slab, rcu: move TINY_RCU variant of kvfree_rcu() to SLAB

Following the move of TREE_RCU implementation, let's move also the
TINY_RCU one for consistency and subsequent refactoring.

For simplicity, remove the separate inline __kvfree_call_rcu() as
TINY_RCU is not meant for high-performance hardware anyway.

Declare kvfree_call_rcu() in rcupdate.h to avoid header dependency
issues.

Also move the kvfree_rcu_barrier() declaration to slab.h

Reviewed-by: Uladzislau Rezki (Sony) <[e-mail]>
Reviewed-by: Joel Fernandes (Google) <[e-mail]>
Reviewed-by: Hyeonggon Yoo <[e-mail]>
Tested-by: Paul E. McKenney <[e-mail]>
Signed-off-by: Vlastimil Babka <[e-mail]>

include/linux/rcupdate.h

···
 #define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
 #define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr)
 
+/*
+ * In mm/slab_common.c, no suitable header to include here.
+ */
+void kvfree_call_rcu(struct rcu_head *head, void *ptr);
+
 #define kvfree_rcu_arg_2(ptr, rhf)					\
 do {									\
 	typeof (ptr) ___p = (ptr);					\

include/linux/rcutiny.h

···
 	synchronize_rcu();
 }
 
-/*
- * Add one more declaration of kvfree() here. It is
- * not so straight forward to just include <linux/mm.h>
- * where it is defined due to getting many compile
- * errors caused by that include.
- */
-extern void kvfree(const void *addr);
-
-static inline void __kvfree_call_rcu(struct rcu_head *head, void *ptr)
-{
-	if (head) {
-		call_rcu(head, (rcu_callback_t) ((void *) head - ptr));
-		return;
-	}
-
-	// kvfree_rcu(one_arg) call.
-	might_sleep();
-	synchronize_rcu();
-	kvfree(ptr);
-}
-
-static inline void kvfree_rcu_barrier(void)
-{
-	rcu_barrier();
-}
-
-#ifdef CONFIG_KASAN_GENERIC
-void kvfree_call_rcu(struct rcu_head *head, void *ptr);
-#else
-static inline void kvfree_call_rcu(struct rcu_head *head, void *ptr)
-{
-	__kvfree_call_rcu(head, ptr);
-}
-#endif
-
 void rcu_qs(void);
 
 static inline void rcu_softirq_qs(void)
···
 static inline bool rcu_inkernel_boot_has_ended(void) { return true; }
 static inline bool rcu_is_watching(void) { return true; }
 static inline void rcu_momentary_eqs(void) { }
-static inline void kfree_rcu_scheduler_running(void) { }
 
 /* Avoid RCU read-side critical sections leaking across. */
 static inline void rcu_all_qs(void) { barrier(); }

include/linux/rcutree.h

···
 }
 
 void synchronize_rcu_expedited(void);
-void kvfree_call_rcu(struct rcu_head *head, void *ptr);
-void kvfree_rcu_barrier(void);
 
 void rcu_barrier(void);
 void rcu_momentary_eqs(void);
-void kfree_rcu_scheduler_running(void);
 
 struct rcu_gp_oldstate {
 	unsigned long rgos_norm;

include/linux/slab.h

···
 #include <linux/gfp.h>
 #include <linux/overflow.h>
 #include <linux/types.h>
+#include <linux/rcupdate.h>
 #include <linux/workqueue.h>
 #include <linux/percpu-refcount.h>
 #include <linux/cleanup.h>
···
 extern void kvfree_sensitive(const void *addr, size_t len);
 
 unsigned int kmem_cache_size(struct kmem_cache *s);
+
+#ifdef CONFIG_TINY_RCU
+static inline void kvfree_rcu_barrier(void)
+{
+	rcu_barrier();
+}
+
+static inline void kfree_rcu_scheduler_running(void) { }
+#else
+void kvfree_rcu_barrier(void);
+
+void kfree_rcu_scheduler_running(void);
+#endif
 
 /**
  * kmalloc_size_roundup - Report allocation bucket size for the given size

kernel/rcu/tiny.c

···
 }
 EXPORT_SYMBOL_GPL(poll_state_synchronize_rcu);
 
-#ifdef CONFIG_KASAN_GENERIC
-void kvfree_call_rcu(struct rcu_head *head, void *ptr)
-{
-	if (head)
-		kasan_record_aux_stack(ptr);
-
-	__kvfree_call_rcu(head, ptr);
-}
-EXPORT_SYMBOL_GPL(kvfree_call_rcu);
-#endif
-
 void __init rcu_init(void)
 {
 	open_softirq(RCU_SOFTIRQ, rcu_process_callbacks);

mm/slab_common.c

···
 EXPORT_TRACEPOINT_SYMBOL(kfree);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
 
+#ifdef CONFIG_TINY_RCU
+
+void kvfree_call_rcu(struct rcu_head *head, void *ptr)
+{
+	if (head) {
+		kasan_record_aux_stack(ptr);
+		call_rcu(head, (rcu_callback_t) ((void *) head - ptr));
+		return;
+	}
+
+	// kvfree_rcu(one_arg) call.
+	might_sleep();
+	synchronize_rcu();
+	kvfree(ptr);
+}
+EXPORT_SYMBOL_GPL(kvfree_call_rcu);
+
+#endif
+
 /*
  * This rcu parameter is runtime-read-only. It reflects
  * a minimum allowed number of objects which can be cached