Re: [PATCH] block: use rcu_work instead of call_rcu to avoid sleep in softirq

["Paul E. McKenney" <paulmck@linux.ibm.com>]

On Wed, Nov 28, 2018 at 04:42:01PM +0800, Yufen Yu wrote:
> We recently got a stack by syzkaller like this:
> 
> BUG: sleeping function called from invalid context at mm/slab.h:361
> in_atomic(): 1, irqs_disabled(): 0, pid: 6644, name: blkid
> INFO: lockdep is turned off.
> CPU: 1 PID: 6644 Comm: blkid Not tainted 4.4.163-514.55.6.9.x86_64+ #76
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014
>  0000000000000000 5ba6a6b879e50c00 ffff8801f6b07b10 ffffffff81cb2194
>  0000000041b58ab3 ffffffff833c7745 ffffffff81cb2080 5ba6a6b879e50c00
>  0000000000000000 0000000000000001 0000000000000004 0000000000000000
> Call Trace:
>  <IRQ>  [<ffffffff81cb2194>] __dump_stack lib/dump_stack.c:15 [inline]
>  <IRQ>  [<ffffffff81cb2194>] dump_stack+0x114/0x1a0 lib/dump_stack.c:51
>  [<ffffffff8129a981>] ___might_sleep+0x291/0x490 kernel/sched/core.c:7675
>  [<ffffffff8129ac33>] __might_sleep+0xb3/0x270 kernel/sched/core.c:7637
>  [<ffffffff81794c13>] slab_pre_alloc_hook mm/slab.h:361 [inline]
>  [<ffffffff81794c13>] slab_alloc_node mm/slub.c:2610 [inline]
>  [<ffffffff81794c13>] slab_alloc mm/slub.c:2692 [inline]
>  [<ffffffff81794c13>] kmem_cache_alloc_trace+0x2c3/0x5c0 mm/slub.c:2709
>  [<ffffffff81cbe9a7>] kmalloc include/linux/slab.h:479 [inline]
>  [<ffffffff81cbe9a7>] kzalloc include/linux/slab.h:623 [inline]
>  [<ffffffff81cbe9a7>] kobject_uevent_env+0x2c7/0x1150 lib/kobject_uevent.c:227
>  [<ffffffff81cbf84f>] kobject_uevent+0x1f/0x30 lib/kobject_uevent.c:374
>  [<ffffffff81cbb5b9>] kobject_cleanup lib/kobject.c:633 [inline]
>  [<ffffffff81cbb5b9>] kobject_release+0x229/0x440 lib/kobject.c:675
>  [<ffffffff81cbb0a2>] kref_sub include/linux/kref.h:73 [inline]
>  [<ffffffff81cbb0a2>] kref_put include/linux/kref.h:98 [inline]
>  [<ffffffff81cbb0a2>] kobject_put+0x72/0xd0 lib/kobject.c:692
>  [<ffffffff8216f095>] put_device+0x25/0x30 drivers/base/core.c:1237
>  [<ffffffff81c4cc34>] delete_partition_rcu_cb+0x1d4/0x2f0 block/partition-generic.c:232
>  [<ffffffff813c08bc>] __rcu_reclaim kernel/rcu/rcu.h:118 [inline]
>  [<ffffffff813c08bc>] rcu_do_batch kernel/rcu/tree.c:2705 [inline]
>  [<ffffffff813c08bc>] invoke_rcu_callbacks kernel/rcu/tree.c:2973 [inline]
>  [<ffffffff813c08bc>] __rcu_process_callbacks kernel/rcu/tree.c:2940 [inline]
>  [<ffffffff813c08bc>] rcu_process_callbacks+0x59c/0x1c70 kernel/rcu/tree.c:2957
>  [<ffffffff8120f509>] __do_softirq+0x299/0xe20 kernel/softirq.c:273
>  [<ffffffff81210496>] invoke_softirq kernel/softirq.c:350 [inline]
>  [<ffffffff81210496>] irq_exit+0x216/0x2c0 kernel/softirq.c:391
>  [<ffffffff82c2cd7b>] exiting_irq arch/x86/include/asm/apic.h:652 [inline]
>  [<ffffffff82c2cd7b>] smp_apic_timer_interrupt+0x8b/0xc0 arch/x86/kernel/apic/apic.c:926
>  [<ffffffff82c2bc25>] apic_timer_interrupt+0xa5/0xb0 arch/x86/entry/entry_64.S:746
>  <EOI>  [<ffffffff814cbf40>] ? audit_kill_trees+0x180/0x180
>  [<ffffffff8187d2f7>] fd_install+0x57/0x80 fs/file.c:626
>  [<ffffffff8180989e>] do_sys_open+0x45e/0x550 fs/open.c:1043
>  [<ffffffff818099c2>] SYSC_open fs/open.c:1055 [inline]
>  [<ffffffff818099c2>] SyS_open+0x32/0x40 fs/open.c:1050
>  [<ffffffff82c299e1>] entry_SYSCALL_64_fastpath+0x1e/0x9a
> 
> In softirq context, we call rcu callback function delete_partition_rcu_cb(),
> which may allocate memory by kzalloc with GFP_KERNEL flag. If the
> allocation cannot be satisfied, it may sleep. However, That is not allowed
> in softirq contex.
> 
> Although we found this problem on linux 4.4, the latest kernel version
> seems to have this problem as well. And it is very similar to the
> previous one:
> 	https://lkml.org/lkml/2018/7/9/391
> 
> Fix it by using RCU workqueue, which allows sleep.
> 
> Signed-off-by: Yufen Yu <yuyufen@huawei.com>

Reviewed-by: Paul E. McKenney <paulmck@linux.ibm.com>

> ---
>  block/partition-generic.c | 8 +++++---
>  include/linux/genhd.h     | 2 +-
>  2 files changed, 6 insertions(+), 4 deletions(-)
> 
> diff --git a/block/partition-generic.c b/block/partition-generic.c
> index d3d14e81fb12..5f8db5c5140f 100644
> --- a/block/partition-generic.c
> +++ b/block/partition-generic.c
> @@ -249,9 +249,10 @@ struct device_type part_type = {
>  	.uevent		= part_uevent,
>  };
> 
> -static void delete_partition_rcu_cb(struct rcu_head *head)
> +static void delete_partition_work_fn(struct work_struct *work)
>  {
> -	struct hd_struct *part = container_of(head, struct hd_struct, rcu_head);
> +	struct hd_struct *part = container_of(to_rcu_work(work), struct hd_struct,
> +					rcu_work);
> 
>  	part->start_sect = 0;
>  	part->nr_sects = 0;
> @@ -262,7 +263,8 @@ static void delete_partition_rcu_cb(struct rcu_head *head)
>  void __delete_partition(struct percpu_ref *ref)
>  {
>  	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
> -	call_rcu(&part->rcu_head, delete_partition_rcu_cb);
> +	INIT_RCU_WORK(&part->rcu_work, delete_partition_work_fn);
> +	queue_rcu_work(system_wq, &part->rcu_work);
>  }
> 
>  /*
> diff --git a/include/linux/genhd.h b/include/linux/genhd.h
> index 70fc838e6773..0c5ee17b4d88 100644
> --- a/include/linux/genhd.h
> +++ b/include/linux/genhd.h
> @@ -129,7 +129,7 @@ struct hd_struct {
>  	struct disk_stats dkstats;
>  #endif
>  	struct percpu_ref ref;
> -	struct rcu_head rcu_head;
> +	struct rcu_work rcu_work;
>  };
> 
>  #define GENHD_FL_REMOVABLE			1
> -- 
> 2.16.2.dirty
>