Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "21 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (21 commits)
  userfaultfd: replace ENOSPC with ESRCH in case mm has gone during copy/zeropage
  zram: rework copy of compressor name in comp_algorithm_store()
  rmap: do not call mmu_notifier_invalidate_page() under ptl
  mm: fix list corruptions on shmem shrinklist
  mm/balloon_compaction.c: don't zero ballooned pages
  MAINTAINERS: copy virtio on balloon_compaction.c
  mm: fix KSM data corruption
  mm: fix MADV_[FREE|DONTNEED] TLB flush miss problem
  mm: make tlb_flush_pending global
  mm: refactor TLB gathering API
  Revert "mm: numa: defer TLB flush for THP migration as long as possible"
  mm: migrate: fix barriers around tlb_flush_pending
  mm: migrate: prevent racy access to tlb_flush_pending
  fault-inject: fix wrong should_fail() decision in task context
  test_kmod: fix small memory leak on filesystem tests
  test_kmod: fix the lock in register_test_dev_kmod()
  test_kmod: fix bug which allows negative values on two config options
  test_kmod: fix spelling mistake: "EMTPY" -> "EMPTY"
  userfaultfd: hugetlbfs: remove superfluous page unlock in VM_SHARED case
  mm: ratelimit PFNs busy info message
  ...

1 files changed, 38 insertions, 26 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7f384bb62d8e..3cadee0a3508 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -487,14 +487,12 @@ struct mm_struct {
         /* numa_scan_seq prevents two threads setting pte_numa */
         int numa_scan_seq;
 #endif
-#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
         /*
          * An operation with batched TLB flushing is going on. Anything that
          * can move process memory needs to flush the TLB when moving a
          * PROT_NONE or PROT_NUMA mapped page.
          */
-        bool tlb_flush_pending;
-#endif
+        atomic_t tlb_flush_pending;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
         /* See flush_tlb_batched_pending() */
         bool tlb_flush_batched;
@@ -522,46 +520,60 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
         return mm->cpu_vm_mask_var;
 }
 
-#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION)
+struct mmu_gather;
+extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
+                                unsigned long start, unsigned long end);
+extern void tlb_finish_mmu(struct mmu_gather *tlb,
+                                unsigned long start, unsigned long end);
+
 /*
  * Memory barriers to keep this state in sync are graciously provided by
  * the page table locks, outside of which no page table modifications happen.
- * The barriers below prevent the compiler from re-ordering the instructions
- * around the memory barriers that are already present in the code.
+ * The barriers are used to ensure the order between tlb_flush_pending updates,
+ * which happen while the lock is not taken, and the PTE updates, which happen
+ * while the lock is taken, are serialized.
  */
 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;
+}
+
+/*
+ * Returns true if there are two above TLB batching threads in parallel.
+ */
+static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
+{
+        return atomic_read(&mm->tlb_flush_pending) > 1;
+}
+
+static inline void init_tlb_flush_pending(struct mm_struct *mm)
+{
+        atomic_set(&mm->tlb_flush_pending, 0);
 }
-static inline void set_tlb_flush_pending(struct mm_struct *mm)
+
+static inline void inc_tlb_flush_pending(struct mm_struct *mm)
 {
-        mm->tlb_flush_pending = true;
+        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)
-{
-        barrier();
-        mm->tlb_flush_pending = false;
-}
-#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 clear_tlb_flush_pending(struct mm_struct *mm)
+static inline void dec_tlb_flush_pending(struct mm_struct *mm)
 {
+        /*
+         * Guarantee that the tlb_flush_pending does not not leak into the
+         * critical section, since we must order the PTE change and changes to
+         * the pending TLB flush indication. We could have relied on TLB flush
+         * as a memory barrier, but this behavior is not clearly documented.
+         */
+        smp_mb__before_atomic();
+        atomic_dec(&mm->tlb_flush_pending);
 }
-#endif
 
 struct vm_fault;