[PATCH v4 6/6] perf tools: determine if LR is the return address

[German Gomez <german.gomez@arm.com>]

From: Alexandre Truong <alexandre.truong@arm.com>

On arm64 and frame pointer mode (e.g: perf record --callgraph fp),
use dwarf unwind info to check if the link register is the return
address in order to inject it to the frame pointer stack.

Write the following application:

	int a = 10;

	void f2(void)
	{
		for (int i = 0; i < 1000000; i++)
			a *= a;
	}

	void f1()
	{
		for (int i = 0; i < 10; i++)
			f2();
	}

	int main(void)
	{
		f1();
		return 0;
	}

with the following compilation flags:
        gcc -fno-omit-frame-pointer -fno-inline -O2

The compiler omits the frame pointer for f2 on arm. This is a problem
with any leaf call, for example an application with many different
calls to malloc() would always omit the calling frame, even if it
can be determined.

	./perf record --call-graph fp ./a.out
	./perf report

currently gives the following stack:

0xffffea52f361
_start
__libc_start_main
main
f2

After this change, perf report correctly shows f1() calling f2(),
even though it was missing from the frame pointer unwind:

	./perf report

0xffffea52f361
_start
__libc_start_main
main
f1
f2

Signed-off-by: Alexandre Truong <alexandre.truong@arm.com>
Signed-off-by: German Gomez <german.gomez@arm.com>
---
 tools/perf/util/Build                         |  1 +
 .../util/arm64-frame-pointer-unwind-support.c | 63 +++++++++++++++++++
 .../util/arm64-frame-pointer-unwind-support.h | 10 +++
 tools/perf/util/machine.c                     | 19 ++++--
 tools/perf/util/machine.h                     |  1 +
 5 files changed, 89 insertions(+), 5 deletions(-)
 create mode 100644 tools/perf/util/arm64-frame-pointer-unwind-support.c
 create mode 100644 tools/perf/util/arm64-frame-pointer-unwind-support.h

diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2e5bfbb69960..03d4c647bd86 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,4 @@
+perf-y += arm64-frame-pointer-unwind-support.o
 perf-y += annotate.o
 perf-y += block-info.o
 perf-y += block-range.o
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
new file mode 100644
index 000000000000..4f5ecf51ed38
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arm64-frame-pointer-unwind-support.h"
+#include "callchain.h"
+#include "event.h"
+#include "perf_regs.h" // SMPL_REG_MASK
+#include "unwind.h"
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+struct entries {
+	u64 stack[2];
+	size_t length;
+};
+
+static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
+{
+	return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs
+		&& sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
+}
+
+static int add_entry(struct unwind_entry *entry, void *arg)
+{
+	struct entries *entries = arg;
+
+	entries->stack[entries->length++] = entry->ip;
+	return 0;
+}
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx)
+{
+	int ret;
+	struct entries entries = {};
+	struct regs_dump old_regs = sample->user_regs;
+
+	if (!get_leaf_frame_caller_enabled(sample))
+		return 0;
+
+	/*
+	 * If PC and SP are not recorded, get the value of PC from the stack
+	 * and set its mask. SP is not used when doing the unwinding but it
+	 * still needs to be set to prevent failures.
+	 */
+
+	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
+		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
+		sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
+	}
+
+	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
+		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
+		sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
+	}
+
+	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+	sample->user_regs = old_regs;
+
+	if (ret || entries.length != 2)
+		return ret;
+
+	return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1];
+}
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h
new file mode 100644
index 000000000000..32af9ce94398
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+
+#include "event.h"
+#include "thread.h"
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx);
+
+#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 3eddad009f78..a00fd6796b35 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -34,6 +34,7 @@
 #include "bpf-event.h"
 #include <internal/lib.h> // page_size
 #include "cgroup.h"
+#include "arm64-frame-pointer-unwind-support.h"
 
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
@@ -2710,10 +2711,13 @@ 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)
+static u64 get_leaf_frame_caller(struct perf_sample *sample,
+		struct thread *thread, int usr_idx)
 {
-	return 0;
+	if (machine__normalize_is(thread->maps->machine, "arm64"))
+		return get_leaf_frame_caller_aarch64(sample, thread, usr_idx);
+	else
+		return 0;
 }
 
 static int thread__resolve_callchain_sample(struct thread *thread,
@@ -3114,14 +3118,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 }
 
 /*
- * Compares the raw arch string. N.B. see instead perf_env__arch() if a
- * normalized arch is needed.
+ * Compares the raw arch string. N.B. see instead perf_env__arch() or
+ * machine__normalize_is() if a normalized arch is needed.
  */
 bool machine__is(struct machine *machine, const char *arch)
 {
 	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
 }
 
+bool machine__normalize_is(struct machine *machine, const char *arch)
+{
+	return machine && !strcmp(perf_env__arch(machine->env), arch);
+}
+
 int machine__nr_cpus_avail(struct machine *machine)
 {
 	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a143087eeb47..665535153411 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -208,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 bool machine__is(struct machine *machine, const char *arch);
+bool machine__normalize_is(struct machine *machine, const char *arch);
 int machine__nr_cpus_avail(struct machine *machine);
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
-- 
2.25.1