From nobody Mon Nov 25 12:25:28 2024 Received: from szxga04-in.huawei.com (szxga04-in.huawei.com [45.249.212.190]) (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 5366D1D9699; Mon, 28 Oct 2024 12:00:19 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.190 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730116822; cv=none; b=JotdwnVf2QrrpEIGF3ozN9QYFoU5bPNZVXr1k3ZMHvRQRBBude1Rvf6hZkdXE1h1A3OFJQrlSLuAx1qxa8WlxKeW6kNlF/7N50jVJbr3pPSXrvFMOs1tIidubeItDCmiq4X5ugAzEMmdH1zBm3ObBbN6/tWXcVnlzzycFoCKegQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730116822; c=relaxed/simple; bh=8PfSSDOt87r46QjCuDFJfyqeriwrfYQvS54WNAvv2Mo=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=HEQ31t8VeslCrDe9Yf5wa3z2UX0aK9wyOHibVw3OAX/u8X5LhMmcbDDJG7m+SDXuZxfjT7tgeL+DY2hhgi1IoNuV34c3HjoYIvHHxJyYkx3y0g+k5d4Js7VAXSocn8sCyFRXXMvZzm038Qh92b3gKxn/0BvRyKZHaKxiDZI+UMw= 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=45.249.212.190 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 [172.19.88.234]) by szxga04-in.huawei.com (SkyGuard) with ESMTP id 4XcX3W319hz2Ddk5; Mon, 28 Oct 2024 19:58:47 +0800 (CST) Received: from dggpemf200006.china.huawei.com (unknown [7.185.36.61]) by mail.maildlp.com (Postfix) with ESMTPS id 0FFF314010C; Mon, 28 Oct 2024 20:00:17 +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 20:00:16 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Alexander Duyck , Andrew Morton , Linux-MM , Alexander Duyck Subject: [PATCH net-next v23 6/7] mm: page_frag: reuse existing space for 'size' and 'pfmemalloc' Date: Mon, 28 Oct 2024 19:53:41 +0800 Message-ID: <20241028115343.3405838-7-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" Currently there is one 'struct page_frag' for every 'struct sock' and 'struct task_struct', we are about to replace the 'struct page_frag' with 'struct page_frag_cache' for them. Before begin the replacing, we need to ensure the size of 'struct page_frag_cache' is not bigger than the size of 'struct page_frag', as there may be tens of thousands of 'struct sock' and 'struct task_struct' instances in the system. By or'ing the page order & pfmemalloc with lower bits of 'va' instead of using 'u16' or 'u32' for page size and 'u8' for pfmemalloc, we are able to avoid 3 or 5 bytes space waste. And page address & pfmemalloc & order is unchanged for the same page in the same 'page_frag_cache' instance, it makes sense to fit them together. After this patch, the size of 'struct page_frag_cache' should be the same as the size of 'struct page_frag'. CC: Alexander Duyck CC: Andrew Morton CC: Linux-MM Signed-off-by: Yunsheng Lin Reviewed-by: Alexander Duyck --- include/linux/mm_types_task.h | 19 +++++---- include/linux/page_frag_cache.h | 24 ++++++++++- mm/page_frag_cache.c | 70 ++++++++++++++++++++++----------- 3 files changed, 81 insertions(+), 32 deletions(-) diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 0ac6daebdd5c..a82aa80c0ba4 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -47,18 +47,21 @@ struct page_frag { #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) + /* encoded_page consists of the virtual address, pfmemalloc bit and + * order of a page. + */ + unsigned long encoded_page; + + /* we maintain a pagecount bias, so that we dont dirty cache line + * containing page->_refcount every time we allocate a fragment. + */ +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <=3D 32) __u16 offset; - __u16 size; + __u16 pagecnt_bias; #else __u32 offset; + __u32 pagecnt_bias; #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; }; =20 /* Track pages that require TLB flushes */ diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cach= e.h index 0a52f7a179c8..41a91df82631 100644 --- a/include/linux/page_frag_cache.h +++ b/include/linux/page_frag_cache.h @@ -3,18 +3,38 @@ #ifndef _LINUX_PAGE_FRAG_CACHE_H #define _LINUX_PAGE_FRAG_CACHE_H =20 +#include #include #include #include =20 +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) +/* Use a full byte here to enable assembler optimization as the shift + * operation is usually expecting a byte. + */ +#define PAGE_FRAG_CACHE_ORDER_MASK GENMASK(7, 0) +#else +/* Compiler should be able to figure out we don't read things as any value + * ANDed with 0 is 0. + */ +#define PAGE_FRAG_CACHE_ORDER_MASK 0 +#endif + +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT (PAGE_FRAG_CACHE_ORDER_MASK + 1) + +static inline bool encoded_page_decode_pfmemalloc(unsigned long encoded_pa= ge) +{ + return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT); +} + static inline void page_frag_cache_init(struct page_frag_cache *nc) { - nc->va =3D NULL; + nc->encoded_page =3D 0; } =20 static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *n= c) { - return !!nc->pfmemalloc; + return encoded_page_decode_pfmemalloc(nc->encoded_page); } =20 void page_frag_cache_drain(struct page_frag_cache *nc); diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c index 4c8e04379cb3..a36fd09bf275 100644 --- a/mm/page_frag_cache.c +++ b/mm/page_frag_cache.c @@ -12,6 +12,7 @@ * be used in the "frags" portion of skb_shared_info. */ =20 +#include #include #include #include @@ -19,9 +20,36 @@ #include #include "internal.h" =20 +static unsigned long encoded_page_create(struct page *page, unsigned int o= rder, + bool pfmemalloc) +{ + BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK); + BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >=3D PAGE_SIZE); + + return (unsigned long)page_address(page) | + (order & PAGE_FRAG_CACHE_ORDER_MASK) | + ((unsigned long)pfmemalloc * PAGE_FRAG_CACHE_PFMEMALLOC_BIT); +} + +static unsigned long encoded_page_decode_order(unsigned long encoded_page) +{ + return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK; +} + +static void *encoded_page_decode_virt(unsigned long encoded_page) +{ + return (void *)(encoded_page & PAGE_MASK); +} + +static struct page *encoded_page_decode_page(unsigned long encoded_page) +{ + return virt_to_page((void *)encoded_page); +} + static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, gfp_t gfp_mask) { + unsigned long order =3D PAGE_FRAG_CACHE_MAX_ORDER; struct page *page =3D NULL; gfp_t gfp =3D gfp_mask; =20 @@ -30,23 +58,26 @@ static struct page *__page_frag_cache_refill(struct pag= e_frag_cache *nc, __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)) + if (unlikely(!page)) { page =3D alloc_pages_node(NUMA_NO_NODE, gfp, 0); + order =3D 0; + } =20 - nc->va =3D page ? page_address(page) : NULL; + nc->encoded_page =3D page ? + encoded_page_create(page, order, page_is_pfmemalloc(page)) : 0; =20 return page; } =20 void page_frag_cache_drain(struct page_frag_cache *nc) { - if (!nc->va) + if (!nc->encoded_page) return; =20 - __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); - nc->va =3D NULL; + __page_frag_cache_drain(encoded_page_decode_page(nc->encoded_page), + nc->pagecnt_bias); + nc->encoded_page =3D 0; } EXPORT_SYMBOL(page_frag_cache_drain); =20 @@ -63,35 +94,29 @@ void *__page_frag_alloc_align(struct page_frag_cache *n= c, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask) { -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - unsigned int size =3D nc->size; -#else - unsigned int size =3D PAGE_SIZE; -#endif - unsigned int offset; + unsigned long encoded_page =3D nc->encoded_page; + unsigned int size, offset; struct page *page; =20 - if (unlikely(!nc->va)) { + if (unlikely(!encoded_page)) { refill: page =3D __page_frag_cache_refill(nc, gfp_mask); if (!page) return NULL; =20 -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - /* if size can vary use size else just use PAGE_SIZE */ - size =3D nc->size; -#endif + encoded_page =3D nc->encoded_page; + /* 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); =20 /* 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 0; } =20 + size =3D PAGE_SIZE << encoded_page_decode_order(encoded_page); offset =3D __ALIGN_KERNEL_MASK(nc->offset, ~align_mask); if (unlikely(offset + fragsz > size)) { if (unlikely(fragsz > PAGE_SIZE)) { @@ -107,13 +132,14 @@ void *__page_frag_alloc_align(struct page_frag_cache = *nc, return NULL; } =20 - page =3D virt_to_page(nc->va); + page =3D encoded_page_decode_page(encoded_page); =20 if (!page_ref_sub_and_test(page, nc->pagecnt_bias)) goto refill; =20 - if (unlikely(nc->pfmemalloc)) { - free_unref_page(page, compound_order(page)); + if (unlikely(encoded_page_decode_pfmemalloc(encoded_page))) { + free_unref_page(page, + encoded_page_decode_order(encoded_page)); goto refill; } =20 @@ -128,7 +154,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *n= c, nc->pagecnt_bias--; nc->offset =3D offset + fragsz; =20 - return nc->va + offset; + return encoded_page_decode_virt(encoded_page) + offset; } EXPORT_SYMBOL(__page_frag_alloc_align); =20 --=20 2.33.0