summaryrefslogtreecommitdiffstats
path: root/drivers/infiniband
diff options
context:
space:
mode:
authorFaisal Latif <faisal.latif@intel.com>2010-08-14 21:04:56 +0000
committerRoland Dreier <rolandd@cisco.com>2010-09-08 14:35:48 -0700
commitdae58728dc64e9ad71c40ac90b463bff6ecce271 (patch)
tree7fcc7fdd26840917594dde63ce338289de5ec89e /drivers/infiniband
parent70c9db0fdfd703781c3b8c2caf9287806f642e02 (diff)
downloadop-kernel-dev-dae58728dc64e9ad71c40ac90b463bff6ecce271.zip
op-kernel-dev-dae58728dc64e9ad71c40ac90b463bff6ecce271.tar.gz
RDMA/nes: Fix double CLOSE event indication crash
During a stress testing in a large cluster, multiple close event are detected and BUG() is hit in the iWARP core. The cause is that the active node gave up while waiting for an MPA response from the peer and tried to close the connection by sending RST. The passive node driver receives the RST but is waiting for MPA response from the user. When the MPA accept is received, the driver offloads the connection and sends a CLOSE event. The driver gets an AE indicating RESET received and also sends a CLOSE event, hitting a BUG(). Fix this by correcting RESET handling and sending CLOSE events. Signed-off-by: Faisal Latif <faisal.latif@intel.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/hw/nes/nes_cm.c18
1 files changed, 10 insertions, 8 deletions
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 443cea5..61e0efd 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -502,7 +502,9 @@ int schedule_nes_timer(struct nes_cm_node *cm_node, struct sk_buff *skb,
static void nes_retrans_expired(struct nes_cm_node *cm_node)
{
struct iw_cm_id *cm_id = cm_node->cm_id;
- switch (cm_node->state) {
+ enum nes_cm_node_state state = cm_node->state;
+ cm_node->state = NES_CM_STATE_CLOSED;
+ switch (state) {
case NES_CM_STATE_SYN_RCVD:
case NES_CM_STATE_CLOSING:
rem_ref_cm_node(cm_node->cm_core, cm_node);
@@ -511,7 +513,6 @@ static void nes_retrans_expired(struct nes_cm_node *cm_node)
case NES_CM_STATE_FIN_WAIT1:
if (cm_node->cm_id)
cm_id->rem_ref(cm_id);
- cm_node->state = NES_CM_STATE_CLOSED;
send_reset(cm_node, NULL);
break;
default:
@@ -1439,9 +1440,6 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
break;
case NES_CM_STATE_MPAREQ_RCVD:
passive_state = atomic_add_return(1, &cm_node->passive_state);
- if (passive_state == NES_SEND_RESET_EVENT)
- create_event(cm_node, NES_CM_EVENT_RESET);
- cm_node->state = NES_CM_STATE_CLOSED;
dev_kfree_skb_any(skb);
break;
case NES_CM_STATE_ESTABLISHED:
@@ -1456,6 +1454,7 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
case NES_CM_STATE_CLOSED:
drop_packet(skb);
break;
+ case NES_CM_STATE_FIN_WAIT2:
case NES_CM_STATE_FIN_WAIT1:
case NES_CM_STATE_LAST_ACK:
cm_node->cm_id->rem_ref(cm_node->cm_id);
@@ -2777,6 +2776,12 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
return -EINVAL;
}
+ passive_state = atomic_add_return(1, &cm_node->passive_state);
+ if (passive_state == NES_SEND_RESET_EVENT) {
+ rem_ref_cm_node(cm_node->cm_core, cm_node);
+ return -ECONNRESET;
+ }
+
/* associate the node with the QP */
nesqp->cm_node = (void *)cm_node;
cm_node->nesqp = nesqp;
@@ -2979,9 +2984,6 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
printk(KERN_ERR "%s[%u] OFA CM event_handler returned, "
"ret=%d\n", __func__, __LINE__, ret);
- passive_state = atomic_add_return(1, &cm_node->passive_state);
- if (passive_state == NES_SEND_RESET_EVENT)
- create_event(cm_node, NES_CM_EVENT_RESET);
return 0;
}
OpenPOWER on IntegriCloud