From mboxrd@z Thu Jan 1 00:00:00 1970 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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 03A97C433EF for ; Wed, 29 Sep 2021 17:22:56 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E18536147F for ; Wed, 29 Sep 2021 17:22:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1344334AbhI2RYf (ORCPT ); Wed, 29 Sep 2021 13:24:35 -0400 Received: from mail-wm1-f51.google.com ([209.85.128.51]:53861 "EHLO mail-wm1-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345497AbhI2RY1 (ORCPT ); Wed, 29 Sep 2021 13:24:27 -0400 Received: by mail-wm1-f51.google.com with SMTP id z2so2422233wmc.3; Wed, 29 Sep 2021 10:22:45 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=2UDPh4La5iwY4VW8a0ZpuzCkHbdxXf3VO7p8sK54Uxs=; b=C+r4Mmh8r/X9VlgjgxRrk8Y1bo9CRKwB5BR3CyGAMLc6YHJQwEjinsqp0NBmhQ7Ai9 56LFjxpwz4g3XdJYrJ+OTb5TJcvsgUOWioRrQDEGfon26dzuv+Y8nYG1ctpwsrzNL+fv Wj4DkfjPJFXmvfL6rqCkhJZAFxoWk4w9qPM+aAFlsHCkolDTDEfj+0JUHAPUC8tkVeKk FpyDG/aw4GJZ6hkaOchRd8/ir0GmeUzGXnchEE1q8GSL3frMw9OFZU4i/SxYlBzBBL1o Fxn4/XKqG6mC2+RTfmPe8nwEIsRARqs8iVnXnR/oxNFHpJMMrvrkH23jf1x6Teu5pGQ8 Eq6g== X-Gm-Message-State: AOAM530p1ztWp3lxSQYbqKCimoeie5cAtmxDby+mfUmIy5+Khhi3iJCW fSTT4Lkz8JpXuyOBcryrnVM= X-Google-Smtp-Source: ABdhPJzOJRD8kTgcIoOlSJO+c6h1SdfYm2RATbr4K5FHw81r5UiWIq687hZBst/OMLPVeCTHb7N7TQ== X-Received: by 2002:a7b:c948:: with SMTP id i8mr11448019wml.193.1632936164903; Wed, 29 Sep 2021 10:22:44 -0700 (PDT) Received: from msft-t490s.. (mob-31-159-120-132.net.vodafone.it. [31.159.120.132]) by smtp.gmail.com with ESMTPSA id n26sm2267502wmi.43.2021.09.29.10.22.43 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 29 Sep 2021 10:22:44 -0700 (PDT) From: Matteo Croce To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Atish Patra , Emil Renner Berthing , Akira Tsukamoto , Drew Fustini , Bin Meng , David Laight , Guo Ren , Christoph Hellwig Subject: [PATCH v5 3/3] riscv: optimized memset Date: Wed, 29 Sep 2021 19:22:34 +0200 Message-Id: <20210929172234.31620-4-mcroce@linux.microsoft.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210929172234.31620-1-mcroce@linux.microsoft.com> References: <20210929172234.31620-1-mcroce@linux.microsoft.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Matteo Croce The generic memset is defined as a byte at time write. This is always safe, but it's slower than a 4 byte or even 8 byte write. Write a generic memset which fills the data one byte at time until the destination is aligned, then fills using the largest size allowed, and finally fills the remaining data one byte at time. Signed-off-by: Matteo Croce --- arch/riscv/include/asm/string.h | 10 +-- arch/riscv/kernel/Makefile | 1 - arch/riscv/kernel/riscv_ksyms.c | 13 ---- arch/riscv/lib/Makefile | 1 - arch/riscv/lib/memset.S | 113 -------------------------------- arch/riscv/lib/string.c | 41 ++++++++++++ 6 files changed, 44 insertions(+), 135 deletions(-) delete mode 100644 arch/riscv/kernel/riscv_ksyms.c delete mode 100644 arch/riscv/lib/memset.S diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h index 25d9b9078569..90500635035a 100644 --- a/arch/riscv/include/asm/string.h +++ b/arch/riscv/include/asm/string.h @@ -6,14 +6,10 @@ #ifndef _ASM_RISCV_STRING_H #define _ASM_RISCV_STRING_H -#include -#include - -#define __HAVE_ARCH_MEMSET -extern asmlinkage void *memset(void *, int, size_t); -extern asmlinkage void *__memset(void *, int, size_t); - #ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE +#define __HAVE_ARCH_MEMSET +extern void *memset(void *s, int c, size_t count); +extern void *__memset(void *s, int c, size_t count); #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *dest, const void *src, size_t count); extern void *__memcpy(void *dest, const void *src, size_t count); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 3397ddac1a30..fecf03822435 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,6 @@ obj-y += syscall_table.o obj-y += sys_riscv.o obj-y += time.o obj-y += traps.o -obj-y += riscv_ksyms.o obj-y += stacktrace.o obj-y += cacheinfo.o obj-y += patch.o diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c deleted file mode 100644 index 361565c4db7e..000000000000 --- a/arch/riscv/kernel/riscv_ksyms.c +++ /dev/null @@ -1,13 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2017 Zihao Yu - */ - -#include -#include - -/* - * Assembly functions that may be used (directly or indirectly) by modules - */ -EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(__memset); diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 484f5ff7b508..e33263cc622a 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only lib-y += delay.o -lib-y += memset.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S deleted file mode 100644 index 34c5360c6705..000000000000 --- a/arch/riscv/lib/memset.S +++ /dev/null @@ -1,113 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2013 Regents of the University of California - */ - - -#include -#include - -/* void *memset(void *, int, size_t) */ -ENTRY(__memset) -WEAK(memset) - move t0, a0 /* Preserve return value */ - - /* Defer to byte-oriented fill for small sizes */ - sltiu a3, a2, 16 - bnez a3, 4f - - /* - * Round to nearest XLEN-aligned address - * greater than or equal to start address - */ - addi a3, t0, SZREG-1 - andi a3, a3, ~(SZREG-1) - beq a3, t0, 2f /* Skip if already aligned */ - /* Handle initial misalignment */ - sub a4, a3, t0 -1: - sb a1, 0(t0) - addi t0, t0, 1 - bltu t0, a3, 1b - sub a2, a2, a4 /* Update count */ - -2: /* Duff's device with 32 XLEN stores per iteration */ - /* Broadcast value into all bytes */ - andi a1, a1, 0xff - slli a3, a1, 8 - or a1, a3, a1 - slli a3, a1, 16 - or a1, a3, a1 -#ifdef CONFIG_64BIT - slli a3, a1, 32 - or a1, a3, a1 -#endif - - /* Calculate end address */ - andi a4, a2, ~(SZREG-1) - add a3, t0, a4 - - andi a4, a4, 31*SZREG /* Calculate remainder */ - beqz a4, 3f /* Shortcut if no remainder */ - neg a4, a4 - addi a4, a4, 32*SZREG /* Calculate initial offset */ - - /* Adjust start address with offset */ - sub t0, t0, a4 - - /* Jump into loop body */ - /* Assumes 32-bit instruction lengths */ - la a5, 3f -#ifdef CONFIG_64BIT - srli a4, a4, 1 -#endif - add a5, a5, a4 - jr a5 -3: - REG_S a1, 0(t0) - REG_S a1, SZREG(t0) - REG_S a1, 2*SZREG(t0) - REG_S a1, 3*SZREG(t0) - REG_S a1, 4*SZREG(t0) - REG_S a1, 5*SZREG(t0) - REG_S a1, 6*SZREG(t0) - REG_S a1, 7*SZREG(t0) - REG_S a1, 8*SZREG(t0) - REG_S a1, 9*SZREG(t0) - REG_S a1, 10*SZREG(t0) - REG_S a1, 11*SZREG(t0) - REG_S a1, 12*SZREG(t0) - REG_S a1, 13*SZREG(t0) - REG_S a1, 14*SZREG(t0) - REG_S a1, 15*SZREG(t0) - REG_S a1, 16*SZREG(t0) - REG_S a1, 17*SZREG(t0) - REG_S a1, 18*SZREG(t0) - REG_S a1, 19*SZREG(t0) - REG_S a1, 20*SZREG(t0) - REG_S a1, 21*SZREG(t0) - REG_S a1, 22*SZREG(t0) - REG_S a1, 23*SZREG(t0) - REG_S a1, 24*SZREG(t0) - REG_S a1, 25*SZREG(t0) - REG_S a1, 26*SZREG(t0) - REG_S a1, 27*SZREG(t0) - REG_S a1, 28*SZREG(t0) - REG_S a1, 29*SZREG(t0) - REG_S a1, 30*SZREG(t0) - REG_S a1, 31*SZREG(t0) - addi t0, t0, 32*SZREG - bltu t0, a3, 3b - andi a2, a2, SZREG-1 /* Update count */ - -4: - /* Handle trailing misalignment */ - beqz a2, 6f - add a3, t0, a2 -5: - sb a1, 0(t0) - addi t0, t0, 1 - bltu t0, a3, 5b -6: - ret -END(__memset) diff --git a/arch/riscv/lib/string.c b/arch/riscv/lib/string.c index 4442ca5ef13c..871ffbfac0ab 100644 --- a/arch/riscv/lib/string.c +++ b/arch/riscv/lib/string.c @@ -111,3 +111,44 @@ EXPORT_SYMBOL(__memmove); void *memmove(void *dest, const void *src, size_t count) __weak __alias(__memmove); EXPORT_SYMBOL(memmove); + +void *__memset(void *s, int c, size_t count) +{ + union types dest = { .as_u8 = s }; + + if (count >= MIN_THRESHOLD) { + unsigned long cu = (unsigned long)c; + + /* Compose an ulong with 'c' repeated 4/8 times */ +#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER + cu *= 0x0101010101010101UL; +#else + cu |= cu << 8; + cu |= cu << 16; + /* Suppress warning on 32 bit machines */ + cu |= (cu << 16) << 16; +#endif + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + /* + * Fill the buffer one byte at time until + * the destination is word aligned. + */ + for (; count && dest.as_uptr & WORD_MASK; count--) + *dest.as_u8++ = c; + } + + /* Copy using the largest size allowed */ + for (; count >= BYTES_LONG; count -= BYTES_LONG) + *dest.as_ulong++ = cu; + } + + /* copy the remainder */ + while (count--) + *dest.as_u8++ = c; + + return s; +} +EXPORT_SYMBOL(__memset); + +void *memset(void *s, int c, size_t count) __weak __alias(__memset); +EXPORT_SYMBOL(memset); -- 2.31.1 From mboxrd@z Thu Jan 1 00:00:00 1970 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 mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id A638EC433F5 for ; Wed, 29 Sep 2021 17:23:12 +0000 (UTC) Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 6750E60E08 for ; Wed, 29 Sep 2021 17:23:12 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 6750E60E08 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.microsoft.com Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=lists.infradead.org DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender: Content-Transfer-Encoding:Content-Type:List-Subscribe:List-Help:List-Post: List-Archive:List-Unsubscribe:List-Id:MIME-Version:References:In-Reply-To: Message-Id:Date:Subject:Cc:To:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=/sX2afOo0XkG+2u6V7Qf80Xg4O60IO0sVdnanVJGB3Q=; b=SeXp+YanPa1ifR GVzGtTX84TXfQIA8BsPRxZIC6rgPMOqa/cGJ0X3b51SiM6EvHzACWxfGLhZt9532sEU9XgSC4/g6I +zmBsv1bS47G/V6k51qvjuuXyLA7l8njgin8lBSFfkgVd4RI6tR0NGTQiNMHgu8z6QFyK6o1iu1aY LZQFhlUmemx0FfsUdoOnhHuYcQb0oKkzzpEffwYZZ0JED3t5wY7ZeksF7BZyJ7/Djz6mq7IhIV/lw xCOHgdiqqOboOZm1p2tb5RwkD6vkLu7WQVKupWN+ose7LaKvcHVlENLPVwCmY7DxW2bUgRXzqL668 debW70Dkq9r0gdhvjk5w==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.94.2 #2 (Red Hat Linux)) id 1mVdIB-00BuW3-2O; Wed, 29 Sep 2021 17:22:51 +0000 Received: from mail-wm1-f48.google.com ([209.85.128.48]) by bombadil.infradead.org with esmtps (Exim 4.94.2 #2 (Red Hat Linux)) id 1mVdI7-00BuUf-01 for linux-riscv@lists.infradead.org; Wed, 29 Sep 2021 17:22:48 +0000 Received: by mail-wm1-f48.google.com with SMTP id j27so2462686wms.0 for ; Wed, 29 Sep 2021 10:22:46 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=2UDPh4La5iwY4VW8a0ZpuzCkHbdxXf3VO7p8sK54Uxs=; b=aU2ibCfg2iRL9e73X1zO6uuDbzWZVlbYNpE/iAHnjY4VlHUwTP33G4B1zXI3ett31J toS6LJwwmjbznsOYoKj6m4eRf4CK6po4rOV7S+FBLzMFWLDaKstJVZIKdZsrxTwhcEeQ L5nkNhc2wMaOWPDmxLewH/zznktQAfLWUMfY6oL0ujLohEakA3iZrp4gR/SE8OrCg6qk HdyhRROk3Jk1aj8lbnLJS+XbrO9H5uV9gCUbhyvdlt5Lv/EORxUE9H/mSqEaQeRqtxeH jELDqFKUXWUmnMjDffFdrpI0+RoEpkOCtmUok+Hbz+7CusfMaH1ru9X25H6Y0+ncBssf u3Iw== X-Gm-Message-State: AOAM532sneq9LgLi6i5kQ+j/zdvng4BjuTSe17aIVsRCiKM6mNLIQ0ub apakSe+LiL91VWrDZgga6KV65Tu+j8kl4g== X-Google-Smtp-Source: ABdhPJzOJRD8kTgcIoOlSJO+c6h1SdfYm2RATbr4K5FHw81r5UiWIq687hZBst/OMLPVeCTHb7N7TQ== X-Received: by 2002:a7b:c948:: with SMTP id i8mr11448019wml.193.1632936164903; Wed, 29 Sep 2021 10:22:44 -0700 (PDT) Received: from msft-t490s.. (mob-31-159-120-132.net.vodafone.it. [31.159.120.132]) by smtp.gmail.com with ESMTPSA id n26sm2267502wmi.43.2021.09.29.10.22.43 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 29 Sep 2021 10:22:44 -0700 (PDT) From: Matteo Croce To: linux-riscv@lists.infradead.org Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org, Paul Walmsley , Palmer Dabbelt , Albert Ou , Atish Patra , Emil Renner Berthing , Akira Tsukamoto , Drew Fustini , Bin Meng , David Laight , Guo Ren , Christoph Hellwig Subject: [PATCH v5 3/3] riscv: optimized memset Date: Wed, 29 Sep 2021 19:22:34 +0200 Message-Id: <20210929172234.31620-4-mcroce@linux.microsoft.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210929172234.31620-1-mcroce@linux.microsoft.com> References: <20210929172234.31620-1-mcroce@linux.microsoft.com> MIME-Version: 1.0 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20210929_102247_081066_CCF3E2EF X-CRM114-Status: GOOD ( 23.14 ) X-BeenThere: linux-riscv@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org From: Matteo Croce The generic memset is defined as a byte at time write. This is always safe, but it's slower than a 4 byte or even 8 byte write. Write a generic memset which fills the data one byte at time until the destination is aligned, then fills using the largest size allowed, and finally fills the remaining data one byte at time. Signed-off-by: Matteo Croce --- arch/riscv/include/asm/string.h | 10 +-- arch/riscv/kernel/Makefile | 1 - arch/riscv/kernel/riscv_ksyms.c | 13 ---- arch/riscv/lib/Makefile | 1 - arch/riscv/lib/memset.S | 113 -------------------------------- arch/riscv/lib/string.c | 41 ++++++++++++ 6 files changed, 44 insertions(+), 135 deletions(-) delete mode 100644 arch/riscv/kernel/riscv_ksyms.c delete mode 100644 arch/riscv/lib/memset.S diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h index 25d9b9078569..90500635035a 100644 --- a/arch/riscv/include/asm/string.h +++ b/arch/riscv/include/asm/string.h @@ -6,14 +6,10 @@ #ifndef _ASM_RISCV_STRING_H #define _ASM_RISCV_STRING_H -#include -#include - -#define __HAVE_ARCH_MEMSET -extern asmlinkage void *memset(void *, int, size_t); -extern asmlinkage void *__memset(void *, int, size_t); - #ifdef CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE +#define __HAVE_ARCH_MEMSET +extern void *memset(void *s, int c, size_t count); +extern void *__memset(void *s, int c, size_t count); #define __HAVE_ARCH_MEMCPY extern void *memcpy(void *dest, const void *src, size_t count); extern void *__memcpy(void *dest, const void *src, size_t count); diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile index 3397ddac1a30..fecf03822435 100644 --- a/arch/riscv/kernel/Makefile +++ b/arch/riscv/kernel/Makefile @@ -31,7 +31,6 @@ obj-y += syscall_table.o obj-y += sys_riscv.o obj-y += time.o obj-y += traps.o -obj-y += riscv_ksyms.o obj-y += stacktrace.o obj-y += cacheinfo.o obj-y += patch.o diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c deleted file mode 100644 index 361565c4db7e..000000000000 --- a/arch/riscv/kernel/riscv_ksyms.c +++ /dev/null @@ -1,13 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2017 Zihao Yu - */ - -#include -#include - -/* - * Assembly functions that may be used (directly or indirectly) by modules - */ -EXPORT_SYMBOL(memset); -EXPORT_SYMBOL(__memset); diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 484f5ff7b508..e33263cc622a 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -1,6 +1,5 @@ # SPDX-License-Identifier: GPL-2.0-only lib-y += delay.o -lib-y += memset.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S deleted file mode 100644 index 34c5360c6705..000000000000 --- a/arch/riscv/lib/memset.S +++ /dev/null @@ -1,113 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2013 Regents of the University of California - */ - - -#include -#include - -/* void *memset(void *, int, size_t) */ -ENTRY(__memset) -WEAK(memset) - move t0, a0 /* Preserve return value */ - - /* Defer to byte-oriented fill for small sizes */ - sltiu a3, a2, 16 - bnez a3, 4f - - /* - * Round to nearest XLEN-aligned address - * greater than or equal to start address - */ - addi a3, t0, SZREG-1 - andi a3, a3, ~(SZREG-1) - beq a3, t0, 2f /* Skip if already aligned */ - /* Handle initial misalignment */ - sub a4, a3, t0 -1: - sb a1, 0(t0) - addi t0, t0, 1 - bltu t0, a3, 1b - sub a2, a2, a4 /* Update count */ - -2: /* Duff's device with 32 XLEN stores per iteration */ - /* Broadcast value into all bytes */ - andi a1, a1, 0xff - slli a3, a1, 8 - or a1, a3, a1 - slli a3, a1, 16 - or a1, a3, a1 -#ifdef CONFIG_64BIT - slli a3, a1, 32 - or a1, a3, a1 -#endif - - /* Calculate end address */ - andi a4, a2, ~(SZREG-1) - add a3, t0, a4 - - andi a4, a4, 31*SZREG /* Calculate remainder */ - beqz a4, 3f /* Shortcut if no remainder */ - neg a4, a4 - addi a4, a4, 32*SZREG /* Calculate initial offset */ - - /* Adjust start address with offset */ - sub t0, t0, a4 - - /* Jump into loop body */ - /* Assumes 32-bit instruction lengths */ - la a5, 3f -#ifdef CONFIG_64BIT - srli a4, a4, 1 -#endif - add a5, a5, a4 - jr a5 -3: - REG_S a1, 0(t0) - REG_S a1, SZREG(t0) - REG_S a1, 2*SZREG(t0) - REG_S a1, 3*SZREG(t0) - REG_S a1, 4*SZREG(t0) - REG_S a1, 5*SZREG(t0) - REG_S a1, 6*SZREG(t0) - REG_S a1, 7*SZREG(t0) - REG_S a1, 8*SZREG(t0) - REG_S a1, 9*SZREG(t0) - REG_S a1, 10*SZREG(t0) - REG_S a1, 11*SZREG(t0) - REG_S a1, 12*SZREG(t0) - REG_S a1, 13*SZREG(t0) - REG_S a1, 14*SZREG(t0) - REG_S a1, 15*SZREG(t0) - REG_S a1, 16*SZREG(t0) - REG_S a1, 17*SZREG(t0) - REG_S a1, 18*SZREG(t0) - REG_S a1, 19*SZREG(t0) - REG_S a1, 20*SZREG(t0) - REG_S a1, 21*SZREG(t0) - REG_S a1, 22*SZREG(t0) - REG_S a1, 23*SZREG(t0) - REG_S a1, 24*SZREG(t0) - REG_S a1, 25*SZREG(t0) - REG_S a1, 26*SZREG(t0) - REG_S a1, 27*SZREG(t0) - REG_S a1, 28*SZREG(t0) - REG_S a1, 29*SZREG(t0) - REG_S a1, 30*SZREG(t0) - REG_S a1, 31*SZREG(t0) - addi t0, t0, 32*SZREG - bltu t0, a3, 3b - andi a2, a2, SZREG-1 /* Update count */ - -4: - /* Handle trailing misalignment */ - beqz a2, 6f - add a3, t0, a2 -5: - sb a1, 0(t0) - addi t0, t0, 1 - bltu t0, a3, 5b -6: - ret -END(__memset) diff --git a/arch/riscv/lib/string.c b/arch/riscv/lib/string.c index 4442ca5ef13c..871ffbfac0ab 100644 --- a/arch/riscv/lib/string.c +++ b/arch/riscv/lib/string.c @@ -111,3 +111,44 @@ EXPORT_SYMBOL(__memmove); void *memmove(void *dest, const void *src, size_t count) __weak __alias(__memmove); EXPORT_SYMBOL(memmove); + +void *__memset(void *s, int c, size_t count) +{ + union types dest = { .as_u8 = s }; + + if (count >= MIN_THRESHOLD) { + unsigned long cu = (unsigned long)c; + + /* Compose an ulong with 'c' repeated 4/8 times */ +#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER + cu *= 0x0101010101010101UL; +#else + cu |= cu << 8; + cu |= cu << 16; + /* Suppress warning on 32 bit machines */ + cu |= (cu << 16) << 16; +#endif + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) { + /* + * Fill the buffer one byte at time until + * the destination is word aligned. + */ + for (; count && dest.as_uptr & WORD_MASK; count--) + *dest.as_u8++ = c; + } + + /* Copy using the largest size allowed */ + for (; count >= BYTES_LONG; count -= BYTES_LONG) + *dest.as_ulong++ = cu; + } + + /* copy the remainder */ + while (count--) + *dest.as_u8++ = c; + + return s; +} +EXPORT_SYMBOL(__memset); + +void *memset(void *s, int c, size_t count) __weak __alias(__memset); +EXPORT_SYMBOL(memset); -- 2.31.1 _______________________________________________ linux-riscv mailing list linux-riscv@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-riscv