RDMA/iw_cxgb4: Handle ULP accept/reject during ABORTING

c4iw_reject() and c4iw_accept() need to handle the case where the
endpoint has timed out and is in the middle of ABORTING the connection.

Here is the flow that causes the BUG_ON() to fire on the server side:

1) offload connection setup and endpoint timer started

2) MPA_START request received from peer, CONNECT_REQUEST passed to ULP

3) endpoint timer fires, and process_timeout() aborts the connection,
this moves the endpoint state to ABORTING until HW sends up the
ABORT_RPL_RSS.

4) application exits closing the CONNECT_REQUEST cm_id.  The IWCM calls
c4iw_reject_cr() to destroy this connection request.

5) WHAMO: BUG_ON() because the state is ABORTING.

The fix is to change c4iw_reject_cr() and c4iw_accept_cr() to fail the
operation if the state is not in MPA_REQ_RCVD vs in DEAD.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This commit is contained in:
Hariprasad S 2016-05-06 22:18:06 +05:30 committed by Doug Ledford
parent ceb110a8c1
commit e8667a9b35

View file

@ -3005,13 +3005,12 @@ int c4iw_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len)
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
mutex_lock(&ep->com.mutex);
if (ep->com.state == DEAD) {
if (ep->com.state != MPA_REQ_RCVD) {
mutex_unlock(&ep->com.mutex);
c4iw_put_ep(&ep->com);
return -ECONNRESET;
}
set_bit(ULP_REJECT, &ep->com.history);
BUG_ON(ep->com.state != MPA_REQ_RCVD);
if (mpa_rev == 0)
disconnect = 2;
else {
@ -3040,12 +3039,11 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
mutex_lock(&ep->com.mutex);
if (ep->com.state == DEAD) {
if (ep->com.state != MPA_REQ_RCVD) {
err = -ECONNRESET;
goto err_out;
}
BUG_ON(ep->com.state != MPA_REQ_RCVD);
BUG_ON(!qp);
set_bit(ULP_ACCEPT, &ep->com.history);