From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.3 required=3.0 tests=DKIM_INVALID,DKIM_SIGNED, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_PASS, USER_AGENT_MUTT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1B82CC4360F for ; Fri, 5 Apr 2019 07:55:34 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id D555821855 for ; Fri, 5 Apr 2019 07:55:33 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=infradead.org header.i=@infradead.org header.b="j3MErZPb" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730409AbfDEHz2 (ORCPT ); Fri, 5 Apr 2019 03:55:28 -0400 Received: from bombadil.infradead.org ([198.137.202.133]:38970 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1730332AbfDEHz0 (ORCPT ); Fri, 5 Apr 2019 03:55:26 -0400 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=bombadil.20170209; h=In-Reply-To:Content-Type:MIME-Version :References:Message-ID:Subject:Cc:To:From:Date:Sender:Reply-To: Content-Transfer-Encoding:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Id: List-Help:List-Unsubscribe:List-Subscribe:List-Post:List-Owner:List-Archive; bh=hSCoH375imCrsPBrV3MZSJaxDjhAhZHTukSSI0h4QLA=; b=j3MErZPbW4xXTAGOQC8tdL5GP hCw4Fe8FCmX9z45Ca6hTCj2qa2PuVQlc03SAiXGh9sbMBu8sdGtMQVSLkPimMNL7COIOrixg9/At1 cCtGioqftMuxP7a1lKPPwVY482nixeb8QkSz58A/APp04aW9oT8wCFy1fFjHT4DRz3jMX1dPLkHYU jbhoqDqrmWbhoCoCdC8y2SEqcO82LQao7Hp+W4gYexAWDj84DaksWhyp6SfzBxHE0tdCQiCvZ3MLL z5g27ly/ap4EjmIg3Yk5O2avj+nLOxHKk3GsBrhwTNPy4yIB63+yXby3am3QPRl+IJprk3ZdAu9QN 6gYFdw//g==; Received: from j217100.upc-j.chello.nl ([24.132.217.100] helo=hirez.programming.kicks-ass.net) by bombadil.infradead.org with esmtpsa (Exim 4.90_1 #2 (Red Hat Linux)) id 1hCJ61-0004k8-R5; Fri, 05 Apr 2019 07:17:06 +0000 Received: by hirez.programming.kicks-ass.net (Postfix, from userid 1000) id 31AA323954638; Fri, 5 Apr 2019 09:17:04 +0200 (CEST) Date: Fri, 5 Apr 2019 09:17:04 +0200 From: Peter Zijlstra To: Kairui Song Cc: linux-kernel@vger.kernel.org, Ingo Molnar , Arnaldo Carvalho de Melo , Alexander Shishkin , Jiri Olsa , Namhyung Kim , Thomas Gleixner , Borislav Petkov , "H. Peter Anvin" , Dave Young , Josh Poimboeuf Subject: Re: [RFC PATCH] perf/x86: make perf callchain work without CONFIG_FRAME_POINTER Message-ID: <20190405071704.GC4038@hirez.programming.kicks-ass.net> References: <20190404172545.20928-1-kasong@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20190404172545.20928-1-kasong@redhat.com> User-Agent: Mutt/1.10.1 (2018-07-13) Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org And you forgot to Cc Josh.. On Fri, Apr 05, 2019 at 01:25:45AM +0800, Kairui Song wrote: > Currently perf callchain is not working properly with ORC unwinder, > we'll get useless in kernel callchain like this: > > perf 6429 [000] 22.498450: kmem:mm_page_alloc: page=0x176a17 pfn=1534487 order=0 migratetype=0 gfp_flags=GFP_KERNEL > ffffffffbe23e32e __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) > 7efdf7f7d3e8 __poll+0x18 (/usr/lib64/libc-2.28.so) > 5651468729c1 [unknown] (/usr/bin/perf) > 5651467ee82a main+0x69a (/usr/bin/perf) > 7efdf7eaf413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) > 5541f689495641d7 [unknown] ([unknown]) > > Without CONFIG_FRAME_POINTER, bp is not reserved as frame pointer so > can't get callers frame pointer, instead current frame pointer is > returned when trying to fetch caller registers. The unwinder will error > out early, and end the stacktrace early. > > So instead of let the unwinder start with the dumped register, we start > it right where the unwinding started when the stacktrace is triggered by > trace event directly. And skip until the frame pointer is reached. > > This makes the callchain get the full in kernel stacktrace again: > > perf 6503 [000] 1567.570191: kmem:mm_page_alloc: page=0x16c904 pfn=1493252 order=0 migratetype=0 gfp_flags=GFP_KERNEL > ffffffffb523e2ae __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb52383bd __get_free_pages+0xd (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb52fd28a __pollwait+0x8a (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb521426f perf_poll+0x2f (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb52fe3e2 do_sys_poll+0x252 (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb52ff027 __x64_sys_poll+0x37 (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb500418b do_syscall_64+0x5b (/lib/modules/5.1.0-rc3+/build/vmlinux) > ffffffffb5a0008c entry_SYSCALL_64_after_hwframe+0x44 (/lib/modules/5.1.0-rc3+/build/vmlinux) > 7f71e92d03e8 __poll+0x18 (/usr/lib64/libc-2.28.so) > 55a22960d9c1 [unknown] (/usr/bin/perf) > 55a22958982a main+0x69a (/usr/bin/perf) > 7f71e9202413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) > 5541f689495641d7 [unknown] ([unknown]) > > ---- > > Just found with ORC unwinder the perf callchain is unusable, and this > seems fixes it well, any suggestion is welcome, thanks! That whole .direct stuff is horrible crap. > --- > arch/x86/events/core.c | 34 ++++++++++++++++++++++++++++------ > include/linux/perf_event.h | 3 ++- > kernel/bpf/stackmap.c | 4 ++-- > kernel/events/callchain.c | 13 +++++++++++-- > kernel/events/core.c | 2 +- > 5 files changed, 44 insertions(+), 12 deletions(-) > > diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c > index e2b1447192a8..3f3e110794ac 100644 > --- a/arch/x86/events/core.c > +++ b/arch/x86/events/core.c > @@ -2355,8 +2355,9 @@ void arch_perf_update_userpage(struct perf_event *event, > cyc2ns_read_end(); > } > > -void > -perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) > +static void > +__perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs, > + bool direct_call) > { > struct unwind_state state; > unsigned long addr; > @@ -2366,17 +2367,38 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re > return; > } > > - if (perf_callchain_store(entry, regs->ip)) > - return; > + /* > + * Without frame pointer, we can't get a reliable caller bp value. > + * If this is called directly from a trace point, just start the > + * unwind from here and skip until the frame is reached. > + */ > + if (IS_ENABLED(CONFIG_FRAME_POINTER) || !direct_call) { > + if (perf_callchain_store(entry, regs->ip)) > + return; > + unwind_start(&state, current, regs, NULL); > + } else { > + unwind_start(&state, current, NULL, (unsigned long*)regs->bp); > + } > > - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); > - unwind_next_frame(&state)) { > + for (; !unwind_done(&state); unwind_next_frame(&state)) { > addr = unwind_get_return_address(&state); > if (!addr || perf_callchain_store(entry, addr)) > return; > } > } > > +void > +perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) > +{ > + __perf_callchain_kernel(entry, regs, false); > +} > + > +void > +perf_callchain_kernel_direct(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) > +{ > + __perf_callchain_kernel(entry, regs, true); > +} > + > static inline int > valid_user_frame(const void __user *fp, unsigned long size) > { > diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h > index e47ef764f613..b0e33ba36695 100644 > --- a/include/linux/perf_event.h > +++ b/include/linux/perf_event.h > @@ -1154,9 +1154,10 @@ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); > > extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); > extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); > +extern void perf_callchain_kernel_direct(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); > extern struct perf_callchain_entry * > get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, > - u32 max_stack, bool crosstask, bool add_mark); > + u32 max_stack, bool crosstask, bool add_mark, bool direct_call); > extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); > extern int get_callchain_buffers(int max_stack); > extern void put_callchain_buffers(void); > diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c > index 950ab2f28922..376d774da6b5 100644 > --- a/kernel/bpf/stackmap.c > +++ b/kernel/bpf/stackmap.c > @@ -368,7 +368,7 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, > return -EINVAL; > > trace = get_perf_callchain(regs, init_nr, kernel, user, > - sysctl_perf_event_max_stack, false, false); > + sysctl_perf_event_max_stack, false, false, false); > > if (unlikely(!trace)) > /* couldn't fetch the stack trace */ > @@ -476,7 +476,7 @@ BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, > else > init_nr = sysctl_perf_event_max_stack - num_elem; > trace = get_perf_callchain(regs, init_nr, kernel, user, > - sysctl_perf_event_max_stack, false, false); > + sysctl_perf_event_max_stack, false, false, false); > if (unlikely(!trace)) > goto err_fault; > > diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c > index c2b41a263166..4cb5861f57ee 100644 > --- a/kernel/events/callchain.c > +++ b/kernel/events/callchain.c > @@ -40,6 +40,12 @@ __weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, > { > } > > +__weak void perf_callchain_kernel_direct(struct perf_callchain_entry_ctx *entry, > + struct pt_regs *regs) > +{ > + perf_callchain_kernel(entry, regs); > +} > + > __weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry, > struct pt_regs *regs) > { > @@ -176,7 +182,7 @@ put_callchain_entry(int rctx) > > struct perf_callchain_entry * > get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, > - u32 max_stack, bool crosstask, bool add_mark) > + u32 max_stack, bool crosstask, bool add_mark, bool direct_call) > { > struct perf_callchain_entry *entry; > struct perf_callchain_entry_ctx ctx; > @@ -198,7 +204,10 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, > if (kernel && !user_mode(regs)) { > if (add_mark) > perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL); > - perf_callchain_kernel(&ctx, regs); > + if (direct_call) > + perf_callchain_kernel_direct(&ctx, regs); > + else > + perf_callchain_kernel(&ctx, regs); > } > > if (user) { > diff --git a/kernel/events/core.c b/kernel/events/core.c > index 72d06e302e99..af9fb9b03283 100644 > --- a/kernel/events/core.c > +++ b/kernel/events/core.c > @@ -6377,7 +6377,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) > return &__empty_callchain; > > callchain = get_perf_callchain(regs, 0, kernel, user, > - max_stack, crosstask, true); > + max_stack, crosstask, true, true); > return callchain ?: &__empty_callchain; > } > > -- > 2.20.1 >