From 7fc6b87a9ff537e7df32b1278118ce9c5bcd6788 Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Thu, 9 Mar 2017 00:05:31 -0800 Subject: blkcg: allocate struct blkcg_gq outside request queue spinlock 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. Update blkg_create() function to temporarily drop the rcu and queue locks when it is allowed by gfp mask. Suggested-by: Tejun Heo Signed-off-by: Tahsin Erdogan Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 01b62e7bac74..955903a8f6cb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -172,7 +172,8 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); + struct request_queue *q, gfp_t gfp, + const struct blkcg_policy *pol); int blkcg_init_queue(struct request_queue *q); void blkcg_drain_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); @@ -694,7 +695,8 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { spin_lock_irq(q->queue_lock); - blkg = blkg_lookup_create(blkcg, q); + blkg = blkg_lookup_create(blkcg, q, GFP_NOWAIT | __GFP_NOWARN, + NULL); if (IS_ERR(blkg)) blkg = NULL; spin_unlock_irq(q->queue_lock); -- cgit v1.2.3