Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
Date:   Tue, 31 May 2022 08:14:12 -0700
From:   Jakub Kicinski <kuba@kernel.org>
To:     Chen Lin <chen45464546@163.com>
Cc:     akpm@linux-foundation.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, alexander.duyck@gmail.com,
        netdev@vger.kernel.org
Subject: Re: [PATCH v2] mm: page_frag: Warn_on when frag_alloc size is
 bigger than PAGE_SIZE
Message-ID: <20220531081412.22db88cc@kernel.org>
In-Reply-To: <1654008072-3136-1-git-send-email-chen45464546@163.com>
References: <20220530122918.549ef054@kernel.org>
        <1654008072-3136-1-git-send-email-chen45464546@163.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Precedence: bulk

On Tue, 31 May 2022 22:41:12 +0800 Chen Lin wrote:
> At 2022-05-31 02:29:18, "Jakub Kicinski" <kuba@kernel.org> wrote:
> >Oh, well, the reuse also needs an update. We can slap a similar
> >condition next to the pfmemalloc check.  
> 
> The sample code above cannot completely solve the current problem.
> For example, when fragsz is greater than PAGE_FRAG_CACHE_MAX_SIZE(32768),
> __page_frag_cache_refill will return a memory of only 32768 bytes, so 
> should we continue to expand the PAGE_FRAG_CACHE_MAX_SIZE? Maybe more 
> work needs to be done

Right, but I can think of two drivers off the top of my head which will
allocate <=32k frags but none which will allocate more.