Virtualization - Mar 2016 - [RFC kernel 0/2]A PV solution for KVM live migration optimization

The current QEMU live migration implementation mark the all the
guest's RAM pages as dirtied in the ram bulk stage, all these pages
will be processed and that takes quit a lot of CPU cycles.
>From guest's point of view, it doesn't care about the content in
free
pages. We can make use of this fact and skip processing the free
pages in the ram bulk stage, it can save a lot CPU cycles and reduce
the network traffic significantly while speed up the live migration
process obviously.

This patch set is the kernel side implementation.

It get the free pages information by traversing
zone->free_area[order].free_list, and construct a free pages bitmap.
The virtio-balloon driver is extended so as to send the free pages
bitmap to QEMU for live migration optimization.

Performance data
===============
Test environment:

CPU: Intel (R) Xeon(R) CPU ES-2699 v3 @ 2.30GHz
Host RAM: 64GB
Host Linux Kernel:  4.2.0             Host OS: CentOS 7.1
Guest Linux Kernel:  4.5.rc6        Guest OS: CentOS 6.6
Network:  X540-AT2 with 10 Gigabit connection
Guest RAM: 8GB

Case 1: Idle guest just boots:
===========================================                    | original  |   
pv
-------------------------------------------
total time(ms)      |    1894   |   421
--------------------------------------------
transferred ram(KB) |   398017  |  353242
===========================================

Case 2: The guest has ever run some memory consuming workload, the
workload is terminated just before live migration.
===========================================                    | original  |   
pv
-------------------------------------------
total time(ms)      |   7436    |   552
--------------------------------------------
transferred ram(KB) |  8146291  |  361375
===========================================
Liang Li (2):
  mm: Add the functions used to get free pages information
  virtio-balloon: extend balloon driver to support a new feature

 drivers/virtio/virtio_balloon.c     | 108 ++++++++++++++++++++++++++++++++++--
 include/uapi/linux/virtio_balloon.h |   1 +
 mm/page_alloc.c                     |  58 +++++++++++++++++++
 3 files changed, 162 insertions(+), 5 deletions(-)

-- 
1.8.3.1

get_total_pages_count() tries to get the page count of the system
RAM.
get_free_pages() is intend to construct a free pages bitmap by
traversing the free_list.

The free pages information will be sent to QEMU through virtio
and used for live migration optimization.

Signed-off-by: Liang Li <liang.z.li at intel.com>
---
 mm/page_alloc.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 838ca8bb..81922e6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3860,6 +3860,63 @@ void show_free_areas(unsigned int filter)
 	show_swap_cache_info();
 }
 
+#define PFN_4G (0x100000000 >> PAGE_SHIFT)
+
+unsigned long get_total_pages_count(unsigned long low_mem)
+{
+	if (max_pfn >= PFN_4G) {
+		unsigned long pfn_gap = PFN_4G - (low_mem >> PAGE_SHIFT);
+
+		return max_pfn - pfn_gap;
+	} else
+		return max_pfn;
+}
+EXPORT_SYMBOL(get_total_pages_count);
+
+static void mark_free_pages_bitmap(struct zone *zone,
+		 unsigned long *free_page_bitmap, unsigned long pfn_gap)
+{
+	unsigned long pfn, flags, i;
+	unsigned int order, t;
+	struct list_head *curr;
+
+	if (zone_is_empty(zone))
+		return;
+
+	spin_lock_irqsave(&zone->lock, flags);
+
+	for_each_migratetype_order(order, t) {
+		list_for_each(curr, &zone->free_area[order].free_list[t]) {
+
+			pfn = page_to_pfn(list_entry(curr, struct page, lru));
+			for (i = 0; i < (1UL << order); i++) {
+				if ((pfn + i) >= PFN_4G)
+					set_bit_le(pfn + i - pfn_gap,
+						   free_page_bitmap);
+				else
+					set_bit_le(pfn + i, free_page_bitmap);
+			}
+		}
+	}
+
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+void get_free_pages(unsigned long *free_page_bitmap,
+		unsigned long *free_pages_count,
+		unsigned long low_mem)
+{
+	struct zone *zone;
+	unsigned long pfn_gap;
+
+	pfn_gap = PFN_4G - (low_mem >> PAGE_SHIFT);
+	for_each_populated_zone(zone)
+		mark_free_pages_bitmap(zone, free_page_bitmap, pfn_gap);
+
+	*free_pages_count = global_page_state(NR_FREE_PAGES);
+}
+EXPORT_SYMBOL(get_free_pages);
+
 static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
 {
 	zoneref->zone = zone;
-- 
1.8.3.1

Extend the virio balloon to support the new feature
VIRTIO_BALLOON_F_GET_FREE_PAGES, so that we can use it to send the
free pages information from guest to QEMU, and then optimize the
live migration process.

Signed-off-by: Liang Li <liang.z.li at intel.com>
---
 drivers/virtio/virtio_balloon.c     | 106 ++++++++++++++++++++++++++++++++++--
 include/uapi/linux/virtio_balloon.h |   1 +
 2 files changed, 102 insertions(+), 5 deletions(-)

diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 0c3691f..7461d3e 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -45,9 +45,18 @@ static int oom_pages = OOM_VBALLOON_DEFAULT_PAGES;
 module_param(oom_pages, int, S_IRUSR | S_IWUSR);
 MODULE_PARM_DESC(oom_pages, "pages to free on OOM");
 
+extern void get_free_pages(unsigned long *free_page_bitmap,
+			unsigned long *free_pages_num,
+			unsigned long lowmem);
+extern unsigned long get_total_pages_count(unsigned long lowmem);
+
+struct mem_layout {
+	unsigned long low_mem;
+};
+
 struct virtio_balloon {
 	struct virtio_device *vdev;
-	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+	struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_pages_vq;
 
 	/* Where the ballooning thread waits for config to change. */
 	wait_queue_head_t config_change;
@@ -75,6 +84,11 @@ struct virtio_balloon {
 	unsigned int num_pfns;
 	u32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
 
+	unsigned long *free_pages;
+	unsigned long free_pages_len;
+	unsigned long free_pages_num;
+	struct mem_layout mem_config;
+
 	/* Memory statistics */
 	int need_stats_update;
 	struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
@@ -245,6 +259,34 @@ static void update_balloon_stats(struct virtio_balloon *vb)
 				pages_to_bytes(i.totalram));
 }
 
+static void update_free_pages_stats(struct virtio_balloon *vb)
+{
+	unsigned long total_page_count, bitmap_bytes;
+
+	total_page_count = get_total_pages_count(vb->mem_config.low_mem);
+	bitmap_bytes = ALIGN(total_page_count, BITS_PER_LONG) / 8;
+
+	if (!vb->free_pages)
+		vb->free_pages = kzalloc(bitmap_bytes, GFP_KERNEL);
+	else {
+		if (bitmap_bytes < vb->free_pages_len)
+			memset(vb->free_pages, 0, bitmap_bytes);
+		else {
+			kfree(vb->free_pages);
+			vb->free_pages = kzalloc(bitmap_bytes, GFP_KERNEL);
+		}
+	}
+	if (!vb->free_pages) {
+		vb->free_pages_len = 0;
+		vb->free_pages_num = 0;
+		return;
+	}
+
+	vb->free_pages_len = bitmap_bytes;
+	get_free_pages(vb->free_pages, &vb->free_pages_num,
+		       vb->mem_config.low_mem);
+}
+
 /*
  * While most virtqueues communicate guest-initiated requests to the
hypervisor,
  * the stats queue operates in reverse.  The driver initializes the virtqueue
@@ -278,6 +320,39 @@ static void stats_handle_request(struct virtio_balloon *vb)
 	virtqueue_kick(vq);
 }
 
+static void free_pages_handle_rq(struct virtio_balloon *vb)
+{
+	struct virtqueue *vq;
+	struct scatterlist sg[3];
+	unsigned int len;
+	struct mem_layout *ptr_mem_layout;
+	struct scatterlist sg_in;
+
+	vq = vb->free_pages_vq;
+	ptr_mem_layout = virtqueue_get_buf(vq, &len);
+
+	if (!ptr_mem_layout)
+		return;
+	update_free_pages_stats(vb);
+	sg_init_table(sg, 3);
+	sg_set_buf(&sg[0], &(vb->free_pages_num),
sizeof(vb->free_pages_num));
+	sg_set_buf(&sg[1], &(vb->free_pages_len),
sizeof(vb->free_pages_len));
+	sg_set_buf(&sg[2], vb->free_pages, vb->free_pages_len);
+
+	sg_init_one(&sg_in, &vb->mem_config, sizeof(vb->mem_config));
+
+	virtqueue_add_outbuf(vq, &sg[0], 3, vb, GFP_KERNEL);
+	virtqueue_add_inbuf(vq, &sg_in, 1, &vb->mem_config, GFP_KERNEL);
+	virtqueue_kick(vq);
+}
+
+static void free_pages_rq(struct virtqueue *vq)
+{
+	struct virtio_balloon *vb = vq->vdev->priv;
+
+	free_pages_handle_rq(vb);
+}
+
 static void virtballoon_changed(struct virtio_device *vdev)
 {
 	struct virtio_balloon *vb = vdev->priv;
@@ -386,16 +461,22 @@ static int balloon(void *_vballoon)
 
 static int init_vqs(struct virtio_balloon *vb)
 {
-	struct virtqueue *vqs[3];
-	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
-	static const char * const names[] = { "inflate",
"deflate", "stats" };
+	struct virtqueue *vqs[4];
+	vq_callback_t *callbacks[] = { balloon_ack, balloon_ack,
+					 stats_request, free_pages_rq };
+	const char *names[] = { "inflate", "deflate",
"stats", "free_pages" };
 	int err, nvqs;
 
 	/*
 	 * We expect two virtqueues: inflate and deflate, and
 	 * optionally stat.
 	 */
-	nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_GET_FREE_PAGES))
+		nvqs = 4;
+	else
+		nvqs = virtio_has_feature(vb->vdev,
+					  VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
+
 	err = vb->vdev->config->find_vqs(vb->vdev, nvqs, vqs, callbacks,
names);
 	if (err)
 		return err;
@@ -416,6 +497,16 @@ static int init_vqs(struct virtio_balloon *vb)
 			BUG();
 		virtqueue_kick(vb->stats_vq);
 	}
+	if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_GET_FREE_PAGES)) {
+		struct scatterlist sg_in;
+
+		vb->free_pages_vq = vqs[3];
+		sg_init_one(&sg_in, &vb->mem_config, sizeof(vb->mem_config));
+		if (virtqueue_add_inbuf(vb->free_pages_vq, &sg_in, 1,
+		    &vb->mem_config, GFP_KERNEL) < 0)
+			BUG();
+		virtqueue_kick(vb->free_pages_vq);
+	}
 	return 0;
 }
 
@@ -505,6 +596,9 @@ static int virtballoon_probe(struct virtio_device *vdev)
 	init_waitqueue_head(&vb->acked);
 	vb->vdev = vdev;
 	vb->need_stats_update = 0;
+	vb->free_pages_num = 0;
+	vb->free_pages_len = 0;
+	vb->free_pages = NULL;
 
 	balloon_devinfo_init(&vb->vb_dev_info);
 #ifdef CONFIG_BALLOON_COMPACTION
@@ -561,6 +655,7 @@ static void virtballoon_remove(struct virtio_device *vdev)
 	unregister_oom_notifier(&vb->nb);
 	kthread_stop(vb->thread);
 	remove_common(vb);
+	kfree(vb->free_pages);
 	kfree(vb);
 }
 
@@ -599,6 +694,7 @@ static unsigned int features[] = {
 	VIRTIO_BALLOON_F_MUST_TELL_HOST,
 	VIRTIO_BALLOON_F_STATS_VQ,
 	VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
+	VIRTIO_BALLOON_F_GET_FREE_PAGES,
 };
 
 static struct virtio_driver virtio_balloon_driver = {
diff --git a/include/uapi/linux/virtio_balloon.h
b/include/uapi/linux/virtio_balloon.h
index d7f1cbc..54aaf20 100644
--- a/include/uapi/linux/virtio_balloon.h
+++ b/include/uapi/linux/virtio_balloon.h
@@ -34,6 +34,7 @@
 #define VIRTIO_BALLOON_F_MUST_TELL_HOST	0 /* Tell before reclaiming pages */
 #define VIRTIO_BALLOON_F_STATS_VQ	1 /* Memory Stats virtqueue */
 #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM	2 /* Deflate balloon on OOM */
+#define VIRTIO_BALLOON_F_GET_FREE_PAGES	3 /* Get free pages bitmap */
 
 /* Size of a PFN in the balloon interface. */
 #define VIRTIO_BALLOON_PFN_SHIFT 12
-- 
1.8.3.1