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 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id C88E6C433EF for ; Fri, 8 Oct 2021 14:50:29 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A620E61039 for ; Fri, 8 Oct 2021 14:50:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S243144AbhJHOwW (ORCPT ); Fri, 8 Oct 2021 10:52:22 -0400 Received: from us-smtp-delivery-124.mimecast.com ([216.205.24.124]:42204 "EHLO us-smtp-delivery-124.mimecast.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S242921AbhJHOvp (ORCPT ); Fri, 8 Oct 2021 10:51:45 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1633704577; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version:content-type:content-type: references:references; bh=kK1fYXuNv+ywQ5icgeMPInL7gyKox4tRv0GlzEiEwao=; b=HaKUnYDOKsMmuyjBO6kW9BIRoi087QoNmCy1BUngXSgfcPFCXXWc9WHnq87g31VPwGtsS3 yFFjpBsMVpVJhsexZLM5vuJL7Nl9HLYZKV1kvvbBEabmoom7PuMkvSpm2aJVuWdIIwilpU 5T/ksCEVEE9OSnTPRr6KSQV+hUgQZKY= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-597-9HsIyXDcNLGU_xTbRMusIw-1; Fri, 08 Oct 2021 10:49:24 -0400 X-MC-Unique: 9HsIyXDcNLGU_xTbRMusIw-1 Received: from smtp.corp.redhat.com (int-mx01.intmail.prod.int.phx2.redhat.com [10.5.11.11]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id DB356100B704; Fri, 8 Oct 2021 14:49:22 +0000 (UTC) Received: from fuller.cnet (ovpn-112-4.gru2.redhat.com [10.97.112.4]) by smtp.corp.redhat.com (Postfix) with ESMTPS id E97D52AF99; Fri, 8 Oct 2021 14:49:04 +0000 (UTC) Received: by fuller.cnet (Postfix, from userid 1000) id EAD77425E3F0; Fri, 8 Oct 2021 11:48:13 -0300 (-03) Message-ID: <20211007193526.308047182@fedora.localdomain> User-Agent: quilt/0.66 Date: Thu, 07 Oct 2021 16:23:51 -0300 From: Marcelo Tosatti To: linux-kernel@vger.kernel.org Cc: Nitesh Lal , Nicolas Saenz Julienne , Frederic Weisbecker , Christoph Lameter , Juri Lelli , Peter Zijlstra , Alex Belits , Peter Xu , Marcelo Tosatti Subject: [patch v4 5/8] task isolation: sync vmstats conditional on changes References: <20211007192346.731667417@fedora.localdomain> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.11 Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Rather than syncing VM-stats on every return to userspace (or VM-entry), keep track of changes through a per-CPU bool. This improves performance when enabling task isolated for vcpu VMs. Signed-off-by: Marcelo Tosatti Index: linux-2.6/include/linux/vmstat.h =================================================================== --- linux-2.6.orig/include/linux/vmstat.h +++ linux-2.6/include/linux/vmstat.h @@ -22,7 +22,16 @@ int sysctl_vm_numa_stat_handler(struct c #endif #ifdef CONFIG_SMP -void sync_vmstat(void); +extern struct static_key vmstat_sync_enabled; + +void __sync_vmstat(void); +static inline void sync_vmstat(void) +{ + if (static_key_false(&vmstat_sync_enabled)) + __sync_vmstat(); +} + +void init_sync_vmstat(void); #else static inline void sync_vmstat(void) { Index: linux-2.6/kernel/task_isolation.c =================================================================== --- linux-2.6.orig/kernel/task_isolation.c +++ linux-2.6/kernel/task_isolation.c @@ -21,6 +21,17 @@ #include #include +void __tsk_isol_exit(struct task_struct *tsk) +{ + struct isol_info *i; + + i = tsk->isol_info; + if (!i) + return; + + static_key_slow_dec(&vmstat_sync_enabled); +} + void __tsk_isol_free(struct task_struct *tsk) { if (!tsk->isol_info) @@ -37,6 +48,12 @@ static struct isol_info *tsk_isol_alloc_ if (unlikely(!info)) return ERR_PTR(-ENOMEM); + preempt_disable(); + init_sync_vmstat(); + preempt_enable(); + + static_key_slow_inc(&vmstat_sync_enabled); + return info; } Index: linux-2.6/mm/vmstat.c =================================================================== --- linux-2.6.orig/mm/vmstat.c +++ linux-2.6/mm/vmstat.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "internal.h" @@ -306,6 +307,22 @@ void set_pgdat_percpu_threshold(pg_data_ } } +struct static_key vmstat_sync_enabled; +static DEFINE_PER_CPU_ALIGNED(bool, vmstat_dirty); + +static inline void mark_vmstat_dirty(void) +{ + if (!static_key_false(&vmstat_sync_enabled)) + return; + + raw_cpu_write(vmstat_dirty, true); +} + +void init_sync_vmstat(void) +{ + raw_cpu_write(vmstat_dirty, true); +} + /* * For use when we know that interrupts are disabled, * or when we know that preemption is disabled and that @@ -338,6 +355,7 @@ void __mod_zone_page_state(struct zone * x = 0; } __this_cpu_write(*p, x); + mark_vmstat_dirty(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); @@ -376,6 +394,7 @@ void __mod_node_page_state(struct pglist x = 0; } __this_cpu_write(*p, x); + mark_vmstat_dirty(); if (IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); @@ -574,6 +593,7 @@ static inline void mod_zone_state(struct if (z) zone_page_state_add(z, zone, item); + mark_vmstat_dirty(); } void mod_zone_page_state(struct zone *zone, enum zone_stat_item item, @@ -642,6 +662,7 @@ static inline void mod_node_state(struct if (z) node_page_state_add(z, pgdat, item); + mark_vmstat_dirty(); } void mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, @@ -1082,6 +1103,7 @@ static void fill_contig_page_info(struct info->free_blocks_suitable += blocks << (order - suitable_order); } + mark_vmstat_dirty(); } /* @@ -1434,6 +1456,7 @@ static void walk_zones_in_node(struct se if (!nolock) spin_unlock_irqrestore(&zone->lock, flags); } + mark_vmstat_dirty(); } #endif @@ -1499,6 +1522,7 @@ static void pagetypeinfo_showfree_print( } seq_putc(m, '\n'); } + mark_vmstat_dirty(); } /* Print out the free pages at each order for each migatetype */ @@ -1917,6 +1941,7 @@ static void vmstat_update(struct work_st this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } + mark_vmstat_dirty(); } /* @@ -2003,13 +2028,18 @@ static void vmstat_shepherd(struct work_ round_jiffies_relative(sysctl_stat_interval)); } -void sync_vmstat(void) +void __sync_vmstat(void) { int cpu; cpu = get_cpu(); + if (per_cpu(vmstat_dirty, cpu) == false) { + put_cpu(); + return; + } refresh_cpu_vm_stats(false); + raw_cpu_write(vmstat_dirty, false); put_cpu(); /* Index: linux-2.6/include/linux/task_isolation.h =================================================================== --- linux-2.6.orig/include/linux/task_isolation.h +++ linux-2.6/include/linux/task_isolation.h @@ -27,6 +27,13 @@ static inline void tsk_isol_free(struct __tsk_isol_free(tsk); } +void __tsk_isol_exit(struct task_struct *tsk); +static inline void tsk_isol_exit(struct task_struct *tsk) +{ + if (tsk->isol_info) + __tsk_isol_exit(tsk); +} + int prctl_task_isolation_feat_get(unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5); int prctl_task_isolation_cfg_get(unsigned long arg2, unsigned long arg3, @@ -58,6 +65,10 @@ static inline void tsk_isol_free(struct { } +static inline void tsk_isol_exit(struct task_struct *tsk) +{ +} + static inline int prctl_task_isolation_feat_get(unsigned long arg2, unsigned long arg3, unsigned long arg4, Index: linux-2.6/kernel/exit.c =================================================================== --- linux-2.6.orig/kernel/exit.c +++ linux-2.6/kernel/exit.c @@ -64,6 +64,7 @@ #include #include #include +#include #include #include @@ -778,6 +779,7 @@ void __noreturn do_exit(long code) } io_uring_files_cancel(); + tsk_isol_exit(tsk); exit_signals(tsk); /* sets PF_EXITING */ /* sync mm's RSS info before statistics gathering */ Index: linux-2.6/kernel/fork.c =================================================================== --- linux-2.6.orig/kernel/fork.c +++ linux-2.6/kernel/fork.c @@ -2446,6 +2446,7 @@ bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_task_isolation: + tsk_isol_exit(p); tsk_isol_free(p); bad_fork_cleanup_thread: exit_thread(p);