From patchwork Fri Sep 2 16:18:44 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sean Wang X-Patchwork-Id: 9311377 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id B082560760 for ; Fri, 2 Sep 2016 16:19:20 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id A1CBB297F3 for ; Fri, 2 Sep 2016 16:19:20 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 9694829811; Fri, 2 Sep 2016 16:19:20 +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=-4.2 required=2.0 tests=BAYES_00, RCVD_IN_DNSWL_MED, UNPARSEABLE_RELAY autolearn=ham version=3.3.1 Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.9]) (using TLSv1.2 with cipher AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 4410A297F3 for ; Fri, 2 Sep 2016 16:19:20 +0000 (UTC) Received: from localhost ([127.0.0.1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.85_2 #1 (Red Hat Linux)) id 1bfrBX-0001Wf-GN; Fri, 02 Sep 2016 16:19:19 +0000 Received: from [210.61.82.183] (helo=mailgw01.mediatek.com) by bombadil.infradead.org with esmtp (Exim 4.85_2 #1 (Red Hat Linux)) id 1bfrBU-0001Qu-Oj for linux-mediatek@lists.infradead.org; Fri, 02 Sep 2016 16:19:17 +0000 Received: from mtkhts09.mediatek.inc [(172.21.101.70)] by mailgw01.mediatek.com (envelope-from ) (mhqrelay.mediatek.com ESMTP with TLS) with ESMTP id 1476299581; Sat, 03 Sep 2016 00:18:53 +0800 Received: from mtkswgap22.mediatek.inc (172.21.77.33) by mtkhts09.mediatek.inc (172.21.101.73) with Microsoft SMTP Server id 14.3.266.1; Sat, 3 Sep 2016 00:18:52 +0800 From: To: , Subject: [PATCH net-next v3 1/2] net: ethernet: mediatek: enhance RX path by reducing the frequency of the memory barrier used Date: Sat, 3 Sep 2016 00:18:44 +0800 Message-ID: <1472833125-17343-2-git-send-email-sean.wang@mediatek.com> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1472833125-17343-1-git-send-email-sean.wang@mediatek.com> References: <1472833125-17343-1-git-send-email-sean.wang@mediatek.com> MIME-Version: 1.0 X-MTK: N X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20160902_091917_007103_738B0BD2 X-CRM114-Status: UNSURE ( 9.22 ) X-CRM114-Notice: Please train this message. X-BeenThere: linux-mediatek@lists.infradead.org X-Mailman-Version: 2.1.20 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: nbd@openwrt.org, keyhaede@gmail.com, netdev@vger.kernel.org, Sean Wang , linux-mediatek@lists.infradead.org, objelf@gmail.com Sender: "Linux-mediatek" Errors-To: linux-mediatek-bounces+patchwork-linux-mediatek=patchwork.kernel.org@lists.infradead.org X-Virus-Scanned: ClamAV using ClamSMTP From: Sean Wang The patch makes move wmb() to outside the loop that could help RX path handling more faster although that RX descriptors aren't freed for DMA to use as soon as possible, but based on my experiment and the result shows it still can reach about 943Mbpis without performance drop that is tested based on the setup with one port using Giga PHY and 256 RX descriptors for DMA to move. Signed-off-by: Sean Wang --- drivers/net/ethernet/mediatek/mtk_eth_soc.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 048d763..33bb10f 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -951,13 +951,14 @@ release_desc: rxd->rxd2 = RX_DMA_PLEN0(ring->buf_size); ring->calc_idx = idx; - /* make sure that all changes to the dma ring are flushed before - * we continue - */ - wmb(); - mtk_w32(eth, ring->calc_idx, MTK_PRX_CRX_IDX0); + done++; } + /* make sure that all changes to the dma ring are flushed before + * we continue + */ + wmb(); + mtk_w32(eth, ring->calc_idx, MTK_PRX_CRX_IDX0); if (done < budget) mtk_w32(eth, MTK_RX_DONE_INT, MTK_PDMA_INT_STATUS);