Re: [PATCH] membarrier: Document scheduler barrier requirements

[Andrea Parri]

On Mon, Sep 18, 2017 at 02:01:22PM -0400, Mathieu Desnoyers wrote:
> Document the membarrier requirement on having a full memory barrier in
> __schedule() after coming from user-space, before storing to rq->curr.
> It is provided by smp_mb__before_spinlock() in __schedule().
> 
> Document that membarrier requires a full barrier on transition from
> kernel thread to userspace thread. We currently have an implicit barrier
> from atomic_dec_and_test() in mmdrop() that ensures this.
> 
> The x86 switch_mm_irqs_off() full barrier is currently provided by many
> cpumask update operations as well as write_cr3(). Document that
> write_cr3() provides this barrier.
> 
> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
> CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> CC: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> CC: Boqun Feng <boqun.feng@xxxxxxxxx>
> CC: Andrew Hunter <ahh@xxxxxxxxxx>
> CC: Maged Michael <maged.michael@xxxxxxxxx>
> CC: gromer@xxxxxxxxxx
> CC: Avi Kivity <avi@xxxxxxxxxxxx>
> CC: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
> CC: Paul Mackerras <paulus@xxxxxxxxx>
> CC: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
> CC: Dave Watson <davejwatson@xxxxxx>
> ---
>  arch/x86/mm/tlb.c        | 5 +++++
>  include/linux/sched/mm.h | 4 ++++
>  kernel/sched/core.c      | 9 +++++++++
>  3 files changed, 18 insertions(+)
> 
> diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
> index 1ab3821f9e26..fa3bbe048af0 100644
> --- a/arch/x86/mm/tlb.c
> +++ b/arch/x86/mm/tlb.c
> @@ -144,6 +144,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
>  	}
>  #endif
>  
> +	/*
> +	 * The membarrier system call requires a full memory barrier
> +	 * after coming from user-space, before storing to rq->curr.

I'm confused: isn't this case covered by the

   rq_lock(rq, &rf);
   smp_mb__after_spinlock();

below (all archs)? You meant "before returning to user-space, after
storing to rq->curr"?


> +	 * Writing to CR3 provides that full memory barrier.
> +	 */
>  	if (real_prev == next) {
>  		VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
>  			  next->context.ctx_id);
> diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
> index df4005e2c4cf..f3bc261fe7c7 100644
> --- a/include/linux/sched/mm.h
> +++ b/include/linux/sched/mm.h
> @@ -38,6 +38,10 @@ static inline void mmgrab(struct mm_struct *mm)
>  extern void __mmdrop(struct mm_struct *);
>  static inline void mmdrop(struct mm_struct *mm)
>  {
> +	/*
> +	 * The implicit full barrier implied by atomic_dec_and_test is
> +	 * required by the membarrier system call.

"before returning to user-space, after storing to rq->curr", right?

(your commit says "on transition from kernel thread _to_ userspace"
 regarding mmdrop()).

  Andrea


> +	 */
>  	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
>  		__mmdrop(mm);
>  }
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index c5c1b2c51807..48d524b18868 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2648,6 +2648,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
>  	finish_arch_post_lock_switch();
>  
>  	fire_sched_in_preempt_notifiers(current);
> +	/*
> +	 * When transitioning from a kernel thread to a userspace
> +	 * thread, mmdrop()'s implicit full barrier is required by the
> +	 * membarrier system call, because the current active_mm can
> +	 * become the current mm without going through switch_mm().
> +	 */
>  	if (mm)
>  		mmdrop(mm);
>  	if (unlikely(prev_state == TASK_DEAD)) {
> @@ -3289,6 +3295,9 @@ static void __sched notrace __schedule(bool preempt)
>  	 * Make sure that signal_pending_state()->signal_pending() below
>  	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
>  	 * done by the caller to avoid the race with signal_wake_up().
> +	 *
> +	 * The membarrier system call requires a full memory barrier
> +	 * after coming from user-space, before storing to rq->curr.
>  	 */
>  	rq_lock(rq, &rf);
>  	smp_mb__after_spinlock();
> -- 
> 2.11.0
>