From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from m12-14.163.com ([220.181.12.14]:55469 "EHLO m12-14.163.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726189AbeIEKPX (ORCPT ); Wed, 5 Sep 2018 06:15:23 -0400 Subject: Re: Affinity managed interrupts vs non-managed interrupts To: Kashyap Desai , Thomas Gleixner Cc: Ming Lei , Sumit Saxena , Ming Lei , Christoph Hellwig , Linux Kernel Mailing List , Shivasharan Srikanteshwara , linux-block , Dou Liyang References: <20180829084618.GA24765@ming.t460p> <300d6fef733ca76ced581f8c6304bac6@mail.gmail.com> <615d78004495aebc53807156d04d988c@mail.gmail.com> <486f94a563d63c4779498fe8829a546c@mail.gmail.com> <602cee6381b9f435a938bbaf852d07f9@mail.gmail.com> <66256272c020be186becdd7a3f049302@mail.gmail.com> From: Dou Liyang Message-ID: Date: Wed, 5 Sep 2018 13:46:16 +0800 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Sender: linux-block-owner@vger.kernel.org List-Id: linux-block@vger.kernel.org Hi Thomas, Kashyap, At 09/04/2018 06:29 PM, Kashyap Desai wrote: >>> I am using " for-4.19/block " and this particular patch "a0c9259 >>> irq/matrix: Spread interrupts on allocation" is included. >> IMO, this patch is just used for non-managed interrupts. >> So if all 16 have their effective affinity set to CPU0 then that's > strange But, all these 16 are managed interrupts, and will be assigned vectors by assign_managed_vector(): { cpumask_and(vector_searchmask, vector_searchmask, affmsk); cpu = cpumask_first(vector_searchmask); ... vector = irq_matrix_alloc_managed(vector_matrix, cpu); ... } Where we always used the *first* cpu in the vector_searchmask(0-71), not the suitable one. So I guess this situation happened. Shall we also spread the managed interrupts on allocation? Thanks, dou -----------------8<---------------------------------------- diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..57dc05691f44 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -314,13 +314,12 @@ assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest) int vector, cpu; cpumask_and(vector_searchmask, vector_searchmask, affmsk); - cpu = cpumask_first(vector_searchmask); - if (cpu >= nr_cpu_ids) - return -EINVAL; + /* set_affinity might call here for nothing */ if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask)) return 0; - vector = irq_matrix_alloc_managed(vector_matrix, cpu); + + vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask, &cpu); trace_vector_alloc_managed(irqd->irq, vector, vector); if (vector < 0) return vector; diff --git a/include/linux/irq.h b/include/linux/irq.h index 201de12a9957..36fdeff5043a 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1151,7 +1151,8 @@ void irq_matrix_offline(struct irq_matrix *m); void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace); int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk); void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk); -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu); +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu); void irq_matrix_reserve(struct irq_matrix *m); void irq_matrix_remove_reserved(struct irq_matrix *m); int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 5092494bf261..d9e4e0a385fa 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -239,21 +239,40 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) * @m: Matrix pointer * @cpu: On which CPU the interrupt should be allocated */ -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu) +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu) { - struct cpumap *cm = per_cpu_ptr(m->maps, cpu); - unsigned int bit, end = m->alloc_end; - - /* Get managed bit which are not allocated */ - bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); - bit = find_first_bit(m->scratch_map, end); - if (bit >= end) - return -ENOSPC; - set_bit(bit, cm->alloc_map); - cm->allocated++; - m->total_allocated++; - trace_irq_matrix_alloc_managed(bit, cpu, m, cm); - return bit; + unsigned int cpu, best_cpu, maxavl = 0; + unsigned int bit, end; + struct cpumap *cm; + + best_cpu = UINT_MAX; + for_each_cpu(cpu, msk) { + cm = per_cpu_ptr(m->maps, cpu); + + if (!cm->online || cm->available <= maxavl) + continue; + + best_cpu = cpu; + maxavl = cm->available; + } + + if (maxavl) { + cm = per_cpu_ptr(m->maps, best_cpu); + end = m->alloc_end; + /* Get managed bit which are not allocated */ + bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); + bit = find_first_bit(m->scratch_map, end); + if (bit >= end) + return -ENOSPC; + set_bit(bit, cm->alloc_map); + cm->allocated++; + m->total_allocated++; + *mapped_cpu = best_cpu; + trace_irq_matrix_alloc_managed(bit, cpu, m, cm); + return bit; + } + return -ENOSPC; } /** 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=-0.7 required=3.0 tests=DKIM_SIGNED,DKIM_VALID, DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_PASS autolearn=ham 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 B16FCC433F5 for ; Wed, 5 Sep 2018 05:46:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 555DC2075E for ; Wed, 5 Sep 2018 05:46:57 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=163.com header.i=@163.com header.b="JplN6/HV" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 555DC2075E Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=163.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726447AbeIEKPX (ORCPT ); Wed, 5 Sep 2018 06:15:23 -0400 Received: from m12-14.163.com ([220.181.12.14]:55469 "EHLO m12-14.163.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726189AbeIEKPX (ORCPT ); Wed, 5 Sep 2018 06:15:23 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=163.com; s=s110527; h=Subject:From:Message-ID:Date:MIME-Version; bh=+G/6g aR2O8MJaBPRYUEBCCyUv0XxIMvwTKgxgdi9abo=; b=JplN6/HVMPyHbYCFcZkxd duTTvaOir6u1LZK0CfXJOT51AzkrpDTErRQIFBWCH0SDsPLG/s8FbaLJIvU3hh0q pbQVBYehGCv3cfxxsxFdXMTSE9NMRi4eI4YC0slTJvU3Jvnb8RyAHLCkNdZKn51j 1M15Y8kCNfI6VBskUI9ozw= Received: from localhost.localdomain (unknown [49.65.59.196]) by smtp10 (Coremail) with SMTP id DsCowABnptWpbY9bPrdaPw--.56241S2; Wed, 05 Sep 2018 13:46:17 +0800 (CST) Subject: Re: Affinity managed interrupts vs non-managed interrupts To: Kashyap Desai , Thomas Gleixner Cc: Ming Lei , Sumit Saxena , Ming Lei , Christoph Hellwig , Linux Kernel Mailing List , Shivasharan Srikanteshwara , linux-block , Dou Liyang References: <20180829084618.GA24765@ming.t460p> <300d6fef733ca76ced581f8c6304bac6@mail.gmail.com> <615d78004495aebc53807156d04d988c@mail.gmail.com> <486f94a563d63c4779498fe8829a546c@mail.gmail.com> <602cee6381b9f435a938bbaf852d07f9@mail.gmail.com> <66256272c020be186becdd7a3f049302@mail.gmail.com> From: Dou Liyang Message-ID: Date: Wed, 5 Sep 2018 13:46:16 +0800 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101 Thunderbird/52.5.2 MIME-Version: 1.0 In-Reply-To: Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit X-CM-TRANSID: DsCowABnptWpbY9bPrdaPw--.56241S2 X-Coremail-Antispam: 1Uf129KBjvJXoWxZF45XF1fZFyUArW7KF43trb_yoWrury8pF Z3Jr17uFWDJ3Wqgw17AayDAFZIy3s7Ar13t3s5u3sa9ryftr1IgF1qqFykZFyUArWrCayU CrZ0qryrZa4UJaUanT9S1TB71UUUUUUqnTZGkaVYY2UrUUUUjbIjqfuFe4nvWSU5nxnvy2 9KBjDUYxBIdaVFxhVjvjDU0xZFpf9x07bUgArUUUUU= X-Originating-IP: [49.65.59.196] X-CM-SenderInfo: pgrxszxl1d0wi6rwjhhfrp/1tbiLgm4olSIcI41IQAAsL Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Thomas, Kashyap, At 09/04/2018 06:29 PM, Kashyap Desai wrote: >>> I am using " for-4.19/block " and this particular patch "a0c9259 >>> irq/matrix: Spread interrupts on allocation" is included. >> IMO, this patch is just used for non-managed interrupts. >> So if all 16 have their effective affinity set to CPU0 then that's > strange But, all these 16 are managed interrupts, and will be assigned vectors by assign_managed_vector(): { cpumask_and(vector_searchmask, vector_searchmask, affmsk); cpu = cpumask_first(vector_searchmask); ... vector = irq_matrix_alloc_managed(vector_matrix, cpu); ... } Where we always used the *first* cpu in the vector_searchmask(0-71), not the suitable one. So I guess this situation happened. Shall we also spread the managed interrupts on allocation? Thanks, dou -----------------8<---------------------------------------- diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..57dc05691f44 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -314,13 +314,12 @@ assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest) int vector, cpu; cpumask_and(vector_searchmask, vector_searchmask, affmsk); - cpu = cpumask_first(vector_searchmask); - if (cpu >= nr_cpu_ids) - return -EINVAL; + /* set_affinity might call here for nothing */ if (apicd->vector && cpumask_test_cpu(apicd->cpu, vector_searchmask)) return 0; - vector = irq_matrix_alloc_managed(vector_matrix, cpu); + + vector = irq_matrix_alloc_managed(vector_matrix, vector_searchmask, &cpu); trace_vector_alloc_managed(irqd->irq, vector, vector); if (vector < 0) return vector; diff --git a/include/linux/irq.h b/include/linux/irq.h index 201de12a9957..36fdeff5043a 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -1151,7 +1151,8 @@ void irq_matrix_offline(struct irq_matrix *m); void irq_matrix_assign_system(struct irq_matrix *m, unsigned int bit, bool replace); int irq_matrix_reserve_managed(struct irq_matrix *m, const struct cpumask *msk); void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk); -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu); +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu); void irq_matrix_reserve(struct irq_matrix *m); void irq_matrix_remove_reserved(struct irq_matrix *m); int irq_matrix_alloc(struct irq_matrix *m, const struct cpumask *msk, diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 5092494bf261..d9e4e0a385fa 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -239,21 +239,40 @@ void irq_matrix_remove_managed(struct irq_matrix *m, const struct cpumask *msk) * @m: Matrix pointer * @cpu: On which CPU the interrupt should be allocated */ -int irq_matrix_alloc_managed(struct irq_matrix *m, unsigned int cpu) +int irq_matrix_alloc_managed(struct irq_matrix *m, const struct cpumask *msk, + unsigned int *mapped_cpu) { - struct cpumap *cm = per_cpu_ptr(m->maps, cpu); - unsigned int bit, end = m->alloc_end; - - /* Get managed bit which are not allocated */ - bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); - bit = find_first_bit(m->scratch_map, end); - if (bit >= end) - return -ENOSPC; - set_bit(bit, cm->alloc_map); - cm->allocated++; - m->total_allocated++; - trace_irq_matrix_alloc_managed(bit, cpu, m, cm); - return bit; + unsigned int cpu, best_cpu, maxavl = 0; + unsigned int bit, end; + struct cpumap *cm; + + best_cpu = UINT_MAX; + for_each_cpu(cpu, msk) { + cm = per_cpu_ptr(m->maps, cpu); + + if (!cm->online || cm->available <= maxavl) + continue; + + best_cpu = cpu; + maxavl = cm->available; + } + + if (maxavl) { + cm = per_cpu_ptr(m->maps, best_cpu); + end = m->alloc_end; + /* Get managed bit which are not allocated */ + bitmap_andnot(m->scratch_map, cm->managed_map, cm->alloc_map, end); + bit = find_first_bit(m->scratch_map, end); + if (bit >= end) + return -ENOSPC; + set_bit(bit, cm->alloc_map); + cm->allocated++; + m->total_allocated++; + *mapped_cpu = best_cpu; + trace_irq_matrix_alloc_managed(bit, cpu, m, cm); + return bit; + } + return -ENOSPC; } /**