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 bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id A487ACCD185 for ; Mon, 13 Oct 2025 20:35:43 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:Content-Transfer-Encoding: Content-Type:MIME-Version:References:In-Reply-To:Message-ID:Date:Subject:Cc: To:From:Reply-To:Content-ID:Content-Description:Resent-Date:Resent-From: Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=MDhmNjrH/ApFrXrP814IcRBr/P0WKwEANNyt3qUOrh8=; b=TNaKcW5ObC8IwpY20y+MhKkpRy /LW79QtP6nLrjl8oRODwVsz0iL/fwSS5uMAhNA0K4e5N5Yqz25VTLrzbLr6QlqUc9lsH20VYvDqkZ HGQ5oxpMpfnuBiZYU/h3V1c54evCpdjbUOB4+ne/RyUBTjxjjcaNwybb6l0e0HSmVeDliVWbg/333 F7VNGfNdCIdQR2gYkaaFh4Z8SaeLCd8YKBMC8NNh3e2pTiR7UmejG967C4cpz3r1Lcp5a1GSpp7nw IpuGBywWw4gTIxY/tJjocSw/t8IdkaHuI3tpFu6bQvJvq6kaWsHHkxlO3HzwjzWuwqTB78Lp4rHyS PGJEso3g==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.98.2 #2 (Red Hat Linux)) id 1v8PGb-0000000EPt9-2f7I; Mon, 13 Oct 2025 20:35:37 +0000 Received: from sea.source.kernel.org ([2600:3c0a:e001:78e:0:1991:8:25]) by bombadil.infradead.org with esmtps (Exim 4.98.2 #2 (Red Hat Linux)) id 1v8PGY-0000000EPqY-2U6T for linux-arm-kernel@lists.infradead.org; Mon, 13 Oct 2025 20:35:36 +0000 Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by sea.source.kernel.org (Postfix) with ESMTP id 3F84F44836; Mon, 13 Oct 2025 20:35:34 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id DE283C4CEE7; Mon, 13 Oct 2025 20:35:26 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1760387734; bh=PsMKH0OPMca3EhEEuIU354JdvA7f16B4eqaq2LuoXwI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=BOcgefUbdM8KZZtxNCa5o0JhMH9FSXBLb7n4WPeOsF2XgdoK83GOUM6roqgwxi6fg lmeI43Wlh9lqJhfgRWkv5kPv0yv8NZJhMRURGFHNTE1N+A2btbuj7S4UK4KPSD//lj N94VL2GZrzRWuYxj7iP5IBsWSKOSinM80+mfqjqim1clnFbPeZF40wiaeoKIbqL6ks GkQ1KbgSilayV8mjiTJNiHaQM3lR8PnlIFvRB73rfRxrAg9FKRdXQDU4Z8S2AHPsRu TGDBiyljEp+s5CxXNwhR3i9ANDzt9nGvwUi4s5urUMUyWglryJ/ELSPTbcf4kHT8IX +SFKeeSMNX4fw== From: Frederic Weisbecker To: LKML Cc: Frederic Weisbecker , =?UTF-8?q?Michal=20Koutn=C3=BD?= , Andrew Morton , Bjorn Helgaas , Catalin Marinas , Danilo Krummrich , "David S . Miller" , Eric Dumazet , Gabriele Monaco , Greg Kroah-Hartman , Ingo Molnar , Jakub Kicinski , Jens Axboe , Johannes Weiner , Lai Jiangshan , Marco Crivellari , Michal Hocko , Muchun Song , Paolo Abeni , Peter Zijlstra , Phil Auld , "Rafael J . Wysocki" , Roman Gushchin , Shakeel Butt , Simon Horman , Tejun Heo , Thomas Gleixner , Vlastimil Babka , Waiman Long , Will Deacon , cgroups@vger.kernel.org, linux-arm-kernel@lists.infradead.org, linux-block@vger.kernel.org, linux-mm@kvack.org, linux-pci@vger.kernel.org, netdev@vger.kernel.org Subject: [PATCH 28/33] kthread: Honour kthreads preferred affinity after cpuset changes Date: Mon, 13 Oct 2025 22:31:41 +0200 Message-ID: <20251013203146.10162-29-frederic@kernel.org> X-Mailer: git-send-email 2.51.0 In-Reply-To: <20251013203146.10162-1-frederic@kernel.org> References: <20251013203146.10162-1-frederic@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20251013_133534_686063_A7FF4CF6 X-CRM114-Status: GOOD ( 17.49 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org When cpuset isolated partitions get updated, unbound kthreads get indifferently affine to all non isolated CPUs, regardless of their individual affinity preferences. For example kswapd is a per-node kthread that prefers to be affine to the node it refers to. Whenever an isolated partition is created, updated or deleted, kswapd's node affinity is going to be broken if any CPU in the related node is not isolated because kswapd will be affine globally. Fix this with letting the consolidated kthread managed affinity code do the affinity update on behalf of cpuset. Signed-off-by: Frederic Weisbecker --- include/linux/kthread.h | 1 + kernel/cgroup/cpuset.c | 5 ++--- kernel/kthread.c | 38 +++++++++++++++++++++++++++++--------- kernel/sched/isolation.c | 2 ++ 4 files changed, 34 insertions(+), 12 deletions(-) diff --git a/include/linux/kthread.h b/include/linux/kthread.h index 8d27403888ce..c92c1149ee6e 100644 --- a/include/linux/kthread.h +++ b/include/linux/kthread.h @@ -100,6 +100,7 @@ void kthread_unpark(struct task_struct *k); void kthread_parkme(void); void kthread_exit(long result) __noreturn; void kthread_complete_and_exit(struct completion *, long) __noreturn; +int kthreads_update_housekeeping(void); int kthreadd(void *unused); extern struct task_struct *kthreadd_task; diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 817c07a7a1b4..bc3f18ead7c8 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1182,11 +1182,10 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) if (top_cs) { /* + * PF_KTHREAD tasks are handled by housekeeping. * PF_NO_SETAFFINITY tasks are ignored. - * All per cpu kthreads should have PF_NO_SETAFFINITY - * flag set, see kthread_set_per_cpu(). */ - if (task->flags & PF_NO_SETAFFINITY) + if (task->flags & (PF_KTHREAD | PF_NO_SETAFFINITY)) continue; cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus); } else { diff --git a/kernel/kthread.c b/kernel/kthread.c index 8d0c8c4c7e46..4d3cc04e5e8b 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -896,14 +896,7 @@ int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) } EXPORT_SYMBOL_GPL(kthread_affine_preferred); -/* - * Re-affine kthreads according to their preferences - * and the newly online CPU. The CPU down part is handled - * by select_fallback_rq() which default re-affines to - * housekeepers from other nodes in case the preferred - * affinity doesn't apply anymore. - */ -static int kthreads_online_cpu(unsigned int cpu) +static int kthreads_update_affinity(bool force) { cpumask_var_t affinity; struct kthread *k; @@ -926,7 +919,7 @@ static int kthreads_online_cpu(unsigned int cpu) continue; } - if (k->preferred_affinity || k->node != NUMA_NO_NODE) { + if (force || k->preferred_affinity || k->node != NUMA_NO_NODE) { kthread_fetch_affinity(k, affinity); set_cpus_allowed_ptr(k->task, affinity); } @@ -937,6 +930,33 @@ static int kthreads_online_cpu(unsigned int cpu) return ret; } +/** + * kthreads_update_housekeeping - Update kthreads affinity on cpuset change + * + * When cpuset changes a partition type to/from "isolated" or updates related + * cpumasks, propagate the housekeeping cpumask change to preferred kthreads + * affinity. + * + * Returns 0 if successful, -ENOMEM if temporary mask couldn't + * be allocated or -EINVAL in case of internal error. + */ +int kthreads_update_housekeeping(void) +{ + return kthreads_update_affinity(true); +} + +/* + * Re-affine kthreads according to their preferences + * and the newly online CPU. The CPU down part is handled + * by select_fallback_rq() which default re-affines to + * housekeepers from other nodes in case the preferred + * affinity doesn't apply anymore. + */ +static int kthreads_online_cpu(unsigned int cpu) +{ + return kthreads_update_affinity(false); +} + static int kthreads_init(void) { return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online", diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 691f045ab758..93de1304e6d4 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -150,6 +150,8 @@ int housekeeping_update(struct cpumask *mask, enum hk_type type) mem_cgroup_flush_workqueue(); vmstat_flush_workqueue(); err = workqueue_unbound_housekeeping_update(housekeeping_cpumask(type)); + WARN_ON_ONCE(err < 0); + err = kthreads_update_housekeeping(); kfree(old); -- 2.51.0