Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 743 insertions, 0 deletions

diff --git a/include/trace/events/block.h b/include/trace/events/block.h
new file mode 100644
index 000000000..9c97a1685
--- /dev/null
+++ b/include/trace/events/block.h
@@ -0,0 +1,743 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
+#if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLOCK_H
+
+#include <linux/blktrace_api.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/tracepoint.h>
+#include <uapi/linux/ioprio.h>
+
+#define RWBS_LEN	10
+
+#define IOPRIO_CLASS_STRINGS \
+	{ IOPRIO_CLASS_NONE,	"none" }, \
+	{ IOPRIO_CLASS_RT,	"rt" }, \
+	{ IOPRIO_CLASS_BE,	"be" }, \
+	{ IOPRIO_CLASS_IDLE,	"idle" }, \
+	{ IOPRIO_CLASS_INVALID,	"invalid"}
+
+#ifdef CONFIG_BUFFER_HEAD
+DECLARE_EVENT_CLASS(block_buffer,
+
+	TP_PROTO(struct buffer_head *bh),
+
+	TP_ARGS(bh),
+
+	TP_STRUCT__entry (
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  size_t,	size			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bh->b_bdev->bd_dev;
+		__entry->sector		= bh->b_blocknr;
+		__entry->size		= bh->b_size;
+	),
+
+	TP_printk("%d,%d sector=%llu size=%zu",
+		MAJOR(__entry->dev), MINOR(__entry->dev),
+		(unsigned long long)__entry->sector, __entry->size
+	)
+);
+
+/**
+ * block_touch_buffer - mark a buffer accessed
+ * @bh: buffer_head being touched
+ *
+ * Called from touch_buffer().
+ */
+DEFINE_EVENT(block_buffer, block_touch_buffer,
+
+	TP_PROTO(struct buffer_head *bh),
+
+	TP_ARGS(bh)
+);
+
+/**
+ * block_dirty_buffer - mark a buffer dirty
+ * @bh: buffer_head being dirtied
+ *
+ * Called from mark_buffer_dirty().
+ */
+DEFINE_EVENT(block_buffer, block_dirty_buffer,
+
+	TP_PROTO(struct buffer_head *bh),
+
+	TP_ARGS(bh)
+);
+#endif /* CONFIG_BUFFER_HEAD */
+
+/**
+ * block_rq_requeue - place block IO request back on a queue
+ * @rq: block IO operation request
+ *
+ * The block operation request @rq is being placed back into queue
+ * @q.  For some reason the request was not completed and needs to be
+ * put back in the queue.
+ */
+TRACE_EVENT(block_rq_requeue,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned short, ioprio		)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	1		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
+		__entry->sector    = blk_rq_trace_sector(rq);
+		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
+		__entry->ioprio    = req_get_ioprio(rq);
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
+		__get_str(cmd)[0] = '\0';
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u %s,%u,%u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector, __entry->nr_sector,
+		  __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio),
+				   IOPRIO_CLASS_STRINGS),
+		  IOPRIO_PRIO_HINT(__entry->ioprio),
+		  IOPRIO_PRIO_LEVEL(__entry->ioprio),  0)
+);
+
+DECLARE_EVENT_CLASS(block_rq_completion,
+
+	TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+	TP_ARGS(rq, error, nr_bytes),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int	,	error			)
+		__field(  unsigned short, ioprio		)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__dynamic_array( char,	cmd,	1		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
+		__entry->sector    = blk_rq_pos(rq);
+		__entry->nr_sector = nr_bytes >> 9;
+		__entry->error     = blk_status_to_errno(error);
+		__entry->ioprio    = req_get_ioprio(rq);
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
+		__get_str(cmd)[0] = '\0';
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u %s,%u,%u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector, __entry->nr_sector,
+		  __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio),
+				   IOPRIO_CLASS_STRINGS),
+		  IOPRIO_PRIO_HINT(__entry->ioprio),
+		  IOPRIO_PRIO_LEVEL(__entry->ioprio), __entry->error)
+);
+
+/**
+ * block_rq_complete - block IO operation completed by device driver
+ * @rq: block operations request
+ * @error: status code
+ * @nr_bytes: number of completed bytes
+ *
+ * The block_rq_complete tracepoint event indicates that some portion
+ * of operation request has been completed by the device driver.  If
+ * the @rq->bio is %NULL, then there is absolutely no additional work to
+ * do for the request. If @rq->bio is non-NULL then there is
+ * additional work required to complete the request.
+ */
+DEFINE_EVENT(block_rq_completion, block_rq_complete,
+
+	TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+	TP_ARGS(rq, error, nr_bytes)
+);
+
+/**
+ * block_rq_error - block IO operation error reported by device driver
+ * @rq: block operations request
+ * @error: status code
+ * @nr_bytes: number of completed bytes
+ *
+ * The block_rq_error tracepoint event indicates that some portion
+ * of operation request has failed as reported by the device driver.
+ */
+DEFINE_EVENT(block_rq_completion, block_rq_error,
+
+	TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
+
+	TP_ARGS(rq, error, nr_bytes)
+);
+
+DECLARE_EVENT_CLASS(block_rq,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__field(  unsigned short, ioprio		)
+		__array(  char,		rwbs,	RWBS_LEN	)
+		__array(  char,         comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	1		)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
+		__entry->sector    = blk_rq_trace_sector(rq);
+		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
+		__entry->bytes     = blk_rq_bytes(rq);
+		__entry->ioprio	   = req_get_ioprio(rq);
+
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
+		__get_str(cmd)[0] = '\0';
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u %s,%u,%u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector, __entry->nr_sector,
+		  __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio),
+				   IOPRIO_CLASS_STRINGS),
+		  IOPRIO_PRIO_HINT(__entry->ioprio),
+		  IOPRIO_PRIO_LEVEL(__entry->ioprio), __entry->comm)
+);
+
+/**
+ * block_rq_tag_wait - triggered when a request is starved of a tag
+ * @q: request queue of the target device
+ * @hctx: hardware context of the request experiencing starvation
+ * @is_sched_tag: indicates whether the starved pool is the software scheduler
+ * @alloc_flags: allocation flags dictating the specific tag pool
+ *
+ * Called immediately before the submitting context is forced to block due
+ * to the exhaustion of available tags (i.e., physical hardware driver
+ * tags, software scheduler tags, or reserved tags). This trace point
+ * indicates that the context will be placed into an uninterruptible state
+ * via sbitmap_prepare_to_wait(). If a tag is not acquired in the final
+ * lockless retry, the context will yield the CPU via io_schedule() until
+ * an active request completes and relinquishes its assigned tag.
+ */
+TRACE_EVENT(block_rq_tag_wait,
+
+	TP_PROTO(struct request_queue *q, struct blk_mq_hw_ctx *hctx,
+		 bool is_sched_tag, unsigned int alloc_flags),
+
+	TP_ARGS(q, hctx, is_sched_tag, alloc_flags),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( u32,		hctx_id			)
+		__field( u32,		nr_tags			)
+		__field( bool,		is_sched_tag		)
+		__field( bool,		is_reserved		)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= q->disk ? disk_devt(q->disk) : 0;
+		__entry->hctx_id	= hctx->queue_num;
+		__entry->is_sched_tag	= is_sched_tag;
+		__entry->is_reserved	= alloc_flags & BLK_MQ_REQ_RESERVED;
+
+		if (__entry->is_reserved) {
+			__entry->nr_tags = is_sched_tag ?
+					   hctx->sched_tags->nr_reserved_tags :
+					   hctx->tags->nr_reserved_tags;
+		} else {
+			if (is_sched_tag)
+				__entry->nr_tags = hctx->sched_tags->nr_tags -
+						   hctx->sched_tags->nr_reserved_tags;
+			else
+				__entry->nr_tags = hctx->tags->nr_tags -
+						   hctx->tags->nr_reserved_tags;
+		}
+
+	),
+
+	TP_printk("%d,%d hctx=%u starved on %s%s tags (depth=%u)",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->hctx_id,
+		  __entry->is_sched_tag ? "scheduler" : "hardware",
+		  __entry->is_reserved ? " reserved" : "",
+		  __entry->nr_tags)
+);
+
+/**
+ * block_rq_insert - insert block operation request into queue
+ * @rq: block IO operation request
+ *
+ * Called immediately before block operation request @rq is inserted
+ * into queue @q.  The fields in the operation request @rq struct can
+ * be examined to determine which device and sectors the pending
+ * operation would access.
+ */
+DEFINE_EVENT(block_rq, block_rq_insert,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
+ * block_rq_issue - issue pending block IO request operation to device driver
+ * @rq: block IO operation request
+ *
+ * Called when block operation request @rq from queue @q is sent to a
+ * device driver for processing.
+ */
+DEFINE_EVENT(block_rq, block_rq_issue,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
+ * block_rq_merge - merge request with another one in the elevator
+ * @rq: block IO operation request
+ *
+ * Called when block operation request @rq from queue @q is merged to another
+ * request queued in the elevator.
+ */
+DEFINE_EVENT(block_rq, block_rq_merge,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
+ * block_io_start - insert a request for execution
+ * @rq: block IO operation request
+ *
+ * Called when block operation request @rq is queued for execution
+ */
+DEFINE_EVENT(block_rq, block_io_start,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
+ * block_io_done - block IO operation request completed
+ * @rq: block IO operation request
+ *
+ * Called when block operation request @rq is completed
+ */
+DEFINE_EVENT(block_rq, block_io_done,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
+ * block_bio_complete - completed all work on the block operation
+ * @q: queue holding the block operation
+ * @bio: block operation completed
+ *
+ * This tracepoint indicates there is no further work to do on this
+ * block IO operation @bio.
+ */
+TRACE_EVENT(block_bio_complete,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned,	nr_sector	)
+		__field( int,		error		)
+		__array( char,		rwbs,	RWBS_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio_dev(bio);
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->nr_sector	= bio_sectors(bio);
+		__entry->error		= blk_status_to_errno(bio->bi_status);
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->error)
+);
+
+DECLARE_EVENT_CLASS(block_bio,
+
+	TP_PROTO(struct bio *bio),
+
+	TP_ARGS(bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	RWBS_LEN	)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__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);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+/**
+ * block_bio_backmerge - merging block operation to the end of an existing operation
+ * @bio: new block operation to merge
+ *
+ * Merging block request @bio to the end of an existing block request.
+ */
+DEFINE_EVENT(block_bio, block_bio_backmerge,
+	TP_PROTO(struct bio *bio),
+	TP_ARGS(bio)
+);
+
+/**
+ * block_bio_frontmerge - merging block operation to the beginning of an existing operation
+ * @bio: new block operation to merge
+ *
+ * Merging block IO operation @bio to the beginning of an existing block request.
+ */
+DEFINE_EVENT(block_bio, block_bio_frontmerge,
+	TP_PROTO(struct bio *bio),
+	TP_ARGS(bio)
+);
+
+/**
+ * block_bio_queue - putting new block IO operation in queue
+ * @bio: new block operation
+ *
+ * About to place the block IO operation @bio into queue @q.
+ */
+DEFINE_EVENT(block_bio, block_bio_queue,
+	TP_PROTO(struct bio *bio),
+	TP_ARGS(bio)
+);
+
+/**
+ * block_getrq - get a free request entry in queue for block IO operations
+ * @bio: pending block IO operation (can be %NULL)
+ *
+ * A request struct has been allocated to handle the block IO operation @bio.
+ */
+DEFINE_EVENT(block_bio, block_getrq,
+	TP_PROTO(struct bio *bio),
+	TP_ARGS(bio)
+);
+
+/**
+ * blk_zone_append_update_request_bio - update bio sector after zone append
+ * @rq: the completed request that sets the bio sector
+ *
+ * Update the bio's bi_sector after a zone append command has been completed.
+ */
+DEFINE_EVENT(block_rq, blk_zone_append_update_request_bio,
+	     TP_PROTO(struct request *rq),
+	     TP_ARGS(rq)
+);
+
+/**
+ * block_plug - keep operations requests in request queue
+ * @q: request queue to plug
+ *
+ * Plug the request queue @q.  Do not allow block operation requests
+ * to be sent to the device driver. Instead, accumulate requests in
+ * the queue to improve throughput performance of the block device.
+ */
+TRACE_EVENT(block_plug,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s]", __entry->comm)
+);
+
+DECLARE_EVENT_CLASS(block_unplug,
+
+	TP_PROTO(struct request_queue *q, unsigned int depth, bool explicit),
+
+	TP_ARGS(q, depth, explicit),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq = depth;
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+/**
+ * block_unplug - release of operations requests in request queue
+ * @q: request queue to unplug
+ * @depth: number of requests just added to the queue
+ * @explicit: whether this was an explicit unplug, or one from schedule()
+ *
+ * Unplug request queue @q because device driver is scheduled to work
+ * on elements in the request queue.
+ */
+DEFINE_EVENT(block_unplug, block_unplug,
+
+	TP_PROTO(struct request_queue *q, unsigned int depth, bool explicit),
+
+	TP_ARGS(q, depth, explicit)
+);
+
+/**
+ * block_split - split a single bio struct into two bio structs
+ * @bio: block operation being split
+ * @new_sector: The starting sector for the new bio
+ *
+ * The bio request @bio needs to be split into two bio requests.  The newly
+ * created @bio request starts at @new_sector. This split may be required due to
+ * hardware limitations such as operation crossing device boundaries in a RAID
+ * system.
+ */
+TRACE_EVENT(block_split,
+
+	TP_PROTO(struct bio *bio, unsigned int new_sector),
+
+	TP_ARGS(bio, new_sector),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev				)
+		__field( sector_t,	sector				)
+		__field( sector_t,	new_sector			)
+		__array( char,		rwbs,		RWBS_LEN	)
+		__array( char,		comm,		TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__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);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu / %llu [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  (unsigned long long)__entry->new_sector,
+		  __entry->comm)
+);
+
+/**
+ * block_bio_remap - map request for a logical device to the raw device
+ * @bio: revised operation
+ * @dev: original device for the operation
+ * @from: original sector for the operation
+ *
+ * An operation for a logical device has been mapped to the
+ * raw block device.
+ */
+TRACE_EVENT(block_bio_remap,
+
+	TP_PROTO(struct bio *bio, dev_t dev, sector_t from),
+
+	TP_ARGS(bio, dev, from),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned int,	nr_sector	)
+		__field( dev_t,		old_dev		)
+		__field( sector_t,	old_sector	)
+		__array( char,		rwbs,	RWBS_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio_dev(bio);
+		__entry->sector		= bio->bi_iter.bi_sector;
+		__entry->nr_sector	= bio_sectors(bio);
+		__entry->old_dev	= dev;
+		__entry->old_sector	= from;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_opf);
+	),
+
+	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector,
+		  MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+		  (unsigned long long)__entry->old_sector)
+);
+
+/**
+ * block_rq_remap - map request for a block operation request
+ * @rq: block IO operation request
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * The block operation request @rq in @q has been remapped.  The block
+ * operation request @rq holds the current information and @from hold
+ * the original sector.
+ */
+TRACE_EVENT(block_rq_remap,
+
+	TP_PROTO(struct request *rq, dev_t dev, sector_t from),
+
+	TP_ARGS(rq, dev, from),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned int,	nr_sector	)
+		__field( dev_t,		old_dev		)
+		__field( sector_t,	old_sector	)
+		__field( unsigned int,	nr_bios		)
+		__array( char,		rwbs,	RWBS_LEN)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= disk_devt(rq->q->disk);
+		__entry->sector		= blk_rq_pos(rq);
+		__entry->nr_sector	= blk_rq_sectors(rq);
+		__entry->old_dev	= dev;
+		__entry->old_sector	= from;
+		__entry->nr_bios	= blk_rq_count_bios(rq);
+		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
+	),
+
+	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector,
+		  MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+		  (unsigned long long)__entry->old_sector, __entry->nr_bios)
+);
+
+/**
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
+ * @bio: The block IO operation sent down to the device
+ * @nr_sectors: The number of sectors affected by this operation
+ *
+ * Execute a zone management operation on a specified range of zones. This
+ * range is encoded in %nr_sectors, which has to be a multiple of the zone
+ * size.
+ */
+TRACE_EVENT(blkdev_zone_mgmt,
+
+	TP_PROTO(struct bio *bio, sector_t nr_sectors),
+
+	TP_ARGS(bio, nr_sectors),
+
+	TP_STRUCT__entry(
+	    __field(  dev_t,	dev		)
+	    __field(  sector_t,	sector		)
+	    __field(  sector_t, nr_sectors	)
+	    __array(  char,	rwbs,	RWBS_LEN)
+	),
+
+	TP_fast_assign(
+	    __entry->dev	= bio_dev(bio);
+	    __entry->sector	= bio->bi_iter.bi_sector;
+	    __entry->nr_sectors	= bio_sectors(bio);
+	    blk_fill_rwbs(__entry->rwbs, bio->bi_opf);
+        ),
+
+	TP_printk("%d,%d %s %llu + %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sectors)
+);
+
+DECLARE_EVENT_CLASS(block_zwplug,
+
+	TP_PROTO(struct request_queue *q, unsigned int zno, sector_t sector,
+		 unsigned int nr_sectors),
+
+	TP_ARGS(q, zno, sector, nr_sectors),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( unsigned int,	zno		)
+		__field( sector_t,	sector		)
+		__field( unsigned int,	nr_sectors	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= disk_devt(q->disk);
+		__entry->zno		= zno;
+		__entry->sector		= sector;
+		__entry->nr_sectors	= nr_sectors;
+	),
+
+	TP_printk("%d,%d zone %u, BIO %llu + %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->zno,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sectors)
+);
+
+DEFINE_EVENT(block_zwplug, disk_zone_wplug_add_bio,
+
+	TP_PROTO(struct request_queue *q, unsigned int zno, sector_t sector,
+		 unsigned int nr_sectors),
+
+	TP_ARGS(q, zno, sector, nr_sectors)
+);
+
+DEFINE_EVENT(block_zwplug, blk_zone_wplug_bio,
+
+	TP_PROTO(struct request_queue *q, unsigned int zno, sector_t sector,
+		 unsigned int nr_sectors),
+
+	TP_ARGS(q, zno, sector, nr_sectors)
+);
+
+#endif /* _TRACE_BLOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+