From patchwork Thu Dec 14 04:28:31 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Liang Chen X-Patchwork-Id: 13492265 X-Patchwork-Delegate: kuba@kernel.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="di7xwpMx" Received: from mail-oi1-x22a.google.com (mail-oi1-x22a.google.com [IPv6:2607:f8b0:4864:20::22a]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 241BD18C for ; Wed, 13 Dec 2023 20:30:01 -0800 (PST) Received: by mail-oi1-x22a.google.com with SMTP id 5614622812f47-3ba2e4ff6e1so475268b6e.3 for ; Wed, 13 Dec 2023 20:30:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1702528201; x=1703133001; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=opH6yKOFCq1stbhjGctisEs2u/geFWIQgreNUuYpY7M=; b=di7xwpMxvO6T6ut9WOCN+BdzD/5vH4Pv4BBz2VNYT21bnzs/oxKv+12P8WxpzXQx/5 ahHLZ4eTGBVNrmgF/4snJtEO1DRwq6Fn1gf4Bl+ktjGGdB5+veNzniUkJhvqFVlvKj77 yEM7fwJgdxC9n5RXjTYhZUvh+fSxWpYP2tKr52hFKmgne+/xzJf3ZWMuraigHWY/WvtO hL/n+UL1j7kdHVQ/aYuNIeIKe5z8yj7IEfteADmbh2UQvxTVFEBh5ElEV9RB0W9okRmU 71RK7I+YgssUzN24Ifj7XdA+qYHMvoMAdB6fvJ1gfjuYaxZOTMQGJz/yBUfyRl2ydWoZ DU2w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1702528201; x=1703133001; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=opH6yKOFCq1stbhjGctisEs2u/geFWIQgreNUuYpY7M=; b=QFwjmI/yVJen/8bO5le+FWFZyrqQcrOE/6UzK8Q5i5ndpLVAFV/FCIJh3BcQg8SqCW AuwvPQYry9BkNKQTrGWzvFin7I6LEn+rsnFVQn6ItvwNOVb+Qf1DO4KOrzxx04ju8jIi fQwt7RJsD1bezKZtZ2LH9BjZrZNHCqaBDXSbabcW6LFWSIRPkZDgoZcZY77w1yuZM1xR IKtjqFqvxpDTVpQWQRei1ykqhHwv7D63gmajP6oFswUg0Zb5QukWAXAGp6qqS/+7JlyV sFdLpdBDKfM8TgEhVGQ7pJ79kCgjHs9dn3OSAmriSIp1ZzENzsNF/C0r11heWDtoVC2j aRRQ== X-Gm-Message-State: AOJu0YwGh+JKaLF+23wBDIgmsTmXbCHaPKu2WCyMuyvZ0pwkjPXQjwc4 6pDI+x4kwmJbP1tRqRXPGDM= X-Google-Smtp-Source: AGHT+IHSq6tyRAQm9rDpjkg41FXCqzWiSEqWUK5GlYuKbUmJf1v17FW4NuGW4kDFUIVkGsgxTsMwOw== X-Received: by 2002:a05:6808:1924:b0:3b8:43d6:8cec with SMTP id bf36-20020a056808192400b003b843d68cecmr12400014oib.33.1702528200859; Wed, 13 Dec 2023 20:30:00 -0800 (PST) Received: from localhost.localdomain ([23.104.213.5]) by smtp.gmail.com with ESMTPSA id jg13-20020a17090326cd00b001cc8cf4ad16sm374412plb.246.2023.12.13.20.29.52 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Dec 2023 20:29:59 -0800 (PST) From: Liang Chen To: davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, hawk@kernel.org, ilias.apalodimas@linaro.org, linyunsheng@huawei.com Cc: netdev@vger.kernel.org, linux-mm@kvack.org, jasowang@redhat.com, almasrymina@google.com, liangchen.linux@gmail.com, Mina Almasry Subject: [PATCH net-next v10 2/4] page_pool: halve BIAS_MAX for multiple user references of a fragment Date: Thu, 14 Dec 2023 12:28:31 +0800 Message-Id: <20231214042833.21316-2-liangchen.linux@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20231214042833.21316-1-liangchen.linux@gmail.com> References: <20231214042833.21316-1-liangchen.linux@gmail.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org Up to now, we were only subtracting from the number of used page fragments to figure out when a page could be freed or recycled. A following patch introduces support for multiple users referencing the same fragment. So reduce the initial page fragments value to half to avoid overflowing. Signed-off-by: Liang Chen Reviewed-by: Yunsheng Lin Reviewed-by: Mina Almasry Reviewed-by: Ilias Apalodimas --- net/core/page_pool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 106220b1f89c..436f7ffea7b4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -26,7 +26,7 @@ #define DEFER_TIME (msecs_to_jiffies(1000)) #define DEFER_WARN_INTERVAL (60 * HZ) -#define BIAS_MAX LONG_MAX +#define BIAS_MAX (LONG_MAX >> 1) #ifdef CONFIG_PAGE_POOL_STATS /* alloc_stat_inc is intended to be used in softirq context */ From patchwork Thu Dec 14 04:28:32 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Liang Chen X-Patchwork-Id: 13492266 X-Patchwork-Delegate: kuba@kernel.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="AwVOsMH7" Received: from mail-oi1-x22f.google.com (mail-oi1-x22f.google.com [IPv6:2607:f8b0:4864:20::22f]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 6A7151988 for ; Wed, 13 Dec 2023 20:30:10 -0800 (PST) Received: by mail-oi1-x22f.google.com with SMTP id 5614622812f47-3b86f3cdca0so5879171b6e.3 for ; Wed, 13 Dec 2023 20:30:10 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1702528209; x=1703133009; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=12hd2wvEpjx1jjZIuoo9JjQkayQ2+EIXRatonagGrWk=; b=AwVOsMH75p3kWL73egN5UefaB9MwK+OcrF6mrobBEgAnP3vtBvzXEycVKitxmMP8gQ Ssugv2fRQ9Mu40AufkI0lHZ9ZLk81DAeHZ1uPRkupm1XlFFYP1PgWHXBCiWC4ka/YGmC bu4y0ZOtg96j678f6AXAyt8vqGhLoZqxQBD/JFQDzRbS2lLn62V0IEcymH6AXYXjNNvn ih1Tp2VGmn8Uezz2TYBaT76duZkEqJ7+b8BDYyUa/ISYi2p3AjqJyZk7uGAyvQpQ6kwv 3qxW0SOq+Uy6lyJW2PZJsIZoa6t1VNysltZjN1AgzUbwHSPnb84+VjwOx0v2AejDUGkC SAtg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1702528209; x=1703133009; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=12hd2wvEpjx1jjZIuoo9JjQkayQ2+EIXRatonagGrWk=; b=Z2LIPwgue9tlHIuC2zyx5buImOVCfiANi7em80lTLf6oifLEHf0QruNwsicXK4z8Zm RX4XnFp9w3UTaJvGEXawdhEBwQTJry+KzrHkKva3ASosWhBRW1AA4I4tIl2P1e0QeTne wDaEynWyeThVYwIWt1fHkQY+szXgo5W2RPK3SRawEoZbviOuhFdpdTLjiHrlWSW/QB5m ex1CtuOYsUF+XEOFyOEQM1Ltx+uMD52F1q9Q+XF9v5Zu7F3d3AqBSrkpcXMUdNN6qtnn +u4I3wW4bDxi8q3W4VvlV3u+vqiHwb7nEkVAxW+eQ2A08RXf4L+MoMsIJKDj28O+gfJ6 FWlQ== X-Gm-Message-State: AOJu0YzCu1UZWupd9obZsH1xwLxBeb5bADN81JySjVJUqZItEA0jMQ5j DKNJ64I9vR8yKDaz4JE5nKw= X-Google-Smtp-Source: AGHT+IH7q5x9Vj87mf/bYUzfkGpUbxYuGGkA/HlVXlnyegK4kal77EqDxUH5wCIoxGeRmD855seHEg== X-Received: by 2002:a05:6808:30a7:b0:3b9:d36e:53ff with SMTP id bl39-20020a05680830a700b003b9d36e53ffmr12302901oib.53.1702528209485; Wed, 13 Dec 2023 20:30:09 -0800 (PST) Received: from localhost.localdomain ([23.104.213.5]) by smtp.gmail.com with ESMTPSA id jg13-20020a17090326cd00b001cc8cf4ad16sm374412plb.246.2023.12.13.20.30.01 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Dec 2023 20:30:08 -0800 (PST) From: Liang Chen To: davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, hawk@kernel.org, ilias.apalodimas@linaro.org, linyunsheng@huawei.com Cc: netdev@vger.kernel.org, linux-mm@kvack.org, jasowang@redhat.com, almasrymina@google.com, liangchen.linux@gmail.com, Mina Almasry Subject: [PATCH net-next v10 3/4] skbuff: Add a function to check if a page belongs to page_pool Date: Thu, 14 Dec 2023 12:28:32 +0800 Message-Id: <20231214042833.21316-3-liangchen.linux@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20231214042833.21316-1-liangchen.linux@gmail.com> References: <20231214042833.21316-1-liangchen.linux@gmail.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org Wrap code for checking if a page is a page_pool page into a function for better readability and ease of reuse. Signed-off-by: Liang Chen Reviewed-by: Yunsheng Lin Reviewed-by: Ilias Apalodimas Reviewed-by: Mina Almasry --- net/core/skbuff.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index b157efea5dea..7e26b56cda38 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -890,6 +890,11 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } +static bool is_pp_page(struct page *page) +{ + return (page->pp_magic & ~0x3UL) == PP_SIGNATURE; +} + #if IS_ENABLED(CONFIG_PAGE_POOL) bool napi_pp_put_page(struct page *page, bool napi_safe) { @@ -905,7 +910,7 @@ bool napi_pp_put_page(struct page *page, bool napi_safe) * and page_is_pfmemalloc() is checked in __page_pool_put_page() * to avoid recycling the pfmemalloc page. */ - if (unlikely((page->pp_magic & ~0x3UL) != PP_SIGNATURE)) + if (unlikely(!is_pp_page(page))) return false; pp = page->pp; From patchwork Thu Dec 14 04:28:33 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Liang Chen X-Patchwork-Id: 13492267 X-Patchwork-Delegate: kuba@kernel.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="hlHCjUyg" Received: from mail-oi1-x236.google.com (mail-oi1-x236.google.com [IPv6:2607:f8b0:4864:20::236]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C58611BF5 for ; Wed, 13 Dec 2023 20:30:18 -0800 (PST) Received: by mail-oi1-x236.google.com with SMTP id 5614622812f47-3b9f8c9307dso4580348b6e.0 for ; Wed, 13 Dec 2023 20:30:18 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1702528218; x=1703133018; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=wH8JE7RX2AG09Ee8T7TBD98rU2IlRL47FNJ/XRL4ggY=; b=hlHCjUygj8ya/4+YDE/2mX/y5DIilvgrcnfjE//8biag/JutO8bfNgym9axc5cJSM7 bS913mQeGh8Gb0jGsNaEQnjQNvCXyG+XGZ18voc4dlS1LfVNy9/uO0SEZgKt/K+52Rlt 5vY2R+wtbk9Y7zkkh+5CZiSK38WbxqYtMTLWa0MHZSnQFM5WIMKewA4Rn6rEevrCdusa G+kbqpkP4fztmyUf9pPvCJCBru1sUdgX02D4U6+aIGUeR32kYAPhaHo56e7EVFph28l+ ycpHpEKj4gbJstLT3q42keNuOH1mx2wPQ1w143fhYa6kZKLyjc/ytV/YirIYlfrgMrGs A8RA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1702528218; x=1703133018; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=wH8JE7RX2AG09Ee8T7TBD98rU2IlRL47FNJ/XRL4ggY=; b=DQfVPDt71fzMufmA4Db6d6iT69W1vzV2YLZ+yXUkKHYkJKkjyC1HEszgt/Fdm7fg4r 6TeYfnMF5L8HbBYgRq7gvKneklTg8Lw76KazIZ6ReYVoAW7JucdtZKrV8ZyAFyDlBgmo pHqNafjW6KCz/KwKprP9mIXSCHrjm+9k1f4OLgUGky+dwiU5utKrLXdcotAt5TKmt7E2 BfsHoaucg6Qfr3Wu/YD/6JPefikJmTKIH+PRnZ/JCdcdjkZJ4odz8mhVIuQwaJFVFzw5 3qJn/mt1uBHMctpMIryunFA11yT8TXmRTHH0pEC9LFtCQG4wNXtweIggvqu9C1Bs+rap nSSQ== X-Gm-Message-State: AOJu0Yz0vIWc08JBoCy5eO5ETA2uQe0dUxj9M3qjPr83Tl3cFFlFh6YC U9E5Smql50sHE++PcA2iEmY= X-Google-Smtp-Source: AGHT+IH0z5Jsc/2aOqdw141+MndIT7KSNK8QOI97WWYMyq7Er73hCdbxtT81RIltsPn/DLZwO6lnnA== X-Received: by 2002:a05:6808:1786:b0:3b9:cc1e:4726 with SMTP id bg6-20020a056808178600b003b9cc1e4726mr12004769oib.75.1702528217746; Wed, 13 Dec 2023 20:30:17 -0800 (PST) Received: from localhost.localdomain ([23.104.213.5]) by smtp.gmail.com with ESMTPSA id jg13-20020a17090326cd00b001cc8cf4ad16sm374412plb.246.2023.12.13.20.30.10 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 13 Dec 2023 20:30:16 -0800 (PST) From: Liang Chen To: davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, hawk@kernel.org, ilias.apalodimas@linaro.org, linyunsheng@huawei.com Cc: netdev@vger.kernel.org, linux-mm@kvack.org, jasowang@redhat.com, almasrymina@google.com, liangchen.linux@gmail.com Subject: [PATCH net-next v10 4/4] skbuff: Optimization of SKB coalescing for page pool Date: Thu, 14 Dec 2023 12:28:33 +0800 Message-Id: <20231214042833.21316-4-liangchen.linux@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20231214042833.21316-1-liangchen.linux@gmail.com> References: <20231214042833.21316-1-liangchen.linux@gmail.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org In order to address the issues encountered with commit 1effe8ca4e34 ("skbuff: fix coalescing for page_pool fragment recycling"), the combination of the following condition was excluded from skb coalescing: from->pp_recycle = 1 from->cloned = 1 to->pp_recycle = 1 However, with page pool environments, the aforementioned combination can be quite common(ex. NetworkMananger may lead to the additional packet_type being registered, thus the cloning). In scenarios with a higher number of small packets, it can significantly affect the success rate of coalescing. For example, considering packets of 256 bytes size, our comparison of coalescing success rate is as follows: Without page pool: 70% With page pool: 13% Consequently, this has an impact on performance: Without page pool: 2.57 Gbits/sec With page pool: 2.26 Gbits/sec Therefore, it seems worthwhile to optimize this scenario and enable coalescing of this particular combination. To achieve this, we need to ensure the correct increment of the "from" SKB page's page pool reference count (pp_ref_count). Following this optimization, the success rate of coalescing measured in our environment has improved as follows: With page pool: 60% This success rate is approaching the rate achieved without using page pool, and the performance has also been improved: With page pool: 2.52 Gbits/sec Below is the performance comparison for small packets before and after this optimization. We observe no impact to packets larger than 4K. packet size before after improved (bytes) (Gbits/sec) (Gbits/sec) 128 1.19 1.27 7.13% 256 2.26 2.52 11.75% 512 4.13 4.81 16.50% 1024 6.17 6.73 9.05% 2048 14.54 15.47 6.45% 4096 25.44 27.87 9.52% Signed-off-by: Liang Chen Reviewed-by: Yunsheng Lin Suggested-by: Jason Wang Reviewed-by: Mina Almasry --- include/net/page_pool/helpers.h | 5 ++++ net/core/skbuff.c | 52 +++++++++++++++++++++++++-------- 2 files changed, 45 insertions(+), 12 deletions(-) diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index d0c5e7e6857a..0dc8fab43bef 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -281,6 +281,11 @@ static inline long page_pool_unref_page(struct page *page, long nr) return ret; } +static inline void page_pool_ref_page(struct page *page) +{ + atomic_long_inc(&page->pp_ref_count); +} + static inline bool page_pool_is_last_ref(struct page *page) { /* If page_pool_unref_page() returns 0, we were the last user */ diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 7e26b56cda38..cebdeafe691b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -947,6 +947,37 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data, bool napi_safe) return napi_pp_put_page(virt_to_page(data), napi_safe); } +/** + * skb_pp_frag_ref() - Increase fragment references of a page pool aware skb + * @skb: page pool aware skb + * + * Increase the fragment reference count (pp_ref_count) of a skb. This is + * intended to gain fragment references only for page pool aware skbs, + * i.e. when skb->pp_recycle is true, and not for fragments in a + * non-pp-recycling skb. It has a fallback to increase references on normal + * pages, as page pool aware skbs may also have normal page fragments. + */ +static int skb_pp_frag_ref(struct sk_buff *skb) +{ + struct skb_shared_info *shinfo; + struct page *head_page; + int i; + + if (!skb->pp_recycle) + return -EINVAL; + + shinfo = skb_shinfo(skb); + + for (i = 0; i < shinfo->nr_frags; i++) { + head_page = compound_head(skb_frag_page(&shinfo->frags[i])); + if (likely(is_pp_page(head_page))) + page_pool_ref_page(head_page); + else + page_ref_inc(head_page); + } + return 0; +} + static void skb_kfree_head(void *head, unsigned int end_offset) { if (end_offset == SKB_SMALL_HEAD_HEADROOM) @@ -5769,17 +5800,12 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, return false; /* 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 (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 - * !@to->pp_recycle but its tricky (due to potential race with - * the clone disappearing) and rare, so not worth dealing with. + * pages within the same SKB. In theory we could take full + * references if @from is cloned and !@to->pp_recycle but its + * tricky (due to potential race with the clone disappearing) and + * rare, so not worth dealing with. */ - if (to->pp_recycle != from->pp_recycle || - (from->pp_recycle && skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle) return false; if (len <= skb_tailroom(to)) { @@ -5836,8 +5862,10 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, /* if the skb is not cloned this does nothing * since we set nr_frags to 0. */ - for (i = 0; i < from_shinfo->nr_frags; i++) - __skb_frag_ref(&from_shinfo->frags[i]); + if (skb_pp_frag_ref(from)) { + for (i = 0; i < from_shinfo->nr_frags; i++) + __skb_frag_ref(&from_shinfo->frags[i]); + } to->truesize += delta; to->len += len;