[PATCH 4.19 116/205] perf intel-pt: Insert callchain context into synthesized callchains

From: Greg Kroah-Hartman
Date: Mon Nov 19 2018 - 11:35:13 EST


4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Adrian Hunter <adrian.hunter@xxxxxxxxx>

commit 242483068b4b9ad02f1653819b6e683577681e0e upstream.

In the absence of a fallback, callchains must encode also the callchain
context. Do that now there is no fallback.

Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
Reviewed-by: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Leo Yan <leo.yan@xxxxxxxxxx>
Cc: Mathieu Poirier <mathieu.poirier@xxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx # 4.19
Link: http://lkml.kernel.org/r/100ea2ec-ed14-b56d-d810-e0a6d2f4b069@xxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
tools/perf/util/intel-pt.c | 6 +++--
tools/perf/util/thread-stack.c | 44 ++++++++++++++++++++++++++++++++---------
tools/perf/util/thread-stack.h | 2 -
3 files changed, 40 insertions(+), 12 deletions(-)

--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -763,7 +763,8 @@ static struct intel_pt_queue *intel_pt_a
if (pt->synth_opts.callchain) {
size_t sz = sizeof(struct ip_callchain);

- sz += pt->synth_opts.callchain_sz * sizeof(u64);
+ /* Add 1 to callchain_sz for callchain context */
+ sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
ptq->chain = zalloc(sz);
if (!ptq->chain)
goto out_free;
@@ -1159,7 +1160,8 @@ static void intel_pt_prep_sample(struct

if (pt->synth_opts.callchain) {
thread_stack__sample(ptq->thread, ptq->chain,
- pt->synth_opts.callchain_sz, sample->ip);
+ pt->synth_opts.callchain_sz + 1,
+ sample->ip, pt->kernel_start);
sample->callchain = ptq->chain;
}

--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -285,20 +285,46 @@ void thread_stack__free(struct thread *t
}
}

+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+ return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
- size_t sz, u64 ip)
+ size_t sz, u64 ip, u64 kernel_start)
{
- size_t i;
+ u64 context = callchain_context(ip, kernel_start);
+ u64 last_context;
+ size_t i, j;
+
+ if (sz < 2) {
+ chain->nr = 0;
+ return;
+ }

- if (!thread || !thread->ts)
- chain->nr = 1;
- else
- chain->nr = min(sz, thread->ts->cnt + 1);
+ chain->ips[0] = context;
+ chain->ips[1] = ip;

- chain->ips[0] = ip;
+ if (!thread || !thread->ts) {
+ chain->nr = 2;
+ return;
+ }
+
+ last_context = context;
+
+ for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+ ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+ context = callchain_context(ip, kernel_start);
+ if (context != last_context) {
+ if (i >= sz - 1)
+ break;
+ chain->ips[i++] = context;
+ last_context = context;
+ }
+ chain->ips[i] = ip;
+ }

- for (i = 1; i < chain->nr; i++)
- chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+ chain->nr = i;
}

struct call_return_processor *
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *t
u64 to_ip, u16 insn_len, u64 trace_nr);
void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
- size_t sz, u64 ip);
+ size_t sz, u64 ip, u64 kernel_start);
int thread_stack__flush(struct thread *thread);
void thread_stack__free(struct thread *thread);
size_t thread_stack__depth(struct thread *thread);