[PATCH] membarrier: Document scheduler barrier requirements

[PATCH] membarrier: Document scheduler barrier requirements

[Mathieu Desnoyers]

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 load_cr3(). However, since
load_cr3() may be done lazily in the future, move the documentation from
load_cr3() to cpumask_set_cpu().

[ Applies on top of "membarrier: expedited private command (v4)". ]

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
---
 arch/x86/mm/tlb.c        | 7 +++++--
 include/linux/sched/mm.h | 4 ++++
 kernel/sched/core.c      | 9 +++++++++
 3 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index bb103d693f33..a79e72691cf1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -105,6 +105,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	this_cpu_write(cpu_tlbstate.loaded_mm, next);
 
 	WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next)));
+	/*
+	 * The full memory barrier implied by mm_cpumask update
+	 * operations is required by the membarrier system call.
+	 */
 	cpumask_set_cpu(cpu, mm_cpumask(next));
 
 	/*
@@ -132,8 +136,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	 * due to instruction fetches or for no reason at all,
 	 * and neither LOCK nor MFENCE orders them.
 	 * Fortunately, load_cr3() is serializing and gives the
-	 * ordering guarantee we need. This full barrier is also
-	 * required by the membarrier system call.
+	 * ordering guarantee we need.
 	 */
 	load_cr3(next->pgd);
 
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2b24a6974847..fe29d06e2800 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.
+	 */
 	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
 		__mmdrop(mm);
 }
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4f85494620d7..0e36d9960d91 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2649,6 +2649,12 @@ 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)) {
@@ -3290,6 +3296,9 @@ 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.
 	 */
 	smp_mb__before_spinlock();
 	rq_lock(rq, &rf);
-- 
2.11.0

[PATCH] membarrier: Document scheduler barrier requirements

[Mathieu Desnoyers]

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@efficios.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
---
 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.
+	 * 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.
+	 */
 	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

Re: [PATCH] membarrier: Document scheduler barrier requirements

[Paul E. McKenney]

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@efficios.com>

Queued for review, thank you Mathieu!

							Thanx, Paul

> CC: Peter Zijlstra <peterz@infradead.org>
> CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> CC: Boqun Feng <boqun.feng@gmail.com>
> CC: Andrew Hunter <ahh@google.com>
> CC: Maged Michael <maged.michael@gmail.com>
> CC: gromer@google.com
> CC: Avi Kivity <avi@scylladb.com>
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> CC: Paul Mackerras <paulus@samba.org>
> CC: Michael Ellerman <mpe@ellerman.id.au>
> CC: Dave Watson <davejwatson@fb.com>
> ---
>  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.
> +	 * 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.
> +	 */
>  	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
> 

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@efficios.com>
> CC: Peter Zijlstra <peterz@infradead.org>
> CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> CC: Boqun Feng <boqun.feng@gmail.com>
> CC: Andrew Hunter <ahh@google.com>
> CC: Maged Michael <maged.michael@gmail.com>
> CC: gromer@google.com
> CC: Avi Kivity <avi@scylladb.com>
> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
> CC: Paul Mackerras <paulus@samba.org>
> CC: Michael Ellerman <mpe@ellerman.id.au>
> CC: Dave Watson <davejwatson@fb.com>
> ---
>  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
> 

Re: [PATCH] membarrier: Document scheduler barrier requirements

[Mathieu Desnoyers]

----- On Sep 18, 2017, at 8:26 PM, Andrea Parri parri.andrea@gmail.com wrote:

> 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@efficios.com>
>> CC: Peter Zijlstra <peterz@infradead.org>
>> CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
>> CC: Boqun Feng <boqun.feng@gmail.com>
>> CC: Andrew Hunter <ahh@google.com>
>> CC: Maged Michael <maged.michael@gmail.com>
>> CC: gromer@google.com
>> CC: Avi Kivity <avi@scylladb.com>
>> CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
>> CC: Paul Mackerras <paulus@samba.org>
>> CC: Michael Ellerman <mpe@ellerman.id.au>
>> CC: Dave Watson <davejwatson@fb.com>
>> ---
>>  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"?

Right, my bad.

> 
> 
>> +	 * 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?

Yes.

I'll send an updated patch to Paul. Thanks for the review!

Mathieu

> 
> (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

-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com