drm/amdgpu: process RAS fatal error MB notification

For RAS error scenario, VF guest driver will check mailbox
and set fed flag to avoid unnecessary HW accesses.
additionally, poll for reset completion message first
to avoid accidentally spamming multiple reset requests to host.

v2: add another mailbox check for handling case where kfd detects
timeout first

v3: set host_flr bit and use wait_for_reset

Signed-off-by: Vignesh Chander <Vignesh.Chander@amd.com>
Reviewed-by: Zhigang Luo <Zhigang.Luo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 8 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index 65656afc6ed1..f5411b798e11 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -408,6 +408,13 @@ static void xgpu_ai_ras_poison_handler(struct amdgpu_device *adev,
 	xgpu_ai_send_access_requests(adev, IDH_RAS_POISON);
 }
 
+static bool xgpu_ai_rcvd_ras_intr(struct amdgpu_device *adev)
+{
+	enum idh_event msg = xgpu_ai_mailbox_peek_msg(adev);
+
+	return (msg == IDH_RAS_ERROR_DETECTED || msg == 0xFFFFFFFF);
+}
+
 const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
 	.req_full_gpu	= xgpu_ai_request_full_gpu_access,
 	.rel_full_gpu	= xgpu_ai_release_full_gpu_access,
@@ -417,4 +424,5 @@ const struct amdgpu_virt_ops xgpu_ai_virt_ops = {
 	.trans_msg = xgpu_ai_mailbox_trans_msg,
 	.req_init_data  = xgpu_ai_request_init_data,
 	.ras_poison_handler = xgpu_ai_ras_poison_handler,
+	.rcvd_ras_intr = xgpu_ai_rcvd_ras_intr,
 };