drm/amdgpu: Handle IOMMU enabled case.

Problem:
Handle all DMA IOMMU group related dependencies before the
group is removed. Those manifest themself in that when IOMMU
enabled DMA map/unmap is dependent on the presence of IOMMU
group the device belongs to but, this group is released once
the device is removed from PCI topology.

Fix:
Expedite all such unmap operations to pci remove driver callback.

v5: Drop IOMMU notifier and switch to lockless call to ttm_tt_unpopulate
v6: Drop the BO unamp list
v7:
Drop amdgpu_gart_fini
In amdgpu_ih_ring_fini do uncinditional  check (!ih->ring)
to avoid freeing uniniitalized rings.
Call amdgpu_ih_ring_fini unconditionally.
v8: Add deatiled explanation

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210517143851.475058-1-andrey.grodzovsky@amd.com

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

@@ -3256,7 +3256,6 @@ static const struct attribute *amdgpu_dev_attributes[] = {
 	NULL
 };
 
-
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -3696,12 +3695,13 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 		amdgpu_ucode_sysfs_fini(adev);
 	sysfs_remove_files(&adev->dev->kobj, amdgpu_dev_attributes);
 
-
 	amdgpu_fbdev_fini(adev);
 
 	amdgpu_irq_fini_hw(adev);
 
 	amdgpu_device_ip_fini_early(adev);
+
+	amdgpu_gart_dummy_page_fini(adev);
 }
 
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)

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

@@ -92,7 +92,7 @@ static int amdgpu_gart_dummy_page_init(struct amdgpu_device *adev)
  *
  * Frees the dummy page used by the driver (all asics).
  */
-static void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev)
+void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev)
 {
 	if (!adev->dummy_page_addr)
 		return;
@@ -365,15 +365,3 @@ int amdgpu_gart_init(struct amdgpu_device *adev)
 
 	return 0;
 }
-
-/**
- * amdgpu_gart_fini - tear down the driver info for managing the gart
- *
- * @adev: amdgpu_device pointer
- *
- * Tear down the gart driver info and free the dummy page (all asics).
- */
-void amdgpu_gart_fini(struct amdgpu_device *adev)
-{
-	amdgpu_gart_dummy_page_fini(adev);
-}

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

@@ -57,7 +57,7 @@ void amdgpu_gart_table_vram_free(struct amdgpu_device *adev);
 int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev);
 void amdgpu_gart_table_vram_unpin(struct amdgpu_device *adev);
 int amdgpu_gart_init(struct amdgpu_device *adev);
-void amdgpu_gart_fini(struct amdgpu_device *adev);
+void amdgpu_gart_dummy_page_fini(struct amdgpu_device *adev);
 int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 		       int pages);
 int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,

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

@@ -115,9 +115,11 @@ int amdgpu_ih_ring_init(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih,
  */
 void amdgpu_ih_ring_fini(struct amdgpu_device *adev, struct amdgpu_ih_ring *ih)
 {
+
+	if (!ih->ring)
+		return;
+
 	if (ih->use_bus_addr) {
-		if (!ih->ring)
-			return;
 
 		/* add 8 bytes for the rptr/wptr shadows and
 		 * add them to the end of the ring allocation.

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

@@ -361,6 +361,11 @@ void amdgpu_irq_fini_hw(struct amdgpu_device *adev)
 		if (!amdgpu_device_has_dc_support(adev))
 			flush_work(&adev->hotplug_work);
 	}
+
+	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
+	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
+	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
+	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
 }
 
 /**

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

@@ -310,7 +310,6 @@ static int cik_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
 	return 0;

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

@@ -302,7 +302,6 @@ static int cz_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c

@@ -953,7 +953,6 @@ static int gmc_v10_0_sw_init(void *handle)
 static void gmc_v10_0_gart_fini(struct amdgpu_device *adev)
 {
 	amdgpu_gart_table_vram_free(adev);
-	amdgpu_gart_fini(adev);
 }
 
 static int gmc_v10_0_sw_fini(void *handle)

drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c

@@ -898,7 +898,6 @@ static int gmc_v6_0_sw_fini(void *handle)
 	amdgpu_vm_manager_fini(adev);
 	amdgpu_gart_table_vram_free(adev);
 	amdgpu_bo_fini(adev);
-	amdgpu_gart_fini(adev);
 	release_firmware(adev->gmc.fw);
 	adev->gmc.fw = NULL;
 

drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c

@@ -1085,7 +1085,6 @@ static int gmc_v7_0_sw_fini(void *handle)
 	kfree(adev->gmc.vm_fault_info);
 	amdgpu_gart_table_vram_free(adev);
 	amdgpu_bo_fini(adev);
-	amdgpu_gart_fini(adev);
 	release_firmware(adev->gmc.fw);
 	adev->gmc.fw = NULL;
 

drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c

@@ -1201,7 +1201,6 @@ static int gmc_v8_0_sw_fini(void *handle)
 	kfree(adev->gmc.vm_fault_info);
 	amdgpu_gart_table_vram_free(adev);
 	amdgpu_bo_fini(adev);
-	amdgpu_gart_fini(adev);
 	release_firmware(adev->gmc.fw);
 	adev->gmc.fw = NULL;
 

drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c

@@ -1602,7 +1602,6 @@ static int gmc_v9_0_sw_fini(void *handle)
 	amdgpu_gart_table_vram_free(adev);
 	amdgpu_bo_unref(&adev->gmc.pdb0_bo);
 	amdgpu_bo_fini(adev);
-	amdgpu_gart_fini(adev);
 
 	return 0;
 }

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

@@ -301,7 +301,6 @@ static int iceland_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/navi10_ih.c

@@ -570,10 +570,6 @@ static int navi10_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 
 	return 0;
 }

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

@@ -176,7 +176,6 @@ static int si_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 
 	return 0;
 }

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

@@ -313,7 +313,6 @@ static int tonga_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 	amdgpu_irq_remove_domain(adev);
 
 	return 0;

drivers/gpu/drm/amd/amdgpu/vega10_ih.c

@@ -514,10 +514,6 @@ static int vega10_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 
 	return 0;
 }

drivers/gpu/drm/amd/amdgpu/vega20_ih.c

@@ -566,10 +566,6 @@ static int vega20_ih_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	amdgpu_irq_fini_sw(adev);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih_soft);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih2);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih1);
-	amdgpu_ih_ring_fini(adev, &adev->irq.ih);
 
 	return 0;
 }