[PATCH RFC v4 07/13] virtio-mem: Allow to offline partially unplugged memory blocks

[David Hildenbrand]

Dropping the reference count of PageOffline() pages allows offlining
code to skip them. However, we also have to convert PG_reserved to
another flag - let's use PG_dirty - so has_unmovable_pages() will
properly handle them. PG_reserved pages get detected as unmovable right
away.

We need the flag to see if we are onlining pages the first time, or if
we allocated them via alloc_contig_range().

Properly take care of offlining code also modifying the stats and
special handling in case the driver gets unloaded.

Cc: "Michael S. Tsirkin" <mst@xxxxxxxxxx>
Cc: Jason Wang <jasowang@xxxxxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Igor Mammedov <imammedo@xxxxxxxxxx>
Cc: Dave Young <dyoung@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: David Hildenbrand <david@xxxxxxxxxx>
---
 drivers/virtio/virtio_mem.c | 64 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 5a142a371222..a12a0f9c076b 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -564,6 +564,53 @@ static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id,
 		virtio_mem_retry(vm);
 }
 
+static void virtio_mem_notify_going_offline(struct virtio_mem *vm,
+					    unsigned long mb_id)
+{
+	const unsigned long nr_pages = PFN_DOWN(vm->subblock_size);
+	unsigned long pfn;
+	int sb_id, i;
+
+	for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
+		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+			continue;
+		/*
+		 * Drop our reference to the pages so the memory can get
+		 * offlined and add the unplugged pages to the managed
+		 * page counters (so offlining code can correctly subtract
+		 * them again).
+		 */
+		pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+			       sb_id * vm->subblock_size);
+		adjust_managed_page_count(pfn_to_page(pfn), nr_pages);
+		for (i = 0; i < nr_pages; i++)
+			page_ref_dec(pfn_to_page(pfn + i));
+	}
+}
+
+static void virtio_mem_notify_cancel_offline(struct virtio_mem *vm,
+					     unsigned long mb_id)
+{
+	const unsigned long nr_pages = PFN_DOWN(vm->subblock_size);
+	unsigned long pfn;
+	int sb_id, i;
+
+	for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
+		if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+			continue;
+		/*
+		 * Get the reference we dropped when going offline and
+		 * subtract the unplugged pages from the managed page
+		 * counters.
+		 */
+		pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+			       sb_id * vm->subblock_size);
+		adjust_managed_page_count(pfn_to_page(pfn), -nr_pages);
+		for (i = 0; i < nr_pages; i++)
+			page_ref_inc(pfn_to_page(pfn + i));
+	}
+}
+
 /*
  * This callback will either be called synchonously from add_memory() or
  * asynchronously (e.g., triggered via user space). We have to be careful
@@ -611,6 +658,7 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
 			break;
 		mutex_lock(&vm->hotplug_mutex);
 		vm->hotplug_active = true;
+		virtio_mem_notify_going_offline(vm, mb_id);
 		break;
 	case MEM_GOING_ONLINE:
 		spin_lock_irq(&vm->removal_lock);
@@ -636,6 +684,12 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
 		mutex_unlock(&vm->hotplug_mutex);
 		break;
 	case MEM_CANCEL_OFFLINE:
+		if (!vm->hotplug_active)
+			break;
+		virtio_mem_notify_cancel_offline(vm, mb_id);
+		vm->hotplug_active = false;
+		mutex_unlock(&vm->hotplug_mutex);
+		break;
 	case MEM_CANCEL_ONLINE:
 		if (!vm->hotplug_active)
 			break;
@@ -660,8 +714,11 @@ static void virtio_mem_set_fake_offline(unsigned long pfn,
 		struct page *page = pfn_to_page(pfn);
 
 		__SetPageOffline(page);
-		if (!onlined)
+		if (!onlined) {
 			SetPageDirty(page);
+			/* FIXME: remove after cleanups */
+			ClearPageReserved(page);
+		}
 	}
 }
 
@@ -1719,6 +1776,11 @@ static void virtio_mem_remove(struct virtio_device *vdev)
 		rc = virtio_mem_mb_remove(vm, mb_id);
 		BUG_ON(rc);
 	}
+	/*
+	 * After we unregistered our callbacks, user space can no longer
+	 * offline partially plugged online memory blocks. No need to worry
+	 * about them.
+	 */
 
 	/* unregister callbacks */
 	unregister_virtio_mem_device(vm);
-- 
2.23.0