From: NeilBrown neilb@suse.com
commit 4d5324f760aacaefeb721b172aa14bf66045c332 upstream
Most often mddev_suspend() is called with reconfig_mutex held. Make this a requirement in preparation a subsequent patch. Also require reconfig_mutex to be held for mddev_resume(), partly for symmetry and partly to guarantee no races with incr/decr of mddev->suspend.
Taking the mutex in r5c_disable_writeback_async() is a little tricky as this is called from a work queue via log->disable_writeback_work, and flush_work() is called on that while holding ->reconfig_mutex. If the work item hasn't run before flush_work() is called, the work function will not be able to get the mutex.
So we use mddev_trylock() inside the wait_event() call, and have that abort when conf->log is set to NULL, which happens before flush_work() is called. We wait in mddev->sb_wait and ensure this is woken when any of the conditions change. This requires waking mddev->sb_wait in mddev_unlock(). This is only like to trigger extra wake_ups of threads that needn't be woken when metadata is being written, and that doesn't happen often enough that the cost would be noticeable.
Signed-off-by: NeilBrown neilb@suse.com Signed-off-by: Shaohua Li shli@fb.com [jwang: cherry-pick to 4.14] Signed-off-by: Jack Wang jinpu.wang@profitbricks.com --- drivers/md/dm-raid.c | 10 ++++++++-- drivers/md/md.c | 3 +++ drivers/md/raid5-cache.c | 18 +++++++++++++----- 3 files changed, 24 insertions(+), 7 deletions(-)
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 33834db..38a2ac2 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -3637,8 +3637,11 @@ static void raid_postsuspend(struct dm_target *ti) { struct raid_set *rs = ti->private;
- if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) + if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { + mddev_lock_nointr(&rs->md); mddev_suspend(&rs->md); + mddev_unlock(&rs->md); + }
rs->md.ro = 1; } @@ -3898,8 +3901,11 @@ static void raid_resume(struct dm_target *ti) if (!(rs->ctr_flags & RESUME_STAY_FROZEN_FLAGS)) clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
- if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) + if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) { + mddev_lock_nointr(mddev); mddev_resume(mddev); + mddev_unlock(mddev); + } }
static struct target_type raid_target = { diff --git a/drivers/md/md.c b/drivers/md/md.c index 24e64b0..436066d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -344,6 +344,7 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio) void mddev_suspend(struct mddev *mddev) { WARN_ON_ONCE(mddev->thread && current == mddev->thread->tsk); + lockdep_assert_held(&mddev->reconfig_mutex); if (mddev->suspended++) return; synchronize_rcu(); @@ -357,6 +358,7 @@ EXPORT_SYMBOL_GPL(mddev_suspend);
void mddev_resume(struct mddev *mddev) { + lockdep_assert_held(&mddev->reconfig_mutex); if (--mddev->suspended) return; wake_up(&mddev->sb_wait); @@ -663,6 +665,7 @@ void mddev_unlock(struct mddev *mddev) */ spin_lock(&pers_lock); md_wakeup_thread(mddev->thread); + wake_up(&mddev->sb_wait); spin_unlock(&pers_lock); } EXPORT_SYMBOL_GPL(mddev_unlock); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 9a34072..79d8127 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -693,6 +693,8 @@ static void r5c_disable_writeback_async(struct work_struct *work) struct r5l_log *log = container_of(work, struct r5l_log, disable_writeback_work); struct mddev *mddev = log->rdev->mddev; + struct r5conf *conf = mddev->private; + int locked = 0;
if (log->r5c_journal_mode == R5C_JOURNAL_MODE_WRITE_THROUGH) return; @@ -701,11 +703,15 @@ static void r5c_disable_writeback_async(struct work_struct *work)
/* wait superblock change before suspend */ wait_event(mddev->sb_wait, - !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)); - - mddev_suspend(mddev); - log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; - mddev_resume(mddev); + conf->log == NULL || + (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) && + (locked = mddev_trylock(mddev)))); + if (locked) { + mddev_suspend(mddev); + log->r5c_journal_mode = R5C_JOURNAL_MODE_WRITE_THROUGH; + mddev_resume(mddev); + mddev_unlock(mddev); + } }
static void r5l_submit_current_io(struct r5l_log *log) @@ -3161,6 +3167,8 @@ void r5l_exit_log(struct r5conf *conf) conf->log = NULL; synchronize_rcu();
+ /* Ensure disable_writeback_work wakes up and exits */ + wake_up(&conf->mddev->sb_wait); flush_work(&log->disable_writeback_work); md_unregister_thread(&log->reclaim_thread); mempool_destroy(log->meta_pool);