Re: spin_lock behavior with ARM64 big.Little/HMP

From: Vikram Mulukutla
Date: Fri Nov 18 2016 - 15:22:30 EST



Hi Sudeep,

Thanks for taking a look!

On 2016-11-18 02:30, Sudeep Holla wrote:
Hi Vikram,

On 18/11/16 02:22, Vikram Mulukutla wrote:
Hello,

This isn't really a bug report, but just a description of a frequency/IPC
dependent behavior that I'm curious if we should worry about. The behavior
is exposed by questionable design so I'm leaning towards don't-care.

Consider these threads running in parallel on two ARM64 CPUs running
mainline
Linux:


Are you seeing this behavior with the mainline kernel on any platforms
as we have a sort of workaround for this ?


If I understand that workaround correctly, the ARM timer event stream is used
to periodically wake up CPUs that are waiting in WFE, is that right? I think
my scenario below may be different because LittleCPU doesn't actually wait
on a WFE event in the loop that is trying to increment lock->next, i.e. it's
stuck in the following loop:

ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
" prfm pstl1strm, %3\n"
"1: ldaxr %w0, %3\n"
" add %w1, %w0, %w5\n"
" stxr %w2, %w1, %3\n"
" cbnz %w2, 1b\n",


I have been testing internal platforms; I'll try to test on something
available publicly that's b.L. In any case, the timer event stream was enabled
when I tried this out.

(Ordering of lines between the two columns does not indicate a sequence of
execution. Assume flag=0 initially.)

LittleARM64_CPU @ 300MHz (e.g.A53) | BigARM64_CPU @ 1.5GHz (e.g. A57)
-------------------------------------+----------------------------------
spin_lock_irqsave(s) | local_irq_save()
/* critical section */
flag = 1 | spin_lock(s)
spin_unlock_irqrestore(s) | while (!flag) {
| spin_unlock(s)
| cpu_relax();
| spin_lock(s)
| }
| spin_unlock(s)
| local_irq_restore()


[...]

Thanks,
Vikram