linux-dev/drivers/misc/habanalabs/common, branch linus/master

habanalabs: use separate structure info for each error collect data

2022-05-22T19:01:21Z

Create separate info structure for each error type. The structures shall be used inside the large structure that contains the last session error. This is more scalable for adding more errors in the future. Signed-off-by: Tal Cohen Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: fix missing handle shift during mmap

2022-05-22T19:01:21Z

During mmap operation on the unified memory manager buffer, the vma page offset is shifted to extract the handle value. Due to a typo, it was not shifted back at the end. That could cause the offset to be modified after mmap operation, that may affect subsequent operations. In addition, in allocation flow, in case of out of memory error, idr would not be correctly destroyed, again because of a missing shift. Signed-off-by: Yuri Nudelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: remove hdev from hl_ctx_get args

2022-05-22T19:01:21Z

This argument is unused by the function. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: do MMU prefetch as deferred work

2022-05-22T19:01:21Z

When user requests to prefetch the MMU translations, the driver will not block the user until prefetch is done. Instead, the prefetch work will be delegated to a WQ which will do it in the background. This way, the prefetch may progress without blocking the user at all. Signed-off-by: Ohad Sharabi Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: order memory manager messages

2022-05-22T19:01:21Z

Changing format of memory manager messages to make it more readable. In addition, reducing the priority of a warning on missing handle during put. This scenario is not an indication of a problem and may happen in a legal flow, when handle is put from multiple flows. For example, in timeout and completion. Signed-off-by: Yuri Nudelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: return -EFAULT on copy_to_user error

2022-05-22T19:01:20Z

If copy_to_user failed in info ioctl, we always return -EFAULT so the user will know there was an error. Reported-by: kernel test robot Reported-by: Dan Carpenter Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: use NULL for eventfd

2022-05-22T19:01:20Z

eventfd is pointer. As such, it should be initialized to NULL, not to 0. In addition, no need to initialize it after creation because the entire structure is zeroed-out. Also, no need to initialize it before release because the entire structure is freed. Reported-by: kernel test robot Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: add support for notification via eventfd

2022-05-22T19:01:20Z

The driver will be able to send notification events towards a user process, using user's registered event file descriptor. The driver uses the notification mechanism to inform the user about an occurred event. A user thread can wait until a notification is received from the driver. The driver stores the occurred event until the user reads it, using HL_INFO_GET_EVENTS - new ioctl opcode in the INFO ioctl. Gaudi specific implementation includes sending a notification on a TPC assertion event that is received from f/w. Signed-off-by: Tal Cohen Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: add topic to memory manager buffer

2022-05-22T19:01:20Z

Currently, buffers from multiple flows pass through the same infra. This way, in logs, we are unable to distinguish between buffers that came from separate flows. To address this problem, add a "topic" to buffer behavior descriptor - a string identifier that will be used to identify in logs the flow this buffer relates to. Signed-off-by: Yuri Nudelman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman

habanalabs: handle race in driver fini

2022-05-22T19:01:20Z

Scenario: 1. During hard reset, driver executes device_kill_open_processes. 2. Drivers file descriptor is not closed yet (user process is alive), hence we are starting loop on all open file descriptors. 3. Just before getting task struct of user process, according to pid, SIGKILL is sent to the user process, hence get_pid_task fails, driver prints a warning and device_kill_open_processes returns an error. 4. Returned error causing driver fini do disable the device object of the process which causes a kernel crash. The fix is to handle this case not as an error and continue fini flow as normal, since the killed process (by the SIGKILL) will release its resources just like it will do when the driver sends him the sigkill. Signed-off-by: Dani Liberman Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay Signed-off-by: Greg Kroah-Hartman