Re: [PATCH 2/2] clean up set_page_dirty()

[Michel Lespinasse <walken@google.com>]

On Wed, Nov 10, 2010 at 1:00 AM, Bob Liu <lliubbo@gmail.com> wrote:
> Use TestSetPageDirty() to clean up set_page_dirty().
>
> Signed-off-by: Bob Liu <lliubbo@gmail.com>
> ---
>  mm/page-writeback.c |    7 ++-----
>  1 files changed, 2 insertions(+), 5 deletions(-)
>
> diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> index e8f5f06..da86224 100644
> --- a/mm/page-writeback.c
> +++ b/mm/page-writeback.c
> @@ -1268,11 +1268,8 @@ int set_page_dirty(struct page *page)
>  #endif
>                return (*spd)(page);
>        }
> -       if (!PageDirty(page)) {
> -               if (!TestSetPageDirty(page))
> -                       return 1;
> -       }
> -       return 0;
> +
> +       return !TestSetPageDirty(page);
>  }
>  EXPORT_SYMBOL(set_page_dirty);

TestSetPageDirty compiles to a locked bts instruction (on x86). This
will acquire the cache line for exclusive access, even when the bit is
already set. I think this is why we have an extra if
(!PageDirty(page)) test - we don't want to cause cache coherency
overhead if the page is already dirty.

-- 
Michel "Walken" Lespinasse
A program is never fully debugged until the last user dies.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>