From patchwork Tue Jul 13 09:24:29 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 477343 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 96AD2C11F68 for ; Tue, 13 Jul 2021 09:25:23 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8135660698 for ; Tue, 13 Jul 2021 09:25:23 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234819AbhGMJ2M (ORCPT ); Tue, 13 Jul 2021 05:28:12 -0400 Received: from szxga02-in.huawei.com ([45.249.212.188]:6919 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235118AbhGMJ2H (ORCPT ); Tue, 13 Jul 2021 05:28:07 -0400 Received: from dggemv711-chm.china.huawei.com (unknown [172.30.72.54]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4GPFWV4XC0z7Byv; Tue, 13 Jul 2021 17:21:42 +0800 (CST) Received: from dggpemm500005.china.huawei.com (7.185.36.74) by dggemv711-chm.china.huawei.com (10.1.198.66) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2176.2; Tue, 13 Jul 2021 17:25:12 +0800 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 15.1.2176.2; Tue, 13 Jul 2021 17:25:12 +0800 From: Yunsheng Lin To: , CC: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , Subject: [PATCH rfc v4 1/4] page_pool: keep pp info as long as page pool owns the page Date: Tue, 13 Jul 2021 17:24:29 +0800 Message-ID: <1626168272-25622-2-git-send-email-linyunsheng@huawei.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> References: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems703-chm.china.huawei.com (10.3.19.180) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Currently, page->pp is cleared and set everytime the page is recycled, which is unnecessary. So only set the page->pp when the page is added to the page pool and only clear it when the page is released from the page pool. This is also a preparation to support allocating frag page in page pool. Signed-off-by: Yunsheng Lin --- drivers/net/ethernet/marvell/mvneta.c | 6 +----- drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +- drivers/net/ethernet/ti/cpsw.c | 2 +- drivers/net/ethernet/ti/cpsw_new.c | 2 +- include/linux/skbuff.h | 4 +--- include/net/page_pool.h | 7 ------- net/core/page_pool.c | 21 +++++++++++++++++---- 7 files changed, 22 insertions(+), 22 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 361bc4f..89bf31fd 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2327,7 +2327,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, if (!skb) return ERR_PTR(-ENOMEM); - skb_mark_for_recycle(skb, virt_to_page(xdp->data), pool); + skb_mark_for_recycle(skb); skb_reserve(skb, xdp->data - xdp->data_hard_start); skb_put(skb, xdp->data_end - xdp->data); @@ -2339,10 +2339,6 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool, skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(frag), skb_frag_off(frag), skb_frag_size(frag), PAGE_SIZE); - /* We don't need to reset pp_recycle here. It's already set, so - * just mark fragments for recycling. - */ - page_pool_store_mem_info(skb_frag_page(frag), pool); } return skb; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 3229baf..320eddb 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3995,7 +3995,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi, } if (pp) - skb_mark_for_recycle(skb, page, pp); + skb_mark_for_recycle(skb); else dma_unmap_single_attrs(dev->dev.parent, dma_addr, bm_pool->buf_size, DMA_FROM_DEVICE, diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index cbbd0f6..9d59143 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -431,7 +431,7 @@ static void cpsw_rx_handler(void *token, int len, int status) skb->protocol = eth_type_trans(skb, ndev); /* mark skb for recycling */ - skb_mark_for_recycle(skb, page, pool); + skb_mark_for_recycle(skb); netif_receive_skb(skb); ndev->stats.rx_bytes += len; diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 57d279f..a4234a3 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -374,7 +374,7 @@ static void cpsw_rx_handler(void *token, int len, int status) skb->protocol = eth_type_trans(skb, ndev); /* mark skb for recycling */ - skb_mark_for_recycle(skb, page, pool); + skb_mark_for_recycle(skb); netif_receive_skb(skb); ndev->stats.rx_bytes += len; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index b2db9cd..7795979 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4711,11 +4711,9 @@ static inline u64 skb_get_kcov_handle(struct sk_buff *skb) } #ifdef CONFIG_PAGE_POOL -static inline void skb_mark_for_recycle(struct sk_buff *skb, struct page *page, - struct page_pool *pp) +static inline void skb_mark_for_recycle(struct sk_buff *skb) { skb->pp_recycle = 1; - page_pool_store_mem_info(page, pp); } #endif diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3dd62dd..8d7744d 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -253,11 +253,4 @@ static inline void page_pool_ring_unlock(struct page_pool *pool) spin_unlock_bh(&pool->ring.producer_lock); } -/* Store mem_info on struct page and use it while recycling skb frags */ -static inline -void page_pool_store_mem_info(struct page *page, struct page_pool *pp) -{ - page->pp = pp; -} - #endif /* _NET_PAGE_POOL_H */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 5e4eb45..78838c6 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -206,6 +206,19 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) return true; } +static void page_pool_set_pp_info(struct page_pool *pool, + struct page *page) +{ + page->pp = pool; + page->pp_magic |= PP_SIGNATURE; +} + +static void page_pool_clear_pp_info(struct page *page) +{ + page->pp_magic = 0; + page->pp = NULL; +} + static struct page *__page_pool_alloc_page_order(struct page_pool *pool, gfp_t gfp) { @@ -222,7 +235,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool, return NULL; } - page->pp_magic |= PP_SIGNATURE; + page_pool_set_pp_info(pool, page); /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -266,7 +279,8 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, put_page(page); continue; } - page->pp_magic |= PP_SIGNATURE; + + page_pool_set_pp_info(pool, page); pool->alloc.cache[pool->alloc.count++] = page; /* Track how many pages are held 'in-flight' */ pool->pages_state_hold_cnt++; @@ -345,7 +359,7 @@ void page_pool_release_page(struct page_pool *pool, struct page *page) DMA_ATTR_SKIP_CPU_SYNC); page_pool_set_dma_addr(page, 0); skip_dma_unmap: - page->pp_magic = 0; + page_pool_clear_pp_info(page); /* This may be the last page returned, releasing the pool, so * it is not safe to reference pool afterwards. @@ -644,7 +658,6 @@ bool page_pool_return_skb_page(struct page *page) * The page will be returned to the pool here regardless of the * 'flipped' fragment being in use or not. */ - page->pp = NULL; page_pool_put_full_page(pp, page, false); return true; From patchwork Tue Jul 13 09:24:30 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 475092 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id AA906C11F67 for ; Tue, 13 Jul 2021 09:25:22 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 8ED1660FF1 for ; Tue, 13 Jul 2021 09:25:22 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235144AbhGMJ2H (ORCPT ); Tue, 13 Jul 2021 05:28:07 -0400 Received: from szxga01-in.huawei.com ([45.249.212.187]:15008 "EHLO szxga01-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234855AbhGMJ2F (ORCPT ); Tue, 13 Jul 2021 05:28:05 -0400 Received: from dggemv704-chm.china.huawei.com (unknown [172.30.72.53]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4GPFWm3b2DzbbwG; Tue, 13 Jul 2021 17:21:56 +0800 (CST) Received: from dggpemm500005.china.huawei.com (7.185.36.74) by dggemv704-chm.china.huawei.com (10.3.19.47) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2176.2; Tue, 13 Jul 2021 17:25:13 +0800 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 15.1.2176.2; Tue, 13 Jul 2021 17:25:12 +0800 From: Yunsheng Lin To: , CC: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , Subject: [PATCH rfc v4 2/4] page_pool: add interface to manipulate bias in page pool Date: Tue, 13 Jul 2021 17:24:30 +0800 Message-ID: <1626168272-25622-3-git-send-email-linyunsheng@huawei.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> References: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems703-chm.china.huawei.com (10.3.19.180) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org As suggested by Alexander, "A DMA mapping should be page aligned anyway so the lower 12 bits would be reserved 0", so it might make more sense to repurpose the lower 12 bits of the dma address to store the bias for frag page support in page pool for 32 bit systems with 64 bit dma, which should be rare those days. For normal system, the dma_addr[1] in 'struct page' is not used, so we can reuse the dma_addr[1] for storing bias. The PAGE_POOP_USE_DMA_ADDR_1 macro is used to decide where to store the bias, as the "sizeof(dma_addr_t) > sizeof( unsigned long)" is false for normal system, so hopefully the compiler will optimize out the unused code for those system. The newly added page_pool_set_bias() should be called before the page is passed to any user. Otherwise, call the newly added page_pool_atomic_sub_bias_return(). Signed-off-by: Yunsheng Lin --- include/net/page_pool.h | 70 ++++++++++++++++++++++++++++++++++++++++++++++--- net/core/page_pool.c | 10 +++++++ 2 files changed, 77 insertions(+), 3 deletions(-) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 8d7744d..315b9f2 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -198,21 +198,85 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOP_USE_DMA_ADDR_1 (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - dma_addr_t ret = page->dma_addr[0]; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) + dma_addr_t ret; + + if (PAGE_POOP_USE_DMA_ADDR_1) { + ret = READ_ONCE(page->dma_addr[0]) & PAGE_MASK; ret |= (dma_addr_t)page->dma_addr[1] << 16 << 16; + } else { + ret = page->dma_addr[0]; + } + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr[0] = addr; - if (sizeof(dma_addr_t) > sizeof(unsigned long)) + if (PAGE_POOP_USE_DMA_ADDR_1) page->dma_addr[1] = upper_32_bits(addr); } +static inline int page_pool_atomic_sub_bias_return(struct page *page, int nr) +{ + int bias; + + if (PAGE_POOP_USE_DMA_ADDR_1) { + unsigned long *bias_ptr = &page->dma_addr[0]; + unsigned long old_bias = READ_ONCE(*bias_ptr); + unsigned long new_bias; + + do { + bias = (int)(old_bias & ~PAGE_MASK); + + /* Warn when page_pool_dev_alloc_pages() is called + * with PP_FLAG_PAGE_FRAG flag in driver. + */ + WARN_ON(!bias); + + /* already the last user */ + if (!(bias - nr)) + return 0; + + new_bias = old_bias - nr; + } while (!try_cmpxchg(bias_ptr, &old_bias, new_bias)); + + WARN_ON((new_bias & PAGE_MASK) != (old_bias & PAGE_MASK)); + + bias = new_bias & ~PAGE_MASK; + } else { + atomic_t *v = (atomic_t *)&page->dma_addr[1]; + + if (atomic_read(v) == nr) + return 0; + + bias = atomic_sub_return(nr, v); + WARN_ON(bias < 0); + } + + return bias; +} + +static inline void page_pool_set_bias(struct page *page, int bias) +{ + if (PAGE_POOP_USE_DMA_ADDR_1) { + unsigned long dma_addr_0 = READ_ONCE(page->dma_addr[0]); + + dma_addr_0 &= PAGE_MASK; + dma_addr_0 |= bias; + + WRITE_ONCE(page->dma_addr[0], dma_addr_0); + } else { + atomic_t *v = (atomic_t *)&page->dma_addr[1]; + + atomic_set(v, bias); + } +} + static inline bool is_page_pool_compiled_in(void) { #ifdef CONFIG_PAGE_POOL diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 78838c6..6ac5b00 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -198,6 +198,16 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page) if (dma_mapping_error(pool->p.dev, dma)) return false; + if (PAGE_POOP_USE_DMA_ADDR_1 && + WARN_ON(pool->p.flags & PP_FLAG_PAGE_FRAG && + dma & ~PAGE_MASK)) { + dma_unmap_page_attrs(pool->p.dev, dma, + PAGE_SIZE << pool->p.order, + pool->p.dma_dir, + DMA_ATTR_SKIP_CPU_SYNC); + return false; + } + page_pool_set_dma_addr(page, dma); if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV) From patchwork Tue Jul 13 09:24:31 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 477344 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 32FCEC07E95 for ; Tue, 13 Jul 2021 09:25:21 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 1BB2660698 for ; Tue, 13 Jul 2021 09:25:21 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235181AbhGMJ2J (ORCPT ); Tue, 13 Jul 2021 05:28:09 -0400 Received: from szxga02-in.huawei.com ([45.249.212.188]:10474 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234947AbhGMJ2F (ORCPT ); Tue, 13 Jul 2021 05:28:05 -0400 Received: from dggemv703-chm.china.huawei.com (unknown [172.30.72.57]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4GPFWm4klhzccwf; Tue, 13 Jul 2021 17:21:56 +0800 (CST) Received: from dggpemm500005.china.huawei.com (7.185.36.74) by dggemv703-chm.china.huawei.com (10.3.19.46) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2176.2; Tue, 13 Jul 2021 17:25:13 +0800 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 15.1.2176.2; Tue, 13 Jul 2021 17:25:12 +0800 From: Yunsheng Lin To: , CC: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , Subject: [PATCH rfc v4 3/4] page_pool: add frag page recycling support in page pool Date: Tue, 13 Jul 2021 17:24:31 +0800 Message-ID: <1626168272-25622-4-git-send-email-linyunsheng@huawei.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> References: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems703-chm.china.huawei.com (10.3.19.180) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Currently page pool only support page recycling only when there is only one user of the page, and the split page reusing implemented in the most driver can not use the page pool as bing-pong way of reusing requires the multi user support in page pool. Those reusing or recycling has below limitations: 1. page from page pool can only be used be one user in order for the page recycling to happen. 2. Bing-pong way of reusing in most driver does not support multi desc using different part of the same page in order to save memory. So add multi-users support and frag page recycling in page pool to overcome the above limitation. Signed-off-by: Yunsheng Lin --- include/net/page_pool.h | 22 +++++++++- net/core/page_pool.c | 104 ++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 112 insertions(+), 14 deletions(-) diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 315b9f2..dd4bb90 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -45,7 +45,10 @@ * Please note DMA-sync-for-CPU is still * device driver responsibility */ -#define PP_FLAG_ALL (PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV) +#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) /* * Fast allocation side cache array/stack @@ -88,6 +91,9 @@ struct page_pool { unsigned long defer_warn; u32 pages_state_hold_cnt; + unsigned int frag_offset; + int frag_bias; + struct page *frag_page; /* * Data structure for allocation side @@ -137,6 +143,20 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } +struct page *page_pool_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size, + gfp_t gfp); + +static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_frag(pool, offset, size, gfp); +} + /* get the stored dma direction. A driver might decide to treat this locally and * avoid the extra cache line from page_pool to determine the direction */ diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 6ac5b00..d172777 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -24,6 +24,8 @@ #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) +#define BIAS_MAX (PAGE_SIZE - 1) + static int page_pool_init(struct page_pool *pool, const struct page_pool_params *params) { @@ -67,6 +69,14 @@ static int page_pool_init(struct page_pool *pool, */ } + /* Make sure there is at least one bias left as we depend on that + * to ensure the frag page is reserved to serve more users. + */ + if (pool->p.flags & PP_FLAG_PAGE_FRAG && + (PAGE_SIZE << pool->p.order > + dma_get_cache_alignment() * (BIAS_MAX - 1))) + return -EINVAL; + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) return -ENOMEM; @@ -429,6 +439,11 @@ static __always_inline struct page * __page_pool_put_page(struct page_pool *pool, struct page *page, unsigned int dma_sync_size, bool allow_direct) { + /* It is not the last user for the page frag case */ + if (pool->p.flags & PP_FLAG_PAGE_FRAG && + page_pool_atomic_sub_bias_return(page, 1)) + return NULL; + /* This allocator is optimized for the XDP mode that uses * one-frame-per-page, but have fallbacks that act like the * regular page allocator APIs. @@ -452,19 +467,7 @@ __page_pool_put_page(struct page_pool *pool, struct page *page, /* Page found as candidate for recycling */ return page; } - /* Fallback/non-XDP mode: API user have elevated refcnt. - * - * Many drivers split up the page into fragments, and some - * want to keep doing this to save memory and do refcnt based - * recycling. Support this use case too, to ease drivers - * switching between XDP/non-XDP. - * - * In-case page_pool maintains the DMA mapping, API user must - * call page_pool_put_page once. In this elevated refcnt - * case, the DMA is unmapped/released, as driver is likely - * doing refcnt based recycle tricks, meaning another process - * will be invoking put_page. - */ + /* Do not replace this with page_pool_return_page() */ page_pool_release_page(pool, page); put_page(page); @@ -521,6 +524,79 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, } EXPORT_SYMBOL(page_pool_put_page_bulk); +static struct page *page_pool_drain_frag(struct page_pool *pool, + struct page *page) +{ + /* page pool is not the last user */ + if (page_pool_atomic_sub_bias_return(page, + BIAS_MAX - pool->frag_bias)) + return NULL; + + if (likely(page_ref_count(page) == 1 && + !page_is_pfmemalloc(page))) + return page; + + page_pool_return_page(pool, page); + return NULL; +} + +static void page_pool_free_frag(struct page_pool *pool) +{ + struct page *page = pool->frag_page; + + if (!page || + page_pool_atomic_sub_bias_return(page, + BIAS_MAX - pool->frag_bias)) + return; + + page_pool_return_page(pool, page); + pool->frag_page = NULL; +} + +struct page *page_pool_alloc_frag(struct page_pool *pool, + unsigned int *offset, + unsigned int size, + gfp_t gfp) +{ + unsigned int max_size = PAGE_SIZE << pool->p.order; + unsigned int frag_offset = pool->frag_offset; + struct page *frag_page = pool->frag_page; + + if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) || + size > max_size)) + return NULL; + + size = ALIGN(size, dma_get_cache_alignment()); + + if (frag_page && frag_offset + size > max_size) { + frag_page = page_pool_drain_frag(pool, frag_page); + if (frag_page) + goto frag_reset; + } + + if (!frag_page) { + frag_page = page_pool_alloc_pages(pool, gfp); + if (unlikely(!frag_page)) { + pool->frag_page = NULL; + return NULL; + } + + pool->frag_page = frag_page; + +frag_reset: + pool->frag_bias = 0; + frag_offset = 0; + page_pool_set_bias(frag_page, BIAS_MAX); + } + + pool->frag_bias++; + *offset = frag_offset; + pool->frag_offset = frag_offset + size; + + return frag_page; +} +EXPORT_SYMBOL(page_pool_alloc_frag); + static void page_pool_empty_ring(struct page_pool *pool) { struct page *page; @@ -626,6 +702,8 @@ void page_pool_destroy(struct page_pool *pool) if (!page_pool_put(pool)) return; + page_pool_free_frag(pool); + if (!page_pool_release(pool)) return; From patchwork Tue Jul 13 09:24:32 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 475091 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 02F5EC07E96 for ; Tue, 13 Jul 2021 09:25:31 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E320E60FF1 for ; Tue, 13 Jul 2021 09:25:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S235238AbhGMJ2S (ORCPT ); Tue, 13 Jul 2021 05:28:18 -0400 Received: from szxga02-in.huawei.com ([45.249.212.188]:6920 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S235209AbhGMJ2P (ORCPT ); Tue, 13 Jul 2021 05:28:15 -0400 Received: from dggemv711-chm.china.huawei.com (unknown [172.30.72.56]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4GPFWg6xfPz7C0B; Tue, 13 Jul 2021 17:21:51 +0800 (CST) Received: from dggpemm500005.china.huawei.com (7.185.36.74) by dggemv711-chm.china.huawei.com (10.1.198.66) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2176.2; Tue, 13 Jul 2021 17:25:13 +0800 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 15.1.2176.2; Tue, 13 Jul 2021 17:25:13 +0800 From: Yunsheng Lin To: , CC: , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , Subject: [PATCH rfc v4 4/4] net: hns3: support skb's frag page recycling based on page pool Date: Tue, 13 Jul 2021 17:24:32 +0800 Message-ID: <1626168272-25622-5-git-send-email-linyunsheng@huawei.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> References: <1626168272-25622-1-git-send-email-linyunsheng@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems703-chm.china.huawei.com (10.3.19.180) To dggpemm500005.china.huawei.com (7.185.36.74) X-CFilter-Loop: Reflected Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org This patch adds skb's frag page recycling support based on the elevated refcnt support in page pool. The performance improves above 10~20% with IOMMU disabled. The performance improves about 200% when IOMMU is enabled and iperf server shares the same cpu with irq/NAPI. Signed-off-by: Yunsheng Lin --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 79 +++++++++++++++++++++++-- drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 3 + 2 files changed, 77 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cdb5f14..c799129 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -3205,6 +3205,21 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring, unsigned int order = hns3_page_order(ring); struct page *p; + if (ring->page_pool) { + p = page_pool_dev_alloc_frag(ring->page_pool, + &cb->page_offset, + hns3_buf_size(ring)); + if (unlikely(!p)) + return -ENOMEM; + + cb->priv = p; + cb->buf = page_address(p); + cb->dma = page_pool_get_dma_addr(p); + cb->type = DESC_TYPE_FRAG; + cb->reuse_flag = 0; + return 0; + } + p = dev_alloc_pages(order); if (!p) return -ENOMEM; @@ -3227,8 +3242,12 @@ static void hns3_free_buffer(struct hns3_enet_ring *ring, if (cb->type & (DESC_TYPE_SKB | DESC_TYPE_BOUNCE_HEAD | DESC_TYPE_BOUNCE_ALL | DESC_TYPE_SGL_SKB)) napi_consume_skb(cb->priv, budget); - else if (!HNAE3_IS_TX_RING(ring) && cb->pagecnt_bias) - __page_frag_cache_drain(cb->priv, cb->pagecnt_bias); + else if (!HNAE3_IS_TX_RING(ring)) { + if (cb->type & DESC_TYPE_PAGE && cb->pagecnt_bias) + __page_frag_cache_drain(cb->priv, cb->pagecnt_bias); + else if (cb->type & DESC_TYPE_FRAG) + page_pool_put_full_page(ring->page_pool, cb->priv, false); + } memset(cb, 0, sizeof(*cb)); } @@ -3315,7 +3334,7 @@ static int hns3_alloc_and_map_buffer(struct hns3_enet_ring *ring, int ret; ret = hns3_alloc_buffer(ring, cb); - if (ret) + if (ret || ring->page_pool) goto out; ret = hns3_map_buffer(ring, cb); @@ -3337,7 +3356,8 @@ static int hns3_alloc_and_attach_buffer(struct hns3_enet_ring *ring, int i) if (ret) return ret; - ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma); + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + + ring->desc_cb[i].page_offset); return 0; } @@ -3367,7 +3387,8 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i, { hns3_unmap_buffer(ring, &ring->desc_cb[i]); ring->desc_cb[i] = *res_cb; - ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma); + ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma + + ring->desc_cb[i].page_offset); ring->desc[i].rx.bd_base_info = 0; } @@ -3539,6 +3560,12 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, u32 frag_size = size - pull_len; bool reused; + if (ring->page_pool) { + skb_add_rx_frag(skb, i, desc_cb->priv, frag_offset, + frag_size, truesize); + return; + } + /* Avoid re-using remote or pfmem page */ if (unlikely(!dev_page_is_reusable(desc_cb->priv))) goto out; @@ -3856,6 +3883,9 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length, /* We can reuse buffer as-is, just make sure it is reusable */ if (dev_page_is_reusable(desc_cb->priv)) desc_cb->reuse_flag = 1; + else if (desc_cb->type & DESC_TYPE_FRAG) + page_pool_put_full_page(ring->page_pool, desc_cb->priv, + false); else /* This page cannot be reused so discard it */ __page_frag_cache_drain(desc_cb->priv, desc_cb->pagecnt_bias); @@ -3863,6 +3893,10 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length, hns3_rx_ring_move_fw(ring); return 0; } + + if (ring->page_pool) + skb_mark_for_recycle(skb); + u64_stats_update_begin(&ring->syncp); ring->stats.seg_pkt_cnt++; u64_stats_update_end(&ring->syncp); @@ -3901,6 +3935,10 @@ static int hns3_add_frag(struct hns3_enet_ring *ring) "alloc rx fraglist skb fail\n"); return -ENXIO; } + + if (ring->page_pool) + skb_mark_for_recycle(new_skb); + ring->frag_num = 0; if (ring->tail_skb) { @@ -4705,6 +4743,29 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv) priv->ring = NULL; } +static void hns3_alloc_page_pool(struct hns3_enet_ring *ring) +{ + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_PAGE_FRAG, + .order = hns3_page_order(ring), + .pool_size = ring->desc_num * hns3_buf_size(ring) / PAGE_SIZE, + .nid = dev_to_node(ring_to_dev(ring)), + .dev = ring_to_dev(ring), + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = 0, + }; + + ring->page_pool = page_pool_create(&pp_params); + if (IS_ERR(ring->page_pool)) { + dev_warn(ring_to_dev(ring), "page pool creation failed: %ld\n", + PTR_ERR(ring->page_pool)); + ring->page_pool = NULL; + } else { + dev_info(ring_to_dev(ring), "page pool creation succeeded\n"); + } +} + static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) { int ret; @@ -4724,6 +4785,8 @@ static int hns3_alloc_ring_memory(struct hns3_enet_ring *ring) goto out_with_desc_cb; if (!HNAE3_IS_TX_RING(ring)) { + hns3_alloc_page_pool(ring); + ret = hns3_alloc_ring_buffers(ring); if (ret) goto out_with_desc; @@ -4764,6 +4827,12 @@ void hns3_fini_ring(struct hns3_enet_ring *ring) devm_kfree(ring_to_dev(ring), tx_spare); ring->tx_spare = NULL; } + + if (!HNAE3_IS_TX_RING(ring) && ring->page_pool) { + page_pool_destroy(ring->page_pool); + ring->page_pool = NULL; + dev_info(ring_to_dev(ring), "page pool destroyed\n"); + } } static int hns3_buf_size2type(u32 buf_size) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 15af3d9..115c0ce 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -6,6 +6,7 @@ #include #include +#include #include "hnae3.h" @@ -307,6 +308,7 @@ enum hns3_desc_type { DESC_TYPE_BOUNCE_ALL = 1 << 3, DESC_TYPE_BOUNCE_HEAD = 1 << 4, DESC_TYPE_SGL_SKB = 1 << 5, + DESC_TYPE_FRAG = 1 << 6, }; struct hns3_desc_cb { @@ -451,6 +453,7 @@ struct hns3_enet_ring { struct hnae3_queue *tqp; int queue_index; struct device *dev; /* will be used for DMA mapping of descriptors */ + struct page_pool *page_pool; /* statistic */ struct ring_stats stats;