[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20170802000818.4760-2-namit@vmware.com>
Date: Tue, 1 Aug 2017 17:08:12 -0700
From: Nadav Amit <namit@...are.com>
To: <linux-mm@...ck.org>
CC: <nadav.amit@...il.com>, <linux-kernel@...r.kernel.org>,
<akpm@...ux-foundation.org>, Andy Lutomirski <luto@...nel.org>,
Nadav Amit <namit@...are.com>
Subject: [PATCH v6 1/7] mm: migrate: prevent racy access to tlb_flush_pending
From: Nadav Amit <nadav.amit@...il.com>
Setting and clearing mm->tlb_flush_pending can be performed by multiple
threads, since mmap_sem may only be acquired for read in
task_numa_work(). If this happens, tlb_flush_pending might be cleared
while one of the threads still changes PTEs and batches TLB flushes.
This can lead to the same race between migration and
change_protection_range() that led to the introduction of
tlb_flush_pending. The result of this race was data corruption, which
means that this patch also addresses a theoretically possible data
corruption.
An actual data corruption was not observed, yet the race was
was confirmed by adding assertion to check tlb_flush_pending is not set
by two threads, adding artificial latency in change_protection_range()
and using sysctl to reduce kernel.numa_balancing_scan_delay_ms.
Fixes: 20841405940e ("mm: fix TLB flush race between migration, and
change_protection_range")
Cc: Andy Lutomirski <luto@...nel.org>
Signed-off-by: Nadav Amit <namit@...are.com>
Acked-by: Mel Gorman <mgorman@...e.de>
Acked-by: Rik van Riel <riel@...hat.com>
Acked-by: Minchan Kim <minchan@...nel.org>
---
include/linux/mm_types.h | 31 ++++++++++++++++++++++---------
kernel/fork.c | 2 +-
mm/debug.c | 2 +-
mm/mprotect.c | 4 ++--
4 files changed, 26 insertions(+), 13 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 45cdb27791a3..f5263dd0f1bc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -493,7 +493,7 @@ struct mm_struct {
* can move process memory needs to flush the TLB when moving a
* PROT_NONE or PROT_NUMA mapped page.
*/
- bool tlb_flush_pending;
+ atomic_t tlb_flush_pending;
#endif
struct uprobes_state uprobes_state;
#ifdef CONFIG_HUGETLB_PAGE
@@ -528,33 +528,46 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
{
barrier();
- return mm->tlb_flush_pending;
+ return atomic_read(&mm->tlb_flush_pending) > 0;
}
-static inline void set_tlb_flush_pending(struct mm_struct *mm)
+
+static inline void init_tlb_flush_pending(struct mm_struct *mm)
{
- mm->tlb_flush_pending = true;
+ atomic_set(&mm->tlb_flush_pending, 0);
+}
+
+static inline void inc_tlb_flush_pending(struct mm_struct *mm)
+{
+ atomic_inc(&mm->tlb_flush_pending);
/*
- * Guarantee that the tlb_flush_pending store does not leak into the
+ * Guarantee that the tlb_flush_pending increase does not leak into the
* critical section updating the page tables
*/
smp_mb__before_spinlock();
}
+
/* Clearing is done after a TLB flush, which also provides a barrier. */
-static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+static inline void dec_tlb_flush_pending(struct mm_struct *mm)
{
barrier();
- mm->tlb_flush_pending = false;
+ atomic_dec(&mm->tlb_flush_pending);
}
#else
static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
{
return false;
}
-static inline void set_tlb_flush_pending(struct mm_struct *mm)
+
+static inline void init_tlb_flush_pending(struct mm_struct *mm)
{
}
-static inline void clear_tlb_flush_pending(struct mm_struct *mm)
+
+static inline void inc_tlb_flush_pending(struct mm_struct *mm)
+{
+}
+
+static inline void dec_tlb_flush_pending(struct mm_struct *mm)
{
}
#endif
diff --git a/kernel/fork.c b/kernel/fork.c
index e53770d2bf95..840e7a7132e1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -809,7 +809,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
mm_init_aio(mm);
mm_init_owner(mm, p);
mmu_notifier_mm_init(mm);
- clear_tlb_flush_pending(mm);
+ init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
diff --git a/mm/debug.c b/mm/debug.c
index db1cd26d8752..d70103bb4731 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -159,7 +159,7 @@ void dump_mm(const struct mm_struct *mm)
mm->numa_next_scan, mm->numa_scan_offset, mm->numa_scan_seq,
#endif
#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
- mm->tlb_flush_pending,
+ atomic_read(&mm->tlb_flush_pending),
#endif
mm->def_flags, &mm->def_flags
);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 8edd0d576254..0c413774c1e3 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -245,7 +245,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
BUG_ON(addr >= end);
pgd = pgd_offset(mm, addr);
flush_cache_range(vma, addr, end);
- set_tlb_flush_pending(mm);
+ inc_tlb_flush_pending(mm);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
@@ -257,7 +257,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
/* Only flush the TLB if we actually modified any entries: */
if (pages)
flush_tlb_range(vma, start, end);
- clear_tlb_flush_pending(mm);
+ dec_tlb_flush_pending(mm);
return pages;
}
--
2.11.0
Powered by blists - more mailing lists