Re: Linux 2.6.25-rc2

[Ingo Molnar]

* Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:

> > > incrementing the variable with a "++" when interrupts are not 
> > > disabled. It's not an atomic add and it's racy. The code within 
> > > stat() does exactly this.
> > 
> > Yes but that is only for used for statistics which can be racy. Note 
> > that the VM event statistics also can be racy.
> 
> Doing ++ on a u32 _is_ atomic wrt interrupts on x86 and probably lots 
> of other architectures, so we're OK using unsigned there. [...]

hm, why should it be atomic wrt. irqs? There's nothing that keeps gcc 
from not doing an "incl memory_address" but do something like: "load 
memory address into regx, incl regx, ... store address into memory 
address" - and that's not atomic at that point.

	Ingo
--
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/