From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752378AbcHHQEB (ORCPT ); Mon, 8 Aug 2016 12:04:01 -0400 Received: from mail-il-dmz.mellanox.com ([193.47.165.129]:49903 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752305AbcHHQD6 (ORCPT ); Mon, 8 Aug 2016 12:03:58 -0400 From: Chris Metcalf To: Peter Zijlstra , "Rafael J. Wysocki" , Petr Mladek , Russell King , Thomas Gleixner , Aaron Tomlin , Ingo Molnar , Andrew Morton , Daniel Thompson , linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Cc: Chris Metcalf Subject: [PATCH v7 2/4] nmi_backtrace: do a local dump_stack() instead of a self-NMI Date: Mon, 8 Aug 2016 12:03:36 -0400 Message-Id: <1470672218-16059-3-git-send-email-cmetcalf@mellanox.com> X-Mailer: git-send-email 2.7.2 In-Reply-To: <1470672218-16059-1-git-send-email-cmetcalf@mellanox.com> References: <1470672218-16059-1-git-send-email-cmetcalf@mellanox.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Currently on arm there is code that checks whether it should call dump_stack() explicitly, to avoid trying to raise an NMI when the current context is not preemptible by the backtrace IPI. Similarly, the forthcoming arch/tile support uses an IPI mechanism that does not support generating an NMI to self. Accordingly, move the code that guards this case into the generic mechanism, and invoke it unconditionally whenever we want a backtrace of the current cpu. It seems plausible that in all cases, dump_stack() will generate better information than generating a stack from the NMI handler. The register state will be missing, but that state is likely not particularly helpful in any case. Or, if we think it is helpful, we should be capturing and emitting the current register state in all cases when regs == NULL is passed to nmi_cpu_backtrace(). Signed-off-by: Chris Metcalf Acked-by: Aaron Tomlin --- arch/arm/kernel/smp.c | 9 --------- lib/nmi_backtrace.c | 9 +++++++++ 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index 732583dcb8f8..157c991f8de2 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -748,15 +748,6 @@ core_initcall(register_cpufreq_notifier); static void raise_nmi(cpumask_t *mask) { - /* - * Generate the backtrace directly if we are running in a calling - * context that is not preemptible by the backtrace IPI. Note - * that nmi_cpu_backtrace() automatically removes the current cpu - * from mask. - */ - if (cpumask_test_cpu(smp_processor_id(), mask) && irqs_disabled()) - nmi_cpu_backtrace(NULL); - smp_cross_call(mask, IPI_CPU_BACKTRACE); } diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c index 5448d6621102..2933f0680174 100644 --- a/lib/nmi_backtrace.c +++ b/lib/nmi_backtrace.c @@ -49,6 +49,15 @@ void nmi_trigger_cpumask_backtrace(bool include_self, if (!include_self) cpumask_clear_cpu(this_cpu, to_cpumask(backtrace_mask)); + /* + * Don't try to send an NMI to this cpu; it may work on some + * architectures, but on others it may not, and we'll get + * information at least as useful just by doing a dump_stack() here. + * Note that nmi_cpu_backtrace(NULL) will clear the cpu bit. + */ + if (cpumask_test_cpu(this_cpu, to_cpumask(backtrace_mask))) + nmi_cpu_backtrace(NULL); + if (!cpumask_empty(to_cpumask(backtrace_mask))) { pr_info("Sending NMI from CPU %d to CPUs %*pbl:\n", this_cpu, nr_cpumask_bits, to_cpumask(backtrace_mask)); -- 2.7.2