On ChromeOS, using this with the increased timeout, we see that we almost always
never need to initiate a new grace period. Testing also shows this frees large
amounts of unreclaimed memory, under intense kfree_rcu() pressure.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
v1->v2: Same logic but use polled grace periods instead of sampling gp_seq.

 kernel/rcu/tree.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 591187b6352e..ed41243f7a49 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2935,6 +2935,7 @@ struct kfree_rcu_cpu_work {
 
 /**
  * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
+ * @gp_snap: The GP snapshot recorded at the last scheduling of monitor work.
  * @head: List of kfree_rcu() objects not yet waiting for a grace period
  * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
  * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
@@ -2964,6 +2965,7 @@ struct kfree_rcu_cpu {
 	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
 	raw_spinlock_t lock;
 	struct delayed_work monitor_work;
+	unsigned long gp_snap;
 	bool initialized;
 	int count;
 
@@ -3167,6 +3169,7 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
 			mod_delayed_work(system_wq, &krcp->monitor_work, delay);
 		return;
 	}
+	krcp->gp_snap = get_state_synchronize_rcu();
 	queue_delayed_work(system_wq, &krcp->monitor_work, delay);
 }
 
@@ -3217,7 +3220,10 @@ static void kfree_rcu_monitor(struct work_struct *work)
 			// be that the work is in the pending state when
 			// channels have been detached following by each
 			// other.
-			queue_rcu_work(system_wq, &krwp->rcu_work);
+			if (poll_state_synchronize_rcu(krcp->gp_snap))
+				queue_work(system_wq, &krwp->rcu_work.work);
+			else
+				queue_rcu_work(system_wq, &krwp->rcu_work);
 		}
 	}
 
-- 
2.38.1.431.g37b22c650d-goog

> On ChromeOS, using this with the increased timeout, we see that we almost always
> never need to initiate a new grace period. Testing also shows this frees large
> amounts of unreclaimed memory, under intense kfree_rcu() pressure.
> 
> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> ---
> v1->v2: Same logic but use polled grace periods instead of sampling gp_seq.
> 
>  kernel/rcu/tree.c | 8 +++++++-
>  1 file changed, 7 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 591187b6352e..ed41243f7a49 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -2935,6 +2935,7 @@ struct kfree_rcu_cpu_work {
>  
>  /**
>   * struct kfree_rcu_cpu - batch up kfree_rcu() requests for RCU grace period
> + * @gp_snap: The GP snapshot recorded at the last scheduling of monitor work.
>   * @head: List of kfree_rcu() objects not yet waiting for a grace period
>   * @bkvhead: Bulk-List of kvfree_rcu() objects not yet waiting for a grace period
>   * @krw_arr: Array of batches of kfree_rcu() objects waiting for a grace period
> @@ -2964,6 +2965,7 @@ struct kfree_rcu_cpu {
>  	struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
>  	raw_spinlock_t lock;
>  	struct delayed_work monitor_work;
> +	unsigned long gp_snap;
>  	bool initialized;
>  	int count;
>  
> @@ -3167,6 +3169,7 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
>  			mod_delayed_work(system_wq, &krcp->monitor_work, delay);
>  		return;
>  	}
> +	krcp->gp_snap = get_state_synchronize_rcu();
>  	queue_delayed_work(system_wq, &krcp->monitor_work, delay);
>  }
>
How do you guarantee a full grace period for objects which proceed
to be placed into an input stream that is not yet detached?

>  
> @@ -3217,7 +3220,10 @@ static void kfree_rcu_monitor(struct work_struct *work)
>  			// be that the work is in the pending state when
>  			// channels have been detached following by each
>  			// other.
> -			queue_rcu_work(system_wq, &krwp->rcu_work);
> +			if (poll_state_synchronize_rcu(krcp->gp_snap))
> +				queue_work(system_wq, &krwp->rcu_work.work);
> +			else
> +				queue_rcu_work(system_wq, &krwp->rcu_work);
>  		}
>
Why do you want to queue a work over RCU-core?

1.
call_rcu()
   -> queue_work();
      -> do reclaim

if it can be improved and simplified as:

2.
queue_work();
    -> cond_synchronize_rcu(), do reclaim

Could you please clarify it?

--
Uladzislau Rezki