*/
#include <linux/module.h>
+#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.h>
#include <linux/raid/bitmap.h>
#include <linux/sysctl.h>
#include <linux/buffer_head.h> /* for invalidate_bdev */
-#include <linux/suspend.h>
#include <linux/poll.h>
#include <linux/mutex.h>
#include <linux/ctype.h>
+#include <linux/freezer.h>
#include <linux/init.h>
atomic_set(&new->active, 1);
spin_lock_init(&new->write_lock);
init_waitqueue_head(&new->sb_wait);
+ new->reshape_position = MaxSector;
new->queue = blk_alloc_queue(GFP_KERNEL);
if (!new->queue) {
if (bio->bi_size)
return 1;
- if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (error || !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
+ printk("md: super_written gets error=%d, uptodate=%d\n",
+ error, test_bit(BIO_UPTODATE, &bio->bi_flags));
+ WARN_ON(test_bit(BIO_UPTODATE, &bio->bi_flags));
md_error(mddev, rdev);
+ }
if (atomic_dec_and_test(&mddev->pending_writes))
wake_up(&mddev->sb_wait);
return ret;
}
+
+static u32 md_csum_fold(u32 csum)
+{
+ csum = (csum & 0xffff) + (csum >> 16);
+ return (csum & 0xffff) + (csum >> 16);
+}
+
static unsigned int calc_sb_csum(mdp_super_t * sb)
{
+ u64 newcsum = 0;
+ u32 *sb32 = (u32*)sb;
+ int i;
unsigned int disk_csum, csum;
disk_csum = sb->sb_csum;
sb->sb_csum = 0;
- csum = csum_partial((void *)sb, MD_SB_BYTES, 0);
+
+ for (i = 0; i < MD_SB_BYTES/4 ; i++)
+ newcsum += sb32[i];
+ csum = (newcsum & 0xffffffff) + (newcsum>>32);
+
+
+#ifdef CONFIG_ALPHA
+ /* This used to use csum_partial, which was wrong for several
+ * reasons including that different results are returned on
+ * different architectures. It isn't critical that we get exactly
+ * the same return value as before (we always csum_fold before
+ * testing, and that removes any differences). However as we
+ * know that csum_partial always returned a 16bit value on
+ * alphas, do a fold to maximise conformity to previous behaviour.
+ */
+ sb->sb_csum = md_csum_fold(disk_csum);
+#else
sb->sb_csum = disk_csum;
+#endif
return csum;
}
if (sb->raid_disks <= 0)
goto abort;
- if (csum_fold(calc_sb_csum(sb)) != csum_fold(sb->sb_csum)) {
+ if (md_csum_fold(calc_sb_csum(sb)) != md_csum_fold(sb->sb_csum)) {
printk(KERN_WARNING "md: invalid superblock checksum on %s\n",
b);
goto abort;
rdev->data_offset = 0;
rdev->sb_size = MD_SB_BYTES;
+ if (sb->state & (1<<MD_SB_BITMAP_PRESENT)) {
+ if (sb->level != 1 && sb->level != 4
+ && sb->level != 5 && sb->level != 6
+ && sb->level != 10) {
+ /* FIXME use a better test */
+ printk(KERN_WARNING
+ "md: bitmaps not supported for this level.\n");
+ goto abort;
+ }
+ }
+
if (sb->level == LEVEL_MULTIPATH)
rdev->desc_nr = -1;
else
mddev->max_disks = MD_SB_DISKS;
if (sb->state & (1<<MD_SB_BITMAP_PRESENT) &&
- mddev->bitmap_file == NULL) {
- if (mddev->level != 1 && mddev->level != 4
- && mddev->level != 5 && mddev->level != 6
- && mddev->level != 10) {
- /* FIXME use a better test */
- printk(KERN_WARNING "md: bitmaps not supported for this level.\n");
- return -EINVAL;
- }
+ mddev->bitmap_file == NULL)
mddev->bitmap_offset = mddev->default_bitmap_offset;
- }
} else if (mddev->pers == NULL) {
/* Insist on good event counter while assembling */
* version 1 superblock
*/
-static unsigned int calc_sb_1_csum(struct mdp_superblock_1 * sb)
+static __le32 calc_sb_1_csum(struct mdp_superblock_1 * sb)
{
- unsigned int disk_csum, csum;
+ __le32 disk_csum;
+ u32 csum;
unsigned long long newcsum;
int size = 256 + le32_to_cpu(sb->max_dev)*2;
- unsigned int *isuper = (unsigned int*)sb;
+ __le32 *isuper = (__le32*)sb;
int i;
disk_csum = sb->sb_csum;
newcsum += le32_to_cpu(*isuper++);
if (size == 2)
- newcsum += le16_to_cpu(*(unsigned short*) isuper);
+ newcsum += le16_to_cpu(*(__le16*) isuper);
csum = (newcsum & 0xffffffff) + (newcsum >> 32);
sb->sb_csum = disk_csum;
bdevname(rdev->bdev,b));
return -EINVAL;
}
+ if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)) {
+ if (sb->level != cpu_to_le32(1) &&
+ sb->level != cpu_to_le32(4) &&
+ sb->level != cpu_to_le32(5) &&
+ sb->level != cpu_to_le32(6) &&
+ sb->level != cpu_to_le32(10)) {
+ printk(KERN_WARNING
+ "md: bitmaps not supported for this level.\n");
+ return -EINVAL;
+ }
+ }
+
rdev->preferred_minor = 0xffff;
rdev->data_offset = le64_to_cpu(sb->data_offset);
atomic_set(&rdev->corrected_errors, le32_to_cpu(sb->cnt_corrected_read));
if (le32_to_cpu(sb->chunksize))
rdev->size &= ~((sector_t)le32_to_cpu(sb->chunksize)/2 - 1);
- if (le32_to_cpu(sb->size) > rdev->size*2)
+ if (le64_to_cpu(sb->size) > rdev->size*2)
return -EINVAL;
return ret;
}
mddev->max_disks = (4096-256)/2;
if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET) &&
- mddev->bitmap_file == NULL ) {
- if (mddev->level != 1 && mddev->level != 5 && mddev->level != 6
- && mddev->level != 10) {
- printk(KERN_WARNING "md: bitmaps not supported for this level.\n");
- return -EINVAL;
- }
+ mddev->bitmap_file == NULL )
mddev->bitmap_offset = (__s32)le32_to_cpu(sb->bitmap_offset);
- }
+
if ((le32_to_cpu(sb->feature_map) & MD_FEATURE_RESHAPE_ACTIVE)) {
mddev->reshape_position = le64_to_cpu(sb->reshape_position);
mddev->delta_disks = le32_to_cpu(sb->delta_disks);
else
sb->resync_offset = cpu_to_le64(0);
- sb->cnt_corrected_read = atomic_read(&rdev->corrected_errors);
+ sb->cnt_corrected_read = cpu_to_le32(atomic_read(&rdev->corrected_errors));
sb->raid_disks = cpu_to_le32(mddev->raid_disks);
sb->size = cpu_to_le64(mddev->size<<1);
ITERATE_RDEV(mddev,rdev2,tmp)
if (rdev2->desc_nr+1 > max_dev)
max_dev = rdev2->desc_nr+1;
-
- sb->max_dev = cpu_to_le32(max_dev);
+
+ if (max_dev > le32_to_cpu(sb->max_dev))
+ sb->max_dev = cpu_to_le32(max_dev);
for (i=0; i<max_dev;i++)
sb->dev_roles[i] = cpu_to_le16(0xfffe);
.sync_super = super_1_sync,
},
};
-
-static mdk_rdev_t * match_dev_unit(mddev_t *mddev, mdk_rdev_t *dev)
-{
- struct list_head *tmp;
- mdk_rdev_t *rdev;
-
- ITERATE_RDEV(mddev,rdev,tmp)
- if (rdev->bdev->bd_contains == dev->bdev->bd_contains)
- return rdev;
-
- return NULL;
-}
static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
{
- struct list_head *tmp;
- mdk_rdev_t *rdev;
+ struct list_head *tmp, *tmp2;
+ mdk_rdev_t *rdev, *rdev2;
ITERATE_RDEV(mddev1,rdev,tmp)
- if (match_dev_unit(mddev2, rdev))
- return 1;
+ ITERATE_RDEV(mddev2, rdev2, tmp2)
+ if (rdev->bdev->bd_contains ==
+ rdev2->bdev->bd_contains)
+ return 1;
return 0;
}
static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
{
- mdk_rdev_t *same_pdev;
- char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ char b[BDEVNAME_SIZE];
struct kobject *ko;
char *s;
+ int err;
if (rdev->mddev) {
MD_BUG();
}
/* make sure rdev->size exceeds mddev->size */
if (rdev->size && (mddev->size == 0 || rdev->size < mddev->size)) {
- if (mddev->pers)
- /* Cannot change size, so fail */
- return -ENOSPC;
- else
+ if (mddev->pers) {
+ /* Cannot change size, so fail
+ * If mddev->level <= 0, then we don't care
+ * about aligning sizes (e.g. linear)
+ */
+ if (mddev->level > 0)
+ return -ENOSPC;
+ } else
mddev->size = rdev->size;
}
- same_pdev = match_dev_unit(mddev, rdev);
- if (same_pdev)
- printk(KERN_WARNING
- "%s: WARNING: %s appears to be on the same physical"
- " disk as %s. True\n protection against single-disk"
- " failure might be compromised.\n",
- mdname(mddev), bdevname(rdev->bdev,b),
- bdevname(same_pdev->bdev,b2));
/* Verify rdev->desc_nr is unique.
* If it is -1, assign a free number, else
while ( (s=strchr(rdev->kobj.k_name, '/')) != NULL)
*s = '!';
- list_add(&rdev->same_set, &mddev->disks);
rdev->mddev = mddev;
printk(KERN_INFO "md: bind<%s>\n", b);
rdev->kobj.parent = &mddev->kobj;
- kobject_add(&rdev->kobj);
+ if ((err = kobject_add(&rdev->kobj)))
+ goto fail;
if (rdev->bdev->bd_part)
ko = &rdev->bdev->bd_part->kobj;
else
ko = &rdev->bdev->bd_disk->kobj;
- sysfs_create_link(&rdev->kobj, ko, "block");
+ if ((err = sysfs_create_link(&rdev->kobj, ko, "block"))) {
+ kobject_del(&rdev->kobj);
+ goto fail;
+ }
+ list_add(&rdev->same_set, &mddev->disks);
bd_claim_by_disk(rdev->bdev, rdev, mddev->gendisk);
return 0;
+
+ fail:
+ printk(KERN_WARNING "md: failed to register dev-%s for %s\n",
+ b, mdname(mddev));
+ return err;
+}
+
+static void delayed_delete(struct work_struct *ws)
+{
+ mdk_rdev_t *rdev = container_of(ws, mdk_rdev_t, del_work);
+ kobject_del(&rdev->kobj);
}
static void unbind_rdev_from_array(mdk_rdev_t * rdev)
printk(KERN_INFO "md: unbind<%s>\n", bdevname(rdev->bdev,b));
rdev->mddev = NULL;
sysfs_remove_link(&rdev->kobj, "block");
- kobject_del(&rdev->kobj);
+
+ /* We need to delay this, otherwise we can deadlock when
+ * writing to 'remove' to "dev/state"
+ */
+ INIT_WORK(&rdev->del_work, delayed_delete);
+ schedule_work(&rdev->del_work);
}
/*
struct block_device *bdev;
char b[BDEVNAME_SIZE];
- bdev = open_partition_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
if (IS_ERR(bdev)) {
printk(KERN_ERR "md: could not open %s.\n",
__bdevname(dev, b));
if (err) {
printk(KERN_ERR "md: could not bd_claim %s.\n",
bdevname(bdev, b));
- blkdev_put_partition(bdev);
+ blkdev_put(bdev);
return err;
}
rdev->bdev = bdev;
if (!bdev)
MD_BUG();
bd_release(bdev);
- blkdev_put_partition(bdev);
+ blkdev_put(bdev);
}
void md_autodetect_dev(dev_t dev);
static void md_update_sb(mddev_t * mddev, int force_change)
{
- int err;
struct list_head *tmp;
mdk_rdev_t *rdev;
int sync_req;
* and 'events' is odd, we can roll back to the previous clean state */
if (nospares
&& (mddev->in_sync && mddev->recovery_cp == MaxSector)
- && (mddev->events & 1))
+ && (mddev->events & 1)
+ && mddev->events != 1)
mddev->events--;
else {
/* otherwise we have to go forward and ... */
"md: updating %s RAID superblock on device (in sync %d)\n",
mdname(mddev),mddev->in_sync);
- err = bitmap_update_sb(mddev->bitmap);
+ bitmap_update_sb(mddev->bitmap);
ITERATE_RDEV(mddev,rdev,tmp) {
char b[BDEVNAME_SIZE];
dprintk(KERN_INFO "md: ");
else {
mddev_t *mddev = rdev->mddev;
kick_rdev_from_array(rdev);
- md_update_sb(mddev, 1);
+ if (mddev->pers)
+ md_update_sb(mddev, 1);
md_new_event(mddev);
err = 0;
}
kobject_init(&rdev->kobj);
rdev->desc_nr = -1;
+ rdev->saved_raid_disk = -1;
+ rdev->raid_disk = -1;
rdev->flags = 0;
rdev->data_offset = 0;
rdev->sb_events = 0;
err = super_types[super_format].
load_super(rdev, NULL, super_minor);
if (err == -EINVAL) {
- printk(KERN_WARNING
- "md: %s has invalid sb, not importing!\n",
- bdevname(rdev->bdev,b));
+ printk(KERN_WARNING
+ "md: %s does not have a valid v%d.%d "
+ "superblock, not importing!\n",
+ bdevname(rdev->bdev,b),
+ super_format, super_minor);
goto abort_free;
}
if (err < 0) {
rdev->desc_nr = i++;
rdev->raid_disk = rdev->desc_nr;
set_bit(In_sync, &rdev->flags);
+ } else if (rdev->raid_disk >= mddev->raid_disks) {
+ rdev->raid_disk = -1;
+ clear_bit(In_sync, &rdev->flags);
}
}
layout_show(mddev_t *mddev, char *page)
{
/* just a number, not meaningful for all levels */
+ if (mddev->reshape_position != MaxSector &&
+ mddev->layout != mddev->new_layout)
+ return sprintf(page, "%d (%d)\n",
+ mddev->new_layout, mddev->layout);
return sprintf(page, "%d\n", mddev->layout);
}
{
char *e;
unsigned long n = simple_strtoul(buf, &e, 10);
- if (mddev->pers)
- return -EBUSY;
if (!*buf || (*e && *e != '\n'))
return -EINVAL;
- mddev->layout = n;
+ if (mddev->pers)
+ return -EBUSY;
+ if (mddev->reshape_position != MaxSector)
+ mddev->new_layout = n;
+ else
+ mddev->layout = n;
return len;
}
static struct md_sysfs_entry md_layout =
{
if (mddev->raid_disks == 0)
return 0;
+ if (mddev->reshape_position != MaxSector &&
+ mddev->delta_disks != 0)
+ return sprintf(page, "%d (%d)\n", mddev->raid_disks,
+ mddev->raid_disks - mddev->delta_disks);
return sprintf(page, "%d\n", mddev->raid_disks);
}
static ssize_t
raid_disks_store(mddev_t *mddev, const char *buf, size_t len)
{
- /* can only set raid_disks if array is not yet active */
char *e;
int rv = 0;
unsigned long n = simple_strtoul(buf, &e, 10);
if (mddev->pers)
rv = update_raid_disks(mddev, n);
- else
+ else if (mddev->reshape_position != MaxSector) {
+ int olddisks = mddev->raid_disks - mddev->delta_disks;
+ mddev->delta_disks = n - olddisks;
+ mddev->raid_disks = n;
+ } else
mddev->raid_disks = n;
return rv ? rv : len;
}
static ssize_t
chunk_size_show(mddev_t *mddev, char *page)
{
+ if (mddev->reshape_position != MaxSector &&
+ mddev->chunk_size != mddev->new_chunk)
+ return sprintf(page, "%d (%d)\n", mddev->new_chunk,
+ mddev->chunk_size);
return sprintf(page, "%d\n", mddev->chunk_size);
}
char *e;
unsigned long n = simple_strtoul(buf, &e, 10);
- if (mddev->pers)
- return -EBUSY;
if (!*buf || (*e && *e != '\n'))
return -EINVAL;
- mddev->chunk_size = n;
+ if (mddev->pers)
+ return -EBUSY;
+ else if (mddev->reshape_position != MaxSector)
+ mddev->new_chunk = n;
+ else
+ mddev->chunk_size = n;
return len;
}
static struct md_sysfs_entry md_chunk_size =
return -EINVAL;
buf = e+1;
minor = simple_strtoul(buf, &e, 10);
- if (e==buf || *e != '\n')
+ if (e==buf || (*e && *e != '\n') )
return -EINVAL;
- if (major >= sizeof(super_types)/sizeof(super_types[0]) ||
- super_types[major].name == NULL)
+ if (major >= ARRAY_SIZE(super_types) || super_types[major].name == NULL)
return -ENOENT;
mddev->major_version = major;
mddev->minor_version = minor;
static struct md_sysfs_entry md_suspend_hi =
__ATTR(suspend_hi, S_IRUGO|S_IWUSR, suspend_hi_show, suspend_hi_store);
+static ssize_t
+reshape_position_show(mddev_t *mddev, char *page)
+{
+ if (mddev->reshape_position != MaxSector)
+ return sprintf(page, "%llu\n",
+ (unsigned long long)mddev->reshape_position);
+ strcpy(page, "none\n");
+ return 5;
+}
+
+static ssize_t
+reshape_position_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *e;
+ unsigned long long new = simple_strtoull(buf, &e, 10);
+ if (mddev->pers)
+ return -EBUSY;
+ if (buf == e || (*e && *e != '\n'))
+ return -EINVAL;
+ mddev->reshape_position = new;
+ mddev->delta_disks = 0;
+ mddev->new_level = mddev->level;
+ mddev->new_layout = mddev->layout;
+ mddev->new_chunk = mddev->chunk_size;
+ return len;
+}
+
+static struct md_sysfs_entry md_reshape_position =
+__ATTR(reshape_position, S_IRUGO|S_IWUSR, reshape_position_show,
+ reshape_position_store);
+
static struct attribute *md_default_attrs[] = {
&md_level.attr,
&md_new_device.attr,
&md_safe_delay.attr,
&md_array_state.attr,
+ &md_reshape_position.attr,
NULL,
};
mddev->kobj.k_name = NULL;
snprintf(mddev->kobj.name, KOBJ_NAME_LEN, "%s", "md");
mddev->kobj.ktype = &md_ktype;
- kobject_register(&mddev->kobj);
+ if (kobject_register(&mddev->kobj))
+ printk(KERN_WARNING "md: cannot register %s/md - name in use\n",
+ disk->disk_name);
return NULL;
}
* Drop all container device buffers, from now on
* the only valid external interface is through the md
* device.
- * Also find largest hardsector size
*/
ITERATE_RDEV(mddev,rdev,tmp) {
if (test_bit(Faulty, &rdev->flags))
continue;
sync_blockdev(rdev->bdev);
- invalidate_bdev(rdev->bdev, 0);
+ invalidate_bdev(rdev->bdev);
+
+ /* perform some consistency tests on the device.
+ * We don't want the data to overlap the metadata,
+ * Internal Bitmap issues has handled elsewhere.
+ */
+ if (rdev->data_offset < rdev->sb_offset) {
+ if (mddev->size &&
+ rdev->data_offset + mddev->size*2
+ > rdev->sb_offset*2) {
+ printk("md: %s: data overlaps metadata\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ } else {
+ if (rdev->sb_offset*2 + rdev->sb_size/512
+ > rdev->data_offset) {
+ printk("md: %s: metadata overlaps data\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ }
}
md_probe(mddev->unit, NULL, NULL);
return -EINVAL;
}
+ if (pers->sync_request) {
+ /* Warn if this is a potentially silly
+ * configuration.
+ */
+ char b[BDEVNAME_SIZE], b2[BDEVNAME_SIZE];
+ mdk_rdev_t *rdev2;
+ struct list_head *tmp2;
+ int warned = 0;
+ ITERATE_RDEV(mddev, rdev, tmp) {
+ ITERATE_RDEV(mddev, rdev2, tmp2) {
+ if (rdev < rdev2 &&
+ rdev->bdev->bd_contains ==
+ rdev2->bdev->bd_contains) {
+ printk(KERN_WARNING
+ "%s: WARNING: %s appears to be"
+ " on the same physical disk as"
+ " %s.\n",
+ mdname(mddev),
+ bdevname(rdev->bdev,b),
+ bdevname(rdev2->bdev,b2));
+ warned = 1;
+ }
+ }
+ }
+ if (warned)
+ printk(KERN_WARNING
+ "True protection against single-disk"
+ " failure might be compromised.\n");
+ }
+
mddev->recovery = 0;
mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
mddev->barriers_work = 1;
bitmap_destroy(mddev);
return err;
}
- if (mddev->pers->sync_request)
- sysfs_create_group(&mddev->kobj, &md_redundancy_group);
- else if (mddev->ro == 2) /* auto-readonly not meaningful */
+ if (mddev->pers->sync_request) {
+ if (sysfs_create_group(&mddev->kobj, &md_redundancy_group))
+ printk(KERN_WARNING
+ "md: cannot register extra attributes for %s\n",
+ mdname(mddev));
+ } else if (mddev->ro == 2) /* auto-readonly not meaningful */
mddev->ro = 0;
atomic_set(&mddev->writes_pending,0);
if (rdev->raid_disk >= 0) {
char nm[20];
sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+ if (sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
+ printk("md: cannot register %s for %s\n",
+ nm, mdname(mddev));
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
mddev->changed = 1;
md_new_event(mddev);
+ kobject_uevent(&mddev->gendisk->kobj, KOBJ_CHANGE);
return 0;
}
set_disk_ro(disk, 0);
blk_queue_make_request(mddev->queue, md_fail_request);
mddev->pers->stop(mddev);
+ mddev->queue->merge_bvec_fn = NULL;
+ mddev->queue->unplug_fn = NULL;
+ mddev->queue->issue_flush_fn = NULL;
+ mddev->queue->backing_dev_info.congested_fn = NULL;
if (mddev->pers->sync_request)
sysfs_remove_group(&mddev->kobj, &md_redundancy_group);
module_put(mddev->pers->owner);
mddev->pers = NULL;
+
+ set_capacity(disk, 0);
+ mddev->changed = 1;
+
if (mddev->ro)
mddev->ro = 0;
}
if (mode == 0) {
mdk_rdev_t *rdev;
struct list_head *tmp;
- struct gendisk *disk;
+
printk(KERN_INFO "md: %s stopped.\n", mdname(mddev));
bitmap_destroy(mddev);
sysfs_remove_link(&mddev->kobj, nm);
}
+ /* make sure all delayed_delete calls have finished */
+ flush_scheduled_work();
+
export_array(mddev);
mddev->array_size = 0;
mddev->size = 0;
mddev->raid_disks = 0;
mddev->recovery_cp = 0;
+ mddev->reshape_position = MaxSector;
- disk = mddev->gendisk;
- if (disk)
- set_capacity(disk, 0);
- mddev->changed = 1;
} else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
return err;
}
+#ifndef MODULE
static void autorun_array(mddev_t *mddev)
{
mdk_rdev_t *rdev;
}
printk(KERN_INFO "md: ... autorun DONE.\n");
}
+#endif /* !MODULE */
static int get_version(void __user * arg)
{
char *ptr, *buf = NULL;
int err = -ENOMEM;
+ md_allow_write(mddev);
+
file = kmalloc(sizeof(*file), GFP_KERNEL);
if (!file)
goto out;
if (err)
export_rdev(rdev);
+ md_update_sb(mddev, 1);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return err;
}
clear_bit(In_sync, &rdev->flags);
rdev->desc_nr = -1;
+ rdev->saved_raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
if (err)
goto abort_export;
if (info->raid_disks == 0) {
/* just setting version number for superblock loading */
if (info->major_version < 0 ||
- info->major_version >= sizeof(super_types)/sizeof(super_types[0]) ||
+ info->major_version >= ARRAY_SIZE(super_types) ||
super_types[info->major_version].name == NULL) {
/* maybe try to auto-load a module? */
printk(KERN_INFO
mddev->major_version = info->major_version;
mddev->minor_version = info->minor_version;
mddev->patch_version = info->patch_version;
+ mddev->persistent = !info->not_persistent;
return 0;
}
mddev->major_version = MD_MAJOR_VERSION;
return -EBUSY;
ITERATE_RDEV(mddev,rdev,tmp) {
sector_t avail;
- if (rdev->sb_offset > rdev->data_offset)
- avail = (rdev->sb_offset*2) - rdev->data_offset;
- else
- avail = get_capacity(rdev->bdev->bd_disk)
- - rdev->data_offset;
+ avail = rdev->size * 2;
+
if (fit && (size == 0 || size > avail/2))
size = avail/2;
if (avail < ((sector_t)size << 1))
* Commands querying/configuring an existing array:
*/
/* if we are not initialised yet, only ADD_NEW_DISK, STOP_ARRAY,
- * RUN_ARRAY, and SET_BITMAP_FILE are allowed */
+ * RUN_ARRAY, and GET_ and SET_BITMAP_FILE are allowed */
if (!mddev->raid_disks && cmd != ADD_NEW_DISK && cmd != STOP_ARRAY
- && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE) {
+ && cmd != RUN_ARRAY && cmd != SET_BITMAP_FILE
+ && cmd != GET_BITMAP_FILE) {
err = -ENODEV;
goto abort_unlock;
}
mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
int err;
- if ((err = mddev_lock(mddev)))
+ if ((err = mutex_lock_interruptible_nested(&mddev->reconfig_mutex, 1)))
goto out;
err = 0;
{
mddev_t *mddev = inode->i_bdev->bd_disk->private_data;
- if (!mddev)
- BUG();
+ BUG_ON(!mddev);
mddev_put(mddev);
return 0;
test_bit(THREAD_WAKEUP, &thread->flags)
|| kthread_should_stop(),
thread->timeout);
- try_to_freeze();
clear_bit(THREAD_WAKEUP, &thread->flags);
chunk_kb ? "KB" : "B");
if (bitmap->file) {
seq_printf(seq, ", file: ");
- seq_path(seq, bitmap->file->f_vfsmnt,
- bitmap->file->f_dentry," \t\n");
+ seq_path(seq, bitmap->file->f_path.mnt,
+ bitmap->file->f_path.dentry," \t\n");
}
seq_printf(seq, "\n");
return error;
}
-static int md_seq_release(struct inode *inode, struct file *file)
-{
- struct seq_file *m = file->private_data;
- struct mdstat_info *mi = m->private;
- m->private = NULL;
- kfree(mi);
- return seq_release(inode, file);
-}
-
static unsigned int mdstat_poll(struct file *filp, poll_table *wait)
{
struct seq_file *m = filp->private_data;
return mask;
}
-static struct file_operations md_seq_fops = {
+static const struct file_operations md_seq_fops = {
+ .owner = THIS_MODULE,
.open = md_seq_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = md_seq_release,
+ .release = seq_release_private,
.poll = mdstat_poll,
};
mdk_rdev_t * rdev;
struct list_head *tmp;
int idle;
- unsigned long curr_events;
+ long curr_events;
idle = 1;
ITERATE_RDEV(mddev,rdev,tmp) {
curr_events = disk_stat_read(disk, sectors[0]) +
disk_stat_read(disk, sectors[1]) -
atomic_read(&disk->sync_io);
- /* The difference between curr_events and last_events
- * will be affected by any new non-sync IO (making
- * curr_events bigger) and any difference in the amount of
- * in-flight syncio (making current_events bigger or smaller)
- * The amount in-flight is currently limited to
- * 32*64K in raid1/10 and 256*PAGE_SIZE in raid5/6
- * which is at most 4096 sectors.
- * These numbers are fairly fragile and should be made
- * more robust, probably by enforcing the
- * 'window size' that md_do_sync sort-of uses.
+ /* sync IO will cause sync_io to increase before the disk_stats
+ * as sync_io is counted when a request starts, and
+ * disk_stats is counted when it completes.
+ * So resync activity will cause curr_events to be smaller than
+ * when there was no such activity.
+ * non-sync IO will cause disk_stat to increase without
+ * increasing sync_io so curr_events will (eventually)
+ * be larger than it was before. Once it becomes
+ * substantially larger, the test below will cause
+ * the array to appear non-idle, and resync will slow
+ * down.
+ * If there is a lot of outstanding resync activity when
+ * we set last_event to curr_events, then all that activity
+ * completing might cause the array to appear non-idle
+ * and resync will be slowed down even though there might
+ * not have been non-resync activity. This will only
+ * happen once though. 'last_events' will soon reflect
+ * the state where there is little or no outstanding
+ * resync requests, and further resync activity will
+ * always make curr_events less than last_events.
*
- * Note: the following is an unsigned comparison.
*/
- if ((curr_events - rdev->last_events + 4096) > 8192) {
+ if (curr_events - rdev->last_events > 4096) {
rdev->last_events = curr_events;
idle = 0;
}
}
}
+/* md_allow_write(mddev)
+ * Calling this ensures that the array is marked 'active' so that writes
+ * may proceed without blocking. It is important to call this before
+ * attempting a GFP_KERNEL allocation while holding the mddev lock.
+ * Must be called with mddev_lock held.
+ */
+void md_allow_write(mddev_t *mddev)
+{
+ if (!mddev->pers)
+ return;
+ if (mddev->ro)
+ return;
+
+ spin_lock_irq(&mddev->write_lock);
+ if (mddev->in_sync) {
+ mddev->in_sync = 0;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ if (mddev->safemode_delay &&
+ mddev->safemode == 0)
+ mddev->safemode = 1;
+ spin_unlock_irq(&mddev->write_lock);
+ md_update_sb(mddev, 0);
+ } else
+ spin_unlock_irq(&mddev->write_lock);
+}
+EXPORT_SYMBOL_GPL(md_allow_write);
+
static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
#define SYNC_MARKS 10
mddev->pers->sync_request(mddev, max_sectors, &skipped, 1);
if (!test_bit(MD_RECOVERY_ERR, &mddev->recovery) &&
- test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
!test_bit(MD_RECOVERY_CHECK, &mddev->recovery) &&
mddev->curr_resync > 2) {
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
rdev->recovery_offset = mddev->curr_resync;
}
}
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
skip:
mddev->curr_resync = 0;
EXPORT_SYMBOL_GPL(md_do_sync);
+static int remove_and_add_spares(mddev_t *mddev)
+{
+ mdk_rdev_t *rdev;
+ struct list_head *rtmp;
+ int spares = 0;
+
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ (test_bit(Faulty, &rdev->flags) ||
+ ! test_bit(In_sync, &rdev->flags)) &&
+ atomic_read(&rdev->nr_pending)==0) {
+ if (mddev->pers->hot_remove_disk(
+ mddev, rdev->raid_disk)==0) {
+ char nm[20];
+ sprintf(nm,"rd%d", rdev->raid_disk);
+ sysfs_remove_link(&mddev->kobj, nm);
+ rdev->raid_disk = -1;
+ }
+ }
+
+ if (mddev->degraded) {
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk < 0
+ && !test_bit(Faulty, &rdev->flags)) {
+ rdev->recovery_offset = 0;
+ if (mddev->pers->hot_add_disk(mddev,rdev)) {
+ char nm[20];
+ sprintf(nm, "rd%d", rdev->raid_disk);
+ if (sysfs_create_link(&mddev->kobj,
+ &rdev->kobj, nm))
+ printk(KERN_WARNING
+ "md: cannot register "
+ "%s for %s\n",
+ nm, mdname(mddev));
+ spares++;
+ md_new_event(mddev);
+ } else
+ break;
+ }
+ }
+ return spares;
+}
/*
* This routine is regularly called by all per-raid-array threads to
* deal with generic issues like resync and super-block update.
return;
if (mddev_trylock(mddev)) {
- int spares =0;
+ int spares = 0;
spin_lock_irq(&mddev->write_lock);
if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
* Spare are also removed and re-added, to allow
* the personality to fail the re-add.
*/
- ITERATE_RDEV(mddev,rdev,rtmp)
- if (rdev->raid_disk >= 0 &&
- (test_bit(Faulty, &rdev->flags) || ! test_bit(In_sync, &rdev->flags)) &&
- atomic_read(&rdev->nr_pending)==0) {
- if (mddev->pers->hot_remove_disk(mddev, rdev->raid_disk)==0) {
- char nm[20];
- sprintf(nm,"rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
- rdev->raid_disk = -1;
- }
- }
- if (mddev->degraded) {
- ITERATE_RDEV(mddev,rdev,rtmp)
- if (rdev->raid_disk < 0
- && !test_bit(Faulty, &rdev->flags)) {
- rdev->recovery_offset = 0;
- if (mddev->pers->hot_add_disk(mddev,rdev)) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
- spares++;
- md_new_event(mddev);
- } else
- break;
- }
- }
-
- if (spares) {
+ if (mddev->reshape_position != MaxSector) {
+ if (mddev->pers->check_reshape(mddev) != 0)
+ /* Cannot proceed */
+ goto unlock;
+ set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+ } else if ((spares = remove_and_add_spares(mddev))) {
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
} else if (mddev->recovery_cp < MaxSector) {
md_probe, NULL, NULL);
register_reboot_notifier(&md_notifier);
- raid_table_header = register_sysctl_table(raid_root_table, 1);
+ raid_table_header = register_sysctl_table(raid_root_table);
md_geninit();
return (0);
for (i = 0; i < dev_cnt; i++) {
dev_t dev = detected_devices[i];
- rdev = md_import_device(dev,0, 0);
+ rdev = md_import_device(dev,0, 90);
if (IS_ERR(rdev))
continue;
autorun_devices(part);
}
-#endif
+#endif /* !MODULE */
static __exit void md_exit(void)
{
}
}
-module_init(md_init)
+subsys_initcall(md_init);
module_exit(md_exit)
static int get_ro(char *buffer, struct kernel_param *kp)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff