diff options
author | Tejun Heo | 2015-07-01 20:53:37 -0400 |
---|---|---|
committer | Jens Axboe | 2015-07-02 08:46:00 -0600 |
commit | a20135ffbc44545596f9b99c970de097fb497bdd (patch) | |
tree | 18d7267ad1c0b0d603b4ca9cb1e43755c344f632 | |
parent | a13f35e8714009145e32ebe2bf25b84e1376e314 (diff) |
writeback: don't drain bdi_writeback_congested on bdi destruction
52ebea749aae ("writeback: make backing_dev_info host cgroup-specific
bdi_writebacks") made bdi (backing_dev_info) host per-cgroup wb's
(bdi_writeback's). As the congested state needs to be per-wb and
referenced from blkcg side and multiple wbs, the patch made all
non-root cong's (bdi_writeback_congested's) reference counted and
indexed on bdi.
When a bdi is destroyed, cgwb_bdi_destroy() tries to drain all
non-root cong's; however, this can hang indefinitely because wb's can
also be referenced from blkcg_gq's which are destroyed after bdi
destruction is complete.
This patch fixes the bug by updating bdi destruction to not wait for
cong's to drain. A cong is unlinked from bdi->cgwb_congested_tree on
bdi destuction regardless of its reference count as the bdi may go
away any point after destruction. wb_congested_put() checks whether
the cong is already unlinked on release.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Jon Christopherson <jon@jons.org>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=100681
Fixes: 52ebea749aae ("writeback: make backing_dev_info host cgroup-specific bdi_writebacks")
Tested-by: Jon Christopherson <jon@jons.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
-rw-r--r-- | mm/backing-dev.c | 22 |
1 files changed, 16 insertions, 6 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 51cc461e7256..dac5bf59309d 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -425,7 +425,6 @@ retry: new_congested = NULL; rb_link_node(&congested->rb_node, parent, node); rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); - atomic_inc(&bdi->usage_cnt); goto found; } @@ -456,7 +455,6 @@ found: */ void wb_congested_put(struct bdi_writeback_congested *congested) { - struct backing_dev_info *bdi = congested->bdi; unsigned long flags; local_irq_save(flags); @@ -465,12 +463,15 @@ void wb_congested_put(struct bdi_writeback_congested *congested) return; } - rb_erase(&congested->rb_node, &congested->bdi->cgwb_congested_tree); + /* bdi might already have been destroyed leaving @congested unlinked */ + if (congested->bdi) { + rb_erase(&congested->rb_node, + &congested->bdi->cgwb_congested_tree); + congested->bdi = NULL; + } + spin_unlock_irqrestore(&cgwb_lock, flags); kfree(congested); - - if (atomic_dec_and_test(&bdi->usage_cnt)) - wake_up_all(&cgwb_release_wait); } static void cgwb_release_workfn(struct work_struct *work) @@ -675,13 +676,22 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { struct radix_tree_iter iter; + struct bdi_writeback_congested *congested, *congested_n; void **slot; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); + radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); + + rbtree_postorder_for_each_entry_safe(congested, congested_n, + &bdi->cgwb_congested_tree, rb_node) { + rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree); + congested->bdi = NULL; /* mark @congested unlinked */ + } + spin_unlock_irq(&cgwb_lock); /* |