Messages in this thread | | | Subject | Re: [PATCH 1/3] perf_event: fix race in perf_swevent_get_recursion_context() | From | Peter Zijlstra <> | Date | Tue, 19 Jan 2010 09:41:03 +0100 |
| |
On Tue, 2010-01-19 at 15:36 +0800, Xiao Guangrong wrote: > Hi Peter, > > Peter Zijlstra wrote: > > On Mon, 2010-01-18 at 21:42 +0800, Xiao Guangrong wrote: > >> It only disable preemption in perf_swevent_get_recursion_context() > >> it can't avoid race of hard-irq and NMI > >> > >> In this patch, we use atomic operation to avoid it and reduce > >> cpu_ctx->recursion size, it also make this patch no need diable > >> preemption > > > > Uhm why? > > > > This patch looks terminally broken > > Please see my explanation in another mail: > http://lkml.org/lkml/2010/1/18/501
Still its not going to happen, we need those 4 recursion contexts. Otherwise we could not receive a software event from an IRQ while we are processing a software event from process context, etc.
| |