Re: 2.6.22 -mm merge plans

[Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>]

* Andrew Morton (akpm@linux-foundation.org) wrote:
> > Although some, like Christoph and myself, think that it would benefit to
> > the kernel community to have a common infrastructure for more than just
> > markers (meaning common serialization and buffering mechanism), it does
> > not change the fact that the markers, being in mainline, are usable by
> > projects through additional kernel modules.
> > 
> > If we are looking at current "potential users" that are already in
> > mainline, we could change blktrace to make it use the markers.
> 
> That'd be a useful demonstration.

Here is a proof of concept patch, for demonstration purpose, of moving
blktrace to the markers.

A few remarks : this patch has the positive effect of removing some code
from the block io tracing hot paths, minimizing the i-cache impact in a
system where the io tracing is compiled in but inactive.

It also moves the blk tracing code from a header (and therefore from the
body of the instrumented functions) to a separate C file.

There, as soon as one device has to be traced, every devices have to
fall into the tracing function call. This is slower than the previous
inline function which tested the condition quickly. If it becomes a
show stopper, it could be fixed by having the possibility to test a
supplementary condition, dependant of the marker context, at the marker
site, just after the enable/disable test.

It does not make the code smaller, since I left all the specialized
tracing functions for requests, bio, generic, remap, which would go away
once a generic infrastructure is in place to serialize the information
passed to the marker. This is mostly why I consider it a proof a
concept.

Patch named "markers-port-blktrace-to-markers.patch", can be placed
after the marker patches in the 2.6.21-rc7-mm2 series.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Index: linux-2.6-lttng/block/elevator.c
===================================================================
--- linux-2.6-lttng.orig/block/elevator.c	2007-05-02 20:33:22.000000000 -0400
+++ linux-2.6-lttng/block/elevator.c	2007-05-02 20:33:49.000000000 -0400
@@ -32,7 +32,7 @@
 #include <linux/init.h>
 #include <linux/compiler.h>
 #include <linux/delay.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
 #include <linux/hash.h>
 
 #include <asm/uaccess.h>
@@ -571,7 +571,7 @@
 	unsigned ordseq;
 	int unplug_it = 1;
 
-	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+	MARK(blk_request_insert, "%p %p", q, rq);
 
 	rq->q = q;
 
@@ -757,7 +757,7 @@
 			 * not be passed by new incoming requests
 			 */
 			rq->cmd_flags |= REQ_STARTED;
-			blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
+			MARK(blk_request_issue, "%p %p", q, rq);
 		}
 
 		if (!q->boundary_rq || q->boundary_rq == rq) {
Index: linux-2.6-lttng/block/ll_rw_blk.c
===================================================================
--- linux-2.6-lttng.orig/block/ll_rw_blk.c	2007-05-02 20:33:32.000000000 -0400
+++ linux-2.6-lttng/block/ll_rw_blk.c	2007-05-02 23:21:02.000000000 -0400
@@ -28,6 +28,7 @@
 #include <linux/task_io_accounting_ops.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/marker.h>
 #include <linux/blktrace_api.h>
 #include <linux/fault-inject.h>
 
@@ -1551,7 +1552,7 @@
 
 	if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags)) {
 		mod_timer(&q->unplug_timer, jiffies + q->unplug_delay);
-		blk_add_trace_generic(q, NULL, 0, BLK_TA_PLUG);
+		MARK(blk_plug_device, "%p %p %d", q, NULL, 0);
 	}
 }
 
@@ -1617,7 +1618,7 @@
 	 * devices don't necessarily have an ->unplug_fn defined
 	 */
 	if (q->unplug_fn) {
-		blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+		MARK(blk_pdu_unplug_io, "%p %p %d", q, NULL,
 					q->rq.count[READ] + q->rq.count[WRITE]);
 
 		q->unplug_fn(q);
@@ -1628,7 +1629,7 @@
 {
 	request_queue_t *q = container_of(work, request_queue_t, unplug_work);
 
-	blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+	MARK(blk_pdu_unplug_io, "%p %p %d", q, NULL,
 				q->rq.count[READ] + q->rq.count[WRITE]);
 
 	q->unplug_fn(q);
@@ -1638,7 +1639,7 @@
 {
 	request_queue_t *q = (request_queue_t *)data;
 
-	blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
+	MARK(blk_pdu_unplug_timer, "%p %p %d", q, NULL,
 				q->rq.count[READ] + q->rq.count[WRITE]);
 
 	kblockd_schedule_work(&q->unplug_work);
@@ -2148,7 +2149,7 @@
 	
 	rq_init(q, rq);
 
-	blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
+	MARK(blk_get_request, "%p %p %d", q, bio, rw);
 out:
 	return rq;
 }
@@ -2178,7 +2179,7 @@
 		if (!rq) {
 			struct io_context *ioc;
 
-			blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);
+			MARK(blk_sleep_request, "%p %p %d", q, bio, rw);
 
 			__generic_unplug_device(q);
 			spin_unlock_irq(q->queue_lock);
@@ -2252,7 +2253,7 @@
  */
 void blk_requeue_request(request_queue_t *q, struct request *rq)
 {
-	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+	MARK(blk_requeue, "%p %p", q, rq);
 
 	if (blk_rq_tagged(rq))
 		blk_queue_end_tag(q, rq);
@@ -2937,7 +2938,7 @@
 			if (!ll_back_merge_fn(q, req, bio))
 				break;
 
-			blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+			MARK(blk_bio_backmerge, "%p %p", q, bio);
 
 			req->biotail->bi_next = bio;
 			req->biotail = bio;
@@ -2954,7 +2955,7 @@
 			if (!ll_front_merge_fn(q, req, bio))
 				break;
 
-			blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+			MARK(blk_bio_frontmerge, "%p %p", q, bio);
 
 			bio->bi_next = req->bio;
 			req->bio = bio;
@@ -3184,10 +3185,10 @@
 		blk_partition_remap(bio);
 
 		if (old_sector != -1)
-			blk_add_trace_remap(q, bio, old_dev, bio->bi_sector, 
-					    old_sector);
+			MARK(blk_remap, "%p %p %u %llu %llu", q, bio, old_dev,
+					(u64)bio->bi_sector, (u64)old_sector);
 
-		blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+		MARK(blk_bio_queue, "%p %p", q, bio);
 
 		old_sector = bio->bi_sector;
 		old_dev = bio->bi_bdev->bd_dev;
@@ -3329,7 +3330,7 @@
 	int total_bytes, bio_nbytes, error, next_idx = 0;
 	struct bio *bio;
 
-	blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);
+	MARK(blk_request_complete, "%p %p", req->q, req);
 
 	/*
 	 * extend uptodate bool to allow < 0 value to be direct io error
Index: linux-2.6-lttng/block/Kconfig
===================================================================
--- linux-2.6-lttng.orig/block/Kconfig	2007-05-02 20:34:30.000000000 -0400
+++ linux-2.6-lttng/block/Kconfig	2007-05-02 20:34:53.000000000 -0400
@@ -32,6 +32,7 @@
 	depends on SYSFS
 	select RELAY
 	select DEBUG_FS
+	select MARKERS
 	help
 	  Say Y here, if you want to be able to trace the block layer actions
 	  on a given queue. Tracing allows you to see any traffic happening
Index: linux-2.6-lttng/block/Makefile
===================================================================
--- linux-2.6-lttng.orig/block/Makefile	2007-05-02 21:20:30.000000000 -0400
+++ linux-2.6-lttng/block/Makefile	2007-05-02 21:20:46.000000000 -0400
@@ -9,4 +9,4 @@
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
 
-obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o
+obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o blk-probe.o
Index: linux-2.6-lttng/block/blk-probe.c
===================================================================
--- /dev/null	1970-01-01 00:00:00.000000000 +0000
+++ linux-2.6-lttng/block/blk-probe.c	2007-05-02 23:43:44.000000000 -0400
@@ -0,0 +1,276 @@
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/crc32.h>
+#include <linux/marker.h>
+#include <linux/blktrace_api.h>
+
+
+/**
+ * blk_add_trace_rq - Add a trace for a request oriented action
+ * Expected variable arguments :
+ * @q:		queue the io is for
+ * @rq:		the source request
+ *
+ * Description:
+ *     Records an action against a request. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_rq(const struct __mark_marker_data *mdata,
+	const char *fmt, ...)
+{
+	va_list args;
+	u32 what;
+	struct blk_trace *bt;
+	int rw;
+	struct blk_probe_data *pinfo = mdata->pdata;
+	struct request_queue *q;
+	struct request *rq;
+
+	va_start(args, fmt);
+	q = va_arg(args, struct request_queue *);
+	rq = va_arg(args, struct request *);
+	va_end(args);
+
+	what = pinfo->flags;
+	bt = q->blk_trace;
+	rw = rq->cmd_flags & 0x03;
+
+	if (likely(!bt))
+		return;
+
+	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);
+	}
+}
+
+/**
+ * blk_add_trace_bio - Add a trace for a bio oriented action
+ * Expected variable arguments :
+ * @q:		queue the io is for
+ * @bio:	the source bio
+ *
+ * Description:
+ *     Records an action against a bio. Will log the bio offset + size.
+ *
+ **/
+static void blk_add_trace_bio(const struct __mark_marker_data *mdata,
+	const char *fmt, ...)
+{
+	va_list args;
+	u32 what;
+	struct blk_trace *bt;
+	struct blk_probe_data *pinfo = mdata->pdata;
+	struct request_queue *q;
+	struct bio *bio;
+
+	va_start(args, fmt);
+	q = va_arg(args, struct request_queue *);
+	bio = va_arg(args, struct bio *);
+	va_end(args);
+
+	what = pinfo->flags;
+	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);
+}
+
+/**
+ * blk_add_trace_generic - Add a trace for a generic action
+ * Expected variable arguments :
+ * @q:		queue the io is for
+ * @bio:	the source bio
+ * @rw:		the data direction
+ *
+ * Description:
+ *     Records a simple trace
+ *
+ **/
+static void blk_add_trace_generic(const struct __mark_marker_data *mdata,
+	const char *fmt, ...)
+{
+	va_list args;
+	struct blk_trace *bt;
+	u32 what;
+	struct blk_probe_data *pinfo = mdata->pdata;
+	struct request_queue *q;
+	struct bio *bio;
+	int rw;
+
+	va_start(args, fmt);
+	q = va_arg(args, struct request_queue *);
+	bio = va_arg(args, struct bio *);
+	rw = va_arg(args, int);
+	va_end(args);
+
+	what = pinfo->flags;
+	bt = q->blk_trace;
+
+	if (likely(!bt))
+		return;
+
+	if (bio)
+		blk_add_trace_bio(mdata, "%p %p", q, bio);
+	else
+		__blk_add_trace(bt, 0, 0, rw, what, 0, 0, NULL);
+}
+
+/**
+ * blk_add_trace_pdu_int - Add a trace for a bio with an integer payload
+ * Expected variable arguments :
+ * @q:		queue the io is for
+ * @bio:	the source bio
+ * @pdu:	the integer payload
+ *
+ * Description:
+ *     Adds a trace with some integer payload. This might be an unplug
+ *     option given as the action, with the depth at unplug time given
+ *     as the payload
+ *
+ **/
+static void blk_add_trace_pdu_int(const struct __mark_marker_data *mdata,
+	const char *fmt, ...)
+{
+	va_list args;
+	struct blk_trace *bt;
+	u32 what;
+	struct blk_probe_data *pinfo = mdata->pdata;
+	struct request_queue *q;
+	struct bio *bio;
+	unsigned int pdu;
+	__be64 rpdu;
+
+	va_start(args, fmt);
+	q = va_arg(args, struct request_queue *);
+	bio = va_arg(args, struct bio *);
+	pdu = va_arg(args, unsigned int);
+	va_end(args);
+
+	what = pinfo->flags;
+	bt = q->blk_trace;
+	rpdu = cpu_to_be64(pdu);
+
+	if (likely(!bt))
+		return;
+
+	if (bio)
+		__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), sizeof(rpdu), &rpdu);
+	else
+		__blk_add_trace(bt, 0, 0, 0, what, 0, sizeof(rpdu), &rpdu);
+}
+
+/**
+ * blk_add_trace_remap - Add a trace for a remap operation
+ * Expected variable arguments :
+ * @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(const struct __mark_marker_data *mdata,
+	const char *fmt, ...)
+{
+	va_list args;
+	struct blk_trace *bt;
+	struct blk_io_trace_remap r;
+	u32 what;
+	struct blk_probe_data *pinfo = mdata->pdata;
+	struct request_queue *q;
+	struct bio *bio;
+	u64 dev, from, to;
+
+	va_start(args, fmt);
+	q = va_arg(args, struct request_queue *);
+	bio = va_arg(args, struct bio *);
+	dev = va_arg(args, u64);
+	from = va_arg(args, u64);
+	to = va_arg(args, u64);
+	va_end(args);
+
+	what = pinfo->flags;
+	bt = q->blk_trace;
+
+	if (likely(!bt))
+		return;
+
+	r.device = cpu_to_be32(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);
+}
+
+#define FACILITY_NAME "blk"
+
+static struct blk_probe_data probe_array[] =
+{
+	{ "blk_bio_queue", "%p %p", BLK_TA_QUEUE, blk_add_trace_bio },
+	{ "blk_bio_backmerge", "%p %p", BLK_TA_BACKMERGE, blk_add_trace_bio },
+	{ "blk_bio_frontmerge", "%p %p", BLK_TA_FRONTMERGE, blk_add_trace_bio },
+	{ "blk_get_request", "%p %p %d", BLK_TA_GETRQ, blk_add_trace_generic },
+	{ "blk_sleep_request", "%p %p %d", BLK_TA_SLEEPRQ,
+		blk_add_trace_generic },
+	{ "blk_requeue", "%p %p", BLK_TA_REQUEUE, blk_add_trace_rq },
+	{ "blk_request_issue", "%p %p", BLK_TA_ISSUE, blk_add_trace_rq },
+	{ "blk_request_complete", "%p %p", BLK_TA_COMPLETE, blk_add_trace_rq },
+	{ "blk_plug_device", "%p %p %d", BLK_TA_PLUG, blk_add_trace_generic },
+	{ "blk_pdu_unplug_io", "%p %p %d", BLK_TA_UNPLUG_IO,
+		blk_add_trace_pdu_int },
+	{ "blk_pdu_unplug_timer", "%p %p %d", BLK_TA_UNPLUG_TIMER,
+		blk_add_trace_pdu_int },
+	{ "blk_request_insert", "%p %p", BLK_TA_INSERT,
+		blk_add_trace_rq },
+	{ "blk_pdu_split", "%p %p %d", BLK_TA_SPLIT,
+		blk_add_trace_pdu_int },
+	{ "blk_bio_bounce", "%p %p", BLK_TA_BOUNCE, blk_add_trace_bio },
+	{ "blk_remap", "%p %p %u %llu %llu", BLK_TA_REMAP,
+		blk_add_trace_remap },
+};
+
+
+#define NUM_PROBES ARRAY_SIZE(probe_array)
+
+int blk_probe_connect(void)
+{
+	int result;
+	uint8_t i;
+
+	for (i = 0; i < NUM_PROBES; i++) {
+		result = marker_set_probe(probe_array[i].name,
+				probe_array[i].format,
+				probe_array[i].callback, &probe_array[i]);
+		if (!result)
+			printk(KERN_INFO
+				"blktrace unable to register probe %s\n",
+				probe_array[i].name);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_probe_connect);
+
+void blk_probe_disconnect(void)
+{
+	uint8_t i;
+
+	for (i = 0; i < NUM_PROBES; i++) {
+		marker_remove_probe(probe_array[i].name);
+	}
+	synchronize_sched();	/* Wait for probes to finish */
+}
+EXPORT_SYMBOL_GPL(blk_probe_disconnect);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Mathieu Desnoyers");
+MODULE_DESCRIPTION(FACILITY_NAME " probe");
Index: linux-2.6-lttng/block/blktrace.c
===================================================================
--- linux-2.6-lttng.orig/block/blktrace.c	2007-05-02 20:33:15.000000000 -0400
+++ linux-2.6-lttng/block/blktrace.c	2007-05-02 23:48:32.000000000 -0400
@@ -28,6 +28,10 @@
 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 struct mutex blk_probe_mutex;
+static int blk_probes_ref = 0;
+
 /*
  * Send out a notify message.
  */
@@ -229,6 +233,12 @@
 	blk_remove_tree(bt->dir);
 	free_percpu(bt->sequence);
 	kfree(bt);
+	mutex_lock(&blk_probe_mutex);
+	if (blk_probes_ref == 1) {
+		blk_probe_disconnect();
+		blk_probes_ref--;
+	}
+	mutex_unlock(&blk_probe_mutex);
 }
 
 static int blk_trace_remove(request_queue_t *q)
@@ -386,6 +396,14 @@
 		goto err;
 	}
 
+	/* Connect probes to markers */
+	mutex_lock(&blk_probe_mutex);
+	if (!blk_probes_ref) {
+		blk_probe_connect();
+		blk_probes_ref++;
+	}
+	mutex_unlock(&blk_probe_mutex);
+
 	return 0;
 err:
 	if (dir)
@@ -552,6 +570,7 @@
 static __init int blk_trace_init(void)
 {
 	mutex_init(&blk_tree_mutex);
+	mutex_init(&blk_probe_mutex);
 	on_each_cpu(blk_trace_check_cpu_time, NULL, 1, 1);
 	blk_trace_set_ht_offsets();
 
Index: linux-2.6-lttng/include/linux/blktrace_api.h
===================================================================
--- linux-2.6-lttng.orig/include/linux/blktrace_api.h	2007-05-02 20:45:58.000000000 -0400
+++ linux-2.6-lttng/include/linux/blktrace_api.h	2007-05-02 22:12:46.000000000 -0400
@@ -3,6 +3,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/relay.h>
+#include <linux/marker.h>
 
 /*
  * Trace categories
@@ -142,149 +143,24 @@
 	u32 pid;
 };
 
+/* Probe data used for probe-marker connection */
+struct blk_probe_data {
+	const char *name;
+	const char *format;
+	u32 flags;
+	marker_probe_func *callback;
+};
+
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(request_queue_t *);
 extern void __blk_add_trace(struct blk_trace *, sector_t, int, int, u32, int, int, void *);
-
-/**
- * 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 inline void blk_add_trace_rq(struct request_queue *q, struct request *rq,
-				    u32 what)
-{
-	struct blk_trace *bt = q->blk_trace;
-	int rw = rq->cmd_flags & 0x03;
-
-	if (likely(!bt))
-		return;
-
-	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);
-	}
-}
-
-/**
- * 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 inline 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);
-}
-
-/**
- * blk_add_trace_generic - Add a trace for a generic action
- * @q:		queue the io is for
- * @bio:	the source bio
- * @rw:		the data direction
- * @what:	the action
- *
- * Description:
- *     Records a simple trace
- *
- **/
-static inline void blk_add_trace_generic(struct request_queue *q,
-					 struct bio *bio, int rw, u32 what)
-{
-	struct blk_trace *bt = q->blk_trace;
-
-	if (likely(!bt))
-		return;
-
-	if (bio)
-		blk_add_trace_bio(q, bio, what);
-	else
-		__blk_add_trace(bt, 0, 0, rw, what, 0, 0, NULL);
-}
-
-/**
- * blk_add_trace_pdu_int - Add a trace for a bio with an integer payload
- * @q:		queue the io is for
- * @what:	the action
- * @bio:	the source bio
- * @pdu:	the integer payload
- *
- * Description:
- *     Adds a trace with some integer payload. This might be an unplug
- *     option given as the action, with the depth at unplug time given
- *     as the payload
- *
- **/
-static inline void blk_add_trace_pdu_int(struct request_queue *q, u32 what,
-					 struct bio *bio, unsigned int pdu)
-{
-	struct blk_trace *bt = q->blk_trace;
-	__be64 rpdu = cpu_to_be64(pdu);
-
-	if (likely(!bt))
-		return;
-
-	if (bio)
-		__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what, !bio_flagged(bio, BIO_UPTODATE), sizeof(rpdu), &rpdu);
-	else
-		__blk_add_trace(bt, 0, 0, 0, what, 0, 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 inline 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.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);
-}
+extern int blk_probe_connect(void);
+extern void blk_probe_disconnect(void);
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 #define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 #define blk_trace_shutdown(q)			do { } while (0)
-#define blk_add_trace_rq(q, rq, what)		do { } while (0)
-#define blk_add_trace_bio(q, rq, what)		do { } while (0)
-#define blk_add_trace_generic(q, rq, rw, what)	do { } while (0)
-#define blk_add_trace_pdu_int(q, what, bio, pdu)	do { } while (0)
-#define blk_add_trace_remap(q, bio, dev, f, t)	do {} while (0)
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #endif
Index: linux-2.6-lttng/mm/bounce.c
===================================================================
--- linux-2.6-lttng.orig/mm/bounce.c	2007-05-02 21:34:39.000000000 -0400
+++ linux-2.6-lttng/mm/bounce.c	2007-05-02 21:36:17.000000000 -0400
@@ -13,7 +13,7 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
 #include <asm/tlbflush.h>
 
 #define POOL_SIZE	64
@@ -237,7 +237,7 @@
 	if (!bio)
 		return;
 
-	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+	MARK(blk_bio_bounce, "%p %p", q, *bio_orig);
 
 	/*
 	 * at least one page was bounced, fill in possible non-highmem
Index: linux-2.6-lttng/mm/highmem.c
===================================================================
--- linux-2.6-lttng.orig/mm/highmem.c	2007-05-02 21:36:27.000000000 -0400
+++ linux-2.6-lttng/mm/highmem.c	2007-05-02 21:36:39.000000000 -0400
@@ -26,7 +26,7 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
 #include <asm/tlbflush.h>
 
 /*
Index: linux-2.6-lttng/fs/bio.c
===================================================================
--- linux-2.6-lttng.orig/fs/bio.c	2007-05-02 21:37:52.000000000 -0400
+++ linux-2.6-lttng/fs/bio.c	2007-05-02 21:40:30.000000000 -0400
@@ -25,7 +25,7 @@
 #include <linux/module.h>
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
 #include <scsi/sg.h>		/* for struct sg_iovec */
 
 #define BIO_POOL_SIZE 2
@@ -1081,7 +1081,7 @@
 	if (!bp)
 		return bp;
 
-	blk_add_trace_pdu_int(bdev_get_queue(bi->bi_bdev), BLK_TA_SPLIT, bi,
+	MARK(blk_pdu_split, "%p %p %d", bdev_get_queue(bi->bi_bdev), bi,
 				bi->bi_sector + first_sectors);
 
 	BUG_ON(bi->bi_vcnt != 1);
Index: linux-2.6-lttng/drivers/block/cciss.c
===================================================================
--- linux-2.6-lttng.orig/drivers/block/cciss.c	2007-05-02 21:44:30.000000000 -0400
+++ linux-2.6-lttng/drivers/block/cciss.c	2007-05-02 21:45:08.000000000 -0400
@@ -37,7 +37,7 @@
 #include <linux/hdreg.h>
 #include <linux/spinlock.h>
 #include <linux/compat.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
@@ -2502,7 +2502,7 @@
 	}
 	cmd->rq->data_len = 0;
 	cmd->rq->completion_data = cmd;
-	blk_add_trace_rq(cmd->rq->q, cmd->rq, BLK_TA_COMPLETE);
+	MARK(blk_request_complete, "%p %p", cmd->rq->q, cmd->rq);
 	blk_complete_request(cmd->rq);
 }
 
Index: linux-2.6-lttng/drivers/md/dm.c
===================================================================
--- linux-2.6-lttng.orig/drivers/md/dm.c	2007-05-02 21:44:41.000000000 -0400
+++ linux-2.6-lttng/drivers/md/dm.c	2007-05-02 21:47:19.000000000 -0400
@@ -19,7 +19,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/hdreg.h>
-#include <linux/blktrace_api.h>
+#include <linux/marker.h>
 #include <linux/smp_lock.h>
 
 #define DM_MSG_PREFIX "core"
@@ -485,8 +485,8 @@
 			wake_up(&io->md->wait);
 
 		if (io->error != DM_ENDIO_REQUEUE) {
-			blk_add_trace_bio(io->md->queue, io->bio,
-					  BLK_TA_COMPLETE);
+			MARK(blk_request_complete, "%p %p",
+				io->md->queue, io->bio);
 
 			bio_endio(io->bio, io->bio->bi_size, io->error);
 		}
@@ -582,10 +582,10 @@
 	r = ti->type->map(ti, clone, &tio->info);
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
-
-		blk_add_trace_remap(bdev_get_queue(clone->bi_bdev), clone,
-				    tio->io->bio->bi_bdev->bd_dev, sector,
-				    clone->bi_sector);
+		MARK(blk_remap, "%p %p %u %llu %llu",
+			bdev_get_queue(clone->bi_bdev), clone,
+			(u64)tio->io->bio->bi_bdev->bd_dev, (u64)sector,
+			(u64)clone->bi_sector);
 
 		generic_make_request(clone);
 	} else if (r < 0 || r == DM_MAPIO_REQUEUE) {
-- 
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68