From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 0799CA0C45; Wed, 22 Sep 2021 15:29:56 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id E7744411E8; Wed, 22 Sep 2021 15:29:55 +0200 (CEST) Received: from szxga02-in.huawei.com (szxga02-in.huawei.com [45.249.212.188]) by mails.dpdk.org (Postfix) with ESMTP id AECDE41198; Wed, 22 Sep 2021 15:29:53 +0200 (CEST) Received: from dggemv711-chm.china.huawei.com (unknown [172.30.72.57]) by szxga02-in.huawei.com (SkyGuard) with ESMTP id 4HDzYp2CKhz8ygx; Wed, 22 Sep 2021 21:25:18 +0800 (CST) Received: from dggpemm500008.china.huawei.com (7.185.36.136) by dggemv711-chm.china.huawei.com (10.1.198.66) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Wed, 22 Sep 2021 21:29:50 +0800 Received: from localhost (10.174.242.157) by dggpemm500008.china.huawei.com (7.185.36.136) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.8; Wed, 22 Sep 2021 21:29:50 +0800 From: Yunjian Wang To: CC: , , , , , Yunjian Wang , Date: Wed, 22 Sep 2021 21:29:36 +0800 Message-ID: <4a8e530c7981069326a5bfffa0f59457022d11ff.1632315160.git.wangyunjian@huawei.com> X-Mailer: git-send-email 1.9.5.msysgit.1 In-Reply-To: References: MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.174.242.157] X-ClientProxiedBy: dggems703-chm.china.huawei.com (10.3.19.180) To dggpemm500008.china.huawei.com (7.185.36.136) X-CFilter-Loop: Reflected Subject: [dpdk-dev] [PATCH v3 3/4] net/i40e: fix memzone leak when re-configure the RX/TX queues X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 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" Normally when closing the device the queue memzone should be freed. But the memzone will be not freed, when device setup ops like: rte_eth_bond_slave_remove -->__eth_bond_slave_remove_lock_free ---->slave_remove ------>rte_eth_dev_internal_reset -------->rte_eth_dev_rx_queue_config ---------->eth_dev_rx_queue_config ------------>i40e_dev_rx_queue_release rte_eth_dev_close -->i40e_dev_close ---->i40e_dev_free_queues ------>i40e_dev_rx_queue_release (not been called due to nb_rx_queues and nb_tx_queues are 0) And when queue number is changed to small size, the BIG memzone queue index will be lost. This will lead to a memory leak. So we should release the memzone when releasing queues. Fixes: 460d1679586e ("drivers/net: delete HW rings while freeing queues") Cc: stable@dpdk.org Signed-off-by: Yunjian Wang --- drivers/net/i40e/i40e_fdir.c | 3 --- drivers/net/i40e/i40e_rxtx.c | 8 ++++++-- drivers/net/i40e/i40e_rxtx.h | 2 ++ 3 files changed, 8 insertions(+), 5 deletions(-) diff --git a/drivers/net/i40e/i40e_fdir.c b/drivers/net/i40e/i40e_fdir.c index af075fda2a..e910346e4d 100644 --- a/drivers/net/i40e/i40e_fdir.c +++ b/drivers/net/i40e/i40e_fdir.c @@ -284,7 +284,6 @@ i40e_fdir_teardown(struct i40e_pf *pf) { struct i40e_hw *hw = I40E_PF_TO_HW(pf); struct i40e_vsi *vsi; - struct rte_eth_dev *dev = &rte_eth_devices[pf->dev_data->port_id]; vsi = pf->fdir.fdir_vsi; if (!vsi) @@ -301,10 +300,8 @@ i40e_fdir_teardown(struct i40e_pf *pf) if (err) PMD_DRV_LOG(DEBUG, "Failed to do FDIR RX switch off"); - rte_eth_dma_zone_free(dev, "fdir_rx_ring", pf->fdir.rxq->queue_id); i40e_dev_rx_queue_release(pf->fdir.rxq); pf->fdir.rxq = NULL; - rte_eth_dma_zone_free(dev, "fdir_tx_ring", pf->fdir.txq->queue_id); i40e_dev_tx_queue_release(pf->fdir.txq); pf->fdir.txq = NULL; i40e_vsi_release(vsi); diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c index 8329cbdd4e..b67eb1ee94 100644 --- a/drivers/net/i40e/i40e_rxtx.c +++ b/drivers/net/i40e/i40e_rxtx.c @@ -2034,6 +2034,7 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev, return -ENOMEM; } + rxq->mz = rz; /* Zero all the descriptors in the ring. */ memset(rz->addr, 0, ring_size); @@ -2113,6 +2114,7 @@ i40e_dev_rx_queue_release(void *rxq) i40e_rx_queue_release_mbufs(q); rte_free(q->sw_ring); + rte_memzone_free(q->mz); rte_free(q); } @@ -2433,6 +2435,7 @@ i40e_dev_tx_queue_setup(struct rte_eth_dev *dev, return -ENOMEM; } + txq->mz = tz; txq->nb_tx_desc = nb_desc; txq->tx_rs_thresh = tx_rs_thresh; txq->tx_free_thresh = tx_free_thresh; @@ -2506,6 +2509,7 @@ i40e_dev_tx_queue_release(void *txq) i40e_tx_queue_release_mbufs(q); rte_free(q->sw_ring); + rte_memzone_free(q->mz); rte_free(q); } @@ -3058,7 +3062,6 @@ i40e_dev_free_queues(struct rte_eth_dev *dev) continue; i40e_dev_rx_queue_release(dev->data->rx_queues[i]); dev->data->rx_queues[i] = NULL; - rte_eth_dma_zone_free(dev, "rx_ring", i); } for (i = 0; i < dev->data->nb_tx_queues; i++) { @@ -3066,7 +3069,6 @@ i40e_dev_free_queues(struct rte_eth_dev *dev) continue; i40e_dev_tx_queue_release(dev->data->tx_queues[i]); dev->data->tx_queues[i] = NULL; - rte_eth_dma_zone_free(dev, "tx_ring", i); } } @@ -3109,6 +3111,7 @@ i40e_fdir_setup_tx_resources(struct i40e_pf *pf) return I40E_ERR_NO_MEMORY; } + txq->mz = tz; txq->nb_tx_desc = I40E_FDIR_NUM_TX_DESC; txq->queue_id = I40E_FDIR_QUEUE_ID; txq->reg_idx = pf->fdir.fdir_vsi->base_queue; @@ -3167,6 +3170,7 @@ i40e_fdir_setup_rx_resources(struct i40e_pf *pf) return I40E_ERR_NO_MEMORY; } + rxq->mz = rz; rxq->nb_rx_desc = I40E_FDIR_NUM_RX_DESC; rxq->queue_id = I40E_FDIR_QUEUE_ID; rxq->reg_idx = pf->fdir.fdir_vsi->base_queue; diff --git a/drivers/net/i40e/i40e_rxtx.h b/drivers/net/i40e/i40e_rxtx.h index 5ccf5773e8..3c1a2fab89 100644 --- a/drivers/net/i40e/i40e_rxtx.h +++ b/drivers/net/i40e/i40e_rxtx.h @@ -121,6 +121,7 @@ struct i40e_rx_queue { uint16_t rx_using_sse; /**