[PATCH] arm64: add missing conversion to __wsum in ip_fast_csum()

[PATCH] arm64: add missing conversion to __wsum in ip_fast_csum()

[Luc Van Oostenryck]

ARM64 implementation of ip_fast_csum() do most of the work
in 128 or 64 bit and call csum_fold() to finalize. csum_fold()
itself take a __wsum argument, to insure that this value is
always a 32bit native-order value.

Fix this by using an helper __csum_fold() taking the native
32 bit value and doing the needed folding to 16 bit (and reuse
this helper for csum_fold() itself).

Note: a simpler patch would to use something like:
		return csum_fold((__wsum __force)(sum >> 32));
      but using an helper __csum_fold() allow to avoid
      a forced cast.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
---
 arch/arm64/include/asm/checksum.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 09f65339d..dcc655137 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -18,12 +18,16 @@
 
 #include <linux/types.h>
 
-static inline __sum16 csum_fold(__wsum csum)
+static inline __sum16 __csum_fold(u32 sum)
 {
-	u32 sum = (__force u32)csum;
 	sum += (sum >> 16) | (sum << 16);
 	return ~(__force __sum16)(sum >> 16);
 }
+
+static inline __sum16 csum_fold(__wsum csum)
+{
+	return __csum_fold((__force u32)csum);
+}
 #define csum_fold csum_fold
 
 static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
@@ -42,7 +46,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	} while (--ihl);
 
 	sum += ((sum >> 32) | (sum << 32));
-	return csum_fold(sum >> 32);
+	return __csum_fold(sum >> 32);
 }
 #define ip_fast_csum ip_fast_csum
 
-- 
2.13.0

[PATCH] arm64: add missing conversion to __wsum in ip_fast_csum()

[Will Deacon]

On Wed, Jun 28, 2017 at 04:58:14PM +0200, Luc Van Oostenryck wrote:
> ARM64 implementation of ip_fast_csum() do most of the work
> in 128 or 64 bit and call csum_fold() to finalize. csum_fold()
> itself take a __wsum argument, to insure that this value is
> always a 32bit native-order value.
> 
> Fix this by using an helper __csum_fold() taking the native
> 32 bit value and doing the needed folding to 16 bit (and reuse
> this helper for csum_fold() itself).
> 
> Note: a simpler patch would to use something like:
> 		return csum_fold((__wsum __force)(sum >> 32));
>       but using an helper __csum_fold() allow to avoid
>       a forced cast.

But you've added a __force cast in csum_fold, and we still have the one in
the return statement of __csum_fold, so I think I prefer the simpler patch.

Will

> 
> Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
> ---
>  arch/arm64/include/asm/checksum.h | 10 +++++++---
>  1 file changed, 7 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
> index 09f65339d..dcc655137 100644
> --- a/arch/arm64/include/asm/checksum.h
> +++ b/arch/arm64/include/asm/checksum.h
> @@ -18,12 +18,16 @@
>  
>  #include <linux/types.h>
>  
> -static inline __sum16 csum_fold(__wsum csum)
> +static inline __sum16 __csum_fold(u32 sum)
>  {
> -	u32 sum = (__force u32)csum;
>  	sum += (sum >> 16) | (sum << 16);
>  	return ~(__force __sum16)(sum >> 16);
>  }
> +
> +static inline __sum16 csum_fold(__wsum csum)
> +{
> +	return __csum_fold((__force u32)csum);
> +}
>  #define csum_fold csum_fold
>  
>  static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
> @@ -42,7 +46,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
>  	} while (--ihl);
>  
>  	sum += ((sum >> 32) | (sum << 32));
> -	return csum_fold(sum >> 32);
> +	return __csum_fold(sum >> 32);
>  }
>  #define ip_fast_csum ip_fast_csum
>  
> -- 
> 2.13.0
> 

[PATCH v2] arm64: add missing conversion to __wsum in ip_fast_csum()

[Luc Van Oostenryck]

ARM64 implementation of ip_fast_csum() do most of the work
in 128 or 64 bit and call csum_fold() to finalize. csum_fold()
itself take a __wsum argument, to insure that this value is
always a 32bit native-order value.

Fix this by adding the sadly needed '__force' to cast the native
'sum' to the type '__wsum'.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>

---
Change since v1:
- use the simple __force cast instead of an intermediate helper.
---
 arch/arm64/include/asm/checksum.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/checksum.h b/arch/arm64/include/asm/checksum.h
index 09f65339d..0b6f5a7d4 100644
--- a/arch/arm64/include/asm/checksum.h
+++ b/arch/arm64/include/asm/checksum.h
@@ -42,7 +42,7 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 	} while (--ihl);
 
 	sum += ((sum >> 32) | (sum << 32));
-	return csum_fold(sum >> 32);
+	return csum_fold((__force u32)(sum >> 32));
 }
 #define ip_fast_csum ip_fast_csum
 
-- 
2.13.0