Re: [PATCH] ath9k: Fix out-of-bound memcpy in ath9k_hif_usb_rx_stream

From: Zekun Shen <bruceshenzk@gmail.com>
To: Kalle Valo <kvalo@codeaurora.org>
Cc: ath9k-devel@qca.qualcomm.com, Kalle Valo <kvalo@codeaurora.org>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	linux-wireless@vger.kernel.org, netdev@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] ath9k: Fix out-of-bound memcpy in ath9k_hif_usb_rx_stream
Date: Fri, 29 Oct 2021 09:46:06 -0400	[thread overview]
Message-ID: <YXv7HpMlTMOIhiy4@Zekuns-MBP-16.fios-router.home> (raw)
In-Reply-To: <87y26cxzb4.fsf@tynnyri.adurom.net>

On Fri, Oct 29, 2021 at 06:52:31AM +0300, Kalle Valo wrote:
> Zekun Shen <bruceshenzk@gmail.com> writes:
> 
> > Large pkt_len can lead to out-out-bound memcpy. Current
> > ath9k_hif_usb_rx_stream allows combining the content of two urb
> > inputs to one pkt. The first input can indicate the size of the
> > pkt. Any remaining size is saved in hif_dev->rx_remain_len.
> > While processing the next input, memcpy is used with rx_remain_len.
> >
> > 4-byte pkt_len can go up to 0xffff, while a single input is 0x4000
> > maximum in size (MAX_RX_BUF_SIZE). Thus, the patch adds a check for
> > pkt_len which must not exceed 2 * MAX_RX_BUG_SIZE.
> >
> > BUG: KASAN: slab-out-of-bounds in ath9k_hif_usb_rx_cb+0x490/0xed7 [ath9k_htc]
> > Read of size 46393 at addr ffff888018798000 by task kworker/0:1/23
> >
> > CPU: 0 PID: 23 Comm: kworker/0:1 Not tainted 5.6.0 #63
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
> > BIOS rel-1.10.2-0-g5f4c7b1-prebuilt.qemu-project.org 04/01/2014
> > Workqueue: events request_firmware_work_func
> > Call Trace:
> >  <IRQ>
> >  dump_stack+0x76/0xa0
> >  print_address_description.constprop.0+0x16/0x200
> >  ? ath9k_hif_usb_rx_cb+0x490/0xed7 [ath9k_htc]
> >  ? ath9k_hif_usb_rx_cb+0x490/0xed7 [ath9k_htc]
> >  __kasan_report.cold+0x37/0x7c
> >  ? ath9k_hif_usb_rx_cb+0x490/0xed7 [ath9k_htc]
> >  kasan_report+0xe/0x20
> >  check_memory_region+0x15a/0x1d0
> >  memcpy+0x20/0x50
> >  ath9k_hif_usb_rx_cb+0x490/0xed7 [ath9k_htc]
> >  ? hif_usb_mgmt_cb+0x2d9/0x2d9 [ath9k_htc]
> >  ? _raw_spin_lock_irqsave+0x7b/0xd0
> >  ? _raw_spin_trylock_bh+0x120/0x120
> >  ? __usb_unanchor_urb+0x12f/0x210
> >  __usb_hcd_giveback_urb+0x1e4/0x380
> >  usb_giveback_urb_bh+0x241/0x4f0
> >  ? __hrtimer_run_queues+0x316/0x740
> >  ? __usb_hcd_giveback_urb+0x380/0x380
> >  tasklet_action_common.isra.0+0x135/0x330
> >  __do_softirq+0x18c/0x634
> >  irq_exit+0x114/0x140
> >  smp_apic_timer_interrupt+0xde/0x380
> >  apic_timer_interrupt+0xf/0x20
> >
> > Signed-off-by: Zekun Shen <bruceshenzk@gmail.com>
> 
> How did you test this?
I found the bug using a custome USBFuzz port. It's a research work
to fuzz USB stack/drivers. I modified it to fuzz ath9k driver only,
providing hand-crafted usb descriptors to QEMU.

After fixing the value of pkt_tag to ATH_USB_RX_STREAM_MODE_TAG in QEMU
emulation, I found the KASAN report. The bug is triggerable whenever
pkt_len is above two MAX_RX_BUG_SIZE. I used the same input that crashes
to test the driver works when applying the patch.
> 
> -- 
> https://patchwork.kernel.org/project/linux-wireless/list/
> 
> https://wireless.wiki.kernel.org/en/developers/documentation/submittingpatches