From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from EX13-EDG-OU-001.vmware.com (ex13-edg-ou-001.vmware.com [208.91.0.189]) by dpdk.org (Postfix) with ESMTP id E32ADBD15 for ; Wed, 26 Oct 2016 20:03:47 +0200 (CEST) Received: from sc9-mailhost2.vmware.com (10.113.161.72) by EX13-EDG-OU-001.vmware.com (10.113.208.155) with Microsoft SMTP Server id 15.0.1156.6; Wed, 26 Oct 2016 11:03:40 -0700 Received: from sc2-edge-ivybridge-01.eng.vmware.com (sc2-edge-ivybridge-01.eng.vmware.com [10.172.139.164]) by sc9-mailhost2.vmware.com (Postfix) with ESMTP id 7DFBAB07AC; Wed, 26 Oct 2016 11:03:46 -0700 (PDT) From: Yong Wang To: Date: Wed, 26 Oct 2016 10:45:07 -0700 Message-ID: <1477503907-11306-1-git-send-email-yongwang@vmware.com> X-Mailer: git-send-email 1.9.1 MIME-Version: 1.0 Content-Type: text/plain Received-SPF: None (EX13-EDG-OU-001.vmware.com: yongwang@vmware.com does not designate permitted sender hosts) Cc: dev@dpdk.org Subject: [dpdk-dev] [PATCH] net/vmxnet3: fix mbuf release on reset/stop X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Oct 2016 18:03:48 -0000 During device reset/stop, vmxnet3 releases all mbufs in tx and rx cmd ring. For rx, we should go over all ring descriptors and free using rte_pktmbuf_free_seg() instead of rte_pktmbuf_free() as the metadata of the mbuf might not be properly initialized (initialization after mempool creation is done in the rx routine) and the mbuf should always be a single-segment one when populated. For tx, we can use the existing way as mbuf, if any, will be a valid one stashed in the eop. Fixes: dfaff37fc46d ("vmxnet3: import new vmxnet3 poll mode driver implementation") Signed-off-by: Yong Wang --- drivers/net/vmxnet3/vmxnet3_rxtx.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c b/drivers/net/vmxnet3/vmxnet3_rxtx.c index 31f396c..b109168 100644 --- a/drivers/net/vmxnet3/vmxnet3_rxtx.c +++ b/drivers/net/vmxnet3/vmxnet3_rxtx.c @@ -140,10 +140,10 @@ vmxnet3_txq_dump(struct vmxnet3_tx_queue *txq) #endif static void -vmxnet3_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring) +vmxnet3_tx_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring) { while (ring->next2comp != ring->next2fill) { - /* No need to worry about tx desc ownership, device is quiesced by now. */ + /* No need to worry about desc ownership, device is quiesced by now. */ vmxnet3_buf_info_t *buf_info = ring->buf_info + ring->next2comp; if (buf_info->m) { @@ -157,9 +157,27 @@ vmxnet3_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring) } static void +vmxnet3_rx_cmd_ring_release_mbufs(vmxnet3_cmd_ring_t *ring) +{ + uint32_t i; + + for (i = 0; i < ring->size; i++) { + /* No need to worry about desc ownership, device is quiesced by now. */ + vmxnet3_buf_info_t *buf_info = &ring->buf_info[i]; + + if (buf_info->m) { + rte_pktmbuf_free_seg(buf_info->m); + buf_info->m = NULL; + buf_info->bufPA = 0; + buf_info->len = 0; + } + vmxnet3_cmd_ring_adv_next2comp(ring); + } +} + +static void vmxnet3_cmd_ring_release(vmxnet3_cmd_ring_t *ring) { - vmxnet3_cmd_ring_release_mbufs(ring); rte_free(ring->buf_info); ring->buf_info = NULL; } @@ -170,6 +188,8 @@ vmxnet3_dev_tx_queue_release(void *txq) vmxnet3_tx_queue_t *tq = txq; if (tq != NULL) { + /* Release mbufs */ + vmxnet3_tx_cmd_ring_release_mbufs(&tq->cmd_ring); /* Release the cmd_ring */ vmxnet3_cmd_ring_release(&tq->cmd_ring); } @@ -182,6 +202,10 @@ vmxnet3_dev_rx_queue_release(void *rxq) vmxnet3_rx_queue_t *rq = rxq; if (rq != NULL) { + /* Release mbufs */ + for (i = 0; i < VMXNET3_RX_CMDRING_SIZE; i++) + vmxnet3_rx_cmd_ring_release_mbufs(&rq->cmd_ring[i]); + /* Release both the cmd_rings */ for (i = 0; i < VMXNET3_RX_CMDRING_SIZE; i++) vmxnet3_cmd_ring_release(&rq->cmd_ring[i]); @@ -199,7 +223,7 @@ vmxnet3_dev_tx_queue_reset(void *txq) if (tq != NULL) { /* Release the cmd_ring mbufs */ - vmxnet3_cmd_ring_release_mbufs(&tq->cmd_ring); + vmxnet3_tx_cmd_ring_release_mbufs(&tq->cmd_ring); } /* Tx vmxnet rings structure initialization*/ @@ -228,7 +252,7 @@ vmxnet3_dev_rx_queue_reset(void *rxq) if (rq != NULL) { /* Release both the cmd_rings mbufs */ for (i = 0; i < VMXNET3_RX_CMDRING_SIZE; i++) - vmxnet3_cmd_ring_release_mbufs(&rq->cmd_ring[i]); + vmxnet3_rx_cmd_ring_release_mbufs(&rq->cmd_ring[i]); } ring0 = &rq->cmd_ring[0]; -- 1.9.1