blk-cgroup: Pre-allocate tree node on blkg_conf_prep (f255c19b) · Commits · 戴 / test

Similarly to commit ("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>

block/blk-cgroup.c

+12 −2

Original line number	Diff line number	Diff line
		@@ -657,6 +657,12 @@ 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);

		@@ -664,7 +670,7 @@ 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) {
		@@ -673,10 +679,12 @@ int blkg_conf_prep(struct blkcg blkcg, const struct blkcg_policy pol,
		blkg = blkg_create(pos, q, new_blkg);
		if (IS_ERR(blkg)) {
		ret = PTR_ERR(blkg);
		goto fail_unlock;
		goto fail_preloaded;
		}
		}

		radix_tree_preload_end();

		if (pos == blkcg)
		goto success;
		}
		@@ -686,6 +694,8 @@ success:
		ctx->body = input;
		return 0;

		fail_preloaded:
		radix_tree_preload_end();
		fail_unlock:
		spin_unlock_irq(&q->queue_lock);
		rcu_read_unlock();

Admin message