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
  ...

8 files changed, 79 insertions, 40 deletions

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index e9168955c42f..fb52aa644aab 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -182,6 +182,21 @@ 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");					\
+}
+
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
 /**
  * __atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
@@ -219,16 +234,6 @@ static __always_inline short int atomic_inc_short(short int *v)
 	return *v;
 }
 
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "andl %0,%1"			\
-		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "orl %0,%1"			\
-		     : : "r" ((unsigned)(mask)), "m" (*(addr))	\
-		     : "memory")
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index b154de75c90c..a11c30b77fb5 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -313,4 +313,18 @@ 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;						\
+}
+
+ATOMIC64_OP(and, &)
+ATOMIC64_OP(or, |)
+ATOMIC64_OP(xor, ^)
+
+#undef ATOMIC64_OP
+
 #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 b965f9e03f2a..50e33eff58de 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -220,4 +220,19 @@ 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");					\
+}
+
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
+
+#undef ATOMIC64_OP
+
 #endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 818cb8788225..0681d2532527 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -57,12 +57,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	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);				\
 	smp_mb();							\
 	___p1;								\
@@ -74,12 +74,12 @@ do {									\
 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/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index a4c1cf7e93f8..5daeca3d0f9e 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -16,15 +16,32 @@
 # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
 #endif
 
-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("1:"
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
-		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
 		".popsection \n\t"
-		: :  "i" (key) : : l_yes);
+		: :  "i" (key), "i" (branch) : : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
+
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:"
+		".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"
+		"2:\n\t"
+		".pushsection __jump_table,  \"aw\" \n\t"
+		_ASM_ALIGN "\n\t"
+		_ASM_PTR "1b, %l[l_yes], %c0 + %c1 \n\t"
+		".popsection \n\t"
+		: :  "i" (key), "i" (branch) : : l_yes);
+
 	return false;
 l_yes:
 	return true;
diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h
index ae0e241e228b..c537cbb038a7 100644
--- a/arch/x86/include/asm/qrwlock.h
+++ b/arch/x86/include/asm/qrwlock.h
@@ -2,16 +2,6 @@
 #define _ASM_X86_QRWLOCK_H
 
 #include <asm-generic/qrwlock_types.h>
-
-#ifndef CONFIG_X86_PPRO_FENCE
-#define queue_write_unlock queue_write_unlock
-static inline void queue_write_unlock(struct qrwlock *lock)
-{
-        barrier();
-        ACCESS_ONCE(*(u8 *)&lock->cnts) = 0;
-}
-#endif
-
 #include <asm-generic/qrwlock.h>
 
 #endif /* _ASM_X86_QRWLOCK_H */
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 26d5a55a2736..e565e0e4d216 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -45,7 +45,7 @@ static void __jump_label_transform(struct jump_entry *entry,
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
-	if (type == JUMP_LABEL_ENABLE) {
+	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			/*
 			 * Jump label is enabled for the first time.
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 79055cf2c497..c8d52cb4cb6e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -38,7 +38,7 @@ static int __read_mostly tsc_unstable;
    erroneous rdtsc usage on !cpu_has_tsc processors */
 static int __read_mostly tsc_disabled = -1;
 
-static struct static_key __use_tsc = STATIC_KEY_INIT;
+static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
 
@@ -274,7 +274,12 @@ done:
  */
 u64 native_sched_clock(void)
 {
-	u64 tsc_now;
+	if (static_branch_likely(&__use_tsc)) {
+		u64 tsc_now = rdtsc();
+
+		/* return the value in ns */
+		return cycles_2_ns(tsc_now);
+	}
 
 	/*
 	 * Fall back to jiffies if there's no TSC available:
@@ -284,16 +289,9 @@ u64 native_sched_clock(void)
 	 *   very important for it to be as fast as the platform
 	 *   can achieve it. )
 	 */
-	if (!static_key_false(&__use_tsc)) {
-		/* No locking but a rare wrong value is not a big deal: */
-		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
-	}
-
-	/* read the Time Stamp Counter: */
-	tsc_now = rdtsc();
 
-	/* return the value in ns */
-	return cycles_2_ns(tsc_now);
+	/* No locking but a rare wrong value is not a big deal: */
+	return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 }
 
 /*
@@ -1212,7 +1210,7 @@ void __init tsc_init(void)
 	/* now allow native_sched_clock() to use rdtsc */
 
 	tsc_disabled = 0;
-	static_key_slow_inc(&__use_tsc);
+	static_branch_enable(&__use_tsc);
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();