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

Author: torvalds

arch/x86/include/asm/atomic.h

@@ -86,23 +86,15 @@ 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)
 {
 	return xadd(&v->counter, i);
 }
 #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)
 {

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
 

arch/x86/include/asm/atomic64_64.h

@@ -80,23 +80,15 @@ 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)
 {
 	return xadd(&v->counter, i);
 }
 #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)
 {