drm/amdgpu: abort KIQ waits when there is a pending reset

Stop waiting for the KIQ to return back when there is a reset pending.
It's quite likely that the KIQ will never response.
Signed-off-by: Koenig Christian <Christian.Koenig@amd.com>
Suggested-by: Lazar Lijo <Lijo.Lazar@amd.com>
Tested-by: Victor Skvortsov <victor.skvortsov@amd.com>
Signed-off-by: Victor Skvortsov <victor.skvortsov@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c

@@ -786,7 +786,8 @@ void amdgpu_gmc_fw_reg_write_reg_wait(struct amdgpu_device *adev,
 		goto failed_kiq;
 
 	might_sleep();
-	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY) {
+	while (r < 1 && cnt++ < MAX_KIQ_REG_TRY &&
+	       !amdgpu_reset_pending(adev->reset_domain)) {
 
 		msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
 		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);

drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h

@@ -136,6 +136,12 @@ static inline bool amdgpu_reset_domain_schedule(struct amdgpu_reset_domain *doma
 	return queue_work(domain->wq, work);
 }
 
+static inline bool amdgpu_reset_pending(struct amdgpu_reset_domain *domain)
+{
+	lockdep_assert_held(&domain->sem);
+	return rwsem_is_contended(&domain->sem);
+}
+
 void amdgpu_device_lock_reset_domain(struct amdgpu_reset_domain *reset_domain);
 
 void amdgpu_device_unlock_reset_domain(struct amdgpu_reset_domain *reset_domain);