From nobody Fri Sep 20 09:25:50 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 ED2C5C46CA3 for ; Tue, 5 Dec 2023 11:35:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1442171AbjLELfX (ORCPT ); Tue, 5 Dec 2023 06:35:23 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:41374 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1347050AbjLELe4 (ORCPT ); Tue, 5 Dec 2023 06:34:56 -0500 Received: from szxga01-in.huawei.com (szxga01-in.huawei.com [45.249.212.187]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 821D8D53; Tue, 5 Dec 2023 03:34:55 -0800 (PST) Received: from dggpemm500005.china.huawei.com (unknown [172.30.72.54]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4Skyyz1RZQzrVDt; Tue, 5 Dec 2023 19:31:07 +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 15.1.2507.35; Tue, 5 Dec 2023 19:34:53 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , "Michael S. Tsirkin" , Jason Wang , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , , , Subject: [PATCH net-next 4/6] vhost/net: remove vhost_net_page_frag_refill() Date: Tue, 5 Dec 2023 19:34:42 +0800 Message-ID: <20231205113444.63015-5-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20231205113444.63015-1-linyunsheng@huawei.com> References: <20231205113444.63015-1-linyunsheng@huawei.com> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Originating-IP: [10.69.192.56] X-ClientProxiedBy: dggems702-chm.china.huawei.com (10.3.19.179) 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" The page frag in vhost_net_page_frag_refill() uses the 'struct page_frag' from skb_page_frag_refill(), but it's implementation is similar to page_frag_alloc_align() now. This patch removes vhost_net_page_frag_refill() by using 'struct page_frag_cache' instead of 'struct page_frag', and allocating frag using page_frag_alloc_align(). The added benefit is that not only unifying the page frag implementation a little, but also having about 0.5% performance boost testing by using the vhost_net_test introduced in the last patch. Signed-off-by: Yunsheng Lin Acked-by: Jason Wang --- drivers/vhost/net.c | 93 ++++++++++++++------------------------------- 1 file changed, 29 insertions(+), 64 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e574e21cc0ca..805e11d598e4 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -141,10 +141,8 @@ 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; + /* Private page frag cache */ + struct page_frag_cache pf_cache; }; =20 static unsigned vhost_net_zcopy_mask __read_mostly; @@ -655,41 +653,6 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, s= ize_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } =20 -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 <=3D pfrag->size) - return true; - __page_frag_cache_drain(pfrag->page, net->refcnt_bias); - } - - pfrag->offset =3D 0; - net->refcnt_bias =3D 0; - if (SKB_FRAG_PAGE_ORDER) { - /* Avoid direct reclaim but allow kswapd to wake */ - pfrag->page =3D alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | - __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY | __GFP_NOMEMALLOC, - SKB_FRAG_PAGE_ORDER); - if (likely(pfrag->page)) { - pfrag->size =3D PAGE_SIZE << SKB_FRAG_PAGE_ORDER; - goto done; - } - } - pfrag->page =3D alloc_page(gfp); - if (likely(pfrag->page)) { - pfrag->size =3D PAGE_SIZE; - goto done; - } - return false; - -done: - net->refcnt_bias =3D USHRT_MAX; - page_ref_add(pfrag->page, USHRT_MAX - 1); - return true; -} - #define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) =20 static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, @@ -699,7 +662,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtque= ue *nvq, struct vhost_net *net =3D container_of(vq->dev, struct vhost_net, dev); struct socket *sock =3D vhost_vq_get_backend(vq); - struct page_frag *alloc_frag =3D &net->page_frag; struct virtio_net_hdr *gso; struct xdp_buff *xdp =3D &nvq->xdp[nvq->batched_xdp]; struct tun_xdp_hdr *hdr; @@ -710,6 +672,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtque= ue *nvq, int sock_hlen =3D nvq->sock_hlen; void *buf; int copied; + int ret; =20 if (unlikely(len < nvq->sock_hlen)) return -EFAULT; @@ -719,18 +682,17 @@ static int vhost_net_build_xdp(struct vhost_net_virtq= ueue *nvq, return -ENOSPC; =20 buflen +=3D SKB_DATA_ALIGN(len + pad); - alloc_frag->offset =3D ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!vhost_net_page_frag_refill(net, buflen, - alloc_frag, GFP_KERNEL))) + buf =3D page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, + SMP_CACHE_BYTES); + if (unlikely(!buf)) return -ENOMEM; =20 - buf =3D (char *)page_address(alloc_frag->page) + alloc_frag->offset; - copied =3D copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + - offsetof(struct tun_xdp_hdr, gso), - sock_hlen, from); - if (copied !=3D sock_hlen) - return -EFAULT; + copied =3D copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso), + sock_hlen, from); + if (copied !=3D sock_hlen) { + ret =3D -EFAULT; + goto err; + } =20 hdr =3D buf; gso =3D &hdr->gso; @@ -743,27 +705,30 @@ static int vhost_net_build_xdp(struct vhost_net_virtq= ueue *nvq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); =20 - if (vhost16_to_cpu(vq, gso->hdr_len) > len) - return -EINVAL; + if (vhost16_to_cpu(vq, gso->hdr_len) > len) { + ret =3D -EINVAL; + goto err; + } } =20 len -=3D sock_hlen; - copied =3D copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + pad, - len, from); - if (copied !=3D len) - return -EFAULT; + copied =3D copy_from_iter(buf + pad, len, from); + if (copied !=3D len) { + ret =3D -EFAULT; + goto err; + } =20 xdp_init_buff(xdp, buflen, NULL); xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen =3D buflen; =20 - --net->refcnt_bias; - alloc_frag->offset +=3D buflen; - ++nvq->batched_xdp; =20 return 0; + +err: + page_frag_free(buf); + return ret; } =20 static void handle_tx_copy(struct vhost_net *net, struct socket *sock) @@ -1353,8 +1318,7 @@ static int vhost_net_open(struct inode *inode, struct= file *f) vqs[VHOST_NET_VQ_RX]); =20 f->private_data =3D n; - n->page_frag.page =3D NULL; - n->refcnt_bias =3D 0; + n->pf_cache.va =3D NULL; =20 return 0; } @@ -1422,8 +1386,9 @@ static int vhost_net_release(struct inode *inode, str= uct 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); + if (n->pf_cache.va) + __page_frag_cache_drain(virt_to_head_page(n->pf_cache.va), + n->pf_cache.pagecnt_bias); kvfree(n); return 0; } --=20 2.33.0