Locking changes for v6.11:

- Jump label fixes, including a perf events fix that originally
    manifested as jump label failures, but was a serialization bug
    at the usage site.
 
  - Mark down_write*() helpers as __always_inline, to improve
    WCHAN debuggability.
 
  - Misc cleanups and fixes.
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmaVEV8RHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1iWbQ/+KBa29udVx0qiX/1R/+4EBNKzFDyvhobu
 9XuAUZJZ9g46PFqnXlnA/VhGff52M2I+1scva11OPnb2NnOhAN1yUFQJaZh0HM+y
 GTsaLQEdJfNKv1Z0i05AnYE7BKFEnoksWInsOg6Or5KoML5RS6vIyLWsBQpCjelM
 ZxAYNHVpI5qeeUT7dqy9bkBxUXgOpc5X5+qZmmBnBDTGvhsPviV88gL1Ol2tjmGi
 hhALK9RdLMltrNEejDc9sBcLw/qRA5QOUDDxSoBykSOBaljJB+3BcTCuXdUJT24Y
 xpufbESHyl7HAmdvRU+n4ypo4kuKSIcyF1+V6LcMmNi0jSsyUG7x+SuhJetQHd2z
 kLsYD18JbHHBVz7/047DnVTtyTcifsDpJi4MqEYYrUhMw1ns/goEiLRgSEYdB/FT
 eCjdZxbCzkKzmV42/gqkM/mv8/pWkhvAqZ1/LNkHSOR/JSa5X3NeR0qrj18OKSrS
 Du+ycGDqk1PqVcqiC1heBayIU/QoY/sEkdktTtbAKSujKCJ+tYhPtqMki6JaOh5I
 VPp9ekcbs+Vvuu1qNDcueoe3TqxO2wfchKMNcSD8+I68EZtxHWZN3iHtTOlqGYVr
 uZuG0V2WSgGvUi7k0UIPpnnmZ2+XejA++VnjVitXM3Z+xf7MlrPNy/4fzUbkgTQn
 T8/Tt7SytQE=
 =T1KT
 -----END PGP SIGNATURE-----

Merge tag 'locking-core-2024-07-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Jump label fixes, including a perf events fix that originally
   manifested as jump label failures, but was a serialization bug at the
   usage site

 - Mark down_write*() helpers as __always_inline, to improve WCHAN
   debuggability

 - Misc cleanups and fixes

* tag 'locking-core-2024-07-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  locking/rwsem: Add __always_inline annotation to __down_write_common() and inlined callers
  jump_label: Simplify and clarify static_key_fast_inc_cpus_locked()
  jump_label: Clarify condition in static_key_fast_inc_not_disabled()
  jump_label: Fix concurrency issues in static_key_slow_dec()
  perf/x86: Serialize set_attr_rdpmc()
  cleanup: Standardize the header guard define's name

arch/x86/events/core.c

@@ -2547,6 +2547,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 			      struct device_attribute *attr,
 			      const char *buf, size_t count)
 {
+	static DEFINE_MUTEX(rdpmc_mutex);
 	unsigned long val;
 	ssize_t ret;
 
@@ -2560,6 +2561,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
 	if (x86_pmu.attr_rdpmc_broken)
 		return -ENOTSUPP;
 
+	guard(mutex)(&rdpmc_mutex);
+
 	if (val != x86_pmu.attr_rdpmc) {
 		/*
 		 * Changing into or out of never available or always available,

include/linux/cleanup.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_GUARDS_H
-#define __LINUX_GUARDS_H
+#ifndef _LINUX_CLEANUP_H
+#define _LINUX_CLEANUP_H
 
 #include <linux/compiler.h>
 
@@ -250,4 +250,4 @@ __DEFINE_LOCK_GUARD_0(_name, _lock)
 	{ return class_##_name##_lock_ptr(_T); }
 
 
-#endif /* __LINUX_GUARDS_H */
+#endif /* _LINUX_CLEANUP_H */

kernel/jump_label.c

@@ -131,13 +131,16 @@ bool static_key_fast_inc_not_disabled(struct static_key *key)
 	STATIC_KEY_CHECK_USE(key);
 	/*
 	 * Negative key->enabled has a special meaning: it sends
-	 * static_key_slow_inc() down the slow path, and it is non-zero
-	 * so it counts as "enabled" in jump_label_update().  Note that
-	 * atomic_inc_unless_negative() checks >= 0, so roll our own.
+	 * static_key_slow_inc/dec() down the slow path, and it is non-zero
+	 * so it counts as "enabled" in jump_label_update().
+	 *
+	 * The INT_MAX overflow condition is either used by the networking
+	 * code to reset or detected in the slow path of
+	 * static_key_slow_inc_cpuslocked().
 	 */
 	v = atomic_read(&key->enabled);
 	do {
-		if (v <= 0 || (v + 1) < 0)
+		if (v <= 0 || v == INT_MAX)
 			return false;
 	} while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1)));
 
@@ -150,7 +153,7 @@ bool static_key_slow_inc_cpuslocked(struct static_key *key)
 	lockdep_assert_cpus_held();
 
 	/*
-	 * Careful if we get concurrent static_key_slow_inc() calls;
+	 * Careful if we get concurrent static_key_slow_inc/dec() calls;
 	 * later calls must wait for the first one to _finish_ the
 	 * jump_label_update() process.  At the same time, however,
 	 * the jump_label_update() call below wants to see
@@ -159,22 +162,24 @@ bool static_key_slow_inc_cpuslocked(struct static_key *key)
 	if (static_key_fast_inc_not_disabled(key))
 		return true;
 
-	jump_label_lock();
-	if (atomic_read(&key->enabled) == 0) {
-		atomic_set(&key->enabled, -1);
+	guard(mutex)(&jump_label_mutex);
+	/* Try to mark it as 'enabling in progress. */
+	if (!atomic_cmpxchg(&key->enabled, 0, -1)) {
 		jump_label_update(key);
 		/*
-		 * Ensure that if the above cmpxchg loop observes our positive
-		 * value, it must also observe all the text changes.
+		 * Ensure that when static_key_fast_inc_not_disabled() or
+		 * static_key_slow_try_dec() observe the positive value,
+		 * they must also observe all the text changes.
 		 */
 		atomic_set_release(&key->enabled, 1);
 	} else {
-		if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) {
-			jump_label_unlock();
+		/*
+		 * While holding the mutex this should never observe
+		 * anything else than a value >= 1 and succeed
+		 */
+		if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key)))
 			return false;
-		}
 	}
-	jump_label_unlock();
 	return true;
 }
 
@@ -247,20 +252,32 @@ EXPORT_SYMBOL_GPL(static_key_disable);
 
 static bool static_key_slow_try_dec(struct static_key *key)
 {
-	int val;
-
-	val = atomic_fetch_add_unless(&key->enabled, -1, 1);
-	if (val == 1)
-		return false;
+	int v;
 
 	/*
-	 * The negative count check is valid even when a negative
-	 * key->enabled is in use by static_key_slow_inc(); a
-	 * __static_key_slow_dec() before the first static_key_slow_inc()
-	 * returns is unbalanced, because all other static_key_slow_inc()
-	 * instances block while the update is in progress.
+	 * Go into the slow path if key::enabled is less than or equal than
+	 * one. One is valid to shut down the key, anything less than one
+	 * is an imbalance, which is handled at the call site.
+	 *
+	 * That includes the special case of '-1' which is set in
+	 * static_key_slow_inc_cpuslocked(), but that's harmless as it is
+	 * fully serialized in the slow path below. By the time this task
+	 * acquires the jump label lock the value is back to one and the
+	 * retry under the lock must succeed.
 	 */
-	WARN(val < 0, "jump label: negative count!\n");
+	v = atomic_read(&key->enabled);
+	do {
+		/*
+		 * Warn about the '-1' case though; since that means a
+		 * decrement is concurrent with a first (0->1) increment. IOW
+		 * people are trying to disable something that wasn't yet fully
+		 * enabled. This suggests an ordering problem on the user side.
+		 */
+		WARN_ON_ONCE(v < 0);
+		if (v <= 1)
+			return false;
+	} while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1)));
+
 	return true;
 }
 
@@ -271,10 +288,11 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
 	if (static_key_slow_try_dec(key))
 		return;
 
-	jump_label_lock();
-	if (atomic_dec_and_test(&key->enabled))
+	guard(mutex)(&jump_label_mutex);
+	if (atomic_cmpxchg(&key->enabled, 1, 0))
 		jump_label_update(key);
-	jump_label_unlock();
+	else
+		WARN_ON_ONCE(!static_key_slow_try_dec(key));
 }
 
 static void __static_key_slow_dec(struct static_key *key)

kernel/locking/rwsem.c

@@ -1297,7 +1297,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 /*
  * lock for writing
  */
-static inline int __down_write_common(struct rw_semaphore *sem, int state)
+static __always_inline int __down_write_common(struct rw_semaphore *sem, int state)
 {
 	int ret = 0;
 
@@ -1310,12 +1310,12 @@ static inline int __down_write_common(struct rw_semaphore *sem, int state)
 	return ret;
 }
 
-static inline void __down_write(struct rw_semaphore *sem)
+static __always_inline void __down_write(struct rw_semaphore *sem)
 {
 	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
 }
 
-static inline int __down_write_killable(struct rw_semaphore *sem)
+static __always_inline int __down_write_killable(struct rw_semaphore *sem)
 {
 	return __down_write_common(sem, TASK_KILLABLE);
 }