Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - virtio-mem: paravirtualized memory hotplug

 - support doorbell mapping for vdpa

 - config interrupt support in ifc

 - fixes all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (40 commits)
  vhost/test: fix up after API change
  virtio_mem: convert device block size into 64bit
  virtio-mem: drop unnecessary initialization
  ifcvf: implement config interrupt in IFCVF
  vhost: replace -1 with VHOST_FILE_UNBIND in ioctls
  vhost_vdpa: Support config interrupt in vdpa
  ifcvf: ignore continuous setting same status value
  virtio-mem: Don't rely on implicit compiler padding for requests
  virtio-mem: Try to unplug the complete online memory block first
  virtio-mem: Use -ETXTBSY as error code if the device is busy
  virtio-mem: Unplug subblocks right-to-left
  virtio-mem: Drop manual check for already present memory
  virtio-mem: Add parent resource for all added "System RAM"
  virtio-mem: Better retry handling
  virtio-mem: Offline and remove completely unplugged memory blocks
  mm/memory_hotplug: Introduce offline_and_remove_memory()
  virtio-mem: Allow to offline partially unplugged memory blocks
  mm: Allow to offline unmovable PageOffline() pages via MEM_GOING_OFFLINE
  virtio-mem: Paravirtualized memory hotunplug part 2
  virtio-mem: Paravirtualized memory hotunplug part 1
  ...

1 files changed, 71 insertions, 10 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c4d5c45820d0..9b34e03e730a 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1201,11 +1201,17 @@ struct zone *test_pages_in_a_zone(unsigned long start_pfn,
 
 /*
  * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
- * non-lru movable pages and hugepages). We scan pfn because it's much
- * easier than scanning over linked list. This function returns the pfn
- * of the first found movable page if it's found, otherwise 0.
+ * non-lru movable pages and hugepages). Will skip over most unmovable
+ * pages (esp., pages that can be skipped when offlining), but bail out on
+ * definitely unmovable pages.
+ *
+ * Returns:
+ *	0 in case a movable page is found and movable_pfn was updated.
+ *	-ENOENT in case no movable page was found.
+ *	-EBUSY in case a definitely unmovable page was found.
  */
-static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
+static int scan_movable_pages(unsigned long start, unsigned long end,
+			      unsigned long *movable_pfn)
 {
 	unsigned long pfn;
 
@@ -1217,18 +1223,30 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
 			continue;
 		page = pfn_to_page(pfn);
 		if (PageLRU(page))
-			return pfn;
+			goto found;
 		if (__PageMovable(page))
-			return pfn;
+			goto found;
+
+		/*
+		 * PageOffline() pages that are not marked __PageMovable() and
+		 * have a reference count > 0 (after MEM_GOING_OFFLINE) are
+		 * definitely unmovable. If their reference count would be 0,
+		 * they could at least be skipped when offlining memory.
+		 */
+		if (PageOffline(page) && page_count(page))
+			return -EBUSY;
 
 		if (!PageHuge(page))
 			continue;
 		head = compound_head(page);
 		if (page_huge_active(head))
-			return pfn;
+			goto found;
 		skip = compound_nr(head) - (page - head);
 		pfn += skip - 1;
 	}
+	return -ENOENT;
+found:
+	*movable_pfn = pfn;
 	return 0;
 }
 
@@ -1491,7 +1509,8 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	}
 
 	do {
-		for (pfn = start_pfn; pfn;) {
+		pfn = start_pfn;
+		do {
 			if (signal_pending(current)) {
 				ret = -EINTR;
 				reason = "signal backoff";
@@ -1501,14 +1520,19 @@ static int __ref __offline_pages(unsigned long start_pfn,
 			cond_resched();
 			lru_add_drain_all();
 
-			pfn = scan_movable_pages(pfn, end_pfn);
-			if (pfn) {
+			ret = scan_movable_pages(pfn, end_pfn, &pfn);
+			if (!ret) {
 				/*
 				 * TODO: fatal migration failures should bail
 				 * out
 				 */
 				do_migrate_range(pfn, end_pfn);
 			}
+		} while (!ret);
+
+		if (ret != -ENOENT) {
+			reason = "unmovable page";
+			goto failed_removal_isolated;
 		}
 
 		/*
@@ -1774,4 +1798,41 @@ int remove_memory(int nid, u64 start, u64 size)
 	return rc;
 }
 EXPORT_SYMBOL_GPL(remove_memory);
+
+/*
+ * Try to offline and remove a memory block. Might take a long time to
+ * finish in case memory is still in use. Primarily useful for memory devices
+ * that logically unplugged all memory (so it's no longer in use) and want to
+ * offline + remove the memory block.
+ */
+int offline_and_remove_memory(int nid, u64 start, u64 size)
+{
+	struct memory_block *mem;
+	int rc = -EINVAL;
+
+	if (!IS_ALIGNED(start, memory_block_size_bytes()) ||
+	    size != memory_block_size_bytes())
+		return rc;
+
+	lock_device_hotplug();
+	mem = find_memory_block(__pfn_to_section(PFN_DOWN(start)));
+	if (mem)
+		rc = device_offline(&mem->dev);
+	/* Ignore if the device is already offline. */
+	if (rc > 0)
+		rc = 0;
+
+	/*
+	 * In case we succeeded to offline the memory block, remove it.
+	 * This cannot fail as it cannot get onlined in the meantime.
+	 */
+	if (!rc) {
+		rc = try_remove_memory(nid, start, size);
+		WARN_ON_ONCE(rc);
+	}
+	unlock_device_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(offline_and_remove_memory);
 #endif /* CONFIG_MEMORY_HOTREMOVE */