Once sync flood interrupt is triggered by RAS error, before
actual GPU recovery job, it's necessary to log on and print
non-zero error counter, this will help user knows where the
RAS error source is from quickly.
Signed-off-by: Guchun Chen <guchun.chen@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 33 +++++++++++++++++++++++++
1 file changed, 33 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index cef94e2169fe..6a9a45d6b9e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1319,6 +1319,33 @@ static int amdgpu_ras_interrupt_remove_all(struct amdgpu_device *adev)
}
/* ih end */
+/* traversal all IPs except NBIO to query error counter */
+static void amdgpu_ras_log_on_err_counter(struct amdgpu_device *adev)
+{
+ struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+ struct ras_manager *obj;
+
+ if (!con)
+ return;
+
+ list_for_each_entry(obj, &con->head, node) {
+ struct ras_query_if info = {
+ .head = obj->head,
+ };
+
+ /*
+ * PCIE_BIF IP has one different isr by ras controller
+ * interrupt, the specific ras counter query will be
+ * done in that isr. So skip such block from common
+ * sync flood interrupt isr calling.
+ */
+ if (info.head.block == AMDGPU_RAS_BLOCK__PCIE_BIF)
+ continue;
+
+ amdgpu_ras_error_query(adev, &info);
+ }
+}
+
/* recovery begin */
/* return 0 on success.
@@ -1373,6 +1400,12 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
struct amdgpu_ras *ras =
container_of(work, struct amdgpu_ras, recovery_work);
+ /*
+ * Query and print non zero error counter per IP block for
+ * awareness before recovering GPU.
+ */
+ amdgpu_ras_log_on_err_counter(ras->adev);
+
if (amdgpu_device_should_recover_gpu(ras->adev))
amdgpu_device_gpu_recover(ras->adev, 0);
atomic_set(&ras->in_recovery, 0);
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
