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
  ...

Documentation/atomic_bitops.txt

@@ -0,0 +1,66 @@
+
+On atomic bitops.
+
+
+While our bitmap_{}() functions are non-atomic, we have a number of operations
+operating on single bits in a bitmap that are atomic.
+
+
+API
+---
+
+The single bit operations are:
+
+Non-RMW ops:
+
+  test_bit()
+
+RMW atomic operations without return value:
+
+  {set,clear,change}_bit()
+  clear_bit_unlock()
+
+RMW atomic operations with return value:
+
+  test_and_{set,clear,change}_bit()
+  test_and_set_bit_lock()
+
+Barriers:
+
+  smp_mb__{before,after}_atomic()
+
+
+All RMW atomic operations have a '__' prefixed variant which is non-atomic.
+
+
+SEMANTICS
+---------
+
+Non-atomic ops:
+
+In particular __clear_bit_unlock() suffers the same issue as atomic_set(),
+which is why the generic version maps to clear_bit_unlock(), see atomic_t.txt.
+
+
+RMW ops:
+
+The test_and_{}_bit() operations return the original value of the bit.
+
+
+ORDERING
+--------
+
+Like with atomic_t, the rule of thumb is:
+
+ - non-RMW operations are unordered;
+
+ - RMW operations that have no return value are unordered;
+
+ - RMW operations that have a return value are fully ordered.
+
+Except for test_and_set_bit_lock() which has ACQUIRE semantics and
+clear_bit_unlock() which has RELEASE semantics.
+
+Since a platform only has a single means of achieving atomic operations
+the same barriers as for atomic_t are used, see atomic_t.txt.
+

Documentation/atomic_t.txt

@@ -0,0 +1,242 @@
+
+On atomic types (atomic_t atomic64_t and atomic_long_t).
+
+The atomic type provides an interface to the architecture's means of atomic
+RMW operations between CPUs (atomic operations on MMIO are not supported and
+can lead to fatal traps on some platforms).
+
+API
+---
+
+The 'full' API consists of (atomic64_ and atomic_long_ prefixes omitted for
+brevity):
+
+Non-RMW ops:
+
+  atomic_read(), atomic_set()
+  atomic_read_acquire(), atomic_set_release()
+
+
+RMW atomic operations:
+
+Arithmetic:
+
+  atomic_{add,sub,inc,dec}()
+  atomic_{add,sub,inc,dec}_return{,_relaxed,_acquire,_release}()
+  atomic_fetch_{add,sub,inc,dec}{,_relaxed,_acquire,_release}()
+
+
+Bitwise:
+
+  atomic_{and,or,xor,andnot}()
+  atomic_fetch_{and,or,xor,andnot}{,_relaxed,_acquire,_release}()
+
+
+Swap:
+
+  atomic_xchg{,_relaxed,_acquire,_release}()
+  atomic_cmpxchg{,_relaxed,_acquire,_release}()
+  atomic_try_cmpxchg{,_relaxed,_acquire,_release}()
+
+
+Reference count (but please see refcount_t):
+
+  atomic_add_unless(), atomic_inc_not_zero()
+  atomic_sub_and_test(), atomic_dec_and_test()
+
+
+Misc:
+
+  atomic_inc_and_test(), atomic_add_negative()
+  atomic_dec_unless_positive(), atomic_inc_unless_negative()
+
+
+Barriers:
+
+  smp_mb__{before,after}_atomic()
+
+
+
+SEMANTICS
+---------
+
+Non-RMW ops:
+
+The non-RMW ops are (typically) regular LOADs and STOREs and are canonically
+implemented using READ_ONCE(), WRITE_ONCE(), smp_load_acquire() and
+smp_store_release() respectively.
+
+The one detail to this is that atomic_set{}() should be observable to the RMW
+ops. That is:
+
+  C atomic-set
+
+  {
+    atomic_set(v, 1);
+  }
+
+  P1(atomic_t *v)
+  {
+    atomic_add_unless(v, 1, 0);
+  }
+
+  P2(atomic_t *v)
+  {
+    atomic_set(v, 0);
+  }
+
+  exists
+  (v=2)
+
+In this case we would expect the atomic_set() from CPU1 to either happen
+before the atomic_add_unless(), in which case that latter one would no-op, or
+_after_ in which case we'd overwrite its result. In no case is "2" a valid
+outcome.
+
+This is typically true on 'normal' platforms, where a regular competing STORE
+will invalidate a LL/SC or fail a CMPXCHG.
+
+The obvious case where this is not so is when we need to implement atomic ops
+with a lock:
+
+  CPU0						CPU1
+
+  atomic_add_unless(v, 1, 0);
+    lock();
+    ret = READ_ONCE(v->counter); // == 1
+						atomic_set(v, 0);
+    if (ret != u)				  WRITE_ONCE(v->counter, 0);
+      WRITE_ONCE(v->counter, ret + 1);
+    unlock();
+
+the typical solution is to then implement atomic_set{}() with atomic_xchg().
+
+
+RMW ops:
+
+These come in various forms:
+
+ - plain operations without return value: atomic_{}()
+
+ - operations which return the modified value: atomic_{}_return()
+
+   these are limited to the arithmetic operations because those are
+   reversible. Bitops are irreversible and therefore the modified value
+   is of dubious utility.
+
+ - operations which return the original value: atomic_fetch_{}()
+
+ - swap operations: xchg(), cmpxchg() and try_cmpxchg()
+
+ - misc; the special purpose operations that are commonly used and would,
+   given the interface, normally be implemented using (try_)cmpxchg loops but
+   are time critical and can, (typically) on LL/SC architectures, be more
+   efficiently implemented.
+
+All these operations are SMP atomic; that is, the operations (for a single
+atomic variable) can be fully ordered and no intermediate state is lost or
+visible.
+
+
+ORDERING  (go read memory-barriers.txt first)
+--------
+
+The rule of thumb:
+
+ - non-RMW operations are unordered;
+
+ - RMW operations that have no return value are unordered;
+
+ - RMW operations that have a return value are fully ordered;
+
+ - RMW operations that are conditional are unordered on FAILURE,
+   otherwise the above rules apply.
+
+Except of course when an operation has an explicit ordering like:
+
+ {}_relaxed: unordered
+ {}_acquire: the R of the RMW (or atomic_read) is an ACQUIRE
+ {}_release: the W of the RMW (or atomic_set)  is a  RELEASE
+
+Where 'unordered' is against other memory locations. Address dependencies are
+not defeated.
+
+Fully ordered primitives are ordered against everything prior and everything
+subsequent. Therefore a fully ordered primitive is like having an smp_mb()
+before and an smp_mb() after the primitive.
+
+
+The barriers:
+
+  smp_mb__{before,after}_atomic()
+
+only apply to the RMW ops and can be used to augment/upgrade the ordering
+inherent to the used atomic op. These barriers provide a full smp_mb().
+
+These helper barriers exist because architectures have varying implicit
+ordering on their SMP atomic primitives. For example our TSO architectures
+provide full ordered atomics and these barriers are no-ops.
+
+Thus:
+
+  atomic_fetch_add();
+
+is equivalent to:
+
+  smp_mb__before_atomic();
+  atomic_fetch_add_relaxed();
+  smp_mb__after_atomic();
+
+However the atomic_fetch_add() might be implemented more efficiently.
+
+Further, while something like:
+
+  smp_mb__before_atomic();
+  atomic_dec(&X);
+
+is a 'typical' RELEASE pattern, the barrier is strictly stronger than
+a RELEASE. Similarly for something like:
+
+  atomic_inc(&X);
+  smp_mb__after_atomic();
+
+is an ACQUIRE pattern (though very much not typical), but again the barrier is
+strictly stronger than ACQUIRE. As illustrated:
+
+  C strong-acquire
+
+  {
+  }
+
+  P1(int *x, atomic_t *y)
+  {
+    r0 = READ_ONCE(*x);
+    smp_rmb();
+    r1 = atomic_read(y);
+  }
+
+  P2(int *x, atomic_t *y)
+  {
+    atomic_inc(y);
+    smp_mb__after_atomic();
+    WRITE_ONCE(*x, 1);
+  }
+
+  exists
+  (r0=1 /\ r1=0)
+
+This should not happen; but a hypothetical atomic_inc_acquire() --
+(void)atomic_fetch_inc_acquire() for instance -- would allow the outcome,
+since then:
+
+  P1			P2
+
+			t = LL.acq *y (0)
+			t++;
+			*x = 1;
+  r0 = *x (1)
+  RMB
+  r1 = *y (0)
+			SC *y, t;
+
+is allowed.

Documentation/memory-barriers.txt

@@ -498,11 +498,11 @@ And a couple of implicit varieties:
      This means that ACQUIRE acts as a minimal "acquire" operation and
      RELEASE acts as a minimal "release" operation.
 
-A subset of the atomic operations described in core-api/atomic_ops.rst have
-ACQUIRE and RELEASE variants in addition to fully-ordered and relaxed (no
-barrier semantics) definitions.  For compound atomics performing both a load
-and a store, ACQUIRE semantics apply only to the load and RELEASE semantics
-apply only to the store portion of the operation.
+A subset of the atomic operations described in atomic_t.txt have ACQUIRE and
+RELEASE variants in addition to fully-ordered and relaxed (no barrier
+semantics) definitions.  For compound atomics performing both a load and a
+store, ACQUIRE semantics apply only to the load and RELEASE semantics apply
+only to the store portion of the operation.
 
 Memory barriers are only required where there's a possibility of interaction
 between two CPUs or between a CPU and a device.  If it can be guaranteed that
@@ -1883,8 +1883,7 @@ There are some more advanced barrier functions:
      This makes sure that the death mark on the object is perceived to be set
      *before* the reference counter is decremented.
 
-     See Documentation/core-api/atomic_ops.rst for more information.  See the
-     "Atomic operations" subsection for information on where to use these.
+     See Documentation/atomic_{t,bitops}.txt for more information.
 
 
  (*) lockless_dereference();
@@ -1989,10 +1988,7 @@ for each construct.  These operations all imply certain barriers:
      ACQUIRE operation has completed.
 
      Memory operations issued before the ACQUIRE may be completed after
-     the ACQUIRE operation has completed.  An smp_mb__before_spinlock(),
-     combined with a following ACQUIRE, orders prior stores against
-     subsequent loads and stores.  Note that this is weaker than smp_mb()!
-     The smp_mb__before_spinlock() primitive is free on many architectures.
+     the ACQUIRE operation has completed.
 
  (2) RELEASE operation implication:
 
@@ -2510,88 +2506,7 @@ operations are noted specially as some of them imply full memory barriers and
 some don't, but they're very heavily relied on as a group throughout the
 kernel.
 
-Any atomic operation that modifies some state in memory and returns information
-about the state (old or new) implies an SMP-conditional general memory barrier
-(smp_mb()) on each side of the actual operation (with the exception of
-explicit lock operations, described later).  These include:
-
-	xchg();
-	atomic_xchg();			atomic_long_xchg();
-	atomic_inc_return();		atomic_long_inc_return();
-	atomic_dec_return();		atomic_long_dec_return();
-	atomic_add_return();		atomic_long_add_return();
-	atomic_sub_return();		atomic_long_sub_return();
-	atomic_inc_and_test();		atomic_long_inc_and_test();
-	atomic_dec_and_test();		atomic_long_dec_and_test();
-	atomic_sub_and_test();		atomic_long_sub_and_test();
-	atomic_add_negative();		atomic_long_add_negative();
-	test_and_set_bit();
-	test_and_clear_bit();
-	test_and_change_bit();
-
-	/* when succeeds */
-	cmpxchg();
-	atomic_cmpxchg();		atomic_long_cmpxchg();
-	atomic_add_unless();		atomic_long_add_unless();
-
-These are used for such things as implementing ACQUIRE-class and RELEASE-class
-operations and adjusting reference counters towards object destruction, and as
-such the implicit memory barrier effects are necessary.
-
-
-The following operations are potential problems as they do _not_ imply memory
-barriers, but might be used for implementing such things as RELEASE-class
-operations:
-
-	atomic_set();
-	set_bit();
-	clear_bit();
-	change_bit();
-
-With these the appropriate explicit memory barrier should be used if necessary
-(smp_mb__before_atomic() for instance).
-
-
-The following also do _not_ imply memory barriers, and so may require explicit
-memory barriers under some circumstances (smp_mb__before_atomic() for
-instance):
-
-	atomic_add();
-	atomic_sub();
-	atomic_inc();
-	atomic_dec();
-
-If they're used for statistics generation, then they probably don't need memory
-barriers, unless there's a coupling between statistical data.
-
-If they're used for reference counting on an object to control its lifetime,
-they probably don't need memory barriers because either the reference count
-will be adjusted inside a locked section, or the caller will already hold
-sufficient references to make the lock, and thus a memory barrier unnecessary.
-
-If they're used for constructing a lock of some description, then they probably
-do need memory barriers as a lock primitive generally has to do things in a
-specific order.
-
-Basically, each usage case has to be carefully considered as to whether memory
-barriers are needed or not.
-
-The following operations are special locking primitives:
-
-	test_and_set_bit_lock();
-	clear_bit_unlock();
-	__clear_bit_unlock();
-
-These implement ACQUIRE-class and RELEASE-class operations.  These should be
-used in preference to other operations when implementing locking primitives,
-because their implementations can be optimised on many architectures.
-
-[!] Note that special memory barrier primitives are available for these
-situations because on some CPUs the atomic instructions used imply full memory
-barriers, and so barrier instructions are superfluous in conjunction with them,
-and in such cases the special barrier primitives will be no-ops.
-
-See Documentation/core-api/atomic_ops.rst for more information.
+See Documentation/atomic_t.txt for more information.
 
 
 ACCESSING DEVICES

Documentation/static-keys.txt

@@ -149,6 +149,26 @@ static_branch_inc(), will change the branch back to true. Likewise, if the
 key is initialized false, a 'static_branch_inc()', will change the branch to
 true. And then a 'static_branch_dec()', will again make the branch false.
 
+The state and the reference count can be retrieved with 'static_key_enabled()'
+and 'static_key_count()'.  In general, if you use these functions, they
+should be protected with the same mutex used around the enable/disable
+or increment/decrement function.
+
+Note that switching branches results in some locks being taken,
+particularly the CPU hotplug lock (in order to avoid races against
+CPUs being brought in the kernel whilst the kernel is getting
+patched). Calling the static key API from within a hotplug notifier is
+thus a sure deadlock recipe. In order to still allow use of the
+functionnality, the following functions are provided:
+
+	static_key_enable_cpuslocked()
+	static_key_disable_cpuslocked()
+	static_branch_enable_cpuslocked()
+	static_branch_disable_cpuslocked()
+
+These functions are *not* general purpose, and must only be used when
+you really know that you're in the above context, and no other.
+
 Where an array of keys is required, it can be defined as::
 
 	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);

Documentation/translations/ko_KR/memory-barriers.txt

@@ -1956,10 +1956,7 @@ MMIO 쓰기 배리어
      뒤에 완료됩니다.
 
      ACQUIRE 앞에서 요청된 메모리 오퍼레이션은 ACQUIRE 오퍼레이션이 완료된 후에
-     완료될 수 있습니다.  smp_mb__before_spinlock() 뒤에 ACQUIRE 가 실행되는
-     코드 블록은 블록 앞의 스토어를 블록 뒤의 로드와 스토어에 대해 순서
-     맞춥니다.  이건 smp_mb() 보다 완화된 것임을 기억하세요!  많은 아키텍쳐에서
-     smp_mb__before_spinlock() 은 사실 아무일도 하지 않습니다.
+     완료될 수 있습니다.
 
  (2) RELEASE 오퍼레이션의 영향:
 

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

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;
 }
 

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
 
 /*

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;
 }
 

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;
 }
 

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;
 }
 

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 */

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,

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() */

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

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;
 }
 

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;
 }
 

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)			\
 {									\

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;
 }