RDMA/bnxt_re: cancel all control path command waiters upon error

When an error is detected in FW, wake up all the waiters as the
all of them need to be completed with timeout. Add the device
error state also as a wait condition.

Signed-off-by: Kashyap Desai <[email protected]>
Signed-off-by: Selvin Xavier <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Leon Romanovsky <[email protected]>

Author: kadesai16

drivers/infiniband/hw/bnxt_re/main.c

@@ -1495,6 +1495,7 @@ static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state)
 	 */
 	set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags);
 	set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
+	wake_up_all(&rdev->rcfw.cmdq.waitq);
 	mutex_unlock(&bnxt_re_mutex);
 
 	return 0;

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -116,10 +116,10 @@ static int __wait_for_resp(struct bnxt_qplib_rcfw *rcfw, u16 cookie, u8 opcode)
 			return -ETIMEDOUT;
 
 		wait_event_timeout(cmdq->waitq,
-				   !test_bit(cbit, cmdq->cmdq_bitmap),
+				   !test_bit(cbit, cmdq->cmdq_bitmap) ||
+				   test_bit(ERR_DEVICE_DETACHED, &cmdq->flags),
 				   msecs_to_jiffies(RCFW_FW_STALL_TIMEOUT_SEC
 						    * 1000));
-
 		if (!test_bit(cbit, cmdq->cmdq_bitmap))
 			return 0;