[PATCH] Block queue IO tracing support (blktrace) as of 2006-03-23

Signed-off-by: Jens Axboe <axboe@suse.de>

5 files changed, 289 insertions, 0 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 56bb6a4e15f3..c179966f1a2f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -22,6 +22,7 @@ typedef struct request_queue request_queue_t;
 struct elevator_queue;
 typedef struct elevator_queue elevator_t;
 struct request_pm_state;
+struct blk_trace;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -416,6 +417,8 @@ struct request_queue
 	unsigned int		sg_reserved_size;
 	int			node;
 
+	struct blk_trace	*blk_trace;
+
 	/*
 	 * reserved for flush operations
 	 */
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
new file mode 100644
index 000000000000..b34d3e73d5ea
--- /dev/null
+++ b/include/linux/blktrace_api.h
@@ -0,0 +1,277 @@
+#ifndef BLKTRACE_H
+#define BLKTRACE_H
+
+#include <linux/config.h>
+#include <linux/blkdev.h>
+#include <linux/relay.h>
+
+/*
+ * Trace categories
+ */
+enum blktrace_cat {
+	BLK_TC_READ	= 1 << 0,	/* reads */
+	BLK_TC_WRITE	= 1 << 1,	/* writes */
+	BLK_TC_BARRIER	= 1 << 2,	/* barrier */
+	BLK_TC_SYNC	= 1 << 3,	/* barrier */
+	BLK_TC_QUEUE	= 1 << 4,	/* queueing/merging */
+	BLK_TC_REQUEUE	= 1 << 5,	/* requeueing */
+	BLK_TC_ISSUE	= 1 << 6,	/* issue */
+	BLK_TC_COMPLETE	= 1 << 7,	/* completions */
+	BLK_TC_FS	= 1 << 8,	/* fs requests */
+	BLK_TC_PC	= 1 << 9,	/* pc requests */
+	BLK_TC_NOTIFY	= 1 << 10,	/* special message */
+
+	BLK_TC_END	= 1 << 15,	/* only 16-bits, reminder */
+};
+
+#define BLK_TC_SHIFT		(16)
+#define BLK_TC_ACT(act)		((act) << BLK_TC_SHIFT)
+
+/*
+ * Basic trace actions
+ */
+enum blktrace_act {
+	__BLK_TA_QUEUE = 1,		/* queued */
+	__BLK_TA_BACKMERGE,		/* back merged to existing rq */
+	__BLK_TA_FRONTMERGE,		/* front merge to existing rq */
+	__BLK_TA_GETRQ,			/* allocated new request */
+	__BLK_TA_SLEEPRQ,		/* sleeping on rq allocation */
+	__BLK_TA_REQUEUE,		/* request requeued */
+	__BLK_TA_ISSUE,			/* sent to driver */
+	__BLK_TA_COMPLETE,		/* completed by driver */
+	__BLK_TA_PLUG,			/* queue was plugged */
+	__BLK_TA_UNPLUG_IO,		/* queue was unplugged by io */
+	__BLK_TA_UNPLUG_TIMER,		/* queue was unplugged by timer */
+	__BLK_TA_INSERT,		/* insert request */
+	__BLK_TA_SPLIT,			/* bio was split */
+	__BLK_TA_BOUNCE,		/* bio was bounced */
+	__BLK_TA_REMAP,			/* bio was remapped */
+};
+
+/*
+ * Trace actions in full. Additionally, read or write is masked
+ */
+#define BLK_TA_QUEUE		(__BLK_TA_QUEUE | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_BACKMERGE	(__BLK_TA_BACKMERGE | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_FRONTMERGE	(__BLK_TA_FRONTMERGE | BLK_TC_ACT(BLK_TC_QUEUE))
+#define	BLK_TA_GETRQ		(__BLK_TA_GETRQ | BLK_TC_ACT(BLK_TC_QUEUE))
+#define	BLK_TA_SLEEPRQ		(__BLK_TA_SLEEPRQ | BLK_TC_ACT(BLK_TC_QUEUE))
+#define	BLK_TA_REQUEUE		(__BLK_TA_REQUEUE | BLK_TC_ACT(BLK_TC_REQUEUE))
+#define BLK_TA_ISSUE		(__BLK_TA_ISSUE | BLK_TC_ACT(BLK_TC_ISSUE))
+#define BLK_TA_COMPLETE		(__BLK_TA_COMPLETE| BLK_TC_ACT(BLK_TC_COMPLETE))
+#define BLK_TA_PLUG		(__BLK_TA_PLUG | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_UNPLUG_IO	(__BLK_TA_UNPLUG_IO | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_UNPLUG_TIMER	(__BLK_TA_UNPLUG_TIMER | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_INSERT		(__BLK_TA_INSERT | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_SPLIT		(__BLK_TA_SPLIT)
+#define BLK_TA_BOUNCE		(__BLK_TA_BOUNCE)
+#define BLK_TA_REMAP		(__BLK_TA_REMAP | BLK_TC_ACT(BLK_TC_QUEUE))
+
+#define BLK_IO_TRACE_MAGIC	0x65617400
+#define BLK_IO_TRACE_VERSION	0x07
+
+/*
+ * The trace itself
+ */
+struct blk_io_trace {
+	u32 magic;		/* MAGIC << 8 | version */
+	u32 sequence;		/* event number */
+	u64 time;		/* in microseconds */
+	u64 sector;		/* disk offset */
+	u32 bytes;		/* transfer length */
+	u32 action;		/* what happened */
+	u32 pid;		/* who did it */
+	u32 device;		/* device number */
+	u32 cpu;		/* on what cpu did it happen */
+	u16 error;		/* completion error */
+	u16 pdu_len;		/* length of data after this trace */
+};
+
+/*
+ * The remap event
+ */
+struct blk_io_trace_remap {
+	u32 device;
+	u32 __pad;
+	u64 sector;
+};
+
+enum {
+	Blktrace_setup = 1,
+	Blktrace_running,
+	Blktrace_stopped,
+};
+
+struct blk_trace {
+	int trace_state;
+	struct rchan *rchan;
+	unsigned long *sequence;
+	u16 act_mask;
+	u64 start_lba;
+	u64 end_lba;
+	u32 pid;
+	u32 dev;
+	struct dentry *dir;
+	struct dentry *dropped_file;
+	atomic_t dropped;
+};
+
+/*
+ * User setup structure passed with BLKTRACESTART
+ */
+struct blk_user_trace_setup {
+	char name[BDEVNAME_SIZE];	/* output */
+	u16 act_mask;			/* input */
+	u32 buf_size;			/* input */
+	u32 buf_nr;			/* input */
+	u64 start_lba;
+	u64 end_lba;
+	u32 pid;
+};
+
+#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->flags & 0x07;
+
+	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;
+	u64 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);
+}
+
+#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
diff --git a/include/linux/compat_ioctl.h b/include/linux/compat_ioctl.h
index ae7dfb790df3..efb518f16bb3 100644
--- a/include/linux/compat_ioctl.h
+++ b/include/linux/compat_ioctl.h
@@ -97,6 +97,10 @@ COMPATIBLE_IOCTL(BLKRRPART)
 COMPATIBLE_IOCTL(BLKFLSBUF)
 COMPATIBLE_IOCTL(BLKSECTSET)
 COMPATIBLE_IOCTL(BLKSSZGET)
+COMPATIBLE_IOCTL(BLKTRACESTART)
+COMPATIBLE_IOCTL(BLKTRACESTOP)
+COMPATIBLE_IOCTL(BLKTRACESETUP)
+COMPATIBLE_IOCTL(BLKTRACETEARDOWN)
 ULONG_IOCTL(BLKRASET)
 ULONG_IOCTL(BLKFRASET)
 /* RAID */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index f9c9dea636d0..9b34a1b03455 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -197,6 +197,10 @@ extern int dir_notify_enable;
 #define BLKBSZGET  _IOR(0x12,112,size_t)
 #define BLKBSZSET  _IOW(0x12,113,size_t)
 #define BLKGETSIZE64 _IOR(0x12,114,size_t)	/* return device size in bytes (u64 *arg) */
+#define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup)
+#define BLKTRACESTART _IO(0x12,116)
+#define BLKTRACESTOP _IO(0x12,117)
+#define BLKTRACETEARDOWN _IO(0x12,118)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 62e6314382f0..e60a91d5b369 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -706,6 +706,7 @@ struct task_struct {
 	prio_array_t *array;
 
 	unsigned short ioprio;
+	unsigned int btrace_seq;
 
 	unsigned long sleep_avg;
 	unsigned long long timestamp, last_ran;