[PATCH v4 14/22] slab: remove defer_deactivate_slab()

[Vlastimil Babka <vbabka@suse.cz>]

There are no more cpu slabs so we don't need their deferred
deactivation. The function is now only used from places where we
allocate a new slab but then can't spin on node list_lock to put it on
the partial list. Instead of the deferred action we can free it directly
via __free_slab(), we just need to tell it to use _nolock() freeing of
the underlying pages and take care of the accounting.

Since free_frozen_pages_nolock() variant does not yet exist for code
outside of the page allocator, create it as a trivial wrapper for
__free_frozen_pages(..., FPI_TRYLOCK).

Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Hao Li <hao.li@linux.dev>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/internal.h   |  1 +
 mm/page_alloc.c |  5 +++++
 mm/slab.h       |  8 +-------
 mm/slub.c       | 58 +++++++++++++++++++++------------------------------------
 4 files changed, 28 insertions(+), 44 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index e430da900430..1f44ccb4badf 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -846,6 +846,7 @@ static inline struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned int ord
 struct page *alloc_frozen_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order);
 #define alloc_frozen_pages_nolock(...) \
 	alloc_hooks(alloc_frozen_pages_nolock_noprof(__VA_ARGS__))
+void free_frozen_pages_nolock(struct page *page, unsigned int order);
 
 extern void zone_pcp_reset(struct zone *zone);
 extern void zone_pcp_disable(struct zone *zone);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c380f063e8b7..0127e9d661ad 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2981,6 +2981,11 @@ void free_frozen_pages(struct page *page, unsigned int order)
 	__free_frozen_pages(page, order, FPI_NONE);
 }
 
+void free_frozen_pages_nolock(struct page *page, unsigned int order)
+{
+	__free_frozen_pages(page, order, FPI_TRYLOCK);
+}
+
 /*
  * Free a batch of folios
  */
diff --git a/mm/slab.h b/mm/slab.h
index 0fbe13bec864..37090a7dffb6 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -71,13 +71,7 @@ struct slab {
 	struct kmem_cache *slab_cache;
 	union {
 		struct {
-			union {
-				struct list_head slab_list;
-				struct { /* For deferred deactivate_slab() */
-					struct llist_node llnode;
-					void *flush_freelist;
-				};
-			};
+			struct list_head slab_list;
 			/* Double-word boundary */
 			struct freelist_counters;
 		};
diff --git a/mm/slub.c b/mm/slub.c
index a63a0eed2c55..82950c2bc26d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3262,7 +3262,7 @@ static struct slab *new_slab(struct kmem_cache *s, gfp_t flags, int node)
 		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
 }
 
-static void __free_slab(struct kmem_cache *s, struct slab *slab)
+static void __free_slab(struct kmem_cache *s, struct slab *slab, bool allow_spin)
 {
 	struct page *page = slab_page(slab);
 	int order = compound_order(page);
@@ -3273,14 +3273,26 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab)
 	__ClearPageSlab(page);
 	mm_account_reclaimed_pages(pages);
 	unaccount_slab(slab, order, s);
-	free_frozen_pages(page, order);
+	if (allow_spin)
+		free_frozen_pages(page, order);
+	else
+		free_frozen_pages_nolock(page, order);
+}
+
+static void free_new_slab_nolock(struct kmem_cache *s, struct slab *slab)
+{
+	/*
+	 * Since it was just allocated, we can skip the actions in
+	 * discard_slab() and free_slab().
+	 */
+	__free_slab(s, slab, false);
 }
 
 static void rcu_free_slab(struct rcu_head *h)
 {
 	struct slab *slab = container_of(h, struct slab, rcu_head);
 
-	__free_slab(slab->slab_cache, slab);
+	__free_slab(slab->slab_cache, slab, true);
 }
 
 static void free_slab(struct kmem_cache *s, struct slab *slab)
@@ -3296,7 +3308,7 @@ static void free_slab(struct kmem_cache *s, struct slab *slab)
 	if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU))
 		call_rcu(&slab->rcu_head, rcu_free_slab);
 	else
-		__free_slab(s, slab);
+		__free_slab(s, slab, true);
 }
 
 static void discard_slab(struct kmem_cache *s, struct slab *slab)
@@ -3389,8 +3401,6 @@ static void *alloc_single_from_partial(struct kmem_cache *s,
 	return object;
 }
 
-static void defer_deactivate_slab(struct slab *slab, void *flush_freelist);
-
 /*
  * Called only for kmem_cache_debug() caches to allocate from a freshly
  * allocated slab. Allocate a single object instead of whole freelist
@@ -3406,8 +3416,8 @@ static void *alloc_single_from_new_slab(struct kmem_cache *s, struct slab *slab,
 	void *object;
 
 	if (!allow_spin && !spin_trylock_irqsave(&n->list_lock, flags)) {
-		/* Unlucky, discard newly allocated slab */
-		defer_deactivate_slab(slab, NULL);
+		/* Unlucky, discard newly allocated slab. */
+		free_new_slab_nolock(s, slab);
 		return NULL;
 	}
 
@@ -4279,7 +4289,7 @@ static unsigned int alloc_from_new_slab(struct kmem_cache *s, struct slab *slab,
 
 		if (!spin_trylock_irqsave(&n->list_lock, flags)) {
 			/* Unlucky, discard newly allocated slab */
-			defer_deactivate_slab(slab, NULL);
+			free_new_slab_nolock(s, slab);
 			return 0;
 		}
 	}
@@ -6056,7 +6066,6 @@ static void free_to_pcs_bulk(struct kmem_cache *s, size_t size, void **p)
 
 struct defer_free {
 	struct llist_head objects;
-	struct llist_head slabs;
 	struct irq_work work;
 };
 
@@ -6064,23 +6073,21 @@ static void free_deferred_objects(struct irq_work *work);
 
 static DEFINE_PER_CPU(struct defer_free, defer_free_objects) = {
 	.objects = LLIST_HEAD_INIT(objects),
-	.slabs = LLIST_HEAD_INIT(slabs),
 	.work = IRQ_WORK_INIT(free_deferred_objects),
 };
 
 /*
  * In PREEMPT_RT irq_work runs in per-cpu kthread, so it's safe
- * to take sleeping spin_locks from __slab_free() and deactivate_slab().
+ * to take sleeping spin_locks from __slab_free().
  * In !PREEMPT_RT irq_work will run after local_unlock_irqrestore().
  */
 static void free_deferred_objects(struct irq_work *work)
 {
 	struct defer_free *df = container_of(work, struct defer_free, work);
 	struct llist_head *objs = &df->objects;
-	struct llist_head *slabs = &df->slabs;
 	struct llist_node *llnode, *pos, *t;
 
-	if (llist_empty(objs) && llist_empty(slabs))
+	if (llist_empty(objs))
 		return;
 
 	llnode = llist_del_all(objs);
@@ -6104,16 +6111,6 @@ static void free_deferred_objects(struct irq_work *work)
 
 		__slab_free(s, slab, x, x, 1, _THIS_IP_);
 	}
-
-	llnode = llist_del_all(slabs);
-	llist_for_each_safe(pos, t, llnode) {
-		struct slab *slab = container_of(pos, struct slab, llnode);
-
-		if (slab->frozen)
-			deactivate_slab(slab->slab_cache, slab, slab->flush_freelist);
-		else
-			free_slab(slab->slab_cache, slab);
-	}
 }
 
 static void defer_free(struct kmem_cache *s, void *head)
@@ -6129,19 +6126,6 @@ static void defer_free(struct kmem_cache *s, void *head)
 		irq_work_queue(&df->work);
 }
 
-static void defer_deactivate_slab(struct slab *slab, void *flush_freelist)
-{
-	struct defer_free *df;
-
-	slab->flush_freelist = flush_freelist;
-
-	guard(preempt)();
-
-	df = this_cpu_ptr(&defer_free_objects);
-	if (llist_add(&slab->llnode, &df->slabs))
-		irq_work_queue(&df->work);
-}
-
 void defer_free_barrier(void)
 {
 	int cpu;

-- 
2.52.0