Merge tag 'locking-core-2021-04-28' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - rtmutex cleanup & spring cleaning pass that removes ~400 lines of
   code

 - Futex simplifications & cleanups

 - Add debugging to the CSD code, to help track down a tenacious race
   (or hw problem)

 - Add lockdep_assert_not_held(), to allow code to require a lock to not
   be held, and propagate this into the ath10k driver

 - Misc LKMM documentation updates

 - Misc KCSAN updates: cleanups & documentation updates

 - Misc fixes and cleanups

 - Fix locktorture bugs with ww_mutexes

* tag 'locking-core-2021-04-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  kcsan: Fix printk format string
  static_call: Relax static_call_update() function argument type
  static_call: Fix unused variable warn w/o MODULE
  locking/rtmutex: Clean up signal handling in __rt_mutex_slowlock()
  locking/rtmutex: Restrict the trylock WARN_ON() to debug
  locking/rtmutex: Fix misleading comment in rt_mutex_postunlock()
  locking/rtmutex: Consolidate the fast/slowpath invocation
  locking/rtmutex: Make text section and inlining consistent
  locking/rtmutex: Move debug functions as inlines into common header
  locking/rtmutex: Decrapify __rt_mutex_init()
  locking/rtmutex: Remove pointless CONFIG_RT_MUTEXES=n stubs
  locking/rtmutex: Inline chainwalk depth check
  locking/rtmutex: Move rt_mutex_debug_task_free() to rtmutex.c
  locking/rtmutex: Remove empty and unused debug stubs
  locking/rtmutex: Consolidate rt_mutex_init()
  locking/rtmutex: Remove output from deadlock detector
  locking/rtmutex: Remove rtmutex deadlock tester leftovers
  locking/rtmutex: Remove rt_mutex_timed_lock()
  MAINTAINERS: Add myself as futex reviewer
  locking/mutex: Remove repeated declaration
  ...

Documentation/admin-guide/kernel-parameters.txt

@@ -782,6 +782,16 @@
 	cs89x0_media=	[HW,NET]
 			Format: { rj45 | aui | bnc }
 
+	csdlock_debug=	[KNL] Enable debug add-ons of cross-CPU function call
+			handling. When switched on, additional debug data is
+			printed to the console in case a hanging CPU is
+			detected, and that CPU is pinged again in order to try
+			to resolve the hang situation.
+			0: disable csdlock debugging (default)
+			1: enable basic csdlock debugging (minor impact)
+			ext: enable extended csdlock debugging (more impact,
+			     but more data)
+
 	dasd=		[HW,NET]
 			See header of drivers/s390/block/dasd_devmap.c.
 

Documentation/dev-tools/kcsan.rst

@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. Copyright (C) 2019, Google LLC.
+
 The Kernel Concurrency Sanitizer (KCSAN)
 ========================================
 

MAINTAINERS

@@ -7452,6 +7452,7 @@ M:	Thomas Gleixner <[email protected]>
 M:	Ingo Molnar <[email protected]>
 R:	Peter Zijlstra <[email protected]>
 R:	Darren Hart <[email protected]>
+R:	Davidlohr Bueso <[email protected]>
 L:	[email protected]
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core

arch/arm/include/asm/spinlock.h

@@ -22,7 +22,7 @@
  * assembler to insert a extra (16-bit) IT instruction, depending on the
  * presence or absence of neighbouring conditional instructions.
  *
- * To avoid this unpredictableness, an approprite IT is inserted explicitly:
+ * To avoid this unpredictability, an appropriate IT is inserted explicitly:
  * the assembler won't change IT instructions which are explicitly present
  * in the input.
  */

arch/x86/include/asm/jump_label.h

@@ -14,7 +14,7 @@
 #include <linux/stringify.h>
 #include <linux/types.h>
 
-static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
 	asm_volatile_goto("1:"
 		".byte " __stringify(BYTES_NOP5) "\n\t"
@@ -30,7 +30,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool bran
 	return true;
 }
 
-static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
 	asm_volatile_goto("1:"
 		".byte 0xe9\n\t .long %l[l_yes] - 2f\n\t"

drivers/net/wireless/ath/ath10k/mac.c

@@ -4727,6 +4727,8 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 /* Must not be called with conf_mutex held as workers can use that also. */
 void ath10k_drain_tx(struct ath10k *ar)
 {
+	lockdep_assert_not_held(&ar->conf_mutex);
+
 	/* make sure rcu-protected mac80211 tx path itself is drained */
 	synchronize_net();
 

include/linux/kcsan-checks.h

@@ -1,4 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KCSAN access checks and modifiers. These can be used to explicitly check
+ * uninstrumented accesses, or change KCSAN checking behaviour of accesses.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #ifndef _LINUX_KCSAN_CHECKS_H
 #define _LINUX_KCSAN_CHECKS_H

include/linux/kcsan.h

@@ -1,4 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * The Kernel Concurrency Sanitizer (KCSAN) infrastructure. Public interface and
+ * data structures to set up runtime. See kcsan-checks.h for explicit checks and
+ * modifiers. For more info please see Documentation/dev-tools/kcsan.rst.
+ *
+ * Copyright (C) 2019, Google LLC.
+ */
 
 #ifndef _LINUX_KCSAN_H
 #define _LINUX_KCSAN_H

include/linux/lockdep.h

@@ -155,7 +155,7 @@ extern void lockdep_set_selftest_task(struct task_struct *task);
 extern void lockdep_init_task(struct task_struct *task);
 
 /*
- * Split the recrursion counter in two to readily detect 'off' vs recursion.
+ * Split the recursion counter in two to readily detect 'off' vs recursion.
  */
 #define LOCKDEP_RECURSION_BITS	16
 #define LOCKDEP_OFF		(1U << LOCKDEP_RECURSION_BITS)
@@ -268,6 +268,11 @@ extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 
 extern void lock_release(struct lockdep_map *lock, unsigned long ip);
 
+/* lock_is_held_type() returns */
+#define LOCK_STATE_UNKNOWN	-1
+#define LOCK_STATE_NOT_HELD	0
+#define LOCK_STATE_HELD		1
+
 /*
  * Same "read" as for lock_acquire(), except -1 means any.
  */
@@ -301,8 +306,14 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 
 #define lockdep_depth(tsk)	(debug_locks ? (tsk)->lockdep_depth : 0)
 
-#define lockdep_assert_held(l)	do {				\
-		WARN_ON(debug_locks && !lockdep_is_held(l));	\
+#define lockdep_assert_held(l)	do {					\
+		WARN_ON(debug_locks &&					\
+			lockdep_is_held(l) == LOCK_STATE_NOT_HELD);	\
+	} while (0)
+
+#define lockdep_assert_not_held(l)	do {				\
+		WARN_ON(debug_locks &&					\
+			lockdep_is_held(l) == LOCK_STATE_HELD);		\
 	} while (0)
 
 #define lockdep_assert_held_write(l)	do {			\
@@ -397,7 +408,8 @@ extern int lockdep_is_held(const void *);
 #define lockdep_is_held_type(l, r)		(1)
 
 #define lockdep_assert_held(l)			do { (void)(l); } while (0)
-#define lockdep_assert_held_write(l)	do { (void)(l); } while (0)
+#define lockdep_assert_not_held(l)		do { (void)(l); } while (0)
+#define lockdep_assert_held_write(l)		do { (void)(l); } while (0)
 #define lockdep_assert_held_read(l)		do { (void)(l); } while (0)
 #define lockdep_assert_held_once(l)		do { (void)(l); } while (0)
 #define lockdep_assert_none_held_once()	do { } while (0)

include/linux/mutex.h

@@ -20,6 +20,7 @@
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
 
+struct ww_class;
 struct ww_acquire_ctx;
 
 /*
@@ -65,9 +66,6 @@ struct mutex {
 #endif
 };
 
-struct ww_class;
-struct ww_acquire_ctx;
-
 struct ww_mutex {
 	struct mutex base;
 	struct ww_acquire_ctx *ctx;

include/linux/rtmutex.h

@@ -31,12 +31,6 @@ struct rt_mutex {
 	raw_spinlock_t		wait_lock;
 	struct rb_root_cached   waiters;
 	struct task_struct	*owner;
-#ifdef CONFIG_DEBUG_RT_MUTEXES
-	int			save_state;
-	const char		*name, *file;
-	int			line;
-	void			*magic;
-#endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -46,35 +40,17 @@ struct rt_mutex_waiter;
 struct hrtimer_sleeper;
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
- extern int rt_mutex_debug_check_no_locks_freed(const void *from,
-						unsigned long len);
- extern void rt_mutex_debug_check_no_locks_held(struct task_struct *task);
+extern void rt_mutex_debug_task_free(struct task_struct *tsk);
 #else
- static inline int rt_mutex_debug_check_no_locks_freed(const void *from,
-						       unsigned long len)
- {
-	return 0;
- }
-# define rt_mutex_debug_check_no_locks_held(task)	do { } while (0)
+static inline void rt_mutex_debug_task_free(struct task_struct *tsk) { }
 #endif
 
-#ifdef CONFIG_DEBUG_RT_MUTEXES
-# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
-	, .name = #mutexname, .file = __FILE__, .line = __LINE__
-
-# define rt_mutex_init(mutex) \
+#define rt_mutex_init(mutex) \
 do { \
 	static struct lock_class_key __key; \
 	__rt_mutex_init(mutex, __func__, &__key); \
 } while (0)
 
- extern void rt_mutex_debug_task_free(struct task_struct *tsk);
-#else
-# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
-# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, NULL, NULL)
-# define rt_mutex_debug_task_free(t)			do { } while (0)
-#endif
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) \
 	, .dep_map = { .name = #mutexname }
@@ -86,7 +62,6 @@ do { \
 	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
 	, .waiters = RB_ROOT_CACHED \
 	, .owner = NULL \
-	__DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
 	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)}
 
 #define DEFINE_RT_MUTEX(mutexname) \
@@ -104,7 +79,6 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock)
 }
 
 extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key);
-extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass);
@@ -115,9 +89,6 @@ extern void rt_mutex_lock(struct rt_mutex *lock);
 #endif
 
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
-extern int rt_mutex_timed_lock(struct rt_mutex *lock,
-			       struct hrtimer_sleeper *timeout);
-
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 
 extern void rt_mutex_unlock(struct rt_mutex *lock);

include/linux/rwsem.h

@@ -110,7 +110,7 @@ do {								\
 
 /*
  * This is the same regardless of which rwsem implementation that is being used.
- * It is just a heuristic meant to be called by somebody alreadying holding the
+ * It is just a heuristic meant to be called by somebody already holding the
  * rwsem to see if somebody from an incompatible type is wanting access to the
  * lock.
  */

include/linux/static_call.h

@@ -118,9 +118,9 @@ extern void arch_static_call_transform(void *site, void *tramp, void *func, bool
 
 #define static_call_update(name, func)					\
 ({									\
-	BUILD_BUG_ON(!__same_type(*(func), STATIC_CALL_TRAMP(name)));	\
+	typeof(&STATIC_CALL_TRAMP(name)) __F = (func);			\
 	__static_call_update(&STATIC_CALL_KEY(name),			\
-			     STATIC_CALL_TRAMP_ADDR(name), func);	\
+			     STATIC_CALL_TRAMP_ADDR(name), __F);	\
 })
 
 #define static_call_query(name) (READ_ONCE(STATIC_CALL_KEY(name).func))

include/linux/ww_mutex.h

@@ -48,39 +48,26 @@ struct ww_acquire_ctx {
 #endif
 };
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) \
-		, .ww_class = class
-#else
-# define __WW_CLASS_MUTEX_INITIALIZER(lockname, class)
-#endif
-
 #define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die)	    \
 		{ .stamp = ATOMIC_LONG_INIT(0) \
 		, .acquire_name = #ww_class "_acquire" \
 		, .mutex_name = #ww_class "_mutex" \
 		, .is_wait_die = _is_wait_die }
 
-#define __WW_MUTEX_INITIALIZER(lockname, class) \
-		{ .base =  __MUTEX_INITIALIZER(lockname.base) \
-		__WW_CLASS_MUTEX_INITIALIZER(lockname, class) }
-
 #define DEFINE_WD_CLASS(classname) \
 	struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1)
 
 #define DEFINE_WW_CLASS(classname) \
 	struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0)
 
-#define DEFINE_WW_MUTEX(mutexname, ww_class) \
-	struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class)
-
 /**
  * ww_mutex_init - initialize the w/w mutex
  * @lock: the mutex to be initialized
  * @ww_class: the w/w class the mutex should belong to
  *
  * Initialize the w/w mutex to unlocked state and associate it with the given
- * class.
+ * class. Static define macro for w/w mutex is not provided and this function
+ * is the only way to properly initialize the w/w mutex.
  *
  * It is not allowed to initialize an already locked mutex.
  */

kernel/futex.c

@@ -981,6 +981,7 @@ static inline void exit_pi_state_list(struct task_struct *curr) { }
  * p->pi_lock:
  *
  *	p->pi_state_list -> pi_state->list, relation
+ *	pi_mutex->owner -> pi_state->owner, relation
  *
  * pi_state->refcount:
  *
@@ -1494,13 +1495,14 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
 {
 	u32 curval, newval;
+	struct rt_mutex_waiter *top_waiter;
 	struct task_struct *new_owner;
 	bool postunlock = false;
 	DEFINE_WAKE_Q(wake_q);
 	int ret = 0;
 
-	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
-	if (WARN_ON_ONCE(!new_owner)) {
+	top_waiter = rt_mutex_top_waiter(&pi_state->pi_mutex);
+	if (WARN_ON_ONCE(!top_waiter)) {
 		/*
 		 * As per the comment in futex_unlock_pi() this should not happen.
 		 *
@@ -1513,6 +1515,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 		goto out_unlock;
 	}
 
+	new_owner = top_waiter->task;
+
 	/*
 	 * We pass it to the next owner. The WAITERS bit is always kept
 	 * enabled while there is PI state around. We cleanup the owner
@@ -2315,19 +2319,15 @@ static int unqueue_me(struct futex_q *q)
 
 /*
  * PI futexes can not be requeued and must remove themself from the
- * hash bucket. The hash bucket lock (i.e. lock_ptr) is held on entry
- * and dropped here.
+ * hash bucket. The hash bucket lock (i.e. lock_ptr) is held.
  */
 static void unqueue_me_pi(struct futex_q *q)
-	__releases(q->lock_ptr)
 {
 	__unqueue_futex(q);
 
 	BUG_ON(!q->pi_state);
 	put_pi_state(q->pi_state);
 	q->pi_state = NULL;
-
-	spin_unlock(q->lock_ptr);
 }
 
 static int __fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
@@ -2909,8 +2909,8 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	if (res)
 		ret = (res < 0) ? res : 0;
 
-	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
+	spin_unlock(q.lock_ptr);
 	goto out;
 
 out_unlock_put_key:
@@ -3237,15 +3237,14 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * reference count.
 	 */
 
-	/* Check if the requeue code acquired the second futex for us. */
+	/*
+	 * Check if the requeue code acquired the second futex for us and do
+	 * any pertinent fixup.
+	 */
 	if (!q.rt_waiter) {
-		/*
-		 * Got the lock. We might not be the anticipated owner if we
-		 * did a lock-steal - fix up the PI-state in that case.
-		 */
 		if (q.pi_state && (q.pi_state->owner != current)) {
 			spin_lock(q.lock_ptr);
-			ret = fixup_pi_state_owner(uaddr2, &q, current);
+			ret = fixup_owner(uaddr2, &q, true);
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
@@ -3287,8 +3286,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		if (res)
 			ret = (res < 0) ? res : 0;
 
-		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
+		spin_unlock(q.lock_ptr);
 	}
 
 	if (ret == -EINTR) {