On 15/3/23 18:01, Jan-Benedict Glaw wrote:
On Thu, 2023-03-09 12:39:19 +1100, Kalvis Duckmanton <kalvisd%gmail.com@localhost> wrote:I have no explanation for why this might be a problem only for large memory configurations, though.I'm so keen to see if this works. But without understanding what's actually happening, that is probably not ready to be merged upstream?
Agreed. The current hypothesis is that there is some task run as the kernel starts which both uses an atomic operation (inc/dec, or mutex) and completes in time proportional to the amount of memory in the system - that might increase the chances of a clock interrupt arriving whilst the code between cas32_ras_start and cas32_ras_end is executing. I haven't had a chance yet to prove this, of course - hoping to do that soon.
cheers kalvis