On Fri, Feb 14, 2025 at 05:27:43PM +0100, Vlastimil Babka wrote:
> The possibility of many barn operations is determined by the current
> number of full or empty sheaves. Taking the barn->lock just to find out
> that e.g. there are no empty sheaves results in unnecessary overhead and
> lock contention. Thus perform these checks outside of the lock with a
> data_race() annotated variable read and fail quickly without taking the
> lock.
>
> Checks for sheaf availability that racily succeed have to be obviously
> repeated under the lock for correctness, but we can skip repeating
> checks if there are too many sheaves on the given list as the limits
> don't need to be strict.
>
> Signed-off-by: Vlastimil Babka <vba...@suse.cz>
Looks good to me,
Reviewed-by: Harry Yoo <harry....@oracle.com>
in kmem_cache_return_sheaf:
> if (!pcs->spare) {
> pcs->spare = sheaf;
> sheaf = NULL;
> } else if (pcs->barn->nr_full >= MAX_FULL_SHEAVES) {
> /* racy check */
> barn = pcs->barn;
> keep = true;
> }
By the way this code also needs data_race()?
--
Cheers,
Harry
> ---
> mm/slub.c | 57 ++++++++++++++++++++++++++++++++++-----------------------
> 1 file changed, 34 insertions(+), 23 deletions(-)
>
> diff --git a/mm/slub.c b/mm/slub.c
> index
> c1df7cf22267f28f743404531bef921e25fac086..72e6437f1d74bfacbb1cd7642af42929c48cc66a
> 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -2685,9 +2685,12 @@ static struct slab_sheaf *barn_get_empty_sheaf(struct
> node_barn *barn)
> struct slab_sheaf *empty = NULL;
> unsigned long flags;
>
> + if (!data_race(barn->nr_empty))
> + return NULL;
> +
> spin_lock_irqsave(&barn->lock, flags);
>
> - if (barn->nr_empty) {
> + if (likely(barn->nr_empty)) {
> empty = list_first_entry(&barn->sheaves_empty,
> struct slab_sheaf, barn_list);
> list_del(&empty->barn_list);
> @@ -2703,38 +2706,36 @@ static int barn_put_empty_sheaf(struct node_barn
> *barn,
> struct slab_sheaf *sheaf, bool ignore_limit)
> {
> unsigned long flags;
> - int ret = 0;
> +
> + /* we don't repeat the check under barn->lock as it's not critical */
> + if (!ignore_limit && data_race(barn->nr_empty) >= MAX_EMPTY_SHEAVES)
> + return -E2BIG;
>
> spin_lock_irqsave(&barn->lock, flags);
>
> - if (!ignore_limit && barn->nr_empty >= MAX_EMPTY_SHEAVES) {
> - ret = -E2BIG;
> - } else {
> - list_add(&sheaf->barn_list, &barn->sheaves_empty);
> - barn->nr_empty++;
> - }
> + list_add(&sheaf->barn_list, &barn->sheaves_empty);
> + barn->nr_empty++;
>
> spin_unlock_irqrestore(&barn->lock, flags);
> - return ret;
> + return 0;
> }
>
> static int barn_put_full_sheaf(struct node_barn *barn, struct slab_sheaf
> *sheaf,
> bool ignore_limit)
> {
> unsigned long flags;
> - int ret = 0;
> +
> + /* we don't repeat the check under barn->lock as it's not critical */
> + if (!ignore_limit && data_race(barn->nr_full) >= MAX_FULL_SHEAVES)
> + return -E2BIG;
>
> spin_lock_irqsave(&barn->lock, flags);
>
> - if (!ignore_limit && barn->nr_full >= MAX_FULL_SHEAVES) {
> - ret = -E2BIG;
> - } else {
> - list_add(&sheaf->barn_list, &barn->sheaves_full);
> - barn->nr_full++;
> - }
> + list_add(&sheaf->barn_list, &barn->sheaves_full);
> + barn->nr_full++;
>
> spin_unlock_irqrestore(&barn->lock, flags);
> - return ret;
> + return 0;
> }
>
> static struct slab_sheaf *barn_get_full_or_empty_sheaf(struct node_barn
> *barn)
> @@ -2742,6 +2743,9 @@ static struct slab_sheaf
> *barn_get_full_or_empty_sheaf(struct node_barn *barn)
> struct slab_sheaf *sheaf = NULL;
> unsigned long flags;
>
> + if (!data_race(barn->nr_full) && !data_race(barn->nr_empty))
> + return NULL;
> +
> spin_lock_irqsave(&barn->lock, flags);
>
> if (barn->nr_full) {
> @@ -2772,9 +2776,12 @@ barn_replace_empty_sheaf(struct node_barn *barn,
> struct slab_sheaf *empty)
> struct slab_sheaf *full = NULL;
> unsigned long flags;
>
> + if (!data_race(barn->nr_full))
> + return NULL;
> +
> spin_lock_irqsave(&barn->lock, flags);
>
> - if (barn->nr_full) {
> + if (likely(barn->nr_full)) {
> full = list_first_entry(&barn->sheaves_full, struct slab_sheaf,
> barn_list);
> list_del(&full->barn_list);
> @@ -2797,19 +2804,23 @@ barn_replace_full_sheaf(struct node_barn *barn,
> struct slab_sheaf *full)
> struct slab_sheaf *empty;
> unsigned long flags;
>
> + /* we don't repeat this check under barn->lock as it's not critical */
> + if (data_race(barn->nr_full) >= MAX_FULL_SHEAVES)
> + return ERR_PTR(-E2BIG);
> + if (!data_race(barn->nr_empty))
> + return ERR_PTR(-ENOMEM);
> +
> spin_lock_irqsave(&barn->lock, flags);
>
> - if (barn->nr_full >= MAX_FULL_SHEAVES) {
> - empty = ERR_PTR(-E2BIG);
> - } else if (!barn->nr_empty) {
> - empty = ERR_PTR(-ENOMEM);
> - } else {
> + if (likely(barn->nr_empty)) {
> empty = list_first_entry(&barn->sheaves_empty, struct
> slab_sheaf,
> barn_list);
> list_del(&empty->barn_list);
> list_add(&full->barn_list, &barn->sheaves_full);
> barn->nr_empty--;
> barn->nr_full++;
> + } else {
> + empty = ERR_PTR(-ENOMEM);
> }
>
> spin_unlock_irqrestore(&barn->lock, flags);
>
> --
> 2.48.1
>
