From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752336AbdINKzz (ORCPT ); Thu, 14 Sep 2017 06:55:55 -0400 Received: from terminus.zytor.com ([65.50.211.136]:55129 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752055AbdINKzy (ORCPT ); Thu, 14 Sep 2017 06:55:54 -0400 Date: Thu, 14 Sep 2017 03:50:10 -0700 From: tip-bot for Thomas Gleixner Message-ID: Cc: uobergfe@redhat.com, peterz@infradead.org, torvalds@linux-foundation.org, tglx@linutronix.de, dzickus@redhat.com, linux-kernel@vger.kernel.org, cmetcalf@mellanox.com, akpm@linux-foundation.org, mingo@kernel.org, bigeasy@linutronix.de, hpa@zytor.com, npiggin@gmail.com, bp@alien8.de Reply-To: tglx@linutronix.de, dzickus@redhat.com, uobergfe@redhat.com, torvalds@linux-foundation.org, peterz@infradead.org, akpm@linux-foundation.org, mingo@kernel.org, bp@alien8.de, hpa@zytor.com, npiggin@gmail.com, bigeasy@linutronix.de, linux-kernel@vger.kernel.org, cmetcalf@mellanox.com In-Reply-To: <20170912194148.259651788@linutronix.de> References: <20170912194148.259651788@linutronix.de> To: linux-tip-commits@vger.kernel.org Subject: [tip:core/urgent] watchdog/hardlockup/perf: Use new perf CPU enable mechanism Git-Commit-ID: 146c9d0e9dfdb62ed6afd43cc263efafbbfd1dcf X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 146c9d0e9dfdb62ed6afd43cc263efafbbfd1dcf Gitweb: http://git.kernel.org/tip/146c9d0e9dfdb62ed6afd43cc263efafbbfd1dcf Author: Thomas Gleixner AuthorDate: Tue, 12 Sep 2017 21:37:21 +0200 Committer: Ingo Molnar CommitDate: Thu, 14 Sep 2017 11:41:08 +0200 watchdog/hardlockup/perf: Use new perf CPU enable mechanism Get rid of the hodgepodge which tries to be smart about perf being unavailable and error printout rate limiting. That's all not required simply because this is never invoked when the perf NMI watchdog is not functional. Signed-off-by: Thomas Gleixner Reviewed-by: Don Zickus Cc: Andrew Morton Cc: Borislav Petkov Cc: Chris Metcalf Cc: Linus Torvalds Cc: Nicholas Piggin Cc: Peter Zijlstra Cc: Sebastian Siewior Cc: Ulrich Obergfell Link: http://lkml.kernel.org/r/20170912194148.259651788@linutronix.de Signed-off-by: Ingo Molnar --- kernel/watchdog.c | 4 ++- kernel/watchdog_hld.c | 88 +++------------------------------------------------ 2 files changed, 8 insertions(+), 84 deletions(-) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index fd8a998..5eb1196 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -107,6 +107,7 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); */ int __weak watchdog_nmi_enable(unsigned int cpu) { + hardlockup_detector_perf_enable(); return 0; } @@ -465,7 +466,8 @@ static void watchdog_enable(unsigned int cpu) /* Initialize timestamp */ __touch_watchdog(); /* Enable the perf event */ - watchdog_nmi_enable(cpu); + if (watchdog_enabled & NMI_WATCHDOG_ENABLED) + watchdog_nmi_enable(cpu); watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); } diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 99a3f22..509bb6b 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -25,7 +25,7 @@ static DEFINE_PER_CPU(struct perf_event *, dead_event); static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; -static bool hardlockup_detector_disabled; +static unsigned int watchdog_cpus; void arch_touch_nmi_watchdog(void) { @@ -160,84 +160,6 @@ static void watchdog_overflow_callback(struct perf_event *event, return; } -/* - * People like the simple clean cpu node info on boot. - * Reduce the watchdog noise by only printing messages - * that are different from what cpu0 displayed. - */ -static unsigned long firstcpu_err; -static atomic_t watchdog_cpus; - -int watchdog_nmi_enable(unsigned int cpu) -{ - struct perf_event_attr *wd_attr; - struct perf_event *event = per_cpu(watchdog_ev, cpu); - int firstcpu = 0; - - /* nothing to do if the hard lockup detector is disabled */ - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) - goto out; - - /* A failure disabled the hardlockup detector permanently */ - if (hardlockup_detector_disabled) - return -ENODEV; - - /* is it already setup and enabled? */ - if (event && event->state > PERF_EVENT_STATE_OFF) - goto out; - - /* it is setup but not enabled */ - if (event != NULL) - goto out_enable; - - if (atomic_inc_return(&watchdog_cpus) == 1) - firstcpu = 1; - - wd_attr = &wd_hw_attr; - wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh); - - /* Try to register using hardware perf events */ - event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL); - - /* save the first cpu's error for future comparision */ - if (firstcpu && IS_ERR(event)) - firstcpu_err = PTR_ERR(event); - - if (!IS_ERR(event)) { - /* only print for the first cpu initialized */ - if (firstcpu || firstcpu_err) - pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n"); - goto out_save; - } - - /* skip displaying the same error again */ - if (!firstcpu && (PTR_ERR(event) == firstcpu_err)) - return PTR_ERR(event); - - /* vary the KERN level based on the returned errno */ - if (PTR_ERR(event) == -EOPNOTSUPP) - pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu); - else if (PTR_ERR(event) == -ENOENT) - pr_warn("disabled (cpu%i): hardware events not enabled\n", - cpu); - else - pr_err("disabled (cpu%i): unable to create perf event: %ld\n", - cpu, PTR_ERR(event)); - - pr_info("Disabling hard lockup detector permanently\n"); - hardlockup_detector_disabled = true; - - return PTR_ERR(event); - - /* success path */ -out_save: - per_cpu(watchdog_ev, cpu) = event; -out_enable: - perf_event_enable(per_cpu(watchdog_ev, cpu)); -out: - return 0; -} - static int hardlockup_detector_event_create(void) { unsigned int cpu = smp_processor_id(); @@ -267,6 +189,9 @@ void hardlockup_detector_perf_enable(void) if (hardlockup_detector_event_create()) return; + if (!watchdog_cpus++) + pr_info("Enabled. Permanently consumes one hw-PMU counter.\n"); + perf_event_enable(this_cpu_read(watchdog_ev)); } @@ -282,10 +207,7 @@ void hardlockup_detector_perf_disable(void) this_cpu_write(watchdog_ev, NULL); this_cpu_write(dead_event, event); cpumask_set_cpu(smp_processor_id(), &dead_events_mask); - - /* watchdog_nmi_enable() expects this to be zero initially. */ - if (atomic_dec_and_test(&watchdog_cpus)) - firstcpu_err = 0; + watchdog_cpus--; } }