[RFC PATCH v7 16/21] riscv: Add vector extension XOR implementation

[Greentime Hu]

This patch adds support for vector optimized XOR it is tested in spike and
qemu.

Logs in spike:
[    0.008365] xor: measuring software checksum speed
[    0.048885]    8regs     :  1719.000 MB/sec
[    0.089080]    32regs    :  1717.000 MB/sec
[    0.129275]    rvv       :  7043.000 MB/sec
[    0.129525] xor: using function: rvv (7043.000 MB/sec)

Logs in qemu:
[    0.098943] xor: measuring software checksum speed
[    0.139391]    8regs     :  2911.000 MB/sec
[    0.181079]    32regs    :  2813.000 MB/sec
[    0.224260]    rvv       :    45.000 MB/sec
[    0.225586] xor: using function: 8regs (2911.000 MB/sec)

Signed-off-by: Han-Kuan Chen <hankuan.chen at sifive.com>
Signed-off-by: Greentime Hu <greentime.hu at sifive.com>
---
 arch/riscv/include/asm/xor.h | 74 ++++++++++++++++++++++++++++++++
 arch/riscv/lib/Makefile      |  1 +
 arch/riscv/lib/xor.S         | 81 ++++++++++++++++++++++++++++++++++++
 3 files changed, 156 insertions(+)
 create mode 100644 arch/riscv/include/asm/xor.h
 create mode 100644 arch/riscv/lib/xor.S

diff --git a/arch/riscv/include/asm/xor.h b/arch/riscv/include/asm/xor.h
new file mode 100644
index 000000000000..60ee0224913d
--- /dev/null
+++ b/arch/riscv/include/asm/xor.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+
+#include <linux/hardirq.h>
+#include <asm-generic/xor.h>
+#ifdef CONFIG_VECTOR
+#include <asm/vector.h>
+
+extern void xor_regs_2_(unsigned long bytes, unsigned long *p1,
+			unsigned long *p2);
+extern void xor_regs_3_(unsigned long bytes, unsigned long *p1,
+			unsigned long *p2, unsigned long *p3);
+extern void xor_regs_4_(unsigned long bytes, unsigned long *p1,
+			unsigned long *p2, unsigned long *p3,
+			unsigned long *p4);
+extern void xor_regs_5_(unsigned long bytes, unsigned long *p1,
+			unsigned long *p2, unsigned long *p3, unsigned long *p4,
+			unsigned long *p5);
+
+static void xor_rvv_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	kernel_rvv_begin();
+	xor_regs_2_(bytes, p1, p2);
+	kernel_rvv_end();
+}
+
+static void
+xor_rvv_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3)
+{
+	kernel_rvv_begin();
+	xor_regs_3_(bytes, p1, p2, p3);
+	kernel_rvv_end();
+}
+
+static void
+xor_rvv_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3, unsigned long *p4)
+{
+	kernel_rvv_begin();
+	xor_regs_4_(bytes, p1, p2, p3, p4);
+	kernel_rvv_end();
+}
+
+static void
+xor_rvv_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	kernel_rvv_begin();
+	xor_regs_5_(bytes, p1, p2, p3, p4, p5);
+	kernel_rvv_end();
+}
+
+static struct xor_block_template xor_block_rvv = {
+	.name = "rvv",
+	.do_2 = xor_rvv_2,
+	.do_3 = xor_rvv_3,
+	.do_4 = xor_rvv_4,
+	.do_5 = xor_rvv_5
+};
+
+extern bool has_vector;
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES           \
+	do {        \
+		xor_speed(&xor_block_8regs);    \
+		xor_speed(&xor_block_32regs);    \
+		if (has_vector) { \
+			xor_speed(&xor_block_rvv);\
+		} \
+	} while (0)
+#endif
diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile
index 0d0db80800c4..cedf8d573dc3 100644
--- a/arch/riscv/lib/Makefile
+++ b/arch/riscv/lib/Makefile
@@ -4,3 +4,4 @@ lib-y			+= memcpy.o
 lib-y			+= memset.o
 lib-y			+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
+lib-$(CONFIG_VECTOR)	+= xor.o
diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S
new file mode 100644
index 000000000000..de2e234c39ed
--- /dev/null
+++ b/arch/riscv/lib/xor.S
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 SiFive
+ */
+#include <linux/linkage.h>
+#include <asm-generic/export.h>
+#include <asm/asm.h>
+
+ENTRY(xor_regs_2_)
+	vsetvli a3, a0, e8, m8
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a3
+	vxor.vv v16, v0, v8
+	add a2, a2, a3
+	vse8.v v16, (a1)
+	add a1, a1, a3
+	bnez a0, xor_regs_2_
+	ret
+END(xor_regs_2_)
+EXPORT_SYMBOL(xor_regs_2_)
+
+ENTRY(xor_regs_3_)
+	vsetvli a4, a0, e8, m8
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a4
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a4
+	vxor.vv v16, v0, v16
+	add a3, a3, a4
+	vse8.v v16, (a1)
+	add a1, a1, a4
+	bnez a0, xor_regs_3_
+	ret
+END(xor_regs_3_)
+EXPORT_SYMBOL(xor_regs_3_)
+
+ENTRY(xor_regs_4_)
+	vsetvli a5, a0, e8, m8
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a5
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a5
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a5
+	vxor.vv v16, v0, v24
+	add a4, a4, a5
+	vse8.v v16, (a1)
+	add a1, a1, a5
+	bnez a0, xor_regs_4_
+	ret
+END(xor_regs_4_)
+EXPORT_SYMBOL(xor_regs_4_)
+
+ENTRY(xor_regs_5_)
+	vsetvli a6, a0, e8, m8
+	vle8.v v0, (a1)
+	vle8.v v8, (a2)
+	sub a0, a0, a6
+	vxor.vv v0, v0, v8
+	vle8.v v16, (a3)
+	add a2, a2, a6
+	vxor.vv v0, v0, v16
+	vle8.v v24, (a4)
+	add a3, a3, a6
+	vxor.vv v0, v0, v24
+	vle8.v v8, (a5)
+	add a4, a4, a6
+	vxor.vv v16, v0, v8
+	add a5, a5, a6
+	vse8.v v16, (a1)
+	add a1, a1, a6
+	bnez a0, xor_regs_5_
+	ret
+END(xor_regs_5_)
+EXPORT_SYMBOL(xor_regs_5_)
-- 
2.28.0