From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-15.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id BBFBBC433DB for ; Sat, 30 Jan 2021 19:19:17 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8950464E11 for ; Sat, 30 Jan 2021 19:19:17 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232462AbhA3TSy (ORCPT ); Sat, 30 Jan 2021 14:18:54 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42894 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232453AbhA3TSl (ORCPT ); Sat, 30 Jan 2021 14:18:41 -0500 Received: from mail-qt1-x835.google.com (mail-qt1-x835.google.com [IPv6:2607:f8b0:4864:20::835]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B7746C0617AB for ; Sat, 30 Jan 2021 11:17:31 -0800 (PST) Received: by mail-qt1-x835.google.com with SMTP id t14so9290982qto.8 for ; Sat, 30 Jan 2021 11:17:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=CrAmvRDdAl33DSpHjA5XcZUSXoY21DiogAG2ynD5om4=; b=L+wtCVRFdftJyNxjUlUwxHuQlSPoxvr5f2BonNocXlpsvaf/fvDLsiMHi9/7BF3FGR fHu6SEBjHfH8sfr/JaSox1NriSUIomGNYee4IpTGDot1p0gKtEWupimgUcsq+szRfhMr 4SMOqF7Bon6i2dh+bAA7Ysw8t0USZuAuTvkwoY1N37RocgQKZJbyN+AY3IQcBRTc2nsr Kix1n0bx94WY/AsEmbZiniBZEhmY+4vCCMIgFPXx89BnBhqxuXW5+pLzQS8OJufuSaCC yXaVWiChJiEhRR+u6YLCtcSNTngngB3P++/hy2e4cmyMN21K6Qnmm0CaLPxqVo6m0Ug9 5+xQ== 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:mime-version:content-transfer-encoding; bh=CrAmvRDdAl33DSpHjA5XcZUSXoY21DiogAG2ynD5om4=; b=GzV0j7DmupebNfW1n31tHYSNkoIeZGwBNAjHnMFBFt0bu/nR5zLG5NLQAFh/ml7wBr EwIuYvTPQEtyqr6qPUwJP3xtuLWVuWnJAsxCknLDDtWaaHoh91KSlRjosbf9xBgrfvwh f3f+m6J7DbFUv0X02KsG2MW5P/UkRo4lI8QIFt6dg3BhoidY+D9//6IK5vbdf3MR76bH /Bt4J7jYF6f3Btkq0ttapwzcvh/vinWpQH9ZjmjACuqLxg2KHibHYjQtDN5bNbp/oAIx HtIUAiwiJXXQIVQCatOlTaUPaDo0kXL4qSh7ZrO+7iVWU3mvwk5dF5qhhM9JvzQT0Lst lbvw== X-Gm-Message-State: AOAM530K8pKcgrDd26pIV8aMXPn1M7RXRzGyqF7d8aAbUhpXkYp9eHiB n0VAjTI6pMlqwwhgtv3rPf8aIPQgrOP3fEzA X-Google-Smtp-Source: ABdhPJxa36sZmDJPtqezzoP0XV3lQt1JIdIaV55LPu5GsSt6faVQkre3cX+Co4z+sh8UeZZYW8rJww== X-Received: by 2002:a05:622a:303:: with SMTP id q3mr9077138qtw.235.1612034250704; Sat, 30 Jan 2021 11:17:30 -0800 (PST) Received: from localhost (d27-96-190-162.evv.wideopenwest.com. [96.27.162.190]) by smtp.gmail.com with ESMTPSA id u65sm9498777qkb.58.2021.01.30.11.17.30 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 30 Jan 2021 11:17:30 -0800 (PST) From: Yury Norov To: linux-m68k@lists.linux-m68k.org, linux-kernel@vger.kernel.org, linux-sh@vger.kernel.org, linux-arch@vger.kernel.org Cc: Yury Norov , Geert Uytterhoeven , Yoshinori Sato , Rich Felker , Arnd Bergmann , Dennis Zhou , Andrew Morton , Wolfram Sang , David Sterba , Andy Shevchenko , Stefano Brivio , "Ma, Jianpeng" , Wei Yang , Josh Poimboeuf , John Paul Adrian Glaubitz , Joe Perches Subject: [PATCH 7/8] lib: add fast path for find_next_*_bit() Date: Sat, 30 Jan 2021 11:17:18 -0800 Message-Id: <20210130191719.7085-8-yury.norov@gmail.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20210130191719.7085-1-yury.norov@gmail.com> References: <20210130191719.7085-1-yury.norov@gmail.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-m68k@vger.kernel.org Similarly to bitmap functions, find_next_*_bit() users will benefit if we'll handle a case of bitmaps that fit into a single word. In the very best case, the compiler may replace a function call with a single ffs or ffz instruction. Signed-off-by: Yury Norov --- include/asm-generic/bitops/find.h | 30 +++++++++++++++++++++++++ include/asm-generic/bitops/le.h | 21 +++++++++++++++++ tools/include/asm-generic/bitops/find.h | 30 +++++++++++++++++++++++++ 3 files changed, 81 insertions(+) diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h index 7ad70dab8e93..8bd7a33a889d 100644 --- a/include/asm-generic/bitops/find.h +++ b/include/asm-generic/bitops/find.h @@ -20,6 +20,16 @@ static inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size - 1)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } #endif @@ -40,6 +50,16 @@ unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size - 1)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & *addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } #endif @@ -58,6 +78,16 @@ static inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size - 1)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } #endif diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h index 21305f6cea0b..18ebcf639d7f 100644 --- a/include/asm-generic/bitops/le.h +++ b/include/asm-generic/bitops/le.h @@ -5,6 +5,7 @@ #include #include #include +#include #if defined(__LITTLE_ENDIAN) @@ -37,6 +38,16 @@ static inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); } #endif @@ -46,6 +57,16 @@ static inline unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size)) { + unsigned long val = *(const unsigned long *)addr; + + if (unlikely(offset >= size)) + return size; + + val = swab(val) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + return _find_next_bit(addr, NULL, size, offset, 0UL, 1); } #endif diff --git a/tools/include/asm-generic/bitops/find.h b/tools/include/asm-generic/bitops/find.h index 9fe62d10b084..eff868bd22f8 100644 --- a/tools/include/asm-generic/bitops/find.h +++ b/tools/include/asm-generic/bitops/find.h @@ -20,6 +20,16 @@ static inline unsigned long find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size - 1)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + return _find_next_bit(addr, NULL, size, offset, 0UL, 0); } #endif @@ -40,6 +50,16 @@ unsigned long find_next_and_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size - 1)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr1 & *addr2 & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); } #endif @@ -58,6 +78,16 @@ static inline unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, unsigned long offset) { + if (SMALL_CONST(size - 1)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = *addr | ~GENMASK(size - 1, offset); + return val == ~0UL ? size : ffz(val); + } + return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); } #endif -- 2.25.1