[PATCH 16/18] drm/amdgpu: recover page tables after gpu reset

[Chunming Zhou]

Change-Id: I963598ba6eb44bc8620d70e026c0175d1a1de120
Signed-off-by: Chunming Zhou <David1.Zhou at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 77 +++++++++++++++++++++++++++++-
 1 file changed, 76 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e5ae0a8..ff11eeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2162,18 +2162,93 @@ retry:
 		amdgpu_atombios_scratch_regs_restore(adev);
 	}
 	if (!r) {
+		struct amdgpu_ring *buffer_ring = adev->mman.buffer_funcs_ring;
+
 		amdgpu_irq_gpu_reset_resume_helper(adev);
 		r = amdgpu_ib_ring_tests(adev);
 		if (r) {
 			dev_err(adev->dev, "ib ring test failed (%d).\n", r);
 			r = amdgpu_suspend(adev);
+			need_full_reset = true;
 			goto retry;
 		}
-
+		/**
+		 * recovery vm page tables, since we cannot depend on VRAM is no problem
+		 * after gpu full reset.
+		 */
+		if (need_full_reset && !(adev->flags & AMD_IS_APU)) {
+			struct amdgpu_vm *vm, *tmp;
+			struct amdgpu_ring *ring;
+			struct fence *fence = NULL;
+			int i;
+
+			DRM_INFO("recover page table from shadow\n");
+			for (i = 0; i < adev->vm_manager.vm_pte_num_rings; i++) {
+				ring = adev->vm_manager.vm_pte_rings[i];
+				amd_sched_rq_block_entity(
+					&ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL], true);
+				amd_sched_rq_block_entity(
+					&ring->sched.sched_rq[AMD_SCHED_PRIORITY_KERNEL], true);
+			}
+			spin_lock(&adev->vm_list_lock);
+			list_for_each_entry_safe(vm, tmp, &adev->vm_list, list) {
+				spin_unlock(&adev->vm_list_lock);
+				amd_sched_block_entity(&vm->shadow_entity, false);
+				spin_lock(&adev->vm_list_lock);
+			}
+			spin_unlock(&adev->vm_list_lock);
+			for (i = 0; i < adev->vm_manager.vm_pte_num_rings; i++) {
+				ring = adev->vm_manager.vm_pte_rings[i];
+				kthread_unpark(ring->sched.thread);
+			}
+			spin_lock(&adev->vm_list_lock);
+			list_for_each_entry_safe(vm, tmp, &adev->vm_list, list) {
+				spin_unlock(&adev->vm_list_lock);
+				/* wait for all shadow jobs finished */
+				if (vm->shadow_entity.last_fence)
+					fence_wait(vm->shadow_entity.last_fence, false);
+				spin_lock(&adev->vm_list_lock);
+			}
+			spin_unlock(&adev->vm_list_lock);
+			for (i = 0; i < adev->vm_manager.vm_pte_num_rings; i++) {
+				ring = adev->vm_manager.vm_pte_rings[i];
+				kthread_park(ring->sched.thread);
+				amd_sched_rq_block_entity(
+					&ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL], true);
+				amd_sched_rq_block_entity(
+					&ring->sched.sched_rq[AMD_SCHED_PRIORITY_KERNEL], true);
+			}
+			amd_sched_block_entity(&adev->mman.entity, false);
+			kthread_unpark(buffer_ring->sched.thread);
+			spin_lock(&adev->vm_list_lock);
+			list_for_each_entry_safe(vm, tmp, &adev->vm_list, list) {
+				spin_unlock(&adev->vm_list_lock);
+				amdgpu_vm_recover_page_table_from_shadow(adev, vm);
+				if (vm->shadow_sync_fence) {
+					fence_put(fence);
+					fence = fence_get(vm->shadow_sync_fence);
+				}
+				spin_lock(&adev->vm_list_lock);
+			}
+			spin_unlock(&adev->vm_list_lock);
+			if (fence)
+				fence_wait(fence, false);
+			fence_put(fence);
+			for (i = 0; i < adev->vm_manager.vm_pte_num_rings; i++) {
+				ring = adev->vm_manager.vm_pte_rings[i];
+				kthread_park(ring->sched.thread);
+				amd_sched_rq_block_entity(
+					&ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL], false);
+				amd_sched_rq_block_entity(
+					&ring->sched.sched_rq[AMD_SCHED_PRIORITY_KERNEL], false);
+			}
+		}
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = adev->rings[i];
 			if (!ring)
 				continue;
+
+			DRM_INFO("ring:%d recover jobs\n", ring->idx);
 			amd_sched_job_recovery(&ring->sched);
 			kthread_unpark(ring->sched.thread);
 		}
-- 
1.9.1