virtio-mem: Offline and remove completely unplugged memory blocks

Let's offline+remove memory blocks once all subblocks are unplugged. We
can use the new Linux MM interface for that. As no memory is in use
anymore, this shouldn't take a long time and shouldn't fail. There might
be corner cases where the offlining could still fail (especially, if
another notifier NACKs the offlining request).

Acked-by: Pankaj Gupta <[email protected]>
Tested-by: Pankaj Gupta <[email protected]>
Cc: "Michael S. Tsirkin" <[email protected]>
Cc: Jason Wang <[email protected]>
Cc: Oscar Salvador <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Igor Mammedov <[email protected]>
Cc: Dave Young <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Dan Williams <[email protected]>
Cc: Pavel Tatashin <[email protected]>
Cc: Stefan Hajnoczi <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Signed-off-by: David Hildenbrand <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Michael S. Tsirkin <[email protected]>

Author: davidhildenbrand

drivers/virtio/virtio_mem.c

@@ -446,6 +446,28 @@ static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id)
 	return remove_memory(nid, addr, memory_block_size_bytes());
 }
 
+/*
+ * Try to offline and remove a memory block from Linux.
+ *
+ * Must not be called with the vm->hotplug_mutex held (possible deadlock with
+ * onlining code).
+ *
+ * Will not modify the state of the memory block.
+ */
+static int virtio_mem_mb_offline_and_remove(struct virtio_mem *vm,
+					    unsigned long mb_id)
+{
+	const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+	int nid = vm->nid;
+
+	if (nid == NUMA_NO_NODE)
+		nid = memory_add_physaddr_to_nid(addr);
+
+	dev_dbg(&vm->vdev->dev, "offlining and removing memory block: %lu\n",
+		mb_id);
+	return offline_and_remove_memory(nid, addr, memory_block_size_bytes());
+}
+
 /*
  * Trigger the workqueue so the device can perform its magic.
  */
@@ -537,7 +559,13 @@ static void virtio_mem_notify_offline(struct virtio_mem *vm,
 		break;
 	}
 
-	/* trigger the workqueue, maybe we can now unplug memory. */
+	/*
+	 * Trigger the workqueue, maybe we can now unplug memory. Also,
+	 * when we offline and remove a memory block, this will re-trigger
+	 * us immediately - which is often nice because the removal of
+	 * the memory block (e.g., memmap) might have freed up memory
+	 * on other memory blocks we manage.
+	 */
 	virtio_mem_retry(vm);
 }
 
@@ -1284,7 +1312,8 @@ static int virtio_mem_mb_unplug_any_sb_offline(struct virtio_mem *vm,
  * Unplug the desired number of plugged subblocks of an online memory block.
  * Will skip subblock that are busy.
  *
- * Will modify the state of the memory block.
+ * Will modify the state of the memory block. Might temporarily drop the
+ * hotplug_mutex.
  *
  * Note: Can fail after some subblocks were successfully unplugged. Can
  *       return 0 even if subblocks were busy and could not get unplugged.
@@ -1340,9 +1369,19 @@ static int virtio_mem_mb_unplug_any_sb_online(struct virtio_mem *vm,
 	}
 
 	/*
-	 * TODO: Once all subblocks of a memory block were unplugged, we want
-	 * to offline the memory block and remove it.
+	 * Once all subblocks of a memory block were unplugged, offline and
+	 * remove it. This will usually not fail, as no memory is in use
+	 * anymore - however some other notifiers might NACK the request.
 	 */
+	if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+		mutex_unlock(&vm->hotplug_mutex);
+		rc = virtio_mem_mb_offline_and_remove(vm, mb_id);
+		mutex_lock(&vm->hotplug_mutex);
+		if (!rc)
+			virtio_mem_mb_set_state(vm, mb_id,
+						VIRTIO_MEM_MB_STATE_UNUSED);
+	}
+
 	return 0;
 }