From nobody Thu Nov 14 05:20:20 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1FCCCC19F5C for ; Fri, 20 Oct 2023 09:59:39 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1376856AbjJTJ7h (ORCPT ); Fri, 20 Oct 2023 05:59:37 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:55998 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1376803AbjJTJ7c (ORCPT ); Fri, 20 Oct 2023 05:59:32 -0400 Received: from szxga03-in.huawei.com (szxga03-in.huawei.com [45.249.212.189]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A16F8D8; Fri, 20 Oct 2023 02:59:29 -0700 (PDT) Received: from dggpemm500005.china.huawei.com (unknown [172.30.72.57]) by szxga03-in.huawei.com (SkyGuard) with ESMTP id 4SBg1f5rwTzMm4B; Fri, 20 Oct 2023 17:55:18 +0800 (CST) Received: from localhost.localdomain (10.69.192.56) by dggpemm500005.china.huawei.com (7.185.36.74) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.31; Fri, 20 Oct 2023 17:59:26 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Lorenzo Bianconi , Alexander Duyck , Liang Chen , Alexander Lobakin , Jesper Dangaard Brouer , Ilias Apalodimas , Eric Dumazet Subject: [PATCH net-next v12 1/5] page_pool: unify frag_count handling in page_pool_is_last_frag() Date: Fri, 20 Oct 2023 17:59:48 +0800 Message-ID: <20231020095952.11055-2-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20231020095952.11055-1-linyunsheng@huawei.com> References: <20231020095952.11055-1-linyunsheng@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Currently when page_pool_create() is called with PP_FLAG_PAGE_FRAG flag, page_pool_alloc_pages() is only allowed to be called under the below constraints: 1. page_pool_fragment_page() need to be called to setup page->pp_frag_count immediately. 2. page_pool_defrag_page() often need to be called to drain the page->pp_frag_count when there is no more user will be holding on to that page. Those constraints exist in order to support a page to be split into multi fragments. And those constraints have some overhead because of the cache line dirtying/bouncing and atomic update. Those constraints are unavoidable for case when we need a page to be split into more than one fragment, but there is also case that we want to avoid the above constraints and their overhead when a page can't be split as it can only hold a fragment as requested by user, depending on different use cases: use case 1: allocate page without page splitting. use case 2: allocate page with page splitting. use case 3: allocate page with or without page splitting depending on the fragment size. Currently page pool only provide page_pool_alloc_pages() and page_pool_alloc_frag() API to enable the 1 & 2 separately, so we can not use a combination of 1 & 2 to enable 3, it is not possible yet because of the per page_pool flag PP_FLAG_PAGE_FRAG. So in order to allow allocating unsplit page without the overhead of split page while still allow allocating split page we need to remove the per page_pool flag in page_pool_is_last_frag(), as best as I can think of, it seems there are two methods as below: 1. Add per page flag/bit to indicate a page is split or not, which means we might need to update that flag/bit everytime the page is recycled, dirtying the cache line of 'struct page' for use case 1. 2. Unify the page->pp_frag_count handling for both split and unsplit page by assuming all pages in the page pool is split into a big fragment initially. As page pool already supports use case 1 without dirtying the cache line of 'struct page' whenever a page is recyclable, we need to support the above use case 3 with minimal overhead, especially not adding any noticeable overhead for use case 1, and we are already doing an optimization by not updating pp_frag_count in page_pool_defrag_page() for the last fragment user, this patch chooses to unify the pp_frag_count handling to support the above use case 3. There is no noticeable performance degradation and some justification for unifying the frag_count handling with this patch applied using a micro-benchmark testing in [1]. 1. https://lore.kernel.org/all/bf2591f8-7b3c-4480-bb2c-31dc9da1d6ac@huawei.= com/ Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Alexander Lobakin --- include/net/page_pool/helpers.h | 47 ++++++++++++++++++++++++--------- net/core/page_pool.c | 10 ++++++- 2 files changed, 43 insertions(+), 14 deletions(-) diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helper= s.h index 8f64adf86f5b..759489c037c7 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -115,28 +115,49 @@ static inline long page_pool_defrag_page(struct page = *page, long nr) long ret; =20 /* If nr =3D=3D pp_frag_count then we have cleared all remaining - * references to the page. No need to actually overwrite it, instead - * we can leave this to be overwritten by the calling function. + * references to the page: + * 1. 'n =3D=3D 1': no need to actually overwrite it. + * 2. 'n !=3D 1': overwrite it with one, which is the rare case + * for pp_frag_count draining. * - * The main advantage to doing this is that an atomic_read is - * generally a much cheaper operation than an atomic update, - * especially when dealing with a page that may be partitioned - * into only 2 or 3 pieces. + * The main advantage to doing this is that not only we avoid a atomic + * update, as an atomic_read is generally a much cheaper operation than + * an atomic update, especially when dealing with a page that may be + * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count + * handling by ensuring all pages have partitioned into only 1 piece + * initially, and only overwrite it when the page is partitioned into + * more than one piece. */ - if (atomic_long_read(&page->pp_frag_count) =3D=3D nr) + if (atomic_long_read(&page->pp_frag_count) =3D=3D nr) { + /* As we have ensured nr is always one for constant case using + * the BUILD_BUG_ON(), only need to handle the non-constant case + * here for pp_frag_count draining, which is a rare case. + */ + BUILD_BUG_ON(__builtin_constant_p(nr) && nr !=3D 1); + if (!__builtin_constant_p(nr)) + atomic_long_set(&page->pp_frag_count, 1); + return 0; + } =20 ret =3D atomic_long_sub_return(nr, &page->pp_frag_count); WARN_ON(ret < 0); + + /* We are the last user here too, reset pp_frag_count back to 1 to + * ensure all pages have been partitioned into 1 piece initially, + * this should be the rare case when the last two fragment users call + * page_pool_defrag_page() currently. + */ + if (unlikely(!ret)) + atomic_long_set(&page->pp_frag_count, 1); + return ret; } =20 -static inline bool page_pool_is_last_frag(struct page_pool *pool, - struct page *page) +static inline bool page_pool_is_last_frag(struct page *page) { - /* If fragments aren't enabled or count is 0 we were the last user */ - return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || - (page_pool_defrag_page(page, 1) =3D=3D 0); + /* If page_pool_defrag_page() returns 0, we were the last user */ + return page_pool_defrag_page(page, 1) =3D=3D 0; } =20 /** @@ -161,7 +182,7 @@ static inline void page_pool_put_page(struct page_pool = *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_frag(pool, page)) + if (!page_pool_is_last_frag(page)) return; =20 page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8a9868ea5067..953535cab081 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -376,6 +376,14 @@ static void page_pool_set_pp_info(struct page_pool *po= ol, { page->pp =3D pool; page->pp_magic |=3D PP_SIGNATURE; + + /* Ensuring all pages have been split into one fragment initially: + * page_pool_set_pp_info() is only called once for every page when it + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_page(page, 1); if (pool->p.init_callback) pool->p.init_callback(page, pool->p.init_arg); } @@ -672,7 +680,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, vo= id **data, struct page *page =3D virt_to_head_page(data[i]); =20 /* It is not the last user for the page frag case */ - if (!page_pool_is_last_frag(pool, page)) + if (!page_pool_is_last_frag(page)) continue; =20 page =3D __page_pool_put_page(pool, page, -1, false); --=20 2.33.0 From nobody Thu Nov 14 05:20:20 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8F320CDB47E for ; Fri, 20 Oct 2023 09:59:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1376886AbjJTJ74 (ORCPT ); Fri, 20 Oct 2023 05:59:56 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:47656 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1376849AbjJTJ7r (ORCPT ); Fri, 20 Oct 2023 05:59:47 -0400 Received: from szxga02-in.huawei.com (szxga02-in.huawei.com [45.249.212.188]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A6FD3D5A; Fri, 20 Oct 2023 02:59:35 -0700 (PDT) Received: from dggpemm500005.china.huawei.com (unknown [172.30.72.56]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4SBg2B1gjJzVlN1; Fri, 20 Oct 2023 17:55:46 +0800 (CST) Received: from localhost.localdomain (10.69.192.56) by dggpemm500005.china.huawei.com (7.185.36.74) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.31; Fri, 20 Oct 2023 17:59:29 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Lorenzo Bianconi , Alexander Duyck , Liang Chen , Alexander Lobakin , Michael Chan , Eric Dumazet , Yisen Zhuang , Salil Mehta , Jesse Brandeburg , Tony Nguyen , Sunil Goutham , Geetha sowjanya , Subbaraya Sundeep , hariprasad , Saeed Mahameed , Leon Romanovsky , Felix Fietkau , Ryder Lee , Shayne Chen , Sean Wang , Kalle Valo , Matthias Brugger , AngeloGioacchino Del Regno , Jesper Dangaard Brouer , Ilias Apalodimas , , , , , Subject: [PATCH net-next v12 2/5] page_pool: remove PP_FLAG_PAGE_FRAG Date: Fri, 20 Oct 2023 17:59:49 +0800 Message-ID: <20231020095952.11055-3-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20231020095952.11055-1-linyunsheng@huawei.com> References: <20231020095952.11055-1-linyunsheng@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" PP_FLAG_PAGE_FRAG is not really needed after pp_frag_count handling is unified and page_pool_alloc_frag() is supported in 32-bit arch with 64-bit DMA, so remove it. Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Alexander Lobakin --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 -- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 +-- drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 --- drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +- drivers/net/wireless/mediatek/mt76/mac80211.c | 2 +- include/net/page_pool/types.h | 6 ++---- net/core/page_pool.c | 3 +-- net/core/skbuff.c | 2 +- 9 files changed, 8 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethern= et/broadcom/bnxt/bnxt.c index 16eb7a7af970..2685d0b7be4b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -3250,8 +3250,6 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, pp.dma_dir =3D bp->rx_dir; pp.max_len =3D PAGE_SIZE; pp.flags =3D PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; - if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) - pp.flags |=3D PP_FLAG_PAGE_FRAG; =20 rxr->page_pool =3D page_pool_create(&pp); if (IS_ERR(rxr->page_pool)) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/= ethernet/hisilicon/hns3/hns3_enet.c index cf50368441b7..06117502001f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4940,8 +4940,7 @@ static void hns3_put_ring_config(struct hns3_nic_priv= *priv) static void hns3_alloc_page_pool(struct hns3_enet_ring *ring) { struct page_pool_params pp_params =3D { - .flags =3D PP_FLAG_DMA_MAP | PP_FLAG_PAGE_FRAG | - PP_FLAG_DMA_SYNC_DEV, + .flags =3D PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, .order =3D hns3_page_order(ring), .pool_size =3D ring->desc_num * hns3_buf_size(ring) / (PAGE_SIZE << hns3_page_order(ring)), diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethe= rnet/intel/idpf/idpf_txrx.c index 6fa79898c42c..55a099986b55 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -595,9 +595,6 @@ static struct page_pool *idpf_rx_create_page_pool(struc= t idpf_queue *rxbufq) .offset =3D 0, }; =20 - if (rxbufq->rx_buf_size =3D=3D IDPF_RX_BUF_2048) - pp.flags |=3D PP_FLAG_PAGE_FRAG; - return page_pool_create(&pp); } =20 diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/dri= vers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 818ce76185b2..1a42bfded872 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1404,7 +1404,7 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, } =20 pp_params.order =3D get_order(buf_size); - pp_params.flags =3D PP_FLAG_PAGE_FRAG | PP_FLAG_DMA_MAP; + pp_params.flags =3D PP_FLAG_DMA_MAP; pp_params.pool_size =3D min(OTX2_PAGE_POOL_SZ, numptrs); pp_params.nid =3D NUMA_NO_NODE; pp_params.dev =3D pfvf->dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/ne= t/ethernet/mellanox/mlx5/core/en_main.c index 9325b8f00af0..ea58c6917433 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -897,7 +897,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, struct page_pool_params pp_params =3D { 0 }; =20 pp_params.order =3D 0; - pp_params.flags =3D PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | PP_FLAG= _PAGE_FRAG; + pp_params.flags =3D PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pp_params.pool_size =3D pool_size; pp_params.nid =3D node; pp_params.dev =3D rq->pdev; diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wi= reless/mediatek/mt76/mac80211.c index cb76053973aa..51a767121b0d 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -570,7 +570,7 @@ int mt76_create_page_pool(struct mt76_dev *dev, struct = mt76_queue *q) { struct page_pool_params pp_params =3D { .order =3D 0, - .flags =3D PP_FLAG_PAGE_FRAG, + .flags =3D 0, .nid =3D NUMA_NO_NODE, .dev =3D dev->dma_dev, }; diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 887e7946a597..6fc5134095ed 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -17,10 +17,8 @@ * Please note DMA-sync-for-CPU is still * device driver responsibility */ -#define PP_FLAG_PAGE_FRAG BIT(2) /* for page frag feature */ #define PP_FLAG_ALL (PP_FLAG_DMA_MAP |\ - PP_FLAG_DMA_SYNC_DEV |\ - PP_FLAG_PAGE_FRAG) + PP_FLAG_DMA_SYNC_DEV) =20 /* * Fast allocation side cache array/stack @@ -45,7 +43,7 @@ struct pp_alloc_cache { =20 /** * struct page_pool_params - page pool parameters - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV * @order: 2^order pages on allocation * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 953535cab081..2a3671c97ca7 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -756,8 +756,7 @@ struct page *page_pool_alloc_frag(struct page_pool *poo= l, unsigned int max_size =3D PAGE_SIZE << pool->p.order; struct page *page =3D pool->frag_page; =20 - if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) || - size > max_size)) + if (WARN_ON(size > max_size)) return NULL; =20 size =3D ALIGN(size, dma_get_cache_alignment()); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 975c9a6ffb4a..c52ddd6891d9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5765,7 +5765,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_b= uff *from, /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. Additionally avoid dealing with clones * with page_pool pages, in case the SKB is using page_pool fragment - * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references (page_pool_alloc_frag()). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. * In theory we could take full references if @from is cloned and --=20 2.33.0 From nobody Thu Nov 14 05:20:20 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id F1272CDB474 for ; Fri, 20 Oct 2023 09:59:49 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1376889AbjJTJ7t (ORCPT ); Fri, 20 Oct 2023 05:59:49 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:56058 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1376845AbjJTJ7g (ORCPT ); Fri, 20 Oct 2023 05:59:36 -0400 Received: from szxga08-in.huawei.com (szxga08-in.huawei.com [45.249.212.255]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 91152C2; Fri, 20 Oct 2023 02:59:33 -0700 (PDT) Received: from dggpemm500005.china.huawei.com (unknown [172.30.72.54]) by szxga08-in.huawei.com (SkyGuard) with ESMTP id 4SBg3K6fQpz15NKl; Fri, 20 Oct 2023 17:56:45 +0800 (CST) Received: from localhost.localdomain (10.69.192.56) by dggpemm500005.china.huawei.com (7.185.36.74) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.31; Fri, 20 Oct 2023 17:59:31 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Lorenzo Bianconi , Alexander Duyck , Liang Chen , Alexander Lobakin , Jesper Dangaard Brouer , Ilias Apalodimas , Eric Dumazet Subject: [PATCH net-next v12 3/5] page_pool: introduce page_pool_alloc() API Date: Fri, 20 Oct 2023 17:59:50 +0800 Message-ID: <20231020095952.11055-4-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20231020095952.11055-1-linyunsheng@huawei.com> References: <20231020095952.11055-1-linyunsheng@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Currently page pool supports the below use cases: use case 1: allocate page without page splitting using page_pool_alloc_pages() API if the driver knows that the memory it need is always bigger than half of the page allocated from page pool. use case 2: allocate page frag with page splitting using page_pool_alloc_frag() API if the driver knows that the memory it need is always smaller than or equal to the half of the page allocated from page pool. There is emerging use case [1] & [2] that is a mix of the above two case: the driver doesn't know the size of memory it need beforehand, so the driver may use something like below to allocate memory with least memory utilization and performance penalty: if (size << 1 > max_size) page =3D page_pool_alloc_pages(); else page =3D page_pool_alloc_frag(); To avoid the driver doing something like above, add the page_pool_alloc() API to support the above use case, and update the true size of memory that is acctually allocated by updating '*size' back to the driver in order to avoid exacerbating truesize underestimate problem. Rename page_pool_free() which is used in the destroy process to __page_pool_destroy() to avoid confusion with the newly added API. 1. https://lore.kernel.org/all/d3ae6bd3537fbce379382ac6a42f67e22f27ece2.168= 3896626.git.lorenzo@kernel.org/ 2. https://lore.kernel.org/all/20230526054621.18371-3-liangchen.linux@gmail= .com/ Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Alexander Lobakin --- include/net/page_pool/helpers.h | 66 +++++++++++++++++++++++++++++++++ net/core/page_pool.c | 4 +- 2 files changed, 68 insertions(+), 2 deletions(-) diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helper= s.h index 759489c037c7..1b76e05dc4d2 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -82,6 +82,66 @@ static inline struct page *page_pool_dev_alloc_frag(stru= ct page_pool *pool, return page_pool_alloc_frag(pool, offset, size, gfp); } =20 +static inline struct page *page_pool_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) +{ + unsigned int max_size =3D PAGE_SIZE << pool->p.order; + struct page *page; + + if ((*size << 1) > max_size) { + *size =3D max_size; + *offset =3D 0; + return page_pool_alloc_pages(pool, gfp); + } + + page =3D page_pool_alloc_frag(pool, offset, *size, gfp); + if (unlikely(!page)) + return NULL; + + /* There is very likely not enough space for another fragment, so append + * the remaining size to the current fragment to avoid truesize + * underestimate problem. + */ + if (pool->frag_offset + *size > max_size) { + *size =3D max_size - *offset; + pool->frag_offset =3D max_size; + } + + return page; +} + +static inline struct page *page_pool_dev_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size) +{ + gfp_t gfp =3D (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc(pool, offset, size, gfp); +} + +static inline void *page_pool_alloc_va(struct page_pool *pool, + unsigned int *size, gfp_t gfp) +{ + unsigned int offset; + struct page *page; + + /* Mask off __GFP_HIGHMEM to ensure we can use page_address() */ + page =3D page_pool_alloc(pool, &offset, size, gfp & ~__GFP_HIGHMEM); + if (unlikely(!page)) + return NULL; + + return page_address(page) + offset; +} + +static inline void *page_pool_dev_alloc_va(struct page_pool *pool, + unsigned int *size) +{ + gfp_t gfp =3D (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_va(pool, size, gfp); +} + /** * page_pool_get_dma_dir() - Retrieve the stored DMA direction. * @pool: pool from which page was allocated @@ -221,6 +281,12 @@ static inline void page_pool_recycle_direct(struct pag= e_pool *pool, #define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA \ (sizeof(dma_addr_t) > sizeof(unsigned long)) =20 +static inline void page_pool_free_va(struct page_pool *pool, void *va, + bool allow_direct) +{ + page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct); +} + /** * page_pool_get_dma_addr() - Retrieve the stored DMA address. * @page: page allocated from a page pool diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 2a3671c97ca7..5e409b98aba0 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -809,7 +809,7 @@ static void page_pool_empty_ring(struct page_pool *pool) } } =20 -static void page_pool_free(struct page_pool *pool) +static void __page_pool_destroy(struct page_pool *pool) { if (pool->disconnect) pool->disconnect(pool); @@ -860,7 +860,7 @@ static int page_pool_release(struct page_pool *pool) page_pool_scrub(pool); inflight =3D page_pool_inflight(pool); if (!inflight) - page_pool_free(pool); + __page_pool_destroy(pool); =20 return inflight; } --=20 2.33.0 From nobody Thu Nov 14 05:20:20 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7D9FAC004C0 for ; Fri, 20 Oct 2023 09:59:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1376760AbjJTJ7w (ORCPT ); Fri, 20 Oct 2023 05:59:52 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52900 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1376871AbjJTJ7q (ORCPT ); Fri, 20 Oct 2023 05:59:46 -0400 Received: from szxga08-in.huawei.com (szxga08-in.huawei.com [45.249.212.255]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 04BA5D8; Fri, 20 Oct 2023 02:59:35 -0700 (PDT) Received: from dggpemm500005.china.huawei.com (unknown [172.30.72.54]) by szxga08-in.huawei.com (SkyGuard) with ESMTP id 4SBg3M5WlYz15NgH; Fri, 20 Oct 2023 17:56:47 +0800 (CST) Received: from localhost.localdomain (10.69.192.56) by dggpemm500005.china.huawei.com (7.185.36.74) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.31; Fri, 20 Oct 2023 17:59:32 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Lorenzo Bianconi , Alexander Duyck , Liang Chen , Alexander Lobakin , Dima Tisnek , Jesper Dangaard Brouer , Ilias Apalodimas , Eric Dumazet , Jonathan Corbet , Alexei Starovoitov , Daniel Borkmann , John Fastabend , , Subject: [PATCH net-next v12 4/5] page_pool: update document about fragment API Date: Fri, 20 Oct 2023 17:59:51 +0800 Message-ID: <20231020095952.11055-5-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20231020095952.11055-1-linyunsheng@huawei.com> References: <20231020095952.11055-1-linyunsheng@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" As more drivers begin to use the fragment API, update the document about how to decide which API to use for the driver author. Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Alexander Lobakin CC: Dima Tisnek --- Documentation/networking/page_pool.rst | 4 +- include/net/page_pool/helpers.h | 93 ++++++++++++++++++++++---- 2 files changed, 83 insertions(+), 14 deletions(-) diff --git a/Documentation/networking/page_pool.rst b/Documentation/network= ing/page_pool.rst index 215ebc92752c..60993cb56b32 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -58,7 +58,9 @@ a page will cause no race conditions is enough. =20 .. kernel-doc:: include/net/page_pool/helpers.h :identifiers: page_pool_put_page page_pool_put_full_page - page_pool_recycle_direct page_pool_dev_alloc_pages + page_pool_recycle_direct page_pool_free_va + page_pool_dev_alloc_pages page_pool_dev_alloc_frag + page_pool_dev_alloc page_pool_dev_alloc_va page_pool_get_dma_addr page_pool_get_dma_dir =20 .. kernel-doc:: net/core/page_pool.c diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helper= s.h index 1b76e05dc4d2..4ebd544ae977 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -8,23 +8,46 @@ /** * DOC: page_pool allocator * - * The page_pool allocator is optimized for the XDP mode that - * uses one frame per-page, but it can fallback on the - * regular page allocator APIs. + * The page_pool allocator is optimized for recycling page or page fragmen= t used + * by skb packet and xdp frame. * - * Basic use involves replacing alloc_pages() calls with the - * page_pool_alloc_pages() call. Drivers should use - * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). + * Basic use involves replacing and alloc_pages() calls with page_pool_all= oc(), + * which allocate memory with or without page splitting depending on the + * requested memory size. * - * The API keeps track of in-flight pages, in order to let API users know - * when it is safe to free a page_pool object. Thus, API users - * must call page_pool_put_page() to free the page, or attach - * the page to a page_pool-aware object like skbs marked with + * If the driver knows that it always requires full pages or its allocatio= ns are + * always smaller than half a page, it can use one of the more specific API + * calls: + * + * 1. page_pool_alloc_pages(): allocate memory without page splitting when + * driver knows that the memory it need is always bigger than half of the = page + * allocated from page pool. There is no cache line dirtying for 'struct p= age' + * when a page is recycled back to the page pool. + * + * 2. page_pool_alloc_frag(): allocate memory with page splitting when dri= ver + * knows that the memory it need is always smaller than or equal to half o= f the + * page allocated from page pool. Page splitting enables memory saving and= thus + * avoids TLB/cache miss for data access, but there also is some cost to + * implement page splitting, mainly some cache line dirtying/bouncing for + * 'struct page' and atomic operation for page->pp_frag_count. + * + * The API keeps track of in-flight pages, in order to let API users know = when + * it is safe to free a page_pool object, the API users must call + * page_pool_put_page() or page_pool_free_va() to free the page_pool objec= t, or + * attach the page_pool object to a page_pool-aware object like skbs marke= d with * skb_mark_for_recycle(). * - * API users must call page_pool_put_page() once on a page, as it - * will either recycle the page, or in case of refcnt > 1, it will - * release the DMA mapping and in-flight state accounting. + * page_pool_put_page() may be called multi times on the same page if a pa= ge is + * split into multi fragments. For the last fragment, it will either recyc= le the + * page, or in case of page->_refcount > 1, it will release the DMA mappin= g and + * in-flight state accounting. + * + * dma_sync_single_range_for_device() is only called for the last fragment= when + * page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on t= he + * last freed fragment to do the sync_for_device operation for all fragmen= ts in + * the same page when a page is split, the API user must setup pool->p.max= _len + * and pool->p.offset correctly and ensure that page_pool_put_page() is ca= lled + * with dma_sync_size being -1 for fragment API. */ #ifndef _NET_PAGE_POOL_HELPERS_H #define _NET_PAGE_POOL_HELPERS_H @@ -73,6 +96,17 @@ static inline struct page *page_pool_dev_alloc_pages(str= uct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } =20 +/** + * page_pool_dev_alloc_frag() - allocate a page fragment. + * @pool: pool from which to allocate + * @offset: offset to the allocated page + * @size: requested size + * + * Get a page fragment from the page allocator or page_pool caches. + * + * Return: + * Return allocated page fragment, otherwise return NULL. + */ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size) @@ -111,6 +145,19 @@ static inline struct page *page_pool_alloc(struct page= _pool *pool, return page; } =20 +/** + * page_pool_dev_alloc() - allocate a page or a page fragment. + * @pool: pool from which to allocate + * @offset: offset to the allocated page + * @size: in as the requested size, out as the allocated size + * + * Get a page or a page fragment from the page allocator or page_pool cach= es + * depending on the requested size in order to allocate memory with least = memory + * utilization and performance penalty. + * + * Return: + * Return allocated page or page fragment, otherwise return NULL. + */ static inline struct page *page_pool_dev_alloc(struct page_pool *pool, unsigned int *offset, unsigned int *size) @@ -134,6 +181,18 @@ static inline void *page_pool_alloc_va(struct page_poo= l *pool, return page_address(page) + offset; } =20 +/** + * page_pool_dev_alloc_va() - allocate a page or a page fragment and retur= n its + * va. + * @pool: pool from which to allocate + * @size: in as the requested size, out as the allocated size + * + * This is just a thin wrapper around the page_pool_alloc() API, and + * it returns va of the allocated page or page fragment. + * + * Return: + * Return the va for the allocated page or page fragment, otherwise return= NULL. + */ static inline void *page_pool_dev_alloc_va(struct page_pool *pool, unsigned int *size) { @@ -281,6 +340,14 @@ static inline void page_pool_recycle_direct(struct pag= e_pool *pool, #define PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA \ (sizeof(dma_addr_t) > sizeof(unsigned long)) =20 +/** + * page_pool_free_va() - free a va into the page_pool + * @pool: pool from which va was allocated + * @va: va to be freed + * @allow_direct: freed by the consumer, allow lockless caching + * + * Free a va allocated from page_pool_allo_va(). + */ static inline void page_pool_free_va(struct page_pool *pool, void *va, bool allow_direct) { --=20 2.33.0 From nobody Thu Nov 14 05:20:20 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 760E0C001DF for ; Fri, 20 Oct 2023 10:00:03 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1376926AbjJTKAA (ORCPT ); Fri, 20 Oct 2023 06:00:00 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52874 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1376878AbjJTJ7s (ORCPT ); Fri, 20 Oct 2023 05:59:48 -0400 Received: from szxga01-in.huawei.com (szxga01-in.huawei.com [45.249.212.187]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3389BD66; Fri, 20 Oct 2023 02:59:38 -0700 (PDT) Received: from dggpemm500005.china.huawei.com (unknown [172.30.72.56]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4SBg136Nf6zcd6k; Fri, 20 Oct 2023 17:54:47 +0800 (CST) Received: from localhost.localdomain (10.69.192.56) by dggpemm500005.china.huawei.com (7.185.36.74) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.31; Fri, 20 Oct 2023 17:59:34 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Lorenzo Bianconi , Alexander Duyck , Liang Chen , Alexander Lobakin , Eric Dumazet , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , Subject: [PATCH net-next v12 5/5] net: veth: use newly added page pool API for veth with xdp Date: Fri, 20 Oct 2023 17:59:52 +0800 Message-ID: <20231020095952.11055-6-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20231020095952.11055-1-linyunsheng@huawei.com> References: <20231020095952.11055-1-linyunsheng@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems704-chm.china.huawei.com (10.3.19.181) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Use page_pool_alloc() API to allocate memory with least memory utilization and performance penalty. Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Alexander Lobakin --- drivers/net/veth.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0deefd1573cf..9980517ed8b0 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -737,10 +737,11 @@ static int veth_convert_skb_to_xdp_buff(struct veth_r= q *rq, if (skb_shared(skb) || skb_head_is_locked(skb) || skb_shinfo(skb)->nr_frags || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - u32 size, len, max_head_size, off; + u32 size, len, max_head_size, off, truesize, page_offset; struct sk_buff *nskb; struct page *page; int i, head_off; + void *va; =20 /* We need a private copy of the skb and data buffers since * the ebpf program can modify it. We segment the original skb @@ -753,14 +754,17 @@ static int veth_convert_skb_to_xdp_buff(struct veth_r= q *rq, if (skb->len > PAGE_SIZE * MAX_SKB_FRAGS + max_head_size) goto drop; =20 + size =3D min_t(u32, skb->len, max_head_size); + truesize =3D SKB_HEAD_ALIGN(size) + VETH_XDP_HEADROOM; + /* Allocate skb head */ - page =3D page_pool_dev_alloc_pages(rq->page_pool); - if (!page) + va =3D page_pool_dev_alloc_va(rq->page_pool, &truesize); + if (!va) goto drop; =20 - nskb =3D napi_build_skb(page_address(page), PAGE_SIZE); + nskb =3D napi_build_skb(va, truesize); if (!nskb) { - page_pool_put_full_page(rq->page_pool, page, true); + page_pool_free_va(rq->page_pool, va, true); goto drop; } =20 @@ -768,7 +772,6 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq = *rq, skb_copy_header(nskb, skb); skb_mark_for_recycle(nskb); =20 - size =3D min_t(u32, skb->len, max_head_size); if (skb_copy_bits(skb, 0, nskb->data, size)) { consume_skb(nskb); goto drop; @@ -783,14 +786,18 @@ static int veth_convert_skb_to_xdp_buff(struct veth_r= q *rq, len =3D skb->len - off; =20 for (i =3D 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { - page =3D page_pool_dev_alloc_pages(rq->page_pool); + size =3D min_t(u32, len, PAGE_SIZE); + truesize =3D size; + + page =3D page_pool_dev_alloc(rq->page_pool, &page_offset, + &truesize); if (!page) { consume_skb(nskb); goto drop; } =20 - size =3D min_t(u32, len, PAGE_SIZE); - skb_add_rx_frag(nskb, i, page, 0, size, PAGE_SIZE); + skb_add_rx_frag(nskb, i, page, page_offset, size, + truesize); if (skb_copy_bits(skb, off, page_address(page), size)) { consume_skb(nskb); --=20 2.33.0