*/
#include <linux/module.h>
+#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/linkage.h>
#include <linux/raid/md.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) {
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 */
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));
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);
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);
}
/* 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;
}
static void md_update_sb(mddev_t * mddev, int force_change)
{
- int err;
struct list_head *tmp;
mdk_rdev_t *rdev;
int sync_req;
"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: ");
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);
}
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 =
minor = simple_strtoul(buf, &e, 10);
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,
};
* 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);
+
+ /* 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);
mddev->size = 0;
mddev->raid_disks = 0;
mddev->recovery_cp = 0;
+ mddev->reshape_position = MaxSector;
} else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
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
* many dirty RAID5 blocks.
*/
- current->flags |= PF_NOFREEZE;
allow_signal(SIGKILL);
while (!kthread_should_stop()) {
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;
.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;
}
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;
}
}
-module_init(md_init)
+subsys_initcall(md_init);
module_exit(md_exit)
static int get_ro(char *buffer, struct kernel_param *kp)