linux-kernel - [PATCH 3.16 087/133] s390/mm: fix race on mm->context.flush

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 22 Nov 2017 01:58:13 +0000
From:   Ben Hutchings <ben@...adent.org.uk>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
CC:     akpm@...ux-foundation.org,
        "Heiko Carstens" <heiko.carstens@...ibm.com>,
        "Martin Schwidefsky" <schwidefsky@...ibm.com>
Subject: [PATCH 3.16 087/133] s390/mm: fix race on mm->context.flush_mm

3.16.51-rc1 review patch.  If anyone has any objections, please let me know.

------------------

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

commit 60f07c8ec5fae06c23e9fd7bab67dabce92b3414 upstream.

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.

Reviewed-by: Heiko Carstens <heiko.carstens@...ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@...ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
 arch/s390/include/asm/mmu.h         | 2 ++
 arch/s390/include/asm/mmu_context.h | 4 ++--
 arch/s390/include/asm/tlbflush.h    | 4 +++-
 3 files changed, 7 insertions(+), 3 deletions(-)

--- a/arch/s390/include/asm/mmu.h
+++ b/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 attach_count;
 	unsigned int flush_mm;
@@ -21,6 +22,7 @@ typedef struct {
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						      \
+	.context.lock =	__SPIN_LOCK_UNLOCKED(name.context.lock),	      \
 	.context.list_lock    = __SPIN_LOCK_UNLOCKED(name.context.list_lock), \
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list),    \
 	.context.gmap_list = LIST_HEAD_INIT(name.context.gmap_list),
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
 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.list_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
 	INIT_LIST_HEAD(&mm->context.gmap_list);
@@ -95,8 +96,7 @@ static inline void finish_arch_post_lock
 			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);
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -164,10 +164,12 @@ static inline void __tlb_flush_mm(struct
 
 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);
 }
 
 /*