perf intel-pt/bts: Calculate cpumode for synthesized samples

In the absence of a fallback, samples must provide a correct cpumode for
the 'ip'. Do that now there is no fallback.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: stable@vger.kernel.org # 4.19
Link: http://lkml.kernel.org/r/20181031091043.23465-6-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 25 insertions, 14 deletions

diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 3b3a3d55dca1..7b27d77306c2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -269,6 +269,13 @@ static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
         return 0;
 }
 
+static inline u8 intel_bts_cpumode(struct intel_bts *bts, uint64_t ip)
+{
+        return machine__kernel_ip(bts->machine, ip) ?
+               PERF_RECORD_MISC_KERNEL :
+               PERF_RECORD_MISC_USER;
+}
+
 static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
                                          struct branch *branch)
 {
@@ -281,12 +288,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
             bts->num_events++ <= bts->synth_opts.initial_skip)
                 return 0;
 
-        event.sample.header.type = PERF_RECORD_SAMPLE;
-        event.sample.header.misc = PERF_RECORD_MISC_USER;
-        event.sample.header.size = sizeof(struct perf_event_header);
-
-        sample.cpumode = PERF_RECORD_MISC_USER;
         sample.ip = le64_to_cpu(branch->from);
+        sample.cpumode = intel_bts_cpumode(bts, sample.ip);
         sample.pid = btsq->pid;
         sample.tid = btsq->tid;
         sample.addr = le64_to_cpu(branch->to);
@@ -298,6 +301,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
         sample.insn_len = btsq->intel_pt_insn.length;
         memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
+        event.sample.header.type = PERF_RECORD_SAMPLE;
+        event.sample.header.misc = sample.cpumode;
+        event.sample.header.size = sizeof(struct perf_event_header);
+
         if (bts->synth_opts.inject) {
                 event.sample.header.size = bts->branches_event_size;
                 ret = perf_event__synthesize_sample(&event,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 60732213d16a..86cc9a64e982 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -407,6 +407,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
         return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
 }
 
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+        return ip >= pt->kernel_start ?
+               PERF_RECORD_MISC_KERNEL :
+               PERF_RECORD_MISC_USER;
+}
+
 static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
                                    uint64_t *insn_cnt_ptr, uint64_t *ip,
                                    uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +436,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
         if (to_ip && *ip == to_ip)
                 goto out_no_cache;
 
-        if (*ip >= ptq->pt->kernel_start)
-                cpumode = PERF_RECORD_MISC_KERNEL;
-        else
-                cpumode = PERF_RECORD_MISC_USER;
+        cpumode = intel_pt_cpumode(ptq->pt, *ip);
 
         thread = ptq->thread;
         if (!thread) {
@@ -1059,15 +1063,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
                                    union perf_event *event,
                                    struct perf_sample *sample)
 {
-        event->sample.header.type = PERF_RECORD_SAMPLE;
-        event->sample.header.misc = PERF_RECORD_MISC_USER;
-        event->sample.header.size = sizeof(struct perf_event_header);
-
         if (!pt->timeless_decoding)
                 sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
-        sample->cpumode = PERF_RECORD_MISC_USER;
         sample->ip = ptq->state->from_ip;
+        sample->cpumode = intel_pt_cpumode(pt, sample->ip);
         sample->pid = ptq->pid;
         sample->tid = ptq->tid;
         sample->addr = ptq->state->to_ip;
@@ -1076,6 +1076,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
         sample->flags = ptq->flags;
         sample->insn_len = ptq->insn_len;
         memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+        event->sample.header.type = PERF_RECORD_SAMPLE;
+        event->sample.header.misc = sample->cpumode;
+        event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,