From nobody Sun Feb 8 12:58:16 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0C7E0C77B75 for ; Fri, 19 May 2023 19:10:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230222AbjESTKa (ORCPT ); Fri, 19 May 2023 15:10:30 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57022 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229877AbjESTKV (ORCPT ); Fri, 19 May 2023 15:10:21 -0400 Received: from mail-vs1-xe2c.google.com (mail-vs1-xe2c.google.com [IPv6:2607:f8b0:4864:20::e2c]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 4FC76E4D for ; Fri, 19 May 2023 12:09:48 -0700 (PDT) Received: by mail-vs1-xe2c.google.com with SMTP id ada2fe7eead31-42c38a6daf3so2289154137.3 for ; Fri, 19 May 2023 12:09:48 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=joelfernandes.org; s=google; t=1684523387; x=1687115387; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=oA7dMwlFmxPwFfHcKnUeZ7hJdv/AmQxUS93JuDL6gPU=; b=PCCuvdHXc4XusTKOuKnfHxqjmcKF33HedUvjSSIEB/LXCB8ftanEMvL27R617BEABE Y/SPIH6C+KoN5BEgulkLv5sqTuTF5fabGZNZo/HEVlSSY07Ygemgsus3/woEkmwUHdjS jaexiTko+LYiXNXWhDhnPmbUFhCF0ImXBUCV8= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684523387; x=1687115387; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=oA7dMwlFmxPwFfHcKnUeZ7hJdv/AmQxUS93JuDL6gPU=; b=O1+jRjyHwYa8vEMhCFauSsxljukPOC//0VmyxxybUy/695PgwmFP1n4i7kHtYDqjVO xImJzheVaTn2kMG58QLS44tU6u3F32PvBxaShjcBjBnSKMQaIgfGToxCJi68E7foTWt3 e5H3l1sE58bAcBqozqRafz1ekkzuR2omb4XBfPLVyZmr49lTtwuPsR4Cwf+TMpSqKFjA 0GcOQUL3hbJLur0juqBAuZPj/PjwPwLlcfk36G57PdQoqfIt66/CE7On8hFZR5Tff62u 8+rboxCt3625KP/twjQU6QvqouI3gaW7cf3czXYq2Ww8rVJXig/e4F2iCUpJQWpyuJjv vxmg== X-Gm-Message-State: AC+VfDxvBWtx8Bxs2J8CgDmqHsyhAcYuMGiHaq6fIMFQwxmHzoo0j9ZA NMtIyejYCQD40BV4EODXHslN0oZdEtlJvQ+nfgU= X-Google-Smtp-Source: ACHHUZ5tNnkzlczdh01+L99WDBDunQiDAPpU6vp4udkIFHQy9fkqGeBYT8FDX47Do14GAQyh+6aSSA== X-Received: by 2002:a05:6102:2ca:b0:436:2c6f:207f with SMTP id h10-20020a05610202ca00b004362c6f207fmr199261vsh.6.1684523386917; Fri, 19 May 2023 12:09:46 -0700 (PDT) Received: from joelboxx.c.googlers.com.com (129.239.188.35.bc.googleusercontent.com. [35.188.239.129]) by smtp.gmail.com with ESMTPSA id q20-20020ae9e414000000b0074e1ee30478sm1317611qkc.37.2023.05.19.12.09.46 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 19 May 2023 12:09:46 -0700 (PDT) From: "Joel Fernandes (Google)" To: linux-kernel@vger.kernel.org Cc: "Joel Fernandes (Google)" , Linus Torvalds , linux-kselftest@vger.kernel.org, linux-mm@kvack.org, Shuah Khan , Vlastimil Babka , Michal Hocko , Lorenzo Stoakes , Kirill A Shutemov , "Liam R. Howlett" , "Paul E. McKenney" , Suren Baghdasaryan Subject: [PATCH v2 1/4] mm/mremap: Optimize the start addresses in move_page_tables() Date: Fri, 19 May 2023 19:09:31 +0000 Message-ID: <20230519190934.339332-2-joel@joelfernandes.org> X-Mailer: git-send-email 2.40.1.698.g37aff9b760-goog In-Reply-To: <20230519190934.339332-1-joel@joelfernandes.org> References: <20230519190934.339332-1-joel@joelfernandes.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Recently, we see reports [1] of a warning that triggers due to move_page_tables() doing a downward and overlapping move on a mutually-aligned offset within a PMD. By mutual alignment, I mean the source and destination addresses of the mremap are at the same offset within a PMD. This mutual alignment along with the fact that the move is downward is sufficient to cause a warning related to having an allocated PMD that does not have PTEs in it. This warning will only trigger when there is mutual alignment in the move operation. A solution, as suggested by Linus Torvalds [2], is to initiate the copy process at the PMD level whenever such alignment is present. Implementing this approach will not only prevent the warning from being triggered, but it will also optimize the operation as this method should enhance the speed of the copy process whenever there's a possibility to start copying at the PMD level. Some more points: a. The optimization can be done only when both the source and destination of the mremap do not have anything mapped below it up to a PMD boundary. I add support to detect that. b. #1 is not a problem for the call to move_page_tables() from exec.c as nothing is expected to be mapped below the source/destination. However, for non-overlapping mutually aligned moves as triggered by mremap(2), I added support for checking such cases. c. I currently only optimize for PMD moves, in the future I/we can build on this work and do PUD moves as well if there is a need for this. But I want to take it one step at a time. [1] https://lore.kernel.org/all/ZB2GTBD%2FLWTrkOiO@dhcp22.suse.cz/ [2] https://lore.kernel.org/all/CAHk-=3Dwhd7msp8reJPfeGNyt0LiySMT0egExx3TVZ= SX3Ok6X=3D9g@mail.gmail.com/ Suggested-by: Linus Torvalds Signed-off-by: Joel Fernandes (Google) --- mm/mremap.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+) diff --git a/mm/mremap.c b/mm/mremap.c index 411a85682b58..be81eb3a80a8 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -478,6 +478,51 @@ static bool move_pgt_entry(enum pgt_entry entry, struc= t vm_area_struct *vma, return moved; } =20 +/* + * A helper to check if a previous mapping exists. Required for + * move_page_tables() and realign_addr() to determine if a previous mapping + * exists before we can do realignment optimizations. + */ +static bool check_addr_in_prev(struct vm_area_struct *vma, unsigned long a= ddr, + unsigned long mask) +{ + int addr_masked =3D addr & mask; + struct vm_area_struct *prev =3D NULL, *cur =3D NULL; + + /* If the masked address is within vma, there is no prev mapping of conce= rn. */ + if (vma->vm_start <=3D addr_masked) + return false; + + /* + * Attempt to find vma before prev that contains the address. + * On any issue, assume the address is within a previous mapping. + * @mmap write lock is held here, so the lookup is safe. + */ + cur =3D find_vma_prev(vma->vm_mm, vma->vm_start, &prev); + if (!cur || cur !=3D vma || !prev) + return true; + + /* The masked address fell within a previous mapping. */ + if (prev->vm_end > addr_masked) + return true; + + return false; +} + +/* Opportunistically realign to specified boundary for faster copy. */ +static void realign_addr(unsigned long *old_addr, struct vm_area_struct *o= ld_vma, + unsigned long *new_addr, struct vm_area_struct *new_vma, + unsigned long mask) +{ + if ((*old_addr & ~mask) && + (*old_addr & ~mask) =3D=3D (*new_addr & ~mask) && + !check_addr_in_prev(old_vma, *old_addr, mask) && + !check_addr_in_prev(new_vma, *new_addr, mask)) { + *old_addr =3D *old_addr & mask; + *new_addr =3D *new_addr & mask; + } +} + unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len, @@ -493,6 +538,10 @@ unsigned long move_page_tables(struct vm_area_struct *= vma, =20 old_end =3D old_addr + len; =20 + /* If possible, realign addresses to PMD boundary for faster copy. */ + if (len >=3D PMD_SIZE - (old_addr & ~PMD_MASK)) + realign_addr(&old_addr, vma, &new_addr, new_vma, PMD_MASK); + if (is_vm_hugetlb_page(vma)) return move_hugetlb_page_tables(vma, new_vma, old_addr, new_addr, len); @@ -565,6 +614,13 @@ unsigned long move_page_tables(struct vm_area_struct *= vma, =20 mmu_notifier_invalidate_range_end(&range); =20 + /* + * Prevent negative return values when {old,new}_addr was realigned + * but we broke out of the above loop for the first PMD itself. + */ + if (len + old_addr < old_end) + return 0; + return len + old_addr - old_end; /* how much done */ } =20 --=20 2.40.1.698.g37aff9b760-goog From nobody Sun Feb 8 12:58:16 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id CEFC0C7EE26 for ; Fri, 19 May 2023 19:10:36 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231792AbjESTKe (ORCPT ); Fri, 19 May 2023 15:10:34 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57026 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231414AbjESTKW (ORCPT ); Fri, 19 May 2023 15:10:22 -0400 Received: from mail-ua1-x92b.google.com (mail-ua1-x92b.google.com [IPv6:2607:f8b0:4864:20::92b]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 44F18171B for ; Fri, 19 May 2023 12:09:49 -0700 (PDT) Received: by mail-ua1-x92b.google.com with SMTP id a1e0cc1a2514c-783eef15004so1198934241.3 for ; Fri, 19 May 2023 12:09:49 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=joelfernandes.org; s=google; t=1684523388; x=1687115388; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=t64UzVHVroabp76Xd4g1LLeTmZtqX+n8nvVYbfjxh90=; b=o7UU9iUhAbrwB44BtKTmc5RQ8dUPaFjHnnyhvbFZd+1u585u1S76A7OrnTd4nASMLC ZkUXlYY0ZOkyICYNTcwic2MeSK8V8ncKEVmdi5sB8vbXKubDEMtEYecQ/rgSsn59s9aX 4//vGzJMsIiFGeko/yn1WZd6ewTT2Ke489JRE= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684523388; x=1687115388; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=t64UzVHVroabp76Xd4g1LLeTmZtqX+n8nvVYbfjxh90=; b=dEBcVAA0E4U1SpxVjea2KiWrD9cCxsqzUUT7PzjQmoG0vN2mEki+wHqlFnMUfqFyvS SbiufRweUZ0cJCoMw7AkCi+ptt/aIjtangPlibysYGxBa/z5uGzA8VPprPLm6tk9J4pc i6/WDHyshVnZ7hL/zh5dJXB13HONlC/XdT8q6sT+f3zDniav9ONjMkCDb3DpOVwHKkhy ztCcxBp5q94M6G2t4dZTad5YHqRuxoXf6lQ2sJCDKiY93HTRxSegAdnnGFsqTfR8mRQC /wzdjjwjU2e3Lk7Vym5rosKyutPe6pazYu+yt50JIYVPfH/pHVywLfxaWRMkzBuyRnBv 3fKA== X-Gm-Message-State: AC+VfDybHroqQNvz2bbfv1CvA4wNk0ntQ7Byb+N/LOd1PnaB5p/bevAX mZD+odNQQbOwb0T1vO8tJyWAKzA8WziMb8x0vDA= X-Google-Smtp-Source: ACHHUZ4jFcbT1ve1tL/ufSb7el3GoyODcR910N727rMH2QSU4iGxgxnP0MXarC1z3MztdTo718x5vw== X-Received: by 2002:a67:f050:0:b0:435:f378:8ee8 with SMTP id q16-20020a67f050000000b00435f3788ee8mr163030vsm.26.1684523388002; Fri, 19 May 2023 12:09:48 -0700 (PDT) Received: from joelboxx.c.googlers.com.com (129.239.188.35.bc.googleusercontent.com. [35.188.239.129]) by smtp.gmail.com with ESMTPSA id q20-20020ae9e414000000b0074e1ee30478sm1317611qkc.37.2023.05.19.12.09.47 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 19 May 2023 12:09:47 -0700 (PDT) From: "Joel Fernandes (Google)" To: linux-kernel@vger.kernel.org Cc: "Joel Fernandes (Google)" , linux-kselftest@vger.kernel.org, linux-mm@kvack.org, Shuah Khan , Vlastimil Babka , Michal Hocko , Linus Torvalds , Lorenzo Stoakes , Kirill A Shutemov , "Liam R. Howlett" , "Paul E. McKenney" , Suren Baghdasaryan Subject: [PATCH v2 2/4] selftests: mm: Fix failure case when new remap region was not found Date: Fri, 19 May 2023 19:09:32 +0000 Message-ID: <20230519190934.339332-3-joel@joelfernandes.org> X-Mailer: git-send-email 2.40.1.698.g37aff9b760-goog In-Reply-To: <20230519190934.339332-1-joel@joelfernandes.org> References: <20230519190934.339332-1-joel@joelfernandes.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" When a valid remap region could not be found, the source mapping is not cleaned up. Fix the goto statement such that the clean up happens. Signed-off-by: Joel Fernandes (Google) --- tools/testing/selftests/mm/mremap_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selft= ests/mm/mremap_test.c index 5c3773de9f0f..6822d657f589 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -316,7 +316,7 @@ static long long remap_region(struct config c, unsigned= int threshold_mb, if (addr + c.dest_alignment < addr) { ksft_print_msg("Couldn't find a valid region to remap to\n"); ret =3D -1; - goto out; + goto clean_up_src; } addr +=3D c.dest_alignment; } --=20 2.40.1.698.g37aff9b760-goog From nobody Sun Feb 8 12:58:16 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id B10D4C77B75 for ; Fri, 19 May 2023 19:10:39 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231809AbjESTKh (ORCPT ); Fri, 19 May 2023 15:10:37 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57278 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231625AbjESTKX (ORCPT ); Fri, 19 May 2023 15:10:23 -0400 Received: from mail-ua1-x932.google.com (mail-ua1-x932.google.com [IPv6:2607:f8b0:4864:20::932]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 55B0110C9 for ; Fri, 19 May 2023 12:09:50 -0700 (PDT) Received: by mail-ua1-x932.google.com with SMTP id a1e0cc1a2514c-783eb14ae3cso2242983241.2 for ; Fri, 19 May 2023 12:09:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=joelfernandes.org; s=google; t=1684523389; x=1687115389; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=8BlbglpAiZ94wJYkjhcCjsilb7jfKjCG904F6yJstFY=; b=x8ZyDrw6ni184t1nPUu9gHzYGnCU4QMuz0CHgZiJdJSkGolahQopXIQzMHUKRX1tuL Sk9VbgqX2HUtPxhGHeN4FRXjhKh1tAahRr6lwwpWuDo763W0ExapWgKq8ZNizk5D6Nj+ cwyjlwYVFmQ1N0AvIKfGAIKpy+GRM3WOTBx+U= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684523389; x=1687115389; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=8BlbglpAiZ94wJYkjhcCjsilb7jfKjCG904F6yJstFY=; b=idZrh4zpzjhcaoDFFXFjXB7Ljz+dPZm0vcCCR0h3VnDP6XO9VfL6+nvvEueB1BJLC9 1Xh+K0Ns00ibJJwqNv1ByV69JcCmgNin9o4be7w/ALiHM+/wNzysp5fKecokiVJXE0EX BEHZVicPj2a7eifINjEJZstV2TpfM7ZY+ETVY80/wXe/LlhU1qxDO/OBfT7WMpuXYuJf OMsV7ZL4n3qbr0Oo7MeIj7ErMFfjr/CtwbUl61x+OjHhS7QKbcWS66c6/3TInC2R8X2/ MblMDqI/l4A6wPqOIvHylSRQgF0tJNT6gpWM+O1UU0/R3ef9na5td/YZ0pYQ0/WPQWHp M4lg== X-Gm-Message-State: AC+VfDyE3Ab6tNn5Y9R26nGAMy0GC40enR13R9PgNg7J14jg9dxNTWcE sDo+366Zq8T1VOQ/wU0XEFj+r4vMleWJZBSav2E= X-Google-Smtp-Source: ACHHUZ7k2Kr/gJkiN5S1M+tfEjayIP8g2cDy6n/x0srwgMQ1712z1LJILIPD/wMAeXbKBNfnKX869w== X-Received: by 2002:a1f:5901:0:b0:43f:ea80:e8af with SMTP id n1-20020a1f5901000000b0043fea80e8afmr1449033vkb.4.1684523388940; Fri, 19 May 2023 12:09:48 -0700 (PDT) Received: from joelboxx.c.googlers.com.com (129.239.188.35.bc.googleusercontent.com. [35.188.239.129]) by smtp.gmail.com with ESMTPSA id q20-20020ae9e414000000b0074e1ee30478sm1317611qkc.37.2023.05.19.12.09.48 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 19 May 2023 12:09:48 -0700 (PDT) From: "Joel Fernandes (Google)" To: linux-kernel@vger.kernel.org Cc: "Joel Fernandes (Google)" , linux-kselftest@vger.kernel.org, linux-mm@kvack.org, Shuah Khan , Vlastimil Babka , Michal Hocko , Linus Torvalds , Lorenzo Stoakes , Kirill A Shutemov , "Liam R. Howlett" , "Paul E. McKenney" , Suren Baghdasaryan Subject: [PATCH v2 3/4] selftests: mm: Add a test for mutually aligned moves > PMD size Date: Fri, 19 May 2023 19:09:33 +0000 Message-ID: <20230519190934.339332-4-joel@joelfernandes.org> X-Mailer: git-send-email 2.40.1.698.g37aff9b760-goog In-Reply-To: <20230519190934.339332-1-joel@joelfernandes.org> References: <20230519190934.339332-1-joel@joelfernandes.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" This patch adds a test case to check if a PMD-alignment optimization successfully happens. I add support to make sure there is some room before the source mapping, otherwise the optimization to trigger PMD-aligned move will be disabled as the kernel will detect that a mapping before the source exists and such optimization becomes impossible. Signed-off-by: Joel Fernandes (Google) --- tools/testing/selftests/mm/mremap_test.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selft= ests/mm/mremap_test.c index 6822d657f589..6304eb0947a3 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -44,6 +44,7 @@ enum { _1MB =3D 1ULL << 20, _2MB =3D 2ULL << 20, _4MB =3D 4ULL << 20, + _5MB =3D 5ULL << 20, _1GB =3D 1ULL << 30, _2GB =3D 2ULL << 30, PMD =3D _2MB, @@ -235,6 +236,11 @@ static void *get_source_mapping(struct config c) unsigned long long mmap_min_addr; =20 mmap_min_addr =3D get_mmap_min_addr(); + /* + * For some tests, we need to not have any mappings below the + * source mapping. Add some headroom to mmap_min_addr for this. + */ + mmap_min_addr +=3D 10 * _4MB; =20 retry: addr +=3D c.src_alignment; @@ -434,7 +440,7 @@ static int parse_args(int argc, char **argv, unsigned i= nt *threshold_mb, return 0; } =20 -#define MAX_TEST 13 +#define MAX_TEST 14 #define MAX_PERF_TEST 3 int main(int argc, char **argv) { @@ -500,6 +506,10 @@ int main(int argc, char **argv) test_cases[12] =3D MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCC= ESS, "2GB mremap - Source PUD-aligned, Destination PUD-aligned"); =20 + /* Src and Dest addr 1MB aligned. 5MB mremap. */ + test_cases[13] =3D MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SU= CCESS, + "5MB mremap - Source 1MB-aligned, Destination 1MB-aligned"); + perf_test_cases[0] =3D MAKE_TEST(page_size, page_size, _1GB, NON_OVERLAP= PING, EXPECT_SUCCESS, "1GB mremap - Source PTE-aligned, Destination PTE-aligned"); /* --=20 2.40.1.698.g37aff9b760-goog From nobody Sun Feb 8 12:58:16 2026 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0B1B2C7EE26 for ; Fri, 19 May 2023 19:10:43 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231665AbjESTKl (ORCPT ); Fri, 19 May 2023 15:10:41 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57290 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229707AbjESTKX (ORCPT ); Fri, 19 May 2023 15:10:23 -0400 Received: from mail-ua1-x92f.google.com (mail-ua1-x92f.google.com [IPv6:2607:f8b0:4864:20::92f]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1AA881700 for ; Fri, 19 May 2023 12:09:51 -0700 (PDT) Received: by mail-ua1-x92f.google.com with SMTP id a1e0cc1a2514c-783e5f8717aso1200658241.2 for ; Fri, 19 May 2023 12:09:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=joelfernandes.org; s=google; t=1684523390; x=1687115390; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=SWo1p3DpVmU0T9mj5qOdTODFP5dx/UDqRA4JPzC/zFM=; b=TcMQgimlGvWiy+Yq9tzs5x+tIAK1mp22aFzOi9aGMKUkP8PwsWwCwhComvsSo4eIKL T1d/hEYoCC9WFsUyijPJFPrQAANt3Hi+H3ilcgnn0iAghrq2U37nMJFcBIWziF4XZgdK 7bKnjZnjYy7fZ+3+sj1+U/9UYLbq0lSUVkjRY= X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684523390; x=1687115390; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=SWo1p3DpVmU0T9mj5qOdTODFP5dx/UDqRA4JPzC/zFM=; b=gymwhlvdP0veNVCdKjctFyadp6tq+myArXxroTCPXKoma90XaKnwUBbj0vmKFJHkH7 lcu2WEViO8OKuGbFgLWzN0GjeTd5yrbTEjwGXm9132ryOkj3UFl6J8ffX0gNoTLJYfxe LE8oX8wFaqyPjYi4YB4PvYuPf1KmFAhFuq/aM45v/5nrVIqe1o0y67iLhNBQWyW2q3pL 5+WSe7BJWVmtGvK59KqFCa/iQm+FWAwusOiJCHoXdiIoKqQ00WF+HI1aswSIZhQjE0tD LRDQc0puyAhQCWn7ywotMVXmnOr3byuaxY0u6YL0PfzjfvhLeyB8QwB2awT6IDNB8n3S qYVA== X-Gm-Message-State: AC+VfDwetZpq/vNrGwmXSYL/IZYOJmGvxMay0DNdlXmvnNPLzEczRpBb i+Df2YHMEJCSmg1qqBNmPbjFdL2BoGNN7TSXFBM= X-Google-Smtp-Source: ACHHUZ5Yk4gah/ju4JKpHlXFRbbbY0acrjXAxd6nBOFP7q9w3aEit22E9N+b9+SyAwAbuG1o5wr0aw== X-Received: by 2002:a67:f101:0:b0:439:30df:6bb1 with SMTP id n1-20020a67f101000000b0043930df6bb1mr202282vsk.1.1684523389774; Fri, 19 May 2023 12:09:49 -0700 (PDT) Received: from joelboxx.c.googlers.com.com (129.239.188.35.bc.googleusercontent.com. [35.188.239.129]) by smtp.gmail.com with ESMTPSA id q20-20020ae9e414000000b0074e1ee30478sm1317611qkc.37.2023.05.19.12.09.49 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 19 May 2023 12:09:49 -0700 (PDT) From: "Joel Fernandes (Google)" To: linux-kernel@vger.kernel.org Cc: "Joel Fernandes (Google)" , linux-kselftest@vger.kernel.org, linux-mm@kvack.org, Shuah Khan , Vlastimil Babka , Michal Hocko , Linus Torvalds , Lorenzo Stoakes , Kirill A Shutemov , "Liam R. Howlett" , "Paul E. McKenney" , Suren Baghdasaryan Subject: [PATCH v2 4/4] selftests: mm: Add a test for remapping to area immediately after existing mapping Date: Fri, 19 May 2023 19:09:34 +0000 Message-ID: <20230519190934.339332-5-joel@joelfernandes.org> X-Mailer: git-send-email 2.40.1.698.g37aff9b760-goog In-Reply-To: <20230519190934.339332-1-joel@joelfernandes.org> References: <20230519190934.339332-1-joel@joelfernandes.org> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" This patch adds support for verifying that we correctly handle the situation where something is already mapped before the destination of the r= emap. Any realignment of destination address and PMD-copy will destroy that existing mapping. In such cases, we need to avoid doing the optimization. To test this, we map an area called the preamble before the remap region. Then we verify after the mremap operation that this region did not = get corrupted. Putting some prints in the kernel, I verified that we optimize correctly in different situations: Optimize when there is alignment and no previous mapping (this is tested by previous patch). check_addr_in_prev(old_vma->vm_start=3D2900000, old_addr=3D2900000, mask=3D= -2097152): 0 check_addr_in_prev(new_vma->vm_start=3D2f00000, new_addr=3D2f00000, mask=3D= -2097152): 0 =3D=3D=3D Starting move_page_tables =3D=3D=3D Doing PUD move for 2800000 -> 2e00000 of extent=3D200000 <-- Optimization Doing PUD move for 2a00000 -> 3000000 of extent=3D200000 Doing PUD move for 2c00000 -> 3200000 of extent=3D200000 Don't optimize when there is alignment but there is previous mapping (this is tested by this patch). Notice that check_addr_in_prev() returns 1 for the destination mapping as we detected there is something there. check_addr_in_prev(old_vma->vm_start=3D2900000, old_addr=3D2900000, mask=3D= -2097152): 0 check_addr_in_prev(new_vma->vm_start=3D5700000, new_addr=3D5700000, mask=3D= -2097152): 1 =3D=3D=3D Starting move_page_tables =3D=3D=3D Doing move_ptes for 2900000 -> 5700000 of extent=3D100000 <-- Unoptimized Doing PUD move for 2a00000 -> 5800000 of extent=3D200000 Doing PUD move for 2c00000 -> 5a00000 of extent=3D200000 Signed-off-by: Joel Fernandes (Google) --- tools/testing/selftests/mm/mremap_test.c | 57 +++++++++++++++++++++--- 1 file changed, 52 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selft= ests/mm/mremap_test.c index 6304eb0947a3..d7366074e2a8 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -29,6 +29,7 @@ struct config { unsigned long long dest_alignment; unsigned long long region_size; int overlapping; + int dest_preamble_size; }; =20 struct test { @@ -283,7 +284,7 @@ static void *get_source_mapping(struct config c) static long long remap_region(struct config c, unsigned int threshold_mb, char pattern_seed) { - void *addr, *src_addr, *dest_addr; + void *addr, *src_addr, *dest_addr, *dest_preamble_addr; unsigned long long i; struct timespec t_start =3D {0, 0}, t_end =3D {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; @@ -300,7 +301,7 @@ static long long remap_region(struct config c, unsigned= int threshold_mb, goto out; } =20 - /* Set byte pattern */ + /* Set byte pattern for source block. */ srand(pattern_seed); for (i =3D 0; i < threshold; i++) memset((char *) src_addr + i, (char) rand(), 1); @@ -312,6 +313,9 @@ static long long remap_region(struct config c, unsigned= int threshold_mb, addr =3D (void *) (((unsigned long long) src_addr + c.region_size + offset) & align_mask); =20 + /* Remap after the destination block preamble. */ + addr +=3D c.dest_preamble_size; + /* See comment in get_source_mapping() */ if (!((unsigned long long) addr & c.dest_alignment)) addr =3D (void *) ((unsigned long long) addr | c.dest_alignment); @@ -327,6 +331,24 @@ static long long remap_region(struct config c, unsigne= d int threshold_mb, addr +=3D c.dest_alignment; } =20 + if (c.dest_preamble_size) { + dest_preamble_addr =3D mmap((void *) addr - c.dest_preamble_size, c.dest= _preamble_size, + PROT_READ | PROT_WRITE, + MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED, + -1, 0); + if (dest_preamble_addr =3D=3D MAP_FAILED) { + ksft_print_msg("Failed to map dest preamble region: %s\n", + strerror(errno)); + ret =3D -1; + goto clean_up_src; + } + + /* Set byte pattern for the dest preamble block. */ + srand(pattern_seed); + for (i =3D 0; i < c.dest_preamble_size; i++) + memset((char *) dest_preamble_addr + i, (char) rand(), 1); + } + clock_gettime(CLOCK_MONOTONIC, &t_start); dest_addr =3D mremap(src_addr, c.region_size, c.region_size, MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr); @@ -335,7 +357,7 @@ static long long remap_region(struct config c, unsigned= int threshold_mb, if (dest_addr =3D=3D MAP_FAILED) { ksft_print_msg("mremap failed: %s\n", strerror(errno)); ret =3D -1; - goto clean_up_src; + goto clean_up_dest_preamble; } =20 /* Verify byte pattern after remapping */ @@ -353,6 +375,23 @@ static long long remap_region(struct config c, unsigne= d int threshold_mb, } } =20 + /* Verify the dest preamble byte pattern after remapping */ + if (c.dest_preamble_size) { + srand(pattern_seed); + for (i =3D 0; i < c.dest_preamble_size; i++) { + char c =3D (char) rand(); + + if (((char *) dest_preamble_addr)[i] !=3D c) { + ksft_print_msg("Preamble data after remap doesn't match at offset %d\n= ", + i); + ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff, + ((char *) dest_preamble_addr)[i] & 0xff); + ret =3D -1; + goto clean_up_dest; + } + } + } + start_ns =3D t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec; end_ns =3D t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec; ret =3D end_ns - start_ns; @@ -365,6 +404,9 @@ static long long remap_region(struct config c, unsigned= int threshold_mb, */ clean_up_dest: munmap(dest_addr, c.region_size); +clean_up_dest_preamble: + if (c.dest_preamble_size && dest_preamble_addr) + munmap(dest_preamble_addr, c.dest_preamble_size); clean_up_src: munmap(src_addr, c.region_size); out: @@ -440,7 +482,7 @@ static int parse_args(int argc, char **argv, unsigned i= nt *threshold_mb, return 0; } =20 -#define MAX_TEST 14 +#define MAX_TEST 15 #define MAX_PERF_TEST 3 int main(int argc, char **argv) { @@ -449,7 +491,7 @@ int main(int argc, char **argv) unsigned int threshold_mb =3D VALIDATION_DEFAULT_THRESHOLD; unsigned int pattern_seed; int num_expand_tests =3D 2; - struct test test_cases[MAX_TEST]; + struct test test_cases[MAX_TEST] =3D {}; struct test perf_test_cases[MAX_PERF_TEST]; int page_size; time_t t; @@ -510,6 +552,11 @@ int main(int argc, char **argv) test_cases[13] =3D MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SU= CCESS, "5MB mremap - Source 1MB-aligned, Destination 1MB-aligned"); =20 + /* Src and Dest addr 1MB aligned. 5MB mremap. */ + test_cases[14] =3D MAKE_TEST(_1MB, _1MB, _5MB, NON_OVERLAPPING, EXPECT_SU= CCESS, + "5MB mremap - Source 1MB-aligned, Dest 1MB-aligned with 40MB Preambl= e"); + test_cases[14].config.dest_preamble_size =3D 10 * _4MB; + perf_test_cases[0] =3D MAKE_TEST(page_size, page_size, _1GB, NON_OVERLAP= PING, EXPECT_SUCCESS, "1GB mremap - Source PTE-aligned, Destination PTE-aligned"); /* --=20 2.40.1.698.g37aff9b760-goog