get_partial_node_bulk() used to move each selected slab from the node partial list to the local pc->slabs list using a remove_partial() and list_add() pair. In practice, the loop often detaches several adjacent slabs, so this repeatedly manipulates list pointers while holding n->list_lock, which causes unnecessary churn. Instead, track contiguous runs of matching slabs and move each run with list_bulk_move_tail() in one operation. This reduces list pointer churn inside the lock critical section. The mmap2 testcase shows a 5% improvement after applying this patch. Signed-off-by: Hao Li --- mm/slub.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 04692a6f9128..180973a4a3d2 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3739,6 +3739,7 @@ static bool get_partial_node_bulk(struct kmem_cache *s, bool allow_spin) { struct slab *slab, *slab2; + struct slab *first = NULL, *last = NULL; unsigned int total_free = 0; unsigned long flags; @@ -3757,8 +3758,15 @@ static bool get_partial_node_bulk(struct kmem_cache *s, struct freelist_counters flc; unsigned int slab_free; - if (!pfmemalloc_match(slab, pc->flags)) + if (!pfmemalloc_match(slab, pc->flags)) { + if (first) { + list_bulk_move_tail(&pc->slabs, + &first->slab_list, + &last->slab_list); + first = NULL; + } continue; + } /* * determine the number of free objects in the slab racily @@ -3775,15 +3783,21 @@ static bool get_partial_node_bulk(struct kmem_cache *s, && total_free + slab_free > pc->max_objects) break; - remove_partial(n, slab); - - list_add(&slab->slab_list, &pc->slabs); + if (!first) + first = slab; + last = slab; + slab_clear_node_partial(slab); + n->nr_partial--; total_free += slab_free; if (total_free >= pc->max_objects) break; } + if (first) + list_bulk_move_tail(&pc->slabs, &first->slab_list, + &last->slab_list); + spin_unlock_irqrestore(&n->list_lock, flags); return total_free > 0; } -- 2.54.0