From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755415Ab3AHWdO (ORCPT ); Tue, 8 Jan 2013 17:33:14 -0500 Received: from mx1.redhat.com ([209.132.183.28]:7613 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754097Ab3AHWdM (ORCPT ); Tue, 8 Jan 2013 17:33:12 -0500 Date: Tue, 8 Jan 2013 17:32:29 -0500 From: Rik van Riel To: linux-kernel@vger.kernel.org Cc: aquini@redhat.com, walken@google.com, eric.dumazet@gmail.com, lwoodman@redhat.com, jeremy@goop.org, Jan Beulich , knoel@redhat.com, chegu_vinod@hp.com, raghavendra.kt@linux.vnet.ibm.com, mingo@redhat.com Subject: [DEBUG PATCH 5/5] x86,smp: add debugging code to track spinlock delay value Message-ID: <20130108173229.784f74bc@annuminas.surriel.com> In-Reply-To: <20130108172632.1126898a@annuminas.surriel.com> References: <20130108172632.1126898a@annuminas.surriel.com> Organization: Red Hat, Inc. Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Eric Dumazet This code prints out the maximum spinlock delay value and the backtrace that pushed it that far. On systems with serial consoles, the act of printing can cause the spinlock delay value to explode. It can be useful as a debugging tool, but is too verbose to merge upstream in this form. Not-signed-off-by: Rik van Riel Not-signed-off-by: Eric Dumazet --- arch/x86/kernel/smp.c | 8 ++++++++ 1 files changed, 8 insertions(+), 0 deletions(-) diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 1877890..d80aee7 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -147,6 +147,8 @@ static DEFINE_PER_CPU(struct delay_entry [1 << DELAY_HASH_SHIFT], spinlock_delay }, }; +static DEFINE_PER_CPU(u32, maxdelay); + void ticket_spin_lock_wait(arch_spinlock_t *lock, struct __raw_tickets inc) { __ticket_t head = inc.head, ticket = inc.tail; @@ -192,6 +194,12 @@ void ticket_spin_lock_wait(arch_spinlock_t *lock, struct __raw_tickets inc) } ent->hash = hash; ent->delay = delay; + + if (__this_cpu_read(maxdelay) * 4 < delay * 3) { + pr_err("cpu %d lock %p delay %d\n", smp_processor_id(), lock, delay>>DELAY_SHIFT); + __this_cpu_write(maxdelay, delay); + WARN_ON(1); + } } /*