Merge tag 'locking-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Core locking & atomics:

     - Convert all architectures to ARCH_ATOMIC: move every architecture
       to ARCH_ATOMIC, then get rid of ARCH_ATOMIC and all the
       transitory facilities and #ifdefs.

       Much reduction in complexity from that series:

           63 files changed, 756 insertions(+), 4094 deletions(-)

     - Self-test enhancements

 - Futexes:

     - Add the new FUTEX_LOCK_PI2 ABI, which is a variant that doesn't
       set FLAGS_CLOCKRT (.e. uses CLOCK_MONOTONIC).

       [ The temptation to repurpose FUTEX_LOCK_PI's implicit setting of
         FLAGS_CLOCKRT & invert the flag's meaning to avoid having to
         introduce a new variant was resisted successfully. ]

     - Enhance futex self-tests

 - Lockdep:

     - Fix dependency path printouts

     - Optimize trace saving

     - Broaden & fix wait-context checks

 - Misc cleanups and fixes.

* tag 'locking-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits)
  locking/lockdep: Correct the description error for check_redundant()
  futex: Provide FUTEX_LOCK_PI2 to support clock selection
  futex: Prepare futex_lock_pi() for runtime clock selection
  lockdep/selftest: Remove wait-type RCU_CALLBACK tests
  lockdep/selftests: Fix selftests vs PROVE_RAW_LOCK_NESTING
  lockdep: Fix wait-type for empty stack
  locking/selftests: Add a selftest for check_irq_usage()
  lockding/lockdep: Avoid to find wrong lock dep path in check_irq_usage()
  locking/lockdep: Remove the unnecessary trace saving
  locking/lockdep: Fix the dep path printing for backwards BFS
  selftests: futex: Add futex compare requeue test
  selftests: futex: Add futex wait test
  seqlock: Remove trailing semicolon in macros
  locking/lockdep: Reduce LOCKDEP dependency list
  locking/lockdep,doc: Improve readability of the block matrix
  locking/atomics: atomic-instrumented: simplify ifdeffery
  locking/atomic: delete !ARCH_ATOMIC remnants
  locking/atomic: xtensa: move to ARCH_ATOMIC
  locking/atomic: sparc: move to ARCH_ATOMIC
  locking/atomic: sh: move to ARCH_ATOMIC
  ...

lib/Kconfig.debug

@@ -1372,7 +1372,6 @@ config LOCKDEP
 	bool
 	depends on DEBUG_KERNEL && LOCK_DEBUGGING_SUPPORT
 	select STACKTRACE
-	depends on FRAME_POINTER || MIPS || PPC || S390 || MICROBLAZE || ARM || ARC || X86
 	select KALLSYMS
 	select KALLSYMS_ALL
 

lib/atomic64.c

@@ -42,7 +42,7 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 	return &atomic64_lock[addr & (NR_LOCKS - 1)].lock;
 }
 
-s64 atomic64_read(const atomic64_t *v)
+s64 generic_atomic64_read(const atomic64_t *v)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -53,9 +53,9 @@ s64 atomic64_read(const atomic64_t *v)
 	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
-EXPORT_SYMBOL(atomic64_read);
+EXPORT_SYMBOL(generic_atomic64_read);
 
-void atomic64_set(atomic64_t *v, s64 i)
+void generic_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -64,10 +64,10 @@ void atomic64_set(atomic64_t *v, s64 i)
 	v->counter = i;
 	raw_spin_unlock_irqrestore(lock, flags);
 }
-EXPORT_SYMBOL(atomic64_set);
+EXPORT_SYMBOL(generic_atomic64_set);
 
 #define ATOMIC64_OP(op, c_op)						\
-void atomic64_##op(s64 a, atomic64_t *v)				\
+void generic_atomic64_##op(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
@@ -76,10 +76,10 @@ void atomic64_##op(s64 a, atomic64_t *v)				\
 	v->counter c_op a;						\
 	raw_spin_unlock_irqrestore(lock, flags);			\
 }									\
-EXPORT_SYMBOL(atomic64_##op);
+EXPORT_SYMBOL(generic_atomic64_##op);
 
 #define ATOMIC64_OP_RETURN(op, c_op)					\
-s64 atomic64_##op##_return(s64 a, atomic64_t *v)			\
+s64 generic_atomic64_##op##_return(s64 a, atomic64_t *v)		\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
@@ -90,10 +90,10 @@ s64 atomic64_##op##_return(s64 a, atomic64_t *v)			\
 	raw_spin_unlock_irqrestore(lock, flags);			\
 	return val;							\
 }									\
-EXPORT_SYMBOL(atomic64_##op##_return);
+EXPORT_SYMBOL(generic_atomic64_##op##_return);
 
 #define ATOMIC64_FETCH_OP(op, c_op)					\
-s64 atomic64_fetch_##op(s64 a, atomic64_t *v)				\
+s64 generic_atomic64_fetch_##op(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
@@ -105,7 +105,7 @@ s64 atomic64_fetch_##op(s64 a, atomic64_t *v)				\
 	raw_spin_unlock_irqrestore(lock, flags);			\
 	return val;							\
 }									\
-EXPORT_SYMBOL(atomic64_fetch_##op);
+EXPORT_SYMBOL(generic_atomic64_fetch_##op);
 
 #define ATOMIC64_OPS(op, c_op)						\
 	ATOMIC64_OP(op, c_op)						\
@@ -130,7 +130,7 @@ ATOMIC64_OPS(xor, ^=)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-s64 atomic64_dec_if_positive(atomic64_t *v)
+s64 generic_atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -143,9 +143,9 @@ s64 atomic64_dec_if_positive(atomic64_t *v)
 	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
-EXPORT_SYMBOL(atomic64_dec_if_positive);
+EXPORT_SYMBOL(generic_atomic64_dec_if_positive);
 
-s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
+s64 generic_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -158,9 +158,9 @@ s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
-EXPORT_SYMBOL(atomic64_cmpxchg);
+EXPORT_SYMBOL(generic_atomic64_cmpxchg);
 
-s64 atomic64_xchg(atomic64_t *v, s64 new)
+s64 generic_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -172,9 +172,9 @@ s64 atomic64_xchg(atomic64_t *v, s64 new)
 	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
-EXPORT_SYMBOL(atomic64_xchg);
+EXPORT_SYMBOL(generic_atomic64_xchg);
 
-s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+s64 generic_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -188,4 +188,4 @@ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 
 	return val;
 }
-EXPORT_SYMBOL(atomic64_fetch_add_unless);
+EXPORT_SYMBOL(generic_atomic64_fetch_add_unless);

lib/locking-selftest.c

@@ -53,6 +53,7 @@ __setup("debug_locks_verbose=", setup_debug_locks_verbose);
 #define LOCKTYPE_WW	0x10
 #define LOCKTYPE_RTMUTEX 0x20
 #define LOCKTYPE_LL	0x40
+#define LOCKTYPE_SPECIAL 0x80
 
 static struct ww_acquire_ctx t, t2;
 static struct ww_mutex o, o2, o3;
@@ -194,6 +195,7 @@ static void init_shared_classes(void)
 #define HARDIRQ_ENTER()				\
 	local_irq_disable();			\
 	__irq_enter();				\
+	lockdep_hardirq_threaded();		\
 	WARN_ON(!in_irq());
 
 #define HARDIRQ_EXIT()				\
@@ -2492,16 +2494,6 @@ static void rcu_sched_exit(int *_)
 	int rcu_sched_guard_##name __guard(rcu_sched_exit);	\
 	rcu_read_lock_sched();
 
-static void rcu_callback_exit(int *_)
-{
-	rcu_lock_release(&rcu_callback_map);
-}
-
-#define RCU_CALLBACK_CONTEXT(name, ...)					\
-	int rcu_callback_guard_##name __guard(rcu_callback_exit);	\
-	rcu_lock_acquire(&rcu_callback_map);
-
-
 static void raw_spinlock_exit(raw_spinlock_t **lock)
 {
 	raw_spin_unlock(*lock);
@@ -2558,8 +2550,6 @@ static void __maybe_unused inner##_in_##outer(void)				\
  * ---------------+-------+----------+------+-------
  * RCU_BH         |   o   |    o     |  o   |  x
  * ---------------+-------+----------+------+-------
- * RCU_CALLBACK   |   o   |    o     |  o   |  x
- * ---------------+-------+----------+------+-------
  * RCU_SCHED      |   o   |    o     |  x   |  x
  * ---------------+-------+----------+------+-------
  * RAW_SPIN       |   o   |    o     |  x   |  x
@@ -2576,7 +2566,6 @@ GENERATE_2_CONTEXT_TESTCASE(NOTTHREADED_HARDIRQ, , inner, inner_lock)		\
 GENERATE_2_CONTEXT_TESTCASE(SOFTIRQ, , inner, inner_lock)			\
 GENERATE_2_CONTEXT_TESTCASE(RCU, , inner, inner_lock)				\
 GENERATE_2_CONTEXT_TESTCASE(RCU_BH, , inner, inner_lock)			\
-GENERATE_2_CONTEXT_TESTCASE(RCU_CALLBACK, , inner, inner_lock)			\
 GENERATE_2_CONTEXT_TESTCASE(RCU_SCHED, , inner, inner_lock)			\
 GENERATE_2_CONTEXT_TESTCASE(RAW_SPINLOCK, raw_lock_A, inner, inner_lock)	\
 GENERATE_2_CONTEXT_TESTCASE(SPINLOCK, lock_A, inner, inner_lock)		\
@@ -2638,10 +2627,6 @@ static void wait_context_tests(void)
 	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU_BH);
 	pr_cont("\n");
 
-	print_testname("in RCU callback context");
-	DO_CONTEXT_TESTCASE_OUTER_LIMITED_PREEMPTIBLE(RCU_CALLBACK);
-	pr_cont("\n");
-
 	print_testname("in RCU-sched context");
 	DO_CONTEXT_TESTCASE_OUTER_NOT_PREEMPTIBLE(RCU_SCHED);
 	pr_cont("\n");
@@ -2744,6 +2729,66 @@ static void local_lock_tests(void)
 	pr_cont("\n");
 }
 
+static void hardirq_deadlock_softirq_not_deadlock(void)
+{
+	/* mutex_A is hardirq-unsafe and softirq-unsafe */
+	/* mutex_A -> lock_C */
+	mutex_lock(&mutex_A);
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_C);
+	spin_unlock(&lock_C);
+	HARDIRQ_ENABLE();
+	mutex_unlock(&mutex_A);
+
+	/* lock_A is hardirq-safe */
+	HARDIRQ_ENTER();
+	spin_lock(&lock_A);
+	spin_unlock(&lock_A);
+	HARDIRQ_EXIT();
+
+	/* lock_A -> lock_B */
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_A);
+	spin_lock(&lock_B);
+	spin_unlock(&lock_B);
+	spin_unlock(&lock_A);
+	HARDIRQ_ENABLE();
+
+	/* lock_B -> lock_C */
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_B);
+	spin_lock(&lock_C);
+	spin_unlock(&lock_C);
+	spin_unlock(&lock_B);
+	HARDIRQ_ENABLE();
+
+	/* lock_D is softirq-safe */
+	SOFTIRQ_ENTER();
+	spin_lock(&lock_D);
+	spin_unlock(&lock_D);
+	SOFTIRQ_EXIT();
+
+	/* And lock_D is hardirq-unsafe */
+	SOFTIRQ_DISABLE();
+	spin_lock(&lock_D);
+	spin_unlock(&lock_D);
+	SOFTIRQ_ENABLE();
+
+	/*
+	 * mutex_A -> lock_C -> lock_D is softirq-unsafe -> softirq-safe, not
+	 * deadlock.
+	 *
+	 * lock_A -> lock_B -> lock_C -> lock_D is hardirq-safe ->
+	 * hardirq-unsafe, deadlock.
+	 */
+	HARDIRQ_DISABLE();
+	spin_lock(&lock_C);
+	spin_lock(&lock_D);
+	spin_unlock(&lock_D);
+	spin_unlock(&lock_C);
+	HARDIRQ_ENABLE();
+}
+
 void locking_selftest(void)
 {
 	/*
@@ -2872,6 +2917,10 @@ void locking_selftest(void)
 
 	local_lock_tests();
 
+	print_testname("hardirq_unsafe_softirq_safe");
+	dotest(hardirq_deadlock_softirq_not_deadlock, FAILURE, LOCKTYPE_SPECIAL);
+	pr_cont("\n");
+
 	if (unexpected_testcase_failures) {
 		printk("-----------------------------------------------------------------\n");
 		debug_locks = 0;