From nobody Fri Dec 19 17:35:25 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 1021528BABD for ; Tue, 15 Apr 2025 10:25:30 +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=1744712732; cv=none; b=UszRLfy8ti3HSwYE8o9kZ3s9KA4N9E7CWMYpampknGkgk0rZSWo8Dx7jMRiyOnWIavgSEKBkuEGFqcSnZ7dYhkii5qVXAWs8DjJtvIiCczf0LbuZhh67a8BEghc1rtN4m5ML0R7NWTnTsHPT8RbudRLUd8OaHwWcPBvxqKO4CkQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1744712732; c=relaxed/simple; bh=tDnXOE4HmetRM9ergwtwOk0oofTBYTeowkzenHyMGxo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=toAhAzcF51yB9PC1p07bIUNE0k5hWj3sl4y6Kh4Tq18edbE4S95TVlh5L5tJLJUS1t0XbNr+BiA5Hx+hvUDlOeNQqPg3Ut9V/StIeSc/ezhtRsapcqd7UuyfuUYIz6DEAAVJyHDSBy2TXtq9fBfu47cZEny9t4XXn+ZxJ5Oxnp0= 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=VecGBN52; 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="VecGBN52" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1744712729; 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=VecGBN52NeJZfv65zSWXw/UqoX01vDvVFaJQt7PrgI67RZ51JgSjed6T2g/pKSlg3fXjoO tGpPev2nUgp9WHewsbJCuoBq1txcIuTJwisQhPbt4EB2xzhEck0Z8+DFLhrx7emQOaSIth FMVe9AuOaUZ22tqyZZs0P1/KwLwZbJw= 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-641-cmHzAyqKPRejHV9fke4t2Q-1; Tue, 15 Apr 2025 06:25:26 -0400 X-MC-Unique: cmHzAyqKPRejHV9fke4t2Q-1 X-Mimecast-MFC-AGG-ID: cmHzAyqKPRejHV9fke4t2Q_1744712725 Received: from mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.111]) (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 B7FBF1955DC6; Tue, 15 Apr 2025 10:25:25 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.32.90]) by mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id AA3D61808867; Tue, 15 Apr 2025 10:25:23 +0000 (UTC) From: Gabriele Monaco To: linux-kernel@vger.kernel.org, Frederic Weisbecker , Thomas Gleixner , Waiman Long Cc: Gabriele Monaco Subject: [PATCH v2 1/3] timers: Rename tmigr 'online' bit to 'available' Date: Tue, 15 Apr 2025 12:25:02 +0200 Message-ID: <20250415102500.100415-6-gmonaco@redhat.com> In-Reply-To: <20250415102500.100415-5-gmonaco@redhat.com> References: <20250415102500.100415-5-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 10.30.177.111 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 Fri Dec 19 17:35:25 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 067AA28DEE9 for ; Tue, 15 Apr 2025 10:25:33 +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=1744712735; cv=none; b=m4VQhgfhpD6qS3YWR5g0SU60Ji6neQgtjnfoPsWG+fRfcRTEZJXLefSKSRJUWs50ZgTi5Lp38ZE+1u6XVOpKQE+Yv+txUTf5tUJFx/Xl1jYqLLz55WYyOObSFeCwBpplSmrVh6+1T6a1kjY2U5amjJMLAv9ib7samegiyY08X6A= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1744712735; c=relaxed/simple; bh=tCUwMlpJ0PLdnGZk91rYJ+Bc4HAjRXkzO9BZr3rqAk8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=U4cQ22LGkNnzsTwS83BnzIBUlNA3qp0NZj5ISdRyutJKWmPhIgTgotrgcdOwYj9pcOFJKoJ/lN7QgcAdt+39vo3/xokToaaLVXwlcNXoKp+EInaLXFpIlYpXpsUR9myjopaFhsty83VFdiyr8F1LhyjCDbXLOXktNDr/cUzUqFY= 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=NdnNeQyh; 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="NdnNeQyh" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1744712732; 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=lsBUT7u//iK7sLk6YoMhB4VJF0MdfDCXAnznK/PHwiQ=; b=NdnNeQyh8LV36GhZ1Vskfxz0mpdmzrBWXr/FQUMLLa9iU9zAL/GcqBgPisSc6JrTgA1P7j abbY3UjgXf5snvdx2x55Wcf9RdHqFx5bEBpRrWyLM58/9bc09qVYjxuv+2/8f/5eSZ4yqg T3fNJFZNRLYoTa71dvuQnceSrMfH+0s= 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-111-L8lAnt0SPhGnrPk8ofJ7RQ-1; Tue, 15 Apr 2025 06:25:29 -0400 X-MC-Unique: L8lAnt0SPhGnrPk8ofJ7RQ-1 X-Mimecast-MFC-AGG-ID: L8lAnt0SPhGnrPk8ofJ7RQ_1744712728 Received: from mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.111]) (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 59B421955BC9; Tue, 15 Apr 2025 10:25:28 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.32.90]) by mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 51EA71809B67; Tue, 15 Apr 2025 10:25:26 +0000 (UTC) From: Gabriele Monaco To: linux-kernel@vger.kernel.org, Frederic Weisbecker , Thomas Gleixner , Waiman Long Cc: Gabriele Monaco Subject: [PATCH v2 2/3] timers: Add the available mask in timer migration Date: Tue, 15 Apr 2025 12:25:03 +0200 Message-ID: <20250415102500.100415-7-gmonaco@redhat.com> In-Reply-To: <20250415102500.100415-5-gmonaco@redhat.com> References: <20250415102500.100415-5-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 10.30.177.111 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..1fae38fbac8c2 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 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 Fri Dec 19 17:35:25 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 482F128E5EE for ; Tue, 15 Apr 2025 10:25:37 +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=1744712739; cv=none; b=qwVX/m5VaDUieszLR4kRzHwM1nR1MXECsPY2FoQejY1ef/WYcCeFREJ+HzIlE1UUGtUhm9Ikrhic9SF9Te0GEEard8Bv737N7ALUjm7D7AKPHXsnRu/cw7Fg1jTwnWSSjtB2Gn6SATjN1pNYAb2we2KelP68gyguHM+2OLHAifg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1744712739; c=relaxed/simple; bh=ptXqHbgHmEUgzcj0KfxsRu45L6G9e4nOytIJeY9ps1M=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=kscSKdcwtHpTbLCcGK+9gT/zGwUJKMNxWAmHdVrywOI3BxOoxvgfbH/+i8PgaJW5Y93cOftfr2heuoe5vtlwpsGfoJJxUG7dMZ+EQrRe0PTiRddG9Z0CWf83I05+aMT3TGix5EUI+fmfQtxRkDaaEU3jgE3GQR+/mnfKeGQsLDk= 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=igjlik+C; 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="igjlik+C" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1744712736; 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=hhxu4PEoJN6tD2HkTMH28lQiJH5iXa7MS3MgOAglwDE=; b=igjlik+CshCFdvyKFLqbWO6LKNc+o8BpToXfmwa8Z0Fyx9DZ82xqICBScEu6IjJxs/rxmA F48omPcVGa7m7x6C4eeW0F9YpQyfPuMlhNCkEWi3+PpRQPKxNY3QtcVQTsQPJzBIiQArpU kxGiCjp4x3/GZVNJ6f/0RtX3s3OUYEk= Received: from mx-prod-mc-01.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-679-P6yWfUfeP9mImkYkZegOyg-1; Tue, 15 Apr 2025 06:25:32 -0400 X-MC-Unique: P6yWfUfeP9mImkYkZegOyg-1 X-Mimecast-MFC-AGG-ID: P6yWfUfeP9mImkYkZegOyg_1744712732 Received: from mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com [10.30.177.111]) (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-01.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id EAFB319560B3; Tue, 15 Apr 2025 10:25:31 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.44.32.90]) by mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 02BC31808867; Tue, 15 Apr 2025 10:25:28 +0000 (UTC) From: Gabriele Monaco To: linux-kernel@vger.kernel.org, Frederic Weisbecker , Thomas Gleixner , Waiman Long Cc: Gabriele Monaco Subject: [PATCH v2 3/3] timers: Exclude isolated cpus from timer migation Date: Tue, 15 Apr 2025 12:25:04 +0200 Message-ID: <20250415102500.100415-8-gmonaco@redhat.com> In-Reply-To: <20250415102500.100415-5-gmonaco@redhat.com> References: <20250415102500.100415-5-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 10.30.177.111 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 idle if: * is in the isolcpus list * is in the nohz_full list * is in an isolated cpuset 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 prevents 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 | 6 ++++++ kernel/cgroup/cpuset.c | 14 ++++++++------ kernel/time/tick-internal.h | 1 + kernel/time/timer.c | 10 ++++++++++ kernel/time/timer_migration.c | 24 +++++++++++++++++++++--- 5 files changed, 46 insertions(+), 9 deletions(-) diff --git a/include/linux/timer.h b/include/linux/timer.h index 10596d7c3a346..4722e075d9843 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -190,4 +190,10 @@ int timers_dead_cpu(unsigned int cpu); #define timers_dead_cpu NULL #endif =20 +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void tmigr_isolated_exclude_cpumask(cpumask_var_t exclude_cpumask); +#else +static inline void tmigr_isolated_exclude_cpumask(cpumask_var_t exclude_cp= umask) { } +#endif + #endif diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 306b604300914..866b4b8188118 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1323,7 +1323,7 @@ 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 @@ -1334,6 +1334,8 @@ static void update_unbound_workqueue_cpumask(bool iso= lcpus_updated) =20 ret =3D workqueue_unbound_exclude_cpumask(isolated_cpus); WARN_ON_ONCE(ret < 0); + + tmigr_isolated_exclude_cpumask(isolated_cpus); } =20 /** @@ -1454,7 +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 @@ -1495,7 +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 /* @@ -1563,7 +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 @@ -1906,7 +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); @@ -2931,7 +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); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index faac36de35b9e..75580f7c69c64 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -167,6 +167,7 @@ extern void fetch_next_timer_interrupt_remote(unsigned = long basej, u64 basem, extern void timer_lock_remote_bases(unsigned int cpu); extern void timer_unlock_remote_bases(unsigned int cpu); extern bool timer_base_is_idle(void); +extern bool timer_base_remote_is_idle(unsigned int cpu); extern void timer_expire_remote(unsigned int cpu); # endif #else /* CONFIG_NO_HZ_COMMON */ diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 4d915c0a263c3..f04960091eba9 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2162,6 +2162,16 @@ bool timer_base_is_idle(void) return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle); } =20 +/** + * timer_base_remote_is_idle() - Return whether timer base is set idle for= cpu + * + * Returns value of local timer base is_idle value for remote cpu. + */ +bool timer_base_remote_is_idle(unsigned int cpu) +{ + return per_cpu(timer_bases[BASE_LOCAL].is_idle, cpu); +} + static void __run_timer_base(struct timer_base *base); =20 /** diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 1fae38fbac8c2..6fe6ca798e98d 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" @@ -1445,7 +1446,7 @@ static long tmigr_trigger_active(void *unused) =20 static int tmigr_cpu_unavailable(unsigned int cpu) { - struct tmigr_cpu *tmc =3D this_cpu_ptr(&tmigr_cpu); + struct tmigr_cpu *tmc =3D per_cpu_ptr(&tmigr_cpu, cpu); int migrator; u64 firstexp; =20 @@ -1472,15 +1473,18 @@ static int tmigr_cpu_unavailable(unsigned int cpu) =20 static int tmigr_cpu_available(unsigned int cpu) { - struct tmigr_cpu *tmc =3D this_cpu_ptr(&tmigr_cpu); + struct tmigr_cpu *tmc =3D per_cpu_ptr(&tmigr_cpu, cpu); =20 /* Check whether CPU data was successfully initialized */ if (WARN_ON_ONCE(!tmc->tmgroup)) return -EINVAL; =20 + /* Isolated CPUs don't participate in timer migration */ + if (cpu_is_isolated(cpu)) + return 0; raw_spin_lock_irq(&tmc->lock); trace_tmigr_cpu_available(tmc); - tmc->idle =3D timer_base_is_idle(); + tmc->idle =3D timer_base_remote_is_idle(cpu); if (!tmc->idle) __tmigr_cpu_activate(tmc); tmc->available =3D true; @@ -1489,6 +1493,20 @@ static int tmigr_cpu_available(unsigned int cpu) return 0; } =20 +void tmigr_isolated_exclude_cpumask(cpumask_var_t exclude_cpumask) +{ + int cpu; + + lockdep_assert_cpus_held(); + + for_each_cpu_and(cpu, exclude_cpumask, tmigr_available_cpumask) + tmigr_cpu_unavailable(cpu); + + for_each_cpu_andnot(cpu, cpu_online_mask, exclude_cpumask) + if (!cpumask_test_cpu(cpu, tmigr_available_cpumask)) + tmigr_cpu_available(cpu); +} + static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, int node) { --=20 2.49.0