DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH] The VMXNET3 PMD can't receive packet suddenly after a lot of traffic coming in. The root cause is due to mbuf allocation fail in vmxnet3_post_rx_bufs() and there is no error handling when it is called from vmxnet3_recv_pkts(). The RXD will not have "free" mbuf for it but the counter still increment. Finally, no packet can be received. This fix is allocate the mbuf first, if the allocation is failed, then don't receive any packet and the packet will remain in RXD to prevent any packet drop.If the allocation is sucess, the vmxnet3_post_rx_bufs() will call vmxnet3_renew_desc() and RXD will be renew inside.
@ 2015-07-23  1:48 mac_leehk
  2015-07-23  5:27 ` Stephen Hemminger
  0 siblings, 1 reply; 5+ messages in thread
From: mac_leehk @ 2015-07-23  1:48 UTC (permalink / raw)
  To: dev

From: marco <marco@ubuntu.(none)>

---
 drivers/net/vmxnet3/vmxnet3_rxtx.c |   54 +++++++++++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)
 mode change 100644 => 100755 drivers/net/vmxnet3/vmxnet3_rxtx.c

diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c b/drivers/net/vmxnet3/vmxnet3_rxtx.c
old mode 100644
new mode 100755
index 39ad6ef..d560bbb
--- a/drivers/net/vmxnet3/vmxnet3_rxtx.c
+++ b/drivers/net/vmxnet3/vmxnet3_rxtx.c
@@ -421,6 +421,51 @@ vmxnet3_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
 	return nb_tx;
 }
 
+static inline void
+vmxnet3_renew_desc(vmxnet3_rx_queue_t *rxq, uint8_t ring_id,struct rte_mbuf *mbuf)
+{
+	uint32_t  val = 0;
+	struct vmxnet3_cmd_ring *ring = &rxq->cmd_ring[ring_id];
+
+	struct Vmxnet3_RxDesc *rxd;
+	vmxnet3_buf_info_t *buf_info = &ring->buf_info[ring->next2fill];
+
+	rxd = (struct Vmxnet3_RxDesc *)(ring->base + ring->next2fill);
+
+	if (ring->rid == 0) {
+	/* Usually: One HEAD type buf per packet
+	 * val = (ring->next2fill % rxq->hw->bufs_per_pkt) ?
+	 * VMXNET3_RXD_BTYPE_BODY : VMXNET3_RXD_BTYPE_HEAD;
+	 */
+
+	/* We use single packet buffer so all heads here */
+		val = VMXNET3_RXD_BTYPE_HEAD;
+	} else {
+	/* All BODY type buffers for 2nd ring; which won't be used at all by ESXi */
+		val = VMXNET3_RXD_BTYPE_BODY;
+	}
+
+	/*
+	 * Load mbuf pointer into buf_info[ring_size]
+	 * buf_info structure is equivalent to cookie for virtio-virtqueue
+	 */
+	buf_info->m = mbuf;
+	buf_info->len = (uint16_t)(mbuf->buf_len -
+					   RTE_PKTMBUF_HEADROOM);
+	buf_info->bufPA = RTE_MBUF_DATA_DMA_ADDR_DEFAULT(mbuf);
+
+	/* Load Rx Descriptor with the buffer's GPA */
+	rxd->addr = buf_info->bufPA;
+
+	/* After this point rxd->addr MUST not be NULL */
+	rxd->btype = val;
+	rxd->len = buf_info->len;
+	/* Flip gen bit at the end to change ownership */
+	rxd->gen = ring->gen;
+
+	vmxnet3_cmd_ring_adv_next2fill(ring);
+
+}
 /*
  *  Allocates mbufs and clusters. Post rx descriptors with buffer details
  *  so that device can receive packets in those buffers.
@@ -575,8 +620,15 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
 	}
 
 	while (rcd->gen == rxq->comp_ring.gen) {
+	        struct rte_mbuf *rep;
 		if (nb_rx >= nb_pkts)
 			break;
+		
+		rep = rte_rxmbuf_alloc(rxq->mp);
+        	if (rep == NULL) {
+            		rxq->stats.rx_buf_alloc_failure++;
+            		break;
+        	}
 
 		idx = rcd->rxdIdx;
 		ring_idx = (uint8_t)((rcd->rqID == rxq->qid1) ? 0 : 1);
@@ -657,7 +709,7 @@ rcd_done:
 		VMXNET3_INC_RING_IDX_ONLY(rxq->cmd_ring[ring_idx].next2comp, rxq->cmd_ring[ring_idx].size);
 
 		/* It's time to allocate some new buf and renew descriptors */
-		vmxnet3_post_rx_bufs(rxq, ring_idx);
+		vmxnet3_renew_desc(rxq, ring_idx,rep);
 		if (unlikely(rxq->shared->ctrl.updateRxProd)) {
 			VMXNET3_WRITE_BAR0_REG(hw, rxprod_reg[ring_idx] + (rxq->queue_id * VMXNET3_REG_ALIGN),
 					       rxq->cmd_ring[ring_idx].next2fill);
-- 
1.7.9.5

^ permalink raw reply	[flat|nested] 5+ messages in thread
end of thread, other threads:[~2015-07-23 16:45 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2015-07-23  1:48 [dpdk-dev] [PATCH] The VMXNET3 PMD can't receive packet suddenly after a lot of traffic coming in. The root cause is due to mbuf allocation fail in vmxnet3_post_rx_bufs() and there is no error handling when it is called from vmxnet3_recv_pkts(). The RXD will not have "free" mbuf for it but the counter still increment. Finally, no packet can be received. This fix is allocate the mbuf first, if the allocation is failed, then don't receive any packet and the packet will remain in RXD to prevent any packet drop.If the allocation is sucess, the vmxnet3_post_rx_bufs() will call vmxnet3_renew_desc() and RXD will be renew inside mac_leehk
2015-07-23  5:27 ` Stephen Hemminger
2015-07-23  5:44   ` [dpdk-dev] 回覆︰ " MAC Lee
2015-07-23  7:31   ` [dpdk-dev] [PATCH] The VMXNET3 PMD can't receive packet suddenly after a lot of traffic coming in. The root cause is due to mbuf allocation fail in vmxnet3_post_rx_bufs() and there is no error handling when it is called from vmxnet3_recv_pkts(). Th Vithal S Mohare
2015-07-23 16:45     ` Stephen Hemminger

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).