From patchwork Wed Sep 8 02:59:10 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andrew Morton X-Patchwork-Id: 12480011 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,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER, INCLUDES_PATCH,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS 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 7C122C433F5 for ; Wed, 8 Sep 2021 02:59:13 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 30ECB61102 for ; Wed, 8 Sep 2021 02:59:13 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.1 mail.kernel.org 30ECB61102 Authentication-Results: mail.kernel.org; dmarc=none (p=none dis=none) header.from=linux-foundation.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=kvack.org Received: by kanga.kvack.org (Postfix) id C9CE9940043; Tue, 7 Sep 2021 22:59:12 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id C4CF4940042; Tue, 7 Sep 2021 22:59:12 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id B146E940043; Tue, 7 Sep 2021 22:59:12 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0215.hostedemail.com [216.40.44.215]) by kanga.kvack.org (Postfix) with ESMTP id A211E940042 for ; Tue, 7 Sep 2021 22:59:12 -0400 (EDT) Received: from smtpin01.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id 66531181AC9B6 for ; Wed, 8 Sep 2021 02:59:12 +0000 (UTC) X-FDA: 78562899744.01.748A566 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by imf04.hostedemail.com (Postfix) with ESMTP id 138D450000A1 for ; Wed, 8 Sep 2021 02:59:11 +0000 (UTC) Received: by mail.kernel.org (Postfix) with ESMTPSA id E698761131; Wed, 8 Sep 2021 02:59:10 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linux-foundation.org; s=korg; t=1631069951; bh=41brlujgaeDpfZOnh6y6wQjbQXnsaqy9bKXeMcC6TAw=; h=Date:From:To:Subject:In-Reply-To:From; b=nRmUkrMci9X3ysdWp4PGRwis/2iWJupRnCLjGXHe6vFjQOVD4voPC4/SD7qNZ/uQU agYsekhZwfGRgfm/lVFwHFcoNsPJpyu6vGG8vL3sfo87G+bfJf2Kq3+YLQvBKy+TOI UhmqAYo9rSNuyXcAEnySF3eOGgO5+eT5xBrhzcNY= Date: Tue, 07 Sep 2021 19:59:10 -0700 From: Andrew Morton To: aklimov@redhat.com, akpm@linux-foundation.org, alobakin@pm.me, andriy.shevchenko@linux.intel.com, dennis@kernel.org, jolsa@redhat.com, linux-mm@kvack.org, mm-commits@vger.kernel.org, torvalds@linux-foundation.org, ulf.hansson@linaro.org, will@kernel.org, wsa+renesas@sang-engineering.com, yury.norov@gmail.com Subject: [patch 111/147] lib: add find_first_and_bit() Message-ID: <20210908025910.Pw_ZatM_E%akpm@linux-foundation.org> In-Reply-To: <20210907195226.14b1d22a07c085b22968b933@linux-foundation.org> User-Agent: s-nail v14.8.16 Authentication-Results: imf04.hostedemail.com; dkim=pass header.d=linux-foundation.org header.s=korg header.b=nRmUkrMc; spf=pass (imf04.hostedemail.com: domain of akpm@linux-foundation.org designates 198.145.29.99 as permitted sender) smtp.mailfrom=akpm@linux-foundation.org; dmarc=none X-Stat-Signature: b9tq8yy69douuf8m3gdbj5yrcgs6pk39 X-Rspamd-Queue-Id: 138D450000A1 X-Rspamd-Server: rspam04 X-HE-Tag: 1631069951-360373 X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: From: Yury Norov Subject: lib: add find_first_and_bit() Currently find_first_and_bit() is an alias to find_next_and_bit(). However, it is widely used in cpumask, so it worth to optimize it. This patch adds its own implementation for find_first_and_bit(). On x86_64 find_bit_benchmark says: Before (#define find_first_and_bit(...) find_next_and_bit(..., 0): Start testing find_bit() with random-filled bitmap [ 140.291468] find_first_and_bit: 46890919 ns, 32671 iterations Start testing find_bit() with sparse bitmap [ 140.295028] find_first_and_bit: 7103 ns, 1 iterations After: Start testing find_bit() with random-filled bitmap [ 162.574907] find_first_and_bit: 25045813 ns, 32846 iterations Start testing find_bit() with sparse bitmap [ 162.578458] find_first_and_bit: 4900 ns, 1 iterations (Thanks to Alexey Klimov for thorough testing.) Link: https://lkml.kernel.org/r/20210814211713.180533-6-yury.norov@gmail.com Signed-off-by: Yury Norov Tested-by: Wolfram Sang Tested-by: Alexey Klimov Cc: Alexander Lobakin Cc: Andy Shevchenko Cc: Dennis Zhou Cc: Jiri Olsa Cc: Ulf Hansson Cc: Will Deacon Signed-off-by: Andrew Morton --- include/linux/find.h | 27 +++++++++++++++++++++++++++ lib/find_bit.c | 21 +++++++++++++++++++++ lib/find_bit_benchmark.c | 21 +++++++++++++++++++++ 3 files changed, 69 insertions(+) --- a/include/linux/find.h~lib-add-find_first_and_bit +++ a/include/linux/find.h @@ -12,6 +12,8 @@ extern unsigned long _find_next_bit(cons const unsigned long *addr2, unsigned long nbits, unsigned long start, unsigned long invert, unsigned long le); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); +extern unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size); extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); @@ -123,6 +125,31 @@ unsigned long find_first_bit(const unsig } #endif +#ifndef find_first_and_bit +/** + * find_first_and_bit - find the first set bit in both memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + if (small_const_nbits(size)) { + unsigned long val = *addr1 & *addr2 & GENMASK(size - 1, 0); + + return val ? __ffs(val) : size; + } + + return _find_first_and_bit(addr1, addr2, size); +} +#endif + #ifndef find_first_zero_bit /** * find_first_zero_bit - find the first cleared bit in a memory region --- a/lib/find_bit_benchmark.c~lib-add-find_first_and_bit +++ a/lib/find_bit_benchmark.c @@ -49,6 +49,25 @@ static int __init test_find_first_bit(vo return 0; } +static int __init test_find_first_and_bit(void *bitmap, const void *bitmap2, unsigned long len) +{ + static DECLARE_BITMAP(cp, BITMAP_LEN) __initdata; + unsigned long i, cnt; + ktime_t time; + + bitmap_copy(cp, bitmap, BITMAP_LEN); + + time = ktime_get(); + for (cnt = i = 0; i < len; cnt++) { + i = find_first_and_bit(cp, bitmap2, len); + __clear_bit(i, cp); + } + time = ktime_get() - time; + pr_err("find_first_and_bit: %18llu ns, %6ld iterations\n", time, cnt); + + return 0; +} + static int __init test_find_next_bit(const void *bitmap, unsigned long len) { unsigned long i, cnt; @@ -129,6 +148,7 @@ static int __init find_bit_test(void) * traverse only part of bitmap to avoid soft lockup. */ test_find_first_bit(bitmap, BITMAP_LEN / 10); + test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN / 2); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); pr_err("\nStart testing find_bit() with sparse bitmap\n"); @@ -145,6 +165,7 @@ static int __init find_bit_test(void) test_find_next_zero_bit(bitmap, BITMAP_LEN); test_find_last_bit(bitmap, BITMAP_LEN); test_find_first_bit(bitmap, BITMAP_LEN); + test_find_first_and_bit(bitmap, bitmap2, BITMAP_LEN); test_find_next_and_bit(bitmap, bitmap2, BITMAP_LEN); /* --- a/lib/find_bit.c~lib-add-find_first_and_bit +++ a/lib/find_bit.c @@ -89,6 +89,27 @@ unsigned long _find_first_bit(const unsi EXPORT_SYMBOL(_find_first_bit); #endif +#ifndef find_first_and_bit +/* + * Find the first set bit in two memory regions. + */ +unsigned long _find_first_and_bit(const unsigned long *addr1, + const unsigned long *addr2, + unsigned long size) +{ + unsigned long idx, val; + + for (idx = 0; idx * BITS_PER_LONG < size; idx++) { + val = addr1[idx] & addr2[idx]; + if (val) + return min(idx * BITS_PER_LONG + __ffs(val), size); + } + + return size; +} +EXPORT_SYMBOL(_find_first_and_bit); +#endif + #ifndef find_first_zero_bit /* * Find the first cleared bit in a memory region.