Re: [PATCH 11/17] mm: move get_dev_pagemap out of line

[Dan Williams]

On Fri, Dec 15, 2017 at 6:09 AM, Christoph Hellwig <hch@xxxxxx> wrote:
> This is a pretty big function, which should be out of line in general,
> and a no-op stub if CONFIG_ZONE_DEVICÐ is not set.
>
> Signed-off-by: Christoph Hellwig <hch@xxxxxx>
> Reviewed-by: Logan Gunthorpe <logang@xxxxxxxxxxxx>
[..]
> +/**
> + * get_dev_pagemap() - take a new live reference on the dev_pagemap for @pfn
> + * @pfn: page frame number to lookup page_map
> + * @pgmap: optional known pgmap that already has a reference
> + *
> + * @pgmap allows the overhead of a lookup to be bypassed when @pfn lands in the
> + * same mapping.
> + */
> +struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
> +               struct dev_pagemap *pgmap)
> +{
> +       const struct resource *res = pgmap ? pgmap->res : NULL;
> +       resource_size_t phys = PFN_PHYS(pfn);
> +
> +       /*
> +        * In the cached case we're already holding a live reference so
> +        * we can simply do a blind increment
> +        */
> +       if (res && phys >= res->start && phys <= res->end) {
> +               percpu_ref_get(pgmap->ref);
> +               return pgmap;
> +       }

I was going to say keep the cached case in the static inline, but with
the optimization to the calling convention in the following patch I
think that makes this moot.

So,

Reviewed-by: Dan Williams <dan.j.williams@xxxxxxxxx>