[RFC PATCH 4/4] slub: apply new local_schedule_work_on() interface

[Leonardo Bras]

Make use of the new local_*lock_n*() and local_schedule_work_on() interface
to improve performance & latency on PREEMTP_RT kernels.

For functions that may be scheduled in a different cpu, replace
local_*lock*() by local_lock_n*(), and replace schedule_work_on() by
local_schedule_work_on(). The same happens for flush_work() and
local_flush_work().

This should bring no relevant performance impact on non-RT kernels:
For functions that may be scheduled in a different cpu, the local_*lock's
this_cpu_ptr() becomes a per_cpu_ptr(smp_processor_id()).

Signed-off-by: Leonardo Bras <leobras@xxxxxxxxxx>
---
 mm/slub.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index e3b5d5c0eb3a..feb4a502d9a8 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -2733,13 +2733,14 @@ static inline void unfreeze_partials_cpu(struct kmem_cache *s,
 
 #endif	/* CONFIG_SLUB_CPU_PARTIAL */
 
-static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
+static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c,
+			      int cpu)
 {
 	unsigned long flags;
 	struct slab *slab;
 	void *freelist;
 
-	local_lock_irqsave(&s->cpu_slab->lock, flags);
+	local_lock_irqsave_n(&s->cpu_slab->lock, flags, cpu);
 
 	slab = c->slab;
 	freelist = c->freelist;
@@ -2748,7 +2749,7 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
 	c->freelist = NULL;
 	c->tid = next_tid(c->tid);
 
-	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
+	local_unlock_irqrestore_n(&s->cpu_slab->lock, flags, cpu);
 
 	if (slab) {
 		deactivate_slab(s, slab, freelist);
@@ -2790,14 +2791,16 @@ static void flush_cpu_slab(struct work_struct *w)
 	struct kmem_cache *s;
 	struct kmem_cache_cpu *c;
 	struct slub_flush_work *sfw;
+	int cpu;
 
+	cpu = w->data.counter;
 	sfw = container_of(w, struct slub_flush_work, work);
 
 	s = sfw->s;
-	c = this_cpu_ptr(s->cpu_slab);
+	c = per_cpu_ptr(s->cpu_slab, cpu);
 
 	if (c->slab)
-		flush_slab(s, c);
+		flush_slab(s, c, cpu);
 
 	unfreeze_partials(s);
 }
@@ -2829,14 +2832,14 @@ static void flush_all_cpus_locked(struct kmem_cache *s)
 		INIT_WORK(&sfw->work, flush_cpu_slab);
 		sfw->skip = false;
 		sfw->s = s;
-		queue_work_on(cpu, flushwq, &sfw->work);
+		local_queue_work_on(cpu, flushwq, &sfw->work);
 	}
 
 	for_each_online_cpu(cpu) {
 		sfw = &per_cpu(slub_flush, cpu);
 		if (sfw->skip)
 			continue;
-		flush_work(&sfw->work);
+		local_flush_work(&sfw->work);
 	}
 
 	mutex_unlock(&flush_lock);
-- 
2.41.0