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=-12.5 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,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 AD281C388F7 for ; Fri, 13 Nov 2020 11:04:23 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 364C12224F for ; Fri, 13 Nov 2020 11:04:23 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com header.i=@bytedance-com.20150623.gappssmtp.com header.b="x4h4tozn" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 364C12224F Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=bytedance.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id B13806B00BC; Fri, 13 Nov 2020 06:04:22 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id AC3E86B00CB; Fri, 13 Nov 2020 06:04:22 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 93F306B00CC; Fri, 13 Nov 2020 06:04:22 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0127.hostedemail.com [216.40.44.127]) by kanga.kvack.org (Postfix) with ESMTP id 649856B00BC for ; Fri, 13 Nov 2020 06:04:22 -0500 (EST) Received: from smtpin22.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay01.hostedemail.com (Postfix) with ESMTP id 0DF73180AD801 for ; Fri, 13 Nov 2020 11:04:22 +0000 (UTC) X-FDA: 77479111164.22.birds46_5409fcf2730e Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin22.hostedemail.com (Postfix) with ESMTP id CEBC618038E67 for ; Fri, 13 Nov 2020 11:04:21 +0000 (UTC) X-HE-Tag: birds46_5409fcf2730e X-Filterd-Recvd-Size: 8847 Received: from mail-pg1-f195.google.com (mail-pg1-f195.google.com [209.85.215.195]) by imf47.hostedemail.com (Postfix) with ESMTP for ; Fri, 13 Nov 2020 11:04:21 +0000 (UTC) Received: by mail-pg1-f195.google.com with SMTP id i7so6819345pgh.6 for ; Fri, 13 Nov 2020 03:04:21 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20150623.gappssmtp.com; s=20150623; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=2dnPV1b6uHWD2D+PaHlh5ehZyTbtQb+H242CmT/tu8g=; b=x4h4toznMW9myqfV4/4rtBvtB3x76JiQu2/IusbB/1Q3+xmDQkJKzs1TsHxWt/zxkF rYvDmGEcnfWEohs8dWmCxfpMQzt24NSGwNE/8jF+QNl7QAMOnnzgFAoAaNkOF+Gs7R5z ObcAsEEqtcE/KIQyrxRkTW1EBlAAjJm02KYO6I/NcZ0TuIKNyDrTkulq8q2o0zu76NJV RMlNYeE2QRpW39xbzGLuIaY4CIkMKnZTo3OHOMKlEdgEUMTm95kK/Tb+3b0ze2akmsxM KqtPCxok9SvhICziSupm5tLHqksj/uRJkxvuQyRQ3bddyhwUldhnUzZSBiFUz0yeyeGZ QrMQ== 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=2dnPV1b6uHWD2D+PaHlh5ehZyTbtQb+H242CmT/tu8g=; b=Z9cb5ZlPVDxFz9QlteALLUwa4HIs/pTKytPptfMDa2X6Ikvjp27dRZOf2Mph/RY61f Fa43ApxsGPrVgPg4gohdXiL59iIknwcd1wyUITwKkqQnoonZezXjr0ZHmNRPYcpIICnX dxYx/RSU24I8NN6Mk9+l2b3zluVS2FHOl30R9g3SmefyMKbZpbibr1WyzjUPkinT26By 85sqerh2Rz+nCG8aL3+dThcMw6220g3AK5jS9OIikiwe2u4MFc6tyK+nskVdFOOVOqSc qj/OqTPw9VRRfdFSeQwOHeuICIfqsh2OYc6zbyQ2FT+VnVVpIEWHIMFr0N7CzLiywIld rRAg== X-Gm-Message-State: AOAM530lcN6R+oFdZxFjw+r5xNPBMXYy7Vg4KGk17WxkU0s8iakSfU3Z Dy6pqUZHf+0M+qqSIAI+ksbanQ== X-Google-Smtp-Source: ABdhPJwej1GeIBlLpEuMCUF9hhhhxhMLbmKZpJvqWgyB4Wj77yK7vWxMgfdOWrnLEfwZC9Rr+9YU8w== X-Received: by 2002:a63:cb51:: with SMTP id m17mr1607379pgi.337.1605265460592; Fri, 13 Nov 2020 03:04:20 -0800 (PST) Received: from localhost.localdomain ([61.120.150.78]) by smtp.gmail.com with ESMTPSA id f1sm8909959pfc.56.2020.11.13.03.04.08 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Fri, 13 Nov 2020 03:04:19 -0800 (PST) From: Muchun Song To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de, mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com, dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org, viro@zeniv.linux.org.uk, akpm@linux-foundation.org, paulmck@kernel.org, mchehab+huawei@kernel.org, pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org, oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de, almasrymina@google.com, rientjes@google.com, willy@infradead.org, osalvador@suse.de, mhocko@suse.com Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, Muchun Song Subject: [PATCH v4 18/21] mm/hugetlb: Merge pte to huge pmd only for gigantic page Date: Fri, 13 Nov 2020 18:59:49 +0800 Message-Id: <20201113105952.11638-19-songmuchun@bytedance.com> X-Mailer: git-send-email 2.21.0 (Apple Git-122) In-Reply-To: <20201113105952.11638-1-songmuchun@bytedance.com> References: <20201113105952.11638-1-songmuchun@bytedance.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable 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: Merge pte to huge pmd if it has ever been split. Now only support gigantic page which's vmemmap pages size is an integer multiple of PMD_SIZE. This is the simplest case to handle. Signed-off-by: Muchun Song --- arch/x86/include/asm/hugetlb.h | 8 +++ mm/hugetlb_vmemmap.c | 118 +++++++++++++++++++++++++++++++++++= +++++- 2 files changed, 124 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetl= b.h index c601fe042832..1de1c519a84a 100644 --- a/arch/x86/include/asm/hugetlb.h +++ b/arch/x86/include/asm/hugetlb.h @@ -12,6 +12,14 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd) { return pmd_large(*pmd); } + +#define vmemmap_pmd_mkhuge vmemmap_pmd_mkhuge +static inline pmd_t vmemmap_pmd_mkhuge(struct page *page) +{ + pte_t entry =3D pfn_pte(page_to_pfn(page), PAGE_KERNEL_LARGE); + + return __pmd(pte_val(entry)); +} #endif =20 #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE) diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 1528b156920c..5c00826a98b3 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -118,6 +118,14 @@ static inline bool vmemmap_pmd_huge(pmd_t *pmd) } #endif =20 +#ifndef vmemmap_pmd_mkhuge +#define vmemmap_pmd_mkhuge vmemmap_pmd_mkhuge +static inline pmd_t vmemmap_pmd_mkhuge(struct page *page) +{ + return pmd_mkhuge(mk_pmd(page, PAGE_KERNEL)); +} +#endif + static bool hugetlb_free_vmemmap_disabled __initdata; =20 static int __init early_hugetlb_free_vmemmap_param(char *buf) @@ -386,6 +394,104 @@ static void __remap_huge_page_pte_vmemmap(struct pa= ge *reuse, pte_t *ptep, } } =20 +static void __replace_huge_page_pte_vmemmap(pte_t *ptep, unsigned long s= tart, + unsigned int nr, struct page *huge, + struct list_head *free_pages) +{ + unsigned long addr; + unsigned long end =3D start + (nr << PAGE_SHIFT); + pgprot_t pgprot =3D PAGE_KERNEL; + + for (addr =3D start; addr < end; addr +=3D PAGE_SIZE, ptep++) { + struct page *page; + pte_t old =3D *ptep; + pte_t entry; + + prepare_vmemmap_page(huge); + + entry =3D mk_pte(huge++, pgprot); + VM_WARN_ON(!pte_present(old)); + page =3D pte_page(old); + list_add(&page->lru, free_pages); + + set_pte_at(&init_mm, addr, ptep, entry); + } +} + +static void replace_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long star= t, + struct page *huge, + struct list_head *free_pages) +{ + unsigned long end =3D start + VMEMMAP_HPAGE_SIZE; + + flush_cache_vunmap(start, end); + __replace_huge_page_pte_vmemmap(pte_offset_kernel(pmd, start), start, + VMEMMAP_HPAGE_NR, huge, free_pages); + flush_tlb_kernel_range(start, end); +} + +static pte_t *merge_vmemmap_pte(pmd_t *pmdp, unsigned long addr) +{ + pte_t *pte; + struct page *page; + + pte =3D pte_offset_kernel(pmdp, addr); + page =3D pte_page(*pte); + set_pmd(pmdp, vmemmap_pmd_mkhuge(page)); + + return pte; +} + +static void merge_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start, + struct page *huge, + struct list_head *free_pages) +{ + replace_huge_page_pmd_vmemmap(pmd, start, huge, free_pages); + pte_free_kernel(&init_mm, merge_vmemmap_pte(pmd, start)); + flush_tlb_kernel_range(start, start + VMEMMAP_HPAGE_SIZE); +} + +static inline void dissolve_compound_page(struct page *page, unsigned in= t order) +{ + int i; + unsigned int nr_pages =3D 1 << order; + + for (i =3D 1; i < nr_pages; i++) + set_page_count(page + i, 1); +} + +static void merge_gigantic_page_vmemmap(struct hstate *h, struct page *h= ead, + pmd_t *pmd) +{ + LIST_HEAD(free_pages); + unsigned long addr =3D (unsigned long)head; + unsigned long end =3D addr + vmemmap_pages_size_per_hpage(h); + + for (; addr < end; addr +=3D VMEMMAP_HPAGE_SIZE) { + void *to; + struct page *page; + + page =3D alloc_pages(GFP_VMEMMAP_PAGE & ~__GFP_NOFAIL, + VMEMMAP_HPAGE_ORDER); + if (!page) + goto out; + + dissolve_compound_page(page, VMEMMAP_HPAGE_ORDER); + to =3D page_to_virt(page); + memcpy(to, (void *)addr, VMEMMAP_HPAGE_SIZE); + + /* + * Make sure that any data that writes to the + * @to is made visible to the physical page. + */ + flush_kernel_vmap_range(to, VMEMMAP_HPAGE_SIZE); + + merge_huge_page_pmd_vmemmap(pmd++, addr, page, &free_pages); + } +out: + free_vmemmap_page_list(&free_pages); +} + static inline void alloc_vmemmap_pages(struct hstate *h, struct list_hea= d *list) { int i; @@ -418,10 +524,18 @@ void alloc_huge_page_vmemmap(struct hstate *h, stru= ct page *head) __remap_huge_page_pte_vmemmap); if (!freed_vmemmap_hpage_dec(pmd_page(*pmd)) && pmd_split(pmd)) { /* - * Todo: - * Merge pte to huge pmd if it has ever been split. + * Merge pte to huge pmd if it has ever been split. Now only + * support gigantic page which's vmemmap pages size is an + * integer multiple of PMD_SIZE. This is the simplest case + * to handle. */ clear_pmd_split(pmd); + + if (IS_ALIGNED(vmemmap_pages_per_hpage(h), VMEMMAP_HPAGE_NR)) { + spin_unlock(ptl); + merge_gigantic_page_vmemmap(h, head, pmd); + return; + } } spin_unlock(ptl); } --=20 2.11.0