Merge branch 'blktrace' of git://brick.kernel.dk/data/git/linux-2.6-block

* 'blktrace' of git://brick.kernel.dk/data/git/linux-2.6-block:
  [PATCH] Block queue IO tracing support (blktrace) as of 2006-03-23
  [PATCH] relay: consolidate sendfile() and read() code
  [PATCH] relay: add sendfile() support
  [PATCH] relay: migrate from relayfs to a generic relay API

block/Kconfig

@@ -11,4 +11,16 @@ config LBD
 	  your machine, or if you want to have a raid or loopback device
 	  bigger than 2TB.  Otherwise say N.
 
+config BLK_DEV_IO_TRACE
+	bool "Support for tracing block io actions"
+	select RELAY
+	select DEBUG_FS
+	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
+	  on a block device queue. For more information (and the user space
+	  support tools needed), fetch the blktrace app from:
+
+	  git://brick.kernel.dk/data/git/blktrace.git
+
 source block/Kconfig.iosched

block/Makefile

@@ -8,3 +8,5 @@ obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
+
+obj-$(CONFIG_BLK_DEV_IO_TRACE)	+= blktrace.o

block/elevator.c

@@ -33,6 +33,7 @@
 #include <linux/init.h>
 #include <linux/compiler.h>
 #include <linux/delay.h>
+#include <linux/blktrace_api.h>
 
 #include <asm/uaccess.h>
 
@@ -333,6 +334,8 @@ void elv_insert(request_queue_t *q, struct request *rq, int where)
 	struct list_head *pos;
 	unsigned ordseq;
 
+	blk_add_trace_rq(q, rq, BLK_TA_INSERT);
+
 	rq->q = q;
 
 	switch (where) {
@@ -499,6 +502,7 @@ struct request *elv_next_request(request_queue_t *q)
 			 * not be passed by new incoming requests
 			 */
 			rq->flags |= REQ_STARTED;
+			blk_add_trace_rq(q, rq, BLK_TA_ISSUE);
 		}
 
 		if (!q->boundary_rq || q->boundary_rq == rq) {

block/ioctl.c

@@ -5,6 +5,7 @@
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
 #include <linux/smp_lock.h>
+#include <linux/blktrace_api.h>
 #include <asm/uaccess.h>
 
 static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg)
@@ -189,6 +190,11 @@ static int blkdev_locked_ioctl(struct file *file, struct block_device *bdev,
 		return put_ulong(arg, bdev->bd_inode->i_size >> 9);
 	case BLKGETSIZE64:
 		return put_u64(arg, bdev->bd_inode->i_size);
+	case BLKTRACESTART:
+	case BLKTRACESTOP:
+	case BLKTRACESETUP:
+	case BLKTRACETEARDOWN:
+		return blk_trace_ioctl(bdev, cmd, (char __user *) arg);
 	}
 	return -ENOIOCTLCMD;
 }

block/ll_rw_blk.c

@@ -28,6 +28,7 @@
 #include <linux/writeback.h>
 #include <linux/interrupt.h>
 #include <linux/cpu.h>
+#include <linux/blktrace_api.h>
 
 /*
  * for max sense size
@@ -1556,8 +1557,10 @@ void blk_plug_device(request_queue_t *q)
 	if (test_bit(QUEUE_FLAG_STOPPED, &q->queue_flags))
 		return;
 
-	if (!test_and_set_bit(QUEUE_FLAG_PLUGGED, &q->queue_flags))
+	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);
+	}
 }
 
 EXPORT_SYMBOL(blk_plug_device);
@@ -1621,14 +1624,21 @@ static void blk_backing_dev_unplug(struct backing_dev_info *bdi,
 	/*
 	 * devices don't necessarily have an ->unplug_fn defined
 	 */
-	if (q->unplug_fn)
+	if (q->unplug_fn) {
+		blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+					q->rq.count[READ] + q->rq.count[WRITE]);
+
 		q->unplug_fn(q);
+	}
 }
 
 static void blk_unplug_work(void *data)
 {
 	request_queue_t *q = data;
 
+	blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_IO, NULL,
+				q->rq.count[READ] + q->rq.count[WRITE]);
+
 	q->unplug_fn(q);
 }
 
@@ -1636,6 +1646,9 @@ static void blk_unplug_timeout(unsigned long data)
 {
 	request_queue_t *q = (request_queue_t *)data;
 
+	blk_add_trace_pdu_int(q, BLK_TA_UNPLUG_TIMER, NULL,
+				q->rq.count[READ] + q->rq.count[WRITE]);
+
 	kblockd_schedule_work(&q->unplug_work);
 }
 
@@ -1753,6 +1766,9 @@ static void blk_release_queue(struct kobject *kobj)
 	if (q->queue_tags)
 		__blk_queue_free_tags(q);
 
+	if (q->blk_trace)
+		blk_trace_shutdown(q);
+
 	kmem_cache_free(requestq_cachep, q);
 }
 
@@ -2129,6 +2145,8 @@ static struct request *get_request(request_queue_t *q, int rw, struct bio *bio,
 	
 	rq_init(q, rq);
 	rq->rl = rl;
+
+	blk_add_trace_generic(q, bio, rw, BLK_TA_GETRQ);
 out:
 	return rq;
 }
@@ -2157,6 +2175,8 @@ static struct request *get_request_wait(request_queue_t *q, int rw,
 		if (!rq) {
 			struct io_context *ioc;
 
+			blk_add_trace_generic(q, bio, rw, BLK_TA_SLEEPRQ);
+
 			__generic_unplug_device(q);
 			spin_unlock_irq(q->queue_lock);
 			io_schedule();
@@ -2210,6 +2230,8 @@ EXPORT_SYMBOL(blk_get_request);
  */
 void blk_requeue_request(request_queue_t *q, struct request *rq)
 {
+	blk_add_trace_rq(q, rq, BLK_TA_REQUEUE);
+
 	if (blk_rq_tagged(rq))
 		blk_queue_end_tag(q, rq);
 
@@ -2844,6 +2866,8 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 			if (!q->back_merge_fn(q, req, bio))
 				break;
 
+			blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+
 			req->biotail->bi_next = bio;
 			req->biotail = bio;
 			req->nr_sectors = req->hard_nr_sectors += nr_sectors;
@@ -2859,6 +2883,8 @@ static int __make_request(request_queue_t *q, struct bio *bio)
 			if (!q->front_merge_fn(q, req, bio))
 				break;
 
+			blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+
 			bio->bi_next = req->bio;
 			req->bio = bio;
 
@@ -2976,6 +3002,7 @@ void generic_make_request(struct bio *bio)
 	request_queue_t *q;
 	sector_t maxsector;
 	int ret, nr_sectors = bio_sectors(bio);
+	dev_t old_dev;
 
 	might_sleep();
 	/* Test device or partition size, when known. */
@@ -3002,6 +3029,8 @@ void generic_make_request(struct bio *bio)
 	 * NOTE: we don't repeat the blk_size check for each new device.
 	 * Stacking drivers are expected to know what they are doing.
 	 */
+	maxsector = -1;
+	old_dev = 0;
 	do {
 		char b[BDEVNAME_SIZE];
 
@@ -3034,6 +3063,15 @@ void generic_make_request(struct bio *bio)
 		 */
 		blk_partition_remap(bio);
 
+		if (maxsector != -1)
+			blk_add_trace_remap(q, bio, old_dev, bio->bi_sector, 
+					    maxsector);
+
+		blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+
+		maxsector = bio->bi_sector;
+		old_dev = bio->bi_bdev->bd_dev;
+
 		ret = q->make_request_fn(q, bio);
 	} while (ret);
 }
@@ -3153,6 +3191,8 @@ static int __end_that_request_first(struct request *req, int uptodate,
 	int total_bytes, bio_nbytes, error, next_idx = 0;
 	struct bio *bio;
 
+	blk_add_trace_rq(req->q, req, BLK_TA_COMPLETE);
+
 	/*
 	 * extend uptodate bool to allow < 0 value to be direct io error
 	 */

drivers/block/cciss.c

@@ -38,6 +38,7 @@
 #include <linux/hdreg.h>
 #include <linux/spinlock.h>
 #include <linux/compat.h>
+#include <linux/blktrace_api.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 
@@ -2331,6 +2332,7 @@ static inline void complete_command( ctlr_info_t *h, CommandList_struct *cmd,
 
 	cmd->rq->completion_data = cmd;
 	cmd->rq->errors = status;
+	blk_add_trace_rq(cmd->rq->q, cmd->rq, BLK_TA_COMPLETE);
 	blk_complete_request(cmd->rq);
 }
 

drivers/md/dm.c

@@ -17,6 +17,7 @@
 #include <linux/mempool.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
+#include <linux/blktrace_api.h>
 
 static const char *_name = DM_NAME;
 
@@ -334,6 +335,8 @@ static void dec_pending(struct dm_io *io, int error)
 			/* nudge anyone waiting on suspend queue */
 			wake_up(&io->md->wait);
 
+		blk_add_trace_bio(io->md->queue, io->bio, BLK_TA_COMPLETE);
+
 		bio_endio(io->bio, io->bio->bi_size, io->error);
 		free_io(io->md, io);
 	}
@@ -392,6 +395,7 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		      struct target_io *tio)
 {
 	int r;
+	sector_t sector;
 
 	/*
 	 * Sanity checks.
@@ -407,10 +411,17 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 	 * this io.
 	 */
 	atomic_inc(&tio->io->io_count);
+	sector = clone->bi_sector;
 	r = ti->type->map(ti, clone, &tio->info);
-	if (r > 0)
+	if (r > 0) {
 		/* 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);
+
 		generic_make_request(clone);
+	}
 
 	else if (r < 0) {
 		/* error the io and bail out */

fs/Kconfig

@@ -859,18 +859,6 @@ config RAMFS
 	  To compile this as a module, choose M here: the module will be called
 	  ramfs.
 
-config RELAYFS_FS
-	tristate "Relayfs file system support"
-	---help---
-	  Relayfs is a high-speed data relay filesystem designed to provide
-	  an efficient mechanism for tools and facilities to relay large
-	  amounts of data from kernel space to user space.
-
-	  To compile this code as a module, choose M here: the module will be
-	  called relayfs.
-
-	  If unsure, say N.
-
 config CONFIGFS_FS
 	tristate "Userspace-driven configuration filesystem (EXPERIMENTAL)"
 	depends on EXPERIMENTAL

fs/Makefile

@@ -91,7 +91,6 @@ obj-$(CONFIG_AUTOFS4_FS)	+= autofs4/
 obj-$(CONFIG_ADFS_FS)		+= adfs/
 obj-$(CONFIG_FUSE_FS)		+= fuse/
 obj-$(CONFIG_UDF_FS)		+= udf/
-obj-$(CONFIG_RELAYFS_FS)	+= relayfs/
 obj-$(CONFIG_SUN_OPENPROMFS)	+= openpromfs/
 obj-$(CONFIG_JFS_FS)		+= jfs/
 obj-$(CONFIG_XFS_FS)		+= xfs/

fs/bio.c

@@ -25,6 +25,7 @@
 #include <linux/module.h>
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
+#include <linux/blktrace_api.h>
 #include <scsi/sg.h>		/* for struct sg_iovec */
 
 #define BIO_POOL_SIZE 256
@@ -1095,6 +1096,9 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
 	if (!bp)
 		return bp;
 
+	blk_add_trace_pdu_int(bdev_get_queue(bi->bi_bdev), BLK_TA_SPLIT, bi,
+				bi->bi_sector + first_sectors);
+
 	BUG_ON(bi->bi_vcnt != 1);
 	BUG_ON(bi->bi_idx != 0);
 	atomic_set(&bp->cnt, 3);

fs/compat_ioctl.c

@@ -72,6 +72,7 @@
 #include <linux/i2c-dev.h>
 #include <linux/wireless.h>
 #include <linux/atalk.h>
+#include <linux/blktrace_api.h>
 
 #include <net/sock.h>          /* siocdevprivate_ioctl */
 #include <net/bluetooth/bluetooth.h>

fs/relayfs/Makefile

-obj-$(CONFIG_RELAYFS_FS) += relayfs.o
-
-relayfs-y := relay.o inode.o buffers.o
-

fs/relayfs/buffers.c

-/*
- * RelayFS buffer management code.
- *
- * Copyright (C) 2002-2005 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp
- * Copyright (C) 1999-2005 - Karim Yaghmour (karim@opersys.com)
- *
- * This file is released under the GPL.
- */
-
-#include <linux/module.h>
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/relayfs_fs.h>
-#include "relay.h"
-#include "buffers.h"
-
-/*
- * close() vm_op implementation for relayfs file mapping.
- */
-static void relay_file_mmap_close(struct vm_area_struct *vma)
-{
-	struct rchan_buf *buf = vma->vm_private_data;
-	buf->chan->cb->buf_unmapped(buf, vma->vm_file);
-}
-
-/*
- * nopage() vm_op implementation for relayfs file mapping.
- */
-static struct page *relay_buf_nopage(struct vm_area_struct *vma,
-				     unsigned long address,
-				     int *type)
-{
-	struct page *page;
-	struct rchan_buf *buf = vma->vm_private_data;
-	unsigned long offset = address - vma->vm_start;
-
-	if (address > vma->vm_end)
-		return NOPAGE_SIGBUS; /* Disallow mremap */
-	if (!buf)
-		return NOPAGE_OOM;
-
-	page = vmalloc_to_page(buf->start + offset);
-	if (!page)
-		return NOPAGE_OOM;
-	get_page(page);
-
-	if (type)
-		*type = VM_FAULT_MINOR;
-
-	return page;
-}
-
-/*
- * vm_ops for relay file mappings.
- */
-static struct vm_operations_struct relay_file_mmap_ops = {
-	.nopage = relay_buf_nopage,
-	.close = relay_file_mmap_close,
-};
-
-/**
- *	relay_mmap_buf: - mmap channel buffer to process address space
- *	@buf: relay channel buffer
- *	@vma: vm_area_struct describing memory to be mapped
- *
- *	Returns 0 if ok, negative on error
- *
- *	Caller should already have grabbed mmap_sem.
- */
-int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma)
-{
-	unsigned long length = vma->vm_end - vma->vm_start;
-	struct file *filp = vma->vm_file;
-
-	if (!buf)
-		return -EBADF;
-
-	if (length != (unsigned long)buf->chan->alloc_size)
-		return -EINVAL;
-
-	vma->vm_ops = &relay_file_mmap_ops;
-	vma->vm_private_data = buf;
-	buf->chan->cb->buf_mapped(buf, filp);
-
-	return 0;
-}
-
-/**
- *	relay_alloc_buf - allocate a channel buffer
- *	@buf: the buffer struct
- *	@size: total size of the buffer
- *
- *	Returns a pointer to the resulting buffer, NULL if unsuccessful
- */
-static void *relay_alloc_buf(struct rchan_buf *buf, unsigned long size)
-{
-	void *mem;
-	unsigned int i, j, n_pages;
-
-	size = PAGE_ALIGN(size);
-	n_pages = size >> PAGE_SHIFT;
-
-	buf->page_array = kcalloc(n_pages, sizeof(struct page *), GFP_KERNEL);
-	if (!buf->page_array)
-		return NULL;
-
-	for (i = 0; i < n_pages; i++) {
-		buf->page_array[i] = alloc_page(GFP_KERNEL);
-		if (unlikely(!buf->page_array[i]))
-			goto depopulate;
-	}
-	mem = vmap(buf->page_array, n_pages, VM_MAP, PAGE_KERNEL);
-	if (!mem)
-		goto depopulate;
-
-	memset(mem, 0, size);
-	buf->page_count = n_pages;
-	return mem;
-
-depopulate:
-	for (j = 0; j < i; j++)
-		__free_page(buf->page_array[j]);
-	kfree(buf->page_array);
-	return NULL;
-}
-
-/**
- *	relay_create_buf - allocate and initialize a channel buffer
- *	@alloc_size: size of the buffer to allocate
- *	@n_subbufs: number of sub-buffers in the channel
- *
- *	Returns channel buffer if successful, NULL otherwise
- */
-struct rchan_buf *relay_create_buf(struct rchan *chan)
-{
-	struct rchan_buf *buf = kcalloc(1, sizeof(struct rchan_buf), GFP_KERNEL);
-	if (!buf)
-		return NULL;
-
-	buf->padding = kmalloc(chan->n_subbufs * sizeof(size_t *), GFP_KERNEL);
-	if (!buf->padding)
-		goto free_buf;
-
-	buf->start = relay_alloc_buf(buf, chan->alloc_size);
-	if (!buf->start)
-		goto free_buf;
-
-	buf->chan = chan;
-	kref_get(&buf->chan->kref);
-	return buf;
-
-free_buf:
-	kfree(buf->padding);
-	kfree(buf);
-	return NULL;
-}
-
-/**
- *	relay_destroy_buf - destroy an rchan_buf struct and associated buffer
- *	@buf: the buffer struct
- */
-void relay_destroy_buf(struct rchan_buf *buf)
-{
-	struct rchan *chan = buf->chan;
-	unsigned int i;
-
-	if (likely(buf->start)) {
-		vunmap(buf->start);
-		for (i = 0; i < buf->page_count; i++)
-			__free_page(buf->page_array[i]);
-		kfree(buf->page_array);
-	}
-	kfree(buf->padding);
-	kfree(buf);
-	kref_put(&chan->kref, relay_destroy_channel);
-}
-
-/**
- *	relay_remove_buf - remove a channel buffer
- *
- *	Removes the file from the relayfs fileystem, which also frees the
- *	rchan_buf_struct and the channel buffer.  Should only be called from
- *	kref_put().
- */
-void relay_remove_buf(struct kref *kref)
-{
-	struct rchan_buf *buf = container_of(kref, struct rchan_buf, kref);
-	buf->chan->cb->remove_buf_file(buf->dentry);
-	relay_destroy_buf(buf);
-}

fs/relayfs/buffers.h

-#ifndef _BUFFERS_H
-#define _BUFFERS_H
-
-/* This inspired by rtai/shmem */
-#define FIX_SIZE(x) (((x) - 1) & PAGE_MASK) + PAGE_SIZE
-
-extern int relay_mmap_buf(struct rchan_buf *buf, struct vm_area_struct *vma);
-extern struct rchan_buf *relay_create_buf(struct rchan *chan);
-extern void relay_destroy_buf(struct rchan_buf *buf);
-extern void relay_remove_buf(struct kref *kref);
-
-#endif/* _BUFFERS_H */

fs/relayfs/relay.h

-#ifndef _RELAY_H
-#define _RELAY_H
-
-extern int relayfs_remove(struct dentry *dentry);
-extern int relay_buf_empty(struct rchan_buf *buf);
-extern void relay_destroy_channel(struct kref *kref);
-
-#endif /* _RELAY_H */

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
 	 */

include/linux/blktrace_api.h

+#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

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 */

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 */

include/linux/relay.h

+/*
+ * linux/include/linux/relay.h
+ *
+ * Copyright (C) 2002, 2003 - Tom Zanussi (zanussi@us.ibm.com), IBM Corp
+ * Copyright (C) 1999, 2000, 2001, 2002 - Karim Yaghmour (karim@opersys.com)
+ *
+ * CONFIG_RELAY definitions and declarations
+ */
+
+#ifndef _LINUX_RELAY_H
+#define _LINUX_RELAY_H
+
+#include <linux/config.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/list.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/kref.h>
+
+/* Needs a _much_ better name... */
+#define FIX_SIZE(x) ((((x) - 1) & PAGE_MASK) + PAGE_SIZE)
+
+/*
+ * Tracks changes to rchan/rchan_buf structs
+ */
+#define RELAYFS_CHANNEL_VERSION		6
+
+/*
+ * Per-cpu relay channel buffer
+ */
+struct rchan_buf
+{
+	void *start;			/* start of channel buffer */
+	void *data;			/* start of current sub-buffer */
+	size_t offset;			/* current offset into sub-buffer */
+	size_t subbufs_produced;	/* count of sub-buffers produced */
+	size_t subbufs_consumed;	/* count of sub-buffers consumed */
+	struct rchan *chan;		/* associated channel */
+	wait_queue_head_t read_wait;	/* reader wait queue */
+	struct work_struct wake_readers; /* reader wake-up work struct */
+	struct dentry *dentry;		/* channel file dentry */
+	struct kref kref;		/* channel buffer refcount */
+	struct page **page_array;	/* array of current buffer pages */
+	unsigned int page_count;	/* number of current buffer pages */
+	unsigned int finalized;		/* buffer has been finalized */
+	size_t *padding;		/* padding counts per sub-buffer */
+	size_t prev_padding;		/* temporary variable */
+	size_t bytes_consumed;		/* bytes consumed in cur read subbuf */
+	unsigned int cpu;		/* this buf's cpu */
+} ____cacheline_aligned;
+
+/*
+ * Relay channel data structure
+ */
+struct rchan
+{
+	u32 version;			/* the version of this struct */
+	size_t subbuf_size;		/* sub-buffer size */
+	size_t n_subbufs;		/* number of sub-buffers per buffer */
+	size_t alloc_size;		/* total buffer size allocated */
+	struct rchan_callbacks *cb;	/* client callbacks */
+	struct kref kref;		/* channel refcount */
+	void *private_data;		/* for user-defined data */
+	size_t last_toobig;		/* tried to log event > subbuf size */
+	struct rchan_buf *buf[NR_CPUS]; /* per-cpu channel buffers */
+};
+
+/*
+ * Relay channel client callbacks
+ */
+struct rchan_callbacks
+{
+	/*
+	 * subbuf_start - called on buffer-switch to a new sub-buffer
+	 * @buf: the channel buffer containing the new sub-buffer
+	 * @subbuf: the start of the new sub-buffer
+	 * @prev_subbuf: the start of the previous sub-buffer
+	 * @prev_padding: unused space at the end of previous sub-buffer
+	 *
+	 * The client should return 1 to continue logging, 0 to stop
+	 * logging.
+	 *
+	 * NOTE: subbuf_start will also be invoked when the buffer is
+	 *       created, so that the first sub-buffer can be initialized
+	 *       if necessary.  In this case, prev_subbuf will be NULL.
+	 *
+	 * NOTE: the client can reserve bytes at the beginning of the new
+	 *       sub-buffer by calling subbuf_start_reserve() in this callback.
+	 */
+	int (*subbuf_start) (struct rchan_buf *buf,
+			     void *subbuf,
+			     void *prev_subbuf,
+			     size_t prev_padding);
+
+	/*
+	 * buf_mapped - relay buffer mmap notification
+	 * @buf: the channel buffer
+	 * @filp: relay file pointer
+	 *
+	 * Called when a relay file is successfully mmapped
+	 */
+        void (*buf_mapped)(struct rchan_buf *buf,
+			   struct file *filp);
+
+	/*
+	 * buf_unmapped - relay buffer unmap notification
+	 * @buf: the channel buffer
+	 * @filp: relay file pointer
+	 *
+	 * Called when a relay file is successfully unmapped
+	 */
+        void (*buf_unmapped)(struct rchan_buf *buf,
+			     struct file *filp);
+	/*
+	 * create_buf_file - create file to represent a relay channel buffer
+	 * @filename: the name of the file to create
+	 * @parent: the parent of the file to create
+	 * @mode: the mode of the file to create
+	 * @buf: the channel buffer
+	 * @is_global: outparam - set non-zero if the buffer should be global
+	 *
+	 * Called during relay_open(), once for each per-cpu buffer,
+	 * to allow the client to create a file to be used to
+	 * represent the corresponding channel buffer.  If the file is
+	 * created outside of relay, the parent must also exist in
+	 * that filesystem.
+	 *
+	 * The callback should return the dentry of the file created
+	 * to represent the relay buffer.
+	 *
+	 * Setting the is_global outparam to a non-zero value will
+	 * cause relay_open() to create a single global buffer rather
+	 * than the default set of per-cpu buffers.
+	 *
+	 * See Documentation/filesystems/relayfs.txt for more info.
+	 */
+	struct dentry *(*create_buf_file)(const char *filename,
+					  struct dentry *parent,
+					  int mode,
+					  struct rchan_buf *buf,
+					  int *is_global);
+
+	/*
+	 * remove_buf_file - remove file representing a relay channel buffer
+	 * @dentry: the dentry of the file to remove
+	 *
+	 * Called during relay_close(), once for each per-cpu buffer,
+	 * to allow the client to remove a file used to represent a
+	 * channel buffer.
+	 *
+	 * The callback should return 0 if successful, negative if not.
+	 */
+	int (*remove_buf_file)(struct dentry *dentry);
+};
+
+/*
+ * CONFIG_RELAY kernel API, kernel/relay.c
+ */
+
+struct rchan *relay_open(const char *base_filename,
+			 struct dentry *parent,
+			 size_t subbuf_size,
+			 size_t n_subbufs,
+			 struct rchan_callbacks *cb);
+extern void relay_close(struct rchan *chan);
+extern void relay_flush(struct rchan *chan);
+extern void relay_subbufs_consumed(struct rchan *chan,
+				   unsigned int cpu,
+				   size_t consumed);
+extern void relay_reset(struct rchan *chan);
+extern int relay_buf_full(struct rchan_buf *buf);
+
+extern size_t relay_switch_subbuf(struct rchan_buf *buf,
+				  size_t length);
+
+/**
+ *	relay_write - write data into the channel
+ *	@chan: relay channel
+ *	@data: data to be written
+ *	@length: number of bytes to write
+ *
+ *	Writes data into the current cpu's channel buffer.
+ *
+ *	Protects the buffer by disabling interrupts.  Use this
+ *	if you might be logging from interrupt context.  Try
+ *	__relay_write() if you know you	won't be logging from
+ *	interrupt context.
+ */
+static inline void relay_write(struct rchan *chan,
+			       const void *data,
+			       size_t length)
+{
+	unsigned long flags;
+	struct rchan_buf *buf;
+
+	local_irq_save(flags);
+	buf = chan->buf[smp_processor_id()];
+	if (unlikely(buf->offset + length > chan->subbuf_size))
+		length = relay_switch_subbuf(buf, length);
+	memcpy(buf->data + buf->offset, data, length);
+	buf->offset += length;
+	local_irq_restore(flags);
+}
+
+/**
+ *	__relay_write - write data into the channel
+ *	@chan: relay channel
+ *	@data: data to be written
+ *	@length: number of bytes to write
+ *
+ *	Writes data into the current cpu's channel buffer.
+ *
+ *	Protects the buffer by disabling preemption.  Use
+ *	relay_write() if you might be logging from interrupt
+ *	context.
+ */
+static inline void __relay_write(struct rchan *chan,
+				 const void *data,
+				 size_t length)
+{
+	struct rchan_buf *buf;
+
+	buf = chan->buf[get_cpu()];
+	if (unlikely(buf->offset + length > buf->chan->subbuf_size))
+		length = relay_switch_subbuf(buf, length);
+	memcpy(buf->data + buf->offset, data, length);
+	buf->offset += length;
+	put_cpu();
+}
+
+/**
+ *	relay_reserve - reserve slot in channel buffer
+ *	@chan: relay channel
+ *	@length: number of bytes to reserve
+ *
+ *	Returns pointer to reserved slot, NULL if full.
+ *
+ *	Reserves a slot in the current cpu's channel buffer.
+ *	Does not protect the buffer at all - caller must provide
+ *	appropriate synchronization.
+ */
+static inline void *relay_reserve(struct rchan *chan, size_t length)
+{
+	void *reserved;
+	struct rchan_buf *buf = chan->buf[smp_processor_id()];
+
+	if (unlikely(buf->offset + length > buf->chan->subbuf_size)) {
+		length = relay_switch_subbuf(buf, length);
+		if (!length)
+			return NULL;
+	}
+	reserved = buf->data + buf->offset;
+	buf->offset += length;
+
+	return reserved;
+}
+
+/**
+ *	subbuf_start_reserve - reserve bytes at the start of a sub-buffer
+ *	@buf: relay channel buffer
+ *	@length: number of bytes to reserve
+ *
+ *	Helper function used to reserve bytes at the beginning of
+ *	a sub-buffer in the subbuf_start() callback.
+ */
+static inline void subbuf_start_reserve(struct rchan_buf *buf,
+					size_t length)
+{
+	BUG_ON(length >= buf->chan->subbuf_size - 1);
+	buf->offset = length;
+}
+
+/*
+ * exported relay file operations, kernel/relay.c
+ */
+extern struct file_operations relay_file_operations;
+
+#endif /* _LINUX_RELAY_H */
+

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;

init/Kconfig

@@ -214,6 +214,17 @@ config CPUSETS
 
 	  Say N if unsure.
 
+config RELAY
+	bool "Kernel->user space relay support (formerly relayfs)"
+	help
+	  This option enables support for relay interface support in
+	  certain file systems (such as debugfs).
+	  It is designed to provide an efficient mechanism for tools and
+	  facilities to relay large amounts of data from kernel space to
+	  user space.
+
+	  If unsure, say N.
+
 source "usr/Kconfig"
 
 config UID16

kernel/Makefile

@@ -34,6 +34,7 @@ obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
 obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
+obj-$(CONFIG_RELAY) += relay.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/fork.c

@@ -181,6 +181,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	/* One for us, one for whoever does the "release_task()" (usually parent) */
 	atomic_set(&tsk->usage,2);
 	atomic_set(&tsk->fs_excl, 0);
+	tsk->btrace_seq = 0;
 	return tsk;
 }
 

mm/highmem.c

@@ -26,6 +26,7 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
+#include <linux/blktrace_api.h>
 #include <asm/tlbflush.h>
 
 static mempool_t *page_pool, *isa_page_pool;
@@ -483,6 +484,8 @@ void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
 		pool = isa_page_pool;
 	}
 
+	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+
 	/*
 	 * slow path
 	 */