From nobody Wed Sep 10 02:04:22 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id F0B39C64ED6 for ; Tue, 28 Feb 2023 00:06:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230152AbjB1AGI (ORCPT ); Mon, 27 Feb 2023 19:06:08 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:35976 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S230054AbjB1AF4 (ORCPT ); Mon, 27 Feb 2023 19:05:56 -0500 Received: from gloria.sntech.de (gloria.sntech.de [185.11.138.130]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A6BD9244B6 for ; Mon, 27 Feb 2023 16:05:53 -0800 (PST) Received: from ip5b412258.dynamic.kabel-deutschland.de ([91.65.34.88] helo=phil.lan) by gloria.sntech.de with esmtpsa (TLS1.3) tls TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384 (Exim 4.94.2) (envelope-from ) id 1pWnV8-000552-0o; Tue, 28 Feb 2023 01:05:50 +0100 From: Heiko Stuebner To: palmer@rivosinc.com Cc: greentime.hu@sifive.com, conor@kernel.org, linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org, christoph.muellner@vrull.eu, heiko@sntech.de, Han-Kuan Chen , Heiko Stuebner Subject: [PATCH RFC v2 02/16] riscv: Add vector extension XOR implementation Date: Tue, 28 Feb 2023 01:05:30 +0100 Message-Id: <20230228000544.2234136-3-heiko@sntech.de> X-Mailer: git-send-email 2.39.0 In-Reply-To: <20230228000544.2234136-1-heiko@sntech.de> References: <20230228000544.2234136-1-heiko@sntech.de> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" From: Greentime Hu This patch adds support for vector optimized XOR and it is tested in qemu. Co-developed-by: Han-Kuan Chen Signed-off-by: Han-Kuan Chen Signed-off-by: Greentime Hu Signed-off-by: Heiko Stuebner --- arch/riscv/include/asm/xor.h | 82 ++++++++++++++++++++++++++++++++++++ arch/riscv/lib/Makefile | 1 + arch/riscv/lib/xor.S | 81 +++++++++++++++++++++++++++++++++++ 3 files changed, 164 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..74867c7fd955 --- /dev/null +++ b/arch/riscv/include/asm/xor.h @@ -0,0 +1,82 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2021 SiFive + */ + +#include +#include +#ifdef CONFIG_VECTOR +#include +#include + +void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2); +void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3); +void xor_regs_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_regs_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); + +static void xor_rvv_2(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2) +{ + kernel_rvv_begin(); + xor_regs_2_(bytes, p1, p2); + kernel_rvv_end(); +} + +static void xor_rvv_3(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3) +{ + kernel_rvv_begin(); + xor_regs_3_(bytes, p1, p2, p3); + kernel_rvv_end(); +} + +static void xor_rvv_4(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3, + const unsigned long *__restrict 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 *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3, + const unsigned long *__restrict p4, + const unsigned long *__restrict p5) +{ + kernel_rvv_begin(); + xor_regs_5_(bytes, p1, p2, p3, p4, p5); + kernel_rvv_end(); +} + +static struct xor_block_template xor_block_rvv =3D { + .name =3D "rvv", + .do_2 =3D xor_rvv_2, + .do_3 =3D xor_rvv_3, + .do_4 =3D xor_rvv_4, + .do_5 =3D xor_rvv_5 +}; + +#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 6c74b0bedd60..d87e0b6fe1d0 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -10,3 +10,4 @@ lib-$(CONFIG_MMU) +=3D uaccess.o lib-$(CONFIG_64BIT) +=3D tishift.o =20 obj-$(CONFIG_FUNCTION_ERROR_INJECTION) +=3D error-inject.o +lib-$(CONFIG_VECTOR) +=3D xor.o diff --git a/arch/riscv/lib/xor.S b/arch/riscv/lib/xor.S new file mode 100644 index 000000000000..3bc059e18171 --- /dev/null +++ b/arch/riscv/lib/xor.S @@ -0,0 +1,81 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2021 SiFive + */ +#include +#include +#include + +ENTRY(xor_regs_2_) + vsetvli a3, a0, e8, m8, ta, ma + 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, ta, ma + 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, ta, ma + 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, ta, ma + 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_) --=20 2.39.0