Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757944AbcJRCsC (ORCPT ); Mon, 17 Oct 2016 22:48:02 -0400 Received: from userp1040.oracle.com ([156.151.31.81]:31853 "EHLO userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755649AbcJRCr7 (ORCPT ); Mon, 17 Oct 2016 22:47:59 -0400 Subject: Re: [PATCH v2 1/2] watchdog: Introduce arch_watchdog_nmi_enable and arch_watchdog_nmi_disable To: Don Zickus References: <1476391082-77928-1-git-send-email-babu.moger@oracle.com> <1476391082-77928-2-git-send-email-babu.moger@oracle.com> <20161017173157.GK98438@redhat.com> Cc: mingo@kernel.org, akpm@linux-foundation.org, ak@linux.intel.com, jkosina@suse.cz, baiyaowei@cmss.chinamobile.com, atomlin@redhat.com, uobergfe@redhat.com, tj@kernel.org, hidehiro.kawai.ez@hitachi.com, johunt@akamai.com, davem@davemloft.net, sparclinux@vger.kernel.org, linux-kernel@vger.kernel.org, sam@ravnborg.org From: Babu Moger Organization: Oracle Corporation Message-ID: <12e7c12f-3862-ab52-7d5d-ba55764c6a79@oracle.com> Date: Mon, 17 Oct 2016 21:46:52 -0500 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Thunderbird/45.4.0 MIME-Version: 1.0 In-Reply-To: <20161017173157.GK98438@redhat.com> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit X-Source-IP: userv0022.oracle.com [156.151.31.74] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 5281 Lines: 166 Don, On 10/17/2016 12:31 PM, Don Zickus wrote: > On Thu, Oct 13, 2016 at 01:38:01PM -0700, Babu Moger wrote: >> Currently we do not have a way to enable/disable arch specific >> watchdog handlers if it was implemented by any of the architectures. >> >> This patch introduces new functions arch_watchdog_nmi_enable and >> arch_watchdog_nmi_disable which can be used to enable/disable architecture >> specific NMI watchdog handlers. These functions are defined as weak as >> architectures can override their definitions to enable/disable nmi >> watchdog behaviour. > Hi Babu, > > This patch tested fine on my x86 box and I am ok with the changes. > > I do have one small cosmetic request below for a failure path. Other than > that I will give my ack. Yes. I am testing these changes. If everything goes as expected, I will post v3 version tomorrow. Thanks Babu > > Cheers, > Don > >> Signed-off-by: Babu Moger >> --- >> kernel/watchdog.c | 65 +++++++++++++++++++++++++++++++++++----------------- >> 1 files changed, 44 insertions(+), 21 deletions(-) >> >> diff --git a/kernel/watchdog.c b/kernel/watchdog.c >> index 9acb29f..d1e84e6 100644 >> --- a/kernel/watchdog.c >> +++ b/kernel/watchdog.c >> @@ -46,7 +46,7 @@ >> >> static DEFINE_MUTEX(watchdog_proc_mutex); >> >> -#ifdef CONFIG_HARDLOCKUP_DETECTOR >> +#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) >> static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED|NMI_WATCHDOG_ENABLED; >> #else >> static unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED; >> @@ -585,15 +585,11 @@ static void watchdog(unsigned int cpu) >> */ >> static unsigned long cpu0_err; >> >> -static int watchdog_nmi_enable(unsigned int cpu) >> +static int arch_watchdog_nmi_enable(unsigned int cpu) >> { >> struct perf_event_attr *wd_attr; >> struct perf_event *event = per_cpu(watchdog_ev, cpu); >> >> - /* nothing to do if the hard lockup detector is disabled */ >> - if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) >> - goto out; >> - >> /* is it already setup and enabled? */ >> if (event && event->state > PERF_EVENT_STATE_OFF) >> goto out; >> @@ -619,18 +615,6 @@ static int watchdog_nmi_enable(unsigned int cpu) >> goto out_save; >> } >> >> - /* >> - * Disable the hard lockup detector if _any_ CPU fails to set up >> - * set up the hardware perf event. The watchdog() function checks >> - * the NMI_WATCHDOG_ENABLED bit periodically. >> - * >> - * The barriers are for syncing up watchdog_enabled across all the >> - * cpus, as clear_bit() does not use barriers. >> - */ >> - smp_mb__before_atomic(); >> - clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); >> - smp_mb__after_atomic(); >> - >> /* skip displaying the same error again */ >> if (cpu > 0 && (PTR_ERR(event) == cpu0_err)) >> return PTR_ERR(event); > In the arch_watchdog_nmi_enable code is a pr_info on failure > > pr_info("Shutting down hard lockup detector on all cpus\n"); > > that should be moved to below.. > > >> @@ -658,7 +642,7 @@ out: >> return 0; >> } >> >> -static void watchdog_nmi_disable(unsigned int cpu) >> +static void arch_watchdog_nmi_disable(unsigned int cpu) >> { >> struct perf_event *event = per_cpu(watchdog_ev, cpu); >> >> @@ -676,8 +660,13 @@ static void watchdog_nmi_disable(unsigned int cpu) >> } >> >> #else >> -static int watchdog_nmi_enable(unsigned int cpu) { return 0; } >> -static void watchdog_nmi_disable(unsigned int cpu) { return; } >> +/* >> + * These two functions are mostly architecture specific >> + * defining them as weak here. >> + */ >> +int __weak arch_watchdog_nmi_enable(unsigned int cpu) { return 0; } >> +void __weak arch_watchdog_nmi_disable(unsigned int cpu) { return; } >> + >> #endif /* CONFIG_HARDLOCKUP_DETECTOR */ >> >> static struct smp_hotplug_thread watchdog_threads = { >> @@ -781,6 +770,40 @@ void lockup_detector_resume(void) >> put_online_cpus(); >> } >> >> +void watchdog_nmi_disable(unsigned int cpu) >> +{ >> + arch_watchdog_nmi_disable(cpu); >> +} >> + >> +int watchdog_nmi_enable(unsigned int cpu) >> +{ >> + int err; >> + >> + /* nothing to do if the hard lockup detector is disabled */ >> + if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED)) >> + return 0; >> + >> + err = arch_watchdog_nmi_enable(cpu); >> + >> + if (err) { >> + /* >> + * Disable the hard lockup detector if _any_ CPU fails to set up >> + * set up the hardware perf event. The watchdog() function checks >> + * the NMI_WATCHDOG_ENABLED bit periodically. >> + * >> + * The barriers are for syncing up watchdog_enabled across all the >> + * cpus, as clear_bit() does not use barriers. >> + */ >> + smp_mb__before_atomic(); >> + clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled); >> + smp_mb__after_atomic(); > moved to here: > > pr_info("Shutting down hard lockup detector on all cpus\n"); > > > This lets the failure message be displayed on all arches instead of just > x86. Though I guess sparc does not call theirs 'hard lockup detector'. > Hmm... > > >> + >> + return err; >> + } >> + >> + return 0; >> +} >> + >> static int update_watchdog_all_cpus(void) >> { >> int ret; >> -- >> 1.7.1 >>