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
  ...

3 files changed, 106 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 */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 727751219003..48eb0f1410d4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -8285,6 +8285,19 @@ struct page *has_unmovable_pages(struct zone *zone, struct page *page,
 		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
 			continue;
 
+		/*
+		 * We treat all PageOffline() pages as movable when offlining
+		 * to give drivers a chance to decrement their reference count
+		 * in MEM_GOING_OFFLINE in order to indicate that these pages
+		 * can be offlined as there are no direct references anymore.
+		 * For actually unmovable PageOffline() where the driver does
+		 * not support this, we will fail later when trying to actually
+		 * move these pages that still have a reference count > 0.
+		 * (false negatives in this function only)
+		 */
+		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
+			continue;
+
 		if (__PageMovable(page) || PageLRU(page))
 			continue;
 
@@ -8516,6 +8529,7 @@ done:
 				pfn_max_align_up(end), migratetype);
 	return ret;
 }
+EXPORT_SYMBOL(alloc_contig_range);
 
 static int __alloc_contig_pages(unsigned long start_pfn,
 				unsigned long nr_pages, gfp_t gfp_mask)
@@ -8631,6 +8645,7 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages)
 	}
 	WARN(count != 0, "%d pages are still in use!\n", count);
 }
+EXPORT_SYMBOL(free_contig_range);
 
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
@@ -8703,6 +8718,17 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 			offlined_pages++;
 			continue;
 		}
+		/*
+		 * At this point all remaining PageOffline() pages have a
+		 * reference count of 0 and can simply be skipped.
+		 */
+		if (PageOffline(page)) {
+			BUG_ON(page_count(page));
+			BUG_ON(PageBuddy(page));
+			pfn++;
+			offlined_pages++;
+			continue;
+		}
 
 		BUG_ON(page_count(page));
 		BUG_ON(!PageBuddy(page));
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 2c11a38d6e87..f6d07c5f0d34 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -151,6 +151,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  *			a bit mask)
  *			MEMORY_OFFLINE - isolate to offline (!allocate) memory
  *					 e.g., skip over PageHWPoison() pages
+ *					 and PageOffline() pages.
  *			REPORT_FAILURE - report details about the failure to
  *			isolate the range
  *
@@ -259,6 +260,14 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
 		else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
 			/* A HWPoisoned page cannot be also PageBuddy */
 			pfn++;
+		else if ((flags & MEMORY_OFFLINE) && PageOffline(page) &&
+			 !page_count(page))
+			/*
+			 * The responsible driver agreed to skip PageOffline()
+			 * pages when offlining memory by dropping its
+			 * reference in MEM_GOING_OFFLINE.
+			 */
+			pfn++;
 		else
 			break;
 	}