[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aBsDj0IGQBJC_JMj@infradead.org>
Date: Tue, 6 May 2025 23:54:07 -0700
From: Christoph Hellwig <hch@...radead.org>
To: Sergey Senozhatsky <senozhatsky@...omium.org>
Cc: Yosry Ahmed <yosry.ahmed@...ux.dev>,
Vitaly Wool <vitaly.wool@...sulko.se>, linux-mm@...ck.org,
akpm@...ux-foundation.org, linux-kernel@...r.kernel.org,
Nhat Pham <nphamcs@...il.com>,
Shakeel Butt <shakeel.butt@...ux.dev>,
Johannes Weiner <hannes@...xchg.org>,
Minchan Kim <minchan@...nel.org>, Igor Belousov <igor.b@...dev.am>,
Herbert Xu <herbert@...dor.apana.org.au>
Subject: Re: [PATCH] mm/zblock: use vmalloc for page allocations
On Wed, May 07, 2025 at 03:08:08PM +0900, Sergey Senozhatsky wrote:
> > This sounds interesting. We might get rid of lots of memcpy()
> > in object read/write paths, and so on. I don't know if 0-order
> > chaining was the only option for zsmalloc, or just happened to
> > be the first one.
>
> I assume we might have problems with zspage release path. vfree()
> should break .swap_slot_free_notify, as far as I can see.
> .swap_slot_free_notify is called under swap-cluster spin-lock,
> so if we free the last object in the zspage we cannot immediately
> free that zspage, because vfree() might_sleep().
Note that swap_slot_free_notify really needs to go away in favor
of just sending a discard bio. Having special block ops for a
single user bypassing the proper block interface is not sustainable.
Powered by blists - more mailing lists