*/
#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>
.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 }
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 (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 */
struct block_device *bdev;
char b[BDEVNAME_SIZE];
- bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ bdev = open_partition_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(bdev);
+ blkdev_put_partition(bdev);
return err;
}
rdev->bdev = bdev;
if (!bdev)
MD_BUG();
bd_release(bdev);
- blkdev_put(bdev);
+ blkdev_put_partition(bdev);
}
void md_autodetect_dev(dev_t dev);
}
}
-void md_update_sb(mddev_t * mddev)
+static void md_update_sb(mddev_t * mddev, int force_change)
{
int err;
struct list_head *tmp;
repeat:
spin_lock_irq(&mddev->write_lock);
- sync_req = mddev->in_sync;
- mddev->utime = get_seconds();
- if (mddev->sb_dirty == 3)
+
+ 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();
/* 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 (mddev->sb_dirty == 3
+ if (nospares
&& (mddev->in_sync && mddev->recovery_cp == MaxSector)
&& (mddev->events & 1))
mddev->events--;
MD_BUG();
mddev->events --;
}
- mddev->sb_dirty = 2;
sync_sbs(mddev, nospares);
/*
* 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;
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.
else {
mddev_t *mddev = rdev->mddev;
kick_rdev_from_array(rdev);
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
md_new_event(mddev);
err = 0;
}
}
return err ? err : len;
}
-static struct rdev_sysfs_entry
-rdev_state = __ATTR(state, 0644, state_show, state_store);
+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);
}
return len;
}
static struct md_sysfs_entry md_safe_delay =
-__ATTR(safe_mode_delay, 0644,safe_delay_show, safe_delay_store);
+__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
return len;
}
static struct md_sysfs_entry md_layout =
-__ATTR(layout, 0655, layout_show, layout_store);
+__ATTR(layout, S_IRUGO|S_IWUSR, layout_show, layout_store);
static ssize_t
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 len;
}
static struct md_sysfs_entry md_resync_start =
-__ATTR(resync_start, 0644, resync_start_show, resync_start_store);
+__ATTR(resync_start, S_IRUGO|S_IWUSR, resync_start_show, resync_start_store);
/*
* The array state can be:
spin_lock_irq(&mddev->write_lock);
if (atomic_read(&mddev->writes_pending) == 0) {
mddev->in_sync = 1;
- mddev->sb_dirty = 1;
+ set_bit(MD_CHANGE_CLEAN, &mddev->flags);
}
spin_unlock_irq(&mddev->write_lock);
} else {
case active:
if (mddev->pers) {
restart_array(mddev);
- mddev->sb_dirty = 0;
+ clear_bit(MD_CHANGE_CLEAN, &mddev->flags);
wake_up(&mddev->sb_wait);
err = 0;
} else {
else
return len;
}
-static struct md_sysfs_entry md_array_state = __ATTR(array_state, 0644, array_state_show, array_state_store);
+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.
}
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)
(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)
&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;
}
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);
* 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) {
+ if (mddev->degraded && !mddev->sync_thread) {
struct list_head *rtmp;
int spares = 0;
ITERATE_RDEV(mddev,rdev,rtmp)
mdname(mddev));
/* leave the spares where they are, it shouldn't hurt */
mddev->recovery = 0;
- } else
- md_wakeup_thread(mddev->sync_thread);
+ }
}
}
+ md_wakeup_thread(mddev->thread);
+ md_wakeup_thread(mddev->sync_thread); /* possibly kick off a reshape */
mddev->changed = 1;
md_new_event(mddev);
if (mddev->ro)
mddev->ro = 0;
}
- if (!mddev->in_sync || mddev->sb_dirty) {
+ 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 (mode == 1)
set_disk_ro(disk, 1);
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;
-
-}
-
-
static int get_version(void __user * arg)
{
mdu_version_t ver;
goto busy;
kick_rdev_from_array(rdev);
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
md_new_event(mddev);
return 0;
rdev->raid_disk = -1;
- md_update_sb(mddev);
+ md_update_sb(mddev, 1);
/*
* Kick recovery, maybe this spare has to be added to the
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;
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
__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);
*/
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)
spin_lock_irq(&mddev->write_lock);
if (mddev->in_sync) {
mddev->in_sync = 0;
- mddev->sb_dirty = 3;
+ 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)
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
!test_bit(In_sync, &rdev->flags) &&
rdev->recovery_offset < mddev->curr_resync)
rdev->recovery_offset = mddev->curr_resync;
- mddev->sb_dirty = 1;
}
}
}
if ( ! (
- mddev->sb_dirty ||
+ mddev->flags ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
(mddev->safemode == 1) ||
if (mddev->safemode && !atomic_read(&mddev->writes_pending) &&
!mddev->in_sync && mddev->recovery_cp == MaxSector) {
mddev->in_sync = 1;
- mddev->sb_dirty = 3;
+ 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
{
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");
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);
git.samba.org / sfrench / cifs-2.6.git / blobdiff