Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.33 as permitted sender) client-ip=23.128.96.33;
From:   Waiman Long <longman@redhat.com>
To:     Tejun Heo <tj@kernel.org>, Zefan Li <lizefan.x@bytedance.com>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Michal Hocko <mhocko@suse.com>,
        Frederic Weisbecker <frederic@kernel.org>
Cc:     cgroups@vger.kernel.org, linux-kernel@vger.kernel.org,
        Mrunal Patel <mpatel@redhat.com>,
        Ryan Phillips <rphillips@redhat.com>,
        Brent Rowsell <browsell@redhat.com>,
        Peter Hunt <pehunt@redhat.com>,
        Waiman Long <longman@redhat.com>
Subject: [PATCH-cgroup 0/2] cgroup/cpuset: Include isolated cpuset CPUs in cpu_is_isolated()
Date:   Sun, 26 Nov 2023 23:19:54 -0500
Message-Id: <20231127041956.266026-1-longman@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

This patchset enables the inclusion of CPUs in isolated cpuset partitions
in the cpu_is_isolated() check to reduce interference caused by vmstat
or memcg local stock flushing.

To reduce cpu_is_isolated() call overhead, a seqcount is used to
protect read access of the isolated cpumask without taking any lock. As
a result, the callback_lock is changed to a raw_spinlock_t to make it
work in PREEMPT_RT kernel too.

Waiman Long (2):
  cgroup/cpuset: Make callback_lock a raw_spinlock_t
  cgroup/cpuset: Include isolated cpuset CPUs in cpu_is_isolated() check

 include/linux/cpuset.h          |   6 ++
 include/linux/sched/isolation.h |   4 +-
 kernel/cgroup/cpuset.c          | 127 +++++++++++++++++++-------------
 3 files changed, 85 insertions(+), 52 deletions(-)

-- 
2.39.3