3 files changed, 52 insertions, 17 deletions

diff --git a/tools/perf/util/intel-pt-decoder/Build b/tools/perf/util/intel-pt-decoder/Build
index 1b704fbea9de..23bf788f84b9 100644
--- a/tools/perf/util/intel-pt-decoder/Build
+++ b/tools/perf/util/intel-pt-decoder/Build
@@ -1,4 +1,4 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
+perf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o intel-pt-log.o intel-pt-decoder.o
 
 inat_tables_script = util/intel-pt-decoder/gen-insn-attr-x86.awk
 inat_tables_maps = util/intel-pt-decoder/x86-opcode-map.txt
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 4503f3ca45ab..872fab163585 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -26,6 +26,7 @@
 
 #include "../cache.h"
 #include "../util.h"
+#include "../auxtrace.h"
 
 #include "intel-pt-insn-decoder.h"
 #include "intel-pt-pkt-decoder.h"
@@ -250,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
@@ -867,7 +864,7 @@ static int intel_pt_get_next_packet(struct intel_pt_decoder *decoder)
 
 		ret = intel_pt_get_packet(decoder->buf, decoder->len,
 					  &decoder->packet);
-		if (ret == INTEL_PT_NEED_MORE_BYTES &&
+		if (ret == INTEL_PT_NEED_MORE_BYTES && BITS_PER_LONG == 32 &&
 		    decoder->len < INTEL_PT_PKT_MAX_SZ && !decoder->next_buf) {
 			ret = intel_pt_get_split_packet(decoder);
 			if (ret < 0)
@@ -1394,7 +1391,6 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 {
 	intel_pt_log("ERROR: Buffer overflow\n");
 	intel_pt_clear_tx_flags(decoder);
-	decoder->cbr = 0;
 	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
@@ -2575,6 +2571,34 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 	}
 }
 
+#define MAX_PADDING (PERF_AUXTRACE_RECORD_ALIGNMENT - 1)
+
+/**
+ * adj_for_padding - adjust overlap to account for padding.
+ * @buf_b: second buffer
+ * @buf_a: first buffer
+ * @len_a: size of first buffer
+ *
+ * @buf_a might have up to 7 bytes of padding appended. Adjust the overlap
+ * accordingly.
+ *
+ * Return: A pointer into @buf_b from where non-overlapped data starts
+ */
+static unsigned char *adj_for_padding(unsigned char *buf_b,
+				      unsigned char *buf_a, size_t len_a)
+{
+	unsigned char *p = buf_b - MAX_PADDING;
+	unsigned char *q = buf_a + len_a - MAX_PADDING;
+	int i;
+
+	for (i = MAX_PADDING; i; i--, p++, q++) {
+		if (*p != *q)
+			break;
+	}
+
+	return p;
+}
+
 /**
  * intel_pt_find_overlap_tsc - determine start of non-overlapped trace data
  *                             using TSC.
@@ -2625,8 +2649,11 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 
 			/* Same TSC, so buffers are consecutive */
 			if (!cmp && rem_b >= rem_a) {
+				unsigned char *start;
+
 				*consecutive = true;
-				return buf_b + len_b - (rem_b - rem_a);
+				start = buf_b + len_b - (rem_b - rem_a);
+				return adj_for_padding(start, buf_a, len_a);
 			}
 			if (cmp < 0)
 				return buf_b; /* tsc_a < tsc_b => no overlap */
@@ -2689,7 +2716,7 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		found = memmem(buf_a, len_a, buf_b, len_a);
 		if (found) {
 			*consecutive = true;
-			return buf_b + len_a;
+			return adj_for_padding(buf_b + len_a, buf_a, len_a);
 		}
 
 		/* Try again at next PSB in buffer 'a' */
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 54818828023b..1c0e289f01e6 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -180,6 +180,14 @@ int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
 	return 0;
 }
 
+int arch_is_branch(const unsigned char *buf, size_t len, int x86_64)
+{
+	struct intel_pt_insn in;
+	if (intel_pt_get_insn(buf, len, x86_64, &in) < 0)
+		return -1;
+	return in.branch != INTEL_PT_BR_NO_BRANCH;
+}
+
 const char *dump_insn(struct perf_insn *x, uint64_t ip __maybe_unused,
 		      u8 *inbuf, int inlen, int *lenp)
 {