4 files changed, 46 insertions, 1 deletions

diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 5950b5a24efd..8a6479c0eac9 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -28,3 +28,7 @@ To change sampling frequency to 100 Hz: perf record -F 100
 See assembly instructions with percentage: perf annotate <symbol>
 If you prefer Intel style assembly, try: perf annotate -M intel
 For hierarchical output, try: perf report --hierarchy
+Order by the overhead of source file name and line number: perf report -s srcline
+System-wide collection from all CPUs: perf record -a
+Show current config key-value pairs: perf config --list
+Show user configuration overrides: perf config --user --list
diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c
index ed9d5d15d5b6..1030a6e504bb 100644
--- a/tools/perf/arch/powerpc/util/sym-handling.c
+++ b/tools/perf/arch/powerpc/util/sym-handling.c
@@ -82,7 +82,8 @@ void arch__fix_tev_from_maps(struct perf_probe_event *pev,
          *
          * In addition, we shouldn't specify an offset for kretprobes.
          */
-        if (pev->point.offset || pev->point.retprobe || !map || !sym)
+        if (pev->point.offset || (!pev->uprobes && pev->point.retprobe) ||
+            !map || !sym)
                 return;
 
         lep_offset = PPC64_LOCAL_ENTRY_OFFSET(sym->arch_sym);
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 79c2133bc534..41611d7f9873 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -312,6 +312,8 @@ static struct fixed {
         const char *event;
 } fixed[] = {
         { "inst_retired.any", "event=0xc0" },
+        { "inst_retired.any_p", "event=0xc0" },
+        { "cpu_clk_unhalted.ref", "event=0x0,umask=0x03" },
         { "cpu_clk_unhalted.thread", "event=0x3c" },
         { "cpu_clk_unhalted.thread_any", "event=0x3c,any=1" },
         { NULL, NULL},
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 7591a0c37473..16c06d3ae577 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -90,6 +90,7 @@ struct intel_pt_decoder {
         bool pge;
         bool have_tma;
         bool have_cyc;
+        bool fixup_last_mtc;
         uint64_t pos;
         uint64_t last_ip;
         uint64_t ip;
@@ -586,10 +587,31 @@ struct intel_pt_calc_cyc_to_tsc_info {
         uint64_t        tsc_timestamp;
         uint64_t        timestamp;
         bool            have_tma;
+        bool            fixup_last_mtc;
         bool            from_mtc;
         double          cbr_cyc_to_tsc;
 };
 
+/*
+ * MTC provides a 8-bit slice of CTC but the TMA packet only provides the lower
+ * 16 bits of CTC. If mtc_shift > 8 then some of the MTC bits are not in the CTC
+ * provided by the TMA packet. Fix-up the last_mtc calculated from the TMA
+ * packet by copying the missing bits from the current MTC assuming the least
+ * difference between the two, and that the current MTC comes after last_mtc.
+ */
+static void intel_pt_fixup_last_mtc(uint32_t mtc, int mtc_shift,
+                                    uint32_t *last_mtc)
+{
+        uint32_t first_missing_bit = 1U << (16 - mtc_shift);
+        uint32_t mask = ~(first_missing_bit - 1);
+
+        *last_mtc |= mtc & mask;
+        if (*last_mtc >= mtc) {
+                *last_mtc -= first_missing_bit;
+                *last_mtc &= 0xff;
+        }
+}
+
 static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 {
         struct intel_pt_decoder *decoder = pkt_info->decoder;
@@ -619,6 +641,11 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
                         return 0;
 
                 mtc = pkt_info->packet.payload;
+                if (decoder->mtc_shift > 8 && data->fixup_last_mtc) {
+                        data->fixup_last_mtc = false;
+                        intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+                                                &data->last_mtc);
+                }
                 if (mtc > data->last_mtc)
                         mtc_delta = mtc - data->last_mtc;
                 else
@@ -687,6 +714,7 @@ static int intel_pt_calc_cyc_cb(struct intel_pt_pkt_info *pkt_info)
 
                 data->ctc_delta = 0;
                 data->have_tma = true;
+                data->fixup_last_mtc = true;
 
                 return 0;
 
@@ -753,6 +781,7 @@ static void intel_pt_calc_cyc_to_tsc(struct intel_pt_decoder *decoder,
                 .tsc_timestamp  = decoder->tsc_timestamp,
                 .timestamp      = decoder->timestamp,
                 .have_tma       = decoder->have_tma,
+                .fixup_last_mtc = decoder->fixup_last_mtc,
                 .from_mtc       = from_mtc,
                 .cbr_cyc_to_tsc = 0,
         };
@@ -1271,6 +1300,7 @@ static void intel_pt_calc_tma(struct intel_pt_decoder *decoder)
         }
         decoder->ctc_delta = 0;
         decoder->have_tma = true;
+        decoder->fixup_last_mtc = true;
         intel_pt_log("CTC timestamp " x64_fmt " last MTC %#x  CTC rem %#x\n",
                      decoder->ctc_timestamp, decoder->last_mtc, ctc_rem);
 }
@@ -1285,6 +1315,12 @@ static void intel_pt_calc_mtc_timestamp(struct intel_pt_decoder *decoder)
 
         mtc = decoder->packet.payload;
 
+        if (decoder->mtc_shift > 8 && decoder->fixup_last_mtc) {
+                decoder->fixup_last_mtc = false;
+                intel_pt_fixup_last_mtc(mtc, decoder->mtc_shift,
+                                        &decoder->last_mtc);
+        }
+
         if (mtc > decoder->last_mtc)
                 mtc_delta = mtc - decoder->last_mtc;
         else
@@ -1353,6 +1389,8 @@ static void intel_pt_calc_cyc_timestamp(struct intel_pt_decoder *decoder)
                              timestamp, decoder->timestamp);
         else
                 decoder->timestamp = timestamp;
+
+        decoder->timestamp_insn_cnt = 0;
 }
 
 /* Walk PSB+ packets when already in sync. */