lib/xor: make xor prototypes more friendly to compiler vectorization

Modern compilers are perfectly capable of extracting parallelism from
the XOR routines, provided that the prototypes reflect the nature of the
input accurately, in particular, the fact that the input vectors are
expected not to overlap. This is not documented explicitly, but is
implied by the interchangeability of the various C routines, some of
which use temporary variables while others don't: this means that these
routines only behave identically for non-overlapping inputs.

So let's decorate these input vectors with the __restrict modifier,
which informs the compiler that there is no overlap. While at it, make
the input-only vectors pointer-to-const as well.

Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Link: https://github.com/ClangBuiltLinux/linux/issues/563
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

2 files changed, 42 insertions, 21 deletions

diff --git a/arch/sparc/include/asm/xor_32.h b/arch/sparc/include/asm/xor_32.h
index 3e5af37e4b9c..0351813cf3af 100644
--- a/arch/sparc/include/asm/xor_32.h
+++ b/arch/sparc/include/asm/xor_32.h
@@ -13,7 +13,8 @@
  */
 
 static void
-sparc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+sparc_2(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2)
 {
 	int lines = bytes / (sizeof (long)) / 8;
 
@@ -50,8 +51,9 @@ sparc_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
 }
 
 static void
-sparc_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	unsigned long *p3)
+sparc_3(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3)
 {
 	int lines = bytes / (sizeof (long)) / 8;
 
@@ -101,8 +103,10 @@ sparc_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 }
 
 static void
-sparc_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	unsigned long *p3, unsigned long *p4)
+sparc_4(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4)
 {
 	int lines = bytes / (sizeof (long)) / 8;
 
@@ -165,8 +169,11 @@ sparc_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
 }
 
 static void
-sparc_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	unsigned long *p3, unsigned long *p4, unsigned long *p5)
+sparc_5(unsigned long bytes, unsigned long * __restrict p1,
+	const unsigned long * __restrict p2,
+	const unsigned long * __restrict p3,
+	const unsigned long * __restrict p4,
+	const unsigned long * __restrict p5)
 {
 	int lines = bytes / (sizeof (long)) / 8;
 
diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h
index 16169f3edcd5..caaddea8ad79 100644
--- a/arch/sparc/include/asm/xor_64.h
+++ b/arch/sparc/include/asm/xor_64.h
@@ -12,13 +12,20 @@
 
 #include <asm/spitfire.h>
 
-void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
-void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
-	       unsigned long *);
-void xor_vis_4(unsigned long, unsigned long *, unsigned long *,
-	       unsigned long *, unsigned long *);
-void xor_vis_5(unsigned long, unsigned long *, unsigned long *,
-	       unsigned long *, unsigned long *, unsigned long *);
+void xor_vis_2(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2);
+void xor_vis_3(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3);
+void xor_vis_4(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3,
+	       const unsigned long * __restrict p4);
+void xor_vis_5(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2,
+	       const unsigned long * __restrict p3,
+	       const unsigned long * __restrict p4,
+	       const unsigned long * __restrict p5);
 
 /* XXX Ugh, write cheetah versions... -DaveM */
 
@@ -30,13 +37,20 @@ static struct xor_block_template xor_block_VIS = {
         .do_5	= xor_vis_5,
 };
 
-void xor_niagara_2(unsigned long, unsigned long *, unsigned long *);
-void xor_niagara_3(unsigned long, unsigned long *, unsigned long *,
-		   unsigned long *);
-void xor_niagara_4(unsigned long, unsigned long *, unsigned long *,
-		   unsigned long *, unsigned long *);
-void xor_niagara_5(unsigned long, unsigned long *, unsigned long *,
-		   unsigned long *, unsigned long *, unsigned long *);
+void xor_niagara_2(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2);
+void xor_niagara_3(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2,
+		   const unsigned long * __restrict p3);
+void xor_niagara_4(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2,
+		   const unsigned long * __restrict p3,
+		   const unsigned long * __restrict p4);
+void xor_niagara_5(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2,
+		   const unsigned long * __restrict p3,
+		   const unsigned long * __restrict p4,
+		   const unsigned long * __restrict p5);
 
 static struct xor_block_template xor_block_niagara = {
         .name	= "Niagara",