[PATCH v2 14/16] rcu: Support reclaim for head-less object

[Uladzislau Rezki (Sony)]

Update the kvfree_call_rcu() function with head-less support.
This allows RCU to reclaim objects without an embedded rcu_head.

tree-RCU:
We introduce two chains of arrays to store SLAB-backed and vmalloc
pointers, each.  Storage in either of these arrays does not require
embedding an rcu_head within the object.

Maintaining the arrays may become impossible due to high memory
pressure. For such cases there is an emergency path. Objects with
rcu_head inside are just queued on a backup rcu_head list. Later on
that list is drained. As for the head-less variant, as the current
context can sleep, the following emergency measures are applied:
   a) Synchronously wait until a grace period has elapsed.
   b) Call kvfree().

tiny-RCU:
For double argument calls, there are no new changes in behavior. For
single argument call, kvfree() is directly inlined on the current
stack after a synchronize_rcu() call. Note that for tiny-RCU, any
call to synchronize_rcu() is actually a quiescent state, therefore
it does nothing.

Reviewed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Co-developed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
---
 include/linux/rcutiny.h | 18 ++++++++++++++++-
 kernel/rcu/tree.c       | 45 +++++++++++++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 00bbd0e328c8..e7e4ec5938af 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -31,9 +31,25 @@ static inline void synchronize_rcu_expedited(void)
 	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, rcu_callback_t func)
 {
-	call_rcu(head, func);
+	if (head) {
+		call_rcu(head, func);
+		return;
+	}
+
+	// kvfree_rcu(one_arg) call.
+	might_sleep();
+	synchronize_rcu();
+	kvfree((void *) func);
 }
 
 void rcu_qs(void);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index da29e6078392..2459830a3851 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3180,6 +3180,13 @@ kvfree_call_rcu_add_ptr_to_bulk(struct kfree_rcu_cpu *krcp, void *ptr)
 			if (IS_ENABLED(CONFIG_PREEMPT_RT))
 				return false;
 
+			/*
+			 * NOTE: For one argument of kvfree_rcu() we can
+			 * drop the lock and get the page in sleepable
+			 * context. That would allow to maintain an array
+			 * for the CONFIG_PREEMPT_RT as well if no cached
+			 * pages are available.
+			 */
 			bnode = (struct kvfree_rcu_bulk_data *)
 				__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		}
@@ -3219,16 +3226,33 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 {
 	unsigned long flags;
 	struct kfree_rcu_cpu *krcp;
+	bool success;
 	void *ptr;
 
+	if (head) {
+		ptr = (void *) head - (unsigned long) func;
+	} else {
+		/*
+		 * Please note there is a limitation for the head-less
+		 * variant, that is why there is a clear rule for such
+		 * objects: it can be used from might_sleep() context
+		 * only. For other places please embed an rcu_head to
+		 * your data.
+		 */
+		might_sleep();
+		ptr = (unsigned long *) func;
+	}
+
 	krcp = krc_this_cpu_lock(&flags);
-	ptr = (void *)head - (unsigned long)func;
 
 	// Queue the object but don't yet schedule the batch.
 	if (debug_rcu_head_queue(ptr)) {
 		// Probable double kfree_rcu(), just leak.
 		WARN_ONCE(1, "%s(): Double-freed call. rcu_head %p\n",
 			  __func__, head);
+
+		// Mark as success and leave.
+		success = true;
 		goto unlock_return;
 	}
 
@@ -3236,10 +3260,16 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 	 * Under high memory pressure GFP_NOWAIT can fail,
 	 * in that case the emergency path is maintained.
 	 */
-	if (unlikely(!kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr))) {
+	success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr);
+	if (!success) {
+		if (head == NULL)
+			// Inline if kvfree_rcu(one_arg) call.
+			goto unlock_return;
+
 		head->func = func;
 		head->next = krcp->head;
 		krcp->head = head;
+		success = true;
 	}
 
 	WRITE_ONCE(krcp->count, krcp->count + 1);
@@ -3253,6 +3283,17 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func)
 
 unlock_return:
 	krc_this_cpu_unlock(krcp, flags);
+
+	/*
+	 * Inline kvfree() after synchronize_rcu(). We can do
+	 * it from might_sleep() context only, so the current
+	 * CPU can pass the QS state.
+	 */
+	if (!success) {
+		debug_rcu_head_unqueue((struct rcu_head *) ptr);
+		synchronize_rcu();
+		kvfree(ptr);
+	}
 }
 EXPORT_SYMBOL_GPL(kvfree_call_rcu);
 
-- 
2.20.1