habanalabs: do MMU prefetch as deferred work

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 <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
Ohad Sharabi 2022-04-11 09:31:32 +03:00 • committed by Greg Kroah-Hartman
commit 9e495e2400
6 changed files with 103 additions and 36 deletions