Skip to contentSkip to conversation

mm: Fix use_mm() vs TLB invalidate

PATCH Superseded Peter Zijlstra 3 participants 4 messages Feb 26, 2020 – Mar 3, 2020 Memory management

v2 of 3 Superseded Latest is v3 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 mm: Fix 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().

[ There are all sorts of reasons this might be harmless for various architecture specific reasons, but best not leave the door open at all. ]

---
v2 now with WARN_ON_ONCE

 mmu_context.c |   11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
mm/mmu_context.c +10 -1
Index: linux-2.6/mm/mmu_context.c
===================================================================
@@ -24,14 +24,19 @@ void use_mm(struct mm_struct *mm)
 	struct mm_struct *active_mm;
 	struct task_struct *tsk = current;
 
+	WARN_ON(!(tsk->flags & PF_KTHREAD));
+	WARN_ON(tsk->mm != NULL);
+
 	task_lock(tsk);
+	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();
@@ -54,11 +59,15 @@ void unuse_mm(struct mm_struct *mm)
 {
 	struct task_struct *tsk = current;
 
+	WARN_ON(!(tsk->flags & PF_KTHREAD));
+
 	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(unuse_mm);
Tested-by on v2 1/1
#1 lore raw
Quoted 21 lines · Peter Zijlstra

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.

Quoted 6 lines

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

[ There are all sorts of reasons this might be harmless for various architecture specific reasons, but best not leave the door open at all. ]

Not that I'm worried about it breaking anything, but ran it through the usual testing and might as well report:

Signature · 1 line
Jens Axboe
#2 lore raw
In reply to Peter Zijlstra

mm/mmu_context.c void use_mm(struct mm_struct *mm)

Quoted 6 lines · Peter Zijlstra

v2 now with WARN_ON_ONCE
[...]

mm/mmu_context.c +3 -0
+	WARN_ON(!(tsk->flags & PF_KTHREAD));
+	WARN_ON(tsk->mm != NULL);
[...]
+	WARN_ON(!(tsk->flags & PF_KTHREAD));

Version mismatch?

Signature · 1 line
Kees Cook
#3 lore raw
Quoted 9 lines · Kees Cook

mm/mmu_context.c void use_mm(struct mm_struct *mm)

Quoted 6 lines · Peter Zijlstra

v2 now with WARN_ON_ONCE
[...]

mm/mmu_context.c +3 -0
+	WARN_ON(!(tsk->flags & PF_KTHREAD));
+	WARN_ON(tsk->mm != NULL);
[...]
+	WARN_ON(!(tsk->flags & PF_KTHREAD));

Version mismatch?

Dammit; no, that's just me being an idiot for doing too many things at once :/

I suppose I'll go send v3..