From nobody Tue Dec 16 07:30:55 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 EAE8523183D for ; Fri, 30 May 2025 14:21:24 +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=1748614886; cv=none; b=osO/1sgDB7L9GDHd8qF2rj+KlSX/ISGORrr3ElI3Wn2EWoFyT7rQjLQnX8HiE7XdDWLxQGRyh/N3pEghlsC/aEdountUd2DKI0GlxPEvfvo/fX/W+i9qE4xJmasVPqYKgVEN0FNZfCeUhO7nmVT+2YFtqwJPKCsHW6hlxvQUOFk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614886; c=relaxed/simple; bh=tDnXOE4HmetRM9ergwtwOk0oofTBYTeowkzenHyMGxo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=stBIB2JNuz9bAQSvwU/q/+BSd9NouJOCHSJYdooZZiH/Jn5+ef3lYzC/ASQpdjVcc5ncHPEnTJYvc4e48nsBYJ70x1yRP7Kdv9hvZqyoLXg8+VTGws8odEgUv+BNCQ02odolaWiPWwtpMEbhk0yzPZ4Y1OmBnuUIqazuFsLEngo= 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=DbZCow/7; 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="DbZCow/7" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1748614883; 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=Eg0z7Pus8n3D8i1OBhTFBP+P7WtdwbC7/sBYnKiCqJU=; b=DbZCow/7/BgYDfNgEaLRvLEyYmU2JWVvjmGs3bGy9KTbVCmWfLdldo9On5JBO7dvTs2SPo RHegcf7T27m2fwWFMQfIqXUtoPB2qd+3MZK655kimd5sKaCOHwj/AqstPuDZt08Rvq1jnn QhF9QstpsehkXq5IStmQjO6D+1NNTRM= Received: from mx-prod-mc-05.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-668-JlTlTtKeOsK5d807e8mgPQ-1; Fri, 30 May 2025 10:21:21 -0400 X-MC-Unique: JlTlTtKeOsK5d807e8mgPQ-1 X-Mimecast-MFC-AGG-ID: JlTlTtKeOsK5d807e8mgPQ_1748614880 Received: from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4]) (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-05.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id 43731195608A; Fri, 30 May 2025 14:21:20 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.33.197]) by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 2757730001B7; Fri, 30 May 2025 14:21:16 +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 v6 1/6] timers: Rename tmigr 'online' bit to 'available' Date: Fri, 30 May 2025 16:20:26 +0200 Message-ID: <20250530142031.215594-2-gmonaco@redhat.com> In-Reply-To: <20250530142031.215594-1-gmonaco@redhat.com> References: <20250530142031.215594-1-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 3.4.1 on 10.30.177.4 Content-Type: text/plain; charset="utf-8" The timer migration hierarchy excludes offline CPUs via the tmigr_is_not_available function, which is essentially checking the online bit for the CPU. Rename the online bit to available and all references in function names and tracepoint to generalise the concept of available CPUs. Signed-off-by: Gabriele Monaco --- include/trace/events/timer_migration.h | 4 ++-- kernel/time/timer_migration.c | 22 +++++++++++----------- kernel/time/timer_migration.h | 2 +- 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/include/trace/events/timer_migration.h b/include/trace/events/= timer_migration.h index 47db5eaf2f9ab..61171b13c687c 100644 --- a/include/trace/events/timer_migration.h +++ b/include/trace/events/timer_migration.h @@ -173,14 +173,14 @@ DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_active, TP_ARGS(tmc) ); =20 -DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_online, +DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_available, =20 TP_PROTO(struct tmigr_cpu *tmc), =20 TP_ARGS(tmc) ); =20 -DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_offline, +DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_unavailable, =20 TP_PROTO(struct tmigr_cpu *tmc), =20 diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 2f6330831f084..7efd897c79599 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -427,7 +427,7 @@ static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); =20 static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc) { - return !(tmc->tmgroup && tmc->online); + return !(tmc->tmgroup && tmc->available); } =20 /* @@ -926,7 +926,7 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u= 64 now, * updated the event takes care when hierarchy is completely * idle. Otherwise the migrator does it as the event is enqueued. */ - if (!tmc->online || tmc->remote || tmc->cpuevt.ignore || + if (!tmc->available || tmc->remote || tmc->cpuevt.ignore || now < tmc->cpuevt.nextevt.expires) { raw_spin_unlock_irq(&tmc->lock); return; @@ -973,7 +973,7 @@ static void tmigr_handle_remote_cpu(unsigned int cpu, u= 64 now, * (See also section "Required event and timerqueue update after a * remote expiry" in the documentation at the top) */ - if (!tmc->online || !tmc->idle) { + if (!tmc->available || !tmc->idle) { timer_unlock_remote_bases(cpu); goto unlock; } @@ -1435,19 +1435,19 @@ static long tmigr_trigger_active(void *unused) { struct tmigr_cpu *tmc =3D this_cpu_ptr(&tmigr_cpu); =20 - WARN_ON_ONCE(!tmc->online || tmc->idle); + WARN_ON_ONCE(!tmc->available || tmc->idle); =20 return 0; } =20 -static int tmigr_cpu_offline(unsigned int cpu) +static int tmigr_cpu_unavailable(unsigned int cpu) { struct tmigr_cpu *tmc =3D this_cpu_ptr(&tmigr_cpu); int migrator; u64 firstexp; =20 raw_spin_lock_irq(&tmc->lock); - tmc->online =3D false; + tmc->available =3D false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); =20 /* @@ -1455,7 +1455,7 @@ static int tmigr_cpu_offline(unsigned int cpu) * offline; Therefore nextevt value is set to KTIME_MAX */ firstexp =3D __tmigr_cpu_deactivate(tmc, KTIME_MAX); - trace_tmigr_cpu_offline(tmc); + trace_tmigr_cpu_unavailable(tmc); raw_spin_unlock_irq(&tmc->lock); =20 if (firstexp !=3D KTIME_MAX) { @@ -1466,7 +1466,7 @@ static int tmigr_cpu_offline(unsigned int cpu) return 0; } =20 -static int tmigr_cpu_online(unsigned int cpu) +static int tmigr_cpu_available(unsigned int cpu) { struct tmigr_cpu *tmc =3D this_cpu_ptr(&tmigr_cpu); =20 @@ -1475,11 +1475,11 @@ static int tmigr_cpu_online(unsigned int cpu) return -EINVAL; =20 raw_spin_lock_irq(&tmc->lock); - trace_tmigr_cpu_online(tmc); + trace_tmigr_cpu_available(tmc); tmc->idle =3D timer_base_is_idle(); if (!tmc->idle) __tmigr_cpu_activate(tmc); - tmc->online =3D true; + tmc->available =3D true; raw_spin_unlock_irq(&tmc->lock); return 0; } @@ -1850,7 +1850,7 @@ static int __init tmigr_init(void) goto err; =20 ret =3D cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online", - tmigr_cpu_online, tmigr_cpu_offline); + tmigr_cpu_available, tmigr_cpu_unavailable); if (ret) goto err; =20 diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index ae19f70f8170f..70879cde6fdd0 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -97,7 +97,7 @@ struct tmigr_group { */ struct tmigr_cpu { raw_spinlock_t lock; - bool online; + bool available; bool idle; bool remote; struct tmigr_group *tmgroup; --=20 2.49.0 From nobody Tue Dec 16 07:30:55 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (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 AE972230D0F for ; Fri, 30 May 2025 14:21:29 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=170.10.129.124 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614891; cv=none; b=dIO38s3EMKOnjXuHAXdl/KaRuimbvHhP+cRknwYZ2bVJ/Iit/emej/ds1NcculMD/dWoXrmmoqWhQ26Vuep+ZzV5f/EISA4HRkTaNW5tKmy0t/LgcU1M0GmAGg5oxFykaUfMI/+UKGm9YIxBp8ztjzPHHCsvGRGcR1oXRumAZ+0= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614891; c=relaxed/simple; bh=H2wgocbVKcVtR7XzOPlkpLLqLftRpXu5qzvUNeXJ0LY=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=aLjyzXOEztpEF4WA0mcVzhuEqsTsavDD73UdREsjqgnOp7jCTu15IRzjcSRX9y3EwDBeZGUTgZF2jR5HVmlEJR92fS2SUJrT//ok1X9NZTxRVZCnGLWTy2c90lny5qDS/LS4vKWjFH8r3xGeV++cazCRcS48KHltZSE+v1rGMlk= 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=dJcqP5J3; arc=none smtp.client-ip=170.10.129.124 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="dJcqP5J3" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1748614888; 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=e+yGQU0A37MWbuh9tXwG6mkH726qolwRUhV6OXI4iwU=; b=dJcqP5J3oDRmTPg9gd5se+rgCw1BT+kFEDhvrJBloZkcd7xEeeHrTrzN1J5lC6q/vuNAtY 8YK+hBljzDxK91BLI5R8OneouapnyeLGloNeCFZn/Qm1ICsoF3FI1k+EHbO2z3U2Vw98Ja 0xxz3DYzxq2ovQ2VpShTDHDdRuT8uDQ= Received: from mx-prod-mc-02.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-589-B12uBvqCMw-0p8myFMe7ZQ-1; Fri, 30 May 2025 10:21:25 -0400 X-MC-Unique: B12uBvqCMw-0p8myFMe7ZQ-1 X-Mimecast-MFC-AGG-ID: B12uBvqCMw-0p8myFMe7ZQ_1748614884 Received: from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4]) (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-02.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id 24BB91956086; Fri, 30 May 2025 14:21:24 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.33.197]) by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id D9B0030001B7; Fri, 30 May 2025 14:21:20 +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 v6 2/6] timers: Add the available mask in timer migration Date: Fri, 30 May 2025 16:20:27 +0200 Message-ID: <20250530142031.215594-3-gmonaco@redhat.com> In-Reply-To: <20250530142031.215594-1-gmonaco@redhat.com> References: <20250530142031.215594-1-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 3.4.1 on 10.30.177.4 Content-Type: text/plain; charset="utf-8" Keep track of the CPUs available for timer migration in a cpumask. This prepares the ground to generalise the concept of unavailable CPUs. Signed-off-by: Gabriele Monaco --- kernel/time/timer_migration.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 7efd897c79599..25439f961ccf8 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -422,6 +422,9 @@ static unsigned int tmigr_crossnode_level __read_mostly; =20 static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); =20 +/* CPUs available for timer migration */ +static cpumask_var_t tmigr_available_cpumask; + #define TMIGR_NONE 0xFF #define BIT_CNT 8 =20 @@ -1449,6 +1452,7 @@ static int tmigr_cpu_unavailable(unsigned int cpu) raw_spin_lock_irq(&tmc->lock); tmc->available =3D false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); + cpumask_clear_cpu(cpu, tmigr_available_cpumask); =20 /* * CPU has to handle the local events on his own, when on the way to @@ -1459,7 +1463,7 @@ static int tmigr_cpu_unavailable(unsigned int cpu) raw_spin_unlock_irq(&tmc->lock); =20 if (firstexp !=3D KTIME_MAX) { - migrator =3D cpumask_any_but(cpu_online_mask, cpu); + migrator =3D cpumask_any(tmigr_available_cpumask); work_on_cpu(migrator, tmigr_trigger_active, NULL); } =20 @@ -1480,6 +1484,7 @@ static int tmigr_cpu_available(unsigned int cpu) if (!tmc->idle) __tmigr_cpu_activate(tmc); tmc->available =3D true; + cpumask_set_cpu(cpu, tmigr_available_cpumask); raw_spin_unlock_irq(&tmc->lock); return 0; } @@ -1801,6 +1806,11 @@ static int __init tmigr_init(void) if (ncpus =3D=3D 1) return 0; =20 + if (!zalloc_cpumask_var(&tmigr_available_cpumask, GFP_KERNEL)) { + ret =3D -ENOMEM; + goto err; + } + /* * Calculate the required hierarchy levels. Unfortunately there is no * reliable information available, unless all possible CPUs have been --=20 2.49.0 From nobody Tue Dec 16 07:30:55 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 AB9EB231A57 for ; Fri, 30 May 2025 14:21:33 +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=1748614895; cv=none; b=pNwgxYF91XvKdfsf3eCUWg3OGMAz5SZ2cjScJkbYVq+jt+s7EzzfG2/pHXuqEajHE2vCW2FqiIUadMhZLPtv6LZC5kDb0PRtsyekSNMrCZ723ZKB85xZhHKoHkcyARUpB6eY7R5jvUX+kOcEaEbVs9smRHbCat1ZKrwntsFziYA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614895; c=relaxed/simple; bh=bWF7cTzo58e8FEJAXTR1xHC4XdCu52qz9BUGyeHyfiY=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Ci4ln2qyoN6LAIfod5lDecYEudnXgOzDKcPYP1XtTkUSFL0lmSSheu7m9OKGaQ87eY4iO+0VYBhZGIy0ZriJ0PfbGF6EYLbHVOnRKmB0jpFQZM7ohRaFfiaV/DQVlbvEJv+tNCD6ob9VpDXgt1mDOkoCZsq/OoaEt7C9CKr8sjE= 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=YZZ9M9lp; 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="YZZ9M9lp" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1748614892; 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=PHKKHnaIUnGjmDt1R62BJHyQuPnUgNgmp6vg7RSSbZk=; b=YZZ9M9lpB7lMvTzPjOHxqYLnNof8ClD6+A69dv7txRNHMbydau2yiYVAjLq/amM+W5vWAv RcRx7NHWEmWX19JQbShOUnWcg3t/6apbZdUfvOaagGz74VStSHpHajUISWiqbT+Uc2fagX w4CLPSNNV19o4iVInKS6jUvuIocL4WE= Received: from mx-prod-mc-06.mail-002.prod.us-west-2.aws.redhat.com (ec2-35-165-154-97.us-west-2.compute.amazonaws.com [35.165.154.97]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-368-REaVvqZxOzyHSPFAVIZ-sg-1; Fri, 30 May 2025 10:21:28 -0400 X-MC-Unique: REaVvqZxOzyHSPFAVIZ-sg-1 X-Mimecast-MFC-AGG-ID: REaVvqZxOzyHSPFAVIZ-sg_1748614887 Received: from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4]) (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-06.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id BD600180035C; Fri, 30 May 2025 14:21:27 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.33.197]) by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id BB47530001B7; Fri, 30 May 2025 14:21:24 +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 v6 3/6] cgroup/cpuset: Rename update_unbound_workqueue_cpumask() to update_exclusion_cpumasks() Date: Fri, 30 May 2025 16:20:28 +0200 Message-ID: <20250530142031.215594-4-gmonaco@redhat.com> In-Reply-To: <20250530142031.215594-1-gmonaco@redhat.com> References: <20250530142031.215594-1-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 3.4.1 on 10.30.177.4 Content-Type: text/plain; charset="utf-8" update_unbound_workqueue_cpumask() updates unbound workqueues settings when there's a change in isolated CPUs, but it can be used for other subsystems requiring updated when isolated CPUs change. Generalise the name to update_exclusion_cpumasks() to prepare for other functions unrelated to workqueues to be called in that spot. Signed-off-by: Gabriele Monaco --- kernel/cgroup/cpuset.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 24b70ea3e6ce9..d0936b5d9920a 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1325,7 +1325,7 @@ static bool partition_xcpus_del(int old_prs, struct c= puset *parent, return isolcpus_updated; } =20 -static void update_unbound_workqueue_cpumask(bool isolcpus_updated) +static void update_exclusion_cpumasks(bool isolcpus_updated) { int ret; =20 @@ -1456,7 +1456,7 @@ static int remote_partition_enable(struct cpuset *cs,= int new_prs, list_add(&cs->remote_sibling, &remote_children); cpumask_copy(cs->effective_xcpus, tmp->new_cpus); spin_unlock_irq(&callback_lock); - update_unbound_workqueue_cpumask(isolcpus_updated); + update_exclusion_cpumasks(isolcpus_updated); cpuset_force_rebuild(); cs->prs_err =3D 0; =20 @@ -1497,7 +1497,7 @@ static void remote_partition_disable(struct cpuset *c= s, struct tmpmasks *tmp) compute_effective_exclusive_cpumask(cs, NULL, NULL); reset_partition_data(cs); spin_unlock_irq(&callback_lock); - update_unbound_workqueue_cpumask(isolcpus_updated); + update_exclusion_cpumasks(isolcpus_updated); cpuset_force_rebuild(); =20 /* @@ -1565,7 +1565,7 @@ static void remote_cpus_update(struct cpuset *cs, str= uct cpumask *xcpus, if (xcpus) cpumask_copy(cs->exclusive_cpus, xcpus); spin_unlock_irq(&callback_lock); - update_unbound_workqueue_cpumask(isolcpus_updated); + update_exclusion_cpumasks(isolcpus_updated); if (adding || deleting) cpuset_force_rebuild(); =20 @@ -1908,7 +1908,7 @@ static int update_parent_effective_cpumask(struct cpu= set *cs, int cmd, WARN_ON_ONCE(parent->nr_subparts < 0); } spin_unlock_irq(&callback_lock); - update_unbound_workqueue_cpumask(isolcpus_updated); + update_exclusion_cpumasks(isolcpus_updated); =20 if ((old_prs !=3D new_prs) && (cmd =3D=3D partcmd_update)) update_partition_exclusive_flag(cs, new_prs); @@ -2933,7 +2933,7 @@ static int update_prstate(struct cpuset *cs, int new_= prs) else if (isolcpus_updated) isolated_cpus_update(old_prs, new_prs, cs->effective_xcpus); spin_unlock_irq(&callback_lock); - update_unbound_workqueue_cpumask(isolcpus_updated); + update_exclusion_cpumasks(isolcpus_updated); =20 /* Force update if switching back to member & update effective_xcpus */ update_cpumasks_hier(cs, &tmpmask, !new_prs); --=20 2.49.0 From nobody Tue Dec 16 07:30:55 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (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 EE94C230BE8 for ; Fri, 30 May 2025 14:21:34 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=170.10.129.124 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614896; cv=none; b=kO7s5CI0m/7Ca15lqIgz1g4VuXxQBHPg/5a5+nWyMmHxscsmLisS7oWnk0V1L55MzKGdKXtsyDcXCP+tm58HuYSiYAifyoNindQG5Y9Q1QZQk1pRRExJkkwjKNmszukNk1/0CvhFwTMl/ZblLdVbhBekZ+hbeVjxDucC6bnWzOY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614896; c=relaxed/simple; bh=2r+ai2x7VLUVZxihBUTVsWqhgUDElI28Kw+ZCl/jX48=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=jgghI1ztbtM/r+2MxETE2WdJBrItWsTtIMzSUZk4kXsmhEqqSxNRboPXNmuNXEoJAzRDvaTdgaZJW+pqcn0KKcNq/4iwArlRbdq7cZSvunf62OHxrPZi81SvB4iN/ndMbreNpnfIhHY4XBULMAgz6WJhq0g4bpRgkyK4kBUdmbA= 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=Iucuuk4a; arc=none smtp.client-ip=170.10.129.124 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="Iucuuk4a" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1748614893; 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=kKwp7iz1+wrQvq1IugChVlL10tKuo/2JPWBotNxH1S0=; b=Iucuuk4avNBDJmVdj3N3opKsy8ZrMCWP0cJ8TOZ/euzEXq7MeW1xJqmu0beEjE7r22Q4MZ TWV42uJrOVW/if2mZOER0FqiiPBv07QCKzQbuSHm4FTD1lr+KUEHEfuN2bO671qtFjm3p/ ZEXgb1O+joWDnQPhhUS+iGvNcJEvgMI= Received: from mx-prod-mc-06.mail-002.prod.us-west-2.aws.redhat.com (ec2-35-165-154-97.us-west-2.compute.amazonaws.com [35.165.154.97]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-5-hpEHG0rGOcCah4yC41Yyvw-1; Fri, 30 May 2025 10:21:32 -0400 X-MC-Unique: hpEHG0rGOcCah4yC41Yyvw-1 X-Mimecast-MFC-AGG-ID: hpEHG0rGOcCah4yC41Yyvw_1748614891 Received: from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4]) (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-06.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id 4DFCF1800115; Fri, 30 May 2025 14:21:31 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.33.197]) by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 6DA0F30002C0; Fri, 30 May 2025 14:21:28 +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 v6 4/6] sched/isolation: Force housekeeping if isolcpus and nohz_full don't leave any Date: Fri, 30 May 2025 16:20:29 +0200 Message-ID: <20250530142031.215594-5-gmonaco@redhat.com> In-Reply-To: <20250530142031.215594-1-gmonaco@redhat.com> References: <20250530142031.215594-1-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 3.4.1 on 10.30.177.4 Content-Type: text/plain; charset="utf-8" Currently the user can set up isolcpus and nohz_full in such a way that leaves no housekeeping CPU (i.e. no CPU that is neither domain isolated nor nohz full). This can be a problem for other subsystems (e.g. the timer wheel imgration). Prevent this configuration by invalidating the last setting in case the union of isolcpus and nohz_full covers all CPUs. Signed-off-by: Gabriele Monaco --- kernel/sched/isolation.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 81bc8b329ef17..b3b348427d2b8 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -165,6 +165,18 @@ static int __init housekeeping_setup(char *str, unsign= ed long flags) } } =20 + /* Check in combination with the previously set cpumask */ + type =3D find_first_bit(&housekeeping.flags, HK_TYPE_MAX); + first_cpu =3D cpumask_first_and_and(cpu_present_mask, + housekeeping_staging, + housekeeping.cpumasks[type]); + if (first_cpu >=3D nr_cpu_ids || first_cpu >=3D setup_max_cpus) { + pr_warn("Housekeeping: must include one present CPU neither " + "in nohz_full=3D nor in isolcpus=3D, ignoring setting %s\n", + str); + goto free_housekeeping_staging; + } + iter_flags =3D flags & ~housekeeping.flags; =20 for_each_set_bit(type, &iter_flags, HK_TYPE_MAX) --=20 2.49.0 From nobody Tue Dec 16 07:30:55 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 9639723184B for ; Fri, 30 May 2025 14:21:40 +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=1748614902; cv=none; b=EC1HnnfEAyMK2jmbZ2+9LtUju/E/C7AtSRuS2RXyeRpFn2APVP1oAKmL6SmKWsRQ1ygOYZLcgGl6PN0jFLWUMo+zjbdAz3djDWPZvr9zrmG/TN/dJ/WKyE7UjXkPV4JN9HxEz3TBQwazE8tS9WzLLNaLMhuCKWwpXsAVeA7o5Mc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614902; c=relaxed/simple; bh=LHjYm8riG8W4R567kU14JUQ+LnoHd1D4nv6V0O90YEE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=FG3604U0NKodHW84xRor4566dcagNX4c/ytuRIwAOuYF0XPcAwclcTTe4XKbv6S5IZKB5AQWZdr/7CQg721nf0iBNzzQr3xCE0oAAeHTFjIdUwyi2lOp3xJYMoEL4XNjO3C+xllCJmLkW6Gg30Qd6B0fn+7STzMdHxvqFDMyBjM= 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=ZYHfB3+q; 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="ZYHfB3+q" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1748614899; 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=eLbPcSf4WIqCItcJwknSUcI5TkWbTxEt4NB28H4eqo0=; b=ZYHfB3+qsSA38XSeJjh4UoBHsqjppl3Rv4tkduihZUDEF59zt9vGe99GYdegv6ohT6rnSC GINxYs/Hh+uE+drjOL4aYw30iJnSvePDbSiuRaODqDERDfK7CxKLqYuG8JG0RP8jcG904U tEpOIAW5QWys6Vn7olH+85VMJ+bw6bQ= Received: from mx-prod-mc-03.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-394-h8CJQSRdMoCgxO7AsqtrAA-1; Fri, 30 May 2025 10:21:36 -0400 X-MC-Unique: h8CJQSRdMoCgxO7AsqtrAA-1 X-Mimecast-MFC-AGG-ID: h8CJQSRdMoCgxO7AsqtrAA_1748614895 Received: from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4]) (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-03.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id DCDB61955D84; Fri, 30 May 2025 14:21:34 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.33.197]) by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 1745B30001B7; Fri, 30 May 2025 14:21:31 +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 v6 5/6] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping Date: Fri, 30 May 2025 16:20:30 +0200 Message-ID: <20250530142031.215594-6-gmonaco@redhat.com> In-Reply-To: <20250530142031.215594-1-gmonaco@redhat.com> References: <20250530142031.215594-1-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 3.4.1 on 10.30.177.4 Content-Type: text/plain; charset="utf-8" Currently the user can set up isolated cpus via cpuset and nohz_full in such a way that leaves no housekeeping CPU (i.e. no CPU that is neither domain isolated nor nohz full). This can be a problem for other subsystems (e.g. the timer wheel imgration). Prevent this configuration by blocking any assignation that would cause the union of domain isolated cpus and nohz_full to covers all CPUs. Signed-off-by: Gabriele Monaco --- kernel/cgroup/cpuset.c | 56 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index d0936b5d9920a..e3494ed677f5c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1261,6 +1261,19 @@ static void isolated_cpus_update(int old_prs, int ne= w_prs, struct cpumask *xcpus cpumask_andnot(isolated_cpus, isolated_cpus, xcpus); } =20 +/* + * isolated_cpus_should_update - Returns if the isolated_cpus mask needs u= pdate + * @prs: new or old partition_root_state + * @parent: parent cpuset + * Return: true if isolated_cpus needs modification, false otherwise + */ +static bool isolated_cpus_should_update(int prs, struct cpuset *parent) +{ + if (!parent) + parent =3D &top_cpuset; + return prs !=3D parent->partition_root_state; +} + /* * partition_xcpus_add - Add new exclusive CPUs to partition * @new_prs: new partition_root_state @@ -1325,6 +1338,35 @@ static bool partition_xcpus_del(int old_prs, struct = cpuset *parent, return isolcpus_updated; } =20 +/* + * isolcpus_nohz_conflict - check for isolated & nohz_full conflicts + * @new_cpus: cpu mask for cpus that are going to be isolated + * Return: true if there is conflict, false otherwise + * + * If nohz_full is enabled and we have isolated CPUs, their combination mu= st + * still leave housekeeping CPUs. + */ +static bool isolcpus_nohz_conflict(struct cpumask *new_cpus) +{ + cpumask_var_t full_hk_cpus; + int res =3D false; + + if (!housekeeping_enabled(HK_TYPE_KERNEL_NOISE)) + return false; + + if (!alloc_cpumask_var(&full_hk_cpus, GFP_KERNEL)) + return true; + + cpumask_and(full_hk_cpus, housekeeping_cpumask(HK_TYPE_KERNEL_NOISE), + housekeeping_cpumask(HK_TYPE_DOMAIN)); + cpumask_and(full_hk_cpus, full_hk_cpus, cpu_online_mask); + if (!cpumask_weight_andnot(full_hk_cpus, new_cpus)) + res =3D true; + + free_cpumask_var(full_hk_cpus); + return res; +} + static void update_exclusion_cpumasks(bool isolcpus_updated) { int ret; @@ -1450,6 +1492,9 @@ static int remote_partition_enable(struct cpuset *cs,= int new_prs, cpumask_intersects(tmp->new_cpus, subpartitions_cpus) || cpumask_subset(top_cpuset.effective_cpus, tmp->new_cpus)) return PERR_INVCPUS; + if (isolated_cpus_should_update(new_prs, NULL) && + isolcpus_nohz_conflict(tmp->new_cpus)) + return PERR_HKEEPING; =20 spin_lock_irq(&callback_lock); isolcpus_updated =3D partition_xcpus_add(new_prs, NULL, tmp->new_cpus); @@ -1548,6 +1593,9 @@ static void remote_cpus_update(struct cpuset *cs, str= uct cpumask *xcpus, else if (cpumask_intersects(tmp->addmask, subpartitions_cpus) || cpumask_subset(top_cpuset.effective_cpus, tmp->addmask)) cs->prs_err =3D PERR_NOCPUS; + else if (isolated_cpus_should_update(prs, NULL) && + isolcpus_nohz_conflict(tmp->addmask)) + cs->prs_err =3D PERR_HKEEPING; if (cs->prs_err) goto invalidate; } @@ -1879,6 +1927,12 @@ static int update_parent_effective_cpumask(struct cp= uset *cs, int cmd, return err; } =20 + if (deleting && isolated_cpus_should_update(new_prs, parent) && + isolcpus_nohz_conflict(tmp->delmask)) { + cs->prs_err =3D PERR_HKEEPING; + return PERR_HKEEPING; + } + /* * Change the parent's effective_cpus & effective_xcpus (top cpuset * only). @@ -2899,6 +2953,8 @@ static int update_prstate(struct cpuset *cs, int new_= prs) * Need to update isolated_cpus. */ isolcpus_updated =3D true; + if (isolcpus_nohz_conflict(cs->effective_xcpus)) + err =3D PERR_HKEEPING; } else { /* * Switching back to member is always allowed even if it --=20 2.49.0 From nobody Tue Dec 16 07:30:55 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (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 9264E233722 for ; Fri, 30 May 2025 14:21:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=170.10.129.124 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614907; cv=none; b=W6/XAH4WiaPx24qrfPFP3of+FBvLjUW+BTwwvs770twvcwOy+l/9G23QihMtNN0v05Agax5sxfjE4IMzvAvq7qZmSNE4ylN9p7fgl+xQHY6QDV0Gb3IvUjKseUnoSNhFVzuoVvRzYlbzV5WVPA5Cipjyo4PxZDwyhsb5m3ZxtAQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748614907; c=relaxed/simple; bh=bXxzjbF7ADDiXfnJhf6+XlGkn+bU/6XfFSvWj8Zgktc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=cMbHSPQ2TYhLmH0STvrfzD/9egMcRdrF5Zcl2mm594a02BDYiMA63qD54ZeCrdvNh1U9QG9Ipg00Gl/bpTx9ICu8TUR66OuWIKnF8FxYOryRFENzZmHhlaTEwwvlDCEwDPXSt8Iqcr1tK4ODz1CYc0xLH6NkivgrbcOp5J1i9UM= 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=FLyn90+9; arc=none smtp.client-ip=170.10.129.124 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="FLyn90+9" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1748614904; 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=q5esWHN7Lixngxf6oIjmMRA2wcLPjjPu3cKumbAoaDU=; b=FLyn90+9PvkWG9paFWjKJsJ3D1xKDukXt+YqkwomHn6JHKdoaBCMs+T1EprEXv/UFz2Ea5 2sQn2hYMiNLCcVsnBBZdphne58W4Cl95ffN5v3jw0HEmnKRWDfgZ6SDm9HS08fDAY1b0w8 CeSsPxxV79J2Ac+ca1S1WCTDueEzJS4= Received: from mx-prod-mc-08.mail-002.prod.us-west-2.aws.redhat.com (ec2-35-165-154-97.us-west-2.compute.amazonaws.com [35.165.154.97]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-647-2WcHFq9PMu66xnhZmP7Eww-1; Fri, 30 May 2025 10:21:40 -0400 X-MC-Unique: 2WcHFq9PMu66xnhZmP7Eww-1 X-Mimecast-MFC-AGG-ID: 2WcHFq9PMu66xnhZmP7Eww_1748614899 Received: from mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.4]) (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-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id 190391800ECC; Fri, 30 May 2025 14:21:39 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.33.197]) by mx-prod-int-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id AF17B30001B7; Fri, 30 May 2025 14:21:35 +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 v6 6/6] timers: Exclude isolated cpus from timer migation Date: Fri, 30 May 2025 16:20:31 +0200 Message-ID: <20250530142031.215594-7-gmonaco@redhat.com> In-Reply-To: <20250530142031.215594-1-gmonaco@redhat.com> References: <20250530142031.215594-1-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 3.4.1 on 10.30.177.4 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. 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) 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 isolated and offline; 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) 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, we 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). Signed-off-by: Gabriele Monaco --- include/linux/timer.h | 9 ++++++ kernel/cgroup/cpuset.c | 3 ++ kernel/time/timer_migration.c | 54 +++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+) diff --git a/include/linux/timer.h b/include/linux/timer.h index 10596d7c3a346..a8b683d9ce25d 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -190,4 +190,13 @@ 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(cpumask_var_t exclude_cpumask); +#else +static inline int tmigr_isolated_exclude_cpumask(cpumask_var_t exclude_cpu= mask) +{ + return 0; +} +#endif + #endif diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index e3494ed677f5c..7b26226f2a276 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1378,6 +1378,9 @@ 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 25439f961ccf8..a14fbca7457fe 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" @@ -1449,6 +1450,13 @@ static int tmigr_cpu_unavailable(unsigned int cpu) int migrator; u64 firstexp; =20 + /* + * 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. + */ + if (!tick_nohz_cpu_hotpluggable(cpu)) + return 0; raw_spin_lock_irq(&tmc->lock); tmc->available =3D false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); @@ -1478,6 +1486,20 @@ static int tmigr_cpu_available(unsigned int cpu) if (WARN_ON_ONCE(!tmc->tmgroup)) return -EINVAL; =20 + /* + * Domain isolated CPUs don't participate in timer migration, nohz_full + * CPUs are still part of the hierarchy but are always considered idle. + * Additionally, the tick CPU during nohz_full cannot be disabled. + * Checking here guarantees that CPUs isolated at boot (e.g. isolcpus) + * are not marked as available when they first become online. + * During runtime, any offline isolated CPU is also not incorrectly + * marked as available once it gets back online. + */ + if ((!housekeeping_cpu(cpu, HK_TYPE_DOMAIN) || + cpuset_cpu_is_isolated(cpu)) && + housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE) && + tick_nohz_cpu_hotpluggable(cpu)) + return 0; raw_spin_lock_irq(&tmc->lock); trace_tmigr_cpu_available(tmc); tmc->idle =3D timer_base_is_idle(); @@ -1489,6 +1511,38 @@ static int tmigr_cpu_available(unsigned int cpu) return 0; } =20 +static void tmigr_remote_cpu_unavailable(void *ignored) +{ + tmigr_cpu_unavailable(smp_processor_id()); +} + +static void tmigr_remote_cpu_available(void *ignored) +{ + tmigr_cpu_available(smp_processor_id()); +} + +int tmigr_isolated_exclude_cpumask(cpumask_var_t exclude_cpumask) +{ + cpumask_var_t cpumask; + int ret =3D 0; + + 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_mask(cpumask, tmigr_remote_cpu_unavailable, NULL, 0); + + cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); + cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); + on_each_cpu_mask(cpumask, tmigr_remote_cpu_available, NULL, 0); + + free_cpumask_var(cpumask); + return ret; +} + static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, int node) { --=20 2.49.0