On Fri, Oct 29, 2021 at 06:52:31AM +0300, Kalle Valo wrote: > Zekun Shen <bruceshenzk@xxxxxxxxx> 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@xxxxxxxxx> > > 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
