From patchwork Wed Feb 15 14:54:18 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141772 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id E5E94C636CC for ; Wed, 15 Feb 2023 14:54:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229905AbjBOOy6 (ORCPT ); Wed, 15 Feb 2023 09:54:58 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50572 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230006AbjBOOyz (ORCPT ); Wed, 15 Feb 2023 09:54:55 -0500 Received: from mail-wr1-x42d.google.com (mail-wr1-x42d.google.com [IPv6:2a00:1450:4864:20::42d]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6E05539CC2 for ; Wed, 15 Feb 2023 06:54:31 -0800 (PST) Received: by mail-wr1-x42d.google.com with SMTP id a2so19440412wrd.6 for ; Wed, 15 Feb 2023 06:54:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=davZpZrHKqcK9/fGgGK/yHqe9BiOZs8yrjIgwy5MeSU=; b=5S3dXQ2q8rFnOsuNvry/KzR1D7Nr4TML7MUZ95MT7I+s/DI/sVyPytbPWT1SkdpEjP d3UC+1f6pWD4PtLrJAvr2jLC8hYzDyzpMEPA1OUED67bozktxRzSYAWKb4zvWebuAwj0 OoaJpq31a2148TSNqGXBe0orWUHSJhHptaISIHXMYjftSk6hApezB72heFNgsvyMAiDh gb1e2dXMysjKNzHSSDhCEFLOep8fHJxetIZzFc9FMZl2qU4prOYVmK2nJwHrBVetmpTx 0qbyIH6pdaZ6THJapfZiYBUouiqnCGztX/qKqPH0K1m91QQyxMfOghVGQUOpnywgDx5/ SKKA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=davZpZrHKqcK9/fGgGK/yHqe9BiOZs8yrjIgwy5MeSU=; b=PQLzEFyS3sUpcJoVQsJyKt9s1qTwssQqCHDttxeTTjngx9qfXp4NhOSi6eAyZgj+Il vzTAqPYhpq1HF9rVlzmmksmwIhjSxkQN83R1Ye1tCtO8kC5LQokjXDBJFbDLHu7Grj/F jZJ/6tapjcnpb/glrBWxwoUiV3fIu3R5CiEm1+v8B8JdtPLUFdbY/nHRH7uRhdpUPE1h YYlpCWWwdvLfAtnAb5H6FdMbelqKvjibB+B8KQlZrdMZ4LaByJsyVjWnR5LabYcXX6le jfKMIyvEJC7QSHF7ekQGv19k8Wzc/C+qDDbLDuqGQy1JWrlSw7kH9DYqnrIUyswvDs95 Txbg== X-Gm-Message-State: AO0yUKUT4x3XAAUDMRdGb2taxOWBu88YvSV5UFJS6HSKIw8ZhzWLcIWf 7B6IODq9tceR1USwRb3Jl1uatw== X-Google-Smtp-Source: AK7set9bmBlb+d8LePHD9fRGUiRQiTwi4t+2xvWZFzuYkMy7+BxsVk/DhQlYDoa4gn7i0lYsBf2kuQ== X-Received: by 2002:adf:e701:0:b0:2c5:5331:5516 with SMTP id c1-20020adfe701000000b002c553315516mr1952908wrm.51.1676472869918; Wed, 15 Feb 2023 06:54:29 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.29 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:29 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 1/8] x86/apic/x2apic: Allow CPU cluster_mask to be populated in parallel Date: Wed, 15 Feb 2023 14:54:18 +0000 Message-Id: <20230215145425.420125-2-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse Each of the sibling CPUs in a cluster uses the same clustermask. The first CPU in a cluster will need a new clustermask allocated, while subsequent siblings will use the same clustermask as the first. However, the CPU being brought up cannot yet perform memory allocations at the point that this occurs in init_x2apic_ldr(). So at present, the alloc_clustermask() function allocates a clustermask just in case it's needed, storing it in the global cluster_hotplug_mask. A CPU which is the first sibling of a cluster will "take" it from there and set cluster_hotplug_mask to NULL, in order for alloc_clustermask() to allocate a new one before bringing up the next CPU. To facilitate parallel bringup of CPUs in future, switch to a model where alloc_clustermask() prepopulates the clustermask in the per_cpu data for each present CPU in the cluster in advance. All that the CPU needs to do for itself in init_x2apic_ldr() is set its own bit in that mask. The 'node' and 'clusterid' members of struct cluster_mask are thus redundant, and it can become a simple struct cpumask instead. Suggested-by: Thomas Gleixner Signed-off-by: David Woodhouse Signed-off-by: Usama Arif Tested-by: Kim Phillips --- arch/x86/kernel/apic/x2apic_cluster.c | 130 +++++++++++++++++--------- 1 file changed, 84 insertions(+), 46 deletions(-) diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index e696e22d0531..d8f513a2287b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -9,11 +9,7 @@ #include "local.h" -struct cluster_mask { - unsigned int clusterid; - int node; - struct cpumask mask; -}; +#define apic_cluster(apicid) ((apicid) >> 4) /* * __x2apic_send_IPI_mask() possibly needs to read @@ -23,8 +19,7 @@ struct cluster_mask { static u32 *x86_cpu_to_logical_apicid __read_mostly; static DEFINE_PER_CPU(cpumask_var_t, ipi_mask); -static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks); -static struct cluster_mask *cluster_hotplug_mask; +static DEFINE_PER_CPU_READ_MOSTLY(struct cpumask *, cluster_masks); static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) { @@ -60,10 +55,10 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) /* Collapse cpus in a cluster so a single IPI per cluster is sent */ for_each_cpu(cpu, tmpmsk) { - struct cluster_mask *cmsk = per_cpu(cluster_masks, cpu); + struct cpumask *cmsk = per_cpu(cluster_masks, cpu); dest = 0; - for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask) + for_each_cpu_and(clustercpu, tmpmsk, cmsk) dest |= x86_cpu_to_logical_apicid[clustercpu]; if (!dest) @@ -71,7 +66,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); /* Remove cluster CPUs from tmpmask */ - cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask); + cpumask_andnot(tmpmsk, tmpmsk, cmsk); } local_irq_restore(flags); @@ -105,55 +100,98 @@ static u32 x2apic_calc_apicid(unsigned int cpu) static void init_x2apic_ldr(void) { - struct cluster_mask *cmsk = this_cpu_read(cluster_masks); - u32 cluster, apicid = apic_read(APIC_LDR); - unsigned int cpu; + struct cpumask *cmsk = this_cpu_read(cluster_masks); - x86_cpu_to_logical_apicid[smp_processor_id()] = apicid; + BUG_ON(!cmsk); - if (cmsk) - goto update; - - cluster = apicid >> 16; - for_each_online_cpu(cpu) { - cmsk = per_cpu(cluster_masks, cpu); - /* Matching cluster found. Link and update it. */ - if (cmsk && cmsk->clusterid == cluster) - goto update; + cpumask_set_cpu(smp_processor_id(), cmsk); +} + +/* + * As an optimisation during boot, set the cluster_mask for all present + * CPUs at once, to prevent each of them having to iterate over the others + * to find the existing cluster_mask. + */ +static void prefill_clustermask(struct cpumask *cmsk, unsigned int cpu, u32 cluster) +{ + int cpu_i; + + for_each_present_cpu(cpu_i) { + struct cpumask **cpu_cmsk = &per_cpu(cluster_masks, cpu_i); + u32 apicid = apic->cpu_present_to_apicid(cpu_i); + + if (apicid == BAD_APICID || cpu_i == cpu || apic_cluster(apicid) != cluster) + continue; + + if (WARN_ON_ONCE(*cpu_cmsk == cmsk)) + continue; + + BUG_ON(*cpu_cmsk); + *cpu_cmsk = cmsk; } - cmsk = cluster_hotplug_mask; - cmsk->clusterid = cluster; - cluster_hotplug_mask = NULL; -update: - this_cpu_write(cluster_masks, cmsk); - cpumask_set_cpu(smp_processor_id(), &cmsk->mask); } -static int alloc_clustermask(unsigned int cpu, int node) +static int alloc_clustermask(unsigned int cpu, u32 cluster, int node) { + struct cpumask *cmsk = NULL; + unsigned int cpu_i; + + /* + * At boot time, the CPU present mask is stable. The cluster mask is + * allocated for the first CPU in the cluster and propagated to all + * present siblings in the cluster. If the cluster mask is already set + * on entry to this function for a given CPU, there is nothing to do. + */ if (per_cpu(cluster_masks, cpu)) return 0; + + if (system_state < SYSTEM_RUNNING) + goto alloc; + /* - * If a hotplug spare mask exists, check whether it's on the right - * node. If not, free it and allocate a new one. + * On post boot hotplug for a CPU which was not present at boot time, + * iterate over all possible CPUs (even those which are not present + * any more) to find any existing cluster mask. */ - if (cluster_hotplug_mask) { - if (cluster_hotplug_mask->node == node) - return 0; - kfree(cluster_hotplug_mask); + for_each_possible_cpu(cpu_i) { + u32 apicid = apic->cpu_present_to_apicid(cpu_i); + + if (apicid != BAD_APICID && apic_cluster(apicid) == cluster) { + cmsk = per_cpu(cluster_masks, cpu_i); + /* + * If the cluster is already initialized, just store + * the mask and return. There's no need to propagate. + */ + if (cmsk) { + per_cpu(cluster_masks, cpu) = cmsk; + return 0; + } + } } - - cluster_hotplug_mask = kzalloc_node(sizeof(*cluster_hotplug_mask), - GFP_KERNEL, node); - if (!cluster_hotplug_mask) - return -ENOMEM; - cluster_hotplug_mask->node = node; - return 0; + /* + * No CPU in the cluster has ever been initialized, so fall through to + * the boot time code which will also populate the cluster mask for any + * other CPU in the cluster which is (now) present. + */ + alloc: + cmsk = kzalloc_node(sizeof(*cmsk), GFP_KERNEL, node); + if (!cmsk) + return -ENOMEM; + per_cpu(cluster_masks, cpu) = cmsk; + prefill_clustermask(cmsk, cpu, cluster); + + return 0; } static int x2apic_prepare_cpu(unsigned int cpu) { - if (alloc_clustermask(cpu, cpu_to_node(cpu)) < 0) + u32 phys_apicid = apic->cpu_present_to_apicid(cpu); + u32 cluster = apic_cluster(phys_apicid); + u32 logical_apicid = (cluster << 16) | (1 << (phys_apicid & 0xf)); + + x86_cpu_to_logical_apicid[cpu] = logical_apicid; + + if (alloc_clustermask(cpu, cluster, cpu_to_node(cpu)) < 0) return -ENOMEM; if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) return -ENOMEM; @@ -162,10 +200,10 @@ static int x2apic_prepare_cpu(unsigned int cpu) static int x2apic_dead_cpu(unsigned int dead_cpu) { - struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu); + struct cpumask *cmsk = per_cpu(cluster_masks, dead_cpu); if (cmsk) - cpumask_clear_cpu(dead_cpu, &cmsk->mask); + cpumask_clear_cpu(dead_cpu, cmsk); free_cpumask_var(per_cpu(ipi_mask, dead_cpu)); return 0; } From patchwork Wed Feb 15 14:54:19 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141773 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 661A2C636D4 for ; Wed, 15 Feb 2023 14:55:08 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229964AbjBOOzH (ORCPT ); Wed, 15 Feb 2023 09:55:07 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50670 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229963AbjBOOzB (ORCPT ); Wed, 15 Feb 2023 09:55:01 -0500 Received: from mail-wr1-x429.google.com (mail-wr1-x429.google.com [IPv6:2a00:1450:4864:20::429]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 59E7D39CCB for ; Wed, 15 Feb 2023 06:54:32 -0800 (PST) Received: by mail-wr1-x429.google.com with SMTP id bu23so19413196wrb.8 for ; Wed, 15 Feb 2023 06:54:32 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=XKydoXD7DOLwoETiq1rVpdNfhGCr3/VFLGt4p4rSeXA=; b=hceQhhwWr1f7FagWsyZzNcBZmbVIP5OsxIHYJcXaYD/J/Q7I26e/dUdp/xuuGbSkQJ Z1qGwNRkGt4p30gy8YpfDwILmLyxZrlBX3CqoFXhW43tR/dxW9GDDPsibinx4GROooJ6 a6+ZWH74IaiAVz2y8cQC+aCaZcHFQLiKSORlFpff73D24PLDeJqCV16qvlFJGrkDEbov AMZWZo413nAzLPloJj5ZR331G+o2Zx5YzVKTb7Z5q4MnJbG0HOeYJWqo7D2qTlV/TLTv eNvlpQ1C/saz9isQ7J0rdwzMfVDOeplNT4Gg3Ee2AqBJ58LccYbudMPLhF9tm2KFukOS xrbA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=XKydoXD7DOLwoETiq1rVpdNfhGCr3/VFLGt4p4rSeXA=; b=JHBjUF6wrdWRkGrlidZ5lhsyXDXRFUeYfS8L2VphlWLhy74xBsZuMImIMiVMJ1LTKY 9Y76bwrxE46ZspiVS9f3+87khEp55zvlD97MT8f1v7GEmzaakrZnSh9SwVijUiipSn2L P7ftww7MWpvBonk4cNoNO2KhekjHceIiWKNOmJONxLSpw9Ok/ikC1PI5oDt+Wg5K9HHP iV6UbQXAgDMeCAj+XuOaw1i97t9tOolrp75bVGS4DZxJR4CcZDJ1Mv+N+F3G2HX26fGE GTxJRdCNlKfcJqqnIIl1V9wqoOGFwK30S/6jS+sQaLul/g8/doiJW3TkEuoEf8WFpW64 /CHw== X-Gm-Message-State: AO0yUKUW4nn3w7Lg/1D8BfIuHsCUnJ8En3s/gKcBZYOWftgSc+3LS/bx XV9dpb1xZcSUMocKhgBdQI0nuw== X-Google-Smtp-Source: AK7set860Rew0tYEOZBESqpmpyGt2v7Hl1tSKNM8QidgJEbU+BU+JoCxhBj+fZDORe++V3Ea+1V2NQ== X-Received: by 2002:a5d:6448:0:b0:2c5:581d:5a1d with SMTP id d8-20020a5d6448000000b002c5581d5a1dmr1567680wrw.43.1676472870810; Wed, 15 Feb 2023 06:54:30 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.30 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:30 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 2/8] cpu/hotplug: Move idle_thread_get() to Date: Wed, 15 Feb 2023 14:54:19 +0000 Message-Id: <20230215145425.420125-3-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse Instead of relying purely on the special-case wrapper in bringup_cpu() to pass the idle thread to __cpu_up(), expose idle_thread_get() so that the architecture code can obtain it directly when necessary. This will be useful when the existing __cpu_up() is split into multiple phases, only *one* of which will actually need the idle thread. If the architecture code is to register its new pre-bringup states with the cpuhp core, having a special-case wrapper to pass extra arguments is non-trivial and it's easier just to let the arch register its function pointer to be invoked with the standard API. Signed-off-by: David Woodhouse Reviewed-by: Thomas Gleixner Signed-off-by: Usama Arif --- include/linux/smpboot.h | 7 +++++++ kernel/smpboot.h | 2 -- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index 9d1bc65d226c..3862addcaa34 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -5,6 +5,13 @@ #include struct task_struct; + +#ifdef CONFIG_GENERIC_SMP_IDLE_THREAD +struct task_struct *idle_thread_get(unsigned int cpu); +#else +static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; } +#endif + /* Cookie handed to the thread_fn*/ struct smpboot_thread_data; diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 34dd3d7ba40b..60c609318ad6 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -5,11 +5,9 @@ struct task_struct; #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD -struct task_struct *idle_thread_get(unsigned int cpu); void idle_thread_set_boot_cpu(void); void idle_threads_init(void); #else -static inline struct task_struct *idle_thread_get(unsigned int cpu) { return NULL; } static inline void idle_thread_set_boot_cpu(void) { } static inline void idle_threads_init(void) { } #endif From patchwork Wed Feb 15 14:54:20 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141774 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 782C6C636D4 for ; Wed, 15 Feb 2023 14:55:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229983AbjBOOzO (ORCPT ); Wed, 15 Feb 2023 09:55:14 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50780 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229982AbjBOOzD (ORCPT ); Wed, 15 Feb 2023 09:55:03 -0500 Received: from mail-wr1-x436.google.com (mail-wr1-x436.google.com [IPv6:2a00:1450:4864:20::436]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1222725E1D for ; Wed, 15 Feb 2023 06:54:33 -0800 (PST) Received: by mail-wr1-x436.google.com with SMTP id m10so10510640wrn.4 for ; Wed, 15 Feb 2023 06:54:32 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=mY6NeUci0HQtTva2v+94F98gv/kbTw7O8GGA4dBnL3M=; b=RzgS+FLM/ZL8EfiD58R96uvNKMjgwm5bOi7+7PQ6Or9lTaw3zgduGS+xE7dGQYaRTg ZLsokzslHP4JB2V75MY5w5uz3I/V4sBYyueQN3r7tX6afiAf1oolknGGJ7JKbWq+yr4S F0+BDpBTTNYWOscGMdfS2NZpmJzz+YOqlL6bfxfwSYNUBOxk5AOLIO6zvGlGXdx6SJ8H 0u0v8xs5CwpkIhQjii/IvLqbOD+VCdyr5q3wA+OZXD2J8wuG5xrjExM+JGfx+PfJIS5o M41oEbqizugfBb9LpBfN6U/nXl2PuECjf91IFv3mjiD02F3GhXC6hZ5YsD4LBB5RSrbQ V19g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=mY6NeUci0HQtTva2v+94F98gv/kbTw7O8GGA4dBnL3M=; b=BFhhcGDXc4cAJS3gFJN4DgqRqrDqdM4ZS/ZrTzMWsAepy6N6H2Ujfk3l5+796IqCP8 8qbb/7ponTHucdgX29TWDhxAakyfKz0rXF9RCkhUS7ajnktjxaT5U9DVsHglzUBL1rwR ve11E5z33wxh/IUqroeomF/C/HBVyvUNV34Sf+DkagAeQ7LAFBgAVGLFS05r77AoLspJ 5NU610TW/H5aGW5fre4OES8NeucUc6ePm80NuXyP9rMfJ4o/5pZCzKlLYV0w7vcq5w1A uJxuYajndncdTI31oKkGoc821gG6qi4dWnx0CYOgg/1rQUu192NhnGyHrnkWJ7RTnVln cAEg== X-Gm-Message-State: AO0yUKUkY8qHujACep5Kpmyaq/tz6oB03JFTDhkD248s4tHZFKvc3pe/ PBZnV+e8VS5Ce5c3tF2ylDrW7Q== X-Google-Smtp-Source: AK7set9JA78qRMULe2QrbC1nrpy5LUjWA9cEncQJHEpXFix3AdtBdJp8lkzIAacyOrl/O/BNpMEBZA== X-Received: by 2002:a5d:4bcd:0:b0:2c3:d707:7339 with SMTP id l13-20020a5d4bcd000000b002c3d7077339mr2478904wrt.6.1676472871636; Wed, 15 Feb 2023 06:54:31 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.30 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:31 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 3/8] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU Date: Wed, 15 Feb 2023 14:54:20 +0000 Message-Id: <20230215145425.420125-4-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse There is often significant latency in the early stages of CPU bringup, and time is wasted by waking each CPU (e.g. with SIPI/INIT/INIT on x86) and then waiting for it to respond before moving on to the next. Allow a platform to register a set of pre-bringup CPUHP states to which each CPU can be stepped in parallel, thus absorbing some of that latency. There is a subtlety here: even with an empty CPUHP_BP_PARALLEL_DYN step, this means that *all* CPUs are brought through the prepare states and to CPUHP_BP_PREPARE_DYN before any of them are taken to CPUHP_BRINGUP_CPU and then are allowed to run for themselves to CPUHP_ONLINE. So any combination of prepare/start calls which depend on A-B ordering for each CPU in turn, such as the X2APIC code which used to allocate a cluster mask 'just in case' and store it in a global variable in the prep stage, then potentially consume that preallocated structure from the AP and set the global pointer to NULL to be reallocated in CPUHP_X2APIC_PREPARE for the next CPU... would explode horribly. Any platform enabling the CPUHP_BP_PARALLEL_DYN steps must be reviewed and tested to ensure that such issues do not exist, and the existing behaviour of bringing CPUs to CPUHP_BP_PREPARE_DYN and then immediately to CPUHP_BRINGUP_CPU and CPUHP_ONLINE only one at a time does not change unless such a state is registered. Note that the new parallel stages do *not* yet bring each AP to the CPUHP_BRINGUP_CPU state at the same time, only to the new states which exist before it. The final loop in bringup_nonboot_cpus() is untouched, bringing each AP in turn from the final PARALLEL_DYN state (or all the way from CPUHP_OFFLINE) to CPUHP_BRINGUP_CPU and then waiting for that AP to do its own processing and reach CPUHP_ONLINE before releasing the next. Parallelising that part by bringing them all to CPUHP_BRINGUP_CPU and then waiting for them all is an exercise for the future. Signed-off-by: David Woodhouse Signed-off-by: Usama Arif --- include/linux/cpuhotplug.h | 2 ++ kernel/cpu.c | 31 +++++++++++++++++++++++++++++-- 2 files changed, 31 insertions(+), 2 deletions(-) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 6c6859bfc454..e5a73ae6ccc0 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -133,6 +133,8 @@ enum cpuhp_state { CPUHP_MIPS_SOC_PREPARE, CPUHP_BP_PREPARE_DYN, CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20, + CPUHP_BP_PARALLEL_DYN, + CPUHP_BP_PARALLEL_DYN_END = CPUHP_BP_PARALLEL_DYN + 4, CPUHP_BRINGUP_CPU, /* diff --git a/kernel/cpu.c b/kernel/cpu.c index 6c0a92ca6bb5..fffb0da61ccc 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1504,8 +1504,30 @@ int bringup_hibernate_cpu(unsigned int sleep_cpu) void bringup_nonboot_cpus(unsigned int setup_max_cpus) { + unsigned int n = setup_max_cpus - num_online_cpus(); unsigned int cpu; + /* + * An architecture may have registered parallel pre-bringup states to + * which each CPU may be brought in parallel. For each such state, + * bring N CPUs to it in turn before the final round of bringing them + * online. + */ + if (n > 0) { + enum cpuhp_state st = CPUHP_BP_PARALLEL_DYN; + + while (st <= CPUHP_BP_PARALLEL_DYN_END && cpuhp_hp_states[st].name) { + int i = n; + + for_each_present_cpu(cpu) { + cpu_up(cpu, st); + if (!--i) + break; + } + st++; + } + } + for_each_present_cpu(cpu) { if (num_online_cpus() >= setup_max_cpus) break; @@ -1882,6 +1904,10 @@ static int cpuhp_reserve_state(enum cpuhp_state state) step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; + case CPUHP_BP_PARALLEL_DYN: + step = cpuhp_hp_states + CPUHP_BP_PARALLEL_DYN; + end = CPUHP_BP_PARALLEL_DYN_END; + break; default: return -EINVAL; } @@ -1906,14 +1932,15 @@ static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, /* * If name is NULL, then the state gets removed. * - * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on + * CPUHP_AP_ONLINE_DYN and CPUHP_BP_P*_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || - state == CPUHP_BP_PREPARE_DYN)) { + state == CPUHP_BP_PREPARE_DYN || + state == CPUHP_BP_PARALLEL_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; From patchwork Wed Feb 15 14:54:21 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141770 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BAFCBC636CC for ; Wed, 15 Feb 2023 14:54:43 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229952AbjBOOyn (ORCPT ); Wed, 15 Feb 2023 09:54:43 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50870 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229935AbjBOOyl (ORCPT ); Wed, 15 Feb 2023 09:54:41 -0500 Received: from mail-wr1-x433.google.com (mail-wr1-x433.google.com [IPv6:2a00:1450:4864:20::433]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E97E339CE7 for ; Wed, 15 Feb 2023 06:54:33 -0800 (PST) Received: by mail-wr1-x433.google.com with SMTP id y1so19446429wru.2 for ; Wed, 15 Feb 2023 06:54:33 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=L+woZryxcmbb99mupmnna5okozeg16DDHF5Mj8G3upM=; b=JRokBhNiWe7Y/h+u2FZ5CkBubYME683ey0UWpdaSILNGaAsASJ37C/R5IanD/HbmRR +hzGlun4CtH+CBtRYw4rDmLhVCRRZmmEU189H4VM6PaX095JhUN+KU8JTcWsajctBZhp /kqS/YbNGo4EpKnZkXYuuwRmOJh/H7jVem17DGVyRH5SJ3ZrTi3f8ZesZE8DtaaEnD2C e9r/uSW7LW6FskT3FkHiDoDPBX9EWmhTlmBnU0jc8S0bBuGMoPoCxzA2Bb1jUnMbQ/ri IpDtTVMkB62W/cjYHnMZnxFqyiadZS+iGFxlbd2g01Esy0uuZRkaVEV8uNsx5JhmYbHX bXpg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=L+woZryxcmbb99mupmnna5okozeg16DDHF5Mj8G3upM=; b=3HFcFGUHz+9MV3Dchzu6EunpVoEIczV8KGRTUsvgB4q8Ksl/OR+fquP+RLqRaRTJa9 AGixI49gq/gwkiYEHuKef90sPPkrBVHEsmLJp/0MNIUeW3+oNecO2VtPdb8o4fVjoz2d GEaPlcwf4dykVoiOsmz4YQ3qsuJI7/czgX/25kfMvtwDWThb7FejCrLl3K34epE4S6iu oVAxXRQMzk1Rg7I0/71nM9UDjK44kcbjg/7k1cYCFu1ZdaS4r4ndvpOefrDKjqT1L7jr jxtVDdIe6Bkqe7zYW5X217bmtK1mTVVHmE5K8ZJOJe0/wjd4USASvUw9OAjUN7DpszXs JtoA== X-Gm-Message-State: AO0yUKWrx5UDM4xtF5GYoaJ4mGbC0TnqLLYze9s3m5Jfq4lGr0WCuY6X KvPPqA6qSeTC2o7DZgIqAttfNg== X-Google-Smtp-Source: AK7set9BrBnpCstfUCDx0aGuY3lcnvjud1haFt2Wp+nw387jfta4pX5lyCMoer1YCoUD3YYnbZHy9w== X-Received: by 2002:a5d:4d87:0:b0:2c5:585e:334f with SMTP id b7-20020a5d4d87000000b002c5585e334fmr1780837wru.41.1676472872371; Wed, 15 Feb 2023 06:54:32 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.31 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:32 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 4/8] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector() Date: Wed, 15 Feb 2023 14:54:21 +0000 Message-Id: <20230215145425.420125-5-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse When bringing up a secondary CPU from do_boot_cpu(), the warm reset flag is set in CMOS and the starting IP for the trampoline written inside the BDA at 0x467. Once the CPU is running, the CMOS flag is unset and the value in the BDA cleared. To allow for parallel bringup of CPUs, add a reference count to track the number of CPUs currently bring brought up, and clear the state only when the count reaches zero. Since the RTC spinlock is required to write to the CMOS, it can be used for mutual exclusion on the refcount too. [Usama Arif: fixed rebase conflict] Signed-off-by: David Woodhouse Signed-off-by: Usama Arif --- arch/x86/kernel/smpboot.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 55cad72715d9..3a793772a2aa 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -121,17 +121,20 @@ int arch_update_cpu_topology(void) return retval; } + +static unsigned int smpboot_warm_reset_vector_count; + static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip) { unsigned long flags; spin_lock_irqsave(&rtc_lock, flags); - CMOS_WRITE(0xa, 0xf); + if (!smpboot_warm_reset_vector_count++) { + CMOS_WRITE(0xa, 0xf); + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = start_eip >> 4; + *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = start_eip & 0xf; + } spin_unlock_irqrestore(&rtc_lock, flags); - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) = - start_eip >> 4; - *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = - start_eip & 0xf; } static inline void smpboot_restore_warm_reset_vector(void) @@ -143,10 +146,12 @@ static inline void smpboot_restore_warm_reset_vector(void) * to default values. */ spin_lock_irqsave(&rtc_lock, flags); - CMOS_WRITE(0, 0xf); + if (!--smpboot_warm_reset_vector_count) { + CMOS_WRITE(0, 0xf); + *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; + } spin_unlock_irqrestore(&rtc_lock, flags); - *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } /* From patchwork Wed Feb 15 14:54:22 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141775 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 3CFF9C636CC for ; Wed, 15 Feb 2023 14:55:22 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230041AbjBOOzV (ORCPT ); Wed, 15 Feb 2023 09:55:21 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50786 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230012AbjBOOzJ (ORCPT ); Wed, 15 Feb 2023 09:55:09 -0500 Received: from mail-wr1-x431.google.com (mail-wr1-x431.google.com [IPv6:2a00:1450:4864:20::431]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E02C539CF3 for ; Wed, 15 Feb 2023 06:54:34 -0800 (PST) Received: by mail-wr1-x431.google.com with SMTP id bu23so19413349wrb.8 for ; Wed, 15 Feb 2023 06:54:34 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=70igdMRKSd94d/Z6B4nTp+zZijhDvqltjmxokObwWsg=; b=FIYX26hYdC4Canft7asdw/ZKDCs3E4unayM6vaxc03lSTi/234IVda89sWkl2vwNCM FkZe/kJbnmtPpwO/g6Cfhy6vdi5CkMAc399pfIYjyk37qH9GTrJPI7wQers+W3UG7kub LayzZEejTKhwVuOlzo+n3KMAQAvbr1vktBcdRoG4pg5PftQJzoStL8GRSueHqgKXN51b AZCVFbsCmBAAGs9RGwpLwDkgejON2m91F5Mng3uC3we8HrVfA/wPLfsYnuk+z3gLYsJB UPpO75p3kUhaMybjrxnwa2MtPt1RuMKf6ty/9/VxToUORDeIhkMDWeL5PKl+pNfZZBh9 c3Og== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=70igdMRKSd94d/Z6B4nTp+zZijhDvqltjmxokObwWsg=; b=u0FoQHq+UatgFrd42bm7L0hudkDtUm1ODLheOtwIrFcFL1XzM5W6/R7h8X5q4Hb9HD D4WPNNHltrhe9pM8ZihhhR5i1YSzvYGEEX0IsMi0msPK03gheWA9YASa4E0XFoCY6ulS IDfdbnBFUBD5O07RSehMBKh5lyHuBV8iZYp4ZkkVmaZNHkZ9jl8Y5JccDsNLEZz05nWu SUey+KmH2u5FFSOs3lG8dDwDXoRcremgqv/NNgQ4Z3CFZHatJBEHN2mfuoX0ojf0SJp0 GQllUHiPjx3fE4FtBTKCRLVOxTONDwss4MrtTD3r6pV2Jrj4nXuujikIvY469FjYSZmr u2LA== X-Gm-Message-State: AO0yUKUIa2/xrF3YQSNrfWeUJzEf7ApatM4lzqyUsdiQinzlCnOSbwC0 tHM87q7upP6bjVPVfXg+SaAn2A== X-Google-Smtp-Source: AK7set8q8yPL4jxnrzcQ2h2n270P/IYspRtW5mx1+YLhI/BFKoYyzQp2AEEOs63odWD+zZqCs5AqaQ== X-Received: by 2002:a5d:4d11:0:b0:2c3:d83a:113a with SMTP id z17-20020a5d4d11000000b002c3d83a113amr2284661wrt.4.1676472873331; Wed, 15 Feb 2023 06:54:33 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.32 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:32 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 5/8] x86/smpboot: Split up native_cpu_up into separate phases and document them Date: Wed, 15 Feb 2023 14:54:22 +0000 Message-Id: <20230215145425.420125-6-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse There are four logical parts to what native_cpu_up() does on the BSP (or on the controlling CPU for a later hotplug): 1) Wake the AP by sending the INIT/SIPI/SIPI sequence. 2) Wait for the AP to make it as far as wait_for_master_cpu() which sets that CPU's bit in cpu_initialized_mask, then sets the bit in cpu_callout_mask to let the AP proceed through cpu_init(). 3) Wait for the AP to finish cpu_init() and get as far as the smp_callin() call, which sets that CPU's bit in cpu_callin_mask. 4) Perform the TSC synchronization and wait for the AP to actually mark itself online in cpu_online_mask. In preparation to allow these phases to operate in parallel on multiple APs, split them out into separate functions and document the interactions a little more clearly in both the BSP and AP code paths. No functional change intended. [Usama Arif: fixed rebase conflict] Signed-off-by: David Woodhouse Signed-off-by: Usama Arif --- arch/x86/kernel/smpboot.c | 181 ++++++++++++++++++++++++++------------ 1 file changed, 127 insertions(+), 54 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 3a793772a2aa..b9366f86c433 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -204,6 +204,10 @@ static void smp_callin(void) wmb(); + /* + * This runs the AP through all the cpuhp states to its target + * state (CPUHP_ONLINE in the case of serial bringup). + */ notify_cpu_starting(cpuid); /* @@ -231,17 +235,32 @@ static void notrace start_secondary(void *unused) load_cr3(swapper_pg_dir); __flush_tlb_all(); #endif + /* + * Sync point with do_wait_cpu_initialized(). Before proceeding through + * cpu_init(), the AP will call wait_for_master_cpu() which sets its + * own bit in cpu_initialized_mask and then waits for the BSP to set + * its bit bit in cpu_callout_mask to release it. + */ cpu_init_secondary(); rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); + + /* + * Sync point with do_wait_cpu_callin(). The AP doesn't wait here + * but just sets the bit to let the controlling CPU (BSP) know that + * it's got this far. + */ smp_callin(); enable_start_cpu0 = 0; /* otherwise gcc will move up smp_processor_id before the cpu_init */ barrier(); + /* - * Check TSC synchronization with the boot CPU: + * Check TSC synchronization with the boot CPU (or whichever CPU + * is controlling the bringup). It will do its part of this from + * do_wait_cpu_online(), making it an implicit sync point. */ check_tsc_sync_target(); @@ -254,6 +273,7 @@ static void notrace start_secondary(void *unused) * half valid vector space. */ lock_vector_lock(); + /* Sync point with do_wait_cpu_online() */ set_cpu_online(smp_processor_id(), true); lapic_online(); unlock_vector_lock(); @@ -1083,7 +1103,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, unsigned long start_ip = real_mode_header->trampoline_start; unsigned long boot_error = 0; - unsigned long timeout; #ifdef CONFIG_X86_64 /* If 64-bit wakeup method exists, use the 64-bit mode trampoline IP */ @@ -1144,55 +1163,94 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, boot_error = wakeup_cpu_via_init_nmi(cpu, start_ip, apicid, cpu0_nmi_registered); - if (!boot_error) { - /* - * Wait 10s total for first sign of life from AP - */ - boot_error = -1; - timeout = jiffies + 10*HZ; - while (time_before(jiffies, timeout)) { - if (cpumask_test_cpu(cpu, cpu_initialized_mask)) { - /* - * Tell AP to proceed with initialization - */ - cpumask_set_cpu(cpu, cpu_callout_mask); - boot_error = 0; - break; - } - schedule(); - } - } + return boot_error; +} - if (!boot_error) { - /* - * Wait till AP completes initial initialization - */ - while (!cpumask_test_cpu(cpu, cpu_callin_mask)) { - /* - * Allow other tasks to run while we wait for the - * AP to come online. This also gives a chance - * for the MTRR work(triggered by the AP coming online) - * to be completed in the stop machine context. - */ - schedule(); - } +static int do_wait_cpu_cpumask(unsigned int cpu, const struct cpumask *mask) +{ + unsigned long timeout; + + /* + * Wait up to 10s for the CPU to report in. + */ + timeout = jiffies + 10*HZ; + while (time_before(jiffies, timeout)) { + if (cpumask_test_cpu(cpu, mask)) + return 0; + + schedule(); } + return -1; +} - if (x86_platform.legacy.warm_reset) { - /* - * Cleanup possible dangling ends... - */ - smpboot_restore_warm_reset_vector(); +/* + * Bringup step two: Wait for the target AP to reach cpu_init_secondary() + * and thus wait_for_master_cpu(), then set cpu_callout_mask to allow it + * to proceed. The AP will then proceed past setting its 'callin' bit + * and end up waiting in check_tsc_sync_target() until we reach + * do_wait_cpu_online() to tend to it. + */ +static int do_wait_cpu_initialized(unsigned int cpu) +{ + /* + * Wait for first sign of life from AP. + */ + if (do_wait_cpu_cpumask(cpu, cpu_initialized_mask)) + return -1; + + cpumask_set_cpu(cpu, cpu_callout_mask); + return 0; +} + +/* + * Bringup step three: Wait for the target AP to reach smp_callin(). + * The AP is not waiting for us here so we don't need to parallelise + * this step. Not entirely clear why we care about this, since we just + * proceed directly to TSC synchronization which is the next sync + * point with the AP anyway. + */ +static int do_wait_cpu_callin(unsigned int cpu) +{ + /* + * Wait till AP completes initial initialization. + */ + return do_wait_cpu_cpumask(cpu, cpu_callin_mask); +} + +/* + * Bringup step four: Synchronize the TSC and wait for the target AP + * to reach set_cpu_online() in start_secondary(). + */ +static int do_wait_cpu_online(unsigned int cpu) +{ + unsigned long flags; + + /* + * Check TSC synchronization with the AP (keep irqs disabled + * while doing so): + */ + local_irq_save(flags); + check_tsc_sync_source(cpu); + local_irq_restore(flags); + + /* + * Wait for the AP to mark itself online. Not entirely + * clear why we care, since the generic cpuhp code will + * wait for it to each CPUHP_AP_ONLINE_IDLE before going + * ahead with the rest of the bringup anyway. + */ + while (!cpu_online(cpu)) { + cpu_relax(); + touch_nmi_watchdog(); } - return boot_error; + return 0; } -int native_cpu_up(unsigned int cpu, struct task_struct *tidle) +static int do_cpu_up(unsigned int cpu, struct task_struct *tidle) { int apicid = apic->cpu_present_to_apicid(cpu); int cpu0_nmi_registered = 0; - unsigned long flags; int err, ret = 0; lockdep_assert_irqs_enabled(); @@ -1239,19 +1297,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) goto unreg_nmi; } - /* - * Check TSC synchronization with the AP (keep irqs disabled - * while doing so): - */ - local_irq_save(flags); - check_tsc_sync_source(cpu); - local_irq_restore(flags); - - while (!cpu_online(cpu)) { - cpu_relax(); - touch_nmi_watchdog(); - } - unreg_nmi: /* * Clean up the nmi handler. Do this after the callin and callout sync @@ -1263,6 +1308,34 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) return ret; } +int native_cpu_up(unsigned int cpu, struct task_struct *tidle) +{ + int ret; + + ret = do_cpu_up(cpu, tidle); + if (ret) + return ret; + + ret = do_wait_cpu_initialized(cpu); + if (ret) + return ret; + + ret = do_wait_cpu_callin(cpu); + if (ret) + return ret; + + ret = do_wait_cpu_online(cpu); + + if (x86_platform.legacy.warm_reset) { + /* + * Cleanup possible dangling ends... + */ + smpboot_restore_warm_reset_vector(); + } + + return ret; +} + /** * arch_disable_smp_support() - disables SMP support for x86 at runtime */ From patchwork Wed Feb 15 14:54:23 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141771 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 23E7AC636D7 for ; Wed, 15 Feb 2023 14:54:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229951AbjBOOyq (ORCPT ); Wed, 15 Feb 2023 09:54:46 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50974 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229948AbjBOOyp (ORCPT ); Wed, 15 Feb 2023 09:54:45 -0500 Received: from mail-wr1-x42c.google.com (mail-wr1-x42c.google.com [IPv6:2a00:1450:4864:20::42c]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E002439BA7 for ; Wed, 15 Feb 2023 06:54:35 -0800 (PST) Received: by mail-wr1-x42c.google.com with SMTP id a2so19440658wrd.6 for ; Wed, 15 Feb 2023 06:54:35 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=Th2e52Ts8GBThcPpakljZ9Li92MFnHMTVi+rZRm810w=; b=QU+oHa7g5LJjD2df5X41sBMZSkYRLCTyrt/PfEtr5DlN3KX0bii+o8MgMXvQ0dzxOC lu8ZLMknp7lBArQ8s5MhtwbSzh6lOsvDBVzuNP6lQACTGhZb7vjHlkCYAI4pASTO253u UKmFRfQR6AKYV9h/j1kdcBnYk5lIIhAmyNXZtUq4LQiwzcWgpgkF5zJSHN2oLvohfCZv MIwCISvgnJ3+0eG3e+6eJ8T2zq1K+CCGem8WtrVn//+Mw+uQuNL/0v/ejQxviOdXv8U1 hrCNVuDPNx6g/ut1X8LPSaVq3ZVgn6u86zo6fjvLR4Qv852MIdKGAXeM6I8gvBC/Nmjz B2lg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Th2e52Ts8GBThcPpakljZ9Li92MFnHMTVi+rZRm810w=; b=g+xEUbEYXjplwqTRVhYL9lvfwYzfRGQhspwjZKm6UMdOKUkpYrMQLHlZk1nFmrdT3D XT2qmDGz48ytCEhRo1E1avh5C5itHMn8PTUo/AW1LVKC3ywKtHHMsOts8QdVgpNm6HPF fvkuSlEY01qBmKGPi7L4uPEv8fYcUfT80gGsNHTIeWnq+00WwWiq6572n9p/YMLCryrP rQ4Q2eq+lgFZnZSo+rfphXFWSXSlX5QncxzrsNv7Nzw9NKtk1ZPKodYFL4FW8fgUPsoU Yn0FDWQIYKt+rw0HIDJ3HCifqfJ+t1l1tyvNsV6Fz8maP+lkNRhH6b926jxjUF+buzm7 YNZw== X-Gm-Message-State: AO0yUKXVvahA2/mtNIHN3s37I3/9SPAd9+B24oN2GmQRRMRtAcTSGMYn /keM0SOjnrdfEBxet0KQ9nCM9Q== X-Google-Smtp-Source: AK7set/fY0xUlnvh1mfQLLs8/gPsHqtxGovqpg57Ta9RzVlYrwzaKK3e8nsM0CLVJ4tlAmPfEy+fiw== X-Received: by 2002:a05:6000:1182:b0:2c3:f812:1cad with SMTP id g2-20020a056000118200b002c3f8121cadmr1732845wrx.37.1676472874283; Wed, 15 Feb 2023 06:54:34 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.33 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:33 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 6/8] x86/smpboot: Support parallel startup of secondary CPUs Date: Wed, 15 Feb 2023 14:54:23 +0000 Message-Id: <20230215145425.420125-7-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse Rework the real-mode startup code to allow for APs to be brought up in parallel. This is in two parts: 1. Introduce a bit-spinlock to prevent them from all using the real mode stack at the same time. 2. Avoid the use of global variables for passing per-CPU information to the APs. To achieve the latter, export the cpuid_to_apicid[] array so that each AP can find its own per_cpu data (and thus initial_gs, initial_stack and early_gdt_descr) by searching therein based on its APIC ID. Introduce a global variable 'smpboot_control' indicating to the AP how it should find its APIC ID. For a serialized bringup, the APIC ID is explicitly passed in the low bits of smpboot_control, while for parallel mode there are flags directing the AP to find its APIC ID in CPUID leaf 0x0b (for X2APIC mode) or CPUID leaf 0x01 where 8 bits are sufficient. Parallel startup may be disabled by a command line option, and also if: • AMD SEV-ES is in use, since the AP may not use CPUID that early. • X2APIC is enabled, but CPUID leaf 0xb is not present and correect. • X2APIC is not enabled but not even CPUID leaf 0x01 exists. Aside from the fact that APs will now look up their per-cpu data via the newly-exported cpuid_to_apicid[] table, there is no behavioural change intended yet, since new parallel CPUHP states have not — yet — been added. [ tglx: Initial proof of concept patch with bitlock and APIC ID lookup ] [ dwmw2: Rework and testing, commit message, CPUID 0x1 and CPU0 support ] [ seanc: Fix stray override of initial_gs in common_cpu_up() ] Co-developed-by: Thomas Gleixner Signed-off-by: Thomas Gleixner Signed-off-by: David Woodhouse Signed-off-by: Usama Arif --- .../admin-guide/kernel-parameters.txt | 3 + arch/x86/include/asm/realmode.h | 3 + arch/x86/include/asm/smp.h | 10 +- arch/x86/kernel/acpi/sleep.c | 1 + arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/head_64.S | 99 ++++++++++++++++++- arch/x86/kernel/smpboot.c | 62 +++++++++++- arch/x86/realmode/init.c | 3 + arch/x86/realmode/rm/trampoline_64.S | 14 +++ kernel/smpboot.c | 2 +- 10 files changed, 191 insertions(+), 8 deletions(-) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 6cfa6e3996cf..ee099b8aac6d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3819,6 +3819,9 @@ nomodule Disable module load + no_parallel_bringup + [X86,SMP] Disable parallel brinugp of secondary cores. + nopat [X86] Disable PAT (page attribute table extension of pagetables) support. diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index a336feef0af1..f0357cfe2fb0 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -52,6 +52,7 @@ struct trampoline_header { u64 efer; u32 cr4; u32 flags; + u32 lock; #endif }; @@ -65,6 +66,8 @@ extern unsigned long initial_stack; extern unsigned long initial_vc_handler; #endif +extern u32 *trampoline_lock; + extern unsigned char real_mode_blob[]; extern unsigned char real_mode_relocs[]; diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index b4dbb20dab1a..33c0d5fd8af6 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -199,5 +199,13 @@ extern void nmi_selftest(void); #define nmi_selftest() do { } while (0) #endif -#endif /* __ASSEMBLY__ */ +extern unsigned int smpboot_control; + +#endif /* !__ASSEMBLY__ */ + +/* Control bits for startup_64 */ +#define STARTUP_SECONDARY 0x80000000 +#define STARTUP_APICID_CPUID_0B 0x40000000 +#define STARTUP_APICID_CPUID_01 0x20000000 + #endif /* _ASM_X86_SMP_H */ diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 3b7f4cdbf2e0..06adf340a0f1 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -115,6 +115,7 @@ int x86_acpi_suspend_lowlevel(void) early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(smp_processor_id()); initial_gs = per_cpu_offset(smp_processor_id()); + smpboot_control = 0; #endif initial_code = (unsigned long)wakeup_long64; saved_magic = 0x123456789abcdef0L; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 20d9a604da7c..ac1d7e5da1f2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2377,7 +2377,7 @@ static int nr_logical_cpuids = 1; /* * Used to store mapping between logical CPU IDs and APIC IDs. */ -static int cpuid_to_apicid[] = { +int cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = -1, }; diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 222efd4a09bc..0e4e53d231db 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -25,6 +25,7 @@ #include #include #include +#include /* * We are not able to switch in one step to the final KERNEL ADDRESS SPACE @@ -241,6 +242,83 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) UNWIND_HINT_EMPTY ANNOTATE_NOENDBR // above +#ifdef CONFIG_SMP + /* + * Is this the boot CPU coming up? If so everything is available + * in initial_gs, initial_stack and early_gdt_descr. + */ + movl smpboot_control(%rip), %edx + testl $STARTUP_SECONDARY, %edx + jz .Lsetup_cpu + + /* + * Secondary CPUs find out the offsets via the APIC ID. For parallel + * boot the APIC ID is retrieved from CPUID, otherwise it's encoded + * in smpboot_control: + * Bit 31 STARTUP_SECONDARY flag (checked above) + * Bit 30 STARTUP_APICID_CPUID_0B flag (use CPUID 0x0b) + * Bit 29 STARTUP_APICID_CPUID_01 flag (use CPUID 0x01) + * Bit 0-24 APIC ID if STARTUP_APICID_CPUID_xx flags are not set + */ + testl $STARTUP_APICID_CPUID_0B, %edx + jnz .Luse_cpuid_0b + testl $STARTUP_APICID_CPUID_01, %edx + jnz .Luse_cpuid_01 + andl $0x0FFFFFFF, %edx + jmp .Lsetup_AP + +.Luse_cpuid_01: + mov $0x01, %eax + cpuid + mov %ebx, %edx + shr $24, %edx + jmp .Lsetup_AP + +.Luse_cpuid_0b: + mov $0x0B, %eax + xorl %ecx, %ecx + cpuid + +.Lsetup_AP: + /* EDX contains the APIC ID of the current CPU */ + xorq %rcx, %rcx + leaq cpuid_to_apicid(%rip), %rbx + +.Lfind_cpunr: + cmpl (%rbx,%rcx,4), %edx + jz .Linit_cpu_data + inc %ecx + cmpl nr_cpu_ids(%rip), %ecx + jb .Lfind_cpunr + + /* APIC ID not found in the table. Drop the trampoline lock and bail. */ + movq trampoline_lock(%rip), %rax + lock + btrl $0, (%rax) + +1: cli + hlt + jmp 1b + +.Linit_cpu_data: + /* Get the per cpu offset for the given CPU# which is in ECX */ + leaq __per_cpu_offset(%rip), %rbx + movq (%rbx,%rcx,8), %rbx + /* Save it for GS BASE setup */ + movq %rbx, initial_gs(%rip) + + /* Calculate the GDT address */ + movq $gdt_page, %rcx + addq %rbx, %rcx + movq %rcx, early_gdt_descr_base(%rip) + + /* Find the idle task stack */ + movq idle_threads(%rbx), %rcx + movq TASK_threadsp(%rcx), %rcx + movq %rcx, initial_stack(%rip) +#endif /* CONFIG_SMP */ + +.Lsetup_cpu: /* * We must switch to a new descriptor in kernel space for the GDT * because soon the kernel won't have access anymore to the userspace @@ -281,6 +359,14 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) */ movq initial_stack(%rip), %rsp + /* Drop the realmode protection. For the boot CPU the pointer is NULL! */ + movq trampoline_lock(%rip), %rax + testq %rax, %rax + jz .Lsetup_idt + lock + btrl $0, (%rax) + +.Lsetup_idt: /* Setup and Load IDT */ pushq %rsi call early_setup_idt @@ -372,7 +458,14 @@ SYM_CODE_END(secondary_startup_64) SYM_CODE_START(start_cpu0) ANNOTATE_NOENDBR UNWIND_HINT_EMPTY - movq initial_stack(%rip), %rsp + /* Load the per-cpu base for CPU#0 */ + leaq __per_cpu_offset(%rip), %rbx + movq (%rbx), %rbx + + /* Find the idle task stack */ + movq idle_threads(%rbx), %rcx + movq TASK_threadsp(%rcx), %rsp + jmp .Ljump_to_C_code SYM_CODE_END(start_cpu0) #endif @@ -426,6 +519,7 @@ SYM_DATA(initial_vc_handler, .quad handle_vc_boot_ghcb) * reliably detect the end of the stack. */ SYM_DATA(initial_stack, .quad init_thread_union + THREAD_SIZE - FRAME_SIZE) +SYM_DATA(trampoline_lock, .quad 0); __FINITDATA __INIT @@ -660,6 +754,9 @@ SYM_DATA_END(level1_fixmap_pgt) SYM_DATA(early_gdt_descr, .word GDT_ENTRIES*8-1) SYM_DATA_LOCAL(early_gdt_descr_base, .quad INIT_PER_CPU_VAR(gdt_page)) + .align 16 +SYM_DATA(smpboot_control, .long 0) + .align 16 /* This must match the first entry in level2_kernel_pgt */ SYM_DATA(phys_base, .quad 0x0) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b9366f86c433..49d6563e4c23 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -797,6 +797,16 @@ static int __init cpu_init_udelay(char *str) } early_param("cpu_init_udelay", cpu_init_udelay); +static bool do_parallel_bringup __ro_after_init = true; + +static int __init no_parallel_bringup(char *str) +{ + do_parallel_bringup = false; + + return 0; +} +early_param("no_parallel_bringup", no_parallel_bringup); + static void __init smp_quirk_init_udelay(void) { /* if cmdline changed it from default, leave it alone */ @@ -1084,8 +1094,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) #ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle); -#else - initial_gs = per_cpu_offset(cpu); #endif return 0; } @@ -1110,9 +1118,14 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle, start_ip = real_mode_header->trampoline_start64; #endif idle->thread.sp = (unsigned long)task_pt_regs(idle); - early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); initial_code = (unsigned long)start_secondary; - initial_stack = idle->thread.sp; + + if (IS_ENABLED(CONFIG_X86_32)) { + early_gdt_descr.address = (unsigned long)get_cpu_gdt_rw(cpu); + initial_stack = idle->thread.sp; + } else if (!do_parallel_bringup) { + smpboot_control = STARTUP_SECONDARY | apicid; + } /* Enable the espfix hack for this CPU */ init_espfix_ap(cpu); @@ -1512,6 +1525,47 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) speculative_store_bypass_ht_init(); + /* + * We can do 64-bit AP bringup in parallel if the CPU reports + * its APIC ID in CPUID (either leaf 0x0B if we need the full + * APIC ID in X2APIC mode, or leaf 0x01 if 8 bits are + * sufficient). Otherwise it's too hard. And not for SEV-ES + * guests because they can't use CPUID that early. + */ + if (IS_ENABLED(CONFIG_X86_32) || boot_cpu_data.cpuid_level < 1 || + (x2apic_mode && boot_cpu_data.cpuid_level < 0xb) || + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + do_parallel_bringup = false; + + if (do_parallel_bringup && x2apic_mode) { + unsigned int eax, ebx, ecx, edx; + + /* + * To support parallel bringup in x2apic mode, the AP will need + * to obtain its APIC ID from CPUID 0x0B, since CPUID 0x01 has + * only 8 bits. Check that it is present and seems correct. + */ + cpuid_count(0xb, 0, &eax, &ebx, &ecx, &edx); + + /* + * AMD says that if executed with an umimplemented level in + * ECX, then it will return all zeroes in EAX. Intel says it + * will return zeroes in both EAX and EBX. Checking only EAX + * should be sufficient. + */ + if (eax) { + pr_debug("Using CPUID 0xb for parallel CPU startup\n"); + smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_0B; + } else { + pr_info("Disabling parallel bringup because CPUID 0xb looks untrustworthy\n"); + do_parallel_bringup = false; + } + } else if (do_parallel_bringup) { + /* Without X2APIC, what's in CPUID 0x01 should suffice. */ + pr_debug("Using CPUID 0x1 for parallel CPU startup\n"); + smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_01; + } + snp_set_wakeup_secondary_cpu(); } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index af565816d2ba..788e5559549f 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -154,6 +154,9 @@ static void __init setup_real_mode(void) trampoline_header->flags = 0; + trampoline_lock = &trampoline_header->lock; + *trampoline_lock = 0; + trampoline_pgd = (u64 *) __va(real_mode_header->trampoline_pgd); /* Map the real mode stub as virtual == physical */ diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index e38d61d6562e..49ebc1636ffd 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -49,6 +49,19 @@ SYM_CODE_START(trampoline_start) mov %ax, %es mov %ax, %ss + /* + * Make sure only one CPU fiddles with the realmode stack + */ +.Llock_rm: + btl $0, tr_lock + jnc 2f + pause + jmp .Llock_rm +2: + lock + btsl $0, tr_lock + jc .Llock_rm + # Setup stack movl $rm_stack_end, %esp @@ -241,6 +254,7 @@ SYM_DATA_START(trampoline_header) SYM_DATA(tr_efer, .space 8) SYM_DATA(tr_cr4, .space 4) SYM_DATA(tr_flags, .space 4) + SYM_DATA(tr_lock, .space 4) SYM_DATA_END(trampoline_header) #include "trampoline_common.S" diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 2c7396da470c..a18a21dff9bc 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -25,7 +25,7 @@ * For the hotplug case we keep the task structs around and reuse * them. */ -static DEFINE_PER_CPU(struct task_struct *, idle_threads); +DEFINE_PER_CPU(struct task_struct *, idle_threads); struct task_struct *idle_thread_get(unsigned int cpu) { From patchwork Wed Feb 15 14:54:24 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141776 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id B9010C636D4 for ; Wed, 15 Feb 2023 14:55:22 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230013AbjBOOzV (ORCPT ); Wed, 15 Feb 2023 09:55:21 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:50996 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230014AbjBOOzJ (ORCPT ); Wed, 15 Feb 2023 09:55:09 -0500 Received: from mail-wr1-x42a.google.com (mail-wr1-x42a.google.com [IPv6:2a00:1450:4864:20::42a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C71FF39CD5 for ; Wed, 15 Feb 2023 06:54:36 -0800 (PST) Received: by mail-wr1-x42a.google.com with SMTP id s13so1705732wrw.3 for ; Wed, 15 Feb 2023 06:54:36 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=JJkpGg1hd8P6OX4RPHIkrzOMjPz7lmvjqBeU21FPpuA=; b=tcdHg6gL/+kmrDf6TMBwvnFfIcz101nGGz3Inam8TJELR9NPia/44bKe58cCe0wion KHhYTtM5JQHVGWkPIJQvS0Pg801b07Sz0tqEwOWT7VkqDg7FrNYl1ho3vnyTmQJyfBwd AKNb4Qbx/3QPWVMJ+ealo/onIWpVGrNLelRhBmyq9YVt99ApYhJ+jmpXsMkCMwQCvTUR XcHyB3YqBuIx5oALw8ygnOcM4MeZHUhQmNkAysqnAOo8sCMHwQeVvHZR0R+bpWuLe5sq Cr7eqqqA6NjXSDEX5DbcmXdJ5jFBjeC7+t5h+aIFic37yrx73YXF1y5DxCQ8rVp7qUF7 4Pcw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=JJkpGg1hd8P6OX4RPHIkrzOMjPz7lmvjqBeU21FPpuA=; b=tO30UHK/2Fqfs8Ef//wfM4QKQwEWRRgfLPuvXugLrZARn2vfIZbinebxj72pDVIQBV 5MMgsL2XNz3JN+WGMH+cOZJXz2qrx2xTQGNP2Xxt346anmsdgecMxXMYA4+08bPBPdZh UuOmTIt8OrrXwd3DBLNPqzC8/8bj/OoHkEQ76oSX/X1Ez4z8Vp6ZfVqcZ96X8WdE47/b RPOb4sZmJeSvjEf3ghoXXyyAOKuLjSdt893LNxgmYDy0IXj1Yl6OnPNMlDQZMJYQprOO bmrqzlnRI+WzCK3/r27xg9A1CmPsLCjEIoPwxku/6Wp0GJN8YV6+C8y44A+M1R56Z3CN FlAA== X-Gm-Message-State: AO0yUKWpvkEavEQzQarKkM1pjkDWX8NPbps9lB9tQ74mQrDhDPqKu09B 4yMgSSKTlATFtBeqbdkFEHBMQQ== X-Google-Smtp-Source: AK7set/T0pWPr2ac0iFIDBkuMj5fFQH6npYOyPRhDiy7cZKHer4TH0/f/yhlUIQu8bqE+A2MmHWpbg== X-Received: by 2002:a5d:68c1:0:b0:2c5:58f5:3c40 with SMTP id p1-20020a5d68c1000000b002c558f53c40mr1698253wrw.47.1676472875295; Wed, 15 Feb 2023 06:54:35 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.34 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:34 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 7/8] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel Date: Wed, 15 Feb 2023 14:54:24 +0000 Message-Id: <20230215145425.420125-8-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse When the APs can find their own APIC ID without assistance, perform the AP bringup in parallel. Register a CPUHP_BP_PARALLEL_DYN stage "x86/cpu:kick" which just calls do_boot_cpu() to deliver INIT/SIPI/SIPI to each AP in turn before the normal native_cpu_up() does the rest of the hand-holding. The APs will then take turns through the real mode code (which has its own bitlock for exclusion) until they make it to their own stack, then proceed through the first few lines of start_secondary() and execute these parts in parallel: start_secondary() -> cr4_init() -> (some 32-bit only stuff so not in the parallel cases) -> cpu_init_secondary() -> cpu_init_exception_handling() -> cpu_init() -> wait_for_master_cpu() At this point they wait for the BSP to set their bit in cpu_callout_mask (from do_wait_cpu_initialized()), and release them to continue through the rest of cpu_init() and beyond. This reduces the time taken for bringup on my 28-thread Haswell system from about 120ms to 80ms. On a socket 96-thread Skylake it takes the bringup time from 500ms to 100ms. There is more speedup to be had by doing the remaining parts in parallel too — especially notify_cpu_starting() in which the AP takes itself through all the stages from CPUHP_BRINGUP_CPU to CPUHP_ONLINE. But those require careful auditing to ensure they are reentrant, before we can go that far. [Usama Arif: fixed rebase conflict] Signed-off-by: David Woodhouse Signed-off-by: Usama Arif --- arch/x86/kernel/smpboot.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 49d6563e4c23..4cea3a0ff503 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -57,6 +57,7 @@ #include #include #include +#include #include #include @@ -1325,9 +1326,12 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) { int ret; - ret = do_cpu_up(cpu, tidle); - if (ret) - return ret; + /* If parallel AP bringup isn't enabled, perform the first steps now. */ + if (!do_parallel_bringup) { + ret = do_cpu_up(cpu, tidle); + if (ret) + return ret; + } ret = do_wait_cpu_initialized(cpu); if (ret) @@ -1349,6 +1353,12 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) return ret; } +/* Bringup step one: Send INIT/SIPI to the target AP */ +static int native_cpu_kick(unsigned int cpu) +{ + return do_cpu_up(cpu, idle_thread_get(cpu)); +} + /** * arch_disable_smp_support() - disables SMP support for x86 at runtime */ @@ -1566,6 +1576,11 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) smpboot_control = STARTUP_SECONDARY | STARTUP_APICID_CPUID_01; } + if (do_parallel_bringup) { + cpuhp_setup_state_nocalls(CPUHP_BP_PARALLEL_DYN, "x86/cpu:kick", + native_cpu_kick, NULL); + } + snp_set_wakeup_secondary_cpu(); } From patchwork Wed Feb 15 14:54:25 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Usama Arif X-Patchwork-Id: 13141777 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0AFEEC636D7 for ; Wed, 15 Feb 2023 14:55:34 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229716AbjBOOzd (ORCPT ); Wed, 15 Feb 2023 09:55:33 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:51140 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229981AbjBOOzO (ORCPT ); Wed, 15 Feb 2023 09:55:14 -0500 Received: from mail-wr1-x430.google.com (mail-wr1-x430.google.com [IPv6:2a00:1450:4864:20::430]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id EF3883A859 for ; Wed, 15 Feb 2023 06:54:37 -0800 (PST) Received: by mail-wr1-x430.google.com with SMTP id k3so11796067wrv.5 for ; Wed, 15 Feb 2023 06:54:37 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20210112.gappssmtp.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=m4n+xHRqfb3zC7+GDP+r77yUnjNERyVG3q5QGzNEUa4=; b=IOApGjClYcmxqxv33/LynrzyxR9Iqblg1jrIfD5wEsadp2xYaTXnAS+Co54ciy3rDm kJQUWusx+3EDUWJssK7Lon4aeIM0j4Rtum5Rd5VZoPQi/khZH9JkrOsGwxMzn8TWE+Oq nX5FFkTKfENl4eiWvInJipWuUZu9SJlpsXSwmtjQK3W/ozQh6Ef8VeU0CaIQYoAqnD73 PzrMLmLUGDtxr/gB1W85taRE7XcftI7jDwnQNfBZSncae9G56MAoyTWs80N/Nlq0slXv dYzwmw7vA3N623pFDHp3oEOCYv9Xm4yKOtzj+MiNhCanPhvMR6YnYNY5unyJszB2gkwW CWHw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=m4n+xHRqfb3zC7+GDP+r77yUnjNERyVG3q5QGzNEUa4=; b=uKujcjbgRDfxArvdBtd2x2mN7f7vM5vp/ifvmxKHdRV59xBUeBTBf8l+AAFIcVqjFD co01SB4pF75X3O+LNWLFpzc9RkkZakq4656mKBkLWcxfoz9hXpKCpnRnDcPBCzxlqnqW YcmD3XmBmsbUkIf0S2xx8g8NXeMcDumzPk2xCMWElTKz4iCDHxYJob+znTSCOx98d451 ijO9D6dMZvFHFBzHgccWgmTrHfWopxFgd/JgBApmHBsPmnH8v6xzry1rhSHLsV3DQqQV hShLnyCw6+4zDBQ41hhhnbXxi851PJQHWQZbojW2CwQocWlZUAyQVHLZ9P20VERkN0i+ mUIQ== X-Gm-Message-State: AO0yUKXWH180HBBUGf70WTLgd0ZLd0Exwc1qADf8p/LyNxIJ+I/Wd7Gy ApF30oMKCj/MRLMhO2watYsmCg== X-Google-Smtp-Source: AK7set84XbTrxf8Vh/0TXooWYS+SEa5C1Pv9PN/a2bwDsmD7leet+cwQIVl8dwDxHIfQxJ1xd5JROQ== X-Received: by 2002:adf:fec3:0:b0:2bf:b68a:e122 with SMTP id q3-20020adffec3000000b002bfb68ae122mr1753650wrs.33.1676472876176; Wed, 15 Feb 2023 06:54:36 -0800 (PST) Received: from usaari01.cust.communityfibre.co.uk ([2a02:6b6a:b566:0:8487:6a9a:3a67:11aa]) by smtp.gmail.com with ESMTPSA id t13-20020adfe44d000000b002c557f82e27sm8495508wrm.99.2023.02.15.06.54.35 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Feb 2023 06:54:35 -0800 (PST) From: Usama Arif To: dwmw2@infradead.org, tglx@linutronix.de, kim.phillips@amd.com Cc: arjan@linux.intel.com, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com, x86@kernel.org, pbonzini@redhat.com, paulmck@kernel.org, linux-kernel@vger.kernel.org, kvm@vger.kernel.org, rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com, thomas.lendacky@amd.com, seanjc@google.com, pmenzel@molgen.mpg.de, fam.zheng@bytedance.com, punit.agrawal@bytedance.com, simon.evans@bytedance.com, liangma@liangbit.com, David Woodhouse , Usama Arif Subject: [PATCH v9 8/8] x86/smpboot: Serialize topology updates for secondary bringup Date: Wed, 15 Feb 2023 14:54:25 +0000 Message-Id: <20230215145425.420125-9-usama.arif@bytedance.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20230215145425.420125-1-usama.arif@bytedance.com> References: <20230215145425.420125-1-usama.arif@bytedance.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: rcu@vger.kernel.org From: David Woodhouse The toplogy update is performed by the AP via smp_callin() after the BSP has called do_wait_cpu_initialized(), setting the AP's bit in cpu_callout_mask to allow it to proceed. In preparation to enable further parallelism of AP bringup, add locking to serialize the update even if multiple APs are (in future) permitted to proceed through the next stages of bringup in parallel. Without such ordering (and with that future extra parallelism), confusion ensues: [ 1.360149] x86: Booting SMP configuration: [ 1.360221] .... node #0, CPUs: #1 #2 #3 #4 #5 #6 #7 #8 #9 #10 #11 #12 #13 #14 #15 #16 #17 #18 #19 #20 #21 #22 #23 [ 1.366225] .... node #1, CPUs: #24 #25 #26 #27 #28 #29 #30 #31 #32 #33 #34 #35 #36 #37 #38 #39 #40 #41 #42 #43 #44 #45 #46 #47 [ 1.370219] .... node #0, CPUs: #48 #49 #50 #51 #52 #53 #54 #55 #56 #57 #58 #59 #60 #61 #62 #63 #64 #65 #66 #67 #68 #69 #70 #71 [ 1.378226] .... node #1, CPUs: #72 #73 #74 #75 #76 #77 #78 #79 #80 #81 #82 #83 #84 #85 #86 #87 #88 #89 #90 #91 #92 #93 #94 #95 [ 1.382037] Brought 96 CPUs to x86/cpu:kick in 72232606 cycles [ 0.104104] smpboot: CPU 26 Converting physical 0 to logical die 1 [ 0.104104] smpboot: CPU 27 Converting physical 1 to logical package 2 [ 0.104104] smpboot: CPU 24 Converting physical 1 to logical package 3 [ 0.104104] smpboot: CPU 27 Converting physical 0 to logical die 2 [ 0.104104] smpboot: CPU 25 Converting physical 1 to logical package 4 [ 1.385609] Brought 96 CPUs to x86/cpu:wait-init in 9269218 cycles [ 1.395285] Brought CPUs online in 28930764 cycles [ 1.395469] smp: Brought up 2 nodes, 96 CPUs [ 1.395689] smpboot: Max logical packages: 2 [ 1.396222] smpboot: Total of 96 processors activated (576000.00 BogoMIPS) [Usama Arif: fixed rebase conflict] Signed-off-by: David Woodhouse Signed-off-by: Usama Arif --- arch/x86/include/asm/smp.h | 4 +- arch/x86/include/asm/topology.h | 2 - arch/x86/kernel/cpu/common.c | 6 +-- arch/x86/kernel/smpboot.c | 73 ++++++++++++++++++++------------- arch/x86/xen/smp_pv.c | 4 +- 5 files changed, 48 insertions(+), 41 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 33c0d5fd8af6..b4b29e052b6e 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -48,8 +48,6 @@ struct smp_ops { }; /* Globals due to paravirt */ -extern void set_cpu_sibling_map(int cpu); - #ifdef CONFIG_SMP extern struct smp_ops smp_ops; @@ -137,7 +135,7 @@ void native_send_call_func_single_ipi(int cpu); void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_boot_cpu_info(void); -void smp_store_cpu_info(int id); +void smp_store_cpu_info(int id, bool force_single_core); asmlinkage __visible void smp_reboot_interrupt(void); __visible void smp_reschedule_interrupt(struct pt_regs *regs); diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 458c891a8273..4bccbd949a99 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -136,8 +136,6 @@ static inline int topology_max_smt_threads(void) return __max_smt_threads; } -int topology_update_package_map(unsigned int apicid, unsigned int cpu); -int topology_update_die_map(unsigned int dieid, unsigned int cpu); int topology_phys_to_logical_pkg(unsigned int pkg); int topology_phys_to_logical_die(unsigned int die, unsigned int cpu); bool topology_is_primary_thread(unsigned int cpu); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 9cfca3d7d0e2..cf1a4eff7a76 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1766,7 +1766,7 @@ static void generic_identify(struct cpuinfo_x86 *c) * Validate that ACPI/mptables have the same information about the * effective APIC id and update the package map. */ -static void validate_apic_and_package_id(struct cpuinfo_x86 *c) +static void validate_apic_id(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP unsigned int apicid, cpu = smp_processor_id(); @@ -1777,8 +1777,6 @@ static void validate_apic_and_package_id(struct cpuinfo_x86 *c) pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n", cpu, apicid, c->initial_apicid); } - BUG_ON(topology_update_package_map(c->phys_proc_id, cpu)); - BUG_ON(topology_update_die_map(c->cpu_die_id, cpu)); #else c->logical_proc_id = 0; #endif @@ -1969,7 +1967,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_32 enable_sep_cpu(); #endif - validate_apic_and_package_id(c); + validate_apic_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 4cea3a0ff503..fecd934e72fb 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -180,16 +180,12 @@ static void smp_callin(void) apic_ap_setup(); /* - * Save our processor parameters. Note: this information - * is needed for clock calibration. - */ - smp_store_cpu_info(cpuid); - - /* + * Save our processor parameters and update topology. + * Note: this information is needed for clock calibration. * The topology information must be up to date before * calibrate_delay() and notify_cpu_starting(). */ - set_cpu_sibling_map(raw_smp_processor_id()); + smp_store_cpu_info(cpuid, false); ap_init_aperfmperf(); @@ -243,6 +239,12 @@ static void notrace start_secondary(void *unused) * its bit bit in cpu_callout_mask to release it. */ cpu_init_secondary(); + + /* + * Even though notify_cpu_starting() will do this, it does so too late + * as the AP may already have triggered lockdep splats by then. See + * commit 29368e093 ("x86/smpboot: Move rcu_cpu_starting() earlier"). + */ rcu_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); @@ -351,7 +353,7 @@ EXPORT_SYMBOL(topology_phys_to_logical_die); * @pkg: The physical package id as retrieved via CPUID * @cpu: The cpu for which this is updated */ -int topology_update_package_map(unsigned int pkg, unsigned int cpu) +static int topology_update_package_map(unsigned int pkg, unsigned int cpu) { int new; @@ -374,7 +376,7 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu) * @die: The die id as retrieved via CPUID * @cpu: The cpu for which this is updated */ -int topology_update_die_map(unsigned int die, unsigned int cpu) +static int topology_update_die_map(unsigned int die, unsigned int cpu) { int new; @@ -405,25 +407,7 @@ void __init smp_store_boot_cpu_info(void) c->initialized = true; } -/* - * The bootstrap kernel entry code has set these up. Save them for - * a given CPU - */ -void smp_store_cpu_info(int id) -{ - struct cpuinfo_x86 *c = &cpu_data(id); - - /* Copy boot_cpu_data only on the first bringup */ - if (!c->initialized) - *c = boot_cpu_data; - c->cpu_index = id; - /* - * During boot time, CPU0 has this setup already. Save the info when - * bringing up AP or offlined CPU0. - */ - identify_secondary_cpu(c); - c->initialized = true; -} +static arch_spinlock_t topology_lock = __ARCH_SPIN_LOCK_UNLOCKED; static bool topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -629,7 +613,7 @@ static struct sched_domain_topology_level x86_topology[] = { */ static bool x86_has_numa_in_package; -void set_cpu_sibling_map(int cpu) +static void set_cpu_sibling_map(int cpu) { bool has_smt = smp_num_siblings > 1; bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; @@ -708,6 +692,37 @@ void set_cpu_sibling_map(int cpu) } } +/* + * The bootstrap kernel entry code has set these up. Save them for + * a given CPU + */ +void smp_store_cpu_info(int id, bool force_single_core) +{ + struct cpuinfo_x86 *c = &cpu_data(id); + + /* Copy boot_cpu_data only on the first bringup */ + if (!c->initialized) + *c = boot_cpu_data; + c->cpu_index = id; + /* + * During boot time, CPU0 has this setup already. Save the info when + * bringing up AP or offlined CPU0. + */ + identify_secondary_cpu(c); + + arch_spin_lock(&topology_lock); + BUG_ON(topology_update_package_map(c->phys_proc_id, id)); + BUG_ON(topology_update_die_map(c->cpu_die_id, id)); + c->initialized = true; + + /* For Xen PV */ + if (force_single_core) + c->x86_max_cores = 1; + + set_cpu_sibling_map(id); + arch_spin_unlock(&topology_lock); +} + /* maps the cpu to the sched domain representing multi-core */ const struct cpumask *cpu_coregroup_mask(int cpu) { diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 6175f2c5c822..09f94f940689 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -71,9 +71,7 @@ static void cpu_bringup(void) xen_enable_syscall(); } cpu = smp_processor_id(); - smp_store_cpu_info(cpu); - cpu_data(cpu).x86_max_cores = 1; - set_cpu_sibling_map(cpu); + smp_store_cpu_info(cpu, true); speculative_store_bypass_ht_init();