#!/usr/bin/bpftrace
/*
 * log rbd opens and releases
 *
 * run like:
 *
 * bpftrace -I /lib/modules/$(uname -r)/source/drivers/block -I /lib/modules/$(uname -r)/build this_script
 *
 * This assumes you have the appropriate linux source and build
 * artifacts available on the machine where you're running bpftrace.
 *
 * Note:
 *   https://github.com/iovisor/bpftrace/pull/2315
 *   BTF for kernel modules
 *
 * Once that lands in your local bpftrace you hopefully don't need the linux
 * source and build stuff, nor the 'extracted' stuff below, and you should be
 * able to simply run this script like:
 *
 * chmod +x ./this_script
 * ./this_script
 *   
 */

////////////////////////////////////////////////////////////
// extracted from
//   linux/drivers/block/rbd.c
//
#include <linux/ceph/osdmap.h>

#include <linux/kernel.h>
#include <linux/device.h>
#include <linux/blk-mq.h>

#include "rbd_types.h"

/*
 * An RBD device name will be "rbd#", where the "rbd" comes from
 * RBD_DRV_NAME above, and # is a unique integer identifier.
 */
#define DEV_NAME_LEN		32

/*
 * block device image metadata (in-memory version)
 */
struct rbd_image_header {
	/* These six fields never change for a given rbd image */
	char *object_prefix;
	__u8 obj_order;
	u64 stripe_unit;
	u64 stripe_count;
	s64 data_pool_id;
	u64 features;		/* Might be changeable someday? */

	/* The remaining fields need to be updated occasionally */
	u64 image_size;
	struct ceph_snap_context *snapc;
	char *snap_names;	/* format 1 only */
	u64 *snap_sizes;	/* format 1 only */
};

enum rbd_watch_state {
	RBD_WATCH_STATE_UNREGISTERED,
	RBD_WATCH_STATE_REGISTERED,
	RBD_WATCH_STATE_ERROR,
};

enum rbd_lock_state {
	RBD_LOCK_STATE_UNLOCKED,
	RBD_LOCK_STATE_LOCKED,
	RBD_LOCK_STATE_RELEASING,
};

/* WatchNotify::ClientId */
struct rbd_client_id {
	u64 gid;
	u64 handle;
};

struct rbd_mapping {
	u64                     size;
};

/*
 * a single device
 */
struct rbd_device {
	int			dev_id;		/* blkdev unique id */

	int			major;		/* blkdev assigned major */
	int			minor;
	struct gendisk		*disk;		/* blkdev's gendisk and rq */

	u32			image_format;	/* Either 1 or 2 */
	struct rbd_client	*rbd_client;

	char			name[DEV_NAME_LEN]; /* blkdev name, e.g. rbd3 */

	spinlock_t		lock;		/* queue, flags, open_count */

	struct rbd_image_header	header;
	unsigned long		flags;		/* possibly lock protected */
	struct rbd_spec		*spec;
	struct rbd_options	*opts;
	char			*config_info;	/* add{,_single_major} string */

	struct ceph_object_id	header_oid;
	struct ceph_object_locator header_oloc;

	struct ceph_file_layout	layout;		/* used for all rbd requests */

	struct mutex		watch_mutex;
	enum rbd_watch_state	watch_state;
	struct ceph_osd_linger_request *watch_handle;
	u64			watch_cookie;
	struct delayed_work	watch_dwork;

	struct rw_semaphore	lock_rwsem;
	enum rbd_lock_state	lock_state;
	char			lock_cookie[32];
	struct rbd_client_id	owner_cid;
	struct work_struct	acquired_lock_work;
	struct work_struct	released_lock_work;
	struct delayed_work	lock_dwork;
	struct work_struct	unlock_work;
	spinlock_t		lock_lists_lock;
	struct list_head	acquiring_list;
	struct list_head	running_list;
	struct completion	acquire_wait;
	int			acquire_err;
	struct completion	releasing_wait;

	spinlock_t		object_map_lock;
	u8			*object_map;
	u64			object_map_size;	/* in objects */
	u64			object_map_flags;

	struct workqueue_struct	*task_wq;

	struct rbd_spec		*parent_spec;
	u64			parent_overlap;
	atomic_t		parent_ref;
	struct rbd_device	*parent;

	/* Block layer tags. */
	struct blk_mq_tag_set	tag_set;

	/* protects updating the header */
	struct rw_semaphore     header_rwsem;

	struct rbd_mapping	mapping;

	struct list_head	node;

	/* sysfs related */
	struct device		dev;
	unsigned long		open_count;	/* protected by lock */
};

//
// end of extraction
////////////////////////////////////////////////////////////

kprobe:rbd_open {
  $bdev = (struct block_device *)arg0;
  $rbd_dev = (struct rbd_device *)($bdev->bd_disk->private_data);

  printf("%s O %d %s %lu %s\n",
    strftime("%T.%f", nsecs), pid, $rbd_dev->name, $rbd_dev->open_count, comm
  );
}

kprobe:rbd_release {
  $disk = (struct gendisk *)arg0;
  $rbd_dev = (struct rbd_device *)($disk->private_data);

  printf("%s R %d %s %lu %s\n",
    strftime("%T.%f", nsecs), pid, $rbd_dev->name, $rbd_dev->open_count, comm
  );
}