[RFC 07/15] slub: Add defrag_used_ratio field and sysfs support

[Tobin C. Harding]

In preparation for enabling defragmentation of slab pages.

"defrag_used_ratio" is used to set the threshold at which
defragmentation should be attempted on a slab page.

"defrag_used_ratio" is a percentage in the range of 0 - 100 (inclusive).
If less than that percentage of slots in a slab page are in use then the
slab page will become subject to defragmentation.

Add a defrag ratio field and set it to 30% by default. A limit of 30%
specifies that more than 3 out of 10 available slots for objects need to
be in use otherwise slab defragmentation will be attempted on the
remaining objects.

Co-developed-by: Christoph Lameter <cl@xxxxxxxxx>
Signed-off-by: Tobin C. Harding <tobin@xxxxxxxxxx>
---
 Documentation/ABI/testing/sysfs-kernel-slab | 14 ++++++++++++
 include/linux/slub_def.h                    |  7 ++++++
 mm/slub.c                                   | 24 +++++++++++++++++++++
 3 files changed, 45 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-kernel-slab b/Documentation/ABI/testing/sysfs-kernel-slab
index 29601d93a1c2..7770c03be6b4 100644
--- a/Documentation/ABI/testing/sysfs-kernel-slab
+++ b/Documentation/ABI/testing/sysfs-kernel-slab
@@ -180,6 +180,20 @@ Description:
 		list.  It can be written to clear the current count.
 		Available when CONFIG_SLUB_STATS is enabled.
 
+What:		/sys/kernel/slab/cache/defrag_used_ratio
+Date:		February 2019
+KernelVersion:	5.0
+Contact:	Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
+		Pekka Enberg <penberg@xxxxxxxxxxxxxx>,
+Description:
+		The defrag_used_ratio file allows the control of how aggressive
+		slab fragmentation reduction works at reclaiming objects from
+		sparsely populated slabs. This is a percentage. If a slab has
+		less than this percentage of objects allocated then reclaim will
+		attempt to reclaim objects so that the whole slab page can be
+		freed. 0% specifies no reclaim attempt (defrag disabled), 100%
+		specifies attempt to reclaim all pages.  The default is 30%.
+
 What:		/sys/kernel/slab/cache/deactivate_to_tail
 Date:		February 2008
 KernelVersion:	2.6.25
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index a7340a1ed5dc..6da6197ca973 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -107,6 +107,13 @@ struct kmem_cache {
 	unsigned int red_left_pad;	/* Left redzone padding size */
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
+	int defrag_used_ratio;	/*
+				 * Ratio used to check against the
+				 * percentage of objects allocated in a
+				 * slab page.  If less than this ratio
+				 * is allocated then reclaim attempts
+				 * are made.
+				 */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 	struct work_struct kobj_remove_work;
diff --git a/mm/slub.c b/mm/slub.c
index f37103e22d3f..515db0f36c55 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3642,6 +3642,7 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
 
 	set_cpu_partial(s);
 
+	s->defrag_used_ratio = 30;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 1000;
 #endif
@@ -5261,6 +5262,28 @@ static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(destroy_by_rcu);
 
+static ssize_t defrag_used_ratio_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%d\n", s->defrag_used_ratio);
+}
+
+static ssize_t defrag_used_ratio_store(struct kmem_cache *s,
+				       const char *buf, size_t length)
+{
+	unsigned long ratio;
+	int err;
+
+	err = kstrtoul(buf, 10, &ratio);
+	if (err)
+		return err;
+
+	if (ratio <= 100)
+		s->defrag_used_ratio = ratio;
+
+	return length;
+}
+SLAB_ATTR(defrag_used_ratio);
+
 #ifdef CONFIG_SLUB_DEBUG
 static ssize_t slabs_show(struct kmem_cache *s, char *buf)
 {
@@ -5585,6 +5608,7 @@ static struct attribute *slab_attrs[] = {
 	&validate_attr.attr,
 	&alloc_calls_attr.attr,
 	&free_calls_attr.attr,
+	&defrag_used_ratio_attr.attr,
 #endif
 #ifdef CONFIG_ZONE_DMA
 	&cache_dma_attr.attr,
-- 
2.21.0