/*
- * Copyright (C) 2006 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/debugfs.h>
+#include <linux/time.h>
+#include <trace/block.h>
#include <asm/uaccess.h>
-static DEFINE_PER_CPU(unsigned long long, blk_trace_cpu_offset) = { 0, };
static unsigned int blktrace_seq __read_mostly = 1;
+/* Global reference count of probes */
+static DEFINE_MUTEX(blk_probe_mutex);
+static atomic_t blk_probes_ref = ATOMIC_INIT(0);
+
+static int blk_register_tracepoints(void);
+static void blk_unregister_tracepoints(void);
+
/*
- * Send out a notify for this process, if we haven't done so since a trace
- * started
+ * Send out a notify message.
*/
-static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+static void trace_note(struct blk_trace *bt, pid_t pid, int action,
+ const void *data, size_t len)
{
struct blk_io_trace *t;
- t = relay_reserve(bt->rchan, sizeof(*t) + sizeof(tsk->comm));
+ t = relay_reserve(bt->rchan, sizeof(*t) + len);
if (t) {
+ const int cpu = smp_processor_id();
+
t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+ t->time = ktime_to_ns(ktime_get());
t->device = bt->dev;
- t->action = BLK_TC_ACT(BLK_TC_NOTIFY);
- t->pid = tsk->pid;
- t->cpu = smp_processor_id();
- t->pdu_len = sizeof(tsk->comm);
- memcpy((void *) t + sizeof(*t), tsk->comm, t->pdu_len);
- tsk->btrace_seq = blktrace_seq;
+ t->action = action;
+ t->pid = pid;
+ t->cpu = cpu;
+ t->pdu_len = len;
+ memcpy((void *) t + sizeof(*t), data, len);
}
}
+/*
+ * Send out a notify for this process, if we haven't done so since a trace
+ * started
+ */
+static void trace_note_tsk(struct blk_trace *bt, struct task_struct *tsk)
+{
+ tsk->btrace_seq = blktrace_seq;
+ trace_note(bt, tsk->pid, BLK_TN_PROCESS, tsk->comm, sizeof(tsk->comm));
+}
+
+static void trace_note_time(struct blk_trace *bt)
+{
+ struct timespec now;
+ unsigned long flags;
+ u32 words[2];
+
+ getnstimeofday(&now);
+ words[0] = now.tv_sec;
+ words[1] = now.tv_nsec;
+
+ local_irq_save(flags);
+ trace_note(bt, 0, BLK_TN_TIMESTAMP, words, sizeof(words));
+ local_irq_restore(flags);
+}
+
+void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
+{
+ int n;
+ va_list args;
+ unsigned long flags;
+ char *buf;
+
+ local_irq_save(flags);
+ buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
+ va_start(args, fmt);
+ n = vscnprintf(buf, BLK_TN_MAX_MSG, fmt, args);
+ va_end(args);
+
+ trace_note(bt, 0, BLK_TN_MESSAGE, buf, n);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(__trace_note_message);
+
static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
pid_t pid)
{
*/
static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK_TC_WRITE) };
-/*
- * Bio action bits of interest
- */
-static u32 bio_act[5] __read_mostly = { 0, BLK_TC_ACT(BLK_TC_BARRIER), BLK_TC_ACT(BLK_TC_SYNC), 0, BLK_TC_ACT(BLK_TC_AHEAD) };
-
-/*
- * More could be added as needed, taking care to increment the decrementer
- * to get correct indexing
- */
-#define trace_barrier_bit(rw) \
- (((rw) & (1 << BIO_RW_BARRIER)) >> (BIO_RW_BARRIER - 0))
-#define trace_sync_bit(rw) \
- (((rw) & (1 << BIO_RW_SYNC)) >> (BIO_RW_SYNC - 1))
-#define trace_ahead_bit(rw) \
- (((rw) & (1 << BIO_RW_AHEAD)) << (BIO_RW_AHEAD - 0))
+/* The ilog2() calls fall out because they're constant */
+#define MASK_TC_BIT(rw, __name) ( (rw & (1 << BIO_RW_ ## __name)) << \
+ (ilog2(BLK_TC_ ## __name) + BLK_TC_SHIFT - BIO_RW_ ## __name) )
/*
* The worker for the various blk_add_trace*() types. Fills out a
* blk_io_trace structure and places it in a per-cpu subbuffer.
*/
-void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
+static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
int rw, u32 what, int error, int pdu_len, void *pdu_data)
{
struct task_struct *tsk = current;
return;
what |= ddir_act[rw & WRITE];
- what |= bio_act[trace_barrier_bit(rw)];
- what |= bio_act[trace_sync_bit(rw)];
- what |= bio_act[trace_ahead_bit(rw)];
+ what |= MASK_TC_BIT(rw, BARRIER);
+ what |= MASK_TC_BIT(rw, SYNCIO);
+ what |= MASK_TC_BIT(rw, AHEAD);
+ what |= MASK_TC_BIT(rw, META);
+ what |= MASK_TC_BIT(rw, DISCARD);
pid = tsk->pid;
if (unlikely(act_log_check(bt, what, sector, pid)))
/*
* A word about the locking here - we disable interrupts to reserve
* some space in the relay per-cpu buffer, to prevent an irq
- * from coming in and stepping on our toes. Once reserved, it's
- * enough to get preemption disabled to prevent read of this data
- * before we are through filling it. get_cpu()/put_cpu() does this
- * for us
+ * from coming in and stepping on our toes.
*/
local_irq_save(flags);
t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
t->sequence = ++(*sequence);
- t->time = sched_clock() - per_cpu(blk_trace_cpu_offset, cpu);
+ t->time = ktime_to_ns(ktime_get());
t->sector = sector;
t->bytes = bytes;
t->action = what;
local_irq_restore(flags);
}
-EXPORT_SYMBOL_GPL(__blk_add_trace);
-
static struct dentry *blk_tree_root;
-static struct mutex blk_tree_mutex;
-static unsigned int root_users;
-
-static inline void blk_remove_root(void)
-{
- if (blk_tree_root) {
- debugfs_remove(blk_tree_root);
- blk_tree_root = NULL;
- }
-}
-
-static void blk_remove_tree(struct dentry *dir)
-{
- mutex_lock(&blk_tree_mutex);
- debugfs_remove(dir);
- if (--root_users == 0)
- blk_remove_root();
- mutex_unlock(&blk_tree_mutex);
-}
-
-static struct dentry *blk_create_tree(const char *blk_name)
-{
- struct dentry *dir = NULL;
-
- mutex_lock(&blk_tree_mutex);
-
- if (!blk_tree_root) {
- blk_tree_root = debugfs_create_dir("block", NULL);
- if (!blk_tree_root)
- goto err;
- }
-
- dir = debugfs_create_dir(blk_name, blk_tree_root);
- if (dir)
- root_users++;
- else
- blk_remove_root();
-
-err:
- mutex_unlock(&blk_tree_mutex);
- return dir;
-}
+static DEFINE_MUTEX(blk_tree_mutex);
static void blk_trace_cleanup(struct blk_trace *bt)
{
- relay_close(bt->rchan);
+ debugfs_remove(bt->msg_file);
debugfs_remove(bt->dropped_file);
- blk_remove_tree(bt->dir);
+ relay_close(bt->rchan);
free_percpu(bt->sequence);
+ free_percpu(bt->msg_data);
kfree(bt);
+ mutex_lock(&blk_probe_mutex);
+ if (atomic_dec_and_test(&blk_probes_ref))
+ blk_unregister_tracepoints();
+ mutex_unlock(&blk_probe_mutex);
}
-static int blk_trace_remove(request_queue_t *q)
+int blk_trace_remove(struct request_queue *q)
{
struct blk_trace *bt;
return 0;
}
+EXPORT_SYMBOL_GPL(blk_trace_remove);
static int blk_dropped_open(struct inode *inode, struct file *filp)
{
- filp->private_data = inode->u.generic_ip;
+ filp->private_data = inode->i_private;
return 0;
}
return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
}
-static struct file_operations blk_dropped_fops = {
+static const struct file_operations blk_dropped_fops = {
.owner = THIS_MODULE,
.open = blk_dropped_open,
.read = blk_dropped_read,
};
+static int blk_msg_open(struct inode *inode, struct file *filp)
+{
+ filp->private_data = inode->i_private;
+
+ return 0;
+}
+
+static ssize_t blk_msg_write(struct file *filp, const char __user *buffer,
+ size_t count, loff_t *ppos)
+{
+ char *msg;
+ struct blk_trace *bt;
+
+ if (count > BLK_TN_MAX_MSG)
+ return -EINVAL;
+
+ msg = kmalloc(count, GFP_KERNEL);
+ if (msg == NULL)
+ return -ENOMEM;
+
+ if (copy_from_user(msg, buffer, count)) {
+ kfree(msg);
+ return -EFAULT;
+ }
+
+ bt = filp->private_data;
+ __trace_note_message(bt, "%s", msg);
+ kfree(msg);
+
+ return count;
+}
+
+static const struct file_operations blk_msg_fops = {
+ .owner = THIS_MODULE,
+ .open = blk_msg_open,
+ .write = blk_msg_write,
+};
+
/*
* Keep track of how many times we encountered a full subbuffer, to aid
* the user space app in telling how many lost events there were.
static int blk_remove_buf_file_callback(struct dentry *dentry)
{
+ struct dentry *parent = dentry->d_parent;
debugfs_remove(dentry);
+
+ /*
+ * this will fail for all but the last file, but that is ok. what we
+ * care about is the top level buts->name directory going away, when
+ * the last trace file is gone. Then we don't have to rmdir() that
+ * manually on trace stop, so it nicely solves the issue with
+ * force killing of running traces.
+ */
+
+ debugfs_remove(parent);
return 0;
}
/*
* Setup everything required to start tracing
*/
-static int blk_trace_setup(request_queue_t *q, struct block_device *bdev,
- char __user *arg)
+int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ struct blk_user_trace_setup *buts)
{
- struct blk_user_trace_setup buts;
struct blk_trace *old_bt, *bt = NULL;
struct dentry *dir = NULL;
- char b[BDEVNAME_SIZE];
int ret, i;
- if (copy_from_user(&buts, arg, sizeof(buts)))
- return -EFAULT;
-
- if (!buts.buf_size || !buts.buf_nr)
+ if (!buts->buf_size || !buts->buf_nr)
return -EINVAL;
- strcpy(buts.name, bdevname(bdev, b));
+ strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
+ buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
/*
* some device names have larger paths - convert the slashes
* to underscores for this to work as expected
*/
- for (i = 0; i < strlen(buts.name); i++)
- if (buts.name[i] == '/')
- buts.name[i] = '_';
-
- if (copy_to_user(arg, &buts, sizeof(buts)))
- return -EFAULT;
+ for (i = 0; i < strlen(buts->name); i++)
+ if (buts->name[i] == '/')
+ buts->name[i] = '_';
ret = -ENOMEM;
bt = kzalloc(sizeof(*bt), GFP_KERNEL);
if (!bt->sequence)
goto err;
+ bt->msg_data = __alloc_percpu(BLK_TN_MAX_MSG);
+ if (!bt->msg_data)
+ goto err;
+
ret = -ENOENT;
- dir = blk_create_tree(buts.name);
+
+ if (!blk_tree_root) {
+ blk_tree_root = debugfs_create_dir("block", NULL);
+ if (!blk_tree_root)
+ return -ENOMEM;
+ }
+
+ dir = debugfs_create_dir(buts->name, blk_tree_root);
+
if (!dir)
goto err;
bt->dir = dir;
- bt->dev = bdev->bd_dev;
+ bt->dev = dev;
atomic_set(&bt->dropped, 0);
ret = -EIO;
if (!bt->dropped_file)
goto err;
- bt->rchan = relay_open("trace", dir, buts.buf_size, buts.buf_nr, &blk_relay_callbacks);
+ bt->msg_file = debugfs_create_file("msg", 0222, dir, bt, &blk_msg_fops);
+ if (!bt->msg_file)
+ goto err;
+
+ bt->rchan = relay_open("trace", dir, buts->buf_size,
+ buts->buf_nr, &blk_relay_callbacks, bt);
if (!bt->rchan)
goto err;
- bt->rchan->private_data = bt;
- bt->act_mask = buts.act_mask;
+ bt->act_mask = buts->act_mask;
if (!bt->act_mask)
bt->act_mask = (u16) -1;
- bt->start_lba = buts.start_lba;
- bt->end_lba = buts.end_lba;
+ bt->start_lba = buts->start_lba;
+ bt->end_lba = buts->end_lba;
if (!bt->end_lba)
bt->end_lba = -1ULL;
- bt->pid = buts.pid;
+ bt->pid = buts->pid;
bt->trace_state = Blktrace_setup;
+ mutex_lock(&blk_probe_mutex);
+ if (atomic_add_return(1, &blk_probes_ref) == 1) {
+ ret = blk_register_tracepoints();
+ if (ret)
+ goto probe_err;
+ }
+ mutex_unlock(&blk_probe_mutex);
+
ret = -EBUSY;
old_bt = xchg(&q->blk_trace, bt);
if (old_bt) {
}
return 0;
+probe_err:
+ atomic_dec(&blk_probes_ref);
+ mutex_unlock(&blk_probe_mutex);
err:
- if (dir)
- blk_remove_tree(dir);
if (bt) {
+ if (bt->msg_file)
+ debugfs_remove(bt->msg_file);
if (bt->dropped_file)
debugfs_remove(bt->dropped_file);
- if (bt->sequence)
- free_percpu(bt->sequence);
+ free_percpu(bt->sequence);
+ free_percpu(bt->msg_data);
if (bt->rchan)
relay_close(bt->rchan);
kfree(bt);
return ret;
}
-static int blk_trace_startstop(request_queue_t *q, int start)
+int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+ char __user *arg)
+{
+ struct blk_user_trace_setup buts;
+ int ret;
+
+ ret = copy_from_user(&buts, arg, sizeof(buts));
+ if (ret)
+ return -EFAULT;
+
+ ret = do_blk_trace_setup(q, name, dev, &buts);
+ if (ret)
+ return ret;
+
+ if (copy_to_user(arg, &buts, sizeof(buts)))
+ return -EFAULT;
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(blk_trace_setup);
+
+int blk_trace_startstop(struct request_queue *q, int start)
{
struct blk_trace *bt;
int ret;
blktrace_seq++;
smp_mb();
bt->trace_state = Blktrace_running;
+
+ trace_note_time(bt);
ret = 0;
}
} else {
return ret;
}
+EXPORT_SYMBOL_GPL(blk_trace_startstop);
/**
* blk_trace_ioctl: - handle the ioctls associated with tracing
**/
int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
{
- request_queue_t *q;
+ struct request_queue *q;
int ret, start = 0;
+ char b[BDEVNAME_SIZE];
q = bdev_get_queue(bdev);
if (!q)
switch (cmd) {
case BLKTRACESETUP:
- ret = blk_trace_setup(q, bdev, arg);
+ bdevname(bdev, b);
+ ret = blk_trace_setup(q, b, bdev->bd_dev, arg);
break;
case BLKTRACESTART:
start = 1;
* @q: the request queue associated with the device
*
**/
-void blk_trace_shutdown(request_queue_t *q)
+void blk_trace_shutdown(struct request_queue *q)
{
- blk_trace_startstop(q, 0);
- blk_trace_remove(q);
+ if (q->blk_trace) {
+ blk_trace_startstop(q, 0);
+ blk_trace_remove(q);
+ }
}
/*
- * Average offset over two calls to sched_clock() with a gettimeofday()
- * in the middle
+ * blktrace probes
*/
-static void blk_check_time(unsigned long long *t)
+
+/**
+ * blk_add_trace_rq - Add a trace for a request oriented action
+ * @q: queue the io is for
+ * @rq: the source request
+ * @what: the action
+ *
+ * Description:
+ * Records an action against a request. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_rq(struct request_queue *q, struct request *rq,
+ u32 what)
{
- unsigned long long a, b;
- struct timeval tv;
+ struct blk_trace *bt = q->blk_trace;
+ int rw = rq->cmd_flags & 0x03;
- a = sched_clock();
- do_gettimeofday(&tv);
- b = sched_clock();
+ if (likely(!bt))
+ return;
- *t = tv.tv_sec * 1000000000 + tv.tv_usec * 1000;
- *t -= (a + b) / 2;
+ if (blk_discard_rq(rq))
+ rw |= (1 << BIO_RW_DISCARD);
+
+ if (blk_pc_request(rq)) {
+ what |= BLK_TC_ACT(BLK_TC_PC);
+ __blk_add_trace(bt, 0, rq->data_len, rw, what, rq->errors,
+ sizeof(rq->cmd), rq->cmd);
+ } else {
+ what |= BLK_TC_ACT(BLK_TC_FS);
+ __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
+ rw, what, rq->errors, 0, NULL);
+ }
}
-static void blk_trace_check_cpu_time(void *data)
+static void blk_add_trace_rq_abort(struct request_queue *q, struct request *rq)
{
- unsigned long long *t;
- int cpu = get_cpu();
+ blk_add_trace_rq(q, rq, BLK_TA_ABORT);
+}
- t = &per_cpu(blk_trace_cpu_offset, cpu);
+static void blk_add_trace_rq_insert(struct request_queue *q, struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+}
- /*
- * Just call it twice, hopefully the second call will be cache hot
- * and a little more precise
- */
- blk_check_time(t);
- blk_check_time(t);
+static void blk_add_trace_rq_issue(struct request_queue *q, struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+}
- put_cpu();
+static void blk_add_trace_rq_requeue(struct request_queue *q, struct request *rq)
+{
+ blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
}
-/*
- * Call blk_trace_check_cpu_time() on each CPU to calibrate our inter-CPU
- * timings
- */
-static void blk_trace_calibrate_offsets(void)
+static void blk_add_trace_rq_complete(struct request_queue *q, struct request *rq)
{
- unsigned long flags;
+ blk_add_trace_rq(q, rq, BLK_TA_COMPLETE);
+}
- smp_call_function(blk_trace_check_cpu_time, NULL, 1, 1);
- local_irq_save(flags);
- blk_trace_check_cpu_time(NULL);
- local_irq_restore(flags);
+/**
+ * blk_add_trace_bio - Add a trace for a bio oriented action
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @what: the action
+ *
+ * Description:
+ * Records an action against a bio. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
+ u32 what)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what,
+ !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
}
-static void blk_trace_set_ht_offsets(void)
+static void blk_add_trace_bio_bounce(struct request_queue *q, struct bio *bio)
{
-#if defined(CONFIG_SCHED_SMT)
- int cpu, i;
+ blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
+}
- /*
- * now make sure HT siblings have the same time offset
- */
- preempt_disable();
- for_each_online_cpu(cpu) {
- unsigned long long *cpu_off, *sibling_off;
+static void blk_add_trace_bio_complete(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
+}
- for_each_cpu_mask(i, cpu_sibling_map[cpu]) {
- if (i == cpu)
- continue;
+static void blk_add_trace_bio_backmerge(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+}
- cpu_off = &per_cpu(blk_trace_cpu_offset, cpu);
- sibling_off = &per_cpu(blk_trace_cpu_offset, i);
- *sibling_off = *cpu_off;
- }
+static void blk_add_trace_bio_frontmerge(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+}
+
+static void blk_add_trace_bio_queue(struct request_queue *q, struct bio *bio)
+{
+ blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+}
+
+static void blk_add_trace_getrq(struct request_queue *q, struct bio *bio, int rw)
+{
+ if (bio)
+ blk_add_trace_bio(q, bio, BLK_TA_GETRQ);
+ else {
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt)
+ __blk_add_trace(bt, 0, 0, rw, BLK_TA_GETRQ, 0, 0, NULL);
}
- preempt_enable();
-#endif
}
-static __init int blk_trace_init(void)
+
+static void blk_add_trace_sleeprq(struct request_queue *q, struct bio *bio, int rw)
{
- mutex_init(&blk_tree_mutex);
- blk_trace_calibrate_offsets();
- blk_trace_set_ht_offsets();
+ if (bio)
+ blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ);
+ else {
+ struct blk_trace *bt = q->blk_trace;
- return 0;
+ if (bt)
+ __blk_add_trace(bt, 0, 0, rw, BLK_TA_SLEEPRQ, 0, 0, NULL);
+ }
+}
+
+static void blk_add_trace_plug(struct request_queue *q)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt)
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_PLUG, 0, 0, NULL);
+}
+
+static void blk_add_trace_unplug_io(struct request_queue *q)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt) {
+ unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
+ __be64 rpdu = cpu_to_be64(pdu);
+
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_IO, 0,
+ sizeof(rpdu), &rpdu);
+ }
+}
+
+static void blk_add_trace_unplug_timer(struct request_queue *q)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt) {
+ unsigned int pdu = q->rq.count[READ] + q->rq.count[WRITE];
+ __be64 rpdu = cpu_to_be64(pdu);
+
+ __blk_add_trace(bt, 0, 0, 0, BLK_TA_UNPLUG_TIMER, 0,
+ sizeof(rpdu), &rpdu);
+ }
}
-module_init(blk_trace_init);
+static void blk_add_trace_split(struct request_queue *q, struct bio *bio,
+ unsigned int pdu)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (bt) {
+ __be64 rpdu = cpu_to_be64(pdu);
+
+ __blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw,
+ BLK_TA_SPLIT, !bio_flagged(bio, BIO_UPTODATE),
+ sizeof(rpdu), &rpdu);
+ }
+}
+/**
+ * blk_add_trace_remap - Add a trace for a remap operation
+ * @q: queue the io is for
+ * @bio: the source bio
+ * @dev: target device
+ * @from: source sector
+ * @to: target sector
+ *
+ * Description:
+ * Device mapper or raid target sometimes need to split a bio because
+ * it spans a stripe (or similar). Add a trace for that action.
+ *
+ **/
+static void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
+ dev_t dev, sector_t from, sector_t to)
+{
+ struct blk_trace *bt = q->blk_trace;
+ struct blk_io_trace_remap r;
+
+ if (likely(!bt))
+ return;
+
+ r.device = cpu_to_be32(dev);
+ r.device_from = cpu_to_be32(bio->bi_bdev->bd_dev);
+ r.sector = cpu_to_be64(to);
+
+ __blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP,
+ !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
+}
+
+/**
+ * blk_add_driver_data - Add binary message with driver-specific data
+ * @q: queue the io is for
+ * @rq: io request
+ * @data: driver-specific data
+ * @len: length of driver-specific data
+ *
+ * Description:
+ * Some drivers might want to write driver-specific data per request.
+ *
+ **/
+void blk_add_driver_data(struct request_queue *q,
+ struct request *rq,
+ void *data, size_t len)
+{
+ struct blk_trace *bt = q->blk_trace;
+
+ if (likely(!bt))
+ return;
+
+ if (blk_pc_request(rq))
+ __blk_add_trace(bt, 0, rq->data_len, 0, BLK_TA_DRV_DATA,
+ rq->errors, len, data);
+ else
+ __blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
+ 0, BLK_TA_DRV_DATA, rq->errors, len, data);
+}
+EXPORT_SYMBOL_GPL(blk_add_driver_data);
+
+static int blk_register_tracepoints(void)
+{
+ int ret;
+
+ ret = register_trace_block_rq_abort(blk_add_trace_rq_abort);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_insert(blk_add_trace_rq_insert);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_issue(blk_add_trace_rq_issue);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+ WARN_ON(ret);
+ ret = register_trace_block_rq_complete(blk_add_trace_rq_complete);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_complete(blk_add_trace_bio_complete);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+ WARN_ON(ret);
+ ret = register_trace_block_bio_queue(blk_add_trace_bio_queue);
+ WARN_ON(ret);
+ ret = register_trace_block_getrq(blk_add_trace_getrq);
+ WARN_ON(ret);
+ ret = register_trace_block_sleeprq(blk_add_trace_sleeprq);
+ WARN_ON(ret);
+ ret = register_trace_block_plug(blk_add_trace_plug);
+ WARN_ON(ret);
+ ret = register_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+ WARN_ON(ret);
+ ret = register_trace_block_unplug_io(blk_add_trace_unplug_io);
+ WARN_ON(ret);
+ ret = register_trace_block_split(blk_add_trace_split);
+ WARN_ON(ret);
+ ret = register_trace_block_remap(blk_add_trace_remap);
+ WARN_ON(ret);
+ return 0;
+}
+
+static void blk_unregister_tracepoints(void)
+{
+ unregister_trace_block_remap(blk_add_trace_remap);
+ unregister_trace_block_split(blk_add_trace_split);
+ unregister_trace_block_unplug_io(blk_add_trace_unplug_io);
+ unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer);
+ unregister_trace_block_plug(blk_add_trace_plug);
+ unregister_trace_block_sleeprq(blk_add_trace_sleeprq);
+ unregister_trace_block_getrq(blk_add_trace_getrq);
+ unregister_trace_block_bio_queue(blk_add_trace_bio_queue);
+ unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge);
+ unregister_trace_block_bio_backmerge(blk_add_trace_bio_backmerge);
+ unregister_trace_block_bio_complete(blk_add_trace_bio_complete);
+ unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce);
+ unregister_trace_block_rq_complete(blk_add_trace_rq_complete);
+ unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue);
+ unregister_trace_block_rq_issue(blk_add_trace_rq_issue);
+ unregister_trace_block_rq_insert(blk_add_trace_rq_insert);
+ unregister_trace_block_rq_abort(blk_add_trace_rq_abort);
+
+ tracepoint_synchronize_unregister();
+}