Merge branch 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fixes from Ingo Molnar:
 "Misc fixes:

   - Fix a S390 boot hang that was caused by the lock-break logic.
     Remove lock-break to begin with, as review suggested it was
     unreasonably fragile and our confidence in its continued good
     health is lower than our confidence in its removal.

   - Remove the lockdep cross-release checking code for now, because of
     unresolved false positive warnings. This should make lockdep work
     well everywhere again.

   - Get rid of the final (and single) ACCESS_ONCE() straggler and
     remove the API from v4.15.

   - Fix a liblockdep build warning"

* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tools/lib/lockdep: Add missing declaration of 'pr_cont()'
  checkpatch: Remove ACCESS_ONCE() warning
  compiler.h: Remove ACCESS_ONCE()
  tools/include: Remove ACCESS_ONCE()
  tools/perf: Convert ACCESS_ONCE() to READ_ONCE()
  locking/lockdep: Remove the cross-release locking checks
  locking/core: Remove break_lock field when CONFIG_GENERIC_LOCKBREAK=y
  locking/core: Fix deadlock during boot on systems with GENERIC_LOCKBREAK

include/linux/compiler.h

@@ -220,21 +220,21 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 /*
  * Prevent the compiler from merging or refetching reads or writes. The
  * compiler is also forbidden from reordering successive instances of
- * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
- * compiler is aware of some particular ordering.  One way to make the
- * compiler aware of ordering is to put the two invocations of READ_ONCE,
- * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
  *
- * In contrast to ACCESS_ONCE these two macros will also work on aggregate
- * data types like structs or unions. If the size of the accessed data
- * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at
- * least two memcpy()s: one for the __builtin_memcpy() and then one for
- * the macro doing the copy of variable - '__u' allocated on the stack.
+ * These two macros will also work on aggregate data types like structs or
+ * unions. If the size of the accessed data type exceeds the word size of
+ * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will
+ * fall back to memcpy(). There's at least two memcpy()s: one for the
+ * __builtin_memcpy() and then one for the macro doing the copy of variable
+ * - '__u' allocated on the stack.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
  * mutilate accesses that either do not require ordering or that interact
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.
@@ -327,29 +327,4 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 	compiletime_assert(__native_word(t),				\
 		"Need native word sized stores/loads for atomicity.")
 
-/*
- * Prevent the compiler from merging or refetching accesses.  The compiler
- * is also forbidden from reordering successive instances of ACCESS_ONCE(),
- * but only when the compiler is aware of some particular ordering.  One way
- * to make the compiler aware of ordering is to put the two invocations of
- * ACCESS_ONCE() in different C statements.
- *
- * ACCESS_ONCE will only work on scalar types. For union types, ACCESS_ONCE
- * on a union member will work as long as the size of the member matches the
- * size of the union and the size is smaller than word size.
- *
- * The major use cases of ACCESS_ONCE used to be (1) Mediating communication
- * between process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
- * mutilate accesses that either do not require ordering or that interact
- * with an explicit memory barrier or atomic instruction that provides the
- * required ordering.
- *
- * If possible use READ_ONCE()/WRITE_ONCE() instead.
- */
-#define __ACCESS_ONCE(x) ({ \
-	 __maybe_unused typeof(x) __var = (__force typeof(x)) 0; \
-	(volatile typeof(x) *)&(x); })
-#define ACCESS_ONCE(x) (*__ACCESS_ONCE(x))
-
 #endif /* __LINUX_COMPILER_H */

include/linux/completion.h

@@ -10,9 +10,6 @@
  */
 
 #include <linux/wait.h>
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-#include <linux/lockdep.h>
-#endif
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -29,58 +26,16 @@
 struct completion {
 	unsigned int done;
 	wait_queue_head_t wait;
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-	struct lockdep_map_cross map;
-#endif
 };
 
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-static inline void complete_acquire(struct completion *x)
-{
-	lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_);
-}
-
-static inline void complete_release(struct completion *x)
-{
-	lock_release((struct lockdep_map *)&x->map, 0, _RET_IP_);
-}
-
-static inline void complete_release_commit(struct completion *x)
-{
-	lock_commit_crosslock((struct lockdep_map *)&x->map);
-}
-
-#define init_completion_map(x, m)					\
-do {									\
-	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
-			(m)->name, (m)->key, 0);				\
-	__init_completion(x);						\
-} while (0)
-
-#define init_completion(x)						\
-do {									\
-	static struct lock_class_key __key;				\
-	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
-			"(completion)" #x,				\
-			&__key, 0);					\
-	__init_completion(x);						\
-} while (0)
-#else
 #define init_completion_map(x, m) __init_completion(x)
 #define init_completion(x) __init_completion(x)
 static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
 static inline void complete_release_commit(struct completion *x) {}
-#endif
 
-#ifdef CONFIG_LOCKDEP_COMPLETIONS
-#define COMPLETION_INITIALIZER(work) \
-	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
-	STATIC_CROSS_LOCKDEP_MAP_INIT("(completion)" #work, &(work)) }
-#else
 #define COMPLETION_INITIALIZER(work) \
 	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
-#endif
 
 #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
 	(*({ init_completion_map(&(work), &(map)); &(work); }))

include/linux/lockdep.h

@@ -158,12 +158,6 @@ struct lockdep_map {
 	int				cpu;
 	unsigned long			ip;
 #endif
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-	/*
-	 * Whether it's a crosslock.
-	 */
-	int				cross;
-#endif
 };
 
 static inline void lockdep_copy_map(struct lockdep_map *to,
@@ -267,95 +261,8 @@ struct held_lock {
 	unsigned int hardirqs_off:1;
 	unsigned int references:12;					/* 32 bits */
 	unsigned int pin_count;
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-	/*
-	 * Generation id.
-	 *
-	 * A value of cross_gen_id will be stored when holding this,
-	 * which is globally increased whenever each crosslock is held.
-	 */
-	unsigned int gen_id;
-#endif
-};
-
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-#define MAX_XHLOCK_TRACE_ENTRIES 5
-
-/*
- * This is for keeping locks waiting for commit so that true dependencies
- * can be added at commit step.
- */
-struct hist_lock {
-	/*
-	 * Id for each entry in the ring buffer. This is used to
-	 * decide whether the ring buffer was overwritten or not.
-	 *
-	 * For example,
-	 *
-	 *           |<----------- hist_lock ring buffer size ------->|
-	 *           pppppppppppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiii
-	 * wrapped > iiiiiiiiiiiiiiiiiiiiiiiiiii.......................
-	 *
-	 *           where 'p' represents an acquisition in process
-	 *           context, 'i' represents an acquisition in irq
-	 *           context.
-	 *
-	 * In this example, the ring buffer was overwritten by
-	 * acquisitions in irq context, that should be detected on
-	 * rollback or commit.
-	 */
-	unsigned int hist_id;
-
-	/*
-	 * Seperate stack_trace data. This will be used at commit step.
-	 */
-	struct stack_trace	trace;
-	unsigned long		trace_entries[MAX_XHLOCK_TRACE_ENTRIES];
-
-	/*
-	 * Seperate hlock instance. This will be used at commit step.
-	 *
-	 * TODO: Use a smaller data structure containing only necessary
-	 * data. However, we should make lockdep code able to handle the
-	 * smaller one first.
-	 */
-	struct held_lock	hlock;
 };
 
-/*
- * To initialize a lock as crosslock, lockdep_init_map_crosslock() should
- * be called instead of lockdep_init_map().
- */
-struct cross_lock {
-	/*
-	 * When more than one acquisition of crosslocks are overlapped,
-	 * we have to perform commit for them based on cross_gen_id of
-	 * the first acquisition, which allows us to add more true
-	 * dependencies.
-	 *
-	 * Moreover, when no acquisition of a crosslock is in progress,
-	 * we should not perform commit because the lock might not exist
-	 * any more, which might cause incorrect memory access. So we
-	 * have to track the number of acquisitions of a crosslock.
-	 */
-	int nr_acquire;
-
-	/*
-	 * Seperate hlock instance. This will be used at commit step.
-	 *
-	 * TODO: Use a smaller data structure containing only necessary
-	 * data. However, we should make lockdep code able to handle the
-	 * smaller one first.
-	 */
-	struct held_lock	hlock;
-};
-
-struct lockdep_map_cross {
-	struct lockdep_map map;
-	struct cross_lock xlock;
-};
-#endif
-
 /*
  * Initialization, self-test and debugging-output methods:
  */
@@ -560,37 +467,6 @@ enum xhlock_context_t {
 	XHLOCK_CTX_NR,
 };
 
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-extern void lockdep_init_map_crosslock(struct lockdep_map *lock,
-				       const char *name,
-				       struct lock_class_key *key,
-				       int subclass);
-extern void lock_commit_crosslock(struct lockdep_map *lock);
-
-/*
- * What we essencially have to initialize is 'nr_acquire'. Other members
- * will be initialized in add_xlock().
- */
-#define STATIC_CROSS_LOCK_INIT() \
-	{ .nr_acquire = 0,}
-
-#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \
-	{ .map.name = (_name), .map.key = (void *)(_key), \
-	  .map.cross = 1, .xlock = STATIC_CROSS_LOCK_INIT(), }
-
-/*
- * To initialize a lockdep_map statically use this macro.
- * Note that _name must not be NULL.
- */
-#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
-	{ .name = (_name), .key = (void *)(_key), .cross = 0, }
-
-extern void crossrelease_hist_start(enum xhlock_context_t c);
-extern void crossrelease_hist_end(enum xhlock_context_t c);
-extern void lockdep_invariant_state(bool force);
-extern void lockdep_init_task(struct task_struct *task);
-extern void lockdep_free_task(struct task_struct *task);
-#else /* !CROSSRELEASE */
 #define lockdep_init_map_crosslock(m, n, k, s) do {} while (0)
 /*
  * To initialize a lockdep_map statically use this macro.
@@ -604,7 +480,6 @@ static inline void crossrelease_hist_end(enum xhlock_context_t c) {}
 static inline void lockdep_invariant_state(bool force) {}
 static inline void lockdep_init_task(struct task_struct *task) {}
 static inline void lockdep_free_task(struct task_struct *task) {}
-#endif /* CROSSRELEASE */
 
 #ifdef CONFIG_LOCK_STAT
 

include/linux/rwlock_types.h

@@ -10,9 +10,6 @@
  */
 typedef struct {
 	arch_rwlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
-	unsigned int break_lock;
-#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	unsigned int magic, owner_cpu;
 	void *owner;

include/linux/sched.h

@@ -849,17 +849,6 @@ struct task_struct {
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
 #endif
 
-#ifdef CONFIG_LOCKDEP_CROSSRELEASE
-#define MAX_XHLOCKS_NR 64UL
-	struct hist_lock *xhlocks; /* Crossrelease history locks */
-	unsigned int xhlock_idx;
-	/* For restoring at history boundaries */
-	unsigned int xhlock_idx_hist[XHLOCK_CTX_NR];
-	unsigned int hist_id;
-	/* For overwrite check at each context exit */
-	unsigned int hist_id_save[XHLOCK_CTX_NR];
-#endif
-
 #ifdef CONFIG_UBSAN
 	unsigned int			in_ubsan;
 #endif

include/linux/spinlock.h

@@ -107,16 +107,11 @@ do {								\
 
 #define raw_spin_is_locked(lock)	arch_spin_is_locked(&(lock)->raw_lock)
 
-#ifdef CONFIG_GENERIC_LOCKBREAK
-#define raw_spin_is_contended(lock) ((lock)->break_lock)
-#else
-
 #ifdef arch_spin_is_contended
 #define raw_spin_is_contended(lock)	arch_spin_is_contended(&(lock)->raw_lock)
 #else
 #define raw_spin_is_contended(lock)	(((void)(lock), 0))
 #endif /*arch_spin_is_contended*/
-#endif
 
 /*
  * This barrier must provide two things:

include/linux/spinlock_types.h

@@ -19,9 +19,6 @@
 
 typedef struct raw_spinlock {
 	arch_spinlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
-	unsigned int break_lock;
-#endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	unsigned int magic, owner_cpu;
 	void *owner;

kernel/locking/spinlock.c

@@ -66,12 +66,8 @@ void __lockfunc __raw_##op##_lock(locktype##_t *lock)			\
 			break;						\
 		preempt_enable();					\
 									\
-		if (!(lock)->break_lock)				\
-			(lock)->break_lock = 1;				\
-		while ((lock)->break_lock)				\
-			arch_##op##_relax(&lock->raw_lock);		\
+		arch_##op##_relax(&lock->raw_lock);			\
 	}								\
-	(lock)->break_lock = 0;						\
 }									\
 									\
 unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock)	\
@@ -86,12 +82,9 @@ unsigned long __lockfunc __raw_##op##_lock_irqsave(locktype##_t *lock)	\
 		local_irq_restore(flags);				\
 		preempt_enable();					\
 									\
-		if (!(lock)->break_lock)				\
-			(lock)->break_lock = 1;				\
-		while ((lock)->break_lock)				\
-			arch_##op##_relax(&lock->raw_lock);		\
+		arch_##op##_relax(&lock->raw_lock);			\
 	}								\
-	(lock)->break_lock = 0;						\
+									\
 	return flags;							\
 }									\
 									\

lib/Kconfig.debug

@@ -1099,8 +1099,6 @@ config PROVE_LOCKING
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
 	select DEBUG_LOCK_ALLOC
-	select LOCKDEP_CROSSRELEASE
-	select LOCKDEP_COMPLETIONS
 	select TRACE_IRQFLAGS
 	default n
 	help
@@ -1170,37 +1168,6 @@ config LOCK_STAT
 	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
 	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
 
-config LOCKDEP_CROSSRELEASE
-	bool
-	help
-	 This makes lockdep work for crosslock which is a lock allowed to
-	 be released in a different context from the acquisition context.
-	 Normally a lock must be released in the context acquiring the lock.
-	 However, relexing this constraint helps synchronization primitives
-	 such as page locks or completions can use the lock correctness
-	 detector, lockdep.
-
-config LOCKDEP_COMPLETIONS
-	bool
-	help
-	 A deadlock caused by wait_for_completion() and complete() can be
-	 detected by lockdep using crossrelease feature.
-
-config BOOTPARAM_LOCKDEP_CROSSRELEASE_FULLSTACK
-	bool "Enable the boot parameter, crossrelease_fullstack"
-	depends on LOCKDEP_CROSSRELEASE
-	default n
-	help
-	 The lockdep "cross-release" feature needs to record stack traces
-	 (of calling functions) for all acquisitions, for eventual later
-	 use during analysis. By default only a single caller is recorded,
-	 because the unwind operation can be very expensive with deeper
-	 stack chains.
-
-	 However a boot parameter, crossrelease_fullstack, was
-	 introduced since sometimes deeper traces are required for full
-	 analysis. This option turns on the boot parameter.
-
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP

scripts/checkpatch.pl

@@ -6233,28 +6233,6 @@ sub process {
 			}
 		}
 
-# whine about ACCESS_ONCE
-		if ($^V && $^V ge 5.10.0 &&
-		    $line =~ /\bACCESS_ONCE\s*$balanced_parens\s*(=(?!=))?\s*($FuncArg)?/) {
-			my $par = $1;
-			my $eq = $2;
-			my $fun = $3;
-			$par =~ s/^\(\s*(.*)\s*\)$/$1/;
-			if (defined($eq)) {
-				if (WARN("PREFER_WRITE_ONCE",
-					 "Prefer WRITE_ONCE(<FOO>, <BAR>) over ACCESS_ONCE(<FOO>) = <BAR>\n" . $herecurr) &&
-				    $fix) {
-					$fixed[$fixlinenr] =~ s/\bACCESS_ONCE\s*\(\s*\Q$par\E\s*\)\s*$eq\s*\Q$fun\E/WRITE_ONCE($par, $fun)/;
-				}
-			} else {
-				if (WARN("PREFER_READ_ONCE",
-					 "Prefer READ_ONCE(<FOO>) over ACCESS_ONCE(<FOO>)\n" . $herecurr) &&
-				    $fix) {
-					$fixed[$fixlinenr] =~ s/\bACCESS_ONCE\s*\(\s*\Q$par\E\s*\)/READ_ONCE($par)/;
-				}
-			}
-		}
-
 # check for mutex_trylock_recursive usage
 		if ($line =~ /mutex_trylock_recursive/) {
 			ERROR("LOCKING",

tools/include/linux/compiler.h

@@ -84,8 +84,6 @@
 
 #define uninitialized_var(x) x = *(&(x))
 
-#define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
-
 #include <linux/types.h>
 
 /*
@@ -135,20 +133,19 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
 /*
  * Prevent the compiler from merging or refetching reads or writes. The
  * compiler is also forbidden from reordering successive instances of
- * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
- * compiler is aware of some particular ordering.  One way to make the
- * compiler aware of ordering is to put the two invocations of READ_ONCE,
- * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
  *
- * In contrast to ACCESS_ONCE these two macros will also work on aggregate
- * data types like structs or unions. If the size of the accessed data
- * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
- * compile-time warning.
+ * These two macros will also work on aggregate data types like structs or
+ * unions. If the size of the accessed data type exceeds the word size of
+ * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will
+ * fall back to memcpy and print a compile-time warning.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
  * mutilate accesses that either do not require ordering or that interact
  * with an explicit memory barrier or atomic instruction that provides the
  * required ordering.

tools/include/linux/lockdep.h

@@ -48,6 +48,7 @@ static inline int debug_locks_off(void)
 #define printk(...) dprintf(STDOUT_FILENO, __VA_ARGS__)
 #define pr_err(format, ...) fprintf (stderr, format, ## __VA_ARGS__)
 #define pr_warn pr_err
+#define pr_cont pr_err
 
 #define list_del_rcu list_del
 

tools/perf/util/mmap.h

@@ -70,7 +70,7 @@ void perf_mmap__read_catchup(struct perf_mmap *md);
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
 	struct perf_event_mmap_page *pc = mm->base;
-	u64 head = ACCESS_ONCE(pc->data_head);
+	u64 head = READ_ONCE(pc->data_head);
 	rmb();
 	return head;
 }