On Fri, Jun 08, 2001 at 03:23:57PM +0100, David Rusling wrote:
> thanks. So, the insertion of the signal handler code into the
> user's execution space is fairly clean/efficient but after each signal
> has been handled, the process transitions back through the
> kernel to get the stack unwound?
Yes.
> Assuming that transitions into and out of the kernel are expensive,
> that's what I'm trying to track.
If that is a concern to you, you can use signal stack switch to
reduce the expense.
The reason its done this way is that user space has no knowledge of
what the kernel has placed on its stack - the only thing that knows
precisely what is there is the kernel itself.
PS, please don't reply to a message on the list to start a new thread.
Those of us with threaded mail clients see it as a continuation of the
original thread, and therefore keys like ^d which wipe out complete
threads have a unfortunate effect.
_____
|_____| ------------------------------------------------- ---+---+-
| | Russell King [EMAIL PROTECTED] --- ---
| | | | http://www.arm.linux.org.uk/ / / |
| +-+-+ --- -+-
/ | THE developer of ARM Linux |+| /|\
/ | | | --- |
+-+-+ ------------------------------------------------- /\\\ |
_______________________________________________
http://lists.arm.linux.org.uk/mailman/listinfo/linux-arm
Please visit the above address for information on this list.
