From: Sebastian Andrzej Siewior Date: Tue, 13 Mar 2018 13:49:16 +0100 Subject: [PATCH 185/351] block: blk-mq: move blk_queue_usage_counter_release() into process context Origin: https://git.kernel.org/cgit/linux/kernel/git/rt/linux-stable-rt.git/commit?id=ea6963bba2bb29ce40ebaf69a1911cb113ffb0f2 | BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 | in_atomic(): 1, irqs_disabled(): 0, pid: 255, name: kworker/u257:6 | 5 locks held by kworker/u257:6/255: | #0: ("events_unbound"){.+.+.+}, at: [] process_one_work+0x171/0x5e0 | #1: ((&entry->work)){+.+.+.}, at: [] process_one_work+0x171/0x5e0 | #2: (&shost->scan_mutex){+.+.+.}, at: [] __scsi_add_device+0xa3/0x130 [scsi_mod] | #3: (&set->tag_list_lock){+.+...}, at: [] blk_mq_init_queue+0x96a/0xa50 | #4: (rcu_read_lock_sched){......}, at: [] percpu_ref_kill_and_confirm+0x1d/0x120 | Preemption disabled at:[] blk_mq_freeze_queue_start+0x56/0x70 | | CPU: 2 PID: 255 Comm: kworker/u257:6 Not tainted 3.18.7-rt0+ #1 | Workqueue: events_unbound async_run_entry_fn | 0000000000000003 ffff8800bc29f998 ffffffff815b3a12 0000000000000000 | 0000000000000000 ffff8800bc29f9b8 ffffffff8109aa16 ffff8800bc29fa28 | ffff8800bc5d1bc8 ffff8800bc29f9e8 ffffffff815b8dd4 ffff880000000000 | Call Trace: | [] dump_stack+0x4f/0x7c | [] __might_sleep+0x116/0x190 | [] rt_spin_lock+0x24/0x60 | [] __wake_up+0x29/0x60 | [] blk_mq_usage_counter_release+0x1e/0x20 | [] percpu_ref_kill_and_confirm+0x106/0x120 | [] blk_mq_freeze_queue_start+0x56/0x70 | [] blk_mq_update_tag_set_depth+0x40/0xd0 | [] blk_mq_init_queue+0x98c/0xa50 | [] scsi_mq_alloc_queue+0x20/0x60 [scsi_mod] | [] scsi_alloc_sdev+0x2f5/0x370 [scsi_mod] | [] scsi_probe_and_add_lun+0x9e4/0xdd0 [scsi_mod] | [] __scsi_add_device+0x126/0x130 [scsi_mod] | [] ata_scsi_scan_host+0xaf/0x200 [libata] | [] async_port_probe+0x46/0x60 [libata] | [] async_run_entry_fn+0x3b/0xf0 | [] process_one_work+0x201/0x5e0 percpu_ref_kill_and_confirm() invokes blk_mq_usage_counter_release() in a rcu-sched region. swait based wake queue can't be used due to wake_up_all() usage and disabled interrupts in !RT configs (as reported by Corey Minyard). The wq_has_sleeper() check has been suggested by Peter Zijlstra. Signed-off-by: Sebastian Andrzej Siewior --- block/blk-core.c | 14 +++++++++++++- include/linux/blkdev.h | 2 ++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/block/blk-core.c b/block/blk-core.c index 461a93c08c14..02835970ef1e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -973,12 +973,21 @@ void blk_queue_exit(struct request_queue *q) percpu_ref_put(&q->q_usage_counter); } +static void blk_queue_usage_counter_release_swork(struct swork_event *sev) +{ + struct request_queue *q = + container_of(sev, struct request_queue, mq_pcpu_wake); + + wake_up_all(&q->mq_freeze_wq); +} + static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); - wake_up_all(&q->mq_freeze_wq); + if (wq_has_sleeper(&q->mq_freeze_wq)) + swork_queue(&q->mq_pcpu_wake); } static void blk_rq_timed_out_timer(struct timer_list *t) @@ -1078,6 +1087,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); init_waitqueue_head(&q->mq_freeze_wq); + INIT_SWORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_swork); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. @@ -3967,6 +3977,8 @@ int __init blk_dev_init(void) if (!kblockd_workqueue) panic("Failed to create kblockd\n"); + BUG_ON(swork_get()); + request_cachep = kmem_cache_create("blkdev_requests", sizeof(struct request), 0, SLAB_PANIC, NULL); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 39d90bf9b5fa..0313098a428d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,6 +27,7 @@ #include #include #include +#include struct module; struct scsi_ioctl_command; @@ -664,6 +665,7 @@ struct request_queue { #endif struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; + struct swork_event mq_pcpu_wake; struct percpu_ref q_usage_counter; struct list_head all_q_node;