From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.0 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 5D76EC10F0E for ; Thu, 4 Apr 2019 09:55:16 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 24232206DD for ; Thu, 4 Apr 2019 09:55:16 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1554371716; bh=sdb6wbZKuO4yjNeksN4gUW26zb3h/1VB9ywLfTspJxM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:List-ID:From; b=1nyexHAx09gI1U6KahSfsUND4VlG5hg9xg+KlWaecEHW1nDr9bD7hZBpUk/CyOBOb 58zjconnAdtuAprIRt+XnGqvRkqMb+roC2ije/sB10gMtsplq3lWWcDZGdjJpg4CFz dQSy/pk0U404eOpwOzKyaS8NwsiHrfW6rOUVFy4Y= Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729500AbfDDIv5 (ORCPT ); Thu, 4 Apr 2019 04:51:57 -0400 Received: from mail.kernel.org ([198.145.29.99]:53872 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729494AbfDDIv4 (ORCPT ); Thu, 4 Apr 2019 04:51:56 -0400 Received: from localhost (83-86-89-107.cable.dynamic.v4.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id 3A10B217D4; Thu, 4 Apr 2019 08:51:55 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1554367915; bh=sdb6wbZKuO4yjNeksN4gUW26zb3h/1VB9ywLfTspJxM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=QRpRBS9aLHPLlfzvGbC9UfF2TMmAYHaQ3vd1C7k/Qvzd3HS8eu6NRD9ywjbTIdorx k7Bda3/ax86F+w2/gVrMhDURBeFz8vt0qR7lCwRa/ahzgKf5EdST4hftB2TyX29e9R c7maIacJ/TgHe74/oHCjiuJ0JWX1BSt814/0lEbc= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Waiman Long , Thomas Gleixner , Marc Zyngier , Davidlohr Bueso , Matthew Wilcox , Andrew Morton , Alexey Dobriyan , Kees Cook , linux-fsdevel@vger.kernel.org, Davidlohr Bueso , Miklos Szeredi , Daniel Colascione , Dave Chinner , Randy Dunlap , Sasha Levin Subject: [PATCH 4.9 61/91] genirq: Avoid summation loops for /proc/stat Date: Thu, 4 Apr 2019 10:47:45 +0200 Message-Id: <20190404084538.964954273@linuxfoundation.org> X-Mailer: git-send-email 2.21.0 In-Reply-To: <20190404084535.450029272@linuxfoundation.org> References: <20190404084535.450029272@linuxfoundation.org> User-Agent: quilt/0.65 X-stable: review X-Patchwork-Hint: ignore MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: stable-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: stable@vger.kernel.org 4.9-stable review patch. If anyone has any objections, please let me know. ------------------ [ Upstream commit 1136b0728969901a091f0471968b2b76ed14d9ad ] Waiman reported that on large systems with a large amount of interrupts the readout of /proc/stat takes a long time to sum up the interrupt statistics. In principle this is not a problem. but for unknown reasons some enterprise quality software reads /proc/stat with a high frequency. The reason for this is that interrupt statistics are accounted per cpu. So the /proc/stat logic has to sum up the interrupt stats for each interrupt. This can be largely avoided for interrupts which are not marked as 'PER_CPU' interrupts by simply adding a per interrupt summation counter which is incremented along with the per interrupt per cpu counter. The PER_CPU interrupts need to avoid that and use only per cpu accounting because they share the interrupt number and the interrupt descriptor and concurrent updates would conflict or require unwanted synchronization. Reported-by: Waiman Long Signed-off-by: Thomas Gleixner Reviewed-by: Waiman Long Reviewed-by: Marc Zyngier Reviewed-by: Davidlohr Bueso Cc: Matthew Wilcox Cc: Andrew Morton Cc: Alexey Dobriyan Cc: Kees Cook Cc: linux-fsdevel@vger.kernel.org Cc: Davidlohr Bueso Cc: Miklos Szeredi Cc: Daniel Colascione Cc: Dave Chinner Cc: Randy Dunlap Link: https://lkml.kernel.org/r/20190208135020.925487496@linutronix.de 8<------------- v2: Undo the unintentional layout change of struct irq_desc. include/linux/irqdesc.h | 1 + kernel/irq/chip.c | 12 ++++++++++-- kernel/irq/internals.h | 8 +++++++- kernel/irq/irqdesc.c | 7 ++++++- 4 files changed, 24 insertions(+), 4 deletions(-) Signed-off-by: Sasha Levin --- include/linux/irqdesc.h | 1 + kernel/irq/chip.c | 12 ++++++++++-- kernel/irq/internals.h | 8 +++++++- kernel/irq/irqdesc.c | 7 ++++++- 4 files changed, 24 insertions(+), 4 deletions(-) diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c9be57931b58..bb5547a83daf 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -61,6 +61,7 @@ struct irq_desc { unsigned int core_internal_state__do_not_mess_with_it; unsigned int depth; /* nested irq disables */ unsigned int wake_depth; /* nested wake enables */ + unsigned int tot_count; unsigned int irq_count; /* For detecting broken IRQs */ unsigned long last_unhandled; /* Aging timer for unhandled count */ unsigned int irqs_unhandled; diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index f30110e1b8c9..9e745cc0726d 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -729,7 +729,11 @@ void handle_percpu_irq(struct irq_desc *desc) { struct irq_chip *chip = irq_desc_get_chip(desc); - kstat_incr_irqs_this_cpu(desc); + /* + * PER CPU interrupts are not serialized. Do not touch + * desc->tot_count. + */ + __kstat_incr_irqs_this_cpu(desc); if (chip->irq_ack) chip->irq_ack(&desc->irq_data); @@ -758,7 +762,11 @@ void handle_percpu_devid_irq(struct irq_desc *desc) unsigned int irq = irq_desc_get_irq(desc); irqreturn_t res; - kstat_incr_irqs_this_cpu(desc); + /* + * PER CPU interrupts are not serialized. Do not touch + * desc->tot_count. + */ + __kstat_incr_irqs_this_cpu(desc); if (chip->irq_ack) chip->irq_ack(&desc->irq_data); diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index bc226e783bd2..22e3f29a30d8 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -199,12 +199,18 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) #undef __irqd_to_state -static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) +static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc) { __this_cpu_inc(*desc->kstat_irqs); __this_cpu_inc(kstat.irqs_sum); } +static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc) +{ + __kstat_incr_irqs_this_cpu(desc); + desc->tot_count++; +} + static inline int irq_desc_get_node(struct irq_desc *desc) { return irq_common_data_get_node(&desc->irq_common_data); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 77977f55dff7..5e0ea17d01a6 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -109,6 +109,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, desc->depth = 1; desc->irq_count = 0; desc->irqs_unhandled = 0; + desc->tot_count = 0; desc->name = NULL; desc->owner = owner; for_each_possible_cpu(cpu) @@ -880,11 +881,15 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); - int cpu; unsigned int sum = 0; + int cpu; if (!desc || !desc->kstat_irqs) return 0; + if (!irq_settings_is_per_cpu_devid(desc) && + !irq_settings_is_per_cpu(desc)) + return desc->tot_count; + for_each_possible_cpu(cpu) sum += *per_cpu_ptr(desc->kstat_irqs, cpu); return sum; -- 2.19.1