From patchwork Thu Nov 15 09:43:09 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jason Wang X-Patchwork-Id: 10684035 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0377F14BA for ; Thu, 15 Nov 2018 09:43:38 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id E770A286F8 for ; Thu, 15 Nov 2018 09:43:37 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id DBA85288C4; Thu, 15 Nov 2018 09:43:37 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-7.9 required=2.0 tests=BAYES_00,MAILING_LIST_MULTI, RCVD_IN_DNSWL_HI autolearn=ham version=3.3.1 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 73D3B286F8 for ; Thu, 15 Nov 2018 09:43:37 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2388098AbeKOTuX (ORCPT ); Thu, 15 Nov 2018 14:50:23 -0500 Received: from mx1.redhat.com ([209.132.183.28]:50052 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729039AbeKOTuX (ORCPT ); Thu, 15 Nov 2018 14:50:23 -0500 Received: from smtp.corp.redhat.com (int-mx08.intmail.prod.int.phx2.redhat.com [10.5.11.23]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 748EFC0495AD; Thu, 15 Nov 2018 09:43:18 +0000 (UTC) Received: from jason-ThinkPad-T450s.redhat.com (ovpn-12-99.pek2.redhat.com [10.72.12.99]) by smtp.corp.redhat.com (Postfix) with ESMTP id E7DDA1A92C; Thu, 15 Nov 2018 09:43:12 +0000 (UTC) From: Jason Wang To: mst@redhat.com, jasowang@redhat.com, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH net-next 1/2] vhost_net: mitigate page reference counting during page frag refill Date: Thu, 15 Nov 2018 17:43:09 +0800 Message-Id: <20181115094310.17307-1-jasowang@redhat.com> X-Scanned-By: MIMEDefang 2.84 on 10.5.11.23 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.31]); Thu, 15 Nov 2018 09:43:18 +0000 (UTC) Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP We do a get_page() which involves a atomic operation. This patch tries to mitigate a per packet atomic operation by maintaining a reference bias which is initially USHRT_MAX. Each time a page is got, instead of calling get_page() we decrease the bias and when we find it's time to use a new page we will decrease the bias at one time through __page_cache_drain_cache(). Testpmd(virtio_user + vhost_net) + XDP_DROP on TAP shows about 1.6% improvement. Before: 4.63Mpps After: 4.71Mpps Signed-off-by: Jason Wang --- drivers/vhost/net.c | 54 ++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 51 insertions(+), 3 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index ab11b2bee273..d919284f103b 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -141,6 +141,10 @@ struct vhost_net { unsigned tx_zcopy_err; /* Flush in progress. Protected by tx vq lock. */ bool tx_flush; + /* Private page frag */ + struct page_frag page_frag; + /* Refcount bias of page frag */ + int refcnt_bias; }; static unsigned vhost_net_zcopy_mask __read_mostly; @@ -637,14 +641,53 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } +#define SKB_FRAG_PAGE_ORDER get_order(32768) + +static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, + struct page_frag *pfrag, gfp_t gfp) +{ + if (pfrag->page) { + if (pfrag->offset + sz <= pfrag->size) + return true; + __page_frag_cache_drain(pfrag->page, net->refcnt_bias); + } + + pfrag->offset = 0; + net->refcnt_bias = 0; + if (SKB_FRAG_PAGE_ORDER) { + /* Avoid direct reclaim but allow kswapd to wake */ + pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | + __GFP_COMP | __GFP_NOWARN | + __GFP_NORETRY, + SKB_FRAG_PAGE_ORDER); + if (likely(pfrag->page)) { + pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; + goto done; + } + } + pfrag->page = alloc_page(gfp); + if (likely(pfrag->page)) { + pfrag->size = PAGE_SIZE; + goto done; + } + return false; + +done: + net->refcnt_bias = USHRT_MAX; + page_ref_add(pfrag->page, USHRT_MAX - 1); + return true; +} + #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct iov_iter *from) { struct vhost_virtqueue *vq = &nvq->vq; + struct vhost_net *net = container_of(vq->dev, struct vhost_net, + dev); struct socket *sock = vq->private_data; - struct page_frag *alloc_frag = ¤t->task_frag; + struct page_frag *alloc_frag = &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; @@ -665,7 +708,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, buflen += SKB_DATA_ALIGN(len + pad); alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) + if (unlikely(!vhost_net_page_frag_refill(net, buflen, + alloc_frag, GFP_KERNEL))) return -ENOMEM; buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; @@ -703,7 +747,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, xdp->data_end = xdp->data + len; hdr->buflen = buflen; - get_page(alloc_frag->page); + --net->refcnt_bias; alloc_frag->offset += buflen; ++nvq->batched_xdp; @@ -1292,6 +1336,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); f->private_data = n; + n->page_frag.page = NULL; + n->refcnt_bias = 0; return 0; } @@ -1366,6 +1412,8 @@ static int vhost_net_release(struct inode *inode, struct file *f) kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); + if (n->page_frag.page) + __page_frag_cache_drain(n->page_frag.page, n->refcnt_bias); kvfree(n); return 0; }