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

Pull locking and atomic updates from Ingo Molnar:
 "Main changes in this cycle are:

   - Extend atomic primitives with coherent logic op primitives
     (atomic_{or,and,xor}()) and deprecate the old partial APIs
     (atomic_{set,clear}_mask())

     The old ops were incoherent with incompatible signatures across
     architectures and with incomplete support.  Now every architecture
     supports the primitives consistently (by Peter Zijlstra)

   - Generic support for 'relaxed atomics':

       - _acquire/release/relaxed() flavours of xchg(), cmpxchg() and {add,sub}_return()
       - atomic_read_acquire()
       - atomic_set_release()

     This came out of porting qwrlock code to arm64 (by Will Deacon)

   - Clean up the fragile static_key APIs that were causing repeat bugs,
     by introducing a new one:

       DEFINE_STATIC_KEY_TRUE(name);
       DEFINE_STATIC_KEY_FALSE(name);

     which define a key of different types with an initial true/false
     value.

     Then allow:

       static_branch_likely()
       static_branch_unlikely()

     to take a key of either type and emit the right instruction for the
     case.  To be able to know the 'type' of the static key we encode it
     in the jump entry (by Peter Zijlstra)

   - Static key self-tests (by Jason Baron)

   - qrwlock optimizations (by Waiman Long)

   - small futex enhancements (by Davidlohr Bueso)

   - ... and misc other changes"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  jump_label/x86: Work around asm build bug on older/backported GCCs
  locking, ARM, atomics: Define our SMP atomics in terms of _relaxed() operations
  locking, include/llist: Use linux/atomic.h instead of asm/cmpxchg.h
  locking/qrwlock: Make use of _{acquire|release|relaxed}() atomics
  locking/qrwlock: Implement queue_write_unlock() using smp_store_release()
  locking/lockref: Remove homebrew cmpxchg64_relaxed() macro definition
  locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'
  locking, asm-generic: Rework atomic-long.h to avoid bulk code duplication
  locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations
  locking, compiler.h: Cast away attributes in the WRITE_ONCE() magic
  locking/static_keys: Make verify_keys() static
  jump label, locking/static_keys: Update docs
  locking/static_keys: Provide a selftest
  jump_label: Provide a self-test
  s390/uaccess, locking/static_keys: employ static_branch_likely()
  x86, tsc, locking/static_keys: Employ static_branch_likely()
  locking/static_keys: Add selftest
  locking/static_keys: Add a new static_key interface
  locking/static_keys: Rework update logic
  locking/static_keys: Add static_key_{en,dis}able() helpers
  ...

3 files changed, 43 insertions, 21 deletions

diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index adbe3802e377..117fa5c921c1 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -27,6 +27,7 @@
 #define __ATOMIC_OR	"lao"
 #define __ATOMIC_AND	"lan"
 #define __ATOMIC_ADD	"laa"
+#define __ATOMIC_XOR	"lax"
 #define __ATOMIC_BARRIER "bcr	14,0\n"
 
 #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -49,6 +50,7 @@
 #define __ATOMIC_OR	"or"
 #define __ATOMIC_AND	"nr"
 #define __ATOMIC_ADD	"ar"
+#define __ATOMIC_XOR	"xr"
 #define __ATOMIC_BARRIER "\n"
 
 #define __ATOMIC_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -118,15 +120,17 @@ static inline void atomic_add(int i, atomic_t *v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 #define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-	__ATOMIC_LOOP(v, ~mask, __ATOMIC_AND, __ATOMIC_NO_BARRIER);
+#define ATOMIC_OP(op, OP)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__ATOMIC_LOOP(v, i, __ATOMIC_##OP, __ATOMIC_NO_BARRIER);	\
 }
 
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-	__ATOMIC_LOOP(v, mask, __ATOMIC_OR, __ATOMIC_NO_BARRIER);
-}
+ATOMIC_OP(and, AND)
+ATOMIC_OP(or, OR)
+ATOMIC_OP(xor, XOR)
+
+#undef ATOMIC_OP
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
@@ -167,6 +171,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"laog"
 #define __ATOMIC64_AND	"lang"
 #define __ATOMIC64_ADD	"laag"
+#define __ATOMIC64_XOR	"laxg"
 #define __ATOMIC64_BARRIER "bcr	14,0\n"
 
 #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -189,6 +194,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define __ATOMIC64_OR	"ogr"
 #define __ATOMIC64_AND	"ngr"
 #define __ATOMIC64_ADD	"agr"
+#define __ATOMIC64_XOR	"xgr"
 #define __ATOMIC64_BARRIER "\n"
 
 #define __ATOMIC64_LOOP(ptr, op_val, op_string, __barrier)		\
@@ -247,16 +253,6 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	__ATOMIC64_LOOP(v, i, __ATOMIC64_ADD, __ATOMIC64_NO_BARRIER);
 }
 
-static inline void atomic64_clear_mask(unsigned long mask, atomic64_t *v)
-{
-	__ATOMIC64_LOOP(v, ~mask, __ATOMIC64_AND, __ATOMIC64_NO_BARRIER);
-}
-
-static inline void atomic64_set_mask(unsigned long mask, atomic64_t *v)
-{
-	__ATOMIC64_LOOP(v, mask, __ATOMIC64_OR, __ATOMIC64_NO_BARRIER);
-}
-
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
 static inline long long atomic64_cmpxchg(atomic64_t *v,
@@ -270,6 +266,17 @@ static inline long long atomic64_cmpxchg(atomic64_t *v,
 	return old;
 }
 
+#define ATOMIC64_OP(op, OP)						\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	__ATOMIC64_LOOP(v, i, __ATOMIC64_##OP, __ATOMIC64_NO_BARRIER);	\
+}
+
+ATOMIC64_OP(and, AND)
+ATOMIC64_OP(or, OR)
+ATOMIC64_OP(xor, XOR)
+
+#undef ATOMIC64_OP
 #undef __ATOMIC64_LOOP
 
 static inline int atomic64_add_unless(atomic64_t *v, long long i, long long u)
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index e6f8615a11eb..d48fe0162331 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -42,12 +42,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
 	___p1;								\
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index 69972b7957ee..7f9fd5e3f1bf 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -12,14 +12,29 @@
  * We use a brcl 0,2 instruction for jump labels at compile time so it
  * can be easily distinguished from a hotpatch generated instruction.
  */
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("0:	brcl 0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
 		".pushsection __jump_table, \"aw\"\n"
 		".balign 8\n"
 		".quad 0b, %l[label], %0\n"
 		".popsection\n"
-		: : "X" (key) : : label);
+		: : "X" (&((char *)key)[branch]) : : label);
+
+	return false;
+label:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("0:	brcl 15, %l[label]\n"
+		".pushsection __jump_table, \"aw\"\n"
+		".balign 8\n"
+		".quad 0b, %l[label], %0\n"
+		".popsection\n"
+		: : "X" (&((char *)key)[branch]) : : label);
+
 	return false;
 label:
 	return true;