From patchwork Tue Jan 30 11:37:07 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 13537380 Received: from szxga07-in.huawei.com (szxga07-in.huawei.com [45.249.212.35]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 05E2B67731; Tue, 30 Jan 2024 11:38:02 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.35 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706614685; cv=none; b=ZyJxfagfvnPmb5IS+TMtX/Nm6lH05mCtls+YSJpTcrnYfa4yvGeGZCzwpDZV/FmVqA1Xa3zgEc0UF4DQvq7vE3mGs3CsG0A2dymZstLuefxpBwMoYIQePI9/NBnVTPq+Wf4yex3JFjXu0gnTUF90ujrES9KTwSGwAovUCvBYCyQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706614685; c=relaxed/simple; bh=iIw9m8E+34rmyeAQdxJf1gG5mn3NGG9OKYzHsTrTvN4=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=Xo2Q3SAiB+uB3k0hj/Gs7EJw/36JCzoMV8jAwGiiqcLobSTGfpFtc0/7/nvxa6NXRBOPp7HWifWm8CK0+BlRRC3aB389LCzxiY4dNcxfe0N1i+gwNzs1rx4v6QXZEj9hX4vGuhFm2CKvqo9zXTtXzjC9r04nkVUUynn3azFw23Y= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com; spf=pass smtp.mailfrom=huawei.com; arc=none smtp.client-ip=45.249.212.35 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huawei.com Received: from mail.maildlp.com (unknown [172.19.88.214]) by szxga07-in.huawei.com (SkyGuard) with ESMTP id 4TPNQz0vJ8z1Q8H5; Tue, 30 Jan 2024 19:36:11 +0800 (CST) Received: from dggpemm500005.china.huawei.com (unknown [7.185.36.74]) by mail.maildlp.com (Postfix) with ESMTPS id 1039C1A016B; Tue, 30 Jan 2024 19:38:01 +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, 30 Jan 2024 19:38:00 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Alexander Duyck , Alexander Duyck , "Michael S. Tsirkin" , Jason Wang , Andrew Morton , Eric Dumazet , , , Subject: [PATCH net-next v4 2/5] page_frag: unify gfp bits for order 3 page allocation Date: Tue, 30 Jan 2024 19:37:07 +0800 Message-ID: <20240130113710.34511-3-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20240130113710.34511-1-linyunsheng@huawei.com> References: <20240130113710.34511-1-linyunsheng@huawei.com> Precedence: bulk X-Mailing-List: kvm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: dggems706-chm.china.huawei.com (10.3.19.183) To dggpemm500005.china.huawei.com (7.185.36.74) Currently there seems to be three page frag implementions which all try to allocate order 3 page, if that fails, it then fail back to allocate order 0 page, and each of them all allow order 3 page allocation to fail under certain condition by using specific gfp bits. The gfp bits for order 3 page allocation are different between different implementation, __GFP_NOMEMALLOC is or'd to forbid access to emergency reserves memory for __page_frag_cache_refill(), but it is not or'd in other implementions, __GFP_DIRECT_RECLAIM is masked off to avoid direct reclaim in skb_page_frag_refill(), but it is not masked off in __page_frag_cache_refill(). This patch unifies the gfp bits used between different implementions by or'ing __GFP_NOMEMALLOC and masking off __GFP_DIRECT_RECLAIM for order 3 page allocation to avoid possible pressure for mm. Signed-off-by: Yunsheng Lin Reviewed-by: Alexander Duyck CC: Alexander Duyck --- drivers/vhost/net.c | 2 +- mm/page_alloc.c | 4 ++-- net/core/sock.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f2ed7167c848..e574e21cc0ca 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -670,7 +670,7 @@ static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NORETRY | __GFP_NOMEMALLOC, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c0f7e67c4250..636145c29f70 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4685,8 +4685,8 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, gfp_t gfp = gfp_mask; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | - __GFP_NOMEMALLOC; + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER); nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; diff --git a/net/core/sock.c b/net/core/sock.c index 88bf810394a5..8289a3d8c375 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2919,7 +2919,7 @@ bool skb_page_frag_refill(unsigned int sz, struct page_frag *pfrag, gfp_t gfp) /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NORETRY | __GFP_NOMEMALLOC, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; From patchwork Tue Jan 30 11:37:09 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yunsheng Lin X-Patchwork-Id: 13537381 Received: from szxga04-in.huawei.com (szxga04-in.huawei.com [45.249.212.190]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7CC906A038; Tue, 30 Jan 2024 11:38:07 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.190 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706614690; cv=none; b=XMgQQz18IqsFDyGfVSgre1feaxzGx8druoOO/selqM7sjNKI3+KALCa4d1+nNqaGTprWZloQxMQiDT6ll3BEGQNltxiVq/XkG8EYFBFzWu/oIPnWQKqCAEysAMJG8JqQgePICp2vav9p4+1pOmOrHqp8COrhXaoZI9BWBISvBFY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706614690; c=relaxed/simple; bh=EkOVPmyG8AwI1ztH4WPEnwo5N1dm4jflvATq8fvXt7Q=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=lkWF3TPHzRDgTYJCZaBPxzWtRy1Z9NTCtjsYJd1/H19my2/SuB/106fi75LKl7lUvNVROeVlvFqUh/Lh3ErweL7oWVO1KpXhu2YrDOYdacSxh07xCzErhBGL1wdhh1YwC1yrotBA2mDjcRoNEp/M/cbR+SvsMhoAkMM9Vj2b58U= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com; spf=pass smtp.mailfrom=huawei.com; arc=none smtp.client-ip=45.249.212.190 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huawei.com Received: from mail.maildlp.com (unknown [172.19.162.112]) by szxga04-in.huawei.com (SkyGuard) with ESMTP id 4TPNS23wNyz1xmr9; Tue, 30 Jan 2024 19:37:06 +0800 (CST) Received: from dggpemm500005.china.huawei.com (unknown [7.185.36.74]) by mail.maildlp.com (Postfix) with ESMTPS id 76D191404FF; Tue, 30 Jan 2024 19:38:05 +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, 30 Jan 2024 19:38:05 +0800 From: Yunsheng Lin To: , , CC: , , Yunsheng Lin , Jason Wang , "Michael S. Tsirkin" , Alexei Starovoitov , Daniel Borkmann , Jesper Dangaard Brouer , John Fastabend , , , Subject: [PATCH net-next v4 4/5] vhost/net: remove vhost_net_page_frag_refill() Date: Tue, 30 Jan 2024 19:37:09 +0800 Message-ID: <20240130113710.34511-5-linyunsheng@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20240130113710.34511-1-linyunsheng@huawei.com> References: <20240130113710.34511-1-linyunsheng@huawei.com> Precedence: bulk X-Mailing-List: kvm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: dggems706-chm.china.huawei.com (10.3.19.183) To dggpemm500005.china.huawei.com (7.185.36.74) 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 | 91 ++++++++++++++------------------------------- 1 file changed, 27 insertions(+), 64 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index e574e21cc0ca..4b2fcb228a0a 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; }; static unsigned vhost_net_zcopy_mask __read_mostly; @@ -655,41 +653,6 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } -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 | __GFP_NOMEMALLOC, - 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, @@ -699,7 +662,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev); struct socket *sock = vhost_vq_get_backend(vq); - 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; @@ -710,6 +672,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, int sock_hlen = nvq->sock_hlen; void *buf; int copied; + int ret; if (unlikely(len < nvq->sock_hlen)) return -EFAULT; @@ -719,18 +682,17 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, return -ENOSPC; buflen += SKB_DATA_ALIGN(len + pad); - alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); - if (unlikely(!vhost_net_page_frag_refill(net, buflen, - alloc_frag, GFP_KERNEL))) + buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL, + SMP_CACHE_BYTES); + if (unlikely(!buf)) return -ENOMEM; - buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + - offsetof(struct tun_xdp_hdr, gso), - sock_hlen, from); - if (copied != sock_hlen) - return -EFAULT; + copied = copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso), + sock_hlen, from); + if (copied != sock_hlen) { + ret = -EFAULT; + goto err; + } hdr = buf; gso = &hdr->gso; @@ -743,27 +705,30 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, vhost16_to_cpu(vq, gso->csum_start) + vhost16_to_cpu(vq, gso->csum_offset) + 2); - if (vhost16_to_cpu(vq, gso->hdr_len) > len) - return -EINVAL; + if (vhost16_to_cpu(vq, gso->hdr_len) > len) { + ret = -EINVAL; + goto err; + } } len -= sock_hlen; - copied = copy_page_from_iter(alloc_frag->page, - alloc_frag->offset + pad, - len, from); - if (copied != len) - return -EFAULT; + copied = copy_from_iter(buf + pad, len, from); + if (copied != len) { + ret = -EFAULT; + goto err; + } xdp_init_buff(xdp, buflen, NULL); xdp_prepare_buff(xdp, buf, pad, len, true); hdr->buflen = buflen; - --net->refcnt_bias; - alloc_frag->offset += buflen; - ++nvq->batched_xdp; return 0; + +err: + page_frag_free(buf); + return ret; } 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]); f->private_data = n; - n->page_frag.page = NULL; - n->refcnt_bias = 0; + n->pf_cache.va = NULL; return 0; } @@ -1422,8 +1386,7 @@ 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); + page_frag_cache_drain(&n->pf_cache); kvfree(n); return 0; }