From 55f6d680970ea922d4ee23d5ac88d3a8046221fb Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 17 Nov 2019 17:41:57 +0200 Subject: [PATCH] habanalabs: flush EQ workers in hard reset 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 Reviewed-by: Tomer Tayar --- 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;