From: Yong Zhao <yong.zhao@xxxxxxx>
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 <yong.zhao at amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 7 +++++++
drivers/gpu/drm/amd/amdkfd/kfd_module.c | 4 ++++
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 5 +++++
3 files changed, 16 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 32e93b5..5d05d12 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1217,6 +1217,13 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
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();
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index ee7bf07..3a8c15a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -92,6 +92,10 @@ MODULE_PARM_DESC(noretry,
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)
{
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d9bf70b..8473e7b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -144,6 +144,11 @@ extern int ignore_crat;
*/
extern int vega10_noretry;
+/*
+ * Halt if HWS hang is detected
+ */
+extern int halt_if_hws_hang;
+
/**
* enum kfd_sched_policy
*
--
2.7.4
