locking/local_lock: Add local nested BH locking infrastructure.

Add local_lock_nested_bh() locking. It is based on local_lock_t and the
naming follows the preempt_disable_nested() example.

For !PREEMPT_RT + !LOCKDEP it is a per-CPU annotation for locking
assumptions based on local_bh_disable(). The macro is optimized away
during compilation.
For !PREEMPT_RT + LOCKDEP the local_lock_nested_bh() is reduced to
the usual lock-acquire plus lockdep_assert_in_softirq() - ensuring that
BH is disabled.

For PREEMPT_RT local_lock_nested_bh() acquires the specified per-CPU
lock. It does not disable CPU migration because it relies on
local_bh_disable() disabling CPU migration.
With LOCKDEP it performans the usual lockdep checks as with !PREEMPT_RT.
Due to include hell the softirq check has been moved spinlock.c.

The intention is to use this locking in places where locking of a per-CPU
variable relies on BH being disabled. Instead of treating disabled
bottom halves as a big per-CPU lock, PREEMPT_RT can use this to reduce
the locking scope to what actually needs protecting.
A side effect is that it also documents the protection scope of the
per-CPU variables.

Acked-by: Peter Zijlstra (Intel) <[e-mail]>
Reviewed-by: Thomas Gleixner <[e-mail]>
Signed-off-by: Sebastian Andrzej Siewior <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/linux/local_lock.h

···
 		    local_unlock_irqrestore(_T->lock, _T->flags),
 		    unsigned long flags)
 
+#define local_lock_nested_bh(_lock)				\
+	__local_lock_nested_bh(_lock)
+
+#define local_unlock_nested_bh(_lock)				\
+	__local_unlock_nested_bh(_lock)
+
+DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*,
+	     local_lock_nested_bh(_T),
+	     local_unlock_nested_bh(_T))
+
 #endif

include/linux/local_lock_internal.h

···
 	local_lock_debug_init(lock);				\
 } while (0)
 
+#define __spinlock_nested_bh_init(lock)				\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key,  \
+			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_NORMAL);			\
+	local_lock_debug_init(lock);				\
+} while (0)
+
 #define __local_lock(lock)					\
 	do {							\
 		preempt_disable();				\
···
 		local_lock_release(this_cpu_ptr(lock));		\
 		local_irq_restore(flags);			\
 	} while (0)
+
+#define __local_lock_nested_bh(lock)				\
+	do {							\
+		lockdep_assert_in_softirq();			\
+		local_lock_acquire(this_cpu_ptr(lock));	\
+	} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+	local_lock_release(this_cpu_ptr(lock))
 
 #else /* !CONFIG_PREEMPT_RT */
 
···
 #define __local_unlock_irq(lock)		__local_unlock(lock)
 
 #define __local_unlock_irqrestore(lock, flags)	__local_unlock(lock)
+
+#define __local_lock_nested_bh(lock)				\
+do {								\
+	lockdep_assert_in_softirq_func();			\
+	spin_lock(this_cpu_ptr(lock));				\
+} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+do {								\
+	spin_unlock(this_cpu_ptr((lock)));			\
+} while (0)
 
 #endif /* CONFIG_PREEMPT_RT */

include/linux/lockdep.h

···
 		     (!in_softirq() || in_irq() || in_nmi()));		\
 } while (0)
 
+extern void lockdep_assert_in_softirq_func(void);
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
···
 # define lockdep_assert_preemption_enabled() do { } while (0)
 # define lockdep_assert_preemption_disabled() do { } while (0)
 # define lockdep_assert_in_softirq() do { } while (0)
+# define lockdep_assert_in_softirq_func() do { } while (0)
 #endif
 
 #ifdef CONFIG_PROVE_RAW_LOCK_NESTING

kernel/locking/spinlock.c

···
 	&& addr < (unsigned long)__lock_text_end;
 }
 EXPORT_SYMBOL(in_lock_functions);
+
+#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_PREEMPT_RT)
+void notrace lockdep_assert_in_softirq_func(void)
+{
+	lockdep_assert_in_softirq();
+}
+EXPORT_SYMBOL(lockdep_assert_in_softirq_func);
+#endif