drm/amdgpu: partial revert VRAM lost handling v2

Keep blocking the CS, but revert everything else. Mapping BOs and info IOCTL
are harmless and can still happen even when VRAM content ist lost.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

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

@@ -1272,16 +1272,12 @@ int amdgpu_cs_wait_ioctl(struct drm_device *dev, void *data,
 {
 	union drm_amdgpu_wait_cs *wait = data;
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	unsigned long timeout = amdgpu_gem_timeout(wait->in.timeout);
 	struct amdgpu_ring *ring = NULL;
 	struct amdgpu_ctx *ctx;
 	struct dma_fence *fence;
 	long r;
 
-	if (amdgpu_kms_vram_lost(adev, fpriv))
-		return -ENODEV;
-
 	ctx = amdgpu_ctx_get(filp->driver_priv, wait->in.ctx_id);
 	if (ctx == NULL)
 		return -EINVAL;
@@ -1350,16 +1346,12 @@ int amdgpu_cs_fence_to_handle_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *filp)
 {
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	union drm_amdgpu_fence_to_handle *info = data;
 	struct dma_fence *fence;
 	struct drm_syncobj *syncobj;
 	struct sync_file *sync_file;
 	int fd, r;
 
-	if (amdgpu_kms_vram_lost(adev, fpriv))
-		return -ENODEV;
-
 	fence = amdgpu_cs_get_fence(adev, filp, &info->in.fence);
 	if (IS_ERR(fence))
 		return PTR_ERR(fence);
@@ -1521,15 +1513,12 @@ int amdgpu_cs_wait_fences_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	union drm_amdgpu_wait_fences *wait = data;
 	uint32_t fence_count = wait->in.fence_count;
 	struct drm_amdgpu_fence *fences_user;
 	struct drm_amdgpu_fence *fences;
 	int r;
 
-	if (amdgpu_kms_vram_lost(adev, fpriv))
-		return -ENODEV;
 	/* Get the fences from userspace */
 	fences = kmalloc_array(fence_count, sizeof(struct drm_amdgpu_fence),
 			GFP_KERNEL);

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

@@ -579,11 +579,6 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			args->operation);
 		return -EINVAL;
 	}
-	if ((args->operation == AMDGPU_VA_OP_MAP) ||
-	    (args->operation == AMDGPU_VA_OP_REPLACE)) {
-		if (amdgpu_kms_vram_lost(adev, fpriv))
-			return -ENODEV;
-	}
 
 	INIT_LIST_HEAD(&list);
 	INIT_LIST_HEAD(&duplicates);

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

@@ -270,7 +270,6 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
 static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct drm_amdgpu_info *info = data;
 	struct amdgpu_mode_info *minfo = &adev->mode_info;
 	void __user *out = (void __user *)(uintptr_t)info->return_pointer;
@@ -283,8 +282,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 	if (!info->return_size || !info->return_pointer)
 		return -EINVAL;
-	if (amdgpu_kms_vram_lost(adev, fpriv))
-		return -ENODEV;
 
 	switch (info->query) {
 	case AMDGPU_INFO_ACCEL_WORKING:
@@ -792,10 +789,19 @@ void amdgpu_driver_lastclose_kms(struct drm_device *dev)
 	vga_switcheroo_process_delayed_switch();
 }
 
+/**
+ * amdgpu_kms_vram_lost - check if VRAM was lost for this client
+ *
+ * @adev: amdgpu device
+ * @fpriv: client private
+ *
+ * Check if all CS is blocked for the client because of lost VRAM
+ */
 bool amdgpu_kms_vram_lost(struct amdgpu_device *adev,
 			  struct amdgpu_fpriv *fpriv)
 {
-	return fpriv->vram_lost_counter != atomic_read(&adev->vram_lost_counter);
+	return fpriv->vram_lost_counter !=
+		atomic_read(&adev->vram_lost_counter);
 }
 
 /**