[PATCH] drm/amdkfd: Add GPU reset SMI event

[Mukul Joshi]

Add support for reporting GPU reset events through SMI.

Signed-off-by: Mukul Joshi <mukul.joshi at amd.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c     |  2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 18 ++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h |  1 +
 include/uapi/linux/kfd_ioctl.h              |  1 +
 4 files changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index d5e790f046b4..d788aa24ef3f 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -811,6 +811,8 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 	if (!kfd->init_complete)
 		return 0;
 
+	kfd_smi_event_update_gpu_reset(kfd);
+
 	kfd->dqm->ops.pre_reset(kfd->dqm);
 
 	kgd2kfd_suspend(kfd, false);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
index 4d4b6e3ab697..4de57923d9f5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c
@@ -174,6 +174,24 @@ static void add_event_to_kfifo(struct kfd_dev *dev, unsigned int smi_event,
 	rcu_read_unlock();
 }
 
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev)
+{
+	/*
+	 * GpuReset msg = empty
+	 * 1 byte event + 1 byte space + 1 byte \n + 1 byte \0 = 4
+	 */
+	char fifo_in[4];
+	int len;
+
+	if (list_empty(&dev->smi_clients)) {
+		return;
+	}
+
+	len = snprintf(fifo_in, 4, "%x \n", KFD_SMI_EVENT_GPU_RESET);
+
+	add_event_to_kfifo(dev, KFD_SMI_EVENT_GPU_RESET, fifo_in, len);
+}
+
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 					     uint32_t throttle_bitmask)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
index 15537b2cccb5..ffdb822d120b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.h
@@ -27,5 +27,6 @@ int kfd_smi_event_open(struct kfd_dev *dev, uint32_t *fd);
 void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid);
 void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev,
 					     uint32_t throttle_bitmask);
+void kfd_smi_event_update_gpu_reset(struct kfd_dev *dev);
 
 #endif
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index cb1f963a84e0..128b6235b540 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -453,6 +453,7 @@ enum kfd_smi_event {
         KFD_SMI_EVENT_NONE = 0, /* not used */
         KFD_SMI_EVENT_VMFAULT = 1, /* event start counting at 1 */
         KFD_SMI_EVENT_THERMAL_THROTTLE = 2,
+	KFD_SMI_EVENT_GPU_RESET = 3,
 };
 
 #define KFD_SMI_EVENT_MASK_FROM_INDEX(i) (1ULL << ((i) - 1))
-- 
2.17.1