[PATCH 2/2] arm64/xor: use EOR3 instructions when available

[Ard Biesheuvel]

Use the EOR3 instruction to implement xor_blocks() if the instruction is
available, which is the case if the CPU implements the SHA-3 extension.
This is about 20% faster on Apple M1 when using the 5-way version.

Signed-off-by: Ard Biesheuvel <ardb at kernel.org>
---
 arch/arm64/Kconfig        |   3 +
 arch/arm64/lib/xor-neon.c | 145 ++++++++++++++++++++
 2 files changed, 148 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 6f2d3e31fb54..14354acba5b4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -2034,6 +2034,9 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
+config CC_HAVE_SHA3
+	def_bool $(cc-option, -march=armv8.2-a+sha3)
+
 menu "Power management options"
 
 source "kernel/power/Kconfig"
diff --git a/arch/arm64/lib/xor-neon.c b/arch/arm64/lib/xor-neon.c
index ee4795f3e166..0415cb94c781 100644
--- a/arch/arm64/lib/xor-neon.c
+++ b/arch/arm64/lib/xor-neon.c
@@ -172,6 +172,135 @@ void xor_arm64_neon_5(unsigned long bytes, unsigned long *p1,
 }
 EXPORT_SYMBOL(xor_arm64_neon_5);
 
+static inline uint64x2_t eor3(uint64x2_t p, uint64x2_t q, uint64x2_t r)
+{
+	uint64x2_t res;
+
+	asm(".arch	armv8.2-a+sha3		\n"
+	    "eor3 %0.16b, %1.16b, %2.16b, %3.16b"
+	    : "=w"(res) : "w"(p), "w"(q), "w"(r));
+	return res;
+}
+
+static void xor_arm64_eor3_3(unsigned long bytes, unsigned long *p1,
+			     unsigned long *p2, unsigned long *p3)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_eor3_4(unsigned long bytes, unsigned long *p1,
+			     unsigned long *p2, unsigned long *p3,
+			     unsigned long *p4)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* p1 ^= p4 */
+		v0 = veorq_u64(v0, vld1q_u64(dp4 + 0));
+		v1 = veorq_u64(v1, vld1q_u64(dp4 + 2));
+		v2 = veorq_u64(v2, vld1q_u64(dp4 + 4));
+		v3 = veorq_u64(v3, vld1q_u64(dp4 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+	} while (--lines > 0);
+}
+
+static void xor_arm64_eor3_5(unsigned long bytes, unsigned long *p1,
+			     unsigned long *p2, unsigned long *p3,
+			     unsigned long *p4, unsigned long *p5)
+{
+	uint64_t *dp1 = (uint64_t *)p1;
+	uint64_t *dp2 = (uint64_t *)p2;
+	uint64_t *dp3 = (uint64_t *)p3;
+	uint64_t *dp4 = (uint64_t *)p4;
+	uint64_t *dp5 = (uint64_t *)p5;
+
+	register uint64x2_t v0, v1, v2, v3;
+	long lines = bytes / (sizeof(uint64x2_t) * 4);
+
+	do {
+		/* p1 ^= p2 ^ p3 */
+		v0 = eor3(vld1q_u64(dp1 + 0), vld1q_u64(dp2 + 0),
+			  vld1q_u64(dp3 + 0));
+		v1 = eor3(vld1q_u64(dp1 + 2), vld1q_u64(dp2 + 2),
+			  vld1q_u64(dp3 + 2));
+		v2 = eor3(vld1q_u64(dp1 + 4), vld1q_u64(dp2 + 4),
+			  vld1q_u64(dp3 + 4));
+		v3 = eor3(vld1q_u64(dp1 + 6), vld1q_u64(dp2 + 6),
+			  vld1q_u64(dp3 + 6));
+
+		/* p1 ^= p4 ^ p5 */
+		v0 = eor3(v0, vld1q_u64(dp4 + 0), vld1q_u64(dp5 + 0));
+		v1 = eor3(v1, vld1q_u64(dp4 + 2), vld1q_u64(dp5 + 2));
+		v2 = eor3(v2, vld1q_u64(dp4 + 4), vld1q_u64(dp5 + 4));
+		v3 = eor3(v3, vld1q_u64(dp4 + 6), vld1q_u64(dp5 + 6));
+
+		/* store */
+		vst1q_u64(dp1 + 0, v0);
+		vst1q_u64(dp1 + 2, v1);
+		vst1q_u64(dp1 + 4, v2);
+		vst1q_u64(dp1 + 6, v3);
+
+		dp1 += 8;
+		dp2 += 8;
+		dp3 += 8;
+		dp4 += 8;
+		dp5 += 8;
+	} while (--lines > 0);
+}
+
 DEFINE_STATIC_CALL(xor_arm64_3, xor_arm64_neon_3);
 DEFINE_STATIC_CALL(xor_arm64_4, xor_arm64_neon_4);
 DEFINE_STATIC_CALL(xor_arm64_5, xor_arm64_neon_5);
@@ -180,6 +309,22 @@ EXPORT_STATIC_CALL(xor_arm64_3);
 EXPORT_STATIC_CALL(xor_arm64_4);
 EXPORT_STATIC_CALL(xor_arm64_5);
 
+static int __init xor_neon_init(void)
+{
+	if (IS_ENABLED(CONFIG_CC_HAVE_SHA3) && cpu_have_named_feature(SHA3)) {
+		static_call_update(xor_arm64_3, xor_arm64_eor3_3);
+		static_call_update(xor_arm64_4, xor_arm64_eor3_4);
+		static_call_update(xor_arm64_5, xor_arm64_eor3_5);
+	}
+	return 0;
+}
+module_init(xor_neon_init);
+
+static void __exit xor_neon_exit(void)
+{
+}
+module_exit(xor_neon_exit);
+
 MODULE_AUTHOR("Jackie Liu <liuyun01 at kylinos.cn>");
 MODULE_DESCRIPTION("ARMv8 XOR Extensions");
 MODULE_LICENSE("GPL");
-- 
2.30.2