Merge tag 'for-4.11/linus-merge-signed' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:

 - blk-mq scheduling framework from me and Omar, with a port of the
   deadline scheduler for this framework. A port of BFQ from Paolo is in
   the works, and should be ready for 4.12.

 - Various fixups and improvements to the above scheduling framework
   from Omar, Paolo, Bart, me, others.

 - Cleanup of the exported sysfs blk-mq data into debugfs, from Omar.
   This allows us to export more information that helps debug hangs or
   performance issues, without cluttering or abusing the sysfs API.

 - Fixes for the sbitmap code, the scalable bitmap code that was
   migrated from blk-mq, from Omar.

 - Removal of the BLOCK_PC support in struct request, and refactoring of
   carrying SCSI payloads in the block layer. This cleans up the code
   nicely, and enables us to kill the SCSI specific parts of struct
   request, shrinking it down nicely. From Christoph mainly, with help
   from Hannes.

 - Support for ranged discard requests and discard merging, also from
   Christoph.

 - Support for OPAL in the block layer, and for NVMe as well. Mainly
   from Scott Bauer, with fixes/updates from various others folks.

 - Error code fixup for gdrom from Christophe.

 - cciss pci irq allocation cleanup from Christoph.

 - Making the cdrom device operations read only, from Kees Cook.

 - Fixes for duplicate bdi registrations and bdi/queue life time
   problems from Jan and Dan.

 - Set of fixes and updates for lightnvm, from Matias and Javier.

 - A few fixes for nbd from Josef, using idr to name devices and a
   workqueue deadlock fix on receive. Also marks Josef as the current
   maintainer of nbd.

 - Fix from Josef, overwriting queue settings when the number of
   hardware queues is updated for a blk-mq device.

 - NVMe fix from Keith, ensuring that we don't repeatedly mark and IO
   aborted, if we didn't end up aborting it.

 - SG gap merging fix from Ming Lei for block.

 - Loop fix also from Ming, fixing a race and crash between setting loop
   status and IO.

 - Two block race fixes from Tahsin, fixing request list iteration and
   fixing a race between device registration and udev device add
   notifiations.

 - Double free fix from cgroup writeback, from Tejun.

 - Another double free fix in blkcg, from Hou Tao.

 - Partition overflow fix for EFI from Alden Tondettar.

* tag 'for-4.11/linus-merge-signed' of git://git.kernel.dk/linux-block: (156 commits)
  nvme: Check for Security send/recv support before issuing commands.
  block/sed-opal: allocate struct opal_dev dynamically
  block/sed-opal: tone down not supported warnings
  block: don't defer flushes on blk-mq + scheduling
  blk-mq-sched: ask scheduler for work, if we failed dispatching leftovers
  blk-mq: don't special case flush inserts for blk-mq-sched
  blk-mq-sched: don't add flushes to the head of requeue queue
  blk-mq: have blk_mq_dispatch_rq_list() return if we queued IO or not
  block: do not allow updates through sysfs until registration completes
  lightnvm: set default lun range when no luns are specified
  lightnvm: fix off-by-one error on target initialization
  Maintainers: Modify SED list from nvme to block
  Move stack parameters for sed_ioctl to prevent oversized stack with CONFIG_KASAN
  uapi: sed-opal fix IOW for activate lsp to use correct struct
  cdrom: Make device operations read-only
  elevator: fix loading wrong elevator type for blk-mq devices
  cciss: switch to pci_irq_alloc_vectors
  block/loop: fix race between I/O and set_status
  blk-mq-sched: don't hold queue_lock when calling exit_icq
  block: set make_request_fn manually in blk_mq_update_nr_hw_queues
  ...

2 files changed, 42 insertions, 5 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 3bfed5ab..39ce616 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -237,6 +237,7 @@ static __init int bdi_class_init(void)
 
 	bdi_class->dev_groups = bdi_dev_groups;
 	bdi_debug_init();
+
 	return 0;
 }
 postcore_initcall(bdi_class_init);
@@ -758,15 +759,20 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	if (!bdi->wb_congested)
 		return -ENOMEM;
 
+	atomic_set(&bdi->wb_congested->refcnt, 1);
+
 	err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
 	if (err) {
-		kfree(bdi->wb_congested);
+		wb_congested_put(bdi->wb_congested);
 		return err;
 	}
 	return 0;
 }
 
-static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
+static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
+{
+	wb_congested_put(bdi->wb_congested);
+}
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
@@ -776,6 +782,7 @@ int bdi_init(struct backing_dev_info *bdi)
 
 	bdi->dev = NULL;
 
+	kref_init(&bdi->refcnt);
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = FPROP_FRAC_BASE;
@@ -791,6 +798,22 @@ int bdi_init(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_init);
 
+struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id)
+{
+	struct backing_dev_info *bdi;
+
+	bdi = kmalloc_node(sizeof(struct backing_dev_info),
+			   gfp_mask | __GFP_ZERO, node_id);
+	if (!bdi)
+		return NULL;
+
+	if (bdi_init(bdi)) {
+		kfree(bdi);
+		return NULL;
+	}
+	return bdi;
+}
+
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
 {
@@ -871,12 +894,26 @@ void bdi_unregister(struct backing_dev_info *bdi)
 	}
 }
 
-void bdi_exit(struct backing_dev_info *bdi)
+static void bdi_exit(struct backing_dev_info *bdi)
 {
 	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
 }
 
+static void release_bdi(struct kref *ref)
+{
+	struct backing_dev_info *bdi =
+			container_of(ref, struct backing_dev_info, refcnt);
+
+	bdi_exit(bdi);
+	kfree(bdi);
+}
+
+void bdi_put(struct backing_dev_info *bdi)
+{
+	kref_put(&bdi->refcnt, release_bdi);
+}
+
 void bdi_destroy(struct backing_dev_info *bdi)
 {
 	bdi_unregister(bdi);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 290e8b7..2164498 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1988,11 +1988,11 @@ void laptop_mode_timer_fn(unsigned long data)
 	 * We want to write everything out, not just down to the dirty
 	 * threshold
 	 */
-	if (!bdi_has_dirty_io(&q->backing_dev_info))
+	if (!bdi_has_dirty_io(q->backing_dev_info))
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(wb, &q->backing_dev_info.wb_list, bdi_node)
+	list_for_each_entry_rcu(wb, &q->backing_dev_info->wb_list, bdi_node)
 		if (wb_has_dirty_io(wb))
 			wb_start_writeback(wb, nr_pages, true,
 					   WB_REASON_LAPTOP_TIMER);