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
  ...

18 files changed, 143 insertions, 81 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1f0720de8990..275c91c99516 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -471,10 +471,11 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-void generic_start_io_acct(int rw, unsigned long sectors,
-			   struct hd_struct *part);
-void generic_end_io_acct(int rw, struct hd_struct *part,
-			 unsigned long start_time);
+void generic_start_io_acct(struct request_queue *q, int rw,
+				unsigned long sectors, struct hd_struct *part);
+void generic_end_io_acct(struct request_queue *q, int rw,
+				struct hd_struct *part,
+				unsigned long start_time);
 
 #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 # error	"You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform"
@@ -501,6 +502,24 @@ extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
 extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 
+#define bio_set_dev(bio, bdev) 			\
+do {						\
+	(bio)->bi_disk = (bdev)->bd_disk;	\
+	(bio)->bi_partno = (bdev)->bd_partno;	\
+} while (0)
+
+#define bio_copy_dev(dst, src)			\
+do {						\
+	(dst)->bi_disk = (src)->bi_disk;	\
+	(dst)->bi_partno = (src)->bi_partno;	\
+} while (0)
+
+#define bio_dev(bio) \
+	disk_devt((bio)->bi_disk)
+
+#define bio_devname(bio, buf) \
+	__bdevname(bio_dev(bio), (buf))
+
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 int bio_associate_current(struct bio *bio);
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 7104bea8dab1..9d92153dd856 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -691,6 +691,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	rcu_read_lock();
 	blkcg = bio_blkcg(bio);
 
+	/* associate blkcg if bio hasn't attached one */
+	bio_associate_blkcg(bio, &blkcg->css);
+
 	blkg = blkg_lookup(blkcg, q);
 	if (unlikely(!blkg)) {
 		spin_lock_irq(q->queue_lock);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 14542308d25b..50c6485cb04f 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -97,7 +97,6 @@ typedef int (init_request_fn)(struct blk_mq_tag_set *set, struct request *,
 		unsigned int, unsigned int);
 typedef void (exit_request_fn)(struct blk_mq_tag_set *set, struct request *,
 		unsigned int);
-typedef int (reinit_request_fn)(void *, struct request *);
 
 typedef void (busy_iter_fn)(struct blk_mq_hw_ctx *, struct request *, void *,
 		bool);
@@ -143,7 +142,6 @@ struct blk_mq_ops {
 	 */
 	init_request_fn		*init_request;
 	exit_request_fn		*exit_request;
-	reinit_request_fn	*reinit_request;
 	/* Called from inside blk_get_request() */
 	void (*initialize_rq_fn)(struct request *rq);
 
@@ -261,7 +259,8 @@ void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
-int blk_mq_reinit_tagset(struct blk_mq_tag_set *set);
+int blk_mq_reinit_tagset(struct blk_mq_tag_set *set,
+			 int (reinit_request)(void *, struct request *));
 
 int blk_mq_map_queues(struct blk_mq_tag_set *set);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d2eb87c84d82..a2d2aa709cef 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -48,7 +48,8 @@ struct blk_issue_stat {
  */
 struct bio {
 	struct bio		*bi_next;	/* request queue link */
-	struct block_device	*bi_bdev;
+	struct gendisk		*bi_disk;
+	u8			bi_partno;
 	blk_status_t		bi_status;
 	unsigned int		bi_opf;		/* bottom bits req flags,
 						 * top bits REQ_OP. Use
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4b99b13c7e68..460294bb0fa5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -600,38 +600,36 @@ struct request_queue {
 	u64			write_hints[BLK_MAX_WRITE_HINTS];
 };
 
-#define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
-#define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
-#define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
-#define QUEUE_FLAG_ASYNCFULL	4	/* write queue has been filled */
-#define QUEUE_FLAG_DYING	5	/* queue being torn down */
-#define QUEUE_FLAG_BYPASS	6	/* act as dumb FIFO queue */
-#define QUEUE_FLAG_BIDI		7	/* queue supports bidi requests */
-#define QUEUE_FLAG_NOMERGES     8	/* disable merge attempts */
-#define QUEUE_FLAG_SAME_COMP	9	/* complete on same CPU-group */
-#define QUEUE_FLAG_FAIL_IO     10	/* fake timeout */
-#define QUEUE_FLAG_STACKABLE   11	/* supports request stacking */
-#define QUEUE_FLAG_NONROT      12	/* non-rotational device (SSD) */
+#define QUEUE_FLAG_QUEUED	0	/* uses generic tag queueing */
+#define QUEUE_FLAG_STOPPED	1	/* queue is stopped */
+#define QUEUE_FLAG_DYING	2	/* queue being torn down */
+#define QUEUE_FLAG_BYPASS	3	/* act as dumb FIFO queue */
+#define QUEUE_FLAG_BIDI		4	/* queue supports bidi requests */
+#define QUEUE_FLAG_NOMERGES     5	/* disable merge attempts */
+#define QUEUE_FLAG_SAME_COMP	6	/* complete on same CPU-group */
+#define QUEUE_FLAG_FAIL_IO	7	/* fake timeout */
+#define QUEUE_FLAG_STACKABLE	8	/* supports request stacking */
+#define QUEUE_FLAG_NONROT	9	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
-#define QUEUE_FLAG_IO_STAT     13	/* do IO stats */
-#define QUEUE_FLAG_DISCARD     14	/* supports DISCARD */
-#define QUEUE_FLAG_NOXMERGES   15	/* No extended merges */
-#define QUEUE_FLAG_ADD_RANDOM  16	/* Contributes to random pool */
-#define QUEUE_FLAG_SECERASE    17	/* supports secure erase */
-#define QUEUE_FLAG_SAME_FORCE  18	/* force complete on same CPU */
-#define QUEUE_FLAG_DEAD        19	/* queue tear-down finished */
-#define QUEUE_FLAG_INIT_DONE   20	/* queue is initialized */
-#define QUEUE_FLAG_NO_SG_MERGE 21	/* don't attempt to merge SG segments*/
-#define QUEUE_FLAG_POLL	       22	/* IO polling enabled if set */
-#define QUEUE_FLAG_WC	       23	/* Write back caching */
-#define QUEUE_FLAG_FUA	       24	/* device supports FUA writes */
-#define QUEUE_FLAG_FLUSH_NQ    25	/* flush not queueuable */
-#define QUEUE_FLAG_DAX         26	/* device supports DAX */
-#define QUEUE_FLAG_STATS       27	/* track rq completion times */
-#define QUEUE_FLAG_POLL_STATS  28	/* collecting stats for hybrid polling */
-#define QUEUE_FLAG_REGISTERED  29	/* queue has been registered to a disk */
-#define QUEUE_FLAG_SCSI_PASSTHROUGH 30	/* queue supports SCSI commands */
-#define QUEUE_FLAG_QUIESCED    31	/* queue has been quiesced */
+#define QUEUE_FLAG_IO_STAT     10	/* do IO stats */
+#define QUEUE_FLAG_DISCARD     11	/* supports DISCARD */
+#define QUEUE_FLAG_NOXMERGES   12	/* No extended merges */
+#define QUEUE_FLAG_ADD_RANDOM  13	/* Contributes to random pool */
+#define QUEUE_FLAG_SECERASE    14	/* supports secure erase */
+#define QUEUE_FLAG_SAME_FORCE  15	/* force complete on same CPU */
+#define QUEUE_FLAG_DEAD        16	/* queue tear-down finished */
+#define QUEUE_FLAG_INIT_DONE   17	/* queue is initialized */
+#define QUEUE_FLAG_NO_SG_MERGE 18	/* don't attempt to merge SG segments*/
+#define QUEUE_FLAG_POLL	       19	/* IO polling enabled if set */
+#define QUEUE_FLAG_WC	       20	/* Write back caching */
+#define QUEUE_FLAG_FUA	       21	/* device supports FUA writes */
+#define QUEUE_FLAG_FLUSH_NQ    22	/* flush not queueuable */
+#define QUEUE_FLAG_DAX         23	/* device supports DAX */
+#define QUEUE_FLAG_STATS       24	/* track rq completion times */
+#define QUEUE_FLAG_POLL_STATS  25	/* collecting stats for hybrid polling */
+#define QUEUE_FLAG_REGISTERED  26	/* queue has been registered to a disk */
+#define QUEUE_FLAG_SCSI_PASSTHROUGH 27	/* queue supports SCSI commands */
+#define QUEUE_FLAG_QUIESCED    28	/* queue has been quiesced */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index d2e908586e3d..67b4d4dfc19c 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -28,10 +28,12 @@ struct blk_trace {
 	atomic_t dropped;
 };
 
+struct blkcg;
+
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern __printf(2, 3)
-void __trace_note_message(struct blk_trace *, const char *fmt, ...);
+extern __printf(3, 4)
+void __trace_note_message(struct blk_trace *, struct blkcg *blkcg, const char *fmt, ...);
 
 /**
  * blk_add_trace_msg - Add a (simple) message to the blktrace stream
@@ -46,12 +48,14 @@ void __trace_note_message(struct blk_trace *, const char *fmt, ...);
  *     NOTE: Can not use 'static inline' due to presence of var args...
  *
  **/
-#define blk_add_trace_msg(q, fmt, ...)					\
+#define blk_add_cgroup_trace_msg(q, cg, fmt, ...)			\
 	do {								\
 		struct blk_trace *bt = (q)->blk_trace;			\
 		if (unlikely(bt))					\
-			__trace_note_message(bt, fmt, ##__VA_ARGS__);	\
+			__trace_note_message(bt, cg, fmt, ##__VA_ARGS__);\
 	} while (0)
+#define blk_add_trace_msg(q, fmt, ...)					\
+	blk_add_cgroup_trace_msg(q, NULL, fmt, ##__VA_ARGS__)
 #define BLK_TN_MAX_MSG		128
 
 static inline bool blk_trace_note_message_enabled(struct request_queue *q)
@@ -82,6 +86,7 @@ extern struct attribute_group blk_trace_attr_group;
 # define blk_trace_startstop(q, start)			(-ENOTTY)
 # define blk_trace_remove(q)				(-ENOTTY)
 # define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
+# define blk_add_cgroup_trace_msg(q, cg, fmt, ...)	do { } while (0)
 # define blk_trace_remove_sysfs(dev)			do { } while (0)
 # define blk_trace_note_message_enabled(q)		(false)
 static inline int blk_trace_init_sysfs(struct device *dev)
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 085056e562b1..d023ac5e377f 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -578,7 +578,7 @@ static inline bool cgroup_is_populated(struct cgroup *cgrp)
 /* returns ino associated with a cgroup */
 static inline ino_t cgroup_ino(struct cgroup *cgrp)
 {
-	return cgrp->kn->ino;
+	return cgrp->kn->id.ino;
 }
 
 /* cft/css accessors for cftype->write() operation */
@@ -644,6 +644,13 @@ static inline void cgroup_kthread_ready(void)
 	current->no_cgroup_migration = 0;
 }
 
+static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
+{
+	return &cgrp->kn->id;
+}
+
+void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
+					char *buf, size_t buflen);
 #else /* !CONFIG_CGROUPS */
 
 struct cgroup_subsys_state;
@@ -666,12 +673,19 @@ static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
 static inline void cgroup_init_kthreadd(void) {}
 static inline void cgroup_kthread_ready(void) {}
+static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
+{
+	return NULL;
+}
 
 static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 					       struct cgroup *ancestor)
 {
 	return true;
 }
+
+static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
+	char *buf, size_t buflen) {}
 #endif /* !CONFIG_CGROUPS */
 
 /*
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 002611c85318..2d0259327721 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -51,7 +51,7 @@
 #endif
 
 extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.4.7"
+#define REL_VERSION "8.4.10"
 #define API_VERSION 1
 #define PRO_VERSION_MIN 86
 #define PRO_VERSION_MAX 101
diff --git a/include/linux/drbd_genl.h b/include/linux/drbd_genl.h
index 2896f93808ae..4e6d4d4c7056 100644
--- a/include/linux/drbd_genl.h
+++ b/include/linux/drbd_genl.h
@@ -132,7 +132,8 @@ GENL_struct(DRBD_NLA_DISK_CONF, 3, disk_conf,
 	__flg_field_def(18, DRBD_GENLA_F_MANDATORY,	disk_drain, DRBD_DISK_DRAIN_DEF)
 	__flg_field_def(19, DRBD_GENLA_F_MANDATORY,	md_flushes, DRBD_MD_FLUSHES_DEF)
 	__flg_field_def(23,     0 /* OPTIONAL */,	al_updates, DRBD_AL_UPDATES_DEF)
-	__flg_field_def(24,     0 /* OPTIONAL */,	discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED)
+	__flg_field_def(24,     0 /* OPTIONAL */,	discard_zeroes_if_aligned, DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF)
+	__flg_field_def(26,     0 /* OPTIONAL */,	disable_write_same, DRBD_DISABLE_WRITE_SAME_DEF)
 )
 
 GENL_struct(DRBD_NLA_RESOURCE_OPTS, 4, res_opts,
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index ddac68422a96..24ae1b9b76c7 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -209,12 +209,18 @@
 #define DRBD_MD_FLUSHES_DEF	1
 #define DRBD_TCP_CORK_DEF	1
 #define DRBD_AL_UPDATES_DEF     1
+
 /* We used to ignore the discard_zeroes_data setting.
  * To not change established (and expected) behaviour,
  * by default assume that, for discard_zeroes_data=0,
  * we can make that an effective discard_zeroes_data=1,
  * if we only explicitly zero-out unaligned partial chunks. */
-#define DRBD_DISCARD_ZEROES_IF_ALIGNED 1
+#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1
+
+/* Some backends pretend to support WRITE SAME,
+ * but fail such requests when they are actually submitted.
+ * This is to tell DRBD to not even try. */
+#define DRBD_DISABLE_WRITE_SAME_DEF 0
 
 #define DRBD_ALLOW_TWO_PRIMARIES_DEF	0
 #define DRBD_ALWAYS_ASBP_DEF	0
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c57002ae6520..7d6079dceb39 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -429,6 +429,7 @@ struct block_device {
 #endif
 	struct block_device *	bd_contains;
 	unsigned		bd_block_size;
+	u8			bd_partno;
 	struct hd_struct *	bd_part;
 	/* number of times partitions within this device have been opened. */
 	unsigned		bd_part_count;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index e619fae2f037..ea652bfcd675 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -362,24 +362,12 @@ static inline void free_part_stats(struct hd_struct *part)
 #define part_stat_sub(cpu, gendiskp, field, subnd)			\
 	part_stat_add(cpu, gendiskp, field, -subnd)
 
-static inline void part_inc_in_flight(struct hd_struct *part, int rw)
-{
-	atomic_inc(&part->in_flight[rw]);
-	if (part->partno)
-		atomic_inc(&part_to_disk(part)->part0.in_flight[rw]);
-}
-
-static inline void part_dec_in_flight(struct hd_struct *part, int rw)
-{
-	atomic_dec(&part->in_flight[rw]);
-	if (part->partno)
-		atomic_dec(&part_to_disk(part)->part0.in_flight[rw]);
-}
-
-static inline int part_in_flight(struct hd_struct *part)
-{
-	return atomic_read(&part->in_flight[0]) + atomic_read(&part->in_flight[1]);
-}
+void part_in_flight(struct request_queue *q, struct hd_struct *part,
+			unsigned int inflight[2]);
+void part_dec_in_flight(struct request_queue *q, struct hd_struct *part,
+			int rw);
+void part_inc_in_flight(struct request_queue *q, struct hd_struct *part,
+			int rw);
 
 static inline struct partition_meta_info *alloc_part_info(struct gendisk *disk)
 {
@@ -395,7 +383,7 @@ static inline void free_part_info(struct hd_struct *part)
 }
 
 /* block/blk-core.c */
-extern void part_round_stats(int cpu, struct hd_struct *part);
+extern void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part);
 
 /* block/genhd.c */
 extern void device_add_disk(struct device *parent, struct gendisk *disk);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index a9b11b8d06f2..ab25c8b6d9e3 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -69,6 +69,12 @@ enum kernfs_root_flag {
 	 * following flag enables that behavior.
 	 */
 	KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK	= 0x0002,
+
+	/*
+	 * The filesystem supports exportfs operation, so userspace can use
+	 * fhandle to access nodes of the fs.
+	 */
+	KERNFS_ROOT_SUPPORT_EXPORTOP		= 0x0004,
 };
 
 /* type-specific structures for kernfs_node union members */
@@ -95,6 +101,21 @@ struct kernfs_elem_attr {
 	struct kernfs_node	*notify_next;	/* for kernfs_notify() */
 };
 
+/* represent a kernfs node */
+union kernfs_node_id {
+	struct {
+		/*
+		 * blktrace will export this struct as a simplified 'struct
+		 * fid' (which is a big data struction), so userspace can use
+		 * it to find kernfs node. The layout must match the first two
+		 * fields of 'struct fid' exactly.
+		 */
+		u32		ino;
+		u32		generation;
+	};
+	u64			id;
+};
+
 /*
  * kernfs_node - the building block of kernfs hierarchy.  Each and every
  * kernfs node is represented by single kernfs_node.  Most fields are
@@ -131,9 +152,9 @@ struct kernfs_node {
 
 	void			*priv;
 
+	union kernfs_node_id	id;
 	unsigned short		flags;
 	umode_t			mode;
-	unsigned int		ino;
 	struct kernfs_iattrs	*iattr;
 };
 
@@ -163,7 +184,8 @@ struct kernfs_root {
 	unsigned int		flags;	/* KERNFS_ROOT_* flags */
 
 	/* private fields, do not use outside kernfs proper */
-	struct ida		ino_ida;
+	struct idr		ino_idr;
+	u32			next_generation;
 	struct kernfs_syscall_ops *syscall_ops;
 
 	/* list of kernfs_super_info of this root, protected by kernfs_mutex */
@@ -336,6 +358,8 @@ struct super_block *kernfs_pin_sb(struct kernfs_root *root, const void *ns);
 
 void kernfs_init(void);
 
+struct kernfs_node *kernfs_get_node_by_id(struct kernfs_root *root,
+	const union kernfs_node_id *id);
 #else	/* CONFIG_KERNFS */
 
 static inline enum kernfs_node_type kernfs_type(struct kernfs_node *kn)
diff --git a/include/trace/events/bcache.h b/include/trace/events/bcache.h
index df3e9ae5ad8d..daf749138ff8 100644
--- a/include/trace/events/bcache.h
+++ b/include/trace/events/bcache.h
@@ -21,7 +21,7 @@ DECLARE_EVENT_CLASS(bcache_request,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->orig_major	= d->disk->major;
 		__entry->orig_minor	= d->disk->first_minor;
 		__entry->sector		= bio->bi_iter.bi_sector;
@@ -98,7 +98,7 @@ DECLARE_EVENT_CLASS(bcache_bio,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
@@ -133,7 +133,7 @@ TRACE_EVENT(bcache_read,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio->bi_iter.bi_size >> 9;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index d0dbe60d8a6d..f815aaaef755 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -236,8 +236,7 @@ TRACE_EVENT(block_bio_bounce,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev ?
-					  bio->bi_bdev->bd_dev : 0;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
@@ -274,7 +273,7 @@ TRACE_EVENT(block_bio_complete,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->error		= error;
@@ -302,7 +301,7 @@ DECLARE_EVENT_CLASS(block_bio_merge,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
@@ -369,7 +368,7 @@ TRACE_EVENT(block_bio_queue,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
@@ -397,7 +396,8 @@ DECLARE_EVENT_CLASS(block_get_rq,
         ),
 
 	TP_fast_assign(
-		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->dev		= bio ? bio_dev(bio) : 0;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio ? bio->bi_iter.bi_sector : 0;
 		__entry->nr_sector	= bio ? bio_sectors(bio) : 0;
 		blk_fill_rwbs(__entry->rwbs,
@@ -532,7 +532,7 @@ TRACE_EVENT(block_split,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->new_sector	= new_sector;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_opf, bio->bi_iter.bi_size);
@@ -573,7 +573,7 @@ TRACE_EVENT(block_bio_remap,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio_dev(bio);
 		__entry->sector		= bio->bi_iter.bi_sector;
 		__entry->nr_sector	= bio_sectors(bio);
 		__entry->old_dev	= dev;
diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
index 6f77a2755abb..bc4dd7837e4c 100644
--- a/include/trace/events/f2fs.h
+++ b/include/trace/events/f2fs.h
@@ -829,7 +829,7 @@ DECLARE_EVENT_CLASS(f2fs__bio,
 
 	TP_fast_assign(
 		__entry->dev		= sb->s_dev;
-		__entry->target		= bio->bi_bdev->bd_dev;
+		__entry->target		= bio_dev(bio);
 		__entry->op		= bio_op(bio);
 		__entry->op_flags	= bio->bi_opf;
 		__entry->type		= type;
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 7bd8783a590f..9b57f014d79d 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -136,7 +136,7 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode,
 
 static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return wb->memcg_css->cgroup->kn->ino;
+	return wb->memcg_css->cgroup->kn->id.ino;
 }
 
 static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h
index c590ca6bfbd9..9cdaedeadb84 100644
--- a/include/uapi/linux/blktrace_api.h
+++ b/include/uapi/linux/blktrace_api.h
@@ -52,6 +52,7 @@ enum blktrace_act {
 	__BLK_TA_REMAP,			/* bio was remapped */
 	__BLK_TA_ABORT,			/* request aborted */
 	__BLK_TA_DRV_DATA,		/* driver-specific binary data */
+	__BLK_TA_CGROUP = 1 << 8,	/* from a cgroup*/
 };
 
 /*
@@ -61,6 +62,7 @@ enum blktrace_notify {
 	__BLK_TN_PROCESS = 0,		/* establish pid/name mapping */
 	__BLK_TN_TIMESTAMP,		/* include system clock */
 	__BLK_TN_MESSAGE,		/* Character string message */
+	__BLK_TN_CGROUP = __BLK_TA_CGROUP, /* from a cgroup */
 };
 
 
@@ -107,6 +109,7 @@ struct blk_io_trace {
 	__u32 cpu;		/* on what cpu did it happen */
 	__u16 error;		/* completion error */
 	__u16 pdu_len;		/* length of data after this trace */
+	/* cgroup id will be stored here if exists */
 };
 
 /*