[dm-devel] [PATCH] dm-io: Prevent the danging point of the sync io callback function

[Mikulas Patocka]

On Fri, 27 Jun 2014, Minfei Huang wrote:

> BUG: unable to handle kernel NULL pointer dereference at 0000000000000046
> IP: [<ffffffffa0009cef>] dec_count+0x5f/0x80 [dm_mod]
> PGD 0
> Oops: 0000 [#1] SMP
> last sysfs file: /sys/devices/pci0000:00/0000:00:02.2/0000:02:00.0/host0/scsi_host/host0/proc_name
> 
> Pid: 2708, comm: kcopyd Tainted: G        W  --------------- H  2.6.32-279.19.5.el6.ucloud.x86_64 #1 Dell Inc. PowerEdge R720xd/0DCWD1
> RIP: 0010:[<ffffffffa0009cef>]  [<ffffffffa0009cef>] dec_count+0x5f/0x80 [dm_mod]
> RSP: 0018:ffff880100603c30  EFLAGS: 00010246
> RAX: 0000000000000046 RBX: ffff8817968a5c30 RCX: 0000000000000000
> RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff8817968a5c00
> RBP: ffff880100603c50 R08: 0000000000000000 R09: 0000000000000000
> R10: ffff880caa594cc0 R11: 0000000000000000 R12: ffff8817968a5c80
> R13: ffffffff81013963 R14: 0000000000001000 R15: 0000000000000000
> FS:  0000000000000000(0000) GS:ffff880100600000(0000) knlGS:0000000000000000
> CS:  0010 DS: 0018 ES: 0018 CR0: 000000008005003b
> CR2: 0000000000000046 CR3: 000000020c309000 CR4: 00000000001426e0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> Process kcopyd (pid: 2708, threadinfo ffff88180cd26000, task ffff881841c9aa80)
> Stack:
>  ffff880100603c40 ffff880aa8b32300 0000000000000000 ffff8817968a5c00
> <d> ffff880100603c80 ffffffffa000a12a 0000000000000000 ffff880aa8b32300
> <d> 0000000000000000 ffff880caa594cc0 ffff880100603c90 ffffffff811bcf6d
> Call Trace:
>  <IRQ>
>  [<ffffffffa000a12a>] endio+0x4a/0x70 [dm_mod]
>  [<ffffffff811bcf6d>] bio_endio+0x1d/0x40
>  [<ffffffff81260beb>] req_bio_endio+0x9b/0xe0
>  [<ffffffff81263114>] blk_update_request+0x104/0x500
>  [<ffffffff81263331>] ? blk_update_request+0x321/0x500
>  [<ffffffff81263537>] blk_update_bidi_request+0x27/0xa0
>  [<ffffffff8126419f>] blk_end_bidi_request+0x2f/0x80
>  [<ffffffff81264240>] blk_end_request+0x10/0x20
>  [<ffffffff81375c6f>] scsi_io_completion+0xaf/0x6c0
>  [<ffffffff8136cb92>] scsi_finish_command+0xc2/0x130
>  [<ffffffff813763e5>] scsi_softirq_done+0x145/0x170
>  [<ffffffff812698ed>] blk_done_softirq+0x8d/0xa0
>  [<ffffffff81074c5f>] __do_softirq+0xdf/0x210
>  [<ffffffff8100c2cc>] call_softirq+0x1c/0x30
>  [<ffffffff8100df9d>] do_softirq+0xad/0xe0
>  [<ffffffff81074995>] irq_exit+0x95/0xa0
>  [<ffffffff81510515>] do_IRQ+0x75/0xf0
>  [<ffffffff8100ba53>] ret_from_intr+0x0/0x16
> 
> The value of rdi register(0xffff8817968a5c00) is the io pointer,
> If the sync io, the address of io point must be alloc from stack.
> SO
> crash> struct thread_info ffff8817968a4000
> struct thread_info {
>   task = 0xffff88180cd9a580,
>   exec_domain = 0xffffffff81a98ac0,
>  ...
> }
> 
> crash> struct task_struct 0xffff88180cd9a580
> struct task_struct {
>   state = 2,
>   stack = 0xffff8817968a4000,
>  ...
> }
> 
> It shows value exactly when use the value of io address.
> 
> The io address in callback function will become the danging point,
> cause by the thread of sync io wakes up by other threads
> and return to relieve the io address,
> 
> Signed-off-by: Minfei Huang <huangminfei at ucloud.cn>
> ---
>  drivers/md/dm-io.c |   19 +++++++++++++++----
>  1 files changed, 15 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
> index 3842ac7..f992913 100644
> --- a/drivers/md/dm-io.c
> +++ b/drivers/md/dm-io.c
> @@ -38,6 +38,7 @@ struct io {
>  	void *context;
>  	void *vma_invalidate_address;
>  	unsigned long vma_invalidate_size;
> +	atomic_t wakeup;
>  } __attribute__((aligned(DM_IO_MAX_REGIONS)));
>  
>  static struct kmem_cache *_dm_io_cache;
> @@ -121,10 +122,16 @@ static void dec_count(struct io *io, unsigned int region, int error)
>  			invalidate_kernel_vmap_range(io->vma_invalidate_address,
>  						     io->vma_invalidate_size);
>  
> -		if (io->sleeper)
> -			wake_up_process(io->sleeper);
> +		if (io->sleeper) {
> +			struct task_struct *sleeper = io->sleeper;
>  
> -		else {
> +			atomic_set(&io->wakeup, 1);

The problem here is that the processor may reorder the read of io->sleeper 
with atomic_set(&io->wakeup, 1); (performing atomic_set first and "sleeper 
= io->sleeper" afterwards) exposing the same race condition.

You need to use memory barriers to avoid reordering, but I think the 
solution with the completion is better (the completion takes care of 
barriers automatically).

Mikulas


> +/*
> + * The thread may be waked up by other threads,
> + * if then the sync io point will become the dangling pointer
> + */
> +			wake_up_process(sleeper);
> +		} else {
>  			unsigned long r = io->error_bits;
>  			io_notify_fn fn = io->callback;
>  			void *context = io->context;
> @@ -401,12 +408,14 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
>  	io->vma_invalidate_address = dp->vma_invalidate_address;
>  	io->vma_invalidate_size = dp->vma_invalidate_size;
>  
> +	atomic_set(&io->wakeup, 0);
> +
>  	dispatch_io(rw, num_regions, where, dp, io, 1);
>  
>  	while (1) {
>  		set_current_state(TASK_UNINTERRUPTIBLE);
>  
> -		if (!atomic_read(&io->count))
> +		if (atomic_read(&io->wakeup))
>  			break;
>  
>  		io_schedule();
> @@ -442,6 +451,8 @@ static int async_io(struct dm_io_client *client, unsigned int num_regions,
>  	io->vma_invalidate_address = dp->vma_invalidate_address;
>  	io->vma_invalidate_size = dp->vma_invalidate_size;
>  
> +	atomic_set(&io->wakeup, 0);
> +
>  	dispatch_io(rw, num_regions, where, dp, io, 0);
>  	return 0;
>  }
> -- 
> 1.7.1
> 
> 
> --
> dm-devel mailing list
> dm-devel at redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
>