On Wed, Jun 22, 2022 at 10:50:55PM +0000, Joel Fernandes (Google) wrote:
[..]
> diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
> index 2ccf5845957d..fec4fad6654b 100644
> --- a/kernel/rcu/tree.h
> +++ b/kernel/rcu/tree.h
> @@ -267,8 +267,9 @@ struct rcu_data {
> /* Values for nocb_defer_wakeup field in struct rcu_data. */
> #define RCU_NOCB_WAKE_NOT 0
> #define RCU_NOCB_WAKE_BYPASS 1
> -#define RCU_NOCB_WAKE 2
> -#define RCU_NOCB_WAKE_FORCE 3
> +#define RCU_NOCB_WAKE_LAZY 2
> +#define RCU_NOCB_WAKE 3
> +#define RCU_NOCB_WAKE_FORCE 4
>
> #define RCU_JIFFIES_TILL_FORCE_QS (1 + (HZ > 250) + (HZ > 500))
> /* For jiffies_till_first_fqs and */
> @@ -436,9 +437,10 @@ static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
> static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq);
> static void rcu_init_one_nocb(struct rcu_node *rnp);
> static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
> - unsigned long j);
> + unsigned long j, bool lazy);
> static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
> - bool *was_alldone, unsigned long flags);
> + bool *was_alldone, unsigned long flags,
> + bool lazy);
> static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty,
> unsigned long flags);
> static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level);
> diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
> index e369efe94fda..b9244f22e102 100644
> --- a/kernel/rcu/tree_nocb.h
> +++ b/kernel/rcu/tree_nocb.h
> @@ -256,6 +256,8 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force)
> return __wake_nocb_gp(rdp_gp, rdp, force, flags);
> }
>
> +#define LAZY_FLUSH_JIFFIES (10 * HZ)
> +
> /*
> * Arrange to wake the GP kthread for this NOCB group at some future
> * time when it is safe to do so.
> @@ -272,7 +274,10 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
> * Bypass wakeup overrides previous deferments. In case
> * of callback storm, no need to wake up too early.
> */
> - if (waketype == RCU_NOCB_WAKE_BYPASS) {
> + if (waketype == RCU_NOCB_WAKE_LAZY) {
> + mod_timer(&rdp_gp->nocb_timer, jiffies + LAZY_FLUSH_JIFFIES);
> + WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
> + } else if (waketype == RCU_NOCB_WAKE_BYPASS) {
> mod_timer(&rdp_gp->nocb_timer, jiffies + 2);
> WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype);
> } else {
> @@ -296,7 +301,7 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype,
> * Note that this function always returns true if rhp is NULL.
> */
> static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
> - unsigned long j)
> + unsigned long j, bool lazy)
> {
> struct rcu_cblist rcl;
>
> @@ -310,7 +315,13 @@ static bool rcu_nocb_do_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
> /* Note: ->cblist.len already accounts for ->nocb_bypass contents. */
> if (rhp)
> rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */
> - rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
> +
> + trace_printk("call_rcu_lazy callbacks = %ld\n", READ_ONCE(rdp->nocb_bypass.lazy_len));
Before anyone yells at me, that trace_printk() has been politely asked to take
a walk :-). It got mad at me, but on the next iteration, it wont be there.
thanks,
- Joel
