From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-dl1-f48.google.com (mail-dl1-f48.google.com [74.125.82.48]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 382D239A04E for ; Mon, 13 Apr 2026 07:45:11 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.82.48 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1776066312; cv=none; b=LDZINAr2ryG35zsu458aAMtutWhoqtPUP7QGQsWnrM8tTvhW1Y3fD8cCQ/GxbpZF1xAY2+6iSzDqPszCx1DDTMK0tlwlAJ2w/SfbN2bKmK6R+PvMUgXqsi439Zoiv8gTQdlpEStA5Tm8x0RZXAUFbCSqYXSZY/KIJyzx5wUsXDE= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1776066312; c=relaxed/simple; bh=BGMSu12m2mn0mDNFXLqooOThMAxDQT2Mpe3BqGwJF8Y=; h=From:Date:Subject:MIME-Version:Content-Type:Message-Id:References: In-Reply-To:To:Cc; b=UcREuSHV0XKspwi8sJWzI6ekR3exeTL/CAG5owfskSnEqR3RARkcIu8J97TX1gg+SqWCxXfOw1He0hSkAwh0WDF2qDWdymjF/VcwWj5hgQxYNmTwVXQz3i8r0cmjV3rPsIUhzMFZSYFQxOu3KlE1GpigJB6tfRlH58QEudHm28g= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=lLKXdpPB; arc=none smtp.client-ip=74.125.82.48 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="lLKXdpPB" Received: by mail-dl1-f48.google.com with SMTP id a92af1059eb24-12732165d1eso13693322c88.1 for ; Mon, 13 Apr 2026 00:45:10 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1776066310; x=1776671110; darn=vger.kernel.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=SQ44lW/U6rKhLB+VxvVCzN9hwjYmEMV1dg+CBNB6cSw=; b=lLKXdpPBMfBYy76+CaTZ33G0g/SF17GwUZRxr6TaGpM1c/pn9+CFp7k6HDUpgtWK+w 12P+NEGwSwE/oboTGvqWLLkki9Uq+qJDl6Vjdne/YwUZpCpRuEOIkKqDO9knbPi0LASN 8lUgZLI3pMxtaWTNiP1FVf5G8wuYV+iDs+TTGmZ4r4Hzvtqp5HD5aLGm4QsydsbewFF6 boXG+moFtgYW8VPVYRCf2LccEt3drxdXLAqbcmM2piO0XSd3F2PuroqdMD2wwCpcD4he /bbOqj2cHlUVAmuqwal7MhQb2sLwnjjkUDUya0oSuIWh7D+Rj8waMGiz+8b/rscAg6FD wZCA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1776066310; x=1776671110; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-gg:x-gm-message-state:from:to :cc:subject:date:message-id:reply-to; bh=SQ44lW/U6rKhLB+VxvVCzN9hwjYmEMV1dg+CBNB6cSw=; b=U4oQnySBjXpqD1uEX8HbUfWCqtqizl3hM33wIwpSu8euUt3LKV40M96SlFLhJBZApJ utFpe9GJ/3WLJDRPn4FcfKZHBT8HNT+JzDZuKGlpM7KHaDopGNjSVzXn1U7TDJv9Yn+V fYBx5qN1dVTXEPo02n8u2KWvHO3r+phz7/UpdNZtb5SBWsGlD0dFGtnncj7JiVC/4yYj KS8O3Vj3pD6NsJ1E/ItdNMY0FHbcLxD+LgJIe6zCpnHOi8AWtThI5P8v0ANRSXF0de+H /RZYJ606VawMOKnBTD5IQLnQVg1fCZZrWF27j+Ux4tJTWL93kxe8Qql8wqOwPSI4FiZv i/Bw== X-Forwarded-Encrypted: i=1; AFNElJ/38zejVrc8VcRo8nmMlpSLQk/OgSyJ+3vNVqBfuw5RxthzS4pK20Js02H9t33/+8SXWiZxjWTSnulokC+FVzQ=@vger.kernel.org X-Gm-Message-State: AOJu0YwyYJe3rTMO1sfdiUex1bah4muVGV56UKhsaOoyNZ+ASjyTj0fT wbL79svdKsdjB+bOoOIYcxhD3L/v0CpC5CbkqxQp+V2eSjJ0e8RbmhVI X-Gm-Gg: AeBDieubehinkBZDigARTFiVy8Zn2qll++oFYc5qTQ2+kgZhsDkHypE3AF+LO+CyYN9 Qm2hq/227mcZZLgQmHgCrZ1IaXpm/f3JGiEn5fxmQqJ3JXvKE3U5rfsuqttXHj9tyizHZEKlamV 80o4X87UxI/XS95M9bxrxCzH0AGQNEyogOSkxyMT7NBXuNnJze+PbDe+J5QtJIzcC0dGO5XARLn bSDvGThcEsE07EcvWBCLP2FgBp2Tg1UwlnrzFU724b/OWCm4ielmDwHWUWexzW93QsnRpn12Omy MoAw/wunWcdmM59Qeghv2TmFFKHdp2MpYFDFUGLVhcDdvFhSoUHUO+CLDWgjAKPlPIBHfJw8D/V o4z2bkX0Gt/EDFYjXuOs7kjsuoP4JvhWAikOZYM70J9jIqD2ToIxn8XU6LS18eGi7nQSgTYAbDO uNX8D/laBYYlx4kQVg X-Received: by 2002:a05:7022:622:b0:128:df80:1852 with SMTP id a92af1059eb24-12c34e55bc9mr6509824c88.9.1776066310149; Mon, 13 Apr 2026 00:45:10 -0700 (PDT) Received: from wujing. ([74.48.213.230]) by smtp.gmail.com with ESMTPSA id a92af1059eb24-12c347fa2c9sm12884610c88.15.2026.04.13.00.44.59 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 13 Apr 2026 00:45:09 -0700 (PDT) From: Qiliang Yuan Date: Mon, 13 Apr 2026 15:43:16 +0800 Subject: [PATCH v2 10/12] cgroup/cpuset: Implement SMT-aware grouping and safety guards Precedence: bulk X-Mailing-List: linux-kselftest@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Message-Id: <20260413-wujing-dhm-v2-10-06df21caba5d@gmail.com> References: <20260413-wujing-dhm-v2-0-06df21caba5d@gmail.com> In-Reply-To: <20260413-wujing-dhm-v2-0-06df21caba5d@gmail.com> To: Ingo Molnar , Peter Zijlstra , Juri Lelli , Vincent Guittot , Dietmar Eggemann , Steven Rostedt , Ben Segall , Mel Gorman , Valentin Schneider , "Paul E. McKenney" , Frederic Weisbecker , Neeraj Upadhyay , Joel Fernandes , Josh Triplett , Boqun Feng , Uladzislau Rezki , Mathieu Desnoyers , Lai Jiangshan , Zqiang , Anna-Maria Behnsen , Ingo Molnar , Thomas Gleixner , Tejun Heo , Andrew Morton , Vlastimil Babka , Suren Baghdasaryan , Michal Hocko , Brendan Jackman , Johannes Weiner , Zi Yan , Waiman Long , Chen Ridong , =?utf-8?q?Michal_Koutn=C3=BD?= , Jonathan Corbet , Shuah Khan , Shuah Khan Cc: linux-kernel@vger.kernel.org, rcu@vger.kernel.org, linux-mm@kvack.org, cgroups@vger.kernel.org, linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org, Qiliang Yuan X-Mailer: b4 0.13.0 Dynamic Housekeeping Management allows runtime configuration of kernel overhead isolation boundaries. However, configuring CPUMASKs that separate SMT siblings (e.g., placing one hardware thread in the housekeeping mask and leaving the other isolated) can lead to severe performance degradation due to shared L1 caches and pipeline resources. This patch introduces `cpuset.housekeeping.smt_aware`, a robust safety guard to prevent user-space from splitting SMT sibling pairs across isolation boundaries. When `cpuset.housekeeping.smt_aware` is enabled (1): - Any write to `cpuset.housekeeping.cpus` must include all SMT siblings for each CPU presented in the new mask (verified via `topology_sibling_cpumask`). - If an invalid mask is supplied, the write operation is aborted with `-EINVAL`. This ensures the kernel's housekeeping constraints are met while maintaining maximum hardware thread efficiency. Signed-off-by: Qiliang Yuan --- kernel/cgroup/cpuset-internal.h | 1 + kernel/cgroup/cpuset.c | 37 +++++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/kernel/cgroup/cpuset-internal.h b/kernel/cgroup/cpuset-internal.h index 3ab437f54ecdf..162594eaf8467 100644 --- a/kernel/cgroup/cpuset-internal.h +++ b/kernel/cgroup/cpuset-internal.h @@ -61,6 +61,7 @@ typedef enum { FILE_EFFECTIVE_XCPULIST, FILE_ISOLATED_CPULIST, FILE_HOUSEKEEPING_CPULIST, + FILE_HOUSEKEEPING_SMT_AWARE, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 5df19dc9bfa89..4272bb298ec3d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -37,6 +37,7 @@ #include #include #include +#include DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); @@ -156,6 +157,9 @@ static bool update_housekeeping; /* RWCS */ */ static cpumask_var_t isolated_hk_cpus; /* T */ +/* DHM: Enable SMT-aware boundary checks */ +static bool cpuset_housekeeping_smt_aware = false; + /* * A flag to force sched domain rebuild at the end of an operation. * It can be set in @@ -3218,6 +3222,16 @@ static ssize_t cpuset_write_housekeeping_cpus(struct kernfs_open_file *of, if (retval) goto out_free; + if (cpuset_housekeeping_smt_aware) { + int cpu; + for_each_cpu(cpu, new_mask) { + if (!cpumask_subset(topology_sibling_cpumask(cpu), new_mask)) { + retval = -EINVAL; + goto out_free; + } + } + } + retval = housekeeping_update_all_types(new_mask); out_free: @@ -3225,6 +3239,18 @@ static ssize_t cpuset_write_housekeeping_cpus(struct kernfs_open_file *of, return retval ?: nbytes; } +static ssize_t cpuset_write_housekeeping_smt_aware(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + bool val; + + if (kstrtobool(buf, &val)) + return -EINVAL; + + cpuset_housekeeping_smt_aware = val; + return nbytes; +} + /* * Common handling for a write to a "cpus" or "mems" file. */ @@ -3317,6 +3343,9 @@ int cpuset_common_seq_show(struct seq_file *sf, void *v) case FILE_HOUSEKEEPING_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(housekeeping_cpumask(HK_TYPE_DOMAIN))); break; + case FILE_HOUSEKEEPING_SMT_AWARE: + seq_printf(sf, "%d\n", cpuset_housekeeping_smt_aware); + break; default: ret = -EINVAL; } @@ -3464,6 +3493,14 @@ static struct cftype dfl_files[] = { .flags = CFTYPE_ONLY_ON_ROOT, }, + { + .name = "housekeeping.smt_aware", + .seq_show = cpuset_common_seq_show, + .write = cpuset_write_housekeeping_smt_aware, + .private = FILE_HOUSEKEEPING_SMT_AWARE, + .flags = CFTYPE_ONLY_ON_ROOT, + }, + { } /* terminate */ }; -- 2.43.0