[PATCH 2/4] drm/amdgpu: Add msg handlers for SRIOV RAS Telemetry

[Victor Skvortsov <victor.skvortsov@xxxxxxx>]

Signed-off-by: Victor Skvortsov <victor.skvortsov@xxxxxxx>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h |  1 +
 drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c    | 16 ++++++++++++++--
 drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h    |  2 ++
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index b650a2032c42..f6eee57338df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -95,6 +95,7 @@ struct amdgpu_virt_ops {
 	void (*ras_poison_handler)(struct amdgpu_device *adev,
 					enum amdgpu_ras_block block);
 	bool (*rcvd_ras_intr)(struct amdgpu_device *adev);
+	int (*req_ras_err_count)(struct amdgpu_device *adev);
 };
 
 /*
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
index f47bd7ada4d7..843dcd112b01 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -61,15 +61,18 @@ static enum idh_event xgpu_nv_mailbox_peek_msg(struct amdgpu_device *adev)
 static int xgpu_nv_mailbox_rcv_msg(struct amdgpu_device *adev,
 				   enum idh_event event)
 {
+	int r = 0;
 	u32 reg;
 
 	reg = RREG32_NO_KIQ(mmMAILBOX_MSGBUF_RCV_DW0);
-	if (reg != event)
+	if (reg == IDH_FAIL)
+		r = -EINVAL;
+	else if (reg != event)
 		return -ENOENT;
 
 	xgpu_nv_mailbox_send_ack(adev);
 
-	return 0;
+	return r;
 }
 
 static uint8_t xgpu_nv_peek_ack(struct amdgpu_device *adev)
@@ -178,6 +181,9 @@ static int xgpu_nv_send_access_requests_with_param(struct amdgpu_device *adev,
 		if (data1 != 0)
 			event = IDH_RAS_POISON_READY;
 		break;
+	case MB_REQ_RAS_ERROR_COUNT:
+		event = IDH_RAS_ERROR_COUNT_READY;
+		break;
 	default:
 		break;
 	}
@@ -456,6 +462,11 @@ static bool xgpu_nv_rcvd_ras_intr(struct amdgpu_device *adev)
 	return (msg == IDH_RAS_ERROR_DETECTED || msg == 0xFFFFFFFF);
 }
 
+static int xgpu_nv_req_ras_err_count(struct amdgpu_device *adev)
+{
+	return xgpu_nv_send_access_requests(adev, MB_REQ_RAS_ERROR_COUNT);
+}
+
 const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
 	.req_full_gpu	= xgpu_nv_request_full_gpu_access,
 	.rel_full_gpu	= xgpu_nv_release_full_gpu_access,
@@ -466,4 +477,5 @@ const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
 	.trans_msg = xgpu_nv_mailbox_trans_msg,
 	.ras_poison_handler = xgpu_nv_ras_poison_handler,
 	.rcvd_ras_intr = xgpu_nv_rcvd_ras_intr,
+	.req_ras_err_count = xgpu_nv_req_ras_err_count,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
index 74e213e1e937..33d56e5f12ff 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
@@ -56,6 +56,8 @@ enum idh_event {
 	IDH_RAS_POISON_READY,
 	IDH_PF_SOFT_FLR_NOTIFICATION,
 	IDH_RAS_ERROR_DETECTED,
+	IDH_RAS_ERROR_COUNT_READY = 11,
+
 	IDH_TEXT_MESSAGE = 255,
 };
 
-- 
2.34.1