From 36fafe87edd636292a4ed6a3af9608f2c7d0d0fb Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Mon, 18 May 2020 22:27:46 +0300 Subject: [PATCH] habanalabs: don't allow hard reset with open processes When the MMU is heavily used by the engines, unmapping might take a lot of time due to a full MMU cache invalidation done as part of the unmap flow. Hence we might not be able to kill all open processes before going to hard reset the device, as it involves unmapping of all user memory. In case of a failure in killing all open processes, we should stop the hard reset flow as it might lead to a kernel crash - one thread (killing of a process) is updating MMU structures that other thread (hard reset) is freeing. Stopping a hard reset flow leaves the device as nonoperational and the user can then initiate a hard reset via sysfs to reinitialize the device. Signed-off-by: Omer Shpigelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 17 +++++++++++------ 1 file changed, 11 insertions(+), 6 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 4a4a446..2b38a1197 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -726,7 +726,7 @@ disable_device: return rc; } -static void device_kill_open_processes(struct hl_device *hdev) +static int device_kill_open_processes(struct hl_device *hdev) { u16 pending_total, pending_cnt; struct hl_fpriv *hpriv; @@ -779,9 +779,7 @@ static void device_kill_open_processes(struct hl_device *hdev) ssleep(1); } - if (!list_empty(&hdev->fpriv_list)) - dev_crit(hdev->dev, - "Going to hard reset with open user contexts\n"); + return list_empty(&hdev->fpriv_list) ? 0 : -EBUSY; } static void device_hard_reset_pending(struct work_struct *work) @@ -908,7 +906,12 @@ again: * process can't really exit until all its CSs are done, which * is what we do in cs rollback */ - device_kill_open_processes(hdev); + rc = device_kill_open_processes(hdev); + if (rc) { + dev_crit(hdev->dev, + "Failed to kill all open processes, stopping hard reset\n"); + goto out_err; + } /* Flush the Event queue workers to make sure no other thread is * reading or writing to registers during the reset @@ -1391,7 +1394,9 @@ void hl_device_fini(struct hl_device *hdev) * can't really exit until all its CSs are done, which is what we * do in cs rollback */ - device_kill_open_processes(hdev); + rc = device_kill_open_processes(hdev); + if (rc) + dev_crit(hdev->dev, "Failed to kill all open processes\n"); hl_cb_pool_fini(hdev); -- 2.7.4