From nobody Sun Oct 5 10:44:51 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 9EAD528B7DD for ; Wed, 6 Aug 2025 09:39:35 +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=1754473177; cv=none; b=Imkjkcw635QySdNDBjdcHPkHxAYjYesVQwCeBf5enau1GC2oijFLDxvgld0BWsY03EWCE9UkwBhMuBUXZindoWQa3KAn3LFpMuxK/iA88FdklhfJ0K26gx67qked54JaPYYiVj28c/zWap5Tfjs0UVJ6u2kCG9a5rY7nWkiF7IU= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1754473177; c=relaxed/simple; bh=CRY0+GnaBWrlfpe8iXJlxsyVpbGWBfiDOGycoYwQiYk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=a11nn8mOpYT5ahmAufuWnH5TCQdAT4D98PumUR5gtOCQS0J9fAKvDqqf/kKlqWGHfeociF/3C48GxGb3uxElaxYIZm5JL6Vxx4FbMWoBlfNbS/+0UQieCdKWAkeGRaf48bRXNlKl6UazjrwP11rpGLEUxoO+Mg539MiILBV/Es8= 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=CJlSE2U3; 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="CJlSE2U3" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1754473174; 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=c/4Yb/ZEMmy5bdm/K/cc0fxTqmOnDgZxgOXUTfhox3U=; b=CJlSE2U3vGkmukmwPBuylysx7YPAgvTxZVpXpzNLPyG958a+QTWL/kZvikOMTcymvg5VhW 3zfR837gm7pPTSM8crOzjW6afYFxAXYBNq4RsP4Ow5gxz+ykAMyp0Mfbqk2ck54El+NBAn m8tWQ41N98PYEvw7uPsD3epMd/WpD+Q= 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-256-wZvVtGD7PkSwOCI_G3HWHg-1; Wed, 06 Aug 2025 05:39:31 -0400 X-MC-Unique: wZvVtGD7PkSwOCI_G3HWHg-1 X-Mimecast-MFC-AGG-ID: wZvVtGD7PkSwOCI_G3HWHg_1754473170 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-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTPS id 63D14180036F; Wed, 6 Aug 2025 09:39:30 +0000 (UTC) Received: from gmonaco-thinkpadt14gen3.rmtit.com (unknown [10.45.224.173]) by mx-prod-int-08.mail-002.prod.us-west-2.aws.redhat.com (Postfix) with ESMTP id 010C11800446; Wed, 6 Aug 2025 09:39:27 +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 v10 7/8] cgroup/cpuset: Fail if isolated and nohz_full don't leave any housekeeping Date: Wed, 6 Aug 2025 11:38:54 +0200 Message-ID: <20250806093855.86469-8-gmonaco@redhat.com> In-Reply-To: <20250806093855.86469-1-gmonaco@redhat.com> References: <20250806093855.86469-1-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 10.30.177.111 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. Acked-by: Frederic Weisbecker Signed-off-by: Gabriele Monaco --- kernel/cgroup/cpuset.c | 57 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 6e3f44ffaa21..7b66ccedbc53 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1275,6 +1275,19 @@ 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 @@ -1339,6 +1352,36 @@ 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_andnot(full_hk_cpus, full_hk_cpus, isolated_cpus); + 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; @@ -1464,6 +1507,9 @@ static int remote_partition_enable(struct cpuset *cs,= int new_prs, if (!cpumask_intersects(tmp->new_cpus, cpu_active_mask) || 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); @@ -1563,6 +1609,9 @@ 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; } @@ -1914,6 +1963,12 @@ 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). @@ -2934,6 +2989,8 @@ 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 2.50.1