linux-kernel - Re: [PATCH v5 1/2] mm: Allow the page cache to allocate large pages

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20190903121952.GU14028@dhcp22.suse.cz>
Date:   Tue, 3 Sep 2019 14:19:52 +0200
From:   Michal Hocko <mhocko@...nel.org>
To:     Matthew Wilcox <willy@...radead.org>
Cc:     William Kucharski <william.kucharski@...cle.com>,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        linux-fsdevel@...r.kernel.org,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Song Liu <songliubraving@...com>,
        Bob Kasten <robert.a.kasten@...el.com>,
        Mike Kravetz <mike.kravetz@...cle.com>,
        Chad Mynhier <chad.mynhier@...cle.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Johannes Weiner <jweiner@...com>
Subject: Re: [PATCH v5 1/2] mm: Allow the page cache to allocate large pages

On Tue 03-09-19 05:11:55, Matthew Wilcox wrote:
> On Tue, Sep 03, 2019 at 01:57:48PM +0200, Michal Hocko wrote:
> > On Mon 02-09-19 03:23:40, William Kucharski wrote:
> > > Add an 'order' argument to __page_cache_alloc() and
> > > do_read_cache_page(). Ensure the allocated pages are compound pages.
> > 
> > Why do we need to touch all the existing callers and change them to use
> > order 0 when none is actually converted to a different order? This just
> > seem to add a lot of code churn without a good reason. If anything I
> > would simply add __page_cache_alloc_order and make __page_cache_alloc
> > call it with order 0 argument.
> 
> Patch 2/2 uses a non-zero order.

It is a new caller and it can use a new function right?

> I agree it's a lot of churn without
> good reason; that's why I tried to add GFP_ORDER flags a few months ago.
> Unfortunately, you didn't like that approach either.

Is there any future plan that all/most __page_cache_alloc will get a
non-zero order argument?

> > Also is it so much to ask callers to provide __GFP_COMP explicitly?
> 
> Yes, it's an unreasonable burden on the callers.

Care to exaplain why? __GFP_COMP tends to be used in the kernel quite
extensively.

> Those that pass 0 will
> have the test optimised away by the compiler (for the non-NUMA case).
> For the NUMA case, passing zero is going to be only a couple of extra
> instructions to not set the GFP_COMP flag.
> 
> > >  #ifdef CONFIG_NUMA
> > > -extern struct page *__page_cache_alloc(gfp_t gfp);
> > > +extern struct page *__page_cache_alloc(gfp_t gfp, unsigned int order);
> > >  #else
> > > -static inline struct page *__page_cache_alloc(gfp_t gfp)
> > > +static inline struct page *__page_cache_alloc(gfp_t gfp, unsigned int order)
> > >  {
> > > -	return alloc_pages(gfp, 0);
> > > +	if (order > 0)
> > > +		gfp |= __GFP_COMP;
> > > +	return alloc_pages(gfp, order);
> > >  }
> > >  #endif

-- 
Michal Hocko
SUSE Labs