*/
#include <linux/module.h>
-#include <linux/config.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/devfs_fs_kernel.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>
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.
.procname = "speed_limit_min",
.data = &sysctl_speed_limit_min,
.maxlen = sizeof(int),
- .mode = 0644,
+ .mode = S_IRUGO|S_IWUSR,
.proc_handler = &proc_dointvec,
},
{
.procname = "speed_limit_max",
.data = &sysctl_speed_limit_max,
.maxlen = sizeof(int),
- .mode = 0644,
+ .mode = S_IRUGO|S_IWUSR,
.proc_handler = &proc_dointvec,
},
{ .ctl_name = 0 }
.ctl_name = DEV_RAID,
.procname = "raid",
.maxlen = 0,
- .mode = 0555,
+ .mode = S_IRUGO|S_IXUGO,
.child = raid_table,
},
{ .ctl_name = 0 }
}
EXPORT_SYMBOL_GPL(md_new_event);
+/* Alternate version that can be called from interrupts
+ * when calling sysfs_notify isn't needed.
+ */
+static 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 (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);
{
mdp_disk_t *desc;
mdp_super_t *sb = (mdp_super_t *)page_address(rdev->sb_page);
+ __u64 ev1 = md_event(sb);
rdev->raid_disk = -1;
rdev->flags = 0;
mddev->layout = sb->layout;
mddev->raid_disks = sb->raid_disks;
mddev->size = sb->size;
- mddev->events = md_event(sb);
+ mddev->events = ev1;
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
} else if (mddev->pers == NULL) {
/* Insist on good event counter while assembling */
- __u64 ev1 = md_event(sb);
++ev1;
if (ev1 < mddev->events)
return -EINVAL;
/* if adding to array with a bitmap, then we can accept an
* older device ... but not too old.
*/
- __u64 ev1 = md_event(sb);
if (ev1 < mddev->bitmap->events_cleared)
return 0;
- } else /* just a hot-add of a new device, leave raid_disk at -1 */
- return 0;
+ } else {
+ if (ev1 < mddev->events)
+ /* just a hot-add of a new device, leave raid_disk at -1 */
+ return 0;
+ }
if (mddev->level != LEVEL_MULTIPATH) {
desc = sb->disks + rdev->desc_nr;
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;
}
* 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;
if (rdev->sb_size & bmask)
rdev-> sb_size = (rdev->sb_size | bmask)+1;
+ if (sb->level == cpu_to_le32(LEVEL_MULTIPATH))
+ rdev->desc_nr = -1;
+ else
+ rdev->desc_nr = le32_to_cpu(sb->dev_number);
+
if (refdev == 0)
ret = 1;
else {
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;
}
static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
{
struct mdp_superblock_1 *sb = (struct mdp_superblock_1*)page_address(rdev->sb_page);
+ __u64 ev1 = le64_to_cpu(sb->events);
rdev->raid_disk = -1;
rdev->flags = 0;
mddev->layout = le32_to_cpu(sb->layout);
mddev->raid_disks = le32_to_cpu(sb->raid_disks);
mddev->size = le64_to_cpu(sb->size)/2;
- mddev->events = le64_to_cpu(sb->events);
+ mddev->events = ev1;
mddev->bitmap_offset = 0;
mddev->default_bitmap_offset = 1024 >> 9;
} else if (mddev->pers == NULL) {
/* Insist of good event counter while assembling */
- __u64 ev1 = le64_to_cpu(sb->events);
++ev1;
if (ev1 < mddev->events)
return -EINVAL;
/* If adding to array with a bitmap, then we can accept an
* older device, but not too old.
*/
- __u64 ev1 = le64_to_cpu(sb->events);
if (ev1 < mddev->bitmap->events_cleared)
return 0;
- } else /* just a hot-add of a new device, leave raid_disk at -1 */
- return 0;
-
+ } else {
+ if (ev1 < mddev->events)
+ /* just a hot-add of a new device, leave raid_disk at -1 */
+ return 0;
+ }
if (mddev->level != LEVEL_MULTIPATH) {
int role;
- rdev->desc_nr = le32_to_cpu(sb->dev_number);
role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]);
switch(role) {
case 0xffff: /* spare */
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));
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);
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);
}
.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;
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
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 void sync_sbs(mddev_t * mddev)
+static void sync_sbs(mddev_t * mddev, int nospares)
{
+ /* Update each superblock (in-memory image), but
+ * if we are allowed to, skip spares which already
+ * have the right event counter, or have one earlier
+ * (which would mean they aren't being marked as dirty
+ * with the rest of the array)
+ */
mdk_rdev_t *rdev;
struct list_head *tmp;
ITERATE_RDEV(mddev,rdev,tmp) {
- super_types[mddev->major_version].
- sync_super(mddev, rdev);
- rdev->sb_loaded = 1;
+ if (rdev->sb_events == mddev->events ||
+ (nospares &&
+ rdev->raid_disk < 0 &&
+ (rdev->sb_events&1)==0 &&
+ rdev->sb_events+1 == mddev->events)) {
+ /* Don't update this superblock */
+ rdev->sb_loaded = 2;
+ } else {
+ super_types[mddev->major_version].
+ sync_super(mddev, rdev);
+ rdev->sb_loaded = 1;
+ }
}
}
-void md_update_sb(mddev_t * mddev)
+static void md_update_sb(mddev_t * mddev, int force_change)
{
int err;
struct list_head *tmp;
mdk_rdev_t *rdev;
int sync_req;
+ int nospares = 0;
repeat:
spin_lock_irq(&mddev->write_lock);
+
+ set_bit(MD_CHANGE_PENDING, &mddev->flags);
+ if (test_and_clear_bit(MD_CHANGE_DEVS, &mddev->flags))
+ force_change = 1;
+ if (test_and_clear_bit(MD_CHANGE_CLEAN, &mddev->flags))
+ /* just a clean<-> dirty transition, possibly leave spares alone,
+ * though if events isn't the right even/odd, we will have to do
+ * spares after all
+ */
+ nospares = 1;
+ if (force_change)
+ nospares = 0;
+ if (mddev->degraded)
+ /* If the array is degraded, then skipping spares is both
+ * dangerous and fairly pointless.
+ * Dangerous because a device that was removed from the array
+ * might have a event_count that still looks up-to-date,
+ * so it can be re-added without a resync.
+ * Pointless because if there are any spares to skip,
+ * then a recovery will happen and soon that array won't
+ * be degraded any more and the spare can go back to sleep then.
+ */
+ nospares = 0;
+
sync_req = mddev->in_sync;
mddev->utime = get_seconds();
- mddev->events ++;
+
+ /* If this is just a dirty<->clean transition, and the array is clean
+ * 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--;
+ else {
+ /* otherwise we have to go forward and ... */
+ mddev->events ++;
+ if (!mddev->in_sync || mddev->recovery_cp != MaxSector) { /* not clean */
+ /* .. if the array isn't clean, insist on an odd 'events' */
+ if ((mddev->events&1)==0) {
+ mddev->events++;
+ nospares = 0;
+ }
+ } else {
+ /* otherwise insist on an even 'events' (for clean states) */
+ if ((mddev->events&1)) {
+ mddev->events++;
+ nospares = 0;
+ }
+ }
+ }
if (!mddev->events) {
/*
MD_BUG();
mddev->events --;
}
- mddev->sb_dirty = 2;
- sync_sbs(mddev);
+ sync_sbs(mddev, nospares);
/*
* do not write anything to disk if using
* nonpersistent superblocks
*/
if (!mddev->persistent) {
- mddev->sb_dirty = 0;
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
return;
ITERATE_RDEV(mddev,rdev,tmp) {
char b[BDEVNAME_SIZE];
dprintk(KERN_INFO "md: ");
+ if (rdev->sb_loaded != 1)
+ continue; /* no noise on spare devices */
if (test_bit(Faulty, &rdev->flags))
dprintk("(skipping faulty ");
dprintk(KERN_INFO "(write) %s's sb offset: %llu\n",
bdevname(rdev->bdev,b),
(unsigned long long)rdev->sb_offset);
+ rdev->sb_events = mddev->events;
} else
dprintk(")\n");
break;
}
md_super_wait(mddev);
- /* if there was a failure, sb_dirty was set to 1, and we re-write super */
+ /* if there was a failure, MD_CHANGE_DEVS was set, and we re-write super */
spin_lock_irq(&mddev->write_lock);
- if (mddev->in_sync != sync_req|| mddev->sb_dirty == 1) {
+ if (mddev->in_sync != sync_req ||
+ test_bit(MD_CHANGE_DEVS, &mddev->flags)) {
/* have to write it out again */
spin_unlock_irq(&mddev->write_lock);
goto repeat;
}
- mddev->sb_dirty = 0;
+ clear_bit(MD_CHANGE_PENDING, &mddev->flags);
spin_unlock_irq(&mddev->write_lock);
wake_up(&mddev->sb_wait);
}
-EXPORT_SYMBOL_GPL(md_update_sb);
/* words written to sysfs files may, or my not, be \n terminated.
* We want to accept with case. For this we use cmd_match.
len += sprintf(page+len, "%sin_sync",sep);
sep = ",";
}
+ if (test_bit(WriteMostly, &rdev->flags)) {
+ len += sprintf(page+len, "%swrite_mostly",sep);
+ sep = ",";
+ }
if (!test_bit(Faulty, &rdev->flags) &&
!test_bit(In_sync, &rdev->flags)) {
len += sprintf(page+len, "%sspare", sep);
return len+sprintf(page+len, "\n");
}
-static struct rdev_sysfs_entry
-rdev_state = __ATTR_RO(state);
+static ssize_t
+state_store(mdk_rdev_t *rdev, const char *buf, size_t len)
+{
+ /* can write
+ * faulty - simulates and error
+ * remove - disconnects the device
+ * writemostly - sets write_mostly
+ * -writemostly - clears write_mostly
+ */
+ int err = -EINVAL;
+ if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
+ md_error(rdev->mddev, rdev);
+ err = 0;
+ } else if (cmd_match(buf, "remove")) {
+ if (rdev->raid_disk >= 0)
+ err = -EBUSY;
+ else {
+ mddev_t *mddev = rdev->mddev;
+ kick_rdev_from_array(rdev);
+ if (mddev->pers)
+ md_update_sb(mddev, 1);
+ md_new_event(mddev);
+ err = 0;
+ }
+ } else if (cmd_match(buf, "writemostly")) {
+ set_bit(WriteMostly, &rdev->flags);
+ err = 0;
+ } else if (cmd_match(buf, "-writemostly")) {
+ clear_bit(WriteMostly, &rdev->flags);
+ err = 0;
+ }
+ return err ? err : len;
+}
+static struct rdev_sysfs_entry rdev_state =
+__ATTR(state, S_IRUGO|S_IWUSR, state_show, state_store);
static ssize_t
super_show(mdk_rdev_t *rdev, char *page)
return -EINVAL;
}
static struct rdev_sysfs_entry rdev_errors =
-__ATTR(errors, 0644, errors_show, errors_store);
+__ATTR(errors, S_IRUGO|S_IWUSR, errors_show, errors_store);
static ssize_t
slot_show(mdk_rdev_t *rdev, char *page)
static struct rdev_sysfs_entry rdev_slot =
-__ATTR(slot, 0644, slot_show, slot_store);
+__ATTR(slot, S_IRUGO|S_IWUSR, slot_show, slot_store);
static ssize_t
offset_show(mdk_rdev_t *rdev, char *page)
}
static struct rdev_sysfs_entry rdev_offset =
-__ATTR(offset, 0644, offset_show, offset_store);
+__ATTR(offset, S_IRUGO|S_IWUSR, offset_show, offset_store);
static ssize_t
rdev_size_show(mdk_rdev_t *rdev, char *page)
}
static struct rdev_sysfs_entry rdev_size =
-__ATTR(size, 0644, rdev_size_show, rdev_size_store);
+__ATTR(size, S_IRUGO|S_IWUSR, rdev_size_show, rdev_size_store);
static struct attribute *rdev_default_attrs[] = {
&rdev_state.attr,
if (!entry->store)
return -EIO;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
return entry->store(rdev, page, length);
}
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;
atomic_set(&rdev->nr_pending, 0);
atomic_set(&rdev->read_errors, 0);
atomic_set(&rdev->corrected_errors, 0);
}
+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, S_IRUGO|S_IWUSR,safe_delay_show, safe_delay_store);
+
static ssize_t
level_show(mddev_t *mddev, char *page)
{
}
static struct md_sysfs_entry md_level =
-__ATTR(level, 0644, level_show, level_store);
+__ATTR(level, S_IRUGO|S_IWUSR, level_show, level_store);
+
+
+static ssize_t
+layout_show(mddev_t *mddev, char *page)
+{
+ /* just a number, not meaningful for all levels */
+ return sprintf(page, "%d\n", mddev->layout);
+}
+
+static ssize_t
+layout_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ 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;
+ return len;
+}
+static struct md_sysfs_entry md_layout =
+__ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);
+
static ssize_t
raid_disks_show(mddev_t *mddev, char *page)
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);
return rv ? rv : len;
}
static struct md_sysfs_entry md_raid_disks =
-__ATTR(raid_disks, 0644, raid_disks_show, raid_disks_store);
+__ATTR(raid_disks, S_IRUGO|S_IWUSR, raid_disks_show, raid_disks_store);
static ssize_t
chunk_size_show(mddev_t *mddev, char *page)
return len;
}
static struct md_sysfs_entry md_chunk_size =
-__ATTR(chunk_size, 0644, chunk_size_show, chunk_size_store);
+__ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);
+
+static ssize_t
+resync_start_show(mddev_t *mddev, char *page)
+{
+ return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
+}
+
+static ssize_t
+resync_start_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ /* can only set chunk_size if array is not yet active */
+ char *e;
+ unsigned long long n = simple_strtoull(buf, &e, 10);
+
+ if (mddev->pers)
+ return -EBUSY;
+ if (!*buf || (*e && *e != '\n'))
+ return -EINVAL;
+
+ mddev->recovery_cp = n;
+ return len;
+}
+static struct md_sysfs_entry md_resync_start =
+__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);
+
+/*
+ * The array state can be:
+ *
+ * clear
+ * No devices, no size, no level
+ * Equivalent to STOP_ARRAY ioctl
+ * inactive
+ * May have some settings, but array is not active
+ * all IO results in error
+ * When written, doesn't tear down array, but just stops it
+ * suspended (not supported yet)
+ * All IO requests will block. The array can be reconfigured.
+ * Writing this, if accepted, will block until array is quiessent
+ * readonly
+ * no resync can happen. no superblocks get written.
+ * write requests fail
+ * read-auto
+ * like readonly, but behaves like 'clean' on a write request.
+ *
+ * clean - no pending writes, but otherwise active.
+ * When written to inactive array, starts without resync
+ * If a write request arrives then
+ * if metadata is known, mark 'dirty' and switch to 'active'.
+ * if not known, block and switch to write-pending
+ * If written to an active array that has pending writes, then fails.
+ * active
+ * fully active: IO and resync can be happening.
+ * When written to inactive array, starts with resync
+ *
+ * write-pending
+ * clean, but writes are blocked waiting for 'active' to be written.
+ *
+ * active-idle
+ * like active, but no writes have been seen for a while (100msec).
+ *
+ */
+enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active,
+ write_pending, active_idle, bad_word};
+static char *array_states[] = {
+ "clear", "inactive", "suspended", "readonly", "read-auto", "clean", "active",
+ "write-pending", "active-idle", NULL };
+
+static int match_word(const char *word, char **list)
+{
+ int n;
+ for (n=0; list[n]; n++)
+ if (cmd_match(word, list[n]))
+ break;
+ return n;
+}
+
+static ssize_t
+array_state_show(mddev_t *mddev, char *page)
+{
+ enum array_state st = inactive;
+
+ if (mddev->pers)
+ switch(mddev->ro) {
+ case 1:
+ st = readonly;
+ break;
+ case 2:
+ st = read_auto;
+ break;
+ case 0:
+ if (mddev->in_sync)
+ st = clean;
+ else if (mddev->safemode)
+ st = active_idle;
+ else
+ st = active;
+ }
+ else {
+ if (list_empty(&mddev->disks) &&
+ mddev->raid_disks == 0 &&
+ mddev->size == 0)
+ st = clear;
+ else
+ st = inactive;
+ }
+ return sprintf(page, "%s\n", array_states[st]);
+}
+
+static int do_md_stop(mddev_t * mddev, int ro);
+static int do_md_run(mddev_t * mddev);
+static int restart_array(mddev_t *mddev);
+
+static ssize_t
+array_state_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ int err = -EINVAL;
+ enum array_state st = match_word(buf, array_states);
+ switch(st) {
+ case bad_word:
+ break;
+ case clear:
+ /* stopping an active array */
+ if (mddev->pers) {
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 0);
+ }
+ break;
+ case inactive:
+ /* stopping an active array */
+ if (mddev->pers) {
+ if (atomic_read(&mddev->active) > 1)
+ return -EBUSY;
+ err = do_md_stop(mddev, 2);
+ }
+ break;
+ case suspended:
+ break; /* not supported yet */
+ case readonly:
+ if (mddev->pers)
+ err = do_md_stop(mddev, 1);
+ else {
+ mddev->ro = 1;
+ err = do_md_run(mddev);
+ }
+ break;
+ case read_auto:
+ /* stopping an active array */
+ if (mddev->pers) {
+ err = do_md_stop(mddev, 1);
+ if (err == 0)
+ mddev->ro = 2; /* FIXME mark devices writable */
+ } else {
+ mddev->ro = 2;
+ err = do_md_run(mddev);
+ }
+ break;
+ case clean:
+ if (mddev->pers) {
+ restart_array(mddev);
+ spin_lock_irq(&mddev->write_lock);
+ if (atomic_read(&mddev->writes_pending) == 0) {
+ mddev->in_sync = 1;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ }
+ spin_unlock_irq(&mddev->write_lock);
+ } else {
+ mddev->ro = 0;
+ mddev->recovery_cp = MaxSector;
+ err = do_md_run(mddev);
+ }
+ break;
+ case active:
+ if (mddev->pers) {
+ restart_array(mddev);
+ clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
+ wake_up(&mddev->sb_wait);
+ err = 0;
+ } else {
+ mddev->ro = 0;
+ err = do_md_run(mddev);
+ }
+ break;
+ case write_pending:
+ case active_idle:
+ /* these cannot be set */
+ break;
+ }
+ if (err)
+ return err;
+ else
+ return len;
+}
+static struct md_sysfs_entry md_array_state =
+__ATTR(array_state, S_IRUGO|S_IWUSR, array_state_show, array_state_store);
static ssize_t
null_show(mddev_t *mddev, char *page)
}
static struct md_sysfs_entry md_new_device =
-__ATTR(new_dev, 0200, null_show, new_dev_store);
+__ATTR(new_dev, S_IWUSR, null_show, new_dev_store);
+
+static ssize_t
+bitmap_store(mddev_t *mddev, const char *buf, size_t len)
+{
+ char *end;
+ unsigned long chunk, end_chunk;
+
+ if (!mddev->bitmap)
+ goto out;
+ /* buf should be <chunk> <chunk> ... or <chunk>-<chunk> ... (range) */
+ while (*buf) {
+ chunk = end_chunk = simple_strtoul(buf, &end, 0);
+ if (buf == end) break;
+ if (*end == '-') { /* range */
+ buf = end + 1;
+ end_chunk = simple_strtoul(buf, &end, 0);
+ if (buf == end) break;
+ }
+ if (*end && !isspace(*end)) break;
+ bitmap_dirty_bits(mddev->bitmap, chunk, end_chunk);
+ buf = end;
+ while (isspace(*buf)) buf++;
+ }
+ bitmap_unplug(mddev->bitmap); /* flush the bits to disk */
+out:
+ return len;
+}
+
+static struct md_sysfs_entry md_bitmap =
+__ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store);
static ssize_t
size_show(mddev_t *mddev, char *page)
if (mddev->pers) {
err = update_size(mddev, size);
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
} else {
if (mddev->size == 0 ||
mddev->size > size)
}
static struct md_sysfs_entry md_size =
-__ATTR(component_size, 0644, size_show, size_store);
+__ATTR(component_size, S_IRUGO|S_IWUSR, size_show, size_store);
/* Metdata version.
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)
}
static struct md_sysfs_entry md_metadata =
-__ATTR(metadata_version, 0644, metadata_show, metadata_store);
+__ATTR(metadata_version, S_IRUGO|S_IWUSR, metadata_show, metadata_store);
static ssize_t
action_show(mddev_t *mddev, char *page)
} else {
if (cmd_match(page, "check"))
set_bit(MD_RECOVERY_CHECK, &mddev->recovery);
- else if (cmd_match(page, "repair"))
+ else if (!cmd_match(page, "repair"))
return -EINVAL;
set_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
(unsigned long long) mddev->resync_mismatches);
}
-static struct md_sysfs_entry
-md_scan_mode = __ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);
+static struct md_sysfs_entry md_scan_mode =
+__ATTR(sync_action, S_IRUGO|S_IWUSR, action_show, action_store);
-static struct md_sysfs_entry
-md_mismatches = __ATTR_RO(mismatch_cnt);
+static struct md_sysfs_entry md_mismatches = __ATTR_RO(mismatch_cnt);
static ssize_t
sync_min_show(mddev_t *mddev, char *page)
sync_speed_show(mddev_t *mddev, char *page)
{
unsigned long resync, dt, db;
- resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
+ resync = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active));
dt = ((jiffies - mddev->resync_mark) / HZ);
if (!dt) dt++;
db = resync - (mddev->resync_mark_cnt);
return sprintf(page, "%ld\n", db/dt/2); /* K/sec */
}
-static struct md_sysfs_entry
-md_sync_speed = __ATTR_RO(sync_speed);
+static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed);
static ssize_t
sync_completed_show(mddev_t *mddev, char *page)
return sprintf(page, "%lu / %lu\n", resync, max_blocks);
}
-static struct md_sysfs_entry
-md_sync_completed = __ATTR_RO(sync_completed);
+static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);
static ssize_t
suspend_lo_show(mddev_t *mddev, char *page)
static struct attribute *md_default_attrs[] = {
&md_level.attr,
+ &md_layout.attr,
&md_raid_disks.attr,
&md_chunk_size.attr,
&md_size.attr,
+ &md_resync_start.attr,
&md_metadata.attr,
&md_new_device.attr,
+ &md_safe_delay.attr,
+ &md_array_state.attr,
NULL,
};
&md_sync_completed.attr,
&md_suspend_lo.attr,
&md_suspend_hi.attr,
+ &md_bitmap.attr,
NULL,
};
static struct attribute_group md_redundancy_group = {
if (!entry->store)
return -EIO;
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
rv = mddev_lock(mddev);
if (!rv) {
rv = entry->store(mddev, page, length);
}
disk->major = MAJOR(dev);
disk->first_minor = unit << shift;
- if (partitioned) {
+ if (partitioned)
sprintf(disk->disk_name, "md_d%d", unit);
- sprintf(disk->devfs_name, "md/d%d", unit);
- } else {
+ else
sprintf(disk->disk_name, "md%d", unit);
- sprintf(disk->devfs_name, "md/%d", unit);
- }
disk->fops = &md_fops;
disk->private_data = mddev;
disk->queue = mddev->queue;
return NULL;
}
-void md_wakeup_thread(mdk_thread_t *thread);
-
static void md_safemode_timeout(unsigned long data)
{
mddev_t *mddev = (mddev_t *) data;
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;
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)
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- md_wakeup_thread(mddev->thread);
- if (mddev->sb_dirty)
- md_update_sb(mddev);
+ if (mddev->flags)
+ md_update_sb(mddev, 0);
set_capacity(disk, mddev->array_size<<1);
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 && !mddev->sync_thread) {
+ 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;
+ }
+ }
+ }
+ md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
+
mddev->changed = 1;
md_new_event(mddev);
+ kobject_uevent(&mddev->gendisk->kobj, KOBJ_CHANGE);
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",
- mdname(mddev));
+ } else
err = -EINVAL;
- }
out:
return err;
}
-static int do_md_stop(mddev_t * mddev, int ro)
+/* 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);
+}
+
+/* mode:
+ * 0 - completely stop and dis-assemble array
+ * 1 - switch to readonly
+ * 2 - stop but do not disassemble array
+ */
+static int do_md_stop(mddev_t * mddev, int mode)
{
int err = 0;
struct gendisk *disk = mddev->gendisk;
}
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;
invalidate_partition(disk, 0);
- if (ro) {
+ switch(mode) {
+ case 1: /* readonly */
err = -ENXIO;
if (mddev->ro==1)
goto out;
mddev->ro = 1;
- } else {
+ break;
+ case 0: /* disassemble */
+ case 2: /* stop */
bitmap_flush(mddev);
md_super_wait(mddev);
if (mddev->ro)
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 (!mddev->in_sync) {
+ if (!mddev->in_sync || mddev->flags) {
/* mark array as shutdown cleanly */
mddev->in_sync = 1;
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
}
- if (ro)
+ if (mode == 1)
set_disk_ro(disk, 1);
+ clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
}
/*
* Free resources if final stop
*/
- if (!ro) {
+ 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);
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;
}
export_array(mddev);
mddev->array_size = 0;
- disk = mddev->gendisk;
- if (disk)
- set_capacity(disk, 0);
- mddev->changed = 1;
- } else
+ mddev->size = 0;
+ mddev->raid_disks = 0;
+ mddev->recovery_cp = 0;
+
+ } else if (mddev->pers)
printk(KERN_INFO "md: %s switched to read-only mode.\n",
mdname(mddev));
err = 0;
return err;
}
+#ifndef MODULE
static void autorun_array(mddev_t *mddev)
{
mdk_rdev_t *rdev;
printk(KERN_INFO "md: autorun ...\n");
while (!list_empty(&pending_raid_disks)) {
+ int unit;
dev_t dev;
LIST_HEAD(candidates);
rdev0 = list_entry(pending_raid_disks.next,
* mostly sane superblocks. It's time to allocate the
* mddev.
*/
- if (rdev0->preferred_minor < 0 || rdev0->preferred_minor >= MAX_MD_DEVS) {
+ if (part) {
+ dev = MKDEV(mdp_major,
+ rdev0->preferred_minor << MdpMinorShift);
+ unit = MINOR(dev) >> MdpMinorShift;
+ } else {
+ dev = MKDEV(MD_MAJOR, rdev0->preferred_minor);
+ unit = MINOR(dev);
+ }
+ if (rdev0->preferred_minor != unit) {
printk(KERN_INFO "md: unit number in %s is bad: %d\n",
bdevname(rdev0->bdev, b), rdev0->preferred_minor);
break;
}
- if (part)
- dev = MKDEV(mdp_major,
- rdev0->preferred_minor << MdpMinorShift);
- else
- dev = MKDEV(MD_MAJOR, rdev0->preferred_minor);
md_probe(dev, NULL, NULL);
mddev = mddev_find(dev);
}
printk(KERN_INFO "md: ... autorun DONE.\n");
}
-
-/*
- * import RAID devices based on one partition
- * if possible, the array gets run as well.
- */
-
-static int autostart_array(dev_t startdev)
-{
- char b[BDEVNAME_SIZE];
- int err = -EINVAL, i;
- mdp_super_t *sb = NULL;
- mdk_rdev_t *start_rdev = NULL, *rdev;
-
- start_rdev = md_import_device(startdev, 0, 0);
- if (IS_ERR(start_rdev))
- return err;
-
-
- /* NOTE: this can only work for 0.90.0 superblocks */
- sb = (mdp_super_t*)page_address(start_rdev->sb_page);
- if (sb->major_version != 0 ||
- sb->minor_version != 90 ) {
- printk(KERN_WARNING "md: can only autostart 0.90.0 arrays\n");
- export_rdev(start_rdev);
- return err;
- }
-
- if (test_bit(Faulty, &start_rdev->flags)) {
- printk(KERN_WARNING
- "md: can not autostart based on faulty %s!\n",
- bdevname(start_rdev->bdev,b));
- export_rdev(start_rdev);
- return err;
- }
- list_add(&start_rdev->same_set, &pending_raid_disks);
-
- for (i = 0; i < MD_SB_DISKS; i++) {
- mdp_disk_t *desc = sb->disks + i;
- dev_t dev = MKDEV(desc->major, desc->minor);
-
- if (!dev)
- continue;
- if (dev == startdev)
- continue;
- if (MAJOR(dev) != desc->major || MINOR(dev) != desc->minor)
- continue;
- rdev = md_import_device(dev, 0, 0);
- if (IS_ERR(rdev))
- continue;
-
- list_add(&rdev->same_set, &pending_raid_disks);
- }
-
- /*
- * possibly return codes
- */
- autorun_devices(0);
- return 0;
-
-}
-
+#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;
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);
+ md_update_sb(mddev, 1);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
return err;
goto busy;
kick_rdev_from_array(rdev);
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
md_new_event(mddev);
return 0;
}
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;
rdev->raid_disk = -1;
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
/*
* Kick recovery, maybe this spare has to be added to the
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;
}
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;
mddev->max_disks = MD_SB_DISKS;
- mddev->sb_dirty = 1;
+ mddev->flags = 0;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
mddev->bitmap_offset = 0;
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))
mddev->bitmap_offset = 0;
}
}
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
return rv;
}
goto abort;
}
-
- if (cmd == START_ARRAY) {
- /* START_ARRAY doesn't need to lock the array as autostart_array
- * does the locking, and it could even be a different array
- */
- static int cnt = 3;
- if (cnt > 0 ) {
- printk(KERN_WARNING
- "md: %s(pid %d) used deprecated START_ARRAY ioctl. "
- "This will not be supported beyond July 2006\n",
- current->comm, current->pid);
- cnt--;
- }
- err = autostart_array(new_decode_dev(arg));
- if (err) {
- printk(KERN_WARNING "md: autostart failed!\n");
- goto abort;
- }
- goto done;
- }
-
err = mddev_lock(mddev);
if (err) {
printk(KERN_INFO
* 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;
}
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;
}
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;
* many dirty RAID5 blocks.
*/
+ current->flags |= PF_NOFREEZE;
allow_signal(SIGKILL);
while (!kthread_should_stop()) {
test_bit(THREAD_WAKEUP, &thread->flags)
|| kthread_should_stop(),
thread->timeout);
- try_to_freeze();
clear_bit(THREAD_WAKEUP, &thread->flags);
__builtin_return_address(0),__builtin_return_address(1),
__builtin_return_address(2),__builtin_return_address(3));
*/
+ if (!mddev->pers)
+ return;
if (!mddev->pers->error_handler)
return;
mddev->pers->error_handler(mddev,rdev);
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 */
seq_printf(seq, " %s =%3u.%u%% (%llu/%llu)",
(test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)?
"reshape" :
- (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?
- "resync" : "recovery")),
- per_milli/10, per_milli % 10,
+ (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)?
+ "check" :
+ (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?
+ "resync" : "recovery"))),
+ per_milli/10, per_milli % 10,
(unsigned long long) resync,
(unsigned long long) max_blocks);
*/
dt = ((jiffies - mddev->resync_mark) / HZ);
if (!dt) dt++;
- db = resync - (mddev->resync_mark_cnt/2);
- rt = (dt * ((unsigned long)(max_blocks-resync) / (db/100+1)))/100;
+ db = (mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active))
+ - mddev->resync_mark_cnt;
+ rt = (dt * ((unsigned long)(max_blocks-resync) / (db/2/100+1)))/100;
seq_printf(seq, " finish=%lu.%lumin", rt / 60, (rt % 60)/6);
- seq_printf(seq, " speed=%ldK/sec", db/dt);
+ seq_printf(seq, " speed=%ldK/sec", db/2/dt);
}
static void *md_seq_start(struct seq_file *seq, loff_t *pos)
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 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,
spin_lock_irq(&mddev->write_lock);
if (mddev->in_sync) {
mddev->in_sync = 0;
- mddev->sb_dirty = 1;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
md_wakeup_thread(mddev->thread);
}
spin_unlock_irq(&mddev->write_lock);
}
- wait_event(mddev->sb_wait, mddev->sb_dirty==0);
+ wait_event(mddev->sb_wait, mddev->flags==0);
}
void md_write_end(mddev_t *mddev)
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);
}
}
+/* 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
struct list_head *tmp;
sector_t last_check;
int skipped = 0;
+ struct list_head *rtmp;
+ mdk_rdev_t *rdev;
+ char *desc;
/* 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;
+
+ if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
+ desc = "data-check";
+ else if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
+ desc = "requested-resync";
+ else
+ desc = "resync";
+ } else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
+ desc = "reshape";
+ else
+ desc = "recovery";
/* we overload curr_resync somewhat here.
* 0 == not engaged in resync at all
prepare_to_wait(&resync_wait, &wq, TASK_UNINTERRUPTIBLE);
if (!kthread_should_stop() &&
mddev2->curr_resync >= mddev->curr_resync) {
- printk(KERN_INFO "md: delaying resync of %s"
- " until %s has finished resync (they"
+ printk(KERN_INFO "md: delaying %s of %s"
+ " until %s has finished (they"
" share one or more physical units)\n",
- mdname(mddev), mdname(mddev2));
+ desc, mdname(mddev), mdname(mddev2));
mddev_put(mddev2);
schedule();
finish_wait(&resync_wait, &wq);
}
} 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:"
- " %d KB/sec/disc.\n", speed_min(mddev));
+ printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
+ printk(KERN_INFO "md: minimum _guaranteed_ speed:"
+ " %d KB/sec/disk.\n", speed_min(mddev));
printk(KERN_INFO "md: using maximum available idle IO bandwidth "
- "(but not more than %d KB/sec) for reconstruction.\n",
- speed_max(mddev));
+ "(but not more than %d KB/sec) for %s.\n",
+ speed_max(mddev), desc);
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 (j>2) {
printk(KERN_INFO
- "md: resuming recovery of %s from checkpoint.\n",
- mdname(mddev));
+ "md: resuming %s of %s from checkpoint.\n",
+ desc, mdname(mddev));
mddev->curr_resync = j;
}
j += sectors;
if (j>1) mddev->curr_resync = j;
+ mddev->curr_mark_cnt = io_sectors;
if (last_check == 0)
/* this is the earliers that rebuilt will be
* visible in /proc/mdstat
}
}
}
- printk(KERN_INFO "md: %s: sync done.\n",mdname(mddev));
+ printk(KERN_INFO "md: %s: %s done.\n",mdname(mddev), desc);
/*
* this also signals 'finished resyncing' to md_stop
*/
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 &&
- 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 %s of %s.\n",
+ desc, 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;
+ }
}
+ 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);
+ sysfs_create_link(&mddev->kobj,
+ &rdev->kobj, nm);
+ 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.
}
if ( ! (
- mddev->sb_dirty ||
+ mddev->flags ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
(mddev->safemode == 1) ||
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) &&
!mddev->in_sync && mddev->recovery_cp == MaxSector) {
mddev->in_sync = 1;
- mddev->sb_dirty = 1;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
}
if (mddev->safemode == 1)
mddev->safemode = 0;
spin_unlock_irq(&mddev->write_lock);
- if (mddev->sb_dirty)
- md_update_sb(mddev);
+ if (mddev->flags)
+ md_update_sb(mddev, 0);
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) &&
/* activate any spares */
mddev->pers->spare_active(mddev);
}
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
/* if array is no-longer degraded, then any saved_raid_disk
* information must be scrapped
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.
* 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)) {
- 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) {
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
static int __init md_init(void)
{
- int minor;
-
- printk(KERN_INFO "md: md driver %d.%d.%d MAX_MD_DEVS=%d,"
- " MD_SB_DISKS=%d\n",
- MD_MAJOR_VERSION, MD_MINOR_VERSION,
- MD_PATCHLEVEL_VERSION, MAX_MD_DEVS, MD_SB_DISKS);
- printk(KERN_INFO "md: bitmap version %d.%d\n", BITMAP_MAJOR_HI,
- BITMAP_MINOR);
-
if (register_blkdev(MAJOR_NR, "md"))
return -1;
if ((mdp_major=register_blkdev(0, "mdp"))<=0) {
unregister_blkdev(MAJOR_NR, "md");
return -1;
}
- devfs_mk_dir("md");
- blk_register_region(MKDEV(MAJOR_NR, 0), MAX_MD_DEVS, THIS_MODULE,
- md_probe, NULL, NULL);
- blk_register_region(MKDEV(mdp_major, 0), MAX_MD_DEVS<<MdpMinorShift, THIS_MODULE,
+ blk_register_region(MKDEV(MAJOR_NR, 0), 1UL<<MINORBITS, THIS_MODULE,
+ md_probe, NULL, NULL);
+ blk_register_region(MKDEV(mdp_major, 0), 1UL<<MINORBITS, THIS_MODULE,
md_probe, NULL, NULL);
-
- for (minor=0; minor < MAX_MD_DEVS; ++minor)
- devfs_mk_bdev(MKDEV(MAJOR_NR, minor),
- S_IFBLK|S_IRUSR|S_IWUSR,
- "md/%d", minor);
-
- for (minor=0; minor < MAX_MD_DEVS; ++minor)
- devfs_mk_bdev(MKDEV(mdp_major, minor<<MdpMinorShift),
- S_IFBLK|S_IRUSR|S_IWUSR,
- "md/mdp%d", minor);
-
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);
autorun_devices(part);
}
-#endif
+#endif /* !MODULE */
static __exit void md_exit(void)
{
mddev_t *mddev;
struct list_head *tmp;
- int i;
- blk_unregister_region(MKDEV(MAJOR_NR,0), MAX_MD_DEVS);
- blk_unregister_region(MKDEV(mdp_major,0), MAX_MD_DEVS << MdpMinorShift);
- for (i=0; i < MAX_MD_DEVS; i++)
- devfs_remove("md/%d", i);
- for (i=0; i < MAX_MD_DEVS; i++)
- devfs_remove("md/d%d", i);
- devfs_remove("md");
+ blk_unregister_region(MKDEV(MAJOR_NR,0), 1U << MINORBITS);
+ blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS);
unregister_blkdev(MAJOR_NR,"md");
unregister_blkdev(mdp_major, "mdp");
return -EINVAL;
}
-module_param_call(start_ro, set_ro, get_ro, NULL, 0600);
-module_param(start_dirty_degraded, int, 0644);
+module_param_call(start_ro, set_ro, get_ro, NULL, S_IRUSR|S_IWUSR);
+module_param(start_dirty_degraded, int, S_IRUGO|S_IWUSR);
EXPORT_SYMBOL(register_md_personality);
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");
Code Review / linux-2.6.git / blobdiff