Merge tag 'locking-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Over a dozen code generation micro-optimizations for the atomic
   and spinlock code

 - Add more __ro_after_init attributes

 - Robustify the lockdevent_*() macros

* tag 'locking-core-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/pvqspinlock/x86: Use _Q_LOCKED_VAL in PV_UNLOCK_ASM macro
  locking/qspinlock/x86: Micro-optimize virt_spin_lock()
  locking/atomic/x86: Merge __arch{,_try}_cmpxchg64_emu_local() with __arch{,_try}_cmpxchg64_emu()
  locking/atomic/x86: Introduce arch_try_cmpxchg64_local()
  locking/pvqspinlock/x86: Remove redundant CMP after CMPXCHG in __raw_callee_save___pv_queued_spin_unlock()
  locking/pvqspinlock: Use try_cmpxchg() in qspinlock_paravirt.h
  locking/pvqspinlock: Use try_cmpxchg_acquire() in trylock_clear_pending()
  locking/qspinlock: Use atomic_try_cmpxchg_relaxed() in xchg_tail()
  locking/atomic/x86: Define arch_atomic_sub() family using arch_atomic_add() functions
  locking/atomic/x86: Rewrite x86_32 arch_atomic64_{,fetch}_{and,or,xor}() functions
  locking/atomic/x86: Introduce arch_atomic64_read_nonatomic() to x86_32
  locking/atomic/x86: Introduce arch_atomic64_try_cmpxchg() to x86_32
  locking/atomic/x86: Introduce arch_try_cmpxchg64() for !CONFIG_X86_CMPXCHG64
  locking/atomic/x86: Modernize x86_32 arch_{,try_}_cmpxchg64{,_local}()
  locking/atomic/x86: Correct the definition of __arch_try_cmpxchg128()
  x86/tsc: Make __use_tsc __ro_after_init
  x86/kvm: Make kvm_async_pf_enabled __ro_after_init
  context_tracking: Make context_tracking_key __ro_after_init
  jump_label,module: Don't alloc static_key_mod for __ro_after_init keys
  locking/qspinlock: Always evaluate lockevent* non-event parameter once

9 files changed, 203 insertions, 137 deletions

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 55a55ec04350..55b4d24356ea 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -86,11 +86,7 @@ static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
 }
 #define arch_atomic_add_return arch_atomic_add_return
 
-static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
-{
-	return arch_atomic_add_return(-i, v);
-}
-#define arch_atomic_sub_return arch_atomic_sub_return
+#define arch_atomic_sub_return(i, v) arch_atomic_add_return(-(i), v)
 
 static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
@@ -98,11 +94,7 @@ static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 }
 #define arch_atomic_fetch_add arch_atomic_fetch_add
 
-static __always_inline int arch_atomic_fetch_sub(int i, atomic_t *v)
-{
-	return xadd(&v->counter, -i);
-}
-#define arch_atomic_fetch_sub arch_atomic_fetch_sub
+#define arch_atomic_fetch_sub(i, v) arch_atomic_fetch_add(-(i), v)
 
 static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
 {
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 3486d91b8595..40ff73b5ec55 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -14,6 +14,32 @@ typedef struct {
 
 #define ATOMIC64_INIT(val)	{ (val) }
 
+/*
+ * Read an atomic64_t non-atomically.
+ *
+ * This is intended to be used in cases where a subsequent atomic operation
+ * will handle the torn value, and can be used to prime the first iteration
+ * of unconditional try_cmpxchg() loops, e.g.:
+ *
+ * 	s64 val = arch_atomic64_read_nonatomic(v);
+ * 	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ *
+ * This is NOT safe to use where the value is not always checked by a
+ * subsequent atomic operation, such as in conditional try_cmpxchg() loops
+ * that can break before the atomic operation, e.g.:
+ *
+ * 	s64 val = arch_atomic64_read_nonatomic(v);
+ * 	do {
+ * 		if (condition(val))
+ * 			break;
+ * 	} while (!arch_atomic64_try_cmpxchg(v, &val, val OP i);
+ */
+static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
+{
+	/* See comment in arch_atomic_read(). */
+	return __READ_ONCE(v->counter);
+}
+
 #define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
 #ifndef ATOMIC64_EXPORT
 #define ATOMIC64_DECL_ONE __ATOMIC64_DECL
@@ -61,12 +87,18 @@ ATOMIC64_DECL(add_unless);
 #undef __ATOMIC64_DECL
 #undef ATOMIC64_EXPORT
 
-static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
-	return arch_cmpxchg64(&v->counter, o, n);
+	return arch_cmpxchg64(&v->counter, old, new);
 }
 #define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
 
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
+{
+	return arch_try_cmpxchg64(&v->counter, old, new);
+}
+#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
+
 static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 {
 	s64 o;
@@ -195,69 +227,62 @@ static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 
 static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 }
 
 static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i));
 
-	return old;
+	return val;
 }
 #define arch_atomic64_fetch_and arch_atomic64_fetch_and
 
 static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 }
 
 static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i));
 
-	return old;
+	return val;
 }
 #define arch_atomic64_fetch_or arch_atomic64_fetch_or
 
 static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 }
 
 static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i));
 
-	return old;
+	return val;
 }
 #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
 
 static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	s64 old, c = 0;
+	s64 val = arch_atomic64_read_nonatomic(v);
 
-	while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
-		c = old;
+	do { } while (!arch_atomic64_try_cmpxchg(v, &val, val + i));
 
-	return old;
+	return val;
 }
 #define arch_atomic64_fetch_add arch_atomic64_fetch_add
 
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 3165c0feedf7..ae12acae5b06 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -80,11 +80,7 @@ static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_add_return arch_atomic64_add_return
 
-static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
-{
-	return arch_atomic64_add_return(-i, v);
-}
-#define arch_atomic64_sub_return arch_atomic64_sub_return
+#define arch_atomic64_sub_return(i, v) arch_atomic64_add_return(-(i), v)
 
 static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
@@ -92,11 +88,7 @@ static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 }
 #define arch_atomic64_fetch_add arch_atomic64_fetch_add
 
-static __always_inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
-{
-	return xadd(&v->counter, -i);
-}
-#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub
+#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), v)
 
 static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index b5731c51f0f4..ed2797f132ce 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -3,103 +3,150 @@
 #define _ASM_X86_CMPXCHG_32_H
 
 /*
- * Note: if you use set64_bit(), __cmpxchg64(), or their variants,
+ * Note: if you use __cmpxchg64(), or their variants,
  *       you need to test for the feature in boot_cpu_data.
  */
 
-#ifdef CONFIG_X86_CMPXCHG64
-#define arch_cmpxchg64(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
-					 (unsigned long long)(n)))
-#define arch_cmpxchg64_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
-					       (unsigned long long)(n)))
-#define arch_try_cmpxchg64(ptr, po, n)					\
-	__try_cmpxchg64((ptr), (unsigned long long *)(po), \
-			(unsigned long long)(n))
-#endif
+union __u64_halves {
+	u64 full;
+	struct {
+		u32 low, high;
+	};
+};
+
+#define __arch_cmpxchg64(_ptr, _old, _new, _lock)			\
+({									\
+	union __u64_halves o = { .full = (_old), },			\
+			   n = { .full = (_new), };			\
+									\
+	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+		     : [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high)			\
+		     : "memory");					\
+									\
+	o.full;								\
+})
+
+
+static __always_inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+	return __arch_cmpxchg64(ptr, old, new, LOCK_PREFIX);
+}
 
-static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
 {
-	u64 prev;
-	asm volatile(LOCK_PREFIX "cmpxchg8b %1"
-		     : "=A" (prev),
-		       "+m" (*ptr)
-		     : "b" ((u32)new),
-		       "c" ((u32)(new >> 32)),
-		       "0" (old)
-		     : "memory");
-	return prev;
+	return __arch_cmpxchg64(ptr, old, new,);
 }
 
-static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+#define __arch_try_cmpxchg64(_ptr, _oldp, _new, _lock)			\
+({									\
+	union __u64_halves o = { .full = *(_oldp), },			\
+			   n = { .full = (_new), };			\
+	bool ret;							\
+									\
+	asm volatile(_lock "cmpxchg8b %[ptr]"				\
+		     CC_SET(e)						\
+		     : CC_OUT(e) (ret),					\
+		       [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high)			\
+		     : "memory");					\
+									\
+	if (unlikely(!ret))						\
+		*(_oldp) = o.full;					\
+									\
+	likely(ret);							\
+})
+
+static __always_inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
 {
-	u64 prev;
-	asm volatile("cmpxchg8b %1"
-		     : "=A" (prev),
-		       "+m" (*ptr)
-		     : "b" ((u32)new),
-		       "c" ((u32)(new >> 32)),
-		       "0" (old)
-		     : "memory");
-	return prev;
+	return __arch_try_cmpxchg64(ptr, oldp, new, LOCK_PREFIX);
 }
 
-static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new)
+static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new)
 {
-	bool success;
-	u64 old = *pold;
-	asm volatile(LOCK_PREFIX "cmpxchg8b %[ptr]"
-		     CC_SET(z)
-		     : CC_OUT(z) (success),
-		       [ptr] "+m" (*ptr),
-		       "+A" (old)
-		     : "b" ((u32)new),
-		       "c" ((u32)(new >> 32))
-		     : "memory");
-
-	if (unlikely(!success))
-		*pold = old;
-	return success;
+	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CMPXCHG64
+
+#define arch_cmpxchg64 __cmpxchg64
+
+#define arch_cmpxchg64_local __cmpxchg64_local
+
+#define arch_try_cmpxchg64 __try_cmpxchg64
+
+#define arch_try_cmpxchg64_local __try_cmpxchg64_local
+
+#else
+
 /*
  * Building a kernel capable running on 80386 and 80486. It may be necessary
  * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
  */
 
-#define arch_cmpxchg64(ptr, o, n)				\
-({								\
-	__typeof__(*(ptr)) __ret;				\
-	__typeof__(*(ptr)) __old = (o);				\
-	__typeof__(*(ptr)) __new = (n);				\
-	alternative_io(LOCK_PREFIX_HERE				\
-			"call cmpxchg8b_emu",			\
-			"lock; cmpxchg8b (%%esi)" ,		\
-		       X86_FEATURE_CX8,				\
-		       "=A" (__ret),				\
-		       "S" ((ptr)), "0" (__old),		\
-		       "b" ((unsigned int)__new),		\
-		       "c" ((unsigned int)(__new>>32))		\
-		       : "memory");				\
-	__ret; })
-
-
-#define arch_cmpxchg64_local(ptr, o, n)				\
-({								\
-	__typeof__(*(ptr)) __ret;				\
-	__typeof__(*(ptr)) __old = (o);				\
-	__typeof__(*(ptr)) __new = (n);				\
-	alternative_io("call cmpxchg8b_emu",			\
-		       "cmpxchg8b (%%esi)" ,			\
-		       X86_FEATURE_CX8,				\
-		       "=A" (__ret),				\
-		       "S" ((ptr)), "0" (__old),		\
-		       "b" ((unsigned int)__new),		\
-		       "c" ((unsigned int)(__new>>32))		\
-		       : "memory");				\
-	__ret; })
+#define __arch_cmpxchg64_emu(_ptr, _old, _new, _lock_loc, _lock)	\
+({									\
+	union __u64_halves o = { .full = (_old), },			\
+			   n = { .full = (_new), };			\
+									\
+	asm volatile(ALTERNATIVE(_lock_loc				\
+				 "call cmpxchg8b_emu",			\
+				 _lock "cmpxchg8b %[ptr]", X86_FEATURE_CX8) \
+		     : [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high), "S" (_ptr)		\
+		     : "memory");					\
+									\
+	o.full;								\
+})
+
+static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
+{
+	return __arch_cmpxchg64_emu(ptr, old, new, LOCK_PREFIX_HERE, "lock; ");
+}
+#define arch_cmpxchg64 arch_cmpxchg64
+
+static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
+{
+	return __arch_cmpxchg64_emu(ptr, old, new, ,);
+}
+#define arch_cmpxchg64_local arch_cmpxchg64_local
+
+#define __arch_try_cmpxchg64_emu(_ptr, _oldp, _new, _lock_loc, _lock)	\
+({									\
+	union __u64_halves o = { .full = *(_oldp), },			\
+			   n = { .full = (_new), };			\
+	bool ret;							\
+									\
+	asm volatile(ALTERNATIVE(_lock_loc				\
+				 "call cmpxchg8b_emu",			\
+				 _lock "cmpxchg8b %[ptr]", X86_FEATURE_CX8) \
+		     CC_SET(e)						\
+		     : CC_OUT(e) (ret),					\
+		       [ptr] "+m" (*(_ptr)),				\
+		       "+a" (o.low), "+d" (o.high)			\
+		     : "b" (n.low), "c" (n.high), "S" (_ptr)		\
+		     : "memory");					\
+									\
+	if (unlikely(!ret))						\
+		*(_oldp) = o.full;					\
+									\
+	likely(ret);							\
+})
+
+static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new)
+{
+	return __arch_try_cmpxchg64_emu(ptr, oldp, new, LOCK_PREFIX_HERE, "lock; ");
+}
+#define arch_try_cmpxchg64 arch_try_cmpxchg64
+
+static __always_inline bool arch_try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new)
+{
+	return __arch_try_cmpxchg64_emu(ptr, oldp, new, ,);
+}
+#define arch_try_cmpxchg64_local arch_try_cmpxchg64_local
 
 #endif
 
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 44b08b53ab32..5e241306db26 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -20,6 +20,12 @@
 	arch_try_cmpxchg((ptr), (po), (n));				\
 })
 
+#define arch_try_cmpxchg64_local(ptr, po, n)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_try_cmpxchg_local((ptr), (po), (n));			\
+})
+
 union __u128_halves {
 	u128 full;
 	struct {
@@ -62,7 +68,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old,
 	asm volatile(_lock "cmpxchg16b %[ptr]"				\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
-		       [ptr] "+m" (*ptr),				\
+		       [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
 		     : "memory");					\
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index cde8357bb226..a053c1293975 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -85,6 +85,8 @@ DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
 #define virt_spin_lock virt_spin_lock
 static inline bool virt_spin_lock(struct qspinlock *lock)
 {
+	int val;
+
 	if (!static_branch_likely(&virt_spin_lock_key))
 		return false;
 
@@ -94,10 +96,13 @@ static inline bool virt_spin_lock(struct qspinlock *lock)
 	 * horrible lock 'holder' preemption issues.
 	 */
 
-	do {
-		while (atomic_read(&lock->val) != 0)
-			cpu_relax();
-	} while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
+ __retry:
+	val = atomic_read(&lock->val);
+
+	if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) {
+		cpu_relax();
+		goto __retry;
+	}
 
 	return true;
 }
diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index ef9697f20129..0a985784be9b 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -25,9 +25,9 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
  *
  * void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock)
  * {
- *	u8 lockval = cmpxchg(&lock->locked, _Q_LOCKED_VAL, 0);
+ *	u8 lockval = _Q_LOCKED_VAL;
  *
- *	if (likely(lockval == _Q_LOCKED_VAL))
+ *	if (try_cmpxchg(&lock->locked, &lockval, 0))
  *		return;
  *	pv_queued_spin_unlock_slowpath(lock, lockval);
  * }
@@ -40,10 +40,9 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text");
 #define PV_UNLOCK_ASM							\
 	FRAME_BEGIN							\
 	"push  %rdx\n\t"						\
-	"mov   $0x1,%eax\n\t"						\
+	"mov   $" __stringify(_Q_LOCKED_VAL) ",%eax\n\t"		\
 	"xor   %edx,%edx\n\t"						\
 	LOCK_PREFIX "cmpxchg %dl,(%rdi)\n\t"				\
-	"cmp   $0x1,%al\n\t"						\
 	"jne   .slowpath\n\t"						\
 	"pop   %rdx\n\t"						\
 	FRAME_END							\
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7f0732bc0ccd..263f8aed4e2c 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -44,7 +44,7 @@
 #include <asm/svm.h>
 #include <asm/e820/api.h>
 
-DEFINE_STATIC_KEY_FALSE(kvm_async_pf_enabled);
+DEFINE_STATIC_KEY_FALSE_RO(kvm_async_pf_enabled);
 
 static int kvmapf = 1;
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 5a69a49acc96..0f7624ed1d1d 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -44,7 +44,7 @@ EXPORT_SYMBOL(tsc_khz);
 static int __read_mostly tsc_unstable;
 static unsigned int __initdata tsc_early_khz;
 
-static DEFINE_STATIC_KEY_FALSE(__use_tsc);
+static DEFINE_STATIC_KEY_FALSE_RO(__use_tsc);
 
 int tsc_clocksource_reliable;