From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sathya Perla Subject: RE: RE: [PATCH] be2net: Bugfix for packet drop with kernel param swiotlb=force Date: Fri, 21 Feb 2014 07:15:47 +0000 Message-ID: <07309948-80e6-4274-80a2-053f0ba65643@CMEXHTCAS1.ad.emulex.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="iso-2022-jp" Content-Transfer-Encoding: 8BIT Cc: Subramanian Seetharaman , Ajit Khaparde , "wang.liang82@zte.com.cn" , "cai.qu@zte.com.cn" , "li.fengmao@zte.com.cn" , "long.chun@zte.com.cn" , David Miller To: "jiang.biao2@zte.com.cn" , "netdev@vger.kernel.org" Return-path: Received: from cmexedge2.ext.emulex.com ([138.239.224.100]:47654 "EHLO CMEXEDGE2.ext.emulex.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751204AbaBUHPx convert rfc822-to-8bit (ORCPT ); Fri, 21 Feb 2014 02:15:53 -0500 In-Reply-To: Content-Language: en-US Sender: netdev-owner@vger.kernel.org List-ID: > -----Original Message----- > From: jiang.biao2@zte.com.cn [mailto:jiang.biao2@zte.com.cn] > > > > > > > From: Li Fengmao > > > > > > There will be packet drop with kernel param "swiotlb = force" on > > > Emulex 10Gb NIC using be2net driver. The problem is caused by > > > receiving skb without calling pci_unmap_page() in get_rx_page_info(). > > > rx_page_info->last_page_user is initialized to false in > > > be_post_rx_frags() when current frag are mapped in the first half of > > > the same page with another frag. But in that case with > > > "swiotlb = force" param, data can not be copied into the page of > > > rx_page_info without calling pci_unmap_page, so the data frag mapped > > > in the first half of the page will be dropped. > > > > > > It can be solved by creating only a mapping relation between frag > > > and page, and deleting rx_page_info->last_page_user to ensure > > > calling pci_unmap_page when handling each receiving frag. > > > > This patch uses an entire page for each RX frag (whose default size is 2048). > > Consequently, on platforms like ppc64 where the default PAGE_SIZE is 64K, > > memory usage becomes very inefficient. > > > > Instead, I've tried a partial-page mapping scheme. This retains the > > page sharing logic, but un-maps each frag separately so that > > the data is copied from the bounce buffers. > > > > Pls see if this works for you; thanks. > > > Our patch indeed has some problem because use an entire page by alloc_pages， > maybe kmalloc should be appropriate. > Your modification works for us, it should be a right patch for the bug. Thanks for verifying. I'll re-post my patch with a proper sign-off. -Sathya