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>

1 files changed, 36 insertions, 17 deletions

diff --git a/arch/alpha/include/asm/xor.h b/arch/alpha/include/asm/xor.h
index 5aeb4fb3cb7c..e0de0c233ab9 100644
--- a/arch/alpha/include/asm/xor.h
+++ b/arch/alpha/include/asm/xor.h
@@ -5,24 +5,43 @@
  * Optimized RAID-5 checksumming functions for alpha EV5 and EV6
  */
 
-extern void xor_alpha_2(unsigned long, unsigned long *, unsigned long *);
-extern void xor_alpha_3(unsigned long, unsigned long *, unsigned long *,
-		        unsigned long *);
-extern void xor_alpha_4(unsigned long, unsigned long *, unsigned long *,
-		        unsigned long *, unsigned long *);
-extern void xor_alpha_5(unsigned long, unsigned long *, unsigned long *,
-		        unsigned long *, unsigned long *, unsigned long *);
+extern void
+xor_alpha_2(unsigned long bytes, unsigned long * __restrict p1,
+	    const unsigned long * __restrict p2);
+extern void
+xor_alpha_3(unsigned long bytes, unsigned long * __restrict p1,
+	    const unsigned long * __restrict p2,
+	    const unsigned long * __restrict p3);
+extern void
+xor_alpha_4(unsigned long bytes, unsigned long * __restrict p1,
+	    const unsigned long * __restrict p2,
+	    const unsigned long * __restrict p3,
+	    const unsigned long * __restrict p4);
+extern void
+xor_alpha_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);
 
-extern void xor_alpha_prefetch_2(unsigned long, unsigned long *,
-				 unsigned long *);
-extern void xor_alpha_prefetch_3(unsigned long, unsigned long *,
-				 unsigned long *, unsigned long *);
-extern void xor_alpha_prefetch_4(unsigned long, unsigned long *,
-				 unsigned long *, unsigned long *,
-				 unsigned long *);
-extern void xor_alpha_prefetch_5(unsigned long, unsigned long *,
-				 unsigned long *, unsigned long *,
-				 unsigned long *, unsigned long *);
+extern void
+xor_alpha_prefetch_2(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2);
+extern void
+xor_alpha_prefetch_3(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2,
+		     const unsigned long * __restrict p3);
+extern void
+xor_alpha_prefetch_4(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2,
+		     const unsigned long * __restrict p3,
+		     const unsigned long * __restrict p4);
+extern void
+xor_alpha_prefetch_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);
 
 asm("								\n\
 	.text							\n\