Re: [PATCH] Avoid indefinite wait in smp_call_function_many() ifcpumask is modified

[Catalin Marinas]

On Tuesday, 15 March 2011, Russell King - ARM Linux
<linux@xxxxxxxxxxxxxxxx> wrote:
> On Tue, Mar 15, 2011 at 06:20:56PM +0000, Catalin Marinas wrote:
>> On ARM processors (and not only) with software broadcasting of the TLB
>> maintenance operations, smp_call_function_many() is given a
>> mm_cpumask(mm) as argument. This cpumask may be modified (bits cleared)
>> during the smp_call_function_many() execution as a result of other
>> events like ASID roll-over.
>
> We shouldn't be modifying a mask which has been passed into one of these
> functions. ÂHaving masks change beneath a function which is actively
> using it and can wait is an obvious recipe for problems and races.

It's not that bad since the mask is copied inside the function.
Anyway, it looks like such patch has been around for more than a
month, so I'm not pushing it anymore.

Catalin

-- 
Catalin
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/