From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7A09218C1A for ; Wed, 3 Jan 2024 09:15:01 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="CeYPuBwx" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273300; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=YJJA5xKvoSxf1aIwLnbJbk4H1JjSjqj4D+JMLQtFT+4=; b=CeYPuBwxAtl9j2+v6pIK0Wz0WCD14dkeoviaOo1ld+BPzhWCeRklgHiqIH/eOuRP9M+8IZ j9WU8CqvEu0/Fy+5oalpUNqUvEufofMyXPJlLTQNEjjKIPLaVWRxKHms1iJvwTw+LvvUEB aZmWCkRhFrbLNXgYqBXIw276znxG33U= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-173-O3owD6t5PRKmlxLnlxARAQ-1; Wed, 03 Jan 2024 04:14:53 -0500 X-MC-Unique: O3owD6t5PRKmlxLnlxARAQ-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id E7E9B87DC02; Wed, 3 Jan 2024 09:14:51 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 40971492BE6; Wed, 3 Jan 2024 09:14:39 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 01/13] mm/Kconfig: CONFIG_PGTABLE_HAS_HUGE_LEAVES Date: Wed, 3 Jan 2024 17:14:11 +0800 Message-ID: <20240103091423.400294-2-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Introduce a config option that will be selected as long as huge leaves are involved in pgtable (thp or hugetlbfs). It would be useful to mark any code with this new config that can process either hugetlb or thp pages in any level that is higher than pte level. Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- mm/Kconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/mm/Kconfig b/mm/Kconfig index cb9d470f0bf7..9350ba180d52 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -904,6 +904,9 @@ config READ_ONLY_THP_FOR_FS =20 endif # TRANSPARENT_HUGEPAGE =20 +config PGTABLE_HAS_HUGE_LEAVES + def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE + # # UP and nommu archs use km based percpu allocator # --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 001C418E14 for ; Wed, 3 Jan 2024 09:15:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="eyLdagZo" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273308; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=UYdbUpgayprdP7mOXYmvw/zAFGJlyw1zyb2FaqhnNyk=; b=eyLdagZoQKSxjruraGbK7BkKzn/SQWlTSmyUFA7CDkEyv2lIGO/Xb5ZK6DFaoTBIrrHxvv T+kiWTmQPx5DtE4sfjfcA0mNqfz4VsB43nIms0WJ0b+evWSs+WcJUH+CByMhtZE/Ym1zFN XAOn2nX9u4ik6lYtdjBIOlz3evqZOdg= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-298-bCcbehl8OCy9I42YtKqcXA-1; Wed, 03 Jan 2024 04:15:05 -0500 X-MC-Unique: bCcbehl8OCy9I42YtKqcXA-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 20CC685CBA6; Wed, 3 Jan 2024 09:15:04 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id B69E3492BE6; Wed, 3 Jan 2024 09:14:52 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 02/13] mm/hugetlb: Declare hugetlbfs_pagecache_present() non-static Date: Wed, 3 Jan 2024 17:14:12 +0800 Message-ID: <20240103091423.400294-3-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu It will be used outside hugetlb.c soon. Signed-off-by: Peter Xu --- include/linux/hugetlb.h | 9 +++++++++ mm/hugetlb.c | 4 ++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index c1ee640d87b1..e8eddd51fc17 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -174,6 +174,9 @@ u32 hugetlb_fault_mutex_hash(struct address_space *mapp= ing, pgoff_t idx); =20 pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); +bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, + unsigned long address); =20 struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage); =20 @@ -1221,6 +1224,12 @@ static inline void hugetlb_register_node(struct node= *node) static inline void hugetlb_unregister_node(struct node *node) { } + +static inline bool hugetlbfs_pagecache_present( + struct hstate *h, struct vm_area_struct *vma, unsigned long address) +{ + return false; +} #endif /* CONFIG_HUGETLB_PAGE */ =20 static inline spinlock_t *huge_pte_lock(struct hstate *h, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0d262784ce60..bfb52bb8b943 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6017,8 +6017,8 @@ static vm_fault_t hugetlb_wp(struct mm_struct *mm, st= ruct vm_area_struct *vma, /* * Return whether there is a pagecache page to back given address within V= MA. */ -static bool hugetlbfs_pagecache_present(struct hstate *h, - struct vm_area_struct *vma, unsigned long address) +bool hugetlbfs_pagecache_present(struct hstate *h, + struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping =3D vma->vm_file->f_mapping; pgoff_t idx =3D linear_page_index(vma, address); --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8BE2318E14 for ; Wed, 3 Jan 2024 09:15:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="gviZcFvb" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273322; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=fpxdFtXHPoqbi8Omg7z7HSYBdI7g84IQc8JywSZrzBY=; b=gviZcFvbiOu45yHuUP4TduVm7bKPdn1p+imduE73g0o8qP1zX97X47DSXQe5a2xCqW7AFW Wgv89ibOLA6RaNKfMRcr30AcifTuV4gPH/IBHkc8aYWW3wptAe30a9DEHZXaRJDJA1Cqnu Qfpl1lrOLpqLbOceSyHbHUU9t9YMv5M= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-479-b9n2pak4N8WkCJuJM8p50w-1; Wed, 03 Jan 2024 04:15:17 -0500 X-MC-Unique: b9n2pak4N8WkCJuJM8p50w-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 806BE85A588; Wed, 3 Jan 2024 09:15:16 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 08899492BE6; Wed, 3 Jan 2024 09:15:04 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 03/13] mm: Provide generic pmd_thp_or_huge() Date: Wed, 3 Jan 2024 17:14:13 +0800 Message-ID: <20240103091423.400294-4-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu ARM defines pmd_thp_or_huge(), detecting either a THP or a huge PMD. It can be a helpful helper if we want to merge more THP and hugetlb code paths. Make it a generic default implementation, only exist when CONFIG_MMU. Arch can overwrite it by defining its own version. For example, ARM's pgtable-2level.h defines it to always return false. Keep the macro declared with all config, it should be optimized to a false anyway if !THP && !HUGETLB. Signed-off-by: Peter Xu --- include/linux/pgtable.h | 4 ++++ mm/gup.c | 3 +-- 2 files changed, 5 insertions(+), 2 deletions(-) diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 466cf477551a..2b42e95a4e3a 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1362,6 +1362,10 @@ static inline int pmd_write(pmd_t pmd) #endif /* pmd_write */ #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ =20 +#ifndef pmd_thp_or_huge +#define pmd_thp_or_huge(pmd) (pmd_huge(pmd) || pmd_trans_huge(pmd)) +#endif + #ifndef pud_write static inline int pud_write(pud_t pud) { diff --git a/mm/gup.c b/mm/gup.c index df83182ec72d..eebae70d2465 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -3004,8 +3004,7 @@ static int gup_pmd_range(pud_t *pudp, pud_t pud, unsi= gned long addr, unsigned lo if (!pmd_present(pmd)) return 0; =20 - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || - pmd_devmap(pmd))) { + if (unlikely(pmd_thp_or_huge(pmd) || pmd_devmap(pmd))) { /* See gup_pte_range() */ if (pmd_protnone(pmd)) return 0; --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 66D9B18EA7 for ; Wed, 3 Jan 2024 09:15:36 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="E1fM4pJc" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273335; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=t8fO7lBnC9by3RspplJseWzRvj3+WjzIcx8hEKl7Z7Y=; b=E1fM4pJcayThRK6FRpk4M6AoSQQY9YEn8zt79JrRs2PqbOA+GPvspCo8e0dFmfypG+8ALq lccQ/0a3kby1WpWmRJkSO1oE/leKsu3dLXWtYHgvpJmJk+Ljdyp2vD/8PjEGjHSLp5leW5 MFPL//oWJqTNK0KbGI6hC+7u7XaeFbs= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-138-l-IHSWebO-mu9VTGyPcb0Q-1; Wed, 03 Jan 2024 04:15:30 -0500 X-MC-Unique: l-IHSWebO-mu9VTGyPcb0Q-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id AFB6887DC01; Wed, 3 Jan 2024 09:15:28 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 4F290492BE6; Wed, 3 Jan 2024 09:15:16 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 04/13] mm: Make HPAGE_PXD_* macros even if !THP Date: Wed, 3 Jan 2024 17:14:14 +0800 Message-ID: <20240103091423.400294-5-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu These macros can be helpful when we plan to merge hugetlb code into generic code. Move them out and define them even if !THP. We actually already defined HPAGE_PMD_NR for other reasons even if !THP. Reorganize these macros. Reviewed-by: Christoph Hellwig Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- include/linux/huge_mm.h | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 5adb86af35fc..96bd4b5d027e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -64,9 +64,6 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; =20 -#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) -#define HPAGE_PMD_NR (1<; Wed, 3 Jan 2024 09:15:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="ao+pTYbt" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273347; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=GERLJEPmXyjsod6a3w+H+MRPlzFy0pZTus1RG/9onmU=; b=ao+pTYbtE0fbLyIB+2qmtoEWSaBaQ3sLSoSNR+BVhku9i1x+CH1qe7tsTGKfH8S2BwOxkR vEeQHl4FAbmRunxWm9rMQY0kUpvh6E+/a5IEpy+t4o/B+mZ8hDewsMuprGR0uGtKyi3OvR P8AlyS3ttMAfIeIlyb3ziq4c2FWY6y4= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-621-AvRlxFvDMHWmUtn2K9LV5Q-1; Wed, 03 Jan 2024 04:15:42 -0500 X-MC-Unique: AvRlxFvDMHWmUtn2K9LV5Q-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 1957D29AA38F; Wed, 3 Jan 2024 09:15:41 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 7C3DE492BE6; Wed, 3 Jan 2024 09:15:29 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 05/13] mm: Introduce vma_pgtable_walk_{begin|end}() Date: Wed, 3 Jan 2024 17:14:15 +0800 Message-ID: <20240103091423.400294-6-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Introduce per-vma begin()/end() helpers for pgtable walks. This is a preparation work to merge hugetlb pgtable walkers with generic mm. The helpers need to be called before and after a pgtable walk, will start to be needed if the pgtable walker code supports hugetlb pages. It's a hook point for any type of VMA, but for now only hugetlb uses it to stablize the pgtable pages from getting away (due to possible pmd unsharing). Reviewed-by: Christoph Hellwig Reviewed-by: Muchun Song Signed-off-by: Peter Xu --- include/linux/mm.h | 3 +++ mm/memory.c | 12 ++++++++++++ 2 files changed, 15 insertions(+) diff --git a/include/linux/mm.h b/include/linux/mm.h index 896c0079f64f..6836da00671a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -4181,4 +4181,7 @@ static inline bool pfn_is_unaccepted_memory(unsigned = long pfn) return range_contains_unaccepted_memory(paddr, paddr + PAGE_SIZE); } =20 +void vma_pgtable_walk_begin(struct vm_area_struct *vma); +void vma_pgtable_walk_end(struct vm_area_struct *vma); + #endif /* _LINUX_MM_H */ diff --git a/mm/memory.c b/mm/memory.c index 7e1f4849463a..89f3caac2ec8 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -6279,3 +6279,15 @@ void ptlock_free(struct ptdesc *ptdesc) kmem_cache_free(page_ptl_cachep, ptdesc->ptl); } #endif + +void vma_pgtable_walk_begin(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_lock_read(vma); +} + +void vma_pgtable_walk_end(struct vm_area_struct *vma) +{ + if (is_vm_hugetlb_page(vma)) + hugetlb_vma_unlock_read(vma); +} --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7D61D19460 for ; Wed, 3 Jan 2024 09:15:58 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="W2nDFnAo" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273357; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=G2mMJAnaoVdNju5RvSwq+KPjZVLCTkTT7F8NTqIl1do=; b=W2nDFnAo2k/r2mcW39A/X1smFLZBFebFY6dVdlmkG+cpBa/G5kzVVIe0fdI9hvcNc5oWNf DelYLVoXhZnROpgS8bGkAsCTxEYKxi08nEdhGsDRZt1vA3QQqcJZbXG+eKrIZHI5cmFBlA Ei37M+7CX10S+m/zLlaHsccumopGPpk= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-597-sJHnyUgTOIGCIKVC1MWAaQ-1; Wed, 03 Jan 2024 04:15:53 -0500 X-MC-Unique: sJHnyUgTOIGCIKVC1MWAaQ-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 731831C0512D; Wed, 3 Jan 2024 09:15:52 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id DBCD9492BE6; Wed, 3 Jan 2024 09:15:41 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 06/13] mm/gup: Drop folio_fast_pin_allowed() in hugepd processing Date: Wed, 3 Jan 2024 17:14:16 +0800 Message-ID: <20240103091423.400294-7-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Hugepd format for GUP is only used in PowerPC with hugetlbfs. There are some kernel usage of hugepd (can refer to hugepd_populate_kernel() for PPC_8XX), however those pages are not candidates for GUP. Commit a6e79df92e4a ("mm/gup: disallow FOLL_LONGTERM GUP-fast writing to file-backed mappings") added a check to fail gup-fast if there's potential risk of violating GUP over writeback file systems. That should never apply to hugepd. Considering that hugepd is an old format (and even software-only), there's no plan to extend hugepd into other file typed memories that is prone to the same issue. Drop that check, not only because it'll never be true for hugepd per any known plan, but also it paves way for reusing the function outside fast-gup. To make sure we'll still remember this issue just in case hugepd will be extended to support non-hugetlbfs memories, add a rich comment above gup_huge_pd(), explaining the issue with proper references. Cc: Christoph Hellwig Cc: Lorenzo Stoakes Cc: Michael Ellerman Cc: linuxppc-dev@lists.ozlabs.org Signed-off-by: Peter Xu --- mm/gup.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index eebae70d2465..fa93e14b7fca 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2820,11 +2820,6 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz= , unsigned long addr, return 0; } =20 - if (!folio_fast_pin_allowed(folio, flags)) { - gup_put_folio(folio, refs, flags); - return 0; - } - if (!pte_write(pte) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; @@ -2835,6 +2830,14 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz= , unsigned long addr, return 1; } =20 +/* + * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file + * systems on Power, which does not have issue with folio writeback against + * GUP updates. When hugepd will be extended to support non-hugetlbfs or + * even anonymous memory, we need to do extra check as what we do with most + * of the other folios. See writable_file_mapping_allowed() and + * folio_fast_pin_allowed() for more information. + */ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 02419199A4 for ; Wed, 3 Jan 2024 09:16:11 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="c21Pn/6/" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273370; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=w96HtEkzdknb+h0JjsHCRRCM9jOy1Kg+MIEx5UNvA1Y=; b=c21Pn/6/nCBSDLyAT3izS9wWdvVfGGVOM5wGNqk95M0KZWcjtTVKbYWRSwmsvWj/j064v4 msXf4b4nv/rn8+z4GJbitHGjz8vYdKnELCNVBbUiuTn4RvUc8BXb2uz6k10LN1vdNZdKWO xFSEnTu2zlVET6OnmQsugQB7+sAqCFA= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-277--A0wl26XO_yPNePIDNUfuA-1; Wed, 03 Jan 2024 04:16:06 -0500 X-MC-Unique: -A0wl26XO_yPNePIDNUfuA-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id B7A993806714; Wed, 3 Jan 2024 09:16:04 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 29D1F492BE6; Wed, 3 Jan 2024 09:15:52 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 07/13] mm/gup: Refactor record_subpages() to find 1st small page Date: Wed, 3 Jan 2024 17:14:17 +0800 Message-ID: <20240103091423.400294-8-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu All the fast-gup functions take a tail page to operate, always need to do page mask calculations before feeding that into record_subpages(). Merge that logic into record_subpages(), so that it will do the nth_page() calculation. Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- mm/gup.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index fa93e14b7fca..3813aad79c4a 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -2767,13 +2767,16 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *= pudp, unsigned long addr, } #endif =20 -static int record_subpages(struct page *page, unsigned long addr, - unsigned long end, struct page **pages) +static int record_subpages(struct page *page, unsigned long sz, + unsigned long addr, unsigned long end, + struct page **pages) { + struct page *start_page; int nr; =20 + start_page =3D nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); for (nr =3D 0; addr !=3D end; nr++, addr +=3D PAGE_SIZE) - pages[nr] =3D nth_page(page, nr); + pages[nr] =3D nth_page(start_page, nr); =20 return nr; } @@ -2808,8 +2811,8 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz,= unsigned long addr, /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); =20 - page =3D nth_page(pte_page(pte), (addr & (sz - 1)) >> PAGE_SHIFT); - refs =3D record_subpages(page, addr, end, pages + *nr); + page =3D pte_page(pte); + refs =3D record_subpages(page, sz, addr, end, pages + *nr); =20 folio =3D try_grab_folio(page, refs, flags); if (!folio) @@ -2882,8 +2885,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsi= gned long addr, pages, nr); } =20 - page =3D nth_page(pmd_page(orig), (addr & ~PMD_MASK) >> PAGE_SHIFT); - refs =3D record_subpages(page, addr, end, pages + *nr); + page =3D pmd_page(orig); + refs =3D record_subpages(page, PMD_SIZE, addr, end, pages + *nr); =20 folio =3D try_grab_folio(page, refs, flags); if (!folio) @@ -2926,8 +2929,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsi= gned long addr, pages, nr); } =20 - page =3D nth_page(pud_page(orig), (addr & ~PUD_MASK) >> PAGE_SHIFT); - refs =3D record_subpages(page, addr, end, pages + *nr); + page =3D pud_page(orig); + refs =3D record_subpages(page, PUD_SIZE, addr, end, pages + *nr); =20 folio =3D try_grab_folio(page, refs, flags); if (!folio) @@ -2966,8 +2969,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsi= gned long addr, =20 BUILD_BUG_ON(pgd_devmap(orig)); =20 - page =3D nth_page(pgd_page(orig), (addr & ~PGDIR_MASK) >> PAGE_SHIFT); - refs =3D record_subpages(page, addr, end, pages + *nr); + page =3D pgd_page(orig); + refs =3D record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); =20 folio =3D try_grab_folio(page, refs, flags); if (!folio) --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E4F6F199A4 for ; Wed, 3 Jan 2024 09:16:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="SB6vapr0" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273381; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=e2/9/uEWavAhcbGvkqENWO1xIuQmr8G4qpstfk2UpBk=; b=SB6vapr06Lb6yI0WaNz1St8AEfA19VPHQFdHLwyTNh9fQdlFzbkPAqvZPIIZ0oAWtqjOTd MpodwMLBOZ8SzVCe4SHZMUj23JYff4K2HD9IvmPT65l/MnpdgYXkomYJ0c7+HDstBce8Zo Hn6kwWZmITn/00kubCwMODHxJXtI0aU= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-562-bfNmJltGNpCYZPt_-QXM8w-1; Wed, 03 Jan 2024 04:16:16 -0500 X-MC-Unique: bfNmJltGNpCYZPt_-QXM8w-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 633D085CBA5; Wed, 3 Jan 2024 09:16:15 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 6E9FD492BE6; Wed, 3 Jan 2024 09:16:05 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 08/13] mm/gup: Handle hugetlb for no_page_table() Date: Wed, 3 Jan 2024 17:14:18 +0800 Message-ID: <20240103091423.400294-9-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu no_page_table() is not yet used for hugetlb code paths. Make it prepared. The major difference here is hugetlb will return -EFAULT as long as page cache does not exist, even if VM_SHARED. See hugetlb_follow_page_mask(). Pass "address" into no_page_table() too, as hugetlb will need it. Reviewed-by: Christoph Hellwig Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- mm/gup.c | 44 ++++++++++++++++++++++++++------------------ 1 file changed, 26 insertions(+), 18 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 3813aad79c4a..b8a80e2bfe08 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -501,19 +501,27 @@ static inline void mm_set_has_pinned_flag(unsigned lo= ng *mm_flags) =20 #ifdef CONFIG_MMU static struct page *no_page_table(struct vm_area_struct *vma, - unsigned int flags) + unsigned int flags, unsigned long address) { + if (!(flags & FOLL_DUMP)) + return NULL; + /* - * When core dumping an enormous anonymous area that nobody - * has touched so far, we don't want to allocate unnecessary pages or + * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ - if ((flags & FOLL_DUMP) && - (vma_is_anonymous(vma) || !vma->vm_ops->fault)) + if (is_vm_hugetlb_page(vma)) { + struct hstate *h =3D hstate_vma(vma); + + if (!hugetlbfs_pagecache_present(h, vma, address)) + return ERR_PTR(-EFAULT); + } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); + } + return NULL; } =20 @@ -593,7 +601,7 @@ static struct page *follow_page_pte(struct vm_area_stru= ct *vma, =20 ptep =3D pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); pte =3D ptep_get(ptep); if (!pte_present(pte)) goto no_page; @@ -685,7 +693,7 @@ static struct page *follow_page_pte(struct vm_area_stru= ct *vma, pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } =20 static struct page *follow_pmd_mask(struct vm_area_struct *vma, @@ -701,27 +709,27 @@ static struct page *follow_pmd_mask(struct vm_area_st= ruct *vma, pmd =3D pmd_offset(pudp, address); pmdval =3D pmdp_get_lockless(pmd); if (pmd_none(pmdval)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); if (pmd_devmap(pmdval)) { ptl =3D pmd_lock(mm, pmd); page =3D follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } if (likely(!pmd_trans_huge(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); =20 if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); =20 ptl =3D pmd_lock(mm, pmd); if (unlikely(!pmd_present(*pmd))) { spin_unlock(ptl); - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); @@ -752,17 +760,17 @@ static struct page *follow_pud_mask(struct vm_area_st= ruct *vma, =20 pud =3D pud_offset(p4dp, address); if (pud_none(*pud)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); if (pud_devmap(*pud)) { ptl =3D pud_lock(mm, pud); page =3D follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); } if (unlikely(pud_bad(*pud))) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); =20 return follow_pmd_mask(vma, address, pud, flags, ctx); } @@ -776,10 +784,10 @@ static struct page *follow_p4d_mask(struct vm_area_st= ruct *vma, =20 p4d =3D p4d_offset(pgdp, address); if (p4d_none(*p4d)) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); BUILD_BUG_ON(p4d_huge(*p4d)); if (unlikely(p4d_bad(*p4d))) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); =20 return follow_pud_mask(vma, address, p4d, flags, ctx); } @@ -829,7 +837,7 @@ static struct page *follow_page_mask(struct vm_area_str= uct *vma, pgd =3D pgd_offset(mm, address); =20 if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return no_page_table(vma, flags); + return no_page_table(vma, flags, address); =20 return follow_p4d_mask(vma, address, pgd, flags, ctx); } --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D180819BCC for ; Wed, 3 Jan 2024 09:16:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="du7VdgO4" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273392; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=dkbsR+hObgkKanb0hWK1+Xo39A1xL8364xJAXCv3uQU=; b=du7VdgO4cxnkmxRWxbfQ1qq5y/m7KFtTHooajSvIdqWs4PL53aO4HuDgOJnsj/wXWQYfEc iPTHK9VOOxXN1ugLPw0RtIHGNSRvnbxnfij7aanlWwtyi+gU6britB/c/FD2UWVPmpDJym mXFRAfMTYQuE3lEg/2LVbTrSxRRiYhE= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-611-7CEiuF6PMvSSKuTScRXfJw-1; Wed, 03 Jan 2024 04:16:28 -0500 X-MC-Unique: 7CEiuF6PMvSSKuTScRXfJw-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 8EF2A185A780; Wed, 3 Jan 2024 09:16:27 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 33861492BE6; Wed, 3 Jan 2024 09:16:15 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 09/13] mm/gup: Cache *pudp in follow_pud_mask() Date: Wed, 3 Jan 2024 17:14:19 +0800 Message-ID: <20240103091423.400294-10-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Introduce "pud_t pud" in the function, so the code won't dereference *pudp multiple time. Not only because that looks less straightforward, but also because if the dereference really happened, it's not clear whether there can be race to see different *pudp values if it's being modified at the same time. Acked-by: James Houghton Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- mm/gup.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index b8a80e2bfe08..63845b3ec44f 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -753,26 +753,27 @@ static struct page *follow_pud_mask(struct vm_area_st= ruct *vma, unsigned int flags, struct follow_page_context *ctx) { - pud_t *pud; + pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm =3D vma->vm_mm; =20 - pud =3D pud_offset(p4dp, address); - if (pud_none(*pud)) + pudp =3D pud_offset(p4dp, address); + pud =3D READ_ONCE(*pudp); + if (pud_none(pud)) return no_page_table(vma, flags, address); - if (pud_devmap(*pud)) { - ptl =3D pud_lock(mm, pud); - page =3D follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); + if (pud_devmap(pud)) { + ptl =3D pud_lock(mm, pudp); + page =3D follow_devmap_pud(vma, address, pudp, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } - if (unlikely(pud_bad(*pud))) + if (unlikely(pud_bad(pud))) return no_page_table(vma, flags, address); =20 - return follow_pmd_mask(vma, address, pud, flags, ctx); + return follow_pmd_mask(vma, address, pudp, flags, ctx); } =20 static struct page *follow_p4d_mask(struct vm_area_struct *vma, --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 194711A582 for ; Wed, 3 Jan 2024 09:16:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="ilsoYJpy" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273406; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=QzOVwYUc2Smk4Qva0KIv5/d0xcVhZ//s5msSCcZkJA4=; b=ilsoYJpyCpGaGej/HBuTvgo0tbU3UdYNCBt7YatgrR5sKLsrW5qcugxQQaCR1mG7be6VCc 3vKPTiJo7mUCnToGgvgSVX2jNQiykcYt3iCOZiGQLKUX5xa3ht7PmZvdxWk8cvn39T7LuZ Zf+2urV6K0A7yEHE4kUsz0+IDh5QmzA= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-117-3JInRm3gNpSknDs2l1d3Mg-1; Wed, 03 Jan 2024 04:16:40 -0500 X-MC-Unique: 3JInRm3gNpSknDs2l1d3Mg-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id BD778101A58E; Wed, 3 Jan 2024 09:16:39 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 61C82492BFA; Wed, 3 Jan 2024 09:16:27 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 10/13] mm/gup: Handle huge pud for follow_pud_mask() Date: Wed, 3 Jan 2024 17:14:20 +0800 Message-ID: <20240103091423.400294-11-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Teach follow_pud_mask() to be able to handle normal PUD pages like hugetlb. Rename follow_devmap_pud() to follow_huge_pud() so that it can process either huge devmap or hugetlb. Move it out of TRANSPARENT_HUGEPAGE_PUD and and huge_memory.c (which relies on CONFIG_THP). In the new follow_huge_pud(), taking care of possible CoR for hugetlb if necessary. touch_pud() needs to be moved out of huge_memory.c to be accessable from gup.c even if !THP. Since at it, optimize the non-present check by adding a pud_present() early check before taking the pgtable lock, failing the follow_page() early if PUD is not present: that is required by both devmap or hugetlb. Use pud_huge() to also cover the pud_devmap() case. One more trivial thing to mention is, introduce "pud_t pud" in the code paths along the way, so the code doesn't dereference *pudp multiple time. Not only because that looks less straightforward, but also because if the dereference really happened, it's not clear whether there can be race to see different *pudp values when it's being modified at the same time. Setting ctx->page_mask properly for a PUD entry. As a side effect, this patch should also be able to optimize devmap GUP on PUD to be able to jump over the whole PUD range, but not yet verified. Hugetlb already can do so prior to this patch. Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- include/linux/huge_mm.h | 8 ----- mm/gup.c | 70 +++++++++++++++++++++++++++++++++++++++-- mm/huge_memory.c | 47 ++------------------------- mm/internal.h | 2 ++ 4 files changed, 71 insertions(+), 56 deletions(-) diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 96bd4b5d027e..3b73d20d537e 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -345,8 +345,6 @@ static inline bool folio_test_pmd_mappable(struct folio= *folio) =20 struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long a= ddr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long a= ddr, - pud_t *pud, int flags, struct dev_pagemap **pgmap); =20 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf); =20 @@ -502,12 +500,6 @@ static inline struct page *follow_devmap_pmd(struct vm= _area_struct *vma, return NULL; } =20 -static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) -{ - return NULL; -} - static inline bool thp_migration_supported(void) { return false; diff --git a/mm/gup.c b/mm/gup.c index 63845b3ec44f..760406180222 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -525,6 +525,70 @@ static struct page *no_page_table(struct vm_area_struc= t *vma, return NULL; } =20 +#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES +static struct page *follow_huge_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, + int flags, struct follow_page_context *ctx) +{ + struct mm_struct *mm =3D vma->vm_mm; + struct page *page; + pud_t pud =3D *pudp; + unsigned long pfn =3D pud_pfn(pud); + int ret; + + assert_spin_locked(pud_lockptr(mm, pudp)); + + if ((flags & FOLL_WRITE) && !pud_write(pud)) + return NULL; + + if (!pud_present(pud)) + return NULL; + + pfn +=3D (addr & ~PUD_MASK) >> PAGE_SHIFT; + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + if (pud_devmap(pud)) { + /* + * device mapped pages can only be returned if the caller + * will manage the page reference count. + * + * At least one of FOLL_GET | FOLL_PIN must be set, so + * assert that here: + */ + if (!(flags & (FOLL_GET | FOLL_PIN))) + return ERR_PTR(-EEXIST); + + if (flags & FOLL_TOUCH) + touch_pud(vma, addr, pudp, flags & FOLL_WRITE); + + ctx->pgmap =3D get_dev_pagemap(pfn, ctx->pgmap); + if (!ctx->pgmap) + return ERR_PTR(-EFAULT); + } +#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ + page =3D pfn_to_page(pfn); + + if (!pud_devmap(pud) && !pud_write(pud) && + gup_must_unshare(vma, flags, page)) + return ERR_PTR(-EMLINK); + + ret =3D try_grab_page(page, flags); + if (ret) + page =3D ERR_PTR(ret); + else + ctx->page_mask =3D HPAGE_PUD_NR - 1; + + return page; +} +#else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ +static struct page *follow_huge_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp, + int flags, struct follow_page_context *ctx) +{ + return NULL; +} +#endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ + static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long addres= s, pte_t *pte, unsigned int flags) { @@ -760,11 +824,11 @@ static struct page *follow_pud_mask(struct vm_area_st= ruct *vma, =20 pudp =3D pud_offset(p4dp, address); pud =3D READ_ONCE(*pudp); - if (pud_none(pud)) + if (pud_none(pud) || !pud_present(pud)) return no_page_table(vma, flags, address); - if (pud_devmap(pud)) { + if (pud_huge(pud)) { ptl =3D pud_lock(mm, pudp); - page =3D follow_devmap_pud(vma, address, pudp, flags, &ctx->pgmap); + page =3D follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 94ef5c02b459..9993d2b18809 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1373,8 +1373,8 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm= _struct *src_mm, } =20 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD -static void touch_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, bool write) +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write) { pud_t _pud; =20 @@ -1386,49 +1386,6 @@ static void touch_pud(struct vm_area_struct *vma, un= signed long addr, update_mmu_cache_pud(vma, addr, pud); } =20 -struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long a= ddr, - pud_t *pud, int flags, struct dev_pagemap **pgmap) -{ - unsigned long pfn =3D pud_pfn(*pud); - struct mm_struct *mm =3D vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pud_lockptr(mm, pud)); - - if (flags & FOLL_WRITE && !pud_write(*pud)) - return NULL; - - if (pud_present(*pud) && pud_devmap(*pud)) - /* pass */; - else - return NULL; - - if (flags & FOLL_TOUCH) - touch_pud(vma, addr, pud, flags & FOLL_WRITE); - - /* - * device mapped pages can only be returned if the - * caller will manage the page reference count. - * - * At least one of FOLL_GET | FOLL_PIN must be set, so assert that here: - */ - if (!(flags & (FOLL_GET | FOLL_PIN))) - return ERR_PTR(-EEXIST); - - pfn +=3D (addr & ~PUD_MASK) >> PAGE_SHIFT; - *pgmap =3D get_dev_pagemap(pfn, *pgmap); - if (!*pgmap) - return ERR_PTR(-EFAULT); - page =3D pfn_to_page(pfn); - - ret =3D try_grab_page(page, flags); - if (ret) - page =3D ERR_PTR(ret); - - return page; -} - int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma) diff --git a/mm/internal.h b/mm/internal.h index f309a010d50f..5821b7a14b62 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1007,6 +1007,8 @@ int __must_check try_grab_page(struct page *page, uns= igned int flags); /* * mm/huge_memory.c */ +void touch_pud(struct vm_area_struct *vma, unsigned long addr, + pud_t *pud, bool write); struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6BC421A5A5 for ; Wed, 3 Jan 2024 09:17:02 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="ACjtqW9Y" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273421; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=08fh3W0fLOF7uiwfuql/fhnzNEx5JUzK5pzA1eiVeOg=; b=ACjtqW9YckIMAjPEMM/bmXQ3T+XjHPdkAD4K/aKcTRZVewDxXCyAS985CBNBIrJz5QgiwC YM2LnOES6wtXrjkfXsSMBELPsQyx2XpHcbTscGA0LXyQ8wsxXgUwuZpjJ9TNpF7mjvNUeT R4h9+lAEsnkCRxRegoPty9jJmjnI4vQ= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-325-_WTwnjDAMc2GdAFTOXr2IA-1; Wed, 03 Jan 2024 04:16:53 -0500 X-MC-Unique: _WTwnjDAMc2GdAFTOXr2IA-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id D792C29AA38D; Wed, 3 Jan 2024 09:16:52 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 8CE8D492BF0; Wed, 3 Jan 2024 09:16:40 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 11/13] mm/gup: Handle huge pmd for follow_pmd_mask() Date: Wed, 3 Jan 2024 17:14:21 +0800 Message-ID: <20240103091423.400294-12-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Replace pmd_trans_huge() with pmd_thp_or_huge() to also cover pmd_huge() as long as enabled. FOLL_TOUCH and FOLL_SPLIT_PMD only apply to THP, not yet huge. Since now follow_trans_huge_pmd() can process hugetlb pages, renaming it into follow_huge_pmd() to match what it does. Move it into gup.c so not depend on CONFIG_THP. When at it, move the ctx->page_mask setup into follow_huge_pmd(), only set it when the page is valid. It was not a bug to set it before even if GUP failed (page=3D=3DNULL), because follow_page_mask() callers always ignores page_mask if so. But doing so makes the code cleaner. Signed-off-by: Peter Xu Reviewed-by: Jason Gunthorpe --- mm/gup.c | 107 ++++++++++++++++++++++++++++++++++++++++++++--- mm/huge_memory.c | 86 +------------------------------------ mm/internal.h | 5 +-- 3 files changed, 105 insertions(+), 93 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index 760406180222..d96429b6fc55 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -580,6 +580,93 @@ static struct page *follow_huge_pud(struct vm_area_str= uct *vma, =20 return page; } + +/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ +static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, + struct vm_area_struct *vma, + unsigned int flags) +{ + /* If the pmd is writable, we can write to the page. */ + if (pmd_write(pmd)) + return true; + + /* Maybe FOLL_FORCE is set to override it? */ + if (!(flags & FOLL_FORCE)) + return false; + + /* But FOLL_FORCE has no effect on shared mappings */ + if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) + return false; + + /* ... or read-only private ones */ + if (!(vma->vm_flags & VM_MAYWRITE)) + return false; + + /* ... or already writable ones that just need to take a write fault */ + if (vma->vm_flags & VM_WRITE) + return false; + + /* + * See can_change_pte_writable(): we broke COW and could map the page + * writable if we have an exclusive anonymous page ... + */ + if (!page || !PageAnon(page) || !PageAnonExclusive(page)) + return false; + + /* ... and a write-fault isn't required for other reasons. */ + if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) + return false; + return !userfaultfd_huge_pmd_wp(vma, pmd); +} + +static struct page *follow_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags, + struct follow_page_context *ctx) +{ + struct mm_struct *mm =3D vma->vm_mm; + pmd_t pmdval =3D *pmd; + struct page *page; + int ret; + + assert_spin_locked(pmd_lockptr(mm, pmd)); + + page =3D pmd_page(pmdval); + VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); + + if ((flags & FOLL_WRITE) && + !can_follow_write_pmd(pmdval, page, vma, flags)) + return NULL; + + /* Avoid dumping huge zero page */ + if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) + return ERR_PTR(-EFAULT); + + if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) + return NULL; + + if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) + return ERR_PTR(-EMLINK); + + VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && + !PageAnonExclusive(page), page); + + ret =3D try_grab_page(page, flags); + if (ret) + return ERR_PTR(ret); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) + touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + + page +=3D (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; + ctx->page_mask =3D HPAGE_PMD_NR - 1; + VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); + + return page; +} + #else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, @@ -587,6 +674,14 @@ static struct page *follow_huge_pud(struct vm_area_str= uct *vma, { return NULL; } + +static struct page *follow_huge_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd, + unsigned int flags, + struct follow_page_context *ctx) +{ + return NULL; +} #endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ =20 static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long addres= s, @@ -784,31 +879,31 @@ static struct page *follow_pmd_mask(struct vm_area_st= ruct *vma, return page; return no_page_table(vma, flags, address); } - if (likely(!pmd_trans_huge(pmdval))) + if (likely(!pmd_thp_or_huge(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); =20 if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address); =20 ptl =3D pmd_lock(mm, pmd); - if (unlikely(!pmd_present(*pmd))) { + pmdval =3D *pmd; + if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); return no_page_table(vma, flags, address); } - if (unlikely(!pmd_trans_huge(*pmd))) { + if (unlikely(!pmd_thp_or_huge(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } - if (flags & FOLL_SPLIT_PMD) { + if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } - page =3D follow_trans_huge_pmd(vma, address, pmd, flags); + page =3D follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); - ctx->page_mask =3D HPAGE_PMD_NR - 1; return page; } =20 diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9993d2b18809..317cb445c442 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1216,8 +1216,8 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, p= fn_t pfn, bool write) EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ =20 -static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, bool write) +void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write) { pmd_t _pmd; =20 @@ -1572,88 +1572,6 @@ static inline bool can_change_pmd_writable(struct vm= _area_struct *vma, return pmd_dirty(pmd); } =20 -/* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ -static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, - struct vm_area_struct *vma, - unsigned int flags) -{ - /* If the pmd is writable, we can write to the page. */ - if (pmd_write(pmd)) - return true; - - /* Maybe FOLL_FORCE is set to override it? */ - if (!(flags & FOLL_FORCE)) - return false; - - /* But FOLL_FORCE has no effect on shared mappings */ - if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) - return false; - - /* ... or read-only private ones */ - if (!(vma->vm_flags & VM_MAYWRITE)) - return false; - - /* ... or already writable ones that just need to take a write fault */ - if (vma->vm_flags & VM_WRITE) - return false; - - /* - * See can_change_pte_writable(): we broke COW and could map the page - * writable if we have an exclusive anonymous page ... - */ - if (!page || !PageAnon(page) || !PageAnonExclusive(page)) - return false; - - /* ... and a write-fault isn't required for other reasons. */ - if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) - return false; - return !userfaultfd_huge_pmd_wp(vma, pmd); -} - -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, - pmd_t *pmd, - unsigned int flags) -{ - struct mm_struct *mm =3D vma->vm_mm; - struct page *page; - int ret; - - assert_spin_locked(pmd_lockptr(mm, pmd)); - - page =3D pmd_page(*pmd); - VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page); - - if ((flags & FOLL_WRITE) && - !can_follow_write_pmd(*pmd, page, vma, flags)) - return NULL; - - /* Avoid dumping huge zero page */ - if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd)) - return ERR_PTR(-EFAULT); - - if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) - return NULL; - - if (!pmd_write(*pmd) && gup_must_unshare(vma, flags, page)) - return ERR_PTR(-EMLINK); - - VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && - !PageAnonExclusive(page), page); - - ret =3D try_grab_page(page, flags); - if (ret) - return ERR_PTR(ret); - - if (flags & FOLL_TOUCH) - touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); - - page +=3D (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; - VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page); - - return page; -} - /* NUMA hinting page fault entry point for trans huge pmds */ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { diff --git a/mm/internal.h b/mm/internal.h index 5821b7a14b62..99994b41a220 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -1009,9 +1009,8 @@ int __must_check try_grab_page(struct page *page, uns= igned int flags); */ void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write); -struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, - unsigned int flags); +void touch_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, bool write); =20 /* * mm/mmap.c --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D0D831A702 for ; Wed, 3 Jan 2024 09:17:12 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="GexmSZNN" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273431; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=8AcO9+0z+3vykJ/cwcx3VMGKR3J7wY17yFKVVVWLkvk=; b=GexmSZNNJ+AN/03lup4TVOWR6MGX8OBzgGo2lna7SnScjul1SDiyYoN7Z1sbVPJM3Htoai ewIaHvcsR4tfKzVWme5b4ZZQjJPlTr3S9+DwzLWJ2NbzUHNDBT8uSxwlLco7DOmiKlBziO DpL/KJe0egmZn0VQn9YEh4/lYMDYX4g= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-628-whtNjjhbNK66iMLnbmrOvA-1; Wed, 03 Jan 2024 04:17:06 -0500 X-MC-Unique: whtNjjhbNK66iMLnbmrOvA-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 744CD3813BC1; Wed, 3 Jan 2024 09:17:05 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id A7283492BF0; Wed, 3 Jan 2024 09:16:53 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 12/13] mm/gup: Handle hugepd for follow_page() Date: Wed, 3 Jan 2024 17:14:22 +0800 Message-ID: <20240103091423.400294-13-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Hugepd is only used in PowerPC so far on 4K page size kernels where hash mmu is used. follow_page_mask() used to leverage hugetlb APIs to access hugepd entries. Teach follow_page_mask() itself on hugepd. With previous refactors on fast-gup gup_huge_pd(), most of the code can be easily leveraged. There's something not needed for follow page, for example, gup_hugepte() tries to detect pgtable entry change which will never happen with slow gup (which has the pgtable lock held), but that's not a problem to check. Since follow_page() always only fetch one page, set the end to "address + PAGE_SIZE" should suffice. We will still do the pgtable walk once for each hugetlb page by setting ctx->page_mask properly. One thing worth mentioning is that some level of pgtable's _bad() helper will report is_hugepd() entries as TRUE on Power8 hash MMUs. I think it at least applies to PUD on Power8 with 4K pgsize. It means feeding a hugepd entry to pud_bad() will report a false positive. Let's leave that for now because it can be arch-specific where I am a bit declined to touch. In this patch it's not a problem as long as hugepd is detected before any bad pgtable entries. Signed-off-by: Peter Xu --- mm/gup.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 69 insertions(+), 9 deletions(-) diff --git a/mm/gup.c b/mm/gup.c index d96429b6fc55..245214b64108 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -30,6 +30,11 @@ struct follow_page_context { unsigned int page_mask; }; =20 +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hug= epd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx); + static inline void sanity_check_pinned_pages(struct page **pages, unsigned long npages) { @@ -871,6 +876,9 @@ static struct page *follow_pmd_mask(struct vm_area_stru= ct *vma, return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval))))) + return follow_hugepd(vma, __hugepd(pmd_val(pmdval)), + address, PMD_SHIFT, flags, ctx); if (pmd_devmap(pmdval)) { ptl =3D pmd_lock(mm, pmd); page =3D follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); @@ -921,6 +929,9 @@ static struct page *follow_pud_mask(struct vm_area_stru= ct *vma, pud =3D READ_ONCE(*pudp); if (pud_none(pud) || !pud_present(pud)) return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) + return follow_hugepd(vma, __hugepd(pud_val(pud)), + address, PUD_SHIFT, flags, ctx); if (pud_huge(pud)) { ptl =3D pud_lock(mm, pudp); page =3D follow_huge_pud(vma, address, pudp, flags, ctx); @@ -940,13 +951,17 @@ static struct page *follow_p4d_mask(struct vm_area_st= ruct *vma, unsigned int flags, struct follow_page_context *ctx) { - p4d_t *p4d; + p4d_t *p4d, p4dval; =20 p4d =3D p4d_offset(pgdp, address); - if (p4d_none(*p4d)) - return no_page_table(vma, flags, address); - BUILD_BUG_ON(p4d_huge(*p4d)); - if (unlikely(p4d_bad(*p4d))) + p4dval =3D *p4d; + BUILD_BUG_ON(p4d_huge(p4dval)); + + if (unlikely(is_hugepd(__hugepd(p4d_val(p4dval))))) + return follow_hugepd(vma, __hugepd(p4d_val(p4dval)), + address, P4D_SHIFT, flags, ctx); + + if (p4d_none(p4dval) || unlikely(p4d_bad(p4dval))) return no_page_table(vma, flags, address); =20 return follow_pud_mask(vma, address, p4d, flags, ctx); @@ -980,7 +995,7 @@ static struct page *follow_page_mask(struct vm_area_str= uct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { - pgd_t *pgd; + pgd_t *pgd, pgdval; struct mm_struct *mm =3D vma->vm_mm; =20 ctx->page_mask =3D 0; @@ -995,11 +1010,17 @@ static struct page *follow_page_mask(struct vm_area_= struct *vma, &ctx->page_mask); =20 pgd =3D pgd_offset(mm, address); + pgdval =3D *pgd; =20 - if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) - return no_page_table(vma, flags, address); + if (unlikely(is_hugepd(__hugepd(pgd_val(pgdval))))) + page =3D follow_hugepd(vma, __hugepd(pgd_val(pgdval)), + address, PGDIR_SHIFT, flags, ctx); + else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + page =3D no_page_table(vma, flags, address); + else + page =3D follow_p4d_mask(vma, address, pgd, flags, ctx); =20 - return follow_p4d_mask(vma, address, pgd, flags, ctx); + return page; } =20 struct page *follow_page(struct vm_area_struct *vma, unsigned long address, @@ -3026,6 +3047,37 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned lon= g addr, =20 return 1; } + +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hug= epd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx) +{ + struct page *page; + struct hstate *h; + spinlock_t *ptl; + int nr =3D 0, ret; + pte_t *ptep; + + /* Only hugetlb supports hugepd */ + if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma))) + return ERR_PTR(-EFAULT); + + h =3D hstate_vma(vma); + ptep =3D hugepte_offset(hugepd, addr, pdshift); + ptl =3D huge_pte_lock(h, vma->vm_mm, ptep); + ret =3D gup_huge_pd(hugepd, addr, pdshift, addr + PAGE_SIZE, + flags, &page, &nr); + spin_unlock(ptl); + + if (ret) { + WARN_ON_ONCE(nr !=3D 1); + ctx->page_mask =3D (1U << huge_page_order(h)) - 1; + return page; + } + + return NULL; +} #else static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, @@ -3033,6 +3085,14 @@ static inline int gup_huge_pd(hugepd_t hugepd, unsig= ned long addr, { return 0; } + +static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hug= epd, + unsigned long addr, unsigned int pdshift, + unsigned int flags, + struct follow_page_context *ctx) +{ + return NULL; +} #endif /* CONFIG_ARCH_HAS_HUGEPD */ =20 static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, --=20 2.41.0 From nobody Mon Dec 15 01:32:23 2025 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 254A71A720 for ; Wed, 3 Jan 2024 09:17:23 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="SMjl682N" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1704273442; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=1p2LWjy53LBaoBTc753xtp3ZFESBZSj8dXlH3kmoDms=; b=SMjl682N8IjoNKoD01jTAAGDpllo5MsqYaN36YwrFOsppQQPITcXZvALph4IPICmA/ZCWM HXO5KqxYrgScwS0pFTOac4xfwHmwl7/HG1uRb9ePN+cXubG11WJCc5IxFn4xOnXD6oo0mW w4Rwasix5N0F82KR/h9wEJzpnfIPRcc= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-595-K7snBKXGMluKlA4u3ja1Zg-1; Wed, 03 Jan 2024 04:17:19 -0500 X-MC-Unique: K7snBKXGMluKlA4u3ja1Zg-1 Received: from smtp.corp.redhat.com (int-mx10.intmail.prod.int.rdu2.redhat.com [10.11.54.10]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 26F8783B86A; Wed, 3 Jan 2024 09:17:18 +0000 (UTC) Received: from x1n.redhat.com (unknown [10.72.116.69]) by smtp.corp.redhat.com (Postfix) with ESMTP id 4404B492BE6; Wed, 3 Jan 2024 09:17:05 +0000 (UTC) From: peterx@redhat.com To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: James Houghton , David Hildenbrand , "Kirill A . Shutemov" , Yang Shi , peterx@redhat.com, linux-riscv@lists.infradead.org, Andrew Morton , "Aneesh Kumar K . V" , Rik van Riel , Andrea Arcangeli , Axel Rasmussen , Mike Rapoport , John Hubbard , Vlastimil Babka , Michael Ellerman , Christophe Leroy , Andrew Jones , linuxppc-dev@lists.ozlabs.org, Mike Kravetz , Muchun Song , linux-arm-kernel@lists.infradead.org, Jason Gunthorpe , Christoph Hellwig , Lorenzo Stoakes , Matthew Wilcox Subject: [PATCH v2 13/13] mm/gup: Handle hugetlb in the generic follow_page_mask code Date: Wed, 3 Jan 2024 17:14:23 +0800 Message-ID: <20240103091423.400294-14-peterx@redhat.com> In-Reply-To: <20240103091423.400294-1-peterx@redhat.com> References: <20240103091423.400294-1-peterx@redhat.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.10 Content-Type: text/plain; charset="utf-8" From: Peter Xu Now follow_page() is ready to handle hugetlb pages in whatever form, and over all architectures. Switch to the generic code path. Time to retire hugetlb_follow_page_mask(), following the previous retirement of follow_hugetlb_page() in 4849807114b8. There may be a slight difference of how the loops run when processing slow GUP over a large hugetlb range on cont_pte/cont_pmd supported archs: each loop of __get_user_pages() will resolve one pgtable entry with the patch applied, rather than relying on the size of hugetlb hstate, the latter may cover multiple entries in one loop. A quick performance test on an aarch64 VM on M1 chip shows 15% degrade over a tight loop of slow gup after the path switched. That shouldn't be a problem because slow-gup should not be a hot path for GUP in general: when page is commonly present, fast-gup will already succeed, while when the page is indeed missing and require a follow up page fault, the slow gup degrade will probably buried in the fault paths anyway. It also explains why slow gup for THP used to be very slow before 57edfcfd3419 ("mm/gup: accelerate thp gup even for "pages !=3D NULL"") lands, the latter not part = of a performance analysis but a side benefit. If the performance will be a concern, we can consider handle CONT_PTE in follow_page(). Before that is justified to be necessary, keep everything clean and simple. Signed-off-by: Peter Xu --- include/linux/hugetlb.h | 7 ---- mm/gup.c | 15 +++------ mm/hugetlb.c | 71 ----------------------------------------- 3 files changed, 5 insertions(+), 88 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index e8eddd51fc17..cdbb53407722 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -332,13 +332,6 @@ static inline void hugetlb_zap_end( { } =20 -static inline struct page *hugetlb_follow_page_mask( - struct vm_area_struct *vma, unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/ -} - static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, diff --git a/mm/gup.c b/mm/gup.c index 245214b64108..4f8a3dc287c9 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -997,18 +997,11 @@ static struct page *follow_page_mask(struct vm_area_s= truct *vma, { pgd_t *pgd, pgdval; struct mm_struct *mm =3D vma->vm_mm; + struct page *page; =20 - ctx->page_mask =3D 0; - - /* - * Call hugetlb_follow_page_mask for hugetlb vmas as it will use - * special hugetlb page table walking code. This eliminates the - * need to check for hugetlb entries in the general walking code. - */ - if (is_vm_hugetlb_page(vma)) - return hugetlb_follow_page_mask(vma, address, flags, - &ctx->page_mask); + vma_pgtable_walk_begin(vma); =20 + ctx->page_mask =3D 0; pgd =3D pgd_offset(mm, address); pgdval =3D *pgd; =20 @@ -1020,6 +1013,8 @@ static struct page *follow_page_mask(struct vm_area_s= truct *vma, else page =3D follow_p4d_mask(vma, address, pgd, flags, ctx); =20 + vma_pgtable_walk_end(vma); + return page; } =20 diff --git a/mm/hugetlb.c b/mm/hugetlb.c index bfb52bb8b943..e13b4e038c2c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -6782,77 +6782,6 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, } #endif /* CONFIG_USERFAULTFD */ =20 -struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask) -{ - struct hstate *h =3D hstate_vma(vma); - struct mm_struct *mm =3D vma->vm_mm; - unsigned long haddr =3D address & huge_page_mask(h); - struct page *page =3D NULL; - spinlock_t *ptl; - pte_t *pte, entry; - int ret; - - hugetlb_vma_lock_read(vma); - pte =3D hugetlb_walk(vma, haddr, huge_page_size(h)); - if (!pte) - goto out_unlock; - - ptl =3D huge_pte_lock(h, mm, pte); - entry =3D huge_ptep_get(pte); - if (pte_present(entry)) { - page =3D pte_page(entry); - - if (!huge_pte_write(entry)) { - if (flags & FOLL_WRITE) { - page =3D NULL; - goto out; - } - - if (gup_must_unshare(vma, flags, page)) { - /* Tell the caller to do unsharing */ - page =3D ERR_PTR(-EMLINK); - goto out; - } - } - - page =3D nth_page(page, ((address & ~huge_page_mask(h)) >> PAGE_SHIFT)); - - /* - * Note that page may be a sub-page, and with vmemmap - * optimizations the page struct may be read only. - * try_grab_page() will increase the ref count on the - * head page, so this will be OK. - * - * try_grab_page() should always be able to get the page here, - * because we hold the ptl lock and have verified pte_present(). - */ - ret =3D try_grab_page(page, flags); - - if (WARN_ON_ONCE(ret)) { - page =3D ERR_PTR(ret); - goto out; - } - - *page_mask =3D (1U << huge_page_order(h)) - 1; - } -out: - spin_unlock(ptl); -out_unlock: - hugetlb_vma_unlock_read(vma); - - /* - * Fixup retval for dump requests: if pagecache doesn't exist, - * don't try to allocate a new page but just skip it. - */ - if (!page && (flags & FOLL_DUMP) && - !hugetlbfs_pagecache_present(h, vma, address)) - page =3D ERR_PTR(-EFAULT); - - return page; -} - long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) --=20 2.41.0