diff options
| -rw-r--r-- | block/blk-cgroup.c | 123 |
1 files changed, 98 insertions, 25 deletions
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index bbe7ee00bd3d..7c2947128f58 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -772,6 +772,27 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, } EXPORT_SYMBOL_GPL(blkg_rwstat_recursive_sum); +/* Performs queue bypass and policy enabled checks then looks up blkg. */ +static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, + const struct blkcg_policy *pol, + struct request_queue *q) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + lockdep_assert_held(q->queue_lock); + + if (!blkcg_policy_enabled(q, pol)) + return ERR_PTR(-EOPNOTSUPP); + + /* + * This could be the first entry point of blkcg implementation and + * we shouldn't allow anything to go through for a bypassing queue. + */ + if (unlikely(blk_queue_bypass(q))) + return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY); + + return __blkg_lookup(blkcg, q, true /* update_hint */); +} + /** * blkg_conf_prep - parse and prepare for per-blkg config update * @blkcg: target block cgroup @@ -789,6 +810,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, __acquires(rcu) __acquires(disk->queue->queue_lock) { struct gendisk *disk; + struct request_queue *q; struct blkcg_gq *blkg; struct module *owner; unsigned int major, minor; @@ -807,44 +829,95 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, if (!disk) return -ENODEV; if (part) { - owner = disk->fops->owner; - put_disk(disk); - module_put(owner); - return -ENODEV; + ret = -ENODEV; + goto fail; } - rcu_read_lock(); - spin_lock_irq(disk->queue->queue_lock); + q = disk->queue; - if (blkcg_policy_enabled(disk->queue, pol)) - blkg = blkg_lookup_create(blkcg, disk->queue); - else - blkg = ERR_PTR(-EOPNOTSUPP); + rcu_read_lock(); + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_check(blkcg, pol, q); if (IS_ERR(blkg)) { ret = PTR_ERR(blkg); + goto fail_unlock; + } + + if (blkg) + goto success; + + /* + * Create blkgs walking down from blkcg_root to @blkcg, so that all + * non-root blkgs have access to their parents. + */ + while (true) { + struct blkcg *pos = blkcg; + struct blkcg *parent; + struct blkcg_gq *new_blkg; + + parent = blkcg_parent(blkcg); + while (parent && !__blkg_lookup(parent, q, false)) { + pos = parent; + parent = blkcg_parent(parent); + } + + /* Drop locks to do new blkg allocation with GFP_KERNEL. */ + spin_unlock_irq(q->queue_lock); rcu_read_unlock(); - spin_unlock_irq(disk->queue->queue_lock); - owner = disk->fops->owner; - put_disk(disk); - module_put(owner); - /* - * If queue was bypassing, we should retry. Do so after a - * short msleep(). It isn't strictly necessary but queue - * can be bypassing for some time and it's always nice to - * avoid busy looping. - */ - if (ret == -EBUSY) { - msleep(10); - ret = restart_syscall(); + + new_blkg = blkg_alloc(pos, q, GFP_KERNEL); + if (unlikely(!new_blkg)) { + ret = -ENOMEM; + goto fail; } - return ret; - } + rcu_read_lock(); + spin_lock_irq(q->queue_lock); + + blkg = blkg_lookup_check(pos, pol, q); + if (IS_ERR(blkg)) { + ret = PTR_ERR(blkg); + goto fail_unlock; + } + + if (blkg) { + blkg_free(new_blkg); + } else { + blkg = blkg_create(pos, q, new_blkg); + if (unlikely(IS_ERR(blkg))) { + ret = PTR_ERR(blkg); + goto fail_unlock; + } + } + + if (pos == blkcg) + goto success; + } +success: ctx->disk = disk; ctx->blkg = blkg; ctx->body = body; return 0; + +fail_unlock: + spin_unlock_irq(q->queue_lock); + rcu_read_unlock(); +fail: + owner = disk->fops->owner; + put_disk(disk); + module_put(owner); + /* + * If queue was bypassing, we should retry. Do so after a + * short msleep(). It isn't strictly necessary but queue + * can be bypassing for some time and it's always nice to + * avoid busy looping. + */ + if (ret == -EBUSY) { + msleep(10); + ret = restart_syscall(); + } + return ret; } EXPORT_SYMBOL_GPL(blkg_conf_prep); |