Received-SPF: pass (google.com: domain of linux-kernel+bounces-95386-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Thu, 7 Mar 2024 12:10:43 +0100 (CET)
From: Richard Weinberger <richard@nod.at>
To: David Hildenbrand <david@redhat.com>
Cc: linux-mm <linux-mm@kvack.org>, linux-fsdevel <linux-fsdevel@vger.kernel.org>, 
	linux-kernel <linux-kernel@vger.kernel.org>, 
	Linux Doc Mailing List <linux-doc@vger.kernel.org>, 
	upstream+pagemap@sigma-star.at, adobriyan@gmail.com, 
	wangkefeng wang <wangkefeng.wang@huawei.com>, 
	ryan roberts <ryan.roberts@arm.com>, hughd@google.com, 
	peterx@redhat.com, avagin@google.com, lstoakes@gmail.com, 
	vbabka <vbabka@suse.cz>, Andrew Morton <akpm@linux-foundation.org>, 
	usama anjum <usama.anjum@collabora.com>, 
	Jonathan Corbet <corbet@lwn.net>
Message-ID: <1058679077.23275.1709809843605.JavaMail.zimbra@nod.at>
In-Reply-To: <d673247b-a67b-43e1-a947-18fdae5f0ea1@redhat.com>
References: <20240306232339.29659-1-richard@nod.at> <d673247b-a67b-43e1-a947-18fdae5f0ea1@redhat.com>
Subject: Re: [PATCH 1/2] [RFC] proc: pagemap: Expose whether a PTE is
 writable
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Thread-Topic: proc: pagemap: Expose whether a PTE is writable
Thread-Index: XSyjIW0X6vSwMkWWDv+zJYc006jxkw==

----- Urspr=C3=BCngliche Mail -----
> Von: "David Hildenbrand" <david@redhat.com>
> But why is that required? What is the target use case? (I did not get
> the cover letter in my inbox)
>=20
> We're running slowly but steadily out of bits, so we better make wise
> decisions.
>=20
> Also, consider: Architectures where the dirty/access bit is not HW
> managed could indicate "writable" here although we *will* get a page
> fault to set the page dirty/accessed.

I'm currently investigating why a real-time application faces unexpected
page faults. Page faults are usually fatal for real-time work loads because
the latency constraints are no longer met.

So, I wrote a small tool to inspect the memory mappings of a process to fin=
d
areas which are not correctly pre-faulted. While doing so I noticed that
there is currently no way to detect CoW mappings.
Exposing the writable property of a PTE seemed like a good start to me.

> So best this can universally do is say "this PTE currently has write
> permissions".

Ok.

Thanks,
//richard