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
  ...

11 files changed, 76 insertions, 16 deletions

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3c47614a4b32..73031ec54a7b 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -884,6 +884,8 @@ static void bdev_evict_inode(struct inode *inode)
 	spin_lock(&bdev_lock);
 	list_del_init(&bdev->bd_list);
 	spin_unlock(&bdev_lock);
+	if (bdev->bd_bdi != &noop_backing_dev_info)
+		bdi_put(bdev->bd_bdi);
 }
 
 static const struct super_operations bdev_sops = {
@@ -954,6 +956,21 @@ static int bdev_set(struct inode *inode, void *data)
 
 static LIST_HEAD(all_bdevs);
 
+/*
+ * If there is a bdev inode for this device, unhash it so that it gets evicted
+ * as soon as last inode reference is dropped.
+ */
+void bdev_unhash_inode(dev_t dev)
+{
+	struct inode *inode;
+
+	inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev);
+	if (inode) {
+		remove_inode_hash(inode);
+		iput(inode);
+	}
+}
+
 struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
@@ -971,6 +988,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
+		bdev->bd_bdi = &noop_backing_dev_info;
 		bdev->bd_block_size = (1 << inode->i_blkbits);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
@@ -1527,6 +1545,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 		bdev->bd_disk = disk;
 		bdev->bd_queue = disk->queue;
 		bdev->bd_contains = bdev;
+		if (bdev->bd_bdi == &noop_backing_dev_info)
+			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 
 		if (!partno) {
 			ret = -ENXIO;
@@ -1622,6 +1642,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 	bdev->bd_disk = NULL;
 	bdev->bd_part = NULL;
 	bdev->bd_queue = NULL;
+	bdi_put(bdev->bd_bdi);
+	bdev->bd_bdi = &noop_backing_dev_info;
 	if (bdev != bdev->bd_contains)
 		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 18004169552c..37a31b12bb0c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1800,7 +1800,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
 		if (!device->bdev)
 			continue;
-		bdi = blk_get_backing_dev_info(device->bdev);
+		bdi = device->bdev->bd_bdi;
 		if (bdi_congested(bdi, bdi_bits)) {
 			ret = 1;
 			break;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3c3c69c0eee4..b2e70073a10d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -366,7 +366,7 @@ static noinline void run_scheduled_bios(struct btrfs_device *device)
 	 */
 	blk_start_plug(&plug);
 
-	bdi = blk_get_backing_dev_info(device->bdev);
+	bdi = device->bdev->bd_bdi;
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
 
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index f17fcf89e18e..7fb1732a3630 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -248,6 +248,42 @@ static struct file_system_type debug_fs_type = {
 };
 MODULE_ALIAS_FS("debugfs");
 
+/**
+ * debugfs_lookup() - look up an existing debugfs file
+ * @name: a pointer to a string containing the name of the file to look up.
+ * @parent: a pointer to the parent dentry of the file.
+ *
+ * This function will return a pointer to a dentry if it succeeds.  If the file
+ * doesn't exist or an error occurs, %NULL will be returned.  The returned
+ * dentry must be passed to dput() when it is no longer needed.
+ *
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	if (IS_ERR(parent))
+		return NULL;
+
+	if (!parent)
+		parent = debugfs_mount->mnt_root;
+
+	inode_lock(d_inode(parent));
+	dentry = lookup_one_len(name, parent, strlen(name));
+	inode_unlock(d_inode(parent));
+
+	if (IS_ERR(dentry))
+		return NULL;
+	if (!d_really_is_positive(dentry)) {
+		dput(dentry);
+		return NULL;
+	}
+	return dentry;
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup);
+
 static struct dentry *start_creating(const char *name, struct dentry *parent)
 {
 	struct dentry *dentry;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 58704799f0b9..b108e7ba81af 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1227,7 +1227,7 @@ static int set_gfs2_super(struct super_block *s, void *data)
 	 * We set the bdi here to the queue backing, file systems can
 	 * overwrite this in ->fill_super()
 	 */
-	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
+	s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 47febcf99185..20b1c17320d5 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -104,6 +104,7 @@ config NFSD_SCSILAYOUT
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
 	select EXPORTFS_BLOCK_OPS
+	select BLK_SCSI_REQUEST
 	help
 	  This option enables support for the exporting pNFS SCSI layouts
 	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 0780ff864539..a06115e31612 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -10,6 +10,7 @@
 #include <linux/nfsd/debug.h>
 #include <scsi/scsi_proto.h>
 #include <scsi/scsi_common.h>
+#include <scsi/scsi_request.h>
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
@@ -213,6 +214,7 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 {
 	struct request_queue *q = bdev->bd_disk->queue;
 	struct request *rq;
+	struct scsi_request *req;
 	size_t bufflen = 252, len, id_len;
 	u8 *buf, *d, type, assoc;
 	int error;
@@ -221,23 +223,24 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 	if (!buf)
 		return -ENOMEM;
 
-	rq = blk_get_request(q, READ, GFP_KERNEL);
+	rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		error = -ENOMEM;
 		goto out_free_buf;
 	}
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
+	scsi_req_init(rq);
 
 	error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
 	if (error)
 		goto out_put_request;
 
-	rq->cmd[0] = INQUIRY;
-	rq->cmd[1] = 1;
-	rq->cmd[2] = 0x83;
-	rq->cmd[3] = bufflen >> 8;
-	rq->cmd[4] = bufflen & 0xff;
-	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+	req->cmd[0] = INQUIRY;
+	req->cmd[1] = 1;
+	req->cmd[2] = 0x83;
+	req->cmd[3] = bufflen >> 8;
+	req->cmd[4] = bufflen & 0xff;
+	req->cmd_len = COMMAND_SIZE(INQUIRY);
 
 	error = blk_execute_rq(rq->q, NULL, rq, 1);
 	if (error) {
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 12eeae62a2b1..e1872f36147f 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
+	sb->s_bdi = bdev_get_queue(sb->s_bdev)->backing_dev_info;
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/super.c b/fs/super.c
index 1709ed029a2c..ea662b0e5e78 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1047,7 +1047,7 @@ static int set_bdev_super(struct super_block *s, void *data)
 	 * We set the bdi here to the queue backing, file systems can
 	 * overwrite this in ->fill_super()
 	 */
-	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
+	s->s_bdi = bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index ac3b4db519df..8c7d01b75922 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -758,7 +758,7 @@ xfs_buf_readahead_map(
 	int			nmaps,
 	const struct xfs_buf_ops *ops)
 {
-	if (bdi_read_congested(target->bt_bdi))
+	if (bdi_read_congested(target->bt_bdev->bd_bdi))
 		return;
 
 	xfs_buf_read_map(target, map, nmaps,
@@ -1791,7 +1791,6 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_bdi = blk_get_backing_dev_info(bdev);
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 8a9d3a9599f0..3c867e5a63e1 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -109,7 +109,6 @@ typedef unsigned int xfs_buf_flags_t;
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
-	struct backing_dev_info	*bt_bdi;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;