/*
* Copyright (C) 2001 Sistina Software (UK) Limited.
+ * Copyright (C) 2004 Red Hat, Inc. All rights reserved.
*
* This file is released under the GPL.
*/
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
+#include <linux/mutex.h>
#include <asm/atomic.h>
+#define DM_MSG_PREFIX "table"
+
#define MAX_DEPTH 16
#define NODE_SIZE L1_CACHE_BYTES
#define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t))
#define CHILDREN_PER_NODE (KEYS_PER_NODE + 1)
struct dm_table {
+ struct mapped_device *md;
atomic_t holders;
/* btree table */
/*
* Similar to ceiling(log_size(n))
*/
-static unsigned int int_log(unsigned long n, unsigned long base)
+static unsigned int int_log(unsigned int n, unsigned int base)
{
int result = 0;
lhs->seg_boundary_mask =
min_not_zero(lhs->seg_boundary_mask, rhs->seg_boundary_mask);
+
+ lhs->no_cluster |= rhs->no_cluster;
}
/*
return 0;
}
-int dm_table_create(struct dm_table **result, int mode, unsigned num_targets)
+int dm_table_create(struct dm_table **result, int mode,
+ unsigned num_targets, struct mapped_device *md)
{
struct dm_table *t = kmalloc(sizeof(*t), GFP_KERNEL);
}
t->mode = mode;
+ t->md = md;
*result = t;
return 0;
}
+int dm_create_error_table(struct dm_table **result, struct mapped_device *md)
+{
+ struct dm_table *t;
+ sector_t dev_size = 1;
+ int r;
+
+ /*
+ * Find current size of device.
+ * Default to 1 sector if inactive.
+ */
+ t = dm_get_table(md);
+ if (t) {
+ dev_size = dm_table_get_size(t);
+ dm_table_put(t);
+ }
+
+ r = dm_table_create(&t, FMODE_READ, 1, md);
+ if (r)
+ return r;
+
+ r = dm_table_add_target(t, "error", 0, dev_size, NULL);
+ if (r)
+ goto out;
+
+ r = dm_table_complete(t);
+ if (r)
+ goto out;
+
+ *result = t;
+
+out:
+ if (r)
+ dm_table_put(t);
+
+ return r;
+}
+EXPORT_SYMBOL_GPL(dm_create_error_table);
+
static void free_devices(struct list_head *devices)
{
struct list_head *tmp, *next;
}
}
-void table_destroy(struct dm_table *t)
+static void table_destroy(struct dm_table *t)
{
unsigned int i;
/*
* Open a device so we can use it as a map destination.
*/
-static int open_dev(struct dm_dev *d, dev_t dev)
+static int open_dev(struct dm_dev *d, dev_t dev, struct mapped_device *md)
{
static char *_claim_ptr = "I belong to device-mapper";
struct block_device *bdev;
int r;
- if (d->bdev)
- BUG();
+ BUG_ON(d->bdev);
bdev = open_by_devnum(dev, d->mode);
if (IS_ERR(bdev))
return PTR_ERR(bdev);
- r = bd_claim(bdev, _claim_ptr);
+ r = bd_claim_by_disk(bdev, _claim_ptr, dm_disk(md));
if (r)
blkdev_put(bdev);
else
/*
* Close a device that we've been using.
*/
-static void close_dev(struct dm_dev *d)
+static void close_dev(struct dm_dev *d, struct mapped_device *md)
{
if (!d->bdev)
return;
- bd_release(d->bdev);
+ bd_release_from_disk(d->bdev, dm_disk(md));
blkdev_put(d->bdev);
d->bdev = NULL;
}
* careful to leave things as they were if we fail to reopen the
* device.
*/
-static int upgrade_mode(struct dm_dev *dd, int new_mode)
+static int upgrade_mode(struct dm_dev *dd, int new_mode, struct mapped_device *md)
{
int r;
struct dm_dev dd_copy;
dd->mode |= new_mode;
dd->bdev = NULL;
- r = open_dev(dd, dev);
+ r = open_dev(dd, dev, md);
if (!r)
- close_dev(&dd_copy);
+ close_dev(&dd_copy, md);
else
*dd = dd_copy;
struct dm_dev *dd;
unsigned int major, minor;
- if (!t)
- BUG();
+ BUG_ON(!t);
if (sscanf(path, "%u:%u", &major, &minor) == 2) {
/* Extract the major/minor numbers */
dd->mode = mode;
dd->bdev = NULL;
- if ((r = open_dev(dd, dev))) {
+ if ((r = open_dev(dd, dev, t->md))) {
kfree(dd);
return r;
}
+ format_dev_t(dd->name, dev);
+
atomic_set(&dd->count, 0);
list_add(&dd->list, &t->devices);
} else if (dd->mode != (mode | dd->mode)) {
- r = upgrade_mode(dd, mode);
+ r = upgrade_mode(dd, mode, t->md);
if (r)
return r;
}
return 0;
}
+void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
+{
+ request_queue_t *q = bdev_get_queue(bdev);
+ struct io_restrictions *rs = &ti->limits;
+
+ /*
+ * Combine the device limits low.
+ *
+ * FIXME: if we move an io_restriction struct
+ * into q this would just be a call to
+ * combine_restrictions_low()
+ */
+ rs->max_sectors =
+ min_not_zero(rs->max_sectors, q->max_sectors);
+
+ /* FIXME: Device-Mapper on top of RAID-0 breaks because DM
+ * currently doesn't honor MD's merge_bvec_fn routine.
+ * In this case, we'll force DM to use PAGE_SIZE or
+ * smaller I/O, just to be safe. A better fix is in the
+ * works, but add this for the time being so it will at
+ * least operate correctly.
+ */
+ if (q->merge_bvec_fn)
+ rs->max_sectors =
+ min_not_zero(rs->max_sectors,
+ (unsigned int) (PAGE_SIZE >> 9));
+
+ rs->max_phys_segments =
+ min_not_zero(rs->max_phys_segments,
+ q->max_phys_segments);
+
+ rs->max_hw_segments =
+ min_not_zero(rs->max_hw_segments, q->max_hw_segments);
+
+ rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
+
+ rs->max_segment_size =
+ min_not_zero(rs->max_segment_size, q->max_segment_size);
+
+ rs->seg_boundary_mask =
+ min_not_zero(rs->seg_boundary_mask,
+ q->seg_boundary_mask);
+
+ rs->no_cluster |= !test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+}
+EXPORT_SYMBOL_GPL(dm_set_device_limits);
int dm_get_device(struct dm_target *ti, const char *path, sector_t start,
sector_t len, int mode, struct dm_dev **result)
{
int r = __table_get_device(ti->table, ti, path,
start, len, mode, result);
- if (!r) {
- request_queue_t *q = bdev_get_queue((*result)->bdev);
- struct io_restrictions *rs = &ti->limits;
-
- /*
- * Combine the device limits low.
- *
- * FIXME: if we move an io_restriction struct
- * into q this would just be a call to
- * combine_restrictions_low()
- */
- rs->max_sectors =
- min_not_zero(rs->max_sectors, q->max_sectors);
-
- /* FIXME: Device-Mapper on top of RAID-0 breaks because DM
- * currently doesn't honor MD's merge_bvec_fn routine.
- * In this case, we'll force DM to use PAGE_SIZE or
- * smaller I/O, just to be safe. A better fix is in the
- * works, but add this for the time being so it will at
- * least operate correctly.
- */
- if (q->merge_bvec_fn)
- rs->max_sectors =
- min_not_zero(rs->max_sectors,
- (unsigned short)(PAGE_SIZE >> 9));
-
- rs->max_phys_segments =
- min_not_zero(rs->max_phys_segments,
- q->max_phys_segments);
-
- rs->max_hw_segments =
- min_not_zero(rs->max_hw_segments, q->max_hw_segments);
-
- rs->hardsect_size = max(rs->hardsect_size, q->hardsect_size);
-
- rs->max_segment_size =
- min_not_zero(rs->max_segment_size, q->max_segment_size);
-
- rs->seg_boundary_mask =
- min_not_zero(rs->seg_boundary_mask,
- q->seg_boundary_mask);
- }
+
+ if (!r)
+ dm_set_device_limits(ti, (*result)->bdev);
return r;
}
void dm_put_device(struct dm_target *ti, struct dm_dev *dd)
{
if (atomic_dec_and_test(&dd->count)) {
- close_dev(dd);
+ close_dev(dd, ti->table->md);
list_del(&dd->list);
kfree(dd);
}
/*
* Destructively splits up the argument list to pass to ctr.
*/
-static int split_args(int *argc, char ***argvp, char *input)
+int dm_split_args(int *argc, char ***argvp, char *input)
{
char *start, *end = input, *out, **argv = NULL;
unsigned array_size = 0;
*argc = 0;
+
+ if (!input) {
+ *argvp = NULL;
+ return 0;
+ }
+
argv = realloc_argv(&array_size, argv);
if (!argv)
return -ENOMEM;
static void check_for_valid_limits(struct io_restrictions *rs)
{
if (!rs->max_sectors)
- rs->max_sectors = MAX_SECTORS;
+ rs->max_sectors = SAFE_MAX_SECTORS;
if (!rs->max_phys_segments)
rs->max_phys_segments = MAX_PHYS_SEGMENTS;
if (!rs->max_hw_segments)
memset(tgt, 0, sizeof(*tgt));
if (!len) {
- tgt->error = "zero-length target";
- DMERR(": %s\n", tgt->error);
+ DMERR("%s: zero-length target", dm_device_name(t->md));
return -EINVAL;
}
tgt->type = dm_get_target_type(type);
if (!tgt->type) {
- tgt->error = "unknown target type";
- DMERR(": %s\n", tgt->error);
+ DMERR("%s: %s: unknown target type", dm_device_name(t->md),
+ type);
return -EINVAL;
}
goto bad;
}
- r = split_args(&argc, &argv, params);
+ r = dm_split_args(&argc, &argv, params);
if (r) {
tgt->error = "couldn't split parameters (insufficient memory)";
goto bad;
return 0;
bad:
- DMERR(": %s\n", tgt->error);
+ DMERR("%s: %s: %s", dm_device_name(t->md), type, tgt->error);
dm_put_target_type(tgt->type);
return r;
}
return r;
}
-static DECLARE_MUTEX(_event_lock);
+static DEFINE_MUTEX(_event_lock);
void dm_table_event_callback(struct dm_table *t,
void (*fn)(void *), void *context)
{
- down(&_event_lock);
+ mutex_lock(&_event_lock);
t->event_fn = fn;
t->event_context = context;
- up(&_event_lock);
+ mutex_unlock(&_event_lock);
}
void dm_table_event(struct dm_table *t)
*/
BUG_ON(in_interrupt());
- down(&_event_lock);
+ mutex_lock(&_event_lock);
if (t->event_fn)
t->event_fn(t->event_context);
- up(&_event_lock);
+ mutex_unlock(&_event_lock);
}
sector_t dm_table_get_size(struct dm_table *t)
struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index)
{
- if (index > t->num_targets)
+ if (index >= t->num_targets)
return NULL;
return t->targets + index;
* Make sure we obey the optimistic sub devices
* restrictions.
*/
- q->max_sectors = t->limits.max_sectors;
+ blk_queue_max_sectors(q, t->limits.max_sectors);
q->max_phys_segments = t->limits.max_phys_segments;
q->max_hw_segments = t->limits.max_hw_segments;
q->hardsect_size = t->limits.hardsect_size;
q->max_segment_size = t->limits.max_segment_size;
q->seg_boundary_mask = t->limits.seg_boundary_mask;
+ if (t->limits.no_cluster)
+ q->queue_flags &= ~(1 << QUEUE_FLAG_CLUSTER);
+ else
+ q->queue_flags |= (1 << QUEUE_FLAG_CLUSTER);
+
}
unsigned int dm_table_get_num_targets(struct dm_table *t)
return t->mode;
}
-void dm_table_suspend_targets(struct dm_table *t)
+static void suspend_targets(struct dm_table *t, unsigned postsuspend)
{
- int i;
+ int i = t->num_targets;
+ struct dm_target *ti = t->targets;
- for (i = 0; i < t->num_targets; i++) {
- struct dm_target *ti = t->targets + i;
+ while (i--) {
+ if (postsuspend) {
+ if (ti->type->postsuspend)
+ ti->type->postsuspend(ti);
+ } else if (ti->type->presuspend)
+ ti->type->presuspend(ti);
- if (ti->type->suspend)
- ti->type->suspend(ti);
+ ti++;
}
}
-void dm_table_resume_targets(struct dm_table *t)
+void dm_table_presuspend_targets(struct dm_table *t)
{
- int i;
+ if (!t)
+ return;
+
+ return suspend_targets(t, 0);
+}
+
+void dm_table_postsuspend_targets(struct dm_table *t)
+{
+ if (!t)
+ return;
+
+ return suspend_targets(t, 1);
+}
+
+int dm_table_resume_targets(struct dm_table *t)
+{
+ int i, r = 0;
+
+ for (i = 0; i < t->num_targets; i++) {
+ struct dm_target *ti = t->targets + i;
+
+ if (!ti->type->preresume)
+ continue;
+
+ r = ti->type->preresume(ti);
+ if (r)
+ return r;
+ }
for (i = 0; i < t->num_targets; i++) {
struct dm_target *ti = t->targets + i;
if (ti->type->resume)
ti->type->resume(ti);
}
+
+ return 0;
}
int dm_table_any_congested(struct dm_table *t, int bdi_bits)
}
}
+int dm_table_flush_all(struct dm_table *t)
+{
+ struct list_head *d, *devices = dm_table_get_devices(t);
+ int ret = 0;
+ unsigned i;
+
+ for (i = 0; i < t->num_targets; i++)
+ if (t->targets[i].type->flush)
+ t->targets[i].type->flush(&t->targets[i]);
+
+ for (d = devices->next; d != devices; d = d->next) {
+ struct dm_dev *dd = list_entry(d, struct dm_dev, list);
+ request_queue_t *q = bdev_get_queue(dd->bdev);
+ int err;
+
+ if (!q->issue_flush_fn)
+ err = -EOPNOTSUPP;
+ else
+ err = q->issue_flush_fn(q, dd->bdev->bd_disk, NULL);
+
+ if (!ret)
+ ret = err;
+ }
+
+ return ret;
+}
+
+struct mapped_device *dm_table_get_md(struct dm_table *t)
+{
+ dm_get(t->md);
+
+ return t->md;
+}
+
EXPORT_SYMBOL(dm_vcalloc);
EXPORT_SYMBOL(dm_get_device);
EXPORT_SYMBOL(dm_put_device);
EXPORT_SYMBOL(dm_table_event);
+EXPORT_SYMBOL(dm_table_get_size);
EXPORT_SYMBOL(dm_table_get_mode);
+EXPORT_SYMBOL(dm_table_get_md);
EXPORT_SYMBOL(dm_table_put);
EXPORT_SYMBOL(dm_table_get);
EXPORT_SYMBOL(dm_table_unplug_all);
+EXPORT_SYMBOL(dm_table_flush_all);