[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAJDx_rgL4bWnftmEfqnt87KuTYrvn-7J+ZOu5fd26q+fi0RVgQ@mail.gmail.com>
Date: Wed, 6 Aug 2025 14:54:38 -0700
From: Juan Yescas <jyescas@...gle.com>
To: Vlastimil Babka <vbabka@...e.cz>
Cc: David Hildenbrand <david@...hat.com>, akash.tyagi@...iatek.com,
Andrew Morton <akpm@...ux-foundation.org>, angelogioacchino.delregno@...labora.com,
hannes@...xchg.org, Brendan Jackman <jackmanb@...gle.com>,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
linux-mediatek@...ts.infradead.org,
Linux Memory Management List <linux-mm@...ck.org>, matthias.bgg@...il.com, Michal Hocko <mhocko@...e.com>,
Suren Baghdasaryan <surenb@...gle.com>, wsd_upstream@...iatek.com, Zi Yan <ziy@...dia.com>,
Kalesh Singh <kaleshsingh@...gle.com>, "T.J. Mercier" <tjmercier@...gle.com>,
Isaac Manjarres <isaacmanjarres@...gle.com>
Subject: Re: [RFC PATCH] mm/page_alloc: Add PCP list for THP CMA
On Tue, Aug 5, 2025 at 2:09 PM Vlastimil Babka <vbabka@...e.cz> wrote:
>
> On 8/5/25 19:12, Juan Yescas wrote:
> > On Tue, Aug 5, 2025 at 2:52 AM Vlastimil Babka <vbabka@...e.cz> wrote:
> >>
> >> >
> >> > Thanks David for the quick overview.
> >> >
> >> >> I still have no clue what this patch here tried to solve: it doesn't
> >> >> make any sense.
> >> >>
> >> >
> >> > The story started with this out of tree patch that is part of Android.
> >> >
> >> > https://lore.kernel.org/lkml/cover.1604282969.git.cgoldswo@codeaurora.org/T/#u
> >> >
> >> > This patch introduced the __GFP_CMA flag that allocates pages from
> >> > MIGRATE_MOVABLE
> >> > or MIGRATE_CMA.
> >>
> >> What kinds of allocations would then use __GFP_CMA?
> >
> > The __GFP_CMA allocations are used to allocate userspace anonymous memory. This
> > was done initially in the alloc_zeroed_user_highpage_movable()
> > function, now it is done
> > in vma_alloc_zeroed_movable_folio().
>
> So that means you perceive the risk of anonymous memory being temporarily
> pinned and thwarting a alloc_contig_pages() device CMA allocation lower than
> for file pages? The pinning can be a gup(), or a compaction migrating the
> page, etc...
>
I think that was the assumption when the patches were sent :(
>
Powered by blists - more mailing lists