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__after_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.
Changes since v2:
- Update changelog (smp_mb__before_spinlock -> smp_mb__after_spinlock).
Changes since v3:
- Clarify comments following feeback from Peter Zijlstra.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoy...@efficios.com>
CC: Peter Zijlstra <pet...@infradead.org>
CC: Paul E. McKenney <paul...@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.f...@gmail.com>
CC: Andrew Hunter <a...@google.com>
CC: Maged Michael <maged.mich...@gmail.com>
CC: gro...@google.com
CC: Avi Kivity <a...@scylladb.com>
CC: Benjamin Herrenschmidt <b...@kernel.crashing.org>
CC: Paul Mackerras <pau...@samba.org>
CC: Michael Ellerman <m...@ellerman.id.au>
CC: Dave Watson <davejwat...@fb.com>
---
arch/x86/mm/tlb.c | 5 +++++
include/linux/sched/mm.h | 5 +++++
kernel/sched/core.c | 38 +++++++++++++++++++++++++++-----------
3 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 93fe97cce581..5ba86b85953b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -143,6 +143,11 @@ 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);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index d3b81e48784d..1bd10c2c0893 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -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);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b9d731283946..6254f87645de 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)) {
@@ -2754,6 +2760,13 @@ context_switch(struct rq *rq, struct task_struct *prev,
*/
arch_start_context_switch(prev);
+ /*
+ * If mm is non-NULL, we pass through switch_mm(). If mm is
+ * NULL, we will pass through mmdrop() in finish_task_switch().
+ * Both of these contain the full memory barrier required by
+ * membarrier after storing to rq->curr, before returning to
+ * user-space.
+ */
if (!mm) {
next->active_mm = oldmm;
mmgrab(oldmm);
@@ -3290,6 +3303,9 @@ 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();
@@ -3337,17 +3353,17 @@ static void __sched notrace __schedule(bool preempt)
/*
* The membarrier system call requires each architecture
* to have a full memory barrier after updating
- * rq->curr, before returning to user-space. For TSO
- * (e.g. x86), the architecture must provide its own
- * barrier in switch_mm(). For weakly ordered machines
- * for which spin_unlock() acts as a full memory
- * barrier, finish_lock_switch() in common code takes
- * care of this barrier. For weakly ordered machines for
- * which spin_unlock() acts as a RELEASE barrier (only
- * arm64 and PowerPC), arm64 has a full barrier in
- * switch_to(), and PowerPC has
- * smp_mb__after_unlock_lock() before
- * finish_lock_switch().
+ * rq->curr, before returning to user-space.
+ *
+ * Here are the schemes providing that barrier on the
+ * various architectures:
+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc,
+ * - finish_lock_switch() for weakly-ordered
+ * architectures where spin_unlock is a full barrier,
+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
+ * is a RELEASE barrier),
+ * - membarrier_arch_sched_in() for PowerPC,
+ * (weakly-ordered, spin_unlock is a RELEASE barrier).
*/
++*switch_count;
--
2.11.0
