On Thu, Oct 29, 2020 at 05:50:04PM +0100, Uladzislau Rezki (Sony) wrote:
> The current memmory-allocation interface presents to following
> difficulties that this patch is designed to overcome
[...]
> ---
> kernel/rcu/tree.c | 109 ++++++++++++++++++++++++++++------------------
> 1 file changed, 66 insertions(+), 43 deletions(-)
>
> diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> index 06895ef85d69..f2da2a1cc716 100644
> --- a/kernel/rcu/tree.c
> +++ b/kernel/rcu/tree.c
> @@ -177,7 +177,7 @@ module_param(rcu_unlock_delay, int, 0444);
> * per-CPU. Object size is equal to one page. This value
> * can be changed at boot time.
> */
> -static int rcu_min_cached_objs = 2;
> +static int rcu_min_cached_objs = 5;
> module_param(rcu_min_cached_objs, int, 0444);
>
> /* Retrieve RCU kthreads priority for rcutorture */
> @@ -3084,6 +3084,9 @@ struct kfree_rcu_cpu_work {
> * In order to save some per-cpu space the list is singular.
> * Even though it is lockless an access has to be protected by the
> * per-cpu lock.
> + * @page_cache_work: A work to refill the cache when it is empty
> + * @work_in_progress: Indicates that page_cache_work is running
> + * @hrtimer: A hrtimer for scheduling a page_cache_work
> * @nr_bkv_objs: number of allocated objects at @bkvcache.
> *
> * This is a per-CPU structure. The reason that it is not included in
> @@ -3100,6 +3103,11 @@ struct kfree_rcu_cpu {
> bool monitor_todo;
> bool initialized;
> int count;
> +
> + struct work_struct page_cache_work;
> + atomic_t work_in_progress;
Does it need to be atomic? run_page_cache_work() is only called under a lock.
You can use xchg() there. And when you do the atomic_set, you can use
WRITE_ONCE as it is a data-race.
> @@ -4449,24 +4482,14 @@ static void __init kfree_rcu_batch_init(void)
>
> for_each_possible_cpu(cpu) {
> struct kfree_rcu_cpu *krcp = per_cpu_ptr(&krc, cpu);
> - struct kvfree_rcu_bulk_data *bnode;
>
> 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;
> }
>
> - for (i = 0; i < rcu_min_cached_objs; i++) {
> - bnode = (struct kvfree_rcu_bulk_data *)
> - __get_free_page(GFP_NOWAIT | __GFP_NOWARN);
> -
> - if (bnode)
> - put_cached_bnode(krcp, bnode);
> - else
> - pr_err("Failed to preallocate for %d CPU!\n", cpu);
> - }
> -
> INIT_DELAYED_WORK(&krcp->monitor_work, kfree_rcu_monitor);
> + INIT_WORK(&krcp->page_cache_work, fill_page_cache_func);
> krcp->initialized = true;
During initialization, is it not better to still pre-allocate? That way you
don't have to wait to get into a situation where you need to initially
allocate.
AFAICS after the above line deletions, the bulk pages are initially empty.
thanks,
- Joel
> }
> if (register_shrinker(&kfree_rcu_shrinker))
> --
> 2.20.1
>
