@@ -7938,18 +7938,9 @@ static int raid5_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
print_raid5_conf(conf);
if (test_bit(Journal, &rdev->flags) && conf->log) {
- /*
- * we can't wait pending write here, as this is called in
- * raid5d, wait will deadlock.
- * neilb: there is no locking about new writes here,
- * so this cannot be safe.
- */
- if (atomic_read(&conf->active_stripes) ||
- atomic_read(&conf->r5c_cached_full_stripes) ||
- atomic_read(&conf->r5c_cached_partial_stripes)) {
- return -EBUSY;
- }
+ mddev_suspend(mddev);
log_exit(conf);
+ mddev_resume(mddev);
return 0;
}
if (rdev == rcu_access_pointer(p->rdev))
@@ -8697,8 +8688,11 @@ static int raid5_change_consistency_policy(struct mddev *mddev, const char *buf)
err = log_init(conf, NULL, true);
if (!err) {
err = resize_stripes(conf, conf->pool_size);
- if (err)
+ if (err) {
+ mddev_suspend(mddev);
log_exit(conf);
+ mddev_resume(mddev);
+ }
}
} else
err = -EINVAL;
The raid5-cache code relies on there being no IO in flight when log_exit() is called. There are two places where this is not guaranteed so add mddev_suspend() and mddev_resume() calls to these sites. The site in raid5_remove_disk() has a comment saying that it is called in raid5d and thus cannot wait for pending writes; however that does not appear to be correct anymore (if it ever was) as raid5_remove_disk() is called from hot_remove_disk() which only appears to be called in the md_ioctl(). Thus, the comment is removed, as well as the racy check and replaced with calls to suspend/resume. The site in raid5_change_consistency_policy() is in the error path, and another similar call site already has suspend/resume calls just below it; so it should be equally safe to make that change here. Signed-off-by: Logan Gunthorpe <logang@deltatee.com> --- drivers/md/raid5.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-)