linux/drivers/mtd/mtd_blkdevs.c

447 lines
10 KiB
C
Raw Normal View History

/*
* (C) 2003 David Woodhouse <dwmw2@infradead.org>
*
* Interface to Linux 2.5 block layer for MTD 'translation layers'.
*
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/fs.h>
#include <linux/mtd/blktrans.h>
#include <linux/mtd/mtd.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/freezer.h>
#include <linux/spinlock.h>
#include <linux/hdreg.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/kthread.h>
#include <asm/uaccess.h>
#include "mtdcore.h"
static LIST_HEAD(blktrans_majors);
struct mtd_blkcore_priv {
struct task_struct *thread;
struct request_queue *rq;
spinlock_t queue_lock;
};
static int do_blktrans_request(struct mtd_blktrans_ops *tr,
struct mtd_blktrans_dev *dev,
struct request *req)
{
unsigned long block, nsect;
char *buf;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:39 +08:00
block = blk_rq_pos(req) << 9 >> tr->blkshift;
nsect = blk_rq_cur_bytes(req) >> tr->blkshift;
buf = req->buffer;
if (!blk_fs_request(req))
2009-04-23 10:05:19 +08:00
return -EIO;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 21:24:39 +08:00
if (blk_rq_pos(req) + blk_rq_cur_sectors(req) >
get_capacity(req->rq_disk))
2009-04-23 10:05:19 +08:00
return -EIO;
if (blk_discard_rq(req))
return tr->discard(dev, block, nsect);
switch(rq_data_dir(req)) {
case READ:
for (; nsect > 0; nsect--, block++, buf += tr->blksize)
if (tr->readsect(dev, block, buf))
2009-04-23 10:05:19 +08:00
return -EIO;
return 0;
case WRITE:
if (!tr->writesect)
2009-04-23 10:05:19 +08:00
return -EIO;
for (; nsect > 0; nsect--, block++, buf += tr->blksize)
if (tr->writesect(dev, block, buf))
2009-04-23 10:05:19 +08:00
return -EIO;
return 0;
default:
printk(KERN_NOTICE "Unknown request %u\n", rq_data_dir(req));
2009-04-23 10:05:19 +08:00
return -EIO;
}
}
static int mtd_blktrans_thread(void *arg)
{
struct mtd_blktrans_ops *tr = arg;
struct request_queue *rq = tr->blkcore_priv->rq;
struct request *req = NULL;
/* we might get involved when memory gets low, so use PF_MEMALLOC */
current->flags |= PF_MEMALLOC;
spin_lock_irq(rq->queue_lock);
while (!kthread_should_stop()) {
struct mtd_blktrans_dev *dev;
2009-04-23 10:05:19 +08:00
int res;
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 10:54:16 +08:00
if (!req && !(req = blk_fetch_request(rq))) {
set_current_state(TASK_INTERRUPTIBLE);
spin_unlock_irq(rq->queue_lock);
schedule();
spin_lock_irq(rq->queue_lock);
continue;
}
dev = req->rq_disk->private_data;
tr = dev->tr;
spin_unlock_irq(rq->queue_lock);
mutex_lock(&dev->lock);
res = do_blktrans_request(tr, dev, req);
mutex_unlock(&dev->lock);
spin_lock_irq(rq->queue_lock);
if (!__blk_end_request_cur(req, res))
req = NULL;
}
if (req)
__blk_end_request_all(req, -EIO);
spin_unlock_irq(rq->queue_lock);
return 0;
}
static void mtd_blktrans_request(struct request_queue *rq)
{
struct mtd_blktrans_ops *tr = rq->queuedata;
wake_up_process(tr->blkcore_priv->thread);
}
static int blktrans_open(struct block_device *bdev, fmode_t mode)
{
struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data;
struct mtd_blktrans_ops *tr = dev->tr;
int ret = -ENODEV;
if (!get_mtd_device(NULL, dev->mtd->index))
goto out;
if (!try_module_get(tr->owner))
goto out_tr;
/* FIXME: Locking. A hot pluggable device can go away
(del_mtd_device can be called for it) without its module
being unloaded. */
dev->mtd->usecount++;
ret = 0;
if (tr->open && (ret = tr->open(dev))) {
dev->mtd->usecount--;
put_mtd_device(dev->mtd);
out_tr:
module_put(tr->owner);
}
out:
return ret;
}
static int blktrans_release(struct gendisk *disk, fmode_t mode)
{
struct mtd_blktrans_dev *dev = disk->private_data;
struct mtd_blktrans_ops *tr = dev->tr;
int ret = 0;
if (tr->release)
ret = tr->release(dev);
if (!ret) {
dev->mtd->usecount--;
put_mtd_device(dev->mtd);
module_put(tr->owner);
}
return ret;
}
static int blktrans_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data;
if (dev->tr->getgeo)
return dev->tr->getgeo(dev, geo);
return -ENOTTY;
}
static int blktrans_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct mtd_blktrans_dev *dev = bdev->bd_disk->private_data;
struct mtd_blktrans_ops *tr = dev->tr;
switch (cmd) {
case BLKFLSBUF:
if (tr->flush)
return tr->flush(dev);
/* The core code did the work, we had nothing to do. */
return 0;
default:
return -ENOTTY;
}
}
static const struct block_device_operations mtd_blktrans_ops = {
.owner = THIS_MODULE,
.open = blktrans_open,
.release = blktrans_release,
.locked_ioctl = blktrans_ioctl,
.getgeo = blktrans_getgeo,
};
int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
{
struct mtd_blktrans_ops *tr = new->tr;
struct mtd_blktrans_dev *d;
int last_devnum = -1;
struct gendisk *gd;
if (mutex_trylock(&mtd_table_mutex)) {
mutex_unlock(&mtd_table_mutex);
BUG();
}
list_for_each_entry(d, &tr->devs, list) {
if (new->devnum == -1) {
/* Use first free number */
if (d->devnum != last_devnum+1) {
/* Found a free devnum. Plug it in here */
new->devnum = last_devnum+1;
list_add_tail(&new->list, &d->list);
goto added;
}
} else if (d->devnum == new->devnum) {
/* Required number taken */
return -EBUSY;
} else if (d->devnum > new->devnum) {
/* Required number was free */
list_add_tail(&new->list, &d->list);
goto added;
}
last_devnum = d->devnum;
}
if (new->devnum == -1)
new->devnum = last_devnum+1;
if ((new->devnum << tr->part_bits) > 256) {
return -EBUSY;
}
list_add_tail(&new->list, &tr->devs);
added:
mutex_init(&new->lock);
if (!tr->writesect)
new->readonly = 1;
gd = alloc_disk(1 << tr->part_bits);
if (!gd) {
list_del(&new->list);
return -ENOMEM;
}
gd->major = tr->major;
gd->first_minor = (new->devnum) << tr->part_bits;
gd->fops = &mtd_blktrans_ops;
if (tr->part_bits)
if (new->devnum < 26)
snprintf(gd->disk_name, sizeof(gd->disk_name),
"%s%c", tr->name, 'a' + new->devnum);
else
snprintf(gd->disk_name, sizeof(gd->disk_name),
"%s%c%c", tr->name,
'a' - 1 + new->devnum / 26,
'a' + new->devnum % 26);
else
snprintf(gd->disk_name, sizeof(gd->disk_name),
"%s%d", tr->name, new->devnum);
/* 2.5 has capacity in units of 512 bytes while still
having BLOCK_SIZE_BITS set to 10. Just to keep us amused. */
set_capacity(gd, (new->size * tr->blksize) >> 9);
gd->private_data = new;
new->blkcore_priv = gd;
gd->queue = tr->blkcore_priv->rq;
gd->driverfs_dev = &new->mtd->dev;
if (new->readonly)
set_disk_ro(gd, 1);
add_disk(gd);
return 0;
}
int del_mtd_blktrans_dev(struct mtd_blktrans_dev *old)
{
if (mutex_trylock(&mtd_table_mutex)) {
mutex_unlock(&mtd_table_mutex);
BUG();
}
list_del(&old->list);
del_gendisk(old->blkcore_priv);
put_disk(old->blkcore_priv);
return 0;
}
static void blktrans_notify_remove(struct mtd_info *mtd)
{
struct mtd_blktrans_ops *tr;
struct mtd_blktrans_dev *dev, *next;
list_for_each_entry(tr, &blktrans_majors, list)
list_for_each_entry_safe(dev, next, &tr->devs, list)
if (dev->mtd == mtd)
tr->remove_dev(dev);
}
static void blktrans_notify_add(struct mtd_info *mtd)
{
struct mtd_blktrans_ops *tr;
if (mtd->type == MTD_ABSENT)
return;
list_for_each_entry(tr, &blktrans_majors, list)
tr->add_mtd(tr, mtd);
}
static struct mtd_notifier blktrans_notifier = {
.add = blktrans_notify_add,
.remove = blktrans_notify_remove,
};
int register_mtd_blktrans(struct mtd_blktrans_ops *tr)
{
int ret, i;
/* Register the notifier if/when the first device type is
registered, to prevent the link/init ordering from fucking
us over. */
if (!blktrans_notifier.list.next)
register_mtd_user(&blktrans_notifier);
tr->blkcore_priv = kzalloc(sizeof(*tr->blkcore_priv), GFP_KERNEL);
if (!tr->blkcore_priv)
return -ENOMEM;
mutex_lock(&mtd_table_mutex);
ret = register_blkdev(tr->major, tr->name);
if (ret) {
printk(KERN_WARNING "Unable to register %s block device on major %d: %d\n",
tr->name, tr->major, ret);
kfree(tr->blkcore_priv);
mutex_unlock(&mtd_table_mutex);
return ret;
}
spin_lock_init(&tr->blkcore_priv->queue_lock);
tr->blkcore_priv->rq = blk_init_queue(mtd_blktrans_request, &tr->blkcore_priv->queue_lock);
if (!tr->blkcore_priv->rq) {
unregister_blkdev(tr->major, tr->name);
kfree(tr->blkcore_priv);
mutex_unlock(&mtd_table_mutex);
return -ENOMEM;
}
tr->blkcore_priv->rq->queuedata = tr;
blk_queue_logical_block_size(tr->blkcore_priv->rq, tr->blksize);
if (tr->discard)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
tr->blkcore_priv->rq);
tr->blkshift = ffs(tr->blksize) - 1;
tr->blkcore_priv->thread = kthread_run(mtd_blktrans_thread, tr,
"%sd", tr->name);
if (IS_ERR(tr->blkcore_priv->thread)) {
int ret = PTR_ERR(tr->blkcore_priv->thread);
blk_cleanup_queue(tr->blkcore_priv->rq);
unregister_blkdev(tr->major, tr->name);
kfree(tr->blkcore_priv);
mutex_unlock(&mtd_table_mutex);
return ret;
}
INIT_LIST_HEAD(&tr->devs);
list_add(&tr->list, &blktrans_majors);
for (i=0; i<MAX_MTD_DEVICES; i++) {
if (mtd_table[i] && mtd_table[i]->type != MTD_ABSENT)
tr->add_mtd(tr, mtd_table[i]);
}
mutex_unlock(&mtd_table_mutex);
return 0;
}
int deregister_mtd_blktrans(struct mtd_blktrans_ops *tr)
{
struct mtd_blktrans_dev *dev, *next;
mutex_lock(&mtd_table_mutex);
/* Clean up the kernel thread */
kthread_stop(tr->blkcore_priv->thread);
/* Remove it from the list of active majors */
list_del(&tr->list);
list_for_each_entry_safe(dev, next, &tr->devs, list)
tr->remove_dev(dev);
blk_cleanup_queue(tr->blkcore_priv->rq);
unregister_blkdev(tr->major, tr->name);
mutex_unlock(&mtd_table_mutex);
kfree(tr->blkcore_priv);
BUG_ON(!list_empty(&tr->devs));
return 0;
}
static void __exit mtd_blktrans_exit(void)
{
/* No race here -- if someone's currently in register_mtd_blktrans
we're screwed anyway. */
if (blktrans_notifier.list.next)
unregister_mtd_user(&blktrans_notifier);
}
module_exit(mtd_blktrans_exit);
EXPORT_SYMBOL_GPL(register_mtd_blktrans);
EXPORT_SYMBOL_GPL(deregister_mtd_blktrans);
EXPORT_SYMBOL_GPL(add_mtd_blktrans_dev);
EXPORT_SYMBOL_GPL(del_mtd_blktrans_dev);
MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Common interface to block layer for MTD 'translation layers'");