habanalabs: release kernel context after hw_fini

Some engines use resources that belong to the kernel context (e.g. MMU
mappings). In case the halt-engines doesn't work properly due to H/W
restriction, we need to make sure the kernel context lives on until after
the hw_fini. The hw_fini resets the ASIC after that no engine is alive and
we can safely close the kernel context.

Reviewed-by: Tomer Tayar <ttayar@habana.ai>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index 196e35d71118867b17ff7b4f29c0b6e4309bc7b2..20572224099a00342e85cb8ecee94566bc199162 100644 (file)
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -967,14 +967,13 @@ again:
                flush_workqueue(hdev->eq_wq);
        }
 
-       /* Release kernel context */
-       if ((hard_reset) && (hl_ctx_put(hdev->kernel_ctx) == 1))
-               hdev->kernel_ctx = NULL;
-
        /* Reset the H/W. It will be in idle state after this returns */
        hdev->asic_funcs->hw_fini(hdev, hard_reset);
 
        if (hard_reset) {
+               /* Release kernel context */
+               if (hl_ctx_put(hdev->kernel_ctx) == 1)
+                       hdev->kernel_ctx = NULL;
                hl_vm_fini(hdev);
                hl_mmu_fini(hdev);
                hl_eq_reset(hdev, &hdev->event_queue);
@@ -1465,13 +1464,13 @@ void hl_device_fini(struct hl_device *hdev)
 
        hl_cb_pool_fini(hdev);
 
+       /* Reset the H/W. It will be in idle state after this returns */
+       hdev->asic_funcs->hw_fini(hdev, true);
+
        /* Release kernel context */
        if ((hdev->kernel_ctx) && (hl_ctx_put(hdev->kernel_ctx) != 1))
                dev_err(hdev->dev, "kernel ctx is still alive\n");
 
-       /* Reset the H/W. It will be in idle state after this returns */
-       hdev->asic_funcs->hw_fini(hdev, true);
-
        hl_vm_fini(hdev);
 
        hl_mmu_fini(hdev);