summaryrefslogtreecommitdiff
path: root/include
diff options
context:
space:
mode:
authorNadav Amit <nadav.amit@gmail.com>2017-08-11 01:23:56 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2017-08-11 01:54:07 +0300
commit16af97dc5a8975371a83d9e30a64038b48f40a2d (patch)
treecd55b61e8761962b892b343b1cc47e7f6c1ebced /include
parent9eeb52ae712e72141c4c1d173048a606ba8f42f6 (diff)
downloadlinux-16af97dc5a8975371a83d9e30a64038b48f40a2d.tar.xz
mm: migrate: prevent racy access to tlb_flush_pending
Patch series "fixes of TLB batching races", v6. It turns out that Linux TLB batching mechanism suffers from various races. Races that are caused due to batching during reclamation were recently handled by Mel and this patch-set deals with others. The more fundamental issue is that concurrent updates of the page-tables allow for TLB flushes to be batched on one core, while another core changes the page-tables. This other core may assume a PTE change does not require a flush based on the updated PTE value, while it is unaware that TLB flushes are still pending. This behavior affects KSM (which may result in memory corruption) and MADV_FREE and MADV_DONTNEED (which may result in incorrect behavior). A proof-of-concept can easily produce the wrong behavior of MADV_DONTNEED. Memory corruption in KSM is harder to produce in practice, but was observed by hacking the kernel and adding a delay before flushing and replacing the KSM page. Finally, there is also one memory barrier missing, which may affect architectures with weak memory model. This patch (of 7): 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. Link: http://lkml.kernel.org/r/20170802000818.4760-2-namit@vmware.com Fixes: 20841405940e ("mm: fix TLB flush race between migration, and change_protection_range") Signed-off-by: Nadav Amit <namit@vmware.com> Acked-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Minchan Kim <minchan@kernel.org> Cc: Andy Lutomirski <luto@kernel.org> Cc: Hugh Dickins <hughd@google.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeff Dike <jdike@addtoit.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Russell King <linux@armlinux.org.uk> Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r--include/linux/mm_types.h31
1 files changed, 22 insertions, 9 deletions
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7f384bb62d8e..f58f76ee1dfa 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
#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
/* See flush_tlb_batched_pending() */
@@ -532,33 +532,46 @@ 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