Re: [patch 09/14] syslets: x86, add move_user_context() method

[Davide Libenzi <davidel@xmailserver.org>]

On Thu, 15 Feb 2007, Davide Libenzi wrote:

> On Thu, 15 Feb 2007, Ingo Molnar wrote:
> 
> >  /*
> > + * Move user-space context from one kernel thread to another.
> > + * This includes registers and FPU state. Callers must make
> > + * sure that neither task is running user context at the moment:
> > + */
> > +void
> > +move_user_context(struct task_struct *new_task, struct task_struct *old_task)
> > +{
> > +	struct pt_regs *old_regs = task_pt_regs(old_task);
> > +	struct pt_regs *new_regs = task_pt_regs(new_task);
> > +	union i387_union *tmp;
> > +
> > +	*new_regs = *old_regs;
> > +	/*
> > +	 * Flip around the FPU state too:
> > +	 */
> > +	tmp = new_task->thread.i387;
> > +	new_task->thread.i387 = old_task->thread.i387;
> > +	old_task->thread.i387 = tmp;
> > +}
> 
> Let's say that old_task ("prev" at the incoming schedule) has TS_USEDFPU 
> set. Its context gets moved to the new_task (the one returning to 
> userspace) *before* the __unlazy_fpu() done in __switch_to(). The 
> __unlazy_fpu() at the following schedule will save the state to the old 
> new_task context, and that fine as far as the going-to-sleep task goes.
> The next fault happening in new_task (return to userspace one) will reload 
> a non up2date context (the one we got from old_task, but never hit by 
> the __unlazy_fpu() flush). Right?

Yeah. Given TS_USEDFPU set, before move_user_context():

CPU  => FPUc
NTSK => FPUn
OTSK => FPUo

After move_user_context():

CPU  => FPUc
NTSK => FPUo
OTSK => FPUn

After the incoming __unlazy_fpu() in __switch_to():

CPU  => FPUc
NTSK => FPUo
OTSK => FPUc

After the first fault in NTSK:

CPU  => FPUo
NTSK => FPUo
OTSK => FPUc

So NTSK loads a non up2date FPUo, instead of the FPUc that was the "dirty" 
context to migrate (since TS_USEDFPU was set).
I think you need an early __unlazy_fpu() in that case.




- Davide