[004/163] mm: fix kthread_use_mm() vs TLB invalidate

Commit Message

Andrew Morton Aug. 7, 2020, 6:17 a.m. UTC

From: Peter Zijlstra <[e-mail]>
Subject: mm: fix kthread_use_mm() vs TLB invalidate

For SMP systems using IPI based TLB invalidation, looking at
current->active_mm is entirely reasonable.  This then presents the
following race condition:


  CPU0			CPU1

  flush_tlb_mm(mm)	use_mm(mm)
    <send-IPI>
			  tsk->active_mm = mm;
			  <IPI>
			    if (tsk->active_mm == mm)
			      // flush TLBs
			  </IPI>
			  switch_mm(old_mm,mm,tsk);


Where it is possible the IPI flushed the TLBs for @old_mm, not @mm,
because the IPI lands before we actually switched.

Avoid this by disabling IRQs across changing ->active_mm and
switch_mm().

Of the (SMP) architectures that have IPI based TLB invalidate:

  Alpha    - checks active_mm
  ARC      - ASID specific
  IA64     - checks active_mm
  MIPS     - ASID specific flush
  OpenRISC - shoots down world
  PARISC   - shoots down world
  SH       - ASID specific
  SPARC    - ASID specific
  x86      - N/A
  xtensa   - checks active_mm

So at the very least Alpha, IA64 and Xtensa are suspect.

On top of this, for scheduler consistency we need at least preemption
disabled across changing tsk->mm and doing switch_mm(), which is
currently provided by task_lock(), but that's not sufficient for
PREEMPT_RT.

[[e-mail]: add comment]
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Reported-by: Andy Lutomirski <[e-mail]>
Cc: Nicholas Piggin <[e-mail]>
Cc: Jens Axboe <[e-mail]>
Cc: Kees Cook <[e-mail]>
Cc: Jann Horn <[e-mail]>
Cc: Will Deacon <[e-mail]>
Cc: Christoph Hellwig <[e-mail]>
Cc: Nicholas Piggin <[e-mail]>
Cc: Mathieu Desnoyers <[e-mail]>
Cc: <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 kernel/kthread.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

Patch

--- a/kernel/kthread.c~mm-fix-kthread_use_mm-vs-tlb-invalidate
+++ a/kernel/kthread.c
@@ -1241,13 +1241,16 @@  void kthread_use_mm(struct mm_struct *mm
 	WARN_ON_ONCE(tsk->mm);
 
 	task_lock(tsk);
+	/* Hold off tlb flush IPIs while switching mm's */
+	local_irq_disable();
 	active_mm = tsk->active_mm;
 	if (active_mm != mm) {
 		mmgrab(mm);
 		tsk->active_mm = mm;
 	}
 	tsk->mm = mm;
-	switch_mm(active_mm, mm, tsk);
+	switch_mm_irqs_off(active_mm, mm, tsk);
+	local_irq_enable();
 	task_unlock(tsk);
 #ifdef finish_arch_post_lock_switch
 	finish_arch_post_lock_switch();
@@ -1276,9 +1279,11 @@  void kthread_unuse_mm(struct mm_struct *
 
 	task_lock(tsk);
 	sync_mm_rss(mm);
+	local_irq_disable();
 	tsk->mm = NULL;
 	/* active_mm is still 'mm' */
 	enter_lazy_tlb(mm, tsk);
+	local_irq_enable();
 	task_unlock(tsk);
 }
 EXPORT_SYMBOL_GPL(kthread_unuse_mm);