[PATCH 3/4] ARM: mm: kill unused TLB_CAN_READ_FROM_L1_CACHE and use ALT_SMP instead

[Will Deacon]

On Wed, May 15, 2013 at 04:36:43PM +0100, Gregory CLEMENT wrote:
> On 05/15/2013 05:04 PM, Will Deacon wrote:
> > On Wed, May 15, 2013 at 03:46:20PM +0100, Gregory CLEMENT wrote:
> >> On 05/15/2013 04:06 PM, Will Deacon wrote:
> >>> You could also try deleting both of the ALT_* lines and just putting a
> >>> W(nop) in there directly.
> >>
> >> If I just delete the both of the ALT_* lines it no more hangs.
> >> If I put a  W(nop) instead it hangs.
> 
> It also hang with a simple nop by the way

Ok. Have you tried adding a different instruction (mov r0, r0, for example)?

> > 
> > Wow. This doesn't sound good for your CPU and you might want to check with
> > the Marvell guys...
> > 
> > Extra things you could try:
> > 
> > 	- Try adding a 16-bit nop instead (remove the W, build thumb-2 and
> > 	  double check in your diasassembly)
> > 
> > 	- Try adding the W(nop) to other places in the kernel and see if you
> > 	  can tickle the lock-up elsewhere.
> 
> I managed to add  W(nop) elsewhere in the kernel without getting any lock-up.
> 
> Is the fact that this nop is the first instruction of the macro could have an
> influence ?

I can't think why -- the macro is just expanded inline during assembly.

> 
> > 
> > 	- Can you reproduce on the Armada XP? (since I have access to one of
> > 	  those)
> 
> No on Armada XP I don't have this kind of problem even on UP.

Is that compiling with CONFIG_SMP=n?

Will