Re: [PATCH] IO-Controller: Fix kernel panic after moving a task

[Vivek Goyal <vgoyal-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>]

On Thu, Apr 16, 2009 at 01:25:35PM +0800, Gui Jianfeng wrote:
> Vivek Goyal wrote:
> > +#ifdef CONFIG_IOSCHED_CFQ_HIER
> > +static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
> > +{
> > +	struct cfq_queue *async_cfqq = cic_to_cfqq(cic, 0);
> > +	struct cfq_queue *sync_cfqq = cic_to_cfqq(cic, 1);
> > +	struct cfq_data *cfqd = cic->key;
> > +	struct io_group *iog, *__iog;
> > +	unsigned long flags;
> > +	struct request_queue *q;
> > +
> > +	if (unlikely(!cfqd))
> > +		return;
> > +
> > +	q = cfqd->q;
> > +
> > +	spin_lock_irqsave(q->queue_lock, flags);
> > +
> > +	iog = io_lookup_io_group_current(q);
> > +
> 
>   Hi Vivek,
> 
>   I triggered another kernel panic when testing. When moving a task to another 
>   cgroup, the corresponding iog may not be setup properly all the time. "iog"
>   might be NULL here. io_ioq_move() receives a NULL iog, kernel crash.
> 
>   Consider the following piece of code:
> 
>  941 int elv_set_request(struct request_queue *q, struct request *rq, gfp_t gfp_mask)
>  942 {
>  943         struct elevator_queue *e = q->elevator;
>  944 
>  945         elv_fq_set_request_io_group(q, rq);
>  
>  -->task moving to a new group is happenning here.
> 
>  946 
>  947         /*
>  948          * Optimization for noop, deadline and AS which maintain only single
>  949          * ioq per io group
>  950          */
>  951         if (elv_iosched_single_ioq(e))
>  952                 return elv_fq_set_request_ioq(q, rq, gfp_mask);
>  953 
>  954         if (e->ops->elevator_set_req_fn)
>  955                 return e->ops->elevator_set_req_fn(q, rq, gfp_mask);
> 
> cfq_set_request() will finally call io_ioq_move(), but the iog is NULL, beacause the iogs in the 
> hierarchy are not built yet. So kernel crashes.
> 
>  956 
>  957         rq->elevator_private = NULL;
>  958         return 0;
>  959 }
> 

Thanks Gui. Good catch. 

> BUG: unable to handle kernel NULL pointer dereference at 000000bc
> IP: [<c04ebf8f>] io_ioq_move+0xf2/0x109
> *pde = 6cc00067
> Oops: 0000 [#1] SMP
> last sysfs file: /sys/block/hdb/queue/slice_idle
> Modules linked in: ipv6 cpufreq_ondemand acpi_cpufreq dm_mirror dm_multipath sbs sbshc battery ac lp snd_hda_codec_realtek snd_hda_intel snd_hda_codec snd_seq_dummy snd_seq_oss snd_seq_midi_event snd_seq snd_seq_device snd_pcm_oss snd_mixer_oss snd_pcm serio_raw snd_timer rtc_cmos parport_pc snd r8169 button rtc_core parport soundcore mii i2c_i801 rtc_lib snd_page_alloc pcspkr i2c_core dm_region_hash dm_log dm_mod ext3 jbd mbcache uhci_hcd ohci_hcd ehci_hcd
> 
> Pid: 5431, comm: dd Not tainted (2.6.29-rc7-vivek #19) Veriton M460
> EIP: 0060:[<c04ebf8f>] EFLAGS: 00010046 CPU: 0
> EIP is at io_ioq_move+0xf2/0x109
> EAX: f6203a88 EBX: f6792c94 ECX: f6203a84 EDX: 00000006
> ESI: 00000000 EDI: 00000000 EBP: f6203a60 ESP: f6304c28
>  DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
> Process dd (pid: 5431, ti=f6304000 task=f669dae0 task.ti=f6304000)
> Stack:
>  f62478c0 0100dd40 f6247908 f62d995c 00000000 00000000 f675b54c c04e9182
>  f638e9b0 00000282 f62d99a4 f6325a2c c04e9113 f5a707c0 c04e7ae0 f675b000
>  f62d95fc f6325a2c c04e8501 00000010 f631e4e8 f675b000 00080000 ffffff10
> Call Trace:
>  [<c04e9182>] changed_cgroup+0x6f/0x8d
>  [<c04e9113>] changed_cgroup+0x0/0x8d
>  [<c04e7ae0>] __call_for_each_cic+0x1b/0x25
>  [<c04e8501>] cfq_set_request+0x158/0x2c7
>  [<c06316e6>] _spin_unlock_irqrestore+0x5/0x6
>  [<c04eb106>] elv_fq_set_request_io_group+0x2b/0x3e
>  [<c04e83a9>] cfq_set_request+0x0/0x2c7
>  [<c04dddcb>] elv_set_request+0x3e/0x4e
>  [<c04df3da>] get_request+0x1ed/0x29b
>  [<c04df9bb>] get_request_wait+0xdf/0xf2
>  [<c04dfd89>] __make_request+0x2c6/0x372
>  [<c049bd76>] do_mpage_readpage+0x4fe/0x5e3
>  [<c04deba5>] generic_make_request+0x2d0/0x355
>  [<c04dff47>] submit_bio+0x92/0x97
>  [<c045bfcb>] add_to_page_cache_locked+0x8a/0xb7
>  [<c049bfa4>] mpage_end_io_read+0x0/0x50
>  [<c049b1b6>] mpage_bio_submit+0x19/0x1d
>  [<c049bf9a>] mpage_readpages+0x9b/0xa5
>  [<f7dd18c7>] ext3_readpages+0x0/0x15 [ext3]
>  [<c0462192>] __do_page_cache_readahead+0xea/0x154
>  [<f7dd2286>] ext3_get_block+0x0/0xbe [ext3]
>  [<c045d34d>] generic_file_aio_read+0x276/0x569
>  [<c047cdd9>] do_sync_read+0xbf/0xfe
>  [<c043a3f2>] getnstimeofday+0x51/0xdb
>  [<c0434d3c>] autoremove_wake_function+0x0/0x2d
>  [<c041bdc3>] sched_slice+0x61/0x6a
>  [<c0423114>] task_tick_fair+0x3d/0x60
>  [<c04c1d79>] security_file_permission+0xc/0xd
>  [<c047cd1a>] do_sync_read+0x0/0xfe
>  [<c047d35a>] vfs_read+0x6c/0x8b
>  [<c047d67e>] sys_read+0x3c/0x63
>  [<c0402fc1>] sysenter_do_call+0x12/0x21
>  [<c0630000>] schedule+0x551/0x830
> Code: 08 31 c9 89 da e8 77 fc ff ff 8b 86 bc 00 00 00 85 ff 89 43 38 8d 46 60 89 43 40 74 1d 83 c4 0c 89 d8 5b 5e 5f 5d e9 aa f9 ff ff <8b> 86 bc 00 00 00 89 43 38 8d 46 60 89 43 40 83 c4 0c 5b 5e 5f
> EIP: [<c04ebf8f>] io_ioq_move+0xf2/0x109 SS:ESP 0068:f6304c28
> 
> Changelog:
> 
> Make sure iogs in the hierarchy are built properly after moving a task to a new cgroup.
> 
> Signed-off-by: Gui Jianfeng <guijianfeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>
> ---
>  block/cfq-iosched.c |    4 +++-
>  block/elevator-fq.c |    1 +
>  block/elevator-fq.h |    1 +
>  3 files changed, 5 insertions(+), 1 deletions(-)
> 
> diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
> index 0ecf7c7..6d7bb8a 100644
> --- a/block/cfq-iosched.c
> +++ b/block/cfq-iosched.c
> @@ -12,6 +12,8 @@
>  #include <linux/rbtree.h>
>  #include <linux/ioprio.h>
>  #include <linux/blktrace_api.h>
> +#include "elevator-fq.h"
> +

I think above explicit inclusion of "elevator-fq.h" might be unnecessary
as elevator.h includes elevator-fq.h and cfq-iosched.c is including
elevator.h

>  /*
>   * tunables
>   */
> @@ -1086,7 +1088,7 @@ static void changed_cgroup(struct io_context *ioc, struct cfq_io_context *cic)
>  
>  	spin_lock_irqsave(q->queue_lock, flags);
>  
> -	iog = io_lookup_io_group_current(q);
> +	iog = io_get_io_group(q);

A one line comment here explaining the need to get_io_group instead of
lookup_io_group will be nice.

Thanks
Vivek

>  
>  	if (async_cfqq != NULL) {
>  		__iog = cfqq_to_io_group(async_cfqq);
> diff --git a/block/elevator-fq.c b/block/elevator-fq.c
> index df53418..f81cf6a 100644
> --- a/block/elevator-fq.c
> +++ b/block/elevator-fq.c
> @@ -1191,6 +1191,7 @@ struct io_group *io_get_io_group(struct request_queue *q)
>  
>  	return iog;
>  }
> +EXPORT_SYMBOL(io_get_io_group);
>  
>  void io_free_root_group(struct elevator_queue *e)
>  {
> diff --git a/block/elevator-fq.h b/block/elevator-fq.h
> index fc4110d..f17e425 100644
> --- a/block/elevator-fq.h
> +++ b/block/elevator-fq.h
> @@ -459,6 +459,7 @@ static inline struct io_group *ioq_to_io_group(struct io_queue *ioq)
>  }
>  
>  #ifdef CONFIG_GROUP_IOSCHED
> +extern struct io_group *io_get_io_group(struct request_queue *q);
>  extern int io_group_allow_merge(struct request *rq, struct bio *bio);
>  extern void io_ioq_move(struct elevator_queue *e, struct io_queue *ioq,
>  					struct io_group *iog);
> -- 
> 1.5.4.rc3
> 
>