perf top: 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.
The option must be used with --call-graph lbr.

Signed-off-by: Kan Liang <[email protected]>
Reviewed-by: Andi Kleen <[email protected]>
Acked-by: Jiri Olsa <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Adrian Hunter <[email protected]>
Cc: Alexey Budankov <[email protected]>
Cc: Mathieu Poirier <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Namhyung Kim <[email protected]>
Cc: Pavel Gerasimov <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ravi Bangoria <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Vitaly Slobodskoy <[email protected]>
Link: http://lore.kernel.org/lkml/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: Kan Liang

tools/perf/Documentation/perf-top.txt

@@ -319,6 +319,15 @@ Default is to monitor all CPUS.
 	go straight to the histogram browser, just like 'perf top' with no events
 	explicitely specified does.
 
+--stitch-lbr::
+	Show callgraph with stitched LBRs, which may have more complete
+	callgraph. The option must be used with --call-graph lbr recording.
+	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.
 
 INTERACTIVE PROMPTING KEYS
 --------------------------

tools/perf/builtin-top.c

@@ -33,6 +33,7 @@
 #include "util/map.h"
 #include "util/mmap.h"
 #include "util/session.h"
+#include "util/thread.h"
 #include "util/symbol.h"
 #include "util/synthetic-events.h"
 #include "util/top.h"
@@ -775,6 +776,9 @@ static void perf_event__process_sample(struct perf_tool *tool,
 	if (machine__resolve(machine, &al, sample) < 0)
 		return;
 
+	if (top->stitch_lbr)
+		al.thread->lbr_stitch_enable = true;
+
 	if (!machine->kptr_restrict_warned &&
 	    symbol_conf.kptr_restrict &&
 	    al.cpumode == PERF_RECORD_MISC_KERNEL) {
@@ -1571,6 +1575,8 @@ int cmd_top(int argc, const char **argv)
 		    "Sort the output by the event at the index n in group. "
 		    "If n is invalid, sort by the first event. "
 		    "WARNING: should be used on grouped events."),
+	OPT_BOOLEAN(0, "stitch-lbr", &top.stitch_lbr,
+		    "Enable LBR callgraph stitching approach"),
 	OPTS_EVSWITCH(&top.evswitch),
 	OPT_END()
 	};
@@ -1640,6 +1646,11 @@ int cmd_top(int argc, const char **argv)
 		}
 	}
 
+	if (top.stitch_lbr && !(callchain_param.record_mode == CALLCHAIN_LBR)) {
+		pr_err("Error: --stitch-lbr must be used with --call-graph lbr\n");
+		goto out_delete_evlist;
+	}
+
 	if (opts->branch_stack && callchain_param.enabled)
 		symbol_conf.show_branchflag_count = true;
 

tools/perf/util/top.h

@@ -36,6 +36,7 @@ struct perf_top {
 	bool		   use_tui, use_stdio;
 	bool		   vmlinux_warned;
 	bool		   dump_symtab;
+	bool		   stitch_lbr;
 	struct hist_entry  *sym_filter_entry;
 	struct evsel 	   *sym_evsel;
 	struct perf_session *session;