Merge branch 'for-linus2' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "Round 2 of this.  I cut back to the bare necessities, the patch is
  still larger than it usually would be at this time, due to the number
  of NVMe fixes in there.  This pull request contains:

   - The 4 core fixes from Ming, that fix both problems with exceeding
     the virtual boundary limit in case of merging, and the gap checking
     for cloned bio's.

   - NVMe fixes from Keith and Christoph:

        - Regression on larger user commands, causing problems with
          reading log pages (for instance). This touches both NVMe,
          and the block core since that is now generally utilized also
          for these types of commands.

        - Hot removal fixes.

        - User exploitable issue with passthrough IO commands, if !length
          is given, causing us to fault on writing to the zero
          page.

        - Fix for a hang under error conditions

   - And finally, the current series regression for umount with cgroup
     writeback, where the final flush would happen async and hence open
     up window after umount where the device wasn't consistent.  fsck
     right after umount would show this.  From Tejun"

* 'for-linus2' of git://git.kernel.dk/linux-block:
  block: support large requests in blk_rq_map_user_iov
  block: fix blk_rq_get_max_sectors for driver private requests
  nvme: fix max_segments integer truncation
  nvme: set queue limits for the admin queue
  writeback: flush inode cgroup wb switches instead of pinning super_block
  NVMe: Fix 0-length integrity payload
  NVMe: Don't allow unsupported flags
  NVMe: Move error handling to failed reset handler
  NVMe: Simplify device reset failure
  NVMe: Fix namespace removal deadlock
  NVMe: Use IDA for namespace disk naming
  NVMe: Don't unmap controller registers on reset
  block: merge: get the 1st and last bvec via helpers
  block: get the 1st and last bvec via helpers
  block: check virt boundary in bio_will_gap()
  block: bio: introduce helpers to get the 1st and last bvec

2 files changed, 42 insertions, 13 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 1f76d8950a57..5c46ed9f3e14 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -223,6 +223,9 @@ static void wb_wait_for_completion(struct backing_dev_info *bdi,
 #define WB_FRN_HIST_MAX_SLOTS	(WB_FRN_HIST_THR_SLOTS / 2 + 1)
 					/* one round can affect upto 5 slots */
 
+static atomic_t isw_nr_in_flight = ATOMIC_INIT(0);
+static struct workqueue_struct *isw_wq;
+
 void __inode_attach_wb(struct inode *inode, struct page *page)
 {
 	struct backing_dev_info *bdi = inode_to_bdi(inode);
@@ -317,7 +320,6 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 	struct inode_switch_wbs_context *isw =
 		container_of(work, struct inode_switch_wbs_context, work);
 	struct inode *inode = isw->inode;
-	struct super_block *sb = inode->i_sb;
 	struct address_space *mapping = inode->i_mapping;
 	struct bdi_writeback *old_wb = inode->i_wb;
 	struct bdi_writeback *new_wb = isw->new_wb;
@@ -424,8 +426,9 @@ skip_switch:
 	wb_put(new_wb);
 
 	iput(inode);
-	deactivate_super(sb);
 	kfree(isw);
+
+	atomic_dec(&isw_nr_in_flight);
 }
 
 static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
@@ -435,7 +438,7 @@ static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
 
 	/* needs to grab bh-unsafe locks, bounce to work item */
 	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
-	schedule_work(&isw->work);
+	queue_work(isw_wq, &isw->work);
 }
 
 /**
@@ -471,20 +474,20 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	/* while holding I_WB_SWITCH, no one else can update the association */
 	spin_lock(&inode->i_lock);
-
-	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
-	    inode_to_wb(inode) == isw->new_wb)
-		goto out_unlock;
-
-	if (!atomic_inc_not_zero(&inode->i_sb->s_active))
-		goto out_unlock;
-
+	if (!(inode->i_sb->s_flags & MS_ACTIVE) ||
+	    inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	    inode_to_wb(inode) == isw->new_wb) {
+		spin_unlock(&inode->i_lock);
+		goto out_free;
+	}
 	inode->i_state |= I_WB_SWITCH;
 	spin_unlock(&inode->i_lock);
 
 	ihold(inode);
 	isw->inode = inode;
 
+	atomic_inc(&isw_nr_in_flight);
+
 	/*
 	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
 	 * the RCU protected stat update paths to grab the mapping's
@@ -494,8 +497,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
 	return;
 
-out_unlock:
-	spin_unlock(&inode->i_lock);
 out_free:
 	if (isw->new_wb)
 		wb_put(isw->new_wb);
@@ -847,6 +848,33 @@ restart:
 		wb_put(last_wb);
 }
 
+/**
+ * cgroup_writeback_umount - flush inode wb switches for umount
+ *
+ * This function is called when a super_block is about to be destroyed and
+ * flushes in-flight inode wb switches.  An inode wb switch goes through
+ * RCU and then workqueue, so the two need to be flushed in order to ensure
+ * that all previously scheduled switches are finished.  As wb switches are
+ * rare occurrences and synchronize_rcu() can take a while, perform
+ * flushing iff wb switches are in flight.
+ */
+void cgroup_writeback_umount(void)
+{
+	if (atomic_read(&isw_nr_in_flight)) {
+		synchronize_rcu();
+		flush_workqueue(isw_wq);
+	}
+}
+
+static int __init cgroup_writeback_init(void)
+{
+	isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0);
+	if (!isw_wq)
+		return -ENOMEM;
+	return 0;
+}
+fs_initcall(cgroup_writeback_init);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static struct bdi_writeback *
diff --git a/fs/super.c b/fs/super.c
index 1182af8fd5ff..74914b1bae70 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -415,6 +415,7 @@ void generic_shutdown_super(struct super_block *sb)
 		sb->s_flags &= ~MS_ACTIVE;
 
 		fsnotify_unmount_inodes(sb);
+		cgroup_writeback_umount();
 
 		evict_inodes(sb);