From patchwork Fri Sep 2 11:40:36 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ard Biesheuvel X-Patchwork-Id: 75297 Delivered-To: patch@linaro.org Received: by 10.140.29.8 with SMTP id a8csp819680qga; Fri, 2 Sep 2016 04:40:48 -0700 (PDT) X-Received: by 10.98.19.214 with SMTP id 83mr36001704pft.117.1472816448444; Fri, 02 Sep 2016 04:40:48 -0700 (PDT) Return-Path: Received: from ml01.01.org (ml01.01.org. [198.145.21.10]) by mx.google.com with ESMTPS id t21si11257738pfj.215.2016.09.02.04.40.48 (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Fri, 02 Sep 2016 04:40:48 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of edk2-devel-bounces@lists.01.org designates 198.145.21.10 as permitted sender) client-ip=198.145.21.10; Authentication-Results: mx.google.com; dkim=neutral (body hash did not verify) header.i=@linaro.org; spf=pass (google.com: best guess record for domain of edk2-devel-bounces@lists.01.org designates 198.145.21.10 as permitted sender) smtp.mailfrom=edk2-devel-bounces@lists.01.org; dmarc=fail (p=NONE dis=NONE) header.from=linaro.org Received: from [127.0.0.1] (localhost [IPv6:::1]) by ml01.01.org (Postfix) with ESMTP id E89A01A1E10; Fri, 2 Sep 2016 04:40:47 -0700 (PDT) X-Original-To: edk2-devel@lists.01.org Delivered-To: edk2-devel@lists.01.org Received: from mail-wm0-x235.google.com (mail-wm0-x235.google.com [IPv6:2a00:1450:400c:c09::235]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by ml01.01.org (Postfix) with ESMTPS id C76EF1A1E0B for ; Fri, 2 Sep 2016 04:40:46 -0700 (PDT) Received: by mail-wm0-x235.google.com with SMTP id v143so26741839wmv.0 for ; Fri, 02 Sep 2016 04:40:46 -0700 (PDT) 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=fCp4fN/ZgIldG17pkMhW2tRr7fn8r1AE4KOghxdC4cI=; b=hNsKJiXYi8GLSdVdeFJPfrUdfTbQjxDB5sNNBhxVyo2suffMwP6V2XE6HhDYzmdtqZ 9yd49yMnfq6JrkUGaeiwKvlUV3OIbFsonXNf5olCF0eMDehn17bnwWBenf0hZ0af1iAU PK44BtFZ2VIFQHYZW7H/pWVNP1t8GxFvwaWnY= 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=fCp4fN/ZgIldG17pkMhW2tRr7fn8r1AE4KOghxdC4cI=; b=ks3ys5FvfM3+tHeDkOCIyYFm/rPUCUxBiJr+CBekAkw2rSh3sJkKmNwgMryDIsS8Ft 8sdkSmq/XP0HZx1mhsA5dOY8Z1uJg3iLy6fexYsoSu4/8sywQGpOt79wOf+U6qdOeQjz TN/JuHM9dC9V93Vxzdyb3gtutrkmnqcXoMbPGznP7Yn6lEyaCdW38xf+OGpMqpyZV5+t hVhMGbZaOTgLyTI1wu13K/lVKobmqYx12NztmNgrUbE3llp2Nd1Bybdje9LemMl2Lqr8 6RMag0Iq9TpK9C9XdxzsimSMsJHearr8h/qsd50zf3ExMHLo8HH8fO9bvMtFfiux7EDh TVyQ== X-Gm-Message-State: AE9vXwPZxxoXnw/QXZkr2kMnJldF/4r7OSexHCH8TB63xOOtnxpr1SNWnPnJG4PVFTU8sSzR X-Received: by 10.28.97.2 with SMTP id v2mr2716009wmb.31.1472816445312; Fri, 02 Sep 2016 04:40:45 -0700 (PDT) Received: from localhost.localdomain ([160.165.63.90]) by smtp.gmail.com with ESMTPSA id h7sm10088490wjd.17.2016.09.02.04.40.43 (version=TLS1_2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Fri, 02 Sep 2016 04:40:44 -0700 (PDT) From: Ard Biesheuvel To: edk2-devel@lists.01.org, liming.gao@intel.com Date: Fri, 2 Sep 2016 12:40:36 +0100 Message-Id: <1472816437-4525-2-git-send-email-ard.biesheuvel@linaro.org> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1472816437-4525-1-git-send-email-ard.biesheuvel@linaro.org> References: <1472816437-4525-1-git-send-email-ard.biesheuvel@linaro.org> Subject: [edk2] [PATCH 1/2] MdePkg/BaseMemoryLib: widen aligned accesses to 32 or 64 bits X-BeenThere: edk2-devel@lists.01.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: EDK II Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: michael.d.kinney@intel.com, lersek@redhat.com, leif.lindholm@linaro.org, Ard Biesheuvel MIME-Version: 1.0 Errors-To: edk2-devel-bounces@lists.01.org Sender: "edk2-devel" Since the default BaseMemoryLib should be callable from any context, including ones where unaligned accesses are not allowed, it implements InternalCopyMem() and InternalSetMem() using byte accesses only. However, especially in a context where the MMU is off, such narrow accesses may be disproportionately costly, and so if the size and alignment of the access allow it, use 32-bit or even 64-bit loads and stores (the latter may be beneficial even on a 32-bit architectures like ARM, which has load pair/store pair instructions) Contributed-under: TianoCore Contribution Agreement 1.0 Signed-off-by: Ard Biesheuvel --- MdePkg/Library/BaseMemoryLib/BaseMemoryLib.inf | 2 +- MdePkg/Library/BaseMemoryLib/CopyMem.c | 112 ++++++++++++++++++-- MdePkg/Library/BaseMemoryLib/SetMem.c | 40 ++++++- 3 files changed, 140 insertions(+), 14 deletions(-) -- 2.7.4 _______________________________________________ edk2-devel mailing list edk2-devel@lists.01.org https://lists.01.org/mailman/listinfo/edk2-devel diff --git a/MdePkg/Library/BaseMemoryLib/BaseMemoryLib.inf b/MdePkg/Library/BaseMemoryLib/BaseMemoryLib.inf index 6d906e93faf3..358eeed4f449 100644 --- a/MdePkg/Library/BaseMemoryLib/BaseMemoryLib.inf +++ b/MdePkg/Library/BaseMemoryLib/BaseMemoryLib.inf @@ -26,7 +26,7 @@ [Defines] # -# VALID_ARCHITECTURES = IA32 X64 IPF EBC +# VALID_ARCHITECTURES = IA32 X64 IPF EBC ARM AARCH64 # [Sources] diff --git a/MdePkg/Library/BaseMemoryLib/CopyMem.c b/MdePkg/Library/BaseMemoryLib/CopyMem.c index 37f03660df5f..6f4fd900df5d 100644 --- a/MdePkg/Library/BaseMemoryLib/CopyMem.c +++ b/MdePkg/Library/BaseMemoryLib/CopyMem.c @@ -4,6 +4,9 @@ particular platform easily if an optimized version is desired. Copyright (c) 2006 - 2010, Intel Corporation. All rights reserved.
+ Copyright (c) 2012 - 2013, ARM Ltd. All rights reserved.
+ Copyright (c) 2016, Linaro Ltd. All rights reserved.
+ This program and the accompanying materials are licensed and made available under the terms and conditions of the BSD License which accompanies this distribution. The full text of the license may be found at @@ -44,18 +47,107 @@ InternalMemCopyMem ( // volatile UINT8 *Destination8; CONST UINT8 *Source8; + volatile UINT32 *Destination32; + CONST UINT32 *Source32; + volatile UINT64 *Destination64; + CONST UINT64 *Source64; + UINTN Alignment; + + if ((((UINTN)DestinationBuffer & 0x7) == 0) && (((UINTN)SourceBuffer & 0x7) == 0) && (Length >= 8)) { + if (SourceBuffer > DestinationBuffer) { + Destination64 = (UINT64*)DestinationBuffer; + Source64 = (CONST UINT64*)SourceBuffer; + while (Length >= 8) { + *(Destination64++) = *(Source64++); + Length -= 8; + } + + // Finish if there are still some bytes to copy + Destination8 = (UINT8*)Destination64; + Source8 = (CONST UINT8*)Source64; + while (Length-- != 0) { + *(Destination8++) = *(Source8++); + } + } else if (SourceBuffer < DestinationBuffer) { + Destination64 = (UINT64*)((UINTN)DestinationBuffer + Length); + Source64 = (CONST UINT64*)((UINTN)SourceBuffer + Length); + + // Destination64 and Source64 were aligned on a 64-bit boundary + // but if length is not a multiple of 8 bytes then they won't be + // anymore. + + Alignment = Length & 0x7; + if (Alignment != 0) { + Destination8 = (UINT8*)Destination64; + Source8 = (CONST UINT8*)Source64; + + while (Alignment-- != 0) { + *(--Destination8) = *(--Source8); + --Length; + } + Destination64 = (UINT64*)Destination8; + Source64 = (CONST UINT64*)Source8; + } + + while (Length > 0) { + *(--Destination64) = *(--Source64); + Length -= 8; + } + } + } else if ((((UINTN)DestinationBuffer & 0x3) == 0) && (((UINTN)SourceBuffer & 0x3) == 0) && (Length >= 4)) { + if (SourceBuffer > DestinationBuffer) { + Destination32 = (UINT32*)DestinationBuffer; + Source32 = (CONST UINT32*)SourceBuffer; + while (Length >= 4) { + *(Destination32++) = *(Source32++); + Length -= 4; + } + + // Finish if there are still some bytes to copy + Destination8 = (UINT8*)Destination32; + Source8 = (CONST UINT8*)Source32; + while (Length-- != 0) { + *(Destination8++) = *(Source8++); + } + } else if (SourceBuffer < DestinationBuffer) { + Destination32 = (UINT32*)((UINTN)DestinationBuffer + Length); + Source32 = (CONST UINT32*)((UINTN)SourceBuffer + Length); + + // Destination32 and Source32 were aligned on a 32-bit boundary + // but if length is not a multiple of 4 bytes then they won't be + // anymore. + + Alignment = Length & 0x3; + if (Alignment != 0) { + Destination8 = (UINT8*)Destination32; + Source8 = (CONST UINT8*)Source32; + + while (Alignment-- != 0) { + *(--Destination8) = *(--Source8); + --Length; + } + Destination32 = (UINT32*)Destination8; + Source32 = (CONST UINT32*)Source8; + } - if (SourceBuffer > DestinationBuffer) { - Destination8 = (UINT8*)DestinationBuffer; - Source8 = (CONST UINT8*)SourceBuffer; - while (Length-- != 0) { - *(Destination8++) = *(Source8++); + while (Length > 0) { + *(--Destination32) = *(--Source32); + Length -= 4; + } } - } else if (SourceBuffer < DestinationBuffer) { - Destination8 = (UINT8*)DestinationBuffer + Length; - Source8 = (CONST UINT8*)SourceBuffer + Length; - while (Length-- != 0) { - *(--Destination8) = *(--Source8); + } else { + if (SourceBuffer > DestinationBuffer) { + Destination8 = (UINT8*)DestinationBuffer; + Source8 = (CONST UINT8*)SourceBuffer; + while (Length-- != 0) { + *(Destination8++) = *(Source8++); + } + } else if (SourceBuffer < DestinationBuffer) { + Destination8 = (UINT8*)DestinationBuffer + Length; + Source8 = (CONST UINT8*)SourceBuffer + Length; + while (Length-- != 0) { + *(--Destination8) = *(--Source8); + } } } return DestinationBuffer; diff --git a/MdePkg/Library/BaseMemoryLib/SetMem.c b/MdePkg/Library/BaseMemoryLib/SetMem.c index 5e74085c56f0..932c61e959f3 100644 --- a/MdePkg/Library/BaseMemoryLib/SetMem.c +++ b/MdePkg/Library/BaseMemoryLib/SetMem.c @@ -5,6 +5,9 @@ is desired. Copyright (c) 2006 - 2010, Intel Corporation. All rights reserved.
+ Copyright (c) 2012 - 2013, ARM Ltd. All rights reserved.
+ Copyright (c) 2016, Linaro Ltd. All rights reserved.
+ This program and the accompanying materials are licensed and made available under the terms and conditions of the BSD License which accompanies this distribution. The full text of the license may be found at @@ -43,11 +46,42 @@ InternalMemSetMem ( // volatile to prevent the optimizer from replacing this function with // the intrinsic memset() // - volatile UINT8 *Pointer; + volatile UINT8 *Pointer8; + volatile UINT32 *Pointer32; + volatile UINT64 *Pointer64; + UINT32 Value32; + UINT64 Value64; + + if ((((UINTN)Buffer & 0x7) == 0) && (Length >= 8)) { + // Generate the 64bit value + Value32 = (Value << 24) | (Value << 16) | (Value << 8) | Value; + Value64 = (((UINT64)Value32) << 32) | Value32; + + Pointer64 = (UINT64*)Buffer; + while (Length >= 8) { + *(Pointer64++) = Value64; + Length -= 8; + } - Pointer = (UINT8*)Buffer; + // Finish with bytes if needed + Pointer8 = (UINT8*)Pointer64; + } else if ((((UINTN)Buffer & 0x3) == 0) && (Length >= 4)) { + // Generate the 32bit value + Value32 = (Value << 24) | (Value << 16) | (Value << 8) | Value; + + Pointer32 = (UINT32*)Buffer; + while (Length >= 4) { + *(Pointer32++) = Value32; + Length -= 4; + } + + // Finish with bytes if needed + Pointer8 = (UINT8*)Pointer32; + } else { + Pointer8 = (UINT8*)Buffer; + } while (Length-- > 0) { - *(Pointer++) = Value; + *(Pointer8++) = Value; } return Buffer; }