drm/amdkfd: Introduce KFD module parameter halt_if_hws_hang

This avoids triggering a GPU reset or otherwise changing the HW
state. Instead KFD will hang, which allows HW debugging tools to
analyze the problem.

Signed-off-by: Yong Zhao <[e-mail]>
Reviewed-by: Felix Kuehling <[e-mail]>
Signed-off-by: Felix Kuehling <[e-mail]>
Acked-by: Christian König <[e-mail]>
Signed-off-by: Oded Gabbay <[e-mail]>

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

···
 	while (*fence_addr != fence_value) {
 		if (time_after(jiffies, end_jiffies)) {
 			pr_err("qcm fence wait loop timeout expired\n");
+			/* In HWS case, this is used to halt the driver thread
+			 * in order not to mess up CP states before doing
+			 * scandumps for FW debugging.
+			 */
+			while (halt_if_hws_hang)
+				schedule();
+
 			return -ETIME;
 		}
 		schedule();

drivers/gpu/drm/amd/amdkfd/kfd_module.c

···
 
 static int amdkfd_init_completed;
 
+int halt_if_hws_hang;
+module_param(halt_if_hws_hang, int, 0644);
+MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
+
 int kgd2kfd_init(unsigned int interface_version,
 		const struct kgd2kfd_calls **g2f)
 {

drivers/gpu/drm/amd/amdkfd/kfd_priv.h

···
  */
 extern int vega10_noretry;
 
+/*
+ * Halt if HWS hang is detected
+ */
+extern int halt_if_hws_hang;
+
 /**
  * enum kfd_sched_policy
  *