LoongArch: Add SIMD-optimized XOR routines

Add LSX and LASX implementations of xor operations, operating on 64
bytes (one L1 cache line) at a time, for a balance between memory
utilization and instruction mix. Huacai confirmed that all future
LoongArch implementations by Loongson (that we care) will likely also
feature 64-byte cache lines, and experiments show no throughput
improvement with further unrolling.

Performance numbers measured during system boot on a 3A5000 @ 2.5GHz:

> 8regs           : 12702 MB/sec
> 8regs_prefetch  : 10920 MB/sec
> 32regs          : 12686 MB/sec
> 32regs_prefetch : 10918 MB/sec
> lsx             : 17589 MB/sec
> lasx            : 26116 MB/sec

Acked-by: Song Liu <song@kernel.org>
Signed-off-by: WANG Xuerui <git@xen0n.name>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

1 files changed, 34 insertions, 0 deletions

diff --git a/arch/loongarch/include/asm/xor_simd.h b/arch/loongarch/include/asm/xor_simd.h
new file mode 100644
index 000000000000..471b96332f38
--- /dev/null
+++ b/arch/loongarch/include/asm/xor_simd.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2023 WANG Xuerui <git@xen0n.name>
+ */
+#ifndef _ASM_LOONGARCH_XOR_SIMD_H
+#define _ASM_LOONGARCH_XOR_SIMD_H
+
+#ifdef CONFIG_CPU_HAS_LSX
+void xor_lsx_2(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2);
+void xor_lsx_3(unsigned long bytes, unsigned long * __restrict p1,
+	       const unsigned long * __restrict p2, const unsigned long * __restrict p3);
+void xor_lsx_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_lsx_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 /* CONFIG_CPU_HAS_LSX */
+
+#ifdef CONFIG_CPU_HAS_LASX
+void xor_lasx_2(unsigned long bytes, unsigned long * __restrict p1,
+	        const unsigned long * __restrict p2);
+void xor_lasx_3(unsigned long bytes, unsigned long * __restrict p1,
+	        const unsigned long * __restrict p2, const unsigned long * __restrict p3);
+void xor_lasx_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_lasx_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 /* CONFIG_CPU_HAS_LASX */
+
+#endif /* _ASM_LOONGARCH_XOR_SIMD_H */