Messages in this thread | | | From | Thomas Gleixner <> | Subject | Re: [PATCH v5 2/9] x86/split_lock: Avoid runtime reads of the TEST_CTRL MSR | Date | Mon, 23 Mar 2020 18:06:31 +0100 |
| |
"Luck, Tony" <tony.luck@intel.com> writes:
> On Sun, Mar 15, 2020 at 01:05:10PM +0800, Xiaoyao Li wrote: >> In a context switch from a task that is detecting split locks >> to one that is not (or vice versa) we need to update the TEST_CTRL >> MSR. Currently this is done with the common sequence: >> read the MSR >> flip the bit >> write the MSR >> in order to avoid changing the value of any reserved bits in the MSR. >> >> Cache the value of the TEST_CTRL MSR when we read it during initialization >> so we can avoid an expensive RDMSR instruction during context switch. >> >> Suggested-by: Sean Christopherson <sean.j.christopherson@intel.com> >> Originally-by: Tony Luck <tony.luck@intel.com> >> Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com> > > Is it bad form to Ack/Review patches originally by oneself?
Only if they are broken ....
| |