Commit-ID: 306e060435d7a3aef8f6f033e43b0f581638adce Gitweb: https://git.kernel.org/tip/306e060435d7a3aef8f6f033e43b0f581638adce Author: Mathieu Desnoyers <mathieu.desnoy...@efficios.com> AuthorDate: Mon, 29 Jan 2018 15:20:12 -0500 Committer: Ingo Molnar <mi...@kernel.org> CommitDate: Mon, 5 Feb 2018 21:34:21 +0100
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__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. Signed-off-by: Mathieu Desnoyers <mathieu.desnoy...@efficios.com> Acked-by: Thomas Gleixner <t...@linutronix.de> Acked-by: Peter Zijlstra (Intel) <pet...@infradead.org> Cc: Andrea Parri <parri.and...@gmail.com> Cc: Andrew Hunter <a...@google.com> Cc: Andy Lutomirski <l...@kernel.org> Cc: Avi Kivity <a...@scylladb.com> Cc: Benjamin Herrenschmidt <b...@kernel.crashing.org> Cc: Boqun Feng <boqun.f...@gmail.com> Cc: Dave Watson <davejwat...@fb.com> Cc: David Sehr <s...@google.com> Cc: Greg Hackmann <ghackm...@google.com> Cc: H. Peter Anvin <h...@zytor.com> Cc: Linus Torvalds <torva...@linux-foundation.org> Cc: Maged Michael <maged.mich...@gmail.com> Cc: Michael Ellerman <m...@ellerman.id.au> Cc: Paul E. McKenney <paul...@linux.vnet.ibm.com> Cc: Paul Mackerras <pau...@samba.org> Cc: Russell King <li...@armlinux.org.uk> Cc: Will Deacon <will.dea...@arm.com> Cc: linux-...@vger.kernel.org Link: http://lkml.kernel.org/r/20180129202020.8515-4-mathieu.desnoy...@efficios.com Signed-off-by: Ingo Molnar <mi...@kernel.org> --- arch/x86/mm/tlb.c | 5 +++++ include/linux/sched/mm.h | 5 +++++ kernel/sched/core.c | 37 ++++++++++++++++++++++++++----------- 3 files changed, 36 insertions(+), 11 deletions(-) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5bfe61a..9fa7d2e 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -228,6 +228,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, #endif this_cpu_write(cpu_tlbstate.is_lazy, false); + /* + * 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_WARN_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 26307cd..b84e0fd 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -39,6 +39,11 @@ 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 ead0c21..11bf4d4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2703,6 +2703,12 @@ 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)) { @@ -2808,6 +2814,13 @@ 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); @@ -3344,6 +3357,9 @@ 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(); @@ -3391,17 +3407,16 @@ 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, PowerPC. + * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. + * - 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), */ ++*switch_count;
