drm/amdgpu: skip fence GFX interrupts disable/enable for S0ix

GFX v11.0.1 reported fence fallback timer expired issue on
SDMA and GFX rings after S0ix resume. This is generated by
EOP interrupts are disabled when S0ix suspend but fails to
re-enable when resume because of the GFX is in GFXOFF.

[  203.349571] [drm] Fence fallback timer expired on ring sdma0
[  203.349572] [drm] Fence fallback timer expired on ring gfx_0.0.0
[  203.861635] [drm] Fence fallback timer expired on ring gfx_0.0.0

For S0ix, GFX is in GFXOFF state, avoid to touch the GFX registers
to configure the fence driver interrupts for rings that belong to GFX.
The interrupts configuration will be restored by GFXOFF exit.

Signed-off-by: Tim Huang <[email protected]>
Reviewed-by: Mario Limonciello <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

Author: Tim Huang

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

@@ -551,6 +551,41 @@ int amdgpu_fence_driver_sw_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_fence_need_ring_interrupt_restore - helper function to check whether
+ * fence driver interrupts need to be restored.
+ *
+ * @ring: ring that to be checked
+ *
+ * Interrupts for rings that belong to GFX IP don't need to be restored
+ * when the target power state is s0ix.
+ *
+ * Return true if need to restore interrupts, false otherwise.
+ */
+static bool amdgpu_fence_need_ring_interrupt_restore(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	bool is_gfx_power_domain = false;
+
+	switch (ring->funcs->type) {
+	case AMDGPU_RING_TYPE_SDMA:
+	/* SDMA 5.x+ is part of GFX power domain so it's covered by GFXOFF */
+		if (adev->ip_versions[SDMA0_HWIP][0] >= IP_VERSION(5, 0, 0))
+			is_gfx_power_domain = true;
+		break;
+	case AMDGPU_RING_TYPE_GFX:
+	case AMDGPU_RING_TYPE_COMPUTE:
+	case AMDGPU_RING_TYPE_KIQ:
+	case AMDGPU_RING_TYPE_MES:
+		is_gfx_power_domain = true;
+		break;
+	default:
+		break;
+	}
+
+	return !(adev->in_s0ix && is_gfx_power_domain);
+}
+
 /**
  * amdgpu_fence_driver_hw_fini - tear down the fence driver
  * for all possible rings.
@@ -579,7 +614,8 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
 			amdgpu_fence_driver_force_completion(ring);
 
 		if (!drm_dev_is_unplugged(adev_to_drm(adev)) &&
-		    ring->fence_drv.irq_src)
+		    ring->fence_drv.irq_src &&
+		    amdgpu_fence_need_ring_interrupt_restore(ring))
 			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 				       ring->fence_drv.irq_type);
 
@@ -655,7 +691,8 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 			continue;
 
 		/* enable the interrupt */
-		if (ring->fence_drv.irq_src)
+		if (ring->fence_drv.irq_src &&
+		    amdgpu_fence_need_ring_interrupt_restore(ring))
 			amdgpu_irq_get(adev, ring->fence_drv.irq_src,
 				       ring->fence_drv.irq_type);
 	}