[PATCH 19/25] xor: avoid indirect calls for arm64-optimized ops

[Christoph Hellwig]

Remove the inner xor_block_templates, and instead have two separate
actual template that call into the neon-enabled compilation unit.

Signed-off-by: Christoph Hellwig <hch@xxxxxx>
---
 arch/arm64/include/asm/xor.h       | 13 ++--
 lib/raid/xor/arm64/xor-neon-glue.c | 95 +++++++++++++++---------------
 lib/raid/xor/arm64/xor-neon.c      | 73 +++++++++--------------
 lib/raid/xor/arm64/xor-neon.h      | 30 ++++++++++
 4 files changed, 114 insertions(+), 97 deletions(-)
 create mode 100644 lib/raid/xor/arm64/xor-neon.h

diff --git a/arch/arm64/include/asm/xor.h b/arch/arm64/include/asm/xor.h
index 81718f010761..4782c760bcac 100644
--- a/arch/arm64/include/asm/xor.h
+++ b/arch/arm64/include/asm/xor.h
@@ -7,15 +7,18 @@
 #include <asm-generic/xor.h>
 #include <asm/simd.h>
 
-extern struct xor_block_template xor_block_arm64;
-void __init xor_neon_init(void);
+extern struct xor_block_template xor_block_neon;
+extern struct xor_block_template xor_block_eor3;
 
 #define arch_xor_init arch_xor_init
 static __always_inline void __init arch_xor_init(void)
 {
-	xor_neon_init();
 	xor_register(&xor_block_8regs);
 	xor_register(&xor_block_32regs);
-	if (cpu_has_neon())
-		xor_register(&xor_block_arm64);
+	if (cpu_has_neon()) {
+		if (cpu_have_named_feature(SHA3))
+			xor_register(&xor_block_eor3);
+		else
+			xor_register(&xor_block_neon);
+	}
 }
diff --git a/lib/raid/xor/arm64/xor-neon-glue.c b/lib/raid/xor/arm64/xor-neon-glue.c
index 067a2095659a..08c3e3573388 100644
--- a/lib/raid/xor/arm64/xor-neon-glue.c
+++ b/lib/raid/xor/arm64/xor-neon-glue.c
@@ -7,51 +7,54 @@
 #include <linux/raid/xor_impl.h>
 #include <asm/simd.h>
 #include <asm/xor.h>
+#include "xor-neon.h"
 
-extern struct xor_block_template const xor_block_inner_neon;
-
-static void
-xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
-	   const unsigned long * __restrict p2)
-{
-	scoped_ksimd()
-		xor_block_inner_neon.do_2(bytes, p1, p2);
-}
-
-static void
-xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
-	   const unsigned long * __restrict p2,
-	   const unsigned long * __restrict p3)
-{
-	scoped_ksimd()
-		xor_block_inner_neon.do_3(bytes, p1, p2, p3);
-}
-
-static void
-xor_neon_4(unsigned long bytes, unsigned long * __restrict p1,
-	   const unsigned long * __restrict p2,
-	   const unsigned long * __restrict p3,
-	   const unsigned long * __restrict p4)
-{
-	scoped_ksimd()
-		xor_block_inner_neon.do_4(bytes, p1, p2, p3, p4);
-}
-
-static void
-xor_neon_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)
-{
-	scoped_ksimd()
-		xor_block_inner_neon.do_5(bytes, p1, p2, p3, p4, p5);
-}
-
-struct xor_block_template xor_block_arm64 = {
-	.name   = "arm64_neon",
-	.do_2   = xor_neon_2,
-	.do_3   = xor_neon_3,
-	.do_4   = xor_neon_4,
-	.do_5	= xor_neon_5
+#define XOR_TEMPLATE(_name)						\
+static void								\
+xor_##_name##_2(unsigned long bytes, unsigned long * __restrict p1,	\
+	   const unsigned long * __restrict p2)				\
+{									\
+	scoped_ksimd()							\
+		__xor_##_name##_2(bytes, p1, p2);			\
+}									\
+									\
+static void								\
+xor_##_name##_3(unsigned long bytes, unsigned long * __restrict p1,	\
+	   const unsigned long * __restrict p2,				\
+	   const unsigned long * __restrict p3)				\
+{									\
+	scoped_ksimd()							\
+		__xor_##_name##_3(bytes, p1, p2, p3);			\
+}									\
+									\
+static void								\
+xor_##_name##_4(unsigned long bytes, unsigned long * __restrict p1,	\
+	   const unsigned long * __restrict p2,				\
+	   const unsigned long * __restrict p3,				\
+	   const unsigned long * __restrict p4)				\
+{									\
+	scoped_ksimd()							\
+		__xor_##_name##_4(bytes, p1, p2, p3, p4);		\
+}									\
+									\
+static void								\
+xor_##_name##_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)				\
+{									\
+	scoped_ksimd()							\
+		__xor_##_name##_5(bytes, p1, p2, p3, p4, p5);		\
+}									\
+									\
+struct xor_block_template xor_block_##_name = {				\
+	.name   = __stringify(_name),					\
+	.do_2   = xor_##_name##_2,					\
+	.do_3   = xor_##_name##_3,					\
+	.do_4   = xor_##_name##_4,					\
+	.do_5	= xor_##_name##_5					\
 };
+
+XOR_TEMPLATE(neon);
+XOR_TEMPLATE(eor3);
diff --git a/lib/raid/xor/arm64/xor-neon.c b/lib/raid/xor/arm64/xor-neon.c
index 8d2d185090db..61194c292917 100644
--- a/lib/raid/xor/arm64/xor-neon.c
+++ b/lib/raid/xor/arm64/xor-neon.c
@@ -8,9 +8,10 @@
 #include <linux/cache.h>
 #include <asm/neon-intrinsics.h>
 #include <asm/xor.h>
+#include "xor-neon.h"
 
-static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1,
-	const unsigned long * __restrict p2)
+void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -36,9 +37,9 @@ static void xor_arm64_neon_2(unsigned long bytes, unsigned long * __restrict p1,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1,
-	const unsigned long * __restrict p2,
-	const unsigned long * __restrict p3)
+void __xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -72,10 +73,10 @@ static void xor_arm64_neon_3(unsigned long bytes, unsigned long * __restrict p1,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_neon_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_neon_4(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3,
+		const unsigned long * __restrict p4)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -117,11 +118,11 @@ static void xor_arm64_neon_4(unsigned long bytes, unsigned long * __restrict p1,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_neon_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)
+void __xor_neon_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)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -171,14 +172,6 @@ static void xor_arm64_neon_5(unsigned long bytes, unsigned long * __restrict p1,
 	} while (--lines > 0);
 }
 
-struct xor_block_template xor_block_inner_neon __ro_after_init = {
-	.name	= "__inner_neon__",
-	.do_2	= xor_arm64_neon_2,
-	.do_3	= xor_arm64_neon_3,
-	.do_4	= xor_arm64_neon_4,
-	.do_5	= xor_arm64_neon_5,
-};
-
 static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
 {
 	uint64x2_t res;
@@ -189,10 +182,9 @@ static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
 	return res;
 }
 
-static void xor_arm64_eor3_3(unsigned long bytes,
-	unsigned long * __restrict p1,
-	const unsigned long * __restrict p2,
-	const unsigned long * __restrict p3)
+void __xor_eor3_3(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -224,11 +216,10 @@ static void xor_arm64_eor3_3(unsigned long bytes,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_eor3_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_eor3_4(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3,
+		const unsigned long * __restrict p4)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -268,12 +259,11 @@ static void xor_arm64_eor3_4(unsigned long bytes,
 	} while (--lines > 0);
 }
 
-static void xor_arm64_eor3_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)
+void __xor_eor3_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)
 {
 	uint64_t *dp1 = (uint64_t *)p1;
 	uint64_t *dp2 = (uint64_t *)p2;
@@ -314,12 +304,3 @@ static void xor_arm64_eor3_5(unsigned long bytes,
 		dp5 += 8;
 	} while (--lines > 0);
 }
-
-void __init xor_neon_init(void)
-{
-	if (cpu_have_named_feature(SHA3)) {
-		xor_block_inner_neon.do_3 = xor_arm64_eor3_3;
-		xor_block_inner_neon.do_4 = xor_arm64_eor3_4;
-		xor_block_inner_neon.do_5 = xor_arm64_eor3_5;
-	}
-}
diff --git a/lib/raid/xor/arm64/xor-neon.h b/lib/raid/xor/arm64/xor-neon.h
new file mode 100644
index 000000000000..cec0ac846fea
--- /dev/null
+++ b/lib/raid/xor/arm64/xor-neon.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+void __xor_neon_2(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2);
+void __xor_neon_3(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3);
+void __xor_neon_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_neon_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);
+
+#define __xor_eor3_2	__xor_neon_2
+void __xor_eor3_3(unsigned long bytes, unsigned long * __restrict p1,
+		const unsigned long * __restrict p2,
+		const unsigned long * __restrict p3);
+void __xor_eor3_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_eor3_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);
-- 
2.47.3