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

5 files changed, 83 insertions, 38 deletions

diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 70ae70d03823..24b1e1143260 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -432,7 +432,7 @@ static __always_inline void ct_kernel_enter(bool user, int offset) { }
 #define CREATE_TRACE_POINTS
 #include <trace/events/context_tracking.h>
 
-DEFINE_STATIC_KEY_FALSE(context_tracking_key);
+DEFINE_STATIC_KEY_FALSE_RO(context_tracking_key);
 EXPORT_SYMBOL_GPL(context_tracking_key);
 
 static noinstr bool context_tracking_recursion_enter(void)
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index d9c822bbffb8..3218fa5688b9 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -530,6 +530,45 @@ void __init jump_label_init(void)
 	cpus_read_unlock();
 }
 
+static inline bool static_key_sealed(struct static_key *key)
+{
+	return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK);
+}
+
+static inline void static_key_seal(struct static_key *key)
+{
+	unsigned long type = key->type & JUMP_TYPE_TRUE;
+	key->type = JUMP_TYPE_LINKED | type;
+}
+
+void jump_label_init_ro(void)
+{
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __stop___jump_table;
+	struct jump_entry *iter;
+
+	if (WARN_ON_ONCE(!static_key_initialized))
+		return;
+
+	cpus_read_lock();
+	jump_label_lock();
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		struct static_key *iterk = jump_entry_key(iter);
+
+		if (!is_kernel_ro_after_init((unsigned long)iterk))
+			continue;
+
+		if (static_key_sealed(iterk))
+			continue;
+
+		static_key_seal(iterk);
+	}
+
+	jump_label_unlock();
+	cpus_read_unlock();
+}
+
 #ifdef CONFIG_MODULES
 
 enum jump_label_type jump_label_init_type(struct jump_entry *entry)
@@ -650,6 +689,15 @@ static int jump_label_add_module(struct module *mod)
 			static_key_set_entries(key, iter);
 			continue;
 		}
+
+		/*
+		 * If the key was sealed at init, then there's no need to keep a
+		 * reference to its module entries - just patch them now and be
+		 * done with it.
+		 */
+		if (static_key_sealed(key))
+			goto do_poke;
+
 		jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
 		if (!jlm)
 			return -ENOMEM;
@@ -675,6 +723,7 @@ static int jump_label_add_module(struct module *mod)
 		static_key_set_linked(key);
 
 		/* Only update if we've changed from our initial state */
+do_poke:
 		if (jump_label_type(iter) != jump_label_init_type(iter))
 			__jump_label_update(key, iter, iter_stop, true);
 	}
@@ -699,6 +748,10 @@ static void jump_label_del_module(struct module *mod)
 		if (within_module((unsigned long)key, mod))
 			continue;
 
+		/* No @jlm allocated because key was sealed at init. */
+		if (static_key_sealed(key))
+			continue;
+
 		/* No memory during module load */
 		if (WARN_ON(!static_key_linked(key)))
 			continue;
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
index a6016b91803d..d2345e9c0190 100644
--- a/kernel/locking/lock_events.h
+++ b/kernel/locking/lock_events.h
@@ -53,8 +53,8 @@ static inline void __lockevent_add(enum lock_events event, int inc)
 #else  /* CONFIG_LOCK_EVENT_COUNTS */
 
 #define lockevent_inc(ev)
-#define lockevent_add(ev, c)
-#define lockevent_cond_inc(ev, c)
+#define lockevent_add(ev, c)		do { (void)(c); } while (0)
+#define lockevent_cond_inc(ev, c)	do { (void)(c); } while (0)
 
 #endif /* CONFIG_LOCK_EVENT_COUNTS */
 
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ebe6b8ec7cb3..1df5fef8a656 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -220,21 +220,18 @@ static __always_inline void clear_pending_set_locked(struct qspinlock *lock)
  */
 static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
-	u32 old, new, val = atomic_read(&lock->val);
+	u32 old, new;
 
-	for (;;) {
-		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
+	old = atomic_read(&lock->val);
+	do {
+		new = (old & _Q_LOCKED_PENDING_MASK) | tail;
 		/*
 		 * We can use relaxed semantics since the caller ensures that
 		 * the MCS node is properly initialized before updating the
 		 * tail.
 		 */
-		old = atomic_cmpxchg_relaxed(&lock->val, val, new);
-		if (old == val)
-			break;
+	} while (!atomic_try_cmpxchg_relaxed(&lock->val, &old, new));
 
-		val = old;
-	}
 	return old;
 }
 #endif /* _Q_PENDING_BITS == 8 */
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index ae2b12f68b90..f5a36e67b593 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -86,9 +86,10 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 	 */
 	for (;;) {
 		int val = atomic_read(&lock->val);
+		u8 old = 0;
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
-		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
+		    try_cmpxchg_acquire(&lock->locked, &old, _Q_LOCKED_VAL)) {
 			lockevent_inc(pv_lock_stealing);
 			return true;
 		}
@@ -116,11 +117,12 @@ static __always_inline void set_pending(struct qspinlock *lock)
  * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the
  * lock just to be sure that it will get it.
  */
-static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
 {
+	u16 old = _Q_PENDING_VAL;
+
 	return !READ_ONCE(lock->locked) &&
-	       (cmpxchg_acquire(&lock->locked_pending, _Q_PENDING_VAL,
-				_Q_LOCKED_VAL) == _Q_PENDING_VAL);
+	       try_cmpxchg_acquire(&lock->locked_pending, &old, _Q_LOCKED_VAL);
 }
 #else /* _Q_PENDING_BITS == 8 */
 static __always_inline void set_pending(struct qspinlock *lock)
@@ -128,27 +130,21 @@ static __always_inline void set_pending(struct qspinlock *lock)
 	atomic_or(_Q_PENDING_VAL, &lock->val);
 }
 
-static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+static __always_inline bool trylock_clear_pending(struct qspinlock *lock)
 {
-	int val = atomic_read(&lock->val);
-
-	for (;;) {
-		int old, new;
-
-		if (val  & _Q_LOCKED_MASK)
-			break;
+	int old, new;
 
+	old = atomic_read(&lock->val);
+	do {
+		if (old & _Q_LOCKED_MASK)
+			return false;
 		/*
 		 * Try to clear pending bit & set locked bit
 		 */
-		old = val;
-		new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
-		val = atomic_cmpxchg_acquire(&lock->val, old, new);
+		new = (old & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
+	} while (!atomic_try_cmpxchg_acquire (&lock->val, &old, new));
 
-		if (val == old)
-			return 1;
-	}
-	return 0;
+	return true;
 }
 #endif /* _Q_PENDING_BITS == 8 */
 
@@ -216,8 +212,9 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
 	int hopcnt = 0;
 
 	for_each_hash_entry(he, offset, hash) {
+		struct qspinlock *old = NULL;
 		hopcnt++;
-		if (!cmpxchg(&he->lock, NULL, lock)) {
+		if (try_cmpxchg(&he->lock, &old, lock)) {
 			WRITE_ONCE(he->node, node);
 			lockevent_pv_hop(hopcnt);
 			return &he->lock;
@@ -294,7 +291,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 {
 	struct pv_node *pn = (struct pv_node *)node;
 	struct pv_node *pp = (struct pv_node *)prev;
-	bool __maybe_unused wait_early;
+	bool wait_early;
 	int loop;
 
 	for (;;) {
@@ -360,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 {
 	struct pv_node *pn = (struct pv_node *)node;
-
+	enum vcpu_state old = vcpu_halted;
 	/*
 	 * If the vCPU is indeed halted, advance its state to match that of
 	 * pv_wait_node(). If OTOH this fails, the vCPU was running and will
@@ -377,8 +374,7 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
 	 * subsequent writes.
 	 */
 	smp_mb__before_atomic();
-	if (cmpxchg_relaxed(&pn->state, vcpu_halted, vcpu_hashed)
-	    != vcpu_halted)
+	if (!try_cmpxchg_relaxed(&pn->state, &old, vcpu_hashed))
 		return;
 
 	/*
@@ -546,15 +542,14 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 #ifndef __pv_queued_spin_unlock
 __visible __lockfunc void __pv_queued_spin_unlock(struct qspinlock *lock)
 {
-	u8 locked;
+	u8 locked = _Q_LOCKED_VAL;
 
 	/*
 	 * We must not unlock if SLOW, because in that case we must first
 	 * unhash. Otherwise it would be possible to have multiple @lock
 	 * entries, which would be BAD.
 	 */
-	locked = cmpxchg_release(&lock->locked, _Q_LOCKED_VAL, 0);
-	if (likely(locked == _Q_LOCKED_VAL))
+	if (try_cmpxchg_release(&lock->locked, &locked, 0))
 		return;
 
 	__pv_queued_spin_unlock_slowpath(lock, locked);