rcu: Remove kfree_call_rcu_nobatch()

Now that the kfree_rcu() special-casing has been removed from tree RCU,
this commit removes kfree_call_rcu_nobatch() since it is no longer needed.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

Documentation/admin-guide/kernel-parameters.txt

@@ -3991,10 +3991,6 @@
 			Number of loops doing rcuperf.kfree_alloc_num number
 			of allocations and frees.
 
-	rcuperf.kfree_no_batch= [KNL]
-			Use the non-batching (less efficient) version of kfree_rcu().
-			This is useful for comparing with the batched version.
-
 	rcuperf.nreaders= [KNL]
 			Set number of RCU readers.  The value -1 selects
 			N, where N is the number of CPUs.  A value

include/linux/rcutiny.h

@@ -39,11 +39,6 @@ static inline void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	call_rcu(head, func);
 }
 
-static inline void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func)
-{
-	call_rcu(head, func);
-}
-
 void rcu_qs(void);
 
 static inline void rcu_softirq_qs(void)

include/linux/rcutree.h

@@ -34,7 +34,6 @@ static inline void rcu_virt_note_context_switch(int cpu)
 
 void synchronize_rcu_expedited(void);
 void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func);
-void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func);
 
 void rcu_barrier(void);
 bool rcu_eqs_special_set(int cpu);

kernel/rcu/rcuperf.c

@@ -593,7 +593,6 @@ rcu_perf_shutdown(void *arg)
 torture_param(int, kfree_nthreads, -1, "Number of threads running loops of kfree_rcu().");
 torture_param(int, kfree_alloc_num, 8000, "Number of allocations and frees done in an iteration.");
 torture_param(int, kfree_loops, 10, "Number of loops doing kfree_alloc_num allocations and frees.");
-torture_param(int, kfree_no_batch, 0, "Use the non-batching (slower) version of kfree_rcu().");
 
 static struct task_struct **kfree_reader_tasks;
 static int kfree_nrealthreads;
@@ -632,14 +631,7 @@ kfree_perf_thread(void *arg)
 			if (!alloc_ptr)
 				return -ENOMEM;
 
-			if (!kfree_no_batch) {
-				kfree_rcu(alloc_ptr, rh);
-			} else {
-				rcu_callback_t cb;
-
-				cb = (rcu_callback_t)(unsigned long)offsetof(struct kfree_obj, rh);
-				kfree_call_rcu_nobatch(&(alloc_ptr->rh), cb);
-			}
+			kfree_rcu(alloc_ptr, rh);
 		}
 
 		cond_resched();

kernel/rcu/tree.c

@@ -2763,8 +2763,10 @@ static void kfree_rcu_work(struct work_struct *work)
 		rcu_lock_acquire(&rcu_callback_map);
 		trace_rcu_invoke_kfree_callback(rcu_state.name, head, offset);
 
-		/* Could be possible to optimize with kfree_bulk in future */
-		kfree((void *)head - offset);
+		if (!WARN_ON_ONCE(!__is_kfree_rcu_offset(offset))) {
+			/* Could be optimized with kfree_bulk() in future. */
+			kfree((void *)head - offset);
+		}
 
 		rcu_lock_release(&rcu_callback_map);
 		cond_resched_tasks_rcu_qs();
@@ -2835,16 +2837,6 @@ static void kfree_rcu_monitor(struct work_struct *work)
 		spin_unlock_irqrestore(&krcp->lock, flags);
 }
 
-/*
- * This version of kfree_call_rcu does not do batching of kfree_rcu() requests.
- * Used only by rcuperf torture test for comparison with kfree_rcu_batch().
- */
-void kfree_call_rcu_nobatch(struct rcu_head *head, rcu_callback_t func)
-{
-	__call_rcu(head, func);
-}
-EXPORT_SYMBOL_GPL(kfree_call_rcu_nobatch);
-
 /*
  * Queue a request for lazy invocation of kfree() after a grace period.
  *
@@ -2864,8 +2856,6 @@ void kfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
 
-	head->func = func;
-
 	local_irq_save(flags);	// For safely calling this_cpu_ptr().
 	krcp = this_cpu_ptr(&krc);
 	if (krcp->initialized)