CTI for power management vs debug
Bernard.Ogden at arm.com
Tue Mar 27 14:59:21 UTC 2012
I work on a debugger that can use the CoreSight CTI (Cross Trigger Interface) to control stop and start of cores when debugging SMP systems, such as Linux-on-Snowball. When using CTI for debug in this case I observe that the target stops continuously (i.e. run results in an immediate stop, at least as perceived from the debugger interface).
We can work around this by not using CTI, but this means greater latency between stop/start of the cores. We believe that the kernel is using CTI to control start/stop of individual cores.
Can anyone comment on whether this belief is correct? If it is, then is it possible for the kernel not to use CTI for power management when configured to permit debug? I'd be happy with a workaround that configures the kernel not to power down cores, but so far I've not found a working configuration for this.
Thanks in advance,
-- IMPORTANT NOTICE: The contents of this email and any attachments are confidential and may also be privileged. If you are not the intended recipient, please notify the sender immediately and do not disclose the contents to any other person, use it for any purpose, or store or copy the information in any medium. Thank you.
More information about the kernel