arm64/xor: use EOR3 instructions when available
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@kernel.org>
Link: https://lore.kernel.org/r/20211213140252.2856053-1-ardb@kernel.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c4207cf..63d41ba 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1545,6 +1545,12 @@
menu "ARMv8.2 architectural features"
+config AS_HAS_ARMV8_2
+ def_bool $(cc-option,-Wa$(comma)-march=armv8.2-a)
+
+config AS_HAS_SHA3
+ def_bool $(as-instr,.arch armv8.2-a+sha3)
+
config ARM64_PMEM
bool "Enable support for persistent memory"
select ARCH_HAS_PMEM_API