Re: [PATCHv4 0/4] zsmalloc: fine-grained fullness and new compaction algorithm

From: Sergey Senozhatsky <senozhatsky@chromium.org>
To: Yosry Ahmed <yosryahmed@google.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>,
	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
Subject: Re: [PATCHv4 0/4] zsmalloc: fine-grained fullness and new compaction algorithm
Date: Mon, 17 Apr 2023 20:12:43 +0900	[thread overview]
Message-ID: <20230417111243.GN25053@google.com> (raw)
In-Reply-To: <CAJD7tkZFufCacfu-EeqwhQBYXt8dpea1DYhyDgponjFjdLt5Sw@mail.gmail.com>

On (23/04/17 01:29), Yosry Ahmed wrote:
> > @@ -2239,8 +2241,8 @@ static unsigned long __zs_compact(struct zs_pool *pool,
> >                 if (fg == ZS_INUSE_RATIO_0) {
> >                         free_zspage(pool, class, src_zspage);
> >                         pages_freed += class->pages_per_zspage;
> > -                       src_zspage = NULL;
> >                 }
> > +               src_zspage = NULL;
> >
> >                 if (get_fullness_group(class, dst_zspage) == ZS_INUSE_RATIO_100
> >                     || spin_is_contended(&pool->lock)) {
> 
> For my own education, how can this result in the "next is NULL" debug
> error Yu Zhao is seeing?
> 
> IIUC if we do not set src_zspage to NULL properly after putback, then
> we will attempt to putback again after the main loop in some cases.
> This can result in a zspage being present more than once in the
> per-class fullness list, right?
> 
> I am not sure how this can lead to "next is NULL", which sounds like a
> corrupted list_head, because the next ptr should never be NULL as far
> as I can tell. I feel like I am missing something.

That's a good question to which I don't have an answer. We can list_add()
the same zspage twice, unlocking the pool after first list_add() so that
another process (including another zs_compact()) can do something to that
zspage. The answer is somewhere between these lines, I guess.

I can see how, for example, another DEBUG_LIST check can be triggered:
"list_add double add", because we basically can do

	list_add(page, list)
	list_add(page, list)

I can also see how lockdep can be unhappy with us doing

	write_unlock(&zspage->lock);
	write_unlock(&zspage->lock);

But I don't think I see how "next is NULL" happens (I haven't observed
it).