Rusty Russell wrote:
> On Wed, 2007-07-11 at 18:55 +0300, Avi Kivity wrote:
>
>> +fire_sched_out_preempt_hooks(current);
>> prepare_lock_switch(rq, next);
>> prepare_arch_switch(next);
>>
>
> Damn, I just found a use for this in lguest.
>
> Any chance of handing "next" to the
On Wed, 2007-07-11 at 18:55 +0300, Avi Kivity wrote:
> + fire_sched_out_preempt_hooks(current);
> prepare_lock_switch(rq, next);
> prepare_arch_switch(next);
Damn, I just found a use for this in lguest.
Any chance of handing "next" to the sched_out hook so we can optimize
the lgue
On Wed, 2007-07-11 at 18:55 +0300, Avi Kivity wrote:
> +config PREEMPT_HOOKS
> + bool
> + depends on X86
> + default y
Hmm, I would have thought that having CONFIG_KVM "select PREEMPT_HOOKS"
would be a little clearer.
> +static void fire_sched_in_preempt_hooks(struct task_struct *tsk)
This adds a general mechanism whereby a task can request the scheduler to
notify it whenever it is preempted or scheduled back in. This allows the
task to swap any special-purpose registers like the fpu or Intel's VT
registers.
Signed-off-by: Avi Kivity <[EMAIL PROTECTED]>
---
include/linux/pree
4 matches
Mail list logo