s390/mm: fix race on mm->context.flush_mm

The order in __tlb_flush_mm_lazy is to flush TLB first and then clear
the mm->context.flush_mm bit. This can lead to missed flushes as the
bit can be set anytime, the order needs to be the other way aronud.

But this leads to a different race, __tlb_flush_mm_lazy may be called
on two CPUs concurrently. If mm->context.flush_mm is cleared first then
another CPU can bypass __tlb_flush_mm_lazy although the first CPU has
not done the flush yet. In a virtualized environment the time until the
flush is finally completed can be arbitrarily long.

Add a spinlock to serialize __tlb_flush_mm_lazy and use the function
in finish_arch_post_lock_switch as well.

Cc: <stable@vger.kernel.org>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/include/asm/mmu.h

@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 
 typedef struct {
+	spinlock_t lock;
 	cpumask_t cpu_attach_mask;
 	atomic_t flush_count;
 	unsigned int flush_mm;
@@ -27,6 +28,7 @@ typedef struct {
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
+	.context.lock =	__SPIN_LOCK_UNLOCKED(name.context.lock),	   \
 	.context.pgtable_lock =						   \
 			__SPIN_LOCK_UNLOCKED(name.context.pgtable_lock),   \
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \

arch/s390/include/asm/mmu_context.h

@@ -17,6 +17,7 @@
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	spin_lock_init(&mm->context.lock);
 	spin_lock_init(&mm->context.pgtable_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
 	spin_lock_init(&mm->context.gmap_lock);
@@ -121,8 +122,7 @@ static inline void finish_arch_post_lock_switch(void)
 		while (atomic_read(&mm->context.flush_count))
 			cpu_relax();
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-		if (mm->context.flush_mm)
-			__tlb_flush_mm(mm);
+		__tlb_flush_mm_lazy(mm);
 		preempt_enable();
 	}
 	set_fs(current->thread.mm_segment);

arch/s390/include/asm/tlbflush.h

@@ -101,10 +101,12 @@ static inline void __tlb_flush_kernel(void)
 
 static inline void __tlb_flush_mm_lazy(struct mm_struct * mm)
 {
+	spin_lock(&mm->context.lock);
 	if (mm->context.flush_mm) {
-		__tlb_flush_mm(mm);
 		mm->context.flush_mm = 0;
+		__tlb_flush_mm(mm);
 	}
+	spin_unlock(&mm->context.lock);
 }
 
 /*