If scrubbing memory after user released device has failed it means
the device is in a bad state and should be reset.
Signed-off-by: Oded Gabbay <ogabbay@xxxxxxxxxx>
---
drivers/accel/habanalabs/common/device.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 5e61761b8c11..d7d9198b2103 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -454,8 +454,10 @@ static void hpriv_release(struct kref *ref)
/* Scrubbing is handled within hl_device_reset(), so here need to do it directly */
int rc = hdev->asic_funcs->scrub_device_mem(hdev);
- if (rc)
+ if (rc) {
dev_err(hdev->dev, "failed to scrub memory from hpriv release (%d)\n", rc);
+ hl_device_reset(hdev, HL_DRV_RESET_HARD);
+ }
}
/* Now we can mark the compute_ctx as not active. Even if a reset is running in a different
--
2.40.1
