Re: lockup on Athlon systems, kernel race condition?

[Terence Ripperda]

On Wed, Sep 04, 2002 at 05:05:58PM +0200, [e-mail] wrote:
> What was cpu1 doing? There are 3 loops in smp_call_function:
> spin_lock(&call_lock), and 2 while loops with barrier() [first one for 
> IPI arrival, second one for synchroneous ipi's. TLB flush is sync].

it was spinning on the first barrier loop, waiting for verification of the IPI arrival:

        /* Wait for response */
        while (atomic_read(&data.started) != cpus)
                barrier();

Terence