Re: [PATCH v2] blktrace: Fix uaf in blk_trace access after removing by sysfs
From: Jens Axboe
Date: Fri Sep 24 2021 - 13:06:35 EST
On 9/23/21 7:49 AM, Zhihao Cheng wrote:
> There is an use-after-free problem triggered by following process:
>
> P1(sda) P2(sdb)
> echo 0 > /sys/block/sdb/trace/enable
> blk_trace_remove_queue
> synchronize_rcu
> blk_trace_free
> relay_close
> rcu_read_lock
> __blk_add_trace
> trace_note_tsk
> (Iterate running_trace_list)
> relay_close_buf
> relay_destroy_buf
> kfree(buf)
> trace_note(sdb's bt)
> relay_reserve
> buf->offset <- nullptr deference (use-after-free) !!!
> rcu_read_unlock
>
> [ 502.714379] BUG: kernel NULL pointer dereference, address:
> 0000000000000010
> [ 502.715260] #PF: supervisor read access in kernel mode
> [ 502.715903] #PF: error_code(0x0000) - not-present page
> [ 502.716546] PGD 103984067 P4D 103984067 PUD 17592b067 PMD 0
> [ 502.717252] Oops: 0000 [#1] SMP
> [ 502.720308] RIP: 0010:trace_note.isra.0+0x86/0x360
> [ 502.732872] Call Trace:
> [ 502.733193] __blk_add_trace.cold+0x137/0x1a3
> [ 502.733734] blk_add_trace_rq+0x7b/0xd0
> [ 502.734207] blk_add_trace_rq_issue+0x54/0xa0
> [ 502.734755] blk_mq_start_request+0xde/0x1b0
> [ 502.735287] scsi_queue_rq+0x528/0x1140
> ...
> [ 502.742704] sg_new_write.isra.0+0x16e/0x3e0
> [ 502.747501] sg_ioctl+0x466/0x1100
>
> Reproduce method:
> ioctl(/dev/sda, BLKTRACESETUP, blk_user_trace_setup[buf_size=127])
> ioctl(/dev/sda, BLKTRACESTART)
> ioctl(/dev/sdb, BLKTRACESETUP, blk_user_trace_setup[buf_size=127])
> ioctl(/dev/sdb, BLKTRACESTART)
>
> echo 0 > /sys/block/sdb/trace/enable &
> // Add delay(mdelay/msleep) before kernel enters blk_trace_free()
>
> ioctl$SG_IO(/dev/sda, SG_IO, ...)
> // Enters trace_note_tsk() after blk_trace_free() returned
> // Use mdelay in rcu region rather than msleep(which may schedule out)
>
> Remove blk_trace from running_list before calling blk_trace_free() by
> sysfs if blk_trace is at Blktrace_running state.
Applied, thanks.
--
Jens Axboe