From patchwork Fri Apr 22 20:18:30 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Collingbourne X-Patchwork-Id: 12824063 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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0B4D5C433EF for ; Fri, 22 Apr 2022 20:18:42 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 776E26B0073; Fri, 22 Apr 2022 16:18:42 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 725586B0074; Fri, 22 Apr 2022 16:18:42 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 612DC6B0075; Fri, 22 Apr 2022 16:18:42 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (relay.a.hostedemail.com [64.99.140.24]) by kanga.kvack.org (Postfix) with ESMTP id 532A86B0073 for ; Fri, 22 Apr 2022 16:18:42 -0400 (EDT) Received: from smtpin16.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay07.hostedemail.com (Postfix) with ESMTP id 1C86B20765 for ; Fri, 22 Apr 2022 20:18:42 +0000 (UTC) X-FDA: 79385628084.16.0D1D057 Received: from mail-yb1-f201.google.com (mail-yb1-f201.google.com [209.85.219.201]) by imf22.hostedemail.com (Postfix) with ESMTP id 10B5AC0028 for ; Fri, 22 Apr 2022 20:18:40 +0000 (UTC) Received: by mail-yb1-f201.google.com with SMTP id h16-20020a056902009000b00628a70584b2so8041514ybs.6 for ; Fri, 22 Apr 2022 13:18:41 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20210112; h=date:message-id:mime-version:subject:from:to:cc; bh=eMAERF62YTPWtGAsO2YVmQloDH5oUr4o6LySCLx0+Cc=; b=F83iESBWnyy6uOnOgeXvhunYpfwEIKcvbOdsfG8Cp6juORqTB5/nyhOk7YWhV15WRD mj/4LWY3xVAfwCdPVkSCNFayj1T36VLUNCxX90pH1FGwsgJKnEql6zrzfIjrQcGdVqLO yw7SVLcseqko8s7na0HZRF6ZmLyDMnO92X2a/jpzJ0ZxcdbuEr0jyUfppc0XxYFFkMZi OlDE09MJDkJ8B4l+ofc7oi+3/oizqB0UL2V0Qctf6ujyteRiJdRTU/qWsbiBdom3DsPT l7G/2dY47aoouvl5TMBEVo7BKXknk054vhzlwt3Y5foEZctZ65TFJ9m3Y+EEbkBK8EhX +vCQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=x-gm-message-state:date:message-id:mime-version:subject:from:to:cc; bh=eMAERF62YTPWtGAsO2YVmQloDH5oUr4o6LySCLx0+Cc=; b=4/7ORogxyREVSBZbY0cpYSeetWGo1LKjVThFnmNEMbAAExiOaE4/FM8wlJZR4NgUkm mG9zaYdGbVbV4KKA1mGH7u5PJ+GbQamoEExtpdRlgmISSXv8jqIfcwS41hckR5hd3NsF 0w0QcP7Bfrhls+D/lVmm4iYor/lrr2ExbhqpUN+jhUVegljzNQjnbjpZpIjis4jgFjFW 9karDrwk4tnt7tFnmOHFUqjKrNddNx9m+/uomx2IIpwgN4AJZ0+Kh/eQrMh/5/1kf3rl Jx7HANOiifVgeEeQmvFvjABFRdHotYZVI+k0CEYMqULUTuhcdhYTesb3yn70NZ8KfQos 1K7Q== X-Gm-Message-State: AOAM532l8bHm32/JkvUD+GZqKlincd3no6MhZ8Mjhs/TR6LBZ/TIYeEX sQuIyX4BgLgssFA/XHDKSY+eZgg= X-Google-Smtp-Source: ABdhPJzs3wUmGnm/6gjGMkcBDBSkTa9dTxn95pedDMqZb3BCTfFfhpQ/gQ6c3EzTP1AHdexsjK2ZhLU= X-Received: from pcc-desktop.svl.corp.google.com ([2620:15c:2ce:200:b874:60b4:62b:9c7a]) (user=pcc job=sendgmr) by 2002:a81:2654:0:b0:2f7:c5f4:a486 with SMTP id m81-20020a812654000000b002f7c5f4a486mr265675ywm.141.1650658720646; Fri, 22 Apr 2022 13:18:40 -0700 (PDT) Date: Fri, 22 Apr 2022 13:18:30 -0700 Message-Id: <20220422201830.288018-1-pcc@google.com> Mime-Version: 1.0 X-Mailer: git-send-email 2.36.0.rc2.479.g8af0fa9b8e-goog Subject: [PATCH v3] mm: make minimum slab alignment a runtime property From: Peter Collingbourne To: Andrey Konovalov , Hyeonggon Yoo <42.hyeyoo@gmail.com>, Andrew Morton , Catalin Marinas Cc: Peter Collingbourne , Linux ARM , Linux Memory Management List , Linux Kernel Mailing List , vbabka@suse.cz, penberg@kernel.org, roman.gushchin@linux.dev, iamjoonsoo.kim@lge.com, rientjes@google.com, Herbert Xu , Andrey Ryabinin , Alexander Potapenko , Dmitry Vyukov , kasan-dev , Eric Biederman , Kees Cook X-Rspamd-Queue-Id: 10B5AC0028 X-Stat-Signature: tiwufubpotxx1ntso9zc946ptromy17q Authentication-Results: imf22.hostedemail.com; dkim=pass header.d=google.com header.s=20210112 header.b=F83iESBW; dmarc=pass (policy=reject) header.from=google.com; spf=pass (imf22.hostedemail.com: domain of 3oA1jYgMKCGEOBBFNNFKD.BNLKHMTW-LLJU9BJ.NQF@flex--pcc.bounces.google.com designates 209.85.219.201 as permitted sender) smtp.mailfrom=3oA1jYgMKCGEOBBFNNFKD.BNLKHMTW-LLJU9BJ.NQF@flex--pcc.bounces.google.com X-Rspam-User: X-Rspamd-Server: rspam08 X-HE-Tag: 1650658720-37613 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: When CONFIG_KASAN_HW_TAGS is enabled we currently increase the minimum slab alignment to 16. This happens even if MTE is not supported in hardware or disabled via kasan=off, which creates an unnecessary memory overhead in those cases. Eliminate this overhead by making the minimum slab alignment a runtime property and only aligning to 16 if KASAN is enabled at runtime. On a DragonBoard 845c (non-MTE hardware) with a kernel built with CONFIG_KASAN_HW_TAGS, waiting for quiescence after a full Android boot I see the following Slab measurements in /proc/meminfo (median of 3 reboots): Before: 169020 kB After: 167304 kB Link: https://linux-review.googlesource.com/id/I752e725179b43b144153f4b6f584ceb646473ead Signed-off-by: Peter Collingbourne Reviewed-by: Andrey Konovalov Reviewed-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com> Acked-by: David Rientjes Reported-by: kernel test robot Reviewed-by: Catalin Marinas --- v3: - go back to ARCH_SLAB_MINALIGN - revert changes to fs/binfmt_flat.c - update arch_slab_minalign() comment to say that it must be a power of two v2: - use max instead of max_t in flat_stack_align() arch/arm64/include/asm/cache.h | 17 ++++++++++++----- include/linux/slab.h | 12 ++++++++++++ mm/slab.c | 7 +++---- mm/slab_common.c | 3 +-- mm/slob.c | 6 +++--- 5 files changed, 31 insertions(+), 14 deletions(-) diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index a074459f8f2f..22b22dc1b1b5 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -6,6 +6,7 @@ #define __ASM_CACHE_H #include +#include #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 @@ -49,16 +50,22 @@ */ #define ARCH_DMA_MINALIGN (128) +#ifndef __ASSEMBLY__ + +#include +#include + #ifdef CONFIG_KASAN_SW_TAGS #define ARCH_SLAB_MINALIGN (1ULL << KASAN_SHADOW_SCALE_SHIFT) #elif defined(CONFIG_KASAN_HW_TAGS) -#define ARCH_SLAB_MINALIGN MTE_GRANULE_SIZE +static inline size_t arch_slab_minalign(void) +{ + return kasan_hw_tags_enabled() ? MTE_GRANULE_SIZE : + __alignof__(unsigned long long); +} +#define arch_slab_minalign() arch_slab_minalign() #endif -#ifndef __ASSEMBLY__ - -#include - #define ICACHEF_ALIASING 0 #define ICACHEF_VPIPT 1 extern unsigned long __icache_flags; diff --git a/include/linux/slab.h b/include/linux/slab.h index 373b3ef99f4e..2c7190db4cc0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -209,6 +209,18 @@ void kmem_dump_obj(void *object); #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long) #endif +/* + * Arches can define this function if they want to decide the minimum slab + * alignment at runtime. The value returned by the function must be a power + * of two and >= ARCH_SLAB_MINALIGN. + */ +#ifndef arch_slab_minalign +static inline size_t arch_slab_minalign(void) +{ + return ARCH_SLAB_MINALIGN; +} +#endif + /* * kmalloc and friends return ARCH_KMALLOC_MINALIGN aligned * pointers. kmem_cache_alloc and friends return ARCH_SLAB_MINALIGN diff --git a/mm/slab.c b/mm/slab.c index 0edb474edef1..97b756976c8b 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3009,10 +3009,9 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, objp += obj_offset(cachep); if (cachep->ctor && cachep->flags & SLAB_POISON) cachep->ctor(objp); - if (ARCH_SLAB_MINALIGN && - ((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) { - pr_err("0x%px: not aligned to ARCH_SLAB_MINALIGN=%d\n", - objp, (int)ARCH_SLAB_MINALIGN); + if ((unsigned long)objp & (arch_slab_minalign() - 1)) { + pr_err("0x%px: not aligned to arch_slab_minalign()=%d\n", objp, + (int)arch_slab_minalign()); } return objp; } diff --git a/mm/slab_common.c b/mm/slab_common.c index 2b3206a2c3b5..33cc49810a54 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -154,8 +154,7 @@ static unsigned int calculate_alignment(slab_flags_t flags, align = max(align, ralign); } - if (align < ARCH_SLAB_MINALIGN) - align = ARCH_SLAB_MINALIGN; + align = max_t(size_t, align, arch_slab_minalign()); return ALIGN(align, sizeof(void *)); } diff --git a/mm/slob.c b/mm/slob.c index 40ea6e2d4ccd..3bd2669bd690 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -478,7 +478,7 @@ static __always_inline void * __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) { unsigned int *m; - int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, arch_slab_minalign()); void *ret; gfp &= gfp_allowed_mask; @@ -555,7 +555,7 @@ void kfree(const void *block) sp = virt_to_folio(block); if (folio_test_slab(sp)) { - int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, arch_slab_minalign()); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); } else { @@ -584,7 +584,7 @@ size_t __ksize(const void *block) if (unlikely(!folio_test_slab(folio))) return folio_size(folio); - align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + align = max_t(size_t, ARCH_KMALLOC_MINALIGN, arch_slab_minalign()); m = (unsigned int *)(block - align); return SLOB_UNITS(*m) * SLOB_UNIT; }