blkcg: make blkcg_print_blkgs() grab q locks instead of blkcg lock

Instead of holding blkcg->lock while walking ->blkg_list and executing
prfill(), RCU walk ->blkg_list and hold the blkg's queue lock while
executing prfill().  This makes prfill() implementations easier as
stats are mostly protected by queue lock.

This will be used to implement hierarchical stats.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index f9797b244eb380c37e2072b079e1a242bbb6e445..87ea95d1f533ead81e8c25adcdabcf98ab1bd431 100644 (file)
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -504,8 +504,9 @@ static const char *blkg_dev_name(struct blkcg_gq *blkg)
  *
  * This function invokes @prfill on each blkg of @blkcg if pd for the
  * policy specified by @pol exists.  @prfill is invoked with @sf, the
- * policy data and @data.  If @show_total is %true, the sum of the return
- * values from @prfill is printed with "Total" label at the end.
+ * policy data and @data and the matching queue lock held.  If @show_total
+ * is %true, the sum of the return values from @prfill is printed with
+ * "Total" label at the end.
  *
  * This is to be used to construct print functions for
  * cftype->read_seq_string method.
@@ -520,11 +521,14 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg,
        struct hlist_node *n;
        u64 total = 0;
 
-       spin_lock_irq(&blkcg->lock);
-       hlist_for_each_entry(blkg, n, &blkcg->blkg_list, blkcg_node)
+       rcu_read_lock();
+       hlist_for_each_entry_rcu(blkg, n, &blkcg->blkg_list, blkcg_node) {
+               spin_lock_irq(blkg->q->queue_lock);
                if (blkcg_policy_enabled(blkg->q, pol))
                        total += prfill(sf, blkg->pd[pol->plid], data);
-       spin_unlock_irq(&blkcg->lock);
+               spin_unlock_irq(blkg->q->queue_lock);
+       }
+       rcu_read_unlock();
 
        if (show_total)
                seq_printf(sf, "Total %llu\n", (unsigned long long)total);