From patchwork Thu Mar 2 07:51:23 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ami Sabo X-Patchwork-Id: 21059 X-Patchwork-Delegate: yuanhan.liu@linux.intel.com Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id 0560EBD28; Thu, 2 Mar 2017 08:51:55 +0100 (CET) Received: from mailout1.radware.com (mailout1.radwarecloud.com [192.115.180.130]) by dpdk.org (Postfix) with ESMTP id DB7C62B94; Thu, 2 Mar 2017 08:51:34 +0100 (CET) Received: from localhost.localdomain (176.200.121.200) by ILCAS1.corp.radware.com (176.200.120.121) with Microsoft SMTP Server id 14.3.319.2; Thu, 2 Mar 2017 09:51:33 +0200 From: Ami Sabo To: , CC: , , Ami Sabo Date: Thu, 2 Mar 2017 09:51:23 +0200 Message-ID: <1488441084-6039-3-git-send-email-amis@radware.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1488441084-6039-1-git-send-email-amis@radware.com> References: <1488102926-24158-2-git-send-email-amis@radware.com> <1488441084-6039-1-git-send-email-amis@radware.com> MIME-Version: 1.0 X-TM-AS-Product-Ver: SMEX-11.0.0.4179-8.100.1062-22916.005 X-TM-AS-Result: No--5.060300-0.000000-31 X-TM-AS-User-Approved-Sender: Yes X-TM-AS-User-Blocked-Sender: No Subject: [dpdk-dev] [PATCH v2 2/3] net/virtio-user: fix multi-process issue X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Secondary process doesn't properly attach to the rte_eth_device initialized by the primary process. ccessing device from secondary process (e.g. via rte_eth_rx_burst), causes process to crash. because rte_eth_dev_data is not properly set. The issue was flood by 'commit 7f95f78a8aea ("ethdev: clear data when allocating device")' which now clears rte_eth_dev_data entry. For pci devices the struct is initialized by rte_eth_dev_pci_probe ->eth_dev_attach_secondary(). However, for virtio-user virtio_user_pmd_probe() is called instead of rte_eth_dev_pci_probe(). The fix is to call rte_eth_dev_attach_secondary(), for secondary process, from virtio_user_pmd_probe. Fixes: 7f95f78a8aea ("ethdev: clear data when allocating device") Cc: stable@dpdk.org Signed-off-by: Ami Sabo --- drivers/net/virtio/virtio_user_ethdev.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/drivers/net/virtio/virtio_user_ethdev.c b/drivers/net/virtio/virtio_user_ethdev.c index 0b226ac..6033908 100644 --- a/drivers/net/virtio/virtio_user_ethdev.c +++ b/drivers/net/virtio/virtio_user_ethdev.c @@ -418,18 +418,24 @@ virtio_user_pmd_probe(const char *name, const char *params) goto end; } - eth_dev = virtio_user_eth_dev_alloc(name); - if (!eth_dev) { - PMD_INIT_LOG(ERR, "virtio_user fails to alloc device"); - goto end; - } + if (rte_eal_process_type() == RTE_PROC_PRIMARY) { + eth_dev = virtio_user_eth_dev_alloc(name); + if (!eth_dev) { + PMD_INIT_LOG(ERR, "virtio_user fails to alloc device"); + goto end; + } - hw = eth_dev->data->dev_private; - if (virtio_user_dev_init(hw->virtio_user_dev, path, queues, cq, + hw = eth_dev->data->dev_private; + if (virtio_user_dev_init(hw->virtio_user_dev, path, queues, cq, queue_size, mac_addr) < 0) { - PMD_INIT_LOG(ERR, "virtio_user_dev_init fails"); - virtio_user_eth_dev_free(eth_dev); - goto end; + PMD_INIT_LOG(ERR, "virtio_user_dev_init fails"); + virtio_user_eth_dev_free(eth_dev); + goto end; + } + } else { + eth_dev = rte_eth_dev_attach_secondary(name); + if (!eth_dev) + goto end; } /* previously called by rte_eal_pci_probe() for physical dev */