From nobody Mon Nov 25 12:34:30 2024 Received: from szxga08-in.huawei.com (szxga08-in.huawei.com [45.249.212.255]) (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 2A6E71D90D7; Mon, 28 Oct 2024 12:00:12 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.255 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730116818; cv=none; b=lIQHslr0/ukm7qP2JtKaTem2AKnuqXvt1Xzq+o6NvYbu81ZAid9mhcpq9z0bDQbO4D1gZQ8KBcWdZnogFW5mWo08+v49cCp0gWmyaDI4QGm6V+0rRVScC3GnjEDkQcbbKOZwU6oORfORhsiCwq0ErEMnOVZ4IQOqPcVj6TyTqVE= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730116818; c=relaxed/simple; bh=NvFB5LS9zFxBzjCyN3OPIN80q1ZdTYK3gc2Smaz02dI=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=kR9cVjwjnfU217TpOvGgis9Se0NUyTT6ZaoknTuc/gap7BRyPc23F32fr98VWxcUW95seGcLoIwny04An5I9OIBunGqlh5HXgDCPX1YgpRAZyMs7QqGYp30P+6Vhbx3izS5DcbxBnGcxQMFaAqfNewQHU2QZMCMO2PWb/EwEm2E= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com; spf=pass smtp.mailfrom=huawei.com; arc=none smtp.client-ip=45.249.212.255 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huawei.com Received: from mail.maildlp.com (unknown [172.19.162.254]) by szxga08-in.huawei.com (SkyGuard) with ESMTP id 4XcX2b4vjJz1T9CN; Mon, 28 Oct 2024 19:57:59 +0800 (CST) Received: from dggpemf200006.china.huawei.com (unknown [7.185.36.61]) by mail.maildlp.com (Postfix) with ESMTPS id ECF2F1800DE; Mon, 28 Oct 2024 20:00:07 +0800 (CST) Received: from localhost.localdomain (10.90.30.45) by dggpemf200006.china.huawei.com (7.185.36.61) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1544.11; Mon, 28 Oct 2024 20:00:07 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , David Howells , Alexander Duyck , Andrew Morton , Linux-MM , Alexander Duyck , Eric Dumazet , Simon Horman , Shuah Khan , Subject: [PATCH net-next v23 2/7] mm: move the page fragment allocator from page_alloc into its own file Date: Mon, 28 Oct 2024 19:53:37 +0800 Message-ID: <20241028115343.3405838-3-linyunsheng@huawei.com> X-Mailer: git-send-email 2.30.0 In-Reply-To: <20241028115343.3405838-1-linyunsheng@huawei.com> References: <20241028115343.3405838-1-linyunsheng@huawei.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-ClientProxiedBy: dggems705-chm.china.huawei.com (10.3.19.182) To dggpemf200006.china.huawei.com (7.185.36.61) Content-Type: text/plain; charset="utf-8" Inspired by [1], move the page fragment allocator from page_alloc into its own c file and header file, as we are about to make more change for it to replace another page_frag implementation in sock.c As this patchset is going to replace 'struct page_frag' with 'struct page_frag_cache' in sched.h, including page_frag_cache.h in sched.h has a compiler error caused by interdependence between mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler error by moving 'struct page_frag_cache' to mm_types_task.h as suggested by Alexander, see [3]. 1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/ 2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.c= om/ 3. https://lore.kernel.org/all/CAKgT0UdH1yD=3DLSCXFJ=3DYM_aiA4OomD-2wXykO42= bizaWMt_HOA@mail.gmail.com/ CC: David Howells CC: Alexander Duyck CC: Andrew Morton CC: Linux-MM Signed-off-by: Yunsheng Lin Acked-by: Andrew Morton Reviewed-by: Alexander Duyck --- include/linux/gfp.h | 22 --- include/linux/mm_types.h | 18 --- include/linux/mm_types_task.h | 18 +++ include/linux/page_frag_cache.h | 31 ++++ include/linux/skbuff.h | 1 + mm/Makefile | 1 + mm/page_alloc.c | 136 ---------------- mm/page_frag_cache.c | 145 ++++++++++++++++++ .../selftests/mm/page_frag/page_frag_test.c | 2 +- 9 files changed, 197 insertions(+), 177 deletions(-) create mode 100644 include/linux/page_frag_cache.h create mode 100644 mm/page_frag_cache.c diff --git a/include/linux/gfp.h b/include/linux/gfp.h index a951de920e20..a0a6d25f883f 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, = size_t size, gfp_t gfp_mas extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); =20 -struct page_frag_cache; -void page_frag_cache_drain(struct page_frag_cache *nc); -extern void __page_frag_cache_drain(struct page *page, unsigned int count); -void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fra= gsz, - gfp_t gfp_mask, unsigned int align_mask); - -static inline void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align) -{ - WARN_ON_ONCE(!is_power_of_2(align)); - return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); -} - -static inline void *page_frag_alloc(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask) -{ - return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); -} - -extern void page_frag_free(void *addr); - #define __free_page(page) __free_pages((page), 0) #define free_page(addr) free_pages((addr), 0) =20 diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6e3bdf8e38bc..92314ef2d978 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <=3D sizeof(struct = page)); */ #define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page))) =20 -#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) -#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) - /* * page_private can be used on tail pages. However, PagePrivate is only * checked by the VM on the head page. So page_private on the tail pages @@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *fo= lio) return folio->private; } =20 -struct page_frag_cache { - void * va; -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - __u16 offset; - __u16 size; -#else - __u32 offset; -#endif - /* we maintain a pagecount bias, so that we dont dirty cache line - * containing page->_refcount every time we allocate a fragment. - */ - unsigned int pagecnt_bias; - bool pfmemalloc; -}; - typedef unsigned long vm_flags_t; =20 /* diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index bff5706b76e1..0ac6daebdd5c 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -8,6 +8,7 @@ * (These are defined separately to decouple sched.h from mm_types.h as mu= ch as possible.) */ =20 +#include #include =20 #include @@ -43,6 +44,23 @@ struct page_frag { #endif }; =20 +#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK) +#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE) +struct page_frag_cache { + void *va; +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + __u16 offset; + __u16 size; +#else + __u32 offset; +#endif + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ + unsigned int pagecnt_bias; + bool pfmemalloc; +}; + /* Track pages that require TLB flushes */ struct tlbflush_unmap_batch { #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cach= e.h new file mode 100644 index 000000000000..67ac8626ed9b --- /dev/null +++ b/include/linux/page_frag_cache.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _LINUX_PAGE_FRAG_CACHE_H +#define _LINUX_PAGE_FRAG_CACHE_H + +#include +#include +#include + +void page_frag_cache_drain(struct page_frag_cache *nc); +void __page_frag_cache_drain(struct page *page, unsigned int count); +void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fra= gsz, + gfp_t gfp_mask, unsigned int align_mask); + +static inline void *page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align) +{ + WARN_ON_ONCE(!is_power_of_2(align)); + return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align); +} + +static inline void *page_frag_alloc(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask) +{ + return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u); +} + +void page_frag_free(void *addr); + +#endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 48f1e0fa2a13..7adca0fa2602 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -31,6 +31,7 @@ #include #include #include +#include #include #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include diff --git a/mm/Makefile b/mm/Makefile index d5639b036166..dba52bb0da8a 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) +=3D shuffle.o memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) +=3D memory_hotplug.o =20 obj-y +=3D page-alloc.o +obj-y +=3D page_frag_cache.o obj-y +=3D init-mm.o obj-y +=3D memblock.o obj-y +=3D $(memory-hotplug-y) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8afab64814dc..6ca2abce857b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4836,142 +4836,6 @@ void free_pages(unsigned long addr, unsigned int or= der) =20 EXPORT_SYMBOL(free_pages); =20 -/* - * Page Fragment: - * An arbitrary-length arbitrary-offset area of memory which resides - * within a 0 or higher order page. Multiple fragments within that page - * are individually refcounted, in the page's reference counter. - * - * The page_frag functions below provide a simple allocation framework for - * page fragments. This is used by the network stack and network device - * drivers to provide a backing region of memory for use as either an - * sk_buff->head, or to be used in the "frags" portion of skb_shared_info. - */ -static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, - gfp_t gfp_mask) -{ - struct page *page =3D NULL; - gfp_t gfp =3D gfp_mask; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask =3D (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; - page =3D alloc_pages_node(NUMA_NO_NODE, gfp_mask, - PAGE_FRAG_CACHE_MAX_ORDER); - nc->size =3D page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -#endif - if (unlikely(!page)) - page =3D alloc_pages_node(NUMA_NO_NODE, gfp, 0); - - nc->va =3D page ? page_address(page) : NULL; - - return page; -} - -void page_frag_cache_drain(struct page_frag_cache *nc) -{ - if (!nc->va) - return; - - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va =3D NULL; -} -EXPORT_SYMBOL(page_frag_cache_drain); - -void __page_frag_cache_drain(struct page *page, unsigned int count) -{ - VM_BUG_ON_PAGE(page_ref_count(page) =3D=3D 0, page); - - if (page_ref_sub_and_test(page, count)) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(__page_frag_cache_drain); - -void *__page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) -{ - unsigned int size =3D PAGE_SIZE; - struct page *page; - int offset; - - if (unlikely(!nc->va)) { -refill: - page =3D __page_frag_cache_refill(nc, gfp_mask); - if (!page) - return NULL; - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size =3D nc->size; -#endif - /* Even if we own the page, we do not use atomic_set(). - * This would break get_page_unless_zero() users. - */ - page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); - - /* reset page count bias and offset to start of new frag */ - nc->pfmemalloc =3D page_is_pfmemalloc(page); - nc->pagecnt_bias =3D PAGE_FRAG_CACHE_MAX_SIZE + 1; - nc->offset =3D size; - } - - offset =3D nc->offset - fragsz; - if (unlikely(offset < 0)) { - page =3D virt_to_page(nc->va); - - if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) - goto refill; - - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); - goto refill; - } - -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size =3D nc->size; -#endif - /* OK, page count is 0, we can safely set it */ - set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); - - /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias =3D PAGE_FRAG_CACHE_MAX_SIZE + 1; - offset =3D size - fragsz; - if (unlikely(offset < 0)) { - /* - * The caller is trying to allocate a fragment - * with fragsz > PAGE_SIZE but the cache isn't big - * enough to satisfy the request, this may - * happen in low memory conditions. - * We don't release the cache page because - * it could make memory pressure worse - * so we simply return NULL here. - */ - return NULL; - } - } - - nc->pagecnt_bias--; - offset &=3D align_mask; - nc->offset =3D offset; - - return nc->va + offset; -} -EXPORT_SYMBOL(__page_frag_alloc_align); - -/* - * Frees a page fragment allocated out of either a compound or order 0 pag= e. - */ -void page_frag_free(void *addr) -{ - struct page *page =3D virt_to_head_page(addr); - - if (unlikely(put_page_testzero(page))) - free_unref_page(page, compound_order(page)); -} -EXPORT_SYMBOL(page_frag_free); - static void *make_alloc_exact(unsigned long addr, unsigned int order, size_t size) { diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c new file mode 100644 index 000000000000..609a485cd02a --- /dev/null +++ b/mm/page_frag_cache.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Page fragment allocator + * + * Page Fragment: + * An arbitrary-length arbitrary-offset area of memory which resides with= in a + * 0 or higher order page. Multiple fragments within that page are + * individually refcounted, in the page's reference counter. + * + * The page_frag functions provide a simple allocation framework for page + * fragments. This is used by the network stack and network device driver= s to + * provide a backing region of memory for use as either an sk_buff->head, = or to + * be used in the "frags" portion of skb_shared_info. + */ + +#include +#include +#include +#include +#include +#include "internal.h" + +static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, + gfp_t gfp_mask) +{ + struct page *page =3D NULL; + gfp_t gfp =3D gfp_mask; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + gfp_mask =3D (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; + page =3D alloc_pages_node(NUMA_NO_NODE, gfp_mask, + PAGE_FRAG_CACHE_MAX_ORDER); + nc->size =3D page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; +#endif + if (unlikely(!page)) + page =3D alloc_pages_node(NUMA_NO_NODE, gfp, 0); + + nc->va =3D page ? page_address(page) : NULL; + + return page; +} + +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va =3D NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + +void __page_frag_cache_drain(struct page *page, unsigned int count) +{ + VM_BUG_ON_PAGE(page_ref_count(page) =3D=3D 0, page); + + if (page_ref_sub_and_test(page, count)) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(__page_frag_cache_drain); + +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) +{ + unsigned int size =3D PAGE_SIZE; + struct page *page; + int offset; + + if (unlikely(!nc->va)) { +refill: + page =3D __page_frag_cache_refill(nc, gfp_mask); + if (!page) + return NULL; + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size =3D nc->size; +#endif + /* Even if we own the page, we do not use atomic_set(). + * This would break get_page_unless_zero() users. + */ + page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE); + + /* reset page count bias and offset to start of new frag */ + nc->pfmemalloc =3D page_is_pfmemalloc(page); + nc->pagecnt_bias =3D PAGE_FRAG_CACHE_MAX_SIZE + 1; + nc->offset =3D size; + } + + offset =3D nc->offset - fragsz; + if (unlikely(offset < 0)) { + page =3D virt_to_page(nc->va); + + if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) + goto refill; + + if (unlikely(nc->pfmemalloc)) { + free_unref_page(page, compound_order(page)); + goto refill; + } + +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) + /* if size can vary use size else just use PAGE_SIZE */ + size =3D nc->size; +#endif + /* OK, page count is 0, we can safely set it */ + set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1); + + /* reset page count bias and offset to start of new frag */ + nc->pagecnt_bias =3D PAGE_FRAG_CACHE_MAX_SIZE + 1; + offset =3D size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } + } + + nc->pagecnt_bias--; + offset &=3D align_mask; + nc->offset =3D offset; + + return nc->va + offset; +} +EXPORT_SYMBOL(__page_frag_alloc_align); + +/* + * Frees a page fragment allocated out of either a compound or order 0 pag= e. + */ +void page_frag_free(void *addr) +{ + struct page *page =3D virt_to_head_page(addr); + + if (unlikely(put_page_testzero(page))) + free_unref_page(page, compound_order(page)); +} +EXPORT_SYMBOL(page_frag_free); diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/= testing/selftests/mm/page_frag/page_frag_test.c index 912d97b99107..13c44133e009 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -6,12 +6,12 @@ * Copyright (C) 2024 Yunsheng Lin */ =20 -#include #include #include #include #include #include +#include =20 #define TEST_FAILED_PREFIX "page_frag_test failed: " =20 --=20 2.33.0