When in gpu reset, don't use kiq, it will generate more TDR.
Signed-off-by: Emily Deng <Emily.Deng at amd.com>
---
drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 15 ++++-----------
1 file changed, 4 insertions(+), 11 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index eec991f..fcdbacb 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -331,15 +331,8 @@ signed long amdgpu_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
- /* don't wait anymore for gpu reset case because this way may
- * block gpu_recover() routine forever, e.g. this virt_kiq_rreg
- * is triggered in TTM and ttm_bo_lock_delayed_workqueue() will
- * never return if we keep waiting in virt_kiq_rreg, which cause
- * gpu_recover() hang there.
- *
- * also don't wait anymore for IRQ context
- * */
- if (r < 1 && (adev->in_gpu_reset || in_interrupt()))
+ /* don't wait anymore for IRQ context */
+ if (r < 1 && in_interrupt())
goto failed_kiq;
might_sleep();
@@ -387,8 +380,8 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev,
u32 tmp = gmc_v9_0_get_invalidate_req(vmid);
if (adev->gfx.kiq.ring.ready &&
- (amdgpu_sriov_runtime(adev) ||
- !amdgpu_sriov_vf(adev))) {
+ (amdgpu_sriov_runtime(adev) || !amdgpu_sriov_vf(adev)) &&
+ !adev->in_gpu_reset) {
r = amdgpu_kiq_reg_write_reg_wait(adev, hub->vm_inv_eng0_req + eng,
hub->vm_inv_eng0_ack + eng, tmp, 1 << vmid);
if (!r)
--
2.7.4
