Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20230304034835.2082479-1-senozhatsky@chromium.org>
 <CAOUHufZ6jPLJYeshO8=2TaqXRmpOFuMQ92E9sg-oCh54fkqW7g@mail.gmail.com>
 <20230416151853.GK25053@google.com> <CAOUHufZk+dxE8UXWwGzGbX1BYxomD_25u2xoWt3vnoQp4xSZqw@mail.gmail.com>
 <20230417024446.GL25053@google.com> <CAOUHufYJtB0n314GnMH1ByXL5PTtzzsrMvi2YbHz2YVqTTcYfA@mail.gmail.com>
 <20230417035232.GM25053@google.com> <CAJD7tkZFufCacfu-EeqwhQBYXt8dpea1DYhyDgponjFjdLt5Sw@mail.gmail.com>
 <20230417111243.GN25053@google.com> <CAJD7tkah9kx2kAcTY47J2R5p7NYS+b+3A9S_R-hSv9z8OSzzqA@mail.gmail.com>
 <20230417112421.GO25053@google.com>
In-Reply-To: <20230417112421.GO25053@google.com>
From:   Yosry Ahmed <yosryahmed@google.com>
Date:   Mon, 17 Apr 2023 04:31:11 -0700
Message-ID: <CAJD7tkbC5drsA2s+=sxXGGm+2RAFXbqs_21KrGaWav_LKjA68w@mail.gmail.com>
Subject: Re: [PATCHv4 0/4] zsmalloc: fine-grained fullness and new compaction algorithm
To:     Sergey Senozhatsky <senozhatsky@chromium.org>
Cc:     Yu Zhao <yuzhao@google.com>, Minchan Kim <minchan@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Mon, Apr 17, 2023 at 4:24=E2=80=AFAM Sergey Senozhatsky
<senozhatsky@chromium.org> wrote:
>
> On (23/04/17 04:16), Yosry Ahmed wrote:
> > > That's a good question to which I don't have an answer. We can list_a=
dd()
> > > the same zspage twice, unlocking the pool after first list_add() so t=
hat
> > > another process (including another zs_compact()) can do something to =
that
> > > zspage. The answer is somewhere between these lines, I guess.
> >
> > But the first list_add() is (in this case) the correct add, so we
> > expect other processes to be able to access the zspage after the first
> > list_add() anyway, right?
>
> Correct. Compaction also can unlock pool->lock and schedule() so that
> another process can access the source zspage, when compaction gets
> scheduled it can attempt putback/unlock the same zspage one more time
> (the zspage may not even exist at this point, I assume).

Good point, that could very well be where the corruption is coming
from. Thanks for pointing this out.