[PATCH 1/2] habanalabs: make the reset code more consistent

[PATCH 1/2] habanalabs: make the reset code more consistent

[Oded Gabbay]

In the hl_device_reset we ask about the hard_reset argument when we want to
differentiate between soft and hard reset, except for three places where
we use "from_hard_reset_thread". Replace one of those locations with the
hard_reset argument as it is guaranteed that if we reached to that
line in the code during hard_reset, it is from a kernel thread.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
---
 drivers/misc/habanalabs/device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 2f5a4da707e7..80205d8584ce 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -891,7 +891,7 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 	 * can't really exit until all its CSs are done, which is what we
 	 * do in cs rollback
 	 */
-	if (from_hard_reset_thread)
+	if (hard_reset)
 		device_kill_open_processes(hdev);
 
 	/* Release kernel context */
-- 
2.17.1

[PATCH 2/2] habanalabs: flush EQ workers in hard reset

[Oded Gabbay]

During hard-reset, there can be multiple events received from the H/W. For
each event, the driver opens a worker thread to handle it. For some of the
events, the driver will read/write registers in the code that handles the
event.

In case of hard-reset, we must prevent reads/writes to the registers during
the reset operation because the device might get stuck if that happens.

Therefore, flush the EQ workers before resetting the device (in hard-reset
only). Additional events won't arrive as we synced and disabled the
interrupts.

Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: Tomer Tayar <ttayar@habana.ai>
---
 drivers/misc/habanalabs/device.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index 80205d8584ce..b155e9549076 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -887,13 +887,19 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 	/* 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 (hard_reset)
+	if (hard_reset) {
+		/* 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);
 
+		/* Flush the Event queue workers to make sure no other thread is
+		 * reading or writing to registers during the reset
+		 */
+		flush_workqueue(hdev->eq_wq);
+	}
+
 	/* Release kernel context */
 	if ((hard_reset) && (hl_ctx_put(hdev->kernel_ctx) == 1))
 		hdev->kernel_ctx = NULL;
-- 
2.17.1