Creation of Cybook 2416 (actually Gen4) repository

block/Kconfig

@@ -0,0 +1,54 @@
+#
+# Block layer core configuration
+#
+config BLOCK
+       bool "Enable the block layer" if EMBEDDED
+       default y
+       help
+	 This permits the block layer to be removed from the kernel if it's not
+	 needed (on some embedded devices for example).  If this option is
+	 disabled, then blockdev files will become unusable and some
+	 filesystems (such as ext3) will become unavailable.
+
+	 This option will also disable SCSI character devices and USB storage
+	 since they make use of various block layer definitions and
+	 facilities.
+
+	 Say Y here unless you know you really don't want to mount disks and
+	 suchlike.
+
+if BLOCK
+
+config LBD
+	bool "Support for Large Block Devices"
+	depends on !64BIT
+	help
+	  Say Y here if you want to attach large (bigger than 2TB) discs to
+	  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"
+	depends on SYSFS
+	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
+
+config LSF
+	bool "Support for Large Single Files"
+	depends on !64BIT
+	help
+	  Say Y here if you want to be able to handle very large files (bigger
+	  than 2TB), otherwise say N.
+
+	  If unsure, say Y.
+
+endif
+
+source block/Kconfig.iosched

block/Kconfig.iosched

@@ -0,0 +1,73 @@
+if BLOCK
+
+menu "IO Schedulers"
+
+config IOSCHED_NOOP
+	bool
+	default y
+	---help---
+	  The no-op I/O scheduler is a minimal scheduler that does basic merging
+	  and sorting. Its main uses include non-disk based block devices like
+	  memory devices, and specialised software or hardware environments
+	  that do their own scheduling and require only minimal assistance from
+	  the kernel.
+
+config IOSCHED_AS
+	tristate "Anticipatory I/O scheduler"
+	default y
+	---help---
+	  The anticipatory I/O scheduler is generally a good choice for most
+	  environments, but is quite large and complex when compared to the
+	  deadline I/O scheduler, it can also be slower in some cases
+	  especially some database loads.
+
+config IOSCHED_DEADLINE
+	tristate "Deadline I/O scheduler"
+	default y
+	---help---
+	  The deadline I/O scheduler is simple and compact, and is often as
+	  good as the anticipatory I/O scheduler, and in some database
+	  workloads, better. In the case of a single process performing I/O to
+	  a disk at any one time, its behaviour is almost identical to the
+	  anticipatory I/O scheduler and so is a good choice.
+
+config IOSCHED_CFQ
+	tristate "CFQ I/O scheduler"
+	default y
+	---help---
+	  The CFQ I/O scheduler tries to distribute bandwidth equally
+	  among all processes in the system. It should provide a fair
+	  working environment, suitable for desktop systems.
+	  This is the default I/O scheduler.
+
+choice
+	prompt "Default I/O scheduler"
+	default DEFAULT_CFQ
+	help
+	  Select the I/O scheduler which will be used by default for all
+	  block devices.
+
+	config DEFAULT_AS
+		bool "Anticipatory" if IOSCHED_AS=y
+
+	config DEFAULT_DEADLINE
+		bool "Deadline" if IOSCHED_DEADLINE=y
+
+	config DEFAULT_CFQ
+		bool "CFQ" if IOSCHED_CFQ=y
+
+	config DEFAULT_NOOP
+		bool "No-op"
+
+endchoice
+
+config DEFAULT_IOSCHED
+	string
+	default "anticipatory" if DEFAULT_AS
+	default "deadline" if DEFAULT_DEADLINE
+	default "cfq" if DEFAULT_CFQ
+	default "noop" if DEFAULT_NOOP
+
+endmenu
+
+endif

block/Makefile

@@ -0,0 +1,12 @@
+#
+# Makefile for the kernel block layer
+#
+
+obj-$(CONFIG_BLOCK) := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o
+
+obj-$(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/blktrace.c

@@ -0,0 +1,562 @@
+/*
+ * 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
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blktrace_api.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/debugfs.h>
+#include <linux/time.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;
+
+/*
+ * Send out a notify message.
+ */
+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) + len);
+	if (t) {
+		const int cpu = smp_processor_id();
+
+		t->magic = BLK_IO_TRACE_MAGIC | BLK_IO_TRACE_VERSION;
+		t->time = sched_clock() - per_cpu(blk_trace_cpu_offset, cpu);
+		t->device = bt->dev;
+		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);
+}
+
+static int act_log_check(struct blk_trace *bt, u32 what, sector_t sector,
+			 pid_t pid)
+{
+	if (((bt->act_mask << BLK_TC_SHIFT) & what) == 0)
+		return 1;
+	if (sector < bt->start_lba || sector > bt->end_lba)
+		return 1;
+	if (bt->pid && pid != bt->pid)
+		return 1;
+
+	return 0;
+}
+
+/*
+ * Data direction bit lookup
+ */
+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[9] __read_mostly = { 0, BLK_TC_ACT(BLK_TC_BARRIER), BLK_TC_ACT(BLK_TC_SYNC), 0, BLK_TC_ACT(BLK_TC_AHEAD), 0, 0, 0, BLK_TC_ACT(BLK_TC_META) };
+
+/*
+ * 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)) << (2 - BIO_RW_AHEAD))
+#define trace_meta_bit(rw)	\
+	(((rw) & (1 << BIO_RW_META)) >> (BIO_RW_META - 3))
+
+/*
+ * 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,
+		     int rw, u32 what, int error, int pdu_len, void *pdu_data)
+{
+	struct task_struct *tsk = current;
+	struct blk_io_trace *t;
+	unsigned long flags;
+	unsigned long *sequence;
+	pid_t pid;
+	int cpu;
+
+	if (unlikely(bt->trace_state != Blktrace_running))
+		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 |= bio_act[trace_meta_bit(rw)];
+
+	pid = tsk->pid;
+	if (unlikely(act_log_check(bt, what, sector, pid)))
+		return;
+
+	/*
+	 * 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
+	 */
+	local_irq_save(flags);
+
+	if (unlikely(tsk->btrace_seq != blktrace_seq))
+		trace_note_tsk(bt, tsk);
+
+	t = relay_reserve(bt->rchan, sizeof(*t) + pdu_len);
+	if (t) {
+		cpu = smp_processor_id();
+		sequence = per_cpu_ptr(bt->sequence, cpu);
+
+		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->sector = sector;
+		t->bytes = bytes;
+		t->action = what;
+		t->pid = pid;
+		t->device = bt->dev;
+		t->cpu = cpu;
+		t->error = error;
+		t->pdu_len = pdu_len;
+
+		if (pdu_len)
+			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
+	}
+
+	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 void blk_trace_cleanup(struct blk_trace *bt)
+{
+	relay_close(bt->rchan);
+	debugfs_remove(bt->dropped_file);
+	blk_remove_tree(bt->dir);
+	free_percpu(bt->sequence);
+	kfree(bt);
+}
+
+static int blk_trace_remove(request_queue_t *q)
+{
+	struct blk_trace *bt;
+
+	bt = xchg(&q->blk_trace, NULL);
+	if (!bt)
+		return -EINVAL;
+
+	if (bt->trace_state == Blktrace_setup ||
+	    bt->trace_state == Blktrace_stopped)
+		blk_trace_cleanup(bt);
+
+	return 0;
+}
+
+static int blk_dropped_open(struct inode *inode, struct file *filp)
+{
+	filp->private_data = inode->i_private;
+
+	return 0;
+}
+
+static ssize_t blk_dropped_read(struct file *filp, char __user *buffer,
+				size_t count, loff_t *ppos)
+{
+	struct blk_trace *bt = filp->private_data;
+	char buf[16];
+
+	snprintf(buf, sizeof(buf), "%u\n", atomic_read(&bt->dropped));
+
+	return simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf));
+}
+
+static const struct file_operations blk_dropped_fops = {
+	.owner =	THIS_MODULE,
+	.open =		blk_dropped_open,
+	.read =		blk_dropped_read,
+};
+
+/*
+ * 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_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
+				     void *prev_subbuf, size_t prev_padding)
+{
+	struct blk_trace *bt;
+
+	if (!relay_buf_full(buf))
+		return 1;
+
+	bt = buf->chan->private_data;
+	atomic_inc(&bt->dropped);
+	return 0;
+}
+
+static int blk_remove_buf_file_callback(struct dentry *dentry)
+{
+	debugfs_remove(dentry);
+	return 0;
+}
+
+static struct dentry *blk_create_buf_file_callback(const char *filename,
+						   struct dentry *parent,
+						   int mode,
+						   struct rchan_buf *buf,
+						   int *is_global)
+{
+	return debugfs_create_file(filename, mode, parent, buf,
+					&relay_file_operations);
+}
+
+static struct rchan_callbacks blk_relay_callbacks = {
+	.subbuf_start		= blk_subbuf_start_callback,
+	.create_buf_file	= blk_create_buf_file_callback,
+	.remove_buf_file	= blk_remove_buf_file_callback,
+};
+
+/*
+ * Setup everything required to start tracing
+ */
+static int blk_trace_setup(request_queue_t *q, struct block_device *bdev,
+			   char __user *arg)
+{
+	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)
+		return -EINVAL;
+
+	strcpy(buts.name, bdevname(bdev, b));
+
+	/*
+	 * 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;
+
+	ret = -ENOMEM;
+	bt = kzalloc(sizeof(*bt), GFP_KERNEL);
+	if (!bt)
+		goto err;
+
+	bt->sequence = alloc_percpu(unsigned long);
+	if (!bt->sequence)
+		goto err;
+
+	ret = -ENOENT;
+	dir = blk_create_tree(buts.name);
+	if (!dir)
+		goto err;
+
+	bt->dir = dir;
+	bt->dev = bdev->bd_dev;
+	atomic_set(&bt->dropped, 0);
+
+	ret = -EIO;
+	bt->dropped_file = debugfs_create_file("dropped", 0444, dir, bt, &blk_dropped_fops);
+	if (!bt->dropped_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->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;
+	if (!bt->end_lba)
+		bt->end_lba = -1ULL;
+
+	bt->pid = buts.pid;
+	bt->trace_state = Blktrace_setup;
+
+	ret = -EBUSY;
+	old_bt = xchg(&q->blk_trace, bt);
+	if (old_bt) {
+		(void) xchg(&q->blk_trace, old_bt);
+		goto err;
+	}
+
+	return 0;
+err:
+	if (dir)
+		blk_remove_tree(dir);
+	if (bt) {
+		if (bt->dropped_file)
+			debugfs_remove(bt->dropped_file);
+		free_percpu(bt->sequence);
+		if (bt->rchan)
+			relay_close(bt->rchan);
+		kfree(bt);
+	}
+	return ret;
+}
+
+static int blk_trace_startstop(request_queue_t *q, int start)
+{
+	struct blk_trace *bt;
+	int ret;
+
+	if ((bt = q->blk_trace) == NULL)
+		return -EINVAL;
+
+	/*
+	 * For starting a trace, we can transition from a setup or stopped
+	 * trace. For stopping a trace, the state must be running
+	 */
+	ret = -EINVAL;
+	if (start) {
+		if (bt->trace_state == Blktrace_setup ||
+		    bt->trace_state == Blktrace_stopped) {
+			blktrace_seq++;
+			smp_mb();
+			bt->trace_state = Blktrace_running;
+
+			trace_note_time(bt);
+			ret = 0;
+		}
+	} else {
+		if (bt->trace_state == Blktrace_running) {
+			bt->trace_state = Blktrace_stopped;
+			relay_flush(bt->rchan);
+			ret = 0;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * blk_trace_ioctl: - handle the ioctls associated with tracing
+ * @bdev:	the block device
+ * @cmd: 	the ioctl cmd
+ * @arg:	the argument data, if any
+ *
+ **/
+int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
+{
+	request_queue_t *q;
+	int ret, start = 0;
+
+	q = bdev_get_queue(bdev);
+	if (!q)
+		return -ENXIO;
+
+	mutex_lock(&bdev->bd_mutex);
+
+	switch (cmd) {
+	case BLKTRACESETUP:
+		ret = blk_trace_setup(q, bdev, arg);
+		break;
+	case BLKTRACESTART:
+		start = 1;
+	case BLKTRACESTOP:
+		ret = blk_trace_startstop(q, start);
+		break;
+	case BLKTRACETEARDOWN:
+		ret = blk_trace_remove(q);
+		break;
+	default:
+		ret = -ENOTTY;
+		break;
+	}
+
+	mutex_unlock(&bdev->bd_mutex);
+	return ret;
+}
+
+/**
+ * blk_trace_shutdown: - stop and cleanup trace structures
+ * @q:    the request queue associated with the device
+ *
+ **/
+void blk_trace_shutdown(request_queue_t *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
+ */
+static void blk_check_time(unsigned long long *t)
+{
+	unsigned long long a, b;
+	struct timeval tv;
+
+	a = sched_clock();
+	do_gettimeofday(&tv);
+	b = sched_clock();
+
+	*t = tv.tv_sec * 1000000000 + tv.tv_usec * 1000;
+	*t -= (a + b) / 2;
+}
+
+/*
+ * calibrate our inter-CPU timings
+ */
+static void blk_trace_check_cpu_time(void *data)
+{
+	unsigned long long *t;
+	int cpu = get_cpu();
+
+	t = &per_cpu(blk_trace_cpu_offset, cpu);
+
+	/*
+	 * 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);
+
+	put_cpu();
+}
+
+static void blk_trace_set_ht_offsets(void)
+{
+#if defined(CONFIG_SCHED_SMT)
+	int cpu, i;
+
+	/*
+	 * now make sure HT siblings have the same time offset
+	 */
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		unsigned long long *cpu_off, *sibling_off;
+
+		for_each_cpu_mask(i, cpu_sibling_map[cpu]) {
+			if (i == cpu)
+				continue;
+
+			cpu_off = &per_cpu(blk_trace_cpu_offset, cpu);
+			sibling_off = &per_cpu(blk_trace_cpu_offset, i);
+			*sibling_off = *cpu_off;
+		}
+	}
+	preempt_enable();
+#endif
+}
+
+static __init int blk_trace_init(void)
+{
+	mutex_init(&blk_tree_mutex);
+	on_each_cpu(blk_trace_check_cpu_time, NULL, 1, 1);
+	blk_trace_set_ht_offsets();
+
+	return 0;
+}
+
+module_init(blk_trace_init);
+

block/deadline-iosched.c

@@ -0,0 +1,485 @@
+/*
+ *  Deadline i/o scheduler.
+ *
+ *  Copyright (C) 2002 Jens Axboe <axboe@kernel.dk>
+ */
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * See Documentation/block/deadline-iosched.txt
+ */
+static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
+static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
+static const int writes_starved = 2;    /* max times reads can starve a write */
+static const int fifo_batch = 16;       /* # of sequential requests treated as one
+				     by the above parameters. For throughput. */
+
+struct deadline_data {
+	/*
+	 * run time data
+	 */
+
+	/*
+	 * requests (deadline_rq s) are present on both sort_list and fifo_list
+	 */
+	struct rb_root sort_list[2];	
+	struct list_head fifo_list[2];
+	
+	/*
+	 * next in sort order. read, write or both are NULL
+	 */
+	struct request *next_rq[2];
+	unsigned int batching;		/* number of sequential requests made */
+	sector_t last_sector;		/* head position */
+	unsigned int starved;		/* times reads have starved writes */
+
+	/*
+	 * settings that change how the i/o scheduler behaves
+	 */
+	int fifo_expire[2];
+	int fifo_batch;
+	int writes_starved;
+	int front_merges;
+};
+
+static void deadline_move_request(struct deadline_data *, struct request *);
+
+#define RQ_RB_ROOT(dd, rq)	(&(dd)->sort_list[rq_data_dir((rq))])
+
+static void
+deadline_add_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	struct rb_root *root = RQ_RB_ROOT(dd, rq);
+	struct request *__alias;
+
+retry:
+	__alias = elv_rb_add(root, rq);
+	if (unlikely(__alias)) {
+		deadline_move_request(dd, __alias);
+		goto retry;
+	}
+}
+
+static inline void
+deadline_del_rq_rb(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+
+	if (dd->next_rq[data_dir] == rq) {
+		struct rb_node *rbnext = rb_next(&rq->rb_node);
+
+		dd->next_rq[data_dir] = NULL;
+		if (rbnext)
+			dd->next_rq[data_dir] = rb_entry_rq(rbnext);
+	}
+
+	elv_rb_del(RQ_RB_ROOT(dd, rq), rq);
+}
+
+/*
+ * add rq to rbtree and fifo
+ */
+static void
+deadline_add_request(struct request_queue *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	const int data_dir = rq_data_dir(rq);
+
+	deadline_add_rq_rb(dd, rq);
+
+	/*
+	 * set expire time (only used for reads) and add to fifo list
+	 */
+	rq_set_fifo_time(rq, jiffies + dd->fifo_expire[data_dir]);
+	list_add_tail(&rq->queuelist, &dd->fifo_list[data_dir]);
+}
+
+/*
+ * remove rq from rbtree and fifo.
+ */
+static void deadline_remove_request(request_queue_t *q, struct request *rq)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	rq_fifo_clear(rq);
+	deadline_del_rq_rb(dd, rq);
+}
+
+static int
+deadline_merge(request_queue_t *q, struct request **req, struct bio *bio)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	struct request *__rq;
+	int ret;
+
+	/*
+	 * check for front merge
+	 */
+	if (dd->front_merges) {
+		sector_t sector = bio->bi_sector + bio_sectors(bio);
+
+		__rq = elv_rb_find(&dd->sort_list[bio_data_dir(bio)], sector);
+		if (__rq) {
+			BUG_ON(sector != __rq->sector);
+
+			if (elv_rq_merge_ok(__rq, bio)) {
+				ret = ELEVATOR_FRONT_MERGE;
+				goto out;
+			}
+		}
+	}
+
+	return ELEVATOR_NO_MERGE;
+out:
+	*req = __rq;
+	return ret;
+}
+
+static void deadline_merged_request(request_queue_t *q, struct request *req,
+				    int type)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	/*
+	 * if the merge was a front merge, we need to reposition request
+	 */
+	if (type == ELEVATOR_FRONT_MERGE) {
+		elv_rb_del(RQ_RB_ROOT(dd, req), req);
+		deadline_add_rq_rb(dd, req);
+	}
+}
+
+static void
+deadline_merged_requests(request_queue_t *q, struct request *req,
+			 struct request *next)
+{
+	/*
+	 * if next expires before rq, assign its expire time to rq
+	 * and move into next position (next will be deleted) in fifo
+	 */
+	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
+		if (time_before(rq_fifo_time(next), rq_fifo_time(req))) {
+			list_move(&req->queuelist, &next->queuelist);
+			rq_set_fifo_time(req, rq_fifo_time(next));
+		}
+	}
+
+	/*
+	 * kill knowledge of next, this one is a goner
+	 */
+	deadline_remove_request(q, next);
+}
+
+/*
+ * move request from sort list to dispatch queue.
+ */
+static inline void
+deadline_move_to_dispatch(struct deadline_data *dd, struct request *rq)
+{
+	request_queue_t *q = rq->q;
+
+	deadline_remove_request(q, rq);
+	elv_dispatch_add_tail(q, rq);
+}
+
+/*
+ * move an entry to dispatch queue
+ */
+static void
+deadline_move_request(struct deadline_data *dd, struct request *rq)
+{
+	const int data_dir = rq_data_dir(rq);
+	struct rb_node *rbnext = rb_next(&rq->rb_node);
+
+	dd->next_rq[READ] = NULL;
+	dd->next_rq[WRITE] = NULL;
+
+	if (rbnext)
+		dd->next_rq[data_dir] = rb_entry_rq(rbnext);
+	
+	dd->last_sector = rq->sector + rq->nr_sectors;
+
+	/*
+	 * take it off the sort and fifo list, move
+	 * to dispatch queue
+	 */
+	deadline_move_to_dispatch(dd, rq);
+}
+
+/*
+ * deadline_check_fifo returns 0 if there are no expired reads on the fifo,
+ * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
+ */
+static inline int deadline_check_fifo(struct deadline_data *dd, int ddir)
+{
+	struct request *rq = rq_entry_fifo(dd->fifo_list[ddir].next);
+
+	/*
+	 * rq is expired!
+	 */
+	if (time_after(jiffies, rq_fifo_time(rq)))
+		return 1;
+
+	return 0;
+}
+
+/*
+ * deadline_dispatch_requests selects the best request according to
+ * read/write expire, fifo_batch, etc
+ */
+static int deadline_dispatch_requests(request_queue_t *q, int force)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+	const int reads = !list_empty(&dd->fifo_list[READ]);
+	const int writes = !list_empty(&dd->fifo_list[WRITE]);
+	struct request *rq;
+	int data_dir;
+
+	/*
+	 * batches are currently reads XOR writes
+	 */
+	if (dd->next_rq[WRITE])
+		rq = dd->next_rq[WRITE];
+	else
+		rq = dd->next_rq[READ];
+
+	if (rq) {
+		/* we have a "next request" */
+		
+		if (dd->last_sector != rq->sector)
+			/* end the batch on a non sequential request */
+			dd->batching += dd->fifo_batch;
+		
+		if (dd->batching < dd->fifo_batch)
+			/* we are still entitled to batch */
+			goto dispatch_request;
+	}
+
+	/*
+	 * at this point we are not running a batch. select the appropriate
+	 * data direction (read / write)
+	 */
+
+	if (reads) {
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[READ]));
+
+		if (writes && (dd->starved++ >= dd->writes_starved))
+			goto dispatch_writes;
+
+		data_dir = READ;
+
+		goto dispatch_find_request;
+	}
+
+	/*
+	 * there are either no reads or writes have been starved
+	 */
+
+	if (writes) {
+dispatch_writes:
+		BUG_ON(RB_EMPTY_ROOT(&dd->sort_list[WRITE]));
+
+		dd->starved = 0;
+
+		data_dir = WRITE;
+
+		goto dispatch_find_request;
+	}
+
+	return 0;
+
+dispatch_find_request:
+	/*
+	 * we are not running a batch, find best request for selected data_dir
+	 */
+	if (deadline_check_fifo(dd, data_dir)) {
+		/* An expired request exists - satisfy it */
+		dd->batching = 0;
+		rq = rq_entry_fifo(dd->fifo_list[data_dir].next);
+		
+	} else if (dd->next_rq[data_dir]) {
+		/*
+		 * The last req was the same dir and we have a next request in
+		 * sort order. No expired requests so continue on from here.
+		 */
+		rq = dd->next_rq[data_dir];
+	} else {
+		struct rb_node *node;
+		/*
+		 * The last req was the other direction or we have run out of
+		 * higher-sectored requests. Go back to the lowest sectored
+		 * request (1 way elevator) and start a new batch.
+		 */
+		dd->batching = 0;
+		node = rb_first(&dd->sort_list[data_dir]);
+		if (node)
+			rq = rb_entry_rq(node);
+	}
+
+dispatch_request:
+	/*
+	 * rq is the selected appropriate request.
+	 */
+	dd->batching++;
+	deadline_move_request(dd, rq);
+
+	return 1;
+}
+
+static int deadline_queue_empty(request_queue_t *q)
+{
+	struct deadline_data *dd = q->elevator->elevator_data;
+
+	return list_empty(&dd->fifo_list[WRITE])
+		&& list_empty(&dd->fifo_list[READ]);
+}
+
+static void deadline_exit_queue(elevator_t *e)
+{
+	struct deadline_data *dd = e->elevator_data;
+
+	BUG_ON(!list_empty(&dd->fifo_list[READ]));
+	BUG_ON(!list_empty(&dd->fifo_list[WRITE]));
+
+	kfree(dd);
+}
+
+/*
+ * initialize elevator private data (deadline_data).
+ */
+static void *deadline_init_queue(request_queue_t *q)
+{
+	struct deadline_data *dd;
+
+	dd = kmalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
+	if (!dd)
+		return NULL;
+	memset(dd, 0, sizeof(*dd));
+
+	INIT_LIST_HEAD(&dd->fifo_list[READ]);
+	INIT_LIST_HEAD(&dd->fifo_list[WRITE]);
+	dd->sort_list[READ] = RB_ROOT;
+	dd->sort_list[WRITE] = RB_ROOT;
+	dd->fifo_expire[READ] = read_expire;
+	dd->fifo_expire[WRITE] = write_expire;
+	dd->writes_starved = writes_starved;
+	dd->front_merges = 1;
+	dd->fifo_batch = fifo_batch;
+	return dd;
+}
+
+/*
+ * sysfs parts below
+ */
+
+static ssize_t
+deadline_var_show(int var, char *page)
+{
+	return sprintf(page, "%d\n", var);
+}
+
+static ssize_t
+deadline_var_store(int *var, const char *page, size_t count)
+{
+	char *p = (char *) page;
+
+	*var = simple_strtol(p, &p, 10);
+	return count;
+}
+
+#define SHOW_FUNCTION(__FUNC, __VAR, __CONV)				\
+static ssize_t __FUNC(elevator_t *e, char *page)			\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data = __VAR;						\
+	if (__CONV)							\
+		__data = jiffies_to_msecs(__data);			\
+	return deadline_var_show(__data, (page));			\
+}
+SHOW_FUNCTION(deadline_read_expire_show, dd->fifo_expire[READ], 1);
+SHOW_FUNCTION(deadline_write_expire_show, dd->fifo_expire[WRITE], 1);
+SHOW_FUNCTION(deadline_writes_starved_show, dd->writes_starved, 0);
+SHOW_FUNCTION(deadline_front_merges_show, dd->front_merges, 0);
+SHOW_FUNCTION(deadline_fifo_batch_show, dd->fifo_batch, 0);
+#undef SHOW_FUNCTION
+
+#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
+static ssize_t __FUNC(elevator_t *e, const char *page, size_t count)	\
+{									\
+	struct deadline_data *dd = e->elevator_data;			\
+	int __data;							\
+	int ret = deadline_var_store(&__data, (page), count);		\
+	if (__data < (MIN))						\
+		__data = (MIN);						\
+	else if (__data > (MAX))					\
+		__data = (MAX);						\
+	if (__CONV)							\
+		*(__PTR) = msecs_to_jiffies(__data);			\
+	else								\
+		*(__PTR) = __data;					\
+	return ret;							\
+}
+STORE_FUNCTION(deadline_read_expire_store, &dd->fifo_expire[READ], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_write_expire_store, &dd->fifo_expire[WRITE], 0, INT_MAX, 1);
+STORE_FUNCTION(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX, 0);
+STORE_FUNCTION(deadline_front_merges_store, &dd->front_merges, 0, 1, 0);
+STORE_FUNCTION(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX, 0);
+#undef STORE_FUNCTION
+
+#define DD_ATTR(name) \
+	__ATTR(name, S_IRUGO|S_IWUSR, deadline_##name##_show, \
+				      deadline_##name##_store)
+
+static struct elv_fs_entry deadline_attrs[] = {
+	DD_ATTR(read_expire),
+	DD_ATTR(write_expire),
+	DD_ATTR(writes_starved),
+	DD_ATTR(front_merges),
+	DD_ATTR(fifo_batch),
+	__ATTR_NULL
+};
+
+static struct elevator_type iosched_deadline = {
+	.ops = {
+		.elevator_merge_fn = 		deadline_merge,
+		.elevator_merged_fn =		deadline_merged_request,
+		.elevator_merge_req_fn =	deadline_merged_requests,
+		.elevator_dispatch_fn =		deadline_dispatch_requests,
+		.elevator_add_req_fn =		deadline_add_request,
+		.elevator_queue_empty_fn =	deadline_queue_empty,
+		.elevator_former_req_fn =	elv_rb_former_request,
+		.elevator_latter_req_fn =	elv_rb_latter_request,
+		.elevator_init_fn =		deadline_init_queue,
+		.elevator_exit_fn =		deadline_exit_queue,
+	},
+
+	.elevator_attrs = deadline_attrs,
+	.elevator_name = "deadline",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init deadline_init(void)
+{
+	return elv_register(&iosched_deadline);
+}
+
+static void __exit deadline_exit(void)
+{
+	elv_unregister(&iosched_deadline);
+}
+
+module_init(deadline_init);
+module_exit(deadline_exit);
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("deadline IO scheduler");

block/genhd.c

@@ -0,0 +1,747 @@
+/*
+ *  gendisk handling
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/genhd.h>
+#include <linux/kdev_t.h>
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/kmod.h>
+#include <linux/kobj_map.h>
+#include <linux/buffer_head.h>
+#include <linux/mutex.h>
+
+struct subsystem block_subsys;
+static DEFINE_MUTEX(block_subsys_lock);
+
+/*
+ * Can be deleted altogether. Later.
+ *
+ */
+static struct blk_major_name {
+	struct blk_major_name *next;
+	int major;
+	char name[16];
+} *major_names[BLKDEV_MAJOR_HASH_SIZE];
+
+/* index in the above - for now: assume no multimajor ranges */
+static inline int major_to_index(int major)
+{
+	return major % BLKDEV_MAJOR_HASH_SIZE;
+}
+
+#ifdef CONFIG_PROC_FS
+
+void blkdev_show(struct seq_file *f, off_t offset)
+{
+	struct blk_major_name *dp;
+
+	if (offset < BLKDEV_MAJOR_HASH_SIZE) {
+		mutex_lock(&block_subsys_lock);
+		for (dp = major_names[offset]; dp; dp = dp->next)
+			seq_printf(f, "%3d %s\n", dp->major, dp->name);
+		mutex_unlock(&block_subsys_lock);
+	}
+}
+
+#endif /* CONFIG_PROC_FS */
+
+int register_blkdev(unsigned int major, const char *name)
+{
+	struct blk_major_name **n, *p;
+	int index, ret = 0;
+
+	mutex_lock(&block_subsys_lock);
+
+	/* temporary */
+	if (major == 0) {
+		for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) {
+			if (major_names[index] == NULL)
+				break;
+		}
+
+		if (index == 0) {
+			printk("register_blkdev: failed to get major for %s\n",
+			       name);
+			ret = -EBUSY;
+			goto out;
+		}
+		major = index;
+		ret = major;
+	}
+
+	p = kmalloc(sizeof(struct blk_major_name), GFP_KERNEL);
+	if (p == NULL) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	p->major = major;
+	strlcpy(p->name, name, sizeof(p->name));
+	p->next = NULL;
+	index = major_to_index(major);
+
+	for (n = &major_names[index]; *n; n = &(*n)->next) {
+		if ((*n)->major == major)
+			break;
+	}
+	if (!*n)
+		*n = p;
+	else
+		ret = -EBUSY;
+
+	if (ret < 0) {
+		printk("register_blkdev: cannot get major %d for %s\n",
+		       major, name);
+		kfree(p);
+	}
+out:
+	mutex_unlock(&block_subsys_lock);
+	return ret;
+}
+
+EXPORT_SYMBOL(register_blkdev);
+
+/* todo: make void - error printk here */
+int unregister_blkdev(unsigned int major, const char *name)
+{
+	struct blk_major_name **n;
+	struct blk_major_name *p = NULL;
+	int index = major_to_index(major);
+	int ret = 0;
+
+	mutex_lock(&block_subsys_lock);
+	for (n = &major_names[index]; *n; n = &(*n)->next)
+		if ((*n)->major == major)
+			break;
+	if (!*n || strcmp((*n)->name, name))
+		ret = -EINVAL;
+	else {
+		p = *n;
+		*n = p->next;
+	}
+	mutex_unlock(&block_subsys_lock);
+	kfree(p);
+
+	return ret;
+}
+
+EXPORT_SYMBOL(unregister_blkdev);
+
+static struct kobj_map *bdev_map;
+
+/*
+ * Register device numbers dev..(dev+range-1)
+ * range must be nonzero
+ * The hash chain is sorted on range, so that subranges can override.
+ */
+void blk_register_region(dev_t dev, unsigned long range, struct module *module,
+			 struct kobject *(*probe)(dev_t, int *, void *),
+			 int (*lock)(dev_t, void *), void *data)
+{
+	kobj_map(bdev_map, dev, range, module, probe, lock, data);
+}
+
+EXPORT_SYMBOL(blk_register_region);
+
+void blk_unregister_region(dev_t dev, unsigned long range)
+{
+	kobj_unmap(bdev_map, dev, range);
+}
+
+EXPORT_SYMBOL(blk_unregister_region);
+
+static struct kobject *exact_match(dev_t dev, int *part, void *data)
+{
+	struct gendisk *p = data;
+	return &p->kobj;
+}
+
+static int exact_lock(dev_t dev, void *data)
+{
+	struct gendisk *p = data;
+
+	if (!get_disk(p))
+		return -1;
+	return 0;
+}
+
+/**
+ * add_disk - add partitioning information to kernel list
+ * @disk: per-device partitioning information
+ *
+ * This function registers the partitioning information in @disk
+ * with the kernel.
+ */
+void add_disk(struct gendisk *disk)
+{
+	disk->flags |= GENHD_FL_UP;
+	blk_register_region(MKDEV(disk->major, disk->first_minor),
+			    disk->minors, NULL, exact_match, exact_lock, disk);
+	register_disk(disk);
+	blk_register_queue(disk);
+}
+
+EXPORT_SYMBOL(add_disk);
+EXPORT_SYMBOL(del_gendisk);	/* in partitions/check.c */
+
+void unlink_gendisk(struct gendisk *disk)
+{
+	blk_unregister_queue(disk);
+	blk_unregister_region(MKDEV(disk->major, disk->first_minor),
+			      disk->minors);
+}
+
+#define to_disk(obj) container_of(obj,struct gendisk,kobj)
+
+/**
+ * get_gendisk - get partitioning information for a given device
+ * @dev: device to get partitioning information for
+ *
+ * This function gets the structure containing partitioning
+ * information for the given device @dev.
+ */
+struct gendisk *get_gendisk(dev_t dev, int *part)
+{
+	struct kobject *kobj = kobj_lookup(bdev_map, dev, part);
+	return  kobj ? to_disk(kobj) : NULL;
+}
+
+#ifdef CONFIG_PROC_FS
+/* iterator */
+static void *part_start(struct seq_file *part, loff_t *pos)
+{
+	struct list_head *p;
+	loff_t l = *pos;
+
+	mutex_lock(&block_subsys_lock);
+	list_for_each(p, &block_subsys.kset.list)
+		if (!l--)
+			return list_entry(p, struct gendisk, kobj.entry);
+	return NULL;
+}
+
+static void *part_next(struct seq_file *part, void *v, loff_t *pos)
+{
+	struct list_head *p = ((struct gendisk *)v)->kobj.entry.next;
+	++*pos;
+	return p==&block_subsys.kset.list ? NULL : 
+		list_entry(p, struct gendisk, kobj.entry);
+}
+
+static void part_stop(struct seq_file *part, void *v)
+{
+	mutex_unlock(&block_subsys_lock);
+}
+
+static int show_partition(struct seq_file *part, void *v)
+{
+	struct gendisk *sgp = v;
+	int n;
+	char buf[BDEVNAME_SIZE];
+
+	if (&sgp->kobj.entry == block_subsys.kset.list.next)
+		seq_puts(part, "major minor  #blocks  name\n\n");
+
+	/* Don't show non-partitionable removeable devices or empty devices */
+	if (!get_capacity(sgp) ||
+			(sgp->minors == 1 && (sgp->flags & GENHD_FL_REMOVABLE)))
+		return 0;
+	if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
+		return 0;
+
+	/* show the full disk and all non-0 size partitions of it */
+	seq_printf(part, "%4d  %4d %10llu %s\n",
+		sgp->major, sgp->first_minor,
+		(unsigned long long)get_capacity(sgp) >> 1,
+		disk_name(sgp, 0, buf));
+	for (n = 0; n < sgp->minors - 1; n++) {
+		if (!sgp->part[n])
+			continue;
+		if (sgp->part[n]->nr_sects == 0)
+			continue;
+		seq_printf(part, "%4d  %4d %10llu %s\n",
+			sgp->major, n + 1 + sgp->first_minor,
+			(unsigned long long)sgp->part[n]->nr_sects >> 1 ,
+			disk_name(sgp, n + 1, buf));
+	}
+
+	return 0;
+}
+
+struct seq_operations partitions_op = {
+	.start =part_start,
+	.next =	part_next,
+	.stop =	part_stop,
+	.show =	show_partition
+};
+#endif
+
+
+extern int blk_dev_init(void);
+
+static struct kobject *base_probe(dev_t dev, int *part, void *data)
+{
+	if (request_module("block-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0)
+		/* Make old-style 2.4 aliases work */
+		request_module("block-major-%d", MAJOR(dev));
+	return NULL;
+}
+
+static int __init genhd_device_init(void)
+{
+	int err;
+
+	bdev_map = kobj_map_init(base_probe, &block_subsys_lock);
+	blk_dev_init();
+	err = subsystem_register(&block_subsys);
+	if (err < 0)
+		printk(KERN_WARNING "%s: subsystem_register error: %d\n",
+			__FUNCTION__, err);
+	return err;
+}
+
+subsys_initcall(genhd_device_init);
+
+
+
+/*
+ * kobject & sysfs bindings for block devices
+ */
+static ssize_t disk_attr_show(struct kobject *kobj, struct attribute *attr,
+			      char *page)
+{
+	struct gendisk *disk = to_disk(kobj);
+	struct disk_attribute *disk_attr =
+		container_of(attr,struct disk_attribute,attr);
+	ssize_t ret = -EIO;
+
+	if (disk_attr->show)
+		ret = disk_attr->show(disk,page);
+	return ret;
+}
+
+static ssize_t disk_attr_store(struct kobject * kobj, struct attribute * attr,
+			       const char *page, size_t count)
+{
+	struct gendisk *disk = to_disk(kobj);
+	struct disk_attribute *disk_attr =
+		container_of(attr,struct disk_attribute,attr);
+	ssize_t ret = 0;
+
+	if (disk_attr->store)
+		ret = disk_attr->store(disk, page, count);
+	return ret;
+}
+
+static struct sysfs_ops disk_sysfs_ops = {
+	.show	= &disk_attr_show,
+	.store	= &disk_attr_store,
+};
+
+static ssize_t disk_uevent_store(struct gendisk * disk,
+				 const char *buf, size_t count)
+{
+	kobject_uevent(&disk->kobj, KOBJ_ADD);
+	return count;
+}
+static ssize_t disk_dev_read(struct gendisk * disk, char *page)
+{
+	dev_t base = MKDEV(disk->major, disk->first_minor); 
+	return print_dev_t(page, base);
+}
+static ssize_t disk_range_read(struct gendisk * disk, char *page)
+{
+	return sprintf(page, "%d\n", disk->minors);
+}
+static ssize_t disk_removable_read(struct gendisk * disk, char *page)
+{
+	return sprintf(page, "%d\n",
+		       (disk->flags & GENHD_FL_REMOVABLE ? 1 : 0));
+
+}
+static ssize_t disk_size_read(struct gendisk * disk, char *page)
+{
+	return sprintf(page, "%llu\n", (unsigned long long)get_capacity(disk));
+}
+
+static ssize_t disk_stats_read(struct gendisk * disk, char *page)
+{
+	preempt_disable();
+	disk_round_stats(disk);
+	preempt_enable();
+	return sprintf(page,
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8lu %8llu %8u "
+		"%8u %8u %8u"
+		"\n",
+		disk_stat_read(disk, ios[READ]),
+		disk_stat_read(disk, merges[READ]),
+		(unsigned long long)disk_stat_read(disk, sectors[READ]),
+		jiffies_to_msecs(disk_stat_read(disk, ticks[READ])),
+		disk_stat_read(disk, ios[WRITE]),
+		disk_stat_read(disk, merges[WRITE]),
+		(unsigned long long)disk_stat_read(disk, sectors[WRITE]),
+		jiffies_to_msecs(disk_stat_read(disk, ticks[WRITE])),
+		disk->in_flight,
+		jiffies_to_msecs(disk_stat_read(disk, io_ticks)),
+		jiffies_to_msecs(disk_stat_read(disk, time_in_queue)));
+}
+static struct disk_attribute disk_attr_uevent = {
+	.attr = {.name = "uevent", .mode = S_IWUSR },
+	.store	= disk_uevent_store
+};
+static struct disk_attribute disk_attr_dev = {
+	.attr = {.name = "dev", .mode = S_IRUGO },
+	.show	= disk_dev_read
+};
+static struct disk_attribute disk_attr_range = {
+	.attr = {.name = "range", .mode = S_IRUGO },
+	.show	= disk_range_read
+};
+static struct disk_attribute disk_attr_removable = {
+	.attr = {.name = "removable", .mode = S_IRUGO },
+	.show	= disk_removable_read
+};
+static struct disk_attribute disk_attr_size = {
+	.attr = {.name = "size", .mode = S_IRUGO },
+	.show	= disk_size_read
+};
+static struct disk_attribute disk_attr_stat = {
+	.attr = {.name = "stat", .mode = S_IRUGO },
+	.show	= disk_stats_read
+};
+
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+
+static ssize_t disk_fail_store(struct gendisk * disk,
+			       const char *buf, size_t count)
+{
+	int i;
+
+	if (count > 0 && sscanf(buf, "%d", &i) > 0) {
+		if (i == 0)
+			disk->flags &= ~GENHD_FL_FAIL;
+		else
+			disk->flags |= GENHD_FL_FAIL;
+	}
+
+	return count;
+}
+static ssize_t disk_fail_read(struct gendisk * disk, char *page)
+{
+	return sprintf(page, "%d\n", disk->flags & GENHD_FL_FAIL ? 1 : 0);
+}
+static struct disk_attribute disk_attr_fail = {
+	.attr = {.name = "make-it-fail", .mode = S_IRUGO | S_IWUSR },
+	.store	= disk_fail_store,
+	.show	= disk_fail_read
+};
+
+#endif
+
+static struct attribute * default_attrs[] = {
+	&disk_attr_uevent.attr,
+	&disk_attr_dev.attr,
+	&disk_attr_range.attr,
+	&disk_attr_removable.attr,
+	&disk_attr_size.attr,
+	&disk_attr_stat.attr,
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+	&disk_attr_fail.attr,
+#endif
+	NULL,
+};
+
+static void disk_release(struct kobject * kobj)
+{
+	struct gendisk *disk = to_disk(kobj);
+	kfree(disk->random);
+	kfree(disk->part);
+	free_disk_stats(disk);
+	kfree(disk);
+}
+
+static struct kobj_type ktype_block = {
+	.release	= disk_release,
+	.sysfs_ops	= &disk_sysfs_ops,
+	.default_attrs	= default_attrs,
+};
+
+extern struct kobj_type ktype_part;
+
+static int block_uevent_filter(struct kset *kset, struct kobject *kobj)
+{
+	struct kobj_type *ktype = get_ktype(kobj);
+
+	return ((ktype == &ktype_block) || (ktype == &ktype_part));
+}
+
+static int block_uevent(struct kset *kset, struct kobject *kobj, char **envp,
+			 int num_envp, char *buffer, int buffer_size)
+{
+	struct kobj_type *ktype = get_ktype(kobj);
+	struct device *physdev;
+	struct gendisk *disk;
+	struct hd_struct *part;
+	int length = 0;
+	int i = 0;
+
+	if (ktype == &ktype_block) {
+		disk = container_of(kobj, struct gendisk, kobj);
+		add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
+			       &length, "MINOR=%u", disk->first_minor);
+	} else if (ktype == &ktype_part) {
+		disk = container_of(kobj->parent, struct gendisk, kobj);
+		part = container_of(kobj, struct hd_struct, kobj);
+		add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
+			       &length, "MINOR=%u",
+			       disk->first_minor + part->partno);
+	} else
+		return 0;
+
+	add_uevent_var(envp, num_envp, &i, buffer, buffer_size, &length,
+		       "MAJOR=%u", disk->major);
+
+	/* add physical device, backing this device  */
+	physdev = disk->driverfs_dev;
+	if (physdev) {
+		char *path = kobject_get_path(&physdev->kobj, GFP_KERNEL);
+
+		add_uevent_var(envp, num_envp, &i, buffer, buffer_size,
+			       &length, "PHYSDEVPATH=%s", path);
+		kfree(path);
+
+		if (physdev->bus)
+			add_uevent_var(envp, num_envp, &i,
+				       buffer, buffer_size, &length,
+				       "PHYSDEVBUS=%s",
+				       physdev->bus->name);
+
+		if (physdev->driver)
+			add_uevent_var(envp, num_envp, &i,
+				       buffer, buffer_size, &length,
+				       "PHYSDEVDRIVER=%s",
+				       physdev->driver->name);
+	}
+
+	/* terminate, set to next free slot, shrink available space */
+	envp[i] = NULL;
+	envp = &envp[i];
+	num_envp -= i;
+	buffer = &buffer[length];
+	buffer_size -= length;
+
+	return 0;
+}
+
+static struct kset_uevent_ops block_uevent_ops = {
+	.filter		= block_uevent_filter,
+	.uevent		= block_uevent,
+};
+
+decl_subsys(block, &ktype_block, &block_uevent_ops);
+
+/*
+ * aggregate disk stat collector.  Uses the same stats that the sysfs
+ * entries do, above, but makes them available through one seq_file.
+ * Watching a few disks may be efficient through sysfs, but watching
+ * all of them will be more efficient through this interface.
+ *
+ * The output looks suspiciously like /proc/partitions with a bunch of
+ * extra fields.
+ */
+
+/* iterator */
+static void *diskstats_start(struct seq_file *part, loff_t *pos)
+{
+	loff_t k = *pos;
+	struct list_head *p;
+
+	mutex_lock(&block_subsys_lock);
+	list_for_each(p, &block_subsys.kset.list)
+		if (!k--)
+			return list_entry(p, struct gendisk, kobj.entry);
+	return NULL;
+}
+
+static void *diskstats_next(struct seq_file *part, void *v, loff_t *pos)
+{
+	struct list_head *p = ((struct gendisk *)v)->kobj.entry.next;
+	++*pos;
+	return p==&block_subsys.kset.list ? NULL :
+		list_entry(p, struct gendisk, kobj.entry);
+}
+
+static void diskstats_stop(struct seq_file *part, void *v)
+{
+	mutex_unlock(&block_subsys_lock);
+}
+
+static int diskstats_show(struct seq_file *s, void *v)
+{
+	struct gendisk *gp = v;
+	char buf[BDEVNAME_SIZE];
+	int n = 0;
+
+	/*
+	if (&sgp->kobj.entry == block_subsys.kset.list.next)
+		seq_puts(s,	"major minor name"
+				"     rio rmerge rsect ruse wio wmerge "
+				"wsect wuse running use aveq"
+				"\n\n");
+	*/
+ 
+	preempt_disable();
+	disk_round_stats(gp);
+	preempt_enable();
+	seq_printf(s, "%4d %4d %s %lu %lu %llu %u %lu %lu %llu %u %u %u %u\n",
+		gp->major, n + gp->first_minor, disk_name(gp, n, buf),
+		disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]),
+		(unsigned long long)disk_stat_read(gp, sectors[0]),
+		jiffies_to_msecs(disk_stat_read(gp, ticks[0])),
+		disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]),
+		(unsigned long long)disk_stat_read(gp, sectors[1]),
+		jiffies_to_msecs(disk_stat_read(gp, ticks[1])),
+		gp->in_flight,
+		jiffies_to_msecs(disk_stat_read(gp, io_ticks)),
+		jiffies_to_msecs(disk_stat_read(gp, time_in_queue)));
+
+	/* now show all non-0 size partitions of it */
+	for (n = 0; n < gp->minors - 1; n++) {
+		struct hd_struct *hd = gp->part[n];
+
+		if (hd && hd->nr_sects)
+			seq_printf(s, "%4d %4d %s %u %u %u %u\n",
+				gp->major, n + gp->first_minor + 1,
+				disk_name(gp, n + 1, buf),
+				hd->ios[0], hd->sectors[0],
+				hd->ios[1], hd->sectors[1]);
+	}
+ 
+	return 0;
+}
+
+struct seq_operations diskstats_op = {
+	.start	= diskstats_start,
+	.next	= diskstats_next,
+	.stop	= diskstats_stop,
+	.show	= diskstats_show
+};
+
+struct gendisk *alloc_disk(int minors)
+{
+	return alloc_disk_node(minors, -1);
+}
+
+struct gendisk *alloc_disk_node(int minors, int node_id)
+{
+	struct gendisk *disk;
+
+	disk = kmalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
+	if (disk) {
+		memset(disk, 0, sizeof(struct gendisk));
+		if (!init_disk_stats(disk)) {
+			kfree(disk);
+			return NULL;
+		}
+		if (minors > 1) {
+			int size = (minors - 1) * sizeof(struct hd_struct *);
+			disk->part = kmalloc_node(size, GFP_KERNEL, node_id);
+			if (!disk->part) {
+				kfree(disk);
+				return NULL;
+			}
+			memset(disk->part, 0, size);
+		}
+		disk->minors = minors;
+		kobj_set_kset_s(disk,block_subsys);
+		kobject_init(&disk->kobj);
+		rand_initialize_disk(disk);
+	}
+	return disk;
+}
+
+EXPORT_SYMBOL(alloc_disk);
+EXPORT_SYMBOL(alloc_disk_node);
+
+struct kobject *get_disk(struct gendisk *disk)
+{
+	struct module *owner;
+	struct kobject *kobj;
+
+	if (!disk->fops)
+		return NULL;
+	owner = disk->fops->owner;
+	if (owner && !try_module_get(owner))
+		return NULL;
+	kobj = kobject_get(&disk->kobj);
+	if (kobj == NULL) {
+		module_put(owner);
+		return NULL;
+	}
+	return kobj;
+
+}
+
+EXPORT_SYMBOL(get_disk);
+
+void put_disk(struct gendisk *disk)
+{
+	if (disk)
+		kobject_put(&disk->kobj);
+}
+
+EXPORT_SYMBOL(put_disk);
+
+void set_device_ro(struct block_device *bdev, int flag)
+{
+	if (bdev->bd_contains != bdev)
+		bdev->bd_part->policy = flag;
+	else
+		bdev->bd_disk->policy = flag;
+}
+
+EXPORT_SYMBOL(set_device_ro);
+
+void set_disk_ro(struct gendisk *disk, int flag)
+{
+	int i;
+	disk->policy = flag;
+	for (i = 0; i < disk->minors - 1; i++)
+		if (disk->part[i]) disk->part[i]->policy = flag;
+}
+
+EXPORT_SYMBOL(set_disk_ro);
+
+int bdev_read_only(struct block_device *bdev)
+{
+	if (!bdev)
+		return 0;
+	else if (bdev->bd_contains != bdev)
+		return bdev->bd_part->policy;
+	else
+		return bdev->bd_disk->policy;
+}
+
+EXPORT_SYMBOL(bdev_read_only);
+
+int invalidate_partition(struct gendisk *disk, int index)
+{
+	int res = 0;
+	struct block_device *bdev = bdget_disk(disk, index);
+	if (bdev) {
+		fsync_bdev(bdev);
+		res = __invalidate_device(bdev);
+		bdput(bdev);
+	}
+	return res;
+}
+
+EXPORT_SYMBOL(invalidate_partition);

block/ioctl.c

@@ -0,0 +1,304 @@
+#include <linux/capability.h>
+#include <linux/blkdev.h>
+#include <linux/blkpg.h>
+#include <linux/hdreg.h>
+#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)
+{
+	struct block_device *bdevp;
+	struct gendisk *disk;
+	struct blkpg_ioctl_arg a;
+	struct blkpg_partition p;
+	long long start, length;
+	int part;
+	int i;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg)))
+		return -EFAULT;
+	if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition)))
+		return -EFAULT;
+	disk = bdev->bd_disk;
+	if (bdev != bdev->bd_contains)
+		return -EINVAL;
+	part = p.pno;
+	if (part <= 0 || part >= disk->minors)
+		return -EINVAL;
+	switch (a.op) {
+		case BLKPG_ADD_PARTITION:
+			start = p.start >> 9;
+			length = p.length >> 9;
+			/* check for fit in a hd_struct */ 
+			if (sizeof(sector_t) == sizeof(long) && 
+			    sizeof(long long) > sizeof(long)) {
+				long pstart = start, plength = length;
+				if (pstart != start || plength != length
+				    || pstart < 0 || plength < 0)
+					return -EINVAL;
+			}
+			/* partition number in use? */
+			mutex_lock(&bdev->bd_mutex);
+			if (disk->part[part - 1]) {
+				mutex_unlock(&bdev->bd_mutex);
+				return -EBUSY;
+			}
+			/* overlap? */
+			for (i = 0; i < disk->minors - 1; i++) {
+				struct hd_struct *s = disk->part[i];
+
+				if (!s)
+					continue;
+				if (!(start+length <= s->start_sect ||
+				      start >= s->start_sect + s->nr_sects)) {
+					mutex_unlock(&bdev->bd_mutex);
+					return -EBUSY;
+				}
+			}
+			/* all seems OK */
+			add_partition(disk, part, start, length, ADDPART_FLAG_NONE);
+			mutex_unlock(&bdev->bd_mutex);
+			return 0;
+		case BLKPG_DEL_PARTITION:
+			if (!disk->part[part-1])
+				return -ENXIO;
+			if (disk->part[part - 1]->nr_sects == 0)
+				return -ENXIO;
+			bdevp = bdget_disk(disk, part);
+			if (!bdevp)
+				return -ENOMEM;
+			mutex_lock(&bdevp->bd_mutex);
+			if (bdevp->bd_openers) {
+				mutex_unlock(&bdevp->bd_mutex);
+				bdput(bdevp);
+				return -EBUSY;
+			}
+			/* all seems OK */
+			fsync_bdev(bdevp);
+			invalidate_bdev(bdevp, 0);
+
+			mutex_lock_nested(&bdev->bd_mutex, 1);
+			delete_partition(disk, part);
+			mutex_unlock(&bdev->bd_mutex);
+			mutex_unlock(&bdevp->bd_mutex);
+			bdput(bdevp);
+
+			return 0;
+		default:
+			return -EINVAL;
+	}
+}
+
+static int blkdev_reread_part(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	int res;
+
+	if (disk->minors == 1 || bdev != bdev->bd_contains)
+		return -EINVAL;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (!mutex_trylock(&bdev->bd_mutex))
+		return -EBUSY;
+	res = rescan_partitions(disk, bdev);
+	mutex_unlock(&bdev->bd_mutex);
+	return res;
+}
+
+static int put_ushort(unsigned long arg, unsigned short val)
+{
+	return put_user(val, (unsigned short __user *)arg);
+}
+
+static int put_int(unsigned long arg, int val)
+{
+	return put_user(val, (int __user *)arg);
+}
+
+static int put_long(unsigned long arg, long val)
+{
+	return put_user(val, (long __user *)arg);
+}
+
+static int put_ulong(unsigned long arg, unsigned long val)
+{
+	return put_user(val, (unsigned long __user *)arg);
+}
+
+static int put_u64(unsigned long arg, u64 val)
+{
+	return put_user(val, (u64 __user *)arg);
+}
+
+static int blkdev_locked_ioctl(struct file *file, struct block_device *bdev,
+				unsigned cmd, unsigned long arg)
+{
+	struct backing_dev_info *bdi;
+	int ret, n;
+
+	switch (cmd) {
+	case BLKRAGET:
+	case BLKFRAGET:
+		if (!arg)
+			return -EINVAL;
+		bdi = blk_get_backing_dev_info(bdev);
+		if (bdi == NULL)
+			return -ENOTTY;
+		return put_long(arg, (bdi->ra_pages * PAGE_CACHE_SIZE) / 512);
+	case BLKROGET:
+		return put_int(arg, bdev_read_only(bdev) != 0);
+	case BLKBSZGET: /* get the logical block size (cf. BLKSSZGET) */
+		return put_int(arg, block_size(bdev));
+	case BLKSSZGET: /* get block device hardware sector size */
+		return put_int(arg, bdev_hardsect_size(bdev));
+	case BLKSECTGET:
+		return put_ushort(arg, bdev_get_queue(bdev)->max_sectors);
+	case BLKRASET:
+	case BLKFRASET:
+		if(!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		bdi = blk_get_backing_dev_info(bdev);
+		if (bdi == NULL)
+			return -ENOTTY;
+		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
+		return 0;
+	case BLKBSZSET:
+		/* set the logical block size */
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		if (!arg)
+			return -EINVAL;
+		if (get_user(n, (int __user *) arg))
+			return -EFAULT;
+		if (bd_claim(bdev, file) < 0)
+			return -EBUSY;
+		ret = set_blocksize(bdev, n);
+		bd_release(bdev);
+		return ret;
+	case BLKPG:
+		return blkpg_ioctl(bdev, (struct blkpg_ioctl_arg __user *) arg);
+	case BLKRRPART:
+		return blkdev_reread_part(bdev);
+	case BLKGETSIZE:
+		if ((bdev->bd_inode->i_size >> 9) > ~0UL)
+			return -EFBIG;
+		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;
+}
+
+int blkdev_driver_ioctl(struct inode *inode, struct file *file,
+			struct gendisk *disk, unsigned cmd, unsigned long arg)
+{
+	int ret;
+	if (disk->fops->unlocked_ioctl)
+		return disk->fops->unlocked_ioctl(file, cmd, arg);
+
+	if (disk->fops->ioctl) {
+		lock_kernel();
+		ret = disk->fops->ioctl(inode, file, cmd, arg);
+		unlock_kernel();
+		return ret;
+	}
+
+	return -ENOTTY;
+}
+EXPORT_SYMBOL_GPL(blkdev_driver_ioctl);
+
+int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
+			unsigned long arg)
+{
+	struct block_device *bdev = inode->i_bdev;
+	struct gendisk *disk = bdev->bd_disk;
+	int ret, n;
+
+	switch(cmd) {
+	case BLKFLSBUF:
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+
+		ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+		/* -EINVAL to handle old uncorrected drivers */
+		if (ret != -EINVAL && ret != -ENOTTY)
+			return ret;
+
+		lock_kernel();
+		fsync_bdev(bdev);
+		invalidate_bdev(bdev, 0);
+		unlock_kernel();
+		return 0;
+
+	case BLKROSET:
+		ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+		/* -EINVAL to handle old uncorrected drivers */
+		if (ret != -EINVAL && ret != -ENOTTY)
+			return ret;
+		if (!capable(CAP_SYS_ADMIN))
+			return -EACCES;
+		if (get_user(n, (int __user *)(arg)))
+			return -EFAULT;
+		lock_kernel();
+		set_device_ro(bdev, n);
+		unlock_kernel();
+		return 0;
+	case HDIO_GETGEO: {
+		struct hd_geometry geo;
+
+		if (!arg)
+			return -EINVAL;
+		if (!disk->fops->getgeo)
+			return -ENOTTY;
+
+		/*
+		 * We need to set the startsect first, the driver may
+		 * want to override it.
+		 */
+		geo.start = get_start_sect(bdev);
+		ret = disk->fops->getgeo(bdev, &geo);
+		if (ret)
+			return ret;
+		if (copy_to_user((struct hd_geometry __user *)arg, &geo,
+					sizeof(geo)))
+			return -EFAULT;
+		return 0;
+	}
+	}
+
+	lock_kernel();
+	ret = blkdev_locked_ioctl(file, bdev, cmd, arg);
+	unlock_kernel();
+	if (ret != -ENOIOCTLCMD)
+		return ret;
+
+	return blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+}
+
+/* Most of the generic ioctls are handled in the normal fallback path.
+   This assumes the blkdev's low level compat_ioctl always returns
+   ENOIOCTLCMD for unknown ioctls. */
+long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	struct block_device *bdev = file->f_path.dentry->d_inode->i_bdev;
+	struct gendisk *disk = bdev->bd_disk;
+	int ret = -ENOIOCTLCMD;
+	if (disk->fops->compat_ioctl) {
+		lock_kernel();
+		ret = disk->fops->compat_ioctl(file, cmd, arg);
+		unlock_kernel();
+	}
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(blkdev_ioctl);

block/noop-iosched.c

@@ -0,0 +1,118 @@
+/*
+ * elevator noop
+ */
+#include <linux/blkdev.h>
+#include <linux/elevator.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/init.h>
+
+struct noop_data {
+	struct list_head queue;
+};
+
+static void noop_merged_requests(request_queue_t *q, struct request *rq,
+				 struct request *next)
+{
+	list_del_init(&next->queuelist);
+}
+
+static int noop_dispatch(request_queue_t *q, int force)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	if (!list_empty(&nd->queue)) {
+		struct request *rq;
+		rq = list_entry(nd->queue.next, struct request, queuelist);
+		list_del_init(&rq->queuelist);
+		elv_dispatch_sort(q, rq);
+		return 1;
+	}
+	return 0;
+}
+
+static void noop_add_request(request_queue_t *q, struct request *rq)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	list_add_tail(&rq->queuelist, &nd->queue);
+}
+
+static int noop_queue_empty(request_queue_t *q)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	return list_empty(&nd->queue);
+}
+
+static struct request *
+noop_former_request(request_queue_t *q, struct request *rq)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	if (rq->queuelist.prev == &nd->queue)
+		return NULL;
+	return list_entry(rq->queuelist.prev, struct request, queuelist);
+}
+
+static struct request *
+noop_latter_request(request_queue_t *q, struct request *rq)
+{
+	struct noop_data *nd = q->elevator->elevator_data;
+
+	if (rq->queuelist.next == &nd->queue)
+		return NULL;
+	return list_entry(rq->queuelist.next, struct request, queuelist);
+}
+
+static void *noop_init_queue(request_queue_t *q)
+{
+	struct noop_data *nd;
+
+	nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
+	if (!nd)
+		return NULL;
+	INIT_LIST_HEAD(&nd->queue);
+	return nd;
+}
+
+static void noop_exit_queue(elevator_t *e)
+{
+	struct noop_data *nd = e->elevator_data;
+
+	BUG_ON(!list_empty(&nd->queue));
+	kfree(nd);
+}
+
+static struct elevator_type elevator_noop = {
+	.ops = {
+		.elevator_merge_req_fn		= noop_merged_requests,
+		.elevator_dispatch_fn		= noop_dispatch,
+		.elevator_add_req_fn		= noop_add_request,
+		.elevator_queue_empty_fn	= noop_queue_empty,
+		.elevator_former_req_fn		= noop_former_request,
+		.elevator_latter_req_fn		= noop_latter_request,
+		.elevator_init_fn		= noop_init_queue,
+		.elevator_exit_fn		= noop_exit_queue,
+	},
+	.elevator_name = "noop",
+	.elevator_owner = THIS_MODULE,
+};
+
+static int __init noop_init(void)
+{
+	return elv_register(&elevator_noop);
+}
+
+static void __exit noop_exit(void)
+{
+	elv_unregister(&elevator_noop);
+}
+
+module_init(noop_init);
+module_exit(noop_exit);
+
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("No-op IO scheduler");

block/scsi_ioctl.c

@@ -0,0 +1,652 @@
+/*
+ * Copyright (C) 2001 Jens Axboe <axboe@suse.de>
+ *
+ * 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
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public Licens
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-
+ *
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/blkdev.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/cdrom.h>
+#include <linux/slab.h>
+#include <linux/times.h>
+#include <asm/uaccess.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/scsi_cmnd.h>
+
+/* Command group 3 is reserved and should never be used.  */
+const unsigned char scsi_command_size[8] =
+{
+	6, 10, 10, 12,
+	16, 12, 10, 10
+};
+
+EXPORT_SYMBOL(scsi_command_size);
+
+#define BLK_DEFAULT_TIMEOUT	(60 * HZ)
+
+#include <scsi/sg.h>
+
+static int sg_get_version(int __user *p)
+{
+	static const int sg_version_num = 30527;
+	return put_user(sg_version_num, p);
+}
+
+static int scsi_get_idlun(request_queue_t *q, int __user *p)
+{
+	return put_user(0, p);
+}
+
+static int scsi_get_bus(request_queue_t *q, int __user *p)
+{
+	return put_user(0, p);
+}
+
+static int sg_get_timeout(request_queue_t *q)
+{
+	return q->sg_timeout / (HZ / USER_HZ);
+}
+
+static int sg_set_timeout(request_queue_t *q, int __user *p)
+{
+	int timeout, err = get_user(timeout, p);
+
+	if (!err)
+		q->sg_timeout = timeout * (HZ / USER_HZ);
+
+	return err;
+}
+
+static int sg_get_reserved_size(request_queue_t *q, int __user *p)
+{
+	return put_user(q->sg_reserved_size, p);
+}
+
+static int sg_set_reserved_size(request_queue_t *q, int __user *p)
+{
+	int size, err = get_user(size, p);
+
+	if (err)
+		return err;
+
+	if (size < 0)
+		return -EINVAL;
+	if (size > (q->max_sectors << 9))
+		size = q->max_sectors << 9;
+
+	q->sg_reserved_size = size;
+	return 0;
+}
+
+/*
+ * will always return that we are ATAPI even for a real SCSI drive, I'm not
+ * so sure this is worth doing anything about (why would you care??)
+ */
+static int sg_emulated_host(request_queue_t *q, int __user *p)
+{
+	return put_user(1, p);
+}
+
+#define CMD_READ_SAFE	0x01
+#define CMD_WRITE_SAFE	0x02
+#define CMD_WARNED	0x04
+#define safe_for_read(cmd)	[cmd] = CMD_READ_SAFE
+#define safe_for_write(cmd)	[cmd] = CMD_WRITE_SAFE
+
+static int verify_command(struct file *file, unsigned char *cmd)
+{
+	static unsigned char cmd_type[256] = {
+
+		/* Basic read-only commands */
+		safe_for_read(TEST_UNIT_READY),
+		safe_for_read(REQUEST_SENSE),
+		safe_for_read(READ_6),
+		safe_for_read(READ_10),
+		safe_for_read(READ_12),
+		safe_for_read(READ_16),
+		safe_for_read(READ_BUFFER),
+		safe_for_read(READ_DEFECT_DATA),
+		safe_for_read(READ_LONG),
+		safe_for_read(INQUIRY),
+		safe_for_read(MODE_SENSE),
+		safe_for_read(MODE_SENSE_10),
+		safe_for_read(LOG_SENSE),
+		safe_for_read(START_STOP),
+		safe_for_read(GPCMD_VERIFY_10),
+		safe_for_read(VERIFY_16),
+
+		/* Audio CD commands */
+		safe_for_read(GPCMD_PLAY_CD),
+		safe_for_read(GPCMD_PLAY_AUDIO_10),
+		safe_for_read(GPCMD_PLAY_AUDIO_MSF),
+		safe_for_read(GPCMD_PLAY_AUDIO_TI),
+		safe_for_read(GPCMD_PAUSE_RESUME),
+
+		/* CD/DVD data reading */
+		safe_for_read(GPCMD_READ_BUFFER_CAPACITY),
+		safe_for_read(GPCMD_READ_CD),
+		safe_for_read(GPCMD_READ_CD_MSF),
+		safe_for_read(GPCMD_READ_DISC_INFO),
+		safe_for_read(GPCMD_READ_CDVD_CAPACITY),
+		safe_for_read(GPCMD_READ_DVD_STRUCTURE),
+		safe_for_read(GPCMD_READ_HEADER),
+		safe_for_read(GPCMD_READ_TRACK_RZONE_INFO),
+		safe_for_read(GPCMD_READ_SUBCHANNEL),
+		safe_for_read(GPCMD_READ_TOC_PMA_ATIP),
+		safe_for_read(GPCMD_REPORT_KEY),
+		safe_for_read(GPCMD_SCAN),
+		safe_for_read(GPCMD_GET_CONFIGURATION),
+		safe_for_read(GPCMD_READ_FORMAT_CAPACITIES),
+		safe_for_read(GPCMD_GET_EVENT_STATUS_NOTIFICATION),
+		safe_for_read(GPCMD_GET_PERFORMANCE),
+		safe_for_read(GPCMD_SEEK),
+		safe_for_read(GPCMD_STOP_PLAY_SCAN),
+
+		/* Basic writing commands */
+		safe_for_write(WRITE_6),
+		safe_for_write(WRITE_10),
+		safe_for_write(WRITE_VERIFY),
+		safe_for_write(WRITE_12),
+		safe_for_write(WRITE_VERIFY_12),
+		safe_for_write(WRITE_16),
+		safe_for_write(WRITE_LONG),
+		safe_for_write(WRITE_LONG_2),
+		safe_for_write(ERASE),
+		safe_for_write(GPCMD_MODE_SELECT_10),
+		safe_for_write(MODE_SELECT),
+		safe_for_write(LOG_SELECT),
+		safe_for_write(GPCMD_BLANK),
+		safe_for_write(GPCMD_CLOSE_TRACK),
+		safe_for_write(GPCMD_FLUSH_CACHE),
+		safe_for_write(GPCMD_FORMAT_UNIT),
+		safe_for_write(GPCMD_REPAIR_RZONE_TRACK),
+		safe_for_write(GPCMD_RESERVE_RZONE_TRACK),
+		safe_for_write(GPCMD_SEND_DVD_STRUCTURE),
+		safe_for_write(GPCMD_SEND_EVENT),
+		safe_for_write(GPCMD_SEND_KEY),
+		safe_for_write(GPCMD_SEND_OPC),
+		safe_for_write(GPCMD_SEND_CUE_SHEET),
+		safe_for_write(GPCMD_SET_SPEED),
+		safe_for_write(GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL),
+		safe_for_write(GPCMD_LOAD_UNLOAD),
+		safe_for_write(GPCMD_SET_STREAMING),
+	};
+	unsigned char type = cmd_type[cmd[0]];
+	int has_write_perm = 0;
+
+	/* Anybody who can open the device can do a read-safe command */
+	if (type & CMD_READ_SAFE)
+		return 0;
+
+	/*
+	 * file can be NULL from ioctl_by_bdev()...
+	 */
+	if (file)
+		has_write_perm = file->f_mode & FMODE_WRITE;
+
+	/* Write-safe commands just require a writable open.. */
+	if ((type & CMD_WRITE_SAFE) && has_write_perm)
+		return 0;
+
+	/* And root can do any command.. */
+	if (capable(CAP_SYS_RAWIO))
+		return 0;
+
+	if (!type) {
+		cmd_type[cmd[0]] = CMD_WARNED;
+		printk(KERN_WARNING "scsi: unknown opcode 0x%02x\n", cmd[0]);
+	}
+
+	/* Otherwise fail it with an "Operation not permitted" */
+	return -EPERM;
+}
+
+static int sg_io(struct file *file, request_queue_t *q,
+		struct gendisk *bd_disk, struct sg_io_hdr *hdr)
+{
+	unsigned long start_time, timeout;
+	int writing = 0, ret = 0;
+	struct request *rq;
+	char sense[SCSI_SENSE_BUFFERSIZE];
+	unsigned char cmd[BLK_MAX_CDB];
+	struct bio *bio;
+
+	if (hdr->interface_id != 'S')
+		return -EINVAL;
+	if (hdr->cmd_len > BLK_MAX_CDB)
+		return -EINVAL;
+	if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
+		return -EFAULT;
+	if (verify_command(file, cmd))
+		return -EPERM;
+
+	if (hdr->dxfer_len > (q->max_hw_sectors << 9))
+		return -EIO;
+
+	if (hdr->dxfer_len)
+		switch (hdr->dxfer_direction) {
+		default:
+			return -EINVAL;
+		case SG_DXFER_TO_DEV:
+			writing = 1;
+			break;
+		case SG_DXFER_TO_FROM_DEV:
+		case SG_DXFER_FROM_DEV:
+			break;
+		}
+
+	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
+	if (!rq)
+		return -ENOMEM;
+
+	/*
+	 * fill in request structure
+	 */
+	rq->cmd_len = hdr->cmd_len;
+	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
+	memcpy(rq->cmd, cmd, hdr->cmd_len);
+
+	memset(sense, 0, sizeof(sense));
+	rq->sense = sense;
+	rq->sense_len = 0;
+
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+
+	timeout = msecs_to_jiffies(hdr->timeout);
+	rq->timeout = (timeout < INT_MAX) ? timeout : INT_MAX;
+	if (!rq->timeout)
+		rq->timeout = q->sg_timeout;
+	if (!rq->timeout)
+		rq->timeout = BLK_DEFAULT_TIMEOUT;
+
+	if (hdr->iovec_count) {
+		const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
+		struct sg_iovec *iov;
+
+		iov = kmalloc(size, GFP_KERNEL);
+		if (!iov) {
+			ret = -ENOMEM;
+			goto out;
+		}
+
+		if (copy_from_user(iov, hdr->dxferp, size)) {
+			kfree(iov);
+			ret = -EFAULT;
+			goto out;
+		}
+
+		ret = blk_rq_map_user_iov(q, rq, iov, hdr->iovec_count,
+					  hdr->dxfer_len);
+		kfree(iov);
+	} else if (hdr->dxfer_len)
+		ret = blk_rq_map_user(q, rq, hdr->dxferp, hdr->dxfer_len);
+
+	if (ret)
+		goto out;
+
+	bio = rq->bio;
+	rq->retries = 0;
+
+	start_time = jiffies;
+
+	/* ignore return value. All information is passed back to caller
+	 * (if he doesn't check that is his problem).
+	 * N.B. a non-zero SCSI status is _not_ necessarily an error.
+	 */
+	blk_execute_rq(q, bd_disk, rq, 0);
+
+	/* write to all output members */
+	hdr->status = 0xff & rq->errors;
+	hdr->masked_status = status_byte(rq->errors);
+	hdr->msg_status = msg_byte(rq->errors);
+	hdr->host_status = host_byte(rq->errors);
+	hdr->driver_status = driver_byte(rq->errors);
+	hdr->info = 0;
+	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
+		hdr->info |= SG_INFO_CHECK;
+	hdr->resid = rq->data_len;
+	hdr->duration = ((jiffies - start_time) * 1000) / HZ;
+	hdr->sb_len_wr = 0;
+
+	if (rq->sense_len && hdr->sbp) {
+		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+
+		if (!copy_to_user(hdr->sbp, rq->sense, len))
+			hdr->sb_len_wr = len;
+	}
+
+	if (blk_rq_unmap_user(bio))
+		ret = -EFAULT;
+
+	/* may not have succeeded, but output values written to control
+	 * structure (struct sg_io_hdr).  */
+out:
+	blk_put_request(rq);
+	return ret;
+}
+
+/**
+ * sg_scsi_ioctl  --  handle deprecated SCSI_IOCTL_SEND_COMMAND ioctl
+ * @file:	file this ioctl operates on (optional)
+ * @q:		request queue to send scsi commands down
+ * @disk:	gendisk to operate on (option)
+ * @sic:	userspace structure describing the command to perform
+ *
+ * Send down the scsi command described by @sic to the device below
+ * the request queue @q.  If @file is non-NULL it's used to perform
+ * fine-grained permission checks that allow users to send down
+ * non-destructive SCSI commands.  If the caller has a struct gendisk
+ * available it should be passed in as @disk to allow the low level
+ * driver to use the information contained in it.  A non-NULL @disk
+ * is only allowed if the caller knows that the low level driver doesn't
+ * need it (e.g. in the scsi subsystem).
+ *
+ * Notes:
+ *   -  This interface is deprecated - users should use the SG_IO
+ *      interface instead, as this is a more flexible approach to
+ *      performing SCSI commands on a device.
+ *   -  The SCSI command length is determined by examining the 1st byte
+ *      of the given command. There is no way to override this.
+ *   -  Data transfers are limited to PAGE_SIZE
+ *   -  The length (x + y) must be at least OMAX_SB_LEN bytes long to
+ *      accommodate the sense buffer when an error occurs.
+ *      The sense buffer is truncated to OMAX_SB_LEN (16) bytes so that
+ *      old code will not be surprised.
+ *   -  If a Unix error occurs (e.g. ENOMEM) then the user will receive
+ *      a negative return and the Unix error code in 'errno'.
+ *      If the SCSI command succeeds then 0 is returned.
+ *      Positive numbers returned are the compacted SCSI error codes (4
+ *      bytes in one int) where the lowest byte is the SCSI status.
+ */
+#define OMAX_SB_LEN 16          /* For backward compatibility */
+int sg_scsi_ioctl(struct file *file, struct request_queue *q,
+		  struct gendisk *disk, struct scsi_ioctl_command __user *sic)
+{
+	struct request *rq;
+	int err;
+	unsigned int in_len, out_len, bytes, opcode, cmdlen;
+	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
+
+	if (!sic)
+		return -EINVAL;
+
+	/*
+	 * get in an out lengths, verify they don't exceed a page worth of data
+	 */
+	if (get_user(in_len, &sic->inlen))
+		return -EFAULT;
+	if (get_user(out_len, &sic->outlen))
+		return -EFAULT;
+	if (in_len > PAGE_SIZE || out_len > PAGE_SIZE)
+		return -EINVAL;
+	if (get_user(opcode, sic->data))
+		return -EFAULT;
+
+	bytes = max(in_len, out_len);
+	if (bytes) {
+		buffer = kmalloc(bytes, q->bounce_gfp | GFP_USER| __GFP_NOWARN);
+		if (!buffer)
+			return -ENOMEM;
+
+		memset(buffer, 0, bytes);
+	}
+
+	rq = blk_get_request(q, in_len ? WRITE : READ, __GFP_WAIT);
+
+	cmdlen = COMMAND_SIZE(opcode);
+
+	/*
+	 * get command and data to send to device, if any
+	 */
+	err = -EFAULT;
+	rq->cmd_len = cmdlen;
+	if (copy_from_user(rq->cmd, sic->data, cmdlen))
+		goto error;
+
+	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
+		goto error;
+
+	err = verify_command(file, rq->cmd);
+	if (err)
+		goto error;
+
+	/* default.  possible overriden later */
+	rq->retries = 5;
+
+	switch (opcode) {
+	case SEND_DIAGNOSTIC:
+	case FORMAT_UNIT:
+		rq->timeout = FORMAT_UNIT_TIMEOUT;
+		rq->retries = 1;
+		break;
+	case START_STOP:
+		rq->timeout = START_STOP_TIMEOUT;
+		break;
+	case MOVE_MEDIUM:
+		rq->timeout = MOVE_MEDIUM_TIMEOUT;
+		break;
+	case READ_ELEMENT_STATUS:
+		rq->timeout = READ_ELEMENT_STATUS_TIMEOUT;
+		break;
+	case READ_DEFECT_DATA:
+		rq->timeout = READ_DEFECT_DATA_TIMEOUT;
+		rq->retries = 1;
+		break;
+	default:
+		rq->timeout = BLK_DEFAULT_TIMEOUT;
+		break;
+	}
+
+	if (bytes && blk_rq_map_kern(q, rq, buffer, bytes, __GFP_WAIT)) {
+		err = DRIVER_ERROR << 24;
+		goto out;
+	}
+
+	memset(sense, 0, sizeof(sense));
+	rq->sense = sense;
+	rq->sense_len = 0;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+
+	blk_execute_rq(q, disk, rq, 0);
+
+out:
+	err = rq->errors & 0xff;	/* only 8 bit SCSI status */
+	if (err) {
+		if (rq->sense_len && rq->sense) {
+			bytes = (OMAX_SB_LEN > rq->sense_len) ?
+				rq->sense_len : OMAX_SB_LEN;
+			if (copy_to_user(sic->data, rq->sense, bytes))
+				err = -EFAULT;
+		}
+	} else {
+		if (copy_to_user(sic->data, buffer, out_len))
+			err = -EFAULT;
+	}
+	
+error:
+	kfree(buffer);
+	blk_put_request(rq);
+	return err;
+}
+EXPORT_SYMBOL_GPL(sg_scsi_ioctl);
+
+/* Send basic block requests */
+static int __blk_send_generic(request_queue_t *q, struct gendisk *bd_disk, int cmd, int data)
+{
+	struct request *rq;
+	int err;
+
+	rq = blk_get_request(q, WRITE, __GFP_WAIT);
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	rq->data = NULL;
+	rq->data_len = 0;
+	rq->timeout = BLK_DEFAULT_TIMEOUT;
+	memset(rq->cmd, 0, sizeof(rq->cmd));
+	rq->cmd[0] = cmd;
+	rq->cmd[4] = data;
+	rq->cmd_len = 6;
+	err = blk_execute_rq(q, bd_disk, rq, 0);
+	blk_put_request(rq);
+
+	return err;
+}
+
+static inline int blk_send_start_stop(request_queue_t *q, struct gendisk *bd_disk, int data)
+{
+	return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data);
+}
+
+int scsi_cmd_ioctl(struct file *file, struct gendisk *bd_disk, unsigned int cmd, void __user *arg)
+{
+	request_queue_t *q;
+	int err;
+
+	q = bd_disk->queue;
+	if (!q)
+		return -ENXIO;
+
+	if (blk_get_queue(q))
+		return -ENXIO;
+
+	switch (cmd) {
+		/*
+		 * new sgv3 interface
+		 */
+		case SG_GET_VERSION_NUM:
+			err = sg_get_version(arg);
+			break;
+		case SCSI_IOCTL_GET_IDLUN:
+			err = scsi_get_idlun(q, arg);
+			break;
+		case SCSI_IOCTL_GET_BUS_NUMBER:
+			err = scsi_get_bus(q, arg);
+			break;
+		case SG_SET_TIMEOUT:
+			err = sg_set_timeout(q, arg);
+			break;
+		case SG_GET_TIMEOUT:
+			err = sg_get_timeout(q);
+			break;
+		case SG_GET_RESERVED_SIZE:
+			err = sg_get_reserved_size(q, arg);
+			break;
+		case SG_SET_RESERVED_SIZE:
+			err = sg_set_reserved_size(q, arg);
+			break;
+		case SG_EMULATED_HOST:
+			err = sg_emulated_host(q, arg);
+			break;
+		case SG_IO: {
+			struct sg_io_hdr hdr;
+
+			err = -EFAULT;
+			if (copy_from_user(&hdr, arg, sizeof(hdr)))
+				break;
+			err = sg_io(file, q, bd_disk, &hdr);
+			if (err == -EFAULT)
+				break;
+
+			if (copy_to_user(arg, &hdr, sizeof(hdr)))
+				err = -EFAULT;
+			break;
+		}
+		case CDROM_SEND_PACKET: {
+			struct cdrom_generic_command cgc;
+			struct sg_io_hdr hdr;
+
+			err = -EFAULT;
+			if (copy_from_user(&cgc, arg, sizeof(cgc)))
+				break;
+			cgc.timeout = clock_t_to_jiffies(cgc.timeout);
+			memset(&hdr, 0, sizeof(hdr));
+			hdr.interface_id = 'S';
+			hdr.cmd_len = sizeof(cgc.cmd);
+			hdr.dxfer_len = cgc.buflen;
+			err = 0;
+			switch (cgc.data_direction) {
+				case CGC_DATA_UNKNOWN:
+					hdr.dxfer_direction = SG_DXFER_UNKNOWN;
+					break;
+				case CGC_DATA_WRITE:
+					hdr.dxfer_direction = SG_DXFER_TO_DEV;
+					break;
+				case CGC_DATA_READ:
+					hdr.dxfer_direction = SG_DXFER_FROM_DEV;
+					break;
+				case CGC_DATA_NONE:
+					hdr.dxfer_direction = SG_DXFER_NONE;
+					break;
+				default:
+					err = -EINVAL;
+			}
+			if (err)
+				break;
+
+			hdr.dxferp = cgc.buffer;
+			hdr.sbp = cgc.sense;
+			if (hdr.sbp)
+				hdr.mx_sb_len = sizeof(struct request_sense);
+			hdr.timeout = cgc.timeout;
+			hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
+			hdr.cmd_len = sizeof(cgc.cmd);
+
+			err = sg_io(file, q, bd_disk, &hdr);
+			if (err == -EFAULT)
+				break;
+
+			if (hdr.status)
+				err = -EIO;
+
+			cgc.stat = err;
+			cgc.buflen = hdr.resid;
+			if (copy_to_user(arg, &cgc, sizeof(cgc)))
+				err = -EFAULT;
+
+			break;
+		}
+
+		/*
+		 * old junk scsi send command ioctl
+		 */
+		case SCSI_IOCTL_SEND_COMMAND:
+			printk(KERN_WARNING "program %s is using a deprecated SCSI ioctl, please convert it to SG_IO\n", current->comm);
+			err = -EINVAL;
+			if (!arg)
+				break;
+
+			err = sg_scsi_ioctl(file, q, bd_disk, arg);
+			break;
+		case CDROMCLOSETRAY:
+			err = blk_send_start_stop(q, bd_disk, 0x03);
+			break;
+		case CDROMEJECT:
+			err = blk_send_start_stop(q, bd_disk, 0x02);
+			break;
+		default:
+			err = -ENOTTY;
+	}
+
+	blk_put_queue(q);
+	return err;
+}
+
+EXPORT_SYMBOL(scsi_cmd_ioctl);