From 72e06c255181537d0b3e1f657a9ed81655d745b1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 5 Mar 2012 13:15:00 -0800 Subject: blkcg: shoot down blkio_groups on elevator switch Elevator switch may involve changes to blkcg policies. Implement shoot down of blkio_groups. Combined with the previous bypass updates, the end goal is updating blkcg core such that it can ensure that blkcg's being affected become quiescent and don't have any per-blkg data hanging around before commencing any policy updates. Until queues are made aware of the policies that applies to them, as an interim step, all per-policy blkg data will be shot down. * blk-throtl doesn't need this change as it can't be disabled for a live queue; however, update it anyway as the scheduled blkg unification requires this behavior change. This means that blk-throtl configuration will be unnecessarily lost over elevator switch. This oddity will be removed after blkcg learns to associate individual policies with request_queues. * blk-throtl dosen't shoot down root_tg. This is to ease transition. Unified blkg will always have persistent root group and not shooting down root_tg for now eases transition to that point by avoiding having to update td->root_tg and is safe as blk-throtl can never be disabled -v2: Vivek pointed out that group list is not guaranteed to be empty on return from clear function if it raced cgroup removal and lost. Fix it by waiting a bit and retrying. This kludge will soon be removed once locking is updated such that blkg is never in limbo state between blkcg and request_queue locks. blk-throtl no longer shoots down root_tg to avoid breaking td->root_tg. Also, Nest queue_lock inside blkio_list_lock not the other way around to avoid introduce possible deadlock via blkcg lock. -v3: blkcg_clear_queue() repositioned and renamed to blkg_destroy_all() to increase consistency with later changes. cfq_clear_queue() updated to check q->elevator before dereferencing it to avoid NULL dereference on not fully initialized queues (used by later change). Signed-off-by: Tejun Heo Cc: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-throttle.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-) (limited to 'block/blk-throttle.c') diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 702c0e64e09..3699ab40d49 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -989,12 +989,17 @@ throtl_destroy_tg(struct throtl_data *td, struct throtl_grp *tg) td->nr_undestroyed_grps--; } -static void throtl_release_tgs(struct throtl_data *td) +static bool throtl_release_tgs(struct throtl_data *td, bool release_root) { struct hlist_node *pos, *n; struct throtl_grp *tg; + bool empty = true; hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) { + /* skip root? */ + if (!release_root && tg == td->root_tg) + continue; + /* * If cgroup removal path got to blk_group first and removed * it from cgroup list, then it will take care of destroying @@ -1002,7 +1007,10 @@ static void throtl_release_tgs(struct throtl_data *td) */ if (!blkiocg_del_blkio_group(&tg->blkg)) throtl_destroy_tg(td, tg); + else + empty = false; } + return empty; } /* @@ -1029,6 +1037,20 @@ void throtl_unlink_blkio_group(void *key, struct blkio_group *blkg) spin_unlock_irqrestore(td->queue->queue_lock, flags); } +static bool throtl_clear_queue(struct request_queue *q) +{ + lockdep_assert_held(q->queue_lock); + + /* + * Clear tgs but leave the root one alone. This is necessary + * because root_tg is expected to be persistent and safe because + * blk-throtl can never be disabled while @q is alive. This is a + * kludge to prepare for unified blkg. This whole function will be + * removed soon. + */ + return throtl_release_tgs(q->td, false); +} + static void throtl_update_blkio_group_common(struct throtl_data *td, struct throtl_grp *tg) { @@ -1097,6 +1119,7 @@ static void throtl_shutdown_wq(struct request_queue *q) static struct blkio_policy_type blkio_policy_throtl = { .ops = { .blkio_unlink_group_fn = throtl_unlink_blkio_group, + .blkio_clear_queue_fn = throtl_clear_queue, .blkio_update_group_read_bps_fn = throtl_update_blkio_group_read_bps, .blkio_update_group_write_bps_fn = @@ -1282,7 +1305,7 @@ void blk_throtl_exit(struct request_queue *q) throtl_shutdown_wq(q); spin_lock_irq(q->queue_lock); - throtl_release_tgs(td); + throtl_release_tgs(td, true); /* If there are other groups */ if (td->nr_undestroyed_grps > 0) -- cgit v1.2.3