Messages in this thread |  | | | Date | Mon, 24 Oct 2011 09:48:17 +0200 | | From | Martin Schwidefsky <> | | Subject | Re: Linux 3.1-rc9 |
| |
On Sun, 23 Oct 2011 13:34:22 +0200 Ingo Molnar <mingo@elte.hu> wrote:
> > * Martin Schwidefsky <schwidefsky@de.ibm.com> wrote: > > > +#define cputime_zero ((__force cputime_t) 0ULL) > > +#define cputime64_zero ((__force cputime64_t) 0ULL) > > Hm, why are these still needed? > > This: > > if (*newval == cputime_zero) > return; > > Could be written as the much simpler: > > if (!*newval) > return; > > with no ill effect that i can see.
These types are still there because cputime_t can be u32 or u64. E.g. this
timer->expires.cpu = 0;
will give the following sparse warning
kernel/posix-cpu-timers.c:463:46: warning: implicit cast to nocast type
if you architecture happens to have a u64 as cputime_t. We could get rid of cputime64_t as it always should be a u64. To keep things symmetrical I choose to keep both defines.
-- blue skies, Martin.
"Reality continues to ruin my life." - Calvin.
|  |