[PATCH v3 2/2] mm/slub: detach and reattach partial slabs in batch

[Hao Li <hao.li@linux.dev>]

get_partial_node_bulk() moves each selected slab from the node's
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. Doing this individually repeatedly manipulates list pointers
while holding n->list_lock, which causes unnecessary churn.

To demonstrate this, the counts below show how often single vs. multiple
consecutive slabs are retrieved during a will-it-scale mmap stress test:

consecutive_slabs_count        frequency
= 1                            277345324
= 2                            335238023
= 3                            175717884
>= 4                           88862337

The data confirms that retrieving multiple contiguous slabs is highly
frequent.

To optimize this, track contiguous runs of matching slabs and move each
run in a single operation using list_bulk_move_tail(). This reduces list
pointer churn inside the lock critical section.

Apply the same optimization to __refill_objects_node() when reattaching
leftover partial slabs back to the node's partial list.

The will-it-scale mmap benchmark shows a 2% ~ 5% performance improvement
after applying this patch.

Signed-off-by: Hao Li <hao.li@linux.dev>
---
 mm/slub.c | 28 ++++++++++++++++++++--------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 45aa0a834f97..4fdf5c36a69b 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3751,6 +3751,7 @@ 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;
 
@@ -3769,8 +3770,15 @@ 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
@@ -3787,15 +3795,20 @@ 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;
+		clear_node_partial_state(n, slab);
 
 		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;
 }
@@ -7206,11 +7219,10 @@ __refill_objects_node(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int mi
 	if (!list_empty(&pc.slabs)) {
 		spin_lock_irqsave(&n->list_lock, flags);
 
-		list_for_each_entry_safe(slab, slab2, &pc.slabs, slab_list) {
+		list_for_each_entry(slab, &pc.slabs, slab_list)
+			set_node_partial_state(n, slab);
 
-			list_del(&slab->slab_list);
-			add_partial(n, slab, ADD_TO_TAIL);
-		}
+		list_splice_tail(&pc.slabs, &n->partial);
 
 		spin_unlock_irqrestore(&n->list_lock, flags);
 	}
-- 
2.54.0