perf machine: Add a mechanism to inject stack frames

Add a mechanism for platforms to inject stack frames for the leaf
frame caller if there is enough information to determine a frame
is missing from dwarf or other post processing mechanisms.

Reviewed-by: James Clark <james.clark@arm.com>
Signed-off-by: Alexandre Truong <alexandre.truong@arm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20211217154521.80603-3-german.gomez@arm.com
Signed-off-by: German Gomez <german.gomez@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb8496d..3eddad0 100644 (file)
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2710,6 +2710,12 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
        return err;
 }
 
+static u64 get_leaf_frame_caller(struct perf_sample *sample __maybe_unused,
+               struct thread *thread __maybe_unused, int usr_idx __maybe_unused)
+{
+       return 0;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
                                            struct callchain_cursor *cursor,
                                            struct evsel *evsel,
@@ -2723,9 +2729,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
        struct ip_callchain *chain = sample->callchain;
        int chain_nr = 0;
        u8 cpumode = PERF_RECORD_MISC_USER;
-       int i, j, err, nr_entries;
+       int i, j, err, nr_entries, usr_idx;
        int skip_idx = -1;
        int first_call = 0;
+       u64 leaf_frame_caller;
 
        if (chain)
                chain_nr = chain->nr;
@@ -2850,6 +2857,34 @@ check_calls:
                        continue;
                }
 
+               /*
+                * PERF_CONTEXT_USER allows us to locate where the user stack ends.
+                * Depending on callchain_param.order and the position of PERF_CONTEXT_USER,
+                * the index will be different in order to add the missing frame
+                * at the right place.
+                */
+
+               usr_idx = callchain_param.order == ORDER_CALLEE ? j-2 : j-1;
+
+               if (usr_idx >= 0 && chain->ips[usr_idx] == PERF_CONTEXT_USER) {
+
+                       leaf_frame_caller = get_leaf_frame_caller(sample, thread, usr_idx);
+
+                       /*
+                        * check if leaf_frame_Caller != ip to not add the same
+                        * value twice.
+                        */
+
+                       if (leaf_frame_caller && leaf_frame_caller != ip) {
+
+                               err = add_callchain_ip(thread, cursor, parent,
+                                              root_al, &cpumode, leaf_frame_caller,
+                                              false, NULL, NULL, 0);
+                               if (err)
+                                       return (err < 0) ? err : 0;
+                       }
+               }
+
                err = add_callchain_ip(thread, cursor, parent,
                                       root_al, &cpumode, ip,
                                       false, NULL, NULL, 0);