Received: by 2002:a05:6a10:8c0a:0:0:0:0 with SMTP id go10csp1406988pxb; Thu, 4 Mar 2021 10:28:13 -0800 (PST) X-Google-Smtp-Source: ABdhPJz/5w6v5Qq0B9ZEpSfyQJ9B3SNE1tGUUQ0GL6QPzecwkkMZnOBuGlJCHV7uFaDLMOTBB57j X-Received: by 2002:a17:906:68c5:: with SMTP id y5mr5782099ejr.371.1614882493628; Thu, 04 Mar 2021 10:28:13 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1614882493; cv=none; d=google.com; s=arc-20160816; b=vLbBeu2AcSAcIxgQzdGUuGC9VMyl/0scb6Qo7tDAy2hvq5+R5WPMFtGZhXxRyuirzx 02oVo7OalYc1pgmag3KhbgU0kVOCN1zbY9D7ypPusAU00UI82JZluWsW7eclBDkBERPv vAJzK7wxz3lYHZV96hsuGxAqAK3CRhOrGLOwrwskbeSsMk3wNNLzGM5Z1L339aLvH9Qm I9RFhyEHKCDGOvuHn7uHaCfYXzID6f/XEtTUleHJN3C8WXFSaz/uzaE+yFgpHKSNZuaZ o9Twee0a2TdscfoppnqUd+F7EDgXqRggRuwdlaTf44emR4+lnCQc3X+MtuBdruIcDt2q KpUA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from; bh=BOmdCdNklzVLwe30IJl3q+Q2xz2eqOSZYXBWsuS824o=; b=jSqkLAFegkdskqzV1fc4d3Xc91GQZeyWtXFtuZ7P5GsnKr6Bo9gAlWZdSPLJDKl2Gb Oq2qOqT7vF4AyjjXJunoAF1VcBLbALnmHO1/fv8SnQlHyYWSV2H7zr+usEEYG4mb9fPj h/UjqpAPtrWdwzZzTo1lRfmLRxO16Wog9EEb+MdaEANmVqK8rSas5tX4qvQ9dctqEsmq 9G7MnDhtBww6zb4FH4ybjgSyn+k5jvPSG6StowTp3gEUR8nmoMtvn6FT4XswxdGlXyqS Ospan/3g8BY61PF3zWZ6b3CWPWq2vJOUY3K/MFItqbAaMQLgGNQevwUxN1eEUn+ctnG7 Dajg== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=arm.com Return-Path: Received: from vger.kernel.org (vger.kernel.org. [23.128.96.18]) by mx.google.com with ESMTP id j22si14496691ejb.269.2021.03.04.10.27.50; Thu, 04 Mar 2021 10:28:13 -0800 (PST) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18; Authentication-Results: mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=arm.com Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S238172AbhCDQee (ORCPT + 99 others); Thu, 4 Mar 2021 11:34:34 -0500 Received: from foss.arm.com ([217.140.110.172]:41126 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S238073AbhCDQeO (ORCPT ); Thu, 4 Mar 2021 11:34:14 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 69E5511D4; Thu, 4 Mar 2021 08:33:28 -0800 (PST) Received: from e125528.arm.com (unknown [10.57.51.148]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 781C23F766; Thu, 4 Mar 2021 08:33:23 -0800 (PST) From: Alexandre Truong To: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org Cc: Alexandre Truong , John Garry , Will Deacon , Mathieu Poirier , Leo Yan , Peter Zijlstra , Ingo Molnar , Arnaldo Carvalho de Melo , Mark Rutland , Alexander Shishkin , Jiri Olsa , Namhyung Kim , Kemeng Shi , Ian Rogers , Andi Kleen , Kan Liang , Jin Yao , Adrian Hunter , Suzuki K Poulose , Al Grant , James Clark , Wilco Dijkstra Subject: [PATCH RESEND WITH CCs v3 4/4] perf tools: determine if LR is the return address Date: Thu, 4 Mar 2021 16:32:55 +0000 Message-Id: <20210304163255.10363-4-alexandre.truong@arm.com> X-Mailer: git-send-email 2.23.0 In-Reply-To: <20210304163255.10363-1-alexandre.truong@arm.com> References: <20210304163255.10363-1-alexandre.truong@arm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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 Cc: John Garry Cc: Will Deacon Cc: Mathieu Poirier Cc: Leo Yan Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: Kemeng Shi Cc: Ian Rogers Cc: Andi Kleen Cc: Kan Liang Cc: Jin Yao Cc: Adrian Hunter Cc: Suzuki K Poulose Cc: Al Grant Cc: James Clark Cc: Wilco Dijkstra --- tools/perf/util/Build | 1 + .../util/arm-frame-pointer-unwind-support.c | 44 +++++++++++++++++++ .../util/arm-frame-pointer-unwind-support.h | 7 +++ tools/perf/util/machine.c | 9 ++-- 4 files changed, 58 insertions(+), 3 deletions(-) create mode 100644 tools/perf/util/arm-frame-pointer-unwind-support.c create mode 100644 tools/perf/util/arm-frame-pointer-unwind-support.h diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 188521f34347..3b82cb992bce 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -1,3 +1,4 @@ +perf-y += arm-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/arm-frame-pointer-unwind-support.c b/tools/perf/util/arm-frame-pointer-unwind-support.c new file mode 100644 index 000000000000..964efd08e72e --- /dev/null +++ b/tools/perf/util/arm-frame-pointer-unwind-support.c @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "../arch/arm64/include/uapi/asm/perf_regs.h" +#include "arch/arm64/include/perf_regs.h" +#include "event.h" +#include "arm-frame-pointer-unwind-support.h" +#include "callchain.h" +#include "unwind.h" + +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 == PERF_REGS_MASK; +} + +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 ret; + + struct entries entries = {{0, 0}, 0}; + + if (!get_leaf_frame_caller_enabled(sample)) + return 0; + + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + + 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/arm-frame-pointer-unwind-support.h b/tools/perf/util/arm-frame-pointer-unwind-support.h new file mode 100644 index 000000000000..16dc03fa9abe --- /dev/null +++ b/tools/perf/util/arm-frame-pointer-unwind-support.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H +#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H + +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread); + +#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 7f03ffa016b0..dfb72dbc0e2d 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -34,6 +34,7 @@ #include "bpf-event.h" #include // page_size #include "cgroup.h" +#include "arm-frame-pointer-unwind-support.h" #include #include @@ -2671,10 +2672,12 @@ 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) +static u64 get_leaf_frame_caller(struct perf_sample *sample, struct thread *thread) { - return 0; + if (strncmp(thread->maps->machine->env->arch, "aarch64", 7) == 0) + return get_leaf_frame_caller_aarch64(sample, thread); + else + return 0; } static int thread__resolve_callchain_sample(struct thread *thread, -- 2.23.0