Merge branch 'for-4.14/block' of git://git.kernel.dk/linux-block

Pull block layer updates from Jens Axboe:
 "This is the first pull request for 4.14, containing most of the code
  changes. It's a quiet series this round, which I think we needed after
  the churn of the last few series. This contains:

   - Fix for a registration race in loop, from Anton Volkov.

   - Overflow complaint fix from Arnd for DAC960.

   - Series of drbd changes from the usual suspects.

   - Conversion of the stec/skd driver to blk-mq. From Bart.

   - A few BFQ improvements/fixes from Paolo.

   - CFQ improvement from Ritesh, allowing idling for group idle.

   - A few fixes found by Dan's smatch, courtesy of Dan.

   - A warning fixup for a race between changing the IO scheduler and
     device remova. From David Jeffery.

   - A few nbd fixes from Josef.

   - Support for cgroup info in blktrace, from Shaohua.

   - Also from Shaohua, new features in the null_blk driver to allow it
     to actually hold data, among other things.

   - Various corner cases and error handling fixes from Weiping Zhang.

   - Improvements to the IO stats tracking for blk-mq from me. Can
     drastically improve performance for fast devices and/or big
     machines.

   - Series from Christoph removing bi_bdev as being needed for IO
     submission, in preparation for nvme multipathing code.

   - Series from Bart, including various cleanups and fixes for switch
     fall through case complaints"

* 'for-4.14/block' of git://git.kernel.dk/linux-block: (162 commits)
  kernfs: checking for IS_ERR() instead of NULL
  drbd: remove BIOSET_NEED_RESCUER flag from drbd_{md_,}io_bio_set
  drbd: Fix allyesconfig build, fix recent commit
  drbd: switch from kmalloc() to kmalloc_array()
  drbd: abort drbd_start_resync if there is no connection
  drbd: move global variables to drbd namespace and make some static
  drbd: rename "usermode_helper" to "drbd_usermode_helper"
  drbd: fix race between handshake and admin disconnect/down
  drbd: fix potential deadlock when trying to detach during handshake
  drbd: A single dot should be put into a sequence.
  drbd: fix rmmod cleanup, remove _all_ debugfs entries
  drbd: Use setup_timer() instead of init_timer() to simplify the code.
  drbd: fix potential get_ldev/put_ldev refcount imbalance during attach
  drbd: new disk-option disable-write-same
  drbd: Fix resource role for newly created resources in events2
  drbd: mark symbols static where possible
  drbd: Send P_NEG_ACK upon write error in protocol != C
  drbd: add explicit plugging when submitting batches
  drbd: change list_for_each_safe to while(list_first_entry_or_null)
  drbd: introduce drbd_recv_header_maybe_unplug
  ...

1 files changed, 47 insertions, 1 deletions

diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index eea0c4aec978..0813c654c893 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -346,7 +346,7 @@ static enum drbd_role min_role(enum drbd_role role1, enum drbd_role role2)
 
 enum drbd_role conn_highest_role(struct drbd_connection *connection)
 {
-	enum drbd_role role = R_UNKNOWN;
+	enum drbd_role role = R_SECONDARY;
 	struct drbd_peer_device *peer_device;
 	int vnr;
 
@@ -579,11 +579,14 @@ drbd_req_state(struct drbd_device *device, union drbd_state mask,
 	unsigned long flags;
 	union drbd_state os, ns;
 	enum drbd_state_rv rv;
+	void *buffer = NULL;
 
 	init_completion(&done);
 
 	if (f & CS_SERIALIZE)
 		mutex_lock(device->state_mutex);
+	if (f & CS_INHIBIT_MD_IO)
+		buffer = drbd_md_get_buffer(device, __func__);
 
 	spin_lock_irqsave(&device->resource->req_lock, flags);
 	os = drbd_read_state(device);
@@ -636,6 +639,8 @@ drbd_req_state(struct drbd_device *device, union drbd_state mask,
 	}
 
 abort:
+	if (buffer)
+		drbd_md_put_buffer(device);
 	if (f & CS_SERIALIZE)
 		mutex_unlock(device->state_mutex);
 
@@ -664,6 +669,47 @@ _drbd_request_state(struct drbd_device *device, union drbd_state mask,
 	return rv;
 }
 
+/*
+ * We grab drbd_md_get_buffer(), because we don't want to "fail" the disk while
+ * there is IO in-flight: the transition into D_FAILED for detach purposes
+ * may get misinterpreted as actual IO error in a confused endio function.
+ *
+ * We wrap it all into wait_event(), to retry in case the drbd_req_state()
+ * returns SS_IN_TRANSIENT_STATE.
+ *
+ * To avoid potential deadlock with e.g. the receiver thread trying to grab
+ * drbd_md_get_buffer() while trying to get out of the "transient state", we
+ * need to grab and release the meta data buffer inside of that wait_event loop.
+ */
+static enum drbd_state_rv
+request_detach(struct drbd_device *device)
+{
+	return drbd_req_state(device, NS(disk, D_FAILED),
+			CS_VERBOSE | CS_ORDERED | CS_INHIBIT_MD_IO);
+}
+
+enum drbd_state_rv
+drbd_request_detach_interruptible(struct drbd_device *device)
+{
+	enum drbd_state_rv rv;
+	int ret;
+
+	drbd_suspend_io(device); /* so no-one is stuck in drbd_al_begin_io */
+	wait_event_interruptible(device->state_wait,
+		(rv = request_detach(device)) != SS_IN_TRANSIENT_STATE);
+	drbd_resume_io(device);
+
+	ret = wait_event_interruptible(device->misc_wait,
+			device->state.disk != D_FAILED);
+
+	if (rv == SS_IS_DISKLESS)
+		rv = SS_NOTHING_TO_DO;
+	if (ret)
+		rv = ERR_INTR;
+
+	return rv;
+}
+
 enum drbd_state_rv
 _drbd_request_state_holding_state_mutex(struct drbd_device *device, union drbd_state mask,
 		    union drbd_state val, enum chg_state_flags f)