From nobody Tue Oct 7 07:01:24 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id AD185255F5E for ; Mon, 14 Jul 2025 13:31:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=170.10.133.124 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1752499917; cv=none; b=Lg8V2JV+XDK9hVb61skLxq5N90c/3EdQEPKDzthP//Hxy3RvayQtSyTqmw6XnyBZj4itJ34Jw2pJLNMp2gjghPU5w7J46t9xZEMOcMNNp+wEVIHr07M0Jd3o2KFzr7cbrHi2TTR3kgq1a7J7UH8HK774yZvaukiEmc0fn9B4PU4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1752499917; c=relaxed/simple; bh=K7qAczb3YQ6z1nXWwVbmqNORemjdg36f/1bzhva0amk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=qEsGVlAOzi+eLRAh2qNrjrPPlboFuhUBXB7sx8pZpjAtbORy2PU9uXPnm8vD2H2KmC0x+Y7lIkQZH7uajnL0MnrI/oPrS+yFzaTHiTLQEHAulJBCgRMoMst2y9Uxl/mq0LLSYXs9V4oxH2M2y5iHp1w+a3qtPUvzZ30FKg30/3s= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=redhat.com; spf=pass smtp.mailfrom=redhat.com; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b=QdttMt7t; arc=none smtp.client-ip=170.10.133.124 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="QdttMt7t" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1752499914; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=WYbbgpzUKB8X3b3r4oh4zjfNRIGhYdLB9UmhVtf7hUw=; b=QdttMt7tj8JB/o7cjp3dJa13o661OeOVlmGtMh9V+KDmhvJWDh0tBxKJeZYGzDzZ+nFHV4 XpzhC1j0ZwB9NfI5HA9GtMLOwSKN00s0pRtuSUD7t1p/om9maPMoOSiciFh/Zm7tT3kXFQ P8PMowCZDe3RU2eNH1ihlVBkI9SvGmM= Received: from mx-prod-mc-04.mail-002.prod.us-west-2.aws.redhat.com (ec2-54-186-198-63.us-west-2.compute.amazonaws.com [54.186.198.63]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-190-OBkFUcPZPOCTtncnJZZBcw-1; Mon, 14 Jul 2025 09:31:50 -0400 X-MC-Unique: OBkFUcPZPOCTtncnJZZBcw-1 X-Mimecast-MFC-AGG-ID: OBkFUcPZPOCTtncnJZZBcw_1752499909 Received: from mx-prod-int-03.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-03.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.12]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mx-prod-mc-04.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id C3BA119560B7; Mon, 14 Jul 2025 13:31:49 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.45.225.215]) by mx-prod-int-03.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 61EED19560A3; Mon, 14 Jul 2025 13:31:46 +0000 (UTC) From: Gabriele Monaco To: linux-kernel@vger.kernel.org, Anna-Maria Behnsen , Frederic Weisbecker , Thomas Gleixner , Waiman Long Cc: Gabriele Monaco Subject: [PATCH v8 7/7] timers: Exclude isolated cpus from timer migration Date: Mon, 14 Jul 2025 15:30:58 +0200 Message-ID: <20250714133050.193108-16-gmonaco@redhat.com> In-Reply-To: <20250714133050.193108-9-gmonaco@redhat.com> References: <20250714133050.193108-9-gmonaco@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.0 on 10.30.177.12 Content-Type: text/plain; charset="utf-8" The timer migration mechanism allows active CPUs to pull timers from idle ones to improve the overall idle time. This is however undesired when CPU intensive workloads run on isolated cores, as the algorithm would move the timers from housekeeping to isolated cores, negatively affecting the isolation. Exclude isolated cores from the timer migration algorithm, extend the concept of unavailable cores, currently used for offline ones, to isolated ones: * A core is unavailable if isolated or offline; * A core is available if non isolated and online; A core is considered unavailable as isolated if it belongs to: * the isolcpus (domain) list * an isolated cpuset Except if it is: * in the nohz_full list (already idle for the hierarchy) * the nohz timekeeper core (must be available to handle global timers) All online CPUs are added to the hierarchy during early boot, isolated CPUs are removed during late boot if configured or whenever the cpuset isolation changes. Due to how the timer migration algorithm works, any CPU part of the hierarchy can have their global timers pulled by remote CPUs and have to pull remote timers, only skipping pulling remote timers would break the logic. For this reason, prevent isolated CPUs from pulling remote global timers, but also the other way around: any global timer started on an isolated CPU will run there. This does not break the concept of isolation (global timers don't come from outside the CPU) and, if considered inappropriate, can usually be mitigated with other isolation techniques (e.g. IRQ pinning). This effect was noticed on a 128 cores machine running oslat on the isolated cores (1-31,33-63,65-95,97-127). The tool monopolises CPUs, and the CPU with lowest count in a timer migration hierarchy (here 1 and 65) appears as always active and continuously pulls global timers, from the housekeeping CPUs. This ends up moving driver work (e.g. delayed work) to isolated CPUs and causes latency spikes: before the change: # oslat -c 1-31,33-63,65-95,97-127 -D 62s ... Maximum: 1203 10 3 4 ... 5 (us) after the change: # oslat -c 1-31,33-63,65-95,97-127 -D 62s ... Maximum: 10 4 3 4 3 ... 5 (us) Signed-off-by: Gabriele Monaco --- include/linux/timer.h | 9 ++++ kernel/cgroup/cpuset.c | 3 ++ kernel/time/timer_migration.c | 90 +++++++++++++++++++++++++++++++++++ 3 files changed, 102 insertions(+) diff --git a/include/linux/timer.h b/include/linux/timer.h index 0414d9e6b4fcd..62e1cea711257 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -188,4 +188,13 @@ int timers_dead_cpu(unsigned int cpu); #define timers_dead_cpu NULL #endif =20 +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask); +#else +static inline int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_c= pumask) +{ + return 0; +} +#endif + #endif diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index a946d85ce954a..ff5b66abd0474 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1392,6 +1392,9 @@ static void update_exclusion_cpumasks(bool isolcpus_u= pdated) =20 ret =3D workqueue_unbound_exclude_cpumask(isolated_cpus); WARN_ON_ONCE(ret < 0); + + ret =3D tmigr_isolated_exclude_cpumask(isolated_cpus); + WARN_ON_ONCE(ret < 0); } =20 /** diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 878fd3af40ecb..c07cc9a2b209d 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -10,6 +10,7 @@ #include #include #include +#include =20 #include "timer_migration.h" #include "tick-internal.h" @@ -428,6 +429,9 @@ static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); */ static cpumask_var_t tmigr_available_cpumask; =20 +/* Enabled during late initcall */ +static bool tmigr_exclude_isolated __read_mostly; + #define TMIGR_NONE 0xFF #define BIT_CNT 8 =20 @@ -436,6 +440,24 @@ static inline bool tmigr_is_not_available(struct tmigr= _cpu *tmc) return !(tmc->tmgroup && tmc->available); } =20 +/* + * Returns true if @cpu should be excluded from the hierarchy as isolated. + * Domain isolated CPUs don't participate in timer migration, nohz_full + * CPUs are still part of the hierarchy but are always considered idle. + * This behaviour depends on the value of tmigr_exclude_isolated, which is + * normally disabled during early boot. + * This check is necessary, for instance, to prevent offline isolated CPU = from + * being incorrectly marked as available once getting back online. + */ +static inline bool tmigr_is_isolated(int cpu) +{ + if (!tmigr_exclude_isolated) + return false; + return (!housekeeping_cpu(cpu, HK_TYPE_DOMAIN) || + cpuset_cpu_is_isolated(cpu)) && + housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE); +} + /* * Returns true, when @childmask corresponds to the group migrator or when= the * group is not active - so no migrator is set. @@ -1454,6 +1476,8 @@ static int tmigr_clear_cpu_available(unsigned int cpu) =20 cpumask_clear_cpu(cpu, tmigr_available_cpumask); scoped_guard(raw_spinlock_irq, &tmc->lock) { + if (!tmc->available) + return 0; tmc->available =3D false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); =20 @@ -1481,8 +1505,12 @@ static int tmigr_set_cpu_available(unsigned int cpu) if (WARN_ON_ONCE(!tmc->tmgroup)) return -EINVAL; =20 + if (tmigr_is_isolated(cpu)) + return 0; cpumask_set_cpu(cpu, tmigr_available_cpumask); scoped_guard(raw_spinlock_irq, &tmc->lock) { + if (tmc->available) + return 0; trace_tmigr_cpu_available(tmc); tmc->idle =3D timer_base_is_idle(); if (!tmc->idle) @@ -1492,6 +1520,67 @@ static int tmigr_set_cpu_available(unsigned int cpu) return 0; } =20 +static bool tmigr_should_isolate_cpu(int cpu, void *ignored) +{ + /* + * The tick CPU can be marked as isolated by the cpuset code, however + * we cannot mark it as unavailable to avoid having no global migrator + * for the nohz_full CPUs. + */ + return tick_nohz_cpu_hotpluggable(cpu); +} + +static void tmigr_cpu_isolate(void *ignored) +{ + tmigr_clear_cpu_available(smp_processor_id()); +} + +static void tmigr_cpu_unisolate(void *ignored) +{ + tmigr_set_cpu_available(smp_processor_id()); +} + +int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) +{ + cpumask_var_t cpumask; + + lockdep_assert_cpus_held(); + + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + + cpumask_and(cpumask, exclude_cpumask, tmigr_available_cpumask); + cpumask_and(cpumask, cpumask, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)); + on_each_cpu_cond_mask(tmigr_should_isolate_cpu, tmigr_cpu_isolate, NULL, + 1, cpumask); + + cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); + cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); + on_each_cpu_mask(cpumask, tmigr_cpu_unisolate, NULL, 1); + + free_cpumask_var(cpumask); + return 0; +} + +static int __init tmigr_init_isolation(void) +{ + cpumask_var_t cpumask; + + tmigr_exclude_isolated =3D true; + if (!housekeeping_enabled(HK_TYPE_DOMAIN)) + return 0; + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + return -ENOMEM; + cpumask_andnot(cpumask, tmigr_available_cpumask, + housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(cpumask, cpumask, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE)); + on_each_cpu_cond_mask(tmigr_should_isolate_cpu, tmigr_cpu_isolate, NULL, + 1, cpumask); + + free_cpumask_var(cpumask); + return 0; +} + static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, int node) { @@ -1874,3 +1963,4 @@ static int __init tmigr_init(void) return ret; } early_initcall(tmigr_init); +late_initcall(tmigr_init_isolation); --=20 2.50.1