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>

4 files changed, 64 insertions, 48 deletions

diff --git a/arch/powerpc/include/asm/xor_altivec.h b/arch/powerpc/include/asm/xor_altivec.h
index 6ca923510b59..294620a25f80 100644
--- a/arch/powerpc/include/asm/xor_altivec.h
+++ b/arch/powerpc/include/asm/xor_altivec.h
@@ -3,17 +3,20 @@
 #define _ASM_POWERPC_XOR_ALTIVEC_H
 
 #ifdef CONFIG_ALTIVEC
-
-void xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
-		   unsigned long *v2_in);
-void xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
-		   unsigned long *v2_in, unsigned long *v3_in);
-void xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
-		   unsigned long *v2_in, unsigned long *v3_in,
-		   unsigned long *v4_in);
-void xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
-		   unsigned long *v2_in, unsigned long *v3_in,
-		   unsigned long *v4_in, unsigned long *v5_in);
+void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2);
+void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2,
+		   const unsigned long * __restrict p3);
+void xor_altivec_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_altivec_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);
 
 #endif
 #endif /* _ASM_POWERPC_XOR_ALTIVEC_H */
diff --git a/arch/powerpc/lib/xor_vmx.c b/arch/powerpc/lib/xor_vmx.c
index 54e61979e80e..aab49d056d18 100644
--- a/arch/powerpc/lib/xor_vmx.c
+++ b/arch/powerpc/lib/xor_vmx.c
@@ -49,8 +49,9 @@ typedef vector signed char unative_t;
 		V1##_3 = vec_xor(V1##_3, V2##_3);	\
 	} while (0)
 
-void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
-		     unsigned long *v2_in)
+void __xor_altivec_2(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in)
 {
 	DEFINE(v1);
 	DEFINE(v2);
@@ -67,8 +68,10 @@ void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
 	} while (--lines > 0);
 }
 
-void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
-		     unsigned long *v2_in, unsigned long *v3_in)
+void __xor_altivec_3(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in,
+		     const unsigned long * __restrict v3_in)
 {
 	DEFINE(v1);
 	DEFINE(v2);
@@ -89,9 +92,11 @@ void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
 	} while (--lines > 0);
 }
 
-void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
-		     unsigned long *v2_in, unsigned long *v3_in,
-		     unsigned long *v4_in)
+void __xor_altivec_4(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in,
+		     const unsigned long * __restrict v3_in,
+		     const unsigned long * __restrict v4_in)
 {
 	DEFINE(v1);
 	DEFINE(v2);
@@ -116,9 +121,12 @@ void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
 	} while (--lines > 0);
 }
 
-void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
-		     unsigned long *v2_in, unsigned long *v3_in,
-		     unsigned long *v4_in, unsigned long *v5_in)
+void __xor_altivec_5(unsigned long bytes,
+		     unsigned long * __restrict v1_in,
+		     const unsigned long * __restrict v2_in,
+		     const unsigned long * __restrict v3_in,
+		     const unsigned long * __restrict v4_in,
+		     const unsigned long * __restrict v5_in)
 {
 	DEFINE(v1);
 	DEFINE(v2);
diff --git a/arch/powerpc/lib/xor_vmx.h b/arch/powerpc/lib/xor_vmx.h
index 5c2b0839b179..573c41d90dac 100644
--- a/arch/powerpc/lib/xor_vmx.h
+++ b/arch/powerpc/lib/xor_vmx.h
@@ -6,16 +6,17 @@
  * outside of the enable/disable altivec block.
  */
 
-void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
-			     unsigned long *v2_in);
-
-void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
-			     unsigned long *v2_in, unsigned long *v3_in);
-
-void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
-			     unsigned long *v2_in, unsigned long *v3_in,
-			     unsigned long *v4_in);
-
-void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
-			     unsigned long *v2_in, unsigned long *v3_in,
-			     unsigned long *v4_in, unsigned long *v5_in);
+void __xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2);
+void __xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1,
+		     const unsigned long * __restrict p2,
+		     const unsigned long * __restrict p3);
+void __xor_altivec_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_altivec_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);
diff --git a/arch/powerpc/lib/xor_vmx_glue.c b/arch/powerpc/lib/xor_vmx_glue.c
index 80dba916c367..35d917ece4d1 100644
--- a/arch/powerpc/lib/xor_vmx_glue.c
+++ b/arch/powerpc/lib/xor_vmx_glue.c
@@ -12,47 +12,51 @@
 #include <asm/xor_altivec.h>
 #include "xor_vmx.h"
 
-void xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
-		   unsigned long *v2_in)
+void xor_altivec_2(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2)
 {
 	preempt_disable();
 	enable_kernel_altivec();
-	__xor_altivec_2(bytes, v1_in, v2_in);
+	__xor_altivec_2(bytes, p1, p2);
 	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_2);
 
-void xor_altivec_3(unsigned long bytes,  unsigned long *v1_in,
-		   unsigned long *v2_in, unsigned long *v3_in)
+void xor_altivec_3(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2,
+		   const unsigned long * __restrict p3)
 {
 	preempt_disable();
 	enable_kernel_altivec();
-	__xor_altivec_3(bytes, v1_in, v2_in, v3_in);
+	__xor_altivec_3(bytes, p1, p2, p3);
 	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_3);
 
-void xor_altivec_4(unsigned long bytes,  unsigned long *v1_in,
-		   unsigned long *v2_in, unsigned long *v3_in,
-		   unsigned long *v4_in)
+void xor_altivec_4(unsigned long bytes, unsigned long * __restrict p1,
+		   const unsigned long * __restrict p2,
+		   const unsigned long * __restrict p3,
+		   const unsigned long * __restrict p4)
 {
 	preempt_disable();
 	enable_kernel_altivec();
-	__xor_altivec_4(bytes, v1_in, v2_in, v3_in, v4_in);
+	__xor_altivec_4(bytes, p1, p2, p3, p4);
 	disable_kernel_altivec();
 	preempt_enable();
 }
 EXPORT_SYMBOL(xor_altivec_4);
 
-void xor_altivec_5(unsigned long bytes,  unsigned long *v1_in,
-		   unsigned long *v2_in, unsigned long *v3_in,
-		   unsigned long *v4_in, unsigned long *v5_in)
+void xor_altivec_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)
 {
 	preempt_disable();
 	enable_kernel_altivec();
-	__xor_altivec_5(bytes, v1_in, v2_in, v3_in, v4_in, v5_in);
+	__xor_altivec_5(bytes, p1, p2, p3, p4, p5);
 	disable_kernel_altivec();
 	preempt_enable();
 }