IRC logs for #openrisc Wednesday, 2017-07-12

--- Log opened Wed Jul 12 00:00:10 2017
stekernshorne: I agree, global clocksource might be nice, but if the non-hacky timer sync works, that's good enough IMO02:09
shornestekern: right, now ... I am getting some strange issues with spinlocks (using the qspinlocks suggested by peterz)02:26
shorneboth cpus get hung trying to aquire locks02:26
shorneIm going to switch out to your spinlock implementation02:26
shorneto see if that fixes it.  The qspinlocks is nice because its fast+generic code using only arch specific cmpxchg02:27
shornebut its not nice if its not working02:27
shornestekern: fyi, I didnt have much luck with your spinlocks either it actually looks almost the same.  So that maybe rules out a spinlock issue05:45
shorne[    3.340000] BUG: spinlock wrong owner on CPU#1, swapper/1/005:47
shorneI have a lot of the spinlock bug detection code enabled05:48
stekernhmm, but what else have you changed? or is it just on real hw you see this?05:49
shornestekern: other than the timers not much has been changed.  And yes, this i only on the fpga where I am seeing this09:22
shorneI have been emulating on qemu so far09:23
shorneit seems a bit different every time09:25
shornethis time I am getting09:25
shornea stack like:09:26
shorneipi_icache_page_inv09:26
shornesmp_call_function_single09:26
shorne  ompic_raise_softirq+09:26
shorne  ipi_icache_page_inv09:26
shorne smp_call_function_single+09:27
shorneipi_icache_page_inv09:27
shorne...09:27
shornesome kind of loop of ipi_icache_page_inv09:27
shornein update_cache(),  called by handle_mm_fault()09:28
shorneanyway, it could be the stack trace is wrong09:28
-!- [X-Scale] is now known as X-Scale12:17
--- Log closed Thu Jul 13 00:00:12 2017

Generated by irclog2html.py 2.15.2 by Marius Gedminas - find it at mg.pov.lt!