From 5962c2c8036b4dcf10ec6c481be656ae4700b664 Mon Sep 17 00:00:00 2001 From: Faisal Latif Date: Wed, 8 Apr 2009 14:23:55 -0700 Subject: RDMA/nes: Fix nes_nic_cm_xmit() error handling We are getting crash or hung situation when we are running network cable pull tests during RDMA traffic. In schedule_nes_timer(), we return an error if nes_nic_cm_xmit() returns failure. This is changed to success as skb is being put on the timer routines to be processed later. In send_syn() case, we are indicating connect failure once from nes_connect() and the other when the rexmit retries expires. The other issue is skb->users which we are incrementing before calling nes_nic_cm_xmit() which calls dev_queue_xmit() but in case of failure we are decrementing the skb->users at the same time putting the skb on the rexmit path. Even if dev_queue_xmit() fails, the skb->users is decremented already. We are removing the decrement of skb->users in case of failure from both schedule_nes_timer() as well as from nes_cm_timer_tick(). There is also extra check in nes_cm_timer_tick() for rexmit failure which does a break from the loop is removed. This causes problem as the other nodes have their cm_node->ref_count incremented and are not processed. Signed-off-by: Faisal Latif Signed-off-by: Roland Dreier --- drivers/infiniband/hw/nes/nes_cm.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c index a09caf5b387..dbd9a75474e 100644 --- a/drivers/infiniband/hw/nes/nes_cm.c +++ b/drivers/infiniband/hw/nes/nes_cm.c @@ -446,8 +446,8 @@ int schedule_nes_timer(struct nes_cm_node *cm_node, struct sk_buff *skb, if (ret != NETDEV_TX_OK) { nes_debug(NES_DBG_CM, "Error sending packet %p " "(jiffies = %lu)\n", new_send, jiffies); - atomic_dec(&new_send->skb->users); new_send->timetosend = jiffies; + ret = NETDEV_TX_OK; } else { cm_packets_sent++; if (!send_retrans) { @@ -631,7 +631,6 @@ static void nes_cm_timer_tick(unsigned long pass) nes_debug(NES_DBG_CM, "rexmit failed for " "node=%p\n", cm_node); cm_packets_bounced++; - atomic_dec(&send_entry->skb->users); send_entry->retrycount--; nexttimeout = jiffies + NES_SHORT_TIME; settimer = 1; @@ -667,11 +666,6 @@ static void nes_cm_timer_tick(unsigned long pass) spin_unlock_irqrestore(&cm_node->retrans_list_lock, flags); rem_ref_cm_node(cm_node->cm_core, cm_node); - if (ret != NETDEV_TX_OK) { - nes_debug(NES_DBG_CM, "rexmit failed for cm_node=%p\n", - cm_node); - break; - } } if (settimer) { -- cgit v1.2.3