@@ -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);
blkg_conf_prep() currently calls blkg_lookup_create() while holding request queue spinlock. This means allocating memory for struct blkcg_gq has to be made non-blocking. This causes occasional -ENOMEM failures in call paths like below: pcpu_alloc+0x68f/0x710 __alloc_percpu_gfp+0xd/0x10 __percpu_counter_init+0x55/0xc0 cfq_pd_alloc+0x3b2/0x4e0 blkg_alloc+0x187/0x230 blkg_create+0x489/0x670 blkg_lookup_create+0x9a/0x230 blkg_conf_prep+0x1fb/0x240 __cfqg_set_weight_device.isra.105+0x5c/0x180 cfq_set_weight_on_dfl+0x69/0xc0 cgroup_file_write+0x39/0x1c0 kernfs_fop_write+0x13f/0x1d0 __vfs_write+0x23/0x120 vfs_write+0xc2/0x1f0 SyS_write+0x44/0xb0 entry_SYSCALL_64_fastpath+0x18/0xad In the code path above, percpu allocator cannot call vmalloc() due to queue spinlock. A failure in this call path gives grief to tools which are trying to configure io weights. We see occasional failures happen shortly after reboots even when system is not under any memory pressure. Machines with a lot of cpus are more vulnerable to this condition. Do struct blkcg_gq allocations outside the queue spinlock to allow blocking during memory allocations. Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Tahsin Erdogan <tahsin@google.com> --- v6: Due to Jens' objection to conditionally dropping locks based on gfp flags, go back to v1 approach. Perform queue bypass and policy enabled checks at every iteration. Add blkg_lookup_check() to reduce code duplication. v5: Removed stale blkg_alloc() in blkcg_init_queue() Pushed down radix_tree_preload() into blkg_create() because it disables preemption on return and makes it unsafe to call blocking memory allocations. v4: Simplified error checking in blkg_create() Factored out __blkg_lookup_create() v3: Pushed down all blkg allocations into blkg_create() v2: Moved blkg creation into blkg_lookup_create() to avoid duplicating blkg_lookup_create() logic. block/blk-cgroup.c | 123 ++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 98 insertions(+), 25 deletions(-)