perf c2c: Add option to enable the LBR stitching approach

With the LBR stitching approach, the reconstructed LBR call stack can
break the HW limitation. However, it may reconstruct invalid call stacks
in some cases, e.g. exception handing such as setjmp/longjmp.  Also, it
may impact the processing time especially when the number of samples
with stitched LBRs are huge.

Add an option to enable the approach.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200319202517.23423-17-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index e6150f2..2133eb3 100644 (file)
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -111,6 +111,17 @@ REPORT OPTIONS
 --display::
        Switch to HITM type (rmt, lcl) to display and sort on. Total HITMs as default.
 
+--stitch-lbr::
+       Show callgraph with stitched LBRs, which may have more complete
+       callgraph. The perf.data file must have been obtained using
+       perf c2c record --call-graph lbr.
+       Disabled by default. In common cases with call stack overflows,
+       it can recreate better call stacks than the default lbr call stack
+       output. But this approach is not full proof. There can be cases
+       where it creates incorrect call stacks from incorrect matches.
+       The known limitations include exception handing such as
+       setjmp/longjmp will have calls/returns not match.
+
 C2C RECORD
 ----------
 The perf c2c record command setup options related to HITM cacheline analysis

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 246ac0b..0d544c4 100644 (file)
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -95,6 +95,7 @@ struct perf_c2c {
        bool                     use_stdio;
        bool                     stats_only;
        bool                     symbol_full;
+       bool                     stitch_lbr;
 
        /* HITM shared clines stats */
        struct c2c_stats        hitm_stats;
@@ -273,6 +274,9 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
                return -1;
        }
 
+       if (c2c.stitch_lbr)
+               al.thread->lbr_stitch_enable = true;
+
        ret = sample__resolve_callchain(sample, &callchain_cursor, NULL,
                                        evsel, &al, sysctl_perf_event_max_stack);
        if (ret)
@@ -2601,6 +2605,12 @@ static int setup_callchain(struct evlist *evlist)
                }
        }
 
+       if (c2c.stitch_lbr && (mode != CALLCHAIN_LBR)) {
+               ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
+                           "Please apply --call-graph lbr when recording.\n");
+               c2c.stitch_lbr = false;
+       }
+
        callchain_param.record_mode = mode;
        callchain_param.min_percent = 0;
        return 0;
@@ -2752,6 +2762,8 @@ static int perf_c2c__report(int argc, const char **argv)
        OPT_STRING('c', "coalesce", &coalesce, "coalesce fields",
                   "coalesce fields: pid,tid,iaddr,dso"),
        OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
+       OPT_BOOLEAN(0, "stitch-lbr", &c2c.stitch_lbr,
+                   "Enable LBR callgraph stitching approach"),
        OPT_PARENT(c2c_options),
        OPT_END()
        };