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

Pull virtio updates from Michael Tsirkin:

 - vdpa sim refactoring

 - virtio mem: Big Block Mode support

 - misc cleanus, fixes

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (61 commits)
  vdpa: Use simpler version of ida allocation
  vdpa: Add missing comment for virtqueue count
  uapi: virtio_ids: add missing device type IDs from OASIS spec
  uapi: virtio_ids.h: consistent indentions
  vhost scsi: fix error return code in vhost_scsi_set_endpoint()
  virtio_ring: Fix two use after free bugs
  virtio_net: Fix error code in probe()
  virtio_ring: Cut and paste bugs in vring_create_virtqueue_packed()
  tools/virtio: add barrier for aarch64
  tools/virtio: add krealloc_array
  tools/virtio: include asm/bug.h
  vdpa/mlx5: Use write memory barrier after updating CQ index
  vdpa: split vdpasim to core and net modules
  vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov
  vdpa_sim: make vdpasim->buffer size configurable
  vdpa_sim: use kvmalloc to allocate vdpasim->buffer
  vdpa_sim: set vringh notify callback
  vdpa_sim: add set_config callback in vdpasim_dev_attr
  vdpa_sim: add get_config callback in vdpasim_dev_attr
  vdpa_sim: make 'config' generic and usable for any device type
  ...

1 files changed, 89 insertions, 16 deletions

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c01604224299..af41fb990820 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1784,39 +1784,112 @@ int remove_memory(int nid, u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(remove_memory);
 
+static int try_offline_memory_block(struct memory_block *mem, void *arg)
+{
+	uint8_t online_type = MMOP_ONLINE_KERNEL;
+	uint8_t **online_types = arg;
+	struct page *page;
+	int rc;
+
+	/*
+	 * Sense the online_type via the zone of the memory block. Offlining
+	 * with multiple zones within one memory block will be rejected
+	 * by offlining code ... so we don't care about that.
+	 */
+	page = pfn_to_online_page(section_nr_to_pfn(mem->start_section_nr));
+	if (page && zone_idx(page_zone(page)) == ZONE_MOVABLE)
+		online_type = MMOP_ONLINE_MOVABLE;
+
+	rc = device_offline(&mem->dev);
+	/*
+	 * Default is MMOP_OFFLINE - change it only if offlining succeeded,
+	 * so try_reonline_memory_block() can do the right thing.
+	 */
+	if (!rc)
+		**online_types = online_type;
+
+	(*online_types)++;
+	/* Ignore if already offline. */
+	return rc < 0 ? rc : 0;
+}
+
+static int try_reonline_memory_block(struct memory_block *mem, void *arg)
+{
+	uint8_t **online_types = arg;
+	int rc;
+
+	if (**online_types != MMOP_OFFLINE) {
+		mem->online_type = **online_types;
+		rc = device_online(&mem->dev);
+		if (rc < 0)
+			pr_warn("%s: Failed to re-online memory: %d",
+				__func__, rc);
+	}
+
+	/* Continue processing all remaining memory blocks. */
+	(*online_types)++;
+	return 0;
+}
+
 /*
- * 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.
+ * Try to offline and remove memory. 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
+ * that memory.
  */
 int offline_and_remove_memory(int nid, u64 start, u64 size)
 {
-	struct memory_block *mem;
-	int rc = -EINVAL;
+	const unsigned long mb_count = size / memory_block_size_bytes();
+	uint8_t *online_types, *tmp;
+	int rc;
 
 	if (!IS_ALIGNED(start, memory_block_size_bytes()) ||
-	    size != memory_block_size_bytes())
-		return rc;
+	    !IS_ALIGNED(size, memory_block_size_bytes()) || !size)
+		return -EINVAL;
+
+	/*
+	 * We'll remember the old online type of each memory block, so we can
+	 * try to revert whatever we did when offlining one memory block fails
+	 * after offlining some others succeeded.
+	 */
+	online_types = kmalloc_array(mb_count, sizeof(*online_types),
+				     GFP_KERNEL);
+	if (!online_types)
+		return -ENOMEM;
+	/*
+	 * Initialize all states to MMOP_OFFLINE, so when we abort processing in
+	 * try_offline_memory_block(), we'll skip all unprocessed blocks in
+	 * try_reonline_memory_block().
+	 */
+	memset(online_types, MMOP_OFFLINE, mb_count);
 
 	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;
+
+	tmp = online_types;
+	rc = walk_memory_blocks(start, size, &tmp, try_offline_memory_block);
 
 	/*
-	 * In case we succeeded to offline the memory block, remove it.
+	 * In case we succeeded to offline all memory, 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);
+		if (rc)
+			pr_err("%s: Failed to remove memory: %d", __func__, rc);
+	}
+
+	/*
+	 * Rollback what we did. While memory onlining might theoretically fail
+	 * (nacked by a notifier), it barely ever happens.
+	 */
+	if (rc) {
+		tmp = online_types;
+		walk_memory_blocks(start, size, &tmp,
+				   try_reonline_memory_block);
 	}
 	unlock_device_hotplug();
 
+	kfree(online_types);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(offline_and_remove_memory);