current pointer question/suggestion
Alexander Kjeldaas (astor@guardian.no)
Wed, 15 Jul 1998 10:46:08 +0200
This just occurred to me. Would it be possible to have current point
to a location within the kernel area that was mapped individually for
each task? The idea is that current could be on a constant address and
you wouldn't have to even mask %esp to get hold of it which would be
even faster than the current approach (just loading a constant). As a
"side effect", it might make it feasible to get back to a single page
of kernel stack. Also, other architectures won't be bugged down with
8k task allocations when they really have no use for it.
One complexity would be that we would have to use a current->this
pointer initialized as task->this = &task instead of current when
doing comparisons with other struct task_struct pointers.
astor
--
Alexander Kjeldaas, Guardian Networks AS, Trondheim, Norway
http://www.guardian.no/
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.altern.org/andrebalsa/doc/lkml-faq.html