Received-SPF: pass (google.com: domain of linux-kernel+bounces-121864-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
Date: Wed, 27 Mar 2024 14:56:59 -0400
From: Peter Xu <peterx@redhat.com>
To: Peng Zhang <zhangpeng362@huawei.com>
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	akpm@linux-foundation.org, david@redhat.com,
	axelrasmussen@google.com, surenb@google.com, lokeshgidra@google.com,
	Liam.Howlett@oracle.com, wangkefeng.wang@huawei.com,
	sunnanyong@huawei.com
Subject: Re: [PATCH] userfaultfd: early return in dup_userfaultfd()
Message-ID: <ZgRr-8PX2Jdk6VKz@x1n>
References: <20240327090835.3232629-1-zhangpeng362@huawei.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20240327090835.3232629-1-zhangpeng362@huawei.com>

On Wed, Mar 27, 2024 at 05:08:35PM +0800, Peng Zhang wrote:
> From: ZhangPeng <zhangpeng362@huawei.com>
> 
> When vma->vm_userfaultfd_ctx.ctx is NULL, vma->vm_flags should have
> cleared __VM_UFFD_FLAGS. Therefore, there is no need to down_write or
> clear the flag, which will affect fork performance. Fix this by
> returning early if octx is NULL in dup_userfaultfd().
> 
> By applying this patch we can get a 1.3% performance improvement for
> lmbench fork_prot. Results are as follows:
>                    base      early return
> Process fork+exit: 419.1106  413.4804
> 
> Signed-off-by: ZhangPeng <zhangpeng362@huawei.com>

Reviewed-by: Peter Xu <peterx@redhat.com>

-- 
Peter Xu