Messages in this thread | | | From | Rusty Russell <> | Subject | Re: [PATCH] percpu_counter: use local_t and atomic_long_t if possible | Date | Thu, 25 Dec 2008 23:56:58 +1030 |
| |
On Tuesday 23 December 2008 22:13:21 Peter Zijlstra wrote: > One think that sprung to mind,.. > > IFF we're going to implement percpu_counter with local_t and make > local_t this funny tri-counter thing which has its own error, you need > to fix up bdi_stat_error() - it expects to be an upper bound for the > counter error, getting that wrong _will_ cause deadlocks.
It's OK: local_add_return() can't have error; that's why the trival implementation disables interrupts around it.
Hope that helps, Rusty.
| |