sched: membarrier: cover kthread_use_mm (v4)

Add comments and memory barrier to kthread_use_mm and kthread_unuse_mm
to allow the effect of membarrier(2) to apply to kthreads accessing
user-space memory as well.

Given that no prior kthread use this guarantee and that it only affects
kthreads, adding this guarantee does not affect user-space ABI.

Refine the check in membarrier_global_expedited to exclude runqueues
running the idle thread rather than all kthreads from the IPI cpumask.

Now that membarrier_global_expedited can IPI kthreads, the scheduler
also needs to update the runqueue's membarrier_state when entering lazy
TLB state.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201020134715.13909-3-mathieu.desnoyers@efficios.com

kernel/kthread.c

@@ -1248,6 +1248,7 @@ void kthread_use_mm(struct mm_struct *mm)
 		tsk->active_mm = mm;
 	}
 	tsk->mm = mm;
+	membarrier_update_current_mm(mm);
 	switch_mm_irqs_off(active_mm, mm, tsk);
 	local_irq_enable();
 	task_unlock(tsk);
@@ -1255,8 +1256,19 @@ void kthread_use_mm(struct mm_struct *mm)
 	finish_arch_post_lock_switch();
 #endif
 
+	/*
+	 * When a kthread starts operating on an address space, the loop
+	 * in membarrier_{private,global}_expedited() may not observe
+	 * that tsk->mm, and not issue an IPI. Membarrier requires a
+	 * memory barrier after storing to tsk->mm, before accessing
+	 * user-space memory. A full memory barrier for membarrier
+	 * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by
+	 * mmdrop(), or explicitly with smp_mb().
+	 */
 	if (active_mm != mm)
 		mmdrop(active_mm);
+	else
+		smp_mb();
 
 	to_kthread(tsk)->oldfs = force_uaccess_begin();
 }
@@ -1276,9 +1288,18 @@ void kthread_unuse_mm(struct mm_struct *mm)
 	force_uaccess_end(to_kthread(tsk)->oldfs);
 
 	task_lock(tsk);
+	/*
+	 * When a kthread stops operating on an address space, the loop
+	 * in membarrier_{private,global}_expedited() may not observe
+	 * that tsk->mm, and not issue an IPI. Membarrier requires a
+	 * memory barrier after accessing user-space memory, before
+	 * clearing tsk->mm.
+	 */
+	smp_mb__after_spinlock();
 	sync_mm_rss(mm);
 	local_irq_disable();
 	tsk->mm = NULL;
+	membarrier_update_current_mm(NULL);
 	/* active_mm is still 'mm' */
 	enter_lazy_tlb(mm, tsk);
 	local_irq_enable();

kernel/sched/idle.c

@@ -338,6 +338,7 @@ void play_idle_precise(u64 duration_ns, u64 latency_ns)
 	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
 	WARN_ON_ONCE(!duration_ns);
+	WARN_ON_ONCE(current->mm);
 
 	rcu_sleep_check();
 	preempt_disable();

kernel/sched/membarrier.c

@@ -126,12 +126,11 @@ static int membarrier_global_expedited(void)
 			continue;
 
 		/*
-		 * Skip the CPU if it runs a kernel thread. The scheduler
-		 * leaves the prior task mm in place as an optimization when
-		 * scheduling a kthread.
+		 * Skip the CPU if it runs a kernel thread which is not using
+		 * a task mm.
 		 */
 		p = rcu_dereference(cpu_rq(cpu)->curr);
-		if (p->flags & PF_KTHREAD)
+		if (!p->mm)
 			continue;
 
 		__cpumask_set_cpu(cpu, tmpmask);