perf tools: Record ARM64 LR register automatically

On ARM64, automatically record the link register if the frame pointer
mode is on. It will be used to do a dwarf unwind to find the caller of
the leaf frame if the frame pointer was omitted.
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/20211217154521.80603-2-german.gomez@arm.comSigned-off-by: German Gomez <german.gomez@arm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/arch/arm64/util/machine.c

@@ -5,6 +5,8 @@
 #include <string.h>
 #include "debug.h"
 #include "symbol.h"
+#include "callchain.h"
+#include "record.h"
 
 /* On arm64, kernel text segment starts at high memory address,
  * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
@@ -26,3 +28,8 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
 		p->end = c->start;
 	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
 }
+
+void arch__add_leaf_frame_record_opts(struct record_opts *opts)
+{
+	opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
+}

tools/perf/builtin-record.c

@@ -2267,6 +2267,10 @@ static int record__parse_mmap_pages(const struct option *opt,
 	return ret;
 }
 
+void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
+{
+}
+
 static int parse_control_option(const struct option *opt,
 				const char *str,
 				int unset __maybe_unused)
@@ -2898,6 +2902,10 @@ int cmd_record(int argc, const char **argv)
 	}
 
 	rec->opts.target.hybrid = perf_pmu__has_hybrid();
+
+	if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP)
+		arch__add_leaf_frame_record_opts(&rec->opts);
+
 	err = -ENOMEM;
 	if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);

tools/perf/util/callchain.h

@@ -280,6 +280,8 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 }
 #endif
 
+void arch__add_leaf_frame_record_opts(struct record_opts *opts);
+
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
 char *callchain_node__scnprintf_value(struct callchain_node *node,