perf intel-pt: Power events and PTWRITE

index 7cf7f7aca4d2..5a9676c6e23f 100644
@@ -2130,15 +2130,18 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 		}
 	} while (err == -ENOLINK);
 
-	decoder->state.err = err ? intel_pt_ext_err(err) : 0;
+	if (err) {
+		decoder->state.err = intel_pt_ext_err(err);
+		decoder->state.from_ip = decoder->ip;
+	} else {
+		decoder->state.err = 0;
+	}
+
 	decoder->state.timestamp = decoder->timestamp;
 	decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
 	decoder->state.cr3 = decoder->cr3;
 	decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;
 
-	if (err)
-		decoder->state.from_ip = decoder->ip;
-
 	return &decoder->state;
 }
 

index 5a9676c6e23f..d5c69e822282 100644
@@ -64,6 +64,25 @@ enum intel_pt_pkt_state {
 	INTEL_PT_STATE_FUP_NO_TIP,
 };
 
+static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
+{
+	switch (pkt_state) {
+	case INTEL_PT_STATE_NO_PSB:
+	case INTEL_PT_STATE_NO_IP:
+	case INTEL_PT_STATE_ERR_RESYNC:
+	case INTEL_PT_STATE_IN_SYNC:
+	case INTEL_PT_STATE_TNT:
+		return true;
+	case INTEL_PT_STATE_TIP:
+	case INTEL_PT_STATE_TIP_PGD:
+	case INTEL_PT_STATE_FUP:
+	case INTEL_PT_STATE_FUP_NO_TIP:
+		return false;
+	default:
+		return true;
+	};
+}
+
 #ifdef INTEL_PT_STRICT
 #define INTEL_PT_STATE_ERR1	INTEL_PT_STATE_NO_PSB
 #define INTEL_PT_STATE_ERR2	INTEL_PT_STATE_NO_PSB

@@ -99,6 +118,7 @@ struct intel_pt_decoder {
 	uint64_t timestamp;
 	uint64_t tsc_timestamp;
 	uint64_t ref_timestamp;
+	uint64_t sample_timestamp;
 	uint64_t ret_addr;
 	uint64_t ctc_timestamp;
 	uint64_t ctc_delta;

@@ -139,6 +159,7 @@ struct intel_pt_decoder {
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
 	uint64_t timestamp_insn_cnt;
+	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;
 	int no_progress;
 	int stuck_ip_prd;

@@ -898,6 +919,7 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 
 	decoder->tot_insn_cnt += insn_cnt;
 	decoder->timestamp_insn_cnt += insn_cnt;
+	decoder->sample_insn_cnt += insn_cnt;
 	decoder->period_insn_cnt += insn_cnt;
 
 	if (err) {

@@ -2069,7 +2091,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 {
-	uint64_t est = decoder->timestamp_insn_cnt << 1;
+	uint64_t est = decoder->sample_insn_cnt << 1;
 
 	if (!decoder->cbr || !decoder->max_non_turbo_ratio)
 		goto out;

@@ -2077,7 +2099,7 @@ static uint64_t intel_pt_est_timestamp(struct intel_pt_decoder *decoder)
 	est *= decoder->max_non_turbo_ratio;
 	est /= decoder->cbr;
 out:
-	return decoder->timestamp + est;
+	return decoder->sample_timestamp + est;
 }
 
 const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)

@@ -2133,11 +2155,17 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 	if (err) {
 		decoder->state.err = intel_pt_ext_err(err);
 		decoder->state.from_ip = decoder->ip;
+		decoder->sample_timestamp = decoder->timestamp;
+		decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
 	} else {
 		decoder->state.err = 0;
+		if (intel_pt_sample_time(decoder->pkt_state)) {
+			decoder->sample_timestamp = decoder->timestamp;
+			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
+		}
 	}
 
-	decoder->state.timestamp = decoder->timestamp;
+	decoder->state.timestamp = decoder->sample_timestamp;
 	decoder->state.est_timestamp = intel_pt_est_timestamp(decoder);
 	decoder->state.cr3 = decoder->cr3;
 	decoder->state.tot_insn_cnt = decoder->tot_insn_cnt;

index d5c69e822282..28b16c3acdde 100644
@@ -1932,6 +1932,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_PSB:
+			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psb(decoder);
 			if (err)
 				return err;

index 28b16c3acdde..f9cd3aaef488 100644
@@ -2117,6 +2117,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			break;
 		case INTEL_PT_STATE_NO_IP:
 			decoder->last_ip = 0;
+			decoder->ip = 0;
 			/* Fall through */
 		case INTEL_PT_STATE_ERR_RESYNC:
 			err = intel_pt_sync_ip(decoder);

index f9cd3aaef488..62e2c2ad3f1d 100644
@@ -111,6 +111,7 @@ struct intel_pt_decoder {
 	bool have_tma;
 	bool have_cyc;
 	bool fixup_last_mtc;
+	bool have_last_ip;
 	uint64_t pos;
 	uint64_t last_ip;
 	uint64_t ip;

@@ -419,6 +420,7 @@ static uint64_t intel_pt_calc_ip(const struct intel_pt_pkt *packet,
 static inline void intel_pt_set_last_ip(struct intel_pt_decoder *decoder)
 {
 	decoder->last_ip = intel_pt_calc_ip(&decoder->packet, decoder->last_ip);
+	decoder->have_last_ip = true;
 }
 
 static inline void intel_pt_set_ip(struct intel_pt_decoder *decoder)

@@ -1672,6 +1674,8 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_PSB:
+			decoder->last_ip = 0;
+			decoder->have_last_ip = true;
 			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psbend(decoder);
 			if (err == -EAGAIN)

@@ -1752,7 +1756,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 
 static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
 {
-	return decoder->last_ip || decoder->packet.count == 0 ||
+	return decoder->have_last_ip || decoder->packet.count == 0 ||
 	       decoder->packet.count == 3 || decoder->packet.count == 6;
 }
 

@@ -1882,7 +1886,7 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 				if (decoder->ip)
 					return 0;
 			}
-			if (decoder->packet.count)
+			if (decoder->packet.count && decoder->have_last_ip)
 				intel_pt_set_last_ip(decoder);
 			break;
 

@@ -1932,6 +1936,8 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_PSB:
+			decoder->last_ip = 0;
+			decoder->have_last_ip = true;
 			intel_pt_clear_stack(&decoder->stack);
 			err = intel_pt_walk_psb(decoder);
 			if (err)

@@ -2066,6 +2072,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 
 	decoder->pge = false;
 	decoder->continuous_period = false;
+	decoder->have_last_ip = false;
 	decoder->last_ip = 0;
 	decoder->ip = 0;
 	intel_pt_clear_stack(&decoder->stack);

@@ -2074,6 +2081,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	if (err)
 		return err;
 
+	decoder->have_last_ip = true;
 	decoder->pkt_state = INTEL_PT_STATE_NO_IP;
 
 	err = intel_pt_walk_psb(decoder);

@@ -2116,6 +2124,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			err = intel_pt_sync(decoder);
 			break;
 		case INTEL_PT_STATE_NO_IP:
+			decoder->have_last_ip = false;
 			decoder->last_ip = 0;
 			decoder->ip = 0;
 			/* Fall through */

index 62e2c2ad3f1d..72b9dc8135a2 100644
@@ -1470,7 +1470,8 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_FUP:
 			decoder->pge = true;
-			intel_pt_set_last_ip(decoder);
+			if (decoder->packet.count)
+				intel_pt_set_last_ip(decoder);
 			break;
 
 		case INTEL_PT_MODE_TSX:

@@ -1756,8 +1757,9 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 
 static inline bool intel_pt_have_ip(struct intel_pt_decoder *decoder)
 {
-	return decoder->have_last_ip || decoder->packet.count == 0 ||
-	       decoder->packet.count == 3 || decoder->packet.count == 6;
+	return decoder->packet.count &&
+	       (decoder->have_last_ip || decoder->packet.count == 3 ||
+		decoder->packet.count == 6);
 }
 
 /* Walk PSB+ packets to get in sync. */

index 72b9dc8135a2..923c60efda26 100644
@@ -1882,14 +1882,10 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 			break;
 
 		case INTEL_PT_FUP:
-			if (decoder->overflow) {
-				if (intel_pt_have_ip(decoder))
-					intel_pt_set_ip(decoder);
-				if (decoder->ip)
-					return 0;
-			}
-			if (decoder->packet.count && decoder->have_last_ip)
-				intel_pt_set_last_ip(decoder);
+			if (intel_pt_have_ip(decoder))
+				intel_pt_set_ip(decoder);
+			if (decoder->ip)
+				return 0;
 			break;
 
 		case INTEL_PT_MTC:

index 923c60efda26..a97710162e07 100644
@@ -1962,6 +1962,8 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 {
 	int err;
 
+	decoder->set_fup_tx_flags = false;
+
 	intel_pt_log("Scanning for full IP\n");
 	err = intel_pt_walk_to_ip(decoder);
 	if (err)

index a97710162e07..cad40fe93bd2 100644
@@ -2127,7 +2127,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 			decoder->have_last_ip = false;
 			decoder->last_ip = 0;
 			decoder->ip = 0;
-			/* Fall through */
+			__fallthrough;
 		case INTEL_PT_STATE_ERR_RESYNC:
 			err = intel_pt_sync_ip(decoder);
 			break;

index cad40fe93bd2..dacb9223e743 100644
@@ -106,6 +106,7 @@ struct intel_pt_decoder {
 	const unsigned char *buf;
 	size_t len;
 	bool return_compression;
+	bool branch_enable;
 	bool mtc_insn;
 	bool pge;
 	bool have_tma;

@@ -214,6 +215,7 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 	decoder->pgd_ip             = params->pgd_ip;
 	decoder->data               = params->data;
 	decoder->return_compression = params->return_compression;
+	decoder->branch_enable      = params->branch_enable;
 
 	decoder->period             = params->period;
 	decoder->period_type        = params->period_type;

@@ -1650,6 +1652,10 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 				break;
 			}
 			intel_pt_set_last_ip(decoder);
+			if (!decoder->branch_enable) {
+				decoder->ip = decoder->last_ip;
+				break;
+			}
 			err = intel_pt_walk_fup(decoder);
 			if (err != -EAGAIN) {
 				if (err)

@@ -1964,6 +1970,13 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 
 	decoder->set_fup_tx_flags = false;
 
+	if (!decoder->branch_enable) {
+		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+		decoder->overflow = false;
+		decoder->state.type = 0; /* Do not have a sample */
+		return 0;
+	}
+
 	intel_pt_log("Scanning for full IP\n");
 	err = intel_pt_walk_to_ip(decoder);
 	if (err)

index e90619a43c0c..add3bed58349 100644
@@ -87,6 +87,7 @@ struct intel_pt_params {
 	bool (*pgd_ip)(uint64_t ip, void *data);
 	void *data;
 	bool return_compression;
+	bool branch_enable;
 	uint64_t period;
 	enum intel_pt_period_type period_type;
 	unsigned max_non_turbo_ratio;

index 4c7718f87a08..5c59b8c6a719 100644
@@ -668,6 +668,19 @@ static bool intel_pt_return_compression(struct intel_pt *pt)
 	return true;
 }
 
+static bool intel_pt_branch_enable(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+	u64 config;
+
+	evlist__for_each_entry(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+		    (config & 1) && !(config & 0x2000))
+			return false;
+	}
+	return true;
+}
+
 static unsigned int intel_pt_mtc_period(struct intel_pt *pt)
 {
 	struct perf_evsel *evsel;

@@ -799,6 +812,7 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
 	params.walk_insn = intel_pt_walk_next_insn;
 	params.data = ptq;
 	params.return_compression = intel_pt_return_compression(pt);
+	params.branch_enable = intel_pt_branch_enable(pt);
 	params.max_non_turbo_ratio = pt->max_non_turbo_ratio;
 	params.mtc_period = intel_pt_mtc_period(pt);
 	params.tsc_ctc_ratio_n = pt->tsc_ctc_ratio_n;

index f630de0206a1..007621a7e420 100644
@@ -196,6 +196,7 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
 	int psb_cyc, psb_periods, psb_period;
 	int pos = 0;
 	u64 config;
+	char c;
 
 	pos += scnprintf(buf + pos, sizeof(buf) - pos, "tsc");
 

@@ -229,6 +230,10 @@ static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
 		}
 	}
 
+	if (perf_pmu__scan_file(intel_pt_pmu, "format/pt", "%c", &c) == 1 &&
+	    perf_pmu__scan_file(intel_pt_pmu, "format/branch", "%c", &c) == 1)
+		pos += scnprintf(buf + pos, sizeof(buf) - pos, ",pt,branch");
+
 	pr_debug2("%s default config: %s\n", intel_pt_pmu->name, buf);
 
 	intel_pt_parse_terms(&intel_pt_pmu->format, buf, &config);

index dacb9223e743..e42804d10001 100644
@@ -158,8 +158,15 @@ struct intel_pt_decoder {
 	bool continuous_period;
 	bool overflow;
 	bool set_fup_tx_flags;
+	bool set_fup_ptw;
+	bool set_fup_mwait;
+	bool set_fup_pwre;
+	bool set_fup_exstop;
 	unsigned int fup_tx_flags;
 	unsigned int tx_flags;
+	uint64_t fup_ptw_payload;
+	uint64_t fup_mwait_payload;
+	uint64_t fup_pwre_payload;
 	uint64_t timestamp_insn_cnt;
 	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;

@@ -660,6 +667,8 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 	case INTEL_PT_PAD:
 	case INTEL_PT_VMCS:
 	case INTEL_PT_MNT:
+	case INTEL_PT_PTWRITE:
+	case INTEL_PT_PTWRITE_IP:
 		return 0;
 
 	case INTEL_PT_MTC:

@@ -758,6 +767,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 
 	case INTEL_PT_TIP_PGD:
 	case INTEL_PT_TRACESTOP:
+	case INTEL_PT_EXSTOP:
+	case INTEL_PT_EXSTOP_IP:
+	case INTEL_PT_MWAIT:
+	case INTEL_PT_PWRE:
+	case INTEL_PT_PWRX:
 	case INTEL_PT_OVF:
 	case INTEL_PT_BAD: /* Does not happen */
 	default:

@@ -1016,6 +1030,57 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 	return err;
 }
 
+static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
+{
+	bool ret = false;
+
+	if (decoder->set_fup_tx_flags) {
+		decoder->set_fup_tx_flags = false;
+		decoder->tx_flags = decoder->fup_tx_flags;
+		decoder->state.type = INTEL_PT_TRANSACTION;
+		decoder->state.from_ip = decoder->ip;
+		decoder->state.to_ip = 0;
+		decoder->state.flags = decoder->fup_tx_flags;
+		return true;
+	}
+	if (decoder->set_fup_ptw) {
+		decoder->set_fup_ptw = false;
+		decoder->state.type = INTEL_PT_PTW;
+		decoder->state.flags |= INTEL_PT_FUP_IP;
+		decoder->state.from_ip = decoder->ip;
+		decoder->state.to_ip = 0;
+		decoder->state.ptw_payload = decoder->fup_ptw_payload;
+		return true;
+	}
+	if (decoder->set_fup_mwait) {
+		decoder->set_fup_mwait = false;
+		decoder->state.type = INTEL_PT_MWAIT_OP;
+		decoder->state.from_ip = decoder->ip;
+		decoder->state.to_ip = 0;
+		decoder->state.mwait_payload = decoder->fup_mwait_payload;
+		ret = true;
+	}
+	if (decoder->set_fup_pwre) {
+		decoder->set_fup_pwre = false;
+		decoder->state.type |= INTEL_PT_PWR_ENTRY;
+		decoder->state.type &= ~INTEL_PT_BRANCH;
+		decoder->state.from_ip = decoder->ip;
+		decoder->state.to_ip = 0;
+		decoder->state.pwre_payload = decoder->fup_pwre_payload;
+		ret = true;
+	}
+	if (decoder->set_fup_exstop) {
+		decoder->set_fup_exstop = false;
+		decoder->state.type |= INTEL_PT_EX_STOP;
+		decoder->state.type &= ~INTEL_PT_BRANCH;
+		decoder->state.flags |= INTEL_PT_FUP_IP;
+		decoder->state.from_ip = decoder->ip;
+		decoder->state.to_ip = 0;
+		ret = true;
+	}
+	return ret;
+}
+
 static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 {
 	struct intel_pt_insn intel_pt_insn;

@@ -1029,15 +1094,8 @@ static int intel_pt_walk_fup(struct intel_pt_decoder *decoder)
 		if (err == INTEL_PT_RETURN)
 			return 0;
 		if (err == -EAGAIN) {
-			if (decoder->set_fup_tx_flags) {
-				decoder->set_fup_tx_flags = false;
-				decoder->tx_flags = decoder->fup_tx_flags;
-				decoder->state.type = INTEL_PT_TRANSACTION;
-				decoder->state.from_ip = decoder->ip;
-				decoder->state.to_ip = 0;
-				decoder->state.flags = decoder->fup_tx_flags;
+			if (intel_pt_fup_event(decoder))
 				return 0;
-			}
 			return err;
 		}
 		decoder->set_fup_tx_flags = false;

@@ -1443,6 +1501,13 @@ static int intel_pt_walk_psbend(struct intel_pt_decoder *decoder)
 		case INTEL_PT_TRACESTOP:
 		case INTEL_PT_BAD:
 		case INTEL_PT_PSB:
+		case INTEL_PT_PTWRITE:
+		case INTEL_PT_PTWRITE_IP:
+		case INTEL_PT_EXSTOP:
+		case INTEL_PT_EXSTOP_IP:
+		case INTEL_PT_MWAIT:
+		case INTEL_PT_PWRE:
+		case INTEL_PT_PWRX:
 			decoder->have_tma = false;
 			intel_pt_log("ERROR: Unexpected packet\n");
 			return -EAGAIN;

@@ -1524,6 +1589,13 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_MODE_TSX:
 		case INTEL_PT_BAD:
 		case INTEL_PT_PSBEND:
+		case INTEL_PT_PTWRITE:
+		case INTEL_PT_PTWRITE_IP:
+		case INTEL_PT_EXSTOP:
+		case INTEL_PT_EXSTOP_IP:
+		case INTEL_PT_MWAIT:
+		case INTEL_PT_PWRE:
+		case INTEL_PT_PWRX:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
 			return -ENOENT;

@@ -1654,8 +1726,13 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 			intel_pt_set_last_ip(decoder);
 			if (!decoder->branch_enable) {
 				decoder->ip = decoder->last_ip;
+				if (intel_pt_fup_event(decoder))
+					return 0;
+				no_tip = false;
 				break;
 			}
+			if (decoder->set_fup_mwait)
+				no_tip = true;
 			err = intel_pt_walk_fup(decoder);
 			if (err != -EAGAIN) {
 				if (err)

@@ -1755,6 +1832,71 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PAD:
 			break;
 
+		case INTEL_PT_PTWRITE_IP:
+			decoder->fup_ptw_payload = decoder->packet.payload;
+			err = intel_pt_get_next_packet(decoder);
+			if (err)
+				return err;
+			if (decoder->packet.type == INTEL_PT_FUP) {
+				decoder->set_fup_ptw = true;
+				no_tip = true;
+			} else {
+				intel_pt_log_at("ERROR: Missing FUP after PTWRITE",
+						decoder->pos);
+			}
+			goto next;
+
+		case INTEL_PT_PTWRITE:
+			decoder->state.type = INTEL_PT_PTW;
+			decoder->state.from_ip = decoder->ip;
+			decoder->state.to_ip = 0;
+			decoder->state.ptw_payload = decoder->packet.payload;
+			return 0;
+
+		case INTEL_PT_MWAIT:
+			decoder->fup_mwait_payload = decoder->packet.payload;
+			decoder->set_fup_mwait = true;
+			break;
+
+		case INTEL_PT_PWRE:
+			if (decoder->set_fup_mwait) {
+				decoder->fup_pwre_payload =
+							decoder->packet.payload;
+				decoder->set_fup_pwre = true;
+				break;
+			}
+			decoder->state.type = INTEL_PT_PWR_ENTRY;
+			decoder->state.from_ip = decoder->ip;
+			decoder->state.to_ip = 0;
+			decoder->state.pwrx_payload = decoder->packet.payload;
+			return 0;
+
+		case INTEL_PT_EXSTOP_IP:
+			err = intel_pt_get_next_packet(decoder);
+			if (err)
+				return err;
+			if (decoder->packet.type == INTEL_PT_FUP) {
+				decoder->set_fup_exstop = true;
+				no_tip = true;
+			} else {
+				intel_pt_log_at("ERROR: Missing FUP after EXSTOP",
+						decoder->pos);
+			}
+			goto next;
+
+		case INTEL_PT_EXSTOP:
+			decoder->state.type = INTEL_PT_EX_STOP;
+			decoder->state.from_ip = decoder->ip;
+			decoder->state.to_ip = 0;
+			return 0;
+
+		case INTEL_PT_PWRX:
+			decoder->state.type = INTEL_PT_PWR_EXIT;
+			decoder->state.from_ip = decoder->ip;
+			decoder->state.to_ip = 0;
+			decoder->state.pwrx_payload = decoder->packet.payload;
+			return 0;
+
 		default:
 			return intel_pt_bug(decoder);
 		}

@@ -1784,6 +1926,13 @@ static int intel_pt_walk_psb(struct intel_pt_decoder *decoder)
 			__fallthrough;
 		case INTEL_PT_TIP_PGE:
 		case INTEL_PT_TIP:
+		case INTEL_PT_PTWRITE:
+		case INTEL_PT_PTWRITE_IP:
+		case INTEL_PT_EXSTOP:
+		case INTEL_PT_EXSTOP_IP:
+		case INTEL_PT_MWAIT:
+		case INTEL_PT_PWRE:
+		case INTEL_PT_PWRX:
 			intel_pt_log("ERROR: Unexpected packet\n");
 			return -ENOENT;
 

@@ -1958,6 +2107,13 @@ static int intel_pt_walk_to_ip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_VMCS:
 		case INTEL_PT_MNT:
 		case INTEL_PT_PAD:
+		case INTEL_PT_PTWRITE:
+		case INTEL_PT_PTWRITE_IP:
+		case INTEL_PT_EXSTOP:
+		case INTEL_PT_EXSTOP_IP:
+		case INTEL_PT_MWAIT:
+		case INTEL_PT_PWRE:
+		case INTEL_PT_PWRX:
 		default:
 			break;
 		}

@@ -1969,6 +2125,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 	int err;
 
 	decoder->set_fup_tx_flags = false;
+	decoder->set_fup_ptw = false;
+	decoder->set_fup_mwait = false;
+	decoder->set_fup_pwre = false;
+	decoder->set_fup_exstop = false;
 
 	if (!decoder->branch_enable) {
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;

index add3bed58349..414c88e9e0da 100644
@@ -25,11 +25,17 @@
 #define INTEL_PT_IN_TX		(1 << 0)
 #define INTEL_PT_ABORT_TX	(1 << 1)
 #define INTEL_PT_ASYNC		(1 << 2)
+#define INTEL_PT_FUP_IP		(1 << 3)
 
 enum intel_pt_sample_type {
 	INTEL_PT_BRANCH		= 1 << 0,
 	INTEL_PT_INSTRUCTION	= 1 << 1,
 	INTEL_PT_TRANSACTION	= 1 << 2,
+	INTEL_PT_PTW		= 1 << 3,
+	INTEL_PT_MWAIT_OP	= 1 << 4,
+	INTEL_PT_PWR_ENTRY	= 1 << 5,
+	INTEL_PT_EX_STOP	= 1 << 6,
+	INTEL_PT_PWR_EXIT	= 1 << 7,
 };
 
 enum intel_pt_period_type {

@@ -63,6 +69,10 @@ struct intel_pt_state {
 	uint64_t timestamp;
 	uint64_t est_timestamp;
 	uint64_t trace_nr;
+	uint64_t ptw_payload;
+	uint64_t mwait_payload;
+	uint64_t pwre_payload;
+	uint64_t pwrx_payload;
 	uint32_t flags;
 	enum intel_pt_insn_op insn_op;
 	int insn_len;

138 lines not on this page · raw message

index 781bb79883bd..73ddc3a88d07 100644
@@ -52,6 +52,13 @@ enum intel_pt_pkt_type {
 	INTEL_PT_PIP,
 	INTEL_PT_OVF,
 	INTEL_PT_MNT,
+	INTEL_PT_PTWRITE,
+	INTEL_PT_PTWRITE_IP,
+	INTEL_PT_EXSTOP,
+	INTEL_PT_EXSTOP_IP,
+	INTEL_PT_MWAIT,
+	INTEL_PT_PWRE,
+	INTEL_PT_PWRX,
 };
 
 struct intel_pt_pkt {

index e42804d10001..96bf8d8e83c0 100644
@@ -1444,7 +1444,7 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 
 static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
 {
-	unsigned int cbr = decoder->packet.payload;
+	unsigned int cbr = decoder->packet.payload & 0xff;
 
 	if (decoder->cbr == cbr)
 		return;

index accdb646a03d..ba4c9dd18643 100644
@@ -130,7 +130,7 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len,
 	if (len < 4)
 		return INTEL_PT_NEED_MORE_BYTES;
 	packet->type = INTEL_PT_CBR;
-	packet->payload = buf[2];
+	packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2));
 	return 4;
 }
 

index 96bf8d8e83c0..5dea06289db5 100644
@@ -141,6 +141,7 @@ struct intel_pt_decoder {
 	int pkt_len;
 	int last_packet_type;
 	unsigned int cbr;
+	unsigned int cbr_seen;
 	unsigned int max_non_turbo_ratio;
 	double max_non_turbo_ratio_fp;
 	double cbr_cyc_to_tsc;

@@ -167,6 +168,7 @@ struct intel_pt_decoder {
 	uint64_t fup_ptw_payload;
 	uint64_t fup_mwait_payload;
 	uint64_t fup_pwre_payload;
+	uint64_t cbr_payload;
 	uint64_t timestamp_insn_cnt;
 	uint64_t sample_insn_cnt;
 	uint64_t stuck_ip;

@@ -1446,6 +1448,8 @@ static void intel_pt_calc_cbr(struct intel_pt_decoder *decoder)
 {
 	unsigned int cbr = decoder->packet.payload & 0xff;
 
+	decoder->cbr_payload = decoder->packet.payload;
+
 	if (decoder->cbr == cbr)
 		return;
 

@@ -1806,6 +1810,16 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_CBR:
 			intel_pt_calc_cbr(decoder);
+			if (!decoder->branch_enable &&
+			    decoder->cbr != decoder->cbr_seen) {
+				decoder->cbr_seen = decoder->cbr;
+				decoder->state.type = INTEL_PT_CBR_CHG;
+				decoder->state.from_ip = decoder->ip;
+				decoder->state.to_ip = 0;
+				decoder->state.cbr_payload =
+							decoder->packet.payload;
+				return 0;
+			}
 			break;
 
 		case INTEL_PT_MODE_EXEC:

@@ -2343,6 +2357,11 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 		decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
 	} else {
 		decoder->state.err = 0;
+		if (decoder->cbr != decoder->cbr_seen && decoder->state.type) {
+			decoder->cbr_seen = decoder->cbr;
+			decoder->state.type |= INTEL_PT_CBR_CHG;
+			decoder->state.cbr_payload = decoder->cbr_payload;
+		}
 		if (intel_pt_sample_time(decoder->pkt_state)) {
 			decoder->sample_timestamp = decoder->timestamp;
 			decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;

index 414c88e9e0da..921b22e8ca0e 100644
@@ -36,6 +36,7 @@ enum intel_pt_sample_type {
 	INTEL_PT_PWR_ENTRY	= 1 << 5,
 	INTEL_PT_EX_STOP	= 1 << 6,
 	INTEL_PT_PWR_EXIT	= 1 << 7,
+	INTEL_PT_CBR_CHG	= 1 << 8,
 };
 
 enum intel_pt_period_type {

@@ -73,6 +74,7 @@ struct intel_pt_state {
 	uint64_t mwait_payload;
 	uint64_t pwre_payload;
 	uint64_t pwrx_payload;
+	uint64_t cbr_payload;
 	uint32_t flags;
 	enum intel_pt_insn_op insn_op;
 	int insn_len;

index 5c59b8c6a719..3ae03f920253 100644
@@ -1322,18 +1322,14 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	ptq->have_sample = false;
 
 	if (pt->sample_instructions &&
-	    (state->type & INTEL_PT_INSTRUCTION) &&
-	    (!pt->synth_opts.initial_skip ||
-	     pt->num_events++ >= pt->synth_opts.initial_skip)) {
+	    (state->type & INTEL_PT_INSTRUCTION)) {
 		err = intel_pt_synth_instruction_sample(ptq);
 		if (err)
 			return err;
 	}
 
 	if (pt->sample_transactions &&
-	    (state->type & INTEL_PT_TRANSACTION) &&
-	    (!pt->synth_opts.initial_skip ||
-	     pt->num_events++ >= pt->synth_opts.initial_skip)) {
+	    (state->type & INTEL_PT_TRANSACTION)) {
 		err = intel_pt_synth_transaction_sample(ptq);
 		if (err)
 			return err;

index 3ae03f920253..6df836469f2b 100644
@@ -2035,6 +2035,7 @@ static int intel_pt_synth_events(struct intel_pt *pt,
 			return err;
 		}
 		pt->sample_transactions = true;
+		pt->transactions_sample_type = attr.sample_type;
 		pt->transactions_id = id;
 		id += 1;
 		evlist__for_each_entry(evlist, evsel) {

index 7dc1096264c5..d19c40a81040 100644
@@ -2035,7 +2035,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 
 		if (!(evsel->attr.sample_type & PERF_SAMPLE_CPU)) {
 			pr_err("File does not contain CPU events. "
-			       "Remove -c option to proceed.\n");
+			       "Remove -C option to proceed.\n");
 			return -1;
 		}
 	}

index d05aec491cff..79a101e0e13b 100644
@@ -383,7 +383,7 @@ static int perf_session__check_output_opt(struct perf_session *session)
 		 */
 		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
 			pr_err("%s events do not exist. "
-			       "Remove corresponding -f option to proceed.\n",
+			       "Remove corresponding -F option to proceed.\n",
 			       event_type(j));
 			return -1;
 		}

index 79a101e0e13b..99167bafe81c 100644
@@ -117,6 +117,11 @@ struct output_option {
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 };
 
+enum {
+	OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX,
+	OUTPUT_TYPE_MAX
+};
+
 /* default set to maintain compatibility with current format */
 static struct {
 	bool user_set;

@@ -124,7 +129,7 @@ struct output_option {
 	unsigned int print_ip_opts;
 	u64 fields;
 	u64 invalid_fields;
-} output[PERF_TYPE_MAX] = {
+} output[OUTPUT_TYPE_MAX] = {
 
 	[PERF_TYPE_HARDWARE] = {
 		.user_set = false,

@@ -182,12 +187,43 @@ struct output_option {
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
+
+	[OUTPUT_TYPE_SYNTH] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+	},
 };
 
+static inline int output_type(unsigned int type)
+{
+	switch (type) {
+	case PERF_TYPE_SYNTH:
+		return OUTPUT_TYPE_SYNTH;
+	default:
+		return type;
+	}
+}
+
+static inline unsigned int attr_type(unsigned int type)
+{
+	switch (type) {
+	case OUTPUT_TYPE_SYNTH:
+		return PERF_TYPE_SYNTH;
+	default:
+		return type;
+	}
+}
+
 static bool output_set_by_user(void)
 {
 	int j;
-	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+	for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
 		if (output[j].user_set)
 			return true;
 	}

@@ -208,7 +244,7 @@ static const char *output_field2str(enum perf_output_field field)
 	return str;
 }
 
-#define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
+#define PRINT_FIELD(x)  (output[output_type(attr->type)].fields & PERF_OUTPUT_##x)
 
 static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
 				      u64 sample_type, const char *sample_msg,

@@ -216,7 +252,7 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
 				      bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	int type = attr->type;
+	int type = output_type(attr->type);
 	const char *evname;
 
 	if (attr->sample_type & sample_type)

@@ -346,7 +382,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 
 static void set_print_ip_opts(struct perf_event_attr *attr)
 {
-	unsigned int type = attr->type;
+	unsigned int type = output_type(attr->type);
 
 	output[type].print_ip_opts = 0;
 	if (PRINT_FIELD(IP))

@@ -374,14 +410,15 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	unsigned int j;
 	struct perf_evsel *evsel;
 
-	for (j = 0; j < PERF_TYPE_MAX; ++j) {
-		evsel = perf_session__find_first_evtype(session, j);
+	for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
+		evsel = perf_session__find_first_evtype(session, attr_type(j));
 
 		/*
 		 * even if fields is set to 0 (ie., show nothing) event must
 		 * exist if user explicitly includes it on the command line
 		 */
-		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
+		if (!evsel && output[j].user_set && !output[j].wildcard_set &&
+		    j != OUTPUT_TYPE_SYNTH) {
 			pr_err("%s events do not exist. "
 			       "Remove corresponding -F option to proceed.\n",
 			       event_type(j));

@@ -906,6 +943,7 @@ static void print_sample_bts(struct perf_sample *sample,
 			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	unsigned int type = output_type(attr->type);
 	bool print_srcline_last = false;
 
 	if (PRINT_FIELD(CALLINDENT))

@@ -913,7 +951,7 @@ static void print_sample_bts(struct perf_sample *sample,
 
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
-		unsigned int print_opts = output[attr->type].print_ip_opts;
+		unsigned int print_opts = output[type].print_ip_opts;
 		struct callchain_cursor *cursor = NULL;
 
 		if (symbol_conf.use_callchain && sample->callchain &&

@@ -936,7 +974,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	/* print branch_to information */
 	if (PRINT_FIELD(ADDR) ||
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
-	     !output[attr->type].user_set)) {
+	     !output[type].user_set)) {
 		printf(" => ");
 		print_sample_addr(sample, thread, attr);
 	}

@@ -1132,8 +1170,9 @@ static void process_event(struct perf_script *script,
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
+	unsigned int type = output_type(attr->type);
 
-	if (output[attr->type].fields == 0)
+	if (output[type].fields == 0)
 		return;
 
 	print_sample_start(sample, thread, evsel);

@@ -1180,7 +1219,7 @@ static void process_event(struct perf_script *script,
 			cursor = &callchain_cursor;
 
 		putchar(cursor ? '\n' : ' ');
-		sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout);
+		sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout);
 	}
 
 	if (PRINT_FIELD(IREGS))

@@ -1325,7 +1364,8 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
-	if (evsel->attr.type >= PERF_TYPE_MAX)
+	if (evsel->attr.type >= PERF_TYPE_MAX &&
+	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
 
 	evlist__for_each_entry(evlist, pos) {

@@ -1749,6 +1789,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			type = PERF_TYPE_RAW;
 		else if (!strcmp(str, "break"))
 			type = PERF_TYPE_BREAKPOINT;
+		else if (!strcmp(str, "synth"))
+			type = OUTPUT_TYPE_SYNTH;
 		else {
 			fprintf(stderr, "Invalid event type in field string.\n");
 			rc = -EINVAL;

@@ -1775,7 +1817,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 		if (output_set_by_user())
 			pr_warning("Overriding previous field request for all events.\n");
 
-		for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
 			output[j].fields = 0;
 			output[j].user_set = true;
 			output[j].wildcard_set = true;

@@ -1801,7 +1843,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			/* add user option to all events types for
 			 * which it is valid
 			 */
-			for (j = 0; j < PERF_TYPE_MAX; ++j) {
+			for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
 				if (output[j].invalid_fields & all_output_options[i].field) {
 					pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
 						   all_output_options[i].str, event_type(j));

@@ -2444,7 +2486,7 @@ int cmd_script(int argc, const char **argv)
 		     symbol__config_symfs),
 	OPT_CALLBACK('F', "fields", NULL, "str",
 		     "comma separated output fields prepend with 'type:'. "
-		     "Valid types: hw,sw,trace,raw. "
+		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
 		     "bpf-output,callindent,insn,insnlen,brstackinsn",

index 27ac047490c3..af285ed951f4 100644
@@ -252,6 +252,9 @@ enum auxtrace_error_type {
 	PERF_AUXTRACE_ERROR_MAX
 };
 
+/* Attribute type for custom synthesized events */
+#define PERF_TYPE_SYNTH		3000000000
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of

index 4bce7d8679cb..2999e7e425f6 100644
@@ -119,6 +119,11 @@ struct output_option {
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
 };
 
+enum {
+	OUTPUT_TYPE_SYNTH = PERF_TYPE_MAX,
+	OUTPUT_TYPE_MAX
+};
+
 /* default set to maintain compatibility with current format */
 static struct {
 	bool user_set;

@@ -126,7 +131,7 @@ struct output_option {
 	unsigned int print_ip_opts;
 	u64 fields;
 	u64 invalid_fields;
-} output[PERF_TYPE_MAX] = {
+} output[OUTPUT_TYPE_MAX] = {
 
 	[PERF_TYPE_HARDWARE] = {
 		.user_set = false,

@@ -184,12 +189,43 @@ struct output_option {
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},
+
+	[OUTPUT_TYPE_SYNTH] = {
+		.user_set = false,
+
+		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
+			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
+			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+
+		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
+	},
 };
 
+static inline int output_type(unsigned int type)
+{
+	switch (type) {
+	case PERF_TYPE_SYNTH:
+		return OUTPUT_TYPE_SYNTH;
+	default:
+		return type;
+	}
+}
+
+static inline unsigned int attr_type(unsigned int type)
+{
+	switch (type) {
+	case OUTPUT_TYPE_SYNTH:
+		return PERF_TYPE_SYNTH;
+	default:
+		return type;
+	}
+}
+
 static bool output_set_by_user(void)
 {
 	int j;
-	for (j = 0; j < PERF_TYPE_MAX; ++j) {
+	for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
 		if (output[j].user_set)
 			return true;
 	}

@@ -210,7 +246,7 @@ static const char *output_field2str(enum perf_output_field field)
 	return str;
 }
 
-#define PRINT_FIELD(x)  (output[attr->type].fields & PERF_OUTPUT_##x)
+#define PRINT_FIELD(x)  (output[output_type(attr->type)].fields & PERF_OUTPUT_##x)
 
 static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
 				      u64 sample_type, const char *sample_msg,

@@ -218,7 +254,7 @@ static int perf_evsel__do_check_stype(struct perf_evsel *evsel,
 				      bool allow_user_set)
 {
 	struct perf_event_attr *attr = &evsel->attr;
-	int type = attr->type;
+	int type = output_type(attr->type);
 	const char *evname;
 
 	if (attr->sample_type & sample_type)

@@ -348,7 +384,7 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel,
 
 static void set_print_ip_opts(struct perf_event_attr *attr)
 {
-	unsigned int type = attr->type;
+	unsigned int type = output_type(attr->type);
 
 	output[type].print_ip_opts = 0;
 	if (PRINT_FIELD(IP))

@@ -376,14 +412,15 @@ static int perf_session__check_output_opt(struct perf_session *session)
 	unsigned int j;
 	struct perf_evsel *evsel;
 
-	for (j = 0; j < PERF_TYPE_MAX; ++j) {
-		evsel = perf_session__find_first_evtype(session, j);
+	for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
+		evsel = perf_session__find_first_evtype(session, attr_type(j));
 
 		/*
 		 * even if fields is set to 0 (ie., show nothing) event must
 		 * exist if user explicitly includes it on the command line
 		 */
-		if (!evsel && output[j].user_set && !output[j].wildcard_set) {
+		if (!evsel && output[j].user_set && !output[j].wildcard_set &&
+		    j != OUTPUT_TYPE_SYNTH) {
 			pr_err("%s events do not exist. "
 			       "Remove corresponding -F option to proceed.\n",
 			       event_type(j));

@@ -989,6 +1026,7 @@ static void print_sample_bts(struct perf_sample *sample,
 			     struct machine *machine)
 {
 	struct perf_event_attr *attr = &evsel->attr;
+	unsigned int type = output_type(attr->type);
 	bool print_srcline_last = false;
 
 	if (PRINT_FIELD(CALLINDENT))

@@ -996,7 +1034,7 @@ static void print_sample_bts(struct perf_sample *sample,
 
 	/* print branch_from information */
 	if (PRINT_FIELD(IP)) {
-		unsigned int print_opts = output[attr->type].print_ip_opts;
+		unsigned int print_opts = output[type].print_ip_opts;
 		struct callchain_cursor *cursor = NULL;
 
 		if (symbol_conf.use_callchain && sample->callchain &&

@@ -1019,7 +1057,7 @@ static void print_sample_bts(struct perf_sample *sample,
 	/* print branch_to information */
 	if (PRINT_FIELD(ADDR) ||
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
-	     !output[attr->type].user_set)) {
+	     !output[type].user_set)) {
 		printf(" => ");
 		print_sample_addr(sample, thread, attr);
 	}

@@ -1215,8 +1253,9 @@ static void process_event(struct perf_script *script,
 {
 	struct thread *thread = al->thread;
 	struct perf_event_attr *attr = &evsel->attr;
+	unsigned int type = output_type(attr->type);
 
-	if (output[attr->type].fields == 0)
+	if (output[type].fields == 0)
 		return;
 
 	print_sample_start(sample, thread, evsel);

@@ -1263,7 +1302,7 @@ static void process_event(struct perf_script *script,
 			cursor = &callchain_cursor;
 
 		putchar(cursor ? '\n' : ' ');
-		sample__fprintf_sym(sample, al, 0, output[attr->type].print_ip_opts, cursor, stdout);
+		sample__fprintf_sym(sample, al, 0, output[type].print_ip_opts, cursor, stdout);
 	}
 
 	if (PRINT_FIELD(IREGS))

@@ -1410,7 +1449,8 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	evlist = *pevlist;
 	evsel = perf_evlist__last(*pevlist);
 
-	if (evsel->attr.type >= PERF_TYPE_MAX)
+	if (evsel->attr.type >= PERF_TYPE_MAX &&
+	    evsel->attr.type != PERF_TYPE_SYNTH)
 		return 0;
 
 	evlist__for_each_entry(evlist, pos) {

@@ -1835,6 +1875,8 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			type = PERF_TYPE_RAW;
 		else if (!strcmp(str, "break"))
 			type = PERF_TYPE_BREAKPOINT;
+		else if (!strcmp(str, "synth"))
+			type = OUTPUT_TYPE_SYNTH;
 		else {
 			fprintf(stderr, "Invalid event type in field string.\n");
 			rc = -EINVAL;

@@ -1865,7 +1907,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 		if (output_set_by_user())
 			pr_warning("Overriding previous field request for all events.\n");
 
-		for (j = 0; j < PERF_TYPE_MAX; ++j) {
+		for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
 			output[j].fields = 0;
 			output[j].user_set = true;
 			output[j].wildcard_set = true;

@@ -1908,7 +1950,7 @@ static int parse_output_fields(const struct option *opt __maybe_unused,
 			/* add user option to all events types for
 			 * which it is valid
 			 */
-			for (j = 0; j < PERF_TYPE_MAX; ++j) {
+			for (j = 0; j < OUTPUT_TYPE_MAX; ++j) {
 				if (output[j].invalid_fields & all_output_options[i].field) {
 					pr_warning("\'%s\' not valid for %s events. Ignoring.\n",
 						   all_output_options[i].str, event_type(j));

@@ -2560,7 +2602,7 @@ int cmd_script(int argc, const char **argv)
 	OPT_CALLBACK('F', "fields", NULL, "str",
 		     "comma separated output fields prepend with 'type:'. "
 		     "+field to add and -field to remove."
-		     "Valid types: hw,sw,trace,raw. "
+		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
 		     "bpf-output,callindent,insn,insnlen,brstackinsn",

index 7c3fa1c8cbcd..4162e72eb1b0 100644
@@ -252,6 +252,9 @@ enum auxtrace_error_type {
 	PERF_AUXTRACE_ERROR_MAX
 };
 
+/* Attribute type for custom synthesized events */
+#define PERF_TYPE_SYNTH		3000000000
+
 /*
  * The kernel collects the number of events it couldn't send in a stretch and
  * when possible sends this number in a PERF_RECORD_LOST event. The number of

index 99167bafe81c..f7a5130d2fd0 100644
@@ -85,6 +85,7 @@ enum perf_output_field {
 	PERF_OUTPUT_INSN	    = 1U << 21,
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
+	PERF_OUTPUT_SYNTH	    = 1U << 24,
 };
 
 struct output_option {

@@ -115,6 +116,7 @@ struct output_option {
 	{.str = "insn", .field = PERF_OUTPUT_INSN},
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
+	{.str = "synth", .field = PERF_OUTPUT_SYNTH},
 };
 
 enum {

@@ -194,7 +196,8 @@ enum {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+			      PERF_OUTPUT_SYNTH,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},

@@ -1117,6 +1120,15 @@ static void print_sample_bpf_output(struct perf_sample *sample)
 		       (char *)(sample->raw_data));
 }
 
+static void print_sample_synth(struct perf_sample *sample __maybe_unused,
+			       struct perf_evsel *evsel)
+{
+	switch (evsel->attr.config) {
+	default:
+		break;
+	}
+}
+
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;

@@ -1201,6 +1213,10 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(TRACE))
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
+
+	if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH))
+		print_sample_synth(sample, evsel);
+
 	if (PRINT_FIELD(ADDR))
 		print_sample_addr(sample, thread, attr);
 

@@ -2489,7 +2505,7 @@ int cmd_script(int argc, const char **argv)
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn",
+		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),

index 2999e7e425f6..8a827e813a9e 100644
@@ -86,6 +86,7 @@ enum perf_output_field {
 	PERF_OUTPUT_INSNLEN	    = 1U << 22,
 	PERF_OUTPUT_BRSTACKINSN	    = 1U << 23,
 	PERF_OUTPUT_BRSTACKOFF	    = 1U << 24,
+	PERF_OUTPUT_SYNTH	    = 1U << 25,
 };
 
 struct output_option {

@@ -117,6 +118,7 @@ struct output_option {
 	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
 	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
+	{.str = "synth", .field = PERF_OUTPUT_SYNTH},
 };
 
 enum {

@@ -196,7 +198,8 @@ enum {
 		.fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 			      PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 			      PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
-			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
+			      PERF_OUTPUT_SYM | PERF_OUTPUT_DSO |
+			      PERF_OUTPUT_SYNTH,
 
 		.invalid_fields = PERF_OUTPUT_TRACE | PERF_OUTPUT_BPF_OUTPUT,
 	},

@@ -1200,6 +1203,15 @@ static void print_sample_bpf_output(struct perf_sample *sample)
 		       (char *)(sample->raw_data));
 }
 
+static void print_sample_synth(struct perf_sample *sample __maybe_unused,
+			       struct perf_evsel *evsel)
+{
+	switch (evsel->attr.config) {
+	default:
+		break;
+	}
+}
+
 struct perf_script {
 	struct perf_tool	tool;
 	struct perf_session	*session;

@@ -1284,6 +1296,10 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(TRACE))
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
+
+	if (attr->type == PERF_TYPE_SYNTH && PRINT_FIELD(SYNTH))
+		print_sample_synth(sample, evsel);
+
 	if (PRINT_FIELD(ADDR))
 		print_sample_addr(sample, thread, attr);
 

@@ -2605,7 +2621,7 @@ int cmd_script(int argc, const char **argv)
 		     "Valid types: hw,sw,trace,raw,synth. "
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,"
 		     "addr,symoff,period,iregs,brstack,brstacksym,flags,"
-		     "bpf-output,callindent,insn,insnlen,brstackinsn",
+		     "bpf-output,callindent,insn,insnlen,brstackinsn,synth",
 		     parse_output_fields),
 	OPT_BOOLEAN('a', "all-cpus", &system_wide,
 		    "system-wide collection from all CPUs"),

index 73ccc48126bb..039bb85e4171 100644
@@ -5,6 +5,8 @@
 #include <stddef.h>
 #include <assert.h>
 #include <linux/compiler.h>
+#include <endian.h>
+#include <byteswap.h>
 
 #ifndef UINT_MAX
 #define UINT_MAX	(~0U)

@@ -67,12 +69,33 @@
 #endif
 #endif
 
-/*
- * Both need more care to handle endianness
- * (Don't use bitmap_copy_le() for now)
- */
-#define cpu_to_le64(x)	(x)
-#define cpu_to_le32(x)	(x)
+#if __BYTE_ORDER == __BIG_ENDIAN
+#define cpu_to_le16 bswap_16
+#define cpu_to_le32 bswap_32
+#define cpu_to_le64 bswap_64
+#define le16_to_cpu bswap_16
+#define le32_to_cpu bswap_32
+#define le64_to_cpu bswap_64
+#define cpu_to_be16
+#define cpu_to_be32
+#define cpu_to_be64
+#define be16_to_cpu
+#define be32_to_cpu
+#define be64_to_cpu
+#else
+#define cpu_to_le16
+#define cpu_to_le32
+#define cpu_to_le64
+#define le16_to_cpu
+#define le32_to_cpu
+#define le64_to_cpu
+#define cpu_to_be16 bswap_16
+#define cpu_to_be32 bswap_32
+#define cpu_to_be64 bswap_64
+#define be16_to_cpu bswap_16
+#define be32_to_cpu bswap_32
+#define be64_to_cpu bswap_64
+#endif
 
 int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
 int scnprintf(char * buf, size_t size, const char * fmt, ...);