aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/md.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/md.c')
-rw-r--r--drivers/md/md.c100
1 files changed, 63 insertions, 37 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ad5cc4e63e..32fc19c540d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3448,6 +3448,8 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
mddev->level = LEVEL_NONE;
return rv;
}
+ if (mddev->ro)
+ return -EROFS;
/* request to change the personality. Need to ensure:
* - array is not engaged in resync/recovery/reshape
@@ -3634,6 +3636,8 @@ layout_store(struct mddev *mddev, const char *buf, size_t len)
int err;
if (mddev->pers->check_reshape == NULL)
return -EBUSY;
+ if (mddev->ro)
+ return -EROFS;
mddev->new_layout = n;
err = mddev->pers->check_reshape(mddev);
if (err) {
@@ -3723,6 +3727,8 @@ chunk_size_store(struct mddev *mddev, const char *buf, size_t len)
int err;
if (mddev->pers->check_reshape == NULL)
return -EBUSY;
+ if (mddev->ro)
+ return -EROFS;
mddev->new_chunk_sectors = n >> 9;
err = mddev->pers->check_reshape(mddev);
if (err) {
@@ -5181,32 +5187,6 @@ static int restart_array(struct mddev *mddev)
return 0;
}
-/* 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;
-}
-
-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 void md_clean(struct mddev *mddev)
{
mddev->array_sectors = 0;
@@ -5427,7 +5407,6 @@ static int do_md_stop(struct mddev * mddev, int mode,
bitmap_destroy(mddev);
if (mddev->bitmap_info.file) {
- restore_bitmap_write_access(mddev->bitmap_info.file);
fput(mddev->bitmap_info.file);
mddev->bitmap_info.file = NULL;
}
@@ -5620,7 +5599,7 @@ static int get_array_info(struct mddev * mddev, void __user * arg)
if (mddev->in_sync)
info.state = (1<<MD_SB_CLEAN);
if (mddev->bitmap && mddev->bitmap_info.offset)
- info.state = (1<<MD_SB_BITMAP_PRESENT);
+ info.state |= (1<<MD_SB_BITMAP_PRESENT);
info.active_disks = insync;
info.working_disks = working;
info.failed_disks = failed;
@@ -5979,7 +5958,7 @@ abort_export:
static int set_bitmap_file(struct mddev *mddev, int fd)
{
- int err;
+ int err = 0;
if (mddev->pers) {
if (!mddev->pers->quiesce)
@@ -5991,6 +5970,7 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
if (fd >= 0) {
+ struct inode *inode;
if (mddev->bitmap)
return -EEXIST; /* cannot add when bitmap is present */
mddev->bitmap_info.file = fget(fd);
@@ -6001,10 +5981,21 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
return -EBADF;
}
- err = deny_bitmap_write_access(mddev->bitmap_info.file);
- if (err) {
+ inode = mddev->bitmap_info.file->f_mapping->host;
+ if (!S_ISREG(inode->i_mode)) {
+ printk(KERN_ERR "%s: error: bitmap file must be a regular file\n",
+ mdname(mddev));
+ err = -EBADF;
+ } else if (!(mddev->bitmap_info.file->f_mode & FMODE_WRITE)) {
+ printk(KERN_ERR "%s: error: bitmap file must open for write\n",
+ mdname(mddev));
+ err = -EBADF;
+ } else if (atomic_read(&inode->i_writecount) != 1) {
printk(KERN_ERR "%s: error: bitmap file is already in use\n",
mdname(mddev));
+ err = -EBUSY;
+ }
+ if (err) {
fput(mddev->bitmap_info.file);
mddev->bitmap_info.file = NULL;
return err;
@@ -6027,10 +6018,8 @@ static int set_bitmap_file(struct mddev *mddev, int fd)
mddev->pers->quiesce(mddev, 0);
}
if (fd < 0) {
- if (mddev->bitmap_info.file) {
- restore_bitmap_write_access(mddev->bitmap_info.file);
+ if (mddev->bitmap_info.file)
fput(mddev->bitmap_info.file);
- }
mddev->bitmap_info.file = NULL;
}
@@ -6152,6 +6141,8 @@ static int update_size(struct mddev *mddev, sector_t num_sectors)
*/
if (mddev->sync_thread)
return -EBUSY;
+ if (mddev->ro)
+ return -EROFS;
rdev_for_each(rdev, mddev) {
sector_t avail = rdev->sectors;
@@ -6174,6 +6165,8 @@ static int update_raid_disks(struct mddev *mddev, int raid_disks)
/* change the number of raid disks */
if (mddev->pers->check_reshape == NULL)
return -EINVAL;
+ if (mddev->ro)
+ return -EROFS;
if (raid_disks <= 0 ||
(mddev->max_disks && raid_disks >= mddev->max_disks))
return -EINVAL;
@@ -7182,11 +7175,14 @@ static int md_seq_open(struct inode *inode, struct file *file)
return error;
}
+static int md_unloading;
static unsigned int mdstat_poll(struct file *filp, poll_table *wait)
{
struct seq_file *seq = filp->private_data;
int mask;
+ if (md_unloading)
+ return POLLIN|POLLRDNORM|POLLERR|POLLPRI;;
poll_wait(filp, &md_event_waiters, wait);
/* always allow read */
@@ -7395,8 +7391,10 @@ void md_do_sync(struct md_thread *thread)
/* just incase thread restarts... */
if (test_bit(MD_RECOVERY_DONE, &mddev->recovery))
return;
- if (mddev->ro) /* never try to sync a read-only array */
+ if (mddev->ro) {/* never try to sync a read-only array */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
return;
+ }
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
@@ -7503,6 +7501,19 @@ void md_do_sync(struct md_thread *thread)
rdev->recovery_offset < j)
j = rdev->recovery_offset;
rcu_read_unlock();
+
+ /* If there is a bitmap, we need to make sure all
+ * writes that started before we added a spare
+ * complete before we start doing a recovery.
+ * Otherwise the write might complete and (via
+ * bitmap_endwrite) set a bit in the bitmap after the
+ * recovery has checked that bit and skipped that
+ * region.
+ */
+ if (mddev->bitmap) {
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ }
}
printk(KERN_INFO "md: %s of RAID array %s\n", desc, mdname(mddev));
@@ -7838,6 +7849,7 @@ void md_check_recovery(struct mddev *mddev)
/* There is no thread, but we need to call
* ->spare_active and clear saved_raid_disk
*/
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_reap_sync_thread(mddev);
clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
goto unlock;
@@ -8344,7 +8356,7 @@ static int md_clear_badblocks(struct badblocks *bb, sector_t s, int sectors)
if (a < s) {
/* we need to split this range */
if (bb->count >= MD_MAX_BADBLOCKS) {
- rv = 0;
+ rv = -ENOSPC;
goto out;
}
memmove(p+lo+1, p+lo, (bb->count - lo) * 8);
@@ -8530,7 +8542,8 @@ static int md_notify_reboot(struct notifier_block *this,
if (mddev_trylock(mddev)) {
if (mddev->pers)
__md_stop_writes(mddev);
- mddev->safemode = 2;
+ if (mddev->persistent)
+ mddev->safemode = 2;
mddev_unlock(mddev);
}
need_delay = 1;
@@ -8672,6 +8685,7 @@ static __exit void md_exit(void)
{
struct mddev *mddev;
struct list_head *tmp;
+ int delay = 1;
blk_unregister_region(MKDEV(MD_MAJOR,0), 1U << MINORBITS);
blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS);
@@ -8680,7 +8694,19 @@ static __exit void md_exit(void)
unregister_blkdev(mdp_major, "mdp");
unregister_reboot_notifier(&md_notifier);
unregister_sysctl_table(raid_table_header);
+
+ /* We cannot unload the modules while some process is
+ * waiting for us in select() or poll() - wake them up
+ */
+ md_unloading = 1;
+ while (waitqueue_active(&md_event_waiters)) {
+ /* not safe to leave yet */
+ wake_up(&md_event_waiters);
+ msleep(delay);
+ delay += delay;
+ }
remove_proc_entry("mdstat", NULL);
+
for_each_mddev(mddev, tmp) {
export_array(mddev);
mddev->hold_active = 0;
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 00:57:23 +0000