Received: by 2002:a05:6358:16cc:b0:ea:6187:17c9 with SMTP id r12csp8314832rwl; Tue, 10 Jan 2023 11:45:51 -0800 (PST) X-Google-Smtp-Source: AMrXdXs9DEzx66V1rKMIEA0MVsmStTZquvxzMRRb4Cc89oWyUrDlaQOg0j9xN1awzUxYqRFWmNrD X-Received: by 2002:a05:6402:3985:b0:467:9976:2e38 with SMTP id fk5-20020a056402398500b0046799762e38mr65021006edb.18.1673379951082; Tue, 10 Jan 2023 11:45:51 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1673379951; cv=none; d=google.com; s=arc-20160816; b=G7ARvDRafg2UlaBs06VUpwO/sBRcRJlfkBUJ3gDj6p0zHTlBwLBsyktT4hTZEtMnfp g4vZH4lk4f2D6giDpOTpjT22TRjFVv1YMW++DZlOZN3URi9nD0oB5DNP23EtzpxcXdL1 jVEwYVw+knpz2nbMBJ4tUX9oiKUZj7iZbeiD8NUs8shoRT9swoXTPs41Mx1DYv4CrbxE TeMBVDP+MhUUnmfyVSXpwZcYSAHN4m+anSVgowPwEFdI8T2kFL4a6f2ZG/1eTusMj+KD hu4PSNydr1h6cbT6o72ZyS+J8AXDdGzVgJXm1hYd2bhzL92GIXTkTb/Nez1x1mGNi+oW YoPg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :message-id:date:subject:cc:to:from:dkim-signature; bh=6WK2Snknx5q6DqgfLKm58fMpMD4ck4a9f8QIfce9Lrc=; b=vdDiM7P/NaKxVRRL4UjDkgdru2bm078wa7qglDmsjGeFSHWZW0q5/3htAlKG1EyCnY IVfqJ//LwGsXC5hMjKuR35ljg4xzRzfQc8nO5eb9te/znPX/MAPQooSt8+2SqrpdRVyy fwtd9VjuI2byEKIlS25hGL9ag51fUhmA+MFVkCf2NrQlOWZwcmIiptFkyHKp2w6J4h77 fkU6oiUDamLDzfW47K5O+9teHKAfaiocsHTiidLppRik1uitkh4xHWxSnXT/F72KRFKx kk6XaDzEehVUSiYmmS026YpP8fy1DNvI/2vTn9/0wV0wqF/epk13GT8VbBiY376INvFh ZVIA== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=p7oPlCmZ; spf=pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-crypto-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Return-Path: Received: from out1.vger.email (out1.vger.email. [2620:137:e000::1:20]) by mx.google.com with ESMTP id c6-20020a05640227c600b0046b807c1a06si14031137ede.350.2023.01.10.11.45.22; Tue, 10 Jan 2023 11:45:51 -0800 (PST) Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20; Authentication-Results: mx.google.com; dkim=pass header.i=@linaro.org header.s=google header.b=p7oPlCmZ; spf=pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) smtp.mailfrom=linux-crypto-owner@vger.kernel.org; dmarc=pass (p=NONE sp=NONE dis=NONE) header.from=linaro.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232392AbjAJTnV (ORCPT + 99 others); Tue, 10 Jan 2023 14:43:21 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47070 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232123AbjAJTnT (ORCPT ); Tue, 10 Jan 2023 14:43:19 -0500 Received: from mail-lf1-x134.google.com (mail-lf1-x134.google.com [IPv6:2a00:1450:4864:20::134]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3FD0DDEB3 for ; Tue, 10 Jan 2023 11:43:18 -0800 (PST) Received: by mail-lf1-x134.google.com with SMTP id b3so20134192lfv.2 for ; Tue, 10 Jan 2023 11:43:18 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to; bh=6WK2Snknx5q6DqgfLKm58fMpMD4ck4a9f8QIfce9Lrc=; b=p7oPlCmZedrWRoiSVeoy6bmdvaGMQJyEi9NfSM/+5ynkmqnG4jo0HqYIBPICn9DdzE r1FhhdCDPNqDDh6Ndj50QzykxA9fkch8rRH7BYMKpAa4EPUF0STAs+fB6zhU1HNiXTDG FZhbGNSylBoJX2GaRXl//tXsJKfFRwtjb2i76FLyyfXh70bhfL7sa7gKlbf5R3Mh/sk9 vCn1sVrUNNUGZlvsqMKD+GfmQfrpg7dqVPxBsAIfaI+r0YC0KvY3zIiQ+cOaOKYdr8Aa pXgZmdaXChhGHvlG8lx3BSyqi+deyUVl8Zo5VNGZ+kQ9OCZeMa1wfj8Z/fxo5bUfhqzI nE/A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=6WK2Snknx5q6DqgfLKm58fMpMD4ck4a9f8QIfce9Lrc=; b=vI3Usjc2aFTVz5lvfpu4Gs6LsdbWxVjJaRetsf1xDiAV4M1llYzSh0bTgGCo6R9I1t 6bxQrMZttQGcIrzIxODANlMUYavQaGpRBkZyufKpsoC7tDeomfyfqS+IxulCebSJhPCE dpBCJrH2MeXG352zh6W1pMQle9qGSDT1lo+nhCoQlNGllXHO3cYPRMbG4J5sdf8uw7MC wpSC8WR8MBjlcexE2iEAHeFjEnKzK1pK+qxIFBqb2VU0gPpmAGtACIkYhyaxhKw2b6du aOrdxTeu+aOyUVO7d23Np3rYg9O+pyNt1gx55aed+iqcE5qICky4vQOLBL/98Yr1K6iK WpjA== X-Gm-Message-State: AFqh2kqkMvcymFI4yllrPvLyhVJHm0x63NmuofrFjmD74SWB8BDp1GMY t+mEyEVkWCT7JCjW6N80uufxdNYsQp91BSQQ X-Received: by 2002:ac2:5c4b:0:b0:4cc:7ff3:ab4d with SMTP id s11-20020ac25c4b000000b004cc7ff3ab4dmr2607900lfp.20.1673379796325; Tue, 10 Jan 2023 11:43:16 -0800 (PST) Received: from Fecusia.lan (c-05d8225c.014-348-6c756e10.bbcust.telenor.se. [92.34.216.5]) by smtp.gmail.com with ESMTPSA id m10-20020a056512358a00b004cb0242704asm2307754lfr.255.2023.01.10.11.43.15 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Tue, 10 Jan 2023 11:43:15 -0800 (PST) From: Linus Walleij To: linux-crypto@vger.kernel.org, Herbert Xu , "David S . Miller" Cc: phone-devel@vger.kernel.org, Stefan Hansson , Lionel Debieve , Maxime Coquelin , Alexandre Torgue , Linus Walleij Subject: [PATCH] crypto: stm32/cryp: Use accelerated readsl/writesl Date: Tue, 10 Jan 2023 20:43:07 +0100 Message-Id: <20230110194307.657918-1-linus.walleij@linaro.org> X-Mailer: git-send-email 2.39.0 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE, SPF_HELO_NONE,SPF_PASS autolearn=unavailable autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on lindbergh.monkeyblade.net Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org When reading or writing crypto buffers the inner loops can be replaced with readsl and writesl which will on ARM result in a tight assembly loop, speeding up encryption/decryption a little bit. This optimization was in the Ux500 driver so let's carry it over to the STM32 driver. Cc: Maxime Coquelin Cc: Alexandre Torgue Cc: Lionel Debieve Signed-off-by: Linus Walleij --- drivers/crypto/stm32/stm32-cryp.c | 37 +++++++++---------------------- 1 file changed, 11 insertions(+), 26 deletions(-) diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c index 4208338e72b6..6b8d731092a4 100644 --- a/drivers/crypto/stm32/stm32-cryp.c +++ b/drivers/crypto/stm32/stm32-cryp.c @@ -597,7 +597,6 @@ static void stm32_crypt_gcmccm_end_header(struct stm32_cryp *cryp) static void stm32_cryp_write_ccm_first_header(struct stm32_cryp *cryp) { - unsigned int i; size_t written; size_t len; u32 alen = cryp->areq->assoclen; @@ -623,8 +622,8 @@ static void stm32_cryp_write_ccm_first_header(struct stm32_cryp *cryp) written = min_t(size_t, AES_BLOCK_SIZE - len, alen); scatterwalk_copychunks((char *)block + len, &cryp->in_walk, written, 0); - for (i = 0; i < AES_BLOCK_32; i++) - stm32_cryp_write(cryp, cryp->caps->din, block[i]); + + writesl(cryp->regs + cryp->caps->din, block, AES_BLOCK_32); cryp->header_in -= written; @@ -1363,18 +1362,14 @@ static int stm32_cryp_read_auth_tag(struct stm32_cryp *cryp) u32 out_tag[AES_BLOCK_32]; /* Get and write tag */ - for (i = 0; i < AES_BLOCK_32; i++) - out_tag[i] = stm32_cryp_read(cryp, cryp->caps->dout); - + readsl(cryp->regs + cryp->caps->dout, out_tag, AES_BLOCK_32); scatterwalk_copychunks(out_tag, &cryp->out_walk, cryp->authsize, 1); } else { /* Get and check tag */ u32 in_tag[AES_BLOCK_32], out_tag[AES_BLOCK_32]; scatterwalk_copychunks(in_tag, &cryp->in_walk, cryp->authsize, 0); - - for (i = 0; i < AES_BLOCK_32; i++) - out_tag[i] = stm32_cryp_read(cryp, cryp->caps->dout); + readsl(cryp->regs + cryp->caps->dout, out_tag, AES_BLOCK_32); if (crypto_memneq(in_tag, out_tag, cryp->authsize)) ret = -EBADMSG; @@ -1415,12 +1410,9 @@ static void stm32_cryp_check_ctr_counter(struct stm32_cryp *cryp) static void stm32_cryp_irq_read_data(struct stm32_cryp *cryp) { - unsigned int i; u32 block[AES_BLOCK_32]; - for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) - block[i] = stm32_cryp_read(cryp, cryp->caps->dout); - + readsl(cryp->regs + cryp->caps->dout, block, cryp->hw_blocksize / sizeof(u32)); scatterwalk_copychunks(block, &cryp->out_walk, min_t(size_t, cryp->hw_blocksize, cryp->payload_out), 1); cryp->payload_out -= min_t(size_t, cryp->hw_blocksize, @@ -1429,14 +1421,11 @@ static void stm32_cryp_irq_read_data(struct stm32_cryp *cryp) static void stm32_cryp_irq_write_block(struct stm32_cryp *cryp) { - unsigned int i; u32 block[AES_BLOCK_32] = {0}; scatterwalk_copychunks(block, &cryp->in_walk, min_t(size_t, cryp->hw_blocksize, cryp->payload_in), 0); - for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) - stm32_cryp_write(cryp, cryp->caps->din, block[i]); - + writesl(cryp->regs + cryp->caps->din, block, cryp->hw_blocksize / sizeof(u32)); cryp->payload_in -= min_t(size_t, cryp->hw_blocksize, cryp->payload_in); } @@ -1480,8 +1469,7 @@ static void stm32_cryp_irq_write_gcm_padded_data(struct stm32_cryp *cryp) * Same code as stm32_cryp_irq_read_data(), but we want to store * block value */ - for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) - block[i] = stm32_cryp_read(cryp, cryp->caps->dout); + readsl(cryp->regs + cryp->caps->dout, block, cryp->hw_blocksize / sizeof(u32)); scatterwalk_copychunks(block, &cryp->out_walk, min_t(size_t, cryp->hw_blocksize, cryp->payload_out), 1); @@ -1499,8 +1487,7 @@ static void stm32_cryp_irq_write_gcm_padded_data(struct stm32_cryp *cryp) stm32_cryp_write(cryp, cryp->caps->cr, cfg); /* f) write padded data */ - for (i = 0; i < AES_BLOCK_32; i++) - stm32_cryp_write(cryp, cryp->caps->din, block[i]); + writesl(cryp->regs + cryp->caps->din, block, AES_BLOCK_32); /* g) Empty fifo out */ err = stm32_cryp_wait_output(cryp); @@ -1580,8 +1567,7 @@ static void stm32_cryp_irq_write_ccm_padded_data(struct stm32_cryp *cryp) * Same code as stm32_cryp_irq_read_data(), but we want to store * block value */ - for (i = 0; i < cryp->hw_blocksize / sizeof(u32); i++) - block[i] = stm32_cryp_read(cryp, cryp->caps->dout); + readsl(cryp->regs + cryp->caps->dout, block, cryp->hw_blocksize / sizeof(u32)); scatterwalk_copychunks(block, &cryp->out_walk, min_t(size_t, cryp->hw_blocksize, cryp->payload_out), 1); @@ -1660,15 +1646,14 @@ static void stm32_cryp_irq_write_data(struct stm32_cryp *cryp) static void stm32_cryp_irq_write_gcmccm_header(struct stm32_cryp *cryp) { - unsigned int i; u32 block[AES_BLOCK_32] = {0}; size_t written; written = min_t(size_t, AES_BLOCK_SIZE, cryp->header_in); scatterwalk_copychunks(block, &cryp->in_walk, written, 0); - for (i = 0; i < AES_BLOCK_32; i++) - stm32_cryp_write(cryp, cryp->caps->din, block[i]); + + writesl(cryp->regs + cryp->caps->din, block, AES_BLOCK_32); cryp->header_in -= written; -- 2.39.0