Re: [PATCH] block/loop: fix race between I/O and set_status
From: Jiri Slaby
Date: Mon Mar 13 2017 - 17:14:14 EST
On 02/11/2017, 04:40 AM, Ming Lei wrote:
> Inside set_status, transfer need to setup again, so
> we have to drain IO before the transition, otherwise
> oops may be triggered like the following:
>
> divide error: 0000 [#1] SMP KASAN
> CPU: 0 PID: 2935 Comm: loop7 Not tainted 4.10.0-rc7+ #213
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs
> 01/01/2011
> task: ffff88006ba1e840 task.stack: ffff880067338000
> RIP: 0010:transfer_xor+0x1d1/0x440 drivers/block/loop.c:110
> RSP: 0018:ffff88006733f108 EFLAGS: 00010246
> RAX: 0000000000000000 RBX: ffff8800688d7000 RCX: 0000000000000059
> RDX: 0000000000000000 RSI: 1ffff1000d743f43 RDI: ffff880068891c08
> RBP: ffff88006733f160 R08: ffff8800688d7001 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000000 R12: ffff8800688d7000
> R13: ffff880067b7d000 R14: dffffc0000000000 R15: 0000000000000000
> FS: 0000000000000000(0000) GS:ffff88006d000000(0000)
> knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: 00000000006c17e0 CR3: 0000000066e3b000 CR4: 00000000001406f0
> Call Trace:
> lo_do_transfer drivers/block/loop.c:251 [inline]
> lo_read_transfer drivers/block/loop.c:392 [inline]
> do_req_filebacked drivers/block/loop.c:541 [inline]
> loop_handle_cmd drivers/block/loop.c:1677 [inline]
> loop_queue_work+0xda0/0x49b0 drivers/block/loop.c:1689
> kthread_worker_fn+0x4c3/0xa30 kernel/kthread.c:630
> kthread+0x326/0x3f0 kernel/kthread.c:227
> ret_from_fork+0x31/0x40 arch/x86/entry/entry_64.S:430
> Code: 03 83 e2 07 41 29 df 42 0f b6 04 30 4d 8d 44 24 01 38 d0 7f 08
> 84 c0 0f 85 62 02 00 00 44 89 f8 41 0f b6 48 ff 25 ff 01 00 00 99 <f7>
> 7d c8 48 63 d2 48 03 55 d0 48 89 d0 48 89 d7 48 c1 e8 03 83
> RIP: transfer_xor+0x1d1/0x440 drivers/block/loop.c:110 RSP:
> ffff88006733f108
> ---[ end trace 0166f7bd3b0c0933 ]---
>
> Reported-by: Dmitry Vyukov <dvyukov@xxxxxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx
> Signed-off-by: Ming Lei <tom.leiming@xxxxxxxxx>
> ---
> drivers/block/loop.c | 17 ++++++++++++-----
> 1 file changed, 12 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/block/loop.c b/drivers/block/loop.c
> index ed5259510857..4b52a1690329 100644
> --- a/drivers/block/loop.c
> +++ b/drivers/block/loop.c
> @@ -1097,9 +1097,12 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
> if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
> return -EINVAL;
>
> + /* I/O need to be drained during transfer transition */
> + blk_mq_freeze_queue(lo->lo_queue);
> +
> err = loop_release_xfer(lo);
> if (err)
> - return err;
> + goto exit;
>
> if (info->lo_encrypt_type) {
> unsigned int type = info->lo_encrypt_type;
> @@ -1114,12 +1117,14 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
I might be missing context, but given this is not explained in the log,
I must ask why are not these returns also converted?
if (info->lo_encrypt_type) {
unsigned int type = info->lo_encrypt_type;
if (type >= MAX_LO_CRYPT)
return -EINVAL;
xfer = xfer_funcs[type];
if (xfer == NULL)
return -EINVAL;
} else
xfer = NULL;
>
> err = loop_init_xfer(lo, xfer, info);
> if (err)
> - return err;
> + goto exit;
>
> if (lo->lo_offset != info->lo_offset ||
> lo->lo_sizelimit != info->lo_sizelimit)
> - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
> - return -EFBIG;
> + if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
> + err = -EFBIG;
> + goto exit;
> + }
>
> loop_config_discard(lo);
>
> @@ -1156,7 +1161,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
> /* update dio if lo_offset or transfer is changed */
> __loop_update_dio(lo, lo->use_dio);
>
> - return 0;
> + exit:
> + blk_mq_unfreeze_queue(lo->lo_queue);
> + return err;
> }
>
> static int
>
thanks,
--
js
suse labs