Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Add 'cross-release' support to lockdep, which allows APIs like
   completions, where it's not the 'owner' who releases the lock, to be
   tracked. It's all activated automatically under
   CONFIG_PROVE_LOCKING=y.

 - Clean up (restructure) the x86 atomics op implementation to be more
   readable, in preparation of KASAN annotations. (Dmitry Vyukov)

 - Fix static keys (Paolo Bonzini)

 - Add killable versions of down_read() et al (Kirill Tkhai)

 - Rework and fix jump_label locking (Marc Zyngier, Paolo Bonzini)

 - Rework (and fix) tlb_flush_pending() barriers (Peter Zijlstra)

 - Remove smp_mb__before_spinlock() and convert its usages, introduce
   smp_mb__after_spinlock() (Peter Zijlstra)

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits)
  locking/lockdep/selftests: Fix mixed read-write ABBA tests
  sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK()
  acpi/nfit: Fix COMPLETION_INITIALIZER_ONSTACK() abuse
  locking/pvqspinlock: Relax cmpxchg's to improve performance on some architectures
  smp: Avoid using two cache lines for struct call_single_data
  locking/lockdep: Untangle xhlock history save/restore from task independence
  locking/refcounts, x86/asm: Disable CONFIG_ARCH_HAS_REFCOUNT for the time being
  futex: Remove duplicated code and fix undefined behaviour
  Documentation/locking/atomic: Finish the document...
  locking/lockdep: Fix workqueue crossrelease annotation
  workqueue/lockdep: 'Fix' flush_work() annotation
  locking/lockdep/selftests: Add mixed read-write ABBA tests
  mm, locking/barriers: Clarify tlb_flush_pending() barriers
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS truly non-interactive
  locking/lockdep: Explicitly initialize wq_barrier::done::map
  locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS
  locking/lockdep: Reword title of LOCKDEP_CROSSRELEASE config
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE part of CONFIG_PROVE_LOCKING
  locking/refcounts, x86/asm: Implement fast refcount overflow protection
  locking/lockdep: Fix the rollback and overwrite detection logic in crossrelease
  ...

1 files changed, 65 insertions, 30 deletions

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3cadee0a3508..57378c7cb5f8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -526,26 +526,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 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 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)
-{
-	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);
@@ -554,27 +534,82 @@ static inline void init_tlb_flush_pending(struct mm_struct *mm)
 static inline void inc_tlb_flush_pending(struct mm_struct *mm)
 {
 	atomic_inc(&mm->tlb_flush_pending);
-
 	/*
-	 * Guarantee that the tlb_flush_pending increase does not leak into the
-	 * critical section updating the page tables
+	 * The only time this value is relevant is when there are indeed pages
+	 * to flush. And we'll only flush pages after changing them, which
+	 * requires the PTL.
+	 *
+	 * So the ordering here is:
+	 *
+	 *	atomic_inc(&mm->tlb_flush_pending);
+	 *	spin_lock(&ptl);
+	 *	...
+	 *	set_pte_at();
+	 *	spin_unlock(&ptl);
+	 *
+	 *				spin_lock(&ptl)
+	 *				mm_tlb_flush_pending();
+	 *				....
+	 *				spin_unlock(&ptl);
+	 *
+	 *	flush_tlb_range();
+	 *	atomic_dec(&mm->tlb_flush_pending);
+	 *
+	 * Where the increment if constrained by the PTL unlock, it thus
+	 * ensures that the increment is visible if the PTE modification is
+	 * visible. After all, if there is no PTE modification, nobody cares
+	 * about TLB flushes either.
+	 *
+	 * This very much relies on users (mm_tlb_flush_pending() and
+	 * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and
+	 * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc
+	 * locks (PPC) the unlock of one doesn't order against the lock of
+	 * another PTL.
+	 *
+	 * The decrement is ordered by the flush_tlb_range(), such that
+	 * mm_tlb_flush_pending() will not return false unless all flushes have
+	 * completed.
 	 */
-	smp_mb__before_spinlock();
 }
 
-/* Clearing is done after a TLB flush, which also provides a barrier. */
 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.
+	 * See inc_tlb_flush_pending().
+	 *
+	 * This cannot be smp_mb__before_atomic() because smp_mb() simply does
+	 * not order against TLB invalidate completion, which is what we need.
+	 *
+	 * Therefore we must rely on tlb_flush_*() to guarantee order.
 	 */
-	smp_mb__before_atomic();
 	atomic_dec(&mm->tlb_flush_pending);
 }
 
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	/*
+	 * Must be called after having acquired the PTL; orders against that
+	 * PTLs release and therefore ensures that if we observe the modified
+	 * PTE we must also observe the increment from inc_tlb_flush_pending().
+	 *
+	 * That is, it only guarantees to return true if there is a flush
+	 * pending for _this_ PTL.
+	 */
+	return atomic_read(&mm->tlb_flush_pending);
+}
+
+static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
+{
+	/*
+	 * Similar to mm_tlb_flush_pending(), we must have acquired the PTL
+	 * for which there is a TLB flush pending in order to guarantee
+	 * we've seen both that PTE modification and the increment.
+	 *
+	 * (no requirement on actually still holding the PTL, that is irrelevant)
+	 */
+	return atomic_read(&mm->tlb_flush_pending) > 1;
+}
+
 struct vm_fault;
 
 struct vm_special_mapping {