membarrier: Document scheduler barrier requirements
PATCH v2 1/1 membarrier: Document scheduler barrier requirements
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.
Changes since v1:
- Update comments to match reality for code paths which are after storing to rq->curr, before returning to user-space.
--- arch/x86/mm/tlb.c | 5 +++++ include/linux/sched/mm.h | 5 +++++ kernel/sched/core.c | 9 +++++++++ 3 files changed, 19 insertions(+)
arch/x86/mm/tlb.c +5 -0
@@ -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 +* 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);
include/linux/sched/mm.h +5 -0
@@ -38,6 +38,11 @@ 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. +*/ if (unlikely (atomic_dec_and_test (&mm->mm_count)))__mmdrop (mm); }
kernel/sched/core.c +9 -0
@@ -2658,6 +2658,12 @@ 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 )) {
@@ -3299,6 +3305,9 @@ 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 ();
Signature · 1 line
2.11.0
Quoted 3 lines · Mathieu Desnoyers
Document the membarrier requirement on having a full memory barrier in
__schedule()after coming from user-space, before storing torq->curr. It is provided bysmp_mb__before_spinlock()in__schedule().
It is smp_mb__after_spinlock(). (Yes: I missed it in my previous email.)
Andrea
Quoted 93 lines
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()inmmdrop()that ensures this.The x86
switch_mm_irqs_off()full barrier is currently provided by many cpumask update operations as well aswrite_cr3(). Document thatwrite_cr3()provides this barrier.Changes since v1:
- Update comments to match reality for code paths which are after storing torq->curr, before returning to user-space.Signed-off-by Mathieu Desnoyers <[email protected]>CC Peter Zijlstra <[email protected]>CC Paul E. McKenney <[email protected]>CC Boqun Feng <[email protected]>CC Andrew Hunter <[email protected]>CC Maged Michael <[email protected]>CC Avi Kivity <[email protected]>CC Benjamin Herrenschmidt <[email protected]>CC Paul Mackerras <[email protected]>CC Michael Ellerman <[email protected]>CC Dave Watson <[email protected]>--- arch/x86/mm/tlb.c | 5 +++++ include/linux/sched/mm.h | 5 +++++ kernel/sched/core.c | 9 +++++++++ 3 files changed, 19 insertions(+)arch/x86/mm/tlb.c +5
-0@@ -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 +* 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);include/linux/sched/mm.h +5
-0@@ -38,6 +38,11 @@ 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. +*/ if (unlikely (atomic_dec_and_test (&mm->mm_count)))__mmdrop (mm); }kernel/sched/core.c +9
-0@@ -2658,6 +2658,12 @@ 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 )) {@@ -3299,6 +3305,9 @@ 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 ();Signature · 1 line
2.11.0
Quoted 6 lines · ----- On Sep 19, 2017, at 5:47 PM, Andrea Parri [email protected] wrote:
Quoted 3 lines · Mathieu Desnoyers
Document the membarrier requirement on having a full memory barrier in
__schedule()after coming from user-space, before storing torq->curr. It is provided bysmp_mb__before_spinlock()in__schedule().It is
smp_mb__after_spinlock(). (Yes: I missed it in my previous email.)
OK. Will send a v3 fixing the changelog.
Thanks,
Mathieu
Quoted 98 lines
Andrea
Quoted 94 lines
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()inmmdrop()that ensures this.The x86
switch_mm_irqs_off()full barrier is currently provided by many cpumask update operations as well aswrite_cr3(). Document thatwrite_cr3()provides this barrier.Changes since v1:
- Update comments to match reality for code paths which are after storing torq->curr, before returning to user-space.Signed-off-by Mathieu Desnoyers <[email protected]>CC Peter Zijlstra <[email protected]>CC Paul E. McKenney <[email protected]>CC Boqun Feng <[email protected]>CC Andrew Hunter <[email protected]>CC Maged Michael <[email protected]>CC Avi Kivity <[email protected]>CC Benjamin Herrenschmidt <[email protected]>CC Paul Mackerras <[email protected]>CC Michael Ellerman <[email protected]>CC Dave Watson <[email protected]>--- arch/x86/mm/tlb.c | 5 +++++ include/linux/sched/mm.h | 5 +++++ kernel/sched/core.c | 9 +++++++++ 3 files changed, 19 insertions(+)arch/x86/mm/tlb.c +5
-0@@ -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 +* 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) !=arch/x86/mm/tlb.c +0
-0next->context.ctx_id);include/linux/sched/mm.h +5
-0@@ -38,6 +38,11 @@ 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. +*/ if (unlikely (atomic_dec_and_test (&mm->mm_count)))__mmdrop (mm); }kernel/sched/core.c +6
-0@@ -2658,6 +2658,12 @@ 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);kernel/sched/core.c +3
-1if (unlikely (prev_state ==TASK_DEAD )) {@@ -3299,6 +3305,9 @@ 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
Signature · 3 lines
Mathieu Desnoyers EfficiOS Inc. http://www.efficios.com