[037/212] mm: slub: move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context

Commit Message

Andrew Morton Sept. 2, 2021, 9:51 p.m. UTC

From: Sebastian Andrzej Siewior <[e-mail]>
Subject: mm: slub: move flush_cpu_slab() invocations __free_slab() invocations out of IRQ context

flush_all() flushes a specific SLAB cache on each CPU (where the cache is
present).  The deactivate_slab()/__free_slab() invocation happens within
IPI handler and is problematic for PREEMPT_RT.

The flush operation is not a frequent operation or a hot path.  The
per-CPU flush operation can be moved to within a workqueue.

[[e-mail]: adapt to new SLUB changes]
[[e-mail]: fix memory and cpu hotplug related lock ordering issues]
  Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: make __kmem_cache_do_shrink static]
  Link: https://lkml.kernel.org/r/[e-mail]
Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Sebastian Andrzej Siewior <[e-mail]>
Signed-off-by: Vlastimil Babka <[e-mail]>
Cc: Qian Cai <[e-mail]>
Cc: Christoph Lameter <[e-mail]>
Cc: David Rientjes <[e-mail]>
Cc: Jann Horn <[e-mail]>
Cc: Jesper Dangaard Brouer <[e-mail]>
Cc: Joonsoo Kim <[e-mail]>
Cc: Mel Gorman <[e-mail]>
Cc: Mike Galbraith <[e-mail]>
Cc: Pekka Enberg <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
---

 mm/slab_common.c |    2 +
 mm/slub.c        |   79 +++++++++++++++++++++++++++++++++++++--------
 2 files changed, 68 insertions(+), 13 deletions(-)

Patch

--- a/mm/slab_common.c~mm-slub-move-flush_cpu_slab-invocations-__free_slab-invocations-out-of-irq-context
+++ a/mm/slab_common.c
@@ -502,6 +502,7 @@  void kmem_cache_destroy(struct kmem_cach
 	if (unlikely(!s))
 		return;
 
+	cpus_read_lock();
 	mutex_lock(&slab_mutex);
 
 	s->refcount--;
@@ -516,6 +517,7 @@  void kmem_cache_destroy(struct kmem_cach
 	}
 out_unlock:
 	mutex_unlock(&slab_mutex);
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
--- a/mm/slub.c~mm-slub-move-flush_cpu_slab-invocations-__free_slab-invocations-out-of-irq-context
+++ a/mm/slub.c
@@ -2516,33 +2516,79 @@  static inline void __flush_cpu_slab(stru
 	unfreeze_partials_cpu(s, c);
 }
 
+struct slub_flush_work {
+	struct work_struct work;
+	struct kmem_cache *s;
+	bool skip;
+};
+
 /*
  * Flush cpu slab.
  *
- * Called from IPI handler with interrupts disabled.
+ * Called from CPU work handler with migration disabled.
  */
-static void flush_cpu_slab(void *d)
+static void flush_cpu_slab(struct work_struct *w)
 {
-	struct kmem_cache *s = d;
-	struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
+	struct kmem_cache *s;
+	struct kmem_cache_cpu *c;
+	struct slub_flush_work *sfw;
+
+	sfw = container_of(w, struct slub_flush_work, work);
+
+	s = sfw->s;
+	c = this_cpu_ptr(s->cpu_slab);
 
 	if (c->page)
-		flush_slab(s, c, false);
+		flush_slab(s, c, true);
 
 	unfreeze_partials(s);
 }
 
-static bool has_cpu_slab(int cpu, void *info)
+static bool has_cpu_slab(int cpu, struct kmem_cache *s)
 {
-	struct kmem_cache *s = info;
 	struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
 
 	return c->page || 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);
+		sfw->skip = false;
+		sfw->s = s;
+		schedule_work_on(cpu, &sfw->work);
+	}
+
+	for_each_online_cpu(cpu) {
+		sfw = &per_cpu(slub_flush, cpu);
+		if (sfw->skip)
+			continue;
+		flush_work(&sfw->work);
+	}
+
+	mutex_unlock(&flush_lock);
+}
+
 static void flush_all(struct kmem_cache *s)
 {
-	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1);
+	cpus_read_lock();
+	flush_all_cpus_locked(s);
+	cpus_read_unlock();
 }
 
 /*
@@ -4087,7 +4133,7 @@  int __kmem_cache_shutdown(struct kmem_ca
 	int node;
 	struct kmem_cache_node *n;
 
-	flush_all(s);
+	flush_all_cpus_locked(s);
 	/* Attempt to free all objects */
 	for_each_kmem_cache_node(s, node, n) {
 		free_partial(s, n);
@@ -4363,7 +4409,7 @@  EXPORT_SYMBOL(kfree);
  * being allocated from last increasing the chance that the last objects
  * are freed in them.
  */
-int __kmem_cache_shrink(struct kmem_cache *s)
+static int __kmem_cache_do_shrink(struct kmem_cache *s)
 {
 	int node;
 	int i;
@@ -4375,7 +4421,6 @@  int __kmem_cache_shrink(struct kmem_cach
 	unsigned long flags;
 	int ret = 0;
 
-	flush_all(s);
 	for_each_kmem_cache_node(s, node, n) {
 		INIT_LIST_HEAD(&discard);
 		for (i = 0; i < SHRINK_PROMOTE_MAX; i++)
@@ -4425,13 +4470,21 @@  int __kmem_cache_shrink(struct kmem_cach
 	return ret;
 }
 
+int __kmem_cache_shrink(struct kmem_cache *s)
+{
+	flush_all(s);
+	return __kmem_cache_do_shrink(s);
+}
+
 static int slab_mem_going_offline_callback(void *arg)
 {
 	struct kmem_cache *s;
 
 	mutex_lock(&slab_mutex);
-	list_for_each_entry(s, &slab_caches, list)
-		__kmem_cache_shrink(s);
+	list_for_each_entry(s, &slab_caches, list) {
+		flush_all_cpus_locked(s);
+		__kmem_cache_do_shrink(s);
+	}
 	mutex_unlock(&slab_mutex);
 
 	return 0;