From patchwork Mon Sep 11 22:57:12 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Charlie Jenkins X-Patchwork-Id: 13380306 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 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 smtp.lore.kernel.org (Postfix) with ESMTPS id AD3D2CA0EC3 for ; Mon, 11 Sep 2023 22:58:05 +0000 (UTC) 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:Cc:To:In-Reply-To:References:Message-Id :MIME-Version:Subject:Date:From:Reply-To:Content-ID:Content-Description: Resent-Date:Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID: List-Owner; bh=c/0DgrEr6LXkvSji6quBVDyS1/Wxw9FYwiIwP9OhrL8=; b=QNkqHQgn7B8+Rq 8iQV4OGyd49tDzAIDYvdAAbbSwAEl1SpApyLVCzB1fSPD5PQZffat3gD9WKtyc2p9zjwyCA2A6Knv vYfRVie8IUkCXwSGhiM7a1P4w6pX3CqRLAenKMutre2V6NsSs+d+ApTVrK5/3ectQYqB9ddhuUpW5 yoJsSpMoNrFyKMWUoHe3XrJcrqHCYp6G6ZBp1XyIo0YMLyekEdivRkq8W/dLc3U1winNDbfkEXiGR GTwITqCMVAAJXDzNFdMSZfhTSuk0PVY0chgWomZmhGCRiHBzh7gGqDGtKbkh4DscVf63MCvptY3gV 2yDWBqVeZ45ylLw+uV7w==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.96 #2 (Red Hat Linux)) id 1qfpqp-001YbZ-3B; Mon, 11 Sep 2023 22:57:51 +0000 Received: from mail-pl1-x635.google.com ([2607:f8b0:4864:20::635]) by bombadil.infradead.org with esmtps (Exim 4.96 #2 (Red Hat Linux)) id 1qfpqm-001YZA-1o for linux-riscv@lists.infradead.org; Mon, 11 Sep 2023 22:57:50 +0000 Received: by mail-pl1-x635.google.com with SMTP id d9443c01a7336-1c3bd829b86so10967365ad.0 for ; Mon, 11 Sep 2023 15:57:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=rivosinc-com.20230601.gappssmtp.com; s=20230601; t=1694473066; x=1695077866; darn=lists.infradead.org; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=+ms8k7ArODaombVNk5ZcEzAPy/MdwZ2bVoWD3cFyslE=; b=bn6IFBH8pSLleOvWr7OKzjtb6YtXbPuCX7J36TX8pexMuz/qhnBOuEjGmKMkM/xqzC em+HKzDwvVp6FxO/VoIQNXXbt+lcwbnIKscCNbW1wW+Bt31eubICQoq1t8GtMsp08zQ5 +rKw60uIoVm1nMXfDfGuK6Dz1CWzTa0eJ+OZOm5eD99wyJKWQUAd/piE+O6v2qz+6R13 4Rwp6bh+TXe5or9xQwUmKM8JREocYgviZks5i8Fw7faiHWyJYOaoWcMnyEIt3Mw7P1/M ki+Px6zrZTBV6EB58jQCaUtpVzTQlfq3r8TLc0t+LV2883HCtLE4SJ0da2z7M1Wb7Wyd LYnA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1694473066; x=1695077866; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=+ms8k7ArODaombVNk5ZcEzAPy/MdwZ2bVoWD3cFyslE=; b=HXLjOtGRnU9QX1i4DVJ7M6DVwjgbV+SyPGFpuImmrjG8KFnZo50TBjNS4GmSyqdMuR gOsYiTZisEffw1nH48X6re2lHJ9BKjBQRdEMR2rUCTwirn5a/BX5EWuq5gmCjaK9yc5W QyuWDdqjbJ9q4B86pOD5d5k7TdqujVxgbnRr99Rja6bTlzvFSxnKEJthKOPkZIZd2tHk pv3GUU2Sn/csHE2dsm+5M/HCBGrINBKF39TFGzoVlIezumfpWAs3YnNqQbMSUcyrjEu/ 7r9WiIYiSv86osVUci913XxSeKhZD6bxQqLrbBOtAIKUpCCVOarmFOIErxS0wX+ztzbu 3LFw== X-Gm-Message-State: AOJu0Yzux5Tn8oD9WlUb0rgAINr9MbiD4lGwZ44nFUCwovJMjuNLaePx ENsbDN+7eNE+Zp9pWfdk777M+w== X-Google-Smtp-Source: AGHT+IFseiIGkQQUYIRDQ2/VHhe3/j+wJs8HSqSOJLA1UVY3oMABntHwFYHSFKd4olHZ2bziTc2/cQ== X-Received: by 2002:a05:6a20:e110:b0:153:6a8b:8f5d with SMTP id kr16-20020a056a20e11000b001536a8b8f5dmr12665316pzb.23.1694473066563; Mon, 11 Sep 2023 15:57:46 -0700 (PDT) Received: from charlie.ba.rivosinc.com ([66.220.2.162]) by smtp.gmail.com with ESMTPSA id y18-20020aa78052000000b0066a2e8431a0sm6021038pfm.183.2023.09.11.15.57.45 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 11 Sep 2023 15:57:46 -0700 (PDT) From: Charlie Jenkins Date: Mon, 11 Sep 2023 15:57:12 -0700 Subject: [PATCH v4 2/5] riscv: Add checksum library MIME-Version: 1.0 Message-Id: <20230911-optimize_checksum-v4-2-77cc2ad9e9d7@rivosinc.com> References: <20230911-optimize_checksum-v4-0-77cc2ad9e9d7@rivosinc.com> In-Reply-To: <20230911-optimize_checksum-v4-0-77cc2ad9e9d7@rivosinc.com> To: Charlie Jenkins , Palmer Dabbelt , Conor Dooley , Samuel Holland , David Laight , linux-riscv@lists.infradead.org, linux-kernel@vger.kernel.org Cc: Paul Walmsley , Albert Ou X-Mailer: b4 0.12.3 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20230911_155748_597508_E1D5C89B X-CRM114-Status: GOOD ( 24.35 ) 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: , Sender: "linux-riscv" Errors-To: linux-riscv-bounces+linux-riscv=archiver.kernel.org@lists.infradead.org Provide a 32 and 64 bit version of do_csum. When compiled for 32-bit will load from the buffer in groups of 32 bits, and when compiled for 64-bit will load in groups of 64 bits. Benchmarking by proxy compiling csum_ipv6_magic (64-bit version) for an x86 chip as well as running the riscv generated code in QEMU, discovered that summing in a tree-like structure is about 4% faster than doing 64-bit reads. Signed-off-by: Charlie Jenkins --- arch/riscv/include/asm/checksum.h | 11 ++ arch/riscv/lib/Makefile | 1 + arch/riscv/lib/csum.c | 210 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 222 insertions(+) diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h index 0d7fc8275a5e..a09a4053fb87 100644 --- a/arch/riscv/include/asm/checksum.h +++ b/arch/riscv/include/asm/checksum.h @@ -16,6 +16,14 @@ typedef unsigned int csum_t; typedef unsigned long csum_t; #endif +/* Default version is sufficient for 32 bit */ +#ifdef CONFIG_64BIT +#define _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum); +#endif + /* * Fold a partial checksum without adding pseudo headers */ @@ -90,6 +98,9 @@ static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) #define ip_fast_csum ip_fast_csum +extern unsigned int do_csum(const unsigned char *buff, int len); +#define do_csum do_csum + #include #endif // __ASM_RISCV_CHECKSUM_H diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile index 26cb2502ecf8..2aa1a4ad361f 100644 --- a/arch/riscv/lib/Makefile +++ b/arch/riscv/lib/Makefile @@ -6,6 +6,7 @@ lib-y += memmove.o lib-y += strcmp.o lib-y += strlen.o lib-y += strncmp.o +lib-y += csum.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_64BIT) += tishift.o lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c new file mode 100644 index 000000000000..47d98c51bab2 --- /dev/null +++ b/arch/riscv/lib/csum.c @@ -0,0 +1,210 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * IP checksum library + * + * Influenced by arch/arm64/lib/csum.c + * Copyright (C) 2023 Rivos Inc. + */ +#include +#include +#include +#include + +#include + +/* Default version is sufficient for 32 bit */ +#ifndef CONFIG_32BIT +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum) +{ + /* + * Inform the compiler/processor that the operation we are performing is + * "Commutative and Associative" by summing parts of the checksum in a + * tree-like structure (Section 2(A) of "Computing the Internet + * Checksum"). Furthermore, defer the overflow until the end of the + * computation which is shown to be valid in Section 2(C)(1) of the + * same handbook. + */ + unsigned long sum, sum1, sum2, sum3, sum4, ulen, uproto; + + uproto = htonl(proto); + ulen = htonl(len); + + sum = saddr->s6_addr32[0]; + sum += saddr->s6_addr32[1]; + sum1 = saddr->s6_addr32[2]; + sum1 += saddr->s6_addr32[3]; + + sum2 = daddr->s6_addr32[0]; + sum2 += daddr->s6_addr32[1]; + sum3 = daddr->s6_addr32[2]; + sum3 += daddr->s6_addr32[3]; + + sum4 = csum; + sum4 += ulen; + sum4 += uproto; + + sum += sum1; + sum2 += sum3; + + sum += sum2; + sum += sum4; + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) { + csum_t fold_temp; + + /* + * Zbb is likely available when the kernel is compiled with Zbb + * support, so nop when Zbb is available and jump when Zbb is + * not available. + */ + asm_volatile_goto(ALTERNATIVE("j %l[no_zbb]", "nop", 0, + RISCV_ISA_EXT_ZBB, 1) + : + : + : + : no_zbb); + asm(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[sum], 32 \n\ + add %[sum], %[fold_temp], %[sum] \n\ + srli %[sum], %[sum], 32 \n\ + not %[fold_temp], %[sum] \n\ + roriw %[sum], %[sum], 16 \n\ + subw %[sum], %[fold_temp], %[sum] \n\ + .option pop" + : [sum] "+r" (sum), [fold_temp] "=&r" (fold_temp)); + return (__force __sum16)(sum >> 16); + } +no_zbb: + sum += (sum >> 32) | (sum << 32); + sum >>= 32; + return csum_fold((__force __wsum)sum); +} +EXPORT_SYMBOL(csum_ipv6_magic); +#endif // !CONFIG_32BIT + +#ifdef CONFIG_32BIT +#define OFFSET_MASK 3 +#elif CONFIG_64BIT +#define OFFSET_MASK 7 +#endif + +/* + * Perform a checksum on an arbitrary memory address. + * Algorithm accounts for buff being misaligned. + * If buff is not aligned, will over-read bytes but not use the bytes that it + * shouldn't. The same thing will occur on the tail-end of the read. + */ +unsigned int __no_sanitize_address do_csum(const unsigned char *buff, int len) +{ + unsigned int offset, shift; + csum_t csum, data; + const csum_t *ptr; + + if (unlikely(len <= 0)) + return 0; + /* + * To align the address, grab the whole first byte in buff. + * Since it is inside of a same byte, it will never cross pages or cache + * lines. + * Directly call KASAN with the alignment we will be using. + */ + offset = (csum_t)buff & OFFSET_MASK; + kasan_check_read(buff, len); + ptr = (const csum_t *)(buff - offset); + len = len + offset - sizeof(csum_t); + + /* + * Clear the most signifant bits that were over-read if buff was not + * aligned. + */ + shift = offset * 8; + data = *ptr; +#ifdef __LITTLE_ENDIAN + data = (data >> shift) << shift; +#else + data = (data << shift) >> shift; +#endif + /* + * Do 32-bit reads on RV32 and 64-bit reads otherwise. This should be + * faster than doing 32-bit reads on architectures that support larger + * reads. + */ + while (len > 0) { + csum += data; + csum += csum < data; + len -= sizeof(csum_t); + ptr += 1; + data = *ptr; + } + + /* + * Perform alignment (and over-read) bytes on the tail if any bytes + * leftover. + */ + shift = len * -8; +#ifdef __LITTLE_ENDIAN + data = (data << shift) >> shift; +#else + data = (data >> shift) << shift; +#endif + csum += data; + csum += csum < data; + + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) + goto no_zbb; + + unsigned int fold_temp; + + if (IS_ENABLED(CONFIG_32BIT)) { + asm_volatile_goto(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 16 \n\ + andi %[offset], %[offset], 1 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + beq %[offset], zero, %l[end] \n\ + rev8 %[csum], %[csum] \n\ + zext.h %[csum], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp) + : [offset] "r" (offset) + : + : end); + + return csum; + } else { + asm_volatile_goto(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 32 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + srli %[csum], %[csum], 32 \n\ + roriw %[fold_temp], %[csum], 16 \n\ + addw %[csum], %[fold_temp], %[csum] \n\ + andi %[offset], %[offset], 1 \n\ + beq %[offset], zero, %l[end] \n\ + rev8 %[csum], %[csum] \n\ + srli %[csum], %[csum], 32 \n\ + zext.h %[csum], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp) + : [offset] "r" (offset) + : + : end); + + return csum; + } +end: + return csum >> 16; +no_zbb: +#ifndef CONFIG_32BIT + csum += (csum >> 32) | (csum << 32); + csum >>= 32; +#endif + csum = (unsigned int)csum + (((unsigned int)csum >> 16) | ((unsigned int)csum << 16)); + if (offset & 1) + return (unsigned short)swab32(csum); + return csum >> 16; +}