Patch "s390/mm: fix local TLB flushing vs. detach of an mm address space" has been added to the 4.9-stable tree

[<gregkh@linuxfoundation.org>]

This is a note to let you know that I've just added the patch titled

    s390/mm: fix local TLB flushing vs. detach of an mm address space

to the 4.9-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     s390-mm-fix-local-tlb-flushing-vs.-detach-of-an-mm-address-space.patch
and it can be found in the queue-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@vger.kernel.org> know about it.


>From b3e5dc45fd1ec2aa1de6b80008f9295eb17e0659 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Wed, 16 Aug 2017 14:10:01 +0200
Subject: s390/mm: fix local TLB flushing vs. detach of an mm address space

From: Martin Schwidefsky <schwidefsky@de.ibm.com>

commit b3e5dc45fd1ec2aa1de6b80008f9295eb17e0659 upstream.

The local TLB flushing code keeps an additional mask in the mm.context,
the cpu_attach_mask. At the time a global flush of an address space is
done the cpu_attach_mask is copied to the mm_cpumask in order to avoid
future global flushes in case the mm is used by a single CPU only after
the flush.

Trouble is that the reset of the mm_cpumask is racy against the detach
of an mm address space by switch_mm. The current order is first the
global TLB flush and then the copy of the cpu_attach_mask to the
mm_cpumask. The order needs to be the other way around.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/s390/include/asm/mmu_context.h |    4 ++--
 arch/s390/include/asm/tlbflush.h    |   26 +++++---------------------
 2 files changed, 7 insertions(+), 23 deletions(-)

--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -93,7 +93,6 @@ static inline void switch_mm(struct mm_s
 	if (prev == next)
 		return;
 	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
-	cpumask_set_cpu(cpu, mm_cpumask(next));
 	/* Clear old ASCE by loading the kernel ASCE. */
 	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
 	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
@@ -111,7 +110,7 @@ static inline void finish_arch_post_lock
 		preempt_disable();
 		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);
 		preempt_enable();
@@ -126,6 +125,7 @@ static inline void activate_mm(struct mm
                                struct mm_struct *next)
 {
 	switch_mm(prev, next, current);
+	cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
 	set_user_asce(next);
 }
 
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -43,23 +43,6 @@ static inline void __tlb_flush_global(vo
  * Flush TLB entries for a specific mm on all CPUs (in case gmap is used
  * this implicates multiple ASCEs!).
  */
-static inline void __tlb_flush_full(struct mm_struct *mm)
-{
-	preempt_disable();
-	atomic_inc(&mm->context.flush_count);
-	if (cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		/* Local TLB flush */
-		__tlb_flush_local();
-	} else {
-		/* Global TLB flush */
-		__tlb_flush_global();
-		/* Reset TLB flush mask */
-		cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
-	}
-	atomic_dec(&mm->context.flush_count);
-	preempt_enable();
-}
-
 static inline void __tlb_flush_mm(struct mm_struct *mm)
 {
 	unsigned long gmap_asce;
@@ -71,16 +54,18 @@ static inline void __tlb_flush_mm(struct
 	 */
 	preempt_disable();
 	atomic_inc(&mm->context.flush_count);
+	/* Reset TLB flush mask */
+	cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
+	barrier();
 	gmap_asce = READ_ONCE(mm->context.gmap_asce);
 	if (MACHINE_HAS_IDTE && gmap_asce != -1UL) {
 		if (gmap_asce)
 			__tlb_flush_idte(gmap_asce);
 		__tlb_flush_idte(mm->context.asce);
 	} else {
-		__tlb_flush_full(mm);
+		/* Global TLB flush */
+		__tlb_flush_global();
 	}
-	/* Reset TLB flush mask */
-	cpumask_copy(mm_cpumask(mm), &mm->context.cpu_attach_mask);
 	atomic_dec(&mm->context.flush_count);
 	preempt_enable();
 }
@@ -94,7 +79,6 @@ static inline void __tlb_flush_kernel(vo
 }
 #else
 #define __tlb_flush_global()	__tlb_flush_local()
-#define __tlb_flush_full(mm)	__tlb_flush_local()
 
 /*
  * Flush TLB entries for a specific ASCE on all CPUs.


Patches currently in stable-queue which might be from schwidefsky@de.ibm.com are

queue-4.9/s390-mm-fix-local-tlb-flushing-vs.-detach-of-an-mm-address-space.patch
queue-4.9/s390-mm-fix-race-on-mm-context.flush_mm.patch