Merge tag 'for-linus-20190125' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes for this release. This contains:

   - Silence sparse rightfully complaining about non-static wbt
     functions (Bart)

   - Fixes for the zoned comments/ioctl documentation (Damien)

   - direct-io fix that's been lingering for a while (Ernesto)

   - cgroup writeback fix (Tejun)

   - Set of NVMe patches for nvme-rdma/tcp (Sagi, Hannes, Raju)

   - Block recursion tracking fix (Ming)

   - Fix debugfs command flag naming for a few flags (Jianchao)"

* tag 'for-linus-20190125' of git://git.kernel.dk/linux-block:
  block: Fix comment typo
  uapi: fix ioctl documentation
  blk-wbt: Declare local functions static
  blk-mq: fix the cmd_flag_name array
  nvme-multipath: drop optimization for static ANA group IDs
  nvmet-rdma: fix null dereference under heavy load
  nvme-rdma: rework queue maps handling
  nvme-tcp: fix timeout handler
  nvme-rdma: fix timeout handler
  writeback: synchronize sync(2) against cgroup writeback membership switches
  block: cover another queue enter recursion via BIO_QUEUE_ENTERED
  direct-io: allow direct writes to empty inodes

2 files changed, 41 insertions, 4 deletions

diff --git a/fs/direct-io.c b/fs/direct-io.c
index dbc1a1f080ce..ec2fb6fe6d37 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -679,6 +679,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 	unsigned long fs_count;	/* Number of filesystem-sized blocks */
 	int create;
 	unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor;
+	loff_t i_size;
 
 	/*
 	 * If there was a memory error and we've overwritten all the
@@ -708,8 +709,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio,
 		 */
 		create = dio->op == REQ_OP_WRITE;
 		if (dio->flags & DIO_SKIP_HOLES) {
-			if (fs_startblk <= ((i_size_read(dio->inode) - 1) >>
-							i_blkbits))
+			i_size = i_size_read(dio->inode);
+			if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits)
 				create = 0;
 		}
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index b40168fcc94a..36855c1f8daf 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -331,11 +331,22 @@ struct inode_switch_wbs_context {
 	struct work_struct	work;
 };
 
+static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi)
+{
+	down_write(&bdi->wb_switch_rwsem);
+}
+
+static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi)
+{
+	up_write(&bdi->wb_switch_rwsem);
+}
+
 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 backing_dev_info *bdi = inode_to_bdi(inode);
 	struct address_space *mapping = inode->i_mapping;
 	struct bdi_writeback *old_wb = inode->i_wb;
 	struct bdi_writeback *new_wb = isw->new_wb;
@@ -344,6 +355,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 	bool switched = false;
 
 	/*
+	 * If @inode switches cgwb membership while sync_inodes_sb() is
+	 * being issued, sync_inodes_sb() might miss it.  Synchronize.
+	 */
+	down_read(&bdi->wb_switch_rwsem);
+
+	/*
 	 * By the time control reaches here, RCU grace period has passed
 	 * since I_WB_SWITCH assertion and all wb stat update transactions
 	 * between unlocked_inode_to_wb_begin/end() are guaranteed to be
@@ -428,6 +445,8 @@ skip_switch:
 	spin_unlock(&new_wb->list_lock);
 	spin_unlock(&old_wb->list_lock);
 
+	up_read(&bdi->wb_switch_rwsem);
+
 	if (switched) {
 		wb_wakeup(new_wb);
 		wb_put(old_wb);
@@ -468,9 +487,18 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	if (inode->i_state & I_WB_SWITCH)
 		return;
 
+	/*
+	 * Avoid starting new switches while sync_inodes_sb() is in
+	 * progress.  Otherwise, if the down_write protected issue path
+	 * blocks heavily, we might end up starting a large number of
+	 * switches which will block on the rwsem.
+	 */
+	if (!down_read_trylock(&bdi->wb_switch_rwsem))
+		return;
+
 	isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
 	if (!isw)
-		return;
+		goto out_unlock;
 
 	/* find and pin the new wb */
 	rcu_read_lock();
@@ -504,12 +532,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	 * Let's continue after I_WB_SWITCH is guaranteed to be visible.
 	 */
 	call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
-	return;
+	goto out_unlock;
 
 out_free:
 	if (isw->new_wb)
 		wb_put(isw->new_wb);
 	kfree(isw);
+out_unlock:
+	up_read(&bdi->wb_switch_rwsem);
 }
 
 /**
@@ -887,6 +917,9 @@ fs_initcall(cgroup_writeback_init);
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
+static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
+static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { }
+
 static struct bdi_writeback *
 locked_inode_to_wb_and_lock_list(struct inode *inode)
 	__releases(&inode->i_lock)
@@ -2413,8 +2446,11 @@ void sync_inodes_sb(struct super_block *sb)
 		return;
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
+	/* protect against inode wb switch, see inode_switch_wbs_work_fn() */
+	bdi_down_write_wb_switch_rwsem(bdi);
 	bdi_split_work_to_wbs(bdi, &work, false);
 	wb_wait_for_completion(bdi, &done);
+	bdi_up_write_wb_switch_rwsem(bdi);
 
 	wait_sb_inodes(sb);
 }