habanalabs: kill user process after CS rollback

This patch calls the kill user process function after we rollback the
in-flight CSs. This is because the user process can't be closed while
there are open CSs. Therefore, there is no point of sending it a SIGKILL
before we do the rollback CS part.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 7a8f9d0b71b54a81b4cce20fcbad3734c0369db9..257438d7a63200ea5373b81b33b8d8aeda4244e8 100644 (file)
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -630,8 +630,6 @@ static void device_hard_reset_pending(struct work_struct *work)
                container_of(work, struct hl_device_reset_work, reset_work);
        struct hl_device *hdev = device_reset_work->hdev;
 
-       device_kill_open_processes(hdev);
-
        hl_device_reset(hdev, true, true);
 
        kfree(device_reset_work);
@@ -736,6 +734,13 @@ again:
        /* Go over all the queues, release all CS and their jobs */
        hl_cs_rollback_all(hdev);
 
+       /* Kill processes here after CS rollback. This is because the process
+        * can't really exit until all its CSs are done, which is what we
+        * do in cs rollback
+        */
+       if (from_hard_reset_thread)
+               device_kill_open_processes(hdev);
+
        /* Release kernel context */
        if ((hard_reset) && (hl_ctx_put(hdev->kernel_ctx) == 1))
                hdev->kernel_ctx = NULL;
@@ -1129,8 +1134,6 @@ void hl_device_fini(struct hl_device *hdev)
 
        hdev->hard_reset_pending = true;
 
-       device_kill_open_processes(hdev);
-
        hl_hwmon_fini(hdev);
 
        device_late_fini(hdev);
@@ -1149,6 +1152,12 @@ void hl_device_fini(struct hl_device *hdev)
        /* Go over all the queues, release all CS and their jobs */
        hl_cs_rollback_all(hdev);
 
+       /* Kill processes here after CS rollback. This is because the process
+        * can't really exit until all its CSs are done, which is what we
+        * do in cs rollback
+        */
+       device_kill_open_processes(hdev);
+
        hl_cb_pool_fini(hdev);
 
        /* Release kernel context */