drm/amdgpu: Add early fini callback

Use it to call disply code dependent on device->drv_data
before it's set to NULL on device unplug

v5:
Move HW finilization into this callback to prevent MMIO accesses
post cpi remove.

v7:
Split kfd suspend from device exit to expdite HW related
stuff to amdgpu_pci_remove

v8:
Squash previous KFD commit into this commit to avoid compile break.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210520032057.497334-1-andrey.grodzovsky@amd.com

1 files changed, 40 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8bee95ad32d9..bc75e35dd8d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2558,34 +2558,26 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-/**
- * amdgpu_device_ip_fini - run fini for hardware IPs
- *
- * @adev: amdgpu_device pointer
- *
- * Main teardown pass for hardware IPs.  The list of all the hardware
- * IPs that make up the asic is walked and the hw_fini and sw_fini callbacks
- * are run.  hw_fini tears down the hardware associated with each IP
- * and sw_fini tears down any software state associated with each IP.
- * Returns 0 on success, negative error code on failure.
- */
-static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
+static int amdgpu_device_ip_fini_early(struct amdgpu_device *adev)
 {
 	int i, r;
 
-	if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
-		amdgpu_virt_release_ras_err_handler_data(adev);
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].version->funcs->early_fini)
+			continue;
 
-	amdgpu_ras_pre_fini(adev);
+		r = adev->ip_blocks[i].version->funcs->early_fini((void *)adev);
+		if (r) {
+			DRM_DEBUG("early_fini of IP block <%s> failed %d\n",
+				  adev->ip_blocks[i].version->funcs->name, r);
+		}
+	}
 
-	if (adev->gmc.xgmi.num_physical_nodes > 1)
-		amdgpu_xgmi_remove_device(adev);
+	amdgpu_amdkfd_suspend(adev, false);
 
 	amdgpu_device_set_pg_state(adev, AMD_PG_STATE_UNGATE);
 	amdgpu_device_set_cg_state(adev, AMD_CG_STATE_UNGATE);
 
-	amdgpu_amdkfd_device_fini(adev);
-
 	/* need to disable SMC first */
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.hw)
@@ -2616,6 +2608,33 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 		adev->ip_blocks[i].status.hw = false;
 	}
 
+	return 0;
+}
+
+/**
+ * amdgpu_device_ip_fini - run fini for hardware IPs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main teardown pass for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked and the hw_fini and sw_fini callbacks
+ * are run.  hw_fini tears down the hardware associated with each IP
+ * and sw_fini tears down any software state associated with each IP.
+ * Returns 0 on success, negative error code on failure.
+ */
+static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	if (amdgpu_sriov_vf(adev) && adev->virt.ras_init_done)
+		amdgpu_virt_release_ras_err_handler_data(adev);
+
+	amdgpu_ras_pre_fini(adev);
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1)
+		amdgpu_xgmi_remove_device(adev);
+
+	amdgpu_amdkfd_device_fini_sw(adev);
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.sw)
@@ -3681,6 +3700,8 @@ void amdgpu_device_fini_hw(struct amdgpu_device *adev)
 	amdgpu_fbdev_fini(adev);
 
 	amdgpu_irq_fini_hw(adev);
+
+	amdgpu_device_ip_fini_early(adev);
 }
 
 void amdgpu_device_fini_sw(struct amdgpu_device *adev)