[RFC PATCH v1 4/4] slub: apply new queue_percpu_work_on() interface

[Leonardo Bras <leobras@xxxxxxxxxx>]

Make use of the new qpw_{un,}lock*() and queue_percpu_work_on()
interface to improve performance & latency on PREEMTP_RT kernels.

For functions that may be scheduled in a different cpu, replace
local_{un,}lock*() by qpw_{un,}lock*(), and replace schedule_work_on() by
queue_percpu_work_on(). The same happens for flush_work() and
flush_percpu_work().

This change requires allocation of qpw_structs instead of a work_structs,
and changing parameters of a few functions to include the cpu parameter.

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 | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/mm/slub.c b/mm/slub.c
index 1373ac365a46..5cd91541906e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -35,20 +35,21 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 #include <linux/kmemleak.h>
 #include <linux/stacktrace.h>
 #include <linux/prefetch.h>
 #include <linux/memcontrol.h>
 #include <linux/random.h>
 #include <kunit/test.h>
 #include <kunit/test-bug.h>
 #include <linux/sort.h>
+#include <linux/qpw.h>
 
 #include <linux/debugfs.h>
 #include <trace/events/kmem.h>
 
 #include "internal.h"
 
 /*
  * Lock order:
  *   1. slab_mutex (Global Mutex)
  *   2. node->list_lock (Spinlock)
@@ -3073,36 +3074,37 @@ static void put_cpu_partial(struct kmem_cache *s, struct slab *slab, int drain)
 }
 
 #else	/* CONFIG_SLUB_CPU_PARTIAL */
 
 static inline void put_partials(struct kmem_cache *s) { }
 static inline void put_partials_cpu(struct kmem_cache *s,
 				    struct kmem_cache_cpu *c) { }
 
 #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);
+	qpw_lock_irqsave(&s->cpu_slab->lock, flags, cpu);
 
 	slab = c->slab;
 	freelist = c->freelist;
 
 	c->slab = NULL;
 	c->freelist = NULL;
 	c->tid = next_tid(c->tid);
 
-	local_unlock_irqrestore(&s->cpu_slab->lock, flags);
+	qpw_unlock_irqrestore(&s->cpu_slab->lock, flags, cpu);
 
 	if (slab) {
 		deactivate_slab(s, slab, freelist);
 		stat(s, CPUSLAB_FLUSH);
 	}
 }
 
 static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 {
 	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
@@ -3115,82 +3117,84 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
 
 	if (slab) {
 		deactivate_slab(s, slab, freelist);
 		stat(s, CPUSLAB_FLUSH);
 	}
 
 	put_partials_cpu(s, c);
 }
 
 struct slub_flush_work {
-	struct work_struct work;
+	struct qpw_struct qpw;
 	struct kmem_cache *s;
 	bool skip;
 };
 
+static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
+
 /*
  * Flush cpu slab.
  *
  * Called from CPU work handler with migration disabled.
  */
 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 = qpw_get_cpu(w);
 
-	sfw = container_of(w, struct slub_flush_work, work);
+	sfw = &per_cpu(slub_flush, cpu);
 
 	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);
 
 	put_partials(s);
 }
 
 static bool has_cpu_slab(int cpu, struct kmem_cache *s)
 {
 	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
 	return c->slab || slub_percpu_partial(c);
 }
 
 static DEFINE_MUTEX(flush_lock);
-static DEFINE_PER_CPU(struct slub_flush_work, slub_flush);
 
 static void flush_all_cpus_locked(struct kmem_cache *s)
 {
 	struct slub_flush_work *sfw;
 	unsigned int cpu;
 
 	lockdep_assert_cpus_held();
 	mutex_lock(&flush_lock);
 
 	for_each_online_cpu(cpu) {
 		sfw = &per_cpu(slub_flush, cpu);
 		if (!has_cpu_slab(cpu, s)) {
 			sfw->skip = true;
 			continue;
 		}
-		INIT_WORK(&sfw->work, flush_cpu_slab);
+		INIT_QPW(&sfw->qpw, flush_cpu_slab, cpu);
 		sfw->skip = false;
 		sfw->s = s;
-		queue_work_on(cpu, flushwq, &sfw->work);
+		queue_percpu_work_on(cpu, flushwq, &sfw->qpw);
 	}
 
 	for_each_online_cpu(cpu) {
 		sfw = &per_cpu(slub_flush, cpu);
 		if (sfw->skip)
 			continue;
-		flush_work(&sfw->work);
+		flush_percpu_work(&sfw->qpw);
 	}
 
 	mutex_unlock(&flush_lock);
 }
 
 static void flush_all(struct kmem_cache *s)
 {
 	cpus_read_lock();
 	flush_all_cpus_locked(s);
 	cpus_read_unlock();
-- 
2.45.2