summaryrefslogtreecommitdiff
path: root/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/intel-pt-decoder/intel-pt-decoder.c')
-rw-r--r--tools/perf/util/intel-pt-decoder/intel-pt-decoder.c88
1 files changed, 66 insertions, 22 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 d404bed7003a..4357141c7c92 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"
@@ -57,6 +58,7 @@ enum intel_pt_pkt_state {
INTEL_PT_STATE_NO_IP,
INTEL_PT_STATE_ERR_RESYNC,
INTEL_PT_STATE_IN_SYNC,
+ INTEL_PT_STATE_TNT_CONT,
INTEL_PT_STATE_TNT,
INTEL_PT_STATE_TIP,
INTEL_PT_STATE_TIP_PGD,
@@ -71,8 +73,9 @@ static inline bool intel_pt_sample_time(enum intel_pt_pkt_state pkt_state)
case INTEL_PT_STATE_NO_IP:
case INTEL_PT_STATE_ERR_RESYNC:
case INTEL_PT_STATE_IN_SYNC:
- case INTEL_PT_STATE_TNT:
+ case INTEL_PT_STATE_TNT_CONT:
return true;
+ case INTEL_PT_STATE_TNT:
case INTEL_PT_STATE_TIP:
case INTEL_PT_STATE_TIP_PGD:
case INTEL_PT_STATE_FUP:
@@ -250,19 +253,15 @@ 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);
@@ -891,16 +890,20 @@ static uint64_t intel_pt_next_period(struct intel_pt_decoder *decoder)
timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
masked_timestamp = timestamp & decoder->period_mask;
if (decoder->continuous_period) {
- if (masked_timestamp != decoder->last_masked_timestamp)
+ if (masked_timestamp > decoder->last_masked_timestamp)
return 1;
} else {
timestamp += 1;
masked_timestamp = timestamp & decoder->period_mask;
- if (masked_timestamp != decoder->last_masked_timestamp) {
+ if (masked_timestamp > decoder->last_masked_timestamp) {
decoder->last_masked_timestamp = masked_timestamp;
decoder->continuous_period = true;
}
}
+
+ if (masked_timestamp < decoder->last_masked_timestamp)
+ return decoder->period_ticks;
+
return decoder->period_ticks - (timestamp - masked_timestamp);
}
@@ -929,7 +932,10 @@ static void intel_pt_sample_insn(struct intel_pt_decoder *decoder)
case INTEL_PT_PERIOD_TICKS:
timestamp = decoder->timestamp + decoder->timestamp_insn_cnt;
masked_timestamp = timestamp & decoder->period_mask;
- decoder->last_masked_timestamp = masked_timestamp;
+ if (masked_timestamp > decoder->last_masked_timestamp)
+ decoder->last_masked_timestamp = masked_timestamp;
+ else
+ decoder->last_masked_timestamp += decoder->period_ticks;
break;
case INTEL_PT_PERIOD_NONE:
case INTEL_PT_PERIOD_MTC:
@@ -1252,7 +1258,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
return -ENOENT;
}
decoder->tnt.count -= 1;
- if (!decoder->tnt.count)
+ if (decoder->tnt.count)
+ decoder->pkt_state = INTEL_PT_STATE_TNT_CONT;
+ else
decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
decoder->tnt.payload <<= 1;
decoder->state.from_ip = decoder->ip;
@@ -1283,7 +1291,9 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
if (intel_pt_insn.branch == INTEL_PT_BR_CONDITIONAL) {
decoder->tnt.count -= 1;
- if (!decoder->tnt.count)
+ if (decoder->tnt.count)
+ decoder->pkt_state = INTEL_PT_STATE_TNT_CONT;
+ else
decoder->pkt_state = INTEL_PT_STATE_IN_SYNC;
if (decoder->tnt.payload & BIT63) {
decoder->tnt.payload <<= 1;
@@ -1303,8 +1313,11 @@ static int intel_pt_walk_tnt(struct intel_pt_decoder *decoder)
return 0;
}
decoder->ip += intel_pt_insn.length;
- if (!decoder->tnt.count)
+ if (!decoder->tnt.count) {
+ decoder->sample_timestamp = decoder->timestamp;
+ decoder->sample_insn_cnt = decoder->timestamp_insn_cnt;
return -EAGAIN;
+ }
decoder->tnt.payload <<= 1;
continue;
}
@@ -1389,7 +1402,6 @@ 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;
@@ -2353,6 +2365,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
err = intel_pt_walk_trace(decoder);
break;
case INTEL_PT_STATE_TNT:
+ case INTEL_PT_STATE_TNT_CONT:
err = intel_pt_walk_tnt(decoder);
if (err == -EAGAIN)
err = intel_pt_walk_trace(decoder);
@@ -2559,6 +2572,34 @@ 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.
@@ -2609,8 +2650,11 @@ 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 */
@@ -2673,7 +2717,7 @@ 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' */
generated by cgit v1.2.3 (git 2.0.4) at 2024-05-29 14:32:28 +0000