Received-SPF: pass (google.com: domain of linux-kernel+bounces-45953-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
From: Florian Weimer <fweimer@redhat.com>
To: Yang Shi <shy828301@gmail.com>
Cc: oliver.sang@intel.com,  riel@surriel.com,  fengwei.yin@intel.com,
  willy@infradead.org,  cl@linux.com,  ying.huang@intel.com,
  akpm@linux-foundation.org,  linux-kernel@vger.kernel.org,
  linux-mm@kvack.org
Subject: Re: [PATCH 2/2] mm: mmap: map MAP_STACK to VM_NOHUGEPAGE
References: <20231221065943.2803551-1-shy828301@gmail.com>
	<20231221065943.2803551-2-shy828301@gmail.com>
Date: Wed, 31 Jan 2024 08:53:40 +0100
In-Reply-To: <20231221065943.2803551-2-shy828301@gmail.com> (Yang Shi's
	message of "Wed, 20 Dec 2023 22:59:43 -0800")
Message-ID: <878r46ym4b.fsf@oldenburg.str.redhat.com>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/28.3 (gnu/linux)
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain

* Yang Shi:

> From: Yang Shi <yang@os.amperecomputing.com>
>
> The commit efa7df3e3bb5 ("mm: align larger anonymous mappings on THP
> boundaries") incured regression for stress-ng pthread benchmark [1].
> It is because THP get allocated to pthread's stack area much more possible
> than before.  Pthread's stack area is allocated by mmap without VM_GROWSDOWN
> or VM_GROWSUP flag, so kernel can't tell whether it is a stack area or not.
>
> The MAP_STACK flag is used to mark the stack area, but it is a no-op on
> Linux.  Mapping MAP_STACK to VM_NOHUGEPAGE to prevent from allocating
> THP for such stack area.

Doesn't this introduce a regression in the other direction, where
workloads expect to use a hugepage TLB entry for the stack?

It's seems an odd approach to fixing the stress-ng regression.  Isn't it
very much coding to the benchmark?

Thanks,
Florian