lkml.org 
[lkml]   [2022]   [Oct]   [29]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH RFC] rcu/kfree: Do not request RCU when not needed
Date
On ChromeOS, I am (almost) always seeing the optimization trigger.
Tested boot up and trace_printk'ing how often it triggers.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
kernel/rcu/tree.c | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 591187b6352e..3e4c50b9fd33 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
+ * @rdp: The rdp of the CPU that this kfree_rcu corresponds to.
* @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 +2965,8 @@ struct kfree_rcu_cpu {
struct kfree_rcu_cpu_work krw_arr[KFREE_N_BATCHES];
raw_spinlock_t lock;
struct delayed_work monitor_work;
+ struct rcu_data *rdp;
+ unsigned long last_gp_seq;
bool initialized;
int count;

@@ -3167,6 +3170,7 @@ schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
mod_delayed_work(system_wq, &krcp->monitor_work, delay);
return;
}
+ krcp->last_gp_seq = krcp->rdp->gp_seq;
queue_delayed_work(system_wq, &krcp->monitor_work, delay);
}

@@ -3217,7 +3221,17 @@ 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);
+ //
+ // NOTE about gp_seq wrap: In case of gp_seq overflow,
+ // it is possible for rdp->gp_seq to be less than
+ // krcp->last_gp_seq even though a GP might be over. In
+ // this rare case, we would just have one extra GP.
+ if (krcp->last_gp_seq &&
+ rcu_seq_completed_gp(krcp->last_gp_seq, krcp->rdp->gp_seq)) {
+ queue_work(system_wq, &krwp->rcu_work.work);
+ } else {
+ queue_rcu_work(system_wq, &krwp->rcu_work);
+ }
}
}

@@ -4802,6 +4816,8 @@ static void __init kfree_rcu_batch_init(void)
for_each_possible_cpu(cpu) {
struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);

+ krcp->rdp = per_cpu_ptr(&rcu_data, cpu);
+ krcp->last_gp_seq = 0;
for (i = 0; i < KFREE_N_BATCHES; i++) {
INIT_RCU_WORK(&krcp->krw_arr[i].rcu_work, kfree_rcu_work);
krcp->krw_arr[i].krcp = krcp;
--
2.38.1.273.g43a17bfeac-goog
\
 
 \ /
  Last update: 2022-10-29 15:30    [W:0.078 / U:0.148 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site