Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933129AbbLHGXK (ORCPT ); Tue, 8 Dec 2015 01:23:10 -0500 Received: from szxga03-in.huawei.com ([119.145.14.66]:31271 "EHLO szxga03-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932460AbbLHGXI (ORCPT ); Tue, 8 Dec 2015 01:23:08 -0500 Subject: Re: [PATCH net-next] net: hns: optimize XGE capability by reducing cpu usage To: "Du, Fan" , , , , , , , References: <1449300749-50275-1-git-send-email-yankejian@huawei.com> <56654A31.4080607@intel.com> CC: , , , , From: "Yankejian (Hackim Yim)" Message-ID: <56667729.1080701@huawei.com> Date: Tue, 8 Dec 2015 14:22:33 +0800 User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:38.0) Gecko/20100101 Thunderbird/38.3.0 MIME-Version: 1.0 In-Reply-To: <56654A31.4080607@intel.com> Content-Type: text/plain; charset="windows-1252" Content-Transfer-Encoding: 7bit X-Originating-IP: [10.57.126.191] X-CFilter-Loop: Reflected X-Mirapoint-Virus-RAPID-Raw: score=unknown(0), refid=str=0001.0A020205.56667736.0044,ss=1,re=0.000,recu=0.000,reip=0.000,cl=1,cld=1,fgs=0, ip=0.0.0.0, so=2013-05-26 15:14:31, dmn=2013-03-21 17:37:32 X-Mirapoint-Loop-Id: 4391dc0cb1bd3e3a69c327be5a7f07e1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 8971 Lines: 234 On 2015/12/7 16:58, Du, Fan wrote: > > > On 2015/12/5 15:32, yankejian wrote: >> here is the patch raising the performance of XGE by: >> 1)changes the way page management method for enet momery, and >> 2)reduces the count of rmb, and >> 3)adds Memory prefetching > > Any numbers on how much it boost performance? > it is almost the same as 82599. >> Signed-off-by: yankejian >> --- >> drivers/net/ethernet/hisilicon/hns/hnae.h | 5 +- >> drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c | 1 - >> drivers/net/ethernet/hisilicon/hns/hns_enet.c | 79 +++++++++++++++-------- >> 3 files changed, 55 insertions(+), 30 deletions(-) >> >> diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h >> index d1f3316..6ca94dc 100644 >> --- a/drivers/net/ethernet/hisilicon/hns/hnae.h >> +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h >> @@ -341,7 +341,8 @@ struct hnae_queue { >> void __iomem *io_base; >> phys_addr_t phy_base; >> struct hnae_ae_dev *dev; /* the device who use this queue */ >> - struct hnae_ring rx_ring, tx_ring; >> + struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp; >> + struct hnae_ring tx_ring ____cacheline_internodealigned_in_smp; >> struct hnae_handle *handle; >> }; >> >> @@ -597,11 +598,9 @@ static inline void hnae_replace_buffer(struct hnae_ring *ring, int i, >> struct hnae_desc_cb *res_cb) >> { >> struct hnae_buf_ops *bops = ring->q->handle->bops; >> - struct hnae_desc_cb tmp_cb = ring->desc_cb[i]; >> >> bops->unmap_buffer(ring, &ring->desc_cb[i]); >> ring->desc_cb[i] = *res_cb; >> - *res_cb = tmp_cb; >> ring->desc[i].addr = (__le64)ring->desc_cb[i].dma; >> ring->desc[i].rx.ipoff_bnum_pid_flag = 0; >> } >> diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c >> index 77c6edb..522b264 100644 >> --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c >> +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c >> @@ -341,7 +341,6 @@ void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask) >> else >> flag = RCB_INT_FLAG_RX; >> >> - hns_rcb_int_clr_hw(ring->q, flag); >> hns_rcb_int_ctrl_hw(ring->q, flag, mask); >> } >> >> diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c >> index cad2663..e2be510 100644 >> --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c >> +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c >> @@ -33,6 +33,7 @@ >> >> #define RCB_IRQ_NOT_INITED 0 >> #define RCB_IRQ_INITED 1 >> +#define HNS_BUFFER_SIZE_2048 2048 >> >> #define BD_MAX_SEND_SIZE 8191 >> #define SKB_TMP_LEN(SKB) \ >> @@ -491,13 +492,51 @@ static unsigned int hns_nic_get_headlen(unsigned char *data, u32 flag, >> return max_size; >> } >> >> -static void >> -hns_nic_reuse_page(struct hnae_desc_cb *desc_cb, int tsize, int last_offset) >> +static void hns_nic_reuse_page(struct sk_buff *skb, int i, >> + struct hnae_ring *ring, int pull_len, >> + struct hnae_desc_cb *desc_cb) >> { >> + struct hnae_desc *desc; >> + int truesize, size; >> + int last_offset = 0; >> + >> + desc = &ring->desc[ring->next_to_clean]; >> + size = le16_to_cpu(desc->rx.size); >> + >> +#if (PAGE_SIZE < 8192) >> + if (hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048) { >> + truesize = hnae_buf_size(ring); >> + } else { >> + truesize = ALIGN(size, L1_CACHE_BYTES); >> + last_offset = hnae_page_size(ring) - hnae_buf_size(ring); >> + } >> + >> +#else >> + truesize = ALIGN(size, L1_CACHE_BYTES); >> + last_offset = hnae_page_size(ring) - hnae_buf_size(ring); >> +#endif >> + >> + skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, >> + size - pull_len, truesize - pull_len); >> + >> /* avoid re-using remote pages,flag default unreuse */ >> if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) { >> +#if (PAGE_SIZE < 8192) >> + if (hnae_buf_size(ring) == HNS_BUFFER_SIZE_2048) { >> + /* if we are only owner of page we can reuse it */ >> + if (likely(page_count(desc_cb->priv) == 1)) { >> + /* flip page offset to other buffer */ >> + desc_cb->page_offset ^= truesize; >> + >> + desc_cb->reuse_flag = 1; >> + /* bump ref count on page before it is given*/ >> + get_page(desc_cb->priv); >> + } >> + return; >> + } >> +#endif >> /* move offset up to the next cache line */ >> - desc_cb->page_offset += tsize; >> + desc_cb->page_offset += truesize; >> >> if (desc_cb->page_offset <= last_offset) { >> desc_cb->reuse_flag = 1; >> @@ -529,11 +568,10 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, >> struct hnae_desc *desc; >> struct hnae_desc_cb *desc_cb; >> unsigned char *va; >> - int bnum, length, size, i, truesize, last_offset; >> + int bnum, length, i; >> int pull_len; >> u32 bnum_flag; >> >> - last_offset = hnae_page_size(ring) - hnae_buf_size(ring); >> desc = &ring->desc[ring->next_to_clean]; >> desc_cb = &ring->desc_cb[ring->next_to_clean]; >> >> @@ -555,17 +593,12 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, >> return -ENOMEM; >> } >> >> + prefetchw(skb->data); >> length = le16_to_cpu(desc->rx.pkt_len); >> bnum_flag = le32_to_cpu(desc->rx.ipoff_bnum_pid_flag); >> priv->ops.get_rxd_bnum(bnum_flag, &bnum); >> *out_bnum = bnum; >> >> - /* we will be copying header into skb->data in >> - * pskb_may_pull so it is in our interest to prefetch >> - * it now to avoid a possible cache miss >> - */ >> - prefetchw(skb->data); >> - >> if (length <= HNS_RX_HEAD_SIZE) { >> memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long))); >> >> @@ -588,13 +621,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, >> memcpy(__skb_put(skb, pull_len), va, >> ALIGN(pull_len, sizeof(long))); >> >> - size = le16_to_cpu(desc->rx.size); >> - truesize = ALIGN(size, L1_CACHE_BYTES); >> - skb_add_rx_frag(skb, 0, desc_cb->priv, >> - desc_cb->page_offset + pull_len, >> - size - pull_len, truesize - pull_len); >> - >> - hns_nic_reuse_page(desc_cb, truesize, last_offset); >> + hns_nic_reuse_page(skb, 0, ring, pull_len, desc_cb); >> ring_ptr_move_fw(ring, next_to_clean); >> >> if (unlikely(bnum >= (int)MAX_SKB_FRAGS)) { /* check err*/ >> @@ -604,13 +631,8 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, >> for (i = 1; i < bnum; i++) { >> desc = &ring->desc[ring->next_to_clean]; >> desc_cb = &ring->desc_cb[ring->next_to_clean]; >> - size = le16_to_cpu(desc->rx.size); >> - truesize = ALIGN(size, L1_CACHE_BYTES); >> - skb_add_rx_frag(skb, i, desc_cb->priv, >> - desc_cb->page_offset, >> - size, truesize); >> >> - hns_nic_reuse_page(desc_cb, truesize, last_offset); >> + hns_nic_reuse_page(skb, i, ring, 0, desc_cb); >> ring_ptr_move_fw(ring, next_to_clean); >> } >> } >> @@ -750,9 +772,10 @@ recv: >> /* make all data has been write before submit */ >> if (recv_pkts < budget) { >> ex_num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); >> - rmb(); /*complete read rx ring bd number*/ >> + >> if (ex_num > clean_count) { >> num += ex_num - clean_count; >> + rmb(); /*complete read rx ring bd number*/ >> goto recv; >> } >> } >> @@ -849,8 +872,11 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, >> >> bytes = 0; >> pkts = 0; >> - while (head != ring->next_to_clean) >> + while (head != ring->next_to_clean) { >> hns_nic_reclaim_one_desc(ring, &bytes, &pkts); >> + /* issue prefetch for next Tx descriptor */ >> + prefetch(&ring->desc_cb[ring->next_to_clean]); >> + } >> >> NETIF_TX_UNLOCK(ndev); >> >> @@ -926,6 +952,7 @@ static int hns_nic_common_poll(struct napi_struct *napi, int budget) >> ring_data->ring, 0); >> >> ring_data->fini_process(ring_data); >> + return 0; >> } >> >> return clean_complete; >> > > . > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/