From patchwork Sat Mar 10 15:22:03 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ard Biesheuvel X-Patchwork-Id: 10273635 X-Patchwork-Delegate: herbert@gondor.apana.org.au Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id CF1DF602BD for ; Sat, 10 Mar 2018 15:23:30 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id BF099294FE for ; Sat, 10 Mar 2018 15:23:30 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id B22C229577; Sat, 10 Mar 2018 15:23:30 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.0 required=2.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 4CF4A294FE for ; Sat, 10 Mar 2018 15:23:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932365AbeCJPX1 (ORCPT ); Sat, 10 Mar 2018 10:23:27 -0500 Received: from mail-wm0-f66.google.com ([74.125.82.66]:54585 "EHLO mail-wm0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932359AbeCJPXY (ORCPT ); Sat, 10 Mar 2018 10:23:24 -0500 Received: by mail-wm0-f66.google.com with SMTP id z81so8854718wmb.4 for ; Sat, 10 Mar 2018 07:23:24 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; h=from:to:cc:subject:date:message-id:in-reply-to:references; bh=/m7DRDk722apMGW0nG/T2Et7TigRr637a0J0fTnO3LM=; b=BP37ZWGOAxd4CxCz4/MEMVsa363tbICpcGqYIV+YjziWEAgRkhZOUGHPU9mlSngTIU 9+TCSKDIIUjpr4R9393lhzMghJfd0BvqDyUiX/Fi3c/ldF9uTqqVF9359CLN0GAHzVxO ocn3tx/ysyGE01XSvelPzvwX08mF1m9DfP6hI= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references; bh=/m7DRDk722apMGW0nG/T2Et7TigRr637a0J0fTnO3LM=; b=EM84w15TwfFa9QZSmrO0edcQT4W2yrD8WcOgLN0oFGtOAomoHp18xRHVrJHMlBfcLN xmSTNywpw5pE6tBtcaH4/pZ8shcPfp/DougmsGFRXdRTD+gqz4+PA59Tj5AtxBqgUD+d 8DbRb4VXZNBeOsKakp0TH1Ix5DL6VKFXMgV/Uc0OshNDq12cRG3LivHr68sWbrpazEqp es/ZwyEreqMVKwnFlPpcvJkpsK/Lqe6fOvdxm8o1p6F5Z1hUiPk8cuOF1wiYYuEObOi6 NEMdOhLGYp7/iGQ4DmMlA3Y0G6GP5xcp6LWvvAMrMjlZBcmKkYEbudYDiQrzvxVtI1ja jSxw== X-Gm-Message-State: AElRT7ExlnoEBKhEjRkvO4vV0bU4iDJ+i/+FxANWhyGbcAIj+bX0DFp4 p12dvDbV2UyTjrDlt12Iid5UaG++N6o= X-Google-Smtp-Source: AG47ELs3gb+Tz1ITx2vrOME6uUbIVlThIxW5UZgSxA6MiUmZk4fx4xzMJ1hslgF6kFMkjCyem9Eg3A== X-Received: by 10.28.193.134 with SMTP id r128mr1328900wmf.85.1520695403388; Sat, 10 Mar 2018 07:23:23 -0800 (PST) Received: from localhost.localdomain ([105.148.128.186]) by smtp.gmail.com with ESMTPSA id m9sm7027531wrf.13.2018.03.10.07.23.20 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Sat, 10 Mar 2018 07:23:22 -0800 (PST) From: Ard Biesheuvel To: linux-crypto@vger.kernel.org Cc: herbert@gondor.apana.org.au, linux-arm-kernel@lists.infradead.org, Ard Biesheuvel , Dave Martin , Russell King - ARM Linux , Sebastian Andrzej Siewior , Mark Rutland , linux-rt-users@vger.kernel.org, Peter Zijlstra , Catalin Marinas , Will Deacon , Steven Rostedt , Thomas Gleixner Subject: [PATCH v5 18/23] crypto: arm64/crc32-ce - yield NEON after every block of input Date: Sat, 10 Mar 2018 15:22:03 +0000 Message-Id: <20180310152208.10369-19-ard.biesheuvel@linaro.org> X-Mailer: git-send-email 2.15.1 In-Reply-To: <20180310152208.10369-1-ard.biesheuvel@linaro.org> References: <20180310152208.10369-1-ard.biesheuvel@linaro.org> Sender: linux-crypto-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-crypto@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP Avoid excessive scheduling delays under a preemptible kernel by conditionally yielding the NEON after every block of input. Signed-off-by: Ard Biesheuvel --- arch/arm64/crypto/crc32-ce-core.S | 40 +++++++++++++++----- 1 file changed, 30 insertions(+), 10 deletions(-) diff --git a/arch/arm64/crypto/crc32-ce-core.S b/arch/arm64/crypto/crc32-ce-core.S index 16ed3c7ebd37..8061bf0f9c66 100644 --- a/arch/arm64/crypto/crc32-ce-core.S +++ b/arch/arm64/crypto/crc32-ce-core.S @@ -100,9 +100,10 @@ dCONSTANT .req d0 qCONSTANT .req q0 - BUF .req x0 - LEN .req x1 - CRC .req x2 + BUF .req x19 + LEN .req x20 + CRC .req x21 + CONST .req x22 vzr .req v9 @@ -123,7 +124,14 @@ ENTRY(crc32_pmull_le) ENTRY(crc32c_pmull_le) adr_l x3, .Lcrc32c_constants -0: bic LEN, LEN, #15 +0: frame_push 4, 64 + + mov BUF, x0 + mov LEN, x1 + mov CRC, x2 + mov CONST, x3 + + bic LEN, LEN, #15 ld1 {v1.16b-v4.16b}, [BUF], #0x40 movi vzr.16b, #0 fmov dCONSTANT, CRC @@ -132,7 +140,7 @@ ENTRY(crc32c_pmull_le) cmp LEN, #0x40 b.lt less_64 - ldr qCONSTANT, [x3] + ldr qCONSTANT, [CONST] loop_64: /* 64 bytes Full cache line folding */ sub LEN, LEN, #0x40 @@ -162,10 +170,21 @@ loop_64: /* 64 bytes Full cache line folding */ eor v4.16b, v4.16b, v8.16b cmp LEN, #0x40 - b.ge loop_64 + b.lt less_64 + + if_will_cond_yield_neon + stp q1, q2, [sp, #.Lframe_local_offset] + stp q3, q4, [sp, #.Lframe_local_offset + 32] + do_cond_yield_neon + ldp q1, q2, [sp, #.Lframe_local_offset] + ldp q3, q4, [sp, #.Lframe_local_offset + 32] + ldr qCONSTANT, [CONST] + movi vzr.16b, #0 + endif_yield_neon + b loop_64 less_64: /* Folding cache line into 128bit */ - ldr qCONSTANT, [x3, #16] + ldr qCONSTANT, [CONST, #16] pmull2 v5.1q, v1.2d, vCONSTANT.2d pmull v1.1q, v1.1d, vCONSTANT.1d @@ -204,8 +223,8 @@ fold_64: eor v1.16b, v1.16b, v2.16b /* final 32-bit fold */ - ldr dCONSTANT, [x3, #32] - ldr d3, [x3, #40] + ldr dCONSTANT, [CONST, #32] + ldr d3, [CONST, #40] ext v2.16b, v1.16b, vzr.16b, #4 and v1.16b, v1.16b, v3.16b @@ -213,7 +232,7 @@ fold_64: eor v1.16b, v1.16b, v2.16b /* Finish up with the bit-reversed barrett reduction 64 ==> 32 bits */ - ldr qCONSTANT, [x3, #48] + ldr qCONSTANT, [CONST, #48] and v2.16b, v1.16b, v3.16b ext v2.16b, vzr.16b, v2.16b, #8 @@ -223,6 +242,7 @@ fold_64: eor v1.16b, v1.16b, v2.16b mov w0, v1.s[1] + frame_pop ret ENDPROC(crc32_pmull_le) ENDPROC(crc32c_pmull_le)