sched: fix exit_mm vs membarrier (v4)

exit_mm should issue memory barriers after user-space memory accesses,
before clearing current->mm, to order user-space memory accesses
performed prior to exit_mm before clearing tsk->mm, which has the
effect of skipping the membarrier private expedited IPIs.

exit_mm should also update the runqueue's membarrier_state so
membarrier global expedited IPIs are not sent when they are not
needed.

The membarrier system call can be issued concurrently with do_exit
if we have thread groups created with CLONE_VM but not CLONE_THREAD.

Here is the scenario I have in mind:

Two thread groups are created, A and B. Thread group B is created by
issuing clone from group A with flag CLONE_VM set, but not CLONE_THREAD.
Let's assume we have a single thread within each thread group (Thread A
and Thread B).

The AFAIU we can have:

Userspace variables:

int x = 0, y = 0;

CPU 0                   CPU 1
Thread A                Thread B
(in thread group A)     (in thread group B)

x = 1
barrier()
y = 1
exit()
exit_mm()
current->mm = NULL;
                        r1 = load y
                        membarrier()
                          skips CPU 0 (no IPI) because its current mm is NULL
                        r2 = load x
                        BUG_ON(r1 == 1 && r2 == 0)

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201020134715.13909-2-mathieu.desnoyers@efficios.com

include/linux/sched/mm.h

@@ -347,6 +347,8 @@ static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 
 extern void membarrier_exec_mmap(struct mm_struct *mm);
 
+extern void membarrier_update_current_mm(struct mm_struct *next_mm);
+
 #else
 #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS
 static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
@@ -361,6 +363,9 @@ static inline void membarrier_exec_mmap(struct mm_struct *mm)
 static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm)
 {
 }
+static inline void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+}
 #endif
 
 #endif /* _LINUX_SCHED_MM_H */

kernel/exit.c

@@ -475,10 +475,24 @@ static void exit_mm(void)
 	BUG_ON(mm != current->active_mm);
 	/* more a memory barrier than a real lock */
 	task_lock(current);
+	/*
+	 * When a thread stops operating on an address space, the loop
+	 * in membarrier_private_expedited() may not observe that
+	 * tsk->mm, and the loop in membarrier_global_expedited() may
+	 * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED
+	 * rq->membarrier_state, so those would not issue an IPI.
+	 * Membarrier requires a memory barrier after accessing
+	 * user-space memory, before clearing tsk->mm or the
+	 * rq->membarrier_state.
+	 */
+	smp_mb__after_spinlock();
+	local_irq_disable();
 	current->mm = NULL;
-	mmap_read_unlock(mm);
+	membarrier_update_current_mm(NULL);
 	enter_lazy_tlb(mm, current);
+	local_irq_enable();
 	task_unlock(current);
+	mmap_read_unlock(mm);
 	mm_update_next_owner(mm);
 	mmput(mm);
 	if (test_thread_flag(TIF_MEMDIE))

kernel/sched/membarrier.c

@@ -76,6 +76,18 @@ void membarrier_exec_mmap(struct mm_struct *mm)
 	this_cpu_write(runqueues.membarrier_state, 0);
 }
 
+void membarrier_update_current_mm(struct mm_struct *next_mm)
+{
+	struct rq *rq = this_rq();
+	int membarrier_state = 0;
+
+	if (next_mm)
+		membarrier_state = atomic_read(&next_mm->membarrier_state);
+	if (READ_ONCE(rq->membarrier_state) == membarrier_state)
+		return;
+	WRITE_ONCE(rq->membarrier_state, membarrier_state);
+}
+
 static int membarrier_global_expedited(void)
 {
 	int cpu;