On 02/23/2018 03:35 AM, Mark Rutland wrote:
On Thu, Feb 22, 2018 at 12:38:39PM -0800, Saravana Kannan wrote:
On 02/22/2018 03:33 AM, Mark Rutland wrote:
On Wed, Feb 21, 2018 at 06:32:46PM -0800, Saravana Kannan wrote:
I'm not exactly sure if we can add entries to perf_type_id. If that's
allowed maybe we need to add something line PERF_TYPE_DSU and use that?

Or if that's not allowed then would it be better to offset the DSU PMU
events by some number (say 0x1000) and then delete the event type check or
pass PERF_TYPE_RAW to perf_pmu_register()?

As above, neither of these should be necessary.

For the userspace interface. How about the kernel interface though?
perf_event_create_kernel_counter() takes attr.type as an input. But there's
no way to look up the DSU PMU's "type".

There is no lookup mechanism currently.

I take it you want to use DSU events from a kernel module?


It would be possible to have a simlar name -> type lookup mechanism
kernel-side, if necessary.

Yeah, this is what I was thinking once you explained how user space handles this. Just wanted to hear it from this thread. I can submit a patch.


Qualcomm Innovation Center, Inc.
The Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum,
a Linux Foundation Collaborative Project

Reply via email to