MIME-Version: 1.0
References: <20211201231757.332199-1-willy@infradead.org> <CAG48ez3YNCNZB7AktmRoYLsBQjwBdwueRUXbkFgNVMsgjmCTGA@mail.gmail.com>
 <YahHZOnT1Uh41XnP@casper.infradead.org> <CAHk-=wiHpPXjA=i6e=3Pk13frRd-RVXfSrT6=KfU2tg4Pu5MmQ@mail.gmail.com>
 <YaklihoYztAoKfxX@casper.infradead.org>
In-Reply-To: <YaklihoYztAoKfxX@casper.infradead.org>
From:   Linus Torvalds <torvalds@linux-foundation.org>
Date:   Thu, 2 Dec 2021 14:33:37 -0800
Message-ID: <CAHk-=wgzk5dTKaciK2pkto=+fz0kAkXxz9g8ekkWfeOKzMR1EQ@mail.gmail.com>
Subject: Re: [5.4 PATCH] mm/gup: Do not force a COW break on file-backed memory
To:     Matthew Wilcox <willy@infradead.org>
Cc:     Jann Horn <jannh@google.com>, Jan Kara <jack@suse.cz>,
        Kirill Shutemov <kirill@shutemov.name>,
        Oleg Nesterov <oleg@redhat.com>,
        Christoph Hellwig <hch@lst.de>, Linux-MM <linux-mm@kvack.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Mike Kravetz <mike.kravetz@oracle.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Thu, Dec 2, 2021 at 11:59 AM Matthew Wilcox <willy@infradead.org> wrote:
>
> Oh absolutely, it's semantically nonsense.  The only reason it fixes the
> problem is that VM_DENYWRITE VMAs are the only ones considered for the
> RO_THP merging, so they're the only ones which we've seen causing a
> problem.

That would be a semantically meaningful argument, but I think the
reverse isn't true: regular pages in VM_DENYWRITE vmas - that aren't
using the RO_THP thing - are open to the same old "COW wrong way"
issue.

So it's not like VM_DENYWRITE is really meaningful for the
conditional, even if it's perhaps a prerequisite for it being a
problem.

> > I suspect a real fix would be bigger and more invasive.
>
> Darn.  I was hoping you were going to say something like "The real
> problem is follow_trans_huge_pmd() is complete garbage and it should
> just do X, Y and Z".  Or "When we force on FOLL_WRITE, we should also
> force on FOLL_SPLIT_PMD".

Well, maybe that "FOLL_SPLIT_PMD" thing would indeed be a valid thing?

But I _think_ that it shouldn't be too painful to do the
should_force_cow_break() call later, when you actually have the exact
page details, so while not exactly a one-liner, I hope that approach
would end up working out.

I only gave it a quick look, though, I might be missing something.

              Linus