Message-ID: <20191113230331.GB6171@redhat.com>
Date:   Wed, 13 Nov 2019 18:03:31 -0500
From:   Jerome Glisse <jglisse@...hat.com>
To:     Dan Williams <dan.j.williams@...el.com>
Cc:     John Hubbard <jhubbard@...dia.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Al Viro <viro@...iv.linux.org.uk>,
        Alex Williamson <alex.williamson@...hat.com>,
        Benjamin Herrenschmidt <benh@...nel.crashing.org>,
        Björn Töpel <bjorn.topel@...el.com>,
        Christoph Hellwig <hch@...radead.org>,
        Daniel Vetter <daniel@...ll.ch>,
        Dave Chinner <david@...morbit.com>,
        David Airlie <airlied@...ux.ie>,
        "David S . Miller" <davem@...emloft.net>,
        Ira Weiny <ira.weiny@...el.com>, Jan Kara <jack@...e.cz>,
        Jason Gunthorpe <jgg@...pe.ca>, Jens Axboe <axboe@...nel.dk>,
        Jonathan Corbet <corbet@....net>,
        Magnus Karlsson <magnus.karlsson@...el.com>,
        Mauro Carvalho Chehab <mchehab@...nel.org>,
        Michael Ellerman <mpe@...erman.id.au>,
        Michal Hocko <mhocko@...e.com>,
        Mike Kravetz <mike.kravetz@...cle.com>,
        Paul Mackerras <paulus@...ba.org>,
        Shuah Khan <shuah@...nel.org>,
        Vlastimil Babka <vbabka@...e.cz>, bpf@...r.kernel.org,
        Maling list - DRI developers 
        <dri-devel@...ts.freedesktop.org>, KVM list <kvm@...r.kernel.org>,
        linux-block@...r.kernel.org,
        Linux Doc Mailing List <linux-doc@...r.kernel.org>,
        linux-fsdevel <linux-fsdevel@...r.kernel.org>,
        linux-kselftest@...r.kernel.org,
        "Linux-media@...r.kernel.org" <linux-media@...r.kernel.org>,
        linux-rdma <linux-rdma@...r.kernel.org>,
        linuxppc-dev <linuxppc-dev@...ts.ozlabs.org>,
        Netdev <netdev@...r.kernel.org>, Linux MM <linux-mm@...ck.org>,
        LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v4 04/23] mm: devmap: refactor 1-based refcounting for
 ZONE_DEVICE pages

On Wed, Nov 13, 2019 at 02:00:06PM -0800, Dan Williams wrote:
> On Wed, Nov 13, 2019 at 11:23 AM Dan Williams <dan.j.williams@...el.com> wrote:
> >
> > On Tue, Nov 12, 2019 at 8:27 PM John Hubbard <jhubbard@...dia.com> wrote:
> > >
> > > An upcoming patch changes and complicates the refcounting and
> > > especially the "put page" aspects of it. In order to keep
> > > everything clean, refactor the devmap page release routines:
> > >
> > > * Rename put_devmap_managed_page() to page_is_devmap_managed(),
> > >   and limit the functionality to "read only": return a bool,
> > >   with no side effects.
> > >
> > > * Add a new routine, put_devmap_managed_page(), to handle checking
> > >   what kind of page it is, and what kind of refcount handling it
> > >   requires.
> > >
> > > * Rename __put_devmap_managed_page() to free_devmap_managed_page(),
> > >   and limit the functionality to unconditionally freeing a devmap
> > >   page.
> > >
> > > This is originally based on a separate patch by Ira Weiny, which
> > > applied to an early version of the put_user_page() experiments.
> > > Since then, Jérôme Glisse suggested the refactoring described above.
> > >
> > > Suggested-by: Jérôme Glisse <jglisse@...hat.com>
> > > Signed-off-by: Ira Weiny <ira.weiny@...el.com>
> > > Signed-off-by: John Hubbard <jhubbard@...dia.com>
> > > ---
> > >  include/linux/mm.h | 27 ++++++++++++++++---
> > >  mm/memremap.c      | 67 ++++++++++++++++++++--------------------------
> > >  2 files changed, 53 insertions(+), 41 deletions(-)
> > >
> > > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > > index a2adf95b3f9c..96228376139c 100644
> > > --- a/include/linux/mm.h
> > > +++ b/include/linux/mm.h
> > > @@ -967,9 +967,10 @@ static inline bool is_zone_device_page(const struct page *page)
> > >  #endif
> > >
> > >  #ifdef CONFIG_DEV_PAGEMAP_OPS
> > > -void __put_devmap_managed_page(struct page *page);
> > > +void free_devmap_managed_page(struct page *page);
> > >  DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
> > > -static inline bool put_devmap_managed_page(struct page *page)
> > > +
> > > +static inline bool page_is_devmap_managed(struct page *page)
> > >  {
> > >         if (!static_branch_unlikely(&devmap_managed_key))
> > >                 return false;
> > > @@ -978,7 +979,6 @@ static inline bool put_devmap_managed_page(struct page *page)
> > >         switch (page->pgmap->type) {
> > >         case MEMORY_DEVICE_PRIVATE:
> > >         case MEMORY_DEVICE_FS_DAX:
> > > -               __put_devmap_managed_page(page);
> > >                 return true;
> > >         default:
> > >                 break;
> > > @@ -986,6 +986,27 @@ static inline bool put_devmap_managed_page(struct page *page)
> > >         return false;
> > >  }
> > >
> > > +static inline bool put_devmap_managed_page(struct page *page)
> > > +{
> > > +       bool is_devmap = page_is_devmap_managed(page);
> > > +
> > > +       if (is_devmap) {
> > > +               int count = page_ref_dec_return(page);
> > > +
> > > +               /*
> > > +                * devmap page refcounts are 1-based, rather than 0-based: if
> > > +                * refcount is 1, then the page is free and the refcount is
> > > +                * stable because nobody holds a reference on the page.
> > > +                */
> > > +               if (count == 1)
> > > +                       free_devmap_managed_page(page);
> > > +               else if (!count)
> > > +                       __put_page(page);
> > > +       }
> > > +
> > > +       return is_devmap;
> > > +}
> > > +
> > >  #else /* CONFIG_DEV_PAGEMAP_OPS */
> > >  static inline bool put_devmap_managed_page(struct page *page)
> > >  {
> > > diff --git a/mm/memremap.c b/mm/memremap.c
> > > index 03ccbdfeb697..bc7e2a27d025 100644
> > > --- a/mm/memremap.c
> > > +++ b/mm/memremap.c
> > > @@ -410,48 +410,39 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
> > >  EXPORT_SYMBOL_GPL(get_dev_pagemap);
> > >
> > >  #ifdef CONFIG_DEV_PAGEMAP_OPS
> > > -void __put_devmap_managed_page(struct page *page)
> > > +void free_devmap_managed_page(struct page *page)
> > >  {
> > > -       int count = page_ref_dec_return(page);
> > > +       /* Clear Active bit in case of parallel mark_page_accessed */
> > > +       __ClearPageActive(page);
> > > +       __ClearPageWaiters(page);
> > > +
> > > +       mem_cgroup_uncharge(page);
> >
> > Ugh, when did all this HMM specific manipulation sneak into the
> > generic ZONE_DEVICE path? It used to be gated by pgmap type with its
> > own put_zone_device_private_page(). For example it's certainly
> > unnecessary and might be broken (would need to check) to call
> > mem_cgroup_uncharge() on a DAX page. ZONE_DEVICE users are not a
> > monolith and the HMM use case leaks pages into code paths that DAX
> > explicitly avoids.
> 
> It's been this way for a while and I did not react previously,
> apologies for that. I think __ClearPageActive, __ClearPageWaiters, and
> mem_cgroup_uncharge, belong behind a device-private conditional. The
> history here is:
> 
> Move some, but not all HMM specifics to hmm_devmem_free():
>     2fa147bdbf67 mm, dev_pagemap: Do not clear ->mapping on final put
> 
> Remove the clearing of mapping since no upstream consumers needed it:
>     b7a523109fb5 mm: don't clear ->mapping in hmm_devmem_free
> 
> Add it back in once an upstream consumer arrived:
>     7ab0ad0e74f8 mm/hmm: fix ZONE_DEVICE anon page mapping reuse
> 
> We're now almost entirely free of ->page_free callbacks except for
> that weird nouveau case, can that FIXME in nouveau_dmem_page_free()
> also result in killing the ->page_free() callback altogether? In the
> meantime I'm proposing a cleanup like this:

No we need the callback, cleanup looks good.

> 
> diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
> index ad8e4df1282b..4eae441f86c9 100644
> --- a/drivers/nvdimm/pmem.c
> +++ b/drivers/nvdimm/pmem.c
> @@ -337,13 +337,7 @@ static void pmem_release_disk(void *__pmem)
>         put_disk(pmem->disk);
>  }
> 
> -static void pmem_pagemap_page_free(struct page *page)
> -{
> -       wake_up_var(&page->_refcount);
> -}
> -
>  static const struct dev_pagemap_ops fsdax_pagemap_ops = {
> -       .page_free              = pmem_pagemap_page_free,
>         .kill                   = pmem_pagemap_kill,
>         .cleanup                = pmem_pagemap_cleanup,
>  };
> diff --git a/mm/memremap.c b/mm/memremap.c
> index 03ccbdfeb697..157edb8f7cf8 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -419,12 +419,6 @@ void __put_devmap_managed_page(struct page *page)
>          * holds a reference on the page.
>          */
>         if (count == 1) {
> -               /* Clear Active bit in case of parallel mark_page_accessed */
> -               __ClearPageActive(page);
> -               __ClearPageWaiters(page);
> -
> -               mem_cgroup_uncharge(page);
> -
>                 /*
>                  * When a device_private page is freed, the page->mapping field
>                  * may still contain a (stale) mapping value. For example, the
> @@ -446,10 +440,17 @@ void __put_devmap_managed_page(struct page *page)
>                  * handled differently or not done at all, so there is no need
>                  * to clear page->mapping.
>                  */
> -               if (is_device_private_page(page))
> -                       page->mapping = NULL;
> +               if (is_device_private_page(page)) {
> +                       /* Clear Active bit in case of parallel
> mark_page_accessed */
> +                       __ClearPageActive(page);
> +                       __ClearPageWaiters(page);
> 
> -               page->pgmap->ops->page_free(page);
> +                       mem_cgroup_uncharge(page);
> +
> +                       page->mapping = NULL;
> +                       page->pgmap->ops->page_free(page);
> +               } else
> +                       wake_up_var(&page->_refcount);
>         } else if (!count)
>                 __put_page(page);
>  }
> 

Powered by blists - more mailing lists