From patchwork Thu Apr 9 10:55:40 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ard Biesheuvel X-Patchwork-Id: 6187271 X-Patchwork-Delegate: herbert@gondor.apana.org.au Return-Path: X-Original-To: patchwork-linux-crypto@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 9AAA59F2EC for ; Thu, 9 Apr 2015 10:56:26 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 96EA220396 for ; Thu, 9 Apr 2015 10:56:25 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 82EE0203B5 for ; Thu, 9 Apr 2015 10:56:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755151AbbDIK4X (ORCPT ); Thu, 9 Apr 2015 06:56:23 -0400 Received: from mail-wg0-f47.google.com ([74.125.82.47]:35822 "EHLO mail-wg0-f47.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933258AbbDIK4X (ORCPT ); Thu, 9 Apr 2015 06:56:23 -0400 Received: by wgyo15 with SMTP id o15so105205394wgy.2 for ; Thu, 09 Apr 2015 03:56:21 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=T2OOSeaF4H7eU54bL/mZz5PfJgvsblB5A+UzPvv/jY4=; b=WsfuT4VQvjCGdmPyxzWBkLLxvPLRvQOWPaPmuMGqa/OBz9QXMsrAG17WBdxrU91p5y noAtrFzDgxVrQZLHJ0UlrRYTHYv8NY8Vg0xvG3cr3bHo/sZP5eJZlRMsFnDdBLxaBJUz W3/G7BcLbX+P1du531IVlER6vPJGbiL3tA/Ua6tOk3SEAfVv/mK/a3uCcJPYxwvIwXmR 1V4qedzt8A+nXmZsbAdMTkWwU5aqHIK4oIbjhYqN99R4sf2fna6lYuFK1W1HYSa8k2bJ W799NXEVMNVYBHEP9OyJMjBCAYT9p8YYzP5x0h/ukUesTIgCbjEBihzi3Q2KymIDQLy5 IjIg== X-Gm-Message-State: ALoCoQlFzcwQkxANL5bcBnblBTRiLblu/hJNLxUxAGgwl8Fch6CMQOstIUzstZ69poSfCfZ5dnrw X-Received: by 10.194.77.230 with SMTP id v6mr60204874wjw.25.1428576981875; Thu, 09 Apr 2015 03:56:21 -0700 (PDT) Received: from ards-macbook-pro.local ([90.174.5.113]) by mx.google.com with ESMTPSA id b10sm2192186wiz.9.2015.04.09.03.56.20 (version=TLSv1.1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Thu, 09 Apr 2015 03:56:21 -0700 (PDT) From: Ard Biesheuvel To: linux-crypto@vger.kernel.org, linux-arm-kernel@lists.infradead.org, x86@kernel.org, herbert@gondor.apana.org.au, samitolvanen@google.com, jussi.kivilinna@iki.fi Cc: stockhausen@collogia.de, Ard Biesheuvel Subject: [PATCH v4 08/16] crypto/arm: move SHA-1 NEON implementation to base layer Date: Thu, 9 Apr 2015 12:55:40 +0200 Message-Id: <1428576948-23863-9-git-send-email-ard.biesheuvel@linaro.org> X-Mailer: git-send-email 1.8.3.2 In-Reply-To: <1428576948-23863-1-git-send-email-ard.biesheuvel@linaro.org> References: <1428576948-23863-1-git-send-email-ard.biesheuvel@linaro.org> Sender: linux-crypto-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP This removes all the boilerplate from the existing implementation, and replaces it with calls into the base layer. Signed-off-by: Ard Biesheuvel --- arch/arm/crypto/sha1_neon_glue.c | 135 +++++++-------------------------------- 1 file changed, 24 insertions(+), 111 deletions(-) diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c index 5d9a1b4aac73..4e22f122f966 100644 --- a/arch/arm/crypto/sha1_neon_glue.c +++ b/arch/arm/crypto/sha1_neon_glue.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include #include @@ -34,138 +34,51 @@ asmlinkage void sha1_transform_neon(void *state_h, const char *data, unsigned int rounds); - -static int sha1_neon_init(struct shash_desc *desc) -{ - struct sha1_state *sctx = shash_desc_ctx(desc); - - *sctx = (struct sha1_state){ - .state = { SHA1_H0, SHA1_H1, SHA1_H2, SHA1_H3, SHA1_H4 }, - }; - - return 0; -} - -static int __sha1_neon_update(struct shash_desc *desc, const u8 *data, - unsigned int len, unsigned int partial) -{ - struct sha1_state *sctx = shash_desc_ctx(desc); - unsigned int done = 0; - - sctx->count += len; - - if (partial) { - done = SHA1_BLOCK_SIZE - partial; - memcpy(sctx->buffer + partial, data, done); - sha1_transform_neon(sctx->state, sctx->buffer, 1); - } - - if (len - done >= SHA1_BLOCK_SIZE) { - const unsigned int rounds = (len - done) / SHA1_BLOCK_SIZE; - - sha1_transform_neon(sctx->state, data + done, rounds); - done += rounds * SHA1_BLOCK_SIZE; - } - - memcpy(sctx->buffer, data + done, len - done); - - return 0; -} - static int sha1_neon_update(struct shash_desc *desc, const u8 *data, - unsigned int len) + unsigned int len) { struct sha1_state *sctx = shash_desc_ctx(desc); - unsigned int partial = sctx->count % SHA1_BLOCK_SIZE; - int res; - /* Handle the fast case right here */ - if (partial + len < SHA1_BLOCK_SIZE) { - sctx->count += len; - memcpy(sctx->buffer + partial, data, len); + if (!may_use_simd() || + (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE) + return sha1_update_arm(desc, data, len); - return 0; - } - - if (!may_use_simd()) { - res = sha1_update_arm(desc, data, len); - } else { - kernel_neon_begin(); - res = __sha1_neon_update(desc, data, len, partial); - kernel_neon_end(); - } - - return res; -} - - -/* Add padding and return the message digest. */ -static int sha1_neon_final(struct shash_desc *desc, u8 *out) -{ - struct sha1_state *sctx = shash_desc_ctx(desc); - unsigned int i, index, padlen; - __be32 *dst = (__be32 *)out; - __be64 bits; - static const u8 padding[SHA1_BLOCK_SIZE] = { 0x80, }; - - bits = cpu_to_be64(sctx->count << 3); - - /* Pad out to 56 mod 64 and append length */ - index = sctx->count % SHA1_BLOCK_SIZE; - padlen = (index < 56) ? (56 - index) : ((SHA1_BLOCK_SIZE+56) - index); - if (!may_use_simd()) { - sha1_update_arm(desc, padding, padlen); - sha1_update_arm(desc, (const u8 *)&bits, sizeof(bits)); - } else { - kernel_neon_begin(); - /* We need to fill a whole block for __sha1_neon_update() */ - if (padlen <= 56) { - sctx->count += padlen; - memcpy(sctx->buffer + index, padding, padlen); - } else { - __sha1_neon_update(desc, padding, padlen, index); - } - __sha1_neon_update(desc, (const u8 *)&bits, sizeof(bits), 56); - kernel_neon_end(); - } - - /* Store state in digest */ - for (i = 0; i < 5; i++) - dst[i] = cpu_to_be32(sctx->state[i]); - - /* Wipe context */ - memset(sctx, 0, sizeof(*sctx)); + kernel_neon_begin(); + sha1_base_do_update(desc, data, len, + (sha1_block_fn *)sha1_transform_neon); + kernel_neon_end(); return 0; } -static int sha1_neon_export(struct shash_desc *desc, void *out) +static int sha1_neon_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) { - struct sha1_state *sctx = shash_desc_ctx(desc); + if (!may_use_simd()) + return sha1_finup_arm(desc, data, len, out); - memcpy(out, sctx, sizeof(*sctx)); + kernel_neon_begin(); + if (len) + sha1_base_do_update(desc, data, len, + (sha1_block_fn *)sha1_transform_neon); + sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_transform_neon); + kernel_neon_end(); - return 0; + return sha1_base_finish(desc, out); } -static int sha1_neon_import(struct shash_desc *desc, const void *in) +static int sha1_neon_final(struct shash_desc *desc, u8 *out) { - struct sha1_state *sctx = shash_desc_ctx(desc); - - memcpy(sctx, in, sizeof(*sctx)); - - return 0; + return sha1_neon_finup(desc, NULL, 0, out); } static struct shash_alg alg = { .digestsize = SHA1_DIGEST_SIZE, - .init = sha1_neon_init, + .init = sha1_base_init, .update = sha1_neon_update, .final = sha1_neon_final, - .export = sha1_neon_export, - .import = sha1_neon_import, + .finup = sha1_neon_finup, .descsize = sizeof(struct sha1_state), - .statesize = sizeof(struct sha1_state), .base = { .cra_name = "sha1", .cra_driver_name = "sha1-neon",