From: Gabriel Krisman Bertazi krisman@collabora.com
[ Upstream commit f255c19b3ab46d3cad3b1b2e1036f4c926cb1d0c ]
Similarly to commit 457e490f2b741 ("blkcg: allocate struct blkcg_gq outside request queue spinlock"), blkg_create can also trigger occasional -ENOMEM failures at the radix insertion because any allocation inside blkg_create has to be non-blocking, making it more likely to fail. This causes trouble for userspace tools trying to configure io weights who need to deal with this condition.
This patch reduces the occurrence of -ENOMEMs on this path by preloading the radix tree element on a GFP_KERNEL context, such that we guarantee the later non-blocking insertion won't fail.
A similar solution exists in blkcg_init_queue for the same situation.
Acked-by: Tejun Heo tj@kernel.org Signed-off-by: Gabriel Krisman Bertazi krisman@collabora.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-cgroup.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index a1282fe901ec..0b61171c3456 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -903,6 +903,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, goto fail; }
+ if (radix_tree_preload(GFP_KERNEL)) { + blkg_free(new_blkg); + ret = -ENOMEM; + goto fail; + } + rcu_read_lock(); spin_lock_irq(q->queue_lock);
@@ -910,7 +916,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); blkg_free(new_blkg); - goto fail_unlock; + goto fail_preloaded; }
if (blkg) { @@ -919,10 +925,12 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, blkg = blkg_create(pos, q, new_blkg); if (unlikely(IS_ERR(blkg))) { ret = PTR_ERR(blkg); - goto fail_unlock; + goto fail_preloaded; } }
+ radix_tree_preload_end(); + if (pos == blkcg) goto success; } @@ -932,6 +940,8 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, ctx->body = input; return 0;
+fail_preloaded: + radix_tree_preload_end(); fail_unlock: spin_unlock_irq(q->queue_lock); rcu_read_unlock();