#include <linux/suspend.h>
#include <linux/poll.h>
#include <linux/mutex.h>
+#include <linux/ctype.h>
#include <linux/init.h>
static LIST_HEAD(pers_list);
static DEFINE_SPINLOCK(pers_lock);
+static void md_print_devices(void);
+
+#define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
+
/*
* Current RAID-1,4,5 parallel reconstruction 'guaranteed speed limit'
* is 1000 KB/sec, so the extra system load does not show up that much.
}
EXPORT_SYMBOL_GPL(md_new_event);
+/* Alternate version that can be called from interrupts
+ * when calling sysfs_notify isn't needed.
+ */
+void md_new_event_inintr(mddev_t *mddev)
+{
+ atomic_inc(&md_event_count);
+ wake_up(&md_event_waiters);
+}
+
/*
* Enables to iterate over all existing md arrays
* all_mddevs_lock protects this list.
if (desc->state & (1<<MD_DISK_FAULTY))
set_bit(Faulty, &rdev->flags);
- else if (desc->state & (1<<MD_DISK_SYNC) &&
- desc->raid_disk < mddev->raid_disks) {
+ else if (desc->state & (1<<MD_DISK_SYNC) /* &&
+ desc->raid_disk < mddev->raid_disks */) {
set_bit(In_sync, &rdev->flags);
rdev->raid_disk = desc->raid_disk;
}
set_bit(Faulty, &rdev->flags);
break;
default:
- set_bit(In_sync, &rdev->flags);
+ if ((le32_to_cpu(sb->feature_map) &
+ MD_FEATURE_RECOVERY_OFFSET))
+ rdev->recovery_offset = le64_to_cpu(sb->recovery_offset);
+ else
+ set_bit(In_sync, &rdev->flags);
rdev->raid_disk = role;
break;
}
sb->feature_map = 0;
sb->pad0 = 0;
+ sb->recovery_offset = cpu_to_le64(0);
memset(sb->pad1, 0, sizeof(sb->pad1));
memset(sb->pad2, 0, sizeof(sb->pad2));
memset(sb->pad3, 0, sizeof(sb->pad3));
sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
sb->feature_map = cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
}
+
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset > 0) {
+ sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
+ sb->recovery_offset = cpu_to_le64(rdev->recovery_offset);
+ }
+
if (mddev->reshape_position != MaxSector) {
sb->feature_map |= cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
sb->reshape_position = cpu_to_le64(mddev->reshape_position);
sb->dev_roles[i] = cpu_to_le16(0xfffe);
else if (test_bit(In_sync, &rdev2->flags))
sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
+ else if (rdev2->raid_disk >= 0 && rdev2->recovery_offset > 0)
+ sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk);
else
sb->dev_roles[i] = cpu_to_le16(0xffff);
}
- sb->recovery_offset = cpu_to_le64(0); /* not supported yet */
sb->sb_csum = calc_sb_1_csum(sb);
}
printk(KERN_INFO "md: no rdev superblock!\n");
}
-void md_print_devices(void)
+static void md_print_devices(void)
{
struct list_head *tmp, *tmp2;
mdk_rdev_t *rdev;
}
+static ssize_t
+safe_delay_show(mddev_t *mddev, char *page)
+{
+ int msec = (mddev->safemode_delay*1000)/HZ;
+ return sprintf(page, "%d.%03d\n", msec/1000, msec%1000);
+}
+static ssize_t
+safe_delay_store(mddev_t *mddev, const char *cbuf, size_t len)
+{
+ int scale=1;
+ int dot=0;
+ int i;
+ unsigned long msec;
+ char buf[30];
+ char *e;
+ /* remove a period, and count digits after it */
+ if (len >= sizeof(buf))
+ return -EINVAL;
+ strlcpy(buf, cbuf, len);
+ buf[len] = 0;
+ for (i=0; i<len; i++) {
+ if (dot) {
+ if (isdigit(buf[i])) {
+ buf[i-1] = buf[i];
+ scale *= 10;
+ }
+ buf[i] = 0;
+ } else if (buf[i] == '.') {
+ dot=1;
+ buf[i] = 0;
+ }
+ }
+ msec = simple_strtoul(buf, &e, 10);
+ if (e == buf || (*e && *e != '\n'))
+ return -EINVAL;
+ msec = (msec * 1000) / scale;
+ if (msec == 0)
+ mddev->safemode_delay = 0;
+ else {
+ mddev->safemode_delay = (msec*HZ)/1000;
+ if (mddev->safemode_delay == 0)
+ mddev->safemode_delay = 1;
+ }
+ return len;
+}
+static struct md_sysfs_entry md_safe_delay =
+__ATTR(safe_mode_delay, 0644,safe_delay_show, safe_delay_store);
+
static ssize_t
level_show(mddev_t *mddev, char *page)
{
&md_size.attr,
&md_metadata.attr,
&md_new_device.attr,
+ &md_safe_delay.attr,
NULL,
};
return NULL;
}
-void md_wakeup_thread(mdk_thread_t *thread);
-
static void md_safemode_timeout(unsigned long data)
{
mddev_t *mddev = (mddev_t *) data;
mddev->safemode = 0;
mddev->safemode_timer.function = md_safemode_timeout;
mddev->safemode_timer.data = (unsigned long) mddev;
- mddev->safemode_delay = (20 * HZ)/1000 +1; /* 20 msec delay */
+ mddev->safemode_delay = (200 * HZ)/1000 +1; /* 200 msec delay */
mddev->in_sync = 1;
ITERATE_RDEV(mddev,rdev,tmp)
mddev->queue->queuedata = mddev;
mddev->queue->make_request_fn = mddev->pers->make_request;
+ /* If there is a partially-recovered drive we need to
+ * start recovery here. If we leave it to md_check_recovery,
+ * it will remove the drives and not do the right thing
+ */
+ if (mddev->degraded) {
+ struct list_head *rtmp;
+ int spares = 0;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(In_sync, &rdev->flags) &&
+ !test_bit(Faulty, &rdev->flags))
+ /* complete an interrupted recovery */
+ spares++;
+ if (spares && mddev->pers->sync_request) {
+ mddev->recovery = 0;
+ set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+ mddev->sync_thread = md_register_thread(md_do_sync,
+ mddev,
+ "%s_resync");
+ if (!mddev->sync_thread) {
+ printk(KERN_ERR "%s: could not start resync"
+ " thread...\n",
+ mdname(mddev));
+ /* leave the spares where they are, it shouldn't hurt */
+ mddev->recovery = 0;
+ } else
+ md_wakeup_thread(mddev->sync_thread);
+ }
+ }
+
mddev->changed = 1;
md_new_event(mddev);
return 0;
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->sync_thread);
err = 0;
} else {
printk(KERN_ERR "md: %s has no personality assigned.\n",
return err;
}
+/* similar to deny_write_access, but accounts for our holding a reference
+ * to the file ourselves */
+static int deny_bitmap_write_access(struct file * file)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ spin_lock(&inode->i_lock);
+ if (atomic_read(&inode->i_writecount) > 1) {
+ spin_unlock(&inode->i_lock);
+ return -ETXTBSY;
+ }
+ atomic_set(&inode->i_writecount, -1);
+ spin_unlock(&inode->i_lock);
+
+ return 0;
+}
+
+static void restore_bitmap_write_access(struct file *file)
+{
+ struct inode *inode = file->f_mapping->host;
+
+ spin_lock(&inode->i_lock);
+ atomic_set(&inode->i_writecount, 1);
+ spin_unlock(&inode->i_lock);
+}
+
static int do_md_stop(mddev_t * mddev, int ro)
{
int err = 0;
}
if (mddev->sync_thread) {
+ set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_unregister_thread(mddev->sync_thread);
mddev->sync_thread = NULL;
if (mddev->ro)
mddev->ro = 0;
}
- if (!mddev->in_sync) {
+ if (!mddev->in_sync || mddev->sb_dirty) {
/* mark array as shutdown cleanly */
mddev->in_sync = 1;
md_update_sb(mddev);
}
if (ro)
set_disk_ro(disk, 1);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
/*
bitmap_destroy(mddev);
if (mddev->bitmap_file) {
- atomic_set(&mddev->bitmap_file->f_dentry->d_inode->i_writecount, 1);
+ restore_bitmap_write_access(mddev->bitmap_file);
fput(mddev->bitmap_file);
mddev->bitmap_file = NULL;
}
if (disk)
set_capacity(disk, 0);
mddev->changed = 1;
- } else
+ } else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
err = 0;
rdev->raid_disk = -1;
err = bind_rdev_to_array(rdev, mddev);
+ if (!err && !mddev->pers->hot_remove_disk) {
+ /* If there is hot_add_disk but no hot_remove_disk
+ * then added disks for geometry changes,
+ * and should be added immediately.
+ */
+ super_types[mddev->major_version].
+ validate_super(mddev, rdev);
+ err = mddev->pers->hot_add_disk(mddev, rdev);
+ if (err)
+ unbind_rdev_from_array(rdev);
+ }
if (err)
export_rdev(rdev);
return err;
}
-/* similar to deny_write_access, but accounts for our holding a reference
- * to the file ourselves */
-static int deny_bitmap_write_access(struct file * file)
-{
- struct inode *inode = file->f_mapping->host;
-
- spin_lock(&inode->i_lock);
- if (atomic_read(&inode->i_writecount) > 1) {
- spin_unlock(&inode->i_lock);
- return -ETXTBSY;
- }
- atomic_set(&inode->i_writecount, -1);
- spin_unlock(&inode->i_lock);
-
- return 0;
-}
-
static int set_bitmap_file(mddev_t *mddev, int fd)
{
int err;
mddev->pers->quiesce(mddev, 1);
if (fd >= 0)
err = bitmap_create(mddev);
- if (fd < 0 || err)
+ if (fd < 0 || err) {
bitmap_destroy(mddev);
+ fd = -1; /* make sure to put the file */
+ }
mddev->pers->quiesce(mddev, 0);
- } else if (fd < 0) {
- if (mddev->bitmap_file)
+ }
+ if (fd < 0) {
+ if (mddev->bitmap_file) {
+ restore_bitmap_write_access(mddev->bitmap_file);
fput(mddev->bitmap_file);
+ }
mddev->bitmap_file = NULL;
}
goto done_unlock;
default:
- if (_IOC_TYPE(cmd) == MD_MAJOR)
- printk(KERN_WARNING "md: %s(pid %d) used"
- " obsolete MD ioctl, upgrade your"
- " software to use new ictls.\n",
- current->comm, current->pid);
err = -EINVAL;
goto abort_unlock;
}
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- md_new_event(mddev);
+ md_new_event_inintr(mddev);
}
/* seq_file implementation /proc/mdstat */
if (atomic_dec_and_test(&mddev->writes_pending)) {
if (mddev->safemode == 2)
md_wakeup_thread(mddev->thread);
- else
+ else if (mddev->safemode_delay)
mod_timer(&mddev->safemode_timer, jiffies + mddev->safemode_delay);
}
}
struct list_head *tmp;
sector_t last_check;
int skipped = 0;
+ struct list_head *rtmp;
+ mdk_rdev_t *rdev;
/* just incase thread restarts... */
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
return;
+ if (mddev->ro) /* never try to sync a read-only array */
+ return;
/* we overload curr_resync somewhat here.
* 0 == not engaged in resync at all
}
} while (mddev->curr_resync < 2);
+ j = 0;
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
/* resync follows the size requested by the personality,
* which defaults to physical size, but can be virtual size
*/
max_sectors = mddev->resync_max_sectors;
mddev->resync_mismatches = 0;
+ /* we don't use the checkpoint if there's a bitmap */
+ if (!mddev->bitmap &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ j = mddev->recovery_cp;
} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
max_sectors = mddev->size << 1;
- else
+ else {
/* recovery follows the physical size of devices */
max_sectors = mddev->size << 1;
+ j = MaxSector;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < j)
+ j = rdev->recovery_offset;
+ }
printk(KERN_INFO "md: syncing RAID array %s\n", mdname(mddev));
printk(KERN_INFO "md: minimum _guaranteed_ reconstruction speed:"
speed_max(mddev));
is_mddev_idle(mddev); /* this also initializes IO event counters */
- /* we don't use the checkpoint if there's a bitmap */
- if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && !mddev->bitmap
- && ! test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
- j = mddev->recovery_cp;
- else
- j = 0;
+
io_sectors = 0;
for (m = 0; m < SYNC_MARKS; m++) {
mark[m] = jiffies;
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 &&
- mddev->curr_resync >= mddev->recovery_cp) {
- if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
- printk(KERN_INFO
- "md: checkpointing recovery of %s.\n",
- mdname(mddev));
- mddev->recovery_cp = mddev->curr_resync;
- } else
- mddev->recovery_cp = MaxSector;
+ mddev->curr_resync > 2) {
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+ if (mddev->curr_resync >= mddev->recovery_cp) {
+ printk(KERN_INFO
+ "md: checkpointing recovery of %s.\n",
+ mdname(mddev));
+ mddev->recovery_cp = mddev->curr_resync;
+ }
+ } else
+ mddev->recovery_cp = MaxSector;
+ } else {
+ if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
+ mddev->curr_resync = MaxSector;
+ ITERATE_RDEV(mddev,rdev,rtmp)
+ if (rdev->raid_disk >= 0 &&
+ !test_bit(Faulty, &rdev->flags) &&
+ !test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset < mddev->curr_resync)
+ rdev->recovery_offset = mddev->curr_resync;
+ mddev->sb_dirty = 1;
+ }
}
skip:
clear_bit(MD_RECOVERY_INTR, &mddev->recovery);
clear_bit(MD_RECOVERY_DONE, &mddev->recovery);
+ if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+ goto unlock;
/* no recovery is running.
* remove any failed drives, then
* add spares if possible.
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);
printk(KERN_INFO "md: stopping all md devices.\n");
ITERATE_MDDEV(mddev,tmp)
- if (mddev_trylock(mddev))
+ if (mddev_trylock(mddev)) {
do_md_stop (mddev, 1);
+ mddev_unlock(mddev);
+ }
/*
* certain more exotic SCSI devices are known to be
* volatile wrt too early system reboots. While the
EXPORT_SYMBOL(md_register_thread);
EXPORT_SYMBOL(md_unregister_thread);
EXPORT_SYMBOL(md_wakeup_thread);
-EXPORT_SYMBOL(md_print_devices);
EXPORT_SYMBOL(md_check_recovery);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md");
projects / linux-2.6 / blobdiff