bnxt_re: Stop issuing further cmds to FW once a cmd times out

Once a cmd to FW times out(after 20s) it is reasonable to
assume the FW or atleast the control path is dead.
No point issuing further cmds to the FW as each subsequent cmd
with another 20s timeout will cascade resulting in unnecessary
traces and/or NMI Lockups.

Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -107,6 +107,9 @@ static int __send_message(struct bnxt_qplib_rcfw *rcfw, struct cmdq_base *req,
 		return -EINVAL;
 	}
 
+	if (test_bit(FIRMWARE_TIMED_OUT, &rcfw->flags))
+		return -ETIMEDOUT;
+
 	/* Cmdq are in 16-byte units, each request can consume 1 or more
 	 * cmdqe
 	 */
@@ -226,6 +229,7 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 		/* timed out */
 		dev_err(&rcfw->pdev->dev, "QPLIB: cmdq[%#x]=%#x timedout (%d)msec",
 			cookie, opcode, RCFW_CMD_WAIT_TIME_MS);
+		set_bit(FIRMWARE_TIMED_OUT, &rcfw->flags);
 		return rc;
 	}
 

drivers/infiniband/hw/bnxt_re/qplib_rcfw.h

@@ -162,8 +162,9 @@ struct bnxt_qplib_rcfw {
 	unsigned long		*cmdq_bitmap;
 	u32			bmap_size;
 	unsigned long		flags;
-#define FIRMWARE_INITIALIZED_FLAG	1
+#define FIRMWARE_INITIALIZED_FLAG	BIT(0)
 #define FIRMWARE_FIRST_FLAG		BIT(31)
+#define FIRMWARE_TIMED_OUT		BIT(3)
 	wait_queue_head_t	waitq;
 	int			(*aeq_handler)(struct bnxt_qplib_rcfw *,
 					       struct creq_func_event *);