[RFC 04/15] slub: Enable Slab Movable Objects (SMO)

[Tobin C. Harding]

We have now in place a mechanism for adding callbacks to a cache in
order to be able to implement object migration.

Add a function __move() that implements SMO by moving all objects in a
slab page using the isolate/migrate callback methods.

Co-developed-by: Christoph Lameter <cl@xxxxxxxxx>
Signed-off-by: Tobin C. Harding <tobin@xxxxxxxxxx>
---
 mm/slub.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 85 insertions(+)

diff --git a/mm/slub.c b/mm/slub.c
index 0133168d1089..6ce866b420f1 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4325,6 +4325,91 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
 	return err;
 }
 
+/*
+ * Allocate a slab scratch space that is sufficient to keep pointers to
+ * individual objects for all objects in cache and also a bitmap for the
+ * objects (used to mark which objects are active).
+ */
+static inline void *alloc_scratch(struct kmem_cache *s)
+{
+	unsigned int size = oo_objects(s->max);
+
+	return kmalloc(size * sizeof(void *) +
+		       BITS_TO_LONGS(size) * sizeof(unsigned long),
+		       GFP_KERNEL);
+}
+
+/*
+ * __move() - Move all objects in the given slab.
+ * @page: The slab we are working on.
+ * @scratch: Pointer to scratch space.
+ * @node: The target node to move objects to.
+ *
+ * If the target node is not the current node then the object is moved
+ * to the target node.  If the target node is the current node then this
+ * is an effective way of defragmentation since the current slab page
+ * with its object is exempt from allocation.
+ */
+static void __move(struct page *page, void *scratch, int node)
+{
+	unsigned long objects;
+	struct kmem_cache *s;
+	unsigned long flags;
+	unsigned long *map;
+	void *private;
+	int count;
+	void *p;
+	void **vector = scratch;
+	void *addr = page_address(page);
+
+	local_irq_save(flags);
+	slab_lock(page);
+
+	BUG_ON(!PageSlab(page)); /* Must be s slab page */
+	BUG_ON(!page->frozen);	 /* Slab must have been frozen earlier */
+
+	s = page->slab_cache;
+	objects = page->objects;
+	map = scratch + objects * sizeof(void **);
+
+	/* Determine used objects */
+	bitmap_fill(map, objects);
+	for (p = page->freelist; p; p = get_freepointer(s, p))
+		__clear_bit(slab_index(p, s, addr), map);
+
+	/* Build vector of pointers to objects */
+	count = 0;
+	memset(vector, 0, objects * sizeof(void **));
+	for_each_object(p, s, addr, objects)
+		if (test_bit(slab_index(p, s, addr), map))
+			vector[count++] = p;
+
+	if (s->isolate)
+		private = s->isolate(s, vector, count);
+	else
+		/* Objects do not need to be isolated */
+		private = NULL;
+
+	/*
+	 * Pinned the objects. Now we can drop the slab lock. The slab
+	 * is frozen so it cannot vanish from under us nor will
+	 * allocations be performed on the slab. However, unlocking the
+	 * slab will allow concurrent slab_frees to proceed. So the
+	 * subsystem must have a way to tell from the content of the
+	 * object that it was freed.
+	 *
+	 * If neither RCU nor ctor is being used then the object may be
+	 * modified by the allocator after being freed which may disrupt
+	 * the ability of the migrate function to tell if the object is
+	 * free or not.
+	 */
+	slab_unlock(page);
+	local_irq_restore(flags);
+
+	/* Perform callback to move the objects */
+	s->migrate(s, vector, count, node, private);
+}
+
 void kmem_cache_setup_mobility(struct kmem_cache *s,
 			       kmem_cache_isolate_func isolate,
 			       kmem_cache_migrate_func migrate)
-- 
2.21.0