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
  ...

38 files changed, 424 insertions, 558 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index 21d0089117fe..2520ca5b42eb 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -931,6 +931,18 @@ config STRICT_MODULE_RWX
 config ARCH_WANT_RELAX_ORDER
 	bool
 
+config ARCH_HAS_REFCOUNT
+	bool
+	help
+	  An architecture selects this when it has implemented refcount_t
+	  using open coded assembly primitives that provide an optimized
+	  refcount_t implementation, possibly at the expense of some full
+	  refcount state checks of CONFIG_REFCOUNT_FULL=y.
+
+	  The refcount overflow check behavior, however, must be retained.
+	  Catching overflows is the primary security concern for protecting
+	  against bugs in reference counts.
+
 config REFCOUNT_FULL
 	bool "Perform full reference count validation at the expense of speed"
 	help
diff --git a/arch/alpha/include/asm/futex.h b/arch/alpha/include/asm/futex.h
index fb01dfb760c2..05a70edd57b6 100644
--- a/arch/alpha/include/asm/futex.h
+++ b/arch/alpha/include/asm/futex.h
@@ -25,18 +25,10 @@
 	:	"r" (uaddr), "r"(oparg)				\
 	:	"memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -62,17 +54,9 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 54b54da6384c..11859287c52a 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -123,6 +123,8 @@ static inline void atomic_set(atomic_t *v, int i)
 	atomic_ops_unlock(flags);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 #endif
 
 /*
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 11e1b1f3acda..eb887dd13e74 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -73,20 +73,11 @@
 
 #endif
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
 #ifndef CONFIG_ARC_HAS_LLSC
 	preempt_disable();	/* to guarantee atomic r-m-w of futex op */
 #endif
@@ -118,30 +109,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	preempt_enable();
 #endif
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 6795368ad023..cc414382dab4 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -128,20 +128,10 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #endif /* !SMP */
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret, tmp;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 #ifndef CONFIG_SMP
 	preempt_disable();
 #endif
@@ -172,17 +162,9 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	preempt_enable();
 #endif
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index f32b42e8725d..5bb2fd4674e7 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -48,20 +48,10 @@ do {									\
 } while (0)
 
 static inline int
-futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (int)(encoded_op << 8) >> 20;
-	int cmparg = (int)(encoded_op << 20) >> 20;
 	int oldval = 0, ret, tmp;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1U << (oparg & 0x1f);
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 	pagefault_disable();
 
 	switch (op) {
@@ -91,17 +81,9 @@ futex_atomic_op_inuser(unsigned int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index f445bd7f2b9f..95ad7102b63c 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -310,14 +310,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	cpu_relax()
 #define arch_write_relax(lock)	cpu_relax()
 
-/*
- * Accesses appearing in program order before a spin_lock() operation
- * can be reordered with accesses inside the critical section, by virtue
- * of arch_spin_lock being constructed using acquire semantics.
- *
- * In cases where this is problematic (e.g. try_to_wake_up), an
- * smp_mb__before_spinlock() can restore the required ordering.
- */
-#define smp_mb__before_spinlock()	smp_mb()
+/* See include/linux/spinlock.h */
+#define smp_mb__after_spinlock()	smp_mb()
 
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/frv/include/asm/futex.h b/arch/frv/include/asm/futex.h
index 2e1da71e27a4..ab346f5f8820 100644
--- a/arch/frv/include/asm/futex.h
+++ b/arch/frv/include/asm/futex.h
@@ -7,7 +7,8 @@
 #include <asm/errno.h>
 #include <linux/uaccess.h>
 
-extern int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr);
+extern int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr);
 
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
diff --git a/arch/frv/kernel/futex.c b/arch/frv/kernel/futex.c
index d155ca9e5098..37f7b2bf7f73 100644
--- a/arch/frv/kernel/futex.c
+++ b/arch/frv/kernel/futex.c
@@ -186,20 +186,10 @@ static inline int atomic_futex_op_xchg_xor(int oparg, u32 __user *uaddr, int *_o
 /*
  * do the futex operations
  */
-int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 	pagefault_disable();
 
 	switch (op) {
@@ -225,18 +215,9 @@ int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS; break;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
 
 	return ret;
 
-} /* end futex_atomic_op_inuser() */
+} /* end arch_futex_atomic_op_inuser() */
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index a62ba368b27d..fb3dfb2a667e 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -42,6 +42,8 @@ static inline void atomic_set(atomic_t *v, int new)
 	);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 /**
  * atomic_read - reads a word, atomically
  * @v: pointer to atomic value
diff --git a/arch/hexagon/include/asm/futex.h b/arch/hexagon/include/asm/futex.h
index 7e597f8434da..c607b77c8215 100644
--- a/arch/hexagon/include/asm/futex.h
+++ b/arch/hexagon/include/asm/futex.h
@@ -31,18 +31,9 @@
 
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -72,30 +63,9 @@ futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/ia64/include/asm/futex.h b/arch/ia64/include/asm/futex.h
index 76acbcd5c060..6d67dc1eaf2b 100644
--- a/arch/ia64/include/asm/futex.h
+++ b/arch/ia64/include/asm/futex.h
@@ -45,18 +45,9 @@ do {									\
 } while (0)
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -84,17 +75,9 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index 6c1380a8a0d4..eee779f26cc4 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -37,6 +37,8 @@ static inline int atomic_set(atomic_t *v, int i)
 	return i;
 }
 
+#define atomic_set_release(v, i) atomic_set((v), (i))
+
 #define ATOMIC_OP(op, c_op)						\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
diff --git a/arch/microblaze/include/asm/futex.h b/arch/microblaze/include/asm/futex.h
index 01848f056f43..a9dad9e5e132 100644
--- a/arch/microblaze/include/asm/futex.h
+++ b/arch/microblaze/include/asm/futex.h
@@ -29,18 +29,9 @@
 })
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -66,30 +57,9 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h
index 1de190bdfb9c..a9e61ea54ca9 100644
--- a/arch/mips/include/asm/futex.h
+++ b/arch/mips/include/asm/futex.h
@@ -83,18 +83,9 @@
 }
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -125,17 +116,9 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 6bace7695788..c7cbddfcdc3b 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -648,12 +648,12 @@ EXPORT_SYMBOL(flush_tlb_one);
 #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
 
 static DEFINE_PER_CPU(atomic_t, tick_broadcast_count);
-static DEFINE_PER_CPU(struct call_single_data, tick_broadcast_csd);
+static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd);
 
 void tick_broadcast(const struct cpumask *mask)
 {
 	atomic_t *count;
-	struct call_single_data *csd;
+	call_single_data_t *csd;
 	int cpu;
 
 	for_each_cpu(cpu, mask) {
@@ -674,7 +674,7 @@ static void tick_broadcast_callee(void *info)
 
 static int __init tick_broadcast_init(void)
 {
-	struct call_single_data *csd;
+	call_single_data_t *csd;
 	int cpu;
 
 	for (cpu = 0; cpu < NR_CPUS; cpu++) {
diff --git a/arch/openrisc/include/asm/futex.h b/arch/openrisc/include/asm/futex.h
index 778087341977..8fed278a24b8 100644
--- a/arch/openrisc/include/asm/futex.h
+++ b/arch/openrisc/include/asm/futex.h
@@ -30,20 +30,10 @@
 })
 
 static inline int
-futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 	pagefault_disable();
 
 	switch (op) {
@@ -68,30 +58,9 @@ futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 5394b9c5f914..17b98a87e5e2 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -65,6 +65,8 @@ static __inline__ void atomic_set(atomic_t *v, int i)
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 static __inline__ int atomic_read(const atomic_t *v)
 {
 	return READ_ONCE((v)->counter);
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
index 0ba14300cd8e..c601aab2fb36 100644
--- a/arch/parisc/include/asm/futex.h
+++ b/arch/parisc/include/asm/futex.h
@@ -32,22 +32,12 @@ _futex_spin_unlock_irqrestore(u32 __user *uaddr, unsigned long int *flags)
 }
 
 static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr)
 {
 	unsigned long int flags;
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval, ret;
 	u32 tmp;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr)))
-		return -EFAULT;
-
 	_futex_spin_lock_irqsave(uaddr, &flags);
 	pagefault_disable();
 
@@ -85,17 +75,9 @@ out_pagefault_enable:
 	pagefault_enable();
 	_futex_spin_unlock_irqrestore(uaddr, &flags);
 
-	if (ret == 0) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index 25d42bd3f114..9c601adfc500 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -74,13 +74,6 @@ do {									\
 	___p1;								\
 })
 
-/*
- * This must resolve to hwsync on SMP for the context switch path.
- * See _switch, and core scheduler context switch memory ordering
- * comments.
- */
-#define smp_mb__before_spinlock()   smp_mb()
-
 #include <asm-generic/barrier.h>
 
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index eaada6c92344..719ed9b61ea7 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -29,18 +29,10 @@
 	: "b" (uaddr), "i" (-EFAULT), "r" (oparg) \
 	: "cr0", "memory")
 
-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -66,17 +58,9 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index d256e448ea49..edbe571bcc54 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -309,5 +309,8 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 #define arch_read_relax(lock)	__rw_yield(lock)
 #define arch_write_relax(lock)	__rw_yield(lock)
 
+/* See include/linux/spinlock.h */
+#define smp_mb__after_spinlock()   smp_mb()
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index a4811aa0304d..8f8eec9e1198 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -21,17 +21,12 @@
 		: "0" (-EFAULT), "d" (oparg), "a" (uaddr),		\
 		  "m" (*uaddr) : "cc");
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, newval, ret;
 
 	load_kernel_asce();
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
 
 	pagefault_disable();
 	switch (op) {
@@ -60,17 +55,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	}
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/sh/include/asm/futex.h b/arch/sh/include/asm/futex.h
index d0078747d308..8f8cf941a8cd 100644
--- a/arch/sh/include/asm/futex.h
+++ b/arch/sh/include/asm/futex.h
@@ -27,21 +27,12 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	return atomic_futex_op_cmpxchg_inatomic(uval, uaddr, oldval, newval);
 }
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	u32 oparg = (encoded_op << 8) >> 20;
-	u32 cmparg = (encoded_op << 20) >> 20;
 	u32 oldval, newval, prev;
 	int ret;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 	pagefault_disable();
 
 	do {
@@ -80,17 +71,8 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = ((int)oldval < (int)cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = ((int)oldval >= (int)cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = ((int)oldval <= (int)cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = ((int)oldval > (int)cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
 
 	return ret;
 }
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index ee3f11c43cda..7643e979e333 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -29,6 +29,8 @@ int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 #define atomic_read(v)          ACCESS_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
diff --git a/arch/sparc/include/asm/futex_64.h b/arch/sparc/include/asm/futex_64.h
index 4e899b0dabf7..1cfd89d92208 100644
--- a/arch/sparc/include/asm/futex_64.h
+++ b/arch/sparc/include/asm/futex_64.h
@@ -29,22 +29,14 @@
 	: "r" (uaddr), "r" (oparg), "i" (-EFAULT)	\
 	: "memory")
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret, tem;
 
-	if (unlikely(!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))))
-		return -EFAULT;
 	if (unlikely((((unsigned long) uaddr) & 0x3UL)))
 		return -EINVAL;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
 	pagefault_disable();
 
 	switch (op) {
@@ -69,17 +61,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index a93774255136..53a423e7cb92 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -101,6 +101,8 @@ static inline void atomic_set(atomic_t *v, int n)
 	_atomic_xchg(&v->counter, n);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 /* A 64bit atomic type */
 
 typedef struct {
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index e64a1b75fc38..83c1e639b411 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -106,12 +106,9 @@
 	lock = __atomic_hashed_lock((int __force *)uaddr)
 #endif
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int uninitialized_var(val), ret;
 
 	__futex_prolog();
@@ -119,12 +116,6 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	/* The 32-bit futex code makes this assumption, so validate it here. */
 	BUILD_BUG_ON(sizeof(atomic_t) != sizeof(int));
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 	pagefault_disable();
 	switch (op) {
 	case FUTEX_OP_SET:
@@ -148,30 +139,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 	}
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (val == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (val != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (val < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (val >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (val <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (val > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = val;
+
 	return ret;
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9c95aa417e9b..cce15191e9e9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -55,6 +55,8 @@ config X86
 	select ARCH_HAS_KCOV			if X86_64
 	select ARCH_HAS_MMIO_FLUSH
 	select ARCH_HAS_PMEM_API		if X86_64
+	# Causing hangs/crashes, see the commit that added this change for details.
+	select ARCH_HAS_REFCOUNT		if BROKEN
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 7a9df3beb89b..676ee5807d86 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -74,6 +74,9 @@
 # define _ASM_EXTABLE_EX(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
+# define _ASM_EXTABLE_REFCOUNT(from, to)			\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
+
 # define _ASM_NOKPROBE(entry)					\
 	.pushsection "_kprobe_blacklist","aw" ;			\
 	_ASM_ALIGN ;						\
@@ -123,6 +126,9 @@
 # define _ASM_EXTABLE_EX(from, to)				\
 	_ASM_EXTABLE_HANDLE(from, to, ex_handler_ext)
 
+# define _ASM_EXTABLE_REFCOUNT(from, to)			\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
+
 /* For C file, we already have NOKPROBE_SYMBOL macro */
 #endif
 
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 33380b871463..0874ebda3069 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -197,35 +197,56 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-#define ATOMIC_OP(op)							\
-static inline void atomic_##op(int i, atomic_t *v)			\
-{									\
-	asm volatile(LOCK_PREFIX #op"l %1,%0"				\
-			: "+m" (v->counter)				\
-			: "ir" (i)					\
-			: "memory");					\
+static inline void atomic_and(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "andl %1,%0"
+			: "+m" (v->counter)
+			: "ir" (i)
+			: "memory");
+}
+
+static inline int atomic_fetch_and(int i, atomic_t *v)
+{
+	int val = atomic_read(v);
+
+	do { } while (!atomic_try_cmpxchg(v, &val, val & i));
+
+	return val;
 }
 
-#define ATOMIC_FETCH_OP(op, c_op)					\
-static inline int atomic_fetch_##op(int i, atomic_t *v)			\
-{									\
-	int val = atomic_read(v);					\
-	do {								\
-	} while (!atomic_try_cmpxchg(v, &val, val c_op i));		\
-	return val;							\
+static inline void atomic_or(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "orl %1,%0"
+			: "+m" (v->counter)
+			: "ir" (i)
+			: "memory");
 }
 
-#define ATOMIC_OPS(op, c_op)						\
-	ATOMIC_OP(op)							\
-	ATOMIC_FETCH_OP(op, c_op)
+static inline int atomic_fetch_or(int i, atomic_t *v)
+{
+	int val = atomic_read(v);
 
-ATOMIC_OPS(and, &)
-ATOMIC_OPS(or , |)
-ATOMIC_OPS(xor, ^)
+	do { } while (!atomic_try_cmpxchg(v, &val, val | i));
 
-#undef ATOMIC_OPS
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP
+	return val;
+}
+
+static inline void atomic_xor(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "xorl %1,%0"
+			: "+m" (v->counter)
+			: "ir" (i)
+			: "memory");
+}
+
+static inline int atomic_fetch_xor(int i, atomic_t *v)
+{
+	int val = atomic_read(v);
+
+	do { } while (!atomic_try_cmpxchg(v, &val, val ^ i));
+
+	return val;
+}
 
 /**
  * __atomic_add_unless - add unless the number is already a given value
@@ -239,10 +260,12 @@ ATOMIC_OPS(xor, ^)
 static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c = atomic_read(v);
+
 	do {
 		if (unlikely(c == u))
 			break;
 	} while (!atomic_try_cmpxchg(v, &c, c + a));
+
 	return c;
 }
 
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 71d7705fb303..9e206f31ce2a 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -312,37 +312,70 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
-#define ATOMIC64_OP(op, c_op)						\
-static inline void atomic64_##op(long long i, atomic64_t *v)		\
-{									\
-	long long old, c = 0;						\
-	while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c)		\
-		c = old;						\
+static inline void atomic64_and(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
+
+	while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+		c = old;
 }
 
-#define ATOMIC64_FETCH_OP(op, c_op)					\
-static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
-{									\
-	long long old, c = 0;						\
-	while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c)		\
-		c = old;						\
-	return old;							\
+static inline long long atomic64_fetch_and(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
+
+	while ((old = atomic64_cmpxchg(v, c, c & i)) != c)
+		c = old;
+
+	return old;
 }
 
-ATOMIC64_FETCH_OP(add, +)
+static inline void atomic64_or(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
 
-#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
+	while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+		c = old;
+}
+
+static inline long long atomic64_fetch_or(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
+
+	while ((old = atomic64_cmpxchg(v, c, c | i)) != c)
+		c = old;
+
+	return old;
+}
 
-#define ATOMIC64_OPS(op, c_op)						\
-	ATOMIC64_OP(op, c_op)						\
-	ATOMIC64_FETCH_OP(op, c_op)
+static inline void atomic64_xor(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
+
+	while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+		c = old;
+}
 
-ATOMIC64_OPS(and, &)
-ATOMIC64_OPS(or, |)
-ATOMIC64_OPS(xor, ^)
+static inline long long atomic64_fetch_xor(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
+
+	while ((old = atomic64_cmpxchg(v, c, c ^ i)) != c)
+		c = old;
+
+	return old;
+}
 
-#undef ATOMIC64_OPS
-#undef ATOMIC64_FETCH_OP
-#undef ATOMIC64_OP
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+{
+	long long old, c = 0;
+
+	while ((old = atomic64_cmpxchg(v, c, c + i)) != c)
+		c = old;
+
+	return old;
+}
+
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6189a433c9a9..5d9de36a2f04 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -177,7 +177,7 @@ static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
 }
 
 #define atomic64_try_cmpxchg atomic64_try_cmpxchg
-static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, long *old, long new)
+static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
@@ -198,7 +198,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  */
 static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
 {
-	long c = atomic64_read(v);
+	s64 c = atomic64_read(v);
 	do {
 		if (unlikely(c == u))
 			return false;
@@ -217,7 +217,7 @@ static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
  */
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
-	long dec, c = atomic64_read(v);
+	s64 dec, c = atomic64_read(v);
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
@@ -226,34 +226,55 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
-#define ATOMIC64_OP(op)							\
-static inline void atomic64_##op(long i, atomic64_t *v)			\
-{									\
-	asm volatile(LOCK_PREFIX #op"q %1,%0"				\
-			: "+m" (v->counter)				\
-			: "er" (i)					\
-			: "memory");					\
+static inline void atomic64_and(long i, atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "andq %1,%0"
+			: "+m" (v->counter)
+			: "er" (i)
+			: "memory");
 }
 
-#define ATOMIC64_FETCH_OP(op, c_op)					\
-static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
-{									\
-	long val = atomic64_read(v);					\
-	do {								\
-	} while (!atomic64_try_cmpxchg(v, &val, val c_op i));		\
-	return val;							\
+static inline long atomic64_fetch_and(long i, atomic64_t *v)
+{
+	s64 val = atomic64_read(v);
+
+	do {
+	} while (!atomic64_try_cmpxchg(v, &val, val & i));
+	return val;
 }
 
-#define ATOMIC64_OPS(op, c_op)						\
-	ATOMIC64_OP(op)							\
-	ATOMIC64_FETCH_OP(op, c_op)
+static inline void atomic64_or(long i, atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "orq %1,%0"
+			: "+m" (v->counter)
+			: "er" (i)
+			: "memory");
+}
 
-ATOMIC64_OPS(and, &)
-ATOMIC64_OPS(or, |)
-ATOMIC64_OPS(xor, ^)
+static inline long atomic64_fetch_or(long i, atomic64_t *v)
+{
+	s64 val = atomic64_read(v);
 
-#undef ATOMIC64_OPS
-#undef ATOMIC64_FETCH_OP
-#undef ATOMIC64_OP
+	do {
+	} while (!atomic64_try_cmpxchg(v, &val, val | i));
+	return val;
+}
+
+static inline void atomic64_xor(long i, atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "xorq %1,%0"
+			: "+m" (v->counter)
+			: "er" (i)
+			: "memory");
+}
+
+static inline long atomic64_fetch_xor(long i, atomic64_t *v)
+{
+	s64 val = atomic64_read(v);
+
+	do {
+	} while (!atomic64_try_cmpxchg(v, &val, val ^ i));
+	return val;
+}
 
 #endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d90296d061e8..b5069e802d5c 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -157,7 +157,7 @@ extern void __add_wrong_size(void)
 #define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock)		\
 ({									\
 	bool success;							\
-	__typeof__(_ptr) _old = (_pold);				\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
 	__typeof__(*(_ptr)) __old = *_old;				\
 	__typeof__(*(_ptr)) __new = (_new);				\
 	switch (size) {							\
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index b4c1f5453436..f4dc9b63bdda 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -41,20 +41,11 @@
 		       "+m" (*uaddr), "=&r" (tem)		\
 		     : "r" (oparg), "i" (-EFAULT), "1" (0))
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret, tem;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
-
 	pagefault_disable();
 
 	switch (op) {
@@ -80,30 +71,9 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
new file mode 100644
index 000000000000..ff871210b9f2
--- /dev/null
+++ b/arch/x86/include/asm/refcount.h
@@ -0,0 +1,109 @@
+#ifndef __ASM_X86_REFCOUNT_H
+#define __ASM_X86_REFCOUNT_H
+/*
+ * x86-specific implementation of refcount_t. Based on PAX_REFCOUNT from
+ * PaX/grsecurity.
+ */
+#include <linux/refcount.h>
+
+/*
+ * This is the first portion of the refcount error handling, which lives in
+ * .text.unlikely, and is jumped to from the CPU flag check (in the
+ * following macros). This saves the refcount value location into CX for
+ * the exception handler to use (in mm/extable.c), and then triggers the
+ * central refcount exception. The fixup address for the exception points
+ * back to the regular execution flow in .text.
+ */
+#define _REFCOUNT_EXCEPTION				\
+	".pushsection .text.unlikely\n"			\
+	"111:\tlea %[counter], %%" _ASM_CX "\n"		\
+	"112:\t" ASM_UD0 "\n"				\
+	ASM_UNREACHABLE					\
+	".popsection\n"					\
+	"113:\n"					\
+	_ASM_EXTABLE_REFCOUNT(112b, 113b)
+
+/* Trigger refcount exception if refcount result is negative. */
+#define REFCOUNT_CHECK_LT_ZERO				\
+	"js 111f\n\t"					\
+	_REFCOUNT_EXCEPTION
+
+/* Trigger refcount exception if refcount result is zero or negative. */
+#define REFCOUNT_CHECK_LE_ZERO				\
+	"jz 111f\n\t"					\
+	REFCOUNT_CHECK_LT_ZERO
+
+/* Trigger refcount exception unconditionally. */
+#define REFCOUNT_ERROR					\
+	"jmp 111f\n\t"					\
+	_REFCOUNT_EXCEPTION
+
+static __always_inline void refcount_add(unsigned int i, refcount_t *r)
+{
+	asm volatile(LOCK_PREFIX "addl %1,%0\n\t"
+		REFCOUNT_CHECK_LT_ZERO
+		: [counter] "+m" (r->refs.counter)
+		: "ir" (i)
+		: "cc", "cx");
+}
+
+static __always_inline void refcount_inc(refcount_t *r)
+{
+	asm volatile(LOCK_PREFIX "incl %0\n\t"
+		REFCOUNT_CHECK_LT_ZERO
+		: [counter] "+m" (r->refs.counter)
+		: : "cc", "cx");
+}
+
+static __always_inline void refcount_dec(refcount_t *r)
+{
+	asm volatile(LOCK_PREFIX "decl %0\n\t"
+		REFCOUNT_CHECK_LE_ZERO
+		: [counter] "+m" (r->refs.counter)
+		: : "cc", "cx");
+}
+
+static __always_inline __must_check
+bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+{
+	GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO,
+				  r->refs.counter, "er", i, "%0", e);
+}
+
+static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r)
+{
+	GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", REFCOUNT_CHECK_LT_ZERO,
+				 r->refs.counter, "%0", e);
+}
+
+static __always_inline __must_check
+bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+{
+	int c, result;
+
+	c = atomic_read(&(r->refs));
+	do {
+		if (unlikely(c == 0))
+			return false;
+
+		result = c + i;
+
+		/* Did we try to increment from/to an undesirable state? */
+		if (unlikely(c < 0 || c == INT_MAX || result < c)) {
+			asm volatile(REFCOUNT_ERROR
+				     : : [counter] "m" (r->refs.counter)
+				     : "cc", "cx");
+			break;
+		}
+
+	} while (!atomic_try_cmpxchg(&(r->refs), &c, result));
+
+	return c != 0;
+}
+
+static __always_inline __must_check bool refcount_inc_not_zero(refcount_t *r)
+{
+	return refcount_add_not_zero(1, r);
+}
+
+#endif
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index fb2ddcdf7c73..c076f710de4c 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -36,6 +36,48 @@ bool ex_handler_fault(const struct exception_table_entry *fixup,
 }
 EXPORT_SYMBOL_GPL(ex_handler_fault);
 
+/*
+ * Handler for UD0 exception following a failed test against the
+ * result of a refcount inc/dec/add/sub.
+ */
+bool ex_handler_refcount(const struct exception_table_entry *fixup,
+			 struct pt_regs *regs, int trapnr)
+{
+	/* First unconditionally saturate the refcount. */
+	*(int *)regs->cx = INT_MIN / 2;
+
+	/*
+	 * Strictly speaking, this reports the fixup destination, not
+	 * the fault location, and not the actually overflowing
+	 * instruction, which is the instruction before the "js", but
+	 * since that instruction could be a variety of lengths, just
+	 * report the location after the overflow, which should be close
+	 * enough for finding the overflow, as it's at least back in
+	 * the function, having returned from .text.unlikely.
+	 */
+	regs->ip = ex_fixup_addr(fixup);
+
+	/*
+	 * This function has been called because either a negative refcount
+	 * value was seen by any of the refcount functions, or a zero
+	 * refcount value was seen by refcount_dec().
+	 *
+	 * If we crossed from INT_MAX to INT_MIN, OF (Overflow Flag: result
+	 * wrapped around) will be set. Additionally, seeing the refcount
+	 * reach 0 will set ZF (Zero Flag: result was zero). In each of
+	 * these cases we want a report, since it's a boundary condition.
+	 *
+	 */
+	if (regs->flags & (X86_EFLAGS_OF | X86_EFLAGS_ZF)) {
+		bool zero = regs->flags & X86_EFLAGS_ZF;
+
+		refcount_error_report(regs, zero ? "hit zero" : "overflow");
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_refcount);
+
 bool ex_handler_ext(const struct exception_table_entry *fixup,
 		   struct pt_regs *regs, int trapnr)
 {
diff --git a/arch/xtensa/include/asm/futex.h b/arch/xtensa/include/asm/futex.h
index b39531babec0..eaaf1ebcc7a4 100644
--- a/arch/xtensa/include/asm/futex.h
+++ b/arch/xtensa/include/asm/futex.h
@@ -44,18 +44,10 @@
 	: "r" (uaddr), "I" (-EFAULT), "r" (oparg)	\
 	: "memory")
 
-static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
+		u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 #if !XCHAL_HAVE_S32C1I
 	return -ENOSYS;
@@ -89,19 +81,10 @@ static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (ret)
-		return ret;
+	if (!ret)
+		*oval = oldval;
 
-	switch (cmp) {
-	case FUTEX_OP_CMP_EQ: return (oldval == cmparg);
-	case FUTEX_OP_CMP_NE: return (oldval != cmparg);
-	case FUTEX_OP_CMP_LT: return (oldval < cmparg);
-	case FUTEX_OP_CMP_GE: return (oldval >= cmparg);
-	case FUTEX_OP_CMP_LE: return (oldval <= cmparg);
-	case FUTEX_OP_CMP_GT: return (oldval > cmparg);
-	}
-
-	return -ENOSYS;
+	return ret;
 }
 
 static inline int