On Fri, 30 Nov 2001, Alan Cox wrote:
> > So You like the idea of stocking structure pointers inside CPU registers
> > or I missed Your point ?
> > The proposed implementation is "uniform" between architectures, that's my
> > point.
>
> An uniform implementation for a totally non uniform set of processors. Not
> actually useful. The x86 is one of the few cpus so short of registers that
> current in a global register is not a win performancewise.
The point is why store kernel pointers in global registers when You can
achieve the same functionality, with a smaller patch, that does not need
to be recoded for each CPU, without using global registers.
> The cache behaviour also heavily depends on the processor. In paticular the
> problem with having to align stacks to do current tricks is absent on non
> x86 processors so they can use properly coloured stacks.
>
> current is far too critical to generalise
This is the diff for current :
static inline struct task_struct * get_current(void)
{
- struct task_struct *current;
- __asm__("andl %%esp,%0; ":"=r" (current) : "0" (~8191UL));
- return current;
+ unsigned long *tskptr;
+ __asm__("andl %%esp,%0; ":"=r" (tskptr) : "0" (~8191UL));
+ return (struct task_struct *) *tskptr;
}
- Davide
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Fri Nov 30 2001 - 21:00:41 EST