[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <d398bcf6-30f2-44a8-9721-1c4c763951b6@redhat.com>
Date: Mon, 6 Oct 2025 10:20:03 +0200
From: David Hildenbrand <david@...hat.com>
To: Ryan Roberts <ryan.roberts@....com>,
Andrew Morton <akpm@...ux-foundation.org>,
Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
"Liam R. Howlett" <Liam.Howlett@...cle.com>, Vlastimil Babka
<vbabka@...e.cz>, Mike Rapoport <rppt@...nel.org>,
Suren Baghdasaryan <surenb@...gle.com>, Michal Hocko <mhocko@...e.com>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v1] mm: Consistently use current->mm in
mm_get_unmapped_area()
On 03.10.25 17:53, Ryan Roberts wrote:
> mm_get_unmapped_area() is a wrapper around arch_get_unmapped_area() /
> arch_get_unmapped_area_topdown(), both of which search current->mm for
> some free space. Neither take an mm_struct - they implicitly operate on
> current->mm.
>
> But the wrapper takes an mm_struct and uses it to decide whether to
> search bottom up or top down. All callers pass in current->mm for this,
> so everything is working consistently. But it feels like an accident
> waiting to happen; eventually someone will call that function with a
> different mm, expecting to find free space in it, but what gets returned
> is free space in the current mm.
>
> So let's simplify by removing the parameter and have the wrapper use
> current->mm to decide which end to start at. Now everything is
> consistent and self-documenting.
>
> Signed-off-by: Ryan Roberts <ryan.roberts@....com>
Yeah, that looks better to me.
Acked-by: David Hildenbrand <david@...hat.com>
--
Cheers
David / dhildenb
Powered by blists - more mailing lists