 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PSB:
 		case INTEL_PT_TSC:
 		case INTEL_PT_TMA:
-		case INTEL_PT_CBR:
 		case INTEL_PT_MODE_TSX:
 		case INTEL_PT_BAD:
 		case INTEL_PT_PSBEND:
@@ -1620,6 +1631,10 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 			decoder->pkt_step = 0;
 			return -ENOENT;
 
+		case INTEL_PT_CBR:
+			intel_pt_calc_cbr(decoder);
+			break;
+
 		case INTEL_PT_OVF:
 			return intel_pt_overflow(decoder);
 
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-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
index ba4c9dd18643..d426761a549d 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c
@@ -366,7 +366,7 @@ static int intel_pt_get_cyc(unsigned int byte, const unsigned char *buf,
 		if (len < offs)
 			return INTEL_PT_NEED_MORE_BYTES;
 		byte = buf[offs++];
-		payload |= (byte >> 1) << shift;
+		payload |= ((uint64_t)byte >> 1) << shift;
 	}
 
 	packet->type = INTEL_PT_CYC;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index d9573c1fa555..3b118fa9da89 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -784,6 +784,7 @@ 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));
@@ -865,6 +866,9 @@ 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;
@@ -1560,6 +1564,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 
 	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
 		switch (ptq->switch_state) {
+		case INTEL_PT_SS_NOT_TRACING:
 		case INTEL_PT_SS_UNKNOWN:
 		case INTEL_PT_SS_EXPECTING_SWITCH_IP:
 			err = intel_pt_next_tid(pt, ptq);