From patchwork Thu Jun 28 18:21:46 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Joel Fernandes X-Patchwork-Id: 10494677 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 53F6C601BE for ; Thu, 28 Jun 2018 18:23:14 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 567872A18C for ; Thu, 28 Jun 2018 18:23:14 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 49FCD2A19F; Thu, 28 Jun 2018 18:23:14 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.8 required=2.0 tests=BAYES_00,DKIM_SIGNED, MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI, T_DKIM_INVALID autolearn=unavailable version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id BAD392A18C for ; Thu, 28 Jun 2018 18:23:13 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S967812AbeF1SXE (ORCPT ); Thu, 28 Jun 2018 14:23:04 -0400 Received: from mail-pf0-f194.google.com ([209.85.192.194]:47070 "EHLO mail-pf0-f194.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030421AbeF1SWB (ORCPT ); Thu, 28 Jun 2018 14:22:01 -0400 Received: by mail-pf0-f194.google.com with SMTP id q1-v6so2970171pff.13 for ; Thu, 28 Jun 2018 11:22:01 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=joelfernandes.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=rP7eurICyIZQBfcjqQ2vzisdGfNYym2lsKWx2Zea9ds=; b=K7eZspCbcWqZ1JicZsv0pU9sTd5mETSHou+0xsvZpY6PfINbK3/SJL4rjVXbYx6pby xNRdhs71FkrrzA1Ub1mzChDpP9Fp1Eip5sEZP+Idh4VoRVR9nAj+u7hFQZiPYXnpnVef xVAXUiAPW7J4M1oAB48tQTVbacrAtcp8MGx2I= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=rP7eurICyIZQBfcjqQ2vzisdGfNYym2lsKWx2Zea9ds=; b=Ocm4Wjcdfw+B9SIGP2GlGFOjRHkqYYYNXmZfMX1vHPKEu2MCobtTdGBmIhxbMFi/xS RHIH1vT3BOGOmqSYUUIdgH6sWXJsFNocf83Ig34YqUtklGYZ9x9GaNuTSBAAERgT6dtL JmrXi/hx86LA8gMmzpfiLAtNeGLhHRAUPjycGOP2hjja5EHm0BR9Ax0AG5F3QmKolslb PDetdCc+zhsCHqUOcn0poUiAhL/y+frY1gJlAVeM/ggMQln8AgQe5B6MDYjb0g9QjCCO LtfPFmphyCjQOAkbTBONOS+uk7E076nOL2cc5P0nH/NyZFiSd+/2li3jcalTQOYI0ZTO DqXA== X-Gm-Message-State: APt69E37nkGxhC69ge3cGG4hNTOceQPEgrlbQGRGkknMhQW7AgrkPVhK bwXidOhQGGEsQzpmwmO7YDI1cA== X-Google-Smtp-Source: ADUXVKJyv09NMNy+evR1Vrd42SJSDtxrU5WPye6lptoX8QzwZyQdlxlcv7lQR0dWYvZKTkkqCzuJ0A== X-Received: by 2002:a63:686:: with SMTP id 128-v6mr9634689pgg.338.1530210120858; Thu, 28 Jun 2018 11:22:00 -0700 (PDT) Received: from joelaf.mtv.corp.google.com ([2620:0:1000:1600:3122:ea9c:d178:eb]) by smtp.gmail.com with ESMTPSA id q10-v6sm13686027pfj.7.2018.06.28.11.21.59 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Thu, 28 Jun 2018 11:22:00 -0700 (PDT) From: Joel Fernandes To: linux-kernel@vger.kernel.org Cc: "Joel Fernandes (Google)" , Boqun Feng , Byungchul Park , Ingo Molnar , Julia Cartwright , linux-kselftest@vger.kernel.org, Masami Hiramatsu , Mathieu Desnoyers , Namhyung Kim , Paul McKenney , Peter Zijlstra , Steven Rostedt , Thomas Glexiner , Tom Zanussi Subject: [PATCH v9 4/7] tracepoint: Make rcuidle tracepoint callers use SRCU Date: Thu, 28 Jun 2018 11:21:46 -0700 Message-Id: <20180628182149.226164-5-joel@joelfernandes.org> X-Mailer: git-send-email 2.18.0.rc2.346.g013aa6912e-goog In-Reply-To: <20180628182149.226164-1-joel@joelfernandes.org> References: <20180628182149.226164-1-joel@joelfernandes.org> Sender: linux-kselftest-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kselftest@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: "Joel Fernandes (Google)" In recent tests with IRQ on/off tracepoints, a large performance overhead ~10% is noticed when running hackbench. This is root caused to calls to rcu_irq_enter_irqson and rcu_irq_exit_irqson from the tracepoint code. Following a long discussion on the list [1] about this, we concluded that srcu is a better alternative for use during rcu idle. Although it does involve extra barriers, its lighter than the sched-rcu version which has to do additional RCU calls to notify RCU idle about entry into RCU sections. In this patch, we change the underlying implementation of the trace_*_rcuidle API to use SRCU. This has shown to improve performance alot for the high frequency irq enable/disable tracepoints. Test: Tested idle and preempt/irq tracepoints. Here are some performance numbers: With a run of the following 30 times on a single core x86 Qemu instance with 1GB memory: hackbench -g 4 -f 2 -l 3000 Completion times in seconds. CONFIG_PROVE_LOCKING=y. No patches (without this series) Mean: 3.048 Median: 3.025 Std Dev: 0.064 With Lockdep using irq tracepoints with RCU implementation: Mean: 3.451 (-11.66 %) Median: 3.447 (-12.22%) Std Dev: 0.049 With Lockdep using irq tracepoints with SRCU implementation (this series): Mean: 3.020 (I would consider the improvement against the "without this series" case as just noise). Median: 3.013 Std Dev: 0.033 [1] https://patchwork.kernel.org/patch/10344297/ Reviewed-by: Mathieu Desnoyers Signed-off-by: Joel Fernandes (Google) --- include/linux/tracepoint.h | 49 +++++++++++++++++++++++++++++++------- kernel/tracepoint.c | 16 ++++++++++++- 2 files changed, 56 insertions(+), 9 deletions(-) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 19a690b559ca..beeb01e147f8 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -15,6 +15,7 @@ */ #include +#include #include #include #include @@ -33,6 +34,8 @@ struct trace_eval_map { #define TRACEPOINT_DEFAULT_PRIO 10 +extern struct srcu_struct tracepoint_srcu; + extern int tracepoint_probe_register(struct tracepoint *tp, void *probe, void *data); extern int @@ -75,10 +78,16 @@ int unregister_tracepoint_module_notifier(struct notifier_block *nb) * probe unregistration and the end of module exit to make sure there is no * caller executing a probe when it is freed. */ +#ifdef CONFIG_TRACEPOINTS static inline void tracepoint_synchronize_unregister(void) { + synchronize_srcu(&tracepoint_srcu); synchronize_sched(); } +#else +static inline void tracepoint_synchronize_unregister(void) +{ } +#endif #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS extern int syscall_regfunc(void); @@ -129,18 +138,38 @@ extern void syscall_unregfunc(void); * as "(void *, void)". The DECLARE_TRACE_NOARGS() will pass in just * "void *data", where as the DECLARE_TRACE() will pass in "void *data, proto". */ -#define __DO_TRACE(tp, proto, args, cond, rcucheck) \ +#define __DO_TRACE(tp, proto, args, cond, rcuidle) \ do { \ struct tracepoint_func *it_func_ptr; \ void *it_func; \ void *__data; \ + int __maybe_unused idx = 0; \ \ if (!(cond)) \ return; \ - if (rcucheck) \ - rcu_irq_enter_irqson(); \ - rcu_read_lock_sched_notrace(); \ - it_func_ptr = rcu_dereference_sched((tp)->funcs); \ + \ + /* \ + * For rcuidle callers, use srcu since sched-rcu \ + * doesn't work from the idle path. \ + */ \ + if (rcuidle) { \ + if (in_nmi()) { \ + WARN_ON_ONCE(1); \ + return; /* no srcu from nmi */ \ + } \ + \ + idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + it_func_ptr = \ + srcu_dereference_notrace((tp)->funcs, \ + &tracepoint_srcu); \ + /* To keep it consistent with !rcuidle path */ \ + preempt_disable_notrace(); \ + } else { \ + rcu_read_lock_sched_notrace(); \ + it_func_ptr = \ + rcu_dereference_sched((tp)->funcs); \ + } \ + \ if (it_func_ptr) { \ do { \ it_func = (it_func_ptr)->func; \ @@ -148,9 +177,13 @@ extern void syscall_unregfunc(void); ((void(*)(proto))(it_func))(args); \ } while ((++it_func_ptr)->func); \ } \ - rcu_read_unlock_sched_notrace(); \ - if (rcucheck) \ - rcu_irq_exit_irqson(); \ + \ + if (rcuidle) { \ + preempt_enable_notrace(); \ + srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } else { \ + rcu_read_unlock_sched_notrace(); \ + } \ } while (0) #ifndef MODULE diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index 6dc6356c3327..955148d91b74 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -31,6 +31,9 @@ extern struct tracepoint * const __start___tracepoints_ptrs[]; extern struct tracepoint * const __stop___tracepoints_ptrs[]; +DEFINE_SRCU(tracepoint_srcu); +EXPORT_SYMBOL_GPL(tracepoint_srcu); + /* Set to 1 to enable tracepoint debug output */ static const int tracepoint_debug; @@ -67,16 +70,27 @@ static inline void *allocate_probes(int count) return p == NULL ? NULL : p->probes; } -static void rcu_free_old_probes(struct rcu_head *head) +static void srcu_free_old_probes(struct rcu_head *head) { kfree(container_of(head, struct tp_probes, rcu)); } +static void rcu_free_old_probes(struct rcu_head *head) +{ + call_srcu(&tracepoint_srcu, head, srcu_free_old_probes); +} + static inline void release_probes(struct tracepoint_func *old) { if (old) { struct tp_probes *tp_probes = container_of(old, struct tp_probes, probes[0]); + /* + * Tracepoint probes are protected by both sched RCU and SRCU, + * by calling the SRCU callback in the sched RCU callback we + * cover both cases. So let us chain the SRCU and sched RCU + * callbacks to wait for both grace periods. + */ call_rcu_sched(&tp_probes->rcu, rcu_free_old_probes); } }