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=-8.5 required=3.0 tests=HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED, 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 E8105C04EBF for ; Tue, 4 Dec 2018 11:12:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id B9E232082D for ; Tue, 4 Dec 2018 11:12:27 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org B9E232082D Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=arm.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1728563AbeLDLM0 (ORCPT ); Tue, 4 Dec 2018 06:12:26 -0500 Received: from foss.arm.com ([217.140.101.70]:57534 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727977AbeLDLMX (ORCPT ); Tue, 4 Dec 2018 06:12:23 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 0FF1AA78; Tue, 4 Dec 2018 03:12:23 -0800 (PST) Received: from edgewater-inn.cambridge.arm.com (usa-sjc-imap-foss1.foss.arm.com [10.72.51.249]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id D31DD3F59C; Tue, 4 Dec 2018 03:12:22 -0800 (PST) Received: by edgewater-inn.cambridge.arm.com (Postfix, from userid 1000) id 288E31AE10A5; Tue, 4 Dec 2018 11:12:43 +0000 (GMT) Date: Tue, 4 Dec 2018 11:12:43 +0000 From: Will Deacon To: Steven Rostedt Cc: Arnd Bergmann , Anders Roxell , Ingo Molnar , Catalin Marinas , Kees Cook , Linux Kernel Mailing List , Linux ARM Subject: Re: [PATCH 3/3] arm64: ftrace: add cond_resched() to func ftrace_make_(call|nop) Message-ID: <20181204111242.GA32596@arm.com> References: <20181130150956.27620-1-anders.roxell@linaro.org> <20181203192228.GC29028@arm.com> <20181204005012.11f73df9@vmware.local.home> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20181204005012.11f73df9@vmware.local.home> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Steve, Arnd, On Tue, Dec 04, 2018 at 12:50:12AM -0500, Steven Rostedt wrote: > On Mon, 3 Dec 2018 22:51:52 +0100 > Arnd Bergmann wrote: > > On Mon, Dec 3, 2018 at 8:22 PM Will Deacon wrote: > > > On Fri, Nov 30, 2018 at 04:09:56PM +0100, Anders Roxell wrote: > > > > Both of those functions end up calling ftrace_modify_code(), which is > > > > expensive because it changes the page tables and flush caches. > > > > Microseconds add up because this is called in a loop for each dyn_ftrace > > > > record, and this triggers the softlockup watchdog unless we let it sleep > > > > occasionally. > > > > Rework so that we call cond_resched() before going into the > > > > ftrace_modify_code() function. > > > > > > > > Co-developed-by: Arnd Bergmann > > > > Signed-off-by: Arnd Bergmann > > > > Signed-off-by: Anders Roxell > > > > --- > > > > arch/arm64/kernel/ftrace.c | 10 ++++++++++ > > > > 1 file changed, 10 insertions(+) > > > > > > It sounds like you're running into issues with the existing code, but I'd > > > like to understand a bit more about exactly what you're seeing. Which part > > > of the ftrace patching is proving to be expensive? > > > > > > The page table manipulation only happens once per module when using PLTs, > > > and the cache maintenance is just a single line per patch site without an > > > IPI. > > > > > > Is it the loop in ftrace_replace_code() that is causing the hassle? > > > > Yes: with an allmodconfig kernel, the ftrace selftest calls ftrace_replace_code > > to look >40000 through ftrace_make_call/ftrace_make_nop, and these > > end up calling Ok, 40000 invocations would do it! > > static int __kprobes __aarch64_insn_write(void *addr, __le32 insn) > > { > > void *waddr = addr; > > unsigned long flags = 0; > > int ret; > > > > raw_spin_lock_irqsave(&patch_lock, flags); > > waddr = patch_map(addr, FIX_TEXT_POKE0); > > > > ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE); > > > > patch_unmap(FIX_TEXT_POKE0); > > raw_spin_unlock_irqrestore(&patch_lock, flags); > > > > return ret; > > } > > int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) > > { > > u32 *tp = addr; > > int ret; > > > > /* A64 instructions must be word aligned */ > > if ((uintptr_t)tp & 0x3) > > return -EINVAL; > > > > ret = aarch64_insn_write(tp, insn); > > if (ret == 0) > > __flush_icache_range((uintptr_t)tp, > > (uintptr_t)tp + AARCH64_INSN_SIZE); > > > > return ret; > > } > > > > which seems to be where the main cost is. This is with inside of > > qemu, and with lots of debugging options (in particular > > kcov and ubsan) enabled, that make each function call > > more expensive. > > I was thinking more about this. Would something like this work? > > -- Steve > > diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c > index 8ef9fc226037..42e89397778b 100644 > --- a/kernel/trace/ftrace.c > +++ b/kernel/trace/ftrace.c > @@ -2393,11 +2393,14 @@ void __weak ftrace_replace_code(int enable) > { > struct dyn_ftrace *rec; > struct ftrace_page *pg; > + bool schedulable; > int failed; > > if (unlikely(ftrace_disabled)) > return; > > + schedulable = !irqs_disabled() & !preempt_count(); Looks suspiciously like a bitwise preemptible() to me! > + > do_for_each_ftrace_rec(pg, rec) { > > if (rec->flags & FTRACE_FL_DISABLED) > @@ -2409,6 +2412,8 @@ void __weak ftrace_replace_code(int enable) > /* Stop processing */ > return; > } > + if (schedulable) > + cond_resched(); > } while_for_each_ftrace_rec(); > } If this solves the problem in core code, them I'm all for it. Otherwise, I was thinking of rolling our own ftrace_replace_code() for arm64, but that's going to involve a fair amount of duplication. Will