Messages in this thread | | | Date | Thu, 10 Apr 2008 17:04:19 +0900 | From | KOSAKI Motohiro <> | Subject | Re: [patch 11/17] Implement immediate update via stop_machine_run |
| |
Hi
> -Updating immediate values, cannot rely on smp_call_function() b/c synchronizing > cpus using IPIs leads to deadlocks. Process A held a read lock on > tasklist_lock, then process B called apply_imv_update(). Process A received the > IPI and begins executing ipi_busy_loop(). Then process C takes a write lock > irq on the task list lock, before receiving the IPI. Thus, process A holds up > process C, and C can't get an IPI b/c interrupts are disabled. Solve this > problem by using a new 'ALL_CPUS' parameter to stop_machine_run(). Which > runs a function on all cpus after they are busy looping and have disabled > irqs. Since this is done in a new process context, we don't have to worry > about interrupted spin_locks. Also, less lines of code. Has survived 24 hours+ > of testing...
it seems this patch is must, Why do you separate patch [10/17] and [11/17]? this patch remove almost portion of [10/17]. IMHO these patch merge into 1 patch is better.
> +static int stop_machine_imv_update(void *imv_ptr) > +{ > + struct __imv *imv = imv_ptr; > + > + if (!wrote_text) {
it seems racy. Why don't need test_and_set?
I think your stop_machine_run(ALL_CPUS) call fn concurrency...
> + text_poke((void *)imv->imv, (void *)imv->var, imv->size); > + wrote_text = 1; > + smp_wmb(); /* make sure other cpus see that this has run */ > + } else > + sync_core(); > + > + flush_icache_range(imv->imv, imv->imv + imv->size); > + > + return 0; > +} > +
| |