Merge tag 'perf-tools-fixes-for-v5.16-2021-12-11' of...

Merge tag 'perf-tools-fixes-for-v5.16-2021-12-11' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tools fixes from Arnaldo Carvalho de Melo:

 - Prevent out-of-bounds access to per sample registers.

 - Fix NULL vs IS_ERR_OR_NULL() checking on the python binding.

 - Intel PT fixes, half of those are one-liners:
      - Fix some PGE (packet generation enable/control flow packets) usage.
      - Fix sync state when a PSB (synchronization) packet is found.
      - Fix intel_pt_fup_event() assumptions about setting state type.
      - Fix state setting when receiving overflow (OVF) packet.
      - Fix next 'err' value, walking trace.
      - Fix missing 'instruction' events with 'q' option.
      - Fix error timestamp setting on the decoder error path.

* tag 'perf-tools-fixes-for-v5.16-2021-12-11' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux:
  perf python: Fix NULL vs IS_ERR_OR_NULL() checking
  perf intel-pt: Fix error timestamp setting on the decoder error path
  perf intel-pt: Fix missing 'instruction' events with 'q' option
  perf intel-pt: Fix next 'err' value, walking trace
  perf intel-pt: Fix state setting when receiving overflow (OVF) packet
  perf intel-pt: Fix intel_pt_fup_event() assumptions about setting state type
  perf intel-pt: Fix sync state when a PSB (synchronization) packet is found
  perf intel-pt: Fix some PGE (packet generation enable/control flow packets) usage
  perf tools: Prevent out-of-bounds access to registers

tools/perf/util/event.h

@@ -44,13 +44,16 @@ struct perf_event_attr;
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
 
+/* number of register is bound by the number of bits in regs_dump::mask (64) */
+#define PERF_SAMPLE_REGS_CACHE_SIZE (8 * sizeof(u64))
+
 struct regs_dump {
 	u64 abi;
 	u64 mask;
 	u64 *regs;
 
 	/* Cached values/mask filled by first register access. */
-	u64 cache_regs[PERF_REGS_MAX];
+	u64 cache_regs[PERF_SAMPLE_REGS_CACHE_SIZE];
 	u64 cache_mask;
 };
 

tools/perf/util/intel-pt-decoder/intel-pt-decoder.c

@@ -1205,61 +1205,69 @@ static int intel_pt_walk_insn(struct intel_pt_decoder *decoder,
 
 static bool intel_pt_fup_event(struct intel_pt_decoder *decoder)
 {
+	enum intel_pt_sample_type type = decoder->state.type;
 	bool ret = false;
 
+	decoder->state.type &= ~INTEL_PT_BRANCH;
+
 	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.type |= INTEL_PT_TRANSACTION;
 		if (decoder->fup_tx_flags & INTEL_PT_ABORT_TX)
 			decoder->state.type |= INTEL_PT_BRANCH;
-		decoder->state.from_ip = decoder->ip;
-		decoder->state.to_ip = 0;
 		decoder->state.flags = decoder->fup_tx_flags;
-		return true;
+		ret = true;
 	}
 	if (decoder->set_fup_ptw) {
 		decoder->set_fup_ptw = false;
-		decoder->state.type = INTEL_PT_PTW;
+		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;
+		ret = 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.type |= INTEL_PT_MWAIT_OP;
 		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;
 	}
 	if (decoder->set_fup_bep) {
 		decoder->set_fup_bep = false;
 		decoder->state.type |= INTEL_PT_BLK_ITEMS;
-		decoder->state.type &= ~INTEL_PT_BRANCH;
+		ret = true;
+	}
+	if (decoder->overflow) {
+		decoder->overflow = false;
+		if (!ret && !decoder->pge) {
+			if (decoder->hop) {
+				decoder->state.type = 0;
+				decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
+			}
+			decoder->pge = true;
+			decoder->state.type |= INTEL_PT_BRANCH | INTEL_PT_TRACE_BEGIN;
+			decoder->state.from_ip = 0;
+			decoder->state.to_ip = decoder->ip;
+			return true;
+		}
+	}
+	if (ret) {
 		decoder->state.from_ip = decoder->ip;
 		decoder->state.to_ip = 0;
-		ret = true;
+	} else {
+		decoder->state.type = type;
 	}
 	return ret;
 }
@@ -1608,7 +1616,16 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	intel_pt_set_nr(decoder);
 	decoder->timestamp_insn_cnt = 0;
-	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
+	decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
+	decoder->state.from_ip = decoder->ip;
+	decoder->ip = 0;
+	decoder->pge = false;
+	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;
+	decoder->set_fup_bep = false;
 	decoder->overflow = true;
 	return -EOVERFLOW;
 }
@@ -2666,6 +2683,8 @@ static int intel_pt_scan_for_psb(struct intel_pt_decoder *decoder);
 /* Hop mode: Ignore TNT, do not walk code, but get ip from FUPs and TIPs */
 static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, int *err)
 {
+	*err = 0;
+
 	/* Leap from PSB to PSB, getting ip from FUP within PSB+ */
 	if (decoder->leap && !decoder->in_psb && decoder->packet.type != INTEL_PT_PSB) {
 		*err = intel_pt_scan_for_psb(decoder);
@@ -2678,6 +2697,7 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		return HOP_IGNORE;
 
 	case INTEL_PT_TIP_PGD:
+		decoder->pge = false;
 		if (!decoder->packet.count) {
 			intel_pt_set_nr(decoder);
 			return HOP_IGNORE;
@@ -2705,18 +2725,21 @@ static int intel_pt_hop_trace(struct intel_pt_decoder *decoder, bool *no_tip, in
 		if (!decoder->packet.count)
 			return HOP_IGNORE;
 		intel_pt_set_ip(decoder);
-		if (intel_pt_fup_event(decoder))
-			return HOP_RETURN;
-		if (!decoder->branch_enable)
+		if (decoder->set_fup_mwait || decoder->set_fup_pwre)
+			*no_tip = true;
+		if (!decoder->branch_enable || !decoder->pge)
 			*no_tip = true;
 		if (*no_tip) {
 			decoder->state.type = INTEL_PT_INSTRUCTION;
 			decoder->state.from_ip = decoder->ip;
 			decoder->state.to_ip = 0;
+			intel_pt_fup_event(decoder);
 			return HOP_RETURN;
 		}
+		intel_pt_fup_event(decoder);
+		decoder->state.type |= INTEL_PT_INSTRUCTION | INTEL_PT_BRANCH;
 		*err = intel_pt_walk_fup_tip(decoder);
-		if (!*err)
+		if (!*err && decoder->state.to_ip)
 			decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 		return HOP_RETURN;
 
@@ -2897,7 +2920,7 @@ static bool intel_pt_psb_with_fup(struct intel_pt_decoder *decoder, int *err)
 {
 	struct intel_pt_psb_info data = { .fup = false };
 
-	if (!decoder->branch_enable || !decoder->pge)
+	if (!decoder->branch_enable)
 		return false;
 
 	intel_pt_pkt_lookahead(decoder, intel_pt_psb_lookahead_cb, &data);
@@ -2924,6 +2947,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 		if (err)
 			return err;
 next:
+		err = 0;
 		if (decoder->cyc_threshold) {
 			if (decoder->sample_cyc && last_packet_type != INTEL_PT_CYC)
 				decoder->sample_cyc = false;
@@ -2962,6 +2986,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 
 		case INTEL_PT_TIP_PGE: {
 			decoder->pge = true;
+			decoder->overflow = false;
 			intel_pt_mtc_cyc_cnt_pge(decoder);
 			intel_pt_set_nr(decoder);
 			if (decoder->packet.count == 0) {
@@ -2999,7 +3024,7 @@ static int intel_pt_walk_trace(struct intel_pt_decoder *decoder)
 				break;
 			}
 			intel_pt_set_last_ip(decoder);
-			if (!decoder->branch_enable) {
+			if (!decoder->branch_enable || !decoder->pge) {
 				decoder->ip = decoder->last_ip;
 				if (intel_pt_fup_event(decoder))
 					return 0;
@@ -3467,10 +3492,10 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 	decoder->set_fup_pwre = false;
 	decoder->set_fup_exstop = false;
 	decoder->set_fup_bep = false;
+	decoder->overflow = 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;
 	}
@@ -3485,7 +3510,6 @@ static int intel_pt_sync_ip(struct intel_pt_decoder *decoder)
 		decoder->pkt_state = INTEL_PT_STATE_RESAMPLE;
 	else
 		decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
-	decoder->overflow = false;
 
 	decoder->state.from_ip = 0;
 	decoder->state.to_ip = decoder->ip;
@@ -3607,7 +3631,7 @@ static int intel_pt_sync(struct intel_pt_decoder *decoder)
 	}
 
 	decoder->have_last_ip = true;
-	decoder->pkt_state = INTEL_PT_STATE_NO_IP;
+	decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
 
 	err = intel_pt_walk_psb(decoder);
 	if (err)
@@ -3704,7 +3728,8 @@ 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;
+		if (err != -EOVERFLOW)
+			decoder->state.from_ip = decoder->ip;
 		intel_pt_update_sample_time(decoder);
 		decoder->sample_tot_cyc_cnt = decoder->tot_cyc_cnt;
 		intel_pt_set_nr(decoder);

tools/perf/util/intel-pt.c

@@ -2565,6 +2565,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
+			ptq->timestamp = state->est_timestamp;
 			if (pt->synth_opts.errors) {
 				err = intel_ptq_synth_error(ptq, state);
 				if (err)

tools/perf/util/perf_regs.c

@@ -25,6 +25,9 @@ int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 	int i, idx = 0;
 	u64 mask = regs->mask;
 
+	if ((u64)id >= PERF_SAMPLE_REGS_CACHE_SIZE)
+		return -EINVAL;
+
 	if (regs->cache_mask & (1ULL << id))
 		goto out;
 

tools/perf/util/python.c

@@ -461,7 +461,7 @@ get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 		struct tep_event *tp_format;
 
 		tp_format = trace_event__tp_format_id(evsel->core.attr.config);
-		if (!tp_format)
+		if (IS_ERR_OR_NULL(tp_format))
 			return NULL;
 
 		evsel->tp_format = tp_format;