[dm-devel] [patch 1/4] x86: optimize memcpy_flushcache

[Dan Williams]

[ add x86 folks for their review / ack ]

On Fri, May 18, 2018 at 10:25 PM, Mikulas Patocka <mpatocka at redhat.com> wrote:
> I use memcpy_flushcache in my persistent memory driver for metadata
> updates and it turns out that the overhead of memcpy_flushcache causes 2%
> performance degradation compared to "movnti" instruction explicitly coded
> using inline assembler.
>
> This patch recognizes memcpy_flushcache calls with constant short length
> and turns them into inline assembler - so that I don't have to use inline
> assembler in the driver.
>
> Signed-off-by: Mikulas Patocka <mpatocka at redhat.com>
>
> ---
>  arch/x86/include/asm/string_64.h |   20 +++++++++++++++++++-
>  arch/x86/lib/usercopy_64.c       |    4 ++--
>  2 files changed, 21 insertions(+), 3 deletions(-)
>
> Index: linux-2.6/arch/x86/include/asm/string_64.h
> ===================================================================
> --- linux-2.6.orig/arch/x86/include/asm/string_64.h     2018-05-18 21:21:15.000000000 +0200
> +++ linux-2.6/arch/x86/include/asm/string_64.h  2018-05-18 21:21:15.000000000 +0200
> @@ -147,7 +147,25 @@ memcpy_mcsafe(void *dst, const void *src
>
>  #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
>  #define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1
> -void memcpy_flushcache(void *dst, const void *src, size_t cnt);
> +void __memcpy_flushcache(void *dst, const void *src, size_t cnt);
> +static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt)
> +{
> +       if (__builtin_constant_p(cnt)) {
> +               switch (cnt) {
> +                       case 4:
> +                               asm ("movntil %1, %0" : "=m"(*(u32 *)dst) : "r"(*(u32 *)src));
> +                               return;
> +                       case 8:
> +                               asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
> +                               return;
> +                       case 16:
> +                               asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src));
> +                               asm ("movntiq %1, %0" : "=m"(*(u64 *)(dst + 8)) : "r"(*(u64 *)(src + 8)));
> +                               return;
> +               }
> +       }
> +       __memcpy_flushcache(dst, src, cnt);
> +}
>  #endif
>
>  #endif /* __KERNEL__ */
> Index: linux-2.6/arch/x86/lib/usercopy_64.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/lib/usercopy_64.c   2018-05-18 21:21:15.000000000 +0200
> +++ linux-2.6/arch/x86/lib/usercopy_64.c        2018-05-18 22:09:49.000000000 +0200
> @@ -133,7 +133,7 @@ long __copy_user_flushcache(void *dst, c
>         return rc;
>  }
>
> -void memcpy_flushcache(void *_dst, const void *_src, size_t size)
> +void __memcpy_flushcache(void *_dst, const void *_src, size_t size)
>  {
>         unsigned long dest = (unsigned long) _dst;
>         unsigned long source = (unsigned long) _src;
> @@ -196,7 +196,7 @@ void memcpy_flushcache(void *_dst, const
>                 clean_cache_range((void *) dest, size);
>         }
>  }
> -EXPORT_SYMBOL_GPL(memcpy_flushcache);
> +EXPORT_SYMBOL_GPL(__memcpy_flushcache);
>
>  void memcpy_page_flushcache(char *to, struct page *page, size_t offset,
>                 size_t len)
>