Richard Henderson wrote:
>
> On Fri, Feb 04, 2000 at 08:42:15PM +0100, Manfred Spraul wrote:
> > It seems that the Alpha port still calls schedule() during tlb flush
> > operations. Could you please remove the pointer_lock() from
> > smp_call_function()? Just replace it with a simple spin_lock() or
> > spin_lock_bh().
>
> Actually, just replace the schedule with a barrier. Using a
> spinlock would require extra storage, which would be wasteful.
>
So you saved 4 bytes. What about saving 20+ lines and killing
pointer_lock?
SMP development is difficult enough, and I prefer if everyone uses a few
primitives (semphore, spinlock, rw_sem, rw_lock) instead of special
functions.
And if you use spin_lock_bh(), then we would allow smp_call_function()
from bottom half handlers - might be important for hardware drivers.
i386 allows that.
-- Manfred- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Mon Feb 07 2000 - 21:00:11 EST